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" @@ -2190,4 +2190,202 @@ Non-default generation parameters: {'max_length': 200, 'early_stopping': True, ' 69%|██████▉ | 39601/57600 [6:57:25<49:56:05, 9.99s/it] 69%|██████▉ | 39602/57600 [6:57:25<35:52:52, 7.18s/it] 69%|██████▉ | 39603/57600 [6:57:26<26:08:24, 5.23s/it] 69%|██████▉ | 39604/57600 [6:57:27<19:25:18, 3.89s/it] 69%|██████▉ | 39605/57600 [6:57:28<14:43:00, 2.94s/it] 69%|██████▉ | 39606/57600 [6:57:28<11:22:16, 2.28s/it] 69%|██████▉ | 39607/57600 [6:57:29<8:59:05, 1.80s/it] 69%|██████▉ | 39608/57600 [6:57:30<7:15:55, 1.45s/it] 69%|██████▉ | 39609/57600 [6:57:30<5:58:33, 1.20s/it] 69%|██████▉ | 39610/57600 [6:57:31<5:08:12, 1.03s/it] 69%|██████▉ | 39611/57600 [6:57:32<4:30:51, 1.11it/s] 69%|██████▉ | 39612/57600 [6:57:32<4:06:36, 1.22it/s] 69%|██████▉ | 39613/57600 [6:57:33<3:55:18, 1.27it/s] 69%|██████▉ | 39614/57600 [6:57:34<3:44:15, 1.34it/s] 69%|██████▉ | 39615/57600 [6:57:34<3:31:56, 1.41it/s] 69%|██████▉ | 39616/57600 [6:57:35<3:20:12, 1.50it/s] 69%|██████▉ | 39617/57600 [6:57:35<3:18:33, 1.51it/s] 69%|██████▉ | 39618/57600 [6:57:36<3:29:29, 1.43it/s] 69%|██████▉ | 39619/57600 [6:57:37<3:27:57, 1.44it/s] 69%|██████▉ | 39620/57600 [6:57:37<3:24:47, 1.46it/s] {'loss': 1.177, 'learning_rate': 3.819163763066202e-07, 'epoch': 437.31} 69%|██████▉ | 39620/57600 [6:57:37<3:24:47, 1.46it/s] 69%|██████▉ | 39621/57600 [6:57:38<3:24:36, 1.46it/s] 69%|██████▉ | 39622/57600 [6:57:39<3:22:43, 1.48it/s] 69%|██████▉ | 39623/57600 [6:57:39<3:19:31, 1.50it/s] 69%|██████▉ | 39624/57600 [6:57:40<3:20:09, 1.50it/s] 69%|██████▉ | 39625/57600 [6:57:41<3:15:45, 1.53it/s] 69%|██████▉ | 39626/57600 [6:57:41<3:18:17, 1.51it/s] 69%|██████▉ | 39627/57600 [6:57:42<3:19:38, 1.50it/s] 69%|██████▉ | 39628/57600 [6:57:43<3:15:06, 1.54it/s] 69%|██████▉ | 39629/57600 [6:57:43<3:18:43, 1.51it/s] 69%|██████▉ | 39630/57600 [6:57:44<3:28:24, 1.44it/s] 69%|██████▉ | 39631/57600 [6:57:45<3:28:48, 1.43it/s] 69%|██████▉ | 39632/57600 [6:57:46<3:21:09, 1.49it/s] 69%|██████▉ | 39633/57600 [6:57:46<3:26:16, 1.45it/s] 69%|██████▉ | 39634/57600 [6:57:47<3:23:51, 1.47it/s] 69%|██████▉ | 39635/57600 [6:57:48<3:18:22, 1.51it/s] 69%|██████▉ | 39636/57600 [6:57:48<3:17:37, 1.52it/s] 69%|██████▉ | 39637/57600 [6:57:49<3:20:17, 1.49it/s] 69%|██████▉ | 39638/57600 [6:57:49<3:13:29, 1.55it/s] 69%|██████▉ | 39639/57600 [6:57:50<3:16:57, 1.52it/s] 69%|██████▉ | 39640/57600 [6:57:51<3:11:48, 1.56it/s] {'loss': 1.1015, 'learning_rate': 3.8160278745644597e-07, 'epoch': 437.53} 69%|██████▉ | 39640/57600 [6:57:51<3:11:48, 1.56it/s] 69%|██████▉ | 39641/57600 [6:57:51<3:13:28, 1.55it/s] 69%|██████▉ | 39642/57600 [6:57:52<3:10:17, 1.57it/s] 69%|██████▉ | 39643/57600 [6:57:53<3:09:02, 1.58it/s] 69%|██████▉ | 39644/57600 [6:57:53<3:11:29, 1.56it/s] 69%|██████▉ | 39645/57600 [6:57:54<3:12:53, 1.55it/s] 69%|██████▉ | 39646/57600 [6:57:55<3:12:25, 1.56it/s] 69%|██████▉ | 39647/57600 [6:57:55<3:15:40, 1.53it/s] 69%|██████▉ | 39648/57600 [6:57:56<3:16:24, 1.52it/s] 69%|██████▉ | 39649/57600 [6:57:57<3:18:12, 1.51it/s] 69%|██████▉ | 39650/57600 [6:57:57<3:13:00, 1.55it/s] 69%|██████▉ | 39651/57600 [6:57:58<3:08:33, 1.59it/s] 69%|██████▉ | 39652/57600 [6:57:58<3:12:17, 1.56it/s] 69%|██████▉ | 39653/57600 [6:57:59<3:08:52, 1.58it/s] 69%|██████▉ | 39654/57600 [6:58:00<3:19:14, 1.50it/s] 69%|██████▉ | 39655/57600 [6:58:01<3:19:12, 1.50it/s] 69%|██████▉ | 39656/57600 [6:58:01<3:18:09, 1.51it/s] 69%|██████▉ | 39657/57600 [6:58:02<3:23:29, 1.47it/s] 69%|██████▉ | 39658/57600 [6:58:03<3:23:03, 1.47it/s] 69%|██████▉ | 39659/57600 [6:58:03<3:20:57, 1.49it/s] 69%|██████▉ | 39660/57600 [6:58:04<3:19:19, 1.50it/s] {'loss': 1.1403, 'learning_rate': 3.8128919860627177e-07, 'epoch': 437.75} - 69%|██████▉ | 39660/57600 [6:58:04<3:19:19, 1.50it/s] 69%|██████▉ | 39661/57600 [6:58:04<3:14:12, 1.54it/s] 69%|██████▉ | 39662/57600 [6:58:05<3:10:12, 1.57it/s] 69%|██████▉ | 39663/57600 [6:58:06<3:13:22, 1.55it/s] 69%|██████▉ | 39664/57600 [6:58:06<3:09:17, 1.58it/s] \ No newline at end of file + 69%|██████▉ | 39660/57600 [6:58:04<3:19:19, 1.50it/s] 69%|██████▉ | 39661/57600 [6:58:04<3:14:12, 1.54it/s] 69%|██████▉ | 39662/57600 [6:58:05<3:10:12, 1.57it/s] 69%|██████▉ | 39663/57600 [6:58:06<3:13:22, 1.55it/s] 69%|██████▉ | 39664/57600 [6:58:06<3:09:17, 1.58it/s] 69%|██████▉ | 39665/57600 [6:58:07<3:07:46, 1.59it/s] 69%|██████▉ | 39666/57600 [6:58:08<3:05:24, 1.61it/s] 69%|██████▉ | 39667/57600 [6:58:08<3:07:08, 1.60it/s] 69%|██████▉ | 39668/57600 [6:58:09<3:12:27, 1.55it/s] 69%|██████▉ | 39669/57600 [6:58:10<3:19:24, 1.50it/s] 69%|██████▉ | 39670/57600 [6:58:10<3:16:47, 1.52it/s] 69%|██████▉ | 39671/57600 [6:58:11<3:18:22, 1.51it/s] 69%|██████▉ | 39672/57600 [6:58:12<3:10:52, 1.57it/s] 69%|██████▉ | 39673/57600 [6:58:12<3:11:31, 1.56it/s] 69%|██████▉ | 39674/57600 [6:58:13<3:06:10, 1.60it/s] 69%|██████▉ | 39675/57600 [6:58:13<3:08:51, 1.58it/s] 69%|██████▉ | 39676/57600 [6:58:14<3:11:09, 1.56it/s] 69%|██████▉ | 39677/57600 [6:58:15<3:11:45, 1.56it/s] 69%|██████▉ | 39678/57600 [6:58:15<3:16:12, 1.52it/s] 69%|██████▉ | 39679/57600 [6:58:16<3:16:04, 1.52it/s] 69%|██████▉ | 39680/57600 [6:58:17<3:17:35, 1.51it/s] {'loss': 1.144, 'learning_rate': 3.809756097560976e-07, 'epoch': 437.97} + 69%|██████▉ | 39680/57600 [6:58:17<3:17:35, 1.51it/s] 69%|██████▉ | 39681/57600 [6:58:17<3:18:04, 1.51it/s] 69%|██████▉ | 39682/57600 [6:58:18<3:20:55, 1.49it/s]/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock. + self.pid = os.fork() + 69%|██████▉ | 39683/57600 [6:58:19<3:27:04, 1.44it/s] 69%|██████▉ | 39684/57600 [6:58:19<3:19:29, 1.50it/s] 69%|██████▉ | 39685/57600 [6:58:20<3:13:04, 1.55it/s] 69%|██████▉ | 39686/57600 [6:58:21<3:12:14, 1.55it/s] 69%|██████▉ | 39687/57600 [6:58:21<3:06:04, 1.60it/s] 69%|██████▉ | 39688/57600 [6:58:22<3:15:27, 1.53it/s] 69%|██████▉ | 39689/57600 [6:58:23<3:18:27, 1.50it/s] 69%|██████▉ | 39690/57600 [6:58:23<3:15:18, 1.53it/s] 69%|██████▉ | 39691/57600 [6:58:24<3:13:15, 1.54it/s] 69%|██████▉ | 39692/57600 [6:58:25<3:13:57, 1.54it/s] 69%|██████▉ | 39693/57600 [6:58:25<3:11:56, 1.55it/s] 69%|██████▉ | 39694/57600 [6:58:26<3:14:34, 1.53it/s] 69%|██████▉ | 39695/57600 [6:58:27<3:15:56, 1.52it/s] 69%|██████▉ | 39696/57600 [6:58:27<3:20:07, 1.49it/s] 69%|██████▉ | 39697/57600 [6:58:28<3:17:53, 1.51it/s] 69%|██████▉ | 39698/57600 [6:58:29<3:15:42, 1.52it/s] 69%|██████▉ | 39699/57600 [6:58:29<3:11:42, 1.56it/s] 69%|██████▉ | 39700/57600 [6:58:30<3:12:54, 1.55it/s] {'loss': 1.1744, 'learning_rate': 3.8066202090592333e-07, 'epoch': 438.19} + 69%|██████▉ | 39700/57600 [6:58:30<3:12:54, 1.55it/s] 69%|██████▉ | 39701/57600 [6:58:31<3:29:15, 1.43it/s] 69%|██████▉ | 39702/57600 [6:58:31<3:21:09, 1.48it/s] 69%|██████▉ | 39703/57600 [6:58:32<3:19:28, 1.50it/s] 69%|██████▉ | 39704/57600 [6:58:33<3:20:46, 1.49it/s] 69%|██████▉ | 39705/57600 [6:58:33<3:18:56, 1.50it/s] 69%|██████▉ | 39706/57600 [6:58:34<3:11:42, 1.56it/s] 69%|██████▉ | 39707/57600 [6:58:35<3:17:21, 1.51it/s] 69%|██████▉ | 39708/57600 [6:58:35<3:19:47, 1.49it/s] 69%|██████▉ | 39709/57600 [6:58:36<3:24:22, 1.46it/s] 69%|██████▉ | 39710/57600 [6:58:37<3:30:05, 1.42it/s] 69%|██████▉ | 39711/57600 [6:58:37<3:24:37, 1.46it/s] 69%|██████▉ | 39712/57600 [6:58:38<3:25:25, 1.45it/s] 69%|██████▉ | 39713/57600 [6:58:39<3:22:41, 1.47it/s] 69%|██████▉ | 39714/57600 [6:58:39<3:21:13, 1.48it/s] 69%|██████▉ | 39715/57600 [6:58:40<3:16:25, 1.52it/s] 69%|██████▉ | 39716/57600 [6:58:41<3:18:13, 1.50it/s] 69%|██████▉ | 39717/57600 [6:58:41<3:12:22, 1.55it/s] 69%|██████▉ | 39718/57600 [6:58:42<3:14:06, 1.54it/s] 69%|██████▉ | 39719/57600 [6:58:43<3:18:54, 1.50it/s] 69%|██████▉ | 39720/57600 [6:58:43<3:13:37, 1.54it/s] {'loss': 1.1481, 'learning_rate': 3.8034843205574913e-07, 'epoch': 438.41} + 69%|██████▉ | 39720/57600 [6:58:43<3:13:37, 1.54it/s] 69%|██████▉ | 39721/57600 [6:58:44<3:10:11, 1.57it/s] 69%|██████▉ | 39722/57600 [6:58:45<3:15:57, 1.52it/s] 69%|██████▉ | 39723/57600 [6:58:45<3:13:35, 1.54it/s] 69%|██████▉ | 39724/57600 [6:58:46<3:17:08, 1.51it/s] 69%|██████▉ | 39725/57600 [6:58:47<3:15:45, 1.52it/s] 69%|██████▉ | 39726/57600 [6:58:47<3:12:34, 1.55it/s] 69%|██████▉ | 39727/57600 [6:58:48<3:10:12, 1.57it/s] 69%|██████▉ | 39728/57600 [6:58:48<3:15:06, 1.53it/s] 69%|██████▉ | 39729/57600 [6:58:49<3:12:46, 1.55it/s] 69%|██████▉ | 39730/57600 [6:58:50<3:11:48, 1.55it/s] 69%|██████▉ | 39731/57600 [6:58:50<3:17:10, 1.51it/s] 69%|██████▉ | 39732/57600 [6:58:51<3:16:13, 1.52it/s] 69%|██████▉ | 39733/57600 [6:58:52<3:08:00, 1.58it/s] 69%|██████▉ | 39734/57600 [6:58:52<3:06:07, 1.60it/s] 69%|██████▉ | 39735/57600 [6:58:53<3:06:39, 1.60it/s] 69%|██████▉ | 39736/57600 [6:58:53<3:05:03, 1.61it/s] 69%|██████▉ | 39737/57600 [6:58:54<3:06:10, 1.60it/s] 69%|██████▉ | 39738/57600 [6:58:55<3:04:04, 1.62it/s] 69%|██████▉ | 39739/57600 [6:58:55<3:04:53, 1.61it/s] 69%|██████▉ | 39740/57600 [6:58:56<3:09:43, 1.57it/s] {'loss': 1.1002, 'learning_rate': 3.800348432055749e-07, 'epoch': 438.63} + 69%|██████▉ | 39740/57600 [6:58:56<3:09:43, 1.57it/s] 69%|██████▉ | 39741/57600 [6:58:57<3:09:38, 1.57it/s] 69%|██████▉ | 39742/57600 [6:58:57<3:09:33, 1.57it/s] 69%|██████▉ | 39743/57600 [6:58:58<3:12:43, 1.54it/s] 69%|██████▉ | 39744/57600 [6:58:59<3:11:52, 1.55it/s] 69%|██████▉ | 39745/57600 [6:58:59<3:11:11, 1.56it/s] 69%|██████▉ | 39746/57600 [6:59:00<3:15:14, 1.52it/s] 69%|██████▉ | 39747/57600 [6:59:00<3:07:56, 1.58it/s] 69%|██████▉ | 39748/57600 [6:59:01<3:05:09, 1.61it/s] 69%|██████▉ | 39749/57600 [6:59:02<3:10:08, 1.56it/s] 69%|██████▉ | 39750/57600 [6:59:02<3:11:52, 1.55it/s] 69%|██████▉ | 39751/57600 [6:59:03<3:15:54, 1.52it/s] 69%|██████▉ | 39752/57600 [6:59:04<3:15:05, 1.52it/s] 69%|██████▉ | 39753/57600 [6:59:04<3:17:20, 1.51it/s] 69%|██████▉ | 39754/57600 [6:59:05<3:17:29, 1.51it/s] 69%|██████▉ | 39755/57600 [6:59:06<3:19:42, 1.49it/s] 69%|██████▉ | 39756/57600 [6:59:06<3:10:15, 1.56it/s] 69%|██████▉ | 39757/57600 [6:59:07<3:10:33, 1.56it/s] 69%|██████▉ | 39758/57600 [6:59:08<3:13:21, 1.54it/s] 69%|██████▉ | 39759/57600 [6:59:08<3:14:32, 1.53it/s] 69%|██████▉ | 39760/57600 [6:59:09<3:13:08, 1.54it/s] {'loss': 1.1463, 'learning_rate': 3.797212543554007e-07, 'epoch': 438.85} + 69%|██████▉ | 39760/57600 [6:59:09<3:13:08, 1.54it/s] 69%|██████▉ | 39761/57600 [6:59:10<3:15:50, 1.52it/s] 69%|██████▉ | 39762/57600 [6:59:10<3:23:13, 1.46it/s] 69%|██████▉ | 39763/57600 [6:59:11<3:18:56, 1.49it/s] 69%|██████▉ | 39764/57600 [6:59:12<3:22:39, 1.47it/s] 69%|██████▉ | 39765/57600 [6:59:13<3:30:22, 1.41it/s] 69%|██████▉ | 39766/57600 [6:59:13<3:20:29, 1.48it/s] 69%|██████▉ | 39767/57600 [6:59:14<3:17:51, 1.50it/s] 69%|██████▉ | 39768/57600 [6:59:14<3:16:20, 1.51it/s] 69%|██████▉ | 39769/57600 [6:59:15<3:24:03, 1.46it/s] 69%|██████▉ | 39770/57600 [6:59:16<3:25:57, 1.44it/s] 69%|██████▉ | 39771/57600 [6:59:17<3:24:00, 1.46it/s] 69%|██████▉ | 39772/57600 [6:59:17<3:25:00, 1.45it/s] 69%|██████▉ | 39773/57600 [6:59:18<3:19:30, 1.49it/s] 69%|██████▉ | 39774/57600 [6:59:19<3:31:33, 1.40it/s] 69%|██████▉ | 39775/57600 [6:59:19<3:23:28, 1.46it/s] 69%|██████▉ | 39776/57600 [6:59:20<3:21:30, 1.47it/s] 69%|██████▉ | 39777/57600 [6:59:21<3:20:14, 1.48it/s] 69%|██████▉ | 39778/57600 [6:59:21<3:18:15, 1.50it/s] 69%|██████▉ | 39779/57600 [6:59:22<3:14:45, 1.53it/s] 69%|██████▉ | 39780/57600 [6:59:23<3:14:01, 1.53it/s] {'loss': 1.1197, 'learning_rate': 3.7940766550522644e-07, 'epoch': 439.07} + 69%|██████▉ | 39780/57600 [6:59:23<3:14:01, 1.53it/s] 69%|██████▉ | 39781/57600 [6:59:23<3:15:54, 1.52it/s] 69%|██████▉ | 39782/57600 [6:59:24<3:19:32, 1.49it/s] 69%|██████▉ | 39783/57600 [6:59:25<3:16:35, 1.51it/s] 69%|██████▉ | 39784/57600 [6:59:25<3:13:42, 1.53it/s] 69%|██████▉ | 39785/57600 [6:59:26<3:11:42, 1.55it/s] 69%|██████▉ | 39786/57600 [6:59:26<3:08:55, 1.57it/s] 69%|██████▉ | 39787/57600 [6:59:27<3:10:47, 1.56it/s] 69%|██████▉ | 39788/57600 [6:59:28<3:11:09, 1.55it/s] 69%|██████▉ | 39789/57600 [6:59:29<3:22:04, 1.47it/s] 69%|██████▉ | 39790/57600 [6:59:29<3:18:48, 1.49it/s] 69%|██████▉ | 39791/57600 [6:59:30<3:16:33, 1.51it/s] 69%|██████▉ | 39792/57600 [6:59:30<3:14:22, 1.53it/s] 69%|██████▉ | 39793/57600 [6:59:31<3:16:55, 1.51it/s] 69%|██████▉ | 39794/57600 [6:59:32<3:13:37, 1.53it/s] 69%|██████▉ | 39795/57600 [6:59:32<3:15:56, 1.51it/s] 69%|██████▉ | 39796/57600 [6:59:33<3:15:27, 1.52it/s] 69%|██████▉ | 39797/57600 [6:59:34<3:12:55, 1.54it/s] 69%|██████▉ | 39798/57600 [6:59:34<3:08:55, 1.57it/s] 69%|██████▉ | 39799/57600 [6:59:35<3:13:52, 1.53it/s] 69%|██████▉ | 39800/57600 [6:59:36<3:19:23, 1.49it/s] {'loss': 1.1338, 'learning_rate': 3.7909407665505225e-07, 'epoch': 439.29} + 69%|██████▉ | 39800/57600 [6:59:36<3:19:23, 1.49it/s] 69%|██████▉ | 39801/57600 [6:59:36<3:18:27, 1.49it/s] 69%|██████▉ | 39802/57600 [6:59:37<3:14:13, 1.53it/s] 69%|██████▉ | 39803/57600 [6:59:38<3:09:28, 1.57it/s] 69%|██████▉ | 39804/57600 [6:59:38<3:07:47, 1.58it/s] 69%|██████▉ | 39805/57600 [6:59:39<3:08:02, 1.58it/s] 69%|██████▉ | 39806/57600 [6:59:39<3:04:29, 1.61it/s] 69%|██████▉ | 39807/57600 [6:59:40<3:11:49, 1.55it/s] 69%|██████▉ | 39808/57600 [6:59:41<3:15:17, 1.52it/s] 69%|██████▉ | 39809/57600 [6:59:41<3:11:48, 1.55it/s] 69%|██████▉ | 39810/57600 [6:59:42<3:23:13, 1.46it/s] 69%|██████▉ | 39811/57600 [6:59:43<3:23:24, 1.46it/s] 69%|██████▉ | 39812/57600 [6:59:44<3:26:16, 1.44it/s] 69%|██████▉ | 39813/57600 [6:59:44<3:23:10, 1.46it/s] 69%|██████▉ | 39814/57600 [6:59:45<3:13:42, 1.53it/s] 69%|██████▉ | 39815/57600 [6:59:45<3:06:20, 1.59it/s] 69%|██████▉ | 39816/57600 [6:59:46<3:06:07, 1.59it/s] 69%|██████▉ | 39817/57600 [6:59:47<3:06:16, 1.59it/s] 69%|██████▉ | 39818/57600 [6:59:47<3:12:27, 1.54it/s] 69%|██████▉ | 39819/57600 [6:59:48<3:05:35, 1.60it/s] 69%|██████▉ | 39820/57600 [6:59:49<3:09:44, 1.56it/s] {'loss': 1.174, 'learning_rate': 3.787804878048781e-07, 'epoch': 439.51} + 69%|██████▉ | 39820/57600 [6:59:49<3:09:44, 1.56it/s] 69%|██████▉ | 39821/57600 [6:59:49<3:10:48, 1.55it/s] 69%|██████▉ | 39822/57600 [6:59:50<3:06:00, 1.59it/s] 69%|██████▉ | 39823/57600 [6:59:51<3:06:35, 1.59it/s] 69%|██████▉ | 39824/57600 [6:59:51<3:13:05, 1.53it/s] 69%|██████▉ | 39825/57600 [6:59:52<3:05:52, 1.59it/s] 69%|██████▉ | 39826/57600 [6:59:52<3:00:16, 1.64it/s] 69%|██████▉ | 39827/57600 [6:59:53<2:53:52, 1.70it/s] 69%|██████▉ | 39828/57600 [6:59:54<3:00:30, 1.64it/s] 69%|██████▉ | 39829/57600 [6:59:54<2:59:17, 1.65it/s] 69%|██████▉ | 39830/57600 [6:59:55<2:56:31, 1.68it/s] 69%|██████▉ | 39831/57600 [6:59:55<2:54:55, 1.69it/s] 69%|██████▉ | 39832/57600 [6:59:56<2:56:40, 1.68it/s] 69%|██████▉ | 39833/57600 [6:59:57<2:58:12, 1.66it/s] 69%|██████▉ | 39834/57600 [6:59:57<3:00:13, 1.64it/s] 69%|██████▉ | 39835/57600 [6:59:58<3:05:19, 1.60it/s] 69%|██████▉ | 39836/57600 [6:59:58<3:06:30, 1.59it/s] 69%|██████▉ | 39837/57600 [6:59:59<3:09:52, 1.56it/s] 69%|██████▉ | 39838/57600 [7:00:00<3:06:03, 1.59it/s] 69%|██████▉ | 39839/57600 [7:00:00<3:08:46, 1.57it/s] 69%|██████▉ | 39840/57600 [7:00:01<3:05:03, 1.60it/s] {'loss': 1.1651, 'learning_rate': 3.784668989547038e-07, 'epoch': 439.74} + 69%|██████▉ | 39840/57600 [7:00:01<3:05:03, 1.60it/s] 69%|██████▉ | 39841/57600 [7:00:02<3:04:17, 1.61it/s] 69%|██████▉ | 39842/57600 [7:00:02<3:06:19, 1.59it/s] 69%|██████▉ | 39843/57600 [7:00:03<3:06:25, 1.59it/s] 69%|██████▉ | 39844/57600 [7:00:04<3:04:30, 1.60it/s] 69%|██████▉ | 39845/57600 [7:00:04<3:00:19, 1.64it/s] 69%|██████▉ | 39846/57600 [7:00:05<2:58:47, 1.66it/s] 69%|██████▉ | 39847/57600 [7:00:05<3:00:10, 1.64it/s] 69%|██████▉ | 39848/57600 [7:00:06<3:02:56, 1.62it/s] 69%|██████▉ | 39849/57600 [7:00:07<3:09:23, 1.56it/s] 69%|██████▉ | 39850/57600 [7:00:07<3:04:34, 1.60it/s] 69%|██████▉ | 39851/57600 [7:00:08<2:58:20, 1.66it/s] 69%|██████▉ | 39852/57600 [7:00:08<2:58:27, 1.66it/s] 69%|██████▉ | 39853/57600 [7:00:09<3:04:55, 1.60it/s] 69%|██████▉ | 39854/57600 [7:00:10<3:06:19, 1.59it/s] 69%|██████▉ | 39855/57600 [7:00:10<3:07:00, 1.58it/s] 69%|██████▉ | 39856/57600 [7:00:11<3:11:49, 1.54it/s] 69%|██████▉ | 39857/57600 [7:00:12<3:09:53, 1.56it/s] 69%|██████▉ | 39858/57600 [7:00:12<3:17:05, 1.50it/s] 69%|██████▉ | 39859/57600 [7:00:13<3:09:23, 1.56it/s] 69%|██████▉ | 39860/57600 [7:00:14<3:06:51, 1.58it/s] {'loss': 1.1388, 'learning_rate': 3.781533101045296e-07, 'epoch': 439.96} + 69%|██████▉ | 39860/57600 [7:00:14<3:06:51, 1.58it/s] 69%|██████▉ | 39861/57600 [7:00:14<3:08:37, 1.57it/s] 69%|██████▉ | 39862/57600 [7:00:15<3:12:39, 1.53it/s] 69%|██████▉ | 39863/57600 [7:00:15<3:06:47, 1.58it/s] 69%|██████▉ | 39864/57600 [7:00:16<3:11:12, 1.55it/s] 69%|██████▉ | 39865/57600 [7:00:17<3:12:59, 1.53it/s] 69%|██████▉ | 39866/57600 [7:00:17<3:10:57, 1.55it/s] 69%|██████▉ | 39867/57600 [7:00:18<3:09:02, 1.56it/s] 69%|██████▉ | 39868/57600 [7:00:19<3:10:08, 1.55it/s] 69%|██████▉ | 39869/57600 [7:00:19<3:08:54, 1.56it/s] 69%|██████▉ | 39870/57600 [7:00:20<3:06:17, 1.59it/s] 69%|██████▉ | 39871/57600 [7:00:21<3:03:24, 1.61it/s] 69%|██████▉ | 39872/57600 [7:00:21<3:00:33, 1.64it/s] 69%|██████▉ | 39873/57600 [7:00:22<2:58:28, 1.66it/s] 69%|██████▉ | 39874/57600 [7:00:22<2:55:33, 1.68it/s] 69%|██████▉ | 39875/57600 [7:00:23<2:59:38, 1.64it/s] 69%|██████▉ | 39876/57600 [7:00:24<3:03:07, 1.61it/s] 69%|██████▉ | 39877/57600 [7:00:24<3:09:00, 1.56it/s] 69%|██████▉ | 39878/57600 [7:00:25<3:06:40, 1.58it/s] 69%|██████▉ | 39879/57600 [7:00:26<3:11:21, 1.54it/s] 69%|██████▉ | 39880/57600 [7:00:26<3:16:29, 1.50it/s] {'loss': 1.1651, 'learning_rate': 3.7783972125435536e-07, 'epoch': 440.18} + 69%|██████▉ | 39880/57600 [7:00:26<3:16:29, 1.50it/s] 69%|██████▉ | 39881/57600 [7:00:27<3:12:55, 1.53it/s] 69%|██████▉ | 39882/57600 [7:00:28<3:07:33, 1.57it/s] 69%|██████▉ | 39883/57600 [7:00:28<2:59:40, 1.64it/s] 69%|██████▉ | 39884/57600 [7:00:29<3:00:10, 1.64it/s] 69%|██████▉ | 39885/57600 [7:00:29<3:02:27, 1.62it/s] 69%|██████▉ | 39886/57600 [7:00:30<3:01:50, 1.62it/s] 69%|██████▉ | 39887/57600 [7:00:31<3:08:37, 1.57it/s] 69%|██████▉ | 39888/57600 [7:00:31<3:02:43, 1.62it/s] 69%|██████▉ | 39889/57600 [7:00:32<3:01:35, 1.63it/s] 69%|██████▉ | 39890/57600 [7:00:32<3:00:05, 1.64it/s] 69%|██████▉ | 39891/57600 [7:00:33<3:01:51, 1.62it/s] 69%|██████▉ | 39892/57600 [7:00:34<3:04:45, 1.60it/s] 69%|██████▉ | 39893/57600 [7:00:34<3:09:26, 1.56it/s] 69%|██████▉ | 39894/57600 [7:00:35<3:05:47, 1.59it/s] 69%|██████▉ | 39895/57600 [7:00:36<3:04:18, 1.60it/s] 69%|██████▉ | 39896/57600 [7:00:36<3:02:04, 1.62it/s] 69%|██████▉ | 39897/57600 [7:00:37<2:58:49, 1.65it/s] 69%|██████▉ | 39898/57600 [7:00:37<3:04:12, 1.60it/s] 69%|██████▉ | 39899/57600 [7:00:38<3:06:29, 1.58it/s] 69%|██████▉ | 39900/57600 [7:00:39<3:07:30, 1.57it/s] {'loss': 1.1577, 'learning_rate': 3.7752613240418116e-07, 'epoch': 440.4} + 69%|██████▉ | 39900/57600 [7:00:39<3:07:30, 1.57it/s] 69%|██████▉ | 39901/57600 [7:00:39<3:08:11, 1.57it/s] 69%|██████▉ | 39902/57600 [7:00:40<3:04:02, 1.60it/s] 69%|████���█▉ | 39903/57600 [7:00:41<3:05:30, 1.59it/s] 69%|██████▉ | 39904/57600 [7:00:41<2:59:47, 1.64it/s] 69%|██████▉ | 39905/57600 [7:00:42<3:01:50, 1.62it/s] 69%|██████▉ | 39906/57600 [7:00:42<3:06:58, 1.58it/s] 69%|██████▉ | 39907/57600 [7:00:43<3:06:53, 1.58it/s] 69%|██████▉ | 39908/57600 [7:00:44<3:04:41, 1.60it/s] 69%|██████▉ | 39909/57600 [7:00:44<3:08:11, 1.57it/s] 69%|██████▉ | 39910/57600 [7:00:45<3:03:41, 1.61it/s] 69%|██████▉ | 39911/57600 [7:00:46<3:02:51, 1.61it/s] 69%|██████▉ | 39912/57600 [7:00:46<3:04:31, 1.60it/s] 69%|██████▉ | 39913/57600 [7:00:47<3:02:41, 1.61it/s] 69%|██████▉ | 39914/57600 [7:00:47<3:03:39, 1.60it/s] 69%|██████▉ | 39915/57600 [7:00:48<3:02:34, 1.61it/s] 69%|██████▉ | 39916/57600 [7:00:49<3:01:21, 1.63it/s] 69%|██████▉ | 39917/57600 [7:00:49<3:04:13, 1.60it/s] 69%|██████▉ | 39918/57600 [7:00:50<3:09:57, 1.55it/s] 69%|██████▉ | 39919/57600 [7:00:51<3:10:17, 1.55it/s] 69%|██████▉ | 39920/57600 [7:00:51<3:08:31, 1.56it/s] {'loss': 1.1453, 'learning_rate': 3.772125435540069e-07, 'epoch': 440.62} + 69%|██████▉ | 39920/57600 [7:00:51<3:08:31, 1.56it/s] 69%|██████▉ | 39921/57600 [7:00:52<3:16:37, 1.50it/s] 69%|██████▉ | 39922/57600 [7:00:53<3:13:56, 1.52it/s] 69%|██████▉ | 39923/57600 [7:00:53<3:10:23, 1.55it/s] 69%|██████▉ | 39924/57600 [7:00:54<3:08:24, 1.56it/s] 69%|██████▉ | 39925/57600 [7:00:55<3:10:48, 1.54it/s] 69%|██████▉ | 39926/57600 [7:00:55<3:03:05, 1.61it/s] 69%|██████▉ | 39927/57600 [7:00:56<3:03:29, 1.61it/s] 69%|██████▉ | 39928/57600 [7:00:56<3:01:42, 1.62it/s] 69%|██████▉ | 39929/57600 [7:00:57<3:03:42, 1.60it/s] 69%|██████▉ | 39930/57600 [7:00:58<2:59:28, 1.64it/s] 69%|██████▉ | 39931/57600 [7:00:58<2:56:37, 1.67it/s] 69%|██████▉ | 39932/57600 [7:00:59<3:00:28, 1.63it/s] 69%|██████▉ | 39933/57600 [7:00:59<2:54:26, 1.69it/s] 69%|██████▉ | 39934/57600 [7:01:00<2:58:06, 1.65it/s] 69%|██████▉ | 39935/57600 [7:01:01<3:04:23, 1.60it/s] 69%|██████▉ | 39936/57600 [7:01:01<3:03:41, 1.60it/s] 69%|██████▉ | 39937/57600 [7:01:02<3:02:57, 1.61it/s] 69%|██████▉ | 39938/57600 [7:01:03<3:05:25, 1.59it/s] 69%|██████▉ | 39939/57600 [7:01:03<3:06:13, 1.58it/s] 69%|██████▉ | 39940/57600 [7:01:04<3:02:51, 1.61it/s] {'loss': 1.1037, 'learning_rate': 3.768989547038327e-07, 'epoch': 440.84} + 69%|██████▉ | 39940/57600 [7:01:04<3:02:51, 1.61it/s] 69%|██████▉ | 39941/57600 [7:01:04<2:58:35, 1.65it/s] 69%|██████▉ | 39942/57600 [7:01:05<3:08:23, 1.56it/s] 69%|██████▉ | 39943/57600 [7:01:06<3:08:13, 1.56it/s] 69%|██████▉ | 39944/57600 [7:01:06<3:09:34, 1.55it/s] 69%|██████▉ | 39945/57600 [7:01:07<3:13:09, 1.52it/s] 69%|██████▉ | 39946/57600 [7:01:08<3:14:17, 1.51it/s] 69%|██████▉ | 39947/57600 [7:01:08<3:08:04, 1.56it/s] 69%|██████▉ | 39948/57600 [7:01:09<3:04:52, 1.59it/s] 69%|██████▉ | 39949/57600 [7:01:10<3:07:32, 1.57it/s] 69%|██████▉ | 39950/57600 [7:01:10<3:12:20, 1.53it/s] 69%|██████▉ | 39951/57600 [7:01:11<3:08:35, 1.56it/s] 69%|██████▉ | 39952/57600 [7:01:11<3:02:29, 1.61it/s] 69%|██████▉ | 39953/57600 [7:01:12<2:59:38, 1.64it/s] 69%|██████▉ | 39954/57600 [7:01:13<3:01:34, 1.62it/s] 69%|██████▉ | 39955/57600 [7:01:13<3:05:29, 1.59it/s] 69%|██████▉ | 39956/57600 [7:01:14<3:11:15, 1.54it/s] 69%|██████▉ | 39957/57600 [7:01:15<3:09:35, 1.55it/s] 69%|██████▉ | 39958/57600 [7:01:15<3:13:41, 1.52it/s] 69%|██████▉ | 39959/57600 [7:01:16<3:12:07, 1.53it/s] 69%|██████▉ | 39960/57600 [7:01:17<3:14:38, 1.51it/s] {'loss': 1.1393, 'learning_rate': 3.765853658536586e-07, 'epoch': 441.06} + 69%|██████▉ | 39960/57600 [7:01:17<3:14:38, 1.51it/s] 69%|██████▉ | 39961/57600 [7:01:17<3:13:49, 1.52it/s] 69%|██████▉ | 39962/57600 [7:01:18<3:06:56, 1.57it/s] 69%|██████▉ | 39963/57600 [7:01:18<3:00:37, 1.63it/s] 69%|██████▉ | 39964/57600 [7:01:19<3:06:45, 1.57it/s] 69%|██████▉ | 39965/57600 [7:01:20<3:07:01, 1.57it/s] 69%|██████▉ | 39966/57600 [7:01:20<3:05:15, 1.59it/s] 69%|██████▉ | 39967/57600 [7:01:21<3:01:07, 1.62it/s] 69%|██████▉ | 39968/57600 [7:01:22<3:04:58, 1.59it/s] 69%|██████▉ | 39969/57600 [7:01:22<3:02:25, 1.61it/s] 69%|██████▉ | 39970/57600 [7:01:23<2:58:57, 1.64it/s] 69%|██████▉ | 39971/57600 [7:01:23<3:06:47, 1.57it/s] 69%|██████▉ | 39972/57600 [7:01:24<3:10:13, 1.54it/s] 69%|██████▉ | 39973/57600 [7:01:25<3:10:41, 1.54it/s] 69%|██████▉ | 39974/57600 [7:01:25<3:12:04, 1.53it/s] 69%|██████▉ | 39975/57600 [7:01:26<3:12:48, 1.52it/s] 69%|██████▉ | 39976/57600 [7:01:27<3:07:22, 1.57it/s] 69%|██████▉ | 39977/57600 [7:01:27<3:10:28, 1.54it/s] 69%|██████▉ | 39978/57600 [7:01:28<3:06:02, 1.58it/s] 69%|██████▉ | 39979/57600 [7:01:29<3:02:21, 1.61it/s] 69%|██████▉ | 39980/57600 [7:01:29<2:57:36, 1.65it/s] {'loss': 1.1566, 'learning_rate': 3.762717770034843e-07, 'epoch': 441.28} + 69%|██████▉ | 39980/57600 [7:01:29<2:57:36, 1.65it/s] 69%|██████▉ | 39981/57600 [7:01:30<2:55:06, 1.68it/s] 69%|██████▉ | 39982/57600 [7:01:30<2:54:19, 1.68it/s] 69%|██████▉ | 39983/57600 [7:01:31<2:56:13, 1.67it/s] 69%|██████▉ | 39984/57600 [7:01:32<2:59:41, 1.63it/s] 69%|██████▉ | 39985/57600 [7:01:32<3:02:39, 1.61it/s] 69%|██████▉ | 39986/57600 [7:01:33<3:00:09, 1.63it/s] 69%|██████▉ | 39987/57600 [7:01:34<3:04:32, 1.59it/s] 69%|██████▉ | 39988/57600 [7:01:34<3:08:31, 1.56it/s] 69%|██████▉ | 39989/57600 [7:01:35<3:13:28, 1.52it/s] 69%|██████▉ | 39990/57600 [7:01:36<3:15:02, 1.50it/s] 69%|██████▉ | 39991/57600 [7:01:36<3:12:44, 1.52it/s] 69%|██████▉ | 39992/57600 [7:01:37<3:07:26, 1.57it/s] 69%|██████▉ | 39993/57600 [7:01:37<3:02:24, 1.61it/s] 69%|██████▉ | 39994/57600 [7:01:38<3:01:08, 1.62it/s] 69%|██████▉ | 39995/57600 [7:01:39<3:01:21, 1.62it/s] 69%|██████▉ | 39996/57600 [7:01:39<3:04:04, 1.59it/s] 69%|██████▉ | 39997/57600 [7:01:40<3:04:55, 1.59it/s] 69%|██████▉ | 39998/57600 [7:01:41<3:11:05, 1.54it/s] 69%|██████▉ | 39999/57600 [7:01:41<3:08:37, 1.56it/s] 69%|██████▉ | 40000/57600 [7:01:42<3:11:34, 1.53it/s] {'loss': 1.0984, 'learning_rate': 3.7595818815331014e-07, 'epoch': 441.5} + 69%|██████▉ | 40000/57600 [7:01:42<3:11:34, 1.53it/s] 69%|██████▉ | 40001/57600 [7:01:43<3:09:21, 1.55it/s] 69%|██████▉ | 40002/57600 [7:01:43<3:06:01, 1.58it/s] 69%|██████▉ | 40003/57600 [7:01:44<3:05:52, 1.58it/s] 69%|██████▉ | 40004/57600 [7:01:44<3:13:49, 1.51it/s] 69%|██████▉ | 40005/57600 [7:01:45<3:10:36, 1.54it/s] 69%|██████▉ | 40006/57600 [7:01:46<3:05:58, 1.58it/s] 69%|██████▉ | 40007/57600 [7:01:46<3:06:56, 1.57it/s] 69%|██████▉ | 40008/57600 [7:01:47<3:06:24, 1.57it/s] 69%|██████▉ | 40009/57600 [7:01:48<3:10:43, 1.54it/s] 69%|██████▉ | 40010/57600 [7:01:48<3:11:55, 1.53it/s] 69%|██████▉ | 40011/57600 [7:01:49<3:19:05, 1.47it/s] 69%|██████▉ | 40012/57600 [7:01:50<3:13:32, 1.51it/s] 69%|██████▉ | 40013/57600 [7:01:50<3:06:10, 1.57it/s] 69%|██████▉ | 40014/57600 [7:01:51<3:05:33, 1.58it/s] 69%|██████▉ | 40015/57600 [7:01:52<3:08:05, 1.56it/s] 69%|██████▉ | 40016/57600 [7:01:52<3:07:09, 1.57it/s] 69%|██████▉ | 40017/57600 [7:01:53<3:03:12, 1.60it/s] 69%|██████▉ | 40018/57600 [7:01:53<2:59:11, 1.64it/s] 69%|██████▉ | 40019/57600 [7:01:54<3:01:23, 1.62it/s] 69%|██████▉ | 40020/57600 [7:01:55<2:58:01, 1.65it/s] {'loss': 1.1659, 'learning_rate': 3.7564459930313583e-07, 'epoch': 441.72} + 69%|██████▉ | 40020/57600 [7:01:55<2:58:01, 1.65it/s] 69%|██████▉ | 40021/57600 [7:01:55<3:06:06, 1.57it/s] 69%|██████▉ | 40022/57600 [7:01:56<3:07:03, 1.57it/s] 69%|██████▉ | 40023/57600 [7:01:57<3:10:09, 1.54it/s] 69%|██████▉ | 40024/57600 [7:01:57<3:07:23, 1.56it/s] 69%|██████▉ | 40025/57600 [7:01:58<3:09:06, 1.55it/s] 69%|██████▉ | 40026/57600 [7:01:58<3:06:43, 1.57it/s] 69%|██████▉ | 40027/57600 [7:01:59<3:07:24, 1.56it/s] 69%|█████���▉ | 40028/57600 [7:02:00<3:06:16, 1.57it/s] 69%|██████▉ | 40029/57600 [7:02:00<3:07:04, 1.57it/s] 69%|██████▉ | 40030/57600 [7:02:01<3:08:51, 1.55it/s] 69%|██████▉ | 40031/57600 [7:02:02<3:12:29, 1.52it/s] 70%|██████▉ | 40032/57600 [7:02:02<3:03:20, 1.60it/s] 70%|██████▉ | 40033/57600 [7:02:03<3:02:44, 1.60it/s] 70%|██████▉ | 40034/57600 [7:02:04<2:59:57, 1.63it/s] 70%|██████▉ | 40035/57600 [7:02:04<3:01:24, 1.61it/s] 70%|██████▉ | 40036/57600 [7:02:05<2:56:40, 1.66it/s] 70%|██████▉ | 40037/57600 [7:02:05<3:06:02, 1.57it/s] 70%|██████▉ | 40038/57600 [7:02:06<3:07:56, 1.56it/s] 70%|██████▉ | 40039/57600 [7:02:07<3:04:45, 1.58it/s] 70%|██████▉ | 40040/57600 [7:02:07<2:57:17, 1.65it/s] {'loss': 1.1299, 'learning_rate': 3.753310104529617e-07, 'epoch': 441.94} + 70%|██████▉ | 40040/57600 [7:02:07<2:57:17, 1.65it/s] 70%|██████▉ | 40041/57600 [7:02:08<3:01:32, 1.61it/s] 70%|██████▉ | 40042/57600 [7:02:08<2:57:29, 1.65it/s] 70%|██████▉ | 40043/57600 [7:02:09<2:59:23, 1.63it/s] 70%|██████▉ | 40044/57600 [7:02:10<3:03:19, 1.60it/s] 70%|██████▉ | 40045/57600 [7:02:10<3:03:38, 1.59it/s] 70%|██████▉ | 40046/57600 [7:02:11<3:07:25, 1.56it/s] 70%|██████▉ | 40047/57600 [7:02:12<3:10:34, 1.54it/s] 70%|██████▉ | 40048/57600 [7:02:12<3:05:49, 1.57it/s] 70%|██████▉ | 40049/57600 [7:02:13<3:07:22, 1.56it/s] 70%|██████▉ | 40050/57600 [7:02:14<3:10:30, 1.54it/s] 70%|██████▉ | 40051/57600 [7:02:14<3:07:50, 1.56it/s] 70%|██████▉ | 40052/57600 [7:02:15<3:06:59, 1.56it/s] 70%|██████▉ | 40053/57600 [7:02:16<3:06:10, 1.57it/s] 70%|██████▉ | 40054/57600 [7:02:16<3:06:49, 1.57it/s] 70%|██████▉ | 40055/57600 [7:02:17<3:01:51, 1.61it/s] 70%|██████▉ | 40056/57600 [7:02:17<2:57:46, 1.64it/s] 70%|██████▉ | 40057/57600 [7:02:18<2:59:21, 1.63it/s] 70%|██████▉ | 40058/57600 [7:02:19<2:57:36, 1.65it/s] 70%|██████▉ | 40059/57600 [7:02:19<2:57:13, 1.65it/s] 70%|██████▉ | 40060/57600 [7:02:20<3:04:56, 1.58it/s] {'loss': 1.1503, 'learning_rate': 3.750174216027874e-07, 'epoch': 442.16} + 70%|██████▉ | 40060/57600 [7:02:20<3:04:56, 1.58it/s] 70%|██████▉ | 40061/57600 [7:02:21<3:09:32, 1.54it/s] 70%|██████▉ | 40062/57600 [7:02:21<3:08:56, 1.55it/s] 70%|██████▉ | 40063/57600 [7:02:22<3:07:03, 1.56it/s] 70%|██████▉ | 40064/57600 [7:02:22<3:04:32, 1.58it/s] 70%|██████▉ | 40065/57600 [7:02:23<3:09:47, 1.54it/s] 70%|██████▉ | 40066/57600 [7:02:24<3:05:58, 1.57it/s] 70%|██████▉ | 40067/57600 [7:02:24<3:08:46, 1.55it/s] 70%|██████▉ | 40068/57600 [7:02:25<3:05:26, 1.58it/s] 70%|██████▉ | 40069/57600 [7:02:26<3:02:42, 1.60it/s] 70%|██████▉ | 40070/57600 [7:02:26<3:06:48, 1.56it/s] 70%|██████▉ | 40071/57600 [7:02:27<3:06:23, 1.57it/s] 70%|██████▉ | 40072/57600 [7:02:28<3:03:39, 1.59it/s] 70%|██████▉ | 40073/57600 [7:02:28<3:02:26, 1.60it/s] 70%|██████▉ | 40074/57600 [7:02:29<3:03:01, 1.60it/s] 70%|██████▉ | 40075/57600 [7:02:29<3:05:25, 1.58it/s] 70%|██████▉ | 40076/57600 [7:02:30<3:11:52, 1.52it/s] 70%|██████▉ | 40077/57600 [7:02:31<3:06:05, 1.57it/s] 70%|██████▉ | 40078/57600 [7:02:31<3:05:21, 1.58it/s] 70%|██████▉ | 40079/57600 [7:02:32<3:01:46, 1.61it/s] 70%|██████▉ | 40080/57600 [7:02:33<2:58:30, 1.64it/s] {'loss': 1.1451, 'learning_rate': 3.7470383275261325e-07, 'epoch': 442.38} + 70%|██████▉ | 40080/57600 [7:02:33<2:58:30, 1.64it/s] 70%|██████▉ | 40081/57600 [7:02:33<2:58:38, 1.63it/s] 70%|██████▉ | 40082/57600 [7:02:34<2:58:05, 1.64it/s] 70%|██████▉ | 40083/57600 [7:02:34<2:57:26, 1.65it/s] 70%|██████▉ | 40084/57600 [7:02:35<3:03:05, 1.59it/s] 70%|██████▉ | 40085/57600 [7:02:36<2:56:25, 1.65it/s] 70%|██████▉ | 40086/57600 [7:02:36<2:58:51, 1.63it/s] 70%|██████▉ | 40087/57600 [7:02:37<2:57:16, 1.65it/s] 70%|██████▉ | 40088/57600 [7:02:37<2:55:41, 1.66it/s] 70%|██████▉ | 40089/57600 [7:02:38<2:56:03, 1.66it/s] 70%|██████▉ | 40090/57600 [7:02:39<2:57:24, 1.65it/s] 70%|██████▉ | 40091/57600 [7:02:39<2:57:38, 1.64it/s] 70%|██████▉ | 40092/57600 [7:02:40<2:55:49, 1.66it/s] 70%|██████▉ | 40093/57600 [7:02:40<2:51:19, 1.70it/s] 70%|██████▉ | 40094/57600 [7:02:41<2:55:39, 1.66it/s] 70%|██████▉ | 40095/57600 [7:02:42<2:57:22, 1.64it/s] 70%|██████▉ | 40096/57600 [7:02:42<2:59:22, 1.63it/s] 70%|██████▉ | 40097/57600 [7:02:43<2:58:44, 1.63it/s] 70%|██████▉ | 40098/57600 [7:02:44<3:04:02, 1.58it/s] 70%|██████▉ | 40099/57600 [7:02:44<3:05:34, 1.57it/s] 70%|██████▉ | 40100/57600 [7:02:45<3:06:33, 1.56it/s] {'loss': 1.1444, 'learning_rate': 3.7439024390243905e-07, 'epoch': 442.6} + 70%|██████▉ | 40100/57600 [7:02:45<3:06:33, 1.56it/s] 70%|██████▉ | 40101/57600 [7:02:45<3:05:53, 1.57it/s] 70%|██████▉ | 40102/57600 [7:02:46<3:11:20, 1.52it/s] 70%|██████▉ | 40103/57600 [7:02:47<3:11:07, 1.53it/s] 70%|██████▉ | 40104/57600 [7:02:47<3:11:46, 1.52it/s] 70%|██████▉ | 40105/57600 [7:02:48<3:10:27, 1.53it/s] 70%|██████▉ | 40106/57600 [7:02:49<3:07:55, 1.55it/s] 70%|██████▉ | 40107/57600 [7:02:49<3:07:41, 1.55it/s] 70%|██████▉ | 40108/57600 [7:02:50<3:08:26, 1.55it/s] 70%|██████▉ | 40109/57600 [7:02:51<3:03:22, 1.59it/s] 70%|██████▉ | 40110/57600 [7:02:51<3:11:34, 1.52it/s] 70%|██████▉ | 40111/57600 [7:02:52<3:13:13, 1.51it/s] 70%|██████▉ | 40112/57600 [7:02:53<3:08:37, 1.55it/s] 70%|██████▉ | 40113/57600 [7:02:53<3:07:05, 1.56it/s] 70%|██████▉ | 40114/57600 [7:02:54<3:05:59, 1.57it/s] 70%|██████▉ | 40115/57600 [7:02:55<3:04:38, 1.58it/s] 70%|██████▉ | 40116/57600 [7:02:55<3:06:00, 1.57it/s] 70%|██████▉ | 40117/57600 [7:02:56<3:04:27, 1.58it/s] 70%|██████▉ | 40118/57600 [7:02:56<3:02:28, 1.60it/s] 70%|██████▉ | 40119/57600 [7:02:57<3:00:33, 1.61it/s] 70%|██████▉ | 40120/57600 [7:02:58<3:04:02, 1.58it/s] {'loss': 1.1223, 'learning_rate': 3.7407665505226475e-07, 'epoch': 442.83} + 70%|██████▉ | 40120/57600 [7:02:58<3:04:02, 1.58it/s] 70%|██████▉ | 40121/57600 [7:02:58<3:00:46, 1.61it/s] 70%|██████▉ | 40122/57600 [7:02:59<2:57:45, 1.64it/s] 70%|██████▉ | 40123/57600 [7:02:59<2:55:13, 1.66it/s] 70%|██████▉ | 40124/57600 [7:03:00<2:56:41, 1.65it/s] 70%|██████▉ | 40125/57600 [7:03:01<3:04:21, 1.58it/s] 70%|██████▉ | 40126/57600 [7:03:01<3:02:57, 1.59it/s] 70%|██████▉ | 40127/57600 [7:03:02<3:01:19, 1.61it/s] 70%|██████▉ | 40128/57600 [7:03:03<2:59:39, 1.62it/s] 70%|██████▉ | 40129/57600 [7:03:03<3:02:28, 1.60it/s] 70%|██████▉ | 40130/57600 [7:03:04<3:05:13, 1.57it/s] 70%|██████▉ | 40131/57600 [7:03:04<3:01:39, 1.60it/s] 70%|██████▉ | 40132/57600 [7:03:05<3:03:35, 1.59it/s] 70%|██████▉ | 40133/57600 [7:03:06<3:06:45, 1.56it/s] 70%|██████▉ | 40134/57600 [7:03:06<3:03:55, 1.58it/s] 70%|██████▉ | 40135/57600 [7:03:07<3:08:24, 1.54it/s] 70%|██████▉ | 40136/57600 [7:03:08<3:12:37, 1.51it/s] 70%|██████▉ | 40137/57600 [7:03:08<3:07:15, 1.55it/s] 70%|██████▉ | 40138/57600 [7:03:09<3:10:03, 1.53it/s] 70%|██████▉ | 40139/57600 [7:03:10<3:11:29, 1.52it/s] 70%|██████▉ | 40140/57600 [7:03:10<3:07:27, 1.55it/s] {'loss': 1.1695, 'learning_rate': 3.7376306620209066e-07, 'epoch': 443.05} + 70%|██████▉ | 40140/57600 [7:03:10<3:07:27, 1.55it/s] 70%|██████▉ | 40141/57600 [7:03:11<3:03:33, 1.59it/s] 70%|██████▉ | 40142/57600 [7:03:11<2:56:42, 1.65it/s] 70%|██████▉ | 40143/57600 [7:03:12<2:56:38, 1.65it/s] 70%|██████▉ | 40144/57600 [7:03:13<2:58:57, 1.63it/s] 70%|██████▉ | 40145/57600 [7:03:13<2:56:39, 1.65it/s] 70%|██████▉ | 40146/57600 [7:03:14<2:55:05, 1.66it/s] 70%|██████▉ | 40147/57600 [7:03:15<3:03:17, 1.59it/s] 70%|██████▉ | 40148/57600 [7:03:15<3:00:42, 1.61it/s] 70%|██████▉ | 40149/57600 [7:03:16<3:04:02, 1.58it/s] 70%|██████▉ | 40150/57600 [7:03:16<2:58:03, 1.63it/s] 70%|██████▉ | 40151/57600 [7:03:17<2:58:43, 1.63it/s] 70%|██████▉ | 40152/57600 [7:03:18<2:58:59, 1.62it/s] 70%|█████��▉ | 40153/57600 [7:03:18<2:57:59, 1.63it/s] 70%|██████▉ | 40154/57600 [7:03:19<3:03:12, 1.59it/s] 70%|██████▉ | 40155/57600 [7:03:20<2:59:41, 1.62it/s] 70%|██████▉ | 40156/57600 [7:03:20<2:55:39, 1.66it/s] 70%|██████▉ | 40157/57600 [7:03:21<2:51:11, 1.70it/s] 70%|██████▉ | 40158/57600 [7:03:21<2:58:20, 1.63it/s] 70%|██████▉ | 40159/57600 [7:03:22<3:00:41, 1.61it/s] 70%|██████▉ | 40160/57600 [7:03:23<3:09:54, 1.53it/s] {'loss': 1.1616, 'learning_rate': 3.734494773519163e-07, 'epoch': 443.27} + 70%|██████▉ | 40160/57600 [7:03:23<3:09:54, 1.53it/s] 70%|██████▉ | 40161/57600 [7:03:23<3:11:13, 1.52it/s] 70%|██████▉ | 40162/57600 [7:03:24<3:09:18, 1.54it/s] 70%|██████▉ | 40163/57600 [7:03:25<3:09:23, 1.53it/s] 70%|██████▉ | 40164/57600 [7:03:25<3:03:02, 1.59it/s] 70%|██████▉ | 40165/57600 [7:03:26<3:05:49, 1.56it/s] 70%|██████▉ | 40166/57600 [7:03:26<2:58:20, 1.63it/s] 70%|██████▉ | 40167/57600 [7:03:27<3:01:14, 1.60it/s] 70%|██████▉ | 40168/57600 [7:03:28<2:57:33, 1.64it/s] 70%|██████▉ | 40169/57600 [7:03:28<2:56:40, 1.64it/s] 70%|██████▉ | 40170/57600 [7:03:29<2:55:19, 1.66it/s] 70%|██████▉ | 40171/57600 [7:03:29<2:58:07, 1.63it/s] 70%|██████▉ | 40172/57600 [7:03:30<3:01:15, 1.60it/s] 70%|██████▉ | 40173/57600 [7:03:31<3:08:07, 1.54it/s] 70%|██████▉ | 40174/57600 [7:03:31<3:07:50, 1.55it/s] 70%|██████▉ | 40175/57600 [7:03:32<3:11:10, 1.52it/s] 70%|██████▉ | 40176/57600 [7:03:33<3:06:25, 1.56it/s] 70%|██████▉ | 40177/57600 [7:03:33<3:12:02, 1.51it/s] 70%|██████▉ | 40178/57600 [7:03:34<3:04:32, 1.57it/s] 70%|██████▉ | 40179/57600 [7:03:35<3:01:13, 1.60it/s] 70%|██████▉ | 40180/57600 [7:03:35<2:57:13, 1.64it/s] {'loss': 1.1511, 'learning_rate': 3.7313588850174217e-07, 'epoch': 443.49} + 70%|██████▉ | 40180/57600 [7:03:35<2:57:13, 1.64it/s] 70%|██████▉ | 40181/57600 [7:03:36<2:57:01, 1.64it/s] 70%|██████▉ | 40182/57600 [7:03:36<3:00:39, 1.61it/s] 70%|██████▉ | 40183/57600 [7:03:37<3:01:37, 1.60it/s] 70%|██████▉ | 40184/57600 [7:03:38<2:58:43, 1.62it/s] 70%|██████▉ | 40185/57600 [7:03:38<3:03:30, 1.58it/s] 70%|██████▉ | 40186/57600 [7:03:39<2:57:57, 1.63it/s] 70%|██████▉ | 40187/57600 [7:03:40<2:59:51, 1.61it/s] 70%|██████▉ | 40188/57600 [7:03:40<3:07:46, 1.55it/s] 70%|██████▉ | 40189/57600 [7:03:41<3:07:13, 1.55it/s] 70%|██████▉ | 40190/57600 [7:03:42<3:03:46, 1.58it/s] 70%|██████▉ | 40191/57600 [7:03:42<3:07:46, 1.55it/s] 70%|██████▉ | 40192/57600 [7:03:43<3:09:14, 1.53it/s] 70%|██████▉ | 40193/57600 [7:03:44<3:14:44, 1.49it/s] 70%|██████▉ | 40194/57600 [7:03:44<3:11:11, 1.52it/s] 70%|██████▉ | 40195/57600 [7:03:45<3:10:21, 1.52it/s] 70%|██████▉ | 40196/57600 [7:03:45<3:03:45, 1.58it/s] 70%|██████▉ | 40197/57600 [7:03:46<3:03:02, 1.58it/s] 70%|██████▉ | 40198/57600 [7:03:47<3:02:16, 1.59it/s] 70%|██████▉ | 40199/57600 [7:03:47<2:59:15, 1.62it/s] 70%|██████▉ | 40200/57600 [7:03:48<3:01:31, 1.60it/s] {'loss': 1.1121, 'learning_rate': 3.7282229965156787e-07, 'epoch': 443.71} + 70%|██████▉ | 40200/57600 [7:03:48<3:01:31, 1.60it/s] 70%|██████▉ | 40201/57600 [7:03:49<2:59:24, 1.62it/s] 70%|██████▉ | 40202/57600 [7:03:49<3:01:55, 1.59it/s] 70%|██████▉ | 40203/57600 [7:03:50<2:58:14, 1.63it/s] 70%|██████▉ | 40204/57600 [7:03:50<3:01:29, 1.60it/s] 70%|██████▉ | 40205/57600 [7:03:51<2:59:36, 1.61it/s] 70%|██████▉ | 40206/57600 [7:03:52<3:01:26, 1.60it/s] 70%|██████▉ | 40207/57600 [7:03:52<3:00:45, 1.60it/s] 70%|██████▉ | 40208/57600 [7:03:53<3:00:44, 1.60it/s] 70%|██████▉ | 40209/57600 [7:03:54<2:58:58, 1.62it/s] 70%|██████▉ | 40210/57600 [7:03:54<3:11:17, 1.52it/s] 70%|██████▉ | 40211/57600 [7:03:55<3:11:42, 1.51it/s] 70%|██████▉ | 40212/57600 [7:03:56<3:16:25, 1.48it/s] 70%|██████▉ | 40213/57600 [7:03:56<3:17:19, 1.47it/s] 70%|██████▉ | 40214/57600 [7:03:57<3:08:49, 1.53it/s] 70%|██████▉ | 40215/57600 [7:03:58<3:07:27, 1.55it/s] 70%|██████▉ | 40216/57600 [7:03:58<3:02:43, 1.59it/s] 70%|██████▉ | 40217/57600 [7:03:59<3:00:31, 1.60it/s] 70%|██████▉ | 40218/57600 [7:03:59<2:59:10, 1.62it/s] 70%|██████▉ | 40219/57600 [7:04:00<3:05:14, 1.56it/s] 70%|██████▉ | 40220/57600 [7:04:01<3:01:22, 1.60it/s] {'loss': 1.121, 'learning_rate': 3.725087108013937e-07, 'epoch': 443.93} + 70%|██████▉ | 40220/57600 [7:04:01<3:01:22, 1.60it/s] 70%|██████▉ | 40221/57600 [7:04:01<3:02:32, 1.59it/s] 70%|██████▉ | 40222/57600 [7:04:02<2:58:30, 1.62it/s] 70%|██████▉ | 40223/57600 [7:04:02<2:57:41, 1.63it/s] 70%|██████▉ | 40224/57600 [7:04:03<3:02:29, 1.59it/s] 70%|██████▉ | 40225/57600 [7:04:04<2:59:48, 1.61it/s] 70%|██████▉ | 40226/57600 [7:04:04<2:58:36, 1.62it/s] 70%|██████▉ | 40227/57600 [7:04:05<3:08:54, 1.53it/s] 70%|██████▉ | 40228/57600 [7:04:06<3:07:13, 1.55it/s] 70%|██████▉ | 40229/57600 [7:04:06<3:04:44, 1.57it/s] 70%|██████▉ | 40230/57600 [7:04:07<3:11:55, 1.51it/s] 70%|██████▉ | 40231/57600 [7:04:08<3:13:39, 1.49it/s] 70%|██████▉ | 40232/57600 [7:04:08<3:05:37, 1.56it/s] 70%|██████▉ | 40233/57600 [7:04:09<3:05:46, 1.56it/s] 70%|██████▉ | 40234/57600 [7:04:10<3:02:15, 1.59it/s] 70%|██████▉ | 40235/57600 [7:04:10<2:59:01, 1.62it/s] 70%|██████▉ | 40236/57600 [7:04:11<2:59:04, 1.62it/s] 70%|██████▉ | 40237/57600 [7:04:12<3:06:43, 1.55it/s] 70%|██████▉ | 40238/57600 [7:04:12<3:00:43, 1.60it/s] 70%|██████▉ | 40239/57600 [7:04:13<2:58:35, 1.62it/s] 70%|██████▉ | 40240/57600 [7:04:13<2:58:05, 1.62it/s] {'loss': 1.1332, 'learning_rate': 3.7219512195121953e-07, 'epoch': 444.15} + 70%|██████▉ | 40240/57600 [7:04:13<2:58:05, 1.62it/s] 70%|██████▉ | 40241/57600 [7:04:14<2:56:33, 1.64it/s] 70%|██████▉ | 40242/57600 [7:04:15<3:01:20, 1.60it/s] 70%|██████▉ | 40243/57600 [7:04:15<3:03:14, 1.58it/s] 70%|██████▉ | 40244/57600 [7:04:16<3:13:23, 1.50it/s] 70%|██████▉ | 40245/57600 [7:04:17<3:13:22, 1.50it/s] 70%|██████▉ | 40246/57600 [7:04:17<3:08:38, 1.53it/s] 70%|██████▉ | 40247/57600 [7:04:18<3:05:04, 1.56it/s] 70%|██████▉ | 40248/57600 [7:04:18<3:03:00, 1.58it/s] 70%|██████▉ | 40249/57600 [7:04:19<2:59:37, 1.61it/s] 70%|██████▉ | 40250/57600 [7:04:20<3:05:18, 1.56it/s] 70%|██████▉ | 40251/57600 [7:04:20<3:00:52, 1.60it/s] 70%|██████▉ | 40252/57600 [7:04:21<2:58:59, 1.62it/s] 70%|██████▉ | 40253/57600 [7:04:22<2:58:57, 1.62it/s] 70%|██████▉ | 40254/57600 [7:04:22<3:04:09, 1.57it/s] 70%|██████▉ | 40255/57600 [7:04:23<3:07:01, 1.55it/s] 70%|██████▉ | 40256/57600 [7:04:24<3:08:37, 1.53it/s] 70%|██████▉ | 40257/57600 [7:04:24<3:02:32, 1.58it/s] 70%|██████▉ | 40258/57600 [7:04:25<3:04:49, 1.56it/s] 70%|██████▉ | 40259/57600 [7:04:25<3:08:00, 1.54it/s] 70%|██████▉ | 40260/57600 [7:04:26<3:06:03, 1.55it/s] {'loss': 1.1323, 'learning_rate': 3.7188153310104533e-07, 'epoch': 444.37} + 70%|██████▉ | 40260/57600 [7:04:26<3:06:03, 1.55it/s] 70%|██████▉ | 40261/57600 [7:04:27<3:09:46, 1.52it/s] 70%|██████▉ | 40262/57600 [7:04:27<3:05:39, 1.56it/s] 70%|██████▉ | 40263/57600 [7:04:28<3:05:21, 1.56it/s] 70%|██████▉ | 40264/57600 [7:04:29<3:03:17, 1.58it/s] 70%|██████▉ | 40265/57600 [7:04:29<2:56:51, 1.63it/s] 70%|██████▉ | 40266/57600 [7:04:30<3:02:59, 1.58it/s] 70%|██████▉ | 40267/57600 [7:04:31<3:04:39, 1.56it/s] 70%|██████▉ | 40268/57600 [7:04:31<3:09:19, 1.53it/s] 70%|██████▉ | 40269/57600 [7:04:32<3:05:01, 1.56it/s] 70%|██████▉ | 40270/57600 [7:04:32<2:59:30, 1.61it/s] 70%|██████▉ | 40271/57600 [7:04:33<3:00:50, 1.60it/s] 70%|██████▉ | 40272/57600 [7:04:34<3:02:48, 1.58it/s] 70%|██████▉ | 40273/57600 [7:04:34<2:58:49, 1.61it/s] 70%|██████▉ | 40274/57600 [7:04:35<2:53:59, 1.66it/s] 70%|██████▉ | 40275/57600 [7:04:35<2:54:23, 1.66it/s] 70%|██████▉ | 40276/57600 [7:04:36<2:55:22, 1.65it/s] 70%|██████▉ | 40277/57600 [7:04:37<2:53:15, 1.67it/s] 70%|██████▉ | 40278/57600 [7:04:37<2:54:41, 1.65it/s] 70%|██████▉ | 40279/57600 [7:04:38<2:58:17, 1.62it/s] 70%|██████▉ | 40280/57600 [7:04:39<2:53:06, 1.67it/s] {'loss': 1.1534, 'learning_rate': 3.715679442508711e-07, 'epoch': 444.59} + 70%|██████▉ | 40280/57600 [7:04:39<2:53:06, 1.67it/s] 70%|██████▉ | 40281/57600 [7:04:39<2:50:29, 1.69it/s] 70%|██████▉ | 40282/57600 [7:04:40<2:56:07, 1.64it/s] 70%|██████▉ | 40283/57600 [7:04:40<2:58:27, 1.62it/s] 70%|██████▉ | 40284/57600 [7:04:41<3:04:20, 1.57it/s] 70%|██████▉ | 40285/57600 [7:04:42<3:10:37, 1.51it/s] 70%|██████▉ | 40286/57600 [7:04:42<3:04:04, 1.57it/s] 70%|██████▉ | 40287/57600 [7:04:43<3:02:32, 1.58it/s] 70%|██████▉ | 40288/57600 [7:04:44<2:59:39, 1.61it/s] 70%|██████▉ | 40289/57600 [7:04:44<3:03:16, 1.57it/s] 70%|██████▉ | 40290/57600 [7:04:45<2:58:26, 1.62it/s] 70%|██████▉ | 40291/57600 [7:04:45<2:53:13, 1.67it/s] 70%|██████▉ | 40292/57600 [7:04:46<2:58:49, 1.61it/s] 70%|██████▉ | 40293/57600 [7:04:47<2:55:42, 1.64it/s] 70%|██████▉ | 40294/57600 [7:04:47<2:59:16, 1.61it/s] 70%|██████▉ | 40295/57600 [7:04:48<2:56:36, 1.63it/s] 70%|██████▉ | 40296/57600 [7:04:49<3:00:58, 1.59it/s] 70%|██████▉ | 40297/57600 [7:04:49<3:05:12, 1.56it/s] 70%|██████▉ | 40298/57600 [7:04:50<3:07:21, 1.54it/s] 70%|██████▉ | 40299/57600 [7:04:51<3:07:08, 1.54it/s] 70%|██████▉ | 40300/57600 [7:04:51<3:03:52, 1.57it/s] {'loss': 1.1098, 'learning_rate': 3.7125435540069684e-07, 'epoch': 444.81} + 70%|██████▉ | 40300/57600 [7:04:51<3:03:52, 1.57it/s] 70%|██████▉ | 40301/57600 [7:04:52<2:57:53, 1.62it/s] 70%|██████▉ | 40302/57600 [7:04:52<2:57:13, 1.63it/s] 70%|██████▉ | 40303/57600 [7:04:53<2:52:23, 1.67it/s] 70%|██████▉ | 40304/57600 [7:04:53<2:52:51, 1.67it/s] 70%|██████▉ | 40305/57600 [7:04:54<2:54:23, 1.65it/s] 70%|██████▉ | 40306/57600 [7:04:55<2:50:19, 1.69it/s] 70%|██████▉ | 40307/57600 [7:04:55<2:50:29, 1.69it/s] 70%|██████▉ | 40308/57600 [7:04:56<3:00:53, 1.59it/s] 70%|██████▉ | 40309/57600 [7:04:57<3:03:34, 1.57it/s] 70%|██████▉ | 40310/57600 [7:04:57<3:04:57, 1.56it/s] 70%|██████▉ | 40311/57600 [7:04:58<3:06:25, 1.55it/s] 70%|██████▉ | 40312/57600 [7:04:59<3:04:10, 1.56it/s] 70%|██████▉ | 40313/57600 [7:04:59<3:05:39, 1.55it/s] 70%|██████▉ | 40314/57600 [7:05:00<3:07:47, 1.53it/s] 70%|██████▉ | 40315/57600 [7:05:01<3:08:02, 1.53it/s] 70%|██████▉ | 40316/57600 [7:05:01<3:00:30, 1.60it/s] 70%|██████▉ | 40317/57600 [7:05:02<2:58:20, 1.62it/s] 70%|██████▉ | 40318/57600 [7:05:02<3:01:34, 1.59it/s] 70%|██████▉ | 40319/57600 [7:05:03<2:57:52, 1.62it/s] 70%|███████ | 40320/57600 [7:05:04<2:57:53, 1.62it/s] {'loss': 1.1334, 'learning_rate': 3.7094076655052264e-07, 'epoch': 445.03} + 70%|███████ | 40320/57600 [7:05:04<2:57:53, 1.62it/s] 70%|███████ | 40321/57600 [7:05:04<2:55:30, 1.64it/s] 70%|███████ | 40322/57600 [7:05:05<3:00:47, 1.59it/s] 70%|███████ | 40323/57600 [7:05:05<2:59:26, 1.60it/s] 70%|███████ | 40324/57600 [7:05:06<3:03:01, 1.57it/s] 70%|███████ | 40325/57600 [7:05:07<3:01:32, 1.59it/s] 70%|███████ | 40326/57600 [7:05:07<3:05:13, 1.55it/s] 70%|███████ | 40327/57600 [7:05:08<2:57:56, 1.62it/s] 70%|███████ | 40328/57600 [7:05:09<2:53:43, 1.66it/s] 70%|███████ | 40329/57600 [7:05:09<2:52:01, 1.67it/s] 70%|███████ | 40330/57600 [7:05:10<2:50:09, 1.69it/s] 70%|███████ | 40331/57600 [7:05:10<2:52:08, 1.67it/s] 70%|███████ | 40332/57600 [7:05:11<2:49:04, 1.70it/s] 70%|███████ | 40333/57600 [7:05:11<2:51:40, 1.68it/s] 70%|███████ | 40334/57600 [7:05:12<2:52:04, 1.67it/s] 70%|███████ | 40335/57600 [7:05:13<2:56:55, 1.63it/s] 70%|███████ | 40336/57600 [7:05:13<2:57:37, 1.62it/s] 70%|███████ | 40337/57600 [7:05:14<3:00:09, 1.60it/s] 70%|███████ | 40338/57600 [7:05:15<3:00:54, 1.59it/s] 70%|███████ | 40339/57600 [7:05:15<2:58:00, 1.62it/s] 70%|███████ | 40340/57600 [7:05:16<3:03:34, 1.57it/s] {'loss': 1.1431, 'learning_rate': 3.706271777003484e-07, 'epoch': 445.25} + 70%|███████ | 40340/57600 [7:05:16<3:03:34, 1.57it/s] 70%|███████ | 40341/57600 [7:05:17<3:00:41, 1.59it/s] 70%|███████ | 40342/57600 [7:05:17<2:58:55, 1.61it/s] 70%|███████ | 40343/57600 [7:05:18<3:01:15, 1.59it/s] 70%|███████ | 40344/57600 [7:05:18<2:59:30, 1.60it/s] 70%|███████ | 40345/57600 [7:05:19<2:56:58, 1.63it/s] 70%|███████ | 40346/57600 [7:05:20<3:01:33, 1.58it/s] 70%|███████ | 40347/57600 [7:05:20<3:01:17, 1.59it/s] 70%|███████ | 40348/57600 [7:05:21<3:03:01, 1.57it/s] 70%|███████ | 40349/57600 [7:05:22<3:07:20, 1.53it/s] 70%|███████ | 40350/57600 [7:05:22<3:02:38, 1.57it/s] 70%|███████ | 40351/57600 [7:05:23<2:59:29, 1.60it/s] 70%|███████ | 40352/57600 [7:05:23<2:58:42, 1.61it/s] 70%|███████ | 40353/57600 [7:05:24<3:02:05, 1.58it/s] 70%|███████ | 40354/57600 [7:05:25<3:01:45, 1.58it/s] 70%|███████ | 40355/57600 [7:05:25<2:58:45, 1.61it/s] 70%|███████ | 40356/57600 [7:05:26<3:07:50, 1.53it/s] 70%|███████ | 40357/57600 [7:05:27<3:14:05, 1.48it/s] 70%|███████ | 40358/57600 [7:05:27<3:06:42, 1.54it/s] 70%|███████ | 40359/57600 [7:05:28<3:01:18, 1.58it/s] 70%|███████ | 40360/57600 [7:05:29<3:05:38, 1.55it/s] {'loss': 1.1335, 'learning_rate': 3.703135888501742e-07, 'epoch': 445.47} + 70%|███████ | 40360/57600 [7:05:29<3:05:38, 1.55it/s] 70%|███████ | 40361/57600 [7:05:29<3:08:49, 1.52it/s] 70%|███████ | 40362/57600 [7:05:30<3:10:54, 1.50it/s] 70%|███████ | 40363/57600 [7:05:31<3:03:34, 1.56it/s] 70%|███████ | 40364/57600 [7:05:31<3:02:47, 1.57it/s] 70%|███████ | 40365/57600 [7:05:32<3:00:53, 1.59it/s] 70%|███████ | 40366/57600 [7:05:32<3:01:27, 1.58it/s] 70%|███████ | 40367/57600 [7:05:33<3:05:45, 1.55it/s] 70%|███████ | 40368/57600 [7:05:34<2:58:19, 1.61it/s] 70%|███████ | 40369/57600 [7:05:34<2:54:45, 1.64it/s] 70%|███████ | 40370/57600 [7:05:35<2:54:02, 1.65it/s] 70%|███████ | 40371/57600 [7:05:35<2:55:44, 1.63it/s] 70%|███████ | 40372/57600 [7:05:36<3:00:39, 1.59it/s] 70%|███████ | 40373/57600 [7:05:37<3:00:07, 1.59it/s] 70%|███████ | 40374/57600 [7:05:37<3:05:19, 1.55it/s] 70%|███████ | 40375/57600 [7:05:38<3:01:05, 1.59it/s] 70%|███████ | 40376/57600 [7:05:39<2:59:05, 1.60it/s] 70%|███████ | 40377/57600 [7:05:39<2:57:50, 1.61it/s] 70%|███████ | 40378/57600 [7:05:40<2:59:07, 1.60it/s] 70%|███████ | 40379/57600 [7:05:41<2:59:07, 1.60it/s] 70%|███████ | 40380/57600 [7:05:41<2:55:57, 1.63it/s] {'loss': 1.1261, 'learning_rate': 3.7e-07, 'epoch': 445.7} + 70%|███████ | 40380/57600 [7:05:41<2:55:57, 1.63it/s] 70%|███████ | 40381/57600 [7:05:42<2:56:28, 1.63it/s] 70%|███████ | 40382/57600 [7:05:42<2:59:33, 1.60it/s] 70%|███████ | 40383/57600 [7:05:43<3:00:17, 1.59it/s] 70%|███████ | 40384/57600 [7:05:44<3:01:12, 1.58it/s] 70%|███████ | 40385/57600 [7:05:44<2:56:39, 1.62it/s] 70%|███████ | 40386/57600 [7:05:45<2:55:48, 1.63it/s] 70%|███████ | 40387/57600 [7:05:46<3:02:32, 1.57it/s] 70%|███████ | 40388/57600 [7:05:46<3:00:02, 1.59it/s] 70%|███████ | 40389/57600 [7:05:47<3:00:37, 1.59it/s] 70%|███████ | 40390/57600 [7:05:47<3:00:17, 1.59it/s] 70%|███████ | 40391/57600 [7:05:48<3:00:50, 1.59it/s] 70%|███████ | 40392/57600 [7:05:49<3:02:32, 1.57it/s] 70%|███████ | 40393/57600 [7:05:49<2:58:08, 1.61it/s] 70%|███████ | 40394/57600 [7:05:50<3:00:02, 1.59it/s] 70%|███████ | 40395/57600 [7:05:51<2:58:40, 1.60it/s] 70%|███████ | 40396/57600 [7:05:51<3:01:01, 1.58it/s] 70%|███████ | 40397/57600 [7:05:52<3:07:39, 1.53it/s] 70%|███████ | 40398/57600 [7:05:53<3:09:10, 1.52it/s] 70%|███████ | 40399/57600 [7:05:53<3:00:31, 1.59it/s] 70%|███████ | 40400/57600 [7:05:54<3:00:31, 1.59it/s] {'loss': 1.115, 'learning_rate': 3.6968641114982576e-07, 'epoch': 445.92} + 70%|███████ | 40400/57600 [7:05:54<3:00:31, 1.59it/s] 70%|███████ | 40401/57600 [7:05:54<3:00:11, 1.59it/s] 70%|███████ | 40402/57600 [7:05:55<3:09:19, 1.51it/s] 70%|███████ | 40403/57600 [7:05:56<3:08:12, 1.52it/s] 70%|███████ | 40404/57600 [7:05:56<3:02:42, 1.57it/s] 70%|███████ | 40405/57600 [7:05:57<3:05:43, 1.54it/s] 70%|███████ | 40406/57600 [7:05:58<3:01:41, 1.58it/s] 70%|███████ | 40407/57600 [7:05:58<3:02:36, 1.57it/s] 70%|███████ | 40408/57600 [7:05:59<3:05:52, 1.54it/s] 70%|███████ | 40409/57600 [7:06:00<3:07:02, 1.53it/s] 70%|███████ | 40410/57600 [7:06:00<3:05:52, 1.54it/s] 70%|███████ | 40411/57600 [7:06:01<3:03:40, 1.56it/s] 70%|███████ | 40412/57600 [7:06:01<2:59:21, 1.60it/s] 70%|███████ | 40413/57600 [7:06:02<2:57:40, 1.61it/s] 70%|███████ | 40414/57600 [7:06:03<2:53:23, 1.65it/s] 70%|███████ | 40415/57600 [7:06:03<2:55:21, 1.63it/s] 70%|███████ | 40416/57600 [7:06:04<2:59:24, 1.60it/s] 70%|███████ | 40417/57600 [7:06:05<2:59:35, 1.59it/s] 70%|███████ | 40418/57600 [7:06:05<3:04:50, 1.55it/s] 70%|███████ | 40419/57600 [7:06:06<3:04:46, 1.55it/s] 70%|███████ | 40420/57600 [7:06:07<3:05:06, 1.55it/s] {'loss': 1.1489, 'learning_rate': 3.6937282229965156e-07, 'epoch': 446.14} + 70%|███████ | 40420/57600 [7:06:07<3:05:06, 1.55it/s] 70%|███████ | 40421/57600 [7:06:07<3:01:59, 1.57it/s] 70%|███████ | 40422/57600 [7:06:08<2:54:14, 1.64it/s] 70%|███████ | 40423/57600 [7:06:08<2:57:54, 1.61it/s] 70%|███████ | 40424/57600 [7:06:09<2:54:05, 1.64it/s] 70%|███████ | 40425/57600 [7:06:10<3:01:16, 1.58it/s] 70%|███████ | 40426/57600 [7:06:10<2:55:46, 1.63it/s] 70%|███████ | 40427/57600 [7:06:11<2:56:18, 1.62it/s] 70%|███████ | 40428/57600 [7:06:11<2:53:37, 1.65it/s] 70%|███████ | 40429/57600 [7:06:12<2:53:21, 1.65it/s] 70%|███████ | 40430/57600 [7:06:13<2:52:45, 1.66it/s] 70%|███████ | 40431/57600 [7:06:13<2:53:59, 1.64it/s] 70%|███████ | 40432/57600 [7:06:14<2:55:53, 1.63it/s] 70%|███████ | 40433/57600 [7:06:15<2:59:00, 1.60it/s] 70%|███████ | 40434/57600 [7:06:15<2:57:18, 1.61it/s] 70%|███████ | 40435/57600 [7:06:16<2:55:43, 1.63it/s] 70%|███████ | 40436/57600 [7:06:16<2:55:42, 1.63it/s] 70%|███████ | 40437/57600 [7:06:17<2:53:00, 1.65it/s] 70%|███████ | 40438/57600 [7:06:18<2:54:31, 1.64it/s] 70%|███████ | 40439/57600 [7:06:18<2:59:52, 1.59it/s] 70%|███████ | 40440/57600 [7:06:19<2:59:41, 1.59it/s] {'loss': 1.1683, 'learning_rate': 3.690592334494773e-07, 'epoch': 446.36} + 70%|███████ | 40440/57600 [7:06:19<2:59:41, 1.59it/s] 70%|███████ | 40441/57600 [7:06:19<2:58:44, 1.60it/s] 70%|███████ | 40442/57600 [7:06:20<2:56:10, 1.62it/s] 70%|███████ | 40443/57600 [7:06:21<2:51:59, 1.66it/s] 70%|███████ | 40444/57600 [7:06:21<2:52:54, 1.65it/s] 70%|███████ | 40445/57600 [7:06:22<2:53:16, 1.65it/s] 70%|███████ | 40446/57600 [7:06:22<2:57:25, 1.61it/s] 70%|███████ | 40447/57600 [7:06:23<3:02:16, 1.57it/s] 70%|███████ | 40448/57600 [7:06:24<3:08:26, 1.52it/s] 70%|███████ | 40449/57600 [7:06:25<3:06:09, 1.54it/s] 70%|███████ | 40450/57600 [7:06:25<3:01:30, 1.57it/s] 70%|███████ | 40451/57600 [7:06:26<2:58:09, 1.60it/s] 70%|███████ | 40452/57600 [7:06:26<2:57:06, 1.61it/s] 70%|███████ | 40453/57600 [7:06:27<2:56:21, 1.62it/s] 70%|███████ | 40454/57600 [7:06:28<3:03:54, 1.55it/s] 70%|███████ | 40455/57600 [7:06:28<3:01:35, 1.57it/s] 70%|███████ | 40456/57600 [7:06:29<2:59:52, 1.59it/s] 70%|███████ | 40457/57600 [7:06:29<2:58:33, 1.60it/s] 70%|███████ | 40458/57600 [7:06:30<2:59:42, 1.59it/s] 70%|███████ | 40459/57600 [7:06:31<3:09:06, 1.51it/s] 70%|███████ | 40460/57600 [7:06:32<3:13:22, 1.48it/s] {'loss': 1.1336, 'learning_rate': 3.687456445993031e-07, 'epoch': 446.58} + 70%|███████ | 40460/57600 [7:06:32<3:13:22, 1.48it/s] 70%|███████ | 40461/57600 [7:06:32<3:08:55, 1.51it/s] 70%|███████ | 40462/57600 [7:06:33<3:07:26, 1.52it/s] 70%|███���███ | 40463/57600 [7:06:33<3:03:55, 1.55it/s] 70%|███████ | 40464/57600 [7:06:34<2:58:06, 1.60it/s] 70%|███████ | 40465/57600 [7:06:35<2:59:54, 1.59it/s] 70%|███████ | 40466/57600 [7:06:35<2:55:56, 1.62it/s] 70%|███████ | 40467/57600 [7:06:36<2:57:21, 1.61it/s] 70%|███████ | 40468/57600 [7:06:37<2:59:35, 1.59it/s] 70%|███████ | 40469/57600 [7:06:37<2:58:45, 1.60it/s] 70%|███████ | 40470/57600 [7:06:38<3:04:35, 1.55it/s] 70%|███████ | 40471/57600 [7:06:39<3:05:11, 1.54it/s] 70%|███████ | 40472/57600 [7:06:39<3:03:14, 1.56it/s] 70%|███████ | 40473/57600 [7:06:40<2:58:26, 1.60it/s] 70%|███████ | 40474/57600 [7:06:40<3:05:44, 1.54it/s] 70%|███████ | 40475/57600 [7:06:41<3:04:41, 1.55it/s] 70%|███████ | 40476/57600 [7:06:42<3:01:08, 1.58it/s] 70%|███████ | 40477/57600 [7:06:42<3:03:58, 1.55it/s] 70%|███████ | 40478/57600 [7:06:43<3:02:20, 1.57it/s] 70%|███████ | 40479/57600 [7:06:44<3:03:27, 1.56it/s] 70%|███████ | 40480/57600 [7:06:44<2:58:13, 1.60it/s] {'loss': 1.1252, 'learning_rate': 3.6843205574912887e-07, 'epoch': 446.8} + 70%|███████ | 40480/57600 [7:06:44<2:58:13, 1.60it/s] 70%|███████ | 40481/57600 [7:06:45<3:03:24, 1.56it/s] 70%|███████ | 40482/57600 [7:06:45<2:59:22, 1.59it/s] 70%|███████ | 40483/57600 [7:06:46<3:04:54, 1.54it/s] 70%|███████ | 40484/57600 [7:06:47<3:06:08, 1.53it/s] 70%|███████ | 40485/57600 [7:06:47<3:03:16, 1.56it/s] 70%|███████ | 40486/57600 [7:06:48<3:01:23, 1.57it/s] 70%|███████ | 40487/57600 [7:06:49<2:59:27, 1.59it/s] 70%|███████ | 40488/57600 [7:06:49<3:05:01, 1.54it/s] 70%|███████ | 40489/57600 [7:06:50<3:03:07, 1.56it/s] 70%|███████ | 40490/57600 [7:06:51<3:00:19, 1.58it/s] 70%|███████ | 40491/57600 [7:06:51<2:58:11, 1.60it/s] 70%|███████ | 40492/57600 [7:06:52<3:02:54, 1.56it/s] 70%|███████ | 40493/57600 [7:06:53<3:00:37, 1.58it/s] 70%|███████ | 40494/57600 [7:06:53<2:58:26, 1.60it/s] 70%|███████ | 40495/57600 [7:06:54<2:55:23, 1.63it/s] 70%|███████ | 40496/57600 [7:06:54<2:53:19, 1.64it/s] 70%|███████ | 40497/57600 [7:06:55<2:54:03, 1.64it/s] 70%|███████ | 40498/57600 [7:06:56<2:56:50, 1.61it/s] 70%|███████ | 40499/57600 [7:06:56<3:06:37, 1.53it/s] 70%|███████ | 40500/57600 [7:06:57<3:05:01, 1.54it/s] {'loss': 1.1317, 'learning_rate': 3.681184668989547e-07, 'epoch': 447.02} + 70%|███████ | 40500/57600 [7:06:57<3:05:01, 1.54it/s] 70%|███████ | 40501/57600 [7:06:58<3:00:09, 1.58it/s] 70%|███████ | 40502/57600 [7:06:58<3:02:15, 1.56it/s] 70%|███████ | 40503/57600 [7:06:59<3:06:10, 1.53it/s] 70%|███████ | 40504/57600 [7:06:59<3:01:47, 1.57it/s] 70%|███████ | 40505/57600 [7:07:00<3:04:44, 1.54it/s] 70%|███████ | 40506/57600 [7:07:01<3:00:29, 1.58it/s] 70%|███████ | 40507/57600 [7:07:01<3:03:49, 1.55it/s] 70%|███████ | 40508/57600 [7:07:02<3:05:19, 1.54it/s] 70%|███████ | 40509/57600 [7:07:03<3:07:13, 1.52it/s] 70%|███████ | 40510/57600 [7:07:03<3:12:46, 1.48it/s] 70%|███████ | 40511/57600 [7:07:04<3:17:32, 1.44it/s] 70%|███████ | 40512/57600 [7:07:05<3:13:00, 1.48it/s] 70%|███████ | 40513/57600 [7:07:05<3:06:04, 1.53it/s] 70%|███████ | 40514/57600 [7:07:06<3:11:34, 1.49it/s] 70%|███████ | 40515/57600 [7:07:07<3:08:35, 1.51it/s] 70%|███████ | 40516/57600 [7:07:07<3:03:30, 1.55it/s] 70%|███████ | 40517/57600 [7:07:08<2:56:40, 1.61it/s] 70%|███████ | 40518/57600 [7:07:09<3:01:06, 1.57it/s] 70%|███████ | 40519/57600 [7:07:09<2:58:15, 1.60it/s] 70%|███████ | 40520/57600 [7:07:10<2:59:52, 1.58it/s] {'loss': 1.1273, 'learning_rate': 3.6780487804878053e-07, 'epoch': 447.24} + 70%|███████ | 40520/57600 [7:07:10<2:59:52, 1.58it/s] 70%|███████ | 40521/57600 [7:07:10<2:55:54, 1.62it/s] 70%|███████ | 40522/57600 [7:07:11<2:57:14, 1.61it/s] 70%|███████ | 40523/57600 [7:07:12<2:56:36, 1.61it/s] 70%|███████ | 40524/57600 [7:07:12<2:59:25, 1.59it/s] 70%|███████ | 40525/57600 [7:07:13<2:56:30, 1.61it/s] 70%|███████ | 40526/57600 [7:07:14<2:58:27, 1.59it/s] 70%|███████ | 40527/57600 [7:07:14<3:00:05, 1.58it/s] 70%|███████ | 40528/57600 [7:07:15<2:53:10, 1.64it/s] 70%|███████ | 40529/57600 [7:07:15<2:56:19, 1.61it/s] 70%|███████ | 40530/57600 [7:07:16<2:57:39, 1.60it/s] 70%|███████ | 40531/57600 [7:07:17<3:00:47, 1.57it/s] 70%|███████ | 40532/57600 [7:07:17<2:59:42, 1.58it/s] 70%|███████ | 40533/57600 [7:07:18<2:56:22, 1.61it/s] 70%|███████ | 40534/57600 [7:07:19<2:57:12, 1.61it/s] 70%|███████ | 40535/57600 [7:07:19<3:01:27, 1.57it/s] 70%|███████ | 40536/57600 [7:07:20<2:58:54, 1.59it/s] 70%|███████ | 40537/57600 [7:07:20<2:53:57, 1.63it/s] 70%|███████ | 40538/57600 [7:07:21<2:55:16, 1.62it/s] 70%|███████ | 40539/57600 [7:07:22<2:56:55, 1.61it/s] 70%|███████ | 40540/57600 [7:07:22<2:55:35, 1.62it/s] {'loss': 1.1509, 'learning_rate': 3.6749128919860623e-07, 'epoch': 447.46} + 70%|███████ | 40540/57600 [7:07:22<2:55:35, 1.62it/s] 70%|███████ | 40541/57600 [7:07:23<2:56:41, 1.61it/s] 70%|███████ | 40542/57600 [7:07:24<2:54:36, 1.63it/s] 70%|███████ | 40543/57600 [7:07:24<2:59:34, 1.58it/s] 70%|███████ | 40544/57600 [7:07:25<2:54:30, 1.63it/s] 70%|███████ | 40545/57600 [7:07:25<2:52:58, 1.64it/s] 70%|███████ | 40546/57600 [7:07:26<2:58:10, 1.60it/s] 70%|███████ | 40547/57600 [7:07:27<2:54:37, 1.63it/s] 70%|███████ | 40548/57600 [7:07:27<3:09:31, 1.50it/s] 70%|███████ | 40549/57600 [7:07:28<3:09:46, 1.50it/s] 70%|███████ | 40550/57600 [7:07:29<3:05:01, 1.54it/s] 70%|███████ | 40551/57600 [7:07:29<3:01:26, 1.57it/s] 70%|███████ | 40552/57600 [7:07:30<2:55:35, 1.62it/s] 70%|███████ | 40553/57600 [7:07:30<2:52:09, 1.65it/s] 70%|███████ | 40554/57600 [7:07:31<2:47:37, 1.69it/s] 70%|███████ | 40555/57600 [7:07:32<2:57:07, 1.60it/s] 70%|███████ | 40556/57600 [7:07:32<2:56:40, 1.61it/s] 70%|███████ | 40557/57600 [7:07:33<2:57:43, 1.60it/s] 70%|███████ | 40558/57600 [7:07:34<2:56:56, 1.61it/s] 70%|███████ | 40559/57600 [7:07:34<2:55:09, 1.62it/s] 70%|███████ | 40560/57600 [7:07:35<2:53:31, 1.64it/s] {'loss': 1.1495, 'learning_rate': 3.6717770034843204e-07, 'epoch': 447.68} + 70%|███████ | 40560/57600 [7:07:35<2:53:31, 1.64it/s] 70%|███████ | 40561/57600 [7:07:35<2:58:20, 1.59it/s] 70%|███████ | 40562/57600 [7:07:36<3:00:05, 1.58it/s] 70%|███████ | 40563/57600 [7:07:37<3:02:50, 1.55it/s] 70%|███████ | 40564/57600 [7:07:37<3:00:17, 1.57it/s] 70%|███████ | 40565/57600 [7:07:38<2:54:44, 1.62it/s] 70%|███████ | 40566/57600 [7:07:39<2:52:39, 1.64it/s] 70%|███████ | 40567/57600 [7:07:39<2:57:25, 1.60it/s] 70%|███████ | 40568/57600 [7:07:40<2:57:06, 1.60it/s] 70%|███████ | 40569/57600 [7:07:40<2:53:53, 1.63it/s] 70%|███████ | 40570/57600 [7:07:41<2:58:52, 1.59it/s] 70%|███████ | 40571/57600 [7:07:42<2:58:50, 1.59it/s] 70%|███████ | 40572/57600 [7:07:42<2:59:07, 1.58it/s] 70%|███████ | 40573/57600 [7:07:43<2:59:12, 1.58it/s] 70%|███████ | 40574/57600 [7:07:44<2:55:21, 1.62it/s] 70%|███████ | 40575/57600 [7:07:44<2:51:52, 1.65it/s] 70%|███████ | 40576/57600 [7:07:45<2:56:06, 1.61it/s] 70%|███████ | 40577/57600 [7:07:45<2:58:28, 1.59it/s] 70%|███████ | 40578/57600 [7:07:46<2:58:27, 1.59it/s] 70%|███████ | 40579/57600 [7:07:47<3:02:41, 1.55it/s] 70%|███████ | 40580/57600 [7:07:47<3:02:37, 1.55it/s] {'loss': 1.1304, 'learning_rate': 3.668641114982578e-07, 'epoch': 447.9} + 70%|███████ | 40580/57600 [7:07:47<3:02:37, 1.55it/s] 70%|███████ | 40581/57600 [7:07:48<3:00:13, 1.57it/s] 70%|███████ | 40582/57600 [7:07:49<3:05:23, 1.53it/s] 70%|███████ | 40583/57600 [7:07:49<3:00:20, 1.57it/s] 70%|███████ | 40584/57600 [7:07:50<3:02:19, 1.56it/s] 70%|███████ | 40585/57600 [7:07:51<2:59:20, 1.58it/s] 70%|███████ | 40586/57600 [7:07:51<2:53:04, 1.64it/s] 70%|███████ | 40587/57600 [7:07:52<2:55:59, 1.61it/s] 70%|███████ | 40588/57600 [7:07:52<2:51:41, 1.65it/s] 70%|███████ | 40589/57600 [7:07:53<3:02:50, 1.55it/s] 70%|███████ | 40590/57600 [7:07:54<3:01:25, 1.56it/s] 70%|███████ | 40591/57600 [7:07:54<3:00:36, 1.57it/s] 70%|███████ | 40592/57600 [7:07:55<2:54:59, 1.62it/s] 70%|███████ | 40593/57600 [7:07:56<2:57:56, 1.59it/s] 70%|███████ | 40594/57600 [7:07:56<2:55:57, 1.61it/s] 70%|███████ | 40595/57600 [7:07:57<2:59:10, 1.58it/s] 70%|███████ | 40596/57600 [7:07:57<3:00:12, 1.57it/s] 70%|███████ | 40597/57600 [7:07:58<3:05:17, 1.53it/s] 70%|███████ | 40598/57600 [7:07:59<3:04:35, 1.54it/s] 70%|███████ | 40599/57600 [7:07:59<2:58:56, 1.58it/s] 70%|███████ | 40600/57600 [7:08:00<2:57:05, 1.60it/s] {'loss': 1.1187, 'learning_rate': 3.665505226480836e-07, 'epoch': 448.12} + 70%|███████ | 40600/57600 [7:08:00<2:57:05, 1.60it/s] 70%|███████ | 40601/57600 [7:08:01<2:58:47, 1.58it/s] 70%|███████ | 40602/57600 [7:08:01<3:05:02, 1.53it/s] 70%|███████ | 40603/57600 [7:08:02<3:06:57, 1.52it/s] 70%|███████ | 40604/57600 [7:08:03<3:03:01, 1.55it/s] 70%|███████ | 40605/57600 [7:08:03<3:07:17, 1.51it/s] 70%|███████ | 40606/57600 [7:08:04<3:03:45, 1.54it/s] 70%|███████ | 40607/57600 [7:08:05<3:03:33, 1.54it/s] 70%|███████ | 40608/57600 [7:08:05<2:57:19, 1.60it/s] 71%|███████ | 40609/57600 [7:08:06<2:56:38, 1.60it/s] 71%|███████ | 40610/57600 [7:08:06<2:59:15, 1.58it/s] 71%|███████ | 40611/57600 [7:08:07<2:54:51, 1.62it/s] 71%|███████ | 40612/57600 [7:08:08<2:53:20, 1.63it/s] 71%|███████ | 40613/57600 [7:08:08<2:53:19, 1.63it/s] 71%|███████ | 40614/57600 [7:08:09<2:53:25, 1.63it/s] 71%|███████ | 40615/57600 [7:08:10<3:02:26, 1.55it/s] 71%|███████ | 40616/57600 [7:08:10<2:59:02, 1.58it/s] 71%|███████ | 40617/57600 [7:08:11<3:02:53, 1.55it/s] 71%|███████ | 40618/57600 [7:08:11<2:58:27, 1.59it/s] 71%|███████ | 40619/57600 [7:08:12<2:57:15, 1.60it/s] 71%|███████ | 40620/57600 [7:08:13<2:57:54, 1.59it/s] {'loss': 1.1221, 'learning_rate': 3.6623693379790935e-07, 'epoch': 448.34} + 71%|███████ | 40620/57600 [7:08:13<2:57:54, 1.59it/s] 71%|███████ | 40621/57600 [7:08:13<2:59:59, 1.57it/s] 71%|███████ | 40622/57600 [7:08:14<2:59:58, 1.57it/s] 71%|███████ | 40623/57600 [7:08:15<2:58:08, 1.59it/s] 71%|███████ | 40624/57600 [7:08:15<3:02:38, 1.55it/s] 71%|███████ | 40625/57600 [7:08:16<3:05:09, 1.53it/s] 71%|███████ | 40626/57600 [7:08:17<3:00:20, 1.57it/s] 71%|███████ | 40627/57600 [7:08:17<2:56:23, 1.60it/s] 71%|███████ | 40628/57600 [7:08:18<2:49:44, 1.67it/s] 71%|███████ | 40629/57600 [7:08:18<2:51:36, 1.65it/s] 71%|███████ | 40630/57600 [7:08:19<2:47:57, 1.68it/s] 71%|███████ | 40631/57600 [7:08:20<2:56:14, 1.60it/s] 71%|███████ | 40632/57600 [7:08:20<2:55:22, 1.61it/s] 71%|███████ | 40633/57600 [7:08:21<2:54:58, 1.62it/s] 71%|███████ | 40634/57600 [7:08:21<2:56:50, 1.60it/s] 71%|███████ | 40635/57600 [7:08:22<2:57:22, 1.59it/s] 71%|███████ | 40636/57600 [7:08:23<2:59:39, 1.57it/s] 71%|███████ | 40637/57600 [7:08:23<2:56:52, 1.60it/s] 71%|███████ | 40638/57600 [7:08:24<2:58:55, 1.58it/s] 71%|███████ | 40639/57600 [7:08:25<2:52:55, 1.63it/s] 71%|███████ | 40640/57600 [7:08:25<2:54:46, 1.62it/s] {'loss': 1.1638, 'learning_rate': 3.6592334494773515e-07, 'epoch': 448.57} + 71%|███████ | 40640/57600 [7:08:25<2:54:46, 1.62it/s] 71%|███████ | 40641/57600 [7:08:26<3:04:27, 1.53it/s] 71%|███████ | 40642/57600 [7:08:27<2:59:30, 1.57it/s] 71%|███████ | 40643/57600 [7:08:27<3:02:24, 1.55it/s] 71%|███████ | 40644/57600 [7:08:28<2:59:21, 1.58it/s] 71%|███████ | 40645/57600 [7:08:28<2:58:15, 1.59it/s] 71%|███████ | 40646/57600 [7:08:29<2:55:15, 1.61it/s] 71%|███████ | 40647/57600 [7:08:30<3:00:25, 1.57it/s] 71%|███████ | 40648/57600 [7:08:30<2:57:43, 1.59it/s] 71%|███████ | 40649/57600 [7:08:31<2:54:42, 1.62it/s] 71%|███████ | 40650/57600 [7:08:32<2:58:47, 1.58it/s] 71%|███████ | 40651/57600 [7:08:32<2:55:04, 1.61it/s] 71%|███████ | 40652/57600 [7:08:33<3:00:53, 1.56it/s] 71%|███████ | 40653/57600 [7:08:33<2:57:31, 1.59it/s] 71%|███████ | 40654/57600 [7:08:34<2:53:42, 1.63it/s] 71%|███████ | 40655/57600 [7:08:35<2:53:38, 1.63it/s] 71%|███████ | 40656/57600 [7:08:35<2:54:19, 1.62it/s] 71%|███████ | 40657/57600 [7:08:36<2:56:30, 1.60it/s] 71%|███████ | 40658/57600 [7:08:37<2:59:02, 1.58it/s] 71%|███████ | 40659/57600 [7:08:37<2:58:05, 1.59it/s] 71%|███████ | 40660/57600 [7:08:38<3:02:00, 1.55it/s] {'loss': 1.1179, 'learning_rate': 3.65609756097561e-07, 'epoch': 448.79} + 71%|███████ | 40660/57600 [7:08:38<3:02:00, 1.55it/s] 71%|███████ | 40661/57600 [7:08:39<3:06:07, 1.52it/s] 71%|███████ | 40662/57600 [7:08:39<3:04:20, 1.53it/s] 71%|███████ | 40663/57600 [7:08:40<2:58:07, 1.58it/s] 71%|███████ | 40664/57600 [7:08:40<3:00:57, 1.56it/s] 71%|███████ | 40665/57600 [7:08:41<2:57:00, 1.59it/s] 71%|███████ | 40666/57600 [7:08:42<2:53:20, 1.63it/s] 71%|███████ | 40667/57600 [7:08:42<2:54:58, 1.61it/s] 71%|███████ | 40668/57600 [7:08:43<3:00:46, 1.56it/s] 71%|███████ | 40669/57600 [7:08:44<2:58:58, 1.58it/s] 71%|███████ | 40670/57600 [7:08:44<2:58:32, 1.58it/s] 71%|███████ | 40671/57600 [7:08:45<2:52:21, 1.64it/s] 71%|███████ | 40672/57600 [7:08:45<2:49:16, 1.67it/s] 71%|███████ | 40673/57600 [7:08:46<2:59:20, 1.57it/s] 71%|███████ | 40674/57600 [7:08:47<2:54:06, 1.62it/s] 71%|███████ | 40675/57600 [7:08:47<2:51:47, 1.64it/s] 71%|███████ | 40676/57600 [7:08:48<2:49:44, 1.66it/s] 71%|███████ | 40677/57600 [7:08:48<2:52:00, 1.64it/s] 71%|███████ | 40678/57600 [7:08:49<2:50:34, 1.65it/s] 71%|███████ | 40679/57600 [7:08:50<2:47:28, 1.68it/s] 71%|███████ | 40680/57600 [7:08:50<2:59:19, 1.57it/s] {'loss': 1.131, 'learning_rate': 3.652961672473867e-07, 'epoch': 449.01} + 71%|███████ | 40680/57600 [7:08:50<2:59:19, 1.57it/s] 71%|███████ | 40681/57600 [7:08:51<2:57:20, 1.59it/s] 71%|███████ | 40682/57600 [7:08:52<2:55:56, 1.60it/s] 71%|███████ | 40683/57600 [7:08:52<3:05:41, 1.52it/s] 71%|███████ | 40684/57600 [7:08:53<3:03:06, 1.54it/s] 71%|███████ | 40685/57600 [7:08:54<3:04:09, 1.53it/s] 71%|███████ | 40686/57600 [7:08:54<3:02:33, 1.54it/s] 71%|███████ | 40687/57600 [7:08:55<2:55:12, 1.61it/s] 71%|███████ | 40688/57600 [7:08:55<2:50:47, 1.65it/s] 71%|███████ | 40689/57600 [7:08:56<2:47:57, 1.68it/s] 71%|███████ | 40690/57600 [7:08:57<2:51:11, 1.65it/s] 71%|███████ | 40691/57600 [7:08:57<2:50:13, 1.66it/s] 71%|███████ | 40692/57600 [7:08:58<2:51:36, 1.64it/s] 71%|███████ | 40693/57600 [7:08:58<2:58:36, 1.58it/s] 71%|███████ | 40694/57600 [7:08:59<2:59:36, 1.57it/s] 71%|███████ | 40695/57600 [7:09:00<2:56:18, 1.60it/s] 71%|███████ | 40696/57600 [7:09:00<2:56:34, 1.60it/s] 71%|███████ | 40697/57600 [7:09:01<2:50:58, 1.65it/s] 71%|███████ | 40698/57600 [7:09:02<2:50:30, 1.65it/s] 71%|███████ | 40699/57600 [7:09:02<2:50:26, 1.65it/s] 71%|███████ | 40700/57600 [7:09:03<2:52:58, 1.63it/s] {'loss': 1.1289, 'learning_rate': 3.6498257839721256e-07, 'epoch': 449.23} + 71%|███████ | 40700/57600 [7:09:03<2:52:58, 1.63it/s] 71%|███████ | 40701/57600 [7:09:03<2:55:33, 1.60it/s] 71%|███████ | 40702/57600 [7:09:04<2:51:53, 1.64it/s] 71%|███████ | 40703/57600 [7:09:05<2:49:19, 1.66it/s] 71%|███████ | 40704/57600 [7:09:05<2:49:56, 1.66it/s] 71%|███████ | 40705/57600 [7:09:06<2:51:17, 1.64it/s] 71%|███████ | 40706/57600 [7:09:06<2:56:21, 1.60it/s] 71%|███████ | 40707/57600 [7:09:07<2:58:39, 1.58it/s] 71%|███████ | 40708/57600 [7:09:08<2:58:39, 1.58it/s] 71%|███████ | 40709/57600 [7:09:08<3:06:29, 1.51it/s] 71%|███████ | 40710/57600 [7:09:09<3:09:15, 1.49it/s] 71%|███████ | 40711/57600 [7:09:10<3:11:51, 1.47it/s] 71%|███████ | 40712/57600 [7:09:10<3:05:57, 1.51it/s] 71%|███████ | 40713/57600 [7:09:11<3:03:19, 1.54it/s] 71%|███████ | 40714/57600 [7:09:12<3:11:00, 1.47it/s] 71%|███████ | 40715/57600 [7:09:12<3:04:44, 1.52it/s] 71%|███████ | 40716/57600 [7:09:13<2:57:26, 1.59it/s] 71%|███████ | 40717/57600 [7:09:14<2:53:59, 1.62it/s] 71%|███████ | 40718/57600 [7:09:14<3:00:23, 1.56it/s] 71%|███████ | 40719/57600 [7:09:15<2:53:42, 1.62it/s] 71%|███████ | 40720/57600 [7:09:16<2:56:31, 1.59it/s] {'loss': 1.1436, 'learning_rate': 3.6466898954703826e-07, 'epoch': 449.45} + 71%|███████ | 40720/57600 [7:09:16<2:56:31, 1.59it/s] 71%|███████ | 40721/57600 [7:09:16<2:55:04, 1.61it/s] 71%|███████ | 40722/57600 [7:09:17<2:53:00, 1.63it/s] 71%|███████ | 40723/57600 [7:09:17<2:53:10, 1.62it/s] 71%|███████ | 40724/57600 [7:09:18<2:56:21, 1.59it/s] 71%|███████ | 40725/57600 [7:09:19<3:04:42, 1.52it/s] 71%|███████ | 40726/57600 [7:09:19<3:03:15, 1.53it/s] 71%|███████ | 40727/57600 [7:09:20<3:00:50, 1.56it/s] 71%|███████ | 40728/57600 [7:09:21<3:02:08, 1.54it/s] 71%|███████ | 40729/57600 [7:09:21<3:04:02, 1.53it/s] 71%|███████ | 40730/57600 [7:09:22<3:00:04, 1.56it/s] 71%|███████ | 40731/57600 [7:09:23<3:01:15, 1.55it/s] 71%|███████ | 40732/57600 [7:09:23<3:00:06, 1.56it/s] 71%|███████ | 40733/57600 [7:09:24<3:03:04, 1.54it/s] 71%|███████ | 40734/57600 [7:09:25<3:06:29, 1.51it/s] 71%|███████ | 40735/57600 [7:09:25<3:03:52, 1.53it/s] 71%|███████ | 40736/57600 [7:09:26<2:59:54, 1.56it/s] 71%|███████ | 40737/57600 [7:09:26<3:00:47, 1.55it/s] 71%|███████ | 40738/57600 [7:09:27<3:00:11, 1.56it/s] 71%|███████ | 40739/57600 [7:09:28<2:57:06, 1.59it/s] 71%|███████ | 40740/57600 [7:09:28<2:54:36, 1.61it/s] {'loss': 1.1178, 'learning_rate': 3.643554006968641e-07, 'epoch': 449.67} + 71%|███████ | 40740/57600 [7:09:28<2:54:36, 1.61it/s] 71%|███████ | 40741/57600 [7:09:29<2:53:00, 1.62it/s] 71%|███████ | 40742/57600 [7:09:30<2:54:00, 1.61it/s] 71%|███████ | 40743/57600 [7:09:30<2:51:50, 1.64it/s] 71%|███████ | 40744/57600 [7:09:31<2:54:48, 1.61it/s] 71%|███████ | 40745/57600 [7:09:31<2:55:11, 1.60it/s] 71%|███████ | 40746/57600 [7:09:32<2:55:23, 1.60it/s] 71%|███████ | 40747/57600 [7:09:33<2:49:39, 1.66it/s] 71%|███████ | 40748/57600 [7:09:33<2:57:01, 1.59it/s] 71%|███████ | 40749/57600 [7:09:34<2:57:54, 1.58it/s] 71%|███████ | 40750/57600 [7:09:35<2:56:22, 1.59it/s] 71%|███████ | 40751/57600 [7:09:35<2:51:37, 1.64it/s] 71%|███████ | 40752/57600 [7:09:36<3:00:12, 1.56it/s] 71%|███████ | 40753/57600 [7:09:36<2:56:17, 1.59it/s] 71%|███████ | 40754/57600 [7:09:37<2:58:34, 1.57it/s] 71%|███████ | 40755/57600 [7:09:38<2:59:31, 1.56it/s] 71%|███████ | 40756/57600 [7:09:38<2:58:11, 1.58it/s] 71%|███████ | 40757/57600 [7:09:39<2:56:41, 1.59it/s] 71%|███████ | 40758/57600 [7:09:40<2:54:15, 1.61it/s] 71%|███████ | 40759/57600 [7:09:40<2:59:41, 1.56it/s] 71%|███████ | 40760/57600 [7:09:41<2:57:56, 1.58it/s] {'loss': 1.1459, 'learning_rate': 3.640418118466899e-07, 'epoch': 449.89} + 71%|███████ | 40760/57600 [7:09:41<2:57:56, 1.58it/s] 71%|███████ | 40761/57600 [7:09:41<2:56:18, 1.59it/s] 71%|███████ | 40762/57600 [7:09:42<2:52:34, 1.63it/s] 71%|███████ | 40763/57600 [7:09:43<2:54:03, 1.61it/s] 71%|███████ | 40764/57600 [7:09:43<2:53:17, 1.62it/s] 71%|███████ | 40765/57600 [7:09:44<2:51:23, 1.64it/s] 71%|███████ | 40766/57600 [7:09:44<2:48:17, 1.67it/s] 71%|███████ | 40767/57600 [7:09:45<2:54:31, 1.61it/s] 71%|███████ | 40768/57600 [7:09:46<2:51:04, 1.64it/s] 71%|███████ | 40769/57600 [7:09:46<2:53:42, 1.61it/s] 71%|███████ | 40770/57600 [7:09:47<2:52:08, 1.63it/s] 71%|███████ | 40771/57600 [7:09:48<2:55:48, 1.60it/s] 71%|███████ | 40772/57600 [7:09:48<3:01:47, 1.54it/s] 71%|███████ | 40773/57600 [7:09:49<2:58:37, 1.57it/s] 71%|███████ | 40774/57600 [7:09:50<2:59:02, 1.57it/s] 71%|███████ | 40775/57600 [7:09:50<2:57:14, 1.58it/s] 71%|███████ | 40776/57600 [7:09:51<2:54:36, 1.61it/s] 71%|███████ | 40777/57600 [7:09:52<3:01:00, 1.55it/s] 71%|███████ | 40778/57600 [7:09:52<3:01:42, 1.54it/s] 71%|███████ | 40779/57600 [7:09:53<3:02:51, 1.53it/s] 71%|███████ | 40780/57600 [7:09:53<2:56:55, 1.58it/s] {'loss': 1.1443, 'learning_rate': 3.637282229965157e-07, 'epoch': 450.11} + 71%|███████ | 40780/57600 [7:09:53<2:56:55, 1.58it/s] 71%|███████ | 40781/57600 [7:09:54<2:57:25, 1.58it/s] 71%|███████ | 40782/57600 [7:09:55<2:53:21, 1.62it/s] 71%|███████ | 40783/57600 [7:09:55<2:53:05, 1.62it/s] 71%|███████ | 40784/57600 [7:09:56<2:59:12, 1.56it/s] 71%|███████ | 40785/57600 [7:09:57<3:00:29, 1.55it/s] 71%|███████ | 40786/57600 [7:09:57<3:02:43, 1.53it/s] 71%|███████ | 40787/57600 [7:09:58<2:57:18, 1.58it/s] 71%|███████ | 40788/57600 [7:09:58<2:53:20, 1.62it/s] 71%|███████ | 40789/57600 [7:09:59<2:53:56, 1.61it/s] 71%|███████ | 40790/57600 [7:10:00<2:46:34, 1.68it/s] 71%|███████ | 40791/57600 [7:10:00<2:57:10, 1.58it/s] 71%|███████ | 40792/57600 [7:10:01<2:55:06, 1.60it/s] 71%|███████ | 40793/57600 [7:10:02<2:59:14, 1.56it/s] 71%|███████ | 40794/57600 [7:10:02<2:59:12, 1.56it/s] 71%|███████ | 40795/57600 [7:10:03<3:03:42, 1.52it/s] 71%|███████ | 40796/57600 [7:10:04<3:02:04, 1.54it/s] 71%|███████ | 40797/57600 [7:10:04<3:03:15, 1.53it/s] 71%|███████ | 40798/57600 [7:10:05<2:58:53, 1.57it/s] 71%|███████ | 40799/57600 [7:10:05<3:00:45, 1.55it/s] 71%|███████ | 40800/57600 [7:10:06<3:02:15, 1.54it/s] {'loss': 1.1279, 'learning_rate': 3.634146341463415e-07, 'epoch': 450.33} + 71%|███████ | 40800/57600 [7:10:06<3:02:15, 1.54it/s] 71%|███████ | 40801/57600 [7:10:07<3:06:31, 1.50it/s] 71%|███████ | 40802/57600 [7:10:07<3:03:17, 1.53it/s] 71%|███████ | 40803/57600 [7:10:08<3:01:13, 1.54it/s] 71%|███████ | 40804/57600 [7:10:09<3:03:17, 1.53it/s] 71%|███████ | 40805/57600 [7:10:09<3:00:47, 1.55it/s] 71%|███████ | 40806/57600 [7:10:10<2:53:55, 1.61it/s] 71%|███████ | 40807/57600 [7:10:11<2:55:12, 1.60it/s] 71%|███████ | 40808/57600 [7:10:11<2:51:42, 1.63it/s] 71%|███████ | 40809/57600 [7:10:12<2:55:10, 1.60it/s] 71%|███████ | 40810/57600 [7:10:12<2:55:31, 1.59it/s] 71%|███████ | 40811/57600 [7:10:13<2:50:07, 1.64it/s] 71%|███████ | 40812/57600 [7:10:14<2:50:13, 1.64it/s] 71%|███████ | 40813/57600 [7:10:14<2:52:29, 1.62it/s] 71%|███████ | 40814/57600 [7:10:15<2:55:46, 1.59it/s] 71%|███████ | 40815/57600 [7:10:16<2:58:36, 1.57it/s] 71%|███████ | 40816/57600 [7:10:16<2:56:03, 1.59it/s] 71%|███████ | 40817/57600 [7:10:17<2:55:14, 1.60it/s] 71%|███████ | 40818/57600 [7:10:17<2:51:41, 1.63it/s] 71%|███████ | 40819/57600 [7:10:18<2:53:51, 1.61it/s] 71%|███████ | 40820/57600 [7:10:19<2:51:54, 1.63it/s] {'loss': 1.1468, 'learning_rate': 3.631010452961672e-07, 'epoch': 450.55} + 71%|███████ | 40820/57600 [7:10:19<2:51:54, 1.63it/s] 71%|███████ | 40821/57600 [7:10:19<2:47:33, 1.67it/s] 71%|███████ | 40822/57600 [7:10:20<2:55:36, 1.59it/s] 71%|███████ | 40823/57600 [7:10:21<2:56:24, 1.59it/s] 71%|███████ | 40824/57600 [7:10:21<2:58:31, 1.57it/s] 71%|███████ | 40825/57600 [7:10:22<2:55:34, 1.59it/s] 71%|███████ | 40826/57600 [7:10:22<2:58:54, 1.56it/s] 71%|███████ | 40827/57600 [7:10:23<2:56:39, 1.58it/s] 71%|███████ | 40828/57600 [7:10:24<2:53:52, 1.61it/s] 71%|███████ | 40829/57600 [7:10:24<2:51:44, 1.63it/s] 71%|███████ | 40830/57600 [7:10:25<2:50:45, 1.64it/s] 71%|███████ | 40831/57600 [7:10:26<2:54:02, 1.61it/s] 71%|███████ | 40832/57600 [7:10:26<2:51:52, 1.63it/s] 71%|███████ | 40833/57600 [7:10:27<2:52:20, 1.62it/s] 71%|███████ | 40834/57600 [7:10:27<2:50:27, 1.64it/s] 71%|███████ | 40835/57600 [7:10:28<2:50:38, 1.64it/s] 71%|███████ | 40836/57600 [7:10:29<2:54:39, 1.60it/s] 71%|███████ | 40837/57600 [7:10:29<2:52:13, 1.62it/s] 71%|███████ | 40838/57600 [7:10:30<2:47:22, 1.67it/s] 71%|███████ | 40839/57600 [7:10:30<2:54:47, 1.60it/s] 71%|███████ | 40840/57600 [7:10:31<2:54:43, 1.60it/s] {'loss': 1.1435, 'learning_rate': 3.627874564459931e-07, 'epoch': 450.77} + 71%|███████ | 40840/57600 [7:10:31<2:54:43, 1.60it/s] 71%|███████ | 40841/57600 [7:10:32<2:55:09, 1.59it/s] 71%|███████ | 40842/57600 [7:10:32<2:54:23, 1.60it/s] 71%|███████ | 40843/57600 [7:10:33<2:56:50, 1.58it/s] 71%|███████ | 40844/57600 [7:10:34<2:55:50, 1.59it/s] 71%|███████ | 40845/57600 [7:10:34<2:52:03, 1.62it/s] 71%|███████ | 40846/57600 [7:10:35<2:50:44, 1.64it/s] 71%|███████ | 40847/57600 [7:10:35<2:48:13, 1.66it/s] 71%|███████ | 40848/57600 [7:10:36<2:53:31, 1.61it/s] 71%|███████ | 40849/57600 [7:10:37<2:47:55, 1.66it/s] 71%|███████ | 40850/57600 [7:10:37<2:49:48, 1.64it/s] 71%|███████ | 40851/57600 [7:10:38<2:47:20, 1.67it/s] 71%|███████ | 40852/57600 [7:10:38<2:49:01, 1.65it/s] 71%|███████ | 40853/57600 [7:10:39<2:46:43, 1.67it/s] 71%|███████ | 40854/57600 [7:10:40<2:51:30, 1.63it/s] 71%|███████ | 40855/57600 [7:10:40<2:52:15, 1.62it/s] 71%|███████ | 40856/57600 [7:10:41<2:51:04, 1.63it/s] 71%|███████ | 40857/57600 [7:10:42<2:53:04, 1.61it/s] 71%|███████ | 40858/57600 [7:10:42<2:51:13, 1.63it/s] 71%|███████ | 40859/57600 [7:10:43<2:50:08, 1.64it/s] 71%|███████ | 40860/57600 [7:10:43<2:52:41, 1.62it/s] {'loss': 1.189, 'learning_rate': 3.6247386759581874e-07, 'epoch': 450.99} + 71%|███████ | 40860/57600 [7:10:43<2:52:41, 1.62it/s] 71%|███████ | 40861/57600 [7:10:44<3:07:14, 1.49it/s] 71%|███████ | 40862/57600 [7:10:45<3:04:08, 1.51it/s] 71%|███████ | 40863/57600 [7:10:45<2:57:00, 1.58it/s] 71%|███████ | 40864/57600 [7:10:46<2:53:08, 1.61it/s] 71%|███████ | 40865/57600 [7:10:47<2:50:07, 1.64it/s] 71%|███████ | 40866/57600 [7:10:47<2:51:36, 1.63it/s] 71%|███████ | 40867/57600 [7:10:48<2:51:32, 1.63it/s] 71%|███████ | 40868/57600 [7:10:48<2:54:13, 1.60it/s] 71%|███████ | 40869/57600 [7:10:49<2:53:40, 1.61it/s] 71%|███████ | 40870/57600 [7:10:50<2:57:08, 1.57it/s] 71%|███████ | 40871/57600 [7:10:50<3:03:56, 1.52it/s] 71%|███████ | 40872/57600 [7:10:51<3:00:15, 1.55it/s] 71%|███████ | 40873/57600 [7:10:52<2:56:34, 1.58it/s] 71%|███████ | 40874/57600 [7:10:52<2:54:47, 1.59it/s] 71%|███████ | 40875/57600 [7:10:53<2:49:56, 1.64it/s] 71%|███████ | 40876/57600 [7:10:53<2:54:55, 1.59it/s] 71%|███████ | 40877/57600 [7:10:54<2:50:36, 1.63it/s] 71%|███████ | 40878/57600 [7:10:55<2:55:27, 1.59it/s] 71%|███████ | 40879/57600 [7:10:55<2:51:59, 1.62it/s] 71%|███████ | 40880/57600 [7:10:56<2:51:52, 1.62it/s] {'loss': 1.1308, 'learning_rate': 3.621602787456446e-07, 'epoch': 451.21} + 71%|███████ | 40880/57600 [7:10:56<2:51:52, 1.62it/s] 71%|███████ | 40881/57600 [7:10:57<2:52:08, 1.62it/s] 71%|███████ | 40882/57600 [7:10:57<2:55:53, 1.58it/s] 71%|███████ | 40883/57600 [7:10:58<2:51:45, 1.62it/s] 71%|███████ | 40884/57600 [7:10:58<2:49:30, 1.64it/s] 71%|███████ | 40885/57600 [7:10:59<2:49:18, 1.65it/s] 71%|███████ | 40886/57600 [7:11:00<2:48:38, 1.65it/s] 71%|███████ | 40887/57600 [7:11:00<2:55:09, 1.59it/s] 71%|███████ | 40888/57600 [7:11:01<2:52:31, 1.61it/s] 71%|███████ | 40889/57600 [7:11:01<2:50:27, 1.63it/s] 71%|███████ | 40890/57600 [7:11:02<2:50:57, 1.63it/s] 71%|███████ | 40891/57600 [7:11:03<2:52:52, 1.61it/s] 71%|███████ | 40892/57600 [7:11:03<2:51:57, 1.62it/s] 71%|███████ | 40893/57600 [7:11:04<2:53:49, 1.60it/s] 71%|███████ | 40894/57600 [7:11:05<2:54:50, 1.59it/s] 71%|███████ | 40895/57600 [7:11:05<2:56:49, 1.57it/s] 71%|███████ | 40896/57600 [7:11:06<2:58:43, 1.56it/s] 71%|███████ | 40897/57600 [7:11:07<2:56:42, 1.58it/s] 71%|███████ | 40898/57600 [7:11:07<2:57:16, 1.57it/s] 71%|███████ | 40899/57600 [7:11:08<2:59:29, 1.55it/s] 71%|███████ | 40900/57600 [7:11:08<2:54:51, 1.59it/s] {'loss': 1.1471, 'learning_rate': 3.618466898954704e-07, 'epoch': 451.43} + 71%|███████ | 40900/57600 [7:11:08<2:54:51, 1.59it/s] 71%|███████ | 40901/57600 [7:11:09<2:58:19, 1.56it/s] 71%|███████ | 40902/57600 [7:11:10<2:58:46, 1.56it/s] 71%|███████ | 40903/57600 [7:11:10<2:58:24, 1.56it/s] 71%|███████ | 40904/57600 [7:11:11<2:52:27, 1.61it/s] 71%|███████ | 40905/57600 [7:11:12<2:54:18, 1.60it/s] 71%|███████ | 40906/57600 [7:11:12<2:52:53, 1.61it/s] 71%|███████ | 40907/57600 [7:11:13<2:51:57, 1.62it/s] 71%|███████ | 40908/57600 [7:11:13<2:48:29, 1.65it/s] 71%|███████ | 40909/57600 [7:11:14<2:50:37, 1.63it/s] 71%|███████ | 40910/57600 [7:11:15<2:57:16, 1.57it/s] 71%|███████ | 40911/57600 [7:11:15<2:55:35, 1.58it/s] 71%|███████ | 40912/57600 [7:11:16<3:00:13, 1.54it/s] 71%|███████ | 40913/57600 [7:11:17<2:58:21, 1.56it/s] 71%|███████ | 40914/57600 [7:11:17<2:54:42, 1.59it/s] 71%|███████ | 40915/57600 [7:11:18<2:58:19, 1.56it/s] 71%|███████ | 40916/57600 [7:11:19<2:59:14, 1.55it/s] 71%|███████ | 40917/57600 [7:11:19<3:08:18, 1.48it/s] 71%|███████ | 40918/57600 [7:11:20<3:03:11, 1.52it/s] 71%|███████ | 40919/57600 [7:11:21<3:01:48, 1.53it/s] 71%|███████ | 40920/57600 [7:11:21<2:56:59, 1.57it/s] {'loss': 1.1316, 'learning_rate': 3.6153310104529615e-07, 'epoch': 451.66} + 71%|███████ | 40920/57600 [7:11:21<2:56:59, 1.57it/s] 71%|███████ | 40921/57600 [7:11:22<2:56:56, 1.57it/s] 71%|███████ | 40922/57600 [7:11:22<2:52:41, 1.61it/s] 71%|███████ | 40923/57600 [7:11:23<2:52:33, 1.61it/s] 71%|███████ | 40924/57600 [7:11:24<2:47:04, 1.66it/s] 71%|███████ | 40925/57600 [7:11:24<2:55:58, 1.58it/s] 71%|███████ | 40926/57600 [7:11:25<2:57:42, 1.56it/s] 71%|███████ | 40927/57600 [7:11:26<2:57:17, 1.57it/s] 71%|███████ | 40928/57600 [7:11:26<2:55:14, 1.59it/s] 71%|███████ | 40929/57600 [7:11:27<2:49:17, 1.64it/s] 71%|███████ | 40930/57600 [7:11:27<2:46:27, 1.67it/s] 71%|███████ | 40931/57600 [7:11:28<2:52:15, 1.61it/s] 71%|███████ | 40932/57600 [7:11:29<2:51:03, 1.62it/s] 71%|███████ | 40933/57600 [7:11:29<2:46:01, 1.67it/s] 71%|███████ | 40934/57600 [7:11:30<2:47:26, 1.66it/s] 71%|███████ | 40935/57600 [7:11:30<2:55:16, 1.58it/s] 71%|███████ | 40936/57600 [7:11:31<2:50:46, 1.63it/s] 71%|███████ | 40937/57600 [7:11:32<2:59:14, 1.55it/s] 71%|███████ | 40938/57600 [7:11:32<2:56:12, 1.58it/s] 71%|███████ | 40939/57600 [7:11:33<2:53:06, 1.60it/s] 71%|███████ | 40940/57600 [7:11:34<2:50:10, 1.63it/s] {'loss': 1.1592, 'learning_rate': 3.6121951219512196e-07, 'epoch': 451.88} + 71%|███████ | 40940/57600 [7:11:34<2:50:10, 1.63it/s] 71%|███████ | 40941/57600 [7:11:34<2:55:35, 1.58it/s] 71%|███████ | 40942/57600 [7:11:35<2:56:38, 1.57it/s] 71%|███████ | 40943/57600 [7:11:36<2:58:34, 1.55it/s] 71%|███████ | 40944/57600 [7:11:36<2:54:17, 1.59it/s] 71%|███████ | 40945/57600 [7:11:37<2:59:13, 1.55it/s] 71%|███████ | 40946/57600 [7:11:38<3:05:44, 1.49it/s] 71%|███████ | 40947/57600 [7:11:38<3:04:21, 1.51it/s] 71%|███████ | 40948/57600 [7:11:39<3:09:02, 1.47it/s] 71%|███████ | 40949/57600 [7:11:40<3:03:11, 1.51it/s] 71%|███████ | 40950/57600 [7:11:40<2:56:25, 1.57it/s] 71%|███████ | 40951/57600 [7:11:41<2:54:20, 1.59it/s] 71%|███████ | 40952/57600 [7:11:41<3:00:49, 1.53it/s] 71%|███████ | 40953/57600 [7:11:42<2:54:07, 1.59it/s] 71%|███████ | 40954/57600 [7:11:43<2:53:33, 1.60it/s] 71%|███████ | 40955/57600 [7:11:43<2:52:33, 1.61it/s] 71%|███████ | 40956/57600 [7:11:44<2:49:38, 1.64it/s] 71%|███████ | 40957/57600 [7:11:44<2:53:21, 1.60it/s] 71%|███████ | 40958/57600 [7:11:45<2:55:53, 1.58it/s] 71%|███████ | 40959/57600 [7:11:46<3:00:25, 1.54it/s] 71%|███████ | 40960/57600 [7:11:46<2:58:51, 1.55it/s] {'loss': 1.1262, 'learning_rate': 3.6090592334494766e-07, 'epoch': 452.1} + 71%|███████ | 40960/57600 [7:11:46<2:58:51, 1.55it/s] 71%|███████ | 40961/57600 [7:11:47<2:51:39, 1.62it/s] 71%|███████ | 40962/57600 [7:11:48<2:52:20, 1.61it/s] 71%|███████ | 40963/57600 [7:11:48<2:55:34, 1.58it/s] 71%|███████ | 40964/57600 [7:11:49<2:59:36, 1.54it/s] 71%|███████ | 40965/57600 [7:11:50<2:54:48, 1.59it/s] 71%|███████ | 40966/57600 [7:11:50<2:53:58, 1.59it/s] 71%|███████ | 40967/57600 [7:11:51<2:50:57, 1.62it/s] 71%|███████ | 40968/57600 [7:11:51<2:52:19, 1.61it/s] 71%|███████ | 40969/57600 [7:11:52<2:57:02, 1.57it/s] 71%|███████ | 40970/57600 [7:11:53<2:58:08, 1.56it/s] 71%|███████ | 40971/57600 [7:11:53<2:52:36, 1.61it/s] 71%|███████ | 40972/57600 [7:11:54<2:53:43, 1.60it/s] 71%|███████ | 40973/57600 [7:11:55<2:48:48, 1.64it/s] 71%|███████ | 40974/57600 [7:11:55<2:53:58, 1.59it/s] 71%|███████ | 40975/57600 [7:11:56<2:51:14, 1.62it/s] 71%|███████ | 40976/57600 [7:11:57<3:01:07, 1.53it/s] 71%|███████ | 40977/57600 [7:11:57<2:55:17, 1.58it/s] 71%|███████ | 40978/57600 [7:11:58<2:56:52, 1.57it/s] 71%|███████ | 40979/57600 [7:11:58<2:51:18, 1.62it/s] 71%|███████ | 40980/57600 [7:11:59<2:47:59, 1.65it/s] {'loss': 1.1274, 'learning_rate': 3.605923344947735e-07, 'epoch': 452.32} + 71%|███████ | 40980/57600 [7:11:59<2:47:59, 1.65it/s] 71%|███████ | 40981/57600 [7:12:00<2:46:01, 1.67it/s] 71%|███████ | 40982/57600 [7:12:00<2:46:47, 1.66it/s] 71%|███████ | 40983/57600 [7:12:01<2:46:55, 1.66it/s] 71%|███████ | 40984/57600 [7:12:01<2:47:17, 1.66it/s] 71%|███████ | 40985/57600 [7:12:02<2:44:55, 1.68it/s] 71%|███████ | 40986/57600 [7:12:02<2:41:58, 1.71it/s] 71%|███████ | 40987/57600 [7:12:03<2:47:50, 1.65it/s] 71%|███████ | 40988/57600 [7:12:04<2:48:01, 1.65it/s] 71%|███████ | 40989/57600 [7:12:04<2:48:11, 1.65it/s] 71%|███████ | 40990/57600 [7:12:05<2:50:46, 1.62it/s] 71%|███████ | 40991/57600 [7:12:06<2:50:16, 1.63it/s] 71%|███████ | 40992/57600 [7:12:06<2:52:49, 1.60it/s] 71%|███████ | 40993/57600 [7:12:07<2:52:11, 1.61it/s] 71%|███████ | 40994/57600 [7:12:08<2:54:51, 1.58it/s] 71%|███████ | 40995/57600 [7:12:08<2:57:51, 1.56it/s] 71%|███████ | 40996/57600 [7:12:09<2:55:10, 1.58it/s] 71%|███████ | 40997/57600 [7:12:09<2:54:10, 1.59it/s] 71%|███████ | 40998/57600 [7:12:10<2:55:05, 1.58it/s] 71%|███████ | 40999/57600 [7:12:11<2:54:09, 1.59it/s] 71%|███████ | 41000/57600 [7:12:11<3:01:08, 1.53it/s] {'loss': 1.1403, 'learning_rate': 3.6027874564459927e-07, 'epoch': 452.54} + 71%|███████ | 41000/57600 [7:12:11<3:01:08, 1.53it/s] 71%|███████ | 41001/57600 [7:12:12<2:58:05, 1.55it/s] 71%|███████ | 41002/57600 [7:12:13<2:52:03, 1.61it/s] 71%|███████ | 41003/57600 [7:12:13<2:51:30, 1.61it/s] 71%|███████ | 41004/57600 [7:12:14<2:51:38, 1.61it/s] 71%|███████ | 41005/57600 [7:12:14<2:54:18, 1.59it/s] 71%|███████ | 41006/57600 [7:12:15<2:50:44, 1.62it/s] 71%|███████ | 41007/57600 [7:12:16<2:52:34, 1.60it/s] 71%|███████ | 41008/57600 [7:12:16<2:57:22, 1.56it/s] 71%|███████ | 41009/57600 [7:12:17<2:53:03, 1.60it/s] 71%|███████ | 41010/57600 [7:12:18<2:55:15, 1.58it/s] 71%|███████ | 41011/57600 [7:12:18<2:56:59, 1.56it/s] 71%|███████ | 41012/57600 [7:12:19<2:55:24, 1.58it/s] 71%|███████ | 41013/57600 [7:12:19<2:48:56, 1.64it/s] 71%|███████ | 41014/57600 [7:12:20<2:46:52, 1.66it/s] 71%|███████ | 41015/57600 [7:12:21<2:56:17, 1.57it/s] 71%|███████ | 41016/57600 [7:12:21<3:04:05, 1.50it/s] 71%|███████ | 41017/57600 [7:12:22<3:01:02, 1.53it/s] 71%|███████ | 41018/57600 [7:12:23<3:01:42, 1.52it/s] 71%|███████ | 41019/57600 [7:12:23<2:58:57, 1.54it/s] 71%|███████ | 41020/57600 [7:12:24<2:54:51, 1.58it/s] {'loss': 1.1721, 'learning_rate': 3.5996515679442507e-07, 'epoch': 452.76} + 71%|███████ | 41020/57600 [7:12:24<2:54:51, 1.58it/s] 71%|███████ | 41021/57600 [7:12:25<2:51:41, 1.61it/s] 71%|███████ | 41022/57600 [7:12:25<2:55:24, 1.58it/s] 71%|███████ | 41023/57600 [7:12:26<2:53:21, 1.59it/s] 71%|███████ | 41024/57600 [7:12:26<2:49:27, 1.63it/s] 71%|███████ | 41025/57600 [7:12:27<2:47:08, 1.65it/s] 71%|███████ | 41026/57600 [7:12:28<2:46:57, 1.65it/s] 71%|███████ | 41027/57600 [7:12:28<2:54:04, 1.59it/s] 71%|███████ | 41028/57600 [7:12:29<2:49:46, 1.63it/s] 71%|███████ | 41029/57600 [7:12:30<2:50:11, 1.62it/s] 71%|███████ | 41030/57600 [7:12:30<2:49:46, 1.63it/s] 71%|███████ | 41031/57600 [7:12:31<2:56:41, 1.56it/s] 71%|███████ | 41032/57600 [7:12:31<2:54:50, 1.58it/s] 71%|███████ | 41033/57600 [7:12:32<3:01:50, 1.52it/s] 71%|███████ | 41034/57600 [7:12:33<2:56:27, 1.56it/s] 71%|███████ | 41035/57600 [7:12:33<2:54:59, 1.58it/s] 71%|███████ | 41036/57600 [7:12:34<2:52:12, 1.60it/s] 71%|███████ | 41037/57600 [7:12:35<2:56:06, 1.57it/s] 71%|███████ | 41038/57600 [7:12:35<2:57:46, 1.55it/s] 71%|███████ | 41039/57600 [7:12:36<2:57:19, 1.56it/s] 71%|███████▏ | 41040/57600 [7:12:37<2:56:38, 1.56it/s] {'loss': 1.1051, 'learning_rate': 3.596515679442509e-07, 'epoch': 452.98} + 71%|███████▏ | 41040/57600 [7:12:37<2:56:38, 1.56it/s] 71%|███████▏ | 41041/57600 [7:12:37<2:56:44, 1.56it/s] 71%|███████▏ | 41042/57600 [7:12:38<2:59:35, 1.54it/s] 71%|███████▏ | 41043/57600 [7:12:38<2:55:14, 1.57it/s] 71%|███████▏ | 41044/57600 [7:12:39<2:51:02, 1.61it/s] 71%|███████▏ | 41045/57600 [7:12:40<2:54:09, 1.58it/s] 71%|███████▏ | 41046/57600 [7:12:40<2:50:29, 1.62it/s] 71%|███████▏ | 41047/57600 [7:12:41<2:54:53, 1.58it/s] 71%|███████▏ | 41048/57600 [7:12:42<2:53:17, 1.59it/s] 71%|███████▏ | 41049/57600 [7:12:42<2:50:31, 1.62it/s] 71%|███████▏ | 41050/57600 [7:12:43<2:49:11, 1.63it/s] 71%|███████▏ | 41051/57600 [7:12:44<2:56:11, 1.57it/s] 71%|███████▏ | 41052/57600 [7:12:44<3:03:23, 1.50it/s] 71%|███████▏ | 41053/57600 [7:12:45<2:55:25, 1.57it/s] 71%|███████▏ | 41054/57600 [7:12:46<3:01:08, 1.52it/s] 71%|███████▏ | 41055/57600 [7:12:46<2:59:07, 1.54it/s] 71%|███████▏ | 41056/57600 [7:12:47<2:54:26, 1.58it/s] 71%|███████▏ | 41057/57600 [7:12:47<2:52:19, 1.60it/s] 71%|███████▏ | 41058/57600 [7:12:48<2:50:47, 1.61it/s] 71%|███████▏ | 41059/57600 [7:12:49<2:50:51, 1.61it/s] 71%|███████▏ | 41060/57600 [7:12:49<2:54:24, 1.58it/s] {'loss': 1.1413, 'learning_rate': 3.5933797909407663e-07, 'epoch': 453.2} + 71%|███████▏ | 41060/57600 [7:12:49<2:54:24, 1.58it/s] 71%|███████▏ | 41061/57600 [7:12:50<2:57:49, 1.55it/s] 71%|███████▏ | 41062/57600 [7:12:51<3:00:15, 1.53it/s] 71%|███████▏ | 41063/57600 [7:12:51<2:55:33, 1.57it/s] 71%|███████▏ | 41064/57600 [7:12:52<2:55:25, 1.57it/s] 71%|███████▏ | 41065/57600 [7:12:52<2:57:24, 1.55it/s] 71%|███████▏ | 41066/57600 [7:12:53<2:53:10, 1.59it/s] 71%|███████▏ | 41067/57600 [7:12:54<2:55:36, 1.57it/s] 71%|███████▏ | 41068/57600 [7:12:54<2:53:24, 1.59it/s] 71%|███████▏ | 41069/57600 [7:12:55<2:50:10, 1.62it/s] 71%|███████▏ | 41070/57600 [7:12:56<2:47:18, 1.65it/s] 71%|███████▏ | 41071/57600 [7:12:56<3:00:18, 1.53it/s] 71%|███████▏ | 41072/57600 [7:12:57<3:05:01, 1.49it/s] 71%|███████▏ | 41073/57600 [7:12:58<3:02:00, 1.51it/s] 71%|███████▏ | 41074/57600 [7:12:58<2:58:05, 1.55it/s] 71%|███████▏ | 41075/57600 [7:12:59<2:54:36, 1.58it/s] 71%|███████▏ | 41076/57600 [7:13:00<3:02:08, 1.51it/s] 71%|███████▏ | 41077/57600 [7:13:00<2:53:59, 1.58it/s] 71%|███████▏ | 41078/57600 [7:13:01<2:52:46, 1.59it/s] 71%|███████▏ | 41079/57600 [7:13:01<2:50:12, 1.62it/s] 71%|███████▏ | 41080/57600 [7:13:02<2:46:24, 1.65it/s] {'loss': 1.1231, 'learning_rate': 3.5902439024390243e-07, 'epoch': 453.42} + 71%|███████▏ | 41080/57600 [7:13:02<2:46:24, 1.65it/s] 71%|███████▏ | 41081/57600 [7:13:03<2:46:31, 1.65it/s] 71%|███████▏ | 41082/57600 [7:13:03<2:46:12, 1.66it/s] 71%|███████▏ | 41083/57600 [7:13:04<2:48:46, 1.63it/s] 71%|███████▏ | 41084/57600 [7:13:04<2:49:23, 1.62it/s] 71%|███████▏ | 41085/57600 [7:13:05<2:48:17, 1.64it/s] 71%|███████▏ | 41086/57600 [7:13:06<2:47:12, 1.65it/s] 71%|███████▏ | 41087/57600 [7:13:06<2:49:14, 1.63it/s] 71%|███████▏ | 41088/57600 [7:13:07<2:59:05, 1.54it/s] 71%|███████▏ | 41089/57600 [7:13:08<2:55:41, 1.57it/s] 71%|███████▏ | 41090/57600 [7:13:08<2:50:47, 1.61it/s] 71%|███████▏ | 41091/57600 [7:13:09<2:51:29, 1.60it/s] 71%|███████▏ | 41092/57600 [7:13:09<2:50:31, 1.61it/s] 71%|███████▏ | 41093/57600 [7:13:10<2:51:45, 1.60it/s] 71%|███████▏ | 41094/57600 [7:13:11<2:58:00, 1.55it/s] 71%|███████▏ | 41095/57600 [7:13:11<2:54:11, 1.58it/s] 71%|███████▏ | 41096/57600 [7:13:12<2:48:02, 1.64it/s] 71%|███████▏ | 41097/57600 [7:13:12<2:42:39, 1.69it/s] 71%|███████▏ | 41098/57600 [7:13:13<2:44:30, 1.67it/s] 71%|███████▏ | 41099/57600 [7:13:14<2:47:09, 1.65it/s] 71%|███████▏ | 41100/57600 [7:13:14<2:45:37, 1.66it/s] {'loss': 1.1572, 'learning_rate': 3.587108013937282e-07, 'epoch': 453.64} + 71%|███████▏ | 41100/57600 [7:13:14<2:45:37, 1.66it/s] 71%|███████▏ | 41101/57600 [7:13:15<2:46:38, 1.65it/s] 71%|███████▏ | 41102/57600 [7:13:16<2:50:16, 1.61it/s] 71%|███████▏ | 41103/57600 [7:13:16<2:57:02, 1.55it/s] 71%|███████▏ | 41104/57600 [7:13:17<2:56:33, 1.56it/s] 71%|███████▏ | 41105/57600 [7:13:18<2:57:38, 1.55it/s] 71%|███████▏ | 41106/57600 [7:13:18<2:57:30, 1.55it/s] 71%|███████▏ | 41107/57600 [7:13:19<2:55:51, 1.56it/s] 71%|███████▏ | 41108/57600 [7:13:19<2:55:49, 1.56it/s] 71%|███████▏ | 41109/57600 [7:13:20<2:55:05, 1.57it/s] 71%|███████▏ | 41110/57600 [7:13:21<2:55:11, 1.57it/s] 71%|███████▏ | 41111/57600 [7:13:21<2:56:10, 1.56it/s] 71%|███████▏ | 41112/57600 [7:13:22<2:53:23, 1.58it/s] 71%|███████▏ | 41113/57600 [7:13:23<2:57:56, 1.54it/s] 71%|███████▏ | 41114/57600 [7:13:23<2:53:54, 1.58it/s] 71%|███████▏ | 41115/57600 [7:13:24<2:58:15, 1.54it/s] 71%|███████▏ | 41116/57600 [7:13:25<2:53:23, 1.58it/s] 71%|███████▏ | 41117/57600 [7:13:25<2:48:29, 1.63it/s] 71%|███████▏ | 41118/57600 [7:13:26<2:47:00, 1.64it/s] 71%|███████▏ | 41119/57600 [7:13:26<2:51:57, 1.60it/s] 71%|███████▏ | 41120/57600 [7:13:27<2:54:47, 1.57it/s] {'loss': 1.121, 'learning_rate': 3.58397212543554e-07, 'epoch': 453.86} + 71%|███████▏ | 41120/57600 [7:13:27<2:54:47, 1.57it/s] 71%|███████▏ | 41121/57600 [7:13:28<2:58:52, 1.54it/s] 71%|███████▏ | 41122/57600 [7:13:28<2:56:54, 1.55it/s] 71%|███████▏ | 41123/57600 [7:13:29<2:52:59, 1.59it/s] 71%|███████▏ | 41124/57600 [7:13:30<2:51:26, 1.60it/s] 71%|███████▏ | 41125/57600 [7:13:30<2:51:23, 1.60it/s] 71%|███████▏ | 41126/57600 [7:13:31<2:52:49, 1.59it/s] 71%|███████▏ | 41127/57600 [7:13:31<2:51:29, 1.60it/s] 71%|███████▏ | 41128/57600 [7:13:32<2:50:09, 1.61it/s] 71%|███████▏ | 41129/57600 [7:13:33<2:46:31, 1.65it/s] 71%|███████▏ | 41130/57600 [7:13:33<2:51:04, 1.60it/s] 71%|███████▏ | 41131/57600 [7:13:34<2:50:32, 1.61it/s] 71%|███████▏ | 41132/57600 [7:13:34<2:49:10, 1.62it/s] 71%|███████▏ | 41133/57600 [7:13:35<3:01:00, 1.52it/s] 71%|███████▏ | 41134/57600 [7:13:36<3:01:49, 1.51it/s] 71%|███████▏ | 41135/57600 [7:13:37<3:01:05, 1.52it/s] 71%|███████▏ | 41136/57600 [7:13:37<3:00:04, 1.52it/s] 71%|███████▏ | 41137/57600 [7:13:38<2:56:39, 1.55it/s] 71%|███████▏ | 41138/57600 [7:13:38<2:50:16, 1.61it/s] 71%|███████▏ | 41139/57600 [7:13:39<2:47:44, 1.64it/s] 71%|███████▏ | 41140/57600 [7:13:40<2:47:49, 1.63it/s] {'loss': 1.1234, 'learning_rate': 3.5808362369337974e-07, 'epoch': 454.08} + 71%|███████▏ | 41140/57600 [7:13:40<2:47:49, 1.63it/s] 71%|███████▏ | 41141/57600 [7:13:40<2:48:24, 1.63it/s] 71%|███████▏ | 41142/57600 [7:13:41<2:46:05, 1.65it/s] 71%|███████▏ | 41143/57600 [7:13:41<2:48:25, 1.63it/s] 71%|███████▏ | 41144/57600 [7:13:42<2:46:21, 1.65it/s] 71%|███████▏ | 41145/57600 [7:13:43<2:45:50, 1.65it/s] 71%|███████▏ | 41146/57600 [7:13:43<2:51:54, 1.60it/s] 71%|███████▏ | 41147/57600 [7:13:44<2:55:30, 1.56it/s] 71%|███████▏ | 41148/57600 [7:13:45<2:51:21, 1.60it/s] 71%|███████▏ | 41149/57600 [7:13:45<2:47:41, 1.64it/s] 71%|███████▏ | 41150/57600 [7:13:46<2:50:11, 1.61it/s] 71%|███████▏ | 41151/57600 [7:13:46<2:48:08, 1.63it/s] 71%|███████▏ | 41152/57600 [7:13:47<2:53:38, 1.58it/s] 71%|███████▏ | 41153/57600 [7:13:48<2:48:11, 1.63it/s] 71%|███████▏ | 41154/57600 [7:13:48<2:54:19, 1.57it/s] 71%|███████▏ | 41155/57600 [7:13:49<2:51:55, 1.59it/s] 71%|███████▏ | 41156/57600 [7:13:50<2:52:57, 1.58it/s] 71%|███████▏ | 41157/57600 [7:13:50<2:56:31, 1.55it/s] 71%|███████▏ | 41158/57600 [7:13:51<3:03:12, 1.50it/s] 71%|███████▏ | 41159/57600 [7:13:52<3:01:04, 1.51it/s] 71%|███████▏ | 41160/57600 [7:13:52<3:06:23, 1.47it/s] {'loss': 1.1248, 'learning_rate': 3.5777003484320555e-07, 'epoch': 454.3} + 71%|███████▏ | 41160/57600 [7:13:52<3:06:23, 1.47it/s] 71%|███████▏ | 41161/57600 [7:13:53<3:06:36, 1.47it/s] 71%|███████▏ | 41162/57600 [7:13:54<3:02:13, 1.50it/s] 71%|███████▏ | 41163/57600 [7:13:54<3:04:43, 1.48it/s] 71%|███████▏ | 41164/57600 [7:13:55<3:04:18, 1.49it/s] 71%|███████▏ | 41165/57600 [7:13:56<3:01:46, 1.51it/s] 71%|███████▏ | 41166/57600 [7:13:56<3:00:51, 1.51it/s] 71%|███████▏ | 41167/57600 [7:13:57<2:58:57, 1.53it/s] 71%|███████▏ | 41168/57600 [7:13:58<2:57:29, 1.54it/s] 71%|███████▏ | 41169/57600 [7:13:58<2:53:59, 1.57it/s] 71%|███████▏ | 41170/57600 [7:13:59<2:50:43, 1.60it/s] 71%|███████▏ | 41171/57600 [7:13:59<2:45:20, 1.66it/s] 71%|███████▏ | 41172/57600 [7:14:00<2:51:30, 1.60it/s] 71%|███████▏ | 41173/57600 [7:14:01<2:58:34, 1.53it/s] 71%|███████▏ | 41174/57600 [7:14:01<2:56:03, 1.56it/s] 71%|███████▏ | 41175/57600 [7:14:02<2:50:51, 1.60it/s] 71%|███████▏ | 41176/57600 [7:14:03<2:49:48, 1.61it/s] 71%|███████▏ | 41177/57600 [7:14:03<2:50:17, 1.61it/s] 71%|███████▏ | 41178/57600 [7:14:04<2:48:03, 1.63it/s] 71%|███████▏ | 41179/57600 [7:14:04<2:46:22, 1.64it/s] 71%|███████▏ | 41180/57600 [7:14:05<2:47:18, 1.64it/s] {'loss': 1.1286, 'learning_rate': 3.574564459930314e-07, 'epoch': 454.53} + 71%|███████▏ | 41180/57600 [7:14:05<2:47:18, 1.64it/s] 71%|███████▏ | 41181/57600 [7:14:06<2:46:36, 1.64it/s] 71%|███████▏ | 41182/57600 [7:14:06<2:49:03, 1.62it/s] 71%|███████▏ | 41183/57600 [7:14:07<2:48:32, 1.62it/s] 72%|███████▏ | 41184/57600 [7:14:07<2:53:03, 1.58it/s] 72%|███████▏ | 41185/57600 [7:14:08<2:53:40, 1.58it/s] 72%|███████▏ | 41186/57600 [7:14:09<2:50:24, 1.61it/s] 72%|███████▏ | 41187/57600 [7:14:09<2:50:24, 1.61it/s] 72%|███████▏ | 41188/57600 [7:14:10<2:48:40, 1.62it/s] 72%|███████▏ | 41189/57600 [7:14:11<2:49:55, 1.61it/s] 72%|███████▏ | 41190/57600 [7:14:11<2:46:44, 1.64it/s] 72%|███████▏ | 41191/57600 [7:14:12<2:45:12, 1.66it/s] 72%|███████▏ | 41192/57600 [7:14:12<2:46:06, 1.65it/s] 72%|███████▏ | 41193/57600 [7:14:13<2:43:35, 1.67it/s] 72%|███████▏ | 41194/57600 [7:14:14<2:42:11, 1.69it/s] 72%|███████▏ | 41195/57600 [7:14:14<2:47:55, 1.63it/s] 72%|███████▏ | 41196/57600 [7:14:15<2:44:38, 1.66it/s] 72%|███████▏ | 41197/57600 [7:14:15<2:47:55, 1.63it/s] 72%|███████▏ | 41198/57600 [7:14:16<2:46:54, 1.64it/s] 72%|███████▏ | 41199/57600 [7:14:17<2:47:02, 1.64it/s] 72%|███████▏ | 41200/57600 [7:14:17<2:48:54, 1.62it/s] {'loss': 1.1519, 'learning_rate': 3.571428571428571e-07, 'epoch': 454.75} + 72%|███████▏ | 41200/57600 [7:14:17<2:48:54, 1.62it/s] 72%|███████▏ | 41201/57600 [7:14:18<2:47:05, 1.64it/s] 72%|███████▏ | 41202/57600 [7:14:18<2:48:27, 1.62it/s] 72%|███████▏ | 41203/57600 [7:14:19<2:53:40, 1.57it/s] 72%|███████▏ | 41204/57600 [7:14:20<2:55:20, 1.56it/s] 72%|███████▏ | 41205/57600 [7:14:20<2:51:47, 1.59it/s] 72%|███████▏ | 41206/57600 [7:14:21<2:50:48, 1.60it/s] 72%|███████▏ | 41207/57600 [7:14:22<2:54:08, 1.57it/s] 72%|███████▏ | 41208/57600 [7:14:22<2:47:39, 1.63it/s] 72%|███████▏ | 41209/57600 [7:14:23<2:51:59, 1.59it/s] 72%|███████▏ | 41210/57600 [7:14:24<2:54:18, 1.57it/s] 72%|███████▏ | 41211/57600 [7:14:24<2:59:08, 1.52it/s] 72%|███████▏ | 41212/57600 [7:14:25<3:03:48, 1.49it/s] 72%|███████▏ | 41213/57600 [7:14:26<3:05:31, 1.47it/s] 72%|███████▏ | 41214/57600 [7:14:26<3:07:14, 1.46it/s] 72%|███████▏ | 41215/57600 [7:14:27<3:03:26, 1.49it/s] 72%|███████▏ | 41216/57600 [7:14:28<2:59:38, 1.52it/s] 72%|███████▏ | 41217/57600 [7:14:28<3:02:29, 1.50it/s] 72%|███████▏ | 41218/57600 [7:14:29<3:00:10, 1.52it/s] 72%|███████▏ | 41219/57600 [7:14:30<2:56:33, 1.55it/s] 72%|███████▏ | 41220/57600 [7:14:30<2:54:19, 1.57it/s] {'loss': 1.1209, 'learning_rate': 3.5682926829268296e-07, 'epoch': 454.97} + 72%|███████▏ | 41220/57600 [7:14:30<2:54:19, 1.57it/s] 72%|███████▏ | 41221/57600 [7:14:31<2:50:06, 1.60it/s] 72%|███████▏ | 41222/57600 [7:14:31<2:52:27, 1.58it/s] 72%|███████▏ | 41223/57600 [7:14:32<2:51:53, 1.59it/s] 72%|███████▏ | 41224/57600 [7:14:33<2:59:08, 1.52it/s] 72%|███████▏ | 41225/57600 [7:14:33<3:00:33, 1.51it/s] 72%|███████▏ | 41226/57600 [7:14:34<2:54:44, 1.56it/s] 72%|███████▏ | 41227/57600 [7:14:35<2:55:37, 1.55it/s] 72%|███████▏ | 41228/57600 [7:14:35<2:58:45, 1.53it/s] 72%|███████▏ | 41229/57600 [7:14:36<2:55:51, 1.55it/s] 72%|███████▏ | 41230/57600 [7:14:37<2:57:53, 1.53it/s] 72%|███████▏ | 41231/57600 [7:14:37<3:04:21, 1.48it/s] 72%|███████▏ | 41232/57600 [7:14:38<2:59:41, 1.52it/s] 72%|███████▏ | 41233/57600 [7:14:39<2:57:04, 1.54it/s] 72%|███████▏ | 41234/57600 [7:14:39<3:00:57, 1.51it/s] 72%|███████▏ | 41235/57600 [7:14:40<3:00:18, 1.51it/s] 72%|███████▏ | 41236/57600 [7:14:41<2:58:46, 1.53it/s] 72%|███████▏ | 41237/57600 [7:14:41<2:59:15, 1.52it/s] 72%|███████▏ | 41238/57600 [7:14:42<2:54:51, 1.56it/s] 72%|███████▏ | 41239/57600 [7:14:42<2:49:10, 1.61it/s] 72%|███████▏ | 41240/57600 [7:14:43<2:49:35, 1.61it/s] {'loss': 1.1182, 'learning_rate': 3.5651567944250866e-07, 'epoch': 455.19} + 72%|███████▏ | 41240/57600 [7:14:43<2:49:35, 1.61it/s] 72%|███████▏ | 41241/57600 [7:14:44<2:56:13, 1.55it/s] 72%|███████▏ | 41242/57600 [7:14:44<2:53:51, 1.57it/s] 72%|███████▏ | 41243/57600 [7:14:45<2:51:44, 1.59it/s] 72%|███████▏ | 41244/57600 [7:14:46<2:48:36, 1.62it/s] 72%|███████▏ | 41245/57600 [7:14:46<2:58:48, 1.52it/s] 72%|███████▏ | 41246/57600 [7:14:47<2:53:01, 1.58it/s] 72%|███████▏ | 41247/57600 [7:14:48<2:50:27, 1.60it/s] 72%|███████▏ | 41248/57600 [7:14:48<2:47:33, 1.63it/s] 72%|███████▏ | 41249/57600 [7:14:49<2:49:16, 1.61it/s] 72%|███████▏ | 41250/57600 [7:14:49<2:45:55, 1.64it/s] 72%|███████▏ | 41251/57600 [7:14:50<2:50:37, 1.60it/s] 72%|███████▏ | 41252/57600 [7:14:51<2:48:46, 1.61it/s] 72%|███████▏ | 41253/57600 [7:14:51<2:49:08, 1.61it/s] 72%|███████▏ | 41254/57600 [7:14:52<2:49:17, 1.61it/s] 72%|███████▏ | 41255/57600 [7:14:53<2:48:38, 1.62it/s] 72%|███████▏ | 41256/57600 [7:14:53<2:51:05, 1.59it/s] 72%|███████▏ | 41257/57600 [7:14:54<2:48:37, 1.62it/s] 72%|███████▏ | 41258/57600 [7:14:54<2:55:38, 1.55it/s] 72%|███████▏ | 41259/57600 [7:14:55<2:55:16, 1.55it/s] 72%|███████▏ | 41260/57600 [7:14:56<2:59:00, 1.52it/s] {'loss': 1.1495, 'learning_rate': 3.5620209059233447e-07, 'epoch': 455.41} + 72%|███████▏ | 41260/57600 [7:14:56<2:59:00, 1.52it/s] 72%|███████▏ | 41261/57600 [7:14:56<2:56:05, 1.55it/s] 72%|███████▏ | 41262/57600 [7:14:57<2:53:42, 1.57it/s] 72%|███████▏ | 41263/57600 [7:14:58<2:52:49, 1.58it/s] 72%|███████▏ | 41264/57600 [7:14:58<2:54:57, 1.56it/s] 72%|███████▏ | 41265/57600 [7:14:59<2:52:23, 1.58it/s] 72%|███████▏ | 41266/57600 [7:15:00<2:48:28, 1.62it/s] 72%|███████▏ | 41267/57600 [7:15:00<2:49:02, 1.61it/s] 72%|███████▏ | 41268/57600 [7:15:01<2:52:25, 1.58it/s] 72%|███████▏ | 41269/57600 [7:15:01<2:49:59, 1.60it/s] 72%|███████▏ | 41270/57600 [7:15:02<2:47:57, 1.62it/s] 72%|███████▏ | 41271/57600 [7:15:03<2:50:46, 1.59it/s] 72%|███████▏ | 41272/57600 [7:15:03<2:48:47, 1.61it/s] 72%|███████▏ | 41273/57600 [7:15:04<2:48:09, 1.62it/s] 72%|███████▏ | 41274/57600 [7:15:05<2:50:22, 1.60it/s] 72%|███████▏ | 41275/57600 [7:15:05<2:44:28, 1.65it/s] 72%|███████▏ | 41276/57600 [7:15:06<2:42:03, 1.68it/s] 72%|███████▏ | 41277/57600 [7:15:06<2:43:23, 1.67it/s] 72%|███████▏ | 41278/57600 [7:15:07<2:53:32, 1.57it/s] 72%|███████▏ | 41279/57600 [7:15:08<2:55:29, 1.55it/s] 72%|███████▏ | 41280/57600 [7:15:08<2:54:58, 1.55it/s] {'loss': 1.1124, 'learning_rate': 3.558885017421602e-07, 'epoch': 455.63} + 72%|███████▏ | 41280/57600 [7:15:08<2:54:58, 1.55it/s] 72%|███████▏ | 41281/57600 [7:15:09<2:50:26, 1.60it/s] 72%|███████▏ | 41282/57600 [7:15:10<2:54:01, 1.56it/s] 72%|███████▏ | 41283/57600 [7:15:10<2:50:21, 1.60it/s] 72%|███████▏ | 41284/57600 [7:15:11<2:54:00, 1.56it/s] 72%|███████▏ | 41285/57600 [7:15:11<2:54:24, 1.56it/s] 72%|███████▏ | 41286/57600 [7:15:12<2:50:56, 1.59it/s] 72%|███████▏ | 41287/57600 [7:15:13<2:49:46, 1.60it/s] 72%|███████▏ | 41288/57600 [7:15:13<2:52:06, 1.58it/s] 72%|███████▏ | 41289/57600 [7:15:14<2:52:05, 1.58it/s] 72%|███████▏ | 41290/57600 [7:15:15<2:45:58, 1.64it/s] 72%|███████▏ | 41291/57600 [7:15:15<2:44:10, 1.66it/s] 72%|███████▏ | 41292/57600 [7:15:16<2:48:18, 1.61it/s] 72%|███████▏ | 41293/57600 [7:15:16<2:49:36, 1.60it/s] 72%|███████▏ | 41294/57600 [7:15:17<2:49:25, 1.60it/s] 72%|███████▏ | 41295/57600 [7:15:18<3:01:02, 1.50it/s] 72%|███████▏ | 41296/57600 [7:15:18<2:56:36, 1.54it/s] 72%|███████▏ | 41297/57600 [7:15:19<2:51:35, 1.58it/s] 72%|███████▏ | 41298/57600 [7:15:20<2:46:23, 1.63it/s] 72%|███████▏ | 41299/57600 [7:15:20<2:44:23, 1.65it/s] 72%|███████▏ | 41300/57600 [7:15:21<2:48:03, 1.62it/s] {'loss': 1.1193, 'learning_rate': 3.55574912891986e-07, 'epoch': 455.85} + 72%|███████▏ | 41300/57600 [7:15:21<2:48:03, 1.62it/s] 72%|███████▏ | 41301/57600 [7:15:21<2:50:24, 1.59it/s] 72%|███████▏ | 41302/57600 [7:15:22<2:50:03, 1.60it/s] 72%|███████▏ | 41303/57600 [7:15:23<2:48:14, 1.61it/s] 72%|███████▏ | 41304/57600 [7:15:23<2:54:07, 1.56it/s] 72%|███████▏ | 41305/57600 [7:15:24<2:53:52, 1.56it/s] 72%|███████▏ | 41306/57600 [7:15:25<2:50:41, 1.59it/s] 72%|███████▏ | 41307/57600 [7:15:25<2:53:38, 1.56it/s] 72%|███████▏ | 41308/57600 [7:15:26<2:54:06, 1.56it/s] 72%|███████▏ | 41309/57600 [7:15:27<2:56:04, 1.54it/s] 72%|███████▏ | 41310/57600 [7:15:27<2:54:13, 1.56it/s] 72%|███████▏ | 41311/57600 [7:15:28<2:49:12, 1.60it/s] 72%|███████▏ | 41312/57600 [7:15:28<2:54:48, 1.55it/s] 72%|███████▏ | 41313/57600 [7:15:29<2:51:15, 1.59it/s] 72%|███████▏ | 41314/57600 [7:15:30<2:53:44, 1.56it/s] 72%|███████▏ | 41315/57600 [7:15:30<2:53:02, 1.57it/s] 72%|███████▏ | 41316/57600 [7:15:31<2:51:12, 1.59it/s] 72%|███████▏ | 41317/57600 [7:15:32<2:49:05, 1.60it/s] 72%|███████▏ | 41318/57600 [7:15:32<2:54:40, 1.55it/s] 72%|███████▏ | 41319/57600 [7:15:33<2:52:17, 1.57it/s] 72%|███████▏ | 41320/57600 [7:15:33<2:47:43, 1.62it/s] {'loss': 1.1411, 'learning_rate': 3.552613240418119e-07, 'epoch': 456.07} + 72%|███████▏ | 41320/57600 [7:15:33<2:47:43, 1.62it/s] 72%|███████▏ | 41321/57600 [7:15:34<2:54:44, 1.55it/s] 72%|███████▏ | 41322/57600 [7:15:35<2:50:02, 1.60it/s] 72%|███████▏ | 41323/57600 [7:15:35<2:48:07, 1.61it/s] 72%|███████▏ | 41324/57600 [7:15:36<2:47:33, 1.62it/s] 72%|███████▏ | 41325/57600 [7:15:37<2:53:44, 1.56it/s] 72%|███████▏ | 41326/57600 [7:15:37<2:53:57, 1.56it/s] 72%|███���███▏ | 41327/57600 [7:15:38<2:55:41, 1.54it/s] 72%|███████▏ | 41328/57600 [7:15:39<2:51:36, 1.58it/s] 72%|███████▏ | 41329/57600 [7:15:39<2:51:08, 1.58it/s] 72%|███████▏ | 41330/57600 [7:15:40<2:48:41, 1.61it/s] 72%|███████▏ | 41331/57600 [7:15:40<2:46:07, 1.63it/s] 72%|███████▏ | 41332/57600 [7:15:41<2:57:07, 1.53it/s] 72%|███████▏ | 41333/57600 [7:15:42<2:54:45, 1.55it/s] 72%|███████▏ | 41334/57600 [7:15:42<2:53:35, 1.56it/s] 72%|███████▏ | 41335/57600 [7:15:43<2:54:33, 1.55it/s] 72%|███████▏ | 41336/57600 [7:15:44<2:51:46, 1.58it/s] 72%|███████▏ | 41337/57600 [7:15:44<2:49:14, 1.60it/s] 72%|███████▏ | 41338/57600 [7:15:45<2:59:18, 1.51it/s] 72%|███████▏ | 41339/57600 [7:15:46<3:00:11, 1.50it/s] 72%|███████▏ | 41340/57600 [7:15:46<2:58:23, 1.52it/s] {'loss': 1.1061, 'learning_rate': 3.549477351916376e-07, 'epoch': 456.29} + 72%|███████▏ | 41340/57600 [7:15:46<2:58:23, 1.52it/s] 72%|███████▏ | 41341/57600 [7:15:47<2:53:44, 1.56it/s] 72%|███████▏ | 41342/57600 [7:15:48<2:50:44, 1.59it/s] 72%|███████▏ | 41343/57600 [7:15:48<2:50:54, 1.59it/s] 72%|███████▏ | 41344/57600 [7:15:49<2:54:17, 1.55it/s] 72%|███████▏ | 41345/57600 [7:15:49<2:50:30, 1.59it/s] 72%|███████▏ | 41346/57600 [7:15:50<2:47:38, 1.62it/s] 72%|███████▏ | 41347/57600 [7:15:51<2:50:30, 1.59it/s] 72%|███████▏ | 41348/57600 [7:15:51<2:44:04, 1.65it/s] 72%|███████▏ | 41349/57600 [7:15:52<2:46:00, 1.63it/s] 72%|███████▏ | 41350/57600 [7:15:52<2:42:43, 1.66it/s] 72%|███████▏ | 41351/57600 [7:15:53<2:50:09, 1.59it/s] 72%|███████▏ | 41352/57600 [7:15:54<2:51:47, 1.58it/s] 72%|███████▏ | 41353/57600 [7:15:54<2:51:38, 1.58it/s] 72%|███████▏ | 41354/57600 [7:15:55<2:50:37, 1.59it/s] 72%|███████▏ | 41355/57600 [7:15:56<2:49:50, 1.59it/s] 72%|███████▏ | 41356/57600 [7:15:56<2:46:59, 1.62it/s] 72%|███████▏ | 41357/57600 [7:15:57<2:43:30, 1.66it/s] 72%|███████▏ | 41358/57600 [7:15:58<2:51:20, 1.58it/s] 72%|███████▏ | 41359/57600 [7:15:58<2:51:45, 1.58it/s] 72%|███████▏ | 41360/57600 [7:15:59<2:47:51, 1.61it/s] {'loss': 1.1603, 'learning_rate': 3.5463414634146344e-07, 'epoch': 456.51} + 72%|███████▏ | 41360/57600 [7:15:59<2:47:51, 1.61it/s] 72%|███████▏ | 41361/57600 [7:15:59<2:48:45, 1.60it/s] 72%|███████▏ | 41362/57600 [7:16:00<2:50:31, 1.59it/s] 72%|███████▏ | 41363/57600 [7:16:01<2:46:55, 1.62it/s] 72%|███████▏ | 41364/57600 [7:16:01<2:45:29, 1.64it/s] 72%|███████▏ | 41365/57600 [7:16:02<2:49:06, 1.60it/s] 72%|███████▏ | 41366/57600 [7:16:02<2:45:33, 1.63it/s] 72%|███████▏ | 41367/57600 [7:16:03<2:53:31, 1.56it/s] 72%|███████▏ | 41368/57600 [7:16:04<2:52:35, 1.57it/s] 72%|███████▏ | 41369/57600 [7:16:04<2:50:20, 1.59it/s] 72%|███████▏ | 41370/57600 [7:16:05<2:52:50, 1.56it/s] 72%|███████▏ | 41371/57600 [7:16:06<2:55:29, 1.54it/s] 72%|███████▏ | 41372/57600 [7:16:06<2:57:24, 1.52it/s] 72%|███████▏ | 41373/57600 [7:16:07<2:55:41, 1.54it/s] 72%|███████▏ | 41374/57600 [7:16:08<2:55:08, 1.54it/s] 72%|███████▏ | 41375/57600 [7:16:08<2:56:48, 1.53it/s] 72%|███████▏ | 41376/57600 [7:16:09<2:54:20, 1.55it/s] 72%|███████▏ | 41377/57600 [7:16:10<2:54:37, 1.55it/s] 72%|███████▏ | 41378/57600 [7:16:10<2:58:56, 1.51it/s] 72%|███████▏ | 41379/57600 [7:16:11<2:57:51, 1.52it/s] 72%|███████▏ | 41380/57600 [7:16:12<2:52:01, 1.57it/s] {'loss': 1.0956, 'learning_rate': 3.5432055749128914e-07, 'epoch': 456.73} + 72%|███████▏ | 41380/57600 [7:16:12<2:52:01, 1.57it/s] 72%|███████▏ | 41381/57600 [7:16:12<2:48:21, 1.61it/s] 72%|███████▏ | 41382/57600 [7:16:13<2:48:16, 1.61it/s] 72%|███████▏ | 41383/57600 [7:16:13<2:48:00, 1.61it/s] 72%|███████▏ | 41384/57600 [7:16:14<2:44:38, 1.64it/s] 72%|███████▏ | 41385/57600 [7:16:15<2:42:02, 1.67it/s] 72%|███████▏ | 41386/57600 [7:16:15<2:42:39, 1.66it/s] 72%|███████▏ | 41387/57600 [7:16:16<2:41:30, 1.67it/s] 72%|███████▏ | 41388/57600 [7:16:16<2:42:59, 1.66it/s] 72%|███████▏ | 41389/57600 [7:16:17<2:45:40, 1.63it/s] 72%|███████▏ | 41390/57600 [7:16:18<2:48:53, 1.60it/s] 72%|███████▏ | 41391/57600 [7:16:18<2:52:05, 1.57it/s] 72%|███████▏ | 41392/57600 [7:16:19<2:53:57, 1.55it/s] 72%|███████▏ | 41393/57600 [7:16:20<2:48:03, 1.61it/s] 72%|███████▏ | 41394/57600 [7:16:20<2:50:48, 1.58it/s] 72%|███████▏ | 41395/57600 [7:16:21<2:46:45, 1.62it/s] 72%|███████▏ | 41396/57600 [7:16:21<2:46:33, 1.62it/s] 72%|███████▏ | 41397/57600 [7:16:22<2:46:09, 1.63it/s] 72%|███████▏ | 41398/57600 [7:16:23<2:55:14, 1.54it/s] 72%|███████▏ | 41399/57600 [7:16:23<2:47:08, 1.62it/s] 72%|███████▏ | 41400/57600 [7:16:24<2:48:28, 1.60it/s] {'loss': 1.1584, 'learning_rate': 3.54006968641115e-07, 'epoch': 456.95} + 72%|███████▏ | 41400/57600 [7:16:24<2:48:28, 1.60it/s] 72%|███████▏ | 41401/57600 [7:16:24<2:45:10, 1.63it/s] 72%|███████▏ | 41402/57600 [7:16:25<2:43:34, 1.65it/s] 72%|███████▏ | 41403/57600 [7:16:26<2:47:05, 1.62it/s] 72%|███████▏ | 41404/57600 [7:16:26<2:44:34, 1.64it/s] 72%|███████▏ | 41405/57600 [7:16:27<2:57:18, 1.52it/s] 72%|███████▏ | 41406/57600 [7:16:28<2:54:31, 1.55it/s] 72%|███████▏ | 41407/57600 [7:16:28<2:51:12, 1.58it/s] 72%|███████▏ | 41408/57600 [7:16:29<3:00:33, 1.49it/s] 72%|███████▏ | 41409/57600 [7:16:30<2:58:40, 1.51it/s] 72%|███████▏ | 41410/57600 [7:16:30<2:56:48, 1.53it/s] 72%|███████▏ | 41411/57600 [7:16:31<2:55:04, 1.54it/s] 72%|███████▏ | 41412/57600 [7:16:32<2:56:33, 1.53it/s] 72%|███████▏ | 41413/57600 [7:16:32<2:54:27, 1.55it/s] 72%|███████▏ | 41414/57600 [7:16:33<2:55:06, 1.54it/s] 72%|███████▏ | 41415/57600 [7:16:34<2:55:44, 1.53it/s] 72%|███████▏ | 41416/57600 [7:16:34<2:55:27, 1.54it/s] 72%|███████▏ | 41417/57600 [7:16:35<2:53:39, 1.55it/s] 72%|███████▏ | 41418/57600 [7:16:35<2:48:40, 1.60it/s] 72%|███████▏ | 41419/57600 [7:16:36<2:53:50, 1.55it/s] 72%|███████▏ | 41420/57600 [7:16:37<2:52:10, 1.57it/s] {'loss': 1.1137, 'learning_rate': 3.536933797909407e-07, 'epoch': 457.17} + 72%|███████▏ | 41420/57600 [7:16:37<2:52:10, 1.57it/s] 72%|███████▏ | 41421/57600 [7:16:37<2:51:10, 1.58it/s] 72%|███████▏ | 41422/57600 [7:16:38<2:47:32, 1.61it/s] 72%|███████▏ | 41423/57600 [7:16:39<2:48:33, 1.60it/s] 72%|███████▏ | 41424/57600 [7:16:39<2:43:31, 1.65it/s] 72%|███████▏ | 41425/57600 [7:16:40<2:40:51, 1.68it/s] 72%|███████▏ | 41426/57600 [7:16:40<2:41:31, 1.67it/s] 72%|███████▏ | 41427/57600 [7:16:41<2:40:09, 1.68it/s] 72%|███████▏ | 41428/57600 [7:16:42<2:43:20, 1.65it/s] 72%|███████▏ | 41429/57600 [7:16:42<2:45:23, 1.63it/s] 72%|███████▏ | 41430/57600 [7:16:43<2:39:11, 1.69it/s] 72%|███████▏ | 41431/57600 [7:16:43<2:48:47, 1.60it/s] 72%|███████▏ | 41432/57600 [7:16:44<2:43:52, 1.64it/s] 72%|███████▏ | 41433/57600 [7:16:45<2:51:25, 1.57it/s] 72%|███████▏ | 41434/57600 [7:16:45<2:49:12, 1.59it/s] 72%|███████▏ | 41435/57600 [7:16:46<2:46:13, 1.62it/s] 72%|███████▏ | 41436/57600 [7:16:47<2:45:50, 1.62it/s] 72%|███████▏ | 41437/57600 [7:16:47<2:43:10, 1.65it/s] 72%|███████▏ | 41438/57600 [7:16:48<2:45:47, 1.62it/s] 72%|███████▏ | 41439/57600 [7:16:48<2:43:26, 1.65it/s] 72%|███████▏ | 41440/57600 [7:16:49<2:43:36, 1.65it/s] {'loss': 1.1808, 'learning_rate': 3.5337979094076655e-07, 'epoch': 457.4} + 72%|███████▏ | 41440/57600 [7:16:49<2:43:36, 1.65it/s] 72%|███████▏ | 41441/57600 [7:16:50<2:45:42, 1.63it/s] 72%|███████▏ | 41442/57600 [7:16:50<2:45:11, 1.63it/s] 72%|███████▏ | 41443/57600 [7:16:51<2:44:41, 1.64it/s] 72%|███████▏ | 41444/57600 [7:16:51<2:48:30, 1.60it/s] 72%|███████▏ | 41445/57600 [7:16:52<2:49:49, 1.59it/s] 72%|███████▏ | 41446/57600 [7:16:53<2:48:04, 1.60it/s] 72%|███████▏ | 41447/57600 [7:16:53<2:52:07, 1.56it/s] 72%|███████▏ | 41448/57600 [7:16:54<2:48:38, 1.60it/s] 72%|███████▏ | 41449/57600 [7:16:55<2:47:21, 1.61it/s] 72%|███████▏ | 41450/57600 [7:16:55<2:46:53, 1.61it/s] 72%|███████▏ | 41451/57600 [7:16:56<2:48:27, 1.60it/s] 72%|███████▏ | 41452/57600 [7:16:56<2:49:54, 1.58it/s] 72%|███████▏ | 41453/57600 [7:16:57<2:47:51, 1.60it/s] 72%|███████▏ | 41454/57600 [7:16:58<2:48:25, 1.60it/s] 72%|███████▏ | 41455/57600 [7:16:58<2:48:18, 1.60it/s] 72%|███████▏ | 41456/57600 [7:16:59<2:41:39, 1.66it/s] 72%|███████▏ | 41457/57600 [7:16:59<2:40:25, 1.68it/s] 72%|███████▏ | 41458/57600 [7:17:00<2:42:52, 1.65it/s] 72%|███████▏ | 41459/57600 [7:17:01<2:40:17, 1.68it/s] 72%|███████▏ | 41460/57600 [7:17:01<2:45:48, 1.62it/s] {'loss': 1.1562, 'learning_rate': 3.5306620209059236e-07, 'epoch': 457.62} + 72%|███████▏ | 41460/57600 [7:17:01<2:45:48, 1.62it/s] 72%|███████▏ | 41461/57600 [7:17:02<2:41:06, 1.67it/s] 72%|███████▏ | 41462/57600 [7:17:03<2:41:37, 1.66it/s] 72%|███████▏ | 41463/57600 [7:17:03<2:43:41, 1.64it/s] 72%|███████▏ | 41464/57600 [7:17:04<2:43:42, 1.64it/s] 72%|███████▏ | 41465/57600 [7:17:04<2:49:40, 1.58it/s] 72%|███████▏ | 41466/57600 [7:17:05<2:50:27, 1.58it/s] 72%|███████▏ | 41467/57600 [7:17:06<2:56:51, 1.52it/s] 72%|███████▏ | 41468/57600 [7:17:06<2:55:13, 1.53it/s] 72%|███████▏ | 41469/57600 [7:17:07<2:55:29, 1.53it/s] 72%|███████▏ | 41470/57600 [7:17:08<2:57:30, 1.51it/s] 72%|███████▏ | 41471/57600 [7:17:08<2:52:46, 1.56it/s] 72%|███████▏ | 41472/57600 [7:17:09<2:54:25, 1.54it/s] 72%|███████▏ | 41473/57600 [7:17:10<2:55:28, 1.53it/s] 72%|███████▏ | 41474/57600 [7:17:10<2:56:44, 1.52it/s] 72%|███████▏ | 41475/57600 [7:17:11<2:53:00, 1.55it/s] 72%|███████▏ | 41476/57600 [7:17:12<2:52:14, 1.56it/s] 72%|███████▏ | 41477/57600 [7:17:12<2:54:15, 1.54it/s] 72%|███████▏ | 41478/57600 [7:17:13<2:58:04, 1.51it/s] 72%|███████▏ | 41479/57600 [7:17:14<2:55:56, 1.53it/s] 72%|███████▏ | 41480/57600 [7:17:14<2:57:05, 1.52it/s] {'loss': 1.0854, 'learning_rate': 3.527526132404181e-07, 'epoch': 457.84} + 72%|███████▏ | 41480/57600 [7:17:14<2:57:05, 1.52it/s] 72%|███████▏ | 41481/57600 [7:17:15<2:50:01, 1.58it/s] 72%|███████▏ | 41482/57600 [7:17:16<2:56:30, 1.52it/s] 72%|███████▏ | 41483/57600 [7:17:16<2:56:46, 1.52it/s] 72%|███████▏ | 41484/57600 [7:17:17<2:50:57, 1.57it/s] 72%|███████▏ | 41485/57600 [7:17:17<2:47:52, 1.60it/s] 72%|███████▏ | 41486/57600 [7:17:18<2:49:08, 1.59it/s] 72%|███████▏ | 41487/57600 [7:17:19<2:52:11, 1.56it/s] 72%|███████▏ | 41488/57600 [7:17:19<2:47:05, 1.61it/s] 72%|███████▏ | 41489/57600 [7:17:20<2:46:23, 1.61it/s] 72%|███████▏ | 41490/57600 [7:17:21<2:44:53, 1.63it/s] 72%|███████▏ | 41491/57600 [7:17:21<2:48:25, 1.59it/s] 72%|███████▏ | 41492/57600 [7:17:22<2:48:41, 1.59it/s] 72%|███████▏ | 41493/57600 [7:17:22<2:52:23, 1.56it/s] 72%|███████▏ | 41494/57600 [7:17:23<2:48:51, 1.59it/s] 72%|███████▏ | 41495/57600 [7:17:24<3:00:03, 1.49it/s] 72%|███████▏ | 41496/57600 [7:17:24<2:55:30, 1.53it/s] 72%|███████▏ | 41497/57600 [7:17:25<2:52:11, 1.56it/s] 72%|███████▏ | 41498/57600 [7:17:26<2:50:21, 1.58it/s] 72%|███████▏ | 41499/57600 [7:17:26<2:54:12, 1.54it/s] 72%|███████▏ | 41500/57600 [7:17:27<2:49:08, 1.59it/s] {'loss': 1.1344, 'learning_rate': 3.524390243902439e-07, 'epoch': 458.06} + 72%|███████▏ | 41500/57600 [7:17:27<2:49:08, 1.59it/s] 72%|███████▏ | 41501/57600 [7:17:28<2:49:41, 1.58it/s] 72%|███████▏ | 41502/57600 [7:17:28<2:46:54, 1.61it/s] 72%|███████▏ | 41503/57600 [7:17:29<2:40:34, 1.67it/s] 72%|███████▏ | 41504/57600 [7:17:29<2:44:13, 1.63it/s] 72%|███████▏ | 41505/57600 [7:17:30<2:41:42, 1.66it/s] 72%|███████▏ | 41506/57600 [7:17:31<2:43:36, 1.64it/s] 72%|███████▏ | 41507/57600 [7:17:31<2:50:28, 1.57it/s] 72%|███████▏ | 41508/57600 [7:17:32<2:50:12, 1.58it/s] 72%|███████▏ | 41509/57600 [7:17:33<2:52:02, 1.56it/s] 72%|███████▏ | 41510/57600 [7:17:33<2:56:10, 1.52it/s] 72%|███████▏ | 41511/57600 [7:17:34<2:52:05, 1.56it/s] 72%|███████▏ | 41512/57600 [7:17:34<2:49:39, 1.58it/s] 72%|███████▏ | 41513/57600 [7:17:35<2:46:03, 1.61it/s] 72%|███████▏ | 41514/57600 [7:17:36<2:45:40, 1.62it/s] 72%|███████▏ | 41515/57600 [7:17:36<2:49:22, 1.58it/s] 72%|███████▏ | 41516/57600 [7:17:37<2:49:13, 1.58it/s] 72%|███████▏ | 41517/57600 [7:17:38<2:52:28, 1.55it/s] 72%|███████▏ | 41518/57600 [7:17:38<2:49:09, 1.58it/s] 72%|███████▏ | 41519/57600 [7:17:39<2:54:07, 1.54it/s] 72%|███████▏ | 41520/57600 [7:17:40<2:51:23, 1.56it/s] {'loss': 1.154, 'learning_rate': 3.521254355400696e-07, 'epoch': 458.28} + 72%|███████▏ | 41520/57600 [7:17:40<2:51:23, 1.56it/s] 72%|███████▏ | 41521/57600 [7:17:40<2:47:56, 1.60it/s] 72%|███████▏ | 41522/57600 [7:17:41<2:54:19, 1.54it/s] 72%|███████▏ | 41523/57600 [7:17:41<2:49:47, 1.58it/s] 72%|███████▏ | 41524/57600 [7:17:42<2:48:50, 1.59it/s] 72%|███████▏ | 41525/57600 [7:17:43<2:47:09, 1.60it/s] 72%|███████▏ | 41526/57600 [7:17:43<2:44:56, 1.62it/s] 72%|███████▏ | 41527/57600 [7:17:44<2:42:16, 1.65it/s] 72%|███████▏ | 41528/57600 [7:17:44<2:44:32, 1.63it/s] 72%|███████▏ | 41529/57600 [7:17:45<2:47:51, 1.60it/s] 72%|███████▏ | 41530/57600 [7:17:46<2:52:50, 1.55it/s] 72%|███████▏ | 41531/57600 [7:17:46<2:53:39, 1.54it/s] 72%|███████▏ | 41532/57600 [7:17:47<2:49:42, 1.58it/s] 72%|███████▏ | 41533/57600 [7:17:48<2:48:22, 1.59it/s] 72%|███████▏ | 41534/57600 [7:17:48<2:43:09, 1.64it/s] 72%|███████▏ | 41535/57600 [7:17:49<2:42:35, 1.65it/s] 72%|███████▏ | 41536/57600 [7:17:49<2:43:06, 1.64it/s] 72%|███████▏ | 41537/57600 [7:17:50<2:46:43, 1.61it/s] 72%|███████▏ | 41538/57600 [7:17:51<2:41:50, 1.65it/s] 72%|███████▏ | 41539/57600 [7:17:51<2:47:59, 1.59it/s] 72%|███████▏ | 41540/57600 [7:17:52<2:49:59, 1.57it/s] {'loss': 1.1108, 'learning_rate': 3.518118466898954e-07, 'epoch': 458.5} + 72%|███████▏ | 41540/57600 [7:17:52<2:49:59, 1.57it/s] 72%|███████▏ | 41541/57600 [7:17:53<2:48:58, 1.58it/s] 72%|███████▏ | 41542/57600 [7:17:53<2:52:52, 1.55it/s] 72%|███████▏ | 41543/57600 [7:17:54<2:49:31, 1.58it/s] 72%|███████▏ | 41544/57600 [7:17:55<2:50:33, 1.57it/s] 72%|███████▏ | 41545/57600 [7:17:55<2:53:01, 1.55it/s] 72%|███████▏ | 41546/57600 [7:17:56<2:52:54, 1.55it/s] 72%|███████▏ | 41547/57600 [7:17:57<2:53:36, 1.54it/s] 72%|███████▏ | 41548/57600 [7:17:57<2:51:56, 1.56it/s] 72%|███████▏ | 41549/57600 [7:17:58<2:45:45, 1.61it/s] 72%|███████▏ | 41550/57600 [7:17:58<2:47:39, 1.60it/s] 72%|███████▏ | 41551/57600 [7:17:59<2:50:22, 1.57it/s] 72%|███████▏ | 41552/57600 [7:18:00<2:50:05, 1.57it/s] 72%|███████▏ | 41553/57600 [7:18:00<2:49:24, 1.58it/s] 72%|███████▏ | 41554/57600 [7:18:01<2:49:59, 1.57it/s] 72%|███████▏ | 41555/57600 [7:18:02<2:46:14, 1.61it/s] 72%|███████▏ | 41556/57600 [7:18:02<2:51:00, 1.56it/s] 72%|███████▏ | 41557/57600 [7:18:03<2:48:18, 1.59it/s] 72%|███████▏ | 41558/57600 [7:18:03<2:48:02, 1.59it/s] 72%|███████▏ | 41559/57600 [7:18:04<2:47:11, 1.60it/s] 72%|███████▏ | 41560/57600 [7:18:05<2:49:08, 1.58it/s] {'loss': 1.1306, 'learning_rate': 3.5149825783972117e-07, 'epoch': 458.72} + 72%|███████▏ | 41560/57600 [7:18:05<2:49:08, 1.58it/s] 72%|███████▏ | 41561/57600 [7:18:05<2:56:47, 1.51it/s] 72%|███████▏ | 41562/57600 [7:18:06<2:54:04, 1.54it/s] 72%|███████▏ | 41563/57600 [7:18:07<2:50:15, 1.57it/s] 72%|███████▏ | 41564/57600 [7:18:07<2:55:39, 1.52it/s] 72%|███████▏ | 41565/57600 [7:18:08<2:52:14, 1.55it/s] 72%|███████▏ | 41566/57600 [7:18:09<2:48:36, 1.58it/s] 72%|███████▏ | 41567/57600 [7:18:09<2:43:56, 1.63it/s] 72%|███████▏ | 41568/57600 [7:18:10<2:41:42, 1.65it/s] 72%|███████▏ | 41569/57600 [7:18:10<2:43:20, 1.64it/s] 72%|███��███▏ | 41570/57600 [7:18:11<2:41:05, 1.66it/s] 72%|███████▏ | 41571/57600 [7:18:12<2:46:46, 1.60it/s] 72%|███████▏ | 41572/57600 [7:18:12<2:44:18, 1.63it/s] 72%|███████▏ | 41573/57600 [7:18:13<2:41:46, 1.65it/s] 72%|███████▏ | 41574/57600 [7:18:13<2:39:31, 1.67it/s] 72%|███████▏ | 41575/57600 [7:18:14<2:46:47, 1.60it/s] 72%|███████▏ | 41576/57600 [7:18:15<2:46:37, 1.60it/s] 72%|███████▏ | 41577/57600 [7:18:16<2:59:15, 1.49it/s] 72%|███████▏ | 41578/57600 [7:18:16<2:59:02, 1.49it/s] 72%|███████▏ | 41579/57600 [7:18:17<2:56:28, 1.51it/s] 72%|███████▏ | 41580/57600 [7:18:17<2:48:43, 1.58it/s] {'loss': 1.1684, 'learning_rate': 3.51184668989547e-07, 'epoch': 458.94} + 72%|███████▏ | 41580/57600 [7:18:17<2:48:43, 1.58it/s] 72%|███████▏ | 41581/57600 [7:18:18<2:50:12, 1.57it/s] 72%|███████▏ | 41582/57600 [7:18:19<2:50:54, 1.56it/s] 72%|███████▏ | 41583/57600 [7:18:19<2:52:40, 1.55it/s] 72%|███████▏ | 41584/57600 [7:18:20<2:51:49, 1.55it/s] 72%|███████▏ | 41585/57600 [7:18:21<2:50:23, 1.57it/s] 72%|███████▏ | 41586/57600 [7:18:21<2:57:43, 1.50it/s] 72%|███████▏ | 41587/57600 [7:18:22<2:51:08, 1.56it/s] 72%|███████▏ | 41588/57600 [7:18:23<2:52:56, 1.54it/s] 72%|███████▏ | 41589/57600 [7:18:23<2:53:52, 1.53it/s] 72%|███████▏ | 41590/57600 [7:18:24<2:51:49, 1.55it/s] 72%|███████▏ | 41591/57600 [7:18:24<2:49:09, 1.58it/s] 72%|███████▏ | 41592/57600 [7:18:25<2:51:32, 1.56it/s] 72%|███████▏ | 41593/57600 [7:18:26<2:54:27, 1.53it/s] 72%|███████▏ | 41594/57600 [7:18:26<2:54:03, 1.53it/s] 72%|███████▏ | 41595/57600 [7:18:27<2:54:29, 1.53it/s] 72%|███████▏ | 41596/57600 [7:18:28<2:52:47, 1.54it/s] 72%|███████▏ | 41597/57600 [7:18:28<2:49:25, 1.57it/s] 72%|███████▏ | 41598/57600 [7:18:29<2:48:25, 1.58it/s] 72%|███████▏ | 41599/57600 [7:18:30<2:48:40, 1.58it/s] 72%|███████▏ | 41600/57600 [7:18:30<2:47:10, 1.60it/s] {'loss': 1.1056, 'learning_rate': 3.5087108013937283e-07, 'epoch': 459.16} + 72%|███████▏ | 41600/57600 [7:18:30<2:47:10, 1.60it/s] 72%|███████▏ | 41601/57600 [7:18:31<2:47:52, 1.59it/s] 72%|███████▏ | 41602/57600 [7:18:31<2:45:20, 1.61it/s] 72%|███████▏ | 41603/57600 [7:18:32<2:45:38, 1.61it/s] 72%|███████▏ | 41604/57600 [7:18:33<2:48:22, 1.58it/s] 72%|███████▏ | 41605/57600 [7:18:33<2:45:36, 1.61it/s] 72%|███████▏ | 41606/57600 [7:18:34<2:44:51, 1.62it/s] 72%|███████▏ | 41607/57600 [7:18:35<2:49:32, 1.57it/s] 72%|███████▏ | 41608/57600 [7:18:35<2:46:15, 1.60it/s] 72%|███████▏ | 41609/57600 [7:18:36<2:49:09, 1.58it/s] 72%|███████▏ | 41610/57600 [7:18:36<2:46:53, 1.60it/s] 72%|███████▏ | 41611/57600 [7:18:37<2:47:11, 1.59it/s] 72%|███████▏ | 41612/57600 [7:18:38<2:47:53, 1.59it/s] 72%|███████▏ | 41613/57600 [7:18:38<2:42:09, 1.64it/s] 72%|███████▏ | 41614/57600 [7:18:39<2:43:45, 1.63it/s] 72%|███████▏ | 41615/57600 [7:18:40<2:48:37, 1.58it/s] 72%|███████▏ | 41616/57600 [7:18:40<2:47:09, 1.59it/s] 72%|███████▏ | 41617/57600 [7:18:41<2:48:24, 1.58it/s] 72%|███████▏ | 41618/57600 [7:18:42<2:48:32, 1.58it/s] 72%|███████▏ | 41619/57600 [7:18:42<2:47:38, 1.59it/s] 72%|███████▏ | 41620/57600 [7:18:43<2:52:48, 1.54it/s] {'loss': 1.125, 'learning_rate': 3.505574912891986e-07, 'epoch': 459.38} + 72%|███████▏ | 41620/57600 [7:18:43<2:52:48, 1.54it/s] 72%|███████▏ | 41621/57600 [7:18:43<2:53:17, 1.54it/s] 72%|███████▏ | 41622/57600 [7:18:44<2:49:31, 1.57it/s] 72%|███████▏ | 41623/57600 [7:18:45<2:45:51, 1.61it/s] 72%|███████▏ | 41624/57600 [7:18:45<2:57:17, 1.50it/s] 72%|███████▏ | 41625/57600 [7:18:46<2:51:45, 1.55it/s] 72%|███████▏ | 41626/57600 [7:18:47<2:48:16, 1.58it/s] 72%|███████▏ | 41627/57600 [7:18:47<2:45:16, 1.61it/s] 72%|███████▏ | 41628/57600 [7:18:48<2:48:40, 1.58it/s] 72%|███████▏ | 41629/57600 [7:18:48<2:45:24, 1.61it/s] 72%|███████▏ | 41630/57600 [7:18:49<2:41:29, 1.65it/s] 72%|███████▏ | 41631/57600 [7:18:50<2:44:50, 1.61it/s] 72%|███████▏ | 41632/57600 [7:18:50<2:46:34, 1.60it/s] 72%|███████▏ | 41633/57600 [7:18:51<2:48:02, 1.58it/s] 72%|███████▏ | 41634/57600 [7:18:52<2:46:10, 1.60it/s] 72%|███████▏ | 41635/57600 [7:18:52<2:45:40, 1.61it/s] 72%|███████▏ | 41636/57600 [7:18:53<2:46:24, 1.60it/s] 72%|███████▏ | 41637/57600 [7:18:53<2:47:24, 1.59it/s] 72%|███████▏ | 41638/57600 [7:18:54<2:46:05, 1.60it/s] 72%|███████▏ | 41639/57600 [7:18:55<2:45:15, 1.61it/s] 72%|███████▏ | 41640/57600 [7:18:55<2:43:15, 1.63it/s] {'loss': 1.1251, 'learning_rate': 3.502439024390244e-07, 'epoch': 459.6} + 72%|███████▏ | 41640/57600 [7:18:55<2:43:15, 1.63it/s] 72%|███████▏ | 41641/57600 [7:18:56<2:41:40, 1.65it/s] 72%|███████▏ | 41642/57600 [7:18:57<2:44:12, 1.62it/s] 72%|███████▏ | 41643/57600 [7:18:57<2:50:36, 1.56it/s] 72%|███████▏ | 41644/57600 [7:18:58<2:52:01, 1.55it/s] 72%|███████▏ | 41645/57600 [7:18:59<2:57:07, 1.50it/s] 72%|███████▏ | 41646/57600 [7:18:59<2:50:05, 1.56it/s] 72%|███████▏ | 41647/57600 [7:19:00<2:50:17, 1.56it/s] 72%|███████▏ | 41648/57600 [7:19:00<2:49:01, 1.57it/s] 72%|███████▏ | 41649/57600 [7:19:01<2:46:57, 1.59it/s] 72%|███████▏ | 41650/57600 [7:19:02<2:51:49, 1.55it/s] 72%|███████▏ | 41651/57600 [7:19:02<2:46:05, 1.60it/s] 72%|███████▏ | 41652/57600 [7:19:03<2:43:35, 1.62it/s] 72%|███████▏ | 41653/57600 [7:19:04<2:42:26, 1.64it/s] 72%|███████▏ | 41654/57600 [7:19:04<2:40:46, 1.65it/s] 72%|███████▏ | 41655/57600 [7:19:05<2:37:18, 1.69it/s] 72%|███████▏ | 41656/57600 [7:19:05<2:42:13, 1.64it/s] 72%|███████▏ | 41657/57600 [7:19:06<2:46:17, 1.60it/s] 72%|███████▏ | 41658/57600 [7:19:07<2:43:21, 1.63it/s] 72%|███████▏ | 41659/57600 [7:19:07<2:52:40, 1.54it/s] 72%|███████▏ | 41660/57600 [7:19:08<2:50:40, 1.56it/s] {'loss': 1.1147, 'learning_rate': 3.499303135888501e-07, 'epoch': 459.82} + 72%|███████▏ | 41660/57600 [7:19:08<2:50:40, 1.56it/s] 72%|███████▏ | 41661/57600 [7:19:09<2:50:51, 1.55it/s] 72%|███████▏ | 41662/57600 [7:19:09<2:47:43, 1.58it/s] 72%|███████▏ | 41663/57600 [7:19:10<2:51:02, 1.55it/s] 72%|███████▏ | 41664/57600 [7:19:10<2:46:25, 1.60it/s] 72%|███████▏ | 41665/57600 [7:19:11<2:42:54, 1.63it/s] 72%|███████▏ | 41666/57600 [7:19:12<2:40:05, 1.66it/s] 72%|███████▏ | 41667/57600 [7:19:12<2:43:47, 1.62it/s] 72%|███████▏ | 41668/57600 [7:19:13<2:40:20, 1.66it/s] 72%|███████▏ | 41669/57600 [7:19:13<2:37:35, 1.68it/s] 72%|███████▏ | 41670/57600 [7:19:14<2:49:46, 1.56it/s] 72%|███████▏ | 41671/57600 [7:19:15<2:52:02, 1.54it/s] 72%|███████▏ | 41672/57600 [7:19:15<2:50:21, 1.56it/s] 72%|███████▏ | 41673/57600 [7:19:16<2:52:33, 1.54it/s] 72%|███████▏ | 41674/57600 [7:19:17<2:52:11, 1.54it/s] 72%|███████▏ | 41675/57600 [7:19:18<2:58:51, 1.48it/s] 72%|███████▏ | 41676/57600 [7:19:18<2:50:58, 1.55it/s] 72%|███████▏ | 41677/57600 [7:19:19<2:52:43, 1.54it/s] 72%|███████▏ | 41678/57600 [7:19:19<2:49:08, 1.57it/s] 72%|███████▏ | 41679/57600 [7:19:20<2:51:11, 1.55it/s] 72%|███████▏ | 41680/57600 [7:19:21<2:47:13, 1.59it/s] {'loss': 1.1571, 'learning_rate': 3.4961672473867594e-07, 'epoch': 460.04} + 72%|███████▏ | 41680/57600 [7:19:21<2:47:13, 1.59it/s] 72%|███████▏ | 41681/57600 [7:19:21<2:48:05, 1.58it/s] 72%|███████▏ | 41682/57600 [7:19:22<2:45:52, 1.60it/s] 72%|███████▏ | 41683/57600 [7:19:22<2:41:53, 1.64it/s] 72%|███████▏ | 41684/57600 [7:19:23<2:38:08, 1.68it/s] 72%|███████▏ | 41685/57600 [7:19:24<2:40:59, 1.65it/s] 72%|███████▏ | 41686/57600 [7:19:24<2:46:37, 1.59it/s] 72%|███████▏ | 41687/57600 [7:19:25<2:47:09, 1.59it/s] 72%|███████▏ | 41688/57600 [7:19:26<2:45:30, 1.60it/s] 72%|███████▏ | 41689/57600 [7:19:26<2:45:23, 1.60it/s] 72%|███████▏ | 41690/57600 [7:19:27<2:46:34, 1.59it/s] 72%|███████▏ | 41691/57600 [7:19:27<2:43:17, 1.62it/s] 72%|███████▏ | 41692/57600 [7:19:28<2:45:59, 1.60it/s] 72%|███████▏ | 41693/57600 [7:19:29<2:47:59, 1.58it/s] 72%|███████▏ | 41694/57600 [7:19:29<2:45:44, 1.60it/s] 72%|███████▏ | 41695/57600 [7:19:30<2:47:41, 1.58it/s] 72%|███████▏ | 41696/57600 [7:19:31<2:45:31, 1.60it/s] 72%|███████▏ | 41697/57600 [7:19:31<2:46:38, 1.59it/s] 72%|███████▏ | 41698/57600 [7:19:32<2:46:37, 1.59it/s] 72%|███████▏ | 41699/57600 [7:19:32<2:46:05, 1.60it/s] 72%|███████▏ | 41700/57600 [7:19:33<2:44:48, 1.61it/s] {'loss': 1.1576, 'learning_rate': 3.493031358885017e-07, 'epoch': 460.26} + 72%|███████▏ | 41700/57600 [7:19:33<2:44:48, 1.61it/s] 72%|███████▏ | 41701/57600 [7:19:34<2:44:32, 1.61it/s] 72%|███████▏ | 41702/57600 [7:19:34<2:45:10, 1.60it/s] 72%|███████▏ | 41703/57600 [7:19:35<2:50:35, 1.55it/s] 72%|███████▏ | 41704/57600 [7:19:36<2:50:41, 1.55it/s] 72%|███████▏ | 41705/57600 [7:19:36<2:45:18, 1.60it/s] 72%|███████▏ | 41706/57600 [7:19:37<2:42:20, 1.63it/s] 72%|███████▏ | 41707/57600 [7:19:37<2:48:16, 1.57it/s] 72%|███████▏ | 41708/57600 [7:19:38<2:47:25, 1.58it/s] 72%|███████▏ | 41709/57600 [7:19:39<2:51:10, 1.55it/s] 72%|███████▏ | 41710/57600 [7:19:39<2:48:45, 1.57it/s] 72%|███████▏ | 41711/57600 [7:19:40<2:44:04, 1.61it/s] 72%|███████▏ | 41712/57600 [7:19:41<2:40:42, 1.65it/s] 72%|███████▏ | 41713/57600 [7:19:41<2:42:19, 1.63it/s] 72%|███████▏ | 41714/57600 [7:19:42<2:40:34, 1.65it/s] 72%|███████▏ | 41715/57600 [7:19:42<2:37:22, 1.68it/s] 72%|███████▏ | 41716/57600 [7:19:43<2:36:01, 1.70it/s] 72%|███████▏ | 41717/57600 [7:19:44<2:39:43, 1.66it/s] 72%|███████▏ | 41718/57600 [7:19:44<2:46:21, 1.59it/s] 72%|███████▏ | 41719/57600 [7:19:45<2:47:45, 1.58it/s] 72%|███████▏ | 41720/57600 [7:19:45<2:43:22, 1.62it/s] {'loss': 1.1273, 'learning_rate': 3.489895470383275e-07, 'epoch': 460.49} + 72%|███████▏ | 41720/57600 [7:19:45<2:43:22, 1.62it/s] 72%|███████▏ | 41721/57600 [7:19:46<2:52:12, 1.54it/s] 72%|███████▏ | 41722/57600 [7:19:47<2:52:18, 1.54it/s] 72%|███████▏ | 41723/57600 [7:19:47<2:47:07, 1.58it/s] 72%|███████▏ | 41724/57600 [7:19:48<2:51:13, 1.55it/s] 72%|███████▏ | 41725/57600 [7:19:49<2:46:50, 1.59it/s] 72%|███████▏ | 41726/57600 [7:19:49<2:48:38, 1.57it/s] 72%|███████▏ | 41727/57600 [7:19:50<2:44:16, 1.61it/s] 72%|███████▏ | 41728/57600 [7:19:51<2:42:58, 1.62it/s] 72%|███████▏ | 41729/57600 [7:19:51<2:43:12, 1.62it/s] 72%|███████▏ | 41730/57600 [7:19:52<2:46:58, 1.58it/s] 72%|███████▏ | 41731/57600 [7:19:52<2:41:11, 1.64it/s] 72%|███████▏ | 41732/57600 [7:19:53<2:51:21, 1.54it/s] 72%|███████▏ | 41733/57600 [7:19:54<2:51:40, 1.54it/s] 72%|███████▏ | 41734/57600 [7:19:54<2:46:07, 1.59it/s] 72%|███████▏ | 41735/57600 [7:19:55<2:41:39, 1.64it/s] 72%|███████▏ | 41736/57600 [7:19:56<2:40:57, 1.64it/s] 72%|███████▏ | 41737/57600 [7:19:56<2:46:27, 1.59it/s] 72%|███████▏ | 41738/57600 [7:19:57<2:46:57, 1.58it/s] 72%|███████▏ | 41739/57600 [7:19:58<2:49:14, 1.56it/s] 72%|███████▏ | 41740/57600 [7:19:58<2:47:37, 1.58it/s] {'loss': 1.1376, 'learning_rate': 3.486759581881533e-07, 'epoch': 460.71} + 72%|███████▏ | 41740/57600 [7:19:58<2:47:37, 1.58it/s] 72%|███████▏ | 41741/57600 [7:19:59<2:59:20, 1.47it/s] 72%|███████▏ | 41742/57600 [7:20:00<2:57:51, 1.49it/s] 72%|███████▏ | 41743/57600 [7:20:00<2:50:52, 1.55it/s] 72%|███████▏ | 41744/57600 [7:20:01<2:50:13, 1.55it/s] 72%|███████▏ | 41745/57600 [7:20:01<2:44:26, 1.61it/s] 72%|███████▏ | 41746/57600 [7:20:02<2:47:48, 1.57it/s] 72%|███████▏ | 41747/57600 [7:20:03<2:41:48, 1.63it/s] 72%|███████▏ | 41748/57600 [7:20:03<2:42:59, 1.62it/s] 72%|███████▏ | 41749/57600 [7:20:04<2:42:42, 1.62it/s] 72%|███████▏ | 41750/57600 [7:20:04<2:44:02, 1.61it/s] 72%|███████▏ | 41751/57600 [7:20:05<2:45:17, 1.60it/s] 72%|███████▏ | 41752/57600 [7:20:06<2:46:49, 1.58it/s] 72%|███████▏ | 41753/57600 [7:20:06<2:51:01, 1.54it/s] 72%|███████▏ | 41754/57600 [7:20:07<2:48:44, 1.57it/s] 72%|███████▏ | 41755/57600 [7:20:08<2:55:33, 1.50it/s] 72%|███████▏ | 41756/57600 [7:20:08<2:51:08, 1.54it/s] 72%|███████▏ | 41757/57600 [7:20:09<2:50:23, 1.55it/s] 72%|███████▏ | 41758/57600 [7:20:10<2:46:30, 1.59it/s] 72%|███████▏ | 41759/57600 [7:20:10<2:47:08, 1.58it/s] 72%|███████▎ | 41760/57600 [7:20:11<2:46:34, 1.58it/s] {'loss': 1.1215, 'learning_rate': 3.4836236933797906e-07, 'epoch': 460.93} + 72%|███████▎ | 41760/57600 [7:20:11<2:46:34, 1.58it/s] 73%|███████▎ | 41761/57600 [7:20:11<2:43:50, 1.61it/s] 73%|███████▎ | 41762/57600 [7:20:12<2:47:57, 1.57it/s] 73%|███████▎ | 41763/57600 [7:20:13<2:52:50, 1.53it/s] 73%|███████▎ | 41764/57600 [7:20:14<2:52:32, 1.53it/s] 73%|███████▎ | 41765/57600 [7:20:14<2:48:04, 1.57it/s] 73%|███████▎ | 41766/57600 [7:20:15<2:48:34, 1.57it/s] 73%|███████▎ | 41767/57600 [7:20:16<3:01:49, 1.45it/s] 73%|███████▎ | 41768/57600 [7:20:16<2:54:06, 1.52it/s] 73%|███████▎ | 41769/57600 [7:20:17<2:49:17, 1.56it/s] 73%|███████▎ | 41770/57600 [7:20:17<2:47:04, 1.58it/s] 73%|███████▎ | 41771/57600 [7:20:18<2:48:46, 1.56it/s] 73%|███████▎ | 41772/57600 [7:20:19<2:53:27, 1.52it/s] 73%|███████▎ | 41773/57600 [7:20:19<2:50:55, 1.54it/s] 73%|███████▎ | 41774/57600 [7:20:20<2:51:19, 1.54it/s] 73%|███████▎ | 41775/57600 [7:20:21<2:52:14, 1.53it/s] 73%|███████▎ | 41776/57600 [7:20:21<2:51:00, 1.54it/s] 73%|███████▎ | 41777/57600 [7:20:22<2:45:36, 1.59it/s] 73%|███████▎ | 41778/57600 [7:20:23<2:47:56, 1.57it/s] 73%|███████▎ | 41779/57600 [7:20:23<2:47:16, 1.58it/s] 73%|███████▎ | 41780/57600 [7:20:24<2:47:12, 1.58it/s] {'loss': 1.1083, 'learning_rate': 3.4804878048780486e-07, 'epoch': 461.15} + 73%|███████▎ | 41780/57600 [7:20:24<2:47:12, 1.58it/s] 73%|███████▎ | 41781/57600 [7:20:24<2:45:49, 1.59it/s] 73%|███████▎ | 41782/57600 [7:20:25<2:44:42, 1.60it/s] 73%|███████▎ | 41783/57600 [7:20:26<2:41:12, 1.64it/s] 73%|███████▎ | 41784/57600 [7:20:26<2:45:38, 1.59it/s] 73%|███████▎ | 41785/57600 [7:20:27<2:42:24, 1.62it/s] 73%|███████▎ | 41786/57600 [7:20:28<2:49:07, 1.56it/s] 73%|███████▎ | 41787/57600 [7:20:28<2:46:40, 1.58it/s] 73%|███████▎ | 41788/57600 [7:20:29<2:49:21, 1.56it/s] 73%|███████▎ | 41789/57600 [7:20:29<2:45:28, 1.59it/s] 73%|███████▎ | 41790/57600 [7:20:30<2:42:09, 1.62it/s] 73%|███████▎ | 41791/57600 [7:20:31<2:43:48, 1.61it/s] 73%|███████▎ | 41792/57600 [7:20:31<2:42:02, 1.63it/s] 73%|███████▎ | 41793/57600 [7:20:32<2:44:47, 1.60it/s] 73%|███████▎ | 41794/57600 [7:20:32<2:41:23, 1.63it/s] 73%|███████▎ | 41795/57600 [7:20:33<2:40:16, 1.64it/s] 73%|███████▎ | 41796/57600 [7:20:34<2:39:34, 1.65it/s] 73%|███████▎ | 41797/57600 [7:20:34<2:37:36, 1.67it/s] 73%|███████▎ | 41798/57600 [7:20:35<2:33:45, 1.71it/s] 73%|███████▎ | 41799/57600 [7:20:36<2:42:29, 1.62it/s] 73%|███████▎ | 41800/57600 [7:20:36<2:42:05, 1.62it/s] {'loss': 1.1667, 'learning_rate': 3.477351916376306e-07, 'epoch': 461.37} + 73%|███████▎ | 41800/57600 [7:20:36<2:42:05, 1.62it/s] 73%|███████▎ | 41801/57600 [7:20:37<2:37:58, 1.67it/s] 73%|███████▎ | 41802/57600 [7:20:37<2:40:18, 1.64it/s] 73%|███████▎ | 41803/57600 [7:20:38<2:41:00, 1.64it/s] 73%|███████▎ | 41804/57600 [7:20:39<2:39:51, 1.65it/s] 73%|███████▎ | 41805/57600 [7:20:39<2:39:09, 1.65it/s] 73%|███████▎ | 41806/57600 [7:20:40<2:37:04, 1.68it/s] 73%|███████▎ | 41807/57600 [7:20:40<2:39:33, 1.65it/s] 73%|███████▎ | 41808/57600 [7:20:41<2:50:49, 1.54it/s] 73%|███████▎ | 41809/57600 [7:20:42<2:47:26, 1.57it/s] 73%|███████▎ | 41810/57600 [7:20:42<2:45:25, 1.59it/s] 73%|███████▎ | 41811/57600 [7:20:43<2:47:35, 1.57it/s] 73%|███████▎ | 41812/57600 [7:20:44<2:49:08, 1.56it/s] 73%|███████▎ | 41813/57600 [7:20:44<2:44:33, 1.60it/s] 73%|███████▎ | 41814/57600 [7:20:45<2:42:44, 1.62it/s] 73%|███████▎ | 41815/57600 [7:20:46<2:51:09, 1.54it/s] 73%|███████▎ | 41816/57600 [7:20:46<2:51:32, 1.53it/s] 73%|███████▎ | 41817/57600 [7:20:47<2:51:44, 1.53it/s] 73%|███████▎ | 41818/57600 [7:20:48<2:52:58, 1.52it/s] 73%|███████▎ | 41819/57600 [7:20:48<2:45:53, 1.59it/s] 73%|███████▎ | 41820/57600 [7:20:49<2:42:43, 1.62it/s] {'loss': 1.1311, 'learning_rate': 3.474216027874564e-07, 'epoch': 461.59} + 73%|███████▎ | 41820/57600 [7:20:49<2:42:43, 1.62it/s] 73%|███████▎ | 41821/57600 [7:20:49<2:44:49, 1.60it/s] 73%|███████▎ | 41822/57600 [7:20:50<2:48:02, 1.56it/s] 73%|███████▎ | 41823/57600 [7:20:51<2:48:47, 1.56it/s] 73%|███████▎ | 41824/57600 [7:20:51<2:43:09, 1.61it/s] 73%|███████▎ | 41825/57600 [7:20:52<2:48:25, 1.56it/s] 73%|███████▎ | 41826/57600 [7:20:53<2:49:08, 1.55it/s] 73%|███████▎ | 41827/57600 [7:20:53<2:44:12, 1.60it/s] 73%|███████▎ | 41828/57600 [7:20:54<2:41:30, 1.63it/s] 73%|███████▎ | 41829/57600 [7:20:54<2:39:45, 1.65it/s] 73%|███████▎ | 41830/57600 [7:20:55<2:36:50, 1.68it/s] 73%|███████▎ | 41831/57600 [7:20:56<2:39:01, 1.65it/s] 73%|███████▎ | 41832/57600 [7:20:56<2:40:26, 1.64it/s] 73%|███████▎ | 41833/57600 [7:20:57<2:44:59, 1.59it/s] 73%|███████▎ | 41834/57600 [7:20:57<2:45:46, 1.59it/s] 73%|███████▎ | 41835/57600 [7:20:58<2:45:38, 1.59it/s] 73%|███████▎ | 41836/57600 [7:20:59<2:50:11, 1.54it/s] 73%|███████▎ | 41837/57600 [7:20:59<2:49:18, 1.55it/s] 73%|███████▎ | 41838/57600 [7:21:00<2:53:56, 1.51it/s] 73%|███████▎ | 41839/57600 [7:21:01<2:49:33, 1.55it/s] 73%|███████▎ | 41840/57600 [7:21:01<2:47:01, 1.57it/s] {'loss': 1.1249, 'learning_rate': 3.471080139372823e-07, 'epoch': 461.81} + 73%|███████▎ | 41840/57600 [7:21:01<2:47:01, 1.57it/s] 73%|███████▎ | 41841/57600 [7:21:02<2:45:55, 1.58it/s] 73%|███████▎ | 41842/57600 [7:21:03<2:44:29, 1.60it/s] 73%|███████▎ | 41843/57600 [7:21:03<2:47:00, 1.57it/s] 73%|███████▎ | 41844/57600 [7:21:04<2:49:08, 1.55it/s] 73%|███████▎ | 41845/57600 [7:21:04<2:46:51, 1.57it/s] 73%|███████▎ | 41846/57600 [7:21:05<2:42:19, 1.62it/s] 73%|███████▎ | 41847/57600 [7:21:06<2:40:34, 1.64it/s] 73%|███████▎ | 41848/57600 [7:21:06<2:41:38, 1.62it/s] 73%|███████▎ | 41849/57600 [7:21:07<2:42:35, 1.61it/s] 73%|███████▎ | 41850/57600 [7:21:08<2:42:24, 1.62it/s] 73%|███████▎ | 41851/57600 [7:21:08<2:40:29, 1.64it/s] 73%|███████▎ | 41852/57600 [7:21:09<2:42:17, 1.62it/s] 73%|███████▎ | 41853/57600 [7:21:09<2:38:54, 1.65it/s] 73%|███████▎ | 41854/57600 [7:21:10<2:38:19, 1.66it/s] 73%|███████▎ | 41855/57600 [7:21:11<2:43:25, 1.61it/s] 73%|███████▎ | 41856/57600 [7:21:11<2:51:04, 1.53it/s] 73%|███████▎ | 41857/57600 [7:21:12<2:50:59, 1.53it/s] 73%|███████▎ | 41858/57600 [7:21:13<3:09:30, 1.38it/s] 73%|███████▎ | 41859/57600 [7:21:14<3:08:29, 1.39it/s] 73%|███████▎ | 41860/57600 [7:21:14<3:01:46, 1.44it/s] {'loss': 1.103, 'learning_rate': 3.46794425087108e-07, 'epoch': 462.03} + 73%|███████▎ | 41860/57600 [7:21:14<3:01:46, 1.44it/s] 73%|███████▎ | 41861/57600 [7:21:15<2:57:16, 1.48it/s] 73%|███████▎ | 41862/57600 [7:21:15<2:52:45, 1.52it/s] 73%|███████▎ | 41863/57600 [7:21:16<2:48:02, 1.56it/s] 73%|███████▎ | 41864/57600 [7:21:17<2:49:10, 1.55it/s] 73%|███████▎ | 41865/57600 [7:21:17<2:48:53, 1.55it/s] 73%|███████▎ | 41866/57600 [7:21:18<2:48:10, 1.56it/s] 73%|███████▎ | 41867/57600 [7:21:19<2:48:19, 1.56it/s] 73%|███████▎ | 41868/57600 [7:21:19<2:45:34, 1.58it/s] 73%|███████▎ | 41869/57600 [7:21:20<2:47:44, 1.56it/s] 73%|███████▎ | 41870/57600 [7:21:21<2:45:15, 1.59it/s] 73%|███████▎ | 41871/57600 [7:21:21<2:41:00, 1.63it/s] 73%|███████▎ | 41872/57600 [7:21:22<2:47:35, 1.56it/s] 73%|███████▎ | 41873/57600 [7:21:22<2:46:02, 1.58it/s] 73%|███████▎ | 41874/57600 [7:21:23<2:40:44, 1.63it/s] 73%|███████▎ | 41875/57600 [7:21:24<2:45:25, 1.58it/s] 73%|███████▎ | 41876/57600 [7:21:24<2:44:58, 1.59it/s] 73%|███████▎ | 41877/57600 [7:21:25<2:38:36, 1.65it/s] 73%|███████▎ | 41878/57600 [7:21:25<2:33:57, 1.70it/s] 73%|███████▎ | 41879/57600 [7:21:26<2:36:05, 1.68it/s] 73%|███████▎ | 41880/57600 [7:21:27<2:37:21, 1.66it/s] {'loss': 1.1352, 'learning_rate': 3.4648083623693383e-07, 'epoch': 462.25} + 73%|███████▎ | 41880/57600 [7:21:27<2:37:21, 1.66it/s] 73%|███████▎ | 41881/57600 [7:21:27<2:35:46, 1.68it/s] 73%|███████▎ | 41882/57600 [7:21:28<2:32:28, 1.72it/s] 73%|███████▎ | 41883/57600 [7:21:28<2:36:27, 1.67it/s] 73%|███████▎ | 41884/57600 [7:21:29<2:41:38, 1.62it/s] 73%|███████▎ | 41885/57600 [7:21:30<2:44:49, 1.59it/s] 73%|███████▎ | 41886/57600 [7:21:30<2:41:55, 1.62it/s] 73%|███████▎ | 41887/57600 [7:21:31<2:47:31, 1.56it/s] 73%|███████▎ | 41888/57600 [7:21:32<2:44:23, 1.59it/s] 73%|███████▎ | 41889/57600 [7:21:32<2:40:06, 1.64it/s] 73%|███████▎ | 41890/57600 [7:21:33<2:38:22, 1.65it/s] 73%|███████▎ | 41891/57600 [7:21:33<2:39:56, 1.64it/s] 73%|███████▎ | 41892/57600 [7:21:34<2:44:16, 1.59it/s] 73%|███████▎ | 41893/57600 [7:21:35<2:46:36, 1.57it/s] 73%|███████▎ | 41894/57600 [7:21:35<2:46:22, 1.57it/s] 73%|███████▎ | 41895/57600 [7:21:36<2:46:34, 1.57it/s] 73%|███████▎ | 41896/57600 [7:21:37<2:41:14, 1.62it/s] 73%|███████▎ | 41897/57600 [7:21:37<2:40:16, 1.63it/s] 73%|███████▎ | 41898/57600 [7:21:38<2:37:44, 1.66it/s] 73%|███████▎ | 41899/57600 [7:21:38<2:42:01, 1.62it/s] 73%|███████▎ | 41900/57600 [7:21:39<2:40:20, 1.63it/s] {'loss': 1.1752, 'learning_rate': 3.4616724738675953e-07, 'epoch': 462.47} + 73%|███████▎ | 41900/57600 [7:21:39<2:40:20, 1.63it/s] 73%|███████▎ | 41901/57600 [7:21:40<2:38:33, 1.65it/s] 73%|███████▎ | 41902/57600 [7:21:40<2:39:15, 1.64it/s] 73%|███████▎ | 41903/57600 [7:21:41<2:44:20, 1.59it/s] 73%|███████▎ | 41904/57600 [7:21:41<2:45:34, 1.58it/s] 73%|███████▎ | 41905/57600 [7:21:42<2:44:01, 1.59it/s] 73%|███████▎ | 41906/57600 [7:21:43<2:47:52, 1.56it/s] 73%|███████▎ | 41907/57600 [7:21:43<2:49:52, 1.54it/s] 73%|███████▎ | 41908/57600 [7:21:44<2:50:15, 1.54it/s] 73%|███████▎ | 41909/57600 [7:21:45<2:46:34, 1.57it/s] 73%|███████▎ | 41910/57600 [7:21:45<2:44:23, 1.59it/s] 73%|███████▎ | 41911/57600 [7:21:46<2:44:09, 1.59it/s] 73%|███████▎ | 41912/57600 [7:21:47<2:42:43, 1.61it/s] 73%|███████▎ | 41913/57600 [7:21:47<2:42:59, 1.60it/s] 73%|███████▎ | 41914/57600 [7:21:48<2:39:02, 1.64it/s] 73%|███████▎ | 41915/57600 [7:21:48<2:35:57, 1.68it/s] 73%|███████▎ | 41916/57600 [7:21:49<2:40:41, 1.63it/s] 73%|███████▎ | 41917/57600 [7:21:50<2:45:09, 1.58it/s] 73%|███████▎ | 41918/57600 [7:21:50<2:43:12, 1.60it/s] 73%|███████▎ | 41919/57600 [7:21:51<2:42:54, 1.60it/s] 73%|███████▎ | 41920/57600 [7:21:51<2:42:47, 1.61it/s] {'loss': 1.1267, 'learning_rate': 3.458536585365854e-07, 'epoch': 462.69} + 73%|███████▎ | 41920/57600 [7:21:51<2:42:47, 1.61it/s] 73%|███████▎ | 41921/57600 [7:21:52<2:40:16, 1.63it/s] 73%|███████▎ | 41922/57600 [7:21:53<2:39:46, 1.64it/s] 73%|███████▎ | 41923/57600 [7:21:53<2:43:01, 1.60it/s] 73%|███████▎ | 41924/57600 [7:21:54<2:42:32, 1.61it/s] 73%|███████▎ | 41925/57600 [7:21:55<2:46:29, 1.57it/s] 73%|███████▎ | 41926/57600 [7:21:55<2:41:16, 1.62it/s] 73%|███████▎ | 41927/57600 [7:21:56<2:42:46, 1.60it/s] 73%|███████▎ | 41928/57600 [7:21:56<2:40:08, 1.63it/s] 73%|███████▎ | 41929/57600 [7:21:57<2:38:05, 1.65it/s] 73%|███████▎ | 41930/57600 [7:21:58<2:39:33, 1.64it/s] 73%|███████▎ | 41931/57600 [7:21:58<2:40:53, 1.62it/s] 73%|███████▎ | 41932/57600 [7:21:59<2:38:22, 1.65it/s] 73%|███████▎ | 41933/57600 [7:21:59<2:38:04, 1.65it/s] 73%|███████▎ | 41934/57600 [7:22:00<2:40:24, 1.63it/s] 73%|███████▎ | 41935/57600 [7:22:01<2:45:36, 1.58it/s] 73%|███████▎ | 41936/57600 [7:22:01<2:51:33, 1.52it/s] 73%|███████▎ | 41937/57600 [7:22:02<2:52:18, 1.52it/s] 73%|███████▎ | 41938/57600 [7:22:03<2:58:43, 1.46it/s] 73%|███████▎ | 41939/57600 [7:22:03<2:52:45, 1.51it/s] 73%|███████▎ | 41940/57600 [7:22:04<2:55:12, 1.49it/s] {'loss': 1.0625, 'learning_rate': 3.455400696864111e-07, 'epoch': 462.91} + 73%|███████▎ | 41940/57600 [7:22:04<2:55:12, 1.49it/s] 73%|███████▎ | 41941/57600 [7:22:05<2:48:40, 1.55it/s] 73%|███████▎ | 41942/57600 [7:22:05<2:47:39, 1.56it/s] 73%|███████▎ | 41943/57600 [7:22:06<2:50:00, 1.53it/s] 73%|███████▎ | 41944/57600 [7:22:07<2:46:44, 1.56it/s] 73%|███████▎ | 41945/57600 [7:22:07<2:46:16, 1.57it/s] 73%|███████▎ | 41946/57600 [7:22:08<2:46:19, 1.57it/s] 73%|███████▎ | 41947/57600 [7:22:09<2:42:39, 1.60it/s] 73%|███████▎ | 41948/57600 [7:22:09<2:49:11, 1.54it/s] 73%|███████▎ | 41949/57600 [7:22:10<2:51:52, 1.52it/s] 73%|███████▎ | 41950/57600 [7:22:11<2:50:23, 1.53it/s] 73%|███████▎ | 41951/57600 [7:22:11<2:49:32, 1.54it/s] 73%|███████▎ | 41952/57600 [7:22:12<2:52:50, 1.51it/s] 73%|███████▎ | 41953/57600 [7:22:13<2:56:05, 1.48it/s] 73%|███████▎ | 41954/57600 [7:22:13<2:48:30, 1.55it/s] 73%|███████▎ | 41955/57600 [7:22:14<2:45:08, 1.58it/s] 73%|███████▎ | 41956/57600 [7:22:14<2:46:07, 1.57it/s] 73%|███████▎ | 41957/57600 [7:22:15<2:45:02, 1.58it/s] 73%|███████▎ | 41958/57600 [7:22:16<2:40:23, 1.63it/s] 73%|███████▎ | 41959/57600 [7:22:16<2:44:09, 1.59it/s] 73%|███████▎ | 41960/57600 [7:22:17<2:41:43, 1.61it/s] {'loss': 1.1038, 'learning_rate': 3.4522648083623695e-07, 'epoch': 463.13} + 73%|███████▎ | 41960/57600 [7:22:17<2:41:43, 1.61it/s] 73%|███████▎ | 41961/57600 [7:22:17<2:40:10, 1.63it/s] 73%|███████▎ | 41962/57600 [7:22:18<2:43:55, 1.59it/s] 73%|███████▎ | 41963/57600 [7:22:19<2:40:18, 1.63it/s] 73%|███████▎ | 41964/57600 [7:22:19<2:46:04, 1.57it/s] 73%|███████▎ | 41965/57600 [7:22:20<2:40:45, 1.62it/s] 73%|███████▎ | 41966/57600 [7:22:21<2:38:17, 1.65it/s] 73%|███████▎ | 41967/57600 [7:22:21<2:44:01, 1.59it/s] 73%|███████▎ | 41968/57600 [7:22:22<2:44:12, 1.59it/s] 73%|███████▎ | 41969/57600 [7:22:22<2:39:24, 1.63it/s] 73%|███████▎ | 41970/57600 [7:22:23<2:42:59, 1.60it/s] 73%|███████▎ | 41971/57600 [7:22:24<2:42:08, 1.61it/s] 73%|███████▎ | 41972/57600 [7:22:24<2:38:48, 1.64it/s] 73%|███████▎ | 41973/57600 [7:22:25<2:45:37, 1.57it/s] 73%|███████▎ | 41974/57600 [7:22:26<2:47:27, 1.56it/s] 73%|███████▎ | 41975/57600 [7:22:26<2:51:55, 1.51it/s] 73%|███████▎ | 41976/57600 [7:22:27<2:51:51, 1.52it/s] 73%|███████▎ | 41977/57600 [7:22:28<2:45:57, 1.57it/s] 73%|███████▎ | 41978/57600 [7:22:28<2:43:36, 1.59it/s] 73%|███████▎ | 41979/57600 [7:22:29<2:39:25, 1.63it/s] 73%|███████▎ | 41980/57600 [7:22:30<2:47:43, 1.55it/s] {'loss': 1.1499, 'learning_rate': 3.4491289198606275e-07, 'epoch': 463.36} + 73%|███████▎ | 41980/57600 [7:22:30<2:47:43, 1.55it/s] 73%|███████▎ | 41981/57600 [7:22:30<2:50:45, 1.52it/s] 73%|███████▎ | 41982/57600 [7:22:31<2:49:57, 1.53it/s] 73%|███████▎ | 41983/57600 [7:22:31<2:45:40, 1.57it/s] 73%|███████▎ | 41984/57600 [7:22:32<2:46:13, 1.57it/s] 73%|███████▎ | 41985/57600 [7:22:33<2:43:54, 1.59it/s] 73%|███████▎ | 41986/57600 [7:22:33<2:43:19, 1.59it/s] 73%|███████▎ | 41987/57600 [7:22:34<2:40:24, 1.62it/s] 73%|███████▎ | 41988/57600 [7:22:34<2:36:59, 1.66it/s] 73%|███████▎ | 41989/57600 [7:22:35<2:37:57, 1.65it/s] 73%|███████▎ | 41990/57600 [7:22:36<2:37:21, 1.65it/s] 73%|███████▎ | 41991/57600 [7:22:36<2:35:47, 1.67it/s] 73%|███████▎ | 41992/57600 [7:22:37<2:34:32, 1.68it/s] 73%|███████▎ | 41993/57600 [7:22:38<2:43:00, 1.60it/s] 73%|███████▎ | 41994/57600 [7:22:38<2:45:35, 1.57it/s] 73%|███████▎ | 41995/57600 [7:22:39<2:47:24, 1.55it/s] 73%|███████▎ | 41996/57600 [7:22:40<2:44:16, 1.58it/s] 73%|███████▎ | 41997/57600 [7:22:40<2:41:42, 1.61it/s] 73%|███████▎ | 41998/57600 [7:22:41<2:43:05, 1.59it/s] 73%|███████▎ | 41999/57600 [7:22:41<2:46:09, 1.56it/s] 73%|███████▎ | 42000/57600 [7:22:42<2:40:36, 1.62it/s] {'loss': 1.1417, 'learning_rate': 3.4459930313588845e-07, 'epoch': 463.58} + 73%|███████▎ | 42000/57600 [7:22:42<2:40:36, 1.62it/s] 73%|███████▎ | 42001/57600 [7:22:43<2:40:00, 1.62it/s] 73%|███████▎ | 42002/57600 [7:22:43<2:35:14, 1.67it/s] 73%|███████▎ | 42003/57600 [7:22:44<2:38:12, 1.64it/s] 73%|███████▎ | 42004/57600 [7:22:44<2:42:06, 1.60it/s] 73%|███████▎ | 42005/57600 [7:22:45<2:39:54, 1.63it/s] 73%|███████▎ | 42006/57600 [7:22:46<2:47:49, 1.55it/s] 73%|███████▎ | 42007/57600 [7:22:46<2:49:14, 1.54it/s] 73%|███████▎ | 42008/57600 [7:22:47<2:46:11, 1.56it/s] 73%|███████▎ | 42009/57600 [7:22:48<2:44:47, 1.58it/s] 73%|███████▎ | 42010/57600 [7:22:48<2:46:50, 1.56it/s] 73%|███████▎ | 42011/57600 [7:22:49<2:41:45, 1.61it/s] 73%|███████▎ | 42012/57600 [7:22:49<2:40:40, 1.62it/s] 73%|███████▎ | 42013/57600 [7:22:50<2:39:43, 1.63it/s] 73%|███████▎ | 42014/57600 [7:22:51<2:38:30, 1.64it/s] 73%|███████▎ | 42015/57600 [7:22:51<2:45:49, 1.57it/s] 73%|███████▎ | 42016/57600 [7:22:52<2:42:49, 1.60it/s] 73%|███████▎ | 42017/57600 [7:22:53<2:46:35, 1.56it/s] 73%|███████▎ | 42018/57600 [7:22:53<2:44:23, 1.58it/s] 73%|███████▎ | 42019/57600 [7:22:54<2:41:49, 1.60it/s] 73%|███████▎ | 42020/57600 [7:22:54<2:40:23, 1.62it/s] {'loss': 1.1291, 'learning_rate': 3.442857142857143e-07, 'epoch': 463.8} + 73%|███████▎ | 42020/57600 [7:22:54<2:40:23, 1.62it/s] 73%|███████▎ | 42021/57600 [7:22:55<2:43:44, 1.59it/s] 73%|███████▎ | 42022/57600 [7:22:56<2:49:01, 1.54it/s] 73%|███████▎ | 42023/57600 [7:22:56<2:46:39, 1.56it/s] 73%|███████▎ | 42024/57600 [7:22:57<2:44:53, 1.57it/s] 73%|███████▎ | 42025/57600 [7:22:58<2:40:48, 1.61it/s] 73%|███████▎ | 42026/57600 [7:22:58<2:38:49, 1.63it/s] 73%|███████▎ | 42027/57600 [7:22:59<2:35:40, 1.67it/s] 73%|███████▎ | 42028/57600 [7:22:59<2:35:47, 1.67it/s] 73%|███████▎ | 42029/57600 [7:23:00<2:33:25, 1.69it/s] 73%|███████▎ | 42030/57600 [7:23:01<2:35:03, 1.67it/s] 73%|███████▎ | 42031/57600 [7:23:01<2:36:09, 1.66it/s] 73%|███████▎ | 42032/57600 [7:23:02<2:35:17, 1.67it/s] 73%|███████▎ | 42033/57600 [7:23:02<2:35:45, 1.67it/s] 73%|███████▎ | 42034/57600 [7:23:03<2:35:05, 1.67it/s] 73%|███████▎ | 42035/57600 [7:23:04<2:35:05, 1.67it/s] 73%|███████▎ | 42036/57600 [7:23:04<2:44:03, 1.58it/s] 73%|███████▎ | 42037/57600 [7:23:05<2:52:19, 1.51it/s] 73%|███████▎ | 42038/57600 [7:23:06<2:49:27, 1.53it/s] 73%|███████▎ | 42039/57600 [7:23:06<2:56:15, 1.47it/s] 73%|███████▎ | 42040/57600 [7:23:07<2:50:36, 1.52it/s] {'loss': 1.142, 'learning_rate': 3.4397212543554e-07, 'epoch': 464.02} + 73%|███████▎ | 42040/57600 [7:23:07<2:50:36, 1.52it/s] 73%|███████▎ | 42041/57600 [7:23:08<2:50:24, 1.52it/s] 73%|███████▎ | 42042/57600 [7:23:08<2:47:48, 1.55it/s] 73%|███████▎ | 42043/57600 [7:23:09<2:52:45, 1.50it/s] 73%|███████▎ | 42044/57600 [7:23:10<2:47:02, 1.55it/s] 73%|███████▎ | 42045/57600 [7:23:10<2:46:56, 1.55it/s] 73%|███████▎ | 42046/57600 [7:23:11<2:46:12, 1.56it/s] 73%|███████▎ | 42047/57600 [7:23:12<2:42:33, 1.59it/s] 73%|███████▎ | 42048/57600 [7:23:12<2:43:05, 1.59it/s] 73%|███████▎ | 42049/57600 [7:23:13<2:41:15, 1.61it/s] 73%|███████▎ | 42050/57600 [7:23:13<2:41:42, 1.60it/s] 73%|███████▎ | 42051/57600 [7:23:14<2:46:16, 1.56it/s] 73%|███████▎ | 42052/57600 [7:23:15<2:40:19, 1.62it/s] 73%|███████▎ | 42053/57600 [7:23:15<2:40:42, 1.61it/s] 73%|███████▎ | 42054/57600 [7:23:16<2:42:00, 1.60it/s] 73%|███████▎ | 42055/57600 [7:23:16<2:40:08, 1.62it/s] 73%|███████▎ | 42056/57600 [7:23:17<2:39:37, 1.62it/s] 73%|███████▎ | 42057/57600 [7:23:18<2:45:10, 1.57it/s] 73%|███████▎ | 42058/57600 [7:23:18<2:47:06, 1.55it/s] 73%|███████▎ | 42059/57600 [7:23:19<2:43:01, 1.59it/s] 73%|███████▎ | 42060/57600 [7:23:20<2:39:29, 1.62it/s] {'loss': 1.0993, 'learning_rate': 3.4365853658536587e-07, 'epoch': 464.24} + 73%|███████▎ | 42060/57600 [7:23:20<2:39:29, 1.62it/s] 73%|███████▎ | 42061/57600 [7:23:20<2:39:42, 1.62it/s] 73%|███████▎ | 42062/57600 [7:23:21<2:44:16, 1.58it/s] 73%|███████▎ | 42063/57600 [7:23:22<2:42:56, 1.59it/s] 73%|███████▎ | 42064/57600 [7:23:22<2:39:52, 1.62it/s] 73%|███████▎ | 42065/57600 [7:23:23<2:37:58, 1.64it/s] 73%|███████▎ | 42066/57600 [7:23:23<2:38:21, 1.63it/s] 73%|███████▎ | 42067/57600 [7:23:24<2:35:56, 1.66it/s] 73%|███████▎ | 42068/57600 [7:23:25<2:36:26, 1.65it/s] 73%|███████▎ | 42069/57600 [7:23:25<2:36:04, 1.66it/s] 73%|███████▎ | 42070/57600 [7:23:26<2:35:56, 1.66it/s] 73%|███████▎ | 42071/57600 [7:23:26<2:40:06, 1.62it/s] 73%|███████▎ | 42072/57600 [7:23:27<2:42:48, 1.59it/s] 73%|███████▎ | 42073/57600 [7:23:28<2:40:58, 1.61it/s] 73%|███████▎ | 42074/57600 [7:23:28<2:39:36, 1.62it/s] 73%|███████▎ | 42075/57600 [7:23:29<2:38:18, 1.63it/s] 73%|███████▎ | 42076/57600 [7:23:29<2:38:21, 1.63it/s] 73%|███████▎ | 42077/57600 [7:23:30<2:39:15, 1.62it/s] 73%|███████▎ | 42078/57600 [7:23:31<2:39:25, 1.62it/s] 73%|███████▎ | 42079/57600 [7:23:31<2:44:19, 1.57it/s] 73%|███████▎ | 42080/57600 [7:23:32<2:44:57, 1.57it/s] {'loss': 1.1713, 'learning_rate': 3.4334494773519157e-07, 'epoch': 464.46} + 73%|███████▎ | 42080/57600 [7:23:32<2:44:57, 1.57it/s] 73%|███████▎ | 42081/57600 [7:23:33<2:39:23, 1.62it/s] 73%|███████▎ | 42082/57600 [7:23:33<2:38:38, 1.63it/s] 73%|███████▎ | 42083/57600 [7:23:34<2:42:57, 1.59it/s] 73%|███████▎ | 42084/57600 [7:23:35<2:48:12, 1.54it/s] 73%|███████▎ | 42085/57600 [7:23:35<2:41:51, 1.60it/s] 73%|███████▎ | 42086/57600 [7:23:36<2:42:40, 1.59it/s] 73%|███████▎ | 42087/57600 [7:23:36<2:43:05, 1.59it/s] 73%|███████▎ | 42088/57600 [7:23:37<2:40:02, 1.62it/s] 73%|███████▎ | 42089/57600 [7:23:38<2:44:36, 1.57it/s] 73%|███████▎ | 42090/57600 [7:23:38<2:44:09, 1.57it/s] 73%|███████▎ | 42091/57600 [7:23:39<2:42:45, 1.59it/s] 73%|███████▎ | 42092/57600 [7:23:40<2:41:46, 1.60it/s] 73%|███████▎ | 42093/57600 [7:23:40<2:41:11, 1.60it/s] 73%|███████▎ | 42094/57600 [7:23:41<2:45:13, 1.56it/s] 73%|███████▎ | 42095/57600 [7:23:42<2:48:10, 1.54it/s] 73%|███████▎ | 42096/57600 [7:23:42<2:48:11, 1.54it/s] 73%|███████▎ | 42097/57600 [7:23:43<2:43:08, 1.58it/s] 73%|███████▎ | 42098/57600 [7:23:43<2:42:23, 1.59it/s] 73%|███████▎ | 42099/57600 [7:23:44<2:40:46, 1.61it/s] 73%|███████▎ | 42100/57600 [7:23:45<2:42:36, 1.59it/s] {'loss': 1.1404, 'learning_rate': 3.430313588850174e-07, 'epoch': 464.68} + 73%|███████▎ | 42100/57600 [7:23:45<2:42:36, 1.59it/s] 73%|███████▎ | 42101/57600 [7:23:45<2:49:26, 1.52it/s] 73%|███████▎ | 42102/57600 [7:23:46<2:47:04, 1.55it/s] 73%|███████▎ | 42103/57600 [7:23:47<2:42:02, 1.59it/s] 73%|███████▎ | 42104/57600 [7:23:47<2:38:03, 1.63it/s] 73%|███████▎ | 42105/57600 [7:23:48<2:39:44, 1.62it/s] 73%|███████▎ | 42106/57600 [7:23:48<2:41:11, 1.60it/s] 73%|███████▎ | 42107/57600 [7:23:49<2:42:31, 1.59it/s] 73%|███████▎ | 42108/57600 [7:23:50<2:42:03, 1.59it/s] 73%|███████▎ | 42109/57600 [7:23:50<2:48:05, 1.54it/s] 73%|███████▎ | 42110/57600 [7:23:51<2:41:16, 1.60it/s] 73%|███████▎ | 42111/57600 [7:23:52<2:39:18, 1.62it/s] 73%|███████▎ | 42112/57600 [7:23:52<2:44:25, 1.57it/s] 73%|███████▎ | 42113/57600 [7:23:53<2:44:21, 1.57it/s] 73%|███████▎ | 42114/57600 [7:23:53<2:41:08, 1.60it/s] 73%|███████▎ | 42115/57600 [7:23:54<2:42:45, 1.59it/s] 73%|███████▎ | 42116/57600 [7:23:55<2:41:39, 1.60it/s] 73%|███████▎ | 42117/57600 [7:23:55<2:41:07, 1.60it/s] 73%|███████▎ | 42118/57600 [7:23:56<2:38:56, 1.62it/s] 73%|███████▎ | 42119/57600 [7:23:57<2:38:07, 1.63it/s] 73%|███████▎ | 42120/57600 [7:23:57<2:43:13, 1.58it/s] {'loss': 1.1187, 'learning_rate': 3.427177700348432e-07, 'epoch': 464.9} + 73%|███████▎ | 42120/57600 [7:23:57<2:43:13, 1.58it/s] 73%|███████▎ | 42121/57600 [7:23:58<2:45:59, 1.55it/s] 73%|███████▎ | 42122/57600 [7:23:58<2:42:09, 1.59it/s] 73%|███████▎ | 42123/57600 [7:23:59<2:43:00, 1.58it/s] 73%|███████▎ | 42124/57600 [7:24:00<2:45:45, 1.56it/s] 73%|███████▎ | 42125/57600 [7:24:00<2:43:09, 1.58it/s] 73%|███████▎ | 42126/57600 [7:24:01<2:42:15, 1.59it/s] 73%|███████▎ | 42127/57600 [7:24:02<2:37:29, 1.64it/s] 73%|███████▎ | 42128/57600 [7:24:02<2:37:08, 1.64it/s] 73%|███████▎ | 42129/57600 [7:24:03<2:38:29, 1.63it/s] 73%|███████▎ | 42130/57600 [7:24:04<2:48:04, 1.53it/s] 73%|███████▎ | 42131/57600 [7:24:04<2:50:19, 1.51it/s] 73%|███████▎ | 42132/57600 [7:24:05<2:44:02, 1.57it/s] 73%|███████▎ | 42133/57600 [7:24:05<2:39:29, 1.62it/s] 73%|███████▎ | 42134/57600 [7:24:06<2:42:32, 1.59it/s] 73%|███████▎ | 42135/57600 [7:24:07<2:38:39, 1.62it/s] 73%|███████▎ | 42136/57600 [7:24:07<2:41:18, 1.60it/s] 73%|███████▎ | 42137/57600 [7:24:08<2:41:32, 1.60it/s] 73%|███████▎ | 42138/57600 [7:24:09<2:40:26, 1.61it/s] 73%|███████▎ | 42139/57600 [7:24:09<2:41:11, 1.60it/s] 73%|███████▎ | 42140/57600 [7:24:10<2:39:39, 1.61it/s] {'loss': 1.1665, 'learning_rate': 3.42404181184669e-07, 'epoch': 465.12} + 73%|███████▎ | 42140/57600 [7:24:10<2:39:39, 1.61it/s] 73%|███████▎ | 42141/57600 [7:24:10<2:40:25, 1.61it/s] 73%|███████▎ | 42142/57600 [7:24:11<2:41:57, 1.59it/s] 73%|███████▎ | 42143/57600 [7:24:12<2:43:33, 1.58it/s] 73%|███████▎ | 42144/57600 [7:24:12<2:41:14, 1.60it/s] 73%|███████▎ | 42145/57600 [7:24:13<2:34:45, 1.66it/s] 73%|███████▎ | 42146/57600 [7:24:13<2:34:59, 1.66it/s] 73%|███████▎ | 42147/57600 [7:24:14<2:34:45, 1.66it/s] 73%|███████▎ | 42148/57600 [7:24:15<2:37:17, 1.64it/s] 73%|███████▎ | 42149/57600 [7:24:15<2:37:55, 1.63it/s] 73%|███████▎ | 42150/57600 [7:24:16<2:35:07, 1.66it/s] 73%|███████▎ | 42151/57600 [7:24:17<2:42:03, 1.59it/s] 73%|███████▎ | 42152/57600 [7:24:17<2:46:15, 1.55it/s] 73%|███████▎ | 42153/57600 [7:24:18<2:43:34, 1.57it/s] 73%|███████▎ | 42154/57600 [7:24:18<2:40:22, 1.61it/s] 73%|███████▎ | 42155/57600 [7:24:19<2:40:11, 1.61it/s] 73%|███████▎ | 42156/57600 [7:24:20<2:39:10, 1.62it/s] 73%|███████▎ | 42157/57600 [7:24:20<2:40:19, 1.61it/s] 73%|███████▎ | 42158/57600 [7:24:21<2:42:48, 1.58it/s] 73%|███████▎ | 42159/57600 [7:24:22<2:40:50, 1.60it/s] 73%|███████▎ | 42160/57600 [7:24:22<2:45:17, 1.56it/s] {'loss': 1.1548, 'learning_rate': 3.420905923344948e-07, 'epoch': 465.34} + 73%|███████▎ | 42160/57600 [7:24:22<2:45:17, 1.56it/s] 73%|███████▎ | 42161/57600 [7:24:23<2:43:04, 1.58it/s] 73%|███████▎ | 42162/57600 [7:24:23<2:37:27, 1.63it/s] 73%|███████▎ | 42163/57600 [7:24:24<2:36:57, 1.64it/s] 73%|███████▎ | 42164/57600 [7:24:25<2:39:51, 1.61it/s] 73%|███████▎ | 42165/57600 [7:24:25<2:43:59, 1.57it/s] 73%|███████▎ | 42166/57600 [7:24:26<2:44:47, 1.56it/s] 73%|███████▎ | 42167/57600 [7:24:27<2:42:29, 1.58it/s] 73%|███████▎ | 42168/57600 [7:24:27<2:44:09, 1.57it/s] 73%|███████▎ | 42169/57600 [7:24:28<2:38:56, 1.62it/s] 73%|███████▎ | 42170/57600 [7:24:28<2:41:25, 1.59it/s] 73%|███████▎ | 42171/57600 [7:24:29<2:36:57, 1.64it/s] 73%|███████▎ | 42172/57600 [7:24:30<2:40:28, 1.60it/s] 73%|███████▎ | 42173/57600 [7:24:30<2:44:00, 1.57it/s] 73%|███████▎ | 42174/57600 [7:24:31<2:45:54, 1.55it/s] 73%|███████▎ | 42175/57600 [7:24:32<2:44:57, 1.56it/s] 73%|███████▎ | 42176/57600 [7:24:32<2:43:52, 1.57it/s] 73%|███████▎ | 42177/57600 [7:24:33<2:43:05, 1.58it/s] 73%|███████▎ | 42178/57600 [7:24:34<2:44:14, 1.57it/s] 73%|███████▎ | 42179/57600 [7:24:34<2:45:27, 1.55it/s] 73%|███████▎ | 42180/57600 [7:24:35<2:41:42, 1.59it/s] {'loss': 1.1313, 'learning_rate': 3.4177700348432054e-07, 'epoch': 465.56} + 73%|███████▎ | 42180/57600 [7:24:35<2:41:42, 1.59it/s] 73%|███████▎ | 42181/57600 [7:24:35<2:38:48, 1.62it/s] 73%|███████▎ | 42182/57600 [7:24:36<2:39:07, 1.61it/s] 73%|███████▎ | 42183/57600 [7:24:37<2:38:49, 1.62it/s] 73%|███████▎ | 42184/57600 [7:24:37<2:39:10, 1.61it/s] 73%|███████▎ | 42185/57600 [7:24:38<2:43:09, 1.57it/s] 73%|███████▎ | 42186/57600 [7:24:39<2:45:24, 1.55it/s] 73%|███████▎ | 42187/57600 [7:24:39<2:42:50, 1.58it/s] 73%|███████▎ | 42188/57600 [7:24:40<2:39:29, 1.61it/s] 73%|███████▎ | 42189/57600 [7:24:40<2:38:46, 1.62it/s] 73%|███████▎ | 42190/57600 [7:24:41<2:41:53, 1.59it/s] 73%|███████▎ | 42191/57600 [7:24:42<2:39:38, 1.61it/s] 73%|███████▎ | 42192/57600 [7:24:42<2:37:44, 1.63it/s] 73%|███████▎ | 42193/57600 [7:24:43<2:44:04, 1.56it/s] 73%|███████▎ | 42194/57600 [7:24:44<2:40:59, 1.59it/s] 73%|███████▎ | 42195/57600 [7:24:44<2:41:28, 1.59it/s] 73%|███████▎ | 42196/57600 [7:24:45<2:39:18, 1.61it/s] 73%|███████▎ | 42197/57600 [7:24:46<2:45:26, 1.55it/s] 73%|███████▎ | 42198/57600 [7:24:46<2:48:46, 1.52it/s] 73%|███████▎ | 42199/57600 [7:24:47<2:44:49, 1.56it/s] 73%|███████▎ | 42200/57600 [7:24:47<2:44:51, 1.56it/s] {'loss': 1.1037, 'learning_rate': 3.4146341463414634e-07, 'epoch': 465.78} + 73%|███████▎ | 42200/57600 [7:24:47<2:44:51, 1.56it/s] 73%|███████▎ | 42201/57600 [7:24:48<2:39:40, 1.61it/s] 73%|███████▎ | 42202/57600 [7:24:49<2:41:57, 1.58it/s] 73%|███████▎ | 42203/57600 [7:24:49<2:41:16, 1.59it/s] 73%|███████▎ | 42204/57600 [7:24:50<2:43:12, 1.57it/s] 73%|███████▎ | 42205/57600 [7:24:51<2:37:52, 1.63it/s] 73%|███████▎ | 42206/57600 [7:24:51<2:38:03, 1.62it/s] 73%|███████▎ | 42207/57600 [7:24:52<2:37:12, 1.63it/s] 73%|███████▎ | 42208/57600 [7:24:52<2:36:52, 1.64it/s] 73%|███████▎ | 42209/57600 [7:24:53<2:35:49, 1.65it/s] 73%|███████▎ | 42210/57600 [7:24:54<2:42:01, 1.58it/s] 73%|███████▎ | 42211/57600 [7:24:54<2:41:09, 1.59it/s] 73%|███████▎ | 42212/57600 [7:24:55<2:43:40, 1.57it/s] 73%|███████▎ | 42213/57600 [7:24:56<2:47:12, 1.53it/s] 73%|███████▎ | 42214/57600 [7:24:56<2:50:28, 1.50it/s] 73%|███████▎ | 42215/57600 [7:24:57<2:47:15, 1.53it/s] 73%|███████▎ | 42216/57600 [7:24:58<2:45:31, 1.55it/s] 73%|███████▎ | 42217/57600 [7:24:58<2:41:19, 1.59it/s] 73%|███████▎ | 42218/57600 [7:24:59<2:42:11, 1.58it/s] 73%|███████▎ | 42219/57600 [7:24:59<2:43:10, 1.57it/s] 73%|███████▎ | 42220/57600 [7:25:00<2:44:35, 1.56it/s] {'loss': 1.1544, 'learning_rate': 3.411498257839721e-07, 'epoch': 466.0} + 73%|███████▎ | 42220/57600 [7:25:00<2:44:35, 1.56it/s] 73%|███████▎ | 42221/57600 [7:25:01<2:41:51, 1.58it/s] 73%|███████▎ | 42222/57600 [7:25:01<2:37:54, 1.62it/s] 73%|███████▎ | 42223/57600 [7:25:02<2:42:40, 1.58it/s] 73%|███████▎ | 42224/57600 [7:25:03<2:41:21, 1.59it/s] 73%|███████▎ | 42225/57600 [7:25:03<2:43:36, 1.57it/s] 73%|███████▎ | 42226/57600 [7:25:04<2:39:40, 1.60it/s] 73%|███████▎ | 42227/57600 [7:25:05<2:44:34, 1.56it/s] 73%|███████▎ | 42228/57600 [7:25:05<2:44:00, 1.56it/s] 73%|███████▎ | 42229/57600 [7:25:06<2:42:32, 1.58it/s] 73%|███████▎ | 42230/57600 [7:25:06<2:42:52, 1.57it/s] 73%|███████▎ | 42231/57600 [7:25:07<2:41:59, 1.58it/s] 73%|███████▎ | 42232/57600 [7:25:08<2:42:13, 1.58it/s] 73%|███████▎ | 42233/57600 [7:25:08<2:41:32, 1.59it/s] 73%|███████▎ | 42234/57600 [7:25:09<2:40:47, 1.59it/s] 73%|███████▎ | 42235/57600 [7:25:09<2:37:38, 1.62it/s] 73%|███████▎ | 42236/57600 [7:25:10<2:40:59, 1.59it/s] 73%|███████▎ | 42237/57600 [7:25:11<2:41:04, 1.59it/s] 73%|███████▎ | 42238/57600 [7:25:11<2:40:48, 1.59it/s] 73%|███████▎ | 42239/57600 [7:25:12<2:41:21, 1.59it/s] 73%|███████▎ | 42240/57600 [7:25:13<2:37:52, 1.62it/s] {'loss': 1.1605, 'learning_rate': 3.4083623693379785e-07, 'epoch': 466.23} + 73%|███████▎ | 42240/57600 [7:25:13<2:37:52, 1.62it/s] 73%|███████▎ | 42241/57600 [7:25:13<2:36:50, 1.63it/s] 73%|███████▎ | 42242/57600 [7:25:14<2:34:09, 1.66it/s] 73%|███████▎ | 42243/57600 [7:25:14<2:32:35, 1.68it/s] 73%|███████▎ | 42244/57600 [7:25:15<2:45:45, 1.54it/s] 73%|███████▎ | 42245/57600 [7:25:16<2:56:00, 1.45it/s] 73%|███████▎ | 42246/57600 [7:25:17<2:49:42, 1.51it/s] 73%|███████▎ | 42247/57600 [7:25:17<2:44:13, 1.56it/s] 73%|███████▎ | 42248/57600 [7:25:18<2:47:38, 1.53it/s] 73%|███████▎ | 42249/57600 [7:25:18<2:42:05, 1.58it/s] 73%|███████▎ | 42250/57600 [7:25:19<2:45:01, 1.55it/s] 73%|███████▎ | 42251/57600 [7:25:20<2:37:57, 1.62it/s] 73%|███████▎ | 42252/57600 [7:25:20<2:41:21, 1.59it/s] 73%|███████▎ | 42253/57600 [7:25:21<2:36:04, 1.64it/s] 73%|███████▎ | 42254/57600 [7:25:21<2:35:06, 1.65it/s] 73%|███████▎ | 42255/57600 [7:25:22<2:34:08, 1.66it/s] 73%|███████▎ | 42256/57600 [7:25:23<2:36:14, 1.64it/s] 73%|███████▎ | 42257/57600 [7:25:23<2:38:47, 1.61it/s] 73%|███████▎ | 42258/57600 [7:25:24<2:37:46, 1.62it/s] 73%|███████▎ | 42259/57600 [7:25:25<2:41:10, 1.59it/s] 73%|███████▎ | 42260/57600 [7:25:25<2:45:10, 1.55it/s] {'loss': 1.1331, 'learning_rate': 3.405226480836237e-07, 'epoch': 466.45} + 73%|███████▎ | 42260/57600 [7:25:25<2:45:10, 1.55it/s] 73%|███████▎ | 42261/57600 [7:25:26<2:44:29, 1.55it/s] 73%|███████▎ | 42262/57600 [7:25:26<2:39:20, 1.60it/s] 73%|███████▎ | 42263/57600 [7:25:27<2:37:52, 1.62it/s] 73%|███████▎ | 42264/57600 [7:25:28<2:38:25, 1.61it/s] 73%|███████▎ | 42265/57600 [7:25:28<2:42:40, 1.57it/s] 73%|███████▎ | 42266/57600 [7:25:29<2:45:00, 1.55it/s] 73%|███████▎ | 42267/57600 [7:25:30<2:47:00, 1.53it/s] 73%|███████▎ | 42268/57600 [7:25:30<2:47:29, 1.53it/s] 73%|███████▎ | 42269/57600 [7:25:31<2:43:53, 1.56it/s] 73%|███████▎ | 42270/57600 [7:25:32<2:45:46, 1.54it/s] 73%|███████▎ | 42271/57600 [7:25:32<2:43:32, 1.56it/s] 73%|███████▎ | 42272/57600 [7:25:33<2:41:11, 1.58it/s] 73%|███████▎ | 42273/57600 [7:25:33<2:38:05, 1.62it/s] 73%|███████▎ | 42274/57600 [7:25:34<2:37:37, 1.62it/s] 73%|███████▎ | 42275/57600 [7:25:35<2:39:11, 1.60it/s] 73%|███████▎ | 42276/57600 [7:25:35<2:35:21, 1.64it/s] 73%|███████▎ | 42277/57600 [7:25:36<2:38:08, 1.61it/s] 73%|███████▎ | 42278/57600 [7:25:37<2:40:45, 1.59it/s] 73%|███████▎ | 42279/57600 [7:25:37<2:38:05, 1.62it/s] 73%|███████▎ | 42280/57600 [7:25:38<2:40:55, 1.59it/s] {'loss': 1.1138, 'learning_rate': 3.4020905923344946e-07, 'epoch': 466.67} + 73%|███████▎ | 42280/57600 [7:25:38<2:40:55, 1.59it/s] 73%|███████▎ | 42281/57600 [7:25:39<2:43:22, 1.56it/s] 73%|███████▎ | 42282/57600 [7:25:39<2:48:33, 1.51it/s] 73%|███████▎ | 42283/57600 [7:25:40<2:45:37, 1.54it/s] 73%|███████▎ | 42284/57600 [7:25:40<2:41:34, 1.58it/s] 73%|███████▎ | 42285/57600 [7:25:41<2:40:23, 1.59it/s] 73%|███████▎ | 42286/57600 [7:25:42<2:39:18, 1.60it/s] 73%|███████▎ | 42287/57600 [7:25:42<2:40:58, 1.59it/s] 73%|███████▎ | 42288/57600 [7:25:43<2:37:53, 1.62it/s] 73%|███████▎ | 42289/57600 [7:25:44<2:36:20, 1.63it/s] 73%|███████▎ | 42290/57600 [7:25:44<2:38:31, 1.61it/s] 73%|███████▎ | 42291/57600 [7:25:45<2:37:20, 1.62it/s] 73%|███████▎ | 42292/57600 [7:25:45<2:45:07, 1.55it/s] 73%|███████▎ | 42293/57600 [7:25:46<2:43:20, 1.56it/s] 73%|███████▎ | 42294/57600 [7:25:47<2:45:54, 1.54it/s] 73%|███████▎ | 42295/57600 [7:25:47<2:43:27, 1.56it/s] 73%|███████▎ | 42296/57600 [7:25:48<2:40:10, 1.59it/s] 73%|███████▎ | 42297/57600 [7:25:49<2:41:58, 1.57it/s] 73%|███████▎ | 42298/57600 [7:25:49<2:37:52, 1.62it/s] 73%|████��██▎ | 42299/57600 [7:25:50<2:35:38, 1.64it/s] 73%|███████▎ | 42300/57600 [7:25:50<2:38:41, 1.61it/s] {'loss': 1.1152, 'learning_rate': 3.3989547038327526e-07, 'epoch': 466.89} + 73%|███████▎ | 42300/57600 [7:25:50<2:38:41, 1.61it/s] 73%|███████▎ | 42301/57600 [7:25:51<2:41:27, 1.58it/s] 73%|███████▎ | 42302/57600 [7:25:52<2:39:31, 1.60it/s] 73%|███████▎ | 42303/57600 [7:25:52<2:37:08, 1.62it/s] 73%|███████▎ | 42304/57600 [7:25:53<2:33:24, 1.66it/s] 73%|███████▎ | 42305/57600 [7:25:53<2:30:32, 1.69it/s] 73%|███████▎ | 42306/57600 [7:25:54<2:38:45, 1.61it/s] 73%|███████▎ | 42307/57600 [7:25:55<2:42:49, 1.57it/s] 73%|███████▎ | 42308/57600 [7:25:55<2:43:47, 1.56it/s] 73%|███████▎ | 42309/57600 [7:25:56<2:43:28, 1.56it/s] 73%|███████▎ | 42310/57600 [7:25:57<2:42:17, 1.57it/s] 73%|███████▎ | 42311/57600 [7:25:57<2:46:54, 1.53it/s] 73%|███████▎ | 42312/57600 [7:25:58<2:45:27, 1.54it/s] 73%|███████▎ | 42313/57600 [7:25:59<2:43:34, 1.56it/s] 73%|███████▎ | 42314/57600 [7:25:59<2:40:30, 1.59it/s] 73%|███████▎ | 42315/57600 [7:26:00<2:38:30, 1.61it/s] 73%|███████▎ | 42316/57600 [7:26:01<2:44:58, 1.54it/s] 73%|███████▎ | 42317/57600 [7:26:01<2:42:01, 1.57it/s] 73%|███████▎ | 42318/57600 [7:26:02<2:42:12, 1.57it/s] 73%|███████▎ | 42319/57600 [7:26:02<2:41:02, 1.58it/s] 73%|███████▎ | 42320/57600 [7:26:03<2:38:25, 1.61it/s] {'loss': 1.1406, 'learning_rate': 3.39581881533101e-07, 'epoch': 467.11} + 73%|███████▎ | 42320/57600 [7:26:03<2:38:25, 1.61it/s] 73%|███████▎ | 42321/57600 [7:26:04<2:33:35, 1.66it/s] 73%|███████▎ | 42322/57600 [7:26:04<2:31:19, 1.68it/s] 73%|███████▎ | 42323/57600 [7:26:05<2:38:39, 1.60it/s] 73%|███████▎ | 42324/57600 [7:26:05<2:33:55, 1.65it/s] 73%|███████▎ | 42325/57600 [7:26:06<2:39:07, 1.60it/s] 73%|███████▎ | 42326/57600 [7:26:07<2:36:12, 1.63it/s] 73%|███████▎ | 42327/57600 [7:26:07<2:36:44, 1.62it/s] 73%|███████▎ | 42328/57600 [7:26:08<2:38:30, 1.61it/s] 73%|███████▎ | 42329/57600 [7:26:09<2:36:19, 1.63it/s] 73%|███████▎ | 42330/57600 [7:26:09<2:37:12, 1.62it/s] 73%|███████▎ | 42331/57600 [7:26:10<2:34:40, 1.65it/s] 73%|███████▎ | 42332/57600 [7:26:10<2:35:59, 1.63it/s] 73%|███████▎ | 42333/57600 [7:26:11<2:33:17, 1.66it/s] 73%|███████▎ | 42334/57600 [7:26:12<2:38:27, 1.61it/s] 73%|███████▎ | 42335/57600 [7:26:12<2:47:21, 1.52it/s] 74%|███████▎ | 42336/57600 [7:26:13<2:44:34, 1.55it/s] 74%|███████▎ | 42337/57600 [7:26:14<2:40:55, 1.58it/s] 74%|███████▎ | 42338/57600 [7:26:14<2:41:51, 1.57it/s] 74%|███████▎ | 42339/57600 [7:26:15<2:45:20, 1.54it/s] 74%|███████▎ | 42340/57600 [7:26:16<2:44:50, 1.54it/s] {'loss': 1.1333, 'learning_rate': 3.392682926829268e-07, 'epoch': 467.33} + 74%|███████▎ | 42340/57600 [7:26:16<2:44:50, 1.54it/s] 74%|███████▎ | 42341/57600 [7:26:16<2:46:46, 1.52it/s] 74%|███████▎ | 42342/57600 [7:26:17<2:43:41, 1.55it/s] 74%|███████▎ | 42343/57600 [7:26:18<2:45:22, 1.54it/s] 74%|███████▎ | 42344/57600 [7:26:18<2:45:47, 1.53it/s] 74%|███████▎ | 42345/57600 [7:26:19<2:39:08, 1.60it/s] 74%|███████▎ | 42346/57600 [7:26:19<2:40:08, 1.59it/s] 74%|███████▎ | 42347/57600 [7:26:20<2:39:46, 1.59it/s] 74%|███████▎ | 42348/57600 [7:26:21<2:46:01, 1.53it/s] 74%|███████▎ | 42349/57600 [7:26:21<2:43:56, 1.55it/s] 74%|███████▎ | 42350/57600 [7:26:22<2:41:15, 1.58it/s] 74%|███████▎ | 42351/57600 [7:26:23<2:38:34, 1.60it/s] 74%|███████▎ | 42352/57600 [7:26:23<2:35:54, 1.63it/s] 74%|███████▎ | 42353/57600 [7:26:24<2:36:55, 1.62it/s] 74%|███████▎ | 42354/57600 [7:26:24<2:34:22, 1.65it/s] 74%|███████▎ | 42355/57600 [7:26:25<2:31:37, 1.68it/s] 74%|███████▎ | 42356/57600 [7:26:26<2:35:03, 1.64it/s] 74%|███████▎ | 42357/57600 [7:26:26<2:38:22, 1.60it/s] 74%|███████▎ | 42358/57600 [7:26:27<2:33:24, 1.66it/s] 74%|███████▎ | 42359/57600 [7:26:27<2:36:21, 1.62it/s] 74%|███████▎ | 42360/57600 [7:26:28<2:45:41, 1.53it/s] {'loss': 1.1324, 'learning_rate': 3.389547038327525e-07, 'epoch': 467.55} + 74%|███████▎ | 42360/57600 [7:26:28<2:45:41, 1.53it/s] 74%|███████▎ | 42361/57600 [7:26:29<2:42:57, 1.56it/s] 74%|███████▎ | 42362/57600 [7:26:29<2:39:42, 1.59it/s] 74%|███████▎ | 42363/57600 [7:26:30<2:37:18, 1.61it/s] 74%|███████▎ | 42364/57600 [7:26:31<2:40:00, 1.59it/s] 74%|███████▎ | 42365/57600 [7:26:31<2:39:00, 1.60it/s] 74%|███████▎ | 42366/57600 [7:26:32<2:45:18, 1.54it/s] 74%|███████▎ | 42367/57600 [7:26:33<2:41:03, 1.58it/s] 74%|███████▎ | 42368/57600 [7:26:33<2:44:33, 1.54it/s] 74%|███████▎ | 42369/57600 [7:26:34<2:38:46, 1.60it/s] 74%|███████▎ | 42370/57600 [7:26:34<2:39:15, 1.59it/s] 74%|███████▎ | 42371/57600 [7:26:35<2:37:03, 1.62it/s] 74%|███████▎ | 42372/57600 [7:26:36<2:35:05, 1.64it/s] 74%|███████▎ | 42373/57600 [7:26:36<2:32:32, 1.66it/s] 74%|███████▎ | 42374/57600 [7:26:37<2:32:36, 1.66it/s] 74%|███████▎ | 42375/57600 [7:26:38<2:38:02, 1.61it/s] 74%|███████▎ | 42376/57600 [7:26:38<2:38:29, 1.60it/s] 74%|███████▎ | 42377/57600 [7:26:39<2:38:35, 1.60it/s] 74%|███████▎ | 42378/57600 [7:26:39<2:38:50, 1.60it/s] 74%|███████▎ | 42379/57600 [7:26:40<2:42:32, 1.56it/s] 74%|███████▎ | 42380/57600 [7:26:41<2:41:10, 1.57it/s] {'loss': 1.1196, 'learning_rate': 3.386411149825784e-07, 'epoch': 467.77} + 74%|███████▎ | 42380/57600 [7:26:41<2:41:10, 1.57it/s] 74%|███████▎ | 42381/57600 [7:26:41<2:49:40, 1.49it/s] 74%|███████▎ | 42382/57600 [7:26:42<2:41:06, 1.57it/s] 74%|███████▎ | 42383/57600 [7:26:43<2:38:55, 1.60it/s] 74%|███████▎ | 42384/57600 [7:26:43<2:39:13, 1.59it/s] 74%|███████▎ | 42385/57600 [7:26:44<2:39:14, 1.59it/s] 74%|███████▎ | 42386/57600 [7:26:44<2:33:18, 1.65it/s] 74%|███████▎ | 42387/57600 [7:26:45<2:35:27, 1.63it/s] 74%|███████▎ | 42388/57600 [7:26:46<2:34:31, 1.64it/s] 74%|███████▎ | 42389/57600 [7:26:46<2:33:18, 1.65it/s] 74%|███████▎ | 42390/57600 [7:26:47<2:36:26, 1.62it/s] 74%|███████▎ | 42391/57600 [7:26:48<2:43:02, 1.55it/s] 74%|███████▎ | 42392/57600 [7:26:48<2:46:58, 1.52it/s] 74%|███████▎ | 42393/57600 [7:26:49<2:47:43, 1.51it/s] 74%|███████▎ | 42394/57600 [7:26:50<2:49:27, 1.50it/s] 74%|███████▎ | 42395/57600 [7:26:50<2:45:07, 1.53it/s] 74%|███████▎ | 42396/57600 [7:26:51<2:42:18, 1.56it/s] 74%|███████▎ | 42397/57600 [7:26:51<2:40:42, 1.58it/s] 74%|███████▎ | 42398/57600 [7:26:52<2:40:47, 1.58it/s] 74%|███████▎ | 42399/57600 [7:26:53<2:37:45, 1.61it/s] 74%|███████▎ | 42400/57600 [7:26:53<2:37:55, 1.60it/s] {'loss': 1.1067, 'learning_rate': 3.383275261324042e-07, 'epoch': 467.99} + 74%|███████▎ | 42400/57600 [7:26:53<2:37:55, 1.60it/s] 74%|███████▎ | 42401/57600 [7:26:54<2:44:50, 1.54it/s] 74%|███████▎ | 42402/57600 [7:26:55<2:42:33, 1.56it/s] 74%|███████▎ | 42403/57600 [7:26:55<2:40:55, 1.57it/s] 74%|███████▎ | 42404/57600 [7:26:56<2:43:52, 1.55it/s] 74%|███████▎ | 42405/57600 [7:26:57<2:43:15, 1.55it/s] 74%|███████▎ | 42406/57600 [7:26:57<2:42:52, 1.55it/s] 74%|███████▎ | 42407/57600 [7:26:58<2:44:20, 1.54it/s] 74%|███████▎ | 42408/57600 [7:26:59<2:41:00, 1.57it/s] 74%|███████▎ | 42409/57600 [7:26:59<2:42:02, 1.56it/s] 74%|███████▎ | 42410/57600 [7:27:00<2:41:38, 1.57it/s] 74%|███████▎ | 42411/57600 [7:27:00<2:41:57, 1.56it/s] 74%|███████▎ | 42412/57600 [7:27:01<2:37:46, 1.60it/s] 74%|███████▎ | 42413/57600 [7:27:02<2:41:33, 1.57it/s] 74%|███████▎ | 42414/57600 [7:27:02<2:41:05, 1.57it/s] 74%|███████▎ | 42415/57600 [7:27:03<2:37:19, 1.61it/s] 74%|███████▎ | 42416/57600 [7:27:04<2:36:44, 1.61it/s] 74%|███████▎ | 42417/57600 [7:27:04<2:33:07, 1.65it/s] 74%|███████▎ | 42418/57600 [7:27:05<2:38:11, 1.60it/s] 74%|███████▎ | 42419/57600 [7:27:05<2:37:06, 1.61it/s] 74%|███████▎ | 42420/57600 [7:27:06<2:36:34, 1.62it/s] {'loss': 1.1315, 'learning_rate': 3.3801393728222993e-07, 'epoch': 468.21} + 74%|███████▎ | 42420/57600 [7:27:06<2:36:34, 1.62it/s] 74%|███████▎ | 42421/57600 [7:27:07<2:32:47, 1.66it/s] 74%|███████▎ | 42422/57600 [7:27:07<2:32:09, 1.66it/s] 74%|███████▎ | 42423/57600 [7:27:08<2:34:05, 1.64it/s] 74%|███████▎ | 42424/57600 [7:27:08<2:36:15, 1.62it/s] 74%|███████▎ | 42425/57600 [7:27:09<2:32:04, 1.66it/s] 74%|███████▎ | 42426/57600 [7:27:10<2:28:49, 1.70it/s] 74%|███████▎ | 42427/57600 [7:27:10<2:28:35, 1.70it/s] 74%|███████▎ | 42428/57600 [7:27:11<2:27:55, 1.71it/s] 74%|███████▎ | 42429/57600 [7:27:11<2:28:16, 1.71it/s] 74%|███████▎ | 42430/57600 [7:27:12<2:32:03, 1.66it/s] 74%|███████▎ | 42431/57600 [7:27:13<2:32:47, 1.65it/s] 74%|███████▎ | 42432/57600 [7:27:13<2:34:24, 1.64it/s] 74%|███████▎ | 42433/57600 [7:27:14<2:34:27, 1.64it/s] 74%|███████▎ | 42434/57600 [7:27:14<2:38:22, 1.60it/s] 74%|███████▎ | 42435/57600 [7:27:15<2:34:44, 1.63it/s] 74%|███████▎ | 42436/57600 [7:27:16<2:35:53, 1.62it/s] 74%|███████▎ | 42437/57600 [7:27:16<2:40:55, 1.57it/s] 74%|███████▎ | 42438/57600 [7:27:17<2:38:33, 1.59it/s] 74%|███████▎ | 42439/57600 [7:27:18<2:37:58, 1.60it/s] 74%|███████▎ | 42440/57600 [7:27:18<2:35:59, 1.62it/s] {'loss': 1.1629, 'learning_rate': 3.377003484320558e-07, 'epoch': 468.43} + 74%|███████▎ | 42440/57600 [7:27:18<2:35:59, 1.62it/s] 74%|███████▎ | 42441/57600 [7:27:19<2:36:42, 1.61it/s] 74%|███████▎ | 42442/57600 [7:27:19<2:33:08, 1.65it/s] 74%|███████▎ | 42443/57600 [7:27:20<2:39:42, 1.58it/s] 74%|███████▎ | 42444/57600 [7:27:21<2:37:37, 1.60it/s] 74%|███████▎ | 42445/57600 [7:27:21<2:36:11, 1.62it/s] 74%|███████▎ | 42446/57600 [7:27:22<2:38:49, 1.59it/s] 74%|███████▎ | 42447/57600 [7:27:23<2:35:01, 1.63it/s] 74%|███████▎ | 42448/57600 [7:27:23<2:36:15, 1.62it/s] 74%|███████▎ | 42449/57600 [7:27:24<2:38:17, 1.60it/s] 74%|███████▎ | 42450/57600 [7:27:24<2:39:08, 1.59it/s] 74%|███████▎ | 42451/57600 [7:27:25<2:38:04, 1.60it/s] 74%|███████▎ | 42452/57600 [7:27:26<2:37:42, 1.60it/s] 74%|███████▎ | 42453/57600 [7:27:26<2:39:54, 1.58it/s] 74%|███████▎ | 42454/57600 [7:27:27<2:38:18, 1.59it/s] 74%|███████▎ | 42455/57600 [7:27:28<2:40:54, 1.57it/s] 74%|███████▎ | 42456/57600 [7:27:28<2:46:02, 1.52it/s] 74%|███████▎ | 42457/57600 [7:27:29<2:49:46, 1.49it/s] 74%|███████▎ | 42458/57600 [7:27:30<2:52:31, 1.46it/s] 74%|███████▎ | 42459/57600 [7:27:30<2:48:54, 1.49it/s] 74%|███████▎ | 42460/57600 [7:27:31<2:44:44, 1.53it/s] {'loss': 1.1046, 'learning_rate': 3.373867595818815e-07, 'epoch': 468.65} + 74%|███████▎ | 42460/57600 [7:27:31<2:44:44, 1.53it/s] 74%|███████▎ | 42461/57600 [7:27:32<2:42:45, 1.55it/s] 74%|███████▎ | 42462/57600 [7:27:32<2:46:08, 1.52it/s] 74%|███████▎ | 42463/57600 [7:27:33<2:44:05, 1.54it/s] 74%|███████▎ | 42464/57600 [7:27:34<2:43:30, 1.54it/s] 74%|███████▎ | 42465/57600 [7:27:34<2:41:03, 1.57it/s] 74%|███████▎ | 42466/57600 [7:27:35<2:43:03, 1.55it/s] 74%|███████▎ | 42467/57600 [7:27:36<2:48:52, 1.49it/s] 74%|███████▎ | 42468/57600 [7:27:36<2:45:08, 1.53it/s] 74%|███████▎ | 42469/57600 [7:27:37<2:38:59, 1.59it/s] 74%|███████▎ | 42470/57600 [7:27:37<2:40:52, 1.57it/s] 74%|███████▎ | 42471/57600 [7:27:38<2:41:11, 1.56it/s] 74%|███████▎ | 42472/57600 [7:27:39<2:37:40, 1.60it/s] 74%|███████▎ | 42473/57600 [7:27:39<2:37:20, 1.60it/s] 74%|███████▎ | 42474/57600 [7:27:40<2:38:14, 1.59it/s] 74%|███████▎ | 42475/57600 [7:27:41<2:37:35, 1.60it/s] 74%|███████▎ | 42476/57600 [7:27:41<2:48:26, 1.50it/s] 74%|███████▎ | 42477/57600 [7:27:42<2:43:36, 1.54it/s] 74%|███████▎ | 42478/57600 [7:27:43<2:40:36, 1.57it/s] 74%|███████▎ | 42479/57600 [7:27:43<2:40:15, 1.57it/s] 74%|███████▍ | 42480/57600 [7:27:44<2:36:45, 1.61it/s] {'loss': 1.1401, 'learning_rate': 3.370731707317073e-07, 'epoch': 468.87} + 74%|███████▍ | 42480/57600 [7:27:44<2:36:45, 1.61it/s] 74%|███████▍ | 42481/57600 [7:27:44<2:35:00, 1.63it/s] 74%|███████▍ | 42482/57600 [7:27:45<2:36:15, 1.61it/s] 74%|███████▍ | 42483/57600 [7:27:46<2:36:29, 1.61it/s] 74%|███████▍ | 42484/57600 [7:27:46<2:46:04, 1.52it/s] 74%|███████▍ | 42485/57600 [7:27:47<2:41:32, 1.56it/s] 74%|███████▍ | 42486/57600 [7:27:48<2:47:32, 1.50it/s] 74%|███████▍ | 42487/57600 [7:27:48<2:43:51, 1.54it/s] 74%|███████▍ | 42488/57600 [7:27:49<2:44:40, 1.53it/s] 74%|███████▍ | 42489/57600 [7:27:50<2:43:26, 1.54it/s] 74%|███████▍ | 42490/57600 [7:27:50<2:41:24, 1.56it/s] 74%|███████▍ | 42491/57600 [7:27:51<2:34:36, 1.63it/s] 74%|███████▍ | 42492/57600 [7:27:51<2:42:30, 1.55it/s] 74%|███████▍ | 42493/57600 [7:27:52<2:39:58, 1.57it/s] 74%|███████▍ | 42494/57600 [7:27:53<2:42:06, 1.55it/s] 74%|███████▍ | 42495/57600 [7:27:53<2:37:12, 1.60it/s] 74%|███████▍ | 42496/57600 [7:27:54<2:32:01, 1.66it/s] 74%|███████▍ | 42497/57600 [7:27:55<2:35:20, 1.62it/s] 74%|███████▍ | 42498/57600 [7:27:55<2:33:43, 1.64it/s] 74%|███████▍ | 42499/57600 [7:27:56<2:39:00, 1.58it/s] 74%|███████▍ | 42500/57600 [7:27:56<2:40:35, 1.57it/s] {'loss': 1.1215, 'learning_rate': 3.3675958188153304e-07, 'epoch': 469.09} + 74%|███████▍ | 42500/57600 [7:27:56<2:40:35, 1.57it/s] 74%|███████▍ | 42501/57600 [7:27:57<2:36:20, 1.61it/s] 74%|███████▍ | 42502/57600 [7:27:58<2:34:06, 1.63it/s] 74%|███████▍ | 42503/57600 [7:27:58<2:35:16, 1.62it/s] 74%|███████▍ | 42504/57600 [7:27:59<2:38:25, 1.59it/s] 74%|███████▍ | 42505/57600 [7:28:00<2:43:55, 1.53it/s] 74%|███████▍ | 42506/57600 [7:28:00<2:39:39, 1.58it/s] 74%|███████▍ | 42507/57600 [7:28:01<2:45:45, 1.52it/s] 74%|███████▍ | 42508/57600 [7:28:02<2:53:02, 1.45it/s] 74%|███████▍ | 42509/57600 [7:28:02<2:45:46, 1.52it/s] 74%|███████▍ | 42510/57600 [7:28:03<2:45:06, 1.52it/s] 74%|███████▍ | 42511/57600 [7:28:04<2:45:24, 1.52it/s] 74%|███████▍ | 42512/57600 [7:28:04<2:41:37, 1.56it/s] 74%|███████▍ | 42513/57600 [7:28:05<2:39:45, 1.57it/s] 74%|███████▍ | 42514/57600 [7:28:05<2:36:27, 1.61it/s] 74%|███████▍ | 42515/57600 [7:28:06<2:39:34, 1.58it/s] 74%|███████▍ | 42516/57600 [7:28:07<2:36:42, 1.60it/s] 74%|███████▍ | 42517/57600 [7:28:07<2:33:51, 1.63it/s] 74%|███████▍ | 42518/57600 [7:28:08<2:37:32, 1.60it/s] 74%|███████▍ | 42519/57600 [7:28:08<2:31:56, 1.65it/s] 74%|███████▍ | 42520/57600 [7:28:09<2:30:44, 1.67it/s] {'loss': 1.1688, 'learning_rate': 3.364459930313589e-07, 'epoch': 469.32} + 74%|███████▍ | 42520/57600 [7:28:09<2:30:44, 1.67it/s] 74%|███████▍ | 42521/57600 [7:28:10<2:37:10, 1.60it/s] 74%|███████▍ | 42522/57600 [7:28:10<2:44:19, 1.53it/s] 74%|███████▍ | 42523/57600 [7:28:11<2:44:33, 1.53it/s] 74%|███████▍ | 42524/57600 [7:28:12<2:36:30, 1.61it/s] 74%|███████▍ | 42525/57600 [7:28:12<2:38:56, 1.58it/s] 74%|███████▍ | 42526/57600 [7:28:13<2:41:19, 1.56it/s] 74%|███████▍ | 42527/57600 [7:28:14<2:41:12, 1.56it/s] 74%|███████▍ | 42528/57600 [7:28:14<2:36:41, 1.60it/s] 74%|███████▍ | 42529/57600 [7:28:15<2:37:22, 1.60it/s] 74%|███████▍ | 42530/57600 [7:28:15<2:36:00, 1.61it/s] 74%|███████▍ | 42531/57600 [7:28:16<2:36:40, 1.60it/s] 74%|███████▍ | 42532/57600 [7:28:17<2:35:15, 1.62it/s] 74%|███████▍ | 42533/57600 [7:28:17<2:35:50, 1.61it/s] 74%|███████▍ | 42534/57600 [7:28:18<2:37:35, 1.59it/s] 74%|███████▍ | 42535/57600 [7:28:19<2:42:11, 1.55it/s] 74%|███████▍ | 42536/57600 [7:28:19<2:39:35, 1.57it/s] 74%|███████▍ | 42537/57600 [7:28:20<2:38:10, 1.59it/s] 74%|███████▍ | 42538/57600 [7:28:20<2:32:36, 1.64it/s] 74%|███████▍ | 42539/57600 [7:28:21<2:29:57, 1.67it/s] 74%|███████▍ | 42540/57600 [7:28:22<2:36:44, 1.60it/s] {'loss': 1.1017, 'learning_rate': 3.3613240418118465e-07, 'epoch': 469.54} + 74%|███████▍ | 42540/57600 [7:28:22<2:36:44, 1.60it/s] 74%|███████▍ | 42541/57600 [7:28:22<2:39:00, 1.58it/s] 74%|███████▍ | 42542/57600 [7:28:23<2:38:39, 1.58it/s] 74%|███████▍ | 42543/57600 [7:28:24<2:36:45, 1.60it/s] 74%|███████▍ | 42544/57600 [7:28:24<2:33:38, 1.63it/s] 74%|███████▍ | 42545/57600 [7:28:25<2:34:30, 1.62it/s] 74%|███████▍ | 42546/57600 [7:28:25<2:32:37, 1.64it/s] 74%|███████▍ | 42547/57600 [7:28:26<2:33:54, 1.63it/s] 74%|███████▍ | 42548/57600 [7:28:27<2:34:03, 1.63it/s] 74%|███████▍ | 42549/57600 [7:28:27<2:33:52, 1.63it/s] 74%|███████▍ | 42550/57600 [7:28:28<2:28:46, 1.69it/s] 74%|███████▍ | 42551/57600 [7:28:28<2:36:14, 1.61it/s] 74%|███████▍ | 42552/57600 [7:28:29<2:35:58, 1.61it/s] 74%|███████▍ | 42553/57600 [7:28:30<2:33:27, 1.63it/s] 74%|███████▍ | 42554/57600 [7:28:30<2:33:47, 1.63it/s] 74%|███████▍ | 42555/57600 [7:28:31<2:35:20, 1.61it/s] 74%|███████▍ | 42556/57600 [7:28:32<2:36:06, 1.61it/s] 74%|███████▍ | 42557/57600 [7:28:32<2:38:33, 1.58it/s] 74%|███████▍ | 42558/57600 [7:28:33<2:41:44, 1.55it/s] 74%|███████▍ | 42559/57600 [7:28:34<2:50:52, 1.47it/s] 74%|███████▍ | 42560/57600 [7:28:34<2:54:39, 1.44it/s] {'loss': 1.1356, 'learning_rate': 3.358188153310104e-07, 'epoch': 469.76} + 74%|███████▍ | 42560/57600 [7:28:34<2:54:39, 1.44it/s] 74%|███████▍ | 42561/57600 [7:28:35<2:50:11, 1.47it/s] 74%|███████▍ | 42562/57600 [7:28:36<2:48:20, 1.49it/s] 74%|███████▍ | 42563/57600 [7:28:36<2:46:38, 1.50it/s] 74%|███████▍ | 42564/57600 [7:28:37<2:45:26, 1.51it/s] 74%|███████▍ | 42565/57600 [7:28:38<2:45:59, 1.51it/s] 74%|███████▍ | 42566/57600 [7:28:38<2:44:02, 1.53it/s] 74%|███████▍ | 42567/57600 [7:28:39<2:46:52, 1.50it/s] 74%|███████▍ | 42568/57600 [7:28:40<2:43:54, 1.53it/s] 74%|███████▍ | 42569/57600 [7:28:40<2:42:00, 1.55it/s] 74%|███████▍ | 42570/57600 [7:28:41<2:37:15, 1.59it/s] 74%|███████▍ | 42571/57600 [7:28:41<2:32:18, 1.64it/s] 74%|███████▍ | 42572/57600 [7:28:42<2:32:41, 1.64it/s] 74%|███████▍ | 42573/57600 [7:28:43<2:31:25, 1.65it/s] 74%|███████▍ | 42574/57600 [7:28:43<2:31:43, 1.65it/s] 74%|███████▍ | 42575/57600 [7:28:44<2:36:02, 1.60it/s] 74%|███████▍ | 42576/57600 [7:28:45<2:40:22, 1.56it/s] 74%|███████▍ | 42577/57600 [7:28:45<2:35:56, 1.61it/s] 74%|███████▍ | 42578/57600 [7:28:46<2:35:40, 1.61it/s] 74%|███████▍ | 42579/57600 [7:28:46<2:33:05, 1.64it/s] 74%|███████▍ | 42580/57600 [7:28:47<2:32:39, 1.64it/s] {'loss': 1.1307, 'learning_rate': 3.3550522648083626e-07, 'epoch': 469.98} + 74%|███████▍ | 42580/57600 [7:28:47<2:32:39, 1.64it/s] 74%|███████▍ | 42581/57600 [7:28:48<2:33:26, 1.63it/s] 74%|███████▍ | 42582/57600 [7:28:48<2:37:40, 1.59it/s] 74%|███████▍ | 42583/57600 [7:28:49<2:39:05, 1.57it/s] 74%|███████▍ | 42584/57600 [7:28:50<2:41:00, 1.55it/s] 74%|███████▍ | 42585/57600 [7:28:50<2:37:59, 1.58it/s] 74%|███████▍ | 42586/57600 [7:28:51<2:32:42, 1.64it/s] 74%|███████▍ | 42587/57600 [7:28:51<2:32:00, 1.65it/s] 74%|███████▍ | 42588/57600 [7:28:52<2:37:13, 1.59it/s] 74%|███████▍ | 42589/57600 [7:28:53<2:37:36, 1.59it/s] 74%|███████▍ | 42590/57600 [7:28:53<2:34:34, 1.62it/s] 74%|███████▍ | 42591/57600 [7:28:54<2:31:46, 1.65it/s] 74%|███████▍ | 42592/57600 [7:28:54<2:31:43, 1.65it/s] 74%|███████▍ | 42593/57600 [7:28:55<2:29:35, 1.67it/s] 74%|███████▍ | 42594/57600 [7:28:56<2:27:33, 1.69it/s] 74%|███████▍ | 42595/57600 [7:28:56<2:35:09, 1.61it/s] 74%|███████▍ | 42596/57600 [7:28:57<2:32:02, 1.64it/s] 74%|███████▍ | 42597/57600 [7:28:57<2:32:51, 1.64it/s] 74%|███████▍ | 42598/57600 [7:28:58<2:33:19, 1.63it/s] 74%|███████▍ | 42599/57600 [7:28:59<2:50:16, 1.47it/s] 74%|███████▍ | 42600/57600 [7:29:00<2:48:56, 1.48it/s] {'loss': 1.1366, 'learning_rate': 3.3519163763066196e-07, 'epoch': 470.2} + 74%|██��████▍ | 42600/57600 [7:29:00<2:48:56, 1.48it/s] 74%|███████▍ | 42601/57600 [7:29:00<2:42:22, 1.54it/s] 74%|███████▍ | 42602/57600 [7:29:01<2:40:23, 1.56it/s] 74%|███████▍ | 42603/57600 [7:29:01<2:36:57, 1.59it/s] 74%|███████▍ | 42604/57600 [7:29:02<2:34:59, 1.61it/s] 74%|███████▍ | 42605/57600 [7:29:03<2:31:34, 1.65it/s] 74%|███████▍ | 42606/57600 [7:29:03<2:32:32, 1.64it/s] 74%|███████▍ | 42607/57600 [7:29:04<2:35:11, 1.61it/s] 74%|███████▍ | 42608/57600 [7:29:04<2:33:12, 1.63it/s] 74%|███████▍ | 42609/57600 [7:29:05<2:33:27, 1.63it/s] 74%|███████▍ | 42610/57600 [7:29:06<2:32:46, 1.64it/s] 74%|███████▍ | 42611/57600 [7:29:06<2:36:39, 1.59it/s] 74%|███████▍ | 42612/57600 [7:29:07<2:33:01, 1.63it/s] 74%|███████▍ | 42613/57600 [7:29:08<2:39:22, 1.57it/s] 74%|███████▍ | 42614/57600 [7:29:08<2:39:38, 1.56it/s] 74%|███████▍ | 42615/57600 [7:29:09<2:38:35, 1.57it/s] 74%|███████▍ | 42616/57600 [7:29:09<2:35:02, 1.61it/s] 74%|███████▍ | 42617/57600 [7:29:10<2:36:11, 1.60it/s] 74%|███████▍ | 42618/57600 [7:29:11<2:38:14, 1.58it/s] 74%|███████▍ | 42619/57600 [7:29:11<2:38:55, 1.57it/s] 74%|███████▍ | 42620/57600 [7:29:12<2:37:18, 1.59it/s] {'loss': 1.1425, 'learning_rate': 3.3487804878048777e-07, 'epoch': 470.42} + 74%|███████▍ | 42620/57600 [7:29:12<2:37:18, 1.59it/s] 74%|███████▍ | 42621/57600 [7:29:13<2:34:25, 1.62it/s] 74%|███████▍ | 42622/57600 [7:29:13<2:35:37, 1.60it/s] 74%|███████▍ | 42623/57600 [7:29:14<2:33:15, 1.63it/s] 74%|███████▍ | 42624/57600 [7:29:14<2:33:26, 1.63it/s] 74%|███████▍ | 42625/57600 [7:29:15<2:35:27, 1.61it/s] 74%|███████▍ | 42626/57600 [7:29:16<2:32:10, 1.64it/s] 74%|███████▍ | 42627/57600 [7:29:16<2:31:58, 1.64it/s] 74%|███████▍ | 42628/57600 [7:29:17<2:35:02, 1.61it/s] 74%|███████▍ | 42629/57600 [7:29:18<2:38:45, 1.57it/s] 74%|███████▍ | 42630/57600 [7:29:18<2:36:59, 1.59it/s] 74%|███████▍ | 42631/57600 [7:29:19<2:34:38, 1.61it/s] 74%|███████▍ | 42632/57600 [7:29:19<2:33:52, 1.62it/s] 74%|███████▍ | 42633/57600 [7:29:20<2:31:55, 1.64it/s] 74%|███████▍ | 42634/57600 [7:29:21<2:30:48, 1.65it/s] 74%|███████▍ | 42635/57600 [7:29:21<2:30:10, 1.66it/s] 74%|███████▍ | 42636/57600 [7:29:22<2:32:04, 1.64it/s] 74%|███████▍ | 42637/57600 [7:29:22<2:32:58, 1.63it/s] 74%|███████▍ | 42638/57600 [7:29:23<2:32:07, 1.64it/s] 74%|███████▍ | 42639/57600 [7:29:24<2:32:14, 1.64it/s] 74%|███████▍ | 42640/57600 [7:29:24<2:35:23, 1.60it/s] {'loss': 1.1551, 'learning_rate': 3.345644599303135e-07, 'epoch': 470.64} + 74%|███████▍ | 42640/57600 [7:29:24<2:35:23, 1.60it/s] 74%|███████▍ | 42641/57600 [7:29:25<2:45:31, 1.51it/s] 74%|███████▍ | 42642/57600 [7:29:26<2:37:17, 1.58it/s] 74%|███████▍ | 42643/57600 [7:29:26<2:34:24, 1.61it/s] 74%|███████▍ | 42644/57600 [7:29:27<2:30:47, 1.65it/s] 74%|███████▍ | 42645/57600 [7:29:27<2:30:08, 1.66it/s] 74%|███████▍ | 42646/57600 [7:29:28<2:32:05, 1.64it/s] 74%|███████▍ | 42647/57600 [7:29:29<2:37:05, 1.59it/s] 74%|███████▍ | 42648/57600 [7:29:29<2:41:14, 1.55it/s] 74%|███████▍ | 42649/57600 [7:29:30<2:34:38, 1.61it/s] 74%|███████▍ | 42650/57600 [7:29:30<2:35:26, 1.60it/s] 74%|███████▍ | 42651/57600 [7:29:31<2:31:28, 1.64it/s] 74%|███████▍ | 42652/57600 [7:29:32<2:30:45, 1.65it/s] 74%|███████▍ | 42653/57600 [7:29:32<2:32:22, 1.63it/s] 74%|███████▍ | 42654/57600 [7:29:33<2:29:45, 1.66it/s] 74%|███████▍ | 42655/57600 [7:29:34<2:34:42, 1.61it/s] 74%|███████▍ | 42656/57600 [7:29:34<2:31:32, 1.64it/s] 74%|███████▍ | 42657/57600 [7:29:35<2:36:50, 1.59it/s] 74%|███████▍ | 42658/57600 [7:29:35<2:38:09, 1.57it/s] 74%|███████▍ | 42659/57600 [7:29:36<2:39:19, 1.56it/s] 74%|███████▍ | 42660/57600 [7:29:37<2:41:55, 1.54it/s] {'loss': 1.1276, 'learning_rate': 3.342508710801394e-07, 'epoch': 470.86} + 74%|███████▍ | 42660/57600 [7:29:37<2:41:55, 1.54it/s] 74%|███████▍ | 42661/57600 [7:29:37<2:39:07, 1.56it/s] 74%|███████▍ | 42662/57600 [7:29:38<2:38:19, 1.57it/s] 74%|███████▍ | 42663/57600 [7:29:39<2:39:03, 1.57it/s] 74%|███████▍ | 42664/57600 [7:29:39<2:39:14, 1.56it/s] 74%|███████▍ | 42665/57600 [7:29:40<2:32:30, 1.63it/s] 74%|███████▍ | 42666/57600 [7:29:41<2:37:09, 1.58it/s] 74%|███████▍ | 42667/57600 [7:29:41<2:41:20, 1.54it/s] 74%|███████▍ | 42668/57600 [7:29:42<2:44:42, 1.51it/s] 74%|███████▍ | 42669/57600 [7:29:43<2:43:01, 1.53it/s] 74%|███████▍ | 42670/57600 [7:29:43<2:39:42, 1.56it/s] 74%|███████▍ | 42671/57600 [7:29:44<2:39:43, 1.56it/s] 74%|███████▍ | 42672/57600 [7:29:44<2:41:48, 1.54it/s] 74%|███████▍ | 42673/57600 [7:29:45<2:49:26, 1.47it/s] 74%|███████▍ | 42674/57600 [7:29:46<2:47:21, 1.49it/s] 74%|███████▍ | 42675/57600 [7:29:46<2:42:04, 1.53it/s] 74%|███████▍ | 42676/57600 [7:29:47<2:36:44, 1.59it/s] 74%|███████▍ | 42677/57600 [7:29:48<2:35:16, 1.60it/s] 74%|███████▍ | 42678/57600 [7:29:48<2:34:06, 1.61it/s] 74%|███████▍ | 42679/57600 [7:29:49<2:33:02, 1.62it/s] 74%|███████▍ | 42680/57600 [7:29:49<2:33:13, 1.62it/s] {'loss': 1.1544, 'learning_rate': 3.339372822299652e-07, 'epoch': 471.08} + 74%|███████▍ | 42680/57600 [7:29:50<2:33:13, 1.62it/s] 74%|███████▍ | 42681/57600 [7:29:50<2:34:31, 1.61it/s] 74%|███████▍ | 42682/57600 [7:29:51<2:36:43, 1.59it/s] 74%|███████▍ | 42683/57600 [7:29:51<2:33:36, 1.62it/s] 74%|███████▍ | 42684/57600 [7:29:52<2:33:58, 1.61it/s] 74%|███████▍ | 42685/57600 [7:29:53<2:30:29, 1.65it/s] 74%|███████▍ | 42686/57600 [7:29:53<2:27:57, 1.68it/s] 74%|███████▍ | 42687/57600 [7:29:54<2:29:09, 1.67it/s] 74%|███████▍ | 42688/57600 [7:29:54<2:28:05, 1.68it/s] 74%|███████▍ | 42689/57600 [7:29:55<2:32:51, 1.63it/s] 74%|███████▍ | 42690/57600 [7:29:56<2:33:35, 1.62it/s] 74%|███████▍ | 42691/57600 [7:29:56<2:32:58, 1.62it/s] 74%|███████▍ | 42692/57600 [7:29:57<2:33:49, 1.62it/s] 74%|███████▍ | 42693/57600 [7:29:57<2:34:41, 1.61it/s] 74%|███████▍ | 42694/57600 [7:29:58<2:32:58, 1.62it/s] 74%|███████▍ | 42695/57600 [7:29:59<2:29:15, 1.66it/s] 74%|███████▍ | 42696/57600 [7:29:59<2:33:35, 1.62it/s] 74%|███████▍ | 42697/57600 [7:30:00<2:36:25, 1.59it/s] 74%|███████▍ | 42698/57600 [7:30:01<2:36:55, 1.58it/s] 74%|███████▍ | 42699/57600 [7:30:01<2:36:35, 1.59it/s] 74%|███████▍ | 42700/57600 [7:30:02<2:35:15, 1.60it/s] {'loss': 1.1279, 'learning_rate': 3.336236933797909e-07, 'epoch': 471.3} + 74%|███████▍ | 42700/57600 [7:30:02<2:35:15, 1.60it/s] 74%|███████▍ | 42701/57600 [7:30:02<2:36:23, 1.59it/s] 74%|███████▍ | 42702/57600 [7:30:03<2:35:57, 1.59it/s] 74%|███████▍ | 42703/57600 [7:30:04<2:39:08, 1.56it/s] 74%|███████▍ | 42704/57600 [7:30:04<2:41:24, 1.54it/s] 74%|███████▍ | 42705/57600 [7:30:05<2:39:32, 1.56it/s] 74%|███████▍ | 42706/57600 [7:30:06<2:37:01, 1.58it/s] 74%|███████▍ | 42707/57600 [7:30:06<2:36:09, 1.59it/s] 74%|███████▍ | 42708/57600 [7:30:07<2:33:06, 1.62it/s] 74%|███████▍ | 42709/57600 [7:30:08<2:34:07, 1.61it/s] 74%|███████▍ | 42710/57600 [7:30:08<2:35:56, 1.59it/s] 74%|███████▍ | 42711/57600 [7:30:09<2:35:45, 1.59it/s] 74%|███████▍ | 42712/57600 [7:30:09<2:34:56, 1.60it/s] 74%|███████▍ | 42713/57600 [7:30:10<2:34:33, 1.61it/s] 74%|███████▍ | 42714/57600 [7:30:11<2:40:16, 1.55it/s] 74%|███████▍ | 42715/57600 [7:30:11<2:43:25, 1.52it/s] 74%|███████▍ | 42716/57600 [7:30:12<2:39:00, 1.56it/s] 74%|███████▍ | 42717/57600 [7:30:13<2:33:19, 1.62it/s] 74%|███████▍ | 42718/57600 [7:30:13<2:36:06, 1.59it/s] 74%|███████▍ | 42719/57600 [7:30:14<2:33:39, 1.61it/s] 74%|███████▍ | 42720/57600 [7:30:15<2:37:56, 1.57it/s] {'loss': 1.1445, 'learning_rate': 3.3331010452961674e-07, 'epoch': 471.52} + 74%|███████▍ | 42720/57600 [7:30:15<2:37:56, 1.57it/s] 74%|███████▍ | 42721/57600 [7:30:15<2:33:31, 1.62it/s] 74%|███████▍ | 42722/57600 [7:30:16<2:32:22, 1.63it/s] 74%|███████▍ | 42723/57600 [7:30:16<2:33:44, 1.61it/s] 74%|███████▍ | 42724/57600 [7:30:17<2:36:47, 1.58it/s] 74%|███████▍ | 42725/57600 [7:30:18<2:33:18, 1.62it/s] 74%|███████▍ | 42726/57600 [7:30:18<2:31:38, 1.63it/s] 74%|███████▍ | 42727/57600 [7:30:19<2:33:17, 1.62it/s] 74%|███████▍ | 42728/57600 [7:30:19<2:28:31, 1.67it/s] 74%|███████▍ | 42729/57600 [7:30:20<2:28:05, 1.67it/s] 74%|███████▍ | 42730/57600 [7:30:21<2:32:55, 1.62it/s] 74%|███████▍ | 42731/57600 [7:30:21<2:34:07, 1.61it/s] 74%|███████▍ | 42732/57600 [7:30:22<2:31:31, 1.64it/s] 74%|███████▍ | 42733/57600 [7:30:23<2:37:16, 1.58it/s] 74%|███████▍ | 42734/57600 [7:30:23<2:33:45, 1.61it/s] 74%|███████▍ | 42735/57600 [7:30:24<2:31:46, 1.63it/s] 74%|███████▍ | 42736/57600 [7:30:24<2:37:31, 1.57it/s] 74%|███████▍ | 42737/57600 [7:30:25<2:38:20, 1.56it/s] 74%|███████▍ | 42738/57600 [7:30:26<2:35:10, 1.60it/s] 74%|███████▍ | 42739/57600 [7:30:26<2:31:34, 1.63it/s] 74%|███████▍ | 42740/57600 [7:30:27<2:31:51, 1.63it/s] {'loss': 1.1409, 'learning_rate': 3.329965156794425e-07, 'epoch': 471.74} + 74%|███████▍ | 42740/57600 [7:30:27<2:31:51, 1.63it/s] 74%|███████▍ | 42741/57600 [7:30:28<2:37:27, 1.57it/s] 74%|███████▍ | 42742/57600 [7:30:28<2:36:33, 1.58it/s] 74%|███████▍ | 42743/57600 [7:30:29<2:32:07, 1.63it/s] 74%|███████▍ | 42744/57600 [7:30:29<2:30:22, 1.65it/s] 74%|███████▍ | 42745/57600 [7:30:30<2:29:55, 1.65it/s] 74%|███████▍ | 42746/57600 [7:30:31<2:35:42, 1.59it/s] 74%|███████▍ | 42747/57600 [7:30:31<2:36:58, 1.58it/s] 74%|███████▍ | 42748/57600 [7:30:32<2:37:47, 1.57it/s] 74%|███████▍ | 42749/57600 [7:30:32<2:31:29, 1.63it/s] 74%|███████▍ | 42750/57600 [7:30:33<2:31:43, 1.63it/s] 74%|███████▍ | 42751/57600 [7:30:34<2:35:27, 1.59it/s] 74%|███████▍ | 42752/57600 [7:30:34<2:37:25, 1.57it/s] 74%|███████▍ | 42753/57600 [7:30:35<2:33:06, 1.62it/s] 74%|███████▍ | 42754/57600 [7:30:36<2:37:33, 1.57it/s] 74%|███████▍ | 42755/57600 [7:30:36<2:35:33, 1.59it/s] 74%|███████▍ | 42756/57600 [7:30:37<2:35:39, 1.59it/s] 74%|███████▍ | 42757/57600 [7:30:38<2:43:28, 1.51it/s] 74%|███████▍ | 42758/57600 [7:30:38<2:40:57, 1.54it/s] 74%|███████▍ | 42759/57600 [7:30:39<2:43:11, 1.52it/s] 74%|███████▍ | 42760/57600 [7:30:40<2:41:10, 1.53it/s] {'loss': 1.1386, 'learning_rate': 3.326829268292683e-07, 'epoch': 471.96} + 74%|███████▍ | 42760/57600 [7:30:40<2:41:10, 1.53it/s] 74%|███████▍ | 42761/57600 [7:30:40<2:38:04, 1.56it/s] 74%|███████▍ | 42762/57600 [7:30:41<2:38:07, 1.56it/s] 74%|███████▍ | 42763/57600 [7:30:41<2:36:28, 1.58it/s] 74%|███████▍ | 42764/57600 [7:30:42<2:50:53, 1.45it/s] 74%|███████▍ | 42765/57600 [7:30:43<2:43:44, 1.51it/s] 74%|███████▍ | 42766/57600 [7:30:44<2:45:35, 1.49it/s] 74%|███████▍ | 42767/57600 [7:30:44<2:41:23, 1.53it/s] 74%|███████▍ | 42768/57600 [7:30:45<2:36:28, 1.58it/s] 74%|███████▍ | 42769/57600 [7:30:45<2:34:28, 1.60it/s] 74%|███████▍ | 42770/57600 [7:30:46<2:42:17, 1.52it/s] 74%|███████▍ | 42771/57600 [7:30:47<2:42:38, 1.52it/s] 74%|███████▍ | 42772/57600 [7:30:47<2:38:28, 1.56it/s] 74%|███████▍ | 42773/57600 [7:30:48<2:41:30, 1.53it/s] 74%|███████▍ | 42774/57600 [7:30:49<2:38:07, 1.56it/s] 74%|███████▍ | 42775/57600 [7:30:49<2:38:42, 1.56it/s] 74%|███████▍ | 42776/57600 [7:30:50<2:42:00, 1.53it/s] 74%|███████▍ | 42777/57600 [7:30:51<2:39:15, 1.55it/s] 74%|███████▍ | 42778/57600 [7:30:51<2:37:04, 1.57it/s] 74%|███████▍ | 42779/57600 [7:30:52<2:35:21, 1.59it/s] 74%|███████▍ | 42780/57600 [7:30:52<2:33:34, 1.61it/s] {'loss': 1.1302, 'learning_rate': 3.323693379790941e-07, 'epoch': 472.19} + 74%|███████▍ | 42780/57600 [7:30:52<2:33:34, 1.61it/s] 74%|███████▍ | 42781/57600 [7:30:53<2:32:24, 1.62it/s] 74%|███████▍ | 42782/57600 [7:30:54<2:30:04, 1.65it/s] 74%|███████▍ | 42783/57600 [7:30:54<2:30:15, 1.64it/s] 74%|███████▍ | 42784/57600 [7:30:55<2:30:19, 1.64it/s] 74%|███████▍ | 42785/57600 [7:30:55<2:30:38, 1.64it/s] 74%|███████▍ | 42786/57600 [7:30:56<2:36:10, 1.58it/s] 74%|███████▍ | 42787/57600 [7:30:57<2:35:17, 1.59it/s] 74%|███████▍ | 42788/57600 [7:30:57<2:35:19, 1.59it/s] 74%|███████▍ | 42789/57600 [7:30:58<2:34:31, 1.60it/s] 74%|███████▍ | 42790/57600 [7:30:59<2:40:31, 1.54it/s] 74%|███████▍ | 42791/57600 [7:30:59<2:41:09, 1.53it/s] 74%|███████▍ | 42792/57600 [7:31:00<2:34:54, 1.59it/s] 74%|███████▍ | 42793/57600 [7:31:01<2:31:32, 1.63it/s] 74%|███████▍ | 42794/57600 [7:31:01<2:33:37, 1.61it/s] 74%|███████▍ | 42795/57600 [7:31:02<2:35:05, 1.59it/s] 74%|███████▍ | 42796/57600 [7:31:02<2:35:32, 1.59it/s] 74%|███████▍ | 42797/57600 [7:31:03<2:33:25, 1.61it/s] 74%|███████▍ | 42798/57600 [7:31:04<2:29:39, 1.65it/s] 74%|███████▍ | 42799/57600 [7:31:04<2:27:35, 1.67it/s] 74%|███████▍ | 42800/57600 [7:31:05<2:34:34, 1.60it/s] {'loss': 1.1509, 'learning_rate': 3.3205574912891985e-07, 'epoch': 472.41} + 74%|███████▍ | 42800/57600 [7:31:05<2:34:34, 1.60it/s] 74%|███████▍ | 42801/57600 [7:31:06<2:35:30, 1.59it/s] 74%|███████▍ | 42802/57600 [7:31:06<2:34:50, 1.59it/s] 74%|███████▍ | 42803/57600 [7:31:07<2:32:56, 1.61it/s] 74%|███████▍ | 42804/57600 [7:31:07<2:29:12, 1.65it/s] 74%|███████▍ | 42805/57600 [7:31:08<2:34:05, 1.60it/s] 74%|███████▍ | 42806/57600 [7:31:09<2:31:15, 1.63it/s] 74%|███████▍ | 42807/57600 [7:31:09<2:36:36, 1.57it/s] 74%|███████▍ | 42808/57600 [7:31:10<2:40:52, 1.53it/s] 74%|███████▍ | 42809/57600 [7:31:11<2:38:51, 1.55it/s] 74%|███████▍ | 42810/57600 [7:31:11<2:37:20, 1.57it/s] 74%|███████▍ | 42811/57600 [7:31:12<2:33:48, 1.60it/s] 74%|███████▍ | 42812/57600 [7:31:12<2:36:59, 1.57it/s] 74%|███████▍ | 42813/57600 [7:31:13<2:34:01, 1.60it/s] 74%|███████▍ | 42814/57600 [7:31:14<2:31:19, 1.63it/s] 74%|███████▍ | 42815/57600 [7:31:14<2:31:53, 1.62it/s] 74%|███████▍ | 42816/57600 [7:31:15<2:29:14, 1.65it/s] 74%|███████▍ | 42817/57600 [7:31:15<2:32:28, 1.62it/s] 74%|███████▍ | 42818/57600 [7:31:16<2:34:51, 1.59it/s] 74%|███████▍ | 42819/57600 [7:31:17<2:37:00, 1.57it/s] 74%|███████▍ | 42820/57600 [7:31:17<2:37:36, 1.56it/s] {'loss': 1.1168, 'learning_rate': 3.3174216027874566e-07, 'epoch': 472.63} + 74%|███████▍ | 42820/57600 [7:31:17<2:37:36, 1.56it/s] 74%|███████▍ | 42821/57600 [7:31:18<2:36:23, 1.58it/s] 74%|███████▍ | 42822/57600 [7:31:19<2:34:40, 1.59it/s] 74%|███████▍ | 42823/57600 [7:31:19<2:33:34, 1.60it/s] 74%|███████▍ | 42824/57600 [7:31:20<2:38:55, 1.55it/s] 74%|███████▍ | 42825/57600 [7:31:21<2:32:18, 1.62it/s] 74%|███████▍ | 42826/57600 [7:31:21<2:40:13, 1.54it/s] 74%|███████▍ | 42827/57600 [7:31:22<2:31:37, 1.62it/s] 74%|███████▍ | 42828/57600 [7:31:22<2:31:39, 1.62it/s] 74%|███████▍ | 42829/57600 [7:31:23<2:36:42, 1.57it/s] 74%|███████▍ | 42830/57600 [7:31:24<2:32:25, 1.61it/s] 74%|███████▍ | 42831/57600 [7:31:24<2:29:29, 1.65it/s] 74%|███████▍ | 42832/57600 [7:31:25<2:31:40, 1.62it/s] 74%|███████▍ | 42833/57600 [7:31:26<2:36:14, 1.58it/s] 74%|███████▍ | 42834/57600 [7:31:26<2:38:17, 1.55it/s] 74%|███████▍ | 42835/57600 [7:31:27<2:40:58, 1.53it/s] 74%|███████▍ | 42836/57600 [7:31:28<2:39:14, 1.55it/s] 74%|███████▍ | 42837/57600 [7:31:28<2:42:13, 1.52it/s] 74%|███████▍ | 42838/57600 [7:31:29<2:40:52, 1.53it/s] 74%|███████▍ | 42839/57600 [7:31:30<2:39:47, 1.54it/s] 74%|███████▍ | 42840/57600 [7:31:30<2:40:30, 1.53it/s] {'loss': 1.095, 'learning_rate': 3.3142857142857136e-07, 'epoch': 472.85} + 74%|███████▍ | 42840/57600 [7:31:30<2:40:30, 1.53it/s] 74%|███████▍ | 42841/57600 [7:31:31<2:35:00, 1.59it/s] 74%|███████▍ | 42842/57600 [7:31:31<2:33:32, 1.60it/s] 74%|██���████▍ | 42843/57600 [7:31:32<2:38:36, 1.55it/s] 74%|███████▍ | 42844/57600 [7:31:33<2:37:12, 1.56it/s] 74%|███████▍ | 42845/57600 [7:31:33<2:35:49, 1.58it/s] 74%|███████▍ | 42846/57600 [7:31:34<2:32:27, 1.61it/s] 74%|███████▍ | 42847/57600 [7:31:34<2:30:27, 1.63it/s] 74%|███████▍ | 42848/57600 [7:31:35<2:31:32, 1.62it/s] 74%|███████▍ | 42849/57600 [7:31:36<2:30:24, 1.63it/s] 74%|███████▍ | 42850/57600 [7:31:36<2:28:47, 1.65it/s] 74%|███████▍ | 42851/57600 [7:31:37<2:28:49, 1.65it/s] 74%|███████▍ | 42852/57600 [7:31:38<2:28:30, 1.66it/s] 74%|███████▍ | 42853/57600 [7:31:38<2:33:40, 1.60it/s] 74%|███████▍ | 42854/57600 [7:31:39<2:38:58, 1.55it/s] 74%|███████▍ | 42855/57600 [7:31:39<2:36:05, 1.57it/s] 74%|███████▍ | 42856/57600 [7:31:40<2:34:46, 1.59it/s] 74%|███████▍ | 42857/57600 [7:31:41<2:31:36, 1.62it/s] 74%|███████▍ | 42858/57600 [7:31:41<2:32:44, 1.61it/s] 74%|███████▍ | 42859/57600 [7:31:42<2:28:05, 1.66it/s] 74%|███████▍ | 42860/57600 [7:31:42<2:27:41, 1.66it/s] {'loss': 1.1584, 'learning_rate': 3.311149825783972e-07, 'epoch': 473.07} + 74%|███████▍ | 42860/57600 [7:31:42<2:27:41, 1.66it/s] 74%|███████▍ | 42861/57600 [7:31:43<2:27:30, 1.67it/s] 74%|███████▍ | 42862/57600 [7:31:44<2:28:47, 1.65it/s] 74%|███████▍ | 42863/57600 [7:31:44<2:26:39, 1.67it/s] 74%|███████▍ | 42864/57600 [7:31:45<2:24:45, 1.70it/s] 74%|███████▍ | 42865/57600 [7:31:46<2:31:59, 1.62it/s] 74%|███████▍ | 42866/57600 [7:31:46<2:29:50, 1.64it/s] 74%|███████▍ | 42867/57600 [7:31:47<2:32:16, 1.61it/s] 74%|███████▍ | 42868/57600 [7:31:47<2:30:08, 1.64it/s] 74%|███████▍ | 42869/57600 [7:31:48<2:36:22, 1.57it/s] 74%|███████▍ | 42870/57600 [7:31:49<2:35:52, 1.58it/s] 74%|███████▍ | 42871/57600 [7:31:49<2:30:12, 1.63it/s] 74%|███████▍ | 42872/57600 [7:31:50<2:33:23, 1.60it/s] 74%|███████▍ | 42873/57600 [7:31:50<2:31:22, 1.62it/s] 74%|███████▍ | 42874/57600 [7:31:51<2:30:32, 1.63it/s] 74%|███████▍ | 42875/57600 [7:31:52<2:35:42, 1.58it/s] 74%|███████▍ | 42876/57600 [7:31:52<2:31:58, 1.61it/s] 74%|███████▍ | 42877/57600 [7:31:53<2:31:38, 1.62it/s] 74%|███████▍ | 42878/57600 [7:31:54<2:32:18, 1.61it/s] 74%|███████▍ | 42879/57600 [7:31:54<2:35:30, 1.58it/s] 74%|███████▍ | 42880/57600 [7:31:55<2:31:33, 1.62it/s] {'loss': 1.1508, 'learning_rate': 3.3080139372822297e-07, 'epoch': 473.29} + 74%|███████▍ | 42880/57600 [7:31:55<2:31:33, 1.62it/s] 74%|███████▍ | 42881/57600 [7:31:55<2:29:46, 1.64it/s] 74%|███████▍ | 42882/57600 [7:31:56<2:32:03, 1.61it/s] 74%|███████▍ | 42883/57600 [7:31:57<2:40:03, 1.53it/s] 74%|███████▍ | 42884/57600 [7:31:57<2:38:54, 1.54it/s] 74%|███████▍ | 42885/57600 [7:31:58<2:35:41, 1.58it/s] 74%|███████▍ | 42886/57600 [7:31:59<2:36:52, 1.56it/s] 74%|███████▍ | 42887/57600 [7:31:59<2:31:41, 1.62it/s] 74%|███████▍ | 42888/57600 [7:32:00<2:30:20, 1.63it/s] 74%|███████▍ | 42889/57600 [7:32:01<2:32:21, 1.61it/s] 74%|███████▍ | 42890/57600 [7:32:01<2:34:13, 1.59it/s] 74%|███████▍ | 42891/57600 [7:32:02<2:34:08, 1.59it/s] 74%|███████▍ | 42892/57600 [7:32:02<2:31:52, 1.61it/s] 74%|███████▍ | 42893/57600 [7:32:03<2:29:49, 1.64it/s] 74%|███████▍ | 42894/57600 [7:32:04<2:30:29, 1.63it/s] 74%|███████▍ | 42895/57600 [7:32:04<2:31:02, 1.62it/s] 74%|███████▍ | 42896/57600 [7:32:05<2:31:27, 1.62it/s] 74%|███████▍ | 42897/57600 [7:32:05<2:31:48, 1.61it/s] 74%|███████▍ | 42898/57600 [7:32:06<2:33:13, 1.60it/s] 74%|███████▍ | 42899/57600 [7:32:07<2:34:16, 1.59it/s] 74%|███████▍ | 42900/57600 [7:32:07<2:35:19, 1.58it/s] {'loss': 1.1147, 'learning_rate': 3.3048780487804877e-07, 'epoch': 473.51} + 74%|███████▍ | 42900/57600 [7:32:07<2:35:19, 1.58it/s] 74%|███████▍ | 42901/57600 [7:32:08<2:34:50, 1.58it/s] 74%|███████▍ | 42902/57600 [7:32:09<2:32:54, 1.60it/s] 74%|███████▍ | 42903/57600 [7:32:09<2:40:37, 1.52it/s] 74%|███████▍ | 42904/57600 [7:32:10<2:36:43, 1.56it/s] 74%|███████▍ | 42905/57600 [7:32:11<2:31:42, 1.61it/s] 74%|███████▍ | 42906/57600 [7:32:11<2:27:48, 1.66it/s] 74%|███████▍ | 42907/57600 [7:32:12<2:30:12, 1.63it/s] 74%|███████▍ | 42908/57600 [7:32:12<2:36:47, 1.56it/s] 74%|███████▍ | 42909/57600 [7:32:13<2:38:23, 1.55it/s] 74%|███████▍ | 42910/57600 [7:32:14<2:33:29, 1.60it/s] 74%|███████▍ | 42911/57600 [7:32:14<2:32:08, 1.61it/s] 74%|███████▍ | 42912/57600 [7:32:15<2:33:35, 1.59it/s] 75%|███████▍ | 42913/57600 [7:32:16<2:36:53, 1.56it/s] 75%|███████▍ | 42914/57600 [7:32:16<2:33:56, 1.59it/s] 75%|███████▍ | 42915/57600 [7:32:17<2:34:28, 1.58it/s] 75%|███████▍ | 42916/57600 [7:32:17<2:31:24, 1.62it/s] 75%|███████▍ | 42917/57600 [7:32:18<2:35:41, 1.57it/s] 75%|███████▍ | 42918/57600 [7:32:19<2:33:18, 1.60it/s] 75%|███████▍ | 42919/57600 [7:32:19<2:34:00, 1.59it/s] 75%|███████▍ | 42920/57600 [7:32:20<2:36:36, 1.56it/s] {'loss': 1.1217, 'learning_rate': 3.301742160278746e-07, 'epoch': 473.73} + 75%|███████▍ | 42920/57600 [7:32:20<2:36:36, 1.56it/s] 75%|███████▍ | 42921/57600 [7:32:21<2:33:12, 1.60it/s] 75%|███████▍ | 42922/57600 [7:32:21<2:34:56, 1.58it/s] 75%|███████▍ | 42923/57600 [7:32:22<2:35:30, 1.57it/s] 75%|███████▍ | 42924/57600 [7:32:23<2:35:54, 1.57it/s] 75%|███████▍ | 42925/57600 [7:32:23<2:38:26, 1.54it/s] 75%|███████▍ | 42926/57600 [7:32:24<2:36:03, 1.57it/s] 75%|███████▍ | 42927/57600 [7:32:24<2:37:02, 1.56it/s] 75%|███████▍ | 42928/57600 [7:32:25<2:36:07, 1.57it/s] 75%|███████▍ | 42929/57600 [7:32:26<2:36:37, 1.56it/s] 75%|███████▍ | 42930/57600 [7:32:26<2:36:17, 1.56it/s] 75%|███████▍ | 42931/57600 [7:32:27<2:39:26, 1.53it/s] 75%|███████▍ | 42932/57600 [7:32:28<2:40:15, 1.53it/s] 75%|███████▍ | 42933/57600 [7:32:28<2:38:03, 1.55it/s] 75%|███████▍ | 42934/57600 [7:32:29<2:40:46, 1.52it/s] 75%|███████▍ | 42935/57600 [7:32:30<2:38:08, 1.55it/s] 75%|███████▍ | 42936/57600 [7:32:30<2:36:21, 1.56it/s] 75%|███████▍ | 42937/57600 [7:32:31<2:32:31, 1.60it/s] 75%|███████▍ | 42938/57600 [7:32:32<2:33:52, 1.59it/s] 75%|███████▍ | 42939/57600 [7:32:32<2:33:34, 1.59it/s] 75%|███████▍ | 42940/57600 [7:32:33<2:31:20, 1.61it/s] {'loss': 1.1099, 'learning_rate': 3.2986062717770033e-07, 'epoch': 473.95} + 75%|███████▍ | 42940/57600 [7:32:33<2:31:20, 1.61it/s] 75%|███████▍ | 42941/57600 [7:32:33<2:29:00, 1.64it/s] 75%|███████▍ | 42942/57600 [7:32:34<2:33:05, 1.60it/s] 75%|███████▍ | 42943/57600 [7:32:35<2:30:14, 1.63it/s] 75%|███████▍ | 42944/57600 [7:32:35<2:37:00, 1.56it/s] 75%|███████▍ | 42945/57600 [7:32:36<2:45:59, 1.47it/s] 75%|███████▍ | 42946/57600 [7:32:37<2:40:17, 1.52it/s] 75%|███████▍ | 42947/57600 [7:32:37<2:36:30, 1.56it/s] 75%|███████▍ | 42948/57600 [7:32:38<2:36:43, 1.56it/s] 75%|███████▍ | 42949/57600 [7:32:39<2:33:19, 1.59it/s] 75%|███████▍ | 42950/57600 [7:32:39<2:30:49, 1.62it/s] 75%|███████▍ | 42951/57600 [7:32:40<2:33:27, 1.59it/s] 75%|███████▍ | 42952/57600 [7:32:40<2:33:34, 1.59it/s] 75%|███████▍ | 42953/57600 [7:32:41<2:31:12, 1.61it/s] 75%|███████▍ | 42954/57600 [7:32:42<2:25:53, 1.67it/s] 75%|███████▍ | 42955/57600 [7:32:42<2:24:29, 1.69it/s] 75%|███████▍ | 42956/57600 [7:32:43<2:26:30, 1.67it/s] 75%|███████▍ | 42957/57600 [7:32:43<2:27:04, 1.66it/s] 75%|███████▍ | 42958/57600 [7:32:44<2:33:10, 1.59it/s] 75%|███████▍ | 42959/57600 [7:32:45<2:31:55, 1.61it/s] 75%|███████▍ | 42960/57600 [7:32:45<2:28:49, 1.64it/s] {'loss': 1.1578, 'learning_rate': 3.295470383275262e-07, 'epoch': 474.17} + 75%|███████▍ | 42960/57600 [7:32:45<2:28:49, 1.64it/s] 75%|███████▍ | 42961/57600 [7:32:46<2:32:11, 1.60it/s] 75%|███████▍ | 42962/57600 [7:32:46<2:28:06, 1.65it/s] 75%|███████▍ | 42963/57600 [7:32:47<2:28:11, 1.65it/s] 75%|███████▍ | 42964/57600 [7:32:48<2:29:09, 1.64it/s] 75%|███████▍ | 42965/57600 [7:32:48<2:32:46, 1.60it/s] 75%|███████▍ | 42966/57600 [7:32:49<2:31:45, 1.61it/s] 75%|███████▍ | 42967/57600 [7:32:50<2:38:00, 1.54it/s] 75%|███████▍ | 42968/57600 [7:32:50<2:32:38, 1.60it/s] 75%|███████▍ | 42969/57600 [7:32:51<2:32:33, 1.60it/s] 75%|███████▍ | 42970/57600 [7:32:51<2:30:30, 1.62it/s] 75%|███████▍ | 42971/57600 [7:32:52<2:28:36, 1.64it/s] 75%|███████▍ | 42972/57600 [7:32:53<2:28:57, 1.64it/s] 75%|███████▍ | 42973/57600 [7:32:53<2:26:39, 1.66it/s] 75%|███████▍ | 42974/57600 [7:32:54<2:28:35, 1.64it/s] 75%|███████▍ | 42975/57600 [7:32:54<2:28:29, 1.64it/s] 75%|███████▍ | 42976/57600 [7:32:55<2:29:04, 1.64it/s] 75%|███████▍ | 42977/57600 [7:32:56<2:34:18, 1.58it/s] 75%|███████▍ | 42978/57600 [7:32:56<2:34:37, 1.58it/s] 75%|███████▍ | 42979/57600 [7:32:57<2:35:52, 1.56it/s] 75%|███████▍ | 42980/57600 [7:32:58<2:33:00, 1.59it/s] {'loss': 1.1245, 'learning_rate': 3.292334494773519e-07, 'epoch': 474.39} + 75%|███████▍ | 42980/57600 [7:32:58<2:33:00, 1.59it/s] 75%|███████▍ | 42981/57600 [7:32:58<2:34:17, 1.58it/s] 75%|███████▍ | 42982/57600 [7:32:59<2:30:28, 1.62it/s] 75%|███████▍ | 42983/57600 [7:33:00<2:34:04, 1.58it/s] 75%|███████▍ | 42984/57600 [7:33:00<2:32:41, 1.60it/s] 75%|███████▍ | 42985/57600 [7:33:01<2:31:45, 1.61it/s] 75%|███████▍ | 42986/57600 [7:33:01<2:32:55, 1.59it/s] 75%|███████▍ | 42987/57600 [7:33:02<2:36:56, 1.55it/s] 75%|███████▍ | 42988/57600 [7:33:03<2:33:40, 1.58it/s] 75%|███████▍ | 42989/57600 [7:33:03<2:34:58, 1.57it/s] 75%|███████▍ | 42990/57600 [7:33:04<2:41:21, 1.51it/s] 75%|███████▍ | 42991/57600 [7:33:05<2:41:12, 1.51it/s] 75%|███████▍ | 42992/57600 [7:33:05<2:36:00, 1.56it/s] 75%|███████▍ | 42993/57600 [7:33:06<2:36:37, 1.55it/s] 75%|███████▍ | 42994/57600 [7:33:07<2:33:31, 1.59it/s] 75%|███████▍ | 42995/57600 [7:33:07<2:35:00, 1.57it/s] 75%|███████▍ | 42996/57600 [7:33:08<2:36:08, 1.56it/s] 75%|███████▍ | 42997/57600 [7:33:08<2:33:51, 1.58it/s] 75%|███████▍ | 42998/57600 [7:33:09<2:34:34, 1.57it/s] 75%|███████▍ | 42999/57600 [7:33:10<2:39:56, 1.52it/s] 75%|███████▍ | 43000/57600 [7:33:10<2:37:55, 1.54it/s] {'loss': 1.1166, 'learning_rate': 3.289198606271777e-07, 'epoch': 474.61} + 75%|███████▍ | 43000/57600 [7:33:10<2:37:55, 1.54it/s] 75%|███████▍ | 43001/57600 [7:33:11<2:43:06, 1.49it/s] 75%|███████▍ | 43002/57600 [7:33:12<2:40:54, 1.51it/s] 75%|███████▍ | 43003/57600 [7:33:12<2:40:38, 1.51it/s] 75%|███████▍ | 43004/57600 [7:33:13<2:41:00, 1.51it/s] 75%|███████▍ | 43005/57600 [7:33:14<2:34:17, 1.58it/s] 75%|███████▍ | 43006/57600 [7:33:14<2:32:44, 1.59it/s] 75%|███████▍ | 43007/57600 [7:33:15<2:33:28, 1.58it/s] 75%|███████▍ | 43008/57600 [7:33:16<2:35:31, 1.56it/s] 75%|███████▍ | 43009/57600 [7:33:16<2:41:24, 1.51it/s] 75%|███████▍ | 43010/57600 [7:33:17<2:36:40, 1.55it/s] 75%|███████▍ | 43011/57600 [7:33:18<2:38:31, 1.53it/s] 75%|███████▍ | 43012/57600 [7:33:18<2:37:45, 1.54it/s] 75%|███████▍ | 43013/57600 [7:33:19<2:36:19, 1.56it/s] 75%|███████▍ | 43014/57600 [7:33:20<2:34:07, 1.58it/s] 75%|███████▍ | 43015/57600 [7:33:20<2:33:04, 1.59it/s] 75%|███████▍ | 43016/57600 [7:33:21<2:36:19, 1.55it/s] 75%|███████▍ | 43017/57600 [7:33:21<2:32:21, 1.60it/s] 75%|███████▍ | 43018/57600 [7:33:22<2:35:57, 1.56it/s] 75%|███████▍ | 43019/57600 [7:33:23<2:37:25, 1.54it/s] 75%|███████▍ | 43020/57600 [7:33:23<2:33:16, 1.59it/s] {'loss': 1.1015, 'learning_rate': 3.2860627177700344e-07, 'epoch': 474.83} + 75%|███████▍ | 43020/57600 [7:33:23<2:33:16, 1.59it/s] 75%|███████▍ | 43021/57600 [7:33:24<2:38:13, 1.54it/s] 75%|███████▍ | 43022/57600 [7:33:25<2:37:32, 1.54it/s] 75%|███████▍ | 43023/57600 [7:33:25<2:32:22, 1.59it/s] 75%|███████▍ | 43024/57600 [7:33:26<2:30:31, 1.61it/s] 75%|███████�� | 43025/57600 [7:33:26<2:30:49, 1.61it/s] 75%|███████▍ | 43026/57600 [7:33:27<2:27:19, 1.65it/s] 75%|███████▍ | 43027/57600 [7:33:28<2:34:47, 1.57it/s] 75%|███████▍ | 43028/57600 [7:33:28<2:33:56, 1.58it/s] 75%|███████▍ | 43029/57600 [7:33:29<2:31:31, 1.60it/s] 75%|███████▍ | 43030/57600 [7:33:30<2:29:34, 1.62it/s] 75%|███████▍ | 43031/57600 [7:33:30<2:28:12, 1.64it/s] 75%|███████▍ | 43032/57600 [7:33:31<2:27:31, 1.65it/s] 75%|███████▍ | 43033/57600 [7:33:31<2:30:54, 1.61it/s] 75%|███████▍ | 43034/57600 [7:33:32<2:29:04, 1.63it/s] 75%|███████▍ | 43035/57600 [7:33:33<2:30:43, 1.61it/s] 75%|███████▍ | 43036/57600 [7:33:33<2:34:09, 1.57it/s] 75%|███████▍ | 43037/57600 [7:33:34<2:32:14, 1.59it/s] 75%|███████▍ | 43038/57600 [7:33:35<2:31:09, 1.61it/s] 75%|███████▍ | 43039/57600 [7:33:35<2:28:39, 1.63it/s] 75%|███████▍ | 43040/57600 [7:33:36<2:29:59, 1.62it/s] {'loss': 1.1511, 'learning_rate': 3.2829268292682925e-07, 'epoch': 475.06} + 75%|███████▍ | 43040/57600 [7:33:36<2:29:59, 1.62it/s] 75%|███████▍ | 43041/57600 [7:33:36<2:29:06, 1.63it/s] 75%|███████▍ | 43042/57600 [7:33:37<2:33:10, 1.58it/s] 75%|███████▍ | 43043/57600 [7:33:38<2:30:19, 1.61it/s] 75%|███████▍ | 43044/57600 [7:33:38<2:24:51, 1.67it/s] 75%|███████▍ | 43045/57600 [7:33:39<2:26:11, 1.66it/s] 75%|███████▍ | 43046/57600 [7:33:39<2:24:12, 1.68it/s] 75%|███████▍ | 43047/57600 [7:33:40<2:27:49, 1.64it/s] 75%|███████▍ | 43048/57600 [7:33:41<2:32:38, 1.59it/s] 75%|███████▍ | 43049/57600 [7:33:41<2:36:39, 1.55it/s] 75%|███████▍ | 43050/57600 [7:33:42<2:35:45, 1.56it/s] 75%|███████▍ | 43051/57600 [7:33:43<2:34:40, 1.57it/s] 75%|███████▍ | 43052/57600 [7:33:43<2:33:40, 1.58it/s] 75%|███████▍ | 43053/57600 [7:33:44<2:40:39, 1.51it/s] 75%|███████▍ | 43054/57600 [7:33:45<2:38:04, 1.53it/s] 75%|███████▍ | 43055/57600 [7:33:45<2:35:13, 1.56it/s] 75%|███████▍ | 43056/57600 [7:33:46<2:35:29, 1.56it/s] 75%|███████▍ | 43057/57600 [7:33:47<2:38:40, 1.53it/s] 75%|███████▍ | 43058/57600 [7:33:47<2:38:35, 1.53it/s] 75%|███████▍ | 43059/57600 [7:33:48<2:33:07, 1.58it/s] 75%|███████▍ | 43060/57600 [7:33:48<2:35:06, 1.56it/s] {'loss': 1.139, 'learning_rate': 3.2797909407665505e-07, 'epoch': 475.28} + 75%|███████▍ | 43060/57600 [7:33:48<2:35:06, 1.56it/s] 75%|███████▍ | 43061/57600 [7:33:49<2:33:01, 1.58it/s] 75%|███████▍ | 43062/57600 [7:33:50<2:33:02, 1.58it/s] 75%|███████▍ | 43063/57600 [7:33:50<2:33:05, 1.58it/s] 75%|███████▍ | 43064/57600 [7:33:51<2:31:07, 1.60it/s] 75%|███████▍ | 43065/57600 [7:33:52<2:28:01, 1.64it/s] 75%|███████▍ | 43066/57600 [7:33:52<2:25:20, 1.67it/s] 75%|███████▍ | 43067/57600 [7:33:53<2:30:51, 1.61it/s] 75%|███████▍ | 43068/57600 [7:33:53<2:33:11, 1.58it/s] 75%|███████▍ | 43069/57600 [7:33:54<2:31:29, 1.60it/s] 75%|███████▍ | 43070/57600 [7:33:55<2:33:55, 1.57it/s] 75%|███████▍ | 43071/57600 [7:33:55<2:28:00, 1.64it/s] 75%|███████▍ | 43072/57600 [7:33:56<2:27:05, 1.65it/s] 75%|███████▍ | 43073/57600 [7:33:56<2:30:20, 1.61it/s] 75%|███████▍ | 43074/57600 [7:33:57<2:30:12, 1.61it/s] 75%|███████▍ | 43075/57600 [7:33:58<2:28:02, 1.64it/s] 75%|███████▍ | 43076/57600 [7:33:58<2:25:06, 1.67it/s] 75%|███████▍ | 43077/57600 [7:33:59<2:22:05, 1.70it/s] 75%|███████▍ | 43078/57600 [7:33:59<2:22:51, 1.69it/s] 75%|███████▍ | 43079/57600 [7:34:00<2:25:32, 1.66it/s] 75%|███████▍ | 43080/57600 [7:34:01<2:28:38, 1.63it/s] {'loss': 1.1502, 'learning_rate': 3.276655052264808e-07, 'epoch': 475.5} + 75%|███████▍ | 43080/57600 [7:34:01<2:28:38, 1.63it/s] 75%|███████▍ | 43081/57600 [7:34:01<2:33:45, 1.57it/s] 75%|███████▍ | 43082/57600 [7:34:02<2:29:50, 1.61it/s] 75%|███████▍ | 43083/57600 [7:34:03<2:32:45, 1.58it/s] 75%|███████▍ | 43084/57600 [7:34:03<2:31:13, 1.60it/s] 75%|███████▍ | 43085/57600 [7:34:04<2:30:00, 1.61it/s] 75%|█��█████▍ | 43086/57600 [7:34:04<2:30:49, 1.60it/s] 75%|███████▍ | 43087/57600 [7:34:05<2:27:51, 1.64it/s] 75%|███████▍ | 43088/57600 [7:34:06<2:32:29, 1.59it/s] 75%|███████▍ | 43089/57600 [7:34:06<2:39:10, 1.52it/s] 75%|███████▍ | 43090/57600 [7:34:07<2:34:12, 1.57it/s] 75%|███████▍ | 43091/57600 [7:34:08<2:33:58, 1.57it/s] 75%|███████▍ | 43092/57600 [7:34:08<2:39:33, 1.52it/s] 75%|███████▍ | 43093/57600 [7:34:09<2:38:49, 1.52it/s] 75%|███████▍ | 43094/57600 [7:34:10<2:32:45, 1.58it/s] 75%|███████▍ | 43095/57600 [7:34:10<2:31:55, 1.59it/s] 75%|███████▍ | 43096/57600 [7:34:11<2:29:30, 1.62it/s] 75%|███████▍ | 43097/57600 [7:34:11<2:29:18, 1.62it/s] 75%|███████▍ | 43098/57600 [7:34:12<2:32:40, 1.58it/s] 75%|███████▍ | 43099/57600 [7:34:13<2:31:21, 1.60it/s] 75%|███████▍ | 43100/57600 [7:34:13<2:35:24, 1.55it/s] {'loss': 1.1129, 'learning_rate': 3.2735191637630666e-07, 'epoch': 475.72} + 75%|███████▍ | 43100/57600 [7:34:13<2:35:24, 1.55it/s] 75%|███████▍ | 43101/57600 [7:34:14<2:32:13, 1.59it/s] 75%|███████▍ | 43102/57600 [7:34:15<2:27:00, 1.64it/s] 75%|███████▍ | 43103/57600 [7:34:15<2:28:40, 1.63it/s] 75%|███████▍ | 43104/57600 [7:34:16<2:31:46, 1.59it/s] 75%|███████▍ | 43105/57600 [7:34:16<2:30:30, 1.61it/s] 75%|███████▍ | 43106/57600 [7:34:17<2:30:42, 1.60it/s] 75%|███████▍ | 43107/57600 [7:34:18<2:38:44, 1.52it/s] 75%|███████▍ | 43108/57600 [7:34:19<2:45:40, 1.46it/s] 75%|███████▍ | 43109/57600 [7:34:19<2:40:37, 1.50it/s] 75%|███████▍ | 43110/57600 [7:34:20<2:34:18, 1.56it/s] 75%|███████▍ | 43111/57600 [7:34:20<2:34:09, 1.57it/s] 75%|███████▍ | 43112/57600 [7:34:21<2:31:35, 1.59it/s] 75%|███████▍ | 43113/57600 [7:34:22<2:32:51, 1.58it/s] 75%|███████▍ | 43114/57600 [7:34:22<2:30:56, 1.60it/s] 75%|███████▍ | 43115/57600 [7:34:23<2:29:23, 1.62it/s] 75%|███████▍ | 43116/57600 [7:34:23<2:28:12, 1.63it/s] 75%|███████▍ | 43117/57600 [7:34:24<2:29:41, 1.61it/s] 75%|███████▍ | 43118/57600 [7:34:25<2:27:00, 1.64it/s] 75%|███████▍ | 43119/57600 [7:34:25<2:25:26, 1.66it/s] 75%|███████▍ | 43120/57600 [7:34:26<2:24:50, 1.67it/s] {'loss': 1.1405, 'learning_rate': 3.2703832752613236e-07, 'epoch': 475.94} + 75%|███████▍ | 43120/57600 [7:34:26<2:24:50, 1.67it/s] 75%|███████▍ | 43121/57600 [7:34:27<2:29:54, 1.61it/s] 75%|███████▍ | 43122/57600 [7:34:27<2:29:48, 1.61it/s] 75%|███████▍ | 43123/57600 [7:34:28<2:36:00, 1.55it/s] 75%|███████▍ | 43124/57600 [7:34:28<2:31:40, 1.59it/s] 75%|███████▍ | 43125/57600 [7:34:29<2:31:43, 1.59it/s] 75%|███████▍ | 43126/57600 [7:34:30<2:37:11, 1.53it/s] 75%|███████▍ | 43127/57600 [7:34:30<2:30:55, 1.60it/s] 75%|███████▍ | 43128/57600 [7:34:31<2:27:10, 1.64it/s] 75%|███████▍ | 43129/57600 [7:34:32<2:26:08, 1.65it/s] 75%|███████▍ | 43130/57600 [7:34:32<2:23:13, 1.68it/s] 75%|███████▍ | 43131/57600 [7:34:33<2:24:37, 1.67it/s] 75%|███████▍ | 43132/57600 [7:34:33<2:30:28, 1.60it/s] 75%|███████▍ | 43133/57600 [7:34:34<2:35:12, 1.55it/s] 75%|███████▍ | 43134/57600 [7:34:35<2:32:22, 1.58it/s] 75%|███████▍ | 43135/57600 [7:34:35<2:36:41, 1.54it/s] 75%|███████▍ | 43136/57600 [7:34:36<2:32:13, 1.58it/s] 75%|███████▍ | 43137/57600 [7:34:37<2:34:59, 1.56it/s] 75%|███████▍ | 43138/57600 [7:34:37<2:29:31, 1.61it/s] 75%|███████▍ | 43139/57600 [7:34:38<2:26:45, 1.64it/s] 75%|███████▍ | 43140/57600 [7:34:38<2:27:42, 1.63it/s] {'loss': 1.1517, 'learning_rate': 3.2672473867595816e-07, 'epoch': 476.16} + 75%|███████▍ | 43140/57600 [7:34:38<2:27:42, 1.63it/s] 75%|███████▍ | 43141/57600 [7:34:39<2:33:22, 1.57it/s] 75%|███████▍ | 43142/57600 [7:34:40<2:30:27, 1.60it/s] 75%|███████▍ | 43143/57600 [7:34:40<2:32:03, 1.58it/s] 75%|███████▍ | 43144/57600 [7:34:41<2:36:03, 1.54it/s] 75%|███████▍ | 43145/57600 [7:34:42<2:31:54, 1.59it/s] 75%|███████▍ | 43146/57600 [7:34:42<2:27:46, 1.63it/s] 75%|███████▍ | 43147/57600 [7:34:43<2:27:02, 1.64it/s] 75%|███████▍ | 43148/57600 [7:34:43<2:31:21, 1.59it/s] 75%|███████▍ | 43149/57600 [7:34:44<2:32:00, 1.58it/s] 75%|███████▍ | 43150/57600 [7:34:45<2:38:37, 1.52it/s] 75%|███████▍ | 43151/57600 [7:34:45<2:33:34, 1.57it/s] 75%|███████▍ | 43152/57600 [7:34:46<2:30:00, 1.61it/s] 75%|███████▍ | 43153/57600 [7:34:47<2:37:00, 1.53it/s] 75%|███████▍ | 43154/57600 [7:34:47<2:39:12, 1.51it/s] 75%|███████▍ | 43155/57600 [7:34:48<2:30:23, 1.60it/s] 75%|███████▍ | 43156/57600 [7:34:49<2:30:15, 1.60it/s] 75%|███████▍ | 43157/57600 [7:34:49<2:33:42, 1.57it/s] 75%|███████▍ | 43158/57600 [7:34:50<2:37:53, 1.52it/s] 75%|███████▍ | 43159/57600 [7:34:51<2:41:38, 1.49it/s] 75%|███████▍ | 43160/57600 [7:34:51<2:41:15, 1.49it/s] {'loss': 1.1224, 'learning_rate': 3.264111498257839e-07, 'epoch': 476.38} + 75%|███████▍ | 43160/57600 [7:34:51<2:41:15, 1.49it/s] 75%|███████▍ | 43161/57600 [7:34:52<2:37:07, 1.53it/s] 75%|███████▍ | 43162/57600 [7:34:53<2:33:31, 1.57it/s] 75%|███████▍ | 43163/57600 [7:34:53<2:33:30, 1.57it/s] 75%|███████▍ | 43164/57600 [7:34:54<2:32:52, 1.57it/s] 75%|███████▍ | 43165/57600 [7:34:54<2:27:43, 1.63it/s] 75%|███████▍ | 43166/57600 [7:34:55<2:32:29, 1.58it/s] 75%|███████▍ | 43167/57600 [7:34:56<2:30:27, 1.60it/s] 75%|███████▍ | 43168/57600 [7:34:56<2:30:25, 1.60it/s] 75%|███████▍ | 43169/57600 [7:34:57<2:27:42, 1.63it/s] 75%|███████▍ | 43170/57600 [7:34:58<2:30:53, 1.59it/s] 75%|███████▍ | 43171/57600 [7:34:58<2:30:46, 1.59it/s] 75%|███████▍ | 43172/57600 [7:34:59<2:33:14, 1.57it/s] 75%|███████▍ | 43173/57600 [7:34:59<2:33:53, 1.56it/s] 75%|███████▍ | 43174/57600 [7:35:00<2:32:13, 1.58it/s] 75%|███████▍ | 43175/57600 [7:35:01<2:34:16, 1.56it/s] 75%|███████▍ | 43176/57600 [7:35:01<2:29:54, 1.60it/s] 75%|███████▍ | 43177/57600 [7:35:02<2:29:44, 1.61it/s] 75%|███████▍ | 43178/57600 [7:35:03<2:30:35, 1.60it/s] 75%|███████▍ | 43179/57600 [7:35:03<2:28:05, 1.62it/s] 75%|███████▍ | 43180/57600 [7:35:04<2:27:51, 1.63it/s] {'loss': 1.1472, 'learning_rate': 3.260975609756098e-07, 'epoch': 476.6} + 75%|███████▍ | 43180/57600 [7:35:04<2:27:51, 1.63it/s] 75%|███████▍ | 43181/57600 [7:35:04<2:29:28, 1.61it/s] 75%|███████▍ | 43182/57600 [7:35:05<2:27:25, 1.63it/s] 75%|███████▍ | 43183/57600 [7:35:06<2:27:36, 1.63it/s] 75%|███████▍ | 43184/57600 [7:35:06<2:30:55, 1.59it/s] 75%|███████▍ | 43185/57600 [7:35:07<2:32:34, 1.57it/s] 75%|███████▍ | 43186/57600 [7:35:08<2:27:55, 1.62it/s] 75%|███████▍ | 43187/57600 [7:35:08<2:24:16, 1.66it/s] 75%|███████▍ | 43188/57600 [7:35:09<2:29:55, 1.60it/s] 75%|███████▍ | 43189/57600 [7:35:09<2:26:02, 1.64it/s] 75%|███████▍ | 43190/57600 [7:35:10<2:24:37, 1.66it/s] 75%|███████▍ | 43191/57600 [7:35:11<2:25:44, 1.65it/s] 75%|███████▍ | 43192/57600 [7:35:11<2:29:15, 1.61it/s] 75%|███████▍ | 43193/57600 [7:35:12<2:32:15, 1.58it/s] 75%|███████▍ | 43194/57600 [7:35:12<2:33:04, 1.57it/s] 75%|███████▍ | 43195/57600 [7:35:13<2:31:58, 1.58it/s] 75%|███████▍ | 43196/57600 [7:35:14<2:34:39, 1.55it/s] 75%|███████▍ | 43197/57600 [7:35:14<2:32:06, 1.58it/s] 75%|███████▍ | 43198/57600 [7:35:15<2:32:51, 1.57it/s] 75%|███████▍ | 43199/57600 [7:35:16<2:35:23, 1.54it/s] 75%|███████▌ | 43200/57600 [7:35:16<2:36:38, 1.53it/s] {'loss': 1.1355, 'learning_rate': 3.257839721254356e-07, 'epoch': 476.82} + 75%|███████▌ | 43200/57600 [7:35:16<2:36:38, 1.53it/s]Generation Kwargs: +{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5} + + 0%| | 0/6 [00:00> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co./docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41. +Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2} + 75%|███████▌ | 43201/57600 [7:35:40<30:36:18, 7.65s/it] 75%|███████▌ | 43202/57600 [7:35:41<22:12:05, 5.55s/it] 75%|███████▌ | 43203/57600 [7:35:42<16:21:47, 4.09s/it] 75%|███████▌ | 43204/57600 [7:35:42<12:21:43, 3.09s/it] 75%|███████▌ | 43205/57600 [7:35:43<9:35:48, 2.40s/it] 75%|███████▌ | 43206/57600 [7:35:44<7:38:28, 1.91s/it] 75%|███████▌ | 43207/57600 [7:35:45<6:10:22, 1.54s/it] 75%|███████▌ | 43208/57600 [7:35:45<5:06:29, 1.28s/it] 75%|███████▌ | 43209/57600 [7:35:46<4:21:45, 1.09s/it] 75%|███████▌ | 43210/57600 [7:35:47<3:50:28, 1.04it/s] 75%|███████▌ | 43211/57600 [7:35:47<3:29:22, 1.15it/s] 75%|███████▌ | 43212/57600 [7:35:48<3:15:58, 1.22it/s] 75%|███████▌ | 43213/57600 [7:35:49<3:02:13, 1.32it/s] 75%|███████▌ | 43214/57600 [7:35:49<2:56:10, 1.36it/s] 75%|███████▌ | 43215/57600 [7:35:50<2:51:23, 1.40it/s] 75%|███████▌ | 43216/57600 [7:35:51<2:46:12, 1.44it/s]/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock. + self.pid = os.fork() + 75%|███████▌ | 43217/57600 [7:35:51<2:49:51, 1.41it/s] 75%|███████▌ | 43218/57600 [7:35:52<2:45:34, 1.45it/s] 75%|███████▌ | 43219/57600 [7:35:53<2:48:04, 1.43it/s] 75%|███████▌ | 43220/57600 [7:35:53<2:48:39, 1.42it/s] {'loss': 1.1215, 'learning_rate': 3.254703832752613e-07, 'epoch': 477.04} + 75%|███████▌ | 43220/57600 [7:35:53<2:48:39, 1.42it/s] 75%|███████▌ | 43221/57600 [7:35:54<2:45:27, 1.45it/s] 75%|███████▌ | 43222/57600 [7:35:55<2:39:45, 1.50it/s] 75%|███████▌ | 43223/57600 [7:35:55<2:32:34, 1.57it/s] 75%|███████▌ | 43224/57600 [7:35:56<2:36:07, 1.53it/s] 75%|███████▌ | 43225/57600 [7:35:57<2:41:47, 1.48it/s] 75%|███████▌ | 43226/57600 [7:35:57<2:44:36, 1.46it/s] 75%|███████▌ | 43227/57600 [7:35:58<2:41:58, 1.48it/s] 75%|███████▌ | 43228/57600 [7:35:59<2:44:09, 1.46it/s] 75%|███████▌ | 43229/57600 [7:35:59<2:39:40, 1.50it/s] 75%|███████▌ | 43230/57600 [7:36:00<2:37:34, 1.52it/s] 75%|███████▌ | 43231/57600 [7:36:01<2:37:12, 1.52it/s] 75%|███████▌ | 43232/57600 [7:36:01<2:41:15, 1.48it/s] 75%|███████▌ | 43233/57600 [7:36:02<2:40:46, 1.49it/s] 75%|███████▌ | 43234/57600 [7:36:03<2:39:41, 1.50it/s] 75%|███████▌ | 43235/57600 [7:36:03<2:38:37, 1.51it/s] 75%|███████▌ | 43236/57600 [7:36:04<2:38:16, 1.51it/s] 75%|███████▌ | 43237/57600 [7:36:05<2:38:17, 1.51it/s] 75%|███████▌ | 43238/57600 [7:36:05<2:35:04, 1.54it/s] 75%|███████▌ | 43239/57600 [7:36:06<2:41:43, 1.48it/s] 75%|███████▌ | 43240/57600 [7:36:07<2:38:15, 1.51it/s] {'loss': 1.0938, 'learning_rate': 3.2515679442508714e-07, 'epoch': 477.26} + 75%|███████▌ | 43240/57600 [7:36:07<2:38:15, 1.51it/s] 75%|███████▌ | 43241/57600 [7:36:07<2:41:03, 1.49it/s] 75%|███████▌ | 43242/57600 [7:36:08<2:41:24, 1.48it/s] 75%|███████▌ | 43243/57600 [7:36:09<2:35:48, 1.54it/s] 75%|███████▌ | 43244/57600 [7:36:09<2:36:10, 1.53it/s] 75%|███████▌ | 43245/57600 [7:36:10<2:32:04, 1.57it/s] 75%|███████▌ | 43246/57600 [7:36:11<2:28:57, 1.61it/s] 75%|███████▌ | 43247/57600 [7:36:11<2:26:05, 1.64it/s] 75%|███████▌ | 43248/57600 [7:36:12<2:26:45, 1.63it/s] 75%|███████▌ | 43249/57600 [7:36:12<2:28:06, 1.61it/s] 75%|███████▌ | 43250/57600 [7:36:13<2:27:23, 1.62it/s] 75%|███████▌ | 43251/57600 [7:36:14<2:36:50, 1.52it/s] 75%|███████▌ | 43252/57600 [7:36:14<2:36:00, 1.53it/s] 75%|███████▌ | 43253/57600 [7:36:15<2:39:20, 1.50it/s] 75%|███████▌ | 43254/57600 [7:36:16<2:36:16, 1.53it/s] 75%|███████▌ | 43255/57600 [7:36:16<2:43:25, 1.46it/s] 75%|███████▌ | 43256/57600 [7:36:17<2:44:07, 1.46it/s] 75%|███████▌ | 43257/57600 [7:36:18<2:45:12, 1.45it/s] 75%|███████▌ | 43258/57600 [7:36:19<2:51:52, 1.39it/s] 75%|███████▌ | 43259/57600 [7:36:19<2:48:01, 1.42it/s] 75%|███████▌ | 43260/57600 [7:36:20<2:44:07, 1.46it/s] {'loss': 1.1255, 'learning_rate': 3.248432055749129e-07, 'epoch': 477.48} + 75%|███████▌ | 43260/57600 [7:36:20<2:44:07, 1.46it/s] 75%|███████▌ | 43261/57600 [7:36:21<2:42:17, 1.47it/s] 75%|███████▌ | 43262/57600 [7:36:21<2:39:36, 1.50it/s] 75%|███████▌ | 43263/57600 [7:36:22<2:37:12, 1.52it/s] \ No newline at end of file