diff --git "a/run-2024-10-02T06:53:25+00:00.log" "b/run-2024-10-02T06:53:25+00:00.log" --- "a/run-2024-10-02T06:53:25+00:00.log" +++ "b/run-2024-10-02T06:53:25+00:00.log" @@ -2584,4 +2584,198 @@ Non-default generation parameters: {'max_length': 200, 'early_stopping': True, ' 81%|████████▏ | 46840/57600 [8:14:26<1:51:48, 1.60it/s]/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock. self.pid = os.fork() 81%|████████▏ | 46841/57600 [8:14:27<2:00:22, 1.49it/s] 81%|████████▏ | 46842/57600 [8:14:27<1:59:00, 1.51it/s] 81%|████████▏ | 46843/57600 [8:14:28<1:59:42, 1.50it/s] 81%|████████▏ | 46844/57600 [8:14:29<2:00:59, 1.48it/s] 81%|████████▏ | 46845/57600 [8:14:29<1:59:27, 1.50it/s] 81%|████████▏ | 46846/57600 [8:14:30<2:01:29, 1.48it/s] 81%|████████▏ | 46847/57600 [8:14:31<2:00:42, 1.48it/s] 81%|████████▏ | 46848/57600 [8:14:31<2:01:04, 1.48it/s] 81%|████████▏ | 46849/57600 [8:14:32<1:59:15, 1.50it/s] 81%|████████▏ | 46850/57600 [8:14:33<1:58:48, 1.51it/s] 81%|████████▏ | 46851/57600 [8:14:33<1:59:12, 1.50it/s] 81%|████████▏ | 46852/57600 [8:14:34<1:57:38, 1.52it/s] 81%|████████▏ | 46853/57600 [8:14:35<1:57:32, 1.52it/s] 81%|████████▏ | 46854/57600 [8:14:35<1:59:43, 1.50it/s] 81%|████████▏ | 46855/57600 [8:14:36<2:00:55, 1.48it/s] 81%|████████▏ | 46856/57600 [8:14:37<2:03:25, 1.45it/s] 81%|████████▏ | 46857/57600 [8:14:37<2:02:22, 1.46it/s] 81%|████████▏ | 46858/57600 [8:14:38<2:03:18, 1.45it/s] 81%|████████▏ | 46859/57600 [8:14:39<2:04:23, 1.44it/s] 81%|████████▏ | 46860/57600 [8:14:39<2:00:33, 1.48it/s] {'loss': 1.0813, 'learning_rate': 2.6839721254355406e-07, 'epoch': 517.22} - 81%|████████▏ | 46860/57600 [8:14:39<2:00:33, 1.48it/s] 81%|████████▏ | 46861/57600 [8:14:40<2:06:26, 1.42it/s] \ No newline at end of file + 81%|████████▏ | 46860/57600 [8:14:39<2:00:33, 1.48it/s] 81%|████████▏ | 46861/57600 [8:14:40<2:06:26, 1.42it/s] 81%|████████▏ | 46862/57600 [8:14:41<2:05:01, 1.43it/s] 81%|████████▏ | 46863/57600 [8:14:42<1:59:14, 1.50it/s] 81%|████████▏ | 46864/57600 [8:14:42<1:58:01, 1.52it/s] 81%|████████▏ | 46865/57600 [8:14:43<1:57:58, 1.52it/s] 81%|████████▏ | 46866/57600 [8:14:43<1:55:12, 1.55it/s] 81%|████████▏ | 46867/57600 [8:14:44<1:57:40, 1.52it/s] 81%|████████▏ | 46868/57600 [8:14:45<1:54:11, 1.57it/s] 81%|████████▏ | 46869/57600 [8:14:45<1:53:12, 1.58it/s] 81%|████████▏ | 46870/57600 [8:14:46<1:57:12, 1.53it/s] 81%|████████▏ | 46871/57600 [8:14:47<1:54:06, 1.57it/s] 81%|████████▏ | 46872/57600 [8:14:47<1:56:26, 1.54it/s] 81%|████████▏ | 46873/57600 [8:14:48<1:56:39, 1.53it/s] 81%|████████▏ | 46874/57600 [8:14:49<1:54:45, 1.56it/s] 81%|████████▏ | 46875/57600 [8:14:49<1:55:48, 1.54it/s] 81%|████████▏ | 46876/57600 [8:14:50<1:52:00, 1.60it/s] 81%|████████▏ | 46877/57600 [8:14:50<1:52:30, 1.59it/s] 81%|████████▏ | 46878/57600 [8:14:51<1:56:40, 1.53it/s] 81%|████████▏ | 46879/57600 [8:14:52<1:56:52, 1.53it/s] 81%|████████▏ | 46880/57600 [8:14:52<1:53:02, 1.58it/s] {'loss': 1.1569, 'learning_rate': 2.6808362369337976e-07, 'epoch': 517.44} + 81%|████████▏ | 46880/57600 [8:14:52<1:53:02, 1.58it/s] 81%|████████▏ | 46881/57600 [8:14:53<1:55:29, 1.55it/s] 81%|████████▏ | 46882/57600 [8:14:54<1:50:22, 1.62it/s] 81%|████████▏ | 46883/57600 [8:14:54<1:47:43, 1.66it/s] 81%|████████▏ | 46884/57600 [8:14:55<1:48:23, 1.65it/s] 81%|████████▏ | 46885/57600 [8:14:56<1:51:10, 1.61it/s] 81%|████████▏ | 46886/57600 [8:14:56<1:54:06, 1.56it/s] 81%|████████▏ | 46887/57600 [8:14:57<1:55:23, 1.55it/s] 81%|████████▏ | 46888/57600 [8:14:58<1:55:40, 1.54it/s] 81%|████████▏ | 46889/57600 [8:14:58<1:59:08, 1.50it/s] 81%|████████▏ | 46890/57600 [8:14:59<1:54:03, 1.56it/s] 81%|████████▏ | 46891/57600 [8:14:59<1:52:32, 1.59it/s] 81%|████████▏ | 46892/57600 [8:15:00<1:54:08, 1.56it/s] 81%|████████▏ | 46893/57600 [8:15:01<1:50:52, 1.61it/s] 81%|████████▏ | 46894/57600 [8:15:01<1:54:45, 1.55it/s] 81%|████████▏ | 46895/57600 [8:15:02<1:53:48, 1.57it/s] 81%|████████▏ | 46896/57600 [8:15:03<1:52:42, 1.58it/s] 81%|████████▏ | 46897/57600 [8:15:03<1:52:23, 1.59it/s] 81%|████████▏ | 46898/57600 [8:15:04<1:54:42, 1.56it/s] 81%|████████▏ | 46899/57600 [8:15:04<1:52:33, 1.58it/s] 81%|████████▏ | 46900/57600 [8:15:05<1:53:14, 1.57it/s] {'loss': 1.1273, 'learning_rate': 2.6777003484320556e-07, 'epoch': 517.66} + 81%|████████▏ | 46900/57600 [8:15:05<1:53:14, 1.57it/s] 81%|████████▏ | 46901/57600 [8:15:06<1:54:03, 1.56it/s] 81%|████████▏ | 46902/57600 [8:15:06<1:52:26, 1.59it/s] 81%|████████▏ | 46903/57600 [8:15:07<1:51:55, 1.59it/s] 81%|████████▏ | 46904/57600 [8:15:08<1:53:08, 1.58it/s] 81%|████████▏ | 46905/57600 [8:15:08<1:54:29, 1.56it/s] 81%|████████▏ | 46906/57600 [8:15:09<1:54:39, 1.55it/s] 81%|████████▏ | 46907/57600 [8:15:10<1:54:49, 1.55it/s] 81%|████████▏ | 46908/57600 [8:15:10<1:56:17, 1.53it/s] 81%|████████▏ | 46909/57600 [8:15:11<2:03:17, 1.45it/s] 81%|████████▏ | 46910/57600 [8:15:12<2:10:52, 1.36it/s] 81%|████████▏ | 46911/57600 [8:15:13<2:11:07, 1.36it/s] 81%|████████▏ | 46912/57600 [8:15:13<2:03:58, 1.44it/s] 81%|████████▏ | 46913/57600 [8:15:14<2:00:12, 1.48it/s] 81%|████████▏ | 46914/57600 [8:15:14<1:56:35, 1.53it/s] 81%|████████▏ | 46915/57600 [8:15:15<1:58:01, 1.51it/s] 81%|████████▏ | 46916/57600 [8:15:16<2:00:53, 1.47it/s] 81%|████████▏ | 46917/57600 [8:15:16<1:56:25, 1.53it/s] 81%|████████▏ | 46918/57600 [8:15:17<1:55:19, 1.54it/s] 81%|████████▏ | 46919/57600 [8:15:18<1:55:49, 1.54it/s] 81%|████████▏ | 46920/57600 [8:15:18<1:57:51, 1.51it/s] {'loss': 1.1095, 'learning_rate': 2.674564459930313e-07, 'epoch': 517.88} + 81%|████████▏ | 46920/57600 [8:15:18<1:57:51, 1.51it/s] 81%|████████▏ | 46921/57600 [8:15:19<1:56:56, 1.52it/s] 81%|████████▏ | 46922/57600 [8:15:20<1:55:27, 1.54it/s] 81%|████████▏ | 46923/57600 [8:15:20<1:56:12, 1.53it/s] 81%|████████▏ | 46924/57600 [8:15:21<1:52:02, 1.59it/s] 81%|████████▏ | 46925/57600 [8:15:22<1:52:57, 1.58it/s] 81%|████████▏ | 46926/57600 [8:15:22<1:53:39, 1.57it/s] 81%|████████▏ | 46927/57600 [8:15:23<1:52:06, 1.59it/s] 81%|████████▏ | 46928/57600 [8:15:24<1:52:47, 1.58it/s] 81%|████████▏ | 46929/57600 [8:15:24<1:52:13, 1.58it/s] 81%|████████▏ | 46930/57600 [8:15:25<1:57:29, 1.51it/s] 81%|████████▏ | 46931/57600 [8:15:26<2:05:13, 1.42it/s] 81%|████████▏ | 46932/57600 [8:15:26<2:04:48, 1.42it/s] 81%|████████▏ | 46933/57600 [8:15:27<2:02:54, 1.45it/s] 81%|████████▏ | 46934/57600 [8:15:28<2:05:33, 1.42it/s] 81%|████████▏ | 46935/57600 [8:15:28<2:02:47, 1.45it/s] 81%|████████▏ | 46936/57600 [8:15:29<2:01:05, 1.47it/s] 81%|████████▏ | 46937/57600 [8:15:30<1:58:16, 1.50it/s] 81%|████████▏ | 46938/57600 [8:15:30<1:56:29, 1.53it/s] 81%|████████▏ | 46939/57600 [8:15:31<1:54:30, 1.55it/s] 81%|████████▏ | 46940/57600 [8:15:32<1:54:55, 1.55it/s] {'loss': 1.1044, 'learning_rate': 2.6714285714285717e-07, 'epoch': 518.1} + 81%|████████▏ | 46940/57600 [8:15:32<1:54:55, 1.55it/s] 81%|████████▏ | 46941/57600 [8:15:32<1:51:00, 1.60it/s] 81%|████████▏ | 46942/57600 [8:15:33<1:51:09, 1.60it/s] 81%|████████▏ | 46943/57600 [8:15:33<1:53:48, 1.56it/s] 82%|████████▏ | 46944/57600 [8:15:34<1:56:23, 1.53it/s] 82%|████████▏ | 46945/57600 [8:15:35<1:58:19, 1.50it/s] 82%|████████▏ | 46946/57600 [8:15:35<1:54:23, 1.55it/s] 82%|████████▏ | 46947/57600 [8:15:36<1:56:52, 1.52it/s] 82%|████████▏ | 46948/57600 [8:15:37<1:56:16, 1.53it/s] 82%|████████▏ | 46949/57600 [8:15:37<1:55:05, 1.54it/s] 82%|████████▏ | 46950/57600 [8:15:38<1:55:39, 1.53it/s] 82%|████████▏ | 46951/57600 [8:15:39<1:53:28, 1.56it/s] 82%|████████▏ | 46952/57600 [8:15:39<1:55:02, 1.54it/s] 82%|████████▏ | 46953/57600 [8:15:40<1:54:13, 1.55it/s] 82%|████████▏ | 46954/57600 [8:15:41<1:54:17, 1.55it/s] 82%|████████▏ | 46955/57600 [8:15:41<1:52:59, 1.57it/s] 82%|████████▏ | 46956/57600 [8:15:42<1:52:46, 1.57it/s] 82%|████████▏ | 46957/57600 [8:15:43<1:52:01, 1.58it/s] 82%|████████▏ | 46958/57600 [8:15:43<1:54:25, 1.55it/s] 82%|████████▏ | 46959/57600 [8:15:44<1:55:00, 1.54it/s] 82%|████████▏ | 46960/57600 [8:15:45<2:02:45, 1.44it/s] {'loss': 1.123, 'learning_rate': 2.668292682926829e-07, 'epoch': 518.32} + 82%|████████▏ | 46960/57600 [8:15:45<2:02:45, 1.44it/s] 82%|████████▏ | 46961/57600 [8:15:45<2:06:30, 1.40it/s] 82%|████████▏ | 46962/57600 [8:15:46<2:06:05, 1.41it/s] 82%|████████▏ | 46963/57600 [8:15:47<2:03:38, 1.43it/s] 82%|████████▏ | 46964/57600 [8:15:47<2:03:34, 1.43it/s] 82%|████████▏ | 46965/57600 [8:15:48<2:07:11, 1.39it/s] 82%|████████▏ | 46966/57600 [8:15:49<2:04:55, 1.42it/s] 82%|████████▏ | 46967/57600 [8:15:50<2:03:44, 1.43it/s] 82%|████████▏ | 46968/57600 [8:15:50<2:02:34, 1.45it/s] 82%|████████▏ | 46969/57600 [8:15:51<2:01:33, 1.46it/s] 82%|████████▏ | 46970/57600 [8:15:52<2:00:48, 1.47it/s] 82%|████████▏ | 46971/57600 [8:15:52<1:58:31, 1.49it/s] 82%|████████▏ | 46972/57600 [8:15:53<1:59:41, 1.48it/s] 82%|████████▏ | 46973/57600 [8:15:54<1:55:34, 1.53it/s] 82%|████████▏ | 46974/57600 [8:15:54<1:56:47, 1.52it/s] 82%|████████▏ | 46975/57600 [8:15:55<1:57:54, 1.50it/s] 82%|████████▏ | 46976/57600 [8:15:56<1:56:46, 1.52it/s] 82%|████████▏ | 46977/57600 [8:15:56<1:57:41, 1.50it/s] 82%|████████▏ | 46978/57600 [8:15:57<1:54:31, 1.55it/s] 82%|████████▏ | 46979/57600 [8:15:58<1:58:12, 1.50it/s] 82%|████████▏ | 46980/57600 [8:15:58<1:59:50, 1.48it/s] {'loss': 1.1064, 'learning_rate': 2.665156794425087e-07, 'epoch': 518.54} + 82%|████████▏ | 46980/57600 [8:15:58<1:59:50, 1.48it/s] 82%|████████▏ | 46981/57600 [8:15:59<1:54:12, 1.55it/s] 82%|████████▏ | 46982/57600 [8:16:00<1:55:28, 1.53it/s] 82%|████████▏ | 46983/57600 [8:16:00<1:57:35, 1.50it/s] 82%|████████▏ | 46984/57600 [8:16:01<1:57:02, 1.51it/s] 82%|████████▏ | 46985/57600 [8:16:01<1:51:19, 1.59it/s] 82%|████████▏ | 46986/57600 [8:16:02<1:51:47, 1.58it/s] 82%|████████▏ | 46987/57600 [8:16:03<1:54:34, 1.54it/s] 82%|████████▏ | 46988/57600 [8:16:03<1:54:00, 1.55it/s] 82%|████████▏ | 46989/57600 [8:16:04<1:55:37, 1.53it/s] 82%|████████▏ | 46990/57600 [8:16:05<1:54:58, 1.54it/s] 82%|████████▏ | 46991/57600 [8:16:05<1:57:09, 1.51it/s] 82%|████████▏ | 46992/57600 [8:16:06<1:57:17, 1.51it/s] 82%|████████▏ | 46993/57600 [8:16:07<1:56:43, 1.51it/s] 82%|████████▏ | 46994/57600 [8:16:07<1:56:42, 1.51it/s] 82%|████████▏ | 46995/57600 [8:16:08<1:54:48, 1.54it/s] 82%|████████▏ | 46996/57600 [8:16:09<1:50:30, 1.60it/s] 82%|████████▏ | 46997/57600 [8:16:09<1:48:24, 1.63it/s] 82%|████████▏ | 46998/57600 [8:16:10<1:49:35, 1.61it/s] 82%|████████▏ | 46999/57600 [8:16:10<1:50:25, 1.60it/s] 82%|████████▏ | 47000/57600 [8:16:11<1:57:57, 1.50it/s] {'loss': 1.1221, 'learning_rate': 2.662020905923346e-07, 'epoch': 518.76} + 82%|████████▏ | 47000/57600 [8:16:11<1:57:57, 1.50it/s] 82%|████████▏ | 47001/57600 [8:16:12<1:53:13, 1.56it/s] 82%|████████▏ | 47002/57600 [8:16:12<1:58:14, 1.49it/s] 82%|████████▏ | 47003/57600 [8:16:13<1:55:50, 1.52it/s] 82%|████████▏ | 47004/57600 [8:16:14<1:51:13, 1.59it/s] 82%|████████▏ | 47005/57600 [8:16:14<1:50:16, 1.60it/s] 82%|████████▏ | 47006/57600 [8:16:15<1:52:28, 1.57it/s] 82%|████████▏ | 47007/57600 [8:16:16<1:50:09, 1.60it/s] 82%|████████▏ | 47008/57600 [8:16:16<1:47:55, 1.64it/s] 82%|████████▏ | 47009/57600 [8:16:17<1:48:25, 1.63it/s] 82%|████████▏ | 47010/57600 [8:16:17<1:46:12, 1.66it/s] 82%|████████▏ | 47011/57600 [8:16:18<1:47:31, 1.64it/s] 82%|████████▏ | 47012/57600 [8:16:19<1:48:05, 1.63it/s] 82%|████████▏ | 47013/57600 [8:16:19<1:51:22, 1.58it/s] 82%|████████▏ | 47014/57600 [8:16:20<1:49:34, 1.61it/s] 82%|████████▏ | 47015/57600 [8:16:20<1:46:57, 1.65it/s] 82%|████████▏ | 47016/57600 [8:16:21<1:50:27, 1.60it/s] 82%|████████▏ | 47017/57600 [8:16:22<1:52:09, 1.57it/s] 82%|████████▏ | 47018/57600 [8:16:22<1:50:17, 1.60it/s] 82%|████████▏ | 47019/57600 [8:16:23<1:56:13, 1.52it/s] 82%|████████▏ | 47020/57600 [8:16:24<1:51:23, 1.58it/s] {'loss': 1.1345, 'learning_rate': 2.6588850174216023e-07, 'epoch': 518.98} + 82%|████████▏ | 47020/57600 [8:16:24<1:51:23, 1.58it/s] 82%|████████▏ | 47021/57600 [8:16:24<1:53:40, 1.55it/s] 82%|████████▏ | 47022/57600 [8:16:25<1:56:28, 1.51it/s] 82%|████████▏ | 47023/57600 [8:16:26<1:54:46, 1.54it/s] 82%|████████▏ | 47024/57600 [8:16:26<1:55:16, 1.53it/s] 82%|████████▏ | 47025/57600 [8:16:27<1:51:28, 1.58it/s] 82%|████████▏ | 47026/57600 [8:16:28<1:51:59, 1.57it/s] 82%|████████▏ | 47027/57600 [8:16:28<1:48:05, 1.63it/s] 82%|████████▏ | 47028/57600 [8:16:29<1:51:40, 1.58it/s] 82%|████████▏ | 47029/57600 [8:16:29<1:52:30, 1.57it/s] 82%|████████▏ | 47030/57600 [8:16:30<1:49:09, 1.61it/s] 82%|████████▏ | 47031/57600 [8:16:31<1:48:48, 1.62it/s] 82%|████████▏ | 47032/57600 [8:16:31<1:50:56, 1.59it/s] 82%|████████▏ | 47033/57600 [8:16:32<1:50:48, 1.59it/s] 82%|████████▏ | 47034/57600 [8:16:32<1:48:34, 1.62it/s] 82%|████████▏ | 47035/57600 [8:16:33<1:52:04, 1.57it/s] 82%|████████▏ | 47036/57600 [8:16:34<1:57:42, 1.50it/s] 82%|████████▏ | 47037/57600 [8:16:35<1:53:45, 1.55it/s] 82%|████████▏ | 47038/57600 [8:16:35<1:51:17, 1.58it/s] 82%|████████▏ | 47039/57600 [8:16:36<1:48:57, 1.62it/s] 82%|████████▏ | 47040/57600 [8:16:36<1:50:25, 1.59it/s] {'loss': 1.1308, 'learning_rate': 2.6557491289198604e-07, 'epoch': 519.21} + 82%|████████▏ | 47040/57600 [8:16:36<1:50:25, 1.59it/s] 82%|████████▏ | 47041/57600 [8:16:37<1:53:22, 1.55it/s] 82%|████████▏ | 47042/57600 [8:16:38<1:50:31, 1.59it/s] 82%|████████▏ | 47043/57600 [8:16:38<1:51:03, 1.58it/s] 82%|████████▏ | 47044/57600 [8:16:39<1:48:22, 1.62it/s] 82%|████████▏ | 47045/57600 [8:16:40<1:50:49, 1.59it/s] 82%|████████▏ | 47046/57600 [8:16:40<1:48:49, 1.62it/s] 82%|████████▏ | 47047/57600 [8:16:41<1:47:04, 1.64it/s] 82%|████████▏ | 47048/57600 [8:16:41<1:49:47, 1.60it/s] 82%|████████▏ | 47049/57600 [8:16:42<1:48:21, 1.62it/s] 82%|████████▏ | 47050/57600 [8:16:43<1:47:34, 1.63it/s] 82%|████████▏ | 47051/57600 [8:16:43<1:50:17, 1.59it/s] 82%|████████▏ | 47052/57600 [8:16:44<1:47:54, 1.63it/s] 82%|████████▏ | 47053/57600 [8:16:44<1:47:48, 1.63it/s] 82%|████████▏ | 47054/57600 [8:16:45<1:47:14, 1.64it/s] 82%|████████▏ | 47055/57600 [8:16:46<1:47:53, 1.63it/s] 82%|████████▏ | 47056/57600 [8:16:46<1:49:08, 1.61it/s] 82%|████████▏ | 47057/57600 [8:16:47<1:51:38, 1.57it/s] 82%|████████▏ | 47058/57600 [8:16:48<1:50:49, 1.59it/s] 82%|████████▏ | 47059/57600 [8:16:48<1:48:55, 1.61it/s] 82%|████████▏ | 47060/57600 [8:16:49<1:49:40, 1.60it/s] {'loss': 1.1336, 'learning_rate': 2.652613240418118e-07, 'epoch': 519.43} + 82%|████████▏ | 47060/57600 [8:16:49<1:49:40, 1.60it/s] 82%|████████▏ | 47061/57600 [8:16:49<1:50:17, 1.59it/s] 82%|████████▏ | 47062/57600 [8:16:50<1:50:19, 1.59it/s] 82%|████████▏ | 47063/57600 [8:16:51<1:48:53, 1.61it/s] 82%|████████▏ | 47064/57600 [8:16:51<1:45:48, 1.66it/s] 82%|████████▏ | 47065/57600 [8:16:52<1:46:21, 1.65it/s] 82%|████████▏ | 47066/57600 [8:16:52<1:47:05, 1.64it/s] 82%|████████▏ | 47067/57600 [8:16:53<1:45:38, 1.66it/s] 82%|████████▏ | 47068/57600 [8:16:54<1:44:32, 1.68it/s] 82%|████████▏ | 47069/57600 [8:16:54<1:42:29, 1.71it/s] 82%|████████▏ | 47070/57600 [8:16:55<1:47:00, 1.64it/s] 82%|████████▏ | 47071/57600 [8:16:56<1:52:01, 1.57it/s] 82%|████████▏ | 47072/57600 [8:16:56<1:52:08, 1.56it/s] 82%|████████▏ | 47073/57600 [8:16:57<1:48:49, 1.61it/s] 82%|████████▏ | 47074/57600 [8:16:57<1:49:30, 1.60it/s] 82%|████████▏ | 47075/57600 [8:16:58<1:48:50, 1.61it/s] 82%|████████▏ | 47076/57600 [8:16:59<1:48:56, 1.61it/s] 82%|████████▏ | 47077/57600 [8:16:59<1:46:02, 1.65it/s] 82%|████████▏ | 47078/57600 [8:17:00<1:43:49, 1.69it/s] 82%|████████▏ | 47079/57600 [8:17:00<1:43:13, 1.70it/s] 82%|████████▏ | 47080/57600 [8:17:01<1:43:23, 1.70it/s] {'loss': 1.1642, 'learning_rate': 2.6494773519163765e-07, 'epoch': 519.65} + 82%|████████▏ | 47080/57600 [8:17:01<1:43:23, 1.70it/s] 82%|████████▏ | 47081/57600 [8:17:02<1:44:44, 1.67it/s] 82%|████████▏ | 47082/57600 [8:17:02<1:45:03, 1.67it/s] 82%|████████▏ | 47083/57600 [8:17:03<1:51:39, 1.57it/s] 82%|████████▏ | 47084/57600 [8:17:03<1:48:27, 1.62it/s] 82%|████████▏ | 47085/57600 [8:17:04<1:48:16, 1.62it/s] 82%|████████▏ | 47086/57600 [8:17:05<1:50:07, 1.59it/s] 82%|████████▏ | 47087/57600 [8:17:05<1:49:34, 1.60it/s] 82%|████████▏ | 47088/57600 [8:17:06<1:50:14, 1.59it/s] 82%|████████▏ | 47089/57600 [8:17:07<1:48:56, 1.61it/s] 82%|████████▏ | 47090/57600 [8:17:07<1:46:51, 1.64it/s] 82%|████████▏ | 47091/57600 [8:17:08<1:47:51, 1.62it/s] 82%|████████▏ | 47092/57600 [8:17:08<1:49:32, 1.60it/s] 82%|████████▏ | 47093/57600 [8:17:09<1:51:09, 1.58it/s] 82%|████████▏ | 47094/57600 [8:17:10<1:51:05, 1.58it/s] 82%|████████▏ | 47095/57600 [8:17:10<1:55:50, 1.51it/s] 82%|████████▏ | 47096/57600 [8:17:11<1:51:46, 1.57it/s] 82%|████████▏ | 47097/57600 [8:17:12<1:51:42, 1.57it/s] 82%|████████▏ | 47098/57600 [8:17:12<1:53:35, 1.54it/s] 82%|████████▏ | 47099/57600 [8:17:13<1:54:30, 1.53it/s] 82%|████████▏ | 47100/57600 [8:17:14<1:56:02, 1.51it/s] {'loss': 1.0879, 'learning_rate': 2.6463414634146345e-07, 'epoch': 519.87} + 82%|████████▏ | 47100/57600 [8:17:14<1:56:02, 1.51it/s] 82%|████████▏ | 47101/57600 [8:17:14<1:54:54, 1.52it/s] 82%|████████▏ | 47102/57600 [8:17:15<1:57:03, 1.49it/s] 82%|████████▏ | 47103/57600 [8:17:16<1:55:04, 1.52it/s] 82%|████████▏ | 47104/57600 [8:17:16<1:50:20, 1.59it/s] 82%|████████▏ | 47105/57600 [8:17:17<1:49:36, 1.60it/s] 82%|████████▏ | 47106/57600 [8:17:18<1:52:20, 1.56it/s] 82%|████████▏ | 47107/57600 [8:17:18<1:50:24, 1.58it/s] 82%|████████▏ | 47108/57600 [8:17:19<1:49:41, 1.59it/s] 82%|████████▏ | 47109/57600 [8:17:19<1:49:55, 1.59it/s] 82%|████████▏ | 47110/57600 [8:17:20<1:50:32, 1.58it/s] 82%|████████▏ | 47111/57600 [8:17:21<1:54:55, 1.52it/s] 82%|████████▏ | 47112/57600 [8:17:21<1:52:49, 1.55it/s] 82%|████████▏ | 47113/57600 [8:17:22<1:53:25, 1.54it/s] 82%|████████▏ | 47114/57600 [8:17:23<1:54:57, 1.52it/s] 82%|████████▏ | 47115/57600 [8:17:23<2:00:37, 1.45it/s] 82%|████████▏ | 47116/57600 [8:17:24<1:56:45, 1.50it/s] 82%|████████▏ | 47117/57600 [8:17:25<1:52:56, 1.55it/s] 82%|████████▏ | 47118/57600 [8:17:25<1:50:17, 1.58it/s] 82%|████████▏ | 47119/57600 [8:17:26<1:51:12, 1.57it/s] 82%|████████▏ | 47120/57600 [8:17:27<1:49:33, 1.59it/s] {'loss': 1.1269, 'learning_rate': 2.6432055749128915e-07, 'epoch': 520.09} + 82%|████████▏ | 47120/57600 [8:17:27<1:49:33, 1.59it/s] 82%|████████▏ | 47121/57600 [8:17:27<1:45:34, 1.65it/s] 82%|████████▏ | 47122/57600 [8:17:28<1:43:52, 1.68it/s] 82%|████████▏ | 47123/57600 [8:17:28<1:46:04, 1.65it/s] 82%|████████▏ | 47124/57600 [8:17:29<1:46:30, 1.64it/s] 82%|████████▏ | 47125/57600 [8:17:30<1:51:05, 1.57it/s] 82%|████████▏ | 47126/57600 [8:17:30<1:52:53, 1.55it/s] 82%|████████▏ | 47127/57600 [8:17:31<1:48:18, 1.61it/s] 82%|████████▏ | 47128/57600 [8:17:31<1:47:07, 1.63it/s] 82%|████████▏ | 47129/57600 [8:17:32<1:49:01, 1.60it/s] 82%|████████▏ | 47130/57600 [8:17:33<1:48:39, 1.61it/s] 82%|████████▏ | 47131/57600 [8:17:33<1:45:29, 1.65it/s] 82%|████████▏ | 47132/57600 [8:17:34<1:49:09, 1.60it/s] 82%|████████▏ | 47133/57600 [8:17:35<1:54:35, 1.52it/s] 82%|████████▏ | 47134/57600 [8:17:35<1:50:36, 1.58it/s] 82%|████████▏ | 47135/57600 [8:17:36<1:51:49, 1.56it/s] 82%|████████▏ | 47136/57600 [8:17:37<1:50:56, 1.57it/s] 82%|████████▏ | 47137/57600 [8:17:37<1:51:12, 1.57it/s] 82%|████████▏ | 47138/57600 [8:17:38<1:51:31, 1.56it/s] 82%|████████▏ | 47139/57600 [8:17:38<1:51:30, 1.56it/s] 82%|████████▏ | 47140/57600 [8:17:39<1:48:32, 1.61it/s] {'loss': 1.1539, 'learning_rate': 2.64006968641115e-07, 'epoch': 520.31} + 82%|████████▏ | 47140/57600 [8:17:39<1:48:32, 1.61it/s] 82%|████████▏ | 47141/57600 [8:17:40<1:49:36, 1.59it/s] 82%|████████▏ | 47142/57600 [8:17:40<1:46:45, 1.63it/s] 82%|████████▏ | 47143/57600 [8:17:41<1:46:03, 1.64it/s] 82%|████████▏ | 47144/57600 [8:17:41<1:46:15, 1.64it/s] 82%|████████▏ | 47145/57600 [8:17:42<1:48:35, 1.60it/s] 82%|████████▏ | 47146/57600 [8:17:43<1:47:04, 1.63it/s] 82%|████████▏ | 47147/57600 [8:17:43<1:47:10, 1.63it/s] 82%|████████▏ | 47148/57600 [8:17:44<1:53:05, 1.54it/s] 82%|████████▏ | 47149/57600 [8:17:45<1:51:00, 1.57it/s] 82%|████████▏ | 47150/57600 [8:17:45<1:50:06, 1.58it/s] 82%|████████▏ | 47151/57600 [8:17:46<1:49:10, 1.60it/s] 82%|████████▏ | 47152/57600 [8:17:46<1:45:39, 1.65it/s] 82%|████████▏ | 47153/57600 [8:17:47<1:46:50, 1.63it/s] 82%|████████▏ | 47154/57600 [8:17:48<1:50:11, 1.58it/s] 82%|████████▏ | 47155/57600 [8:17:48<1:49:22, 1.59it/s] 82%|████████▏ | 47156/57600 [8:17:49<1:49:26, 1.59it/s] 82%|████████▏ | 47157/57600 [8:17:50<1:52:51, 1.54it/s] 82%|████████▏ | 47158/57600 [8:17:50<1:49:00, 1.60it/s] 82%|████████▏ | 47159/57600 [8:17:51<1:48:25, 1.61it/s] 82%|████████▏ | 47160/57600 [8:17:52<1:47:41, 1.62it/s] {'loss': 1.1108, 'learning_rate': 2.6369337979094076e-07, 'epoch': 520.53} + 82%|████████▏ | 47160/57600 [8:17:52<1:47:41, 1.62it/s] 82%|████████▏ | 47161/57600 [8:17:52<1:47:09, 1.62it/s] 82%|████████▏ | 47162/57600 [8:17:53<1:51:34, 1.56it/s] 82%|████████▏ | 47163/57600 [8:17:53<1:50:40, 1.57it/s] 82%|████████▏ | 47164/57600 [8:17:54<1:48:47, 1.60it/s] 82%|████████▏ | 47165/57600 [8:17:55<1:51:44, 1.56it/s] 82%|████████▏ | 47166/57600 [8:17:55<1:50:08, 1.58it/s] 82%|████████▏ | 47167/57600 [8:17:56<1:48:15, 1.61it/s] 82%|████████▏ | 47168/57600 [8:17:57<1:47:51, 1.61it/s] 82%|████████▏ | 47169/57600 [8:17:57<1:46:20, 1.63it/s] 82%|████████▏ | 47170/57600 [8:17:58<1:44:08, 1.67it/s] 82%|████████▏ | 47171/57600 [8:17:58<1:42:46, 1.69it/s] 82%|████████▏ | 47172/57600 [8:17:59<1:45:06, 1.65it/s] 82%|████████▏ | 47173/57600 [8:17:59<1:43:18, 1.68it/s] 82%|████████▏ | 47174/57600 [8:18:00<1:48:55, 1.60it/s] 82%|████████▏ | 47175/57600 [8:18:01<1:45:06, 1.65it/s] 82%|████████▏ | 47176/57600 [8:18:01<1:48:05, 1.61it/s] 82%|████████▏ | 47177/57600 [8:18:02<1:49:05, 1.59it/s] 82%|████████▏ | 47178/57600 [8:18:03<1:49:52, 1.58it/s] 82%|████████▏ | 47179/57600 [8:18:03<1:50:19, 1.57it/s] 82%|████████▏ | 47180/57600 [8:18:04<1:50:48, 1.57it/s] {'loss': 1.1258, 'learning_rate': 2.6337979094076657e-07, 'epoch': 520.75} + 82%|████████▏ | 47180/57600 [8:18:04<1:50:48, 1.57it/s] 82%|████████▏ | 47181/57600 [8:18:05<1:50:17, 1.57it/s] 82%|████████▏ | 47182/57600 [8:18:05<1:49:04, 1.59it/s] 82%|████████▏ | 47183/57600 [8:18:06<1:50:52, 1.57it/s] 82%|████████▏ | 47184/57600 [8:18:06<1:48:17, 1.60it/s] 82%|████████▏ | 47185/57600 [8:18:07<1:47:31, 1.61it/s] 82%|████████▏ | 47186/57600 [8:18:08<1:45:34, 1.64it/s] 82%|████████▏ | 47187/57600 [8:18:08<1:45:27, 1.65it/s] 82%|████████▏ | 47188/57600 [8:18:09<1:48:56, 1.59it/s] 82%|████████▏ | 47189/57600 [8:18:10<1:46:31, 1.63it/s] 82%|██��█████▏ | 47190/57600 [8:18:10<1:46:41, 1.63it/s] 82%|████████▏ | 47191/57600 [8:18:11<1:45:29, 1.64it/s] 82%|████████▏ | 47192/57600 [8:18:11<1:51:03, 1.56it/s] 82%|████████▏ | 47193/57600 [8:18:12<1:50:55, 1.56it/s] 82%|████████▏ | 47194/57600 [8:18:13<1:47:51, 1.61it/s] 82%|████████▏ | 47195/57600 [8:18:13<1:48:32, 1.60it/s] 82%|████████▏ | 47196/57600 [8:18:14<1:47:24, 1.61it/s] 82%|████████▏ | 47197/57600 [8:18:15<1:47:08, 1.62it/s] 82%|████████▏ | 47198/57600 [8:18:15<1:51:58, 1.55it/s] 82%|████████▏ | 47199/57600 [8:18:16<1:50:34, 1.57it/s] 82%|████████▏ | 47200/57600 [8:18:16<1:49:57, 1.58it/s] {'loss': 1.1445, 'learning_rate': 2.6306620209059226e-07, 'epoch': 520.97} + 82%|████████▏ | 47200/57600 [8:18:16<1:49:57, 1.58it/s] 82%|████████▏ | 47201/57600 [8:18:17<1:50:01, 1.58it/s] 82%|████████▏ | 47202/57600 [8:18:18<1:50:46, 1.56it/s] 82%|████████▏ | 47203/57600 [8:18:18<1:53:50, 1.52it/s] 82%|████████▏ | 47204/57600 [8:18:19<1:51:45, 1.55it/s] 82%|████████▏ | 47205/57600 [8:18:20<1:47:36, 1.61it/s] 82%|████████▏ | 47206/57600 [8:18:20<1:52:21, 1.54it/s] 82%|████████▏ | 47207/57600 [8:18:21<1:51:05, 1.56it/s] 82%|████████▏ | 47208/57600 [8:18:22<1:47:00, 1.62it/s] 82%|████████▏ | 47209/57600 [8:18:22<1:45:33, 1.64it/s] 82%|████████▏ | 47210/57600 [8:18:23<1:48:34, 1.59it/s] 82%|████████▏ | 47211/57600 [8:18:23<1:47:11, 1.62it/s] 82%|████████▏ | 47212/57600 [8:18:24<1:46:35, 1.62it/s] 82%|████████▏ | 47213/57600 [8:18:25<1:48:53, 1.59it/s] 82%|████████▏ | 47214/57600 [8:18:25<1:45:57, 1.63it/s] 82%|████████▏ | 47215/57600 [8:18:26<1:45:03, 1.65it/s] 82%|████████▏ | 47216/57600 [8:18:26<1:47:22, 1.61it/s] 82%|████████▏ | 47217/57600 [8:18:27<1:48:58, 1.59it/s] 82%|████████▏ | 47218/57600 [8:18:28<1:48:00, 1.60it/s] 82%|████████▏ | 47219/57600 [8:18:28<1:47:10, 1.61it/s] 82%|████████▏ | 47220/57600 [8:18:29<1:47:02, 1.62it/s] {'loss': 1.1007, 'learning_rate': 2.627526132404181e-07, 'epoch': 521.19} + 82%|████████▏ | 47220/57600 [8:18:29<1:47:02, 1.62it/s] 82%|████████▏ | 47221/57600 [8:18:30<1:49:40, 1.58it/s] 82%|████████▏ | 47222/57600 [8:18:30<1:49:06, 1.59it/s] 82%|████████▏ | 47223/57600 [8:18:31<1:51:13, 1.56it/s] 82%|████████▏ | 47224/57600 [8:18:32<1:52:24, 1.54it/s] 82%|████████▏ | 47225/57600 [8:18:32<1:52:02, 1.54it/s] 82%|████████▏ | 47226/57600 [8:18:33<1:48:33, 1.59it/s] 82%|████████▏ | 47227/57600 [8:18:33<1:48:21, 1.60it/s] 82%|████████▏ | 47228/57600 [8:18:34<1:46:28, 1.62it/s] 82%|████████▏ | 47229/57600 [8:18:35<1:49:09, 1.58it/s] 82%|████████▏ | 47230/57600 [8:18:35<1:46:57, 1.62it/s] 82%|████████▏ | 47231/57600 [8:18:36<1:48:55, 1.59it/s] 82%|████████▏ | 47232/57600 [8:18:37<1:48:36, 1.59it/s] 82%|████████▏ | 47233/57600 [8:18:37<1:47:06, 1.61it/s] 82%|████████▏ | 47234/57600 [8:18:38<1:48:29, 1.59it/s] 82%|████████▏ | 47235/57600 [8:18:39<1:50:46, 1.56it/s] 82%|████████▏ | 47236/57600 [8:18:39<1:50:18, 1.57it/s] 82%|████████▏ | 47237/57600 [8:18:40<1:48:25, 1.59it/s] 82%|████████▏ | 47238/57600 [8:18:40<1:46:11, 1.63it/s] 82%|████████▏ | 47239/57600 [8:18:41<1:44:32, 1.65it/s] 82%|████████▏ | 47240/57600 [8:18:42<1:44:44, 1.65it/s] {'loss': 1.1411, 'learning_rate': 2.6243902439024393e-07, 'epoch': 521.41} + 82%|████████▏ | 47240/57600 [8:18:42<1:44:44, 1.65it/s] 82%|████████▏ | 47241/57600 [8:18:42<1:44:59, 1.64it/s] 82%|████████▏ | 47242/57600 [8:18:43<1:48:52, 1.59it/s] 82%|████████▏ | 47243/57600 [8:18:43<1:47:00, 1.61it/s] 82%|████████▏ | 47244/57600 [8:18:44<1:44:49, 1.65it/s] 82%|████████▏ | 47245/57600 [8:18:45<1:47:33, 1.60it/s] 82%|████████▏ | 47246/57600 [8:18:45<1:47:29, 1.61it/s] 82%|████████▏ | 47247/57600 [8:18:46<1:49:48, 1.57it/s] 82%|████████▏ | 47248/57600 [8:18:47<1:47:46, 1.60it/s] 82%|████████▏ | 47249/57600 [8:18:47<1:49:46, 1.57it/s] 82%|████████▏ | 47250/57600 [8:18:48<1:46:34, 1.62it/s] 82%|████████▏ | 47251/57600 [8:18:48<1:45:10, 1.64it/s] 82%|████████▏ | 47252/57600 [8:18:49<1:43:37, 1.66it/s] 82%|████████▏ | 47253/57600 [8:18:50<1:42:37, 1.68it/s] 82%|████████▏ | 47254/57600 [8:18:50<1:49:08, 1.58it/s] 82%|████████▏ | 47255/57600 [8:18:51<1:51:21, 1.55it/s] 82%|████████▏ | 47256/57600 [8:18:52<1:51:05, 1.55it/s] 82%|████████▏ | 47257/57600 [8:18:52<1:51:00, 1.55it/s] 82%|████████▏ | 47258/57600 [8:18:53<1:56:22, 1.48it/s] 82%|████████▏ | 47259/57600 [8:18:54<1:53:29, 1.52it/s] 82%|████████▏ | 47260/57600 [8:18:54<1:48:08, 1.59it/s] {'loss': 1.0919, 'learning_rate': 2.621254355400696e-07, 'epoch': 521.63} + 82%|████████▏ | 47260/57600 [8:18:54<1:48:08, 1.59it/s] 82%|████████▏ | 47261/57600 [8:18:55<1:45:42, 1.63it/s] 82%|████████▏ | 47262/57600 [8:18:55<1:45:20, 1.64it/s] 82%|████████▏ | 47263/57600 [8:18:56<1:47:39, 1.60it/s] 82%|████████▏ | 47264/57600 [8:18:57<1:49:57, 1.57it/s] 82%|████████▏ | 47265/57600 [8:18:57<1:49:46, 1.57it/s] 82%|████████▏ | 47266/57600 [8:18:58<1:49:13, 1.58it/s] 82%|████████▏ | 47267/57600 [8:18:59<1:48:27, 1.59it/s] 82%|████████▏ | 47268/57600 [8:18:59<1:46:56, 1.61it/s] 82%|████████▏ | 47269/57600 [8:19:00<1:45:27, 1.63it/s] 82%|████████▏ | 47270/57600 [8:19:00<1:47:06, 1.61it/s] 82%|████████▏ | 47271/57600 [8:19:01<1:44:54, 1.64it/s] 82%|████████▏ | 47272/57600 [8:19:02<1:47:34, 1.60it/s] 82%|████████▏ | 47273/57600 [8:19:02<1:45:59, 1.62it/s] 82%|████████▏ | 47274/57600 [8:19:03<1:44:17, 1.65it/s] 82%|████████▏ | 47275/57600 [8:19:03<1:45:47, 1.63it/s] 82%|████████▏ | 47276/57600 [8:19:04<1:48:48, 1.58it/s] 82%|████████▏ | 47277/57600 [8:19:05<1:45:56, 1.62it/s] 82%|████████▏ | 47278/57600 [8:19:05<1:46:53, 1.61it/s] 82%|████████▏ | 47279/57600 [8:19:06<1:48:47, 1.58it/s] 82%|████████▏ | 47280/57600 [8:19:07<1:51:11, 1.55it/s] {'loss': 1.1141, 'learning_rate': 2.618118466898955e-07, 'epoch': 521.85} + 82%|████████▏ | 47280/57600 [8:19:07<1:51:11, 1.55it/s] 82%|████████▏ | 47281/57600 [8:19:07<1:50:38, 1.55it/s] 82%|████████▏ | 47282/57600 [8:19:08<1:52:24, 1.53it/s] 82%|████████▏ | 47283/57600 [8:19:09<1:49:02, 1.58it/s] 82%|████████▏ | 47284/57600 [8:19:09<1:50:05, 1.56it/s] 82%|████████▏ | 47285/57600 [8:19:10<1:52:52, 1.52it/s] 82%|████████▏ | 47286/57600 [8:19:10<1:49:05, 1.58it/s] 82%|████████▏ | 47287/57600 [8:19:11<1:51:53, 1.54it/s] 82%|████████▏ | 47288/57600 [8:19:12<1:49:12, 1.57it/s] 82%|████████▏ | 47289/57600 [8:19:12<1:49:26, 1.57it/s] 82%|████████▏ | 47290/57600 [8:19:13<1:46:23, 1.62it/s] 82%|████████▏ | 47291/57600 [8:19:14<1:49:26, 1.57it/s] 82%|████████▏ | 47292/57600 [8:19:14<1:45:45, 1.62it/s] 82%|████████▏ | 47293/57600 [8:19:15<1:45:58, 1.62it/s] 82%|████████▏ | 47294/57600 [8:19:16<1:55:41, 1.48it/s] 82%|████████▏ | 47295/57600 [8:19:16<1:52:12, 1.53it/s] 82%|████████▏ | 47296/57600 [8:19:17<1:54:49, 1.50it/s] 82%|████████▏ | 47297/57600 [8:19:18<1:53:10, 1.52it/s] 82%|████████▏ | 47298/57600 [8:19:18<1:49:01, 1.57it/s] 82%|████████▏ | 47299/57600 [8:19:19<1:51:00, 1.55it/s] 82%|████████▏ | 47300/57600 [8:19:20<1:52:17, 1.53it/s] {'loss': 1.1354, 'learning_rate': 2.6149825783972124e-07, 'epoch': 522.08} + 82%|████████▏ | 47300/57600 [8:19:20<1:52:17, 1.53it/s] 82%|████████▏ | 47301/57600 [8:19:20<1:50:09, 1.56it/s] 82%|████████▏ | 47302/57600 [8:19:21<1:47:29, 1.60it/s] 82%|████████▏ | 47303/57600 [8:19:21<1:44:21, 1.64it/s] 82%|████████▏ | 47304/57600 [8:19:22<1:46:08, 1.62it/s] 82%|████████▏ | 47305/57600 [8:19:23<1:48:23, 1.58it/s] 82%|████████▏ | 47306/57600 [8:19:23<1:48:31, 1.58it/s] 82%|████████▏ | 47307/57600 [8:19:24<1:46:15, 1.61it/s] 82%|█████��██▏ | 47308/57600 [8:19:25<1:51:10, 1.54it/s] 82%|████████▏ | 47309/57600 [8:19:25<1:48:33, 1.58it/s] 82%|████████▏ | 47310/57600 [8:19:26<1:45:24, 1.63it/s] 82%|████████▏ | 47311/57600 [8:19:26<1:48:19, 1.58it/s] 82%|████████▏ | 47312/57600 [8:19:27<1:47:15, 1.60it/s] 82%|████████▏ | 47313/57600 [8:19:28<1:46:19, 1.61it/s] 82%|████████▏ | 47314/57600 [8:19:28<1:51:14, 1.54it/s] 82%|████████▏ | 47315/57600 [8:19:29<1:52:39, 1.52it/s] 82%|████████▏ | 47316/57600 [8:19:30<1:53:23, 1.51it/s] 82%|████████▏ | 47317/57600 [8:19:30<1:49:43, 1.56it/s] 82%|████████▏ | 47318/57600 [8:19:31<1:50:27, 1.55it/s] 82%|████████▏ | 47319/57600 [8:19:31<1:47:35, 1.59it/s] 82%|████████▏ | 47320/57600 [8:19:32<1:46:05, 1.61it/s] {'loss': 1.1543, 'learning_rate': 2.6118466898954704e-07, 'epoch': 522.3} + 82%|████████▏ | 47320/57600 [8:19:32<1:46:05, 1.61it/s] 82%|████████▏ | 47321/57600 [8:19:33<1:44:11, 1.64it/s] 82%|████████▏ | 47322/57600 [8:19:33<1:47:08, 1.60it/s] 82%|████████▏ | 47323/57600 [8:19:34<1:44:49, 1.63it/s] 82%|████████▏ | 47324/57600 [8:19:35<1:52:02, 1.53it/s] 82%|████████▏ | 47325/57600 [8:19:35<1:46:59, 1.60it/s] 82%|████████▏ | 47326/57600 [8:19:36<1:44:27, 1.64it/s] 82%|████████▏ | 47327/57600 [8:19:36<1:46:08, 1.61it/s] 82%|████████▏ | 47328/57600 [8:19:37<1:43:12, 1.66it/s] 82%|████████▏ | 47329/57600 [8:19:38<1:41:18, 1.69it/s] 82%|████████▏ | 47330/57600 [8:19:38<1:48:22, 1.58it/s] 82%|████████▏ | 47331/57600 [8:19:39<1:48:10, 1.58it/s] 82%|████████▏ | 47332/57600 [8:19:40<1:50:34, 1.55it/s] 82%|████████▏ | 47333/57600 [8:19:40<1:51:58, 1.53it/s] 82%|████████▏ | 47334/57600 [8:19:41<1:47:33, 1.59it/s] 82%|████████▏ | 47335/57600 [8:19:41<1:44:29, 1.64it/s] 82%|████████▏ | 47336/57600 [8:19:42<1:45:20, 1.62it/s] 82%|████████▏ | 47337/57600 [8:19:43<1:46:04, 1.61it/s] 82%|████████▏ | 47338/57600 [8:19:43<1:48:37, 1.57it/s] 82%|████████▏ | 47339/57600 [8:19:44<1:49:37, 1.56it/s] 82%|████████▏ | 47340/57600 [8:19:45<1:48:21, 1.58it/s] {'loss': 1.1414, 'learning_rate': 2.6087108013937274e-07, 'epoch': 522.52} + 82%|████████▏ | 47340/57600 [8:19:45<1:48:21, 1.58it/s] 82%|████████▏ | 47341/57600 [8:19:45<1:46:27, 1.61it/s] 82%|████████▏ | 47342/57600 [8:19:46<1:49:29, 1.56it/s] 82%|████████▏ | 47343/57600 [8:19:47<1:49:42, 1.56it/s] 82%|████████▏ | 47344/57600 [8:19:47<1:51:23, 1.53it/s] 82%|████████▏ | 47345/57600 [8:19:48<1:47:45, 1.59it/s] 82%|████████▏ | 47346/57600 [8:19:48<1:46:35, 1.60it/s] 82%|████████▏ | 47347/57600 [8:19:49<1:45:10, 1.62it/s] 82%|████████▏ | 47348/57600 [8:19:50<1:48:37, 1.57it/s] 82%|████████▏ | 47349/57600 [8:19:50<1:47:38, 1.59it/s] 82%|████████▏ | 47350/57600 [8:19:51<1:46:28, 1.60it/s] 82%|████████▏ | 47351/57600 [8:19:52<1:44:54, 1.63it/s] 82%|████████▏ | 47352/57600 [8:19:52<1:44:46, 1.63it/s] 82%|████████▏ | 47353/57600 [8:19:53<1:44:08, 1.64it/s] 82%|████████▏ | 47354/57600 [8:19:53<1:44:24, 1.64it/s] 82%|████████▏ | 47355/57600 [8:19:54<1:43:31, 1.65it/s] 82%|████████▏ | 47356/57600 [8:19:55<1:47:30, 1.59it/s] 82%|████████▏ | 47357/57600 [8:19:55<1:49:30, 1.56it/s] 82%|████████▏ | 47358/57600 [8:19:56<1:49:29, 1.56it/s] 82%|████████▏ | 47359/57600 [8:19:57<1:47:17, 1.59it/s] 82%|████████▏ | 47360/57600 [8:19:57<1:44:11, 1.64it/s] {'loss': 1.1354, 'learning_rate': 2.605574912891986e-07, 'epoch': 522.74} + 82%|████████▏ | 47360/57600 [8:19:57<1:44:11, 1.64it/s] 82%|████████▏ | 47361/57600 [8:19:58<1:42:52, 1.66it/s] 82%|████████▏ | 47362/57600 [8:19:58<1:41:39, 1.68it/s] 82%|████████▏ | 47363/57600 [8:19:59<1:42:16, 1.67it/s] 82%|████████▏ | 47364/57600 [8:19:59<1:41:27, 1.68it/s] 82%|████████▏ | 47365/57600 [8:20:00<1:44:48, 1.63it/s] 82%|████████▏ | 47366/57600 [8:20:01<1:45:23, 1.62it/s] 82%|███████���▏ | 47367/57600 [8:20:01<1:45:34, 1.62it/s] 82%|████████▏ | 47368/57600 [8:20:02<1:45:28, 1.62it/s] 82%|████████▏ | 47369/57600 [8:20:03<1:45:58, 1.61it/s] 82%|████████▏ | 47370/57600 [8:20:03<1:44:57, 1.62it/s] 82%|████████▏ | 47371/57600 [8:20:04<1:44:24, 1.63it/s] 82%|████████▏ | 47372/57600 [8:20:04<1:45:32, 1.62it/s] 82%|████████▏ | 47373/57600 [8:20:05<1:45:28, 1.62it/s] 82%|████████▏ | 47374/57600 [8:20:06<1:42:52, 1.66it/s] 82%|████████▏ | 47375/57600 [8:20:06<1:44:33, 1.63it/s] 82%|████████▏ | 47376/57600 [8:20:07<1:43:44, 1.64it/s] 82%|████████▏ | 47377/57600 [8:20:08<1:45:07, 1.62it/s] 82%|████████▏ | 47378/57600 [8:20:08<1:44:21, 1.63it/s] 82%|████████▏ | 47379/57600 [8:20:09<1:43:27, 1.65it/s] 82%|████████▏ | 47380/57600 [8:20:09<1:43:52, 1.64it/s] {'loss': 1.1349, 'learning_rate': 2.6024390243902446e-07, 'epoch': 522.96} + 82%|████████▏ | 47380/57600 [8:20:09<1:43:52, 1.64it/s] 82%|████████▏ | 47381/57600 [8:20:10<1:42:28, 1.66it/s] 82%|████████▏ | 47382/57600 [8:20:11<1:45:33, 1.61it/s] 82%|████████▏ | 47383/57600 [8:20:11<1:45:39, 1.61it/s] 82%|████████▏ | 47384/57600 [8:20:12<1:50:24, 1.54it/s] 82%|████████▏ | 47385/57600 [8:20:12<1:47:18, 1.59it/s] 82%|████████▏ | 47386/57600 [8:20:13<1:48:13, 1.57it/s] 82%|████████▏ | 47387/57600 [8:20:14<1:48:26, 1.57it/s] 82%|████████▏ | 47388/57600 [8:20:14<1:46:56, 1.59it/s] 82%|████████▏ | 47389/57600 [8:20:15<1:44:39, 1.63it/s] 82%|████████▏ | 47390/57600 [8:20:16<1:43:48, 1.64it/s] 82%|████████▏ | 47391/57600 [8:20:16<1:42:24, 1.66it/s] 82%|████████▏ | 47392/57600 [8:20:17<1:43:14, 1.65it/s] 82%|████████▏ | 47393/57600 [8:20:17<1:41:05, 1.68it/s] 82%|████████▏ | 47394/57600 [8:20:18<1:45:36, 1.61it/s] 82%|████████▏ | 47395/57600 [8:20:19<1:46:58, 1.59it/s] 82%|████████▏ | 47396/57600 [8:20:19<1:43:26, 1.64it/s] 82%|████████▏ | 47397/57600 [8:20:20<1:44:51, 1.62it/s] 82%|████████▏ | 47398/57600 [8:20:21<1:48:31, 1.57it/s] 82%|████████▏ | 47399/57600 [8:20:21<1:50:31, 1.54it/s] 82%|████████▏ | 47400/57600 [8:20:22<1:50:26, 1.54it/s] {'loss': 1.0901, 'learning_rate': 2.5993031358885015e-07, 'epoch': 523.18} + 82%|████████▏ | 47400/57600 [8:20:22<1:50:26, 1.54it/s] 82%|████████▏ | 47401/57600 [8:20:23<1:51:45, 1.52it/s] 82%|████████▏ | 47402/57600 [8:20:23<1:48:31, 1.57it/s] 82%|████████▏ | 47403/57600 [8:20:24<1:46:43, 1.59it/s] 82%|████████▏ | 47404/57600 [8:20:24<1:45:17, 1.61it/s] 82%|████████▏ | 47405/57600 [8:20:25<1:44:25, 1.63it/s] 82%|████████▏ | 47406/57600 [8:20:26<1:44:50, 1.62it/s] 82%|████████▏ | 47407/57600 [8:20:26<1:50:28, 1.54it/s] 82%|████████▏ | 47408/57600 [8:20:27<1:50:41, 1.53it/s] 82%|████████▏ | 47409/57600 [8:20:28<1:48:59, 1.56it/s] 82%|████████▏ | 47410/57600 [8:20:28<1:45:00, 1.62it/s] 82%|████████▏ | 47411/57600 [8:20:29<1:44:45, 1.62it/s] 82%|████████▏ | 47412/57600 [8:20:29<1:44:08, 1.63it/s] 82%|████████▏ | 47413/57600 [8:20:30<1:45:11, 1.61it/s] 82%|████████▏ | 47414/57600 [8:20:31<1:45:17, 1.61it/s] 82%|████████▏ | 47415/57600 [8:20:31<1:43:36, 1.64it/s] 82%|████████▏ | 47416/57600 [8:20:32<1:43:46, 1.64it/s] 82%|████████▏ | 47417/57600 [8:20:32<1:44:58, 1.62it/s] 82%|████████▏ | 47418/57600 [8:20:33<1:43:54, 1.63it/s] 82%|████████▏ | 47419/57600 [8:20:34<1:45:46, 1.60it/s] 82%|████████▏ | 47420/57600 [8:20:34<1:45:59, 1.60it/s] {'loss': 1.1694, 'learning_rate': 2.5961672473867596e-07, 'epoch': 523.4} + 82%|████████▏ | 47420/57600 [8:20:34<1:45:59, 1.60it/s] 82%|████████▏ | 47421/57600 [8:20:35<1:46:33, 1.59it/s] 82%|████████▏ | 47422/57600 [8:20:36<1:51:24, 1.52it/s] 82%|████████▏ | 47423/57600 [8:20:36<1:55:31, 1.47it/s] 82%|████████▏ | 47424/57600 [8:20:37<1:52:57, 1.50it/s] 82%|████████▏ | 47425/57600 [8:20:38<1:51:10, 1.53it/s] 82%|████████�� | 47426/57600 [8:20:38<1:47:21, 1.58it/s] 82%|████████▏ | 47427/57600 [8:20:39<1:46:16, 1.60it/s] 82%|████████▏ | 47428/57600 [8:20:39<1:46:03, 1.60it/s] 82%|████████▏ | 47429/57600 [8:20:40<1:48:52, 1.56it/s] 82%|████████▏ | 47430/57600 [8:20:41<1:47:29, 1.58it/s] 82%|████████▏ | 47431/57600 [8:20:41<1:46:25, 1.59it/s] 82%|████████▏ | 47432/57600 [8:20:42<1:43:50, 1.63it/s] 82%|████████▏ | 47433/57600 [8:20:43<1:45:19, 1.61it/s] 82%|████████▏ | 47434/57600 [8:20:43<1:44:11, 1.63it/s] 82%|████████▏ | 47435/57600 [8:20:44<1:45:10, 1.61it/s] 82%|████████▏ | 47436/57600 [8:20:44<1:44:14, 1.63it/s] 82%|████████▏ | 47437/57600 [8:20:45<1:46:35, 1.59it/s] 82%|████████▏ | 47438/57600 [8:20:46<1:45:15, 1.61it/s] 82%|████████▏ | 47439/57600 [8:20:46<1:47:41, 1.57it/s] 82%|████████▏ | 47440/57600 [8:20:47<1:45:15, 1.61it/s] {'loss': 1.1072, 'learning_rate': 2.593031358885017e-07, 'epoch': 523.62} + 82%|████████▏ | 47440/57600 [8:20:47<1:45:15, 1.61it/s] 82%|████████▏ | 47441/57600 [8:20:48<1:45:42, 1.60it/s] 82%|████████▏ | 47442/57600 [8:20:48<1:48:44, 1.56it/s] 82%|████████▏ | 47443/57600 [8:20:49<1:46:10, 1.59it/s] 82%|████████▏ | 47444/57600 [8:20:49<1:44:52, 1.61it/s] 82%|████████▏ | 47445/57600 [8:20:50<1:42:25, 1.65it/s] 82%|████████▏ | 47446/57600 [8:20:51<1:42:42, 1.65it/s] 82%|████████▏ | 47447/57600 [8:20:51<1:45:30, 1.60it/s] 82%|████████▏ | 47448/57600 [8:20:52<1:46:10, 1.59it/s] 82%|████████▏ | 47449/57600 [8:20:53<1:42:48, 1.65it/s] 82%|████████▏ | 47450/57600 [8:20:53<1:42:35, 1.65it/s] 82%|████████▏ | 47451/57600 [8:20:54<1:43:41, 1.63it/s] 82%|████████▏ | 47452/57600 [8:20:54<1:47:11, 1.58it/s] 82%|████████▏ | 47453/57600 [8:20:55<1:49:49, 1.54it/s] 82%|████████▏ | 47454/57600 [8:20:56<1:48:21, 1.56it/s] 82%|████████▏ | 47455/57600 [8:20:56<1:47:17, 1.58it/s] 82%|████████▏ | 47456/57600 [8:20:57<1:48:35, 1.56it/s] 82%|████████▏ | 47457/57600 [8:20:58<1:54:10, 1.48it/s] 82%|████████▏ | 47458/57600 [8:20:58<1:51:12, 1.52it/s] 82%|████████▏ | 47459/57600 [8:20:59<1:53:51, 1.48it/s] 82%|████████▏ | 47460/57600 [8:21:00<1:51:43, 1.51it/s] {'loss': 1.1324, 'learning_rate': 2.589895470383275e-07, 'epoch': 523.84} + 82%|████████▏ | 47460/57600 [8:21:00<1:51:43, 1.51it/s] 82%|████████▏ | 47461/57600 [8:21:00<1:52:31, 1.50it/s] 82%|████████▏ | 47462/57600 [8:21:01<1:48:23, 1.56it/s] 82%|████████▏ | 47463/57600 [8:21:02<1:48:21, 1.56it/s] 82%|████████▏ | 47464/57600 [8:21:02<1:45:56, 1.59it/s] 82%|████████▏ | 47465/57600 [8:21:03<1:50:41, 1.53it/s] 82%|████████▏ | 47466/57600 [8:21:04<1:47:04, 1.58it/s] 82%|████████▏ | 47467/57600 [8:21:04<1:47:59, 1.56it/s] 82%|████████▏ | 47468/57600 [8:21:05<1:47:02, 1.58it/s] 82%|████████▏ | 47469/57600 [8:21:05<1:44:50, 1.61it/s] 82%|████████▏ | 47470/57600 [8:21:06<1:46:46, 1.58it/s] 82%|████████▏ | 47471/57600 [8:21:07<1:47:20, 1.57it/s] 82%|████████▏ | 47472/57600 [8:21:07<1:45:16, 1.60it/s] 82%|████████▏ | 47473/57600 [8:21:08<1:43:42, 1.63it/s] 82%|████████▏ | 47474/57600 [8:21:09<1:43:28, 1.63it/s] 82%|████████▏ | 47475/57600 [8:21:09<1:47:15, 1.57it/s] 82%|████████▏ | 47476/57600 [8:21:10<1:45:19, 1.60it/s] 82%|████████▏ | 47477/57600 [8:21:10<1:43:48, 1.63it/s] 82%|████████▏ | 47478/57600 [8:21:11<1:43:46, 1.63it/s] 82%|████████▏ | 47479/57600 [8:21:12<1:41:50, 1.66it/s] 82%|████████▏ | 47480/57600 [8:21:12<1:40:31, 1.68it/s] {'loss': 1.1341, 'learning_rate': 2.5867595818815316e-07, 'epoch': 524.06} + 82%|████████▏ | 47480/57600 [8:21:12<1:40:31, 1.68it/s] 82%|████████▏ | 47481/57600 [8:21:13<1:45:04, 1.60it/s] 82%|████████▏ | 47482/57600 [8:21:13<1:42:27, 1.65it/s] 82%|████████▏ | 47483/57600 [8:21:14<1:42:50, 1.64it/s] 82%|████████▏ | 47484/57600 [8:21:15<1:42:28, 1.65it/s] 82%|████████▏ | 47485/57600 [8:21:15<1:44:25, 1.61it/s] 82%|████████▏ | 47486/57600 [8:21:16<1:45:23, 1.60it/s] 82%|████████▏ | 47487/57600 [8:21:17<1:45:27, 1.60it/s] 82%|████████▏ | 47488/57600 [8:21:17<1:44:01, 1.62it/s] 82%|████████▏ | 47489/57600 [8:21:18<1:44:46, 1.61it/s] 82%|████████▏ | 47490/57600 [8:21:18<1:44:37, 1.61it/s] 82%|████████▏ | 47491/57600 [8:21:19<1:45:13, 1.60it/s] 82%|████████▏ | 47492/57600 [8:21:20<1:47:29, 1.57it/s] 82%|████████▏ | 47493/57600 [8:21:20<1:47:20, 1.57it/s] 82%|████████▏ | 47494/57600 [8:21:21<1:47:06, 1.57it/s] 82%|████████▏ | 47495/57600 [8:21:22<1:48:45, 1.55it/s] 82%|████████▏ | 47496/57600 [8:21:22<1:47:35, 1.57it/s] 82%|████████▏ | 47497/57600 [8:21:23<1:47:53, 1.56it/s] 82%|████████▏ | 47498/57600 [8:21:24<1:46:29, 1.58it/s] 82%|████████▏ | 47499/57600 [8:21:24<1:46:42, 1.58it/s] 82%|████████▏ | 47500/57600 [8:21:25<1:48:54, 1.55it/s] {'loss': 1.1216, 'learning_rate': 2.5836236933797907e-07, 'epoch': 524.28} + 82%|████████▏ | 47500/57600 [8:21:25<1:48:54, 1.55it/s] 82%|████████▏ | 47501/57600 [8:21:25<1:46:32, 1.58it/s] 82%|████████▏ | 47502/57600 [8:21:26<1:43:12, 1.63it/s] 82%|████████▏ | 47503/57600 [8:21:27<1:48:21, 1.55it/s] 82%|████████▏ | 47504/57600 [8:21:27<1:47:22, 1.57it/s] 82%|████████▏ | 47505/57600 [8:21:28<1:43:16, 1.63it/s] 82%|████████▏ | 47506/57600 [8:21:29<1:44:53, 1.60it/s] 82%|████████▏ | 47507/57600 [8:21:29<1:43:25, 1.63it/s] 82%|████████▏ | 47508/57600 [8:21:30<1:50:56, 1.52it/s] 82%|████████▏ | 47509/57600 [8:21:31<1:51:56, 1.50it/s] 82%|████████▏ | 47510/57600 [8:21:31<1:51:56, 1.50it/s] 82%|████████▏ | 47511/57600 [8:21:32<1:49:50, 1.53it/s] 82%|████████▏ | 47512/57600 [8:21:33<1:53:36, 1.48it/s] 82%|████████▏ | 47513/57600 [8:21:33<1:49:30, 1.54it/s] 82%|████████▏ | 47514/57600 [8:21:34<1:51:08, 1.51it/s] 82%|████████▏ | 47515/57600 [8:21:34<1:48:02, 1.56it/s] 82%|████████▏ | 47516/57600 [8:21:35<1:47:58, 1.56it/s] 82%|████████▏ | 47517/57600 [8:21:36<1:46:28, 1.58it/s] 82%|████████▏ | 47518/57600 [8:21:36<1:46:58, 1.57it/s] 82%|████████▏ | 47519/57600 [8:21:37<1:45:30, 1.59it/s] 82%|████████▎ | 47520/57600 [8:21:38<1:44:33, 1.61it/s] {'loss': 1.1209, 'learning_rate': 2.5804878048780493e-07, 'epoch': 524.5} + 82%|████████▎ | 47520/57600 [8:21:38<1:44:33, 1.61it/s] 83%|████████▎ | 47521/57600 [8:21:38<1:44:30, 1.61it/s] 83%|████████▎ | 47522/57600 [8:21:39<1:44:18, 1.61it/s] 83%|████████▎ | 47523/57600 [8:21:39<1:44:46, 1.60it/s] 83%|████████▎ | 47524/57600 [8:21:40<1:46:38, 1.57it/s] 83%|████████▎ | 47525/57600 [8:21:41<1:45:38, 1.59it/s] 83%|████████▎ | 47526/57600 [8:21:41<1:47:29, 1.56it/s] 83%|████████▎ | 47527/57600 [8:21:42<1:48:30, 1.55it/s] 83%|████████▎ | 47528/57600 [8:21:43<1:45:43, 1.59it/s] 83%|████████▎ | 47529/57600 [8:21:43<1:45:16, 1.59it/s] 83%|████████▎ | 47530/57600 [8:21:44<1:44:11, 1.61it/s] 83%|████████▎ | 47531/57600 [8:21:44<1:42:43, 1.63it/s] 83%|████████▎ | 47532/57600 [8:21:45<1:45:32, 1.59it/s] 83%|████████▎ | 47533/57600 [8:21:46<1:41:59, 1.65it/s] 83%|████████▎ | 47534/57600 [8:21:46<1:41:14, 1.66it/s] 83%|████████▎ | 47535/57600 [8:21:47<1:43:40, 1.62it/s] 83%|████████▎ | 47536/57600 [8:21:48<1:44:09, 1.61it/s] 83%|████████▎ | 47537/57600 [8:21:48<1:43:29, 1.62it/s] 83%|████████▎ | 47538/57600 [8:21:49<1:43:47, 1.62it/s] 83%|████████▎ | 47539/57600 [8:21:49<1:42:49, 1.63it/s] 83%|████████▎ | 47540/57600 [8:21:50<1:41:33, 1.65it/s] {'loss': 1.141, 'learning_rate': 2.5773519163763063e-07, 'epoch': 524.72} + 83%|████████▎ | 47540/57600 [8:21:50<1:41:33, 1.65it/s] 83%|████████▎ | 47541/57600 [8:21:51<1:44:02, 1.61it/s] 83%|████████▎ | 47542/57600 [8:21:51<1:43:16, 1.62it/s] 83%|████████▎ | 47543/57600 [8:21:52<1:45:58, 1.58it/s] 83%|████████▎ | 47544/57600 [8:21:53<1:43:37, 1.62it/s] 83%|████████▎ | 47545/57600 [8:21:53<1:44:12, 1.61it/s] 83%|████████▎ | 47546/57600 [8:21:54<1:45:21, 1.59it/s] 83%|████████▎ | 47547/57600 [8:21:54<1:47:14, 1.56it/s] 83%|████████▎ | 47548/57600 [8:21:55<1:47:46, 1.55it/s] 83%|████████▎ | 47549/57600 [8:21:56<1:45:51, 1.58it/s] 83%|████████▎ | 47550/57600 [8:21:56<1:44:14, 1.61it/s] 83%|████████▎ | 47551/57600 [8:21:57<1:44:10, 1.61it/s] 83%|████████▎ | 47552/57600 [8:21:58<1:44:49, 1.60it/s] 83%|████████▎ | 47553/57600 [8:21:58<1:42:44, 1.63it/s] 83%|████████▎ | 47554/57600 [8:21:59<1:42:45, 1.63it/s] 83%|████████▎ | 47555/57600 [8:21:59<1:43:14, 1.62it/s] 83%|████████▎ | 47556/57600 [8:22:00<1:49:16, 1.53it/s] 83%|████████▎ | 47557/57600 [8:22:01<1:47:54, 1.55it/s] 83%|████████▎ | 47558/57600 [8:22:01<1:48:49, 1.54it/s] 83%|████████▎ | 47559/57600 [8:22:02<1:45:57, 1.58it/s] 83%|████████▎ | 47560/57600 [8:22:03<1:47:43, 1.55it/s] {'loss': 1.1072, 'learning_rate': 2.5742160278745643e-07, 'epoch': 524.94} + 83%|████████▎ | 47560/57600 [8:22:03<1:47:43, 1.55it/s] 83%|████████▎ | 47561/57600 [8:22:03<1:47:23, 1.56it/s] 83%|████████▎ | 47562/57600 [8:22:04<1:45:45, 1.58it/s] 83%|████████▎ | 47563/57600 [8:22:05<1:43:26, 1.62it/s] 83%|████████▎ | 47564/57600 [8:22:05<1:49:57, 1.52it/s] 83%|████████▎ | 47565/57600 [8:22:06<1:51:27, 1.50it/s] 83%|████████▎ | 47566/57600 [8:22:07<1:55:26, 1.45it/s] 83%|████████▎ | 47567/57600 [8:22:07<1:54:40, 1.46it/s] 83%|████████▎ | 47568/57600 [8:22:08<1:50:55, 1.51it/s] 83%|████████▎ | 47569/57600 [8:22:09<1:48:56, 1.53it/s] 83%|████████▎ | 47570/57600 [8:22:09<1:46:14, 1.57it/s] 83%|████████▎ | 47571/57600 [8:22:10<1:44:46, 1.60it/s] 83%|████████▎ | 47572/57600 [8:22:10<1:44:14, 1.60it/s] 83%|████████▎ | 47573/57600 [8:22:11<1:45:39, 1.58it/s] 83%|████████▎ | 47574/57600 [8:22:12<1:44:26, 1.60it/s] 83%|████████▎ | 47575/57600 [8:22:12<1:42:46, 1.63it/s] 83%|████████▎ | 47576/57600 [8:22:13<1:42:32, 1.63it/s] 83%|████████▎ | 47577/57600 [8:22:14<1:44:22, 1.60it/s] 83%|████████▎ | 47578/57600 [8:22:14<1:42:29, 1.63it/s] 83%|████████▎ | 47579/57600 [8:22:15<1:40:01, 1.67it/s] 83%|████████▎ | 47580/57600 [8:22:15<1:39:54, 1.67it/s] {'loss': 1.1676, 'learning_rate': 2.571080139372822e-07, 'epoch': 525.17} + 83%|████████▎ | 47580/57600 [8:22:15<1:39:54, 1.67it/s] 83%|████████▎ | 47581/57600 [8:22:16<1:40:26, 1.66it/s] 83%|████████▎ | 47582/57600 [8:22:17<1:41:04, 1.65it/s] 83%|████████▎ | 47583/57600 [8:22:17<1:43:25, 1.61it/s] 83%|████████▎ | 47584/57600 [8:22:18<1:42:24, 1.63it/s] 83%|████████▎ | 47585/57600 [8:22:18<1:43:09, 1.62it/s] 83%|████████▎ | 47586/57600 [8:22:19<1:40:08, 1.67it/s] 83%|████████▎ | 47587/57600 [8:22:20<1:39:48, 1.67it/s] 83%|████████▎ | 47588/57600 [8:22:20<1:42:55, 1.62it/s] 83%|████████▎ | 47589/57600 [8:22:21<1:42:08, 1.63it/s] 83%|████████▎ | 47590/57600 [8:22:21<1:41:11, 1.65it/s] 83%|████████▎ | 47591/57600 [8:22:22<1:39:07, 1.68it/s] 83%|████████▎ | 47592/57600 [8:22:23<1:41:33, 1.64it/s] 83%|████████▎ | 47593/57600 [8:22:23<1:42:55, 1.62it/s] 83%|████████▎ | 47594/57600 [8:22:24<1:45:46, 1.58it/s] 83%|████████▎ | 47595/57600 [8:22:24<1:41:52, 1.64it/s] 83%|████████▎ | 47596/57600 [8:22:25<1:40:41, 1.66it/s] 83%|████████▎ | 47597/57600 [8:22:26<1:38:55, 1.69it/s] 83%|████████▎ | 47598/57600 [8:22:26<1:39:49, 1.67it/s] 83%|████████▎ | 47599/57600 [8:22:27<1:40:52, 1.65it/s] 83%|████████▎ | 47600/57600 [8:22:27<1:40:50, 1.65it/s] {'loss': 1.1765, 'learning_rate': 2.5679442508710804e-07, 'epoch': 525.39} + 83%|████████▎ | 47600/57600 [8:22:27<1:40:50, 1.65it/s] 83%|████████▎ | 47601/57600 [8:22:28<1:41:50, 1.64it/s] 83%|████████▎ | 47602/57600 [8:22:29<1:40:10, 1.66it/s] 83%|████████▎ | 47603/57600 [8:22:29<1:40:20, 1.66it/s] 83%|████████▎ | 47604/57600 [8:22:30<1:42:22, 1.63it/s] 83%|████████▎ | 47605/57600 [8:22:31<1:41:59, 1.63it/s] 83%|████████▎ | 47606/57600 [8:22:31<1:45:42, 1.58it/s] 83%|████████▎ | 47607/57600 [8:22:32<1:46:31, 1.56it/s] 83%|████████▎ | 47608/57600 [8:22:33<1:48:11, 1.54it/s] 83%|████████▎ | 47609/57600 [8:22:33<1:50:04, 1.51it/s] 83%|████████▎ | 47610/57600 [8:22:34<1:50:00, 1.51it/s] 83%|████████▎ | 47611/57600 [8:22:35<1:48:24, 1.54it/s] 83%|████████▎ | 47612/57600 [8:22:35<1:48:34, 1.53it/s] 83%|████████▎ | 47613/57600 [8:22:36<1:46:02, 1.57it/s] 83%|████████▎ | 47614/57600 [8:22:36<1:46:20, 1.57it/s] 83%|████████▎ | 47615/57600 [8:22:37<1:48:48, 1.53it/s] 83%|████████▎ | 47616/57600 [8:22:38<1:49:04, 1.53it/s] 83%|████████▎ | 47617/57600 [8:22:38<1:48:01, 1.54it/s] 83%|████████▎ | 47618/57600 [8:22:39<1:48:31, 1.53it/s] 83%|████████▎ | 47619/57600 [8:22:40<1:45:46, 1.57it/s] 83%|████████▎ | 47620/57600 [8:22:40<1:45:47, 1.57it/s] {'loss': 1.1005, 'learning_rate': 2.5648083623693374e-07, 'epoch': 525.61} + 83%|████████▎ | 47620/57600 [8:22:40<1:45:47, 1.57it/s] 83%|████████▎ | 47621/57600 [8:22:41<1:50:51, 1.50it/s] 83%|████████▎ | 47622/57600 [8:22:42<1:50:55, 1.50it/s] 83%|████████▎ | 47623/57600 [8:22:42<1:47:18, 1.55it/s] 83%|████████▎ | 47624/57600 [8:22:43<1:49:56, 1.51it/s] 83%|████████▎ | 47625/57600 [8:22:44<1:48:52, 1.53it/s] 83%|████████▎ | 47626/57600 [8:22:44<1:45:07, 1.58it/s] 83%|████████▎ | 47627/57600 [8:22:45<1:44:42, 1.59it/s] 83%|████████▎ | 47628/57600 [8:22:46<1:47:25, 1.55it/s] 83%|████████▎ | 47629/57600 [8:22:46<1:46:53, 1.55it/s] 83%|████████▎ | 47630/57600 [8:22:47<1:47:51, 1.54it/s] 83%|████████▎ | 47631/57600 [8:22:47<1:43:58, 1.60it/s] 83%|████████▎ | 47632/57600 [8:22:48<1:41:26, 1.64it/s] 83%|████████▎ | 47633/57600 [8:22:49<1:40:57, 1.65it/s] 83%|████████▎ | 47634/57600 [8:22:49<1:43:24, 1.61it/s] 83%|████████▎ | 47635/57600 [8:22:50<1:41:15, 1.64it/s] 83%|████████▎ | 47636/57600 [8:22:51<1:47:10, 1.55it/s] 83%|████████▎ | 47637/57600 [8:22:51<1:47:11, 1.55it/s] 83%|████████▎ | 47638/57600 [8:22:52<1:44:08, 1.59it/s] 83%|████████▎ | 47639/57600 [8:22:52<1:41:05, 1.64it/s] 83%|████████▎ | 47640/57600 [8:22:53<1:42:34, 1.62it/s] {'loss': 1.0937, 'learning_rate': 2.5616724738675955e-07, 'epoch': 525.83} + 83%|████████▎ | 47640/57600 [8:22:53<1:42:34, 1.62it/s] 83%|████████▎ | 47641/57600 [8:22:54<1:45:11, 1.58it/s] 83%|████████▎ | 47642/57600 [8:22:54<1:46:39, 1.56it/s] 83%|████████▎ | 47643/57600 [8:22:55<1:44:29, 1.59it/s] 83%|████████▎ | 47644/57600 [8:22:56<1:48:39, 1.53it/s] 83%|████████▎ | 47645/57600 [8:22:56<1:47:09, 1.55it/s] 83%|████████▎ | 47646/57600 [8:22:57<1:43:46, 1.60it/s] 83%|████████▎ | 47647/57600 [8:22:57<1:44:34, 1.59it/s] 83%|████████▎ | 47648/57600 [8:22:58<1:46:22, 1.56it/s] 83%|████████▎ | 47649/57600 [8:22:59<1:49:38, 1.51it/s] 83%|████████▎ | 47650/57600 [8:22:59<1:44:06, 1.59it/s] 83%|████████▎ | 47651/57600 [8:23:00<1:44:55, 1.58it/s] 83%|████████▎ | 47652/57600 [8:23:01<1:45:51, 1.57it/s] 83%|████████▎ | 47653/57600 [8:23:01<1:46:36, 1.56it/s] 83%|████████▎ | 47654/57600 [8:23:02<1:45:39, 1.57it/s] 83%|████████▎ | 47655/57600 [8:23:03<1:44:56, 1.58it/s] 83%|████████▎ | 47656/57600 [8:23:03<1:54:07, 1.45it/s] 83%|████████▎ | 47657/57600 [8:23:04<1:49:58, 1.51it/s] 83%|████████▎ | 47658/57600 [8:23:05<1:51:42, 1.48it/s] 83%|████████▎ | 47659/57600 [8:23:05<1:51:42, 1.48it/s] 83%|████████▎ | 47660/57600 [8:23:06<1:50:09, 1.50it/s] {'loss': 1.0996, 'learning_rate': 2.558536585365854e-07, 'epoch': 526.05} + 83%|████████▎ | 47660/57600 [8:23:06<1:50:09, 1.50it/s] 83%|████████▎ | 47661/57600 [8:23:07<1:48:15, 1.53it/s] 83%|████████▎ | 47662/57600 [8:23:07<1:46:47, 1.55it/s] 83%|████████▎ | 47663/57600 [8:23:08<1:50:52, 1.49it/s] 83%|████████▎ | 47664/57600 [8:23:09<1:52:20, 1.47it/s] 83%|████████▎ | 47665/57600 [8:23:09<1:48:56, 1.52it/s] 83%|████████▎ | 47666/57600 [8:23:10<1:47:41, 1.54it/s] 83%|████████▎ | 47667/57600 [8:23:11<1:43:43, 1.60it/s] 83%|████████▎ | 47668/57600 [8:23:11<1:42:40, 1.61it/s] 83%|████████▎ | 47669/57600 [8:23:12<1:41:53, 1.62it/s] 83%|████████▎ | 47670/57600 [8:23:12<1:46:20, 1.56it/s] 83%|████████▎ | 47671/57600 [8:23:13<1:43:44, 1.60it/s] 83%|████████▎ | 47672/57600 [8:23:14<1:43:06, 1.60it/s] 83%|████████▎ | 47673/57600 [8:23:14<1:40:47, 1.64it/s] 83%|████████▎ | 47674/57600 [8:23:15<1:42:10, 1.62it/s] 83%|████████▎ | 47675/57600 [8:23:15<1:41:12, 1.63it/s] 83%|████████▎ | 47676/57600 [8:23:16<1:46:19, 1.56it/s] 83%|████████▎ | 47677/57600 [8:23:17<1:46:31, 1.55it/s] 83%|████████▎ | 47678/57600 [8:23:17<1:45:14, 1.57it/s] 83%|████████▎ | 47679/57600 [8:23:18<1:44:26, 1.58it/s] 83%|████████▎ | 47680/57600 [8:23:19<1:41:19, 1.63it/s] {'loss': 1.1112, 'learning_rate': 2.5554006968641116e-07, 'epoch': 526.27} + 83%|████████▎ | 47680/57600 [8:23:19<1:41:19, 1.63it/s] 83%|████████▎ | 47681/57600 [8:23:19<1:44:51, 1.58it/s] 83%|████████▎ | 47682/57600 [8:23:20<1:42:27, 1.61it/s] 83%|████████▎ | 47683/57600 [8:23:20<1:40:24, 1.65it/s] 83%|████████▎ | 47684/57600 [8:23:21<1:39:15, 1.66it/s] 83%|████████▎ | 47685/57600 [8:23:22<1:38:01, 1.69it/s] 83%|████████▎ | 47686/57600 [8:23:22<1:36:36, 1.71it/s] 83%|████████▎ | 47687/57600 [8:23:23<1:39:02, 1.67it/s] 83%|████████▎ | 47688/57600 [8:23:23<1:40:32, 1.64it/s] 83%|████████▎ | 47689/57600 [8:23:24<1:40:27, 1.64it/s] 83%|████████▎ | 47690/57600 [8:23:25<1:45:07, 1.57it/s] 83%|████████▎ | 47691/57600 [8:23:25<1:40:42, 1.64it/s] 83%|████████▎ | 47692/57600 [8:23:26<1:41:37, 1.62it/s] 83%|████████▎ | 47693/57600 [8:23:27<1:43:08, 1.60it/s] 83%|████████▎ | 47694/57600 [8:23:27<1:43:26, 1.60it/s] 83%|████████▎ | 47695/57600 [8:23:28<1:43:07, 1.60it/s] 83%|████████▎ | 47696/57600 [8:23:28<1:40:47, 1.64it/s] 83%|████████▎ | 47697/57600 [8:23:29<1:40:10, 1.65it/s] 83%|████████▎ | 47698/57600 [8:23:30<1:41:53, 1.62it/s] 83%|████████▎ | 47699/57600 [8:23:30<1:39:32, 1.66it/s] 83%|████████▎ | 47700/57600 [8:23:31<1:38:20, 1.68it/s] {'loss': 1.1295, 'learning_rate': 2.552264808362369e-07, 'epoch': 526.49} + 83%|████████▎ | 47700/57600 [8:23:31<1:38:20, 1.68it/s] 83%|████████▎ | 47701/57600 [8:23:31<1:38:22, 1.68it/s] 83%|████████▎ | 47702/57600 [8:23:32<1:38:26, 1.68it/s] 83%|████████▎ | 47703/57600 [8:23:33<1:39:54, 1.65it/s] 83%|████████▎ | 47704/57600 [8:23:33<1:40:24, 1.64it/s] 83%|████████▎ | 47705/57600 [8:23:34<1:44:46, 1.57it/s] 83%|████████▎ | 47706/57600 [8:23:35<1:43:21, 1.60it/s] 83%|████████▎ | 47707/57600 [8:23:35<1:43:58, 1.59it/s] 83%|████████▎ | 47708/57600 [8:23:36<1:47:33, 1.53it/s] 83%|████████▎ | 47709/57600 [8:23:36<1:45:18, 1.57it/s] 83%|████████▎ | 47710/57600 [8:23:37<1:44:05, 1.58it/s] 83%|████████▎ | 47711/57600 [8:23:38<1:43:51, 1.59it/s] 83%|████████▎ | 47712/57600 [8:23:38<1:43:07, 1.60it/s] 83%|████████▎ | 47713/57600 [8:23:39<1:42:42, 1.60it/s] 83%|████████▎ | 47714/57600 [8:23:40<1:43:40, 1.59it/s] 83%|████████▎ | 47715/57600 [8:23:40<1:43:44, 1.59it/s] 83%|████████▎ | 47716/57600 [8:23:41<1:47:12, 1.54it/s] 83%|████████▎ | 47717/57600 [8:23:42<1:48:18, 1.52it/s] 83%|████████▎ | 47718/57600 [8:23:42<1:52:47, 1.46it/s] 83%|████████▎ | 47719/57600 [8:23:43<1:46:28, 1.55it/s] 83%|████████▎ | 47720/57600 [8:23:44<1:49:55, 1.50it/s] {'loss': 1.0978, 'learning_rate': 2.5491289198606266e-07, 'epoch': 526.71} + 83%|████████▎ | 47720/57600 [8:23:44<1:49:55, 1.50it/s] 83%|████████▎ | 47721/57600 [8:23:44<1:48:03, 1.52it/s] 83%|████████▎ | 47722/57600 [8:23:45<1:48:50, 1.51it/s] 83%|████████▎ | 47723/57600 [8:23:46<1:46:35, 1.54it/s] 83%|████████▎ | 47724/57600 [8:23:46<1:44:06, 1.58it/s] 83%|████████▎ | 47725/57600 [8:23:47<1:42:41, 1.60it/s] 83%|████████▎ | 47726/57600 [8:23:47<1:45:09, 1.56it/s] 83%|████████▎ | 47727/57600 [8:23:48<1:46:13, 1.55it/s] 83%|████████▎ | 47728/57600 [8:23:49<1:48:57, 1.51it/s] 83%|████████▎ | 47729/57600 [8:23:49<1:48:01, 1.52it/s] 83%|████████▎ | 47730/57600 [8:23:50<1:52:40, 1.46it/s] 83%|████████▎ | 47731/57600 [8:23:51<1:46:08, 1.55it/s] 83%|████████▎ | 47732/57600 [8:23:51<1:43:14, 1.59it/s] 83%|████████▎ | 47733/57600 [8:23:52<1:46:07, 1.55it/s] 83%|████████▎ | 47734/57600 [8:23:53<1:47:58, 1.52it/s] 83%|████████▎ | 47735/57600 [8:23:53<1:44:27, 1.57it/s] 83%|████████▎ | 47736/57600 [8:23:54<1:45:43, 1.55it/s] 83%|████████▎ | 47737/57600 [8:23:55<1:45:07, 1.56it/s] 83%|████████▎ | 47738/57600 [8:23:55<1:44:09, 1.58it/s] 83%|████████▎ | 47739/57600 [8:23:56<1:44:29, 1.57it/s] 83%|████████▎ | 47740/57600 [8:23:56<1:44:49, 1.57it/s] {'loss': 1.0924, 'learning_rate': 2.545993031358885e-07, 'epoch': 526.93} + 83%|████████▎ | 47740/57600 [8:23:56<1:44:49, 1.57it/s] 83%|████████▎ | 47741/57600 [8:23:57<1:45:17, 1.56it/s] 83%|████████▎ | 47742/57600 [8:23:58<1:43:25, 1.59it/s] 83%|████████▎ | 47743/57600 [8:23:58<1:41:45, 1.61it/s] 83%|████████▎ | 47744/57600 [8:23:59<1:41:56, 1.61it/s] 83%|████████▎ | 47745/57600 [8:24:00<1:38:47, 1.66it/s] 83%|████████▎ | 47746/57600 [8:24:00<1:39:20, 1.65it/s] 83%|████████▎ | 47747/57600 [8:24:01<1:43:10, 1.59it/s] 83%|████████▎ | 47748/57600 [8:24:01<1:42:52, 1.60it/s] 83%|████████▎ | 47749/57600 [8:24:02<1:41:16, 1.62it/s] 83%|████████▎ | 47750/57600 [8:24:03<1:39:37, 1.65it/s] 83%|████████▎ | 47751/57600 [8:24:03<1:40:19, 1.64it/s] 83%|████████▎ | 47752/57600 [8:24:04<1:40:19, 1.64it/s] 83%|████████▎ | 47753/57600 [8:24:04<1:39:01, 1.66it/s] 83%|████████▎ | 47754/57600 [8:24:05<1:37:51, 1.68it/s] 83%|████████▎ | 47755/57600 [8:24:06<1:36:29, 1.70it/s] 83%|████████▎ | 47756/57600 [8:24:06<1:39:23, 1.65it/s] 83%|████████▎ | 47757/57600 [8:24:07<1:46:54, 1.53it/s] 83%|████████▎ | 47758/57600 [8:24:08<1:42:09, 1.61it/s] 83%|████████▎ | 47759/57600 [8:24:08<1:39:18, 1.65it/s] 83%|████████▎ | 47760/57600 [8:24:09<1:39:34, 1.65it/s] {'loss': 1.184, 'learning_rate': 2.542857142857142e-07, 'epoch': 527.15} + 83%|████████▎ | 47760/57600 [8:24:09<1:39:34, 1.65it/s] 83%|████████▎ | 47761/57600 [8:24:09<1:40:59, 1.62it/s] 83%|████████▎ | 47762/57600 [8:24:10<1:46:59, 1.53it/s] 83%|████████▎ | 47763/57600 [8:24:11<1:46:23, 1.54it/s] 83%|████████▎ | 47764/57600 [8:24:11<1:43:04, 1.59it/s] 83%|████████▎ | 47765/57600 [8:24:12<1:42:52, 1.59it/s] 83%|████████▎ | 47766/57600 [8:24:13<1:41:06, 1.62it/s] 83%|████████▎ | 47767/57600 [8:24:13<1:42:23, 1.60it/s] 83%|████████▎ | 47768/57600 [8:24:14<1:43:02, 1.59it/s] 83%|████████▎ | 47769/57600 [8:24:14<1:42:42, 1.60it/s] 83%|████████▎ | 47770/57600 [8:24:15<1:44:47, 1.56it/s] 83%|████████▎ | 47771/57600 [8:24:16<1:45:16, 1.56it/s] 83%|████████▎ | 47772/57600 [8:24:16<1:43:09, 1.59it/s] 83%|████████▎ | 47773/57600 [8:24:17<1:41:42, 1.61it/s] 83%|████████▎ | 47774/57600 [8:24:18<1:43:29, 1.58it/s] 83%|████████▎ | 47775/57600 [8:24:18<1:40:46, 1.62it/s] 83%|████████▎ | 47776/57600 [8:24:19<1:41:54, 1.61it/s] 83%|████████▎ | 47777/57600 [8:24:19<1:41:36, 1.61it/s] 83%|████████▎ | 47778/57600 [8:24:20<1:43:58, 1.57it/s] 83%|████████▎ | 47779/57600 [8:24:21<1:41:35, 1.61it/s] 83%|████████▎ | 47780/57600 [8:24:21<1:42:00, 1.60it/s] {'loss': 1.1071, 'learning_rate': 2.5397212543554e-07, 'epoch': 527.37} + 83%|████████▎ | 47780/57600 [8:24:21<1:42:00, 1.60it/s] 83%|████████▎ | 47781/57600 [8:24:22<1:42:12, 1.60it/s] 83%|████████▎ | 47782/57600 [8:24:23<1:42:54, 1.59it/s] 83%|████████▎ | 47783/57600 [8:24:23<1:41:12, 1.62it/s] 83%|████████▎ | 47784/57600 [8:24:24<1:41:49, 1.61it/s] 83%|████████▎ | 47785/57600 [8:24:25<1:47:48, 1.52it/s] 83%|████████▎ | 47786/57600 [8:24:25<1:44:47, 1.56it/s] 83%|████████▎ | 47787/57600 [8:24:26<1:50:20, 1.48it/s] 83%|████████▎ | 47788/57600 [8:24:26<1:45:37, 1.55it/s] 83%|████████▎ | 47789/57600 [8:24:27<1:43:30, 1.58it/s] 83%|████████▎ | 47790/57600 [8:24:28<1:44:41, 1.56it/s] 83%|████████▎ | 47791/57600 [8:24:28<1:44:50, 1.56it/s] 83%|████████▎ | 47792/57600 [8:24:29<1:42:37, 1.59it/s] 83%|████████▎ | 47793/57600 [8:24:30<1:43:40, 1.58it/s] 83%|████████▎ | 47794/57600 [8:24:30<1:43:44, 1.58it/s] 83%|████████▎ | 47795/57600 [8:24:31<1:41:02, 1.62it/s] 83%|████████▎ | 47796/57600 [8:24:31<1:38:54, 1.65it/s] 83%|████████▎ | 47797/57600 [8:24:32<1:39:42, 1.64it/s] 83%|████████▎ | 47798/57600 [8:24:33<1:39:19, 1.64it/s] 83%|████████▎ | 47799/57600 [8:24:33<1:39:25, 1.64it/s] 83%|████████▎ | 47800/57600 [8:24:34<1:40:03, 1.63it/s] {'loss': 1.1094, 'learning_rate': 2.536585365853659e-07, 'epoch': 527.59} + 83%|████████▎ | 47800/57600 [8:24:34<1:40:03, 1.63it/s] 83%|████████▎ | 47801/57600 [8:24:35<1:40:53, 1.62it/s] 83%|████████▎ | 47802/57600 [8:24:35<1:42:18, 1.60it/s] 83%|████████▎ | 47803/57600 [8:24:36<1:45:59, 1.54it/s] 83%|████████▎ | 47804/57600 [8:24:36<1:42:39, 1.59it/s] 83%|████████▎ | 47805/57600 [8:24:37<1:43:43, 1.57it/s] 83%|████████▎ | 47806/57600 [8:24:38<1:42:34, 1.59it/s] 83%|████████▎ | 47807/57600 [8:24:38<1:46:35, 1.53it/s] 83%|████████▎ | 47808/57600 [8:24:39<1:49:18, 1.49it/s] 83%|████████▎ | 47809/57600 [8:24:40<1:46:30, 1.53it/s] 83%|████████▎ | 47810/57600 [8:24:40<1:41:47, 1.60it/s] 83%|████████▎ | 47811/57600 [8:24:41<1:43:10, 1.58it/s] 83%|████████▎ | 47812/57600 [8:24:42<1:41:18, 1.61it/s] 83%|████████▎ | 47813/57600 [8:24:42<1:39:40, 1.64it/s] 83%|████████▎ | 47814/57600 [8:24:43<1:39:25, 1.64it/s] 83%|████████▎ | 47815/57600 [8:24:43<1:40:12, 1.63it/s] 83%|████████▎ | 47816/57600 [8:24:44<1:38:34, 1.65it/s] 83%|████████▎ | 47817/57600 [8:24:45<1:42:19, 1.59it/s] 83%|████████▎ | 47818/57600 [8:24:45<1:41:08, 1.61it/s] 83%|████████▎ | 47819/57600 [8:24:46<1:46:18, 1.53it/s] 83%|████████▎ | 47820/57600 [8:24:47<1:42:55, 1.58it/s] {'loss': 1.1137, 'learning_rate': 2.533449477351916e-07, 'epoch': 527.81} + 83%|████████▎ | 47820/57600 [8:24:47<1:42:55, 1.58it/s] 83%|████████▎ | 47821/57600 [8:24:47<1:40:53, 1.62it/s] 83%|████████▎ | 47822/57600 [8:24:48<1:41:36, 1.60it/s] 83%|████████▎ | 47823/57600 [8:24:48<1:39:54, 1.63it/s] 83%|████████▎ | 47824/57600 [8:24:49<1:39:01, 1.65it/s] 83%|████████▎ | 47825/57600 [8:24:50<1:44:42, 1.56it/s] 83%|████████▎ | 47826/57600 [8:24:50<1:41:14, 1.61it/s] 83%|████████▎ | 47827/57600 [8:24:51<1:43:44, 1.57it/s] 83%|████████▎ | 47828/57600 [8:24:52<1:45:50, 1.54it/s] 83%|████████▎ | 47829/57600 [8:24:52<1:41:46, 1.60it/s] 83%|████████▎ | 47830/57600 [8:24:53<1:39:31, 1.64it/s] 83%|████████▎ | 47831/57600 [8:24:53<1:42:47, 1.58it/s] 83%|████████▎ | 47832/57600 [8:24:54<1:41:52, 1.60it/s] 83%|████████▎ | 47833/57600 [8:24:55<1:40:36, 1.62it/s] 83%|████████▎ | 47834/57600 [8:24:55<1:41:26, 1.60it/s] 83%|████████▎ | 47835/57600 [8:24:56<1:47:12, 1.52it/s] 83%|████████▎ | 47836/57600 [8:24:57<1:45:35, 1.54it/s] 83%|████████▎ | 47837/57600 [8:24:57<1:47:32, 1.51it/s] 83%|████████▎ | 47838/57600 [8:24:58<1:50:26, 1.47it/s] 83%|████████▎ | 47839/57600 [8:24:59<1:50:32, 1.47it/s] 83%|████████▎ | 47840/57600 [8:24:59<1:48:32, 1.50it/s] {'loss': 1.1011, 'learning_rate': 2.5303135888501744e-07, 'epoch': 528.04} + 83%|████████▎ | 47840/57600 [8:24:59<1:48:32, 1.50it/s] 83%|████████▎ | 47841/57600 [8:25:00<1:47:07, 1.52it/s] 83%|████████▎ | 47842/57600 [8:25:01<1:48:46, 1.50it/s] 83%|████████▎ | 47843/57600 [8:25:01<1:46:12, 1.53it/s] 83%|████████▎ | 47844/57600 [8:25:02<1:44:34, 1.55it/s] 83%|████████▎ | 47845/57600 [8:25:03<1:43:55, 1.56it/s] 83%|████████▎ | 47846/57600 [8:25:03<1:43:34, 1.57it/s] 83%|████████▎ | 47847/57600 [8:25:04<1:42:21, 1.59it/s] 83%|████████▎ | 47848/57600 [8:25:04<1:39:44, 1.63it/s] 83%|████████▎ | 47849/57600 [8:25:05<1:40:21, 1.62it/s] 83%|████████▎ | 47850/57600 [8:25:06<1:39:29, 1.63it/s] 83%|████████▎ | 47851/57600 [8:25:06<1:40:04, 1.62it/s] 83%|████████▎ | 47852/57600 [8:25:07<1:42:49, 1.58it/s] 83%|████████▎ | 47853/57600 [8:25:08<1:40:52, 1.61it/s] 83%|████████▎ | 47854/57600 [8:25:08<1:39:19, 1.64it/s] 83%|████████▎ | 47855/57600 [8:25:09<1:38:00, 1.66it/s] 83%|████████▎ | 47856/57600 [8:25:09<1:41:22, 1.60it/s] 83%|████████▎ | 47857/57600 [8:25:10<1:42:08, 1.59it/s] 83%|████████▎ | 47858/57600 [8:25:11<1:42:39, 1.58it/s] 83%|████████▎ | 47859/57600 [8:25:11<1:42:45, 1.58it/s] 83%|████████▎ | 47860/57600 [8:25:12<1:39:29, 1.63it/s] {'loss': 1.129, 'learning_rate': 2.5271777003484314e-07, 'epoch': 528.26} + 83%|████████▎ | 47860/57600 [8:25:12<1:39:29, 1.63it/s] 83%|████████▎ | 47861/57600 [8:25:12<1:38:01, 1.66it/s] 83%|████████▎ | 47862/57600 [8:25:13<1:39:01, 1.64it/s] 83%|████████▎ | 47863/57600 [8:25:14<1:39:29, 1.63it/s] 83%|████████▎ | 47864/57600 [8:25:14<1:37:45, 1.66it/s] 83%|████████▎ | 47865/57600 [8:25:15<1:38:36, 1.65it/s] 83%|████████▎ | 47866/57600 [8:25:15<1:37:18, 1.67it/s] 83%|████████▎ | 47867/57600 [8:25:16<1:38:33, 1.65it/s] 83%|████████▎ | 47868/57600 [8:25:17<1:37:57, 1.66it/s] 83%|████████▎ | 47869/57600 [8:25:17<1:35:14, 1.70it/s] 83%|████████▎ | 47870/57600 [8:25:18<1:39:43, 1.63it/s] 83%|████████▎ | 47871/57600 [8:25:19<1:45:27, 1.54it/s] 83%|████████▎ | 47872/57600 [8:25:19<1:43:20, 1.57it/s] 83%|████████▎ | 47873/57600 [8:25:20<1:40:33, 1.61it/s] 83%|████████▎ | 47874/57600 [8:25:21<1:45:23, 1.54it/s] 83%|████████▎ | 47875/57600 [8:25:21<1:45:29, 1.54it/s] 83%|████████▎ | 47876/57600 [8:25:22<1:47:15, 1.51it/s] 83%|████████▎ | 47877/57600 [8:25:22<1:45:12, 1.54it/s] 83%|████████▎ | 47878/57600 [8:25:23<1:40:41, 1.61it/s] 83%|████████▎ | 47879/57600 [8:25:24<1:37:46, 1.66it/s] 83%|████████▎ | 47880/57600 [8:25:24<1:37:03, 1.67it/s] {'loss': 1.1166, 'learning_rate': 2.52404181184669e-07, 'epoch': 528.48} + 83%|████████▎ | 47880/57600 [8:25:24<1:37:03, 1.67it/s] 83%|████████▎ | 47881/57600 [8:25:25<1:43:07, 1.57it/s] 83%|████████▎ | 47882/57600 [8:25:26<1:41:24, 1.60it/s] 83%|████████▎ | 47883/57600 [8:25:26<1:41:30, 1.60it/s] 83%|████████▎ | 47884/57600 [8:25:27<1:38:48, 1.64it/s] 83%|████████▎ | 47885/57600 [8:25:27<1:42:24, 1.58it/s] 83%|████████▎ | 47886/57600 [8:25:28<1:42:56, 1.57it/s] 83%|████████▎ | 47887/57600 [8:25:29<1:40:49, 1.61it/s] 83%|████████▎ | 47888/57600 [8:25:29<1:39:26, 1.63it/s] 83%|████████▎ | 47889/57600 [8:25:30<1:41:41, 1.59it/s] 83%|████████▎ | 47890/57600 [8:25:30<1:40:19, 1.61it/s] 83%|████████▎ | 47891/57600 [8:25:31<1:38:17, 1.65it/s] 83%|████████▎ | 47892/57600 [8:25:32<1:38:23, 1.64it/s] 83%|████████▎ | 47893/57600 [8:25:32<1:39:06, 1.63it/s] 83%|████████▎ | 47894/57600 [8:25:33<1:37:43, 1.66it/s] 83%|████████▎ | 47895/57600 [8:25:34<1:38:25, 1.64it/s] 83%|████████▎ | 47896/57600 [8:25:34<1:36:36, 1.67it/s] 83%|████████▎ | 47897/57600 [8:25:35<1:36:32, 1.68it/s] 83%|████████▎ | 47898/57600 [8:25:35<1:35:24, 1.69it/s] 83%|████████▎ | 47899/57600 [8:25:36<1:39:02, 1.63it/s] 83%|████████▎ | 47900/57600 [8:25:37<1:38:53, 1.63it/s] {'loss': 1.153, 'learning_rate': 2.520905923344948e-07, 'epoch': 528.7} + 83%|████████▎ | 47900/57600 [8:25:37<1:38:53, 1.63it/s] 83%|████████▎ | 47901/57600 [8:25:37<1:37:20, 1.66it/s] 83%|████████▎ | 47902/57600 [8:25:38<1:35:57, 1.68it/s] 83%|████████▎ | 47903/57600 [8:25:38<1:41:21, 1.59it/s] 83%|████████▎ | 47904/57600 [8:25:39<1:44:28, 1.55it/s] 83%|████████▎ | 47905/57600 [8:25:40<1:45:32, 1.53it/s] 83%|████████▎ | 47906/57600 [8:25:40<1:41:51, 1.59it/s] 83%|████████▎ | 47907/57600 [8:25:41<1:44:21, 1.55it/s] 83%|████████▎ | 47908/57600 [8:25:42<1:42:28, 1.58it/s] 83%|████████▎ | 47909/57600 [8:25:42<1:45:20, 1.53it/s] 83%|████████▎ | 47910/57600 [8:25:43<1:44:28, 1.55it/s] 83%|████████▎ | 47911/57600 [8:25:44<1:41:05, 1.60it/s] 83%|████████▎ | 47912/57600 [8:25:44<1:41:34, 1.59it/s] 83%|████████▎ | 47913/57600 [8:25:45<1:40:48, 1.60it/s] 83%|████████▎ | 47914/57600 [8:25:45<1:38:41, 1.64it/s] 83%|████████▎ | 47915/57600 [8:25:46<1:36:36, 1.67it/s] 83%|████████▎ | 47916/57600 [8:25:46<1:35:14, 1.69it/s] 83%|████████▎ | 47917/57600 [8:25:47<1:36:07, 1.68it/s] 83%|████████▎ | 47918/57600 [8:25:48<1:39:52, 1.62it/s] 83%|████████▎ | 47919/57600 [8:25:48<1:43:39, 1.56it/s] 83%|████████▎ | 47920/57600 [8:25:49<1:41:33, 1.59it/s] {'loss': 1.1238, 'learning_rate': 2.5177700348432055e-07, 'epoch': 528.92} + 83%|████████▎ | 47920/57600 [8:25:49<1:41:33, 1.59it/s] 83%|████████▎ | 47921/57600 [8:25:50<1:40:26, 1.61it/s] 83%|████████▎ | 47922/57600 [8:25:50<1:39:50, 1.62it/s] 83%|████████▎ | 47923/57600 [8:25:51<1:37:40, 1.65it/s] 83%|████████▎ | 47924/57600 [8:25:51<1:38:10, 1.64it/s] 83%|████████▎ | 47925/57600 [8:25:52<1:38:22, 1.64it/s] 83%|████████▎ | 47926/57600 [8:25:53<1:40:47, 1.60it/s] 83%|████████▎ | 47927/57600 [8:25:53<1:42:12, 1.58it/s] 83%|████████▎ | 47928/57600 [8:25:54<1:46:58, 1.51it/s] 83%|████████▎ | 47929/57600 [8:25:55<1:45:17, 1.53it/s] 83%|████████▎ | 47930/57600 [8:25:55<1:42:34, 1.57it/s] 83%|████████▎ | 47931/57600 [8:25:56<1:42:38, 1.57it/s] 83%|████████▎ | 47932/57600 [8:25:57<1:41:55, 1.58it/s] 83%|████████▎ | 47933/57600 [8:25:57<1:42:32, 1.57it/s] 83%|████████▎ | 47934/57600 [8:25:58<1:42:31, 1.57it/s] 83%|████████▎ | 47935/57600 [8:25:59<1:43:18, 1.56it/s] 83%|████████▎ | 47936/57600 [8:25:59<1:41:57, 1.58it/s] 83%|████████▎ | 47937/57600 [8:26:00<1:40:47, 1.60it/s] 83%|████████▎ | 47938/57600 [8:26:00<1:40:17, 1.61it/s] 83%|████████▎ | 47939/57600 [8:26:01<1:41:59, 1.58it/s] 83%|████████▎ | 47940/57600 [8:26:02<1:41:28, 1.59it/s] {'loss': 1.1209, 'learning_rate': 2.5146341463414636e-07, 'epoch': 529.14} + 83%|████████▎ | 47940/57600 [8:26:02<1:41:28, 1.59it/s] 83%|████████▎ | 47941/57600 [8:26:02<1:42:21, 1.57it/s] 83%|████████▎ | 47942/57600 [8:26:03<1:44:03, 1.55it/s] 83%|████████▎ | 47943/57600 [8:26:04<1:43:13, 1.56it/s] 83%|████████▎ | 47944/57600 [8:26:04<1:42:23, 1.57it/s] 83%|████████▎ | 47945/57600 [8:26:05<1:42:23, 1.57it/s] 83%|████████▎ | 47946/57600 [8:26:06<1:42:30, 1.57it/s] 83%|████████▎ | 47947/57600 [8:26:06<1:42:25, 1.57it/s] 83%|████████▎ | 47948/57600 [8:26:07<1:41:25, 1.59it/s] 83%|████████▎ | 47949/57600 [8:26:07<1:38:25, 1.63it/s] 83%|████████▎ | 47950/57600 [8:26:08<1:39:16, 1.62it/s] 83%|████████▎ | 47951/57600 [8:26:09<1:45:45, 1.52it/s] 83%|████████▎ | 47952/57600 [8:26:09<1:45:54, 1.52it/s] 83%|████████▎ | 47953/57600 [8:26:10<1:43:26, 1.55it/s] 83%|████████▎ | 47954/57600 [8:26:11<1:45:53, 1.52it/s] 83%|████████▎ | 47955/57600 [8:26:11<1:44:44, 1.53it/s] 83%|████████▎ | 47956/57600 [8:26:12<1:41:28, 1.58it/s] 83%|████████▎ | 47957/57600 [8:26:13<1:41:25, 1.58it/s] 83%|████████▎ | 47958/57600 [8:26:13<1:41:02, 1.59it/s] 83%|████████▎ | 47959/57600 [8:26:14<1:37:59, 1.64it/s] 83%|████████▎ | 47960/57600 [8:26:14<1:37:55, 1.64it/s] {'loss': 1.1242, 'learning_rate': 2.511498257839721e-07, 'epoch': 529.36} + 83%|████████▎ | 47960/57600 [8:26:14<1:37:55, 1.64it/s] 83%|████████▎ | 47961/57600 [8:26:15<1:40:08, 1.60it/s] 83%|████████▎ | 47962/57600 [8:26:16<1:40:30, 1.60it/s] 83%|████████▎ | 47963/57600 [8:26:16<1:42:49, 1.56it/s] 83%|████████▎ | 47964/57600 [8:26:17<1:41:09, 1.59it/s] 83%|████████▎ | 47965/57600 [8:26:18<1:40:21, 1.60it/s] 83%|████████▎ | 47966/57600 [8:26:18<1:41:06, 1.59it/s] 83%|████████▎ | 47967/57600 [8:26:19<1:41:47, 1.58it/s] 83%|████████▎ | 47968/57600 [8:26:19<1:40:29, 1.60it/s] 83%|████████▎ | 47969/57600 [8:26:20<1:39:01, 1.62it/s] 83%|████████▎ | 47970/57600 [8:26:21<1:41:14, 1.59it/s] 83%|████████▎ | 47971/57600 [8:26:21<1:40:07, 1.60it/s] 83%|████████▎ | 47972/57600 [8:26:22<1:39:43, 1.61it/s] 83%|████████▎ | 47973/57600 [8:26:23<1:44:41, 1.53it/s] 83%|████████▎ | 47974/57600 [8:26:23<1:41:41, 1.58it/s] 83%|████████▎ | 47975/57600 [8:26:24<1:37:51, 1.64it/s] 83%|████████▎ | 47976/57600 [8:26:24<1:43:42, 1.55it/s] 83%|████████▎ | 47977/57600 [8:26:25<1:43:28, 1.55it/s] 83%|████████▎ | 47978/57600 [8:26:26<1:42:15, 1.57it/s] 83%|████████▎ | 47979/57600 [8:26:26<1:40:17, 1.60it/s] 83%|████████▎ | 47980/57600 [8:26:27<1:40:41, 1.59it/s] {'loss': 1.1133, 'learning_rate': 2.508362369337979e-07, 'epoch': 529.58} + 83%|████████▎ | 47980/57600 [8:26:27<1:40:41, 1.59it/s] 83%|████████▎ | 47981/57600 [8:26:28<1:40:42, 1.59it/s] 83%|████████▎ | 47982/57600 [8:26:28<1:40:06, 1.60it/s] 83%|████████▎ | 47983/57600 [8:26:29<1:38:54, 1.62it/s] 83%|████████▎ | 47984/57600 [8:26:29<1:39:35, 1.61it/s] 83%|████████▎ | 47985/57600 [8:26:30<1:36:40, 1.66it/s] 83%|████████▎ | 47986/57600 [8:26:31<1:36:29, 1.66it/s] 83%|████████▎ | 47987/57600 [8:26:31<1:37:05, 1.65it/s] 83%|████████▎ | 47988/57600 [8:26:32<1:37:00, 1.65it/s] 83%|████████▎ | 47989/57600 [8:26:33<1:40:18, 1.60it/s] 83%|████████▎ | 47990/57600 [8:26:33<1:41:05, 1.58it/s] 83%|████████▎ | 47991/57600 [8:26:34<1:40:15, 1.60it/s] 83%|████████▎ | 47992/57600 [8:26:34<1:41:41, 1.57it/s] 83%|████████▎ | 47993/57600 [8:26:35<1:40:45, 1.59it/s] 83%|████████▎ | 47994/57600 [8:26:36<1:37:44, 1.64it/s] 83%|████████▎ | 47995/57600 [8:26:36<1:39:53, 1.60it/s] 83%|████████▎ | 47996/57600 [8:26:37<1:41:03, 1.58it/s] 83%|████████▎ | 47997/57600 [8:26:38<1:40:36, 1.59it/s] 83%|████████▎ | 47998/57600 [8:26:38<1:41:18, 1.58it/s] 83%|████████▎ | 47999/57600 [8:26:39<1:39:26, 1.61it/s] 83%|████████▎ | 48000/57600 [8:26:39<1:40:27, 1.59it/s] {'loss': 1.13, 'learning_rate': 2.505226480836236e-07, 'epoch': 529.8} + 83%|████████▎ | 48000/57600 [8:26:39<1:40:27, 1.59it/s] 83%|████████▎ | 48001/57600 [8:26:40<1:41:42, 1.57it/s] 83%|████████▎ | 48002/57600 [8:26:41<1:37:41, 1.64it/s] 83%|████████▎ | 48003/57600 [8:26:41<1:39:34, 1.61it/s] 83%|████████▎ | 48004/57600 [8:26:42<1:39:37, 1.61it/s] 83%|████████▎ | 48005/57600 [8:26:43<1:39:41, 1.60it/s] 83%|████████▎ | 48006/57600 [8:26:43<1:37:21, 1.64it/s] 83%|████████▎ | 48007/57600 [8:26:44<1:36:17, 1.66it/s] 83%|████████▎ | 48008/57600 [8:26:44<1:35:54, 1.67it/s] 83%|████████▎ | 48009/57600 [8:26:45<1:38:17, 1.63it/s] 83%|████████▎ | 48010/57600 [8:26:46<1:39:30, 1.61it/s] 83%|████████▎ | 48011/57600 [8:26:46<1:38:15, 1.63it/s] 83%|████████▎ | 48012/57600 [8:26:47<1:38:42, 1.62it/s] 83%|████████▎ | 48013/57600 [8:26:47<1:38:27, 1.62it/s] 83%|████████▎ | 48014/57600 [8:26:48<1:37:52, 1.63it/s] 83%|████████▎ | 48015/57600 [8:26:49<1:36:37, 1.65it/s] 83%|████████▎ | 48016/57600 [8:26:49<1:36:06, 1.66it/s] 83%|████████▎ | 48017/57600 [8:26:50<1:34:19, 1.69it/s] 83%|████████▎ | 48018/57600 [8:26:50<1:35:08, 1.68it/s] 83%|████████▎ | 48019/57600 [8:26:51<1:41:52, 1.57it/s] 83%|████████▎ | 48020/57600 [8:26:52<1:43:42, 1.54it/s] {'loss': 1.1395, 'learning_rate': 2.5020905923344947e-07, 'epoch': 530.02} + 83%|████████▎ | 48020/57600 [8:26:52<1:43:42, 1.54it/s] 83%|████████▎ | 48021/57600 [8:26:52<1:43:53, 1.54it/s] 83%|████████▎ | 48022/57600 [8:26:53<1:44:06, 1.53it/s] 83%|████████▎ | 48023/57600 [8:26:54<1:40:56, 1.58it/s] 83%|████████▎ | 48024/57600 [8:26:54<1:40:51, 1.58it/s] 83%|████████▎ | 48025/57600 [8:26:55<1:39:40, 1.60it/s] 83%|████████▎ | 48026/57600 [8:26:56<1:41:12, 1.58it/s] 83%|████████▎ | 48027/57600 [8:26:56<1:45:49, 1.51it/s] 83%|████████▎ | 48028/57600 [8:26:57<1:42:55, 1.55it/s] 83%|████████▎ | 48029/57600 [8:26:58<1:46:17, 1.50it/s] 83%|████████▎ | 48030/57600 [8:26:58<1:45:09, 1.52it/s] 83%|████████▎ | 48031/57600 [8:26:59<1:42:21, 1.56it/s] 83%|████████▎ | 48032/57600 [8:26:59<1:40:57, 1.58it/s] 83%|████████▎ | 48033/57600 [8:27:00<1:38:00, 1.63it/s] 83%|████████▎ | 48034/57600 [8:27:01<1:37:17, 1.64it/s] 83%|████████▎ | 48035/57600 [8:27:01<1:39:51, 1.60it/s] 83%|████████▎ | 48036/57600 [8:27:02<1:40:18, 1.59it/s] 83%|████████▎ | 48037/57600 [8:27:03<1:37:54, 1.63it/s] 83%|████████▎ | 48038/57600 [8:27:03<1:38:30, 1.62it/s] 83%|████████▎ | 48039/57600 [8:27:04<1:36:33, 1.65it/s] 83%|████████▎ | 48040/57600 [8:27:04<1:39:58, 1.59it/s] {'loss': 1.0835, 'learning_rate': 2.4989547038327533e-07, 'epoch': 530.24} + 83%|████████▎ | 48040/57600 [8:27:04<1:39:58, 1.59it/s] 83%|████████▎ | 48041/57600 [8:27:05<1:40:16, 1.59it/s] 83%|████████▎ | 48042/57600 [8:27:06<1:38:06, 1.62it/s] 83%|████████▎ | 48043/57600 [8:27:06<1:37:01, 1.64it/s] 83%|████████▎ | 48044/57600 [8:27:07<1:35:55, 1.66it/s] 83%|████████▎ | 48045/57600 [8:27:07<1:35:02, 1.68it/s] 83%|████████▎ | 48046/57600 [8:27:08<1:34:36, 1.68it/s] 83%|████████▎ | 48047/57600 [8:27:09<1:34:23, 1.69it/s] 83%|████████▎ | 48048/57600 [8:27:09<1:37:09, 1.64it/s] 83%|████████▎ | 48049/57600 [8:27:10<1:40:56, 1.58it/s] 83%|████████▎ | 48050/57600 [8:27:11<1:40:03, 1.59it/s] 83%|████████▎ | 48051/57600 [8:27:11<1:40:14, 1.59it/s] 83%|████████▎ | 48052/57600 [8:27:12<1:36:41, 1.65it/s] 83%|████████▎ | 48053/57600 [8:27:12<1:35:03, 1.67it/s] 83%|████████▎ | 48054/57600 [8:27:13<1:35:46, 1.66it/s] 83%|████████▎ | 48055/57600 [8:27:13<1:35:37, 1.66it/s] 83%|████████▎ | 48056/57600 [8:27:14<1:35:49, 1.66it/s] 83%|████████▎ | 48057/57600 [8:27:15<1:35:10, 1.67it/s] 83%|████████▎ | 48058/57600 [8:27:15<1:39:55, 1.59it/s] 83%|████████▎ | 48059/57600 [8:27:16<1:40:55, 1.58it/s] 83%|████████▎ | 48060/57600 [8:27:17<1:40:19, 1.58it/s] {'loss': 1.1185, 'learning_rate': 2.4958188153310103e-07, 'epoch': 530.46} + 83%|████████▎ | 48060/57600 [8:27:17<1:40:19, 1.58it/s] 83%|████████▎ | 48061/57600 [8:27:17<1:40:10, 1.59it/s] 83%|████████▎ | 48062/57600 [8:27:18<1:45:06, 1.51it/s] 83%|████████▎ | 48063/57600 [8:27:19<1:44:16, 1.52it/s] 83%|████████▎ | 48064/57600 [8:27:19<1:44:09, 1.53it/s] 83%|████████▎ | 48065/57600 [8:27:20<1:44:33, 1.52it/s] 83%|████████▎ | 48066/57600 [8:27:21<1:38:48, 1.61it/s] 83%|████████▎ | 48067/57600 [8:27:21<1:36:25, 1.65it/s] 83%|████████▎ | 48068/57600 [8:27:22<1:35:36, 1.66it/s] 83%|████████▎ | 48069/57600 [8:27:22<1:37:10, 1.63it/s] 83%|████████▎ | 48070/57600 [8:27:23<1:37:18, 1.63it/s] 83%|████████▎ | 48071/57600 [8:27:24<1:38:13, 1.62it/s] 83%|████████▎ | 48072/57600 [8:27:24<1:37:51, 1.62it/s] 83%|████████▎ | 48073/57600 [8:27:25<1:39:31, 1.60it/s] 83%|████████▎ | 48074/57600 [8:27:25<1:37:58, 1.62it/s] 83%|████████▎ | 48075/57600 [8:27:26<1:37:59, 1.62it/s] 83%|████████▎ | 48076/57600 [8:27:27<1:36:54, 1.64it/s] 83%|████████▎ | 48077/57600 [8:27:27<1:37:21, 1.63it/s] 83%|████████▎ | 48078/57600 [8:27:28<1:36:28, 1.65it/s] 83%|████████▎ | 48079/57600 [8:27:29<1:39:01, 1.60it/s] 83%|████████▎ | 48080/57600 [8:27:29<1:36:24, 1.65it/s] {'loss': 1.157, 'learning_rate': 2.4926829268292683e-07, 'epoch': 530.68} + 83%|████████▎ | 48080/57600 [8:27:29<1:36:24, 1.65it/s] 83%|████████▎ | 48081/57600 [8:27:30<1:36:22, 1.65it/s] 83%|████████▎ | 48082/57600 [8:27:30<1:36:39, 1.64it/s] 83%|████████▎ | 48083/57600 [8:27:31<1:37:22, 1.63it/s] 83%|████████▎ | 48084/57600 [8:27:32<1:43:53, 1.53it/s] 83%|████████▎ | 48085/57600 [8:27:32<1:41:15, 1.57it/s] 83%|████████▎ | 48086/57600 [8:27:33<1:41:54, 1.56it/s] 83%|████████▎ | 48087/57600 [8:27:34<1:40:24, 1.58it/s] 83%|████████▎ | 48088/57600 [8:27:34<1:40:06, 1.58it/s] 83%|████████▎ | 48089/57600 [8:27:35<1:41:04, 1.57it/s] 83%|████████▎ | 48090/57600 [8:27:35<1:38:55, 1.60it/s] 83%|████████▎ | 48091/57600 [8:27:36<1:39:31, 1.59it/s] 83%|████████▎ | 48092/57600 [8:27:37<1:41:58, 1.55it/s] 83%|████████▎ | 48093/57600 [8:27:37<1:39:08, 1.60it/s] 83%|████████▎ | 48094/57600 [8:27:38<1:38:21, 1.61it/s] 83%|████████▎ | 48095/57600 [8:27:38<1:35:49, 1.65it/s] 84%|████████▎ | 48096/57600 [8:27:39<1:37:45, 1.62it/s] 84%|████████▎ | 48097/57600 [8:27:40<1:35:16, 1.66it/s] 84%|████████▎ | 48098/57600 [8:27:40<1:36:30, 1.64it/s] 84%|████████▎ | 48099/57600 [8:27:41<1:35:56, 1.65it/s] 84%|████████▎ | 48100/57600 [8:27:42<1:35:23, 1.66it/s] {'loss': 1.1264, 'learning_rate': 2.489547038327526e-07, 'epoch': 530.91} + 84%|████████▎ | 48100/57600 [8:27:42<1:35:23, 1.66it/s] 84%|████████▎ | 48101/57600 [8:27:42<1:41:52, 1.55it/s] 84%|████████▎ | 48102/57600 [8:27:43<1:43:19, 1.53it/s] 84%|████████▎ | 48103/57600 [8:27:44<1:43:01, 1.54it/s] 84%|████████▎ | 48104/57600 [8:27:44<1:45:36, 1.50it/s] 84%|████████▎ | 48105/57600 [8:27:45<1:43:06, 1.53it/s] 84%|████████▎ | 48106/57600 [8:27:45<1:40:20, 1.58it/s] 84%|████████▎ | 48107/57600 [8:27:46<1:38:42, 1.60it/s] 84%|████████▎ | 48108/57600 [8:27:47<1:39:10, 1.60it/s] 84%|████████▎ | 48109/57600 [8:27:47<1:44:27, 1.51it/s] 84%|████████▎ | 48110/57600 [8:27:48<1:41:07, 1.56it/s] 84%|████████▎ | 48111/57600 [8:27:49<1:42:46, 1.54it/s] 84%|████████▎ | 48112/57600 [8:27:49<1:40:52, 1.57it/s] 84%|████████▎ | 48113/57600 [8:27:50<1:43:32, 1.53it/s] 84%|████████▎ | 48114/57600 [8:27:51<1:47:54, 1.47it/s] 84%|████████▎ | 48115/57600 [8:27:51<1:45:05, 1.50it/s] 84%|████████▎ | 48116/57600 [8:27:52<1:43:11, 1.53it/s] 84%|████████▎ | 48117/57600 [8:27:53<1:44:37, 1.51it/s] 84%|████████▎ | 48118/57600 [8:27:53<1:43:02, 1.53it/s] 84%|████████▎ | 48119/57600 [8:27:54<1:39:09, 1.59it/s] 84%|████████▎ | 48120/57600 [8:27:55<1:43:36, 1.52it/s] {'loss': 1.0726, 'learning_rate': 2.4864111498257844e-07, 'epoch': 531.13} + 84%|████████▎ | 48120/57600 [8:27:55<1:43:36, 1.52it/s] 84%|████████▎ | 48121/57600 [8:27:55<1:41:17, 1.56it/s] 84%|████████▎ | 48122/57600 [8:27:56<1:41:10, 1.56it/s] 84%|████████▎ | 48123/57600 [8:27:56<1:39:05, 1.59it/s] 84%|████████▎ | 48124/57600 [8:27:57<1:39:15, 1.59it/s] 84%|████████▎ | 48125/57600 [8:27:58<1:40:24, 1.57it/s] 84%|████████▎ | 48126/57600 [8:27:58<1:40:00, 1.58it/s] 84%|████████▎ | 48127/57600 [8:27:59<1:38:37, 1.60it/s] 84%|████████▎ | 48128/57600 [8:28:00<1:37:40, 1.62it/s] 84%|████████▎ | 48129/57600 [8:28:00<1:37:22, 1.62it/s] 84%|████████▎ | 48130/57600 [8:28:01<1:35:16, 1.66it/s] 84%|████████▎ | 48131/57600 [8:28:01<1:35:14, 1.66it/s] 84%|████████▎ | 48132/57600 [8:28:02<1:35:11, 1.66it/s] 84%|████████▎ | 48133/57600 [8:28:03<1:37:55, 1.61it/s] 84%|████████▎ | 48134/57600 [8:28:03<1:46:11, 1.49it/s] 84%|████████▎ | 48135/57600 [8:28:04<1:42:46, 1.53it/s] 84%|████████▎ | 48136/57600 [8:28:05<1:41:18, 1.56it/s] 84%|████████▎ | 48137/57600 [8:28:05<1:39:34, 1.58it/s] 84%|████████▎ | 48138/57600 [8:28:06<1:38:43, 1.60it/s] 84%|████████▎ | 48139/57600 [8:28:06<1:35:50, 1.65it/s] 84%|████████▎ | 48140/57600 [8:28:07<1:33:32, 1.69it/s] {'loss': 1.1548, 'learning_rate': 2.4832752613240414e-07, 'epoch': 531.35} + 84%|████████▎ | 48140/57600 [8:28:07<1:33:32, 1.69it/s] 84%|████████▎ | 48141/57600 [8:28:08<1:36:13, 1.64it/s] 84%|████████▎ | 48142/57600 [8:28:08<1:36:13, 1.64it/s] 84%|████████▎ | 48143/57600 [8:28:09<1:37:48, 1.61it/s] 84%|████████▎ | 48144/57600 [8:28:10<1:38:14, 1.60it/s] 84%|████████▎ | 48145/57600 [8:28:10<1:35:52, 1.64it/s] 84%|████████▎ | 48146/57600 [8:28:11<1:36:27, 1.63it/s] 84%|████████▎ | 48147/57600 [8:28:11<1:37:03, 1.62it/s] 84%|████████▎ | 48148/57600 [8:28:12<1:37:45, 1.61it/s] 84%|████████▎ | 48149/57600 [8:28:13<1:37:51, 1.61it/s] 84%|████████▎ | 48150/57600 [8:28:13<1:38:38, 1.60it/s] 84%|████████▎ | 48151/57600 [8:28:14<1:38:37, 1.60it/s] 84%|████████▎ | 48152/57600 [8:28:15<1:40:38, 1.56it/s] 84%|████████▎ | 48153/57600 [8:28:15<1:42:06, 1.54it/s] 84%|████████▎ | 48154/57600 [8:28:16<1:42:05, 1.54it/s] 84%|████████▎ | 48155/57600 [8:28:16<1:40:02, 1.57it/s] 84%|████████▎ | 48156/57600 [8:28:17<1:38:16, 1.60it/s] 84%|████████▎ | 48157/57600 [8:28:18<1:38:09, 1.60it/s] 84%|████████▎ | 48158/57600 [8:28:18<1:37:26, 1.62it/s] 84%|████████▎ | 48159/57600 [8:28:19<1:35:36, 1.65it/s] 84%|████████▎ | 48160/57600 [8:28:19<1:35:40, 1.64it/s] {'loss': 1.1144, 'learning_rate': 2.4801393728222995e-07, 'epoch': 531.57} + 84%|████████▎ | 48160/57600 [8:28:19<1:35:40, 1.64it/s] 84%|████████▎ | 48161/57600 [8:28:20<1:37:03, 1.62it/s] 84%|████████▎ | 48162/57600 [8:28:21<1:37:19, 1.62it/s] 84%|████████▎ | 48163/57600 [8:28:21<1:41:50, 1.54it/s] 84%|████████▎ | 48164/57600 [8:28:22<1:37:59, 1.60it/s] 84%|████████▎ | 48165/57600 [8:28:23<1:34:35, 1.66it/s] 84%|████████▎ | 48166/57600 [8:28:23<1:37:46, 1.61it/s] 84%|████████▎ | 48167/57600 [8:28:24<1:35:48, 1.64it/s] 84%|████████▎ | 48168/57600 [8:28:24<1:37:51, 1.61it/s] 84%|████████▎ | 48169/57600 [8:28:25<1:41:06, 1.55it/s] 84%|████████▎ | 48170/57600 [8:28:26<1:43:14, 1.52it/s] 84%|████████▎ | 48171/57600 [8:28:27<1:44:12, 1.51it/s] 84%|████████▎ | 48172/57600 [8:28:27<1:40:47, 1.56it/s] 84%|████████▎ | 48173/57600 [8:28:28<1:38:18, 1.60it/s] 84%|████████▎ | 48174/57600 [8:28:28<1:38:41, 1.59it/s] 84%|████████▎ | 48175/57600 [8:28:29<1:38:15, 1.60it/s] 84%|████████▎ | 48176/57600 [8:28:30<1:43:08, 1.52it/s] 84%|████████▎ | 48177/57600 [8:28:30<1:39:03, 1.59it/s] 84%|████████▎ | 48178/57600 [8:28:31<1:36:48, 1.62it/s] 84%|████████▎ | 48179/57600 [8:28:32<1:38:58, 1.59it/s] 84%|████████▎ | 48180/57600 [8:28:32<1:40:30, 1.56it/s] {'loss': 1.1134, 'learning_rate': 2.477003484320558e-07, 'epoch': 531.79} + 84%|████████▎ | 48180/57600 [8:28:32<1:40:30, 1.56it/s] 84%|████████▎ | 48181/57600 [8:28:33<1:39:32, 1.58it/s] 84%|████████▎ | 48182/57600 [8:28:33<1:39:47, 1.57it/s] 84%|████████▎ | 48183/57600 [8:28:34<1:38:16, 1.60it/s] 84%|████████▎ | 48184/57600 [8:28:35<1:40:18, 1.56it/s] 84%|████████▎ | 48185/57600 [8:28:35<1:41:24, 1.55it/s] 84%|████████▎ | 48186/57600 [8:28:36<1:40:01, 1.57it/s] 84%|████████▎ | 48187/57600 [8:28:37<1:38:44, 1.59it/s] 84%|████████▎ | 48188/57600 [8:28:37<1:40:29, 1.56it/s] 84%|████████▎ | 48189/57600 [8:28:38<1:43:33, 1.51it/s] 84%|████████▎ | 48190/57600 [8:28:39<1:41:24, 1.55it/s] 84%|████████▎ | 48191/57600 [8:28:39<1:43:47, 1.51it/s] 84%|████████▎ | 48192/57600 [8:28:40<1:40:12, 1.56it/s] 84%|████████▎ | 48193/57600 [8:28:41<1:40:21, 1.56it/s] 84%|████████▎ | 48194/57600 [8:28:41<1:39:47, 1.57it/s] 84%|████████▎ | 48195/57600 [8:28:42<1:40:26, 1.56it/s] 84%|████████▎ | 48196/57600 [8:28:42<1:40:25, 1.56it/s] 84%|��███████▎ | 48197/57600 [8:28:43<1:37:44, 1.60it/s] 84%|████████▎ | 48198/57600 [8:28:44<1:38:04, 1.60it/s] 84%|████████▎ | 48199/57600 [8:28:44<1:37:39, 1.60it/s] 84%|████████▎ | 48200/57600 [8:28:45<1:42:59, 1.52it/s] {'loss': 1.1017, 'learning_rate': 2.473867595818815e-07, 'epoch': 532.01} + 84%|████████▎ | 48200/57600 [8:28:45<1:42:59, 1.52it/s] 84%|████████▎ | 48201/57600 [8:28:46<1:39:46, 1.57it/s] 84%|████████▎ | 48202/57600 [8:28:46<1:40:19, 1.56it/s] 84%|████████▎ | 48203/57600 [8:28:47<1:37:55, 1.60it/s] 84%|████████▎ | 48204/57600 [8:28:48<1:43:54, 1.51it/s] 84%|████████▎ | 48205/57600 [8:28:48<1:44:41, 1.50it/s] 84%|████████▎ | 48206/57600 [8:28:49<1:43:37, 1.51it/s] 84%|████████▎ | 48207/57600 [8:28:50<1:39:53, 1.57it/s] 84%|████████▎ | 48208/57600 [8:28:50<1:36:20, 1.62it/s] 84%|████████▎ | 48209/57600 [8:28:51<1:36:01, 1.63it/s] 84%|████████▎ | 48210/57600 [8:28:51<1:35:31, 1.64it/s] 84%|████████▎ | 48211/57600 [8:28:52<1:37:40, 1.60it/s] 84%|████████▎ | 48212/57600 [8:28:53<1:39:17, 1.58it/s] 84%|████████▎ | 48213/57600 [8:28:53<1:37:30, 1.60it/s] 84%|████████▎ | 48214/57600 [8:28:54<1:38:55, 1.58it/s] 84%|████████▎ | 48215/57600 [8:28:54<1:39:34, 1.57it/s] 84%|████████▎ | 48216/57600 [8:28:55<1:37:17, 1.61it/s] 84%|████████▎ | 48217/57600 [8:28:56<1:38:46, 1.58it/s] 84%|████████▎ | 48218/57600 [8:28:56<1:43:13, 1.51it/s] 84%|████████▎ | 48219/57600 [8:28:57<1:40:11, 1.56it/s] 84%|████████▎ | 48220/57600 [8:28:58<1:40:21, 1.56it/s] {'loss': 1.1188, 'learning_rate': 2.470731707317073e-07, 'epoch': 532.23} + 84%|████████▎ | 48220/57600 [8:28:58<1:40:21, 1.56it/s] 84%|████████▎ | 48221/57600 [8:28:58<1:40:11, 1.56it/s] 84%|████████▎ | 48222/57600 [8:28:59<1:38:36, 1.58it/s] 84%|████████▎ | 48223/57600 [8:29:00<1:40:24, 1.56it/s] 84%|████████▎ | 48224/57600 [8:29:00<1:42:50, 1.52it/s] 84%|████████▎ | 48225/57600 [8:29:01<1:39:17, 1.57it/s] 84%|████████▎ | 48226/57600 [8:29:02<1:38:13, 1.59it/s] 84%|████████▎ | 48227/57600 [8:29:02<1:41:27, 1.54it/s] 84%|████████▎ | 48228/57600 [8:29:03<1:39:31, 1.57it/s] 84%|████████▎ | 48229/57600 [8:29:03<1:37:48, 1.60it/s] 84%|████████▎ | 48230/57600 [8:29:04<1:37:11, 1.61it/s] 84%|████████▎ | 48231/57600 [8:29:05<1:39:29, 1.57it/s] 84%|████████▎ | 48232/57600 [8:29:05<1:41:34, 1.54it/s] 84%|████████▎ | 48233/57600 [8:29:06<1:39:10, 1.57it/s] 84%|████████▎ | 48234/57600 [8:29:07<1:36:58, 1.61it/s] 84%|████████▎ | 48235/57600 [8:29:07<1:34:57, 1.64it/s] 84%|████████▎ | 48236/57600 [8:29:08<1:34:56, 1.64it/s] 84%|████████▎ | 48237/57600 [8:29:08<1:36:43, 1.61it/s] 84%|████████▎ | 48238/57600 [8:29:09<1:37:30, 1.60it/s] 84%|████████▎ | 48239/57600 [8:29:10<1:37:22, 1.60it/s] 84%|████████▍ | 48240/57600 [8:29:10<1:39:03, 1.57it/s] {'loss': 1.1032, 'learning_rate': 2.4675958188153306e-07, 'epoch': 532.45} + 84%|████████▍ | 48240/57600 [8:29:10<1:39:03, 1.57it/s] 84%|████████▍ | 48241/57600 [8:29:11<1:37:39, 1.60it/s] 84%|████████▍ | 48242/57600 [8:29:12<1:35:55, 1.63it/s] 84%|████████▍ | 48243/57600 [8:29:12<1:37:07, 1.61it/s] 84%|████████▍ | 48244/57600 [8:29:13<1:37:34, 1.60it/s] 84%|████████▍ | 48245/57600 [8:29:13<1:36:18, 1.62it/s] 84%|████████▍ | 48246/57600 [8:29:14<1:34:22, 1.65it/s] 84%|████████▍ | 48247/57600 [8:29:15<1:32:03, 1.69it/s] 84%|████████▍ | 48248/57600 [8:29:15<1:31:15, 1.71it/s] 84%|████████▍ | 48249/57600 [8:29:16<1:34:59, 1.64it/s] 84%|████████▍ | 48250/57600 [8:29:16<1:35:04, 1.64it/s] 84%|████████▍ | 48251/57600 [8:29:17<1:40:50, 1.55it/s] 84%|████████▍ | 48252/57600 [8:29:18<1:39:42, 1.56it/s] 84%|████████▍ | 48253/57600 [8:29:18<1:40:13, 1.55it/s] 84%|████████▍ | 48254/57600 [8:29:19<1:40:22, 1.55it/s] 84%|████████▍ | 48255/57600 [8:29:20<1:38:02, 1.59it/s] 84%|██���█████▍ | 48256/57600 [8:29:20<1:37:35, 1.60it/s] 84%|████████▍ | 48257/57600 [8:29:21<1:40:36, 1.55it/s] 84%|████████▍ | 48258/57600 [8:29:22<1:38:21, 1.58it/s] 84%|████████▍ | 48259/57600 [8:29:22<1:37:42, 1.59it/s] 84%|████████▍ | 48260/57600 [8:29:23<1:34:41, 1.64it/s] {'loss': 1.1564, 'learning_rate': 2.464459930313589e-07, 'epoch': 532.67} + 84%|████████▍ | 48260/57600 [8:29:23<1:34:41, 1.64it/s] 84%|████████▍ | 48261/57600 [8:29:23<1:35:26, 1.63it/s] 84%|████████▍ | 48262/57600 [8:29:24<1:36:12, 1.62it/s] 84%|████████▍ | 48263/57600 [8:29:25<1:34:13, 1.65it/s] 84%|████████▍ | 48264/57600 [8:29:25<1:34:57, 1.64it/s] 84%|████████▍ | 48265/57600 [8:29:26<1:33:19, 1.67it/s] 84%|████████▍ | 48266/57600 [8:29:26<1:35:03, 1.64it/s] 84%|████████▍ | 48267/57600 [8:29:27<1:38:28, 1.58it/s] 84%|████████▍ | 48268/57600 [8:29:28<1:35:56, 1.62it/s] 84%|████████▍ | 48269/57600 [8:29:28<1:34:48, 1.64it/s] 84%|████████▍ | 48270/57600 [8:29:29<1:33:59, 1.65it/s] 84%|████████▍ | 48271/57600 [8:29:29<1:32:27, 1.68it/s] 84%|████████▍ | 48272/57600 [8:29:30<1:31:48, 1.69it/s] 84%|████████▍ | 48273/57600 [8:29:31<1:36:57, 1.60it/s] 84%|████████▍ | 48274/57600 [8:29:31<1:36:00, 1.62it/s] 84%|████████▍ | 48275/57600 [8:29:32<1:38:29, 1.58it/s] 84%|████████▍ | 48276/57600 [8:29:33<1:39:38, 1.56it/s] 84%|████████▍ | 48277/57600 [8:29:33<1:40:51, 1.54it/s] 84%|████████▍ | 48278/57600 [8:29:34<1:40:50, 1.54it/s] 84%|████████▍ | 48279/57600 [8:29:35<1:43:15, 1.50it/s] 84%|████████▍ | 48280/57600 [8:29:35<1:41:13, 1.53it/s] {'loss': 1.1129, 'learning_rate': 2.461324041811846e-07, 'epoch': 532.89} + 84%|████████▍ | 48280/57600 [8:29:35<1:41:13, 1.53it/s] 84%|████████▍ | 48281/57600 [8:29:36<1:42:11, 1.52it/s] 84%|████████▍ | 48282/57600 [8:29:37<1:43:26, 1.50it/s] 84%|████████▍ | 48283/57600 [8:29:37<1:41:09, 1.54it/s] 84%|████████▍ | 48284/57600 [8:29:38<1:40:33, 1.54it/s] 84%|████████▍ | 48285/57600 [8:29:38<1:39:44, 1.56it/s] 84%|████████▍ | 48286/57600 [8:29:39<1:38:45, 1.57it/s] 84%|████████▍ | 48287/57600 [8:29:40<1:39:06, 1.57it/s] 84%|████████▍ | 48288/57600 [8:29:40<1:38:04, 1.58it/s] 84%|████████▍ | 48289/57600 [8:29:41<1:38:04, 1.58it/s] 84%|████████▍ | 48290/57600 [8:29:42<1:39:02, 1.57it/s] 84%|████████▍ | 48291/57600 [8:29:42<1:40:20, 1.55it/s] 84%|████████▍ | 48292/57600 [8:29:43<1:39:35, 1.56it/s] 84%|████████▍ | 48293/57600 [8:29:44<1:38:02, 1.58it/s] 84%|████████▍ | 48294/57600 [8:29:44<1:40:18, 1.55it/s] 84%|████████▍ | 48295/57600 [8:29:45<1:40:34, 1.54it/s] 84%|████████▍ | 48296/57600 [8:29:45<1:37:37, 1.59it/s] 84%|████████▍ | 48297/57600 [8:29:46<1:41:17, 1.53it/s] 84%|████████▍ | 48298/57600 [8:29:47<1:39:10, 1.56it/s] 84%|████████▍ | 48299/57600 [8:29:47<1:40:42, 1.54it/s] 84%|████████▍ | 48300/57600 [8:29:48<1:38:44, 1.57it/s] {'loss': 1.0803, 'learning_rate': 2.458188153310104e-07, 'epoch': 533.11} + 84%|████████▍ | 48300/57600 [8:29:48<1:38:44, 1.57it/s] 84%|████████▍ | 48301/57600 [8:29:49<1:36:17, 1.61it/s] 84%|████████▍ | 48302/57600 [8:29:49<1:36:02, 1.61it/s] 84%|████████▍ | 48303/57600 [8:29:50<1:36:15, 1.61it/s] 84%|████████▍ | 48304/57600 [8:29:51<1:39:18, 1.56it/s] 84%|████████▍ | 48305/57600 [8:29:51<1:39:47, 1.55it/s] 84%|████████▍ | 48306/57600 [8:29:52<1:38:26, 1.57it/s] 84%|████████▍ | 48307/57600 [8:29:52<1:37:12, 1.59it/s] 84%|████████▍ | 48308/57600 [8:29:53<1:41:31, 1.53it/s] 84%|████████▍ | 48309/57600 [8:29:54<1:40:05, 1.55it/s] 84%|████████▍ | 48310/57600 [8:29:54<1:38:04, 1.58it/s] 84%|████████▍ | 48311/57600 [8:29:55<1:37:29, 1.59it/s] 84%|████████▍ | 48312/57600 [8:29:56<1:36:45, 1.60it/s] 84%|████████▍ | 48313/57600 [8:29:56<1:37:15, 1.59it/s] 84%|████████▍ | 48314/57600 [8:29:57<1:37:41, 1.58it/s] 84%|████���███▍ | 48315/57600 [8:29:58<1:36:38, 1.60it/s] 84%|████████▍ | 48316/57600 [8:29:58<1:36:27, 1.60it/s] 84%|████████▍ | 48317/57600 [8:29:59<1:40:55, 1.53it/s] 84%|████████▍ | 48318/57600 [8:30:00<1:40:13, 1.54it/s] 84%|████████▍ | 48319/57600 [8:30:00<1:40:18, 1.54it/s] 84%|████████▍ | 48320/57600 [8:30:01<1:38:55, 1.56it/s] {'loss': 1.1, 'learning_rate': 2.455052264808363e-07, 'epoch': 533.33} + 84%|████████▍ | 48320/57600 [8:30:01<1:38:55, 1.56it/s] 84%|████████▍ | 48321/57600 [8:30:01<1:38:26, 1.57it/s] 84%|████████▍ | 48322/57600 [8:30:02<1:38:21, 1.57it/s] 84%|████████▍ | 48323/57600 [8:30:03<1:34:52, 1.63it/s] 84%|████████▍ | 48324/57600 [8:30:03<1:34:09, 1.64it/s] 84%|████████▍ | 48325/57600 [8:30:04<1:38:43, 1.57it/s] 84%|████████▍ | 48326/57600 [8:30:05<1:38:13, 1.57it/s] 84%|████████▍ | 48327/57600 [8:30:05<1:36:00, 1.61it/s] 84%|████████▍ | 48328/57600 [8:30:06<1:35:30, 1.62it/s] 84%|████████▍ | 48329/57600 [8:30:06<1:34:55, 1.63it/s] 84%|████████▍ | 48330/57600 [8:30:07<1:34:57, 1.63it/s] 84%|████████▍ | 48331/57600 [8:30:08<1:34:02, 1.64it/s] 84%|████████▍ | 48332/57600 [8:30:08<1:33:08, 1.66it/s] 84%|████████▍ | 48333/57600 [8:30:09<1:33:53, 1.64it/s] 84%|████████▍ | 48334/57600 [8:30:09<1:36:15, 1.60it/s] 84%|████████▍ | 48335/57600 [8:30:10<1:33:52, 1.64it/s] 84%|████████▍ | 48336/57600 [8:30:11<1:33:35, 1.65it/s] 84%|████████▍ | 48337/57600 [8:30:11<1:39:32, 1.55it/s] 84%|████████▍ | 48338/57600 [8:30:12<1:39:45, 1.55it/s] 84%|████████▍ | 48339/57600 [8:30:13<1:39:09, 1.56it/s] 84%|████████▍ | 48340/57600 [8:30:13<1:36:38, 1.60it/s] {'loss': 1.1149, 'learning_rate': 2.4519163763066203e-07, 'epoch': 533.55} + 84%|████████▍ | 48340/57600 [8:30:13<1:36:38, 1.60it/s] 84%|████████▍ | 48341/57600 [8:30:14<1:37:39, 1.58it/s] 84%|████████▍ | 48342/57600 [8:30:14<1:36:04, 1.61it/s] 84%|████████▍ | 48343/57600 [8:30:15<1:38:10, 1.57it/s] 84%|████████▍ | 48344/57600 [8:30:16<1:36:09, 1.60it/s] 84%|████████▍ | 48345/57600 [8:30:16<1:35:36, 1.61it/s] 84%|████████▍ | 48346/57600 [8:30:17<1:40:41, 1.53it/s] 84%|████████▍ | 48347/57600 [8:30:18<1:42:50, 1.50it/s] 84%|████████▍ | 48348/57600 [8:30:18<1:40:14, 1.54it/s] 84%|████████▍ | 48349/57600 [8:30:19<1:39:40, 1.55it/s] 84%|████████▍ | 48350/57600 [8:30:20<1:37:43, 1.58it/s] 84%|████████▍ | 48351/57600 [8:30:20<1:36:23, 1.60it/s] 84%|████████▍ | 48352/57600 [8:30:21<1:35:56, 1.61it/s] 84%|████████▍ | 48353/57600 [8:30:21<1:35:40, 1.61it/s] 84%|████████▍ | 48354/57600 [8:30:22<1:37:53, 1.57it/s] 84%|████████▍ | 48355/57600 [8:30:23<1:38:21, 1.57it/s] 84%|████████▍ | 48356/57600 [8:30:23<1:37:05, 1.59it/s] 84%|████████▍ | 48357/57600 [8:30:24<1:38:58, 1.56it/s] 84%|████████▍ | 48358/57600 [8:30:25<1:35:18, 1.62it/s] 84%|████████▍ | 48359/57600 [8:30:25<1:33:07, 1.65it/s] 84%|████████▍ | 48360/57600 [8:30:26<1:33:05, 1.65it/s] {'loss': 1.1505, 'learning_rate': 2.4487804878048783e-07, 'epoch': 533.77} + 84%|████████▍ | 48360/57600 [8:30:26<1:33:05, 1.65it/s] 84%|████████▍ | 48361/57600 [8:30:26<1:33:59, 1.64it/s] 84%|████████▍ | 48362/57600 [8:30:27<1:33:13, 1.65it/s] 84%|████████▍ | 48363/57600 [8:30:28<1:32:31, 1.66it/s] 84%|████████▍ | 48364/57600 [8:30:28<1:37:13, 1.58it/s] 84%|████████▍ | 48365/57600 [8:30:29<1:34:27, 1.63it/s] 84%|████████▍ | 48366/57600 [8:30:29<1:33:25, 1.65it/s] 84%|████████▍ | 48367/57600 [8:30:30<1:35:00, 1.62it/s] 84%|████████▍ | 48368/57600 [8:30:31<1:35:45, 1.61it/s] 84%|████████▍ | 48369/57600 [8:30:31<1:38:40, 1.56it/s] 84%|████████▍ | 48370/57600 [8:30:32<1:37:49, 1.57it/s] 84%|████████▍ | 48371/57600 [8:30:33<1:38:43, 1.56it/s] 84%|████████▍ | 48372/57600 [8:30:33<1:36:56, 1.59it/s] 84%|████████▍ | 48373/57600 [8:30:34<1:38:24, 1.56it/s] 84%|██████��█▍ | 48374/57600 [8:30:35<1:36:47, 1.59it/s] 84%|████████▍ | 48375/57600 [8:30:35<1:35:11, 1.62it/s] 84%|████████▍ | 48376/57600 [8:30:36<1:38:00, 1.57it/s] 84%|████████▍ | 48377/57600 [8:30:37<1:38:55, 1.55it/s] 84%|████████▍ | 48378/57600 [8:30:37<1:40:04, 1.54it/s] 84%|████████▍ | 48379/57600 [8:30:38<1:39:16, 1.55it/s] 84%|████████▍ | 48380/57600 [8:30:38<1:36:22, 1.59it/s] {'loss': 1.1273, 'learning_rate': 2.4456445993031353e-07, 'epoch': 534.0} + 84%|████████▍ | 48380/57600 [8:30:38<1:36:22, 1.59it/s] 84%|████████▍ | 48381/57600 [8:30:39<1:39:18, 1.55it/s] 84%|████████▍ | 48382/57600 [8:30:40<1:37:14, 1.58it/s] 84%|████████▍ | 48383/57600 [8:30:40<1:35:15, 1.61it/s] 84%|████████▍ | 48384/57600 [8:30:41<1:35:38, 1.61it/s] 84%|████████▍ | 48385/57600 [8:30:41<1:32:43, 1.66it/s] 84%|████████▍ | 48386/57600 [8:30:42<1:31:09, 1.68it/s] 84%|████████▍ | 48387/57600 [8:30:43<1:36:17, 1.59it/s] 84%|████████▍ | 48388/57600 [8:30:43<1:37:05, 1.58it/s] 84%|████████▍ | 48389/57600 [8:30:44<1:38:43, 1.56it/s] 84%|████████▍ | 48390/57600 [8:30:45<1:35:47, 1.60it/s] 84%|████████▍ | 48391/57600 [8:30:45<1:33:33, 1.64it/s] 84%|████████▍ | 48392/57600 [8:30:46<1:34:17, 1.63it/s] 84%|████████▍ | 48393/57600 [8:30:46<1:33:28, 1.64it/s] 84%|████████▍ | 48394/57600 [8:30:47<1:31:42, 1.67it/s] 84%|████████▍ | 48395/57600 [8:30:48<1:32:02, 1.67it/s] 84%|████████▍ | 48396/57600 [8:30:48<1:32:02, 1.67it/s] 84%|████████▍ | 48397/57600 [8:30:49<1:37:59, 1.57it/s] 84%|████████▍ | 48398/57600 [8:30:50<1:38:31, 1.56it/s] 84%|████████▍ | 48399/57600 [8:30:50<1:38:20, 1.56it/s] 84%|████████▍ | 48400/57600 [8:30:51<1:39:16, 1.54it/s] {'loss': 1.1458, 'learning_rate': 2.442508710801394e-07, 'epoch': 534.22} + 84%|████████▍ | 48400/57600 [8:30:51<1:39:16, 1.54it/s] 84%|████████▍ | 48401/57600 [8:30:51<1:37:03, 1.58it/s] 84%|████████▍ | 48402/57600 [8:30:52<1:38:35, 1.55it/s] 84%|████████▍ | 48403/57600 [8:30:53<1:37:39, 1.57it/s] 84%|████████▍ | 48404/57600 [8:30:53<1:36:57, 1.58it/s] 84%|████████▍ | 48405/57600 [8:30:54<1:36:13, 1.59it/s] 84%|████████▍ | 48406/57600 [8:30:55<1:36:11, 1.59it/s] 84%|████████▍ | 48407/57600 [8:30:55<1:35:33, 1.60it/s] 84%|████████▍ | 48408/57600 [8:30:56<1:36:10, 1.59it/s] 84%|████████▍ | 48409/57600 [8:30:56<1:34:10, 1.63it/s] 84%|████████▍ | 48410/57600 [8:30:57<1:36:28, 1.59it/s] 84%|████████▍ | 48411/57600 [8:30:58<1:36:39, 1.58it/s] 84%|████████▍ | 48412/57600 [8:30:58<1:34:54, 1.61it/s] 84%|████████▍ | 48413/57600 [8:30:59<1:36:55, 1.58it/s] 84%|████████▍ | 48414/57600 [8:31:00<1:38:26, 1.56it/s] 84%|████████▍ | 48415/57600 [8:31:00<1:38:12, 1.56it/s] 84%|████████▍ | 48416/57600 [8:31:01<1:38:01, 1.56it/s] 84%|████████▍ | 48417/57600 [8:31:02<1:37:29, 1.57it/s] 84%|████████▍ | 48418/57600 [8:31:02<1:36:29, 1.59it/s] 84%|████████▍ | 48419/57600 [8:31:03<1:35:52, 1.60it/s] 84%|████████▍ | 48420/57600 [8:31:03<1:34:59, 1.61it/s] {'loss': 1.0934, 'learning_rate': 2.439372822299651e-07, 'epoch': 534.44} + 84%|████████▍ | 48420/57600 [8:31:03<1:34:59, 1.61it/s] 84%|████████▍ | 48421/57600 [8:31:04<1:36:05, 1.59it/s] 84%|████████▍ | 48422/57600 [8:31:05<1:37:27, 1.57it/s] 84%|████████▍ | 48423/57600 [8:31:05<1:40:15, 1.53it/s] 84%|████████▍ | 48424/57600 [8:31:06<1:40:05, 1.53it/s] 84%|████████▍ | 48425/57600 [8:31:07<1:38:30, 1.55it/s] 84%|████████▍ | 48426/57600 [8:31:07<1:40:57, 1.51it/s] 84%|████████▍ | 48427/57600 [8:31:08<1:42:25, 1.49it/s] 84%|████████▍ | 48428/57600 [8:31:09<1:38:29, 1.55it/s] 84%|████████▍ | 48429/57600 [8:31:09<1:34:51, 1.61it/s] 84%|████████▍ | 48430/57600 [8:31:10<1:34:25, 1.62it/s] 84%|████████▍ | 48431/57600 [8:31:10<1:32:35, 1.65it/s] 84%|████████▍ | 48432/57600 [8:31:11<1:33:34, 1.63it/s] 84%|████████�� | 48433/57600 [8:31:12<1:33:37, 1.63it/s] 84%|████████▍ | 48434/57600 [8:31:12<1:33:50, 1.63it/s] 84%|████████▍ | 48435/57600 [8:31:13<1:33:35, 1.63it/s] 84%|████████▍ | 48436/57600 [8:31:14<1:35:23, 1.60it/s] 84%|████████▍ | 48437/57600 [8:31:14<1:36:08, 1.59it/s] 84%|████████▍ | 48438/57600 [8:31:15<1:34:59, 1.61it/s] 84%|████████▍ | 48439/57600 [8:31:15<1:34:35, 1.61it/s] 84%|████████▍ | 48440/57600 [8:31:16<1:35:25, 1.60it/s] {'loss': 1.0883, 'learning_rate': 2.436236933797909e-07, 'epoch': 534.66} + 84%|████████▍ | 48440/57600 [8:31:16<1:35:25, 1.60it/s] 84%|████████▍ | 48441/57600 [8:31:17<1:39:01, 1.54it/s] 84%|████████▍ | 48442/57600 [8:31:17<1:37:54, 1.56it/s] 84%|████████▍ | 48443/57600 [8:31:18<1:37:50, 1.56it/s] 84%|████████▍ | 48444/57600 [8:31:19<1:37:10, 1.57it/s] 84%|████████▍ | 48445/57600 [8:31:19<1:37:42, 1.56it/s] 84%|████████▍ | 48446/57600 [8:31:20<1:38:53, 1.54it/s] 84%|████████▍ | 48447/57600 [8:31:21<1:38:06, 1.55it/s] 84%|████████▍ | 48448/57600 [8:31:21<1:35:38, 1.59it/s] 84%|████████▍ | 48449/57600 [8:31:22<1:36:30, 1.58it/s] 84%|████████▍ | 48450/57600 [8:31:22<1:34:38, 1.61it/s] 84%|████████▍ | 48451/57600 [8:31:23<1:37:09, 1.57it/s] 84%|████████▍ | 48452/57600 [8:31:24<1:36:16, 1.58it/s] 84%|████████▍ | 48453/57600 [8:31:24<1:36:41, 1.58it/s] 84%|████████▍ | 48454/57600 [8:31:25<1:36:47, 1.57it/s] 84%|████████▍ | 48455/57600 [8:31:26<1:34:43, 1.61it/s] 84%|████████▍ | 48456/57600 [8:31:26<1:35:21, 1.60it/s] 84%|████████▍ | 48457/57600 [8:31:27<1:32:38, 1.64it/s] 84%|████████▍ | 48458/57600 [8:31:27<1:35:09, 1.60it/s] 84%|████████▍ | 48459/57600 [8:31:28<1:34:41, 1.61it/s] 84%|████████▍ | 48460/57600 [8:31:29<1:35:21, 1.60it/s] {'loss': 1.1175, 'learning_rate': 2.4331010452961675e-07, 'epoch': 534.88} + 84%|████████▍ | 48460/57600 [8:31:29<1:35:21, 1.60it/s] 84%|████████▍ | 48461/57600 [8:31:29<1:35:19, 1.60it/s] 84%|████████▍ | 48462/57600 [8:31:30<1:41:57, 1.49it/s] 84%|████████▍ | 48463/57600 [8:31:31<1:40:03, 1.52it/s] 84%|████████▍ | 48464/57600 [8:31:31<1:37:28, 1.56it/s] 84%|████████▍ | 48465/57600 [8:31:32<1:34:57, 1.60it/s] 84%|████████▍ | 48466/57600 [8:31:32<1:31:07, 1.67it/s] 84%|████████▍ | 48467/57600 [8:31:33<1:29:34, 1.70it/s] 84%|████████▍ | 48468/57600 [8:31:34<1:29:41, 1.70it/s] 84%|████████▍ | 48469/57600 [8:31:34<1:33:16, 1.63it/s] 84%|████████▍ | 48470/57600 [8:31:35<1:33:00, 1.64it/s] 84%|████████▍ | 48471/57600 [8:31:36<1:33:14, 1.63it/s] 84%|████████▍ | 48472/57600 [8:31:36<1:37:45, 1.56it/s] 84%|████████▍ | 48473/57600 [8:31:37<1:36:06, 1.58it/s] 84%|████████▍ | 48474/57600 [8:31:37<1:33:53, 1.62it/s] 84%|████████▍ | 48475/57600 [8:31:38<1:36:29, 1.58it/s] 84%|████████▍ | 48476/57600 [8:31:39<1:35:38, 1.59it/s] 84%|████████▍ | 48477/57600 [8:31:39<1:35:07, 1.60it/s] 84%|████████▍ | 48478/57600 [8:31:40<1:34:58, 1.60it/s] 84%|████████▍ | 48479/57600 [8:31:41<1:35:21, 1.59it/s] 84%|████████▍ | 48480/57600 [8:31:41<1:37:43, 1.56it/s] {'loss': 1.1428, 'learning_rate': 2.429965156794425e-07, 'epoch': 535.1} + 84%|████████▍ | 48480/57600 [8:31:41<1:37:43, 1.56it/s] 84%|████████▍ | 48481/57600 [8:31:42<1:39:42, 1.52it/s] 84%|████████▍ | 48482/57600 [8:31:43<1:36:46, 1.57it/s] 84%|████████▍ | 48483/57600 [8:31:43<1:34:56, 1.60it/s] 84%|████████▍ | 48484/57600 [8:31:44<1:34:23, 1.61it/s] 84%|████████▍ | 48485/57600 [8:31:44<1:32:35, 1.64it/s] 84%|████████▍ | 48486/57600 [8:31:45<1:33:46, 1.62it/s] 84%|████████▍ | 48487/57600 [8:31:46<1:36:39, 1.57it/s] 84%|████████▍ | 48488/57600 [8:31:46<1:35:23, 1.59it/s] 84%|████████▍ | 48489/57600 [8:31:47<1:33:09, 1.63it/s] 84%|████████▍ | 48490/57600 [8:31:47<1:32:03, 1.65it/s] 84%|████████▍ | 48491/57600 [8:31:48<1:31:54, 1.65it/s] 84%|████████▍ | 48492/57600 [8:31:49<1:30:24, 1.68it/s] 84%|████████▍ | 48493/57600 [8:31:49<1:30:40, 1.67it/s] 84%|████████▍ | 48494/57600 [8:31:50<1:33:25, 1.62it/s] 84%|████████▍ | 48495/57600 [8:31:50<1:33:01, 1.63it/s] 84%|████████▍ | 48496/57600 [8:31:51<1:33:03, 1.63it/s] 84%|████████▍ | 48497/57600 [8:31:52<1:36:00, 1.58it/s] 84%|████████▍ | 48498/57600 [8:31:52<1:33:22, 1.62it/s] 84%|████████▍ | 48499/57600 [8:31:53<1:37:56, 1.55it/s] 84%|████████▍ | 48500/57600 [8:31:54<1:38:47, 1.54it/s] {'loss': 1.1469, 'learning_rate': 2.426829268292683e-07, 'epoch': 535.32} + 84%|████████▍ | 48500/57600 [8:31:54<1:38:47, 1.54it/s] 84%|████████▍ | 48501/57600 [8:31:54<1:41:44, 1.49it/s] 84%|████████▍ | 48502/57600 [8:31:55<1:38:22, 1.54it/s] 84%|████████▍ | 48503/57600 [8:31:56<1:38:37, 1.54it/s] 84%|████████▍ | 48504/57600 [8:31:56<1:36:33, 1.57it/s] 84%|████████▍ | 48505/57600 [8:31:57<1:37:29, 1.55it/s] 84%|████████▍ | 48506/57600 [8:31:58<1:40:00, 1.52it/s] 84%|████████▍ | 48507/57600 [8:31:58<1:36:53, 1.56it/s] 84%|████████▍ | 48508/57600 [8:31:59<1:34:35, 1.60it/s] 84%|████████▍ | 48509/57600 [8:31:59<1:36:15, 1.57it/s] 84%|████████▍ | 48510/57600 [8:32:00<1:35:10, 1.59it/s] 84%|████████▍ | 48511/57600 [8:32:01<1:36:01, 1.58it/s] 84%|████████▍ | 48512/57600 [8:32:01<1:35:43, 1.58it/s] 84%|████████▍ | 48513/57600 [8:32:02<1:34:26, 1.60it/s] 84%|████████▍ | 48514/57600 [8:32:03<1:34:17, 1.61it/s] 84%|████████▍ | 48515/57600 [8:32:03<1:33:40, 1.62it/s] 84%|████████▍ | 48516/57600 [8:32:04<1:36:05, 1.58it/s] 84%|████████▍ | 48517/57600 [8:32:04<1:35:14, 1.59it/s] 84%|████████▍ | 48518/57600 [8:32:05<1:33:13, 1.62it/s] 84%|████████▍ | 48519/57600 [8:32:06<1:32:31, 1.64it/s] 84%|████████▍ | 48520/57600 [8:32:06<1:35:38, 1.58it/s] {'loss': 1.0978, 'learning_rate': 2.42369337979094e-07, 'epoch': 535.54} + 84%|████████▍ | 48520/57600 [8:32:06<1:35:38, 1.58it/s] 84%|████████▍ | 48521/57600 [8:32:07<1:38:03, 1.54it/s] 84%|████████▍ | 48522/57600 [8:32:08<1:37:11, 1.56it/s] 84%|████████▍ | 48523/57600 [8:32:08<1:35:47, 1.58it/s] 84%|████████▍ | 48524/57600 [8:32:09<1:34:53, 1.59it/s] 84%|████████▍ | 48525/57600 [8:32:09<1:33:13, 1.62it/s] 84%|████████▍ | 48526/57600 [8:32:10<1:29:50, 1.68it/s] 84%|████████▍ | 48527/57600 [8:32:11<1:29:52, 1.68it/s] 84%|████████▍ | 48528/57600 [8:32:11<1:34:28, 1.60it/s] 84%|████████▍ | 48529/57600 [8:32:12<1:39:30, 1.52it/s] 84%|████████▍ | 48530/57600 [8:32:13<1:35:17, 1.59it/s] 84%|████████▍ | 48531/57600 [8:32:13<1:35:39, 1.58it/s] 84%|████████▍ | 48532/57600 [8:32:14<1:37:20, 1.55it/s] 84%|████████▍ | 48533/57600 [8:32:15<1:35:16, 1.59it/s] 84%|████████▍ | 48534/57600 [8:32:15<1:34:30, 1.60it/s] 84%|████████▍ | 48535/57600 [8:32:16<1:34:25, 1.60it/s] 84%|████████▍ | 48536/57600 [8:32:16<1:34:57, 1.59it/s] 84%|████████▍ | 48537/57600 [8:32:17<1:31:49, 1.65it/s] 84%|████████▍ | 48538/57600 [8:32:18<1:30:51, 1.66it/s] 84%|████████▍ | 48539/57600 [8:32:18<1:32:06, 1.64it/s] 84%|████████▍ | 48540/57600 [8:32:19<1:29:54, 1.68it/s] {'loss': 1.1107, 'learning_rate': 2.4205574912891987e-07, 'epoch': 535.76} + 84%|████████▍ | 48540/57600 [8:32:19<1:29:54, 1.68it/s] 84%|████████▍ | 48541/57600 [8:32:19<1:32:13, 1.64it/s] 84%|████████▍ | 48542/57600 [8:32:20<1:36:18, 1.57it/s] 84%|████████▍ | 48543/57600 [8:32:21<1:36:17, 1.57it/s] 84%|████████▍ | 48544/57600 [8:32:21<1:35:38, 1.58it/s] 84%|████████▍ | 48545/57600 [8:32:22<1:33:53, 1.61it/s] 84%|████████▍ | 48546/57600 [8:32:23<1:30:58, 1.66it/s] 84%|████████▍ | 48547/57600 [8:32:23<1:30:14, 1.67it/s] 84%|████████▍ | 48548/57600 [8:32:24<1:32:47, 1.63it/s] 84%|████████▍ | 48549/57600 [8:32:24<1:32:35, 1.63it/s] 84%|████████▍ | 48550/57600 [8:32:25<1:33:56, 1.61it/s] 84%|████████▍ | 48551/57600 [8:32:26<1:31:37, 1.65it/s] 84%|████████▍ | 48552/57600 [8:32:26<1:35:10, 1.58it/s] 84%|████████▍ | 48553/57600 [8:32:27<1:34:43, 1.59it/s] 84%|████████▍ | 48554/57600 [8:32:28<1:34:25, 1.60it/s] 84%|████████▍ | 48555/57600 [8:32:28<1:35:38, 1.58it/s] 84%|████████▍ | 48556/57600 [8:32:29<1:37:18, 1.55it/s] 84%|████████▍ | 48557/57600 [8:32:30<1:38:19, 1.53it/s] 84%|████████▍ | 48558/57600 [8:32:30<1:39:16, 1.52it/s] 84%|████████▍ | 48559/57600 [8:32:31<1:38:07, 1.54it/s] 84%|████████▍ | 48560/57600 [8:32:31<1:37:52, 1.54it/s] {'loss': 1.1489, 'learning_rate': 2.417421602787456e-07, 'epoch': 535.98} + 84%|████████▍ | 48560/57600 [8:32:31<1:37:52, 1.54it/s] 84%|████████▍ | 48561/57600 [8:32:32<1:38:02, 1.54it/s] 84%|████████▍ | 48562/57600 [8:32:33<1:42:14, 1.47it/s] 84%|████████▍ | 48563/57600 [8:32:33<1:37:22, 1.55it/s] 84%|████████▍ | 48564/57600 [8:32:34<1:34:20, 1.60it/s] 84%|████████▍ | 48565/57600 [8:32:35<1:31:49, 1.64it/s] 84%|████████▍ | 48566/57600 [8:32:35<1:31:49, 1.64it/s] 84%|████████▍ | 48567/57600 [8:32:36<1:34:18, 1.60it/s] 84%|████████▍ | 48568/57600 [8:32:37<1:35:52, 1.57it/s] 84%|████████▍ | 48569/57600 [8:32:37<1:39:06, 1.52it/s] 84%|████████▍ | 48570/57600 [8:32:38<1:38:42, 1.52it/s] 84%|████████▍ | 48571/57600 [8:32:38<1:34:09, 1.60it/s] 84%|████████▍ | 48572/57600 [8:32:39<1:34:00, 1.60it/s] 84%|████████▍ | 48573/57600 [8:32:40<1:34:25, 1.59it/s] 84%|████████▍ | 48574/57600 [8:32:40<1:33:00, 1.62it/s] 84%|████████▍ | 48575/57600 [8:32:41<1:33:56, 1.60it/s] 84%|████████▍ | 48576/57600 [8:32:42<1:34:47, 1.59it/s] 84%|████████▍ | 48577/57600 [8:32:42<1:34:33, 1.59it/s] 84%|████████▍ | 48578/57600 [8:32:43<1:31:21, 1.65it/s] 84%|████████▍ | 48579/57600 [8:32:43<1:31:14, 1.65it/s] 84%|████████▍ | 48580/57600 [8:32:44<1:34:52, 1.58it/s] {'loss': 1.1286, 'learning_rate': 2.414285714285714e-07, 'epoch': 536.2} + 84%|████████▍ | 48580/57600 [8:32:44<1:34:52, 1.58it/s] 84%|████████▍ | 48581/57600 [8:32:45<1:33:21, 1.61it/s] 84%|████████▍ | 48582/57600 [8:32:45<1:32:15, 1.63it/s] 84%|████████▍ | 48583/57600 [8:32:46<1:33:38, 1.61it/s] 84%|████████▍ | 48584/57600 [8:32:47<1:36:05, 1.56it/s] 84%|████████▍ | 48585/57600 [8:32:47<1:37:29, 1.54it/s] 84%|████████▍ | 48586/57600 [8:32:48<1:34:36, 1.59it/s] 84%|████████▍ | 48587/57600 [8:32:48<1:36:27, 1.56it/s] 84%|████████▍ | 48588/57600 [8:32:49<1:34:37, 1.59it/s] 84%|████████▍ | 48589/57600 [8:32:50<1:33:22, 1.61it/s] 84%|████████▍ | 48590/57600 [8:32:50<1:30:14, 1.66it/s] 84%|████████▍ | 48591/57600 [8:32:51<1:30:00, 1.67it/s] 84%|████████▍ | 48592/57600 [8:32:51<1:30:59, 1.65it/s] 84%|████████▍ | 48593/57600 [8:32:52<1:32:39, 1.62it/s] 84%|████████▍ | 48594/57600 [8:32:53<1:31:56, 1.63it/s] 84%|████████▍ | 48595/57600 [8:32:53<1:32:00, 1.63it/s] 84%|████████▍ | 48596/57600 [8:32:54<1:29:59, 1.67it/s] 84%|████████▍ | 48597/57600 [8:32:55<1:31:45, 1.64it/s] 84%|████████▍ | 48598/57600 [8:32:55<1:34:14, 1.59it/s] 84%|████████▍ | 48599/57600 [8:32:56<1:33:25, 1.61it/s] 84%|████████▍ | 48600/57600 [8:32:56<1:33:52, 1.60it/s] {'loss': 1.132, 'learning_rate': 2.4111498257839723e-07, 'epoch': 536.42} + 84%|████████▍ | 48600/57600 [8:32:56<1:33:52, 1.60it/s] 84%|████████▍ | 48601/57600 [8:32:57<1:36:36, 1.55it/s] 84%|████████▍ | 48602/57600 [8:32:58<1:36:12, 1.56it/s] 84%|████████▍ | 48603/57600 [8:32:58<1:35:56, 1.56it/s] 84%|████████▍ | 48604/57600 [8:32:59<1:39:37, 1.51it/s] 84%|████████▍ | 48605/57600 [8:33:00<1:38:17, 1.53it/s] 84%|████████▍ | 48606/57600 [8:33:00<1:39:46, 1.50it/s] 84%|████████▍ | 48607/57600 [8:33:01<1:42:12, 1.47it/s] 84%|████████▍ | 48608/57600 [8:33:02<1:43:51, 1.44it/s] 84%|████████▍ | 48609/57600 [8:33:03<1:43:45, 1.44it/s] 84%|████████▍ | 48610/57600 [8:33:03<1:43:00, 1.45it/s] 84%|████████▍ | 48611/57600 [8:33:04<1:40:25, 1.49it/s] 84%|████████▍ | 48612/57600 [8:33:04<1:36:51, 1.55it/s] 84%|████████▍ | 48613/57600 [8:33:05<1:34:49, 1.58it/s] 84%|████████▍ | 48614/57600 [8:33:06<1:35:24, 1.57it/s] 84%|████████▍ | 48615/57600 [8:33:06<1:34:01, 1.59it/s] 84%|████████▍ | 48616/57600 [8:33:07<1:36:45, 1.55it/s] 84%|████████▍ | 48617/57600 [8:33:08<1:34:33, 1.58it/s] 84%|████████▍ | 48618/57600 [8:33:08<1:33:11, 1.61it/s] 84%|████████▍ | 48619/57600 [8:33:09<1:34:55, 1.58it/s] 84%|████████▍ | 48620/57600 [8:33:10<1:37:05, 1.54it/s] {'loss': 1.076, 'learning_rate': 2.40801393728223e-07, 'epoch': 536.64} + 84%|████████▍ | 48620/57600 [8:33:10<1:37:05, 1.54it/s] 84%|████████▍ | 48621/57600 [8:33:10<1:35:24, 1.57it/s] 84%|████████▍ | 48622/57600 [8:33:11<1:32:13, 1.62it/s] 84%|████████▍ | 48623/57600 [8:33:11<1:32:28, 1.62it/s] 84%|████████▍ | 48624/57600 [8:33:12<1:29:58, 1.66it/s] 84%|████████▍ | 48625/57600 [8:33:13<1:30:16, 1.66it/s] 84%|████████▍ | 48626/57600 [8:33:13<1:30:28, 1.65it/s] 84%|████████▍ | 48627/57600 [8:33:14<1:32:36, 1.61it/s] 84%|████████▍ | 48628/57600 [8:33:14<1:31:21, 1.64it/s] 84%|████████▍ | 48629/57600 [8:33:15<1:30:04, 1.66it/s] 84%|████████▍ | 48630/57600 [8:33:16<1:31:53, 1.63it/s] 84%|████████▍ | 48631/57600 [8:33:16<1:33:10, 1.60it/s] 84%|████████▍ | 48632/57600 [8:33:17<1:31:52, 1.63it/s] 84%|████████▍ | 48633/57600 [8:33:17<1:30:39, 1.65it/s] 84%|████████▍ | 48634/57600 [8:33:18<1:30:53, 1.64it/s] 84%|████████▍ | 48635/57600 [8:33:19<1:31:19, 1.64it/s] 84%|████████▍ | 48636/57600 [8:33:19<1:32:40, 1.61it/s] 84%|████████▍ | 48637/57600 [8:33:20<1:31:20, 1.64it/s] 84%|████████▍ | 48638/57600 [8:33:21<1:34:30, 1.58it/s] 84%|████████▍ | 48639/57600 [8:33:21<1:32:47, 1.61it/s] 84%|████████▍ | 48640/57600 [8:33:22<1:33:11, 1.60it/s] {'loss': 1.1494, 'learning_rate': 2.404878048780488e-07, 'epoch': 536.87} + 84%|████████▍ | 48640/57600 [8:33:22<1:33:11, 1.60it/s] 84%|████████▍ | 48641/57600 [8:33:22<1:34:04, 1.59it/s] 84%|████████▍ | 48642/57600 [8:33:23<1:32:29, 1.61it/s] 84%|████████▍ | 48643/57600 [8:33:24<1:33:03, 1.60it/s] 84%|████████▍ | 48644/57600 [8:33:24<1:31:01, 1.64it/s] 84%|████████▍ | 48645/57600 [8:33:25<1:30:59, 1.64it/s] 84%|████████▍ | 48646/57600 [8:33:25<1:30:47, 1.64it/s] 84%|████████▍ | 48647/57600 [8:33:26<1:34:58, 1.57it/s] 84%|████████▍ | 48648/57600 [8:33:27<1:35:17, 1.57it/s] 84%|████████▍ | 48649/57600 [8:33:27<1:35:20, 1.56it/s] 84%|████████▍ | 48650/57600 [8:33:28<1:34:15, 1.58it/s] 84%|████████▍ | 48651/57600 [8:33:29<1:58:12, 1.26it/s] 84%|████████▍ | 48652/57600 [8:33:30<1:47:16, 1.39it/s] 84%|████████▍ | 48653/57600 [8:33:31<1:47:54, 1.38it/s] 84%|████████▍ | 48654/57600 [8:33:31<1:43:46, 1.44it/s] 84%|████████▍ | 48655/57600 [8:33:32<1:38:09, 1.52it/s] 84%|████████▍ | 48656/57600 [8:33:32<1:37:29, 1.53it/s] 84%|████████▍ | 48657/57600 [8:33:33<1:39:24, 1.50it/s] 84%|████████▍ | 48658/57600 [8:33:34<1:38:00, 1.52it/s] 84%|████████▍ | 48659/57600 [8:33:34<1:38:00, 1.52it/s] 84%|████████▍ | 48660/57600 [8:33:35<1:34:58, 1.57it/s] {'loss': 1.1247, 'learning_rate': 2.401742160278745e-07, 'epoch': 537.09} + 84%|████████▍ | 48660/57600 [8:33:35<1:34:58, 1.57it/s] 84%|████████▍ | 48661/57600 [8:33:36<1:36:01, 1.55it/s] 84%|████████▍ | 48662/57600 [8:33:36<1:36:22, 1.55it/s] 84%|████████▍ | 48663/57600 [8:33:37<1:34:23, 1.58it/s] 84%|████████▍ | 48664/57600 [8:33:37<1:34:42, 1.57it/s] 84%|████████▍ | 48665/57600 [8:33:38<1:34:13, 1.58it/s] 84%|████████▍ | 48666/57600 [8:33:39<1:32:32, 1.61it/s] 84%|████████▍ | 48667/57600 [8:33:39<1:31:13, 1.63it/s] 84%|████████▍ | 48668/57600 [8:33:40<1:31:41, 1.62it/s] 84%|████████▍ | 48669/57600 [8:33:41<1:29:44, 1.66it/s] 84%|████████▍ | 48670/57600 [8:33:41<1:30:34, 1.64it/s] 84%|████████▍ | 48671/57600 [8:33:42<1:30:37, 1.64it/s] 84%|████████▍ | 48672/57600 [8:33:42<1:34:58, 1.57it/s] 85%|████████▍ | 48673/57600 [8:33:43<1:37:20, 1.53it/s] 85%|████████▍ | 48674/57600 [8:33:44<1:35:37, 1.56it/s] 85%|████████▍ | 48675/57600 [8:33:44<1:35:06, 1.56it/s] 85%|████████▍ | 48676/57600 [8:33:45<1:37:06, 1.53it/s] 85%|████████▍ | 48677/57600 [8:33:46<1:34:53, 1.57it/s] 85%|████████▍ | 48678/57600 [8:33:46<1:36:53, 1.53it/s] 85%|████████▍ | 48679/57600 [8:33:47<1:35:14, 1.56it/s] 85%|████████▍ | 48680/57600 [8:33:48<1:33:24, 1.59it/s] {'loss': 1.1095, 'learning_rate': 2.3986062717770034e-07, 'epoch': 537.31} + 85%|████████▍ | 48680/57600 [8:33:48<1:33:24, 1.59it/s] 85%|████████▍ | 48681/57600 [8:33:48<1:34:24, 1.57it/s] 85%|████████▍ | 48682/57600 [8:33:49<1:36:17, 1.54it/s] 85%|████████▍ | 48683/57600 [8:33:50<1:36:57, 1.53it/s] 85%|████████▍ | 48684/57600 [8:33:50<1:35:31, 1.56it/s] 85%|████████▍ | 48685/57600 [8:33:51<1:34:51, 1.57it/s] 85%|████████▍ | 48686/57600 [8:33:52<1:37:24, 1.53it/s] 85%|████████▍ | 48687/57600 [8:33:52<1:34:44, 1.57it/s] 85%|████████▍ | 48688/57600 [8:33:53<1:33:08, 1.59it/s] 85%|████████▍ | 48689/57600 [8:33:53<1:33:07, 1.59it/s] 85%|████████▍ | 48690/57600 [8:33:54<1:34:07, 1.58it/s] 85%|████████▍ | 48691/57600 [8:33:55<1:34:49, 1.57it/s] 85%|████████▍ | 48692/57600 [8:33:55<1:32:24, 1.61it/s] 85%|████████▍ | 48693/57600 [8:33:56<1:30:53, 1.63it/s] 85%|████████▍ | 48694/57600 [8:33:56<1:28:44, 1.67it/s] 85%|████████▍ | 48695/57600 [8:33:57<1:34:16, 1.57it/s] 85%|████████▍ | 48696/57600 [8:33:58<1:31:29, 1.62it/s] 85%|████████▍ | 48697/57600 [8:33:58<1:32:24, 1.61it/s] 85%|████████▍ | 48698/57600 [8:33:59<1:30:31, 1.64it/s] 85%|████████▍ | 48699/57600 [8:33:59<1:31:06, 1.63it/s] 85%|████████▍ | 48700/57600 [8:34:00<1:31:39, 1.62it/s] {'loss': 1.1362, 'learning_rate': 2.395470383275261e-07, 'epoch': 537.53} + 85%|████████▍ | 48700/57600 [8:34:00<1:31:39, 1.62it/s] 85%|████████▍ | 48701/57600 [8:34:01<1:33:04, 1.59it/s] 85%|████████▍ | 48702/57600 [8:34:01<1:31:48, 1.62it/s] 85%|████████▍ | 48703/57600 [8:34:02<1:31:36, 1.62it/s] 85%|████████▍ | 48704/57600 [8:34:03<1:32:14, 1.61it/s] 85%|████████▍ | 48705/57600 [8:34:03<1:30:27, 1.64it/s] 85%|████████▍ | 48706/57600 [8:34:04<1:33:12, 1.59it/s] 85%|████████▍ | 48707/57600 [8:34:05<1:38:45, 1.50it/s] 85%|████████▍ | 48708/57600 [8:34:05<1:36:04, 1.54it/s] 85%|████████▍ | 48709/57600 [8:34:06<1:34:30, 1.57it/s] 85%|████████▍ | 48710/57600 [8:34:06<1:33:46, 1.58it/s] 85%|████████▍ | 48711/57600 [8:34:07<1:33:11, 1.59it/s] 85%|████████▍ | 48712/57600 [8:34:08<1:33:09, 1.59it/s] 85%|████████▍ | 48713/57600 [8:34:08<1:29:25, 1.66it/s] 85%|████████▍ | 48714/57600 [8:34:09<1:28:21, 1.68it/s] 85%|████████▍ | 48715/57600 [8:34:09<1:29:32, 1.65it/s] 85%|████████▍ | 48716/57600 [8:34:10<1:29:23, 1.66it/s] 85%|████████▍ | 48717/57600 [8:34:11<1:34:01, 1.57it/s] 85%|████████▍ | 48718/57600 [8:34:11<1:36:44, 1.53it/s] 85%|████████▍ | 48719/57600 [8:34:12<1:36:46, 1.53it/s] 85%|████████▍ | 48720/57600 [8:34:13<1:36:09, 1.54it/s] {'loss': 1.1193, 'learning_rate': 2.392334494773519e-07, 'epoch': 537.75} + 85%|████████▍ | 48720/57600 [8:34:13<1:36:09, 1.54it/s] 85%|████████▍ | 48721/57600 [8:34:13<1:34:20, 1.57it/s] 85%|████████▍ | 48722/57600 [8:34:14<1:32:36, 1.60it/s] 85%|████████▍ | 48723/57600 [8:34:15<1:34:54, 1.56it/s] 85%|████████▍ | 48724/57600 [8:34:15<1:31:26, 1.62it/s] 85%|████████▍ | 48725/57600 [8:34:16<1:31:02, 1.62it/s] 85%|████████▍ | 48726/57600 [8:34:16<1:30:26, 1.64it/s] 85%|████████▍ | 48727/57600 [8:34:17<1:31:43, 1.61it/s] 85%|████████▍ | 48728/57600 [8:34:18<1:29:41, 1.65it/s] 85%|████████▍ | 48729/57600 [8:34:18<1:33:18, 1.58it/s] 85%|████████▍ | 48730/57600 [8:34:19<1:31:58, 1.61it/s] 85%|████████▍ | 48731/57600 [8:34:20<1:33:49, 1.58it/s] 85%|████████▍ | 48732/57600 [8:34:20<1:32:48, 1.59it/s] 85%|████████▍ | 48733/57600 [8:34:21<1:31:00, 1.62it/s] 85%|████████▍ | 48734/57600 [8:34:21<1:30:15, 1.64it/s] 85%|████████▍ | 48735/57600 [8:34:22<1:31:21, 1.62it/s] 85%|████████▍ | 48736/57600 [8:34:23<1:31:40, 1.61it/s] 85%|████████▍ | 48737/57600 [8:34:23<1:30:47, 1.63it/s] 85%|████████▍ | 48738/57600 [8:34:24<1:28:49, 1.66it/s] 85%|████████▍ | 48739/57600 [8:34:24<1:29:07, 1.66it/s] 85%|████████▍ | 48740/57600 [8:34:25<1:29:19, 1.65it/s] {'loss': 1.1645, 'learning_rate': 2.389198606271777e-07, 'epoch': 537.97} + 85%|████████▍ | 48740/57600 [8:34:25<1:29:19, 1.65it/s] 85%|████████▍ | 48741/57600 [8:34:26<1:32:01, 1.60it/s] 85%|████████▍ | 48742/57600 [8:34:26<1:30:20, 1.63it/s] 85%|████████▍ | 48743/57600 [8:34:27<1:34:08, 1.57it/s] 85%|████████▍ | 48744/57600 [8:34:28<1:31:59, 1.60it/s] 85%|████████▍ | 48745/57600 [8:34:28<1:30:25, 1.63it/s] 85%|████████▍ | 48746/57600 [8:34:29<1:31:03, 1.62it/s] 85%|████████▍ | 48747/57600 [8:34:29<1:28:58, 1.66it/s] 85%|████████▍ | 48748/57600 [8:34:30<1:31:59, 1.60it/s] 85%|████████▍ | 48749/57600 [8:34:31<1:30:51, 1.62it/s] 85%|████████▍ | 48750/57600 [8:34:31<1:31:04, 1.62it/s] 85%|████████▍ | 48751/57600 [8:34:32<1:35:09, 1.55it/s] 85%|████████▍ | 48752/57600 [8:34:33<1:32:50, 1.59it/s] 85%|████████▍ | 48753/57600 [8:34:33<1:31:11, 1.62it/s] 85%|████████▍ | 48754/57600 [8:34:34<1:30:43, 1.63it/s] 85%|████████▍ | 48755/57600 [8:34:34<1:33:58, 1.57it/s] 85%|████████▍ | 48756/57600 [8:34:35<1:34:39, 1.56it/s] 85%|████████▍ | 48757/57600 [8:34:36<1:35:44, 1.54it/s] 85%|████████▍ | 48758/57600 [8:34:36<1:34:49, 1.55it/s] 85%|████████▍ | 48759/57600 [8:34:37<1:33:33, 1.58it/s] 85%|████████▍ | 48760/57600 [8:34:38<1:34:46, 1.55it/s] {'loss': 1.1336, 'learning_rate': 2.3860627177700346e-07, 'epoch': 538.19} + 85%|████████▍ | 48760/57600 [8:34:38<1:34:46, 1.55it/s] 85%|████████▍ | 48761/57600 [8:34:38<1:30:46, 1.62it/s] 85%|████████▍ | 48762/57600 [8:34:39<1:31:54, 1.60it/s] 85%|████████▍ | 48763/57600 [8:34:40<1:34:18, 1.56it/s] 85%|████████▍ | 48764/57600 [8:34:40<1:32:58, 1.58it/s] 85%|████████▍ | 48765/57600 [8:34:41<1:32:12, 1.60it/s] 85%|████████▍ | 48766/57600 [8:34:41<1:31:31, 1.61it/s] 85%|████████▍ | 48767/57600 [8:34:42<1:30:53, 1.62it/s] 85%|████████▍ | 48768/57600 [8:34:43<1:28:18, 1.67it/s] 85%|████████▍ | 48769/57600 [8:34:43<1:28:30, 1.66it/s] 85%|████████▍ | 48770/57600 [8:34:44<1:28:02, 1.67it/s] 85%|████████▍ | 48771/57600 [8:34:44<1:29:58, 1.64it/s] 85%|████████▍ | 48772/57600 [8:34:45<1:29:06, 1.65it/s] 85%|████████▍ | 48773/57600 [8:34:46<1:29:14, 1.65it/s] 85%|████████▍ | 48774/57600 [8:34:46<1:30:41, 1.62it/s] 85%|████████▍ | 48775/57600 [8:34:47<1:31:40, 1.60it/s] 85%|████████▍ | 48776/57600 [8:34:47<1:30:58, 1.62it/s] 85%|████████▍ | 48777/57600 [8:34:48<1:36:03, 1.53it/s] 85%|████████▍ | 48778/57600 [8:34:49<1:37:21, 1.51it/s] 85%|████████▍ | 48779/57600 [8:34:50<1:37:03, 1.51it/s] 85%|████████▍ | 48780/57600 [8:34:50<1:34:13, 1.56it/s] {'loss': 1.1218, 'learning_rate': 2.382926829268293e-07, 'epoch': 538.41} + 85%|████████▍ | 48780/57600 [8:34:50<1:34:13, 1.56it/s] 85%|████████▍ | 48781/57600 [8:34:51<1:31:44, 1.60it/s] 85%|████████▍ | 48782/57600 [8:34:51<1:31:05, 1.61it/s] 85%|████████▍ | 48783/57600 [8:34:52<1:29:19, 1.64it/s] 85%|████████▍ | 48784/57600 [8:34:52<1:27:39, 1.68it/s] 85%|████████▍ | 48785/57600 [8:34:53<1:31:14, 1.61it/s] 85%|████████▍ | 48786/57600 [8:34:54<1:30:23, 1.63it/s] 85%|████████▍ | 48787/57600 [8:34:54<1:34:28, 1.55it/s] 85%|████████▍ | 48788/57600 [8:34:55<1:33:37, 1.57it/s] 85%|████████▍ | 48789/57600 [8:34:56<1:35:26, 1.54it/s] 85%|████████▍ | 48790/57600 [8:34:56<1:33:31, 1.57it/s] 85%|████████▍ | 48791/57600 [8:34:57<1:35:08, 1.54it/s] 85%|████████▍ | 48792/57600 [8:34:58<1:32:24, 1.59it/s] 85%|████████▍ | 48793/57600 [8:34:58<1:33:54, 1.56it/s] 85%|████████▍ | 48794/57600 [8:34:59<1:31:52, 1.60it/s] 85%|████████▍ | 48795/57600 [8:35:00<1:32:08, 1.59it/s] 85%|████████▍ | 48796/57600 [8:35:00<1:30:43, 1.62it/s] 85%|████████▍ | 48797/57600 [8:35:01<1:33:03, 1.58it/s] 85%|████████▍ | 48798/57600 [8:35:02<1:38:29, 1.49it/s] 85%|████████▍ | 48799/57600 [8:35:02<1:34:35, 1.55it/s] 85%|████████▍ | 48800/57600 [8:35:03<1:30:59, 1.61it/s] {'loss': 1.104, 'learning_rate': 2.37979094076655e-07, 'epoch': 538.63} + 85%|████████▍ | 48800/57600 [8:35:03<1:30:59, 1.61it/s] 85%|████████▍ | 48801/57600 [8:35:03<1:33:32, 1.57it/s] 85%|████████▍ | 48802/57600 [8:35:04<1:33:04, 1.58it/s] 85%|████████▍ | 48803/57600 [8:35:05<1:32:45, 1.58it/s] 85%|████████▍ | 48804/57600 [8:35:05<1:30:26, 1.62it/s] 85%|████████▍ | 48805/57600 [8:35:06<1:30:19, 1.62it/s] 85%|████████▍ | 48806/57600 [8:35:06<1:28:48, 1.65it/s] 85%|████████▍ | 48807/57600 [8:35:07<1:29:03, 1.65it/s] 85%|████████▍ | 48808/57600 [8:35:08<1:31:25, 1.60it/s] 85%|████████▍ | 48809/57600 [8:35:08<1:32:34, 1.58it/s] 85%|████████▍ | 48810/57600 [8:35:09<1:31:17, 1.60it/s] 85%|████████▍ | 48811/57600 [8:35:10<1:32:02, 1.59it/s] 85%|████████▍ | 48812/57600 [8:35:10<1:31:58, 1.59it/s] 85%|████████▍ | 48813/57600 [8:35:11<1:33:52, 1.56it/s] 85%|████████▍ | 48814/57600 [8:35:12<1:35:11, 1.54it/s] 85%|████████▍ | 48815/57600 [8:35:12<1:33:26, 1.57it/s] 85%|████████▍ | 48816/57600 [8:35:13<1:33:42, 1.56it/s] 85%|████████▍ | 48817/57600 [8:35:13<1:32:46, 1.58it/s] 85%|████████▍ | 48818/57600 [8:35:14<1:31:48, 1.59it/s] 85%|████████▍ | 48819/57600 [8:35:15<1:30:27, 1.62it/s] 85%|████████▍ | 48820/57600 [8:35:15<1:30:29, 1.62it/s] {'loss': 1.1036, 'learning_rate': 2.3766550522648084e-07, 'epoch': 538.85} + 85%|████████▍ | 48820/57600 [8:35:15<1:30:29, 1.62it/s] 85%|████████▍ | 48821/57600 [8:35:16<1:31:30, 1.60it/s] 85%|████████▍ | 48822/57600 [8:35:17<1:31:49, 1.59it/s] 85%|████████▍ | 48823/57600 [8:35:17<1:29:46, 1.63it/s] 85%|████████▍ | 48824/57600 [8:35:18<1:34:20, 1.55it/s] 85%|████████▍ | 48825/57600 [8:35:19<1:36:49, 1.51it/s] 85%|████████▍ | 48826/57600 [8:35:19<1:36:59, 1.51it/s] 85%|████████▍ | 48827/57600 [8:35:20<1:35:59, 1.52it/s] 85%|████████▍ | 48828/57600 [8:35:20<1:34:22, 1.55it/s] 85%|████████▍ | 48829/57600 [8:35:21<1:33:08, 1.57it/s] 85%|████████▍ | 48830/57600 [8:35:22<1:32:23, 1.58it/s] 85%|████████▍ | 48831/57600 [8:35:22<1:33:32, 1.56it/s] 85%|████████▍ | 48832/57600 [8:35:23<1:32:25, 1.58it/s] 85%|████████▍ | 48833/57600 [8:35:24<1:32:18, 1.58it/s] 85%|████████▍ | 48834/57600 [8:35:24<1:35:17, 1.53it/s] 85%|████████▍ | 48835/57600 [8:35:25<1:32:10, 1.58it/s] 85%|████████▍ | 48836/57600 [8:35:25<1:29:59, 1.62it/s] 85%|████████▍ | 48837/57600 [8:35:26<1:33:11, 1.57it/s] 85%|████████▍ | 48838/57600 [8:35:27<1:30:53, 1.61it/s] 85%|████████▍ | 48839/57600 [8:35:27<1:29:05, 1.64it/s] 85%|████████▍ | 48840/57600 [8:35:28<1:28:19, 1.65it/s] {'loss': 1.1054, 'learning_rate': 2.3735191637630657e-07, 'epoch': 539.07} + 85%|████████▍ | 48840/57600 [8:35:28<1:28:19, 1.65it/s] 85%|████████▍ | 48841/57600 [8:35:28<1:26:16, 1.69it/s] 85%|████████▍ | 48842/57600 [8:35:29<1:30:12, 1.62it/s] 85%|████████▍ | 48843/57600 [8:35:30<1:28:37, 1.65it/s] 85%|████████▍ | 48844/57600 [8:35:30<1:29:31, 1.63it/s] 85%|████████▍ | 48845/57600 [8:35:31<1:27:46, 1.66it/s] 85%|████████▍ | 48846/57600 [8:35:32<1:27:02, 1.68it/s] 85%|████████▍ | 48847/57600 [8:35:32<1:29:28, 1.63it/s] 85%|████████▍ | 48848/57600 [8:35:33<1:30:46, 1.61it/s] 85%|████████▍ | 48849/57600 [8:35:33<1:32:28, 1.58it/s] 85%|████████▍ | 48850/57600 [8:35:34<1:29:54, 1.62it/s] 85%|████████▍ | 48851/57600 [8:35:35<1:32:05, 1.58it/s] 85%|████████▍ | 48852/57600 [8:35:35<1:32:10, 1.58it/s] 85%|████████▍ | 48853/57600 [8:35:36<1:31:52, 1.59it/s] 85%|████████▍ | 48854/57600 [8:35:37<1:30:33, 1.61it/s] 85%|████████▍ | 48855/57600 [8:35:37<1:31:02, 1.60it/s] 85%|████████▍ | 48856/57600 [8:35:38<1:30:07, 1.62it/s] 85%|████████▍ | 48857/57600 [8:35:38<1:31:14, 1.60it/s] 85%|████████▍ | 48858/57600 [8:35:39<1:31:34, 1.59it/s] 85%|████████▍ | 48859/57600 [8:35:40<1:32:01, 1.58it/s] 85%|████████▍ | 48860/57600 [8:35:40<1:36:03, 1.52it/s] {'loss': 1.1439, 'learning_rate': 2.3703832752613237e-07, 'epoch': 539.29} + 85%|████████▍ | 48860/57600 [8:35:40<1:36:03, 1.52it/s] 85%|████████▍ | 48861/57600 [8:35:41<1:37:13, 1.50it/s] 85%|████████▍ | 48862/57600 [8:35:42<1:36:39, 1.51it/s] 85%|████████▍ | 48863/57600 [8:35:42<1:35:55, 1.52it/s] 85%|████████▍ | 48864/57600 [8:35:43<1:36:12, 1.51it/s] 85%|████████▍ | 48865/57600 [8:35:44<1:35:06, 1.53it/s] 85%|████████▍ | 48866/57600 [8:35:44<1:32:44, 1.57it/s] 85%|████████▍ | 48867/57600 [8:35:45<1:32:30, 1.57it/s] 85%|████████▍ | 48868/57600 [8:35:46<1:32:57, 1.57it/s] 85%|████████▍ | 48869/57600 [8:35:46<1:32:17, 1.58it/s] 85%|████████▍ | 48870/57600 [8:35:47<1:29:22, 1.63it/s] 85%|████████▍ | 48871/57600 [8:35:47<1:29:54, 1.62it/s] 85%|████████▍ | 48872/57600 [8:35:48<1:33:54, 1.55it/s] 85%|████████▍ | 48873/57600 [8:35:49<1:32:01, 1.58it/s] 85%|████████▍ | 48874/57600 [8:35:49<1:29:07, 1.63it/s] 85%|████████▍ | 48875/57600 [8:35:50<1:34:57, 1.53it/s] 85%|████████▍ | 48876/57600 [8:35:51<1:34:58, 1.53it/s] 85%|████████▍ | 48877/57600 [8:35:51<1:33:32, 1.55it/s] 85%|████████▍ | 48878/57600 [8:35:52<1:32:54, 1.56it/s] 85%|████████▍ | 48879/57600 [8:35:53<1:34:02, 1.55it/s] 85%|████████▍ | 48880/57600 [8:35:53<1:34:29, 1.54it/s] {'loss': 1.08, 'learning_rate': 2.367247386759582e-07, 'epoch': 539.51} + 85%|████████▍ | 48880/57600 [8:35:53<1:34:29, 1.54it/s] 85%|████████▍ | 48881/57600 [8:35:54<1:33:39, 1.55it/s] 85%|████████▍ | 48882/57600 [8:35:55<1:32:03, 1.58it/s] 85%|████████▍ | 48883/57600 [8:35:55<1:32:01, 1.58it/s] 85%|████████▍ | 48884/57600 [8:35:56<1:32:34, 1.57it/s] 85%|████████▍ | 48885/57600 [8:35:56<1:33:52, 1.55it/s] 85%|████████▍ | 48886/57600 [8:35:57<1:31:22, 1.59it/s] 85%|████████▍ | 48887/57600 [8:35:58<1:30:23, 1.61it/s] 85%|████████▍ | 48888/57600 [8:35:58<1:27:38, 1.66it/s] 85%|████████▍ | 48889/57600 [8:35:59<1:26:08, 1.69it/s] 85%|████████▍ | 48890/57600 [8:35:59<1:27:56, 1.65it/s] 85%|████████▍ | 48891/57600 [8:36:00<1:27:35, 1.66it/s] 85%|████████▍ | 48892/57600 [8:36:01<1:28:01, 1.65it/s] 85%|████████▍ | 48893/57600 [8:36:01<1:27:19, 1.66it/s] 85%|████████▍ | 48894/57600 [8:36:02<1:32:21, 1.57it/s] 85%|████████▍ | 48895/57600 [8:36:03<1:30:07, 1.61it/s] 85%|████████▍ | 48896/57600 [8:36:03<1:26:38, 1.67it/s] 85%|████████▍ | 48897/57600 [8:36:04<1:27:26, 1.66it/s] 85%|████████▍ | 48898/57600 [8:36:04<1:26:16, 1.68it/s] 85%|████████▍ | 48899/57600 [8:36:05<1:29:33, 1.62it/s] 85%|████████▍ | 48900/57600 [8:36:06<1:28:29, 1.64it/s] {'loss': 1.1405, 'learning_rate': 2.364111498257839e-07, 'epoch': 539.74} + 85%|████████▍ | 48900/57600 [8:36:06<1:28:29, 1.64it/s] 85%|████████▍ | 48901/57600 [8:36:06<1:30:27, 1.60it/s] 85%|████████▍ | 48902/57600 [8:36:07<1:29:12, 1.63it/s] 85%|████████▍ | 48903/57600 [8:36:07<1:29:45, 1.61it/s] 85%|████████▍ | 48904/57600 [8:36:08<1:29:30, 1.62it/s] 85%|████████▍ | 48905/57600 [8:36:09<1:32:09, 1.57it/s] 85%|████████▍ | 48906/57600 [8:36:09<1:33:15, 1.55it/s] 85%|████████▍ | 48907/57600 [8:36:10<1:30:58, 1.59it/s] 85%|████████▍ | 48908/57600 [8:36:11<1:31:46, 1.58it/s] 85%|████████▍ | 48909/57600 [8:36:11<1:36:08, 1.51it/s] 85%|████████▍ | 48910/57600 [8:36:12<1:31:43, 1.58it/s] 85%|████████▍ | 48911/57600 [8:36:13<1:35:54, 1.51it/s] 85%|████████▍ | 48912/57600 [8:36:13<1:34:52, 1.53it/s] 85%|████████▍ | 48913/57600 [8:36:14<1:32:43, 1.56it/s] 85%|████████▍ | 48914/57600 [8:36:14<1:30:48, 1.59it/s] 85%|████████▍ | 48915/57600 [8:36:15<1:30:52, 1.59it/s] 85%|████████▍ | 48916/57600 [8:36:16<1:32:13, 1.57it/s] 85%|████████▍ | 48917/57600 [8:36:16<1:33:30, 1.55it/s] 85%|████████▍ | 48918/57600 [8:36:17<1:30:51, 1.59it/s] 85%|████████▍ | 48919/57600 [8:36:18<1:34:14, 1.54it/s] 85%|████████▍ | 48920/57600 [8:36:18<1:37:33, 1.48it/s] {'loss': 1.0862, 'learning_rate': 2.3609756097560976e-07, 'epoch': 539.96} + 85%|████████▍ | 48920/57600 [8:36:18<1:37:33, 1.48it/s] 85%|████████▍ | 48921/57600 [8:36:19<1:36:50, 1.49it/s] 85%|████████▍ | 48922/57600 [8:36:20<1:32:45, 1.56it/s] 85%|████████▍ | 48923/57600 [8:36:20<1:34:10, 1.54it/s] 85%|████████▍ | 48924/57600 [8:36:21<1:30:32, 1.60it/s] 85%|████████▍ | 48925/57600 [8:36:22<1:32:06, 1.57it/s] 85%|████████▍ | 48926/57600 [8:36:22<1:34:05, 1.54it/s] 85%|████████▍ | 48927/57600 [8:36:23<1:32:17, 1.57it/s] 85%|████████▍ | 48928/57600 [8:36:24<1:31:45, 1.58it/s] 85%|████████▍ | 48929/57600 [8:36:24<1:30:30, 1.60it/s] 85%|████████▍ | 48930/57600 [8:36:25<1:31:13, 1.58it/s] 85%|████████▍ | 48931/57600 [8:36:25<1:31:56, 1.57it/s] 85%|████████▍ | 48932/57600 [8:36:26<1:33:28, 1.55it/s] 85%|████████▍ | 48933/57600 [8:36:27<1:33:23, 1.55it/s] 85%|████████▍ | 48934/57600 [8:36:27<1:31:43, 1.57it/s] 85%|████████▍ | 48935/57600 [8:36:28<1:31:28, 1.58it/s] 85%|████████▍ | 48936/57600 [8:36:29<1:31:04, 1.59it/s] 85%|████████▍ | 48937/57600 [8:36:29<1:30:01, 1.60it/s] 85%|████████▍ | 48938/57600 [8:36:30<1:29:36, 1.61it/s] 85%|████████▍ | 48939/57600 [8:36:30<1:30:48, 1.59it/s] 85%|████████▍ | 48940/57600 [8:36:31<1:33:10, 1.55it/s] {'loss': 1.1428, 'learning_rate': 2.357839721254355e-07, 'epoch': 540.18} + 85%|████████▍ | 48940/57600 [8:36:31<1:33:10, 1.55it/s] 85%|████████▍ | 48941/57600 [8:36:32<1:34:18, 1.53it/s] 85%|████████▍ | 48942/57600 [8:36:32<1:34:44, 1.52it/s] 85%|████████▍ | 48943/57600 [8:36:33<1:31:26, 1.58it/s] 85%|████████▍ | 48944/57600 [8:36:34<1:29:32, 1.61it/s] 85%|████████▍ | 48945/57600 [8:36:34<1:29:58, 1.60it/s] 85%|████████▍ | 48946/57600 [8:36:35<1:31:42, 1.57it/s] 85%|████████▍ | 48947/57600 [8:36:36<1:30:31, 1.59it/s] 85%|████████▍ | 48948/57600 [8:36:36<1:31:47, 1.57it/s] 85%|████████▍ | 48949/57600 [8:36:37<1:29:03, 1.62it/s] 85%|████████▍ | 48950/57600 [8:36:37<1:30:42, 1.59it/s] 85%|████████▍ | 48951/57600 [8:36:38<1:32:33, 1.56it/s] 85%|████████▍ | 48952/57600 [8:36:39<1:33:04, 1.55it/s] 85%|████████▍ | 48953/57600 [8:36:39<1:33:16, 1.55it/s] 85%|████████▍ | 48954/57600 [8:36:40<1:32:28, 1.56it/s] 85%|████████▍ | 48955/57600 [8:36:41<1:29:38, 1.61it/s] 85%|████████▍ | 48956/57600 [8:36:41<1:29:32, 1.61it/s] 85%|████████▍ | 48957/57600 [8:36:42<1:31:23, 1.58it/s] 85%|████████▍ | 48958/57600 [8:36:43<1:32:29, 1.56it/s] 85%|████████▍ | 48959/57600 [8:36:43<1:32:47, 1.55it/s] 85%|████████▌ | 48960/57600 [8:36:44<1:31:51, 1.57it/s] {'loss': 1.1379, 'learning_rate': 2.3547038327526132e-07, 'epoch': 540.4} + 85%|████████▌ | 48960/57600 [8:36:44<1:31:51, 1.57it/s] 85%|████████▌ | 48961/57600 [8:36:45<1:34:00, 1.53it/s] 85%|████████▌ | 48962/57600 [8:36:45<1:32:19, 1.56it/s] 85%|████████▌ | 48963/57600 [8:36:46<1:30:05, 1.60it/s] 85%|████████▌ | 48964/57600 [8:36:46<1:32:11, 1.56it/s] 85%|█��██████▌ | 48965/57600 [8:36:47<1:28:34, 1.62it/s] 85%|████████▌ | 48966/57600 [8:36:48<1:29:14, 1.61it/s] 85%|████████▌ | 48967/57600 [8:36:48<1:29:14, 1.61it/s] 85%|████████▌ | 48968/57600 [8:36:49<1:32:02, 1.56it/s] 85%|████████▌ | 48969/57600 [8:36:50<1:36:18, 1.49it/s] 85%|████████▌ | 48970/57600 [8:36:50<1:33:54, 1.53it/s] 85%|████████▌ | 48971/57600 [8:36:51<1:29:52, 1.60it/s] 85%|████████▌ | 48972/57600 [8:36:51<1:28:12, 1.63it/s] 85%|████████▌ | 48973/57600 [8:36:52<1:32:02, 1.56it/s] 85%|████████▌ | 48974/57600 [8:36:53<1:31:30, 1.57it/s] 85%|████████▌ | 48975/57600 [8:36:53<1:31:59, 1.56it/s] 85%|████████▌ | 48976/57600 [8:36:54<1:29:56, 1.60it/s] 85%|████████▌ | 48977/57600 [8:36:55<1:34:00, 1.53it/s] 85%|████████▌ | 48978/57600 [8:36:55<1:31:24, 1.57it/s] 85%|████████▌ | 48979/57600 [8:36:56<1:29:55, 1.60it/s] 85%|████████▌ | 48980/57600 [8:36:56<1:28:29, 1.62it/s] {'loss': 1.1155, 'learning_rate': 2.3515679442508715e-07, 'epoch': 540.62} + 85%|████████▌ | 48980/57600 [8:36:56<1:28:29, 1.62it/s] 85%|████████▌ | 48981/57600 [8:36:57<1:29:02, 1.61it/s] 85%|████████▌ | 48982/57600 [8:36:58<1:27:41, 1.64it/s] 85%|████████▌ | 48983/57600 [8:36:58<1:26:39, 1.66it/s] 85%|████████▌ | 48984/57600 [8:36:59<1:31:34, 1.57it/s] 85%|████████▌ | 48985/57600 [8:37:00<1:35:37, 1.50it/s] 85%|████████▌ | 48986/57600 [8:37:00<1:32:17, 1.56it/s] 85%|████████▌ | 48987/57600 [8:37:01<1:33:29, 1.54it/s] 85%|████████▌ | 48988/57600 [8:37:02<1:32:25, 1.55it/s] 85%|████████▌ | 48989/57600 [8:37:02<1:32:18, 1.55it/s] 85%|████████▌ | 48990/57600 [8:37:03<1:35:18, 1.51it/s] 85%|████████▌ | 48991/57600 [8:37:04<1:34:02, 1.53it/s] 85%|████████▌ | 48992/57600 [8:37:04<1:34:30, 1.52it/s] 85%|████████▌ | 48993/57600 [8:37:05<1:31:31, 1.57it/s] 85%|████████▌ | 48994/57600 [8:37:05<1:29:11, 1.61it/s] 85%|████████▌ | 48995/57600 [8:37:06<1:31:58, 1.56it/s] 85%|████████▌ | 48996/57600 [8:37:07<1:30:25, 1.59it/s] 85%|████████▌ | 48997/57600 [8:37:07<1:30:25, 1.59it/s] 85%|████████▌ | 48998/57600 [8:37:08<1:28:39, 1.62it/s] 85%|████████▌ | 48999/57600 [8:37:09<1:28:59, 1.61it/s] 85%|████████▌ | 49000/57600 [8:37:09<1:27:58, 1.63it/s] {'loss': 1.0901, 'learning_rate': 2.3484320557491288e-07, 'epoch': 540.84} + 85%|████████▌ | 49000/57600 [8:37:09<1:27:58, 1.63it/s] 85%|████████▌ | 49001/57600 [8:37:10<1:25:17, 1.68it/s] 85%|████████▌ | 49002/57600 [8:37:10<1:25:03, 1.68it/s] 85%|████████▌ | 49003/57600 [8:37:11<1:25:52, 1.67it/s] 85%|████████▌ | 49004/57600 [8:37:12<1:26:40, 1.65it/s] 85%|████████▌ | 49005/57600 [8:37:12<1:27:07, 1.64it/s] 85%|████████▌ | 49006/57600 [8:37:13<1:29:53, 1.59it/s] 85%|████████▌ | 49007/57600 [8:37:13<1:30:17, 1.59it/s] 85%|████████▌ | 49008/57600 [8:37:14<1:31:36, 1.56it/s] 85%|████████▌ | 49009/57600 [8:37:15<1:30:38, 1.58it/s] 85%|████████▌ | 49010/57600 [8:37:15<1:30:29, 1.58it/s] 85%|████████▌ | 49011/57600 [8:37:16<1:30:08, 1.59it/s] 85%|████████▌ | 49012/57600 [8:37:17<1:28:11, 1.62it/s] 85%|████████▌ | 49013/57600 [8:37:17<1:28:26, 1.62it/s] 85%|████████▌ | 49014/57600 [8:37:18<1:27:14, 1.64it/s] 85%|████████▌ | 49015/57600 [8:37:19<1:32:28, 1.55it/s] 85%|████████▌ | 49016/57600 [8:37:19<1:32:56, 1.54it/s] 85%|████████▌ | 49017/57600 [8:37:20<1:32:37, 1.54it/s] 85%|████████▌ | 49018/57600 [8:37:20<1:31:20, 1.57it/s] 85%|████████▌ | 49019/57600 [8:37:21<1:29:05, 1.61it/s] 85%|████████▌ | 49020/57600 [8:37:22<1:28:11, 1.62it/s] {'loss': 1.1415, 'learning_rate': 2.345296167247387e-07, 'epoch': 541.06} + 85%|████████▌ | 49020/57600 [8:37:22<1:28:11, 1.62it/s] 85%|████████▌ | 49021/57600 [8:37:22<1:26:55, 1.64it/s] 85%|████████▌ | 49022/57600 [8:37:23<1:30:00, 1.59it/s] 85%|████████▌ | 49023/57600 [8:37:24<1:28:26, 1.62it/s] 85%|████████▌ | 49024/57600 [8:37:24<1:28:01, 1.62it/s] 85%|████████▌ | 49025/57600 [8:37:25<1:31:04, 1.57it/s] 85%|████████▌ | 49026/57600 [8:37:25<1:30:01, 1.59it/s] 85%|████████▌ | 49027/57600 [8:37:26<1:29:10, 1.60it/s] 85%|████████▌ | 49028/57600 [8:37:27<1:29:17, 1.60it/s] 85%|████████▌ | 49029/57600 [8:37:27<1:29:58, 1.59it/s] 85%|████████▌ | 49030/57600 [8:37:28<1:29:30, 1.60it/s] 85%|████████▌ | 49031/57600 [8:37:29<1:30:11, 1.58it/s] 85%|████████▌ | 49032/57600 [8:37:29<1:31:59, 1.55it/s] 85%|████████▌ | 49033/57600 [8:37:30<1:30:02, 1.59it/s] 85%|████████▌ | 49034/57600 [8:37:30<1:27:20, 1.63it/s] 85%|████████▌ | 49035/57600 [8:37:31<1:27:33, 1.63it/s] 85%|████████▌ | 49036/57600 [8:37:32<1:26:47, 1.64it/s] 85%|████████▌ | 49037/57600 [8:37:32<1:29:49, 1.59it/s] 85%|████████▌ | 49038/57600 [8:37:33<1:29:47, 1.59it/s] 85%|████████▌ | 49039/57600 [8:37:34<1:30:10, 1.58it/s] 85%|████████▌ | 49040/57600 [8:37:34<1:31:11, 1.56it/s] {'loss': 1.1008, 'learning_rate': 2.3421602787456443e-07, 'epoch': 541.28} + 85%|████████▌ | 49040/57600 [8:37:34<1:31:11, 1.56it/s] 85%|████████▌ | 49041/57600 [8:37:35<1:32:55, 1.54it/s] 85%|████████▌ | 49042/57600 [8:37:36<1:31:13, 1.56it/s] 85%|████████▌ | 49043/57600 [8:37:36<1:32:50, 1.54it/s] 85%|████████▌ | 49044/57600 [8:37:37<1:30:33, 1.57it/s] 85%|████████▌ | 49045/57600 [8:37:37<1:30:35, 1.57it/s] 85%|████████▌ | 49046/57600 [8:37:38<1:34:57, 1.50it/s] 85%|████████▌ | 49047/57600 [8:37:39<1:33:14, 1.53it/s] 85%|████████▌ | 49048/57600 [8:37:39<1:31:15, 1.56it/s] 85%|████████▌ | 49049/57600 [8:37:40<1:32:36, 1.54it/s] 85%|████████▌ | 49050/57600 [8:37:41<1:34:03, 1.51it/s] 85%|████████▌ | 49051/57600 [8:37:41<1:31:17, 1.56it/s] 85%|████████▌ | 49052/57600 [8:37:42<1:33:22, 1.53it/s] 85%|████████▌ | 49053/57600 [8:37:43<1:31:10, 1.56it/s] 85%|████████▌ | 49054/57600 [8:37:43<1:30:34, 1.57it/s] 85%|████████▌ | 49055/57600 [8:37:44<1:29:30, 1.59it/s] 85%|████████▌ | 49056/57600 [8:37:44<1:28:05, 1.62it/s] 85%|████████▌ | 49057/57600 [8:37:45<1:28:23, 1.61it/s] 85%|████████▌ | 49058/57600 [8:37:46<1:30:54, 1.57it/s] 85%|████████▌ | 49059/57600 [8:37:46<1:29:34, 1.59it/s] 85%|████████▌ | 49060/57600 [8:37:47<1:28:48, 1.60it/s] {'loss': 1.1034, 'learning_rate': 2.3390243902439026e-07, 'epoch': 541.5} + 85%|████████▌ | 49060/57600 [8:37:47<1:28:48, 1.60it/s] 85%|████████▌ | 49061/57600 [8:37:48<1:29:25, 1.59it/s] 85%|████████▌ | 49062/57600 [8:37:48<1:26:18, 1.65it/s] 85%|████████▌ | 49063/57600 [8:37:49<1:30:27, 1.57it/s] 85%|████████▌ | 49064/57600 [8:37:50<1:33:00, 1.53it/s] 85%|████████▌ | 49065/57600 [8:37:50<1:30:28, 1.57it/s] 85%|████████▌ | 49066/57600 [8:37:51<1:29:18, 1.59it/s] 85%|████████▌ | 49067/57600 [8:37:51<1:26:53, 1.64it/s] 85%|████████▌ | 49068/57600 [8:37:52<1:28:03, 1.61it/s] 85%|████████▌ | 49069/57600 [8:37:53<1:30:56, 1.56it/s] 85%|████████▌ | 49070/57600 [8:37:53<1:27:53, 1.62it/s] 85%|████████▌ | 49071/57600 [8:37:54<1:27:38, 1.62it/s] 85%|████████▌ | 49072/57600 [8:37:54<1:26:44, 1.64it/s] 85%|████████▌ | 49073/57600 [8:37:55<1:24:48, 1.68it/s] 85%|████████▌ | 49074/57600 [8:37:56<1:25:58, 1.65it/s] 85%|████████▌ | 49075/57600 [8:37:56<1:27:07, 1.63it/s] 85%|████████▌ | 49076/57600 [8:37:57<1:27:14, 1.63it/s] 85%|████████▌ | 49077/57600 [8:37:58<1:29:52, 1.58it/s] 85%|████████▌ | 49078/57600 [8:37:58<1:31:58, 1.54it/s] 85%|████████▌ | 49079/57600 [8:37:59<1:30:30, 1.57it/s] 85%|████████▌ | 49080/57600 [8:37:59<1:28:06, 1.61it/s] {'loss': 1.0984, 'learning_rate': 2.33588850174216e-07, 'epoch': 541.72} + 85%|████████▌ | 49080/57600 [8:37:59<1:28:06, 1.61it/s] 85%|████████▌ | 49081/57600 [8:38:00<1:26:52, 1.63it/s] 85%|████████▌ | 49082/57600 [8:38:01<1:29:29, 1.59it/s] 85%|████████▌ | 49083/57600 [8:38:01<1:28:19, 1.61it/s] 85%|████████▌ | 49084/57600 [8:38:02<1:26:05, 1.65it/s] 85%|████████▌ | 49085/57600 [8:38:03<1:26:45, 1.64it/s] 85%|████████▌ | 49086/57600 [8:38:03<1:27:10, 1.63it/s] 85%|████████▌ | 49087/57600 [8:38:04<1:25:15, 1.66it/s] 85%|████████▌ | 49088/57600 [8:38:04<1:25:50, 1.65it/s] 85%|████████▌ | 49089/57600 [8:38:05<1:29:55, 1.58it/s] 85%|████████▌ | 49090/57600 [8:38:06<1:29:49, 1.58it/s] 85%|████████▌ | 49091/57600 [8:38:06<1:33:50, 1.51it/s] 85%|████████▌ | 49092/57600 [8:38:07<1:33:32, 1.52it/s] 85%|████████▌ | 49093/57600 [8:38:08<1:29:55, 1.58it/s] 85%|████████▌ | 49094/57600 [8:38:08<1:32:17, 1.54it/s] 85%|████████▌ | 49095/57600 [8:38:09<1:32:17, 1.54it/s] 85%|████████▌ | 49096/57600 [8:38:10<1:28:26, 1.60it/s] 85%|████████▌ | 49097/57600 [8:38:10<1:28:01, 1.61it/s] 85%|████████▌ | 49098/57600 [8:38:11<1:27:56, 1.61it/s] 85%|████████▌ | 49099/57600 [8:38:11<1:27:30, 1.62it/s] 85%|████████▌ | 49100/57600 [8:38:12<1:27:12, 1.62it/s] {'loss': 1.1269, 'learning_rate': 2.332752613240418e-07, 'epoch': 541.94} + 85%|████████▌ | 49100/57600 [8:38:12<1:27:12, 1.62it/s] 85%|████████▌ | 49101/57600 [8:38:13<1:25:47, 1.65it/s] 85%|████████▌ | 49102/57600 [8:38:13<1:26:50, 1.63it/s] 85%|████████▌ | 49103/57600 [8:38:14<1:27:24, 1.62it/s] 85%|████████▌ | 49104/57600 [8:38:14<1:26:42, 1.63it/s] 85%|████████▌ | 49105/57600 [8:38:15<1:25:23, 1.66it/s] 85%|████████▌ | 49106/57600 [8:38:16<1:30:25, 1.57it/s] 85%|████████▌ | 49107/57600 [8:38:16<1:32:12, 1.54it/s] 85%|████████▌ | 49108/57600 [8:38:17<1:31:10, 1.55it/s] 85%|████████▌ | 49109/57600 [8:38:18<1:27:59, 1.61it/s] 85%|████████▌ | 49110/57600 [8:38:18<1:27:34, 1.62it/s] 85%|████████▌ | 49111/57600 [8:38:19<1:27:26, 1.62it/s] 85%|████████▌ | 49112/57600 [8:38:19<1:27:34, 1.62it/s] 85%|████████▌ | 49113/57600 [8:38:20<1:30:38, 1.56it/s] 85%|████████▌ | 49114/57600 [8:38:21<1:31:06, 1.55it/s] 85%|████████▌ | 49115/57600 [8:38:21<1:29:48, 1.57it/s] 85%|████████▌ | 49116/57600 [8:38:22<1:28:02, 1.61it/s] 85%|████████▌ | 49117/57600 [8:38:23<1:25:32, 1.65it/s] 85%|████████▌ | 49118/57600 [8:38:23<1:25:25, 1.65it/s] 85%|████████▌ | 49119/57600 [8:38:24<1:28:05, 1.60it/s] 85%|████████▌ | 49120/57600 [8:38:24<1:29:07, 1.59it/s] {'loss': 1.1275, 'learning_rate': 2.3296167247386763e-07, 'epoch': 542.16} + 85%|████████▌ | 49120/57600 [8:38:24<1:29:07, 1.59it/s] 85%|████████▌ | 49121/57600 [8:38:25<1:30:04, 1.57it/s] 85%|████████▌ | 49122/57600 [8:38:26<1:29:14, 1.58it/s] 85%|████████▌ | 49123/57600 [8:38:26<1:31:08, 1.55it/s] 85%|████████▌ | 49124/57600 [8:38:27<1:31:34, 1.54it/s] 85%|████████▌ | 49125/57600 [8:38:28<1:27:55, 1.61it/s] 85%|████████▌ | 49126/57600 [8:38:28<1:26:41, 1.63it/s] 85%|████████▌ | 49127/57600 [8:38:29<1:27:05, 1.62it/s] 85%|████████▌ | 49128/57600 [8:38:29<1:27:12, 1.62it/s] 85%|████████▌ | 49129/57600 [8:38:30<1:27:53, 1.61it/s] 85%|████████▌ | 49130/57600 [8:38:31<1:26:07, 1.64it/s] 85%|████████▌ | 49131/57600 [8:38:31<1:24:16, 1.67it/s] 85%|████████▌ | 49132/57600 [8:38:32<1:23:44, 1.69it/s] 85%|████████▌ | 49133/57600 [8:38:33<1:26:04, 1.64it/s] 85%|████████▌ | 49134/57600 [8:38:33<1:26:39, 1.63it/s] 85%|████████▌ | 49135/57600 [8:38:34<1:29:42, 1.57it/s] 85%|████████▌ | 49136/57600 [8:38:35<1:31:56, 1.53it/s] 85%|████████▌ | 49137/57600 [8:38:35<1:32:21, 1.53it/s] 85%|████████▌ | 49138/57600 [8:38:36<1:29:36, 1.57it/s] 85%|████████▌ | 49139/57600 [8:38:36<1:30:08, 1.56it/s] 85%|████████▌ | 49140/57600 [8:38:37<1:30:51, 1.55it/s] {'loss': 1.0807, 'learning_rate': 2.3264808362369335e-07, 'epoch': 542.38} + 85%|████████▌ | 49140/57600 [8:38:37<1:30:51, 1.55it/s] 85%|████████▌ | 49141/57600 [8:38:38<1:29:42, 1.57it/s] 85%|██████���█▌ | 49142/57600 [8:38:38<1:28:44, 1.59it/s] 85%|████████▌ | 49143/57600 [8:38:39<1:29:17, 1.58it/s] 85%|████████▌ | 49144/57600 [8:38:40<1:29:40, 1.57it/s] 85%|████████▌ | 49145/57600 [8:38:40<1:27:15, 1.61it/s] 85%|████████▌ | 49146/57600 [8:38:41<1:27:44, 1.61it/s] 85%|████████▌ | 49147/57600 [8:38:41<1:28:09, 1.60it/s] 85%|████████▌ | 49148/57600 [8:38:42<1:25:33, 1.65it/s] 85%|████████▌ | 49149/57600 [8:38:43<1:24:40, 1.66it/s] 85%|████████▌ | 49150/57600 [8:38:43<1:24:54, 1.66it/s] 85%|████████▌ | 49151/57600 [8:38:44<1:25:33, 1.65it/s] 85%|████████▌ | 49152/57600 [8:38:44<1:28:48, 1.59it/s] 85%|████████▌ | 49153/57600 [8:38:45<1:31:52, 1.53it/s] 85%|████████▌ | 49154/57600 [8:38:46<1:28:16, 1.59it/s] 85%|████████▌ | 49155/57600 [8:38:46<1:29:52, 1.57it/s] 85%|████████▌ | 49156/57600 [8:38:47<1:28:16, 1.59it/s] 85%|████████▌ | 49157/57600 [8:38:48<1:30:11, 1.56it/s] 85%|████████▌ | 49158/57600 [8:38:48<1:30:22, 1.56it/s] 85%|████████▌ | 49159/57600 [8:38:49<1:33:09, 1.51it/s] 85%|████████▌ | 49160/57600 [8:38:50<1:34:16, 1.49it/s] {'loss': 1.1037, 'learning_rate': 2.3233449477351918e-07, 'epoch': 542.6} + 85%|████████▌ | 49160/57600 [8:38:50<1:34:16, 1.49it/s] 85%|████████▌ | 49161/57600 [8:38:50<1:31:11, 1.54it/s] 85%|████████▌ | 49162/57600 [8:38:51<1:32:23, 1.52it/s] 85%|████████▌ | 49163/57600 [8:38:52<1:29:56, 1.56it/s] 85%|████████▌ | 49164/57600 [8:38:52<1:29:56, 1.56it/s] 85%|████████▌ | 49165/57600 [8:38:53<1:31:27, 1.54it/s] 85%|████████▌ | 49166/57600 [8:38:54<1:29:00, 1.58it/s] 85%|████████▌ | 49167/57600 [8:38:54<1:27:10, 1.61it/s] 85%|████████▌ | 49168/57600 [8:38:55<1:27:10, 1.61it/s] 85%|████████▌ | 49169/57600 [8:38:55<1:26:05, 1.63it/s] 85%|████████▌ | 49170/57600 [8:38:56<1:28:11, 1.59it/s] 85%|████████▌ | 49171/57600 [8:38:57<1:31:36, 1.53it/s] 85%|████████▌ | 49172/57600 [8:38:57<1:32:50, 1.51it/s] 85%|████████▌ | 49173/57600 [8:38:58<1:31:19, 1.54it/s] 85%|████████▌ | 49174/57600 [8:38:59<1:28:58, 1.58it/s] 85%|████████▌ | 49175/57600 [8:38:59<1:29:00, 1.58it/s] 85%|████████▌ | 49176/57600 [8:39:00<1:28:56, 1.58it/s] 85%|████████▌ | 49177/57600 [8:39:00<1:26:31, 1.62it/s] 85%|████████▌ | 49178/57600 [8:39:01<1:25:36, 1.64it/s] 85%|████████▌ | 49179/57600 [8:39:02<1:26:08, 1.63it/s] 85%|████████▌ | 49180/57600 [8:39:02<1:23:41, 1.68it/s] {'loss': 1.1319, 'learning_rate': 2.320209059233449e-07, 'epoch': 542.83} + 85%|████████▌ | 49180/57600 [8:39:02<1:23:41, 1.68it/s] 85%|████████▌ | 49181/57600 [8:39:03<1:25:17, 1.65it/s] 85%|████████▌ | 49182/57600 [8:39:03<1:26:33, 1.62it/s] 85%|████████▌ | 49183/57600 [8:39:04<1:31:40, 1.53it/s] 85%|████████▌ | 49184/57600 [8:39:05<1:31:35, 1.53it/s] 85%|████████▌ | 49185/57600 [8:39:06<1:33:15, 1.50it/s] 85%|████████▌ | 49186/57600 [8:39:06<1:34:58, 1.48it/s] 85%|████████▌ | 49187/57600 [8:39:07<1:31:15, 1.54it/s] 85%|████████▌ | 49188/57600 [8:39:07<1:29:29, 1.57it/s] 85%|████████▌ | 49189/57600 [8:39:08<1:30:03, 1.56it/s] 85%|████████▌ | 49190/57600 [8:39:09<1:32:27, 1.52it/s] 85%|████████▌ | 49191/57600 [8:39:09<1:31:46, 1.53it/s] 85%|████████▌ | 49192/57600 [8:39:10<1:27:58, 1.59it/s] 85%|████████▌ | 49193/57600 [8:39:11<1:30:04, 1.56it/s] 85%|████████▌ | 49194/57600 [8:39:11<1:27:46, 1.60it/s] 85%|████████▌ | 49195/57600 [8:39:12<1:27:44, 1.60it/s] 85%|████████▌ | 49196/57600 [8:39:13<1:29:37, 1.56it/s] 85%|████████▌ | 49197/57600 [8:39:13<1:28:44, 1.58it/s] 85%|████████▌ | 49198/57600 [8:39:14<1:26:03, 1.63it/s] 85%|████████▌ | 49199/57600 [8:39:14<1:26:32, 1.62it/s] 85%|████████▌ | 49200/57600 [8:39:15<1:24:27, 1.66it/s] {'loss': 1.1208, 'learning_rate': 2.3170731707317074e-07, 'epoch': 543.05} + 85%|████████▌ | 49200/57600 [8:39:15<1:24:27, 1.66it/s] 85%|████████▌ | 49201/57600 [8:39:16<1:23:02, 1.69it/s] 85%|████████▌ | 49202/57600 [8:39:16<1:25:56, 1.63it/s] 85%|████████▌ | 49203/57600 [8:39:17<1:25:59, 1.63it/s] 85%|████████▌ | 49204/57600 [8:39:17<1:24:07, 1.66it/s] 85%|████████▌ | 49205/57600 [8:39:18<1:28:44, 1.58it/s] 85%|████████▌ | 49206/57600 [8:39:19<1:28:02, 1.59it/s] 85%|████████▌ | 49207/57600 [8:39:19<1:27:04, 1.61it/s] 85%|████████▌ | 49208/57600 [8:39:20<1:28:09, 1.59it/s] 85%|████████▌ | 49209/57600 [8:39:21<1:28:22, 1.58it/s] 85%|████████▌ | 49210/57600 [8:39:21<1:27:37, 1.60it/s] 85%|████████▌ | 49211/57600 [8:39:22<1:29:05, 1.57it/s] 85%|████████▌ | 49212/57600 [8:39:23<1:29:43, 1.56it/s] 85%|████████▌ | 49213/57600 [8:39:23<1:25:12, 1.64it/s] 85%|████████▌ | 49214/57600 [8:39:24<1:27:51, 1.59it/s] 85%|████████▌ | 49215/57600 [8:39:24<1:27:29, 1.60it/s] 85%|████████▌ | 49216/57600 [8:39:25<1:26:18, 1.62it/s] 85%|████████▌ | 49217/57600 [8:39:26<1:26:07, 1.62it/s] 85%|████████▌ | 49218/57600 [8:39:26<1:25:45, 1.63it/s] 85%|████████▌ | 49219/57600 [8:39:27<1:26:39, 1.61it/s] 85%|████████▌ | 49220/57600 [8:39:27<1:24:01, 1.66it/s] {'loss': 1.126, 'learning_rate': 2.3139372822299646e-07, 'epoch': 543.27} + 85%|████████▌ | 49220/57600 [8:39:27<1:24:01, 1.66it/s] 85%|████████▌ | 49221/57600 [8:39:28<1:25:11, 1.64it/s] 85%|████████▌ | 49222/57600 [8:39:29<1:26:43, 1.61it/s] 85%|████████▌ | 49223/57600 [8:39:29<1:27:15, 1.60it/s] 85%|████████▌ | 49224/57600 [8:39:30<1:24:56, 1.64it/s] 85%|████████▌ | 49225/57600 [8:39:30<1:24:45, 1.65it/s] 85%|████████▌ | 49226/57600 [8:39:31<1:26:41, 1.61it/s] 85%|████████▌ | 49227/57600 [8:39:32<1:25:24, 1.63it/s] 85%|████████▌ | 49228/57600 [8:39:32<1:25:38, 1.63it/s] 85%|████████▌ | 49229/57600 [8:39:33<1:25:20, 1.63it/s] 85%|████████▌ | 49230/57600 [8:39:34<1:23:44, 1.67it/s] 85%|████████▌ | 49231/57600 [8:39:34<1:23:29, 1.67it/s] 85%|████████▌ | 49232/57600 [8:39:35<1:25:06, 1.64it/s] 85%|████████▌ | 49233/57600 [8:39:35<1:25:24, 1.63it/s] 85%|████████▌ | 49234/57600 [8:39:36<1:28:41, 1.57it/s] 85%|████████▌ | 49235/57600 [8:39:37<1:29:07, 1.56it/s] 85%|████████▌ | 49236/57600 [8:39:37<1:27:33, 1.59it/s] 85%|████████▌ | 49237/57600 [8:39:38<1:30:26, 1.54it/s] 85%|████████▌ | 49238/57600 [8:39:39<1:29:40, 1.55it/s] 85%|████████▌ | 49239/57600 [8:39:39<1:28:55, 1.57it/s] 85%|████████▌ | 49240/57600 [8:39:40<1:27:53, 1.59it/s] {'loss': 1.0764, 'learning_rate': 2.310801393728223e-07, 'epoch': 543.49} + 85%|████████▌ | 49240/57600 [8:39:40<1:27:53, 1.59it/s] 85%|████████▌ | 49241/57600 [8:39:41<1:28:58, 1.57it/s] 85%|████████▌ | 49242/57600 [8:39:41<1:28:46, 1.57it/s] 85%|████████▌ | 49243/57600 [8:39:42<1:28:34, 1.57it/s] 85%|████████▌ | 49244/57600 [8:39:42<1:28:14, 1.58it/s] 85%|████████▌ | 49245/57600 [8:39:43<1:27:09, 1.60it/s] 85%|████████▌ | 49246/57600 [8:39:44<1:27:58, 1.58it/s] 85%|████████▌ | 49247/57600 [8:39:44<1:27:13, 1.60it/s] 86%|████████▌ | 49248/57600 [8:39:45<1:25:20, 1.63it/s] 86%|████████▌ | 49249/57600 [8:39:46<1:26:45, 1.60it/s] 86%|████████▌ | 49250/57600 [8:39:46<1:27:51, 1.58it/s] 86%|████████▌ | 49251/57600 [8:39:47<1:26:16, 1.61it/s] 86%|████████▌ | 49252/57600 [8:39:47<1:25:22, 1.63it/s] 86%|████████▌ | 49253/57600 [8:39:48<1:24:35, 1.64it/s] 86%|████████▌ | 49254/57600 [8:39:49<1:24:14, 1.65it/s] 86%|████████▌ | 49255/57600 [8:39:49<1:25:39, 1.62it/s] 86%|████████▌ | 49256/57600 [8:39:50<1:24:52, 1.64it/s] 86%|████████▌ | 49257/57600 [8:39:51<1:29:12, 1.56it/s] 86%|████████▌ | 49258/57600 [8:39:51<1:30:25, 1.54it/s] 86%|████████▌ | 49259/57600 [8:39:52<1:31:41, 1.52it/s] 86%|████████▌ | 49260/57600 [8:39:53<1:33:57, 1.48it/s] {'loss': 1.104, 'learning_rate': 2.3076655052264813e-07, 'epoch': 543.71} + 86%|████████▌ | 49260/57600 [8:39:53<1:33:57, 1.48it/s] 86%|████████▌ | 49261/57600 [8:39:53<1:32:24, 1.50it/s] 86%|████████▌ | 49262/57600 [8:39:54<1:29:11, 1.56it/s] 86%|████████▌ | 49263/57600 [8:39:54<1:26:26, 1.61it/s] 86%|████████▌ | 49264/57600 [8:39:55<1:26:22, 1.61it/s] 86%|████████▌ | 49265/57600 [8:39:56<1:28:57, 1.56it/s] 86%|████████▌ | 49266/57600 [8:39:56<1:26:55, 1.60it/s] 86%|████████▌ | 49267/57600 [8:39:57<1:26:17, 1.61it/s] 86%|████████▌ | 49268/57600 [8:39:58<1:26:20, 1.61it/s] 86%|████████▌ | 49269/57600 [8:39:58<1:25:55, 1.62it/s] 86%|████████▌ | 49270/57600 [8:39:59<1:27:50, 1.58it/s] 86%|████████▌ | 49271/57600 [8:39:59<1:29:19, 1.55it/s] 86%|████████▌ | 49272/57600 [8:40:00<1:28:04, 1.58it/s] 86%|████████▌ | 49273/57600 [8:40:01<1:28:02, 1.58it/s] 86%|████████▌ | 49274/57600 [8:40:01<1:26:52, 1.60it/s] 86%|████████▌ | 49275/57600 [8:40:02<1:25:49, 1.62it/s] 86%|████████▌ | 49276/57600 [8:40:03<1:27:46, 1.58it/s] 86%|████████▌ | 49277/57600 [8:40:03<1:29:10, 1.56it/s] 86%|████████▌ | 49278/57600 [8:40:04<1:29:52, 1.54it/s] 86%|████████▌ | 49279/57600 [8:40:05<1:29:49, 1.54it/s] 86%|████████▌ | 49280/57600 [8:40:05<1:26:54, 1.60it/s] {'loss': 1.1319, 'learning_rate': 2.3045296167247385e-07, 'epoch': 543.93} + 86%|████████▌ | 49280/57600 [8:40:05<1:26:54, 1.60it/s] 86%|████████▌ | 49281/57600 [8:40:06<1:32:09, 1.50it/s] 86%|████████▌ | 49282/57600 [8:40:07<1:31:00, 1.52it/s] 86%|████████▌ | 49283/57600 [8:40:07<1:30:55, 1.52it/s] 86%|████████▌ | 49284/57600 [8:40:08<1:29:17, 1.55it/s] 86%|████████▌ | 49285/57600 [8:40:08<1:27:04, 1.59it/s] 86%|████████▌ | 49286/57600 [8:40:09<1:27:57, 1.58it/s] 86%|████████▌ | 49287/57600 [8:40:10<1:31:04, 1.52it/s] 86%|████████▌ | 49288/57600 [8:40:10<1:28:53, 1.56it/s] 86%|████████▌ | 49289/57600 [8:40:11<1:28:02, 1.57it/s] 86%|████████▌ | 49290/57600 [8:40:12<1:29:40, 1.54it/s] 86%|████████▌ | 49291/57600 [8:40:12<1:27:50, 1.58it/s] 86%|████████▌ | 49292/57600 [8:40:13<1:27:34, 1.58it/s] 86%|████████▌ | 49293/57600 [8:40:14<1:29:06, 1.55it/s] 86%|████████▌ | 49294/57600 [8:40:14<1:25:24, 1.62it/s] 86%|████████▌ | 49295/57600 [8:40:15<1:24:00, 1.65it/s] 86%|████████▌ | 49296/57600 [8:40:15<1:22:34, 1.68it/s] 86%|████████▌ | 49297/57600 [8:40:16<1:25:03, 1.63it/s] 86%|████████▌ | 49298/57600 [8:40:17<1:24:57, 1.63it/s] 86%|████████▌ | 49299/57600 [8:40:17<1:25:41, 1.61it/s] 86%|████████▌ | 49300/57600 [8:40:18<1:25:30, 1.62it/s] {'loss': 1.1423, 'learning_rate': 2.3013937282229968e-07, 'epoch': 544.15} + 86%|████████▌ | 49300/57600 [8:40:18<1:25:30, 1.62it/s] 86%|████████▌ | 49301/57600 [8:40:18<1:26:47, 1.59it/s] 86%|████████▌ | 49302/57600 [8:40:19<1:26:43, 1.59it/s] 86%|████████▌ | 49303/57600 [8:40:20<1:25:57, 1.61it/s] 86%|████████▌ | 49304/57600 [8:40:20<1:27:37, 1.58it/s] 86%|████████▌ | 49305/57600 [8:40:21<1:29:53, 1.54it/s] 86%|████████▌ | 49306/57600 [8:40:22<1:28:39, 1.56it/s] 86%|████████▌ | 49307/57600 [8:40:22<1:29:32, 1.54it/s] 86%|████████▌ | 49308/57600 [8:40:23<1:27:26, 1.58it/s] 86%|████████▌ | 49309/57600 [8:40:23<1:25:17, 1.62it/s] 86%|████████▌ | 49310/57600 [8:40:24<1:23:50, 1.65it/s] 86%|████████▌ | 49311/57600 [8:40:25<1:22:55, 1.67it/s] 86%|████████▌ | 49312/57600 [8:40:25<1:22:16, 1.68it/s] 86%|████████▌ | 49313/57600 [8:40:26<1:22:59, 1.66it/s] 86%|████████▌ | 49314/57600 [8:40:26<1:23:01, 1.66it/s] 86%|████████▌ | 49315/57600 [8:40:27<1:24:53, 1.63it/s] 86%|████████▌ | 49316/57600 [8:40:28<1:26:26, 1.60it/s] 86%|████████▌ | 49317/57600 [8:40:28<1:26:17, 1.60it/s] 86%|████████▌ | 49318/57600 [8:40:29<1:24:57, 1.62it/s] 86%|████████▌ | 49319/57600 [8:40:30<1:29:52, 1.54it/s] 86%|████████▌ | 49320/57600 [8:40:30<1:29:21, 1.54it/s] {'loss': 1.1174, 'learning_rate': 2.298257839721254e-07, 'epoch': 544.37} + 86%|████████▌ | 49320/57600 [8:40:30<1:29:21, 1.54it/s] 86%|████████▌ | 49321/57600 [8:40:31<1:28:48, 1.55it/s] 86%|████████▌ | 49322/57600 [8:40:32<1:30:59, 1.52it/s] 86%|████████▌ | 49323/57600 [8:40:32<1:30:42, 1.52it/s] 86%|████████▌ | 49324/57600 [8:40:33<1:29:20, 1.54it/s] 86%|████████▌ | 49325/57600 [8:40:34<1:27:29, 1.58it/s] 86%|████████▌ | 49326/57600 [8:40:34<1:25:34, 1.61it/s] 86%|████████▌ | 49327/57600 [8:40:35<1:26:04, 1.60it/s] 86%|████████▌ | 49328/57600 [8:40:35<1:28:17, 1.56it/s] 86%|████████▌ | 49329/57600 [8:40:36<1:27:14, 1.58it/s] 86%|████████▌ | 49330/57600 [8:40:37<1:29:10, 1.55it/s] 86%|████████▌ | 49331/57600 [8:40:37<1:29:35, 1.54it/s] 86%|████████▌ | 49332/57600 [8:40:38<1:29:40, 1.54it/s] 86%|████████▌ | 49333/57600 [8:40:39<1:28:14, 1.56it/s] 86%|████████▌ | 49334/57600 [8:40:39<1:26:51, 1.59it/s] 86%|████████▌ | 49335/57600 [8:40:40<1:28:37, 1.55it/s] 86%|████████▌ | 49336/57600 [8:40:41<1:27:02, 1.58it/s] 86%|████████▌ | 49337/57600 [8:40:41<1:29:20, 1.54it/s] 86%|████████▌ | 49338/57600 [8:40:42<1:29:32, 1.54it/s] 86%|████████▌ | 49339/57600 [8:40:42<1:27:29, 1.57it/s] 86%|████████▌ | 49340/57600 [8:40:43<1:28:07, 1.56it/s] {'loss': 1.0878, 'learning_rate': 2.2951219512195121e-07, 'epoch': 544.59} + 86%|████████▌ | 49340/57600 [8:40:43<1:28:07, 1.56it/s] 86%|████████▌ | 49341/57600 [8:40:44<1:24:42, 1.62it/s] 86%|████████▌ | 49342/57600 [8:40:44<1:26:58, 1.58it/s] 86%|████████▌ | 49343/57600 [8:40:45<1:28:02, 1.56it/s] 86%|████████▌ | 49344/57600 [8:40:46<1:26:51, 1.58it/s] 86%|████████▌ | 49345/57600 [8:40:46<1:26:40, 1.59it/s] 86%|████████▌ | 49346/57600 [8:40:47<1:31:01, 1.51it/s] 86%|████████▌ | 49347/57600 [8:40:48<1:26:52, 1.58it/s] 86%|████████▌ | 49348/57600 [8:40:48<1:27:32, 1.57it/s] 86%|████████▌ | 49349/57600 [8:40:49<1:25:49, 1.60it/s] 86%|████████▌ | 49350/57600 [8:40:49<1:26:27, 1.59it/s] 86%|████████▌ | 49351/57600 [8:40:50<1:25:51, 1.60it/s] 86%|████████▌ | 49352/57600 [8:40:51<1:28:01, 1.56it/s] 86%|████████▌ | 49353/57600 [8:40:51<1:28:42, 1.55it/s] 86%|████████▌ | 49354/57600 [8:40:52<1:30:24, 1.52it/s] 86%|████████▌ | 49355/57600 [8:40:53<1:32:53, 1.48it/s] 86%|████████▌ | 49356/57600 [8:40:53<1:29:55, 1.53it/s] 86%|████████▌ | 49357/57600 [8:40:54<1:26:29, 1.59it/s] 86%|████████▌ | 49358/57600 [8:40:55<1:27:28, 1.57it/s] 86%|████████▌ | 49359/57600 [8:40:55<1:26:53, 1.58it/s] 86%|████████▌ | 49360/57600 [8:40:56<1:25:04, 1.61it/s] {'loss': 1.1226, 'learning_rate': 2.2919860627177694e-07, 'epoch': 544.81} + 86%|████████▌ | 49360/57600 [8:40:56<1:25:04, 1.61it/s] 86%|████████▌ | 49361/57600 [8:40:56<1:24:17, 1.63it/s] 86%|████████▌ | 49362/57600 [8:40:57<1:23:08, 1.65it/s] 86%|████████▌ | 49363/57600 [8:40:58<1:24:24, 1.63it/s] 86%|████████▌ | 49364/57600 [8:40:58<1:24:03, 1.63it/s] 86%|████████▌ | 49365/57600 [8:40:59<1:25:18, 1.61it/s] 86%|████████▌ | 49366/57600 [8:41:00<1:25:11, 1.61it/s] 86%|████████▌ | 49367/57600 [8:41:00<1:24:12, 1.63it/s] 86%|████████▌ | 49368/57600 [8:41:01<1:24:01, 1.63it/s] 86%|████████▌ | 49369/57600 [8:41:01<1:25:18, 1.61it/s] 86%|████████▌ | 49370/57600 [8:41:02<1:24:07, 1.63it/s] 86%|████████▌ | 49371/57600 [8:41:03<1:24:23, 1.63it/s] 86%|████████▌ | 49372/57600 [8:41:03<1:22:26, 1.66it/s] 86%|████████▌ | 49373/57600 [8:41:04<1:23:40, 1.64it/s] 86%|████████▌ | 49374/57600 [8:41:04<1:24:20, 1.63it/s] 86%|████████▌ | 49375/57600 [8:41:05<1:24:35, 1.62it/s] 86%|████████▌ | 49376/57600 [8:41:06<1:23:59, 1.63it/s] 86%|████████▌ | 49377/57600 [8:41:06<1:28:38, 1.55it/s] 86%|████████▌ | 49378/57600 [8:41:07<1:29:43, 1.53it/s] 86%|████████▌ | 49379/57600 [8:41:08<1:27:34, 1.56it/s] 86%|████████▌ | 49380/57600 [8:41:08<1:29:42, 1.53it/s] {'loss': 1.1167, 'learning_rate': 2.2888501742160277e-07, 'epoch': 545.03} + 86%|████████▌ | 49380/57600 [8:41:08<1:29:42, 1.53it/s] 86%|████████▌ | 49381/57600 [8:41:09<1:28:50, 1.54it/s] 86%|████████▌ | 49382/57600 [8:41:10<1:34:20, 1.45it/s] 86%|████████▌ | 49383/57600 [8:41:10<1:29:53, 1.52it/s] 86%|████████▌ | 49384/57600 [8:41:11<1:31:51, 1.49it/s] 86%|████████▌ | 49385/57600 [8:41:12<1:31:40, 1.49it/s] 86%|████████▌ | 49386/57600 [8:41:12<1:36:00, 1.43it/s] 86%|████████▌ | 49387/57600 [8:41:13<1:35:10, 1.44it/s] 86%|████████▌ | 49388/57600 [8:41:14<1:32:13, 1.48it/s] 86%|████████▌ | 49389/57600 [8:41:14<1:29:24, 1.53it/s] 86%|████████▌ | 49390/57600 [8:41:15<1:26:50, 1.58it/s] 86%|████████▌ | 49391/57600 [8:41:16<1:26:18, 1.59it/s] 86%|████████▌ | 49392/57600 [8:41:16<1:27:38, 1.56it/s] 86%|████████▌ | 49393/57600 [8:41:17<1:25:53, 1.59it/s] 86%|████████▌ | 49394/57600 [8:41:18<1:26:59, 1.57it/s] 86%|████████▌ | 49395/57600 [8:41:18<1:29:13, 1.53it/s] 86%|████████▌ | 49396/57600 [8:41:19<1:28:03, 1.55it/s] 86%|████████▌ | 49397/57600 [8:41:19<1:25:52, 1.59it/s] 86%|████████▌ | 49398/57600 [8:41:20<1:23:55, 1.63it/s] 86%|████████▌ | 49399/57600 [8:41:21<1:23:49, 1.63it/s] 86%|████████▌ | 49400/57600 [8:41:21<1:22:37, 1.65it/s] {'loss': 1.074, 'learning_rate': 2.285714285714286e-07, 'epoch': 545.25} + 86%|████████▌ | 49400/57600 [8:41:21<1:22:37, 1.65it/s] 86%|████████▌ | 49401/57600 [8:41:22<1:24:00, 1.63it/s] 86%|████████▌ | 49402/57600 [8:41:22<1:22:50, 1.65it/s] 86%|████████▌ | 49403/57600 [8:41:23<1:24:55, 1.61it/s] 86%|████████▌ | 49404/57600 [8:41:24<1:26:19, 1.58it/s] 86%|████████▌ | 49405/57600 [8:41:24<1:27:19, 1.56it/s] 86%|████████▌ | 49406/57600 [8:41:25<1:25:42, 1.59it/s] 86%|████████▌ | 49407/57600 [8:41:26<1:28:19, 1.55it/s] 86%|████████▌ | 49408/57600 [8:41:26<1:27:20, 1.56it/s] 86%|████████▌ | 49409/57600 [8:41:27<1:26:53, 1.57it/s] 86%|████████▌ | 49410/57600 [8:41:28<1:25:29, 1.60it/s] 86%|████████▌ | 49411/57600 [8:41:28<1:25:41, 1.59it/s] 86%|████████▌ | 49412/57600 [8:41:29<1:26:10, 1.58it/s] 86%|████████▌ | 49413/57600 [8:41:29<1:25:34, 1.59it/s] 86%|████████▌ | 49414/57600 [8:41:30<1:25:28, 1.60it/s] 86%|████████▌ | 49415/57600 [8:41:31<1:23:22, 1.64it/s] 86%|████████▌ | 49416/57600 [8:41:31<1:24:31, 1.61it/s] 86%|████████▌ | 49417/57600 [8:41:32<1:22:11, 1.66it/s] 86%|████████▌ | 49418/57600 [8:41:32<1:21:56, 1.66it/s] 86%|████████▌ | 49419/57600 [8:41:33<1:25:57, 1.59it/s] 86%|████████▌ | 49420/57600 [8:41:34<1:25:57, 1.59it/s] {'loss': 1.1233, 'learning_rate': 2.2825783972125435e-07, 'epoch': 545.47} + 86%|████████▌ | 49420/57600 [8:41:34<1:25:57, 1.59it/s] 86%|████████▌ | 49421/57600 [8:41:34<1:25:25, 1.60it/s] 86%|████████▌ | 49422/57600 [8:41:35<1:22:34, 1.65it/s] 86%|████████▌ | 49423/57600 [8:41:36<1:23:53, 1.62it/s] 86%|████████▌ | 49424/57600 [8:41:36<1:29:06, 1.53it/s] 86%|████████▌ | 49425/57600 [8:41:37<1:28:06, 1.55it/s] 86%|████████▌ | 49426/57600 [8:41:38<1:27:31, 1.56it/s] 86%|████████▌ | 49427/57600 [8:41:38<1:29:43, 1.52it/s] 86%|████████▌ | 49428/57600 [8:41:39<1:26:45, 1.57it/s] 86%|████████▌ | 49429/57600 [8:41:40<1:26:27, 1.58it/s] 86%|████████▌ | 49430/57600 [8:41:40<1:23:48, 1.62it/s] 86%|████████▌ | 49431/57600 [8:41:41<1:23:32, 1.63it/s] 86%|████████▌ | 49432/57600 [8:41:41<1:23:36, 1.63it/s] 86%|████████▌ | 49433/57600 [8:41:42<1:21:51, 1.66it/s] 86%|████████▌ | 49434/57600 [8:41:43<1:23:01, 1.64it/s] 86%|████████▌ | 49435/57600 [8:41:43<1:22:03, 1.66it/s] 86%|████████▌ | 49436/57600 [8:41:44<1:21:02, 1.68it/s] 86%|████████▌ | 49437/57600 [8:41:44<1:24:16, 1.61it/s] 86%|████████▌ | 49438/57600 [8:41:45<1:23:44, 1.62it/s] 86%|████████▌ | 49439/57600 [8:41:46<1:24:25, 1.61it/s] 86%|████████��� | 49440/57600 [8:41:46<1:23:58, 1.62it/s] {'loss': 1.1342, 'learning_rate': 2.2794425087108016e-07, 'epoch': 545.7} + 86%|████████▌ | 49440/57600 [8:41:46<1:23:58, 1.62it/s] 86%|████████▌ | 49441/57600 [8:41:47<1:22:22, 1.65it/s] 86%|████████▌ | 49442/57600 [8:41:47<1:24:42, 1.61it/s] 86%|████████▌ | 49443/57600 [8:41:48<1:26:42, 1.57it/s] 86%|████████▌ | 49444/57600 [8:41:49<1:26:45, 1.57it/s] 86%|████████▌ | 49445/57600 [8:41:49<1:24:22, 1.61it/s] 86%|████████▌ | 49446/57600 [8:41:50<1:25:03, 1.60it/s] 86%|████████▌ | 49447/57600 [8:41:51<1:21:46, 1.66it/s] 86%|████████▌ | 49448/57600 [8:41:51<1:25:14, 1.59it/s] 86%|████████▌ | 49449/57600 [8:41:52<1:25:33, 1.59it/s] 86%|████████▌ | 49450/57600 [8:41:52<1:25:11, 1.59it/s] 86%|████████▌ | 49451/57600 [8:41:53<1:24:10, 1.61it/s] 86%|████████▌ | 49452/57600 [8:41:54<1:24:49, 1.60it/s] 86%|████████▌ | 49453/57600 [8:41:54<1:24:32, 1.61it/s] 86%|████████▌ | 49454/57600 [8:41:55<1:24:18, 1.61it/s] 86%|████████▌ | 49455/57600 [8:41:56<1:22:40, 1.64it/s] 86%|████████▌ | 49456/57600 [8:41:56<1:23:54, 1.62it/s] 86%|████████▌ | 49457/57600 [8:41:57<1:27:33, 1.55it/s] 86%|████████▌ | 49458/57600 [8:41:58<1:29:20, 1.52it/s] 86%|████████▌ | 49459/57600 [8:41:58<1:27:01, 1.56it/s] 86%|████████▌ | 49460/57600 [8:41:59<1:26:10, 1.57it/s] {'loss': 1.1092, 'learning_rate': 2.2763066202090588e-07, 'epoch': 545.92} + 86%|████████▌ | 49460/57600 [8:41:59<1:26:10, 1.57it/s] 86%|████████▌ | 49461/57600 [8:41:59<1:27:01, 1.56it/s] 86%|████████▌ | 49462/57600 [8:42:00<1:26:31, 1.57it/s] 86%|████████▌ | 49463/57600 [8:42:01<1:24:16, 1.61it/s] 86%|████████▌ | 49464/57600 [8:42:01<1:22:42, 1.64it/s] 86%|████████▌ | 49465/57600 [8:42:02<1:20:47, 1.68it/s] 86%|████████▌ | 49466/57600 [8:42:02<1:20:45, 1.68it/s] 86%|████████▌ | 49467/57600 [8:42:03<1:21:59, 1.65it/s] 86%|████████▌ | 49468/57600 [8:42:04<1:22:34, 1.64it/s] 86%|████████▌ | 49469/57600 [8:42:04<1:22:29, 1.64it/s] 86%|████████▌ | 49470/57600 [8:42:05<1:23:09, 1.63it/s] 86%|████████▌ | 49471/57600 [8:42:06<1:27:40, 1.55it/s] 86%|████████▌ | 49472/57600 [8:42:06<1:27:02, 1.56it/s] 86%|████████▌ | 49473/57600 [8:42:07<1:25:40, 1.58it/s] 86%|████████▌ | 49474/57600 [8:42:07<1:22:43, 1.64it/s] 86%|████████▌ | 49475/57600 [8:42:08<1:24:35, 1.60it/s] 86%|████████▌ | 49476/57600 [8:42:09<1:24:36, 1.60it/s] 86%|████████▌ | 49477/57600 [8:42:09<1:21:55, 1.65it/s] 86%|████████▌ | 49478/57600 [8:42:10<1:21:06, 1.67it/s] 86%|████████▌ | 49479/57600 [8:42:10<1:21:42, 1.66it/s] 86%|████████▌ | 49480/57600 [8:42:11<1:21:44, 1.66it/s] {'loss': 1.151, 'learning_rate': 2.2731707317073172e-07, 'epoch': 546.14} + 86%|████████▌ | 49480/57600 [8:42:11<1:21:44, 1.66it/s] 86%|████████▌ | 49481/57600 [8:42:12<1:22:53, 1.63it/s] 86%|████████▌ | 49482/57600 [8:42:12<1:27:38, 1.54it/s] 86%|████████▌ | 49483/57600 [8:42:13<1:30:50, 1.49it/s] 86%|████████▌ | 49484/57600 [8:42:14<1:29:54, 1.50it/s] 86%|████████▌ | 49485/57600 [8:42:14<1:28:49, 1.52it/s] 86%|████████▌ | 49486/57600 [8:42:15<1:26:47, 1.56it/s] 86%|████████▌ | 49487/57600 [8:42:16<1:24:35, 1.60it/s] 86%|████████▌ | 49488/57600 [8:42:16<1:24:06, 1.61it/s] 86%|████████▌ | 49489/57600 [8:42:17<1:24:44, 1.60it/s] 86%|████████▌ | 49490/57600 [8:42:17<1:24:55, 1.59it/s] 86%|████████▌ | 49491/57600 [8:42:18<1:23:19, 1.62it/s] 86%|████████▌ | 49492/57600 [8:42:19<1:23:06, 1.63it/s] 86%|████████▌ | 49493/57600 [8:42:19<1:21:13, 1.66it/s] 86%|████████▌ | 49494/57600 [8:42:20<1:19:30, 1.70it/s] 86%|████████▌ | 49495/57600 [8:42:20<1:18:15, 1.73it/s] 86%|████████▌ | 49496/57600 [8:42:21<1:21:25, 1.66it/s] 86%|████████▌ | 49497/57600 [8:42:22<1:19:54, 1.69it/s] 86%|████████▌ | 49498/57600 [8:42:22<1:21:58, 1.65it/s] 86%|████████▌ | 49499/57600 [8:42:23<1:23:57, 1.61it/s] 86%|████████▌ | 49500/57600 [8:42:23<1:22:37, 1.63it/s] {'loss': 1.1341, 'learning_rate': 2.2700348432055744e-07, 'epoch': 546.36} + 86%|████████▌ | 49500/57600 [8:42:23<1:22:37, 1.63it/s] 86%|████████▌ | 49501/57600 [8:42:24<1:23:04, 1.62it/s] 86%|████████▌ | 49502/57600 [8:42:25<1:22:42, 1.63it/s] 86%|████████▌ | 49503/57600 [8:42:25<1:26:18, 1.56it/s] 86%|████████▌ | 49504/57600 [8:42:26<1:27:25, 1.54it/s] 86%|████████▌ | 49505/57600 [8:42:27<1:25:03, 1.59it/s] 86%|████████▌ | 49506/57600 [8:42:27<1:27:42, 1.54it/s] 86%|████████▌ | 49507/57600 [8:42:28<1:27:42, 1.54it/s] 86%|████████▌ | 49508/57600 [8:42:29<1:25:25, 1.58it/s] 86%|████████▌ | 49509/57600 [8:42:29<1:26:11, 1.56it/s] 86%|████████▌ | 49510/57600 [8:42:30<1:27:11, 1.55it/s] 86%|████████▌ | 49511/57600 [8:42:31<1:26:00, 1.57it/s] 86%|████████▌ | 49512/57600 [8:42:31<1:24:54, 1.59it/s] 86%|████████▌ | 49513/57600 [8:42:32<1:23:45, 1.61it/s] 86%|████████▌ | 49514/57600 [8:42:32<1:23:10, 1.62it/s] 86%|████████▌ | 49515/57600 [8:42:33<1:23:19, 1.62it/s] 86%|████████▌ | 49516/57600 [8:42:34<1:22:39, 1.63it/s] 86%|████████▌ | 49517/57600 [8:42:34<1:21:21, 1.66it/s] 86%|████████▌ | 49518/57600 [8:42:35<1:24:10, 1.60it/s] 86%|████████▌ | 49519/57600 [8:42:35<1:21:36, 1.65it/s] 86%|████████▌ | 49520/57600 [8:42:36<1:25:05, 1.58it/s] {'loss': 1.1053, 'learning_rate': 2.2668989547038327e-07, 'epoch': 546.58} + 86%|████████▌ | 49520/57600 [8:42:36<1:25:05, 1.58it/s] 86%|████████▌ | 49521/57600 [8:42:37<1:25:20, 1.58it/s] 86%|████████▌ | 49522/57600 [8:42:37<1:24:57, 1.58it/s] 86%|████████▌ | 49523/57600 [8:42:38<1:25:03, 1.58it/s] 86%|████████▌ | 49524/57600 [8:42:39<1:24:23, 1.59it/s] 86%|████████▌ | 49525/57600 [8:42:39<1:24:20, 1.60it/s] 86%|████████▌ | 49526/57600 [8:42:40<1:23:27, 1.61it/s] 86%|████████▌ | 49527/57600 [8:42:40<1:25:01, 1.58it/s] 86%|████████▌ | 49528/57600 [8:42:41<1:25:27, 1.57it/s] 86%|████████▌ | 49529/57600 [8:42:42<1:23:03, 1.62it/s] 86%|████████▌ | 49530/57600 [8:42:42<1:23:55, 1.60it/s] 86%|████████▌ | 49531/57600 [8:42:43<1:24:08, 1.60it/s] 86%|████████▌ | 49532/57600 [8:42:44<1:24:57, 1.58it/s] 86%|████████▌ | 49533/57600 [8:42:44<1:25:55, 1.56it/s] 86%|████████▌ | 49534/57600 [8:42:45<1:27:04, 1.54it/s] 86%|████████▌ | 49535/57600 [8:42:46<1:28:30, 1.52it/s] 86%|████████▌ | 49536/57600 [8:42:46<1:27:09, 1.54it/s] 86%|████████▌ | 49537/57600 [8:42:47<1:26:07, 1.56it/s] 86%|████████▌ | 49538/57600 [8:42:48<1:25:09, 1.58it/s] 86%|████████▌ | 49539/57600 [8:42:48<1:22:45, 1.62it/s] 86%|████████▌ | 49540/57600 [8:42:49<1:24:03, 1.60it/s] {'loss': 1.1347, 'learning_rate': 2.2637630662020908e-07, 'epoch': 546.8} + 86%|████████▌ | 49540/57600 [8:42:49<1:24:03, 1.60it/s] 86%|████████▌ | 49541/57600 [8:42:49<1:23:33, 1.61it/s] 86%|████████▌ | 49542/57600 [8:42:50<1:24:16, 1.59it/s] 86%|████████▌ | 49543/57600 [8:42:51<1:25:20, 1.57it/s] 86%|████████▌ | 49544/57600 [8:42:51<1:23:57, 1.60it/s] 86%|████████▌ | 49545/57600 [8:42:52<1:24:30, 1.59it/s] 86%|████████▌ | 49546/57600 [8:42:53<1:24:26, 1.59it/s] 86%|████████▌ | 49547/57600 [8:42:53<1:23:32, 1.61it/s] 86%|████████▌ | 49548/57600 [8:42:54<1:23:31, 1.61it/s] 86%|████████▌ | 49549/57600 [8:42:54<1:25:06, 1.58it/s] 86%|████████▌ | 49550/57600 [8:42:55<1:23:51, 1.60it/s] 86%|████████▌ | 49551/57600 [8:42:56<1:24:38, 1.58it/s] 86%|████████▌ | 49552/57600 [8:42:56<1:28:49, 1.51it/s] 86%|████████▌ | 49553/57600 [8:42:57<1:26:12, 1.56it/s] 86%|████████▌ | 49554/57600 [8:42:58<1:25:32, 1.57it/s] 86%|████████▌ | 49555/57600 [8:42:58<1:24:11, 1.59it/s] 86%|████████▌ | 49556/57600 [8:42:59<1:25:01, 1.58it/s] 86%|████████▌ | 49557/57600 [8:42:59<1:22:45, 1.62it/s] 86%|████████▌ | 49558/57600 [8:43:00<1:26:15, 1.55it/s] 86%|████████▌ | 49559/57600 [8:43:01<1:29:14, 1.50it/s] 86%|████████▌ | 49560/57600 [8:43:01<1:27:44, 1.53it/s] {'loss': 1.1326, 'learning_rate': 2.260627177700348e-07, 'epoch': 547.02} + 86%|████████▌ | 49560/57600 [8:43:01<1:27:44, 1.53it/s] 86%|████████▌ | 49561/57600 [8:43:02<1:25:56, 1.56it/s] 86%|████████▌ | 49562/57600 [8:43:03<1:25:04, 1.57it/s] 86%|████████▌ | 49563/57600 [8:43:03<1:24:30, 1.58it/s] 86%|████████▌ | 49564/57600 [8:43:04<1:24:41, 1.58it/s] 86%|████████▌ | 49565/57600 [8:43:05<1:24:47, 1.58it/s] 86%|████████▌ | 49566/57600 [8:43:05<1:27:26, 1.53it/s] 86%|████████▌ | 49567/57600 [8:43:06<1:25:08, 1.57it/s] 86%|████████▌ | 49568/57600 [8:43:07<1:26:35, 1.55it/s] 86%|████████▌ | 49569/57600 [8:43:07<1:25:00, 1.57it/s] 86%|████████▌ | 49570/57600 [8:43:08<1:24:35, 1.58it/s] 86%|████████▌ | 49571/57600 [8:43:08<1:25:02, 1.57it/s] 86%|████████▌ | 49572/57600 [8:43:09<1:23:10, 1.61it/s] 86%|████████▌ | 49573/57600 [8:43:10<1:24:27, 1.58it/s] 86%|████████▌ | 49574/57600 [8:43:10<1:27:50, 1.52it/s] 86%|████████▌ | 49575/57600 [8:43:11<1:26:19, 1.55it/s] 86%|████████▌ | 49576/57600 [8:43:12<1:30:55, 1.47it/s] 86%|████████▌ | 49577/57600 [8:43:12<1:27:00, 1.54it/s] 86%|████████▌ | 49578/57600 [8:43:13<1:28:03, 1.52it/s] 86%|████████▌ | 49579/57600 [8:43:14<1:24:42, 1.58it/s] 86%|████████▌ | 49580/57600 [8:43:14<1:25:22, 1.57it/s] {'loss': 1.1167, 'learning_rate': 2.2574912891986063e-07, 'epoch': 547.24} + 86%|████████▌ | 49580/57600 [8:43:14<1:25:22, 1.57it/s] 86%|████████▌ | 49581/57600 [8:43:15<1:25:14, 1.57it/s] 86%|████████▌ | 49582/57600 [8:43:15<1:23:01, 1.61it/s] 86%|████████▌ | 49583/57600 [8:43:16<1:26:10, 1.55it/s] 86%|████████▌ | 49584/57600 [8:43:17<1:24:33, 1.58it/s] 86%|████████▌ | 49585/57600 [8:43:17<1:23:56, 1.59it/s] 86%|████████▌ | 49586/57600 [8:43:18<1:26:01, 1.55it/s] 86%|████████▌ | 49587/57600 [8:43:19<1:21:46, 1.63it/s] 86%|████████▌ | 49588/57600 [8:43:19<1:21:55, 1.63it/s] 86%|████████▌ | 49589/57600 [8:43:20<1:23:48, 1.59it/s] 86%|████████▌ | 49590/57600 [8:43:20<1:21:47, 1.63it/s] 86%|████████▌ | 49591/57600 [8:43:21<1:22:59, 1.61it/s] 86%|████████▌ | 49592/57600 [8:43:22<1:22:56, 1.61it/s] 86%|████████▌ | 49593/57600 [8:43:22<1:22:39, 1.61it/s] 86%|████████▌ | 49594/57600 [8:43:23<1:21:58, 1.63it/s] 86%|████████▌ | 49595/57600 [8:43:24<1:21:10, 1.64it/s] 86%|████████▌ | 49596/57600 [8:43:24<1:23:59, 1.59it/s] 86%|████████▌ | 49597/57600 [8:43:25<1:24:23, 1.58it/s] 86%|████████▌ | 49598/57600 [8:43:25<1:23:34, 1.60it/s] 86%|████████▌ | 49599/57600 [8:43:26<1:22:46, 1.61it/s] 86%|████████▌ | 49600/57600 [8:43:27<1:23:26, 1.60it/s] {'loss': 1.1193, 'learning_rate': 2.2543554006968636e-07, 'epoch': 547.46} + 86%|████████▌ | 49600/57600 [8:43:27<1:23:26, 1.60it/s] 86%|████████▌ | 49601/57600 [8:43:27<1:25:16, 1.56it/s] 86%|████████▌ | 49602/57600 [8:43:28<1:26:16, 1.55it/s] 86%|████████▌ | 49603/57600 [8:43:29<1:23:32, 1.60it/s] 86%|████████▌ | 49604/57600 [8:43:29<1:22:37, 1.61it/s] 86%|████████▌ | 49605/57600 [8:43:30<1:24:13, 1.58it/s] 86%|████████▌ | 49606/57600 [8:43:31<1:24:30, 1.58it/s] 86%|████████▌ | 49607/57600 [8:43:31<1:22:26, 1.62it/s] 86%|████████▌ | 49608/57600 [8:43:32<1:21:27, 1.64it/s] 86%|████████▌ | 49609/57600 [8:43:32<1:20:38, 1.65it/s] 86%|████████▌ | 49610/57600 [8:43:33<1:21:36, 1.63it/s] 86%|████████▌ | 49611/57600 [8:43:34<1:23:10, 1.60it/s] 86%|████████▌ | 49612/57600 [8:43:34<1:22:59, 1.60it/s] 86%|████████▌ | 49613/57600 [8:43:35<1:22:38, 1.61it/s] 86%|████████▌ | 49614/57600 [8:43:36<1:25:40, 1.55it/s] 86%|████████▌ | 49615/57600 [8:43:36<1:23:53, 1.59it/s] 86%|████████▌ | 49616/57600 [8:43:37<1:22:22, 1.62it/s] 86%|████████▌ | 49617/57600 [8:43:37<1:23:39, 1.59it/s] 86%|████████▌ | 49618/57600 [8:43:38<1:23:10, 1.60it/s] 86%|████████▌ | 49619/57600 [8:43:39<1:26:13, 1.54it/s] 86%|████████▌ | 49620/57600 [8:43:39<1:25:39, 1.55it/s] {'loss': 1.0693, 'learning_rate': 2.251219512195122e-07, 'epoch': 547.68} + 86%|████████▌ | 49620/57600 [8:43:39<1:25:39, 1.55it/s] 86%|████████▌ | 49621/57600 [8:43:40<1:22:25, 1.61it/s] 86%|████████▌ | 49622/57600 [8:43:41<1:21:46, 1.63it/s] 86%|████████▌ | 49623/57600 [8:43:41<1:23:39, 1.59it/s] 86%|████████▌ | 49624/57600 [8:43:42<1:21:03, 1.64it/s] 86%|████████▌ | 49625/57600 [8:43:42<1:21:07, 1.64it/s] 86%|████████▌ | 49626/57600 [8:43:43<1:20:45, 1.65it/s] 86%|████████▌ | 49627/57600 [8:43:44<1:23:00, 1.60it/s] 86%|████████▌ | 49628/57600 [8:43:44<1:22:16, 1.62it/s] 86%|████████▌ | 49629/57600 [8:43:45<1:20:10, 1.66it/s] 86%|████████▌ | 49630/57600 [8:43:45<1:20:34, 1.65it/s] 86%|████████▌ | 49631/57600 [8:43:46<1:23:19, 1.59it/s] 86%|████████▌ | 49632/57600 [8:43:47<1:24:32, 1.57it/s] 86%|████████▌ | 49633/57600 [8:43:47<1:22:36, 1.61it/s] 86%|████████▌ | 49634/57600 [8:43:48<1:22:03, 1.62it/s] 86%|████████▌ | 49635/57600 [8:43:49<1:23:17, 1.59it/s] 86%|████████▌ | 49636/57600 [8:43:49<1:20:10, 1.66it/s] 86%|████████▌ | 49637/57600 [8:43:50<1:20:46, 1.64it/s] 86%|████████▌ | 49638/57600 [8:43:50<1:20:23, 1.65it/s] 86%|████████▌ | 49639/57600 [8:43:51<1:22:00, 1.62it/s] 86%|████████▌ | 49640/57600 [8:43:52<1:20:21, 1.65it/s] {'loss': 1.1476, 'learning_rate': 2.2480836236933792e-07, 'epoch': 547.9} + 86%|████████▌ | 49640/57600 [8:43:52<1:20:21, 1.65it/s] 86%|████████▌ | 49641/57600 [8:43:52<1:22:32, 1.61it/s] 86%|████████▌ | 49642/57600 [8:43:53<1:21:30, 1.63it/s] 86%|████████▌ | 49643/57600 [8:43:53<1:22:49, 1.60it/s] 86%|████████▌ | 49644/57600 [8:43:54<1:22:15, 1.61it/s] 86%|████████▌ | 49645/57600 [8:43:55<1:25:01, 1.56it/s] 86%|████████▌ | 49646/57600 [8:43:55<1:25:51, 1.54it/s] 86%|████████▌ | 49647/57600 [8:43:56<1:25:47, 1.55it/s] 86%|████████▌ | 49648/57600 [8:43:57<1:25:42, 1.55it/s] 86%|████████▌ | 49649/57600 [8:43:58<1:30:35, 1.46it/s] 86%|████████▌ | 49650/57600 [8:43:58<1:28:26, 1.50it/s] 86%|████████▌ | 49651/57600 [8:43:59<1:27:56, 1.51it/s] 86%|████████▌ | 49652/57600 [8:43:59<1:29:52, 1.47it/s] 86%|████████▌ | 49653/57600 [8:44:00<1:28:32, 1.50it/s] 86%|████████▌ | 49654/57600 [8:44:01<1:27:40, 1.51it/s] 86%|████████▌ | 49655/57600 [8:44:01<1:25:33, 1.55it/s] 86%|████████▌ | 49656/57600 [8:44:02<1:26:31, 1.53it/s] 86%|████████▌ | 49657/57600 [8:44:03<1:25:00, 1.56it/s] 86%|████████▌ | 49658/57600 [8:44:03<1:27:28, 1.51it/s] 86%|████████▌ | 49659/57600 [8:44:04<1:28:22, 1.50it/s] 86%|████████▌ | 49660/57600 [8:44:05<1:25:43, 1.54it/s] {'loss': 1.0626, 'learning_rate': 2.2449477351916375e-07, 'epoch': 548.12} + 86%|████████▌ | 49660/57600 [8:44:05<1:25:43, 1.54it/s] 86%|████████▌ | 49661/57600 [8:44:05<1:23:38, 1.58it/s] 86%|████████▌ | 49662/57600 [8:44:06<1:22:17, 1.61it/s] 86%|████████▌ | 49663/57600 [8:44:06<1:22:30, 1.60it/s] 86%|████████▌ | 49664/57600 [8:44:07<1:24:52, 1.56it/s] 86%|████████▌ | 49665/57600 [8:44:08<1:22:15, 1.61it/s] 86%|████████▌ | 49666/57600 [8:44:08<1:23:14, 1.59it/s] 86%|████████▌ | 49667/57600 [8:44:09<1:25:30, 1.55it/s] 86%|████████▌ | 49668/57600 [8:44:10<1:27:58, 1.50it/s] 86%|████████▌ | 49669/57600 [8:44:10<1:24:36, 1.56it/s] 86%|████████▌ | 49670/57600 [8:44:11<1:22:03, 1.61it/s] 86%|████████▌ | 49671/57600 [8:44:12<1:22:29, 1.60it/s] 86%|████████▌ | 49672/57600 [8:44:12<1:22:13, 1.61it/s] 86%|████████▌ | 49673/57600 [8:44:13<1:23:05, 1.59it/s] 86%|████████▌ | 49674/57600 [8:44:13<1:21:19, 1.62it/s] 86%|████████▌ | 49675/57600 [8:44:14<1:20:58, 1.63it/s] 86%|████████▌ | 49676/57600 [8:44:15<1:19:57, 1.65it/s] 86%|████████▌ | 49677/57600 [8:44:15<1:17:55, 1.69it/s] 86%|████████▌ | 49678/57600 [8:44:16<1:17:45, 1.70it/s] 86%|████████▌ | 49679/57600 [8:44:16<1:21:31, 1.62it/s] 86%|████████▋ | 49680/57600 [8:44:17<1:21:52, 1.61it/s] {'loss': 1.116, 'learning_rate': 2.2418118466898958e-07, 'epoch': 548.34} + 86%|████████▋ | 49680/57600 [8:44:17<1:21:52, 1.61it/s] 86%|████████▋ | 49681/57600 [8:44:18<1:21:19, 1.62it/s] 86%|████████▋ | 49682/57600 [8:44:18<1:22:19, 1.60it/s] 86%|████████▋ | 49683/57600 [8:44:19<1:21:31, 1.62it/s] 86%|████████▋ | 49684/57600 [8:44:20<1:20:48, 1.63it/s] 86%|████████▋ | 49685/57600 [8:44:20<1:21:04, 1.63it/s] 86%|████████▋ | 49686/57600 [8:44:21<1:21:32, 1.62it/s] 86%|████████▋ | 49687/57600 [8:44:21<1:24:45, 1.56it/s] 86%|████████▋ | 49688/57600 [8:44:22<1:23:19, 1.58it/s] 86%|████████▋ | 49689/57600 [8:44:23<1:24:23, 1.56it/s] 86%|████████▋ | 49690/57600 [8:44:23<1:22:12, 1.60it/s] 86%|████████▋ | 49691/57600 [8:44:24<1:22:21, 1.60it/s] 86%|████████▋ | 49692/57600 [8:44:25<1:22:18, 1.60it/s] 86%|████████▋ | 49693/57600 [8:44:25<1:19:47, 1.65it/s] 86%|████████▋ | 49694/57600 [8:44:26<1:22:18, 1.60it/s] 86%|████████▋ | 49695/57600 [8:44:26<1:19:52, 1.65it/s] 86%|████████▋ | 49696/57600 [8:44:27<1:24:49, 1.55it/s] 86%|████████▋ | 49697/57600 [8:44:28<1:21:59, 1.61it/s] 86%|████████▋ | 49698/57600 [8:44:28<1:20:16, 1.64it/s] 86%|████████▋ | 49699/57600 [8:44:29<1:22:22, 1.60it/s] 86%|████████▋ | 49700/57600 [8:44:30<1:20:39, 1.63it/s] {'loss': 1.1424, 'learning_rate': 2.238675958188153e-07, 'epoch': 548.57} + 86%|████████▋ | 49700/57600 [8:44:30<1:20:39, 1.63it/s] 86%|████████▋ | 49701/57600 [8:44:30<1:22:13, 1.60it/s] 86%|████████▋ | 49702/57600 [8:44:31<1:22:42, 1.59it/s] 86%|████████▋ | 49703/57600 [8:44:31<1:22:08, 1.60it/s] 86%|████████▋ | 49704/57600 [8:44:32<1:19:15, 1.66it/s] 86%|████████▋ | 49705/57600 [8:44:33<1:21:42, 1.61it/s] 86%|████████▋ | 49706/57600 [8:44:33<1:23:21, 1.58it/s] 86%|████████▋ | 49707/57600 [8:44:34<1:22:59, 1.59it/s] 86%|████████▋ | 49708/57600 [8:44:35<1:23:02, 1.58it/s] 86%|████████▋ | 49709/57600 [8:44:35<1:26:18, 1.52it/s] 86%|████████▋ | 49710/57600 [8:44:36<1:29:20, 1.47it/s] 86%|████████▋ | 49711/57600 [8:44:37<1:30:07, 1.46it/s] 86%|████████▋ | 49712/57600 [8:44:37<1:29:29, 1.47it/s] 86%|████████▋ | 49713/57600 [8:44:38<1:30:09, 1.46it/s] 86%|████████▋ | 49714/57600 [8:44:39<1:29:37, 1.47it/s] 86%|████████▋ | 49715/57600 [8:44:39<1:27:00, 1.51it/s] 86%|████████▋ | 49716/57600 [8:44:40<1:23:47, 1.57it/s] 86%|████████▋ | 49717/57600 [8:44:41<1:21:54, 1.60it/s] 86%|████████▋ | 49718/57600 [8:44:41<1:20:05, 1.64it/s] 86%|████████▋ | 49719/57600 [8:44:42<1:23:43, 1.57it/s] 86%|████████▋ | 49720/57600 [8:44:42<1:21:23, 1.61it/s] {'loss': 1.1374, 'learning_rate': 2.2355400696864114e-07, 'epoch': 548.79} + 86%|████████▋ | 49720/57600 [8:44:42<1:21:23, 1.61it/s] 86%|████████▋ | 49721/57600 [8:44:43<1:22:37, 1.59it/s] 86%|████████▋ | 49722/57600 [8:44:44<1:21:15, 1.62it/s] 86%|████████▋ | 49723/57600 [8:44:44<1:19:52, 1.64it/s] 86%|████████▋ | 49724/57600 [8:44:45<1:21:37, 1.61it/s] 86%|████████▋ | 49725/57600 [8:44:45<1:20:52, 1.62it/s] 86%|████████▋ | 49726/57600 [8:44:46<1:20:02, 1.64it/s] 86%|████████▋ | 49727/57600 [8:44:47<1:23:33, 1.57it/s] 86%|████████▋ | 49728/57600 [8:44:47<1:24:32, 1.55it/s] 86%|████████▋ | 49729/57600 [8:44:48<1:23:30, 1.57it/s] 86%|████████▋ | 49730/57600 [8:44:49<1:21:46, 1.60it/s] 86%|████████▋ | 49731/57600 [8:44:49<1:20:41, 1.63it/s] 86%|████████▋ | 49732/57600 [8:44:50<1:19:48, 1.64it/s] 86%|████████▋ | 49733/57600 [8:44:50<1:20:06, 1.64it/s] 86%|████████▋ | 49734/57600 [8:44:51<1:19:16, 1.65it/s] 86%|████████▋ | 49735/57600 [8:44:52<1:18:10, 1.68it/s] 86%|████████▋ | 49736/57600 [8:44:52<1:20:46, 1.62it/s] 86%|████████▋ | 49737/57600 [8:44:53<1:21:17, 1.61it/s] 86%|████████▋ | 49738/57600 [8:44:54<1:20:52, 1.62it/s] 86%|████████▋ | 49739/57600 [8:44:54<1:19:56, 1.64it/s] 86%|████████▋ | 49740/57600 [8:44:55<1:23:44, 1.56it/s] {'loss': 1.1343, 'learning_rate': 2.2324041811846686e-07, 'epoch': 549.01} + 86%|████████▋ | 49740/57600 [8:44:55<1:23:44, 1.56it/s] 86%|████████▋ | 49741/57600 [8:44:55<1:22:01, 1.60it/s] 86%|████████▋ | 49742/57600 [8:44:56<1:19:47, 1.64it/s] 86%|████████▋ | 49743/57600 [8:44:57<1:19:40, 1.64it/s] 86%|████████▋ | 49744/57600 [8:44:57<1:21:35, 1.60it/s] 86%|████████▋ | 49745/57600 [8:44:58<1:24:47, 1.54it/s] 86%|████████▋ | 49746/57600 [8:44:59<1:23:58, 1.56it/s] 86%|████████▋ | 49747/57600 [8:44:59<1:24:59, 1.54it/s] 86%|████████▋ | 49748/57600 [8:45:00<1:22:45, 1.58it/s] 86%|████████▋ | 49749/57600 [8:45:00<1:21:12, 1.61it/s] 86%|████████▋ | 49750/57600 [8:45:01<1:20:11, 1.63it/s] 86%|████████▋ | 49751/57600 [8:45:02<1:19:52, 1.64it/s] 86%|████████▋ | 49752/57600 [8:45:02<1:21:02, 1.61it/s] 86%|████████▋ | 49753/57600 [8:45:03<1:18:47, 1.66it/s] 86%|████████▋ | 49754/57600 [8:45:03<1:19:56, 1.64it/s] 86%|████████▋ | 49755/57600 [8:45:04<1:21:52, 1.60it/s] 86%|████████▋ | 49756/57600 [8:45:05<1:23:47, 1.56it/s] 86%|████████▋ | 49757/57600 [8:45:05<1:24:24, 1.55it/s] 86%|████████▋ | 49758/57600 [8:45:06<1:24:04, 1.55it/s] 86%|████████▋ | 49759/57600 [8:45:07<1:22:17, 1.59it/s] 86%|████████▋ | 49760/57600 [8:45:07<1:22:51, 1.58it/s] {'loss': 1.1125, 'learning_rate': 2.229268292682927e-07, 'epoch': 549.23} + 86%|████████▋ | 49760/57600 [8:45:07<1:22:51, 1.58it/s] 86%|████████▋ | 49761/57600 [8:45:08<1:27:29, 1.49it/s] 86%|████████▋ | 49762/57600 [8:45:09<1:28:38, 1.47it/s] 86%|████████▋ | 49763/57600 [8:45:09<1:27:45, 1.49it/s] 86%|████████▋ | 49764/57600 [8:45:10<1:28:46, 1.47it/s] 86%|████████▋ | 49765/57600 [8:45:11<1:26:29, 1.51it/s] 86%|████████▋ | 49766/57600 [8:45:11<1:24:26, 1.55it/s] 86%|████████▋ | 49767/57600 [8:45:12<1:21:06, 1.61it/s] 86%|████████▋ | 49768/57600 [8:45:13<1:20:25, 1.62it/s] 86%|████████▋ | 49769/57600 [8:45:13<1:19:04, 1.65it/s] 86%|████████▋ | 49770/57600 [8:45:14<1:18:25, 1.66it/s] 86%|████████▋ | 49771/57600 [8:45:14<1:18:56, 1.65it/s] 86%|████████▋ | 49772/57600 [8:45:15<1:19:47, 1.63it/s] 86%|████████▋ | 49773/57600 [8:45:16<1:17:50, 1.68it/s] 86%|████████▋ | 49774/57600 [8:45:16<1:19:12, 1.65it/s] 86%|████████▋ | 49775/57600 [8:45:17<1:20:34, 1.62it/s] 86%|████████▋ | 49776/57600 [8:45:17<1:23:14, 1.57it/s] 86%|████████▋ | 49777/57600 [8:45:18<1:24:34, 1.54it/s] 86%|████████▋ | 49778/57600 [8:45:19<1:22:28, 1.58it/s] 86%|████████▋ | 49779/57600 [8:45:19<1:25:20, 1.53it/s] 86%|████████▋ | 49780/57600 [8:45:20<1:23:30, 1.56it/s] {'loss': 1.1081, 'learning_rate': 2.2261324041811842e-07, 'epoch': 549.45} + 86%|████████▋ | 49780/57600 [8:45:20<1:23:30, 1.56it/s] 86%|████████▋ | 49781/57600 [8:45:21<1:20:59, 1.61it/s] 86%|████████▋ | 49782/57600 [8:45:21<1:23:43, 1.56it/s] 86%|████████▋ | 49783/57600 [8:45:22<1:21:40, 1.60it/s] 86%|████████▋ | 49784/57600 [8:45:23<1:21:39, 1.60it/s] 86%|████████▋ | 49785/57600 [8:45:23<1:21:01, 1.61it/s] 86%|████████▋ | 49786/57600 [8:45:24<1:19:00, 1.65it/s] 86%|████████▋ | 49787/57600 [8:45:24<1:18:21, 1.66it/s] 86%|████████▋ | 49788/57600 [8:45:25<1:17:35, 1.68it/s] 86%|████████▋ | 49789/57600 [8:45:26<1:22:07, 1.59it/s] 86%|████████▋ | 49790/57600 [8:45:26<1:20:53, 1.61it/s] 86%|████████▋ | 49791/57600 [8:45:27<1:19:37, 1.63it/s] 86%|████████▋ | 49792/57600 [8:45:27<1:19:04, 1.65it/s] 86%|████████▋ | 49793/57600 [8:45:28<1:18:50, 1.65it/s] 86%|████████▋ | 49794/57600 [8:45:29<1:18:57, 1.65it/s] 86%|████████▋ | 49795/57600 [8:45:29<1:20:54, 1.61it/s] 86%|████████▋ | 49796/57600 [8:45:30<1:20:37, 1.61it/s] 86%|████████▋ | 49797/57600 [8:45:31<1:24:25, 1.54it/s] 86%|████████▋ | 49798/57600 [8:45:31<1:23:57, 1.55it/s] 86%|████████▋ | 49799/57600 [8:45:32<1:26:17, 1.51it/s] 86%|████████▋ | 49800/57600 [8:45:33<1:27:32, 1.49it/s] {'loss': 1.1289, 'learning_rate': 2.2229965156794422e-07, 'epoch': 549.67} + 86%|████████▋ | 49800/57600 [8:45:33<1:27:32, 1.49it/s] 86%|████████▋ | 49801/57600 [8:45:33<1:24:28, 1.54it/s] 86%|████████▋ | 49802/57600 [8:45:34<1:24:05, 1.55it/s] 86%|████████▋ | 49803/57600 [8:45:35<1:24:54, 1.53it/s] 86%|████████▋ | 49804/57600 [8:45:35<1:23:44, 1.55it/s] 86%|████████▋ | 49805/57600 [8:45:36<1:24:00, 1.55it/s] 86%|████████▋ | 49806/57600 [8:45:36<1:21:44, 1.59it/s] 86%|████████▋ | 49807/57600 [8:45:37<1:19:09, 1.64it/s] 86%|████████▋ | 49808/57600 [8:45:38<1:17:34, 1.67it/s] 86%|████████▋ | 49809/57600 [8:45:38<1:17:07, 1.68it/s] 86%|████████▋ | 49810/57600 [8:45:39<1:16:57, 1.69it/s] 86%|████████▋ | 49811/57600 [8:45:39<1:16:48, 1.69it/s] 86%|████████▋ | 49812/57600 [8:45:40<1:18:08, 1.66it/s] 86%|████████▋ | 49813/57600 [8:45:41<1:19:22, 1.63it/s] 86%|████████▋ | 49814/57600 [8:45:41<1:20:22, 1.61it/s] 86%|████████▋ | 49815/57600 [8:45:42<1:19:27, 1.63it/s] 86%|████████▋ | 49816/57600 [8:45:42<1:19:11, 1.64it/s] 86%|████████▋ | 49817/57600 [8:45:43<1:23:46, 1.55it/s] 86%|████████▋ | 49818/57600 [8:45:44<1:22:19, 1.58it/s] 86%|████████▋ | 49819/57600 [8:45:44<1:22:03, 1.58it/s] 86%|████████▋ | 49820/57600 [8:45:45<1:25:05, 1.52it/s] {'loss': 1.0951, 'learning_rate': 2.2198606271777005e-07, 'epoch': 549.89} + 86%|████████▋ | 49820/57600 [8:45:45<1:25:05, 1.52it/s] 86%|████████▋ | 49821/57600 [8:45:46<1:25:33, 1.52it/s] 86%|████████▋ | 49822/57600 [8:45:46<1:23:46, 1.55it/s] 86%|████████▋ | 49823/57600 [8:45:47<1:23:41, 1.55it/s] 86%|████████▋ | 49824/57600 [8:45:48<1:23:58, 1.54it/s] 87%|████████▋ | 49825/57600 [8:45:48<1:21:44, 1.59it/s] 87%|████████▋ | 49826/57600 [8:45:49<1:23:00, 1.56it/s] 87%|████████▋ | 49827/57600 [8:45:50<1:25:31, 1.51it/s] 87%|████████▋ | 49828/57600 [8:45:50<1:25:14, 1.52it/s] 87%|████████▋ | 49829/57600 [8:45:51<1:23:07, 1.56it/s] 87%|████████▋ | 49830/57600 [8:45:52<1:25:35, 1.51it/s] 87%|████████▋ | 49831/57600 [8:45:52<1:28:32, 1.46it/s] 87%|████████▋ | 49832/57600 [8:45:53<1:23:34, 1.55it/s] 87%|████████▋ | 49833/57600 [8:45:53<1:20:21, 1.61it/s] 87%|████████▋ | 49834/57600 [8:45:54<1:18:59, 1.64it/s] 87%|████████▋ | 49835/57600 [8:45:55<1:19:47, 1.62it/s] 87%|████████▋ | 49836/57600 [8:45:55<1:20:50, 1.60it/s] 87%|████████▋ | 49837/57600 [8:45:56<1:23:02, 1.56it/s] 87%|████████▋ | 49838/57600 [8:45:57<1:23:01, 1.56it/s] 87%|████████▋ | 49839/57600 [8:45:57<1:21:50, 1.58it/s] 87%|████████▋ | 49840/57600 [8:45:58<1:20:41, 1.60it/s] {'loss': 1.1194, 'learning_rate': 2.2167247386759578e-07, 'epoch': 550.11} + 87%|████████▋ | 49840/57600 [8:45:58<1:20:41, 1.60it/s] 87%|████████▋ | 49841/57600 [8:45:58<1:20:38, 1.60it/s] 87%|████████▋ | 49842/57600 [8:45:59<1:22:49, 1.56it/s] 87%|████████▋ | 49843/57600 [8:46:00<1:23:51, 1.54it/s] 87%|████████▋ | 49844/57600 [8:46:00<1:24:54, 1.52it/s] 87%|████████▋ | 49845/57600 [8:46:01<1:23:37, 1.55it/s] 87%|████████▋ | 49846/57600 [8:46:02<1:22:15, 1.57it/s] 87%|████████▋ | 49847/57600 [8:46:02<1:22:28, 1.57it/s] 87%|████████▋ | 49848/57600 [8:46:03<1:20:54, 1.60it/s] 87%|████████▋ | 49849/57600 [8:46:04<1:19:51, 1.62it/s] 87%|████████▋ | 49850/57600 [8:46:04<1:22:52, 1.56it/s] 87%|████████▋ | 49851/57600 [8:46:05<1:22:14, 1.57it/s] 87%|████████▋ | 49852/57600 [8:46:05<1:20:12, 1.61it/s] 87%|████████▋ | 49853/57600 [8:46:06<1:21:24, 1.59it/s] 87%|████████▋ | 49854/57600 [8:46:07<1:22:53, 1.56it/s] 87%|████████▋ | 49855/57600 [8:46:07<1:23:42, 1.54it/s] 87%|████████▋ | 49856/57600 [8:46:08<1:22:50, 1.56it/s] 87%|████████▋ | 49857/57600 [8:46:09<1:21:10, 1.59it/s] 87%|████████▋ | 49858/57600 [8:46:09<1:19:03, 1.63it/s] 87%|████████▋ | 49859/57600 [8:46:10<1:20:24, 1.60it/s] 87%|████████▋ | 49860/57600 [8:46:11<1:21:49, 1.58it/s] {'loss': 1.0951, 'learning_rate': 2.213588850174216e-07, 'epoch': 550.33} + 87%|████████▋ | 49860/57600 [8:46:11<1:21:49, 1.58it/s] 87%|████████▋ | 49861/57600 [8:46:11<1:22:02, 1.57it/s] 87%|████████▋ | 49862/57600 [8:46:12<1:22:25, 1.56it/s] 87%|████████▋ | 49863/57600 [8:46:13<1:23:50, 1.54it/s] 87%|████████▋ | 49864/57600 [8:46:13<1:23:23, 1.55it/s] 87%|████████▋ | 49865/57600 [8:46:14<1:20:08, 1.61it/s] 87%|████████▋ | 49866/57600 [8:46:14<1:19:23, 1.62it/s] 87%|████████▋ | 49867/57600 [8:46:15<1:21:57, 1.57it/s] 87%|████████▋ | 49868/57600 [8:46:16<1:21:20, 1.58it/s] 87%|████████▋ | 49869/57600 [8:46:16<1:21:57, 1.57it/s] 87%|████████▋ | 49870/57600 [8:46:17<1:24:47, 1.52it/s] 87%|████████▋ | 49871/57600 [8:46:18<1:21:54, 1.57it/s] 87%|████████▋ | 49872/57600 [8:46:18<1:20:42, 1.60it/s] 87%|████████▋ | 49873/57600 [8:46:19<1:21:22, 1.58it/s] 87%|████████▋ | 49874/57600 [8:46:20<1:24:02, 1.53it/s] 87%|████████▋ | 49875/57600 [8:46:20<1:24:38, 1.52it/s] 87%|████████▋ | 49876/57600 [8:46:21<1:22:39, 1.56it/s] 87%|████████▋ | 49877/57600 [8:46:21<1:22:05, 1.57it/s] 87%|████████▋ | 49878/57600 [8:46:22<1:21:23, 1.58it/s] 87%|████████▋ | 49879/57600 [8:46:23<1:19:55, 1.61it/s] 87%|████████▋ | 49880/57600 [8:46:23<1:19:51, 1.61it/s] {'loss': 1.103, 'learning_rate': 2.2104529616724734e-07, 'epoch': 550.55} + 87%|████████▋ | 49880/57600 [8:46:23<1:19:51, 1.61it/s] 87%|████████▋ | 49881/57600 [8:46:24<1:18:47, 1.63it/s] 87%|████████▋ | 49882/57600 [8:46:24<1:16:41, 1.68it/s] 87%|████████▋ | 49883/57600 [8:46:25<1:15:35, 1.70it/s] 87%|████████▋ | 49884/57600 [8:46:26<1:17:33, 1.66it/s] 87%|████████▋ | 49885/57600 [8:46:26<1:18:31, 1.64it/s] 87%|████████▋ | 49886/57600 [8:46:27<1:18:11, 1.64it/s] 87%|████████▋ | 49887/57600 [8:46:27<1:17:56, 1.65it/s] 87%|████████▋ | 49888/57600 [8:46:28<1:18:37, 1.63it/s] 87%|████████▋ | 49889/57600 [8:46:29<1:21:01, 1.59it/s] 87%|████████▋ | 49890/57600 [8:46:29<1:23:56, 1.53it/s] 87%|████████▋ | 49891/57600 [8:46:30<1:23:16, 1.54it/s] 87%|████████▋ | 49892/57600 [8:46:31<1:23:02, 1.55it/s] 87%|████████▋ | 49893/57600 [8:46:31<1:21:56, 1.57it/s] 87%|████████▋ | 49894/57600 [8:46:32<1:19:23, 1.62it/s] 87%|████████▋ | 49895/57600 [8:46:33<1:18:30, 1.64it/s] 87%|████████▋ | 49896/57600 [8:46:33<1:18:24, 1.64it/s] 87%|████████▋ | 49897/57600 [8:46:34<1:20:39, 1.59it/s] 87%|████████▋ | 49898/57600 [8:46:34<1:19:37, 1.61it/s] 87%|████████▋ | 49899/57600 [8:46:35<1:18:09, 1.64it/s] 87%|████████▋ | 49900/57600 [8:46:36<1:20:05, 1.60it/s] {'loss': 1.1474, 'learning_rate': 2.2073170731707317e-07, 'epoch': 550.77} + 87%|████████▋ | 49900/57600 [8:46:36<1:20:05, 1.60it/s] 87%|████████▋ | 49901/57600 [8:46:36<1:21:58, 1.57it/s] 87%|████████▋ | 49902/57600 [8:46:37<1:20:41, 1.59it/s] 87%|████████▋ | 49903/57600 [8:46:38<1:19:58, 1.60it/s] 87%|████████▋ | 49904/57600 [8:46:38<1:19:37, 1.61it/s] 87%|████████▋ | 49905/57600 [8:46:39<1:18:25, 1.64it/s] 87%|████████▋ | 49906/57600 [8:46:39<1:18:56, 1.62it/s] 87%|████████▋ | 49907/57600 [8:46:40<1:20:44, 1.59it/s] 87%|████████▋ | 49908/57600 [8:46:41<1:20:25, 1.59it/s] 87%|████████▋ | 49909/57600 [8:46:41<1:24:30, 1.52it/s] 87%|████████▋ | 49910/57600 [8:46:42<1:20:29, 1.59it/s] 87%|████████▋ | 49911/57600 [8:46:43<1:20:22, 1.59it/s] 87%|████████▋ | 49912/57600 [8:46:43<1:18:41, 1.63it/s] 87%|████████▋ | 49913/57600 [8:46:44<1:17:44, 1.65it/s] 87%|████████▋ | 49914/57600 [8:46:44<1:17:16, 1.66it/s] 87%|████████▋ | 49915/57600 [8:46:45<1:19:59, 1.60it/s] 87%|████████▋ | 49916/57600 [8:46:46<1:21:35, 1.57it/s] 87%|████████▋ | 49917/57600 [8:46:46<1:22:54, 1.54it/s] 87%|████████▋ | 49918/57600 [8:46:47<1:25:42, 1.49it/s] 87%|████████▋ | 49919/57600 [8:46:48<1:24:05, 1.52it/s] 87%|████████▋ | 49920/57600 [8:46:48<1:21:16, 1.57it/s] {'loss': 1.1227, 'learning_rate': 2.20418118466899e-07, 'epoch': 550.99} + 87%|████████▋ | 49920/57600 [8:46:48<1:21:16, 1.57it/s] 87%|████████▋ | 49921/57600 [8:46:49<1:23:23, 1.53it/s] 87%|████████▋ | 49922/57600 [8:46:50<1:22:38, 1.55it/s] 87%|████████▋ | 49923/57600 [8:46:50<1:19:40, 1.61it/s] 87%|████████▋ | 49924/57600 [8:46:51<1:18:48, 1.62it/s] 87%|████████▋ | 49925/57600 [8:46:51<1:19:49, 1.60it/s] 87%|████████▋ | 49926/57600 [8:46:52<1:18:56, 1.62it/s] 87%|████████▋ | 49927/57600 [8:46:53<1:19:33, 1.61it/s] 87%|████████▋ | 49928/57600 [8:46:53<1:18:10, 1.64it/s] 87%|████████▋ | 49929/57600 [8:46:54<1:19:05, 1.62it/s] 87%|████████▋ | 49930/57600 [8:46:54<1:19:30, 1.61it/s] 87%|████████▋ | 49931/57600 [8:46:55<1:19:42, 1.60it/s] 87%|████████▋ | 49932/57600 [8:46:56<1:21:14, 1.57it/s] 87%|████████▋ | 49933/57600 [8:46:56<1:19:26, 1.61it/s] 87%|████████▋ | 49934/57600 [8:46:57<1:18:32, 1.63it/s] 87%|████████▋ | 49935/57600 [8:46:58<1:16:23, 1.67it/s] 87%|████████▋ | 49936/57600 [8:46:58<1:15:41, 1.69it/s] 87%|████████▋ | 49937/57600 [8:46:59<1:17:40, 1.64it/s] 87%|████████▋ | 49938/57600 [8:46:59<1:18:08, 1.63it/s] 87%|████████▋ | 49939/57600 [8:47:00<1:17:09, 1.65it/s] 87%|████████▋ | 49940/57600 [8:47:01<1:17:49, 1.64it/s] {'loss': 1.1563, 'learning_rate': 2.2010452961672473e-07, 'epoch': 551.21} + 87%|████████▋ | 49940/57600 [8:47:01<1:17:49, 1.64it/s] 87%|████████▋ | 49941/57600 [8:47:01<1:18:45, 1.62it/s] 87%|████████▋ | 49942/57600 [8:47:02<1:17:03, 1.66it/s] 87%|████████▋ | 49943/57600 [8:47:02<1:17:53, 1.64it/s] 87%|████████▋ | 49944/57600 [8:47:03<1:18:36, 1.62it/s] 87%|████████▋ | 49945/57600 [8:47:04<1:17:43, 1.64it/s] 87%|████████▋ | 49946/57600 [8:47:04<1:17:59, 1.64it/s] 87%|████████▋ | 49947/57600 [8:47:05<1:19:13, 1.61it/s] 87%|████████▋ | 49948/57600 [8:47:05<1:18:21, 1.63it/s] 87%|████████▋ | 49949/57600 [8:47:06<1:21:24, 1.57it/s] 87%|████████▋ | 49950/57600 [8:47:07<1:20:05, 1.59it/s] 87%|████████▋ | 49951/57600 [8:47:07<1:18:52, 1.62it/s] 87%|████████▋ | 49952/57600 [8:47:08<1:20:16, 1.59it/s] 87%|████████▋ | 49953/57600 [8:47:09<1:22:06, 1.55it/s] 87%|████████▋ | 49954/57600 [8:47:09<1:22:26, 1.55it/s] 87%|████████▋ | 49955/57600 [8:47:10<1:22:05, 1.55it/s] 87%|████████▋ | 49956/57600 [8:47:11<1:21:18, 1.57it/s] 87%|████████▋ | 49957/57600 [8:47:11<1:21:09, 1.57it/s] 87%|████████▋ | 49958/57600 [8:47:12<1:19:50, 1.60it/s] 87%|████████▋ | 49959/57600 [8:47:12<1:19:10, 1.61it/s] 87%|████████▋ | 49960/57600 [8:47:13<1:19:02, 1.61it/s] {'loss': 1.1112, 'learning_rate': 2.1979094076655056e-07, 'epoch': 551.43} + 87%|████████▋ | 49960/57600 [8:47:13<1:19:02, 1.61it/s] 87%|████████▋ | 49961/57600 [8:47:14<1:19:49, 1.60it/s] 87%|████████▋ | 49962/57600 [8:47:14<1:20:57, 1.57it/s] 87%|████████▋ | 49963/57600 [8:47:15<1:23:29, 1.52it/s] 87%|████████▋ | 49964/57600 [8:47:16<1:24:19, 1.51it/s] 87%|████████▋ | 49965/57600 [8:47:16<1:22:36, 1.54it/s] 87%|████████▋ | 49966/57600 [8:47:17<1:25:07, 1.49it/s] 87%|████████▋ | 49967/57600 [8:47:18<1:25:30, 1.49it/s] 87%|████████▋ | 49968/57600 [8:47:18<1:23:05, 1.53it/s] 87%|████████▋ | 49969/57600 [8:47:19<1:20:39, 1.58it/s] 87%|████████▋ | 49970/57600 [8:47:20<1:20:55, 1.57it/s] 87%|████████▋ | 49971/57600 [8:47:20<1:22:29, 1.54it/s] 87%|████████▋ | 49972/57600 [8:47:21<1:24:56, 1.50it/s] 87%|████████▋ | 49973/57600 [8:47:22<1:24:55, 1.50it/s] 87%|████████▋ | 49974/57600 [8:47:22<1:24:52, 1.50it/s] 87%|████████▋ | 49975/57600 [8:47:23<1:24:41, 1.50it/s] 87%|████████▋ | 49976/57600 [8:47:24<1:22:48, 1.53it/s] 87%|████████▋ | 49977/57600 [8:47:24<1:27:42, 1.45it/s] 87%|████████▋ | 49978/57600 [8:47:25<1:24:32, 1.50it/s] 87%|████████▋ | 49979/57600 [8:47:26<1:24:52, 1.50it/s] 87%|████████▋ | 49980/57600 [8:47:26<1:28:18, 1.44it/s] {'loss': 1.0947, 'learning_rate': 2.1947735191637628e-07, 'epoch': 551.66} + 87%|████████▋ | 49980/57600 [8:47:26<1:28:18, 1.44it/s] 87%|████████▋ | 49981/57600 [8:47:27<1:24:49, 1.50it/s] 87%|████████▋ | 49982/57600 [8:47:28<1:24:57, 1.49it/s] 87%|████████▋ | 49983/57600 [8:47:28<1:25:24, 1.49it/s] 87%|████████▋ | 49984/57600 [8:47:29<1:23:27, 1.52it/s] 87%|████████▋ | 49985/57600 [8:47:30<1:22:21, 1.54it/s] 87%|████████▋ | 49986/57600 [8:47:30<1:24:04, 1.51it/s] 87%|████████▋ | 49987/57600 [8:47:31<1:24:07, 1.51it/s] 87%|████████▋ | 49988/57600 [8:47:32<1:23:27, 1.52it/s] 87%|████████▋ | 49989/57600 [8:47:32<1:23:20, 1.52it/s] 87%|████████▋ | 49990/57600 [8:47:33<1:24:08, 1.51it/s] 87%|████████▋ | 49991/57600 [8:47:34<1:21:18, 1.56it/s] 87%|████████▋ | 49992/57600 [8:47:34<1:21:53, 1.55it/s] 87%|████████▋ | 49993/57600 [8:47:35<1:20:00, 1.58it/s] 87%|████████▋ | 49994/57600 [8:47:36<1:24:12, 1.51it/s] 87%|████████▋ | 49995/57600 [8:47:36<1:25:06, 1.49it/s] 87%|████████▋ | 49996/57600 [8:47:37<1:26:24, 1.47it/s] 87%|████████▋ | 49997/57600 [8:47:38<1:28:22, 1.43it/s] 87%|████████▋ | 49998/57600 [8:47:38<1:31:23, 1.39it/s] 87%|████████▋ | 49999/57600 [8:47:39<1:29:12, 1.42it/s] 87%|████████▋ | 50000/57600 [8:47:40<1:27:27, 1.45it/s] {'loss': 1.0799, 'learning_rate': 2.1916376306620206e-07, 'epoch': 551.88} + 87%|████████▋ | 50000/57600 [8:47:40<1:27:27, 1.45it/s] 87%|████████▋ | 50001/57600 [8:47:40<1:25:12, 1.49it/s] 87%|████████▋ | 50002/57600 [8:47:41<1:25:44, 1.48it/s] 87%|████████▋ | 50003/57600 [8:47:42<1:23:41, 1.51it/s] 87%|████████▋ | 50004/57600 [8:47:42<1:21:48, 1.55it/s] 87%|████████▋ | 50005/57600 [8:47:43<1:21:11, 1.56it/s] 87%|████████▋ | 50006/57600 [8:47:44<1:21:44, 1.55it/s] 87%|████████▋ | 50007/57600 [8:47:44<1:22:08, 1.54it/s] 87%|████████▋ | 50008/57600 [8:47:45<1:21:24, 1.55it/s] 87%|████████▋ | 50009/57600 [8:47:46<1:24:59, 1.49it/s] 87%|████████▋ | 50010/57600 [8:47:46<1:26:23, 1.46it/s] 87%|████████▋ | 50011/57600 [8:47:47<1:26:55, 1.45it/s] 87%|████████▋ | 50012/57600 [8:47:48<1:27:56, 1.44it/s] 87%|████████▋ | 50013/57600 [8:47:49<1:30:05, 1.40it/s] 87%|████████▋ | 50014/57600 [8:47:49<1:26:40, 1.46it/s] 87%|████████▋ | 50015/57600 [8:47:50<1:24:06, 1.50it/s] 87%|████████▋ | 50016/57600 [8:47:50<1:23:42, 1.51it/s] 87%|████████▋ | 50017/57600 [8:47:51<1:22:09, 1.54it/s] 87%|████████▋ | 50018/57600 [8:47:52<1:25:49, 1.47it/s] 87%|████████▋ | 50019/57600 [8:47:52<1:25:36, 1.48it/s] 87%|████████▋ | 50020/57600 [8:47:53<1:25:41, 1.47it/s] {'loss': 1.0955, 'learning_rate': 2.1885017421602784e-07, 'epoch': 552.1} + 87%|████████▋ | 50020/57600 [8:47:53<1:25:41, 1.47it/s] 87%|████████▋ | 50021/57600 [8:47:54<1:23:55, 1.51it/s] 87%|████████▋ | 50022/57600 [8:47:54<1:24:33, 1.49it/s] 87%|████████▋ | 50023/57600 [8:47:55<1:25:44, 1.47it/s] 87%|████████▋ | 50024/57600 [8:47:56<1:25:17, 1.48it/s] 87%|████████▋ | 50025/57600 [8:47:56<1:22:55, 1.52it/s] 87%|████████▋ | 50026/57600 [8:47:57<1:21:12, 1.55it/s] 87%|████████▋ | 50027/57600 [8:47:58<1:21:42, 1.54it/s] 87%|████████▋ | 50028/57600 [8:47:58<1:22:26, 1.53it/s] 87%|████████▋ | 50029/57600 [8:47:59<1:20:36, 1.57it/s] 87%|████████▋ | 50030/57600 [8:48:00<1:20:18, 1.57it/s] 87%|████████▋ | 50031/57600 [8:48:00<1:20:02, 1.58it/s] 87%|████████▋ | 50032/57600 [8:48:01<1:18:50, 1.60it/s] 87%|████████▋ | 50033/57600 [8:48:02<1:20:41, 1.56it/s] 87%|████████▋ | 50034/57600 [8:48:02<1:19:48, 1.58it/s] 87%|████████▋ | 50035/57600 [8:48:03<1:21:00, 1.56it/s] 87%|████████▋ | 50036/57600 [8:48:03<1:21:08, 1.55it/s] 87%|████████▋ | 50037/57600 [8:48:04<1:23:39, 1.51it/s] 87%|████████▋ | 50038/57600 [8:48:05<1:24:52, 1.48it/s] 87%|████████▋ | 50039/57600 [8:48:06<1:24:31, 1.49it/s] 87%|████████▋ | 50040/57600 [8:48:06<1:24:40, 1.49it/s] {'loss': 1.1181, 'learning_rate': 2.1853658536585364e-07, 'epoch': 552.32} + 87%|████████▋ | 50040/57600 [8:48:06<1:24:40, 1.49it/s] 87%|████████▋ | 50041/57600 [8:48:07<1:26:31, 1.46it/s] 87%|████████▋ | 50042/57600 [8:48:08<1:24:36, 1.49it/s] 87%|████████▋ | 50043/57600 [8:48:08<1:23:47, 1.50it/s] 87%|████████▋ | 50044/57600 [8:48:09<1:21:51, 1.54it/s] 87%|████████▋ | 50045/57600 [8:48:10<1:24:28, 1.49it/s] 87%|████████▋ | 50046/57600 [8:48:10<1:25:16, 1.48it/s] 87%|████████▋ | 50047/57600 [8:48:11<1:24:43, 1.49it/s] 87%|████████▋ | 50048/57600 [8:48:12<1:23:49, 1.50it/s] 87%|████████▋ | 50049/57600 [8:48:12<1:24:03, 1.50it/s] 87%|████████▋ | 50050/57600 [8:48:13<1:21:39, 1.54it/s] 87%|████████▋ | 50051/57600 [8:48:14<1:22:13, 1.53it/s] 87%|████████▋ | 50052/57600 [8:48:14<1:23:17, 1.51it/s] 87%|████████▋ | 50053/57600 [8:48:15<1:24:50, 1.48it/s] 87%|████████▋ | 50054/57600 [8:48:16<1:24:23, 1.49it/s] 87%|████████▋ | 50055/57600 [8:48:16<1:21:42, 1.54it/s] 87%|████████▋ | 50056/57600 [8:48:17<1:22:26, 1.53it/s] 87%|████████▋ | 50057/57600 [8:48:18<1:23:34, 1.50it/s] 87%|████████▋ | 50058/57600 [8:48:18<1:22:22, 1.53it/s] 87%|████████▋ | 50059/57600 [8:48:19<1:20:35, 1.56it/s] 87%|████████▋ | 50060/57600 [8:48:19<1:19:17, 1.58it/s] {'loss': 1.1288, 'learning_rate': 2.1822299651567948e-07, 'epoch': 552.54} + 87%|████████▋ | 50060/57600 [8:48:19<1:19:17, 1.58it/s] 87%|████████▋ | 50061/57600 [8:48:20<1:22:05, 1.53it/s] 87%|████████▋ | 50062/57600 [8:48:21<1:21:43, 1.54it/s] 87%|████████▋ | 50063/57600 [8:48:21<1:19:21, 1.58it/s] 87%|████████▋ | 50064/57600 [8:48:22<1:21:41, 1.54it/s] 87%|████████▋ | 50065/57600 [8:48:23<1:21:23, 1.54it/s] 87%|████████▋ | 50066/57600 [8:48:23<1:21:40, 1.54it/s] 87%|████████▋ | 50067/57600 [8:48:24<1:19:26, 1.58it/s] 87%|████████▋ | 50068/57600 [8:48:25<1:20:21, 1.56it/s] 87%|████████▋ | 50069/57600 [8:48:25<1:19:09, 1.59it/s] 87%|████████▋ | 50070/57600 [8:48:26<1:18:41, 1.59it/s] 87%|████████▋ | 50071/57600 [8:48:26<1:18:27, 1.60it/s] 87%|████████▋ | 50072/57600 [8:48:27<1:19:21, 1.58it/s] 87%|████████▋ | 50073/57600 [8:48:28<1:18:11, 1.60it/s] 87%|████████▋ | 50074/57600 [8:48:28<1:17:36, 1.62it/s] 87%|████████▋ | 50075/57600 [8:48:29<1:16:40, 1.64it/s] 87%|████████▋ | 50076/57600 [8:48:30<1:18:55, 1.59it/s] 87%|████████▋ | 50077/57600 [8:48:30<1:18:58, 1.59it/s] 87%|████████▋ | 50078/57600 [8:48:31<1:19:03, 1.59it/s] 87%|████████▋ | 50079/57600 [8:48:31<1:18:45, 1.59it/s] 87%|████████▋ | 50080/57600 [8:48:32<1:19:35, 1.57it/s] {'loss': 1.1118, 'learning_rate': 2.179094076655052e-07, 'epoch': 552.76} + 87%|████████▋ | 50080/57600 [8:48:32<1:19:35, 1.57it/s] 87%|████████▋ | 50081/57600 [8:48:33<1:22:01, 1.53it/s] 87%|████████▋ | 50082/57600 [8:48:33<1:22:09, 1.53it/s] 87%|████████▋ | 50083/57600 [8:48:34<1:24:28, 1.48it/s] 87%|████████▋ | 50084/57600 [8:48:35<1:21:56, 1.53it/s] 87%|████████▋ | 50085/57600 [8:48:35<1:20:50, 1.55it/s] 87%|████████▋ | 50086/57600 [8:48:36<1:21:21, 1.54it/s] 87%|████████▋ | 50087/57600 [8:48:37<1:21:14, 1.54it/s] 87%|████████▋ | 50088/57600 [8:48:37<1:21:23, 1.54it/s] 87%|████████▋ | 50089/57600 [8:48:38<1:21:10, 1.54it/s] 87%|████████▋ | 50090/57600 [8:48:39<1:22:18, 1.52it/s] 87%|████████▋ | 50091/57600 [8:48:39<1:23:31, 1.50it/s] 87%|████████▋ | 50092/57600 [8:48:40<1:24:56, 1.47it/s] 87%|████████▋ | 50093/57600 [8:48:41<1:22:02, 1.52it/s] 87%|████████▋ | 50094/57600 [8:48:41<1:21:30, 1.53it/s] 87%|████████▋ | 50095/57600 [8:48:42<1:21:39, 1.53it/s] 87%|████████▋ | 50096/57600 [8:48:43<1:20:30, 1.55it/s] 87%|████████▋ | 50097/57600 [8:48:43<1:18:49, 1.59it/s] 87%|████████▋ | 50098/57600 [8:48:44<1:18:32, 1.59it/s] 87%|████████▋ | 50099/57600 [8:48:44<1:17:57, 1.60it/s] 87%|████████▋ | 50100/57600 [8:48:45<1:17:25, 1.61it/s] {'loss': 1.0934, 'learning_rate': 2.1759581881533103e-07, 'epoch': 552.98} + 87%|████████▋ | 50100/57600 [8:48:45<1:17:25, 1.61it/s] 87%|████████▋ | 50101/57600 [8:48:46<1:17:17, 1.62it/s] 87%|████████▋ | 50102/57600 [8:48:46<1:21:23, 1.54it/s] 87%|████████▋ | 50103/57600 [8:48:47<1:20:14, 1.56it/s] 87%|████████▋ | 50104/57600 [8:48:48<1:17:54, 1.60it/s] 87%|████████▋ | 50105/57600 [8:48:48<1:19:25, 1.57it/s] 87%|████████▋ | 50106/57600 [8:48:49<1:21:39, 1.53it/s] 87%|████████▋ | 50107/57600 [8:48:50<1:22:28, 1.51it/s] 87%|████████▋ | 50108/57600 [8:48:50<1:21:56, 1.52it/s] 87%|████████▋ | 50109/57600 [8:48:51<1:20:27, 1.55it/s] 87%|████████▋ | 50110/57600 [8:48:52<1:22:31, 1.51it/s] 87%|████████▋ | 50111/57600 [8:48:52<1:22:34, 1.51it/s] 87%|████████▋ | 50112/57600 [8:48:53<1:21:52, 1.52it/s] 87%|████████▋ | 50113/57600 [8:48:53<1:20:19, 1.55it/s] 87%|████████▋ | 50114/57600 [8:48:54<1:19:48, 1.56it/s] 87%|████████▋ | 50115/57600 [8:48:55<1:21:26, 1.53it/s] 87%|████████▋ | 50116/57600 [8:48:55<1:23:18, 1.50it/s] 87%|████████▋ | 50117/57600 [8:48:56<1:24:08, 1.48it/s] 87%|████████▋ | 50118/57600 [8:48:57<1:24:56, 1.47it/s] 87%|████████▋ | 50119/57600 [8:48:58<1:23:35, 1.49it/s] 87%|████████▋ | 50120/57600 [8:48:58<1:23:17, 1.50it/s] {'loss': 1.0997, 'learning_rate': 2.1728222996515673e-07, 'epoch': 553.2} + 87%|████████▋ | 50120/57600 [8:48:58<1:23:17, 1.50it/s] 87%|████████▋ | 50121/57600 [8:48:59<1:21:32, 1.53it/s] 87%|████████▋ | 50122/57600 [8:48:59<1:20:30, 1.55it/s] 87%|████████▋ | 50123/57600 [8:49:00<1:21:36, 1.53it/s] 87%|████████▋ | 50124/57600 [8:49:01<1:24:49, 1.47it/s] 87%|████████▋ | 50125/57600 [8:49:01<1:23:26, 1.49it/s] 87%|████████▋ | 50126/57600 [8:49:02<1:21:58, 1.52it/s] 87%|████████▋ | 50127/57600 [8:49:03<1:21:47, 1.52it/s] 87%|████████▋ | 50128/57600 [8:49:03<1:22:27, 1.51it/s] 87%|████████▋ | 50129/57600 [8:49:04<1:22:13, 1.51it/s] 87%|████████▋ | 50130/57600 [8:49:05<1:22:27, 1.51it/s] 87%|████████▋ | 50131/57600 [8:49:05<1:21:11, 1.53it/s] 87%|████████▋ | 50132/57600 [8:49:06<1:21:52, 1.52it/s] 87%|████████▋ | 50133/57600 [8:49:07<1:23:31, 1.49it/s] 87%|████████▋ | 50134/57600 [8:49:07<1:23:32, 1.49it/s] 87%|████████▋ | 50135/57600 [8:49:08<1:20:36, 1.54it/s] 87%|████████▋ | 50136/57600 [8:49:09<1:19:31, 1.56it/s] 87%|████████▋ | 50137/57600 [8:49:09<1:19:04, 1.57it/s] 87%|████████▋ | 50138/57600 [8:49:10<1:18:59, 1.57it/s] 87%|████████▋ | 50139/57600 [8:49:11<1:20:01, 1.55it/s] 87%|████████▋ | 50140/57600 [8:49:11<1:18:33, 1.58it/s] {'loss': 1.1146, 'learning_rate': 2.169686411149826e-07, 'epoch': 553.42} + 87%|████████▋ | 50140/57600 [8:49:11<1:18:33, 1.58it/s] 87%|████████▋ | 50141/57600 [8:49:12<1:21:16, 1.53it/s] 87%|████████▋ | 50142/57600 [8:49:13<1:19:56, 1.55it/s] 87%|████████▋ | 50143/57600 [8:49:13<1:20:47, 1.54it/s] 87%|████████▋ | 50144/57600 [8:49:14<1:23:04, 1.50it/s] 87%|████████▋ | 50145/57600 [8:49:15<1:22:06, 1.51it/s] 87%|████████▋ | 50146/57600 [8:49:15<1:23:20, 1.49it/s] 87%|████████▋ | 50147/57600 [8:49:16<1:24:45, 1.47it/s] 87%|████████▋ | 50148/57600 [8:49:17<1:25:34, 1.45it/s] 87%|��███████▋ | 50149/57600 [8:49:17<1:23:45, 1.48it/s] 87%|████████▋ | 50150/57600 [8:49:18<1:22:53, 1.50it/s] 87%|████████▋ | 50151/57600 [8:49:19<1:21:41, 1.52it/s] 87%|████████▋ | 50152/57600 [8:49:19<1:21:26, 1.52it/s] 87%|████████▋ | 50153/57600 [8:49:20<1:19:48, 1.56it/s] 87%|████████▋ | 50154/57600 [8:49:20<1:18:19, 1.58it/s] 87%|████████▋ | 50155/57600 [8:49:21<1:20:07, 1.55it/s] 87%|████████▋ | 50156/57600 [8:49:22<1:18:17, 1.58it/s] 87%|████████▋ | 50157/57600 [8:49:22<1:18:18, 1.58it/s] 87%|████████▋ | 50158/57600 [8:49:23<1:17:23, 1.60it/s] 87%|████████▋ | 50159/57600 [8:49:24<1:17:20, 1.60it/s] 87%|████████▋ | 50160/57600 [8:49:24<1:19:08, 1.57it/s] {'loss': 1.1399, 'learning_rate': 2.1665505226480831e-07, 'epoch': 553.64} + 87%|████████▋ | 50160/57600 [8:49:24<1:19:08, 1.57it/s] 87%|████████▋ | 50161/57600 [8:49:25<1:17:49, 1.59it/s] 87%|████████▋ | 50162/57600 [8:49:25<1:18:07, 1.59it/s] 87%|████████▋ | 50163/57600 [8:49:26<1:20:11, 1.55it/s] 87%|████████▋ | 50164/57600 [8:49:27<1:20:31, 1.54it/s] 87%|████████▋ | 50165/57600 [8:49:28<1:21:32, 1.52it/s] 87%|████████▋ | 50166/57600 [8:49:28<1:20:56, 1.53it/s] 87%|████████▋ | 50167/57600 [8:49:29<1:19:12, 1.56it/s] 87%|████████▋ | 50168/57600 [8:49:29<1:17:52, 1.59it/s] 87%|████████▋ | 50169/57600 [8:49:30<1:16:19, 1.62it/s] 87%|████████▋ | 50170/57600 [8:49:31<1:18:28, 1.58it/s] 87%|████████▋ | 50171/57600 [8:49:31<1:22:37, 1.50it/s] 87%|████████▋ | 50172/57600 [8:49:32<1:21:39, 1.52it/s] 87%|████████▋ | 50173/57600 [8:49:33<1:23:01, 1.49it/s] 87%|████████▋ | 50174/57600 [8:49:33<1:22:55, 1.49it/s] 87%|████████▋ | 50175/57600 [8:49:34<1:23:25, 1.48it/s] 87%|████████▋ | 50176/57600 [8:49:35<1:22:32, 1.50it/s] 87%|████████▋ | 50177/57600 [8:49:35<1:21:42, 1.51it/s] 87%|████████▋ | 50178/57600 [8:49:36<1:21:55, 1.51it/s] 87%|████████▋ | 50179/57600 [8:49:37<1:22:44, 1.49it/s] 87%|████████▋ | 50180/57600 [8:49:37<1:24:15, 1.47it/s] {'loss': 1.105, 'learning_rate': 2.1634146341463415e-07, 'epoch': 553.86} + 87%|████████▋ | 50180/57600 [8:49:37<1:24:15, 1.47it/s] 87%|████████▋ | 50181/57600 [8:49:38<1:20:53, 1.53it/s] 87%|████████▋ | 50182/57600 [8:49:39<1:19:54, 1.55it/s] 87%|████████▋ | 50183/57600 [8:49:39<1:19:27, 1.56it/s] 87%|████████▋ | 50184/57600 [8:49:40<1:17:14, 1.60it/s] 87%|████████▋ | 50185/57600 [8:49:40<1:17:37, 1.59it/s] 87%|████████▋ | 50186/57600 [8:49:41<1:17:49, 1.59it/s] 87%|████████▋ | 50187/57600 [8:49:42<1:16:52, 1.61it/s] 87%|████████▋ | 50188/57600 [8:49:42<1:16:06, 1.62it/s] 87%|████████▋ | 50189/57600 [8:49:43<1:19:40, 1.55it/s] 87%|████████▋ | 50190/57600 [8:49:44<1:21:04, 1.52it/s] 87%|████████▋ | 50191/57600 [8:49:44<1:20:43, 1.53it/s] 87%|████████▋ | 50192/57600 [8:49:45<1:20:00, 1.54it/s] 87%|████████▋ | 50193/57600 [8:49:46<1:23:36, 1.48it/s] 87%|████████▋ | 50194/57600 [8:49:46<1:23:51, 1.47it/s] 87%|████████▋ | 50195/57600 [8:49:47<1:21:30, 1.51it/s] 87%|████████▋ | 50196/57600 [8:49:48<1:20:10, 1.54it/s] 87%|████████▋ | 50197/57600 [8:49:48<1:19:11, 1.56it/s] 87%|████████▋ | 50198/57600 [8:49:49<1:18:30, 1.57it/s] 87%|████████▋ | 50199/57600 [8:49:50<1:17:25, 1.59it/s] 87%|████████▋ | 50200/57600 [8:49:50<1:20:33, 1.53it/s] {'loss': 1.1155, 'learning_rate': 2.1602787456445998e-07, 'epoch': 554.08} + 87%|████████▋ | 50200/57600 [8:49:50<1:20:33, 1.53it/s] 87%|████████▋ | 50201/57600 [8:49:51<1:22:33, 1.49it/s] 87%|████████▋ | 50202/57600 [8:49:52<1:21:48, 1.51it/s] 87%|████████▋ | 50203/57600 [8:49:52<1:24:17, 1.46it/s] 87%|████████▋ | 50204/57600 [8:49:53<1:25:10, 1.45it/s] 87%|████████▋ | 50205/57600 [8:49:54<1:22:52, 1.49it/s] 87%|████████▋ | 50206/57600 [8:49:54<1:21:26, 1.51it/s] 87%|████████▋ | 50207/57600 [8:49:55<1:21:03, 1.52it/s] 87%|████████▋ | 50208/57600 [8:49:56<1:18:46, 1.56it/s] 87%|████████▋ | 50209/57600 [8:49:56<1:19:22, 1.55it/s] 87%|████████▋ | 50210/57600 [8:49:57<1:17:44, 1.58it/s] 87%|████████▋ | 50211/57600 [8:49:57<1:18:28, 1.57it/s] 87%|████████▋ | 50212/57600 [8:49:58<1:17:16, 1.59it/s] 87%|████████▋ | 50213/57600 [8:49:59<1:18:16, 1.57it/s] 87%|████████▋ | 50214/57600 [8:49:59<1:18:56, 1.56it/s] 87%|████████▋ | 50215/57600 [8:50:00<1:17:45, 1.58it/s] 87%|████████▋ | 50216/57600 [8:50:01<1:21:23, 1.51it/s] 87%|████████▋ | 50217/57600 [8:50:01<1:19:51, 1.54it/s] 87%|████████▋ | 50218/57600 [8:50:02<1:19:19, 1.55it/s] 87%|████████▋ | 50219/57600 [8:50:03<1:17:21, 1.59it/s] 87%|████████▋ | 50220/57600 [8:50:03<1:16:01, 1.62it/s] {'loss': 1.1422, 'learning_rate': 2.1571428571428568e-07, 'epoch': 554.3} + 87%|████████▋ | 50220/57600 [8:50:03<1:16:01, 1.62it/s] 87%|████████▋ | 50221/57600 [8:50:04<1:16:19, 1.61it/s] 87%|████████▋ | 50222/57600 [8:50:04<1:15:57, 1.62it/s] 87%|████████▋ | 50223/57600 [8:50:05<1:18:32, 1.57it/s] 87%|████████▋ | 50224/57600 [8:50:06<1:20:19, 1.53it/s] 87%|████████▋ | 50225/57600 [8:50:06<1:19:41, 1.54it/s] 87%|████████▋ | 50226/57600 [8:50:07<1:16:42, 1.60it/s] 87%|████████▋ | 50227/57600 [8:50:08<1:15:41, 1.62it/s] 87%|████████▋ | 50228/57600 [8:50:08<1:17:37, 1.58it/s] 87%|████████▋ | 50229/57600 [8:50:09<1:18:30, 1.56it/s] 87%|████████▋ | 50230/57600 [8:50:09<1:16:04, 1.61it/s] 87%|████████▋ | 50231/57600 [8:50:10<1:15:58, 1.62it/s] 87%|████████▋ | 50232/57600 [8:50:11<1:16:01, 1.62it/s] 87%|████████▋ | 50233/57600 [8:50:11<1:16:34, 1.60it/s] 87%|████████▋ | 50234/57600 [8:50:12<1:15:45, 1.62it/s] 87%|████████▋ | 50235/57600 [8:50:13<1:14:59, 1.64it/s] 87%|████████▋ | 50236/57600 [8:50:13<1:14:47, 1.64it/s] 87%|████████▋ | 50237/57600 [8:50:14<1:16:23, 1.61it/s] 87%|████████▋ | 50238/57600 [8:50:14<1:19:16, 1.55it/s] 87%|████████▋ | 50239/57600 [8:50:15<1:20:16, 1.53it/s] 87%|████████▋ | 50240/57600 [8:50:16<1:20:41, 1.52it/s] {'loss': 1.0936, 'learning_rate': 2.1540069686411153e-07, 'epoch': 554.53} + 87%|████████▋ | 50240/57600 [8:50:16<1:20:41, 1.52it/s] 87%|████████▋ | 50241/57600 [8:50:16<1:20:34, 1.52it/s] 87%|████████▋ | 50242/57600 [8:50:17<1:20:11, 1.53it/s] 87%|████████▋ | 50243/57600 [8:50:18<1:18:33, 1.56it/s] 87%|████████▋ | 50244/57600 [8:50:18<1:17:32, 1.58it/s] 87%|████████▋ | 50245/57600 [8:50:19<1:17:00, 1.59it/s] 87%|████████▋ | 50246/57600 [8:50:20<1:17:36, 1.58it/s] 87%|████████▋ | 50247/57600 [8:50:20<1:18:48, 1.55it/s] 87%|████████▋ | 50248/57600 [8:50:21<1:17:46, 1.58it/s] 87%|████████▋ | 50249/57600 [8:50:22<1:18:25, 1.56it/s] 87%|████████▋ | 50250/57600 [8:50:22<1:20:38, 1.52it/s] 87%|████████▋ | 50251/57600 [8:50:23<1:21:02, 1.51it/s] 87%|████████▋ | 50252/57600 [8:50:24<1:19:13, 1.55it/s] 87%|████████▋ | 50253/57600 [8:50:24<1:21:06, 1.51it/s] 87%|████████▋ | 50254/57600 [8:50:25<1:21:26, 1.50it/s] 87%|████████▋ | 50255/57600 [8:50:26<1:20:56, 1.51it/s] 87%|████████▋ | 50256/57600 [8:50:26<1:21:30, 1.50it/s] 87%|████████▋ | 50257/57600 [8:50:27<1:21:18, 1.51it/s] 87%|████████▋ | 50258/57600 [8:50:28<1:20:09, 1.53it/s] 87%|████████▋ | 50259/57600 [8:50:28<1:19:26, 1.54it/s] 87%|████████▋ | 50260/57600 [8:50:29<1:19:33, 1.54it/s] {'loss': 1.103, 'learning_rate': 2.1508710801393723e-07, 'epoch': 554.75} + 87%|████████▋ | 50260/57600 [8:50:29<1:19:33, 1.54it/s] 87%|████████▋ | 50261/57600 [8:50:30<1:21:36, 1.50it/s] 87%|████████▋ | 50262/57600 [8:50:30<1:23:00, 1.47it/s] 87%|████████▋ | 50263/57600 [8:50:31<1:21:33, 1.50it/s] 87%|████████▋ | 50264/57600 [8:50:32<1:23:18, 1.47it/s] 87%|████████▋ | 50265/57600 [8:50:32<1:20:44, 1.51it/s] 87%|████████▋ | 50266/57600 [8:50:33<1:20:00, 1.53it/s] 87%|███��████▋ | 50267/57600 [8:50:33<1:18:02, 1.57it/s] 87%|████████▋ | 50268/57600 [8:50:34<1:16:46, 1.59it/s] 87%|████████▋ | 50269/57600 [8:50:35<1:15:40, 1.61it/s] 87%|████████▋ | 50270/57600 [8:50:35<1:16:14, 1.60it/s] 87%|████████▋ | 50271/57600 [8:50:36<1:16:45, 1.59it/s] 87%|████████▋ | 50272/57600 [8:50:36<1:15:00, 1.63it/s] 87%|████████▋ | 50273/57600 [8:50:37<1:17:50, 1.57it/s] 87%|████████▋ | 50274/57600 [8:50:38<1:15:31, 1.62it/s] 87%|████████▋ | 50275/57600 [8:50:38<1:14:41, 1.63it/s] 87%|████████▋ | 50276/57600 [8:50:39<1:17:26, 1.58it/s] 87%|████████▋ | 50277/57600 [8:50:40<1:17:25, 1.58it/s] 87%|████████▋ | 50278/57600 [8:50:40<1:16:04, 1.60it/s] 87%|████████▋ | 50279/57600 [8:50:41<1:16:01, 1.60it/s] 87%|████████▋ | 50280/57600 [8:50:42<1:16:54, 1.59it/s] {'loss': 1.1244, 'learning_rate': 2.147735191637631e-07, 'epoch': 554.97} + 87%|████████▋ | 50280/57600 [8:50:42<1:16:54, 1.59it/s] 87%|████████▋ | 50281/57600 [8:50:42<1:16:21, 1.60it/s] 87%|████████▋ | 50282/57600 [8:50:43<1:16:06, 1.60it/s] 87%|████████▋ | 50283/57600 [8:50:43<1:16:51, 1.59it/s] 87%|████████▋ | 50284/57600 [8:50:44<1:21:13, 1.50it/s] 87%|████████▋ | 50285/57600 [8:50:45<1:21:24, 1.50it/s] 87%|████████▋ | 50286/57600 [8:50:45<1:20:01, 1.52it/s] 87%|████████▋ | 50287/57600 [8:50:46<1:18:06, 1.56it/s] 87%|████████▋ | 50288/57600 [8:50:47<1:16:53, 1.58it/s] 87%|████████▋ | 50289/57600 [8:50:47<1:17:47, 1.57it/s] 87%|████████▋ | 50290/57600 [8:50:48<1:18:09, 1.56it/s] 87%|████████▋ | 50291/57600 [8:50:49<1:15:19, 1.62it/s] 87%|████████▋ | 50292/57600 [8:50:49<1:16:26, 1.59it/s] 87%|████████▋ | 50293/57600 [8:50:50<1:16:15, 1.60it/s] 87%|████████▋ | 50294/57600 [8:50:50<1:15:12, 1.62it/s] 87%|████████▋ | 50295/57600 [8:50:51<1:16:06, 1.60it/s] 87%|████████▋ | 50296/57600 [8:50:52<1:18:18, 1.55it/s] 87%|████████▋ | 50297/57600 [8:50:52<1:17:43, 1.57it/s] 87%|████████▋ | 50298/57600 [8:50:53<1:18:06, 1.56it/s] 87%|████████▋ | 50299/57600 [8:50:54<1:18:42, 1.55it/s] 87%|████████▋ | 50300/57600 [8:50:54<1:19:30, 1.53it/s] {'loss': 1.119, 'learning_rate': 2.144599303135888e-07, 'epoch': 555.19} + 87%|████████▋ | 50300/57600 [8:50:54<1:19:30, 1.53it/s] 87%|████████▋ | 50301/57600 [8:50:55<1:20:45, 1.51it/s] 87%|████████▋ | 50302/57600 [8:50:56<1:17:26, 1.57it/s] 87%|████████▋ | 50303/57600 [8:50:56<1:17:34, 1.57it/s] 87%|████████▋ | 50304/57600 [8:50:57<1:17:58, 1.56it/s] 87%|████████▋ | 50305/57600 [8:50:58<1:16:32, 1.59it/s] 87%|████████▋ | 50306/57600 [8:50:58<1:15:54, 1.60it/s] 87%|████████▋ | 50307/57600 [8:50:59<1:19:47, 1.52it/s] 87%|████████▋ | 50308/57600 [8:50:59<1:17:52, 1.56it/s] 87%|████████▋ | 50309/57600 [8:51:00<1:22:24, 1.47it/s] 87%|████████▋ | 50310/57600 [8:51:01<1:22:49, 1.47it/s] 87%|████████▋ | 50311/57600 [8:51:02<1:19:22, 1.53it/s] 87%|████████▋ | 50312/57600 [8:51:02<1:18:41, 1.54it/s] 87%|████████▋ | 50313/57600 [8:51:03<1:16:39, 1.58it/s] 87%|████████▋ | 50314/57600 [8:51:03<1:15:41, 1.60it/s] 87%|████████▋ | 50315/57600 [8:51:04<1:18:39, 1.54it/s] 87%|████████▋ | 50316/57600 [8:51:05<1:22:17, 1.48it/s] 87%|████████▋ | 50317/57600 [8:51:05<1:19:05, 1.53it/s] 87%|████████▋ | 50318/57600 [8:51:06<1:18:57, 1.54it/s] 87%|████████▋ | 50319/57600 [8:51:07<1:19:35, 1.52it/s] 87%|████████▋ | 50320/57600 [8:51:07<1:18:36, 1.54it/s] {'loss': 1.1021, 'learning_rate': 2.1414634146341462e-07, 'epoch': 555.41} + 87%|████████▋ | 50320/57600 [8:51:07<1:18:36, 1.54it/s] 87%|████████▋ | 50321/57600 [8:51:08<1:16:18, 1.59it/s] 87%|████████▋ | 50322/57600 [8:51:09<1:14:51, 1.62it/s] 87%|████████▋ | 50323/57600 [8:51:09<1:13:40, 1.65it/s] 87%|████████▋ | 50324/57600 [8:51:10<1:17:16, 1.57it/s] 87%|████████▋ | 50325/57600 [8:51:10<1:15:31, 1.61it/s] 87%|█████��██▋ | 50326/57600 [8:51:11<1:14:05, 1.64it/s] 87%|████████▋ | 50327/57600 [8:51:12<1:13:21, 1.65it/s] 87%|████████▋ | 50328/57600 [8:51:12<1:16:28, 1.58it/s] 87%|████████▋ | 50329/57600 [8:51:13<1:16:04, 1.59it/s] 87%|████████▋ | 50330/57600 [8:51:14<1:16:48, 1.58it/s] 87%|████████▋ | 50331/57600 [8:51:14<1:14:46, 1.62it/s] 87%|████████▋ | 50332/57600 [8:51:15<1:14:45, 1.62it/s] 87%|████████▋ | 50333/57600 [8:51:15<1:15:09, 1.61it/s] 87%|████████▋ | 50334/57600 [8:51:16<1:16:38, 1.58it/s] 87%|████████▋ | 50335/57600 [8:51:17<1:16:17, 1.59it/s] 87%|████████▋ | 50336/57600 [8:51:17<1:17:37, 1.56it/s] 87%|████████▋ | 50337/57600 [8:51:18<1:16:48, 1.58it/s] 87%|████████▋ | 50338/57600 [8:51:19<1:19:35, 1.52it/s] 87%|████████▋ | 50339/57600 [8:51:19<1:17:56, 1.55it/s] 87%|████████▋ | 50340/57600 [8:51:20<1:17:35, 1.56it/s] {'loss': 1.1232, 'learning_rate': 2.1383275261324045e-07, 'epoch': 555.63} + 87%|████████▋ | 50340/57600 [8:51:20<1:17:35, 1.56it/s] 87%|████████▋ | 50341/57600 [8:51:21<1:18:26, 1.54it/s] 87%|████████▋ | 50342/57600 [8:51:21<1:18:12, 1.55it/s] 87%|████████▋ | 50343/57600 [8:51:22<1:18:13, 1.55it/s] 87%|████████▋ | 50344/57600 [8:51:23<1:19:41, 1.52it/s] 87%|████████▋ | 50345/57600 [8:51:23<1:19:03, 1.53it/s] 87%|████████▋ | 50346/57600 [8:51:24<1:17:38, 1.56it/s] 87%|████████▋ | 50347/57600 [8:51:24<1:15:35, 1.60it/s] 87%|████████▋ | 50348/57600 [8:51:25<1:15:14, 1.61it/s] 87%|████████▋ | 50349/57600 [8:51:26<1:15:03, 1.61it/s] 87%|████████▋ | 50350/57600 [8:51:26<1:16:22, 1.58it/s] 87%|████████▋ | 50351/57600 [8:51:27<1:16:07, 1.59it/s] 87%|████████▋ | 50352/57600 [8:51:28<1:16:12, 1.59it/s] 87%|████████▋ | 50353/57600 [8:51:28<1:17:10, 1.57it/s] 87%|████████▋ | 50354/57600 [8:51:29<1:17:47, 1.55it/s] 87%|████████▋ | 50355/57600 [8:51:29<1:14:55, 1.61it/s] 87%|████████▋ | 50356/57600 [8:51:30<1:15:42, 1.59it/s] 87%|████████▋ | 50357/57600 [8:51:31<1:17:29, 1.56it/s] 87%|████████▋ | 50358/57600 [8:51:31<1:20:11, 1.51it/s] 87%|████████▋ | 50359/57600 [8:51:32<1:19:28, 1.52it/s] 87%|████████▋ | 50360/57600 [8:51:33<1:18:33, 1.54it/s] {'loss': 1.0915, 'learning_rate': 2.1351916376306618e-07, 'epoch': 555.85} + 87%|████████▋ | 50360/57600 [8:51:33<1:18:33, 1.54it/s] 87%|████████▋ | 50361/57600 [8:51:33<1:21:09, 1.49it/s] 87%|████████▋ | 50362/57600 [8:51:34<1:19:07, 1.52it/s] 87%|████████▋ | 50363/57600 [8:51:35<1:17:13, 1.56it/s] 87%|████████▋ | 50364/57600 [8:51:35<1:17:49, 1.55it/s] 87%|████████▋ | 50365/57600 [8:51:36<1:17:27, 1.56it/s] 87%|████████▋ | 50366/57600 [8:51:37<1:16:04, 1.58it/s] 87%|████████▋ | 50367/57600 [8:51:37<1:15:18, 1.60it/s] 87%|████████▋ | 50368/57600 [8:51:38<1:15:01, 1.61it/s] 87%|████████▋ | 50369/57600 [8:51:38<1:15:13, 1.60it/s] 87%|████████▋ | 50370/57600 [8:51:39<1:14:48, 1.61it/s] 87%|████████▋ | 50371/57600 [8:51:40<1:14:40, 1.61it/s] 87%|████████▋ | 50372/57600 [8:51:40<1:13:13, 1.65it/s] 87%|████████▋ | 50373/57600 [8:51:41<1:15:23, 1.60it/s] 87%|████████▋ | 50374/57600 [8:51:42<1:20:05, 1.50it/s] 87%|████████▋ | 50375/57600 [8:51:42<1:19:27, 1.52it/s] 87%|████████▋ | 50376/57600 [8:51:43<1:18:14, 1.54it/s] 87%|████████▋ | 50377/57600 [8:51:43<1:15:24, 1.60it/s] 87%|████████▋ | 50378/57600 [8:51:44<1:15:29, 1.59it/s] 87%|████████▋ | 50379/57600 [8:51:45<1:15:51, 1.59it/s] 87%|████████▋ | 50380/57600 [8:51:45<1:13:37, 1.63it/s] {'loss': 1.141, 'learning_rate': 2.13205574912892e-07, 'epoch': 556.07} + 87%|████████▋ | 50380/57600 [8:51:45<1:13:37, 1.63it/s] 87%|████████▋ | 50381/57600 [8:51:46<1:15:50, 1.59it/s] 87%|████████▋ | 50382/57600 [8:51:47<1:13:36, 1.63it/s] 87%|████████▋ | 50383/57600 [8:51:47<1:17:13, 1.56it/s] 87%|████████▋ | 50384/57600 [8:51:48<1:18:28, 1.53it/s] 87%|███████��▋ | 50385/57600 [8:51:49<1:19:25, 1.51it/s] 87%|████████▋ | 50386/57600 [8:51:49<1:18:38, 1.53it/s] 87%|████████▋ | 50387/57600 [8:51:50<1:17:01, 1.56it/s] 87%|████████▋ | 50388/57600 [8:51:50<1:15:58, 1.58it/s] 87%|████████▋ | 50389/57600 [8:51:51<1:16:32, 1.57it/s] 87%|████████▋ | 50390/57600 [8:51:52<1:18:51, 1.52it/s] 87%|████████▋ | 50391/57600 [8:51:52<1:16:32, 1.57it/s] 87%|████████▋ | 50392/57600 [8:51:53<1:15:57, 1.58it/s] 87%|████████▋ | 50393/57600 [8:51:54<1:16:12, 1.58it/s] 87%|████████▋ | 50394/57600 [8:51:54<1:17:19, 1.55it/s] 87%|████████▋ | 50395/57600 [8:51:55<1:15:13, 1.60it/s] 87%|████████▋ | 50396/57600 [8:51:56<1:14:33, 1.61it/s] 87%|████████▋ | 50397/57600 [8:51:56<1:12:56, 1.65it/s] 87%|████████▋ | 50398/57600 [8:51:57<1:13:09, 1.64it/s] 87%|████████▋ | 50399/57600 [8:51:57<1:12:22, 1.66it/s] 88%|████████▊ | 50400/57600 [8:51:58<1:12:35, 1.65it/s] {'loss': 1.1132, 'learning_rate': 2.1289198606271773e-07, 'epoch': 556.29} + 88%|████████▊ | 50400/57600 [8:51:58<1:12:35, 1.65it/s]Generation Kwargs: +{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5} + + 0%| | 0/6 [00:00> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co./docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41. +Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2} + 88%|████████▊ | 50401/57600 [8:52:33<21:37:27, 10.81s/it] 88%|████████▊ | 50402/57600 [8:52:33<15:35:38, 7.80s/it] 88%|████████▊ | 50403/57600 [8:52:34<11:21:19, 5.68s/it] 88%|████████▊ | 50404/57600 [8:52:35<8:22:28, 4.19s/it] 88%|████████▊ | 50405/57600 [8:52:36<6:21:00, 3.18s/it] 88%|████████▊ | 50406/57600 [8:52:36<4:54:36, 2.46s/it] 88%|████████▊ | 50407/57600 [8:52:37<3:54:43, 1.96s/it] 88%|████████▊ | 50408/57600 [8:52:38<3:08:53, 1.58s/it] 88%|████████▊ | 50409/57600 [8:52:39<2:37:45, 1.32s/it] 88%|████████▊ | 50410/57600 [8:52:39<2:14:15, 1.12s/it] 88%|████████▊ | 50411/57600 [8:52:40<1:58:55, 1.01it/s] 88%|████████▊ | 50412/57600 [8:52:41<1:47:06, 1.12it/s] 88%|████████▊ | 50413/57600 [8:52:41<1:37:38, 1.23it/s] 88%|████████▊ | 50414/57600 [8:52:42<1:32:59, 1.29it/s] 88%|████████▊ | 50415/57600 [8:52:43<1:28:11, 1.36it/s] 88%|████████▊ | 50416/57600 [8:52:43<1:25:40, 1.40it/s] 88%|████████▊ | 50417/57600 [8:52:44<1:24:08, 1.42it/s] 88%|████████▊ | 50418/57600 [8:52:45<1:24:48, 1.41it/s] 88%|████████▊ | 50419/57600 [8:52:45<1:23:18, 1.44it/s] 88%|████████▊ | 50420/57600 [8:52:46<1:23:53, 1.43it/s] {'loss': 1.0638, 'learning_rate': 2.1257839721254357e-07, 'epoch': 556.51} + 88%|████████▊ | 50420/57600 [8:52:46<1:23:53, 1.43it/s] 88%|████████▊ | 50421/57600 [8:52:47<1:21:43, 1.46it/s] 88%|████████▊ | 50422/57600 [8:52:47<1:21:20, 1.47it/s] 88%|████████▊ | 50423/57600 [8:52:48<1:22:05, 1.46it/s] 88%|████████▊ | 50424/57600 [8:52:49<1:20:27, 1.49it/s] 88%|████████▊ | 50425/57600 [8:52:49<1:22:17, 1.45it/s] 88%|████████▊ | 50426/57600 [8:52:50<1:23:34, 1.43it/s] 88%|████████▊ | 50427/57600 [8:52:51<1:20:42, 1.48it/s] 88%|████████▊ | 50428/57600 [8:52:51<1:19:29, 1.50it/s] 88%|████████▊ | 50429/57600 [8:52:52<1:18:24, 1.52it/s] 88%|████████▊ | 50430/57600 [8:52:53<1:19:53, 1.50it/s] 88%|████████▊ | 50431/57600 [8:52:53<1:21:20, 1.47it/s] 88%|████████▊ | 50432/57600 [8:52:54<1:23:06, 1.44it/s] 88%|████████▊ | 50433/57600 [8:52:55<1:22:46, 1.44it/s] 88%|████████▊ | 50434/57600 [8:52:55<1:22:11, 1.45it/s] 88%|████████▊ | 50435/57600 [8:52:56<1:21:27, 1.47it/s] 88%|████████▊ | 50436/57600 [8:52:57<1:19:52, 1.49it/s] 88%|████████▊ | 50437/57600 [8:52:57<1:20:11, 1.49it/s] 88%|████████▊ | 50438/57600 [8:52:58<1:23:13, 1.43it/s] 88%|████████▊ | 50439/57600 [8:52:59<1:21:01, 1.47it/s] 88%|████████▊ | 50440/57600 [8:53:00<1:19:57, 1.49it/s] {'loss': 1.0955, 'learning_rate': 2.122648083623693e-07, 'epoch': 556.73} + 88%|████████▊ | 50440/57600 [8:53:00<1:19:57, 1.49it/s] 88%|████████▊ | 50441/57600 [8:53:00<1:20:54, 1.47it/s] 88%|████████▊ | 50442/57600 [8:53:01<1:19:48, 1.49it/s] 88%|████████▊ | 50443/57600 [8:53:02<1:21:01, 1.47it/s] 88%|████████▊ | 50444/57600 [8:53:02<1:22:02, 1.45it/s] 88%|████████▊ | 50445/57600 [8:53:03<1:20:12, 1.49it/s] 88%|████████▊ | 50446/57600 [8:53:04<1:19:35, 1.50it/s] 88%|████████▊ | 50447/57600 [8:53:04<1:22:15, 1.45it/s] 88%|████████▊ | 50448/57600 [8:53:05<1:21:16, 1.47it/s] 88%|████████▊ | 50449/57600 [8:53:06<1:19:48, 1.49it/s] 88%|████████▊ | 50450/57600 [8:53:06<1:19:06, 1.51it/s] 88%|████████▊ | 50451/57600 [8:53:07<1:17:43, 1.53it/s] 88%|████████▊ | 50452/57600 [8:53:08<1:18:10, 1.52it/s] 88%|████████▊ | 50453/57600 [8:53:08<1:16:18, 1.56it/s] 88%|████████▊ | 50454/57600 [8:53:09<1:17:15, 1.54it/s] 88%|████████▊ | 50455/57600 [8:53:10<1:18:55, 1.51it/s] 88%|████████▊ | 50456/57600 [8:53:10<1:18:54, 1.51it/s] 88%|████████▊ | 50457/57600 [8:53:11<1:19:41, 1.49it/s] 88%|████████▊ | 50458/57600 [8:53:12<1:22:59, 1.43it/s] 88%|████████▊ | 50459/57600 [8:53:12<1:23:40, 1.42it/s] 88%|████████▊ | 50460/57600 [8:53:13<1:24:30, 1.41it/s] {'loss': 1.134, 'learning_rate': 2.1195121951219512e-07, 'epoch': 556.95} + 88%|████████▊ | 50460/57600 [8:53:13<1:24:30, 1.41it/s] 88%|████████▊ | 50461/57600 [8:53:14<1:22:39, 1.44it/s] 88%|████████▊ | 50462/57600 [8:53:14<1:21:29, 1.46it/s] \ No newline at end of file