diff --git "a/run-2024-10-28T15:22:08+00:00.log" "b/run-2024-10-28T15:22:08+00:00.log" --- "a/run-2024-10-28T15:22:08+00:00.log" +++ "b/run-2024-10-28T15:22:08+00:00.log" @@ -2175,4 +2175,1069 @@ Non-default generation parameters: {'max_length': 200, 'early_stopping': True, ' 81%|████████▏ | 50299/61904 [3:25:39<801:28:38, 248.63s/it] 81%|████████▏ | 50300/61904 [3:25:40<562:17:08, 174.44s/it] {'loss': 2.4458, 'learning_rate': 1.1880591209646052e-07, 'epoch': 13.0} 81%|████████▏ | 50300/61904 [3:25:40<562:17:08, 174.44s/it] 81%|████████▏ | 50301/61904 [3:25:41<395:00:00, 122.55s/it] 81%|████████▏ | 50302/61904 [3:25:43<277:48:17, 86.20s/it] 81%|████████▏ | 50303/61904 [3:25:44<195:50:25, 60.77s/it] 81%|████████▏ | 50304/61904 [3:25:46<138:34:48, 43.01s/it] 81%|████████▏ | 50305/61904 [3:25:47<98:20:57, 30.52s/it] 81%|████████▏ | 50306/61904 [3:25:49<70:17:02, 21.82s/it] 81%|████████▏ | 50307/61904 [3:25:50<50:36:28, 15.71s/it] 81%|████████▏ | 50308/61904 [3:25:52<37:05:05, 11.51s/it] 81%|████████▏ | 50309/61904 [3:25:53<27:20:55, 8.49s/it] 81%|████████▏ | 50310/61904 [3:25:55<20:43:34, 6.44s/it] 81%|████████▏ | 50311/61904 [3:25:56<15:51:23, 4.92s/it] 81%|████████▏ | 50312/61904 [3:25:58<12:40:13, 3.93s/it] 81%|████████▏ | 50313/61904 [3:25:59<10:05:09, 3.13s/it] 81%|████████▏ | 50314/61904 [3:26:01<8:21:01, 2.59s/it] 81%|████████▏ | 50315/61904 [3:26:02<7:11:31, 2.23s/it] 81%|████████▏ | 50316/61904 [3:26:03<6:28:10, 2.01s/it] 81%|████████▏ | 50317/61904 [3:26:05<5:57:31, 1.85s/it] 81%|████████▏ | 50318/61904 [3:26:06<5:26:54, 1.69s/it] 81%|████████▏ | 50319/61904 [3:26:08<5:07:49, 1.59s/it] 81%|████████▏ | 50320/61904 [3:26:09<4:54:45, 1.53s/it] {'loss': 2.4137, 'learning_rate': 1.1877349928691818e-07, 'epoch': 13.01} 81%|████████▏ | 50320/61904 [3:26:09<4:54:45, 1.53s/it] 81%|████████▏ | 50321/61904 [3:26:10<4:50:45, 1.51s/it] 81%|████████▏ | 50322/61904 [3:26:12<4:58:52, 1.55s/it] 81%|████████▏ | 50323/61904 [3:26:13<4:52:51, 1.52s/it] 81%|████████▏ | 50324/61904 [3:26:15<4:43:36, 1.47s/it] 81%|████████▏ | 50325/61904 [3:26:16<4:43:21, 1.47s/it] 81%|████████▏ | 50326/61904 [3:26:18<4:30:04, 1.40s/it] 81%|████████▏ | 50327/61904 [3:26:19<4:27:21, 1.39s/it] 81%|████████▏ | 50328/61904 [3:26:20<4:33:28, 1.42s/it] 81%|████████▏ | 50329/61904 [3:26:22<4:44:52, 1.48s/it] 81%|████████▏ | 50330/61904 [3:26:23<4:39:17, 1.45s/it] 81%|████████▏ | 50331/61904 [3:26:25<4:29:00, 1.39s/it] 81%|████████▏ | 50332/61904 [3:26:26<4:35:12, 1.43s/it] 81%|████████▏ | 50333/61904 [3:26:27<4:29:27, 1.40s/it] 81%|████████▏ | 50334/61904 [3:26:29<4:30:29, 1.40s/it] 81%|████████▏ | 50335/61904 [3:26:30<4:32:54, 1.42s/it] 81%|████████▏ | 50336/61904 [3:26:32<4:30:00, 1.40s/it] 81%|████████▏ | 50337/61904 [3:26:33<4:28:53, 1.39s/it] 81%|████████▏ | 50338/61904 [3:26:34<4:28:09, 1.39s/it] 81%|████████▏ | 50339/61904 [3:26:36<4:24:50, 1.37s/it] 81%|████████▏ | 50340/61904 [3:26:37<4:30:35, 1.40s/it] {'loss': 2.4151, 'learning_rate': 1.1874108647737586e-07, 'epoch': 13.01} - 81%|████████▏ | 50340/61904 [3:26:37<4:30:35, 1.40s/it] 81%|████████▏ | 50341/61904 [3:26:39<4:35:51, 1.43s/it] 81%|████████▏ | 50342/61904 [3:26:40<4:39:49, 1.45s/it] 81%|████████▏ | 50343/61904 [3:26:42<4:40:57, 1.46s/it] 81%|████████▏ | 50344/61904 [3:26:43<4:39:15, 1.45s/it] \ No newline at end of file + 81%|████████▏ | 50340/61904 [3:26:37<4:30:35, 1.40s/it] 81%|████████▏ | 50341/61904 [3:26:39<4:35:51, 1.43s/it] 81%|████████▏ | 50342/61904 [3:26:40<4:39:49, 1.45s/it] 81%|████████▏ | 50343/61904 [3:26:42<4:40:57, 1.46s/it] 81%|████████▏ | 50344/61904 [3:26:43<4:39:15, 1.45s/it] 81%|████████▏ | 50345/61904 [3:26:45<4:44:38, 1.48s/it] 81%|████████▏ | 50346/61904 [3:26:46<4:39:47, 1.45s/it] 81%|████████▏ | 50347/61904 [3:26:48<4:38:41, 1.45s/it] 81%|████████▏ | 50348/61904 [3:26:49<4:39:41, 1.45s/it] 81%|████████▏ | 50349/61904 [3:26:50<4:34:51, 1.43s/it] 81%|████████▏ | 50350/61904 [3:26:52<4:43:31, 1.47s/it] 81%|████████▏ | 50351/61904 [3:26:53<4:37:19, 1.44s/it] 81%|████████▏ | 50352/61904 [3:26:55<4:37:09, 1.44s/it] 81%|████████▏ | 50353/61904 [3:26:56<4:38:24, 1.45s/it] 81%|████████▏ | 50354/61904 [3:26:58<4:35:26, 1.43s/it] 81%|████████▏ | 50355/61904 [3:26:59<4:52:19, 1.52s/it] 81%|████████▏ | 50356/61904 [3:27:01<4:40:38, 1.46s/it] 81%|████████▏ | 50357/61904 [3:27:02<4:35:36, 1.43s/it] 81%|████████▏ | 50358/61904 [3:27:03<4:33:32, 1.42s/it] 81%|████████▏ | 50359/61904 [3:27:05<4:28:19, 1.39s/it] 81%|████████▏ | 50360/61904 [3:27:06<4:33:39, 1.42s/it] {'loss': 2.4124, 'learning_rate': 1.1870867366783353e-07, 'epoch': 13.02} + 81%|████████▏ | 50360/61904 [3:27:06<4:33:39, 1.42s/it] 81%|████████▏ | 50361/61904 [3:27:08<4:30:40, 1.41s/it] 81%|████████▏ | 50362/61904 [3:27:09<4:33:33, 1.42s/it] 81%|████████▏ | 50363/61904 [3:27:10<4:32:10, 1.41s/it] 81%|████████▏ | 50364/61904 [3:27:12<4:28:37, 1.40s/it] 81%|████████▏ | 50365/61904 [3:27:13<4:34:51, 1.43s/it] 81%|████████▏ | 50366/61904 [3:27:15<4:34:22, 1.43s/it] 81%|████████▏ | 50367/61904 [3:27:16<4:35:39, 1.43s/it] 81%|████████▏ | 50368/61904 [3:27:18<4:31:43, 1.41s/it] 81%|████████▏ | 50369/61904 [3:27:19<4:31:00, 1.41s/it] 81%|████████▏ | 50370/61904 [3:27:20<4:25:28, 1.38s/it] 81%|████████▏ | 50371/61904 [3:27:22<4:26:57, 1.39s/it] 81%|████████▏ | 50372/61904 [3:27:23<4:34:03, 1.43s/it] 81%|████████▏ | 50373/61904 [3:27:25<4:54:52, 1.53s/it] 81%|████████▏ | 50374/61904 [3:27:26<4:52:11, 1.52s/it] 81%|████████▏ | 50375/61904 [3:27:28<4:40:02, 1.46s/it] 81%|████████▏ | 50376/61904 [3:27:29<4:34:29, 1.43s/it] 81%|████████▏ | 50377/61904 [3:27:31<4:37:39, 1.45s/it] 81%|████████▏ | 50378/61904 [3:27:32<4:36:36, 1.44s/it] 81%|████████▏ | 50379/61904 [3:27:33<4:33:55, 1.43s/it] 81%|████████▏ | 50380/61904 [3:27:35<4:30:47, 1.41s/it] {'loss': 2.4259, 'learning_rate': 1.1867626085829119e-07, 'epoch': 13.02} + 81%|████████▏ | 50380/61904 [3:27:35<4:30:47, 1.41s/it] 81%|████████▏ | 50381/61904 [3:27:36<4:30:50, 1.41s/it] 81%|████████▏ | 50382/61904 [3:27:38<4:31:55, 1.42s/it] 81%|████████▏ | 50383/61904 [3:27:39<4:26:12, 1.39s/it] 81%|████████▏ | 50384/61904 [3:27:40<4:32:18, 1.42s/it] 81%|████████▏ | 50385/61904 [3:27:42<4:21:36, 1.36s/it] 81%|████████▏ | 50386/61904 [3:27:43<4:28:13, 1.40s/it] 81%|████████▏ | 50387/61904 [3:27:45<4:27:40, 1.39s/it] 81%|████████▏ | 50388/61904 [3:27:46<4:31:16, 1.41s/it] 81%|████████▏ | 50389/61904 [3:27:47<4:26:26, 1.39s/it] 81%|████████▏ | 50390/61904 [3:27:49<4:26:18, 1.39s/it] 81%|████████▏ | 50391/61904 [3:27:50<4:35:51, 1.44s/it] 81%|████████▏ | 50392/61904 [3:27:52<4:26:39, 1.39s/it] 81%|████████▏ | 50393/61904 [3:27:53<4:27:13, 1.39s/it] 81%|████████▏ | 50394/61904 [3:27:54<4:28:32, 1.40s/it] 81%|████████▏ | 50395/61904 [3:27:56<4:26:57, 1.39s/it] 81%|████████▏ | 50396/61904 [3:27:57<4:37:07, 1.44s/it] 81%|████████▏ | 50397/61904 [3:27:59<4:49:00, 1.51s/it] 81%|████████▏ | 50398/61904 [3:28:00<4:46:41, 1.50s/it] 81%|████████▏ | 50399/61904 [3:28:02<4:45:32, 1.49s/it] 81%|████████▏ | 50400/61904 [3:28:03<4:38:01, 1.45s/it] {'loss': 2.4933, 'learning_rate': 1.1864384804874886e-07, 'epoch': 13.03} + 81%|████████▏ | 50400/61904 [3:28:03<4:38:01, 1.45s/it] 81%|████████▏ | 50401/61904 [3:28:05<4:27:43, 1.40s/it] 81%|████████▏ | 50402/61904 [3:28:06<4:44:53, 1.49s/it] 81%|████████▏ | 50403/61904 [3:28:08<4:35:18, 1.44s/it] 81%|████████▏ | 50404/61904 [3:28:09<4:33:34, 1.43s/it] 81%|████████▏ | 50405/61904 [3:28:10<4:35:00, 1.43s/it] 81%|████████▏ | 50406/61904 [3:28:12<4:34:16, 1.43s/it] 81%|████████▏ | 50407/61904 [3:28:13<4:28:58, 1.40s/it] 81%|████████▏ | 50408/61904 [3:28:15<4:30:22, 1.41s/it] 81%|████████▏ | 50409/61904 [3:28:16<4:30:25, 1.41s/it] 81%|████████▏ | 50410/61904 [3:28:17<4:29:13, 1.41s/it] 81%|████████▏ | 50411/61904 [3:28:19<4:27:26, 1.40s/it] 81%|████████▏ | 50412/61904 [3:28:20<4:22:51, 1.37s/it] 81%|████████▏ | 50413/61904 [3:28:22<4:23:06, 1.37s/it] 81%|████████▏ | 50414/61904 [3:28:23<4:15:02, 1.33s/it] 81%|████████▏ | 50415/61904 [3:28:24<4:13:33, 1.32s/it] 81%|████████▏ | 50416/61904 [3:28:25<4:20:31, 1.36s/it] 81%|████████▏ | 50417/61904 [3:28:27<4:15:53, 1.34s/it] 81%|████████▏ | 50418/61904 [3:28:28<4:25:00, 1.38s/it] 81%|████████▏ | 50419/61904 [3:28:30<4:21:01, 1.36s/it] 81%|████████▏ | 50420/61904 [3:28:31<4:26:18, 1.39s/it] {'loss': 2.4579, 'learning_rate': 1.1861143523920653e-07, 'epoch': 13.03} + 81%|████████▏ | 50420/61904 [3:28:31<4:26:18, 1.39s/it] 81%|████████▏ | 50421/61904 [3:28:32<4:25:04, 1.39s/it] 81%|████████▏ | 50422/61904 [3:28:34<4:28:09, 1.40s/it] 81%|████████▏ | 50423/61904 [3:28:35<4:32:01, 1.42s/it] 81%|████████▏ | 50424/61904 [3:28:37<4:24:02, 1.38s/it] 81%|████████▏ | 50425/61904 [3:28:38<4:16:50, 1.34s/it] 81%|████████▏ | 50426/61904 [3:28:39<4:12:23, 1.32s/it] 81%|████████▏ | 50427/61904 [3:28:40<4:11:22, 1.31s/it] 81%|████████▏ | 50428/61904 [3:28:42<4:19:59, 1.36s/it] 81%|████████▏ | 50429/61904 [3:28:43<4:21:16, 1.37s/it] 81%|████████▏ | 50430/61904 [3:28:45<4:27:05, 1.40s/it] 81%|████████▏ | 50431/61904 [3:28:46<4:27:27, 1.40s/it] 81%|████████▏ | 50432/61904 [3:28:47<4:20:55, 1.36s/it] 81%|████████▏ | 50433/61904 [3:28:49<4:19:36, 1.36s/it] 81%|████████▏ | 50434/61904 [3:28:50<4:18:14, 1.35s/it] 81%|████████▏ | 50435/61904 [3:28:51<4:16:54, 1.34s/it] 81%|████████▏ | 50436/61904 [3:28:53<4:18:20, 1.35s/it] 81%|████████▏ | 50437/61904 [3:28:54<4:24:55, 1.39s/it] 81%|████████▏ | 50438/61904 [3:28:56<4:22:04, 1.37s/it] 81%|████████▏ | 50439/61904 [3:28:57<4:18:00, 1.35s/it] 81%|████████▏ | 50440/61904 [3:28:58<4:10:35, 1.31s/it] {'loss': 2.4766, 'learning_rate': 1.185790224296642e-07, 'epoch': 13.04} + 81%|████████▏ | 50440/61904 [3:28:58<4:10:35, 1.31s/it] 81%|████████▏ | 50441/61904 [3:28:59<4:13:15, 1.33s/it] 81%|████████▏ | 50442/61904 [3:29:01<4:09:08, 1.30s/it] 81%|████████▏ | 50443/61904 [3:29:02<4:18:44, 1.35s/it] 81%|████████▏ | 50444/61904 [3:29:04<4:19:36, 1.36s/it] 81%|████████▏ | 50445/61904 [3:29:05<4:24:10, 1.38s/it] 81%|████████▏ | 50446/61904 [3:29:06<4:22:15, 1.37s/it] 81%|████████▏ | 50447/61904 [3:29:08<4:24:12, 1.38s/it] 81%|████████▏ | 50448/61904 [3:29:09<4:22:34, 1.38s/it] 81%|████████▏ | 50449/61904 [3:29:10<4:20:02, 1.36s/it] 81%|████████▏ | 50450/61904 [3:29:12<4:14:02, 1.33s/it] 81%|████████▏ | 50451/61904 [3:29:13<4:15:07, 1.34s/it] 82%|████████▏ | 50452/61904 [3:29:14<4:12:55, 1.33s/it] 82%|████████▏ | 50453/61904 [3:29:16<4:16:30, 1.34s/it] 82%|████████▏ | 50454/61904 [3:29:17<4:13:05, 1.33s/it] 82%|████████▏ | 50455/61904 [3:29:18<4:16:44, 1.35s/it] 82%|████████▏ | 50456/61904 [3:29:20<4:25:40, 1.39s/it] 82%|████████▏ | 50457/61904 [3:29:21<4:26:46, 1.40s/it] 82%|████████▏ | 50458/61904 [3:29:23<4:27:02, 1.40s/it] 82%|████████▏ | 50459/61904 [3:29:24<4:21:21, 1.37s/it] 82%|████████▏ | 50460/61904 [3:29:25<4:15:57, 1.34s/it] {'loss': 2.4438, 'learning_rate': 1.1854660962012187e-07, 'epoch': 13.04} + 82%|████████▏ | 50460/61904 [3:29:25<4:15:57, 1.34s/it] 82%|████████▏ | 50461/61904 [3:29:27<4:20:21, 1.37s/it] 82%|████████▏ | 50462/61904 [3:29:28<4:11:45, 1.32s/it] 82%|████████▏ | 50463/61904 [3:29:29<4:23:53, 1.38s/it] 82%|████████▏ | 50464/61904 [3:29:31<4:17:28, 1.35s/it] 82%|████████▏ | 50465/61904 [3:29:32<4:18:09, 1.35s/it] 82%|████████▏ | 50466/61904 [3:29:34<4:26:10, 1.40s/it] 82%|████████▏ | 50467/61904 [3:29:35<4:27:14, 1.40s/it] 82%|████████▏ | 50468/61904 [3:29:37<4:36:48, 1.45s/it] 82%|████████▏ | 50469/61904 [3:29:38<4:38:58, 1.46s/it] 82%|████████▏ | 50470/61904 [3:29:40<4:36:56, 1.45s/it] 82%|████████▏ | 50471/61904 [3:29:41<4:29:31, 1.41s/it] 82%|████████▏ | 50472/61904 [3:29:42<4:34:26, 1.44s/it] 82%|████████▏ | 50473/61904 [3:29:44<4:28:42, 1.41s/it] 82%|████████▏ | 50474/61904 [3:29:45<4:26:28, 1.40s/it] 82%|████████▏ | 50475/61904 [3:29:46<4:19:57, 1.36s/it] 82%|████████▏ | 50476/61904 [3:29:48<4:24:39, 1.39s/it] 82%|████████▏ | 50477/61904 [3:29:49<4:19:10, 1.36s/it] 82%|████████▏ | 50478/61904 [3:29:51<4:34:15, 1.44s/it] 82%|████████▏ | 50479/61904 [3:29:52<4:35:03, 1.44s/it] 82%|████████▏ | 50480/61904 [3:29:54<4:36:10, 1.45s/it] {'loss': 2.4372, 'learning_rate': 1.1851419681057953e-07, 'epoch': 13.05} + 82%|████████▏ | 50480/61904 [3:29:54<4:36:10, 1.45s/it] 82%|████████▏ | 50481/61904 [3:29:55<4:26:58, 1.40s/it] 82%|████████▏ | 50482/61904 [3:29:56<4:26:41, 1.40s/it] 82%|████████▏ | 50483/61904 [3:29:58<4:21:45, 1.38s/it] 82%|████████▏ | 50484/61904 [3:29:59<4:24:56, 1.39s/it] 82%|████████▏ | 50485/61904 [3:30:01<4:43:22, 1.49s/it] 82%|████████▏ | 50486/61904 [3:30:02<4:30:27, 1.42s/it] 82%|████████▏ | 50487/61904 [3:30:03<4:29:15, 1.42s/it] 82%|████████▏ | 50488/61904 [3:30:05<4:30:45, 1.42s/it] 82%|████████▏ | 50489/61904 [3:30:06<4:28:18, 1.41s/it] 82%|████████▏ | 50490/61904 [3:30:08<4:29:07, 1.41s/it] 82%|████████▏ | 50491/61904 [3:30:09<4:30:02, 1.42s/it] 82%|████████▏ | 50492/61904 [3:30:10<4:27:00, 1.40s/it] 82%|████████▏ | 50493/61904 [3:30:12<4:30:43, 1.42s/it] 82%|████████▏ | 50494/61904 [3:30:14<4:43:29, 1.49s/it] 82%|████████▏ | 50495/61904 [3:30:15<4:30:53, 1.42s/it] 82%|████████▏ | 50496/61904 [3:30:16<4:30:32, 1.42s/it] 82%|████████▏ | 50497/61904 [3:30:18<4:23:49, 1.39s/it] 82%|████████▏ | 50498/61904 [3:30:19<4:13:31, 1.33s/it] 82%|████████▏ | 50499/61904 [3:30:20<4:11:32, 1.32s/it] 82%|████████▏ | 50500/61904 [3:30:22<4:14:54, 1.34s/it] {'loss': 2.4097, 'learning_rate': 1.184817840010372e-07, 'epoch': 13.05} + 82%|████████▏ | 50500/61904 [3:30:22<4:14:54, 1.34s/it] 82%|████████▏ | 50501/61904 [3:30:23<4:22:57, 1.38s/it] 82%|████████▏ | 50502/61904 [3:30:25<4:32:16, 1.43s/it] 82%|████████▏ | 50503/61904 [3:30:26<4:23:06, 1.38s/it] 82%|████████▏ | 50504/61904 [3:30:27<4:26:45, 1.40s/it] 82%|████████▏ | 50505/61904 [3:30:29<4:19:56, 1.37s/it] 82%|████████▏ | 50506/61904 [3:30:30<4:29:43, 1.42s/it] 82%|████████▏ | 50507/61904 [3:30:31<4:23:29, 1.39s/it] 82%|████████▏ | 50508/61904 [3:30:33<4:27:32, 1.41s/it] 82%|████████▏ | 50509/61904 [3:30:34<4:18:57, 1.36s/it] 82%|████████▏ | 50510/61904 [3:30:35<4:15:48, 1.35s/it] 82%|████████▏ | 50511/61904 [3:30:37<4:16:59, 1.35s/it] 82%|████████▏ | 50512/61904 [3:30:38<4:11:41, 1.33s/it] 82%|████████▏ | 50513/61904 [3:30:39<4:11:51, 1.33s/it] 82%|████████▏ | 50514/61904 [3:30:41<4:09:29, 1.31s/it] 82%|████████▏ | 50515/61904 [3:30:42<4:14:55, 1.34s/it] 82%|████████▏ | 50516/61904 [3:30:43<4:15:57, 1.35s/it] 82%|████████▏ | 50517/61904 [3:30:45<4:09:11, 1.31s/it] 82%|████████▏ | 50518/61904 [3:30:46<4:18:14, 1.36s/it] 82%|████████▏ | 50519/61904 [3:30:47<4:15:06, 1.34s/it] 82%|████████▏ | 50520/61904 [3:30:49<4:16:19, 1.35s/it] {'loss': 2.4199, 'learning_rate': 1.1844937119149488e-07, 'epoch': 13.06} + 82%|████████▏ | 50520/61904 [3:30:49<4:16:19, 1.35s/it] 82%|████████▏ | 50521/61904 [3:30:50<4:15:30, 1.35s/it] 82%|████████▏ | 50522/61904 [3:30:52<4:22:36, 1.38s/it] 82%|████████▏ | 50523/61904 [3:30:53<4:26:46, 1.41s/it] 82%|████████▏ | 50524/61904 [3:30:54<4:19:42, 1.37s/it] 82%|████████▏ | 50525/61904 [3:30:56<4:13:23, 1.34s/it] 82%|████████▏ | 50526/61904 [3:30:57<4:19:14, 1.37s/it] 82%|████████▏ | 50527/61904 [3:30:58<4:16:05, 1.35s/it] 82%|████████▏ | 50528/61904 [3:31:00<4:12:56, 1.33s/it] 82%|████████▏ | 50529/61904 [3:31:01<4:11:55, 1.33s/it] 82%|████████▏ | 50530/61904 [3:31:02<4:09:10, 1.31s/it] 82%|████████▏ | 50531/61904 [3:31:04<4:22:40, 1.39s/it] 82%|████████▏ | 50532/61904 [3:31:05<4:23:14, 1.39s/it] 82%|████████▏ | 50533/61904 [3:31:07<4:33:33, 1.44s/it] 82%|████████▏ | 50534/61904 [3:31:08<4:32:00, 1.44s/it] 82%|████████▏ | 50535/61904 [3:31:09<4:24:30, 1.40s/it] 82%|████████▏ | 50536/61904 [3:31:11<4:28:12, 1.42s/it] 82%|████████▏ | 50537/61904 [3:31:12<4:27:35, 1.41s/it] 82%|████████▏ | 50538/61904 [3:31:14<4:25:43, 1.40s/it] 82%|████████▏ | 50539/61904 [3:31:15<4:22:03, 1.38s/it] 82%|████████▏ | 50540/61904 [3:31:16<4:21:02, 1.38s/it] {'loss': 2.477, 'learning_rate': 1.1841695838195254e-07, 'epoch': 13.06} + 82%|████████▏ | 50540/61904 [3:31:16<4:21:02, 1.38s/it] 82%|████████▏ | 50541/61904 [3:31:18<4:15:12, 1.35s/it] 82%|████████▏ | 50542/61904 [3:31:19<4:15:43, 1.35s/it] 82%|████████▏ | 50543/61904 [3:31:21<4:25:45, 1.40s/it] 82%|████████▏ | 50544/61904 [3:31:22<4:17:53, 1.36s/it] 82%|████████▏ | 50545/61904 [3:31:23<4:15:49, 1.35s/it] 82%|████████▏ | 50546/61904 [3:31:24<4:10:15, 1.32s/it] 82%|████████▏ | 50547/61904 [3:31:26<4:11:46, 1.33s/it] 82%|████████▏ | 50548/61904 [3:31:27<4:22:32, 1.39s/it] 82%|████████▏ | 50549/61904 [3:31:29<4:17:33, 1.36s/it] 82%|████████▏ | 50550/61904 [3:31:30<4:14:28, 1.34s/it] 82%|████████▏ | 50551/61904 [3:31:31<4:16:51, 1.36s/it] 82%|████████▏ | 50552/61904 [3:31:33<4:18:37, 1.37s/it] 82%|████████▏ | 50553/61904 [3:31:34<4:14:15, 1.34s/it] 82%|████████▏ | 50554/61904 [3:31:35<4:11:36, 1.33s/it] 82%|████████▏ | 50555/61904 [3:31:37<4:05:29, 1.30s/it] 82%|████████▏ | 50556/61904 [3:31:38<4:12:55, 1.34s/it] 82%|████████▏ | 50557/61904 [3:31:39<4:17:17, 1.36s/it] 82%|████████▏ | 50558/61904 [3:31:41<4:18:59, 1.37s/it] 82%|████████▏ | 50559/61904 [3:31:42<4:17:35, 1.36s/it] 82%|████████▏ | 50560/61904 [3:31:43<4:10:13, 1.32s/it] {'loss': 2.3863, 'learning_rate': 1.183845455724102e-07, 'epoch': 13.07} + 82%|████████▏ | 50560/61904 [3:31:43<4:10:13, 1.32s/it] 82%|████████▏ | 50561/61904 [3:31:45<4:15:33, 1.35s/it] 82%|████████▏ | 50562/61904 [3:31:46<4:23:20, 1.39s/it] 82%|████████▏ | 50563/61904 [3:31:48<4:20:09, 1.38s/it] 82%|████████▏ | 50564/61904 [3:31:49<4:22:24, 1.39s/it] 82%|████████▏ | 50565/61904 [3:31:50<4:22:16, 1.39s/it] 82%|████████▏ | 50566/61904 [3:31:52<4:22:20, 1.39s/it] 82%|████████▏ | 50567/61904 [3:31:53<4:19:07, 1.37s/it] 82%|████████▏ | 50568/61904 [3:31:54<4:15:11, 1.35s/it] 82%|████████▏ | 50569/61904 [3:31:56<4:20:06, 1.38s/it] 82%|████████▏ | 50570/61904 [3:31:57<4:15:01, 1.35s/it] 82%|████████▏ | 50571/61904 [3:31:59<4:30:27, 1.43s/it] 82%|████████▏ | 50572/61904 [3:32:00<4:17:07, 1.36s/it] 82%|████████▏ | 50573/61904 [3:32:01<4:14:32, 1.35s/it] 82%|████████▏ | 50574/61904 [3:32:03<4:23:07, 1.39s/it] 82%|████████▏ | 50575/61904 [3:32:04<4:38:30, 1.47s/it] 82%|████████▏ | 50576/61904 [3:32:06<4:31:31, 1.44s/it] 82%|████████▏ | 50577/61904 [3:32:07<4:30:10, 1.43s/it] 82%|████████▏ | 50578/61904 [3:32:09<4:25:21, 1.41s/it] 82%|████████▏ | 50579/61904 [3:32:10<4:19:05, 1.37s/it] 82%|████████▏ | 50580/61904 [3:32:11<4:24:53, 1.40s/it] {'loss': 2.4797, 'learning_rate': 1.1835213276286788e-07, 'epoch': 13.07} + 82%|████████▏ | 50580/61904 [3:32:11<4:24:53, 1.40s/it] 82%|████████▏ | 50581/61904 [3:32:13<4:14:54, 1.35s/it] 82%|████████▏ | 50582/61904 [3:32:14<4:14:26, 1.35s/it] 82%|████████▏ | 50583/61904 [3:32:15<4:16:08, 1.36s/it] 82%|████████▏ | 50584/61904 [3:32:17<4:18:11, 1.37s/it] 82%|████████▏ | 50585/61904 [3:32:18<4:33:34, 1.45s/it] 82%|████████▏ | 50586/61904 [3:32:20<4:26:58, 1.42s/it] 82%|███��████▏ | 50587/61904 [3:32:21<4:20:06, 1.38s/it] 82%|████████▏ | 50588/61904 [3:32:22<4:13:43, 1.35s/it] 82%|████████▏ | 50589/61904 [3:32:24<4:21:00, 1.38s/it] 82%|████████▏ | 50590/61904 [3:32:25<4:21:15, 1.39s/it] 82%|████████▏ | 50591/61904 [3:32:26<4:17:35, 1.37s/it] 82%|████████▏ | 50592/61904 [3:32:28<4:17:52, 1.37s/it] 82%|████████▏ | 50593/61904 [3:32:29<4:21:15, 1.39s/it] 82%|████████▏ | 50594/61904 [3:32:30<4:17:31, 1.37s/it] 82%|████████▏ | 50595/61904 [3:32:32<4:15:59, 1.36s/it] 82%|████████▏ | 50596/61904 [3:32:33<4:13:42, 1.35s/it] 82%|████████▏ | 50597/61904 [3:32:35<4:15:02, 1.35s/it] 82%|████████▏ | 50598/61904 [3:32:36<4:13:13, 1.34s/it] 82%|████████▏ | 50599/61904 [3:32:37<4:13:40, 1.35s/it] 82%|████████▏ | 50600/61904 [3:32:39<4:22:28, 1.39s/it] {'loss': 2.4302, 'learning_rate': 1.1831971995332555e-07, 'epoch': 13.08} + 82%|████████▏ | 50600/61904 [3:32:39<4:22:28, 1.39s/it] 82%|████████▏ | 50601/61904 [3:32:40<4:19:00, 1.37s/it] 82%|████████▏ | 50602/61904 [3:32:41<4:21:18, 1.39s/it] 82%|████████▏ | 50603/61904 [3:32:43<4:18:58, 1.38s/it] 82%|████████▏ | 50604/61904 [3:32:44<4:26:47, 1.42s/it] 82%|████████▏ | 50605/61904 [3:32:46<4:26:53, 1.42s/it] 82%|████████▏ | 50606/61904 [3:32:47<4:30:55, 1.44s/it] 82%|████████▏ | 50607/61904 [3:32:49<4:27:24, 1.42s/it] 82%|████████▏ | 50608/61904 [3:32:50<4:22:43, 1.40s/it] 82%|████████▏ | 50609/61904 [3:32:51<4:16:15, 1.36s/it] 82%|████████▏ | 50610/61904 [3:32:52<4:10:14, 1.33s/it] 82%|████████▏ | 50611/61904 [3:32:54<4:15:48, 1.36s/it] 82%|████████▏ | 50612/61904 [3:32:55<4:16:54, 1.37s/it] 82%|████████▏ | 50613/61904 [3:32:57<4:13:24, 1.35s/it] 82%|████████▏ | 50614/61904 [3:32:58<4:06:05, 1.31s/it] 82%|████████▏ | 50615/61904 [3:32:59<4:10:09, 1.33s/it] 82%|████████▏ | 50616/61904 [3:33:01<4:10:05, 1.33s/it] 82%|████████▏ | 50617/61904 [3:33:02<4:11:01, 1.33s/it] 82%|████████▏ | 50618/61904 [3:33:03<4:18:05, 1.37s/it] 82%|████████▏ | 50619/61904 [3:33:05<4:21:48, 1.39s/it] 82%|████████▏ | 50620/61904 [3:33:06<4:21:12, 1.39s/it] {'loss': 2.4693, 'learning_rate': 1.1828730714378322e-07, 'epoch': 13.08} + 82%|████████▏ | 50620/61904 [3:33:06<4:21:12, 1.39s/it] 82%|████████▏ | 50621/61904 [3:33:08<4:20:22, 1.38s/it] 82%|████████▏ | 50622/61904 [3:33:09<4:24:20, 1.41s/it] 82%|████████▏ | 50623/61904 [3:33:10<4:23:35, 1.40s/it] 82%|████████▏ | 50624/61904 [3:33:12<4:18:38, 1.38s/it] 82%|████████▏ | 50625/61904 [3:33:13<4:21:26, 1.39s/it] 82%|████████▏ | 50626/61904 [3:33:14<4:21:55, 1.39s/it] 82%|████████▏ | 50627/61904 [3:33:16<4:20:35, 1.39s/it] 82%|████████▏ | 50628/61904 [3:33:17<4:33:50, 1.46s/it] 82%|████████▏ | 50629/61904 [3:33:19<4:31:57, 1.45s/it] 82%|████████▏ | 50630/61904 [3:33:20<4:29:01, 1.43s/it] 82%|████████▏ | 50631/61904 [3:33:22<4:26:35, 1.42s/it] 82%|████████▏ | 50632/61904 [3:33:23<4:35:17, 1.47s/it] 82%|████████▏ | 50633/61904 [3:33:25<4:22:06, 1.40s/it] 82%|████████▏ | 50634/61904 [3:33:26<4:33:20, 1.46s/it] 82%|████████▏ | 50635/61904 [3:33:27<4:26:00, 1.42s/it] 82%|████████▏ | 50636/61904 [3:33:29<4:19:26, 1.38s/it] 82%|████████▏ | 50637/61904 [3:33:30<4:17:06, 1.37s/it] 82%|████████▏ | 50638/61904 [3:33:31<4:19:14, 1.38s/it] 82%|████████▏ | 50639/61904 [3:33:33<4:13:59, 1.35s/it] 82%|████████▏ | 50640/61904 [3:33:34<4:19:06, 1.38s/it] {'loss': 2.5014, 'learning_rate': 1.1825489433424088e-07, 'epoch': 13.09} + 82%|████████▏ | 50640/61904 [3:33:34<4:19:06, 1.38s/it] 82%|████████▏ | 50641/61904 [3:33:35<4:14:22, 1.36s/it] 82%|████████▏ | 50642/61904 [3:33:37<4:21:31, 1.39s/it] 82%|████████▏ | 50643/61904 [3:33:39<4:36:35, 1.47s/it] 82%|████████▏ | 50644/61904 [3:33:40<4:27:41, 1.43s/it] 82%|████████▏ | 50645/61904 [3:33:41<4:26:04, 1.42s/it] 82%|█████��██▏ | 50646/61904 [3:33:43<4:26:24, 1.42s/it] 82%|████████▏ | 50647/61904 [3:33:44<4:26:00, 1.42s/it] 82%|████████▏ | 50648/61904 [3:33:45<4:18:27, 1.38s/it] 82%|████████▏ | 50649/61904 [3:33:47<4:20:59, 1.39s/it] 82%|████████▏ | 50650/61904 [3:33:49<4:33:59, 1.46s/it] 82%|████████▏ | 50651/61904 [3:33:50<4:36:09, 1.47s/it] 82%|████████▏ | 50652/61904 [3:33:52<4:45:35, 1.52s/it] 82%|████████▏ | 50653/61904 [3:33:53<4:48:36, 1.54s/it] 82%|████████▏ | 50654/61904 [3:33:55<4:36:39, 1.48s/it] 82%|████████▏ | 50655/61904 [3:33:56<4:24:25, 1.41s/it] 82%|████████▏ | 50656/61904 [3:33:57<4:18:57, 1.38s/it] 82%|████████▏ | 50657/61904 [3:33:58<4:15:59, 1.37s/it] 82%|████████▏ | 50658/61904 [3:34:00<4:18:29, 1.38s/it] 82%|████████▏ | 50659/61904 [3:34:01<4:17:06, 1.37s/it] 82%|████████▏ | 50660/61904 [3:34:03<4:30:46, 1.44s/it] {'loss': 2.4204, 'learning_rate': 1.1822248152469855e-07, 'epoch': 13.09} + 82%|████████▏ | 50660/61904 [3:34:03<4:30:46, 1.44s/it] 82%|████████▏ | 50661/61904 [3:34:04<4:24:51, 1.41s/it] 82%|████████▏ | 50662/61904 [3:34:06<4:28:39, 1.43s/it] 82%|████████▏ | 50663/61904 [3:34:07<4:31:45, 1.45s/it] 82%|████████▏ | 50664/61904 [3:34:09<4:33:58, 1.46s/it] 82%|████████▏ | 50665/61904 [3:34:10<4:25:45, 1.42s/it] 82%|████████▏ | 50666/61904 [3:34:11<4:18:47, 1.38s/it] 82%|████████▏ | 50667/61904 [3:34:13<4:21:34, 1.40s/it] 82%|████████▏ | 50668/61904 [3:34:14<4:10:57, 1.34s/it] 82%|████████▏ | 50669/61904 [3:34:15<4:10:16, 1.34s/it] 82%|████████▏ | 50670/61904 [3:34:16<4:04:58, 1.31s/it] 82%|████████▏ | 50671/61904 [3:34:18<3:56:52, 1.27s/it] 82%|████████▏ | 50672/61904 [3:34:19<3:59:17, 1.28s/it] 82%|████████▏ | 50673/61904 [3:34:20<4:07:41, 1.32s/it] 82%|████████▏ | 50674/61904 [3:34:22<4:07:33, 1.32s/it] 82%|████████▏ | 50675/61904 [3:34:23<4:11:15, 1.34s/it] 82%|████████▏ | 50676/61904 [3:34:24<4:09:52, 1.34s/it] 82%|████████▏ | 50677/61904 [3:34:26<4:15:43, 1.37s/it] 82%|████████▏ | 50678/61904 [3:34:27<4:10:54, 1.34s/it] 82%|████████▏ | 50679/61904 [3:34:28<4:10:15, 1.34s/it] 82%|████████▏ | 50680/61904 [3:34:30<4:07:15, 1.32s/it] {'loss': 2.4063, 'learning_rate': 1.1819006871515623e-07, 'epoch': 13.1} + 82%|████████▏ | 50680/61904 [3:34:30<4:07:15, 1.32s/it] 82%|████████▏ | 50681/61904 [3:34:31<4:12:22, 1.35s/it] 82%|████████▏ | 50682/61904 [3:34:33<4:13:12, 1.35s/it] 82%|████████▏ | 50683/61904 [3:34:34<4:22:21, 1.40s/it] 82%|████████▏ | 50684/61904 [3:34:35<4:13:37, 1.36s/it] 82%|████████▏ | 50685/61904 [3:34:37<4:16:32, 1.37s/it] 82%|████████▏ | 50686/61904 [3:34:38<4:14:20, 1.36s/it] 82%|████████▏ | 50687/61904 [3:34:39<4:10:54, 1.34s/it] 82%|████████▏ | 50688/61904 [3:34:41<4:09:33, 1.34s/it] 82%|████████▏ | 50689/61904 [3:34:42<4:08:59, 1.33s/it] 82%|████████▏ | 50690/61904 [3:34:43<4:18:24, 1.38s/it] 82%|████████▏ | 50691/61904 [3:34:45<4:15:11, 1.37s/it] 82%|████████▏ | 50692/61904 [3:34:46<4:11:15, 1.34s/it] 82%|████████▏ | 50693/61904 [3:34:48<4:19:48, 1.39s/it] 82%|████████▏ | 50694/61904 [3:34:49<4:22:56, 1.41s/it] 82%|████████▏ | 50695/61904 [3:34:51<4:27:42, 1.43s/it] 82%|████████▏ | 50696/61904 [3:34:52<4:27:47, 1.43s/it] 82%|████████▏ | 50697/61904 [3:34:53<4:19:09, 1.39s/it] 82%|████████▏ | 50698/61904 [3:34:55<4:22:27, 1.41s/it] 82%|████████▏ | 50699/61904 [3:34:56<4:24:27, 1.42s/it] 82%|████████▏ | 50700/61904 [3:34:58<4:22:38, 1.41s/it] {'loss': 2.4893, 'learning_rate': 1.1815765590561389e-07, 'epoch': 13.1} + 82%|████████▏ | 50700/61904 [3:34:58<4:22:38, 1.41s/it] 82%|████████▏ | 50701/61904 [3:34:59<4:18:01, 1.38s/it] 82%|████████▏ | 50702/61904 [3:35:00<4:16:22, 1.37s/it] 82%|████████▏ | 50703/61904 [3:35:02<4:15:10, 1.37s/it] 82%|████████▏ | 50704/61904 [3:35:03<4:13:07, 1.36s/it] 82%|████████��� | 50705/61904 [3:35:04<4:11:57, 1.35s/it] 82%|████████▏ | 50706/61904 [3:35:06<4:14:10, 1.36s/it] 82%|████████▏ | 50707/61904 [3:35:07<4:15:32, 1.37s/it] 82%|████████▏ | 50708/61904 [3:35:08<4:14:36, 1.36s/it] 82%|████████▏ | 50709/61904 [3:35:10<4:10:50, 1.34s/it] 82%|████████▏ | 50710/61904 [3:35:11<4:06:03, 1.32s/it] 82%|████████▏ | 50711/61904 [3:35:12<4:21:28, 1.40s/it] 82%|████████▏ | 50712/61904 [3:35:14<4:18:58, 1.39s/it] 82%|████████▏ | 50713/61904 [3:35:15<4:27:12, 1.43s/it] 82%|████████▏ | 50714/61904 [3:35:17<4:46:12, 1.53s/it] 82%|████████▏ | 50715/61904 [3:35:18<4:29:37, 1.45s/it] 82%|████████▏ | 50716/61904 [3:35:20<4:25:39, 1.42s/it] 82%|████████▏ | 50717/61904 [3:35:21<4:21:42, 1.40s/it] 82%|████████▏ | 50718/61904 [3:35:22<4:13:27, 1.36s/it] 82%|████████▏ | 50719/61904 [3:35:24<4:20:02, 1.39s/it] 82%|████████▏ | 50720/61904 [3:35:25<4:23:39, 1.41s/it] {'loss': 2.4443, 'learning_rate': 1.1812524309607155e-07, 'epoch': 13.11} + 82%|████████▏ | 50720/61904 [3:35:25<4:23:39, 1.41s/it] 82%|████████▏ | 50721/61904 [3:35:27<4:19:00, 1.39s/it] 82%|████████▏ | 50722/61904 [3:35:28<4:14:44, 1.37s/it] 82%|████████▏ | 50723/61904 [3:35:29<4:10:15, 1.34s/it] 82%|████████▏ | 50724/61904 [3:35:31<4:24:41, 1.42s/it] 82%|████████▏ | 50725/61904 [3:35:32<4:22:43, 1.41s/it] 82%|████████▏ | 50726/61904 [3:35:34<4:25:51, 1.43s/it] 82%|████████▏ | 50727/61904 [3:35:35<4:27:16, 1.43s/it] 82%|████████▏ | 50728/61904 [3:35:36<4:18:19, 1.39s/it] 82%|████████▏ | 50729/61904 [3:35:38<4:18:28, 1.39s/it] 82%|████████▏ | 50730/61904 [3:35:39<4:09:55, 1.34s/it] 82%|████████▏ | 50731/61904 [3:35:40<4:13:22, 1.36s/it] 82%|████████▏ | 50732/61904 [3:35:42<4:11:03, 1.35s/it] 82%|████████▏ | 50733/61904 [3:35:43<4:12:43, 1.36s/it] 82%|████████▏ | 50734/61904 [3:35:45<4:14:19, 1.37s/it] 82%|████████▏ | 50735/61904 [3:35:46<4:07:39, 1.33s/it] 82%|████████▏ | 50736/61904 [3:35:47<4:04:34, 1.31s/it] 82%|████████▏ | 50737/61904 [3:35:48<4:05:31, 1.32s/it] 82%|████████▏ | 50738/61904 [3:35:50<4:11:13, 1.35s/it] 82%|████████▏ | 50739/61904 [3:35:51<4:12:36, 1.36s/it] 82%|████████▏ | 50740/61904 [3:35:53<4:10:53, 1.35s/it] {'loss': 2.4188, 'learning_rate': 1.1809283028652923e-07, 'epoch': 13.11} + 82%|████████▏ | 50740/61904 [3:35:53<4:10:53, 1.35s/it] 82%|████████▏ | 50741/61904 [3:35:54<4:14:15, 1.37s/it] 82%|████████▏ | 50742/61904 [3:35:55<4:20:43, 1.40s/it] 82%|████████▏ | 50743/61904 [3:35:57<4:15:01, 1.37s/it] 82%|████████▏ | 50744/61904 [3:35:58<4:12:48, 1.36s/it] 82%|████████▏ | 50745/61904 [3:36:00<4:21:02, 1.40s/it] 82%|████████▏ | 50746/61904 [3:36:01<4:22:15, 1.41s/it] 82%|████████▏ | 50747/61904 [3:36:02<4:21:12, 1.40s/it] 82%|████████▏ | 50748/61904 [3:36:04<4:15:02, 1.37s/it] 82%|████████▏ | 50749/61904 [3:36:05<4:15:58, 1.38s/it] 82%|████████▏ | 50750/61904 [3:36:06<4:09:42, 1.34s/it] 82%|████████▏ | 50751/61904 [3:36:08<4:21:11, 1.41s/it] 82%|████████▏ | 50752/61904 [3:36:09<4:14:06, 1.37s/it] 82%|████████▏ | 50753/61904 [3:36:10<4:12:33, 1.36s/it] 82%|████████▏ | 50754/61904 [3:36:12<4:11:51, 1.36s/it] 82%|████████▏ | 50755/61904 [3:36:13<4:21:12, 1.41s/it] 82%|████████▏ | 50756/61904 [3:36:15<4:20:11, 1.40s/it] 82%|████████▏ | 50757/61904 [3:36:16<4:16:53, 1.38s/it] 82%|████████▏ | 50758/61904 [3:36:17<4:13:49, 1.37s/it] 82%|████████▏ | 50759/61904 [3:36:19<4:16:02, 1.38s/it] 82%|████████▏ | 50760/61904 [3:36:20<4:15:22, 1.37s/it] {'loss': 2.4566, 'learning_rate': 1.180604174769869e-07, 'epoch': 13.12} + 82%|████████▏ | 50760/61904 [3:36:20<4:15:22, 1.37s/it] 82%|████████▏ | 50761/61904 [3:36:21<4:06:41, 1.33s/it] 82%|████████▏ | 50762/61904 [3:36:23<4:07:26, 1.33s/it] 82%|████████▏ | 50763/61904 [3:36:24<4:09:28, 1.34s/it] 82%|████████▏ | 50764/61904 [3:36:25<4:06:30, 1.33s/it] 82%|████████▏ | 50765/61904 [3:36:27<4:14:56, 1.37s/it] 82%|████████▏ | 50766/61904 [3:36:28<4:22:29, 1.41s/it] 82%|████████▏ | 50767/61904 [3:36:30<4:16:32, 1.38s/it] 82%|████████▏ | 50768/61904 [3:36:31<4:12:07, 1.36s/it] 82%|████████▏ | 50769/61904 [3:36:32<4:15:41, 1.38s/it] 82%|████████▏ | 50770/61904 [3:36:34<4:14:14, 1.37s/it] 82%|████████▏ | 50771/61904 [3:36:35<4:13:01, 1.36s/it] 82%|████████▏ | 50772/61904 [3:36:36<4:12:41, 1.36s/it] 82%|████████▏ | 50773/61904 [3:36:38<4:15:23, 1.38s/it] 82%|████████▏ | 50774/61904 [3:36:40<4:31:05, 1.46s/it] 82%|████████▏ | 50775/61904 [3:36:41<4:22:27, 1.42s/it] 82%|████████▏ | 50776/61904 [3:36:42<4:12:57, 1.36s/it] 82%|████████▏ | 50777/61904 [3:36:44<4:24:42, 1.43s/it] 82%|████████▏ | 50778/61904 [3:36:45<4:24:31, 1.43s/it] 82%|████████▏ | 50779/61904 [3:36:46<4:21:14, 1.41s/it] 82%|████████▏ | 50780/61904 [3:36:48<4:20:11, 1.40s/it] {'loss': 2.4187, 'learning_rate': 1.1802800466744456e-07, 'epoch': 13.12} + 82%|████████▏ | 50780/61904 [3:36:48<4:20:11, 1.40s/it] 82%|████████▏ | 50781/61904 [3:36:49<4:26:24, 1.44s/it] 82%|████████▏ | 50782/61904 [3:36:51<4:22:15, 1.41s/it] 82%|████████▏ | 50783/61904 [3:36:52<4:29:29, 1.45s/it] 82%|████████▏ | 50784/61904 [3:36:54<4:23:05, 1.42s/it] 82%|████████▏ | 50785/61904 [3:36:55<4:22:21, 1.42s/it] 82%|████████▏ | 50786/61904 [3:36:56<4:13:22, 1.37s/it] 82%|████████▏ | 50787/61904 [3:36:58<4:11:10, 1.36s/it] 82%|████████▏ | 50788/61904 [3:36:59<4:13:15, 1.37s/it] 82%|████████▏ | 50789/61904 [3:37:00<4:18:07, 1.39s/it] 82%|████████▏ | 50790/61904 [3:37:02<4:15:03, 1.38s/it] 82%|████████▏ | 50791/61904 [3:37:03<4:28:01, 1.45s/it] 82%|████████▏ | 50792/61904 [3:37:05<4:24:43, 1.43s/it] 82%|████████▏ | 50793/61904 [3:37:06<4:17:53, 1.39s/it] 82%|████████▏ | 50794/61904 [3:37:08<4:17:22, 1.39s/it] 82%|████████▏ | 50795/61904 [3:37:09<4:19:54, 1.40s/it] 82%|████████▏ | 50796/61904 [3:37:10<4:26:45, 1.44s/it] 82%|████████▏ | 50797/61904 [3:37:12<4:26:55, 1.44s/it] 82%|████████▏ | 50798/61904 [3:37:13<4:22:11, 1.42s/it] 82%|████████▏ | 50799/61904 [3:37:15<4:17:34, 1.39s/it] 82%|████████▏ | 50800/61904 [3:37:16<4:22:16, 1.42s/it] {'loss': 2.4418, 'learning_rate': 1.1799559185790222e-07, 'epoch': 13.13} + 82%|████████▏ | 50800/61904 [3:37:16<4:22:16, 1.42s/it] 82%|████████▏ | 50801/61904 [3:37:17<4:21:20, 1.41s/it] 82%|████████▏ | 50802/61904 [3:37:19<4:19:01, 1.40s/it] 82%|████████▏ | 50803/61904 [3:37:20<4:17:35, 1.39s/it] 82%|████████▏ | 50804/61904 [3:37:22<4:21:01, 1.41s/it] 82%|████████▏ | 50805/61904 [3:37:23<4:20:15, 1.41s/it] 82%|████████▏ | 50806/61904 [3:37:25<4:21:39, 1.41s/it] 82%|████████▏ | 50807/61904 [3:37:26<4:21:40, 1.41s/it] 82%|████████▏ | 50808/61904 [3:37:27<4:20:52, 1.41s/it] 82%|████████▏ | 50809/61904 [3:37:29<4:19:11, 1.40s/it] 82%|████████▏ | 50810/61904 [3:37:30<4:22:53, 1.42s/it] 82%|████████▏ | 50811/61904 [3:37:32<4:24:04, 1.43s/it] 82%|████████▏ | 50812/61904 [3:37:33<4:22:14, 1.42s/it] 82%|████████▏ | 50813/61904 [3:37:34<4:16:15, 1.39s/it] 82%|████████▏ | 50814/61904 [3:37:36<4:18:01, 1.40s/it] 82%|████████▏ | 50815/61904 [3:37:37<4:17:26, 1.39s/it] 82%|████████▏ | 50816/61904 [3:37:38<4:12:04, 1.36s/it] 82%|████████▏ | 50817/61904 [3:37:40<4:19:24, 1.40s/it] 82%|████████▏ | 50818/61904 [3:37:41<4:14:14, 1.38s/it] 82%|████████▏ | 50819/61904 [3:37:43<4:15:46, 1.38s/it] 82%|████████▏ | 50820/61904 [3:37:44<4:14:37, 1.38s/it] {'loss': 2.4705, 'learning_rate': 1.179631790483599e-07, 'epoch': 13.13} + 82%|████████▏ | 50820/61904 [3:37:44<4:14:37, 1.38s/it] 82%|████████▏ | 50821/61904 [3:37:45<4:11:45, 1.36s/it] 82%|████████▏ | 50822/61904 [3:37:47<4:04:35, 1.32s/it] 82%|████████▏ | 50823/61904 [3:37:48<4:00:43, 1.30s/it] 82%|████████▏ | 50824/61904 [3:37:49<4:08:17, 1.34s/it] 82%|████████▏ | 50825/61904 [3:37:51<4:10:51, 1.36s/it] 82%|████████▏ | 50826/61904 [3:37:52<4:03:17, 1.32s/it] 82%|████████▏ | 50827/61904 [3:37:53<3:59:56, 1.30s/it] 82%|████████▏ | 50828/61904 [3:37:55<4:11:52, 1.36s/it] 82%|████████▏ | 50829/61904 [3:37:56<4:16:17, 1.39s/it] 82%|████████▏ | 50830/61904 [3:37:57<4:06:56, 1.34s/it] 82%|████████▏ | 50831/61904 [3:37:59<4:08:29, 1.35s/it] 82%|████████▏ | 50832/61904 [3:38:00<4:08:37, 1.35s/it] 82%|████████▏ | 50833/61904 [3:38:01<4:06:52, 1.34s/it] 82%|████████▏ | 50834/61904 [3:38:03<4:10:29, 1.36s/it] 82%|████████▏ | 50835/61904 [3:38:04<4:07:09, 1.34s/it] 82%|████████▏ | 50836/61904 [3:38:06<4:14:57, 1.38s/it] 82%|████████▏ | 50837/61904 [3:38:07<4:19:03, 1.40s/it] 82%|████████▏ | 50838/61904 [3:38:08<4:20:12, 1.41s/it] 82%|████████▏ | 50839/61904 [3:38:10<4:20:50, 1.41s/it] 82%|████████▏ | 50840/61904 [3:38:11<4:19:31, 1.41s/it] {'loss': 2.4966, 'learning_rate': 1.1793076623881758e-07, 'epoch': 13.14} + 82%|████████▏ | 50840/61904 [3:38:11<4:19:31, 1.41s/it] 82%|████████▏ | 50841/61904 [3:38:13<4:15:31, 1.39s/it] 82%|████████▏ | 50842/61904 [3:38:14<4:18:57, 1.40s/it] 82%|████████▏ | 50843/61904 [3:38:15<4:23:33, 1.43s/it] 82%|████████▏ | 50844/61904 [3:38:17<4:32:38, 1.48s/it] 82%|████████▏ | 50845/61904 [3:38:18<4:23:56, 1.43s/it] 82%|████████▏ | 50846/61904 [3:38:20<4:20:07, 1.41s/it] 82%|████████▏ | 50847/61904 [3:38:21<4:25:06, 1.44s/it] 82%|████████▏ | 50848/61904 [3:38:23<4:30:10, 1.47s/it] 82%|████████▏ | 50849/61904 [3:38:24<4:29:26, 1.46s/it] 82%|████████▏ | 50850/61904 [3:38:26<4:26:52, 1.45s/it] 82%|████████▏ | 50851/61904 [3:38:27<4:29:03, 1.46s/it] 82%|████████▏ | 50852/61904 [3:38:29<4:33:04, 1.48s/it] 82%|████████▏ | 50853/61904 [3:38:30<4:35:44, 1.50s/it] 82%|████████▏ | 50854/61904 [3:38:32<4:32:16, 1.48s/it] 82%|████████▏ | 50855/61904 [3:38:33<4:31:42, 1.48s/it] 82%|████████▏ | 50856/61904 [3:38:34<4:21:43, 1.42s/it] 82%|████████▏ | 50857/61904 [3:38:36<4:22:46, 1.43s/it] 82%|████████▏ | 50858/61904 [3:38:37<4:16:21, 1.39s/it] 82%|████████▏ | 50859/61904 [3:38:39<4:16:36, 1.39s/it] 82%|████████▏ | 50860/61904 [3:38:40<4:13:49, 1.38s/it] {'loss': 2.4615, 'learning_rate': 1.1789835342927524e-07, 'epoch': 13.15} + 82%|████████▏ | 50860/61904 [3:38:40<4:13:49, 1.38s/it] 82%|████████▏ | 50861/61904 [3:38:41<4:13:08, 1.38s/it] 82%|████████▏ | 50862/61904 [3:38:43<4:13:02, 1.37s/it] 82%|████████▏ | 50863/61904 [3:38:44<4:10:54, 1.36s/it] 82%|████████▏ | 50864/61904 [3:38:45<4:10:14, 1.36s/it] 82%|████████▏ | 50865/61904 [3:38:47<4:12:01, 1.37s/it] 82%|████████▏ | 50866/61904 [3:38:48<4:10:45, 1.36s/it] 82%|████████▏ | 50867/61904 [3:38:50<4:29:09, 1.46s/it] 82%|████████▏ | 50868/61904 [3:38:51<4:22:12, 1.43s/it] 82%|████████▏ | 50869/61904 [3:38:52<4:13:08, 1.38s/it] 82%|████████▏ | 50870/61904 [3:38:54<4:16:04, 1.39s/it] 82%|████████▏ | 50871/61904 [3:38:55<4:11:53, 1.37s/it] 82%|████████▏ | 50872/61904 [3:38:56<4:07:27, 1.35s/it] 82%|████████▏ | 50873/61904 [3:38:58<4:05:50, 1.34s/it] 82%|████████▏ | 50874/61904 [3:38:59<4:18:15, 1.40s/it] 82%|████████▏ | 50875/61904 [3:39:01<4:16:33, 1.40s/it] 82%|████████▏ | 50876/61904 [3:39:02<4:19:16, 1.41s/it] 82%|████████▏ | 50877/61904 [3:39:03<4:16:35, 1.40s/it] 82%|████████▏ | 50878/61904 [3:39:05<4:10:41, 1.36s/it] 82%|████████▏ | 50879/61904 [3:39:06<4:03:03, 1.32s/it] 82%|████████▏ | 50880/61904 [3:39:08<4:16:06, 1.39s/it] {'loss': 2.4513, 'learning_rate': 1.1786594061973291e-07, 'epoch': 13.15} + 82%|████████▏ | 50880/61904 [3:39:08<4:16:06, 1.39s/it] 82%|████████▏ | 50881/61904 [3:39:09<4:11:40, 1.37s/it] 82%|████████▏ | 50882/61904 [3:39:10<4:19:10, 1.41s/it] 82%|████████▏ | 50883/61904 [3:39:12<4:21:58, 1.43s/it] 82%|████████▏ | 50884/61904 [3:39:13<4:15:56, 1.39s/it] 82%|████████▏ | 50885/61904 [3:39:15<4:22:30, 1.43s/it] 82%|████████▏ | 50886/61904 [3:39:16<4:18:13, 1.41s/it] 82%|████████▏ | 50887/61904 [3:39:18<4:23:03, 1.43s/it] 82%|████████▏ | 50888/61904 [3:39:19<4:23:17, 1.43s/it] 82%|████████▏ | 50889/61904 [3:39:20<4:15:30, 1.39s/it] 82%|████████▏ | 50890/61904 [3:39:22<4:09:45, 1.36s/it] 82%|████████▏ | 50891/61904 [3:39:23<4:08:50, 1.36s/it] 82%|████████▏ | 50892/61904 [3:39:24<4:10:11, 1.36s/it] 82%|████████▏ | 50893/61904 [3:39:26<4:16:11, 1.40s/it] 82%|████████▏ | 50894/61904 [3:39:27<4:15:19, 1.39s/it] 82%|████████▏ | 50895/61904 [3:39:28<4:04:54, 1.33s/it] 82%|████████▏ | 50896/61904 [3:39:30<4:08:20, 1.35s/it] 82%|████████▏ | 50897/61904 [3:39:31<4:14:59, 1.39s/it] 82%|████████▏ | 50898/61904 [3:39:33<4:18:03, 1.41s/it] 82%|████████▏ | 50899/61904 [3:39:34<4:16:36, 1.40s/it] 82%|████████▏ | 50900/61904 [3:39:35<4:19:09, 1.41s/it] {'loss': 2.4163, 'learning_rate': 1.1783352781019059e-07, 'epoch': 13.16} + 82%|████████▏ | 50900/61904 [3:39:35<4:19:09, 1.41s/it] 82%|████████▏ | 50901/61904 [3:39:37<4:16:02, 1.40s/it] 82%|████████▏ | 50902/61904 [3:39:38<4:08:58, 1.36s/it] 82%|████████▏ | 50903/61904 [3:39:39<4:06:33, 1.34s/it] 82%|████████▏ | 50904/61904 [3:39:41<4:18:02, 1.41s/it] 82%|████████▏ | 50905/61904 [3:39:42<4:18:13, 1.41s/it] 82%|████████▏ | 50906/61904 [3:39:44<4:23:09, 1.44s/it] 82%|████████▏ | 50907/61904 [3:39:45<4:14:33, 1.39s/it] 82%|████████▏ | 50908/61904 [3:39:47<4:14:38, 1.39s/it] 82%|████████▏ | 50909/61904 [3:39:48<4:12:48, 1.38s/it] 82%|████████▏ | 50910/61904 [3:39:49<4:20:10, 1.42s/it] 82%|████████▏ | 50911/61904 [3:39:51<4:19:32, 1.42s/it] 82%|████████▏ | 50912/61904 [3:39:52<4:20:25, 1.42s/it] 82%|████████▏ | 50913/61904 [3:39:54<4:14:14, 1.39s/it] 82%|████████▏ | 50914/61904 [3:39:55<4:14:23, 1.39s/it] 82%|████████▏ | 50915/61904 [3:39:56<4:18:18, 1.41s/it] 82%|████████▏ | 50916/61904 [3:39:58<4:16:30, 1.40s/it] 82%|████████▏ | 50917/61904 [3:39:59<4:18:07, 1.41s/it] 82%|████████▏ | 50918/61904 [3:40:01<4:23:54, 1.44s/it] 82%|████████▏ | 50919/61904 [3:40:02<4:18:35, 1.41s/it] 82%|████████▏ | 50920/61904 [3:40:04<4:20:15, 1.42s/it] {'loss': 2.457, 'learning_rate': 1.1780111500064825e-07, 'epoch': 13.16} + 82%|████████▏ | 50920/61904 [3:40:04<4:20:15, 1.42s/it] 82%|████████▏ | 50921/61904 [3:40:05<4:12:26, 1.38s/it] 82%|████████▏ | 50922/61904 [3:40:06<4:07:32, 1.35s/it] 82%|████████▏ | 50923/61904 [3:40:07<4:09:47, 1.36s/it] 82%|████████▏ | 50924/61904 [3:40:09<4:20:54, 1.43s/it] 82%|████████▏ | 50925/61904 [3:40:10<4:19:09, 1.42s/it] 82%|████████▏ | 50926/61904 [3:40:12<4:11:33, 1.37s/it] 82%|████████▏ | 50927/61904 [3:40:13<4:11:07, 1.37s/it] 82%|████████▏ | 50928/61904 [3:40:14<4:12:40, 1.38s/it] 82%|████████▏ | 50929/61904 [3:40:16<4:11:39, 1.38s/it] 82%|████████▏ | 50930/61904 [3:40:17<4:11:12, 1.37s/it] 82%|████████▏ | 50931/61904 [3:40:19<4:16:37, 1.40s/it] 82%|████████▏ | 50932/61904 [3:40:20<4:22:45, 1.44s/it] 82%|████████▏ | 50933/61904 [3:40:22<4:21:53, 1.43s/it] 82%|████████▏ | 50934/61904 [3:40:23<4:21:02, 1.43s/it] 82%|████████▏ | 50935/61904 [3:40:25<4:23:10, 1.44s/it] 82%|████████▏ | 50936/61904 [3:40:26<4:20:32, 1.43s/it] 82%|████████▏ | 50937/61904 [3:40:27<4:12:35, 1.38s/it] 82%|████████▏ | 50938/61904 [3:40:29<4:21:46, 1.43s/it] 82%|████████▏ | 50939/61904 [3:40:30<4:20:36, 1.43s/it] 82%|████████▏ | 50940/61904 [3:40:32<4:33:43, 1.50s/it] {'loss': 2.4637, 'learning_rate': 1.1776870219110591e-07, 'epoch': 13.17} + 82%|████████▏ | 50940/61904 [3:40:32<4:33:43, 1.50s/it] 82%|████████▏ | 50941/61904 [3:40:33<4:24:18, 1.45s/it] 82%|████████▏ | 50942/61904 [3:40:34<4:16:50, 1.41s/it] 82%|████████▏ | 50943/61904 [3:40:36<4:17:38, 1.41s/it] 82%|████████▏ | 50944/61904 [3:40:37<4:15:34, 1.40s/it] 82%|████████▏ | 50945/61904 [3:40:39<4:23:40, 1.44s/it] 82%|████████▏ | 50946/61904 [3:40:40<4:24:06, 1.45s/it] 82%|████████▏ | 50947/61904 [3:40:42<4:19:53, 1.42s/it] 82%|████████▏ | 50948/61904 [3:40:43<4:16:37, 1.41s/it] 82%|████████▏ | 50949/61904 [3:40:44<4:14:01, 1.39s/it] 82%|████████▏ | 50950/61904 [3:40:46<4:17:01, 1.41s/it] 82%|████████▏ | 50951/61904 [3:40:47<4:18:45, 1.42s/it] 82%|████████▏ | 50952/61904 [3:40:49<4:11:33, 1.38s/it] 82%|████████▏ | 50953/61904 [3:40:50<4:14:34, 1.39s/it] 82%|████████▏ | 50954/61904 [3:40:51<4:16:05, 1.40s/it] 82%|████████▏ | 50955/61904 [3:40:53<4:26:02, 1.46s/it] 82%|████████▏ | 50956/61904 [3:40:54<4:17:06, 1.41s/it] 82%|████████▏ | 50957/61904 [3:40:55<4:07:42, 1.36s/it] 82%|████████▏ | 50958/61904 [3:40:57<4:00:14, 1.32s/it] 82%|████████▏ | 50959/61904 [3:40:58<4:03:46, 1.34s/it] 82%|████████▏ | 50960/61904 [3:41:00<4:12:51, 1.39s/it] {'loss': 2.4972, 'learning_rate': 1.1773628938156359e-07, 'epoch': 13.17} + 82%|████████▏ | 50960/61904 [3:41:00<4:12:51, 1.39s/it] 82%|████████▏ | 50961/61904 [3:41:01<4:07:02, 1.35s/it] 82%|████████▏ | 50962/61904 [3:41:02<4:10:03, 1.37s/it] 82%|████████▏ | 50963/61904 [3:41:04<4:12:34, 1.39s/it] 82%|████████▏ | 50964/61904 [3:41:05<4:12:36, 1.39s/it] 82%|████████▏ | 50965/61904 [3:41:07<4:16:04, 1.40s/it] 82%|████████▏ | 50966/61904 [3:41:08<4:36:14, 1.52s/it] 82%|████████▏ | 50967/61904 [3:41:10<4:31:05, 1.49s/it] 82%|████████▏ | 50968/61904 [3:41:11<4:28:55, 1.48s/it] 82%|████████▏ | 50969/61904 [3:41:12<4:14:26, 1.40s/it] 82%|████████▏ | 50970/61904 [3:41:14<4:11:33, 1.38s/it] 82%|████████▏ | 50971/61904 [3:41:15<4:16:23, 1.41s/it] 82%|████████▏ | 50972/61904 [3:41:17<4:26:10, 1.46s/it] 82%|████████▏ | 50973/61904 [3:41:18<4:21:13, 1.43s/it] 82%|████████▏ | 50974/61904 [3:41:20<4:26:34, 1.46s/it] 82%|████████▏ | 50975/61904 [3:41:21<4:24:44, 1.45s/it] 82%|████████▏ | 50976/61904 [3:41:23<4:20:20, 1.43s/it] 82%|████████▏ | 50977/61904 [3:41:24<4:20:54, 1.43s/it] 82%|████████▏ | 50978/61904 [3:41:25<4:18:31, 1.42s/it] 82%|████████▏ | 50979/61904 [3:41:27<4:17:51, 1.42s/it] 82%|████████▏ | 50980/61904 [3:41:28<4:17:36, 1.41s/it] {'loss': 2.4628, 'learning_rate': 1.1770387657202126e-07, 'epoch': 13.18} + 82%|████████▏ | 50980/61904 [3:41:28<4:17:36, 1.41s/it] 82%|████████▏ | 50981/61904 [3:41:30<4:19:54, 1.43s/it] 82%|████████▏ | 50982/61904 [3:41:31<4:23:22, 1.45s/it] 82%|████████▏ | 50983/61904 [3:41:32<4:19:57, 1.43s/it] 82%|████████▏ | 50984/61904 [3:41:34<4:17:30, 1.41s/it] 82%|████████▏ | 50985/61904 [3:41:35<4:25:23, 1.46s/it] 82%|████████▏ | 50986/61904 [3:41:37<4:18:46, 1.42s/it] 82%|████████▏ | 50987/61904 [3:41:38<4:18:13, 1.42s/it] 82%|████████▏ | 50988/61904 [3:41:40<4:17:17, 1.41s/it] 82%|████████▏ | 50989/61904 [3:41:41<4:13:32, 1.39s/it] 82%|████████▏ | 50990/61904 [3:41:42<4:15:05, 1.40s/it] 82%|████████▏ | 50991/61904 [3:41:44<4:19:21, 1.43s/it] 82%|████████▏ | 50992/61904 [3:41:45<4:20:18, 1.43s/it] 82%|████████▏ | 50993/61904 [3:41:47<4:13:45, 1.40s/it] 82%|████████▏ | 50994/61904 [3:41:48<4:13:29, 1.39s/it] 82%|████████▏ | 50995/61904 [3:41:49<4:11:43, 1.38s/it] 82%|████████▏ | 50996/61904 [3:41:51<4:13:30, 1.39s/it] 82%|████████▏ | 50997/61904 [3:41:52<4:10:06, 1.38s/it] 82%|████████▏ | 50998/61904 [3:41:53<4:09:13, 1.37s/it] 82%|████████▏ | 50999/61904 [3:41:55<4:24:44, 1.46s/it] 82%|████████▏ | 51000/61904 [3:41:57<4:23:13, 1.45s/it] {'loss': 2.404, 'learning_rate': 1.1767146376247892e-07, 'epoch': 13.18} + 82%|████████▏ | 51000/61904 [3:41:57<4:23:13, 1.45s/it] 82%|████████▏ | 51001/61904 [3:41:58<4:17:24, 1.42s/it] 82%|████████▏ | 51002/61904 [3:41:59<4:15:01, 1.40s/it] 82%|████████▏ | 51003/61904 [3:42:01<4:22:15, 1.44s/it] 82%|████████▏ | 51004/61904 [3:42:02<4:11:46, 1.39s/it] 82%|████████▏ | 51005/61904 [3:42:04<4:21:24, 1.44s/it] 82%|████████▏ | 51006/61904 [3:42:05<4:13:59, 1.40s/it] 82%|████████▏ | 51007/61904 [3:42:06<4:13:50, 1.40s/it] 82%|████████▏ | 51008/61904 [3:42:08<4:19:14, 1.43s/it] 82%|████████▏ | 51009/61904 [3:42:09<4:12:09, 1.39s/it] 82%|████████▏ | 51010/61904 [3:42:10<4:11:31, 1.39s/it] 82%|████████▏ | 51011/61904 [3:42:12<4:08:44, 1.37s/it] 82%|████████▏ | 51012/61904 [3:42:13<4:07:42, 1.36s/it] 82%|████████▏ | 51013/61904 [3:42:15<4:09:26, 1.37s/it] 82%|████████▏ | 51014/61904 [3:42:16<4:02:57, 1.34s/it] 82%|████████▏ | 51015/61904 [3:42:17<4:03:01, 1.34s/it] 82%|████████▏ | 51016/61904 [3:42:18<4:01:32, 1.33s/it] 82%|████████▏ | 51017/61904 [3:42:20<4:08:01, 1.37s/it] 82%|████████▏ | 51018/61904 [3:42:21<4:08:40, 1.37s/it] 82%|████████▏ | 51019/61904 [3:42:23<4:07:15, 1.36s/it] 82%|████████▏ | 51020/61904 [3:42:24<4:09:00, 1.37s/it] {'loss': 2.4146, 'learning_rate': 1.1763905095293658e-07, 'epoch': 13.19} + 82%|████████▏ | 51020/61904 [3:42:24<4:09:00, 1.37s/it] 82%|████████▏ | 51021/61904 [3:42:25<4:05:33, 1.35s/it] 82%|████████▏ | 51022/61904 [3:42:27<4:04:48, 1.35s/it] 82%|████████▏ | 51023/61904 [3:42:28<4:06:45, 1.36s/it] 82%|████████▏ | 51024/61904 [3:42:30<4:11:46, 1.39s/it] 82%|████████▏ | 51025/61904 [3:42:31<4:08:50, 1.37s/it] 82%|████████▏ | 51026/61904 [3:42:32<4:10:16, 1.38s/it] 82%|████████▏ | 51027/61904 [3:42:34<4:08:38, 1.37s/it] 82%|████████▏ | 51028/61904 [3:42:35<4:04:20, 1.35s/it] 82%|████████▏ | 51029/61904 [3:42:36<4:03:40, 1.34s/it] 82%|████████▏ | 51030/61904 [3:42:38<4:09:54, 1.38s/it] 82%|████████▏ | 51031/61904 [3:42:39<4:15:21, 1.41s/it] 82%|████████▏ | 51032/61904 [3:42:41<4:12:39, 1.39s/it] 82%|████████▏ | 51033/61904 [3:42:42<4:13:15, 1.40s/it] 82%|████████▏ | 51034/61904 [3:42:43<4:10:33, 1.38s/it] 82%|████████▏ | 51035/61904 [3:42:45<4:11:59, 1.39s/it] 82%|████████▏ | 51036/61904 [3:42:46<4:08:01, 1.37s/it] 82%|████████▏ | 51037/61904 [3:42:47<4:12:17, 1.39s/it] 82%|████████▏ | 51038/61904 [3:42:49<4:07:41, 1.37s/it] 82%|████████▏ | 51039/61904 [3:42:50<4:01:56, 1.34s/it] 82%|████████▏ | 51040/61904 [3:42:52<4:14:37, 1.41s/it] {'loss': 2.4528, 'learning_rate': 1.1760663814339426e-07, 'epoch': 13.19} + 82%|████████▏ | 51040/61904 [3:42:52<4:14:37, 1.41s/it] 82%|████████▏ | 51041/61904 [3:42:53<4:17:53, 1.42s/it] 82%|████████▏ | 51042/61904 [3:42:54<4:14:40, 1.41s/it] 82%|████████▏ | 51043/61904 [3:42:56<4:13:11, 1.40s/it] 82%|████████▏ | 51044/61904 [3:42:57<4:13:01, 1.40s/it] 82%|████████▏ | 51045/61904 [3:42:59<4:11:14, 1.39s/it] 82%|████████▏ | 51046/61904 [3:43:00<4:08:50, 1.38s/it] 82%|████████▏ | 51047/61904 [3:43:01<4:09:03, 1.38s/it] 82%|████████▏ | 51048/61904 [3:43:03<4:04:59, 1.35s/it] 82%|████████▏ | 51049/61904 [3:43:04<4:13:57, 1.40s/it] 82%|████████▏ | 51050/61904 [3:43:06<4:16:45, 1.42s/it] 82%|████████▏ | 51051/61904 [3:43:07<4:08:21, 1.37s/it] 82%|████████▏ | 51052/61904 [3:43:08<4:03:07, 1.34s/it] 82%|████████▏ | 51053/61904 [3:43:09<4:03:15, 1.35s/it] 82%|████████▏ | 51054/61904 [3:43:11<4:03:18, 1.35s/it] 82%|████████▏ | 51055/61904 [3:43:12<4:02:31, 1.34s/it] 82%|████████▏ | 51056/61904 [3:43:14<4:11:07, 1.39s/it] 82%|████████▏ | 51057/61904 [3:43:15<4:08:37, 1.38s/it] 82%|████████▏ | 51058/61904 [3:43:16<4:08:49, 1.38s/it] 82%|████████▏ | 51059/61904 [3:43:18<4:09:55, 1.38s/it] 82%|████████▏ | 51060/61904 [3:43:19<4:10:53, 1.39s/it] {'loss': 2.4843, 'learning_rate': 1.1757422533385193e-07, 'epoch': 13.2} + 82%|████████▏ | 51060/61904 [3:43:19<4:10:53, 1.39s/it] 82%|████████▏ | 51061/61904 [3:43:21<4:20:11, 1.44s/it] 82%|████████▏ | 51062/61904 [3:43:22<4:15:29, 1.41s/it] 82%|████████▏ | 51063/61904 [3:43:23<4:14:04, 1.41s/it] 82%|████████▏ | 51064/61904 [3:43:25<4:09:08, 1.38s/it] 82%|████████▏ | 51065/61904 [3:43:26<4:11:40, 1.39s/it] 82%|████████▏ | 51066/61904 [3:43:27<4:05:32, 1.36s/it] 82%|████████▏ | 51067/61904 [3:43:29<3:59:06, 1.32s/it] 82%|████████▏ | 51068/61904 [3:43:30<3:57:40, 1.32s/it] 82%|████████▏ | 51069/61904 [3:43:32<4:07:15, 1.37s/it] 82%|████████▏ | 51070/61904 [3:43:33<4:00:20, 1.33s/it] 83%|████████▎ | 51071/61904 [3:43:34<4:01:16, 1.34s/it] 83%|████████▎ | 51072/61904 [3:43:35<3:58:10, 1.32s/it] 83%|████████▎ | 51073/61904 [3:43:37<4:05:04, 1.36s/it] 83%|████████▎ | 51074/61904 [3:43:38<4:10:03, 1.39s/it] 83%|████████▎ | 51075/61904 [3:43:40<4:18:47, 1.43s/it] 83%|████████▎ | 51076/61904 [3:43:41<4:11:42, 1.39s/it] 83%|████████▎ | 51077/61904 [3:43:42<4:08:35, 1.38s/it] 83%|████████▎ | 51078/61904 [3:43:44<4:03:19, 1.35s/it] 83%|████████▎ | 51079/61904 [3:43:45<3:59:59, 1.33s/it] 83%|████████▎ | 51080/61904 [3:43:46<3:59:25, 1.33s/it] {'loss': 2.4556, 'learning_rate': 1.175418125243096e-07, 'epoch': 13.2} + 83%|████████▎ | 51080/61904 [3:43:46<3:59:25, 1.33s/it] 83%|████████▎ | 51081/61904 [3:43:48<4:08:49, 1.38s/it] 83%|████████▎ | 51082/61904 [3:43:49<4:04:27, 1.36s/it] 83%|████████▎ | 51083/61904 [3:43:51<4:07:05, 1.37s/it] 83%|████████▎ | 51084/61904 [3:43:52<3:59:33, 1.33s/it] 83%|████████▎ | 51085/61904 [3:43:53<4:02:29, 1.34s/it] 83%|████████▎ | 51086/61904 [3:43:55<4:09:47, 1.39s/it] 83%|████████▎ | 51087/61904 [3:43:56<4:16:08, 1.42s/it] 83%|████████▎ | 51088/61904 [3:43:58<4:14:59, 1.41s/it] 83%|████████▎ | 51089/61904 [3:43:59<4:09:24, 1.38s/it] 83%|████████▎ | 51090/61904 [3:44:00<4:04:43, 1.36s/it] 83%|████████▎ | 51091/61904 [3:44:02<4:09:03, 1.38s/it] 83%|████████▎ | 51092/61904 [3:44:03<4:21:30, 1.45s/it] 83%|████████▎ | 51093/61904 [3:44:05<4:15:21, 1.42s/it] 83%|████████▎ | 51094/61904 [3:44:06<4:09:03, 1.38s/it] 83%|████████▎ | 51095/61904 [3:44:07<4:04:26, 1.36s/it] 83%|████████▎ | 51096/61904 [3:44:08<4:00:22, 1.33s/it] 83%|████████▎ | 51097/61904 [3:44:10<3:59:21, 1.33s/it] 83%|████████▎ | 51098/61904 [3:44:11<4:00:10, 1.33s/it] 83%|████████▎ | 51099/61904 [3:44:13<4:10:06, 1.39s/it] 83%|████████▎ | 51100/61904 [3:44:14<4:05:12, 1.36s/it] {'loss': 2.4307, 'learning_rate': 1.1750939971476726e-07, 'epoch': 13.21} + 83%|████████▎ | 51100/61904 [3:44:14<4:05:12, 1.36s/it] 83%|████████▎ | 51101/61904 [3:44:15<3:58:50, 1.33s/it] 83%|████████▎ | 51102/61904 [3:44:17<4:01:29, 1.34s/it] 83%|████████▎ | 51103/61904 [3:44:18<3:59:09, 1.33s/it] 83%|████████▎ | 51104/61904 [3:44:19<3:53:39, 1.30s/it] 83%|████████▎ | 51105/61904 [3:44:21<4:05:23, 1.36s/it] 83%|████████▎ | 51106/61904 [3:44:22<4:10:51, 1.39s/it] 83%|████████▎ | 51107/61904 [3:44:23<4:07:46, 1.38s/it] 83%|████████▎ | 51108/61904 [3:44:25<4:21:20, 1.45s/it] 83%|████████▎ | 51109/61904 [3:44:26<4:10:48, 1.39s/it] 83%|████████▎ | 51110/61904 [3:44:28<4:06:53, 1.37s/it] 83%|████████▎ | 51111/61904 [3:44:29<4:04:19, 1.36s/it] 83%|████████▎ | 51112/61904 [3:44:30<4:05:08, 1.36s/it] 83%|████████▎ | 51113/61904 [3:44:32<4:04:13, 1.36s/it] 83%|████████▎ | 51114/61904 [3:44:33<4:06:26, 1.37s/it] 83%|████████▎ | 51115/61904 [3:44:34<4:03:31, 1.35s/it] 83%|████████▎ | 51116/61904 [3:44:36<4:00:58, 1.34s/it] 83%|████████▎ | 51117/61904 [3:44:37<4:10:42, 1.39s/it] 83%|████████▎ | 51118/61904 [3:44:38<4:04:34, 1.36s/it] 83%|████████▎ | 51119/61904 [3:44:40<4:04:56, 1.36s/it] 83%|████████▎ | 51120/61904 [3:44:41<4:09:29, 1.39s/it] {'loss': 2.4733, 'learning_rate': 1.1747698690522493e-07, 'epoch': 13.21} + 83%|████████▎ | 51120/61904 [3:44:41<4:09:29, 1.39s/it] 83%|████████▎ | 51121/61904 [3:44:43<4:10:45, 1.40s/it] 83%|████████▎ | 51122/61904 [3:44:44<4:07:49, 1.38s/it] 83%|████████▎ | 51123/61904 [3:44:46<4:13:04, 1.41s/it] 83%|████████▎ | 51124/61904 [3:44:47<4:06:57, 1.37s/it] 83%|████████▎ | 51125/61904 [3:44:48<4:07:34, 1.38s/it] 83%|████████▎ | 51126/61904 [3:44:50<4:07:44, 1.38s/it] 83%|████████▎ | 51127/61904 [3:44:51<4:08:12, 1.38s/it] 83%|████████▎ | 51128/61904 [3:44:52<4:07:39, 1.38s/it] 83%|████████▎ | 51129/61904 [3:44:54<4:07:20, 1.38s/it] 83%|████████▎ | 51130/61904 [3:44:55<4:07:01, 1.38s/it] 83%|████████▎ | 51131/61904 [3:44:56<4:00:31, 1.34s/it] 83%|████████▎ | 51132/61904 [3:44:58<4:02:16, 1.35s/it] 83%|████████▎ | 51133/61904 [3:44:59<4:01:54, 1.35s/it] 83%|████████▎ | 51134/61904 [3:45:01<4:15:52, 1.43s/it] 83%|████████▎ | 51135/61904 [3:45:02<4:11:06, 1.40s/it] 83%|████████▎ | 51136/61904 [3:45:03<4:09:37, 1.39s/it] 83%|████████▎ | 51137/61904 [3:45:05<4:08:20, 1.38s/it] 83%|████████▎ | 51138/61904 [3:45:06<4:09:32, 1.39s/it] 83%|████████▎ | 51139/61904 [3:45:07<4:02:57, 1.35s/it] 83%|████████▎ | 51140/61904 [3:45:09<3:59:59, 1.34s/it] {'loss': 2.4003, 'learning_rate': 1.1744457409568261e-07, 'epoch': 13.22} + 83%|████████▎ | 51140/61904 [3:45:09<3:59:59, 1.34s/it] 83%|████████▎ | 51141/61904 [3:45:10<4:04:17, 1.36s/it] 83%|████████▎ | 51142/61904 [3:45:12<4:09:19, 1.39s/it] 83%|████████▎ | 51143/61904 [3:45:13<4:04:30, 1.36s/it] 83%|████████▎ | 51144/61904 [3:45:14<4:08:44, 1.39s/it] 83%|████████▎ | 51145/61904 [3:45:16<4:01:13, 1.35s/it] 83%|████████▎ | 51146/61904 [3:45:17<4:02:33, 1.35s/it] 83%|████████▎ | 51147/61904 [3:45:18<3:55:32, 1.31s/it] 83%|████████▎ | 51148/61904 [3:45:20<3:58:56, 1.33s/it] 83%|████████▎ | 51149/61904 [3:45:21<4:06:17, 1.37s/it] 83%|████████▎ | 51150/61904 [3:45:23<4:17:45, 1.44s/it] 83%|████████▎ | 51151/61904 [3:45:24<4:20:00, 1.45s/it] 83%|████████▎ | 51152/61904 [3:45:26<4:18:59, 1.45s/it] 83%|████████▎ | 51153/61904 [3:45:27<4:17:20, 1.44s/it] 83%|████████▎ | 51154/61904 [3:45:28<4:12:58, 1.41s/it] 83%|████████▎ | 51155/61904 [3:45:30<4:04:51, 1.37s/it] 83%|████████▎ | 51156/61904 [3:45:31<4:01:50, 1.35s/it] 83%|████████▎ | 51157/61904 [3:45:32<4:08:30, 1.39s/it] 83%|████████▎ | 51158/61904 [3:45:34<4:09:41, 1.39s/it] 83%|████████▎ | 51159/61904 [3:45:35<4:10:25, 1.40s/it] 83%|████████▎ | 51160/61904 [3:45:37<4:18:45, 1.45s/it] {'loss': 2.4786, 'learning_rate': 1.1741216128614027e-07, 'epoch': 13.22} + 83%|████████▎ | 51160/61904 [3:45:37<4:18:45, 1.45s/it] 83%|████████▎ | 51161/61904 [3:45:38<4:13:35, 1.42s/it] 83%|████████▎ | 51162/61904 [3:45:39<4:08:45, 1.39s/it] 83%|████████▎ | 51163/61904 [3:45:41<4:05:42, 1.37s/it] 83%|████████▎ | 51164/61904 [3:45:42<4:06:51, 1.38s/it] 83%|████████▎ | 51165/61904 [3:45:43<4:04:02, 1.36s/it] 83%|████████▎ | 51166/61904 [3:45:45<4:03:24, 1.36s/it] 83%|████████▎ | 51167/61904 [3:45:46<4:09:06, 1.39s/it] 83%|████████▎ | 51168/61904 [3:45:48<4:12:46, 1.41s/it] 83%|████████▎ | 51169/61904 [3:45:49<4:12:49, 1.41s/it] 83%|████████▎ | 51170/61904 [3:45:50<4:08:36, 1.39s/it] 83%|████████▎ | 51171/61904 [3:45:52<4:08:07, 1.39s/it] 83%|████████▎ | 51172/61904 [3:45:53<4:06:02, 1.38s/it] 83%|████████▎ | 51173/61904 [3:45:55<4:04:45, 1.37s/it] 83%|████████▎ | 51174/61904 [3:45:56<4:10:44, 1.40s/it] 83%|████████▎ | 51175/61904 [3:45:57<4:06:25, 1.38s/it] 83%|████████▎ | 51176/61904 [3:45:59<4:01:12, 1.35s/it] 83%|████████▎ | 51177/61904 [3:46:00<4:13:08, 1.42s/it] 83%|████████▎ | 51178/61904 [3:46:02<4:06:44, 1.38s/it] 83%|████████▎ | 51179/61904 [3:46:03<4:08:17, 1.39s/it] 83%|████████▎ | 51180/61904 [3:46:04<3:59:13, 1.34s/it] {'loss': 2.4754, 'learning_rate': 1.1737974847659795e-07, 'epoch': 13.23} + 83%|████████▎ | 51180/61904 [3:46:04<3:59:13, 1.34s/it] 83%|████████▎ | 51181/61904 [3:46:06<4:00:29, 1.35s/it] 83%|████████▎ | 51182/61904 [3:46:07<4:00:47, 1.35s/it] 83%|████████▎ | 51183/61904 [3:46:08<4:02:12, 1.36s/it] 83%|████████▎ | 51184/61904 [3:46:10<4:05:07, 1.37s/it] 83%|████████▎ | 51185/61904 [3:46:11<3:58:59, 1.34s/it] 83%|████████▎ | 51186/61904 [3:46:12<3:54:54, 1.32s/it] 83%|████████▎ | 51187/61904 [3:46:13<3:54:43, 1.31s/it] 83%|████████▎ | 51188/61904 [3:46:15<3:58:25, 1.34s/it] 83%|████████▎ | 51189/61904 [3:46:16<3:55:22, 1.32s/it] 83%|████████▎ | 51190/61904 [3:46:18<4:10:02, 1.40s/it] 83%|████████▎ | 51191/61904 [3:46:19<4:08:41, 1.39s/it] 83%|████████▎ | 51192/61904 [3:46:21<4:10:29, 1.40s/it] 83%|████████▎ | 51193/61904 [3:46:22<4:08:20, 1.39s/it] 83%|████████▎ | 51194/61904 [3:46:23<4:09:27, 1.40s/it] 83%|████████▎ | 51195/61904 [3:46:25<4:05:28, 1.38s/it] 83%|████████▎ | 51196/61904 [3:46:26<4:03:53, 1.37s/it] 83%|████████▎ | 51197/61904 [3:46:27<4:09:03, 1.40s/it] 83%|████████▎ | 51198/61904 [3:46:29<4:15:46, 1.43s/it] 83%|████████▎ | 51199/61904 [3:46:30<4:17:57, 1.45s/it] 83%|████████▎ | 51200/61904 [3:46:32<4:16:40, 1.44s/it] {'loss': 2.4504, 'learning_rate': 1.1734733566705561e-07, 'epoch': 13.23} + 83%|████████▎ | 51200/61904 [3:46:32<4:16:40, 1.44s/it] 83%|████████▎ | 51201/61904 [3:46:33<4:27:09, 1.50s/it] 83%|████████▎ | 51202/61904 [3:46:35<4:27:08, 1.50s/it] 83%|████████▎ | 51203/61904 [3:46:36<4:15:43, 1.43s/it] 83%|████████▎ | 51204/61904 [3:46:38<4:06:19, 1.38s/it] 83%|████████▎ | 51205/61904 [3:46:39<4:05:34, 1.38s/it] 83%|████████▎ | 51206/61904 [3:46:40<4:03:12, 1.36s/it] 83%|████████▎ | 51207/61904 [3:46:42<4:03:54, 1.37s/it] 83%|████████▎ | 51208/61904 [3:46:43<4:08:54, 1.40s/it] 83%|████████▎ | 51209/61904 [3:46:44<4:07:51, 1.39s/it] 83%|████████▎ | 51210/61904 [3:46:46<4:09:11, 1.40s/it] 83%|████████▎ | 51211/61904 [3:46:47<3:59:20, 1.34s/it] 83%|████████▎ | 51212/61904 [3:46:49<4:03:36, 1.37s/it] 83%|████████▎ | 51213/61904 [3:46:50<3:57:11, 1.33s/it] 83%|████████▎ | 51214/61904 [3:46:51<4:03:52, 1.37s/it] 83%|████████▎ | 51215/61904 [3:46:53<4:08:42, 1.40s/it] 83%|████████▎ | 51216/61904 [3:46:54<4:10:56, 1.41s/it] 83%|████████▎ | 51217/61904 [3:46:55<4:04:38, 1.37s/it] 83%|████████▎ | 51218/61904 [3:46:57<3:59:29, 1.34s/it] 83%|████████▎ | 51219/61904 [3:46:58<4:01:05, 1.35s/it] 83%|████████▎ | 51220/61904 [3:47:00<4:06:40, 1.39s/it] {'loss': 2.3622, 'learning_rate': 1.1731492285751328e-07, 'epoch': 13.24} + 83%|████████▎ | 51220/61904 [3:47:00<4:06:40, 1.39s/it] 83%|████████▎ | 51221/61904 [3:47:01<4:04:22, 1.37s/it] 83%|████████▎ | 51222/61904 [3:47:02<4:06:16, 1.38s/it] 83%|████████▎ | 51223/61904 [3:47:04<4:03:53, 1.37s/it] 83%|████████▎ | 51224/61904 [3:47:05<4:05:22, 1.38s/it] 83%|████████▎ | 51225/61904 [3:47:06<4:03:04, 1.37s/it] 83%|████████▎ | 51226/61904 [3:47:08<4:03:38, 1.37s/it] 83%|████████▎ | 51227/61904 [3:47:09<4:09:22, 1.40s/it] 83%|████████▎ | 51228/61904 [3:47:11<4:10:20, 1.41s/it] 83%|████████▎ | 51229/61904 [3:47:12<4:04:23, 1.37s/it] 83%|████████▎ | 51230/61904 [3:47:13<4:04:28, 1.37s/it] 83%|████████▎ | 51231/61904 [3:47:15<3:58:57, 1.34s/it] 83%|████████▎ | 51232/61904 [3:47:16<4:02:43, 1.36s/it] 83%|████████▎ | 51233/61904 [3:47:18<4:15:30, 1.44s/it] 83%|████████▎ | 51234/61904 [3:47:19<4:17:18, 1.45s/it] 83%|████████▎ | 51235/61904 [3:47:20<4:08:00, 1.39s/it] 83%|████████▎ | 51236/61904 [3:47:22<4:15:36, 1.44s/it] 83%|████████▎ | 51237/61904 [3:47:23<4:09:40, 1.40s/it] 83%|████████▎ | 51238/61904 [3:47:25<4:17:21, 1.45s/it] 83%|████████▎ | 51239/61904 [3:47:26<4:11:29, 1.41s/it] 83%|████████▎ | 51240/61904 [3:47:27<4:09:55, 1.41s/it] {'loss': 2.4765, 'learning_rate': 1.1728251004797094e-07, 'epoch': 13.24} + 83%|████████▎ | 51240/61904 [3:47:27<4:09:55, 1.41s/it] 83%|████████▎ | 51241/61904 [3:47:29<4:02:53, 1.37s/it] 83%|████████▎ | 51242/61904 [3:47:30<4:03:14, 1.37s/it] 83%|████████▎ | 51243/61904 [3:47:31<4:02:11, 1.36s/it] 83%|████████▎ | 51244/61904 [3:47:33<4:11:48, 1.42s/it] 83%|████████▎ | 51245/61904 [3:47:34<4:11:00, 1.41s/it] 83%|████████▎ | 51246/61904 [3:47:36<4:04:35, 1.38s/it] 83%|████████▎ | 51247/61904 [3:47:37<4:04:07, 1.37s/it] 83%|████████▎ | 51248/61904 [3:47:39<4:09:03, 1.40s/it] 83%|████████▎ | 51249/61904 [3:47:40<4:04:15, 1.38s/it] 83%|████████▎ | 51250/61904 [3:47:41<4:05:58, 1.39s/it] 83%|████████▎ | 51251/61904 [3:47:43<4:06:33, 1.39s/it] 83%|████████▎ | 51252/61904 [3:47:44<4:12:55, 1.42s/it] 83%|████████▎ | 51253/61904 [3:47:46<4:18:08, 1.45s/it] 83%|████████▎ | 51254/61904 [3:47:47<4:18:24, 1.46s/it] 83%|████████▎ | 51255/61904 [3:47:49<4:19:15, 1.46s/it] 83%|████████▎ | 51256/61904 [3:47:50<4:17:44, 1.45s/it] 83%|████████▎ | 51257/61904 [3:47:51<4:15:49, 1.44s/it] 83%|████████▎ | 51258/61904 [3:47:53<4:08:35, 1.40s/it] 83%|████████▎ | 51259/61904 [3:47:54<4:15:11, 1.44s/it] 83%|████████▎ | 51260/61904 [3:47:56<4:14:37, 1.44s/it] {'loss': 2.5202, 'learning_rate': 1.1725009723842862e-07, 'epoch': 13.25} + 83%|████████▎ | 51260/61904 [3:47:56<4:14:37, 1.44s/it] 83%|████████▎ | 51261/61904 [3:47:57<4:07:17, 1.39s/it] 83%|████████▎ | 51262/61904 [3:47:58<4:03:01, 1.37s/it] 83%|████████▎ | 51263/61904 [3:48:00<3:59:14, 1.35s/it] 83%|████████▎ | 51264/61904 [3:48:01<4:00:49, 1.36s/it] 83%|████████▎ | 51265/61904 [3:48:03<4:10:24, 1.41s/it] 83%|████████▎ | 51266/61904 [3:48:04<4:02:20, 1.37s/it] 83%|████████▎ | 51267/61904 [3:48:05<4:06:59, 1.39s/it] 83%|████████▎ | 51268/61904 [3:48:07<4:08:27, 1.40s/it] 83%|████████▎ | 51269/61904 [3:48:08<4:01:15, 1.36s/it] 83%|████████▎ | 51270/61904 [3:48:09<4:02:36, 1.37s/it] 83%|████████▎ | 51271/61904 [3:48:11<4:03:02, 1.37s/it] 83%|████████▎ | 51272/61904 [3:48:12<3:57:17, 1.34s/it] 83%|████████▎ | 51273/61904 [3:48:13<3:58:28, 1.35s/it] 83%|████████▎ | 51274/61904 [3:48:15<4:08:18, 1.40s/it] 83%|████████▎ | 51275/61904 [3:48:16<4:00:44, 1.36s/it] 83%|████████▎ | 51276/61904 [3:48:18<4:04:47, 1.38s/it] 83%|████████▎ | 51277/61904 [3:48:19<4:11:25, 1.42s/it] 83%|████████▎ | 51278/61904 [3:48:20<4:05:09, 1.38s/it] 83%|████████▎ | 51279/61904 [3:48:22<4:13:40, 1.43s/it] 83%|████████▎ | 51280/61904 [3:48:23<4:07:17, 1.40s/it] {'loss': 2.4383, 'learning_rate': 1.1721768442888628e-07, 'epoch': 13.25} + 83%|████████▎ | 51280/61904 [3:48:23<4:07:17, 1.40s/it] 83%|████████▎ | 51281/61904 [3:48:25<4:02:12, 1.37s/it] 83%|████████▎ | 51282/61904 [3:48:26<3:55:51, 1.33s/it] 83%|████████▎ | 51283/61904 [3:48:27<3:55:55, 1.33s/it] 83%|████████▎ | 51284/61904 [3:48:28<3:54:36, 1.33s/it] 83%|████████▎ | 51285/61904 [3:48:30<3:58:29, 1.35s/it] 83%|████████▎ | 51286/61904 [3:48:31<4:00:17, 1.36s/it] 83%|████████▎ | 51287/61904 [3:48:33<3:58:05, 1.35s/it] 83%|████████▎ | 51288/61904 [3:48:34<4:09:41, 1.41s/it] 83%|████████▎ | 51289/61904 [3:48:35<4:04:42, 1.38s/it] 83%|████████▎ | 51290/61904 [3:48:37<4:03:55, 1.38s/it] 83%|████████▎ | 51291/61904 [3:48:38<4:00:36, 1.36s/it] 83%|████████▎ | 51292/61904 [3:48:39<3:58:08, 1.35s/it] 83%|████████▎ | 51293/61904 [3:48:41<4:02:57, 1.37s/it] 83%|████████▎ | 51294/61904 [3:48:42<4:08:06, 1.40s/it] 83%|████████▎ | 51295/61904 [3:48:44<4:02:43, 1.37s/it] 83%|████████▎ | 51296/61904 [3:48:45<3:57:02, 1.34s/it] 83%|████████▎ | 51297/61904 [3:48:46<3:58:31, 1.35s/it] 83%|████████▎ | 51298/61904 [3:48:48<4:05:30, 1.39s/it] 83%|████████▎ | 51299/61904 [3:48:49<4:08:07, 1.40s/it] 83%|████████▎ | 51300/61904 [3:48:51<4:06:04, 1.39s/it] {'loss': 2.4267, 'learning_rate': 1.1718527161934396e-07, 'epoch': 13.26} + 83%|████████▎ | 51300/61904 [3:48:51<4:06:04, 1.39s/it] 83%|████████▎ | 51301/61904 [3:48:52<4:04:14, 1.38s/it] 83%|████████▎ | 51302/61904 [3:48:53<4:09:05, 1.41s/it] 83%|████████▎ | 51303/61904 [3:48:55<4:15:56, 1.45s/it] 83%|████████▎ | 51304/61904 [3:48:56<4:09:36, 1.41s/it] 83%|████████▎ | 51305/61904 [3:48:58<4:04:30, 1.38s/it] 83%|████████▎ | 51306/61904 [3:48:59<4:12:23, 1.43s/it] 83%|████████▎ | 51307/61904 [3:49:00<4:06:21, 1.39s/it] 83%|████████▎ | 51308/61904 [3:49:02<4:03:55, 1.38s/it] 83%|████████▎ | 51309/61904 [3:49:03<4:15:46, 1.45s/it] 83%|████████▎ | 51310/61904 [3:49:05<4:09:23, 1.41s/it] 83%|████████▎ | 51311/61904 [3:49:06<4:16:46, 1.45s/it] 83%|████████▎ | 51312/61904 [3:49:08<4:06:59, 1.40s/it] 83%|████████▎ | 51313/61904 [3:49:09<4:05:04, 1.39s/it] 83%|████████▎ | 51314/61904 [3:49:10<3:59:50, 1.36s/it] 83%|████████▎ | 51315/61904 [3:49:12<4:00:42, 1.36s/it] 83%|████████▎ | 51316/61904 [3:49:13<4:00:09, 1.36s/it] 83%|████████▎ | 51317/61904 [3:49:14<3:59:13, 1.36s/it] 83%|████████▎ | 51318/61904 [3:49:16<3:58:42, 1.35s/it] 83%|████████▎ | 51319/61904 [3:49:17<3:56:27, 1.34s/it] 83%|████████▎ | 51320/61904 [3:49:18<4:09:05, 1.41s/it] {'loss': 2.4442, 'learning_rate': 1.1715285880980162e-07, 'epoch': 13.26} + 83%|████████▎ | 51320/61904 [3:49:18<4:09:05, 1.41s/it] 83%|████████▎ | 51321/61904 [3:49:20<4:05:27, 1.39s/it] 83%|████████▎ | 51322/61904 [3:49:21<4:11:22, 1.43s/it] 83%|████████▎ | 51323/61904 [3:49:23<4:09:19, 1.41s/it] 83%|████████▎ | 51324/61904 [3:49:24<4:07:22, 1.40s/it] 83%|████████▎ | 51325/61904 [3:49:25<3:56:41, 1.34s/it] 83%|████████▎ | 51326/61904 [3:49:27<4:01:19, 1.37s/it] 83%|████████▎ | 51327/61904 [3:49:28<4:03:19, 1.38s/it] 83%|████████▎ | 51328/61904 [3:49:30<4:07:38, 1.40s/it] 83%|████████▎ | 51329/61904 [3:49:31<4:03:05, 1.38s/it] 83%|████████▎ | 51330/61904 [3:49:32<4:11:51, 1.43s/it] 83%|████████▎ | 51331/61904 [3:49:34<4:05:59, 1.40s/it] 83%|████████▎ | 51332/61904 [3:49:35<4:05:34, 1.39s/it] 83%|████████▎ | 51333/61904 [3:49:37<4:10:55, 1.42s/it] 83%|████████▎ | 51334/61904 [3:49:38<4:16:32, 1.46s/it] 83%|████████▎ | 51335/61904 [3:49:40<4:13:30, 1.44s/it] 83%|████████▎ | 51336/61904 [3:49:41<4:10:54, 1.42s/it] 83%|████████▎ | 51337/61904 [3:49:42<4:02:47, 1.38s/it] 83%|████████▎ | 51338/61904 [3:49:44<4:08:48, 1.41s/it] 83%|████████▎ | 51339/61904 [3:49:45<4:03:18, 1.38s/it] 83%|████████▎ | 51340/61904 [3:49:47<4:08:46, 1.41s/it] {'loss': 2.4723, 'learning_rate': 1.171204460002593e-07, 'epoch': 13.27} + 83%|████████▎ | 51340/61904 [3:49:47<4:08:46, 1.41s/it] 83%|████████▎ | 51341/61904 [3:49:48<4:06:13, 1.40s/it] 83%|████████▎ | 51342/61904 [3:49:49<4:06:56, 1.40s/it] 83%|████████▎ | 51343/61904 [3:49:51<4:04:01, 1.39s/it] 83%|████████▎ | 51344/61904 [3:49:52<4:02:40, 1.38s/it] 83%|████████▎ | 51345/61904 [3:49:53<4:02:31, 1.38s/it] 83%|████████▎ | 51346/61904 [3:49:55<3:58:41, 1.36s/it] 83%|████████▎ | 51347/61904 [3:49:56<4:05:04, 1.39s/it] 83%|████████▎ | 51348/61904 [3:49:57<3:57:07, 1.35s/it] 83%|████████▎ | 51349/61904 [3:49:59<4:05:26, 1.40s/it] 83%|████████▎ | 51350/61904 [3:50:00<4:01:42, 1.37s/it] 83%|████████▎ | 51351/61904 [3:50:02<4:02:11, 1.38s/it] 83%|████████▎ | 51352/61904 [3:50:03<4:07:56, 1.41s/it] 83%|████████▎ | 51353/61904 [3:50:04<4:00:30, 1.37s/it] 83%|████████▎ | 51354/61904 [3:50:06<4:00:18, 1.37s/it] 83%|████████▎ | 51355/61904 [3:50:07<3:59:10, 1.36s/it] 83%|████████▎ | 51356/61904 [3:50:08<3:55:02, 1.34s/it] 83%|████████▎ | 51357/61904 [3:50:10<4:09:41, 1.42s/it] 83%|█��██████▎ | 51358/61904 [3:50:11<4:03:02, 1.38s/it] 83%|████████▎ | 51359/61904 [3:50:13<4:03:15, 1.38s/it] 83%|████████▎ | 51360/61904 [3:50:14<4:08:27, 1.41s/it] {'loss': 2.4552, 'learning_rate': 1.1708803319071696e-07, 'epoch': 13.27} + 83%|████████▎ | 51360/61904 [3:50:14<4:08:27, 1.41s/it] 83%|████████▎ | 51361/61904 [3:50:16<4:09:40, 1.42s/it] 83%|████████▎ | 51362/61904 [3:50:17<4:02:26, 1.38s/it] 83%|████████▎ | 51363/61904 [3:50:18<4:04:05, 1.39s/it] 83%|████████▎ | 51364/61904 [3:50:20<4:00:53, 1.37s/it] 83%|████████▎ | 51365/61904 [3:50:21<4:03:08, 1.38s/it] 83%|████████▎ | 51366/61904 [3:50:22<4:01:39, 1.38s/it] 83%|████████▎ | 51367/61904 [3:50:24<4:04:54, 1.39s/it] 83%|████████▎ | 51368/61904 [3:50:25<3:58:49, 1.36s/it] 83%|████████▎ | 51369/61904 [3:50:26<3:56:06, 1.34s/it] 83%|████████▎ | 51370/61904 [3:50:28<3:52:36, 1.32s/it] 83%|████████▎ | 51371/61904 [3:50:29<4:01:48, 1.38s/it] 83%|████████▎ | 51372/61904 [3:50:31<4:00:15, 1.37s/it] 83%|████████▎ | 51373/61904 [3:50:32<3:56:16, 1.35s/it] 83%|████████▎ | 51374/61904 [3:50:33<4:04:00, 1.39s/it] 83%|████████▎ | 51375/61904 [3:50:35<4:04:59, 1.40s/it] 83%|████████▎ | 51376/61904 [3:50:36<3:58:39, 1.36s/it] 83%|████████▎ | 51377/61904 [3:50:37<3:55:56, 1.34s/it] 83%|████████▎ | 51378/61904 [3:50:39<3:51:47, 1.32s/it] 83%|████████▎ | 51379/61904 [3:50:40<4:01:33, 1.38s/it] 83%|████████▎ | 51380/61904 [3:50:42<4:05:28, 1.40s/it] {'loss': 2.4261, 'learning_rate': 1.1705562038117463e-07, 'epoch': 13.28} + 83%|████████▎ | 51380/61904 [3:50:42<4:05:28, 1.40s/it] 83%|████████▎ | 51381/61904 [3:50:43<4:05:19, 1.40s/it] 83%|████████▎ | 51382/61904 [3:50:44<4:11:21, 1.43s/it] 83%|████████▎ | 51383/61904 [3:50:46<4:09:23, 1.42s/it] 83%|████████▎ | 51384/61904 [3:50:47<4:06:06, 1.40s/it] 83%|████████▎ | 51385/61904 [3:50:49<4:06:44, 1.41s/it] 83%|████████▎ | 51386/61904 [3:50:50<4:02:40, 1.38s/it] 83%|████████▎ | 51387/61904 [3:50:51<4:00:02, 1.37s/it] 83%|████████▎ | 51388/61904 [3:50:53<4:03:40, 1.39s/it] 83%|████████▎ | 51389/61904 [3:50:54<4:04:44, 1.40s/it] 83%|████████▎ | 51390/61904 [3:50:55<4:00:13, 1.37s/it] 83%|████████▎ | 51391/61904 [3:50:57<4:02:46, 1.39s/it] 83%|████████▎ | 51392/61904 [3:50:58<3:58:24, 1.36s/it] 83%|████████▎ | 51393/61904 [3:51:00<3:59:20, 1.37s/it] 83%|████████▎ | 51394/61904 [3:51:01<4:02:10, 1.38s/it] 83%|████████▎ | 51395/61904 [3:51:02<4:03:37, 1.39s/it] 83%|████████▎ | 51396/61904 [3:51:04<4:06:05, 1.41s/it] 83%|████████▎ | 51397/61904 [3:51:05<4:13:55, 1.45s/it] 83%|████████▎ | 51398/61904 [3:51:07<4:11:55, 1.44s/it] 83%|████████▎ | 51399/61904 [3:51:08<4:09:02, 1.42s/it] 83%|████████▎ | 51400/61904 [3:51:09<4:02:16, 1.38s/it] {'loss': 2.3728, 'learning_rate': 1.1702320757163229e-07, 'epoch': 13.28} + 83%|████████▎ | 51400/61904 [3:51:09<4:02:16, 1.38s/it] 83%|████████▎ | 51401/61904 [3:51:11<4:05:58, 1.41s/it] 83%|████████▎ | 51402/61904 [3:51:12<4:01:15, 1.38s/it] 83%|████████▎ | 51403/61904 [3:51:14<4:26:48, 1.52s/it] 83%|████████▎ | 51404/61904 [3:51:15<4:18:29, 1.48s/it] 83%|████████▎ | 51405/61904 [3:51:17<4:11:55, 1.44s/it] 83%|████████▎ | 51406/61904 [3:51:18<4:09:52, 1.43s/it] 83%|████████▎ | 51407/61904 [3:51:20<4:03:15, 1.39s/it] 83%|████████▎ | 51408/61904 [3:51:21<4:06:51, 1.41s/it] 83%|████████▎ | 51409/61904 [3:51:23<4:11:39, 1.44s/it] 83%|████████▎ | 51410/61904 [3:51:24<4:05:49, 1.41s/it] 83%|████████▎ | 51411/61904 [3:51:25<4:06:35, 1.41s/it] 83%|████████▎ | 51412/61904 [3:51:27<4:06:21, 1.41s/it] 83%|████████▎ | 51413/61904 [3:51:28<4:02:18, 1.39s/it] 83%|████████▎ | 51414/61904 [3:51:29<4:05:36, 1.40s/it] 83%|████████▎ | 51415/61904 [3:51:31<4:02:58, 1.39s/it] 83%|████████▎ | 51416/61904 [3:51:32<3:58:23, 1.36s/it] 83%|███��████▎ | 51417/61904 [3:51:34<4:09:07, 1.43s/it] 83%|████████▎ | 51418/61904 [3:51:35<4:16:14, 1.47s/it] 83%|████████▎ | 51419/61904 [3:51:37<4:15:19, 1.46s/it] 83%|████████▎ | 51420/61904 [3:51:38<4:26:12, 1.52s/it] {'loss': 2.4434, 'learning_rate': 1.1699079476208997e-07, 'epoch': 13.29} + 83%|████████▎ | 51420/61904 [3:51:38<4:26:12, 1.52s/it] 83%|████████▎ | 51421/61904 [3:51:40<4:18:57, 1.48s/it] 83%|████████▎ | 51422/61904 [3:51:41<4:12:13, 1.44s/it] 83%|████████▎ | 51423/61904 [3:51:43<4:11:58, 1.44s/it] 83%|████████▎ | 51424/61904 [3:51:44<4:13:55, 1.45s/it] 83%|████████▎ | 51425/61904 [3:51:46<4:22:35, 1.50s/it] 83%|████████▎ | 51426/61904 [3:51:47<4:15:32, 1.46s/it] 83%|████████▎ | 51427/61904 [3:51:48<4:13:15, 1.45s/it] 83%|████████▎ | 51428/61904 [3:51:50<4:09:51, 1.43s/it] 83%|████████▎ | 51429/61904 [3:51:51<4:07:38, 1.42s/it] 83%|████████▎ | 51430/61904 [3:51:53<4:05:29, 1.41s/it] 83%|████████▎ | 51431/61904 [3:51:54<4:03:02, 1.39s/it] 83%|████████▎ | 51432/61904 [3:51:55<3:58:56, 1.37s/it] 83%|████████▎ | 51433/61904 [3:51:57<3:56:03, 1.35s/it] 83%|████████▎ | 51434/61904 [3:51:58<3:57:53, 1.36s/it] 83%|████████▎ | 51435/61904 [3:51:59<3:57:43, 1.36s/it] 83%|████████▎ | 51436/61904 [3:52:01<3:57:45, 1.36s/it] 83%|████████▎ | 51437/61904 [3:52:02<3:55:22, 1.35s/it] 83%|████████▎ | 51438/61904 [3:52:03<3:54:51, 1.35s/it] 83%|████████▎ | 51439/61904 [3:52:05<3:51:58, 1.33s/it] 83%|████████▎ | 51440/61904 [3:52:06<3:53:02, 1.34s/it] {'loss': 2.433, 'learning_rate': 1.1695838195254763e-07, 'epoch': 13.3} + 83%|████████▎ | 51440/61904 [3:52:06<3:53:02, 1.34s/it] 83%|████████▎ | 51441/61904 [3:52:07<3:56:17, 1.36s/it] 83%|████████▎ | 51442/61904 [3:52:09<3:55:58, 1.35s/it] 83%|████████▎ | 51443/61904 [3:52:10<4:01:35, 1.39s/it] 83%|████████▎ | 51444/61904 [3:52:12<4:11:15, 1.44s/it] 83%|████████▎ | 51445/61904 [3:52:13<3:59:53, 1.38s/it] 83%|████████▎ | 51446/61904 [3:52:14<3:58:47, 1.37s/it] 83%|████████▎ | 51447/61904 [3:52:16<3:57:43, 1.36s/it] 83%|████████▎ | 51448/61904 [3:52:17<4:04:14, 1.40s/it] 83%|████████▎ | 51449/61904 [3:52:19<4:04:04, 1.40s/it] 83%|████████▎ | 51450/61904 [3:52:20<3:58:52, 1.37s/it] 83%|████████▎ | 51451/61904 [3:52:21<4:03:33, 1.40s/it] 83%|████████▎ | 51452/61904 [3:52:23<3:59:51, 1.38s/it] 83%|████████▎ | 51453/61904 [3:52:24<4:06:58, 1.42s/it] 83%|████████▎ | 51454/61904 [3:52:26<4:03:49, 1.40s/it] 83%|████████▎ | 51455/61904 [3:52:27<4:03:32, 1.40s/it] 83%|████████▎ | 51456/61904 [3:52:28<3:59:00, 1.37s/it] 83%|████████▎ | 51457/61904 [3:52:30<4:04:14, 1.40s/it] 83%|████████▎ | 51458/61904 [3:52:31<4:02:32, 1.39s/it] 83%|████████▎ | 51459/61904 [3:52:32<3:58:56, 1.37s/it] 83%|████████▎ | 51460/61904 [3:52:34<4:01:59, 1.39s/it] {'loss': 2.4091, 'learning_rate': 1.169259691430053e-07, 'epoch': 13.3} + 83%|████████▎ | 51460/61904 [3:52:34<4:01:59, 1.39s/it] 83%|████████▎ | 51461/61904 [3:52:35<3:57:36, 1.37s/it] 83%|████████▎ | 51462/61904 [3:52:37<4:07:16, 1.42s/it] 83%|████████▎ | 51463/61904 [3:52:38<4:05:14, 1.41s/it] 83%|████████▎ | 51464/61904 [3:52:39<3:58:35, 1.37s/it] 83%|████████▎ | 51465/61904 [3:52:41<4:02:12, 1.39s/it] 83%|████████▎ | 51466/61904 [3:52:42<4:02:08, 1.39s/it] 83%|████████▎ | 51467/61904 [3:52:44<4:03:50, 1.40s/it] 83%|████████▎ | 51468/61904 [3:52:45<4:01:13, 1.39s/it] 83%|████████▎ | 51469/61904 [3:52:46<4:05:56, 1.41s/it] 83%|████████▎ | 51470/61904 [3:52:48<4:04:07, 1.40s/it] 83%|████████▎ | 51471/61904 [3:52:49<4:12:20, 1.45s/it] 83%|████████▎ | 51472/61904 [3:52:51<4:01:14, 1.39s/it] 83%|████████▎ | 51473/61904 [3:52:52<4:03:30, 1.40s/it] 83%|████████▎ | 51474/61904 [3:52:53<3:56:12, 1.36s/it] 83%|████████▎ | 51475/61904 [3:52:55<4:02:13, 1.39s/it] 83%|████████▎ | 51476/61904 [3:52:56<3:54:24, 1.35s/it] 83%|████████▎ | 51477/61904 [3:52:58<4:01:43, 1.39s/it] 83%|████████▎ | 51478/61904 [3:52:59<4:01:17, 1.39s/it] 83%|████████▎ | 51479/61904 [3:53:00<4:04:55, 1.41s/it] 83%|████████▎ | 51480/61904 [3:53:02<4:01:11, 1.39s/it] {'loss': 2.418, 'learning_rate': 1.1689355633346298e-07, 'epoch': 13.31} + 83%|████████▎ | 51480/61904 [3:53:02<4:01:11, 1.39s/it] 83%|████████▎ | 51481/61904 [3:53:03<3:56:34, 1.36s/it] 83%|████████▎ | 51482/61904 [3:53:04<3:59:27, 1.38s/it] 83%|████████▎ | 51483/61904 [3:53:06<4:03:06, 1.40s/it] 83%|████████▎ | 51484/61904 [3:53:07<3:58:54, 1.38s/it] 83%|████████▎ | 51485/61904 [3:53:08<3:53:06, 1.34s/it] 83%|████████▎ | 51486/61904 [3:53:10<3:51:41, 1.33s/it] 83%|████████▎ | 51487/61904 [3:53:11<3:48:28, 1.32s/it] 83%|████████▎ | 51488/61904 [3:53:12<3:55:01, 1.35s/it] 83%|████████▎ | 51489/61904 [3:53:14<3:50:19, 1.33s/it] 83%|████████▎ | 51490/61904 [3:53:15<3:51:25, 1.33s/it] 83%|████████▎ | 51491/61904 [3:53:16<3:52:37, 1.34s/it] 83%|████████▎ | 51492/61904 [3:53:18<3:55:24, 1.36s/it] 83%|████████▎ | 51493/61904 [3:53:19<3:58:17, 1.37s/it] 83%|████████▎ | 51494/61904 [3:53:21<4:07:31, 1.43s/it] 83%|████████▎ | 51495/61904 [3:53:22<4:07:45, 1.43s/it] 83%|████████▎ | 51496/61904 [3:53:24<4:15:22, 1.47s/it] 83%|████████▎ | 51497/61904 [3:53:25<4:14:09, 1.47s/it] 83%|████████▎ | 51498/61904 [3:53:27<4:08:28, 1.43s/it] 83%|████████▎ | 51499/61904 [3:53:28<4:12:19, 1.46s/it] 83%|████████▎ | 51500/61904 [3:53:30<4:12:23, 1.46s/it] {'loss': 2.4226, 'learning_rate': 1.1686114352392064e-07, 'epoch': 13.31} + 83%|████████▎ | 51500/61904 [3:53:30<4:12:23, 1.46s/it] 83%|████████▎ | 51501/61904 [3:53:31<4:09:58, 1.44s/it] 83%|████████▎ | 51502/61904 [3:53:32<4:01:24, 1.39s/it] 83%|████████▎ | 51503/61904 [3:53:34<3:59:23, 1.38s/it] 83%|████████▎ | 51504/61904 [3:53:35<3:54:49, 1.35s/it] 83%|████████▎ | 51505/61904 [3:53:36<3:55:23, 1.36s/it] 83%|████████▎ | 51506/61904 [3:53:38<4:01:02, 1.39s/it] 83%|████████▎ | 51507/61904 [3:53:39<3:55:05, 1.36s/it] 83%|████████▎ | 51508/61904 [3:53:40<3:57:08, 1.37s/it] 83%|████████▎ | 51509/61904 [3:53:42<4:05:42, 1.42s/it] 83%|████████▎ | 51510/61904 [3:53:43<4:00:17, 1.39s/it] 83%|████████▎ | 51511/61904 [3:53:45<3:57:20, 1.37s/it] 83%|████████▎ | 51512/61904 [3:53:46<4:00:34, 1.39s/it] 83%|████████▎ | 51513/61904 [3:53:48<4:06:00, 1.42s/it] 83%|████████▎ | 51514/61904 [3:53:49<4:04:37, 1.41s/it] 83%|████████▎ | 51515/61904 [3:53:50<4:09:20, 1.44s/it] 83%|████████▎ | 51516/61904 [3:53:52<4:02:56, 1.40s/it] 83%|████████▎ | 51517/61904 [3:53:53<4:14:42, 1.47s/it] 83%|████████▎ | 51518/61904 [3:53:55<4:09:39, 1.44s/it] 83%|████████▎ | 51519/61904 [3:53:56<4:08:40, 1.44s/it] 83%|████████▎ | 51520/61904 [3:53:58<4:20:22, 1.50s/it] {'loss': 2.4603, 'learning_rate': 1.168287307143783e-07, 'epoch': 13.32} + 83%|████████▎ | 51520/61904 [3:53:58<4:20:22, 1.50s/it] 83%|████████▎ | 51521/61904 [3:53:59<4:13:59, 1.47s/it] 83%|████████▎ | 51522/61904 [3:54:01<4:03:53, 1.41s/it] 83%|████████▎ | 51523/61904 [3:54:02<3:56:51, 1.37s/it] 83%|████████▎ | 51524/61904 [3:54:03<3:54:05, 1.35s/it] 83%|████████▎ | 51525/61904 [3:54:05<3:58:44, 1.38s/it] 83%|████████▎ | 51526/61904 [3:54:06<4:06:03, 1.42s/it] 83%|████████▎ | 51527/61904 [3:54:08<4:11:41, 1.46s/it] 83%|████████▎ | 51528/61904 [3:54:09<4:09:58, 1.45s/it] 83%|████████▎ | 51529/61904 [3:54:10<4:06:01, 1.42s/it] 83%|████████▎ | 51530/61904 [3:54:12<3:54:55, 1.36s/it] 83%|████████▎ | 51531/61904 [3:54:13<3:55:01, 1.36s/it] 83%|████████▎ | 51532/61904 [3:54:14<3:58:42, 1.38s/it] 83%|████████▎ | 51533/61904 [3:54:16<3:53:54, 1.35s/it] 83%|████████▎ | 51534/61904 [3:54:17<3:51:55, 1.34s/it] 83%|████████▎ | 51535/61904 [3:54:18<3:48:40, 1.32s/it] 83%|████████▎ | 51536/61904 [3:54:20<3:46:30, 1.31s/it] 83%|████████▎ | 51537/61904 [3:54:21<3:46:13, 1.31s/it] 83%|████████▎ | 51538/61904 [3:54:22<3:53:44, 1.35s/it] 83%|████████▎ | 51539/61904 [3:54:24<3:54:25, 1.36s/it] 83%|████████▎ | 51540/61904 [3:54:25<3:58:23, 1.38s/it] {'loss': 2.4939, 'learning_rate': 1.1679631790483598e-07, 'epoch': 13.32} + 83%|████████▎ | 51540/61904 [3:54:25<3:58:23, 1.38s/it] 83%|████████▎ | 51541/61904 [3:54:26<3:53:32, 1.35s/it] 83%|████████▎ | 51542/61904 [3:54:28<4:05:13, 1.42s/it] 83%|████████▎ | 51543/61904 [3:54:29<4:02:28, 1.40s/it] 83%|████████▎ | 51544/61904 [3:54:31<4:06:35, 1.43s/it] 83%|████████▎ | 51545/61904 [3:54:32<4:00:33, 1.39s/it] 83%|████████▎ | 51546/61904 [3:54:34<4:00:59, 1.40s/it] 83%|████████▎ | 51547/61904 [3:54:35<4:09:52, 1.45s/it] 83%|████████▎ | 51548/61904 [3:54:36<4:06:02, 1.43s/it] 83%|████████▎ | 51549/61904 [3:54:38<4:11:30, 1.46s/it] 83%|████████▎ | 51550/61904 [3:54:39<4:06:13, 1.43s/it] 83%|████████▎ | 51551/61904 [3:54:41<4:09:07, 1.44s/it] 83%|████████▎ | 51552/61904 [3:54:42<3:59:29, 1.39s/it] 83%|████████▎ | 51553/61904 [3:54:44<3:59:40, 1.39s/it] 83%|████████▎ | 51554/61904 [3:54:45<3:57:03, 1.37s/it] 83%|████████▎ | 51555/61904 [3:54:46<4:02:31, 1.41s/it] 83%|████████▎ | 51556/61904 [3:54:48<3:58:34, 1.38s/it] 83%|████████▎ | 51557/61904 [3:54:49<4:01:52, 1.40s/it] 83%|████████▎ | 51558/61904 [3:54:50<4:00:45, 1.40s/it] 83%|████████▎ | 51559/61904 [3:54:52<3:52:01, 1.35s/it] 83%|████████▎ | 51560/61904 [3:54:53<3:52:50, 1.35s/it] {'loss': 2.444, 'learning_rate': 1.1676390509529365e-07, 'epoch': 13.33} + 83%|████████▎ | 51560/61904 [3:54:53<3:52:50, 1.35s/it] 83%|████████▎ | 51561/61904 [3:54:54<3:51:12, 1.34s/it] 83%|████████▎ | 51562/61904 [3:54:56<3:44:46, 1.30s/it] 83%|████████▎ | 51563/61904 [3:54:57<4:06:03, 1.43s/it] 83%|████████▎ | 51564/61904 [3:54:59<4:00:40, 1.40s/it] 83%|████████▎ | 51565/61904 [3:55:00<3:58:07, 1.38s/it] 83%|████████▎ | 51566/61904 [3:55:01<4:00:52, 1.40s/it] 83%|████████▎ | 51567/61904 [3:55:03<3:58:33, 1.38s/it] 83%|████████▎ | 51568/61904 [3:55:04<4:04:04, 1.42s/it] 83%|████████▎ | 51569/61904 [3:55:06<4:05:22, 1.42s/it] 83%|████████▎ | 51570/61904 [3:55:07<4:14:34, 1.48s/it] 83%|████████▎ | 51571/61904 [3:55:09<4:03:55, 1.42s/it] 83%|████████▎ | 51572/61904 [3:55:10<4:06:43, 1.43s/it] 83%|████████▎ | 51573/61904 [3:55:11<4:04:51, 1.42s/it] 83%|████████▎ | 51574/61904 [3:55:13<3:58:52, 1.39s/it] 83%|████████▎ | 51575/61904 [3:55:14<4:07:26, 1.44s/it] 83%|████████▎ | 51576/61904 [3:55:16<4:07:34, 1.44s/it] 83%|████████▎ | 51577/61904 [3:55:17<3:57:00, 1.38s/it] 83%|████████▎ | 51578/61904 [3:55:18<3:53:06, 1.35s/it] 83%|████████▎ | 51579/61904 [3:55:20<3:52:30, 1.35s/it] 83%|████████▎ | 51580/61904 [3:55:21<3:58:29, 1.39s/it] {'loss': 2.5078, 'learning_rate': 1.1673149228575132e-07, 'epoch': 13.33} + 83%|████████▎ | 51580/61904 [3:55:21<3:58:29, 1.39s/it] 83%|████████▎ | 51581/61904 [3:55:22<3:58:33, 1.39s/it] 83%|████████▎ | 51582/61904 [3:55:24<3:56:14, 1.37s/it] 83%|████████▎ | 51583/61904 [3:55:25<3:56:38, 1.38s/it] 83%|████████▎ | 51584/61904 [3:55:27<4:01:10, 1.40s/it] 83%|████████▎ | 51585/61904 [3:55:28<3:55:01, 1.37s/it] 83%|████████▎ | 51586/61904 [3:55:29<4:02:12, 1.41s/it] 83%|████████▎ | 51587/61904 [3:55:31<3:55:00, 1.37s/it] 83%|████████▎ | 51588/61904 [3:55:32<3:52:21, 1.35s/it] 83%|████████▎ | 51589/61904 [3:55:33<3:55:20, 1.37s/it] 83%|████████▎ | 51590/61904 [3:55:35<3:57:56, 1.38s/it] 83%|████████▎ | 51591/61904 [3:55:36<3:59:05, 1.39s/it] 83%|████████▎ | 51592/61904 [3:55:38<3:58:07, 1.39s/it] 83%|████████▎ | 51593/61904 [3:55:39<3:56:19, 1.38s/it] 83%|████████▎ | 51594/61904 [3:55:40<3:56:19, 1.38s/it] 83%|████████▎ | 51595/61904 [3:55:42<4:02:38, 1.41s/it] 83%|████████▎ | 51596/61904 [3:55:43<4:05:37, 1.43s/it] 83%|████████▎ | 51597/61904 [3:55:45<4:10:20, 1.46s/it] 83%|████████▎ | 51598/61904 [3:55:46<4:03:28, 1.42s/it] 83%|████████▎ | 51599/61904 [3:55:47<3:56:17, 1.38s/it] 83%|████████▎ | 51600/61904 [3:55:49<3:56:40, 1.38s/it] {'loss': 2.5158, 'learning_rate': 1.1669907947620898e-07, 'epoch': 13.34} + 83%|████████▎ | 51600/61904 [3:55:49<3:56:40, 1.38s/it] 83%|████████▎ | 51601/61904 [3:55:50<3:49:18, 1.34s/it] 83%|████████▎ | 51602/61904 [3:55:51<3:46:05, 1.32s/it] 83%|████████▎ | 51603/61904 [3:55:53<3:41:00, 1.29s/it] 83%|████████▎ | 51604/61904 [3:55:54<3:43:28, 1.30s/it] 83%|████████▎ | 51605/61904 [3:55:55<3:41:47, 1.29s/it] 83%|████████▎ | 51606/61904 [3:55:57<3:50:04, 1.34s/it] 83%|████████▎ | 51607/61904 [3:55:58<3:53:06, 1.36s/it] 83%|████████▎ | 51608/61904 [3:56:00<4:03:36, 1.42s/it] 83%|████████▎ | 51609/61904 [3:56:01<4:09:50, 1.46s/it] 83%|████████▎ | 51610/61904 [3:56:03<4:03:58, 1.42s/it] 83%|████████▎ | 51611/61904 [3:56:04<4:05:10, 1.43s/it] 83%|████████▎ | 51612/61904 [3:56:05<4:04:24, 1.42s/it] 83%|████████▎ | 51613/61904 [3:56:07<3:59:22, 1.40s/it] 83%|████████▎ | 51614/61904 [3:56:08<4:06:47, 1.44s/it] 83%|████████▎ | 51615/61904 [3:56:10<4:05:00, 1.43s/it] 83%|████████▎ | 51616/61904 [3:56:11<4:05:49, 1.43s/it] 83%|████████▎ | 51617/61904 [3:56:12<3:56:46, 1.38s/it] 83%|████████▎ | 51618/61904 [3:56:14<3:55:24, 1.37s/it] 83%|████████▎ | 51619/61904 [3:56:15<4:05:27, 1.43s/it] 83%|████████▎ | 51620/61904 [3:56:17<4:04:32, 1.43s/it] {'loss': 2.5183, 'learning_rate': 1.1666666666666665e-07, 'epoch': 13.34} + 83%|████████▎ | 51620/61904 [3:56:17<4:04:32, 1.43s/it] 83%|████████▎ | 51621/61904 [3:56:18<4:03:04, 1.42s/it] 83%|████████▎ | 51622/61904 [3:56:19<3:59:18, 1.40s/it] 83%|████████▎ | 51623/61904 [3:56:21<3:56:18, 1.38s/it] 83%|████████▎ | 51624/61904 [3:56:22<4:05:07, 1.43s/it] 83%|████████▎ | 51625/61904 [3:56:24<4:03:37, 1.42s/it] 83%|████████▎ | 51626/61904 [3:56:25<3:58:59, 1.40s/it] 83%|████████▎ | 51627/61904 [3:56:26<3:55:30, 1.37s/it] 83%|████████▎ | 51628/61904 [3:56:28<3:57:42, 1.39s/it] 83%|████████▎ | 51629/61904 [3:56:29<3:55:06, 1.37s/it] 83%|████████▎ | 51630/61904 [3:56:31<3:57:52, 1.39s/it] 83%|████████▎ | 51631/61904 [3:56:32<4:02:36, 1.42s/it] 83%|████████▎ | 51632/61904 [3:56:34<4:15:31, 1.49s/it] 83%|████████▎ | 51633/61904 [3:56:35<4:07:42, 1.45s/it] 83%|████████▎ | 51634/61904 [3:56:36<4:03:20, 1.42s/it] 83%|████████▎ | 51635/61904 [3:56:38<3:59:04, 1.40s/it] 83%|████████▎ | 51636/61904 [3:56:39<4:04:25, 1.43s/it] 83%|████████▎ | 51637/61904 [3:56:41<4:06:53, 1.44s/it] 83%|████████▎ | 51638/61904 [3:56:42<4:04:33, 1.43s/it] 83%|████████▎ | 51639/61904 [3:56:44<4:05:03, 1.43s/it] 83%|████████▎ | 51640/61904 [3:56:45<4:02:14, 1.42s/it] {'loss': 2.3932, 'learning_rate': 1.1663425385712433e-07, 'epoch': 13.35} + 83%|████████▎ | 51640/61904 [3:56:45<4:02:14, 1.42s/it] 83%|████████▎ | 51641/61904 [3:56:46<3:56:53, 1.38s/it] 83%|████████▎ | 51642/61904 [3:56:48<3:50:54, 1.35s/it] 83%|████████▎ | 51643/61904 [3:56:49<3:50:52, 1.35s/it] 83%|████████▎ | 51644/61904 [3:56:50<3:48:09, 1.33s/it] 83%|████████▎ | 51645/61904 [3:56:51<3:46:27, 1.32s/it] 83%|████████▎ | 51646/61904 [3:56:53<3:41:22, 1.29s/it] 83%|████████▎ | 51647/61904 [3:56:54<3:46:25, 1.32s/it] 83%|████████▎ | 51648/61904 [3:56:56<3:51:19, 1.35s/it] 83%|████████▎ | 51649/61904 [3:56:57<3:51:42, 1.36s/it] 83%|████████▎ | 51650/61904 [3:56:58<3:53:47, 1.37s/it] 83%|████████▎ | 51651/61904 [3:57:00<4:01:40, 1.41s/it] 83%|████████▎ | 51652/61904 [3:57:01<4:03:27, 1.42s/it] 83%|████████▎ | 51653/61904 [3:57:03<4:04:22, 1.43s/it] 83%|████████▎ | 51654/61904 [3:57:04<4:02:23, 1.42s/it] 83%|████████▎ | 51655/61904 [3:57:05<4:01:43, 1.42s/it] 83%|████████▎ | 51656/61904 [3:57:07<3:53:45, 1.37s/it] 83%|████████▎ | 51657/61904 [3:57:08<3:54:58, 1.38s/it] 83%|████████▎ | 51658/61904 [3:57:09<3:48:46, 1.34s/it] 83%|████████▎ | 51659/61904 [3:57:11<3:47:21, 1.33s/it] 83%|████████▎ | 51660/61904 [3:57:12<3:50:13, 1.35s/it] {'loss': 2.413, 'learning_rate': 1.1660184104758199e-07, 'epoch': 13.35} + 83%|████████▎ | 51660/61904 [3:57:12<3:50:13, 1.35s/it] 83%|████████▎ | 51661/61904 [3:57:13<3:51:52, 1.36s/it] 83%|████████▎ | 51662/61904 [3:57:15<3:54:32, 1.37s/it] 83%|████████▎ | 51663/61904 [3:57:16<3:48:56, 1.34s/it] 83%|████████▎ | 51664/61904 [3:57:18<3:49:52, 1.35s/it] 83%|████████▎ | 51665/61904 [3:57:19<3:49:18, 1.34s/it] 83%|████████▎ | 51666/61904 [3:57:20<3:46:18, 1.33s/it] 83%|████████▎ | 51667/61904 [3:57:21<3:45:51, 1.32s/it] 83%|████████▎ | 51668/61904 [3:57:23<3:49:38, 1.35s/it] 83%|████████▎ | 51669/61904 [3:57:24<3:52:11, 1.36s/it] 83%|████████▎ | 51670/61904 [3:57:26<3:49:58, 1.35s/it] 83%|████████▎ | 51671/61904 [3:57:27<3:50:57, 1.35s/it] 83%|████████▎ | 51672/61904 [3:57:28<3:55:36, 1.38s/it] 83%|████████▎ | 51673/61904 [3:57:30<3:53:39, 1.37s/it] 83%|████████▎ | 51674/61904 [3:57:31<3:53:47, 1.37s/it] 83%|████████▎ | 51675/61904 [3:57:33<4:01:12, 1.41s/it] 83%|████████▎ | 51676/61904 [3:57:34<3:59:10, 1.40s/it] 83%|████████▎ | 51677/61904 [3:57:35<4:01:06, 1.41s/it] 83%|████████▎ | 51678/61904 [3:57:37<3:58:19, 1.40s/it] 83%|████████▎ | 51679/61904 [3:57:38<3:57:26, 1.39s/it] 83%|████████▎ | 51680/61904 [3:57:40<3:57:18, 1.39s/it] {'loss': 2.4563, 'learning_rate': 1.1656942823803965e-07, 'epoch': 13.36} + 83%|████████▎ | 51680/61904 [3:57:40<3:57:18, 1.39s/it] 83%|████████▎ | 51681/61904 [3:57:41<3:50:49, 1.35s/it] 83%|████████▎ | 51682/61904 [3:57:42<3:50:44, 1.35s/it] 83%|████████▎ | 51683/61904 [3:57:44<4:00:25, 1.41s/it] 83%|████████▎ | 51684/61904 [3:57:45<3:57:55, 1.40s/it] 83%|████████▎ | 51685/61904 [3:57:46<3:55:48, 1.38s/it] 83%|████████▎ | 51686/61904 [3:57:48<3:57:46, 1.40s/it] 83%|████████▎ | 51687/61904 [3:57:49<3:57:13, 1.39s/it] 83%|████████▎ | 51688/61904 [3:57:51<3:56:54, 1.39s/it] 83%|████████▎ | 51689/61904 [3:57:52<3:51:53, 1.36s/it] 84%|████████▎ | 51690/61904 [3:57:53<3:59:25, 1.41s/it] 84%|████████▎ | 51691/61904 [3:57:55<4:01:33, 1.42s/it] 84%|████████▎ | 51692/61904 [3:57:56<3:53:42, 1.37s/it] 84%|████████▎ | 51693/61904 [3:57:57<3:51:16, 1.36s/it] 84%|████████▎ | 51694/61904 [3:57:59<3:48:19, 1.34s/it] 84%|████████▎ | 51695/61904 [3:58:00<3:47:57, 1.34s/it] 84%|████████▎ | 51696/61904 [3:58:01<3:49:21, 1.35s/it] 84%|████████▎ | 51697/61904 [3:58:03<3:48:09, 1.34s/it] 84%|████████▎ | 51698/61904 [3:58:04<3:51:57, 1.36s/it] 84%|████████▎ | 51699/61904 [3:58:06<3:53:38, 1.37s/it] 84%|████████▎ | 51700/61904 [3:58:07<3:58:38, 1.40s/it] {'loss': 2.4141, 'learning_rate': 1.1653701542849733e-07, 'epoch': 13.36} + 84%|████████▎ | 51700/61904 [3:58:07<3:58:38, 1.40s/it] 84%|████████▎ | 51701/61904 [3:58:09<4:01:51, 1.42s/it] 84%|████████▎ | 51702/61904 [3:58:10<4:06:08, 1.45s/it] 84%|████████▎ | 51703/61904 [3:58:11<3:59:11, 1.41s/it] 84%|████████▎ | 51704/61904 [3:58:13<3:56:41, 1.39s/it] 84%|████████▎ | 51705/61904 [3:58:14<4:01:30, 1.42s/it] 84%|████████▎ | 51706/61904 [3:58:16<4:01:07, 1.42s/it] 84%|████████▎ | 51707/61904 [3:58:17<4:06:01, 1.45s/it] 84%|████████▎ | 51708/61904 [3:58:19<4:02:51, 1.43s/it] 84%|████████▎ | 51709/61904 [3:58:20<3:57:16, 1.40s/it] 84%|████████▎ | 51710/61904 [3:58:21<4:05:01, 1.44s/it] 84%|████████▎ | 51711/61904 [3:58:23<3:58:59, 1.41s/it] 84%|████████▎ | 51712/61904 [3:58:24<3:57:58, 1.40s/it] 84%|████████▎ | 51713/61904 [3:58:25<3:50:05, 1.35s/it] 84%|████████▎ | 51714/61904 [3:58:27<3:46:21, 1.33s/it] 84%|████████▎ | 51715/61904 [3:58:28<3:45:32, 1.33s/it] 84%|████████▎ | 51716/61904 [3:58:29<3:44:28, 1.32s/it] 84%|████████▎ | 51717/61904 [3:58:31<3:43:24, 1.32s/it] 84%|████████▎ | 51718/61904 [3:58:32<3:53:43, 1.38s/it] 84%|████████▎ | 51719/61904 [3:58:33<3:51:49, 1.37s/it] 84%|████████▎ | 51720/61904 [3:58:35<3:47:26, 1.34s/it] {'loss': 2.486, 'learning_rate': 1.16504602618955e-07, 'epoch': 13.37} + 84%|████████▎ | 51720/61904 [3:58:35<3:47:26, 1.34s/it] 84%|████████▎ | 51721/61904 [3:58:36<3:45:45, 1.33s/it] 84%|████████▎ | 51722/61904 [3:58:37<3:42:37, 1.31s/it] 84%|████████▎ | 51723/61904 [3:58:39<3:49:33, 1.35s/it] 84%|████████▎ | 51724/61904 [3:58:40<3:54:05, 1.38s/it] 84%|████████▎ | 51725/61904 [3:58:42<3:55:59, 1.39s/it] 84%|████████▎ | 51726/61904 [3:58:43<3:55:43, 1.39s/it] 84%|████████▎ | 51727/61904 [3:58:44<3:52:27, 1.37s/it] 84%|████████▎ | 51728/61904 [3:58:46<3:50:22, 1.36s/it] 84%|████████▎ | 51729/61904 [3:58:47<3:47:58, 1.34s/it] 84%|████████▎ | 51730/61904 [3:58:48<3:44:30, 1.32s/it] 84%|████████▎ | 51731/61904 [3:58:50<3:47:44, 1.34s/it] 84%|████████▎ | 51732/61904 [3:58:51<3:48:21, 1.35s/it] 84%|████████▎ | 51733/61904 [3:58:52<3:49:11, 1.35s/it] 84%|████████▎ | 51734/61904 [3:58:54<3:48:22, 1.35s/it] 84%|████████▎ | 51735/61904 [3:58:55<3:45:53, 1.33s/it] 84%|████████▎ | 51736/61904 [3:58:56<3:51:54, 1.37s/it] 84%|████████▎ | 51737/61904 [3:58:58<4:01:07, 1.42s/it] 84%|████████▎ | 51738/61904 [3:58:59<3:56:34, 1.40s/it] 84%|████████▎ | 51739/61904 [3:59:01<3:56:02, 1.39s/it] 84%|████████▎ | 51740/61904 [3:59:02<3:54:03, 1.38s/it] {'loss': 2.444, 'learning_rate': 1.1647218980941266e-07, 'epoch': 13.37} + 84%|████████▎ | 51740/61904 [3:59:02<3:54:03, 1.38s/it] 84%|████████▎ | 51741/61904 [3:59:04<4:03:16, 1.44s/it] 84%|████████▎ | 51742/61904 [3:59:05<3:55:58, 1.39s/it] 84%|████████▎ | 51743/61904 [3:59:06<3:47:03, 1.34s/it] 84%|████████▎ | 51744/61904 [3:59:08<3:51:44, 1.37s/it] 84%|████████▎ | 51745/61904 [3:59:09<3:54:14, 1.38s/it] 84%|████████▎ | 51746/61904 [3:59:10<3:55:42, 1.39s/it] 84%|████████▎ | 51747/61904 [3:59:12<3:59:46, 1.42s/it] 84%|████████▎ | 51748/61904 [3:59:13<3:55:01, 1.39s/it] 84%|████████▎ | 51749/61904 [3:59:15<3:58:54, 1.41s/it] 84%|████████▎ | 51750/61904 [3:59:16<3:50:44, 1.36s/it] 84%|████████▎ | 51751/61904 [3:59:17<3:43:25, 1.32s/it] 84%|████████▎ | 51752/61904 [3:59:19<3:48:16, 1.35s/it] 84%|████████▎ | 51753/61904 [3:59:20<3:50:00, 1.36s/it] 84%|████████▎ | 51754/61904 [3:59:21<3:53:40, 1.38s/it] 84%|████████▎ | 51755/61904 [3:59:23<3:51:38, 1.37s/it] 84%|████████▎ | 51756/61904 [3:59:24<3:50:21, 1.36s/it] 84%|████████▎ | 51757/61904 [3:59:25<3:52:55, 1.38s/it] 84%|████████▎ | 51758/61904 [3:59:27<3:51:06, 1.37s/it] 84%|████████▎ | 51759/61904 [3:59:28<3:47:48, 1.35s/it] 84%|████████▎ | 51760/61904 [3:59:29<3:46:44, 1.34s/it] {'loss': 2.4608, 'learning_rate': 1.1643977699987033e-07, 'epoch': 13.38} + 84%|████████▎ | 51760/61904 [3:59:29<3:46:44, 1.34s/it] 84%|████████▎ | 51761/61904 [3:59:31<3:41:41, 1.31s/it] 84%|████████▎ | 51762/61904 [3:59:32<3:47:57, 1.35s/it] 84%|████████▎ | 51763/61904 [3:59:33<3:45:40, 1.34s/it] 84%|████████▎ | 51764/61904 [3:59:35<3:42:28, 1.32s/it] 84%|████████▎ | 51765/61904 [3:59:36<3:48:33, 1.35s/it] 84%|████████▎ | 51766/61904 [3:59:38<3:57:39, 1.41s/it] 84%|████████▎ | 51767/61904 [3:59:39<3:55:26, 1.39s/it] 84%|████████▎ | 51768/61904 [3:59:40<3:54:32, 1.39s/it] 84%|████████▎ | 51769/61904 [3:59:42<3:58:00, 1.41s/it] 84%|████████▎ | 51770/61904 [3:59:43<3:51:33, 1.37s/it] 84%|████████▎ | 51771/61904 [3:59:45<3:55:37, 1.40s/it] 84%|████████▎ | 51772/61904 [3:59:46<4:00:44, 1.43s/it] 84%|████████▎ | 51773/61904 [3:59:47<3:57:52, 1.41s/it] 84%|████████▎ | 51774/61904 [3:59:49<3:51:26, 1.37s/it] 84%|████████▎ | 51775/61904 [3:59:50<3:50:21, 1.36s/it] 84%|████████▎ | 51776/61904 [3:59:52<3:53:00, 1.38s/it] 84%|████████▎ | 51777/61904 [3:59:53<3:55:53, 1.40s/it] 84%|████████▎ | 51778/61904 [3:59:54<3:55:57, 1.40s/it] 84%|████████▎ | 51779/61904 [3:59:56<3:55:22, 1.39s/it] 84%|████████▎ | 51780/61904 [3:59:57<3:54:46, 1.39s/it] {'loss': 2.4173, 'learning_rate': 1.1640736419032801e-07, 'epoch': 13.38} + 84%|████████▎ | 51780/61904 [3:59:57<3:54:46, 1.39s/it] 84%|████████▎ | 51781/61904 [3:59:59<4:01:39, 1.43s/it] 84%|████████▎ | 51782/61904 [4:00:00<3:56:40, 1.40s/it] 84%|████████▎ | 51783/61904 [4:00:01<3:52:36, 1.38s/it] 84%|████████▎ | 51784/61904 [4:00:03<3:54:01, 1.39s/it] 84%|████████▎ | 51785/61904 [4:00:04<3:53:13, 1.38s/it] 84%|████████▎ | 51786/61904 [4:00:05<3:44:38, 1.33s/it] 84%|████████▎ | 51787/61904 [4:00:07<3:49:24, 1.36s/it] 84%|████████▎ | 51788/61904 [4:00:08<3:54:36, 1.39s/it] 84%|████████▎ | 51789/61904 [4:00:10<3:54:20, 1.39s/it] 84%|████████▎ | 51790/61904 [4:00:11<3:50:20, 1.37s/it] 84%|████████▎ | 51791/61904 [4:00:12<3:52:05, 1.38s/it] 84%|████████▎ | 51792/61904 [4:00:14<3:50:53, 1.37s/it] 84%|████████▎ | 51793/61904 [4:00:15<3:55:56, 1.40s/it] 84%|████████▎ | 51794/61904 [4:00:16<3:48:37, 1.36s/it] 84%|████████▎ | 51795/61904 [4:00:18<3:46:05, 1.34s/it] 84%|████████▎ | 51796/61904 [4:00:19<3:47:01, 1.35s/it] 84%|████████▎ | 51797/61904 [4:00:20<3:47:22, 1.35s/it] 84%|████████▎ | 51798/61904 [4:00:22<3:41:38, 1.32s/it] 84%|████████▎ | 51799/61904 [4:00:23<3:46:50, 1.35s/it] 84%|████████▎ | 51800/61904 [4:00:24<3:49:23, 1.36s/it] {'loss': 2.4247, 'learning_rate': 1.1637495138078568e-07, 'epoch': 13.39} + 84%|████████▎ | 51800/61904 [4:00:24<3:49:23, 1.36s/it] 84%|████████▎ | 51801/61904 [4:00:26<3:44:06, 1.33s/it] 84%|████████▎ | 51802/61904 [4:00:27<3:45:50, 1.34s/it] 84%|████████▎ | 51803/61904 [4:00:28<3:49:27, 1.36s/it] 84%|████████▎ | 51804/61904 [4:00:30<3:47:49, 1.35s/it] 84%|████████▎ | 51805/61904 [4:00:31<3:45:49, 1.34s/it] 84%|████████▎ | 51806/61904 [4:00:32<3:44:55, 1.34s/it] 84%|████████▎ | 51807/61904 [4:00:34<3:44:14, 1.33s/it] 84%|████████▎ | 51808/61904 [4:00:35<3:45:01, 1.34s/it] 84%|████████▎ | 51809/61904 [4:00:37<3:48:22, 1.36s/it] 84%|████████▎ | 51810/61904 [4:00:38<3:47:00, 1.35s/it] 84%|████████▎ | 51811/61904 [4:00:39<3:45:56, 1.34s/it] 84%|████████▎ | 51812/61904 [4:00:41<3:48:00, 1.36s/it] 84%|████████▎ | 51813/61904 [4:00:42<3:48:20, 1.36s/it] 84%|████████▎ | 51814/61904 [4:00:43<3:58:32, 1.42s/it] 84%|████████▎ | 51815/61904 [4:00:45<3:59:39, 1.43s/it] 84%|████████▎ | 51816/61904 [4:00:46<4:02:28, 1.44s/it] 84%|████████▎ | 51817/61904 [4:00:48<3:58:52, 1.42s/it] 84%|████████▎ | 51818/61904 [4:00:49<4:01:01, 1.43s/it] 84%|████████▎ | 51819/61904 [4:00:51<3:54:33, 1.40s/it] 84%|████████▎ | 51820/61904 [4:00:52<3:47:28, 1.35s/it] {'loss': 2.4383, 'learning_rate': 1.1634253857124334e-07, 'epoch': 13.39} + 84%|████████▎ | 51820/61904 [4:00:52<3:47:28, 1.35s/it] 84%|████████▎ | 51821/61904 [4:00:53<3:47:47, 1.36s/it] 84%|████████▎ | 51822/61904 [4:00:54<3:44:06, 1.33s/it] 84%|████████▎ | 51823/61904 [4:00:56<3:40:39, 1.31s/it] 84%|████████▎ | 51824/61904 [4:00:57<3:38:57, 1.30s/it] 84%|████████▎ | 51825/61904 [4:00:58<3:44:10, 1.33s/it] 84%|████████▎ | 51826/61904 [4:01:00<3:49:27, 1.37s/it] 84%|████████▎ | 51827/61904 [4:01:01<3:56:06, 1.41s/it] 84%|████████▎ | 51828/61904 [4:01:03<3:53:55, 1.39s/it] 84%|████████▎ | 51829/61904 [4:01:04<3:51:41, 1.38s/it] 84%|████████▎ | 51830/61904 [4:01:06<3:58:19, 1.42s/it] 84%|████████▎ | 51831/61904 [4:01:07<3:47:28, 1.35s/it] 84%|████████▎ | 51832/61904 [4:01:08<3:49:45, 1.37s/it] 84%|████████▎ | 51833/61904 [4:01:10<3:53:57, 1.39s/it] 84%|████████▎ | 51834/61904 [4:01:11<3:53:38, 1.39s/it] 84%|████████▎ | 51835/61904 [4:01:13<4:01:45, 1.44s/it] 84%|████████▎ | 51836/61904 [4:01:14<4:03:16, 1.45s/it] 84%|████████▎ | 51837/61904 [4:01:15<4:01:29, 1.44s/it] 84%|████████▎ | 51838/61904 [4:01:17<4:02:05, 1.44s/it] 84%|████████▎ | 51839/61904 [4:01:18<3:55:38, 1.40s/it] 84%|████████▎ | 51840/61904 [4:01:20<4:03:09, 1.45s/it] {'loss': 2.4455, 'learning_rate': 1.16310125761701e-07, 'epoch': 13.4} + 84%|████████▎ | 51840/61904 [4:01:20<4:03:09, 1.45s/it] 84%|████████▎ | 51841/61904 [4:01:21<4:04:25, 1.46s/it] 84%|████████▎ | 51842/61904 [4:01:23<3:57:10, 1.41s/it] 84%|████████▎ | 51843/61904 [4:01:24<3:50:50, 1.38s/it] 84%|████████▎ | 51844/61904 [4:01:25<3:48:49, 1.36s/it] 84%|████████▍ | 51845/61904 [4:01:27<3:48:02, 1.36s/it] 84%|████████▍ | 51846/61904 [4:01:28<3:53:56, 1.40s/it] 84%|████████▍ | 51847/61904 [4:01:29<3:45:10, 1.34s/it] 84%|████████▍ | 51848/61904 [4:01:31<3:43:58, 1.34s/it] 84%|████████▍ | 51849/61904 [4:01:32<3:40:57, 1.32s/it] 84%|████████▍ | 51850/61904 [4:01:33<3:37:11, 1.30s/it] 84%|████████▍ | 51851/61904 [4:01:34<3:37:28, 1.30s/it] 84%|████████▍ | 51852/61904 [4:01:36<3:37:34, 1.30s/it] 84%|████████▍ | 51853/61904 [4:01:37<3:39:51, 1.31s/it] 84%|████████▍ | 51854/61904 [4:01:39<3:50:27, 1.38s/it] 84%|████████▍ | 51855/61904 [4:01:40<3:47:32, 1.36s/it] 84%|████████▍ | 51856/61904 [4:01:41<3:48:11, 1.36s/it] 84%|████████▍ | 51857/61904 [4:01:43<3:48:57, 1.37s/it] 84%|████████▍ | 51858/61904 [4:01:44<3:47:23, 1.36s/it] 84%|████████▍ | 51859/61904 [4:01:45<3:51:57, 1.39s/it] 84%|████████▍ | 51860/61904 [4:01:47<3:50:39, 1.38s/it] {'loss': 2.4771, 'learning_rate': 1.1627771295215869e-07, 'epoch': 13.4} + 84%|████████▍ | 51860/61904 [4:01:47<3:50:39, 1.38s/it] 84%|████████▍ | 51861/61904 [4:01:48<3:43:04, 1.33s/it] 84%|████████▍ | 51862/61904 [4:01:49<3:42:30, 1.33s/it] 84%|████████▍ | 51863/61904 [4:01:51<3:45:24, 1.35s/it] 84%|████████▍ | 51864/61904 [4:01:52<3:43:26, 1.34s/it] 84%|████████▍ | 51865/61904 [4:01:53<3:43:59, 1.34s/it] 84%|████████▍ | 51866/61904 [4:01:55<3:50:41, 1.38s/it] 84%|████████▍ | 51867/61904 [4:01:56<3:50:01, 1.38s/it] 84%|████████▍ | 51868/61904 [4:01:58<3:51:17, 1.38s/it] 84%|████████▍ | 51869/61904 [4:01:59<3:54:17, 1.40s/it] 84%|████████▍ | 51870/61904 [4:02:01<3:57:37, 1.42s/it] 84%|████████▍ | 51871/61904 [4:02:02<3:55:53, 1.41s/it] 84%|████████▍ | 51872/61904 [4:02:03<3:59:26, 1.43s/it] 84%|████████▍ | 51873/61904 [4:02:05<3:59:48, 1.43s/it] 84%|████████▍ | 51874/61904 [4:02:06<4:06:10, 1.47s/it] 84%|████████▍ | 51875/61904 [4:02:08<4:07:31, 1.48s/it] 84%|████████▍ | 51876/61904 [4:02:09<4:00:12, 1.44s/it] 84%|████████▍ | 51877/61904 [4:02:11<3:59:58, 1.44s/it] 84%|████████▍ | 51878/61904 [4:02:12<4:00:05, 1.44s/it] 84%|████████▍ | 51879/61904 [4:02:13<3:55:28, 1.41s/it] 84%|████████▍ | 51880/61904 [4:02:15<3:54:18, 1.40s/it] {'loss': 2.4686, 'learning_rate': 1.1624530014261635e-07, 'epoch': 13.41} + 84%|████████▍ | 51880/61904 [4:02:15<3:54:18, 1.40s/it] 84%|████████▍ | 51881/61904 [4:02:16<3:47:00, 1.36s/it] 84%|████████▍ | 51882/61904 [4:02:17<3:44:56, 1.35s/it] 84%|████████▍ | 51883/61904 [4:02:19<3:52:13, 1.39s/it] 84%|████████▍ | 51884/61904 [4:02:20<3:46:04, 1.35s/it] 84%|████████▍ | 51885/61904 [4:02:21<3:43:47, 1.34s/it] 84%|████████▍ | 51886/61904 [4:02:23<3:53:17, 1.40s/it] 84%|████████▍ | 51887/61904 [4:02:24<3:48:29, 1.37s/it] 84%|████████▍ | 51888/61904 [4:02:26<3:46:51, 1.36s/it] 84%|████████▍ | 51889/61904 [4:02:27<3:50:14, 1.38s/it] 84%|████████▍ | 51890/61904 [4:02:28<3:49:20, 1.37s/it] 84%|████████▍ | 51891/61904 [4:02:30<3:47:09, 1.36s/it] 84%|████████▍ | 51892/61904 [4:02:31<3:46:16, 1.36s/it] 84%|████████▍ | 51893/61904 [4:02:32<3:48:01, 1.37s/it] 84%|████████▍ | 51894/61904 [4:02:34<3:45:48, 1.35s/it] 84%|████████▍ | 51895/61904 [4:02:35<3:46:25, 1.36s/it] 84%|████████▍ | 51896/61904 [4:02:36<3:44:16, 1.34s/it] 84%|████████▍ | 51897/61904 [4:02:38<3:39:26, 1.32s/it] 84%|████████▍ | 51898/61904 [4:02:39<3:49:26, 1.38s/it] 84%|████████▍ | 51899/61904 [4:02:41<3:52:46, 1.40s/it] 84%|████████▍ | 51900/61904 [4:02:42<3:57:02, 1.42s/it] {'loss': 2.4417, 'learning_rate': 1.1621288733307401e-07, 'epoch': 13.41} + 84%|████████▍ | 51900/61904 [4:02:42<3:57:02, 1.42s/it] 84%|████████▍ | 51901/61904 [4:02:43<3:50:16, 1.38s/it] 84%|████████▍ | 51902/61904 [4:02:45<3:54:23, 1.41s/it] 84%|████████▍ | 51903/61904 [4:02:46<3:51:08, 1.39s/it] 84%|████████▍ | 51904/61904 [4:02:48<3:49:41, 1.38s/it] 84%|████████▍ | 51905/61904 [4:02:49<3:49:01, 1.37s/it] 84%|████████▍ | 51906/61904 [4:02:50<3:46:54, 1.36s/it] 84%|████████▍ | 51907/61904 [4:02:52<3:51:06, 1.39s/it] 84%|████████▍ | 51908/61904 [4:02:53<3:57:01, 1.42s/it] 84%|████████▍ | 51909/61904 [4:02:55<3:49:39, 1.38s/it] 84%|████████▍ | 51910/61904 [4:02:56<3:51:31, 1.39s/it] 84%|████████▍ | 51911/61904 [4:02:57<3:45:03, 1.35s/it] 84%|████████▍ | 51912/61904 [4:02:59<3:43:33, 1.34s/it] 84%|████████▍ | 51913/61904 [4:03:00<3:39:52, 1.32s/it] 84%|████████▍ | 51914/61904 [4:03:01<3:41:01, 1.33s/it] 84%|████████▍ | 51915/61904 [4:03:02<3:39:28, 1.32s/it] 84%|████████▍ | 51916/61904 [4:03:04<3:34:40, 1.29s/it] 84%|████████▍ | 51917/61904 [4:03:05<3:36:28, 1.30s/it] 84%|████████▍ | 51918/61904 [4:03:06<3:37:14, 1.31s/it] 84%|████████▍ | 51919/61904 [4:03:08<3:34:36, 1.29s/it] 84%|████████▍ | 51920/61904 [4:03:09<3:46:04, 1.36s/it] {'loss': 2.4765, 'learning_rate': 1.1618047452353167e-07, 'epoch': 13.42} + 84%|████████▍ | 51920/61904 [4:03:09<3:46:04, 1.36s/it] 84%|████████▍ | 51921/61904 [4:03:11<3:52:14, 1.40s/it] 84%|████████▍ | 51922/61904 [4:03:12<3:45:43, 1.36s/it] 84%|████████▍ | 51923/61904 [4:03:13<3:45:20, 1.35s/it] 84%|████████▍ | 51924/61904 [4:03:15<3:51:35, 1.39s/it] 84%|████████▍ | 51925/61904 [4:03:16<3:51:50, 1.39s/it] 84%|████████▍ | 51926/61904 [4:03:17<3:48:04, 1.37s/it] 84%|████████▍ | 51927/61904 [4:03:19<3:45:39, 1.36s/it] 84%|████████▍ | 51928/61904 [4:03:20<3:45:40, 1.36s/it] 84%|████████▍ | 51929/61904 [4:03:21<3:43:36, 1.35s/it] 84%|████████▍ | 51930/61904 [4:03:23<3:43:44, 1.35s/it] 84%|████████▍ | 51931/61904 [4:03:24<3:44:27, 1.35s/it] 84%|████████▍ | 51932/61904 [4:03:25<3:43:51, 1.35s/it] 84%|████████▍ | 51933/61904 [4:03:27<3:43:37, 1.35s/it] 84%|████████▍ | 51934/61904 [4:03:28<3:44:30, 1.35s/it] 84%|████████▍ | 51935/61904 [4:03:30<3:46:23, 1.36s/it] 84%|████████▍ | 51936/61904 [4:03:31<3:43:57, 1.35s/it] 84%|████████▍ | 51937/61904 [4:03:32<3:42:53, 1.34s/it] 84%|████████▍ | 51938/61904 [4:03:34<3:44:09, 1.35s/it] 84%|████████▍ | 51939/61904 [4:03:35<3:41:38, 1.33s/it] 84%|████████▍ | 51940/61904 [4:03:36<3:43:01, 1.34s/it] {'loss': 2.4501, 'learning_rate': 1.1614806171398936e-07, 'epoch': 13.42} + 84%|████████▍ | 51940/61904 [4:03:36<3:43:01, 1.34s/it] 84%|████████▍ | 51941/61904 [4:03:38<3:47:43, 1.37s/it] 84%|████████▍ | 51942/61904 [4:03:39<3:43:49, 1.35s/it] 84%|████████▍ | 51943/61904 [4:03:40<3:40:59, 1.33s/it] 84%|████████▍ | 51944/61904 [4:03:42<3:43:10, 1.34s/it] 84%|████████▍ | 51945/61904 [4:03:43<3:47:45, 1.37s/it] 84%|████████▍ | 51946/61904 [4:03:44<3:48:35, 1.38s/it] 84%|████████▍ | 51947/61904 [4:03:46<3:47:02, 1.37s/it] 84%|████████▍ | 51948/61904 [4:03:47<3:46:04, 1.36s/it] 84%|█��██████▍ | 51949/61904 [4:03:49<3:47:46, 1.37s/it] 84%|████████▍ | 51950/61904 [4:03:50<3:43:30, 1.35s/it] 84%|████████▍ | 51951/61904 [4:03:51<3:42:37, 1.34s/it] 84%|████████▍ | 51952/61904 [4:03:52<3:38:20, 1.32s/it] 84%|████████▍ | 51953/61904 [4:03:54<3:42:38, 1.34s/it] 84%|████████▍ | 51954/61904 [4:03:55<3:42:08, 1.34s/it] 84%|████████▍ | 51955/61904 [4:03:56<3:38:35, 1.32s/it] 84%|████████▍ | 51956/61904 [4:03:58<3:43:15, 1.35s/it] 84%|████████▍ | 51957/61904 [4:03:59<3:47:10, 1.37s/it] 84%|████████▍ | 51958/61904 [4:04:01<3:48:16, 1.38s/it] 84%|████████▍ | 51959/61904 [4:04:02<3:53:40, 1.41s/it] 84%|████████▍ | 51960/61904 [4:04:04<3:53:50, 1.41s/it] {'loss': 2.467, 'learning_rate': 1.1611564890444702e-07, 'epoch': 13.43} + 84%|████████▍ | 51960/61904 [4:04:04<3:53:50, 1.41s/it] 84%|████████▍ | 51961/61904 [4:04:05<3:50:30, 1.39s/it] 84%|████████▍ | 51962/61904 [4:04:06<3:47:12, 1.37s/it] 84%|████████▍ | 51963/61904 [4:04:08<3:46:30, 1.37s/it] 84%|████████▍ | 51964/61904 [4:04:09<3:47:38, 1.37s/it] 84%|████████▍ | 51965/61904 [4:04:10<3:40:53, 1.33s/it] 84%|████████▍ | 51966/61904 [4:04:12<3:42:41, 1.34s/it] 84%|████████▍ | 51967/61904 [4:04:13<3:46:29, 1.37s/it] 84%|████████▍ | 51968/61904 [4:04:14<3:41:00, 1.33s/it] 84%|████████▍ | 51969/61904 [4:04:16<3:40:04, 1.33s/it] 84%|████████▍ | 51970/61904 [4:04:17<3:46:14, 1.37s/it] 84%|████████▍ | 51971/61904 [4:04:18<3:50:29, 1.39s/it] 84%|████████▍ | 51972/61904 [4:04:20<3:47:33, 1.37s/it] 84%|████████▍ | 51973/61904 [4:04:21<3:55:22, 1.42s/it] 84%|████████▍ | 51974/61904 [4:04:23<3:50:18, 1.39s/it] 84%|████████▍ | 51975/61904 [4:04:24<3:40:44, 1.33s/it] 84%|████████▍ | 51976/61904 [4:04:26<3:57:48, 1.44s/it] 84%|████████▍ | 51977/61904 [4:04:27<3:55:23, 1.42s/it] 84%|████████▍ | 51978/61904 [4:04:28<4:01:22, 1.46s/it] 84%|████████▍ | 51979/61904 [4:04:30<3:56:30, 1.43s/it] 84%|████████▍ | 51980/61904 [4:04:31<3:48:05, 1.38s/it] {'loss': 2.4404, 'learning_rate': 1.1608323609490469e-07, 'epoch': 13.43} + 84%|████████▍ | 51980/61904 [4:04:31<3:48:05, 1.38s/it] 84%|████████▍ | 51981/61904 [4:04:33<3:51:57, 1.40s/it] 84%|████████▍ | 51982/61904 [4:04:34<3:47:44, 1.38s/it] 84%|████████▍ | 51983/61904 [4:04:35<3:38:49, 1.32s/it] 84%|████████▍ | 51984/61904 [4:04:36<3:35:05, 1.30s/it] 84%|████████▍ | 51985/61904 [4:04:38<3:45:51, 1.37s/it] 84%|████████▍ | 51986/61904 [4:04:39<3:41:35, 1.34s/it] 84%|████████▍ | 51987/61904 [4:04:40<3:41:30, 1.34s/it] 84%|████████▍ | 51988/61904 [4:04:42<3:54:03, 1.42s/it] 84%|████████▍ | 51989/61904 [4:04:44<4:04:00, 1.48s/it] 84%|████████▍ | 51990/61904 [4:04:45<3:51:15, 1.40s/it] 84%|████████▍ | 51991/61904 [4:04:46<3:49:16, 1.39s/it] 84%|████████▍ | 51992/61904 [4:04:47<3:41:17, 1.34s/it] 84%|████████▍ | 51993/61904 [4:04:49<3:43:40, 1.35s/it] 84%|████████▍ | 51994/61904 [4:04:50<3:41:40, 1.34s/it] 84%|████████▍ | 51995/61904 [4:04:51<3:34:22, 1.30s/it] 84%|████████▍ | 51996/61904 [4:04:53<3:35:18, 1.30s/it] 84%|████████▍ | 51997/61904 [4:04:54<3:45:56, 1.37s/it] 84%|████████▍ | 51998/61904 [4:04:56<3:45:03, 1.36s/it] 84%|████████▍ | 51999/61904 [4:04:57<3:49:39, 1.39s/it] 84%|████████▍ | 52000/61904 [4:04:58<3:47:44, 1.38s/it] {'loss': 2.4413, 'learning_rate': 1.1605082328536235e-07, 'epoch': 13.44} + 84%|████████▍ | 52000/61904 [4:04:58<3:47:44, 1.38s/it] 84%|████████▍ | 52001/61904 [4:05:00<3:46:11, 1.37s/it] 84%|████████▍ | 52002/61904 [4:05:01<3:46:39, 1.37s/it] 84%|████████▍ | 52003/61904 [4:05:02<3:46:40, 1.37s/it] 84%|████████▍ | 52004/61904 [4:05:04<3:48:17, 1.38s/it] 84%|████████▍ | 52005/61904 [4:05:05<3:48:11, 1.38s/it] 84%|████████▍ | 52006/61904 [4:05:06<3:39:20, 1.33s/it] 84%|████████▍ | 52007/61904 [4:05:08<3:39:53, 1.33s/it] 84%|████████▍ | 52008/61904 [4:05:09<3:51:12, 1.40s/it] 84%|████████▍ | 52009/61904 [4:05:11<3:51:43, 1.41s/it] 84%|████████▍ | 52010/61904 [4:05:12<4:05:52, 1.49s/it] 84%|████████▍ | 52011/61904 [4:05:14<3:57:08, 1.44s/it] 84%|████████▍ | 52012/61904 [4:05:15<3:51:10, 1.40s/it] 84%|████████▍ | 52013/61904 [4:05:16<3:44:14, 1.36s/it] 84%|████████▍ | 52014/61904 [4:05:18<3:40:17, 1.34s/it] 84%|████████▍ | 52015/61904 [4:05:19<3:40:04, 1.34s/it] 84%|████████▍ | 52016/61904 [4:05:20<3:48:27, 1.39s/it] 84%|████████▍ | 52017/61904 [4:05:22<3:45:53, 1.37s/it] 84%|████████▍ | 52018/61904 [4:05:23<3:45:29, 1.37s/it] 84%|████████▍ | 52019/61904 [4:05:25<3:46:53, 1.38s/it] 84%|████████▍ | 52020/61904 [4:05:26<3:42:13, 1.35s/it] {'loss': 2.4529, 'learning_rate': 1.1601841047582004e-07, 'epoch': 13.45} + 84%|████████▍ | 52020/61904 [4:05:26<3:42:13, 1.35s/it] 84%|████████▍ | 52021/61904 [4:05:27<3:39:39, 1.33s/it] 84%|████████▍ | 52022/61904 [4:05:29<3:42:58, 1.35s/it] 84%|████████▍ | 52023/61904 [4:05:30<3:41:12, 1.34s/it] 84%|████████▍ | 52024/61904 [4:05:31<3:45:24, 1.37s/it] 84%|████████▍ | 52025/61904 [4:05:33<3:43:17, 1.36s/it] 84%|████████▍ | 52026/61904 [4:05:34<3:41:47, 1.35s/it] 84%|████████▍ | 52027/61904 [4:05:35<3:38:17, 1.33s/it] 84%|████████▍ | 52028/61904 [4:05:37<3:42:55, 1.35s/it] 84%|████████▍ | 52029/61904 [4:05:38<3:45:24, 1.37s/it] 84%|████████▍ | 52030/61904 [4:05:39<3:44:45, 1.37s/it] 84%|████████▍ | 52031/61904 [4:05:41<3:41:35, 1.35s/it] 84%|████████▍ | 52032/61904 [4:05:42<3:40:37, 1.34s/it] 84%|████████▍ | 52033/61904 [4:05:44<3:46:59, 1.38s/it] 84%|████████▍ | 52034/61904 [4:05:45<3:47:51, 1.39s/it] 84%|████████▍ | 52035/61904 [4:05:46<3:39:30, 1.33s/it] 84%|████████▍ | 52036/61904 [4:05:47<3:39:16, 1.33s/it] 84%|████████▍ | 52037/61904 [4:05:49<3:46:54, 1.38s/it] 84%|████████▍ | 52038/61904 [4:05:50<3:42:32, 1.35s/it] 84%|████████▍ | 52039/61904 [4:05:52<3:38:55, 1.33s/it] 84%|████████▍ | 52040/61904 [4:05:53<3:40:21, 1.34s/it] {'loss': 2.4719, 'learning_rate': 1.159859976662777e-07, 'epoch': 13.45} + 84%|████████▍ | 52040/61904 [4:05:53<3:40:21, 1.34s/it] 84%|████████▍ | 52041/61904 [4:05:54<3:43:19, 1.36s/it] 84%|████████▍ | 52042/61904 [4:05:56<3:43:43, 1.36s/it] 84%|████████▍ | 52043/61904 [4:05:57<3:46:59, 1.38s/it] 84%|████████▍ | 52044/61904 [4:05:59<3:51:15, 1.41s/it] 84%|████████▍ | 52045/61904 [4:06:00<3:53:12, 1.42s/it] 84%|████████▍ | 52046/61904 [4:06:01<3:48:34, 1.39s/it] 84%|████████▍ | 52047/61904 [4:06:03<3:48:56, 1.39s/it] 84%|████████▍ | 52048/61904 [4:06:04<3:51:17, 1.41s/it] 84%|████████▍ | 52049/61904 [4:06:05<3:40:59, 1.35s/it] 84%|████████▍ | 52050/61904 [4:06:07<3:37:37, 1.33s/it] 84%|████████▍ | 52051/61904 [4:06:08<3:44:48, 1.37s/it] 84%|████████▍ | 52052/61904 [4:06:09<3:42:38, 1.36s/it] 84%|████████▍ | 52053/61904 [4:06:11<3:41:44, 1.35s/it] 84%|████████▍ | 52054/61904 [4:06:12<3:41:38, 1.35s/it] 84%|████████▍ | 52055/61904 [4:06:13<3:39:22, 1.34s/it] 84%|████████▍ | 52056/61904 [4:06:15<3:38:07, 1.33s/it] 84%|████████▍ | 52057/61904 [4:06:16<3:44:46, 1.37s/it] 84%|████████▍ | 52058/61904 [4:06:18<3:42:17, 1.35s/it] 84%|████████▍ | 52059/61904 [4:06:19<3:43:06, 1.36s/it] 84%|████████▍ | 52060/61904 [4:06:20<3:38:01, 1.33s/it] {'loss': 2.3729, 'learning_rate': 1.1595358485673536e-07, 'epoch': 13.46} + 84%|████████▍ | 52060/61904 [4:06:20<3:38:01, 1.33s/it] 84%|████████▍ | 52061/61904 [4:06:22<3:44:57, 1.37s/it] 84%|████████▍ | 52062/61904 [4:06:23<3:49:00, 1.40s/it] 84%|████████▍ | 52063/61904 [4:06:24<3:47:19, 1.39s/it] 84%|████████▍ | 52064/61904 [4:06:26<3:46:58, 1.38s/it] 84%|████████▍ | 52065/61904 [4:06:27<3:59:04, 1.46s/it] 84%|████████▍ | 52066/61904 [4:06:29<3:51:43, 1.41s/it] 84%|██████���█▍ | 52067/61904 [4:06:30<3:45:47, 1.38s/it] 84%|████████▍ | 52068/61904 [4:06:31<3:46:57, 1.38s/it] 84%|████████▍ | 52069/61904 [4:06:33<3:42:05, 1.35s/it] 84%|████████▍ | 52070/61904 [4:06:34<3:45:13, 1.37s/it] 84%|████████▍ | 52071/61904 [4:06:36<3:46:35, 1.38s/it] 84%|████████▍ | 52072/61904 [4:06:37<3:45:22, 1.38s/it] 84%|████████▍ | 52073/61904 [4:06:38<3:45:43, 1.38s/it] 84%|████████▍ | 52074/61904 [4:06:40<3:46:12, 1.38s/it] 84%|████████▍ | 52075/61904 [4:06:41<3:51:58, 1.42s/it] 84%|████████▍ | 52076/61904 [4:06:42<3:46:56, 1.39s/it] 84%|████████▍ | 52077/61904 [4:06:44<3:50:13, 1.41s/it] 84%|████████▍ | 52078/61904 [4:06:45<3:47:49, 1.39s/it] 84%|████████▍ | 52079/61904 [4:06:47<3:41:34, 1.35s/it] 84%|████████▍ | 52080/61904 [4:06:48<3:45:53, 1.38s/it] {'loss': 2.4296, 'learning_rate': 1.1592117204719305e-07, 'epoch': 13.46} + 84%|████████▍ | 52080/61904 [4:06:48<3:45:53, 1.38s/it] 84%|████████▍ | 52081/61904 [4:06:49<3:38:34, 1.34s/it] 84%|████████▍ | 52082/61904 [4:06:51<3:40:39, 1.35s/it] 84%|████████▍ | 52083/61904 [4:06:52<3:43:10, 1.36s/it] 84%|████████▍ | 52084/61904 [4:06:53<3:48:08, 1.39s/it] 84%|████████▍ | 52085/61904 [4:06:55<3:47:01, 1.39s/it] 84%|████████▍ | 52086/61904 [4:06:56<3:46:56, 1.39s/it] 84%|████████▍ | 52087/61904 [4:06:58<3:53:16, 1.43s/it] 84%|████████▍ | 52088/61904 [4:06:59<3:48:27, 1.40s/it] 84%|████████▍ | 52089/61904 [4:07:01<3:52:01, 1.42s/it] 84%|████████▍ | 52090/61904 [4:07:02<3:48:19, 1.40s/it] 84%|████████▍ | 52091/61904 [4:07:03<3:43:53, 1.37s/it] 84%|████████▍ | 52092/61904 [4:07:04<3:39:30, 1.34s/it] 84%|████████▍ | 52093/61904 [4:07:06<3:47:31, 1.39s/it] 84%|████████▍ | 52094/61904 [4:07:07<3:50:40, 1.41s/it] 84%|████████▍ | 52095/61904 [4:07:09<3:51:49, 1.42s/it] 84%|████████▍ | 52096/61904 [4:07:10<3:48:25, 1.40s/it] 84%|████████▍ | 52097/61904 [4:07:12<3:45:36, 1.38s/it] 84%|████████▍ | 52098/61904 [4:07:13<3:46:40, 1.39s/it] 84%|████████▍ | 52099/61904 [4:07:14<3:45:02, 1.38s/it] 84%|████████▍ | 52100/61904 [4:07:16<3:44:53, 1.38s/it] {'loss': 2.4939, 'learning_rate': 1.1588875923765071e-07, 'epoch': 13.47} + 84%|████████▍ | 52100/61904 [4:07:16<3:44:53, 1.38s/it] 84%|████████▍ | 52101/61904 [4:07:17<3:44:32, 1.37s/it] 84%|████████▍ | 52102/61904 [4:07:18<3:46:01, 1.38s/it] 84%|████████▍ | 52103/61904 [4:07:20<3:51:06, 1.41s/it] 84%|████████▍ | 52104/61904 [4:07:21<3:42:19, 1.36s/it] 84%|████████▍ | 52105/61904 [4:07:23<3:56:41, 1.45s/it] 84%|████████▍ | 52106/61904 [4:07:24<3:57:52, 1.46s/it] 84%|████████▍ | 52107/61904 [4:07:26<3:55:22, 1.44s/it] 84%|████████▍ | 52108/61904 [4:07:27<3:48:48, 1.40s/it] 84%|████████▍ | 52109/61904 [4:07:28<3:46:20, 1.39s/it] 84%|████████▍ | 52110/61904 [4:07:30<3:43:54, 1.37s/it] 84%|████████▍ | 52111/61904 [4:07:31<3:47:37, 1.39s/it] 84%|████████▍ | 52112/61904 [4:07:32<3:42:39, 1.36s/it] 84%|████████▍ | 52113/61904 [4:07:34<3:49:25, 1.41s/it] 84%|████████▍ | 52114/61904 [4:07:35<3:49:32, 1.41s/it] 84%|████████▍ | 52115/61904 [4:07:37<3:48:49, 1.40s/it] 84%|████████▍ | 52116/61904 [4:07:38<3:45:31, 1.38s/it] 84%|████████▍ | 52117/61904 [4:07:39<3:45:45, 1.38s/it] 84%|████████▍ | 52118/61904 [4:07:41<3:41:34, 1.36s/it] 84%|████████▍ | 52119/61904 [4:07:42<3:37:23, 1.33s/it] 84%|████████▍ | 52120/61904 [4:07:43<3:38:02, 1.34s/it] {'loss': 2.4214, 'learning_rate': 1.1585634642810837e-07, 'epoch': 13.47} + 84%|████████▍ | 52120/61904 [4:07:43<3:38:02, 1.34s/it] 84%|████████▍ | 52121/61904 [4:07:45<3:36:13, 1.33s/it] 84%|████████▍ | 52122/61904 [4:07:46<3:34:15, 1.31s/it] 84%|████████▍ | 52123/61904 [4:07:47<3:32:44, 1.31s/it] 84%|████████▍ | 52124/61904 [4:07:49<3:39:50, 1.35s/it] 84%|████████▍ | 52125/61904 [4:07:50<3:49:30, 1.41s/it] 84%|████████��� | 52126/61904 [4:07:51<3:39:39, 1.35s/it] 84%|████████▍ | 52127/61904 [4:07:53<3:34:59, 1.32s/it] 84%|████████▍ | 52128/61904 [4:07:54<3:37:41, 1.34s/it] 84%|████████▍ | 52129/61904 [4:07:55<3:35:07, 1.32s/it] 84%|████████▍ | 52130/61904 [4:07:57<3:43:45, 1.37s/it] 84%|████████▍ | 52131/61904 [4:07:58<3:40:02, 1.35s/it] 84%|████████▍ | 52132/61904 [4:08:00<3:42:28, 1.37s/it] 84%|████████▍ | 52133/61904 [4:08:01<3:45:33, 1.39s/it] 84%|████████▍ | 52134/61904 [4:08:02<3:41:26, 1.36s/it] 84%|████████▍ | 52135/61904 [4:08:04<3:40:30, 1.35s/it] 84%|████████▍ | 52136/61904 [4:08:05<3:45:28, 1.38s/it] 84%|████████▍ | 52137/61904 [4:08:07<3:46:38, 1.39s/it] 84%|████████▍ | 52138/61904 [4:08:08<3:46:23, 1.39s/it] 84%|████████▍ | 52139/61904 [4:08:09<3:47:31, 1.40s/it] 84%|████████▍ | 52140/61904 [4:08:11<3:44:18, 1.38s/it] {'loss': 2.4435, 'learning_rate': 1.1582393361856603e-07, 'epoch': 13.48} + 84%|████████▍ | 52140/61904 [4:08:11<3:44:18, 1.38s/it] 84%|████████▍ | 52141/61904 [4:08:12<3:34:50, 1.32s/it] 84%|████████▍ | 52142/61904 [4:08:13<3:43:52, 1.38s/it] 84%|████████▍ | 52143/61904 [4:08:15<3:40:16, 1.35s/it] 84%|████████▍ | 52144/61904 [4:08:16<3:47:42, 1.40s/it] 84%|████████▍ | 52145/61904 [4:08:18<3:46:40, 1.39s/it] 84%|████████▍ | 52146/61904 [4:08:19<3:40:41, 1.36s/it] 84%|████████▍ | 52147/61904 [4:08:20<3:37:48, 1.34s/it] 84%|████████▍ | 52148/61904 [4:08:21<3:37:19, 1.34s/it] 84%|████████▍ | 52149/61904 [4:08:23<3:42:25, 1.37s/it] 84%|████████▍ | 52150/61904 [4:08:24<3:35:50, 1.33s/it] 84%|████████▍ | 52151/61904 [4:08:25<3:36:21, 1.33s/it] 84%|████████▍ | 52152/61904 [4:08:27<3:36:46, 1.33s/it] 84%|████████▍ | 52153/61904 [4:08:28<3:39:59, 1.35s/it] 84%|████████▍ | 52154/61904 [4:08:30<3:39:57, 1.35s/it] 84%|████████▍ | 52155/61904 [4:08:31<3:48:36, 1.41s/it] 84%|████████▍ | 52156/61904 [4:08:32<3:45:59, 1.39s/it] 84%|████████▍ | 52157/61904 [4:08:34<3:50:05, 1.42s/it] 84%|████████▍ | 52158/61904 [4:08:35<3:43:15, 1.37s/it] 84%|████████▍ | 52159/61904 [4:08:37<3:39:52, 1.35s/it] 84%|████████▍ | 52160/61904 [4:08:38<3:40:51, 1.36s/it] {'loss': 2.4724, 'learning_rate': 1.1579152080902372e-07, 'epoch': 13.48} + 84%|████████▍ | 52160/61904 [4:08:38<3:40:51, 1.36s/it] 84%|████████▍ | 52161/61904 [4:08:39<3:38:15, 1.34s/it] 84%|████████▍ | 52162/61904 [4:08:41<3:53:06, 1.44s/it] 84%|████████▍ | 52163/61904 [4:08:42<3:49:48, 1.42s/it] 84%|████████▍ | 52164/61904 [4:08:44<3:48:25, 1.41s/it] 84%|████████▍ | 52165/61904 [4:08:45<3:52:26, 1.43s/it] 84%|████████▍ | 52166/61904 [4:08:47<4:05:13, 1.51s/it] 84%|████████▍ | 52167/61904 [4:08:48<3:55:43, 1.45s/it] 84%|████████▍ | 52168/61904 [4:08:49<3:51:29, 1.43s/it] 84%|████████▍ | 52169/61904 [4:08:51<3:44:46, 1.39s/it] 84%|████████▍ | 52170/61904 [4:08:52<3:52:14, 1.43s/it] 84%|████████▍ | 52171/61904 [4:08:54<3:45:54, 1.39s/it] 84%|████████▍ | 52172/61904 [4:08:55<3:45:56, 1.39s/it] 84%|████████▍ | 52173/61904 [4:08:56<3:44:28, 1.38s/it] 84%|████████▍ | 52174/61904 [4:08:58<3:42:47, 1.37s/it] 84%|████████▍ | 52175/61904 [4:08:59<3:42:03, 1.37s/it] 84%|████████▍ | 52176/61904 [4:09:00<3:42:50, 1.37s/it] 84%|████████▍ | 52177/61904 [4:09:02<3:43:55, 1.38s/it] 84%|████████▍ | 52178/61904 [4:09:03<3:42:25, 1.37s/it] 84%|████████▍ | 52179/61904 [4:09:05<3:46:28, 1.40s/it] 84%|████████▍ | 52180/61904 [4:09:06<3:45:41, 1.39s/it] {'loss': 2.4219, 'learning_rate': 1.1575910799948138e-07, 'epoch': 13.49} + 84%|████████▍ | 52180/61904 [4:09:06<3:45:41, 1.39s/it] 84%|████████▍ | 52181/61904 [4:09:07<3:47:39, 1.40s/it] 84%|████████▍ | 52182/61904 [4:09:09<3:48:11, 1.41s/it] 84%|████████▍ | 52183/61904 [4:09:10<3:48:18, 1.41s/it] 84%|████████▍ | 52184/61904 [4:09:12<3:46:16, 1.40s/it] 84%|████████▍ | 52185/61904 [4:09:13<3:46:41, 1.40s/it] 84%|████████▍ | 52186/61904 [4:09:14<3:45:11, 1.39s/it] 84%|████████▍ | 52187/61904 [4:09:16<3:38:51, 1.35s/it] 84%|████████▍ | 52188/61904 [4:09:17<3:37:33, 1.34s/it] 84%|████████▍ | 52189/61904 [4:09:18<3:34:05, 1.32s/it] 84%|████████▍ | 52190/61904 [4:09:20<3:37:49, 1.35s/it] 84%|████████▍ | 52191/61904 [4:09:21<3:39:54, 1.36s/it] 84%|████████▍ | 52192/61904 [4:09:23<3:44:50, 1.39s/it] 84%|████████▍ | 52193/61904 [4:09:24<3:41:37, 1.37s/it] 84%|████████▍ | 52194/61904 [4:09:25<3:41:31, 1.37s/it] 84%|████████▍ | 52195/61904 [4:09:27<3:43:47, 1.38s/it] 84%|████████▍ | 52196/61904 [4:09:28<3:40:56, 1.37s/it] 84%|████████▍ | 52197/61904 [4:09:29<3:46:25, 1.40s/it] 84%|████████▍ | 52198/61904 [4:09:31<3:48:21, 1.41s/it] 84%|████████▍ | 52199/61904 [4:09:32<3:41:32, 1.37s/it] 84%|████████▍ | 52200/61904 [4:09:33<3:34:50, 1.33s/it] {'loss': 2.4166, 'learning_rate': 1.1572669518993905e-07, 'epoch': 13.49} + 84%|████████▍ | 52200/61904 [4:09:33<3:34:50, 1.33s/it] 84%|████████▍ | 52201/61904 [4:09:35<3:38:38, 1.35s/it] 84%|████████▍ | 52202/61904 [4:09:36<3:37:41, 1.35s/it] 84%|████████▍ | 52203/61904 [4:09:38<3:41:34, 1.37s/it] 84%|████████▍ | 52204/61904 [4:09:39<3:40:47, 1.37s/it] 84%|████████▍ | 52205/61904 [4:09:40<3:47:27, 1.41s/it] 84%|████████▍ | 52206/61904 [4:09:42<3:48:09, 1.41s/it] 84%|████████▍ | 52207/61904 [4:09:43<3:51:21, 1.43s/it] 84%|████████▍ | 52208/61904 [4:09:45<3:48:45, 1.42s/it] 84%|████████▍ | 52209/61904 [4:09:46<3:50:26, 1.43s/it] 84%|████████▍ | 52210/61904 [4:09:47<3:43:26, 1.38s/it] 84%|████████▍ | 52211/61904 [4:09:49<3:39:43, 1.36s/it] 84%|████████▍ | 52212/61904 [4:09:50<3:39:48, 1.36s/it] 84%|████████▍ | 52213/61904 [4:09:52<3:43:19, 1.38s/it] 84%|████████▍ | 52214/61904 [4:09:53<3:43:41, 1.39s/it] 84%|████████▍ | 52215/61904 [4:09:54<3:46:16, 1.40s/it] 84%|████████▍ | 52216/61904 [4:09:56<3:37:22, 1.35s/it] 84%|████████▍ | 52217/61904 [4:09:57<3:37:11, 1.35s/it] 84%|████████▍ | 52218/61904 [4:09:58<3:46:27, 1.40s/it] 84%|████████▍ | 52219/61904 [4:10:00<3:49:00, 1.42s/it] 84%|████████▍ | 52220/61904 [4:10:01<3:42:59, 1.38s/it] {'loss': 2.456, 'learning_rate': 1.1569428238039671e-07, 'epoch': 13.5} + 84%|████████▍ | 52220/61904 [4:10:01<3:42:59, 1.38s/it] 84%|████████▍ | 52221/61904 [4:10:03<3:39:45, 1.36s/it] 84%|████████▍ | 52222/61904 [4:10:04<3:44:47, 1.39s/it] 84%|████████▍ | 52223/61904 [4:10:05<3:43:59, 1.39s/it] 84%|████████▍ | 52224/61904 [4:10:07<3:38:10, 1.35s/it] 84%|████████▍ | 52225/61904 [4:10:08<3:35:10, 1.33s/it] 84%|████████▍ | 52226/61904 [4:10:09<3:32:52, 1.32s/it] 84%|████████▍ | 52227/61904 [4:10:11<3:33:19, 1.32s/it] 84%|████████▍ | 52228/61904 [4:10:12<3:34:29, 1.33s/it] 84%|████████▍ | 52229/61904 [4:10:13<3:38:33, 1.36s/it] 84%|████████▍ | 52230/61904 [4:10:15<3:39:00, 1.36s/it] 84%|████████▍ | 52231/61904 [4:10:16<3:38:47, 1.36s/it] 84%|████████▍ | 52232/61904 [4:10:17<3:36:50, 1.35s/it] 84%|████████▍ | 52233/61904 [4:10:19<3:42:42, 1.38s/it] 84%|████████▍ | 52234/61904 [4:10:20<3:38:47, 1.36s/it] 84%|████████▍ | 52235/61904 [4:10:22<3:40:49, 1.37s/it] 84%|████████▍ | 52236/61904 [4:10:23<3:36:29, 1.34s/it] 84%|████████▍ | 52237/61904 [4:10:24<3:34:41, 1.33s/it] 84%|████████▍ | 52238/61904 [4:10:26<3:38:17, 1.36s/it] 84%|████████▍ | 52239/61904 [4:10:27<3:41:53, 1.38s/it] 84%|████████▍ | 52240/61904 [4:10:28<3:40:06, 1.37s/it] {'loss': 2.4335, 'learning_rate': 1.156618695708544e-07, 'epoch': 13.5} + 84%|████████▍ | 52240/61904 [4:10:28<3:40:06, 1.37s/it] 84%|████████▍ | 52241/61904 [4:10:30<3:36:20, 1.34s/it] 84%|████████▍ | 52242/61904 [4:10:31<3:35:47, 1.34s/it] 84%|████████▍ | 52243/61904 [4:10:32<3:43:18, 1.39s/it] 84%|████████▍ | 52244/61904 [4:10:34<3:42:24, 1.38s/it] 84%|████████▍ | 52245/61904 [4:10:35<3:44:17, 1.39s/it] 84%|████████▍ | 52246/61904 [4:10:36<3:38:29, 1.36s/it] 84%|████████▍ | 52247/61904 [4:10:38<3:43:53, 1.39s/it] 84%|████████▍ | 52248/61904 [4:10:39<3:45:46, 1.40s/it] 84%|████████▍ | 52249/61904 [4:10:41<3:49:27, 1.43s/it] 84%|████████▍ | 52250/61904 [4:10:42<3:48:08, 1.42s/it] 84%|████████▍ | 52251/61904 [4:10:44<3:45:24, 1.40s/it] 84%|████████▍ | 52252/61904 [4:10:45<3:46:44, 1.41s/it] 84%|████████▍ | 52253/61904 [4:10:46<3:46:15, 1.41s/it] 84%|████████▍ | 52254/61904 [4:10:48<3:43:45, 1.39s/it] 84%|████████▍ | 52255/61904 [4:10:49<3:39:00, 1.36s/it] 84%|████████▍ | 52256/61904 [4:10:50<3:41:14, 1.38s/it] 84%|████████▍ | 52257/61904 [4:10:52<3:42:28, 1.38s/it] 84%|████████▍ | 52258/61904 [4:10:53<3:45:53, 1.41s/it] 84%|████████▍ | 52259/61904 [4:10:55<3:50:17, 1.43s/it] 84%|████████▍ | 52260/61904 [4:10:56<3:42:51, 1.39s/it] {'loss': 2.4549, 'learning_rate': 1.1562945676131206e-07, 'epoch': 13.51} + 84%|████████▍ | 52260/61904 [4:10:56<3:42:51, 1.39s/it] 84%|████████▍ | 52261/61904 [4:10:58<3:43:05, 1.39s/it] 84%|████████▍ | 52262/61904 [4:10:59<3:39:02, 1.36s/it] 84%|████████▍ | 52263/61904 [4:11:00<3:41:11, 1.38s/it] 84%|████████▍ | 52264/61904 [4:11:02<3:37:28, 1.35s/it] 84%|████████▍ | 52265/61904 [4:11:03<3:37:00, 1.35s/it] 84%|████████▍ | 52266/61904 [4:11:04<3:41:57, 1.38s/it] 84%|████████▍ | 52267/61904 [4:11:06<3:35:45, 1.34s/it] 84%|████████▍ | 52268/61904 [4:11:07<3:41:32, 1.38s/it] 84%|████████▍ | 52269/61904 [4:11:09<3:48:13, 1.42s/it] 84%|████████▍ | 52270/61904 [4:11:10<3:50:23, 1.43s/it] 84%|████████▍ | 52271/61904 [4:11:11<3:47:57, 1.42s/it] 84%|████████▍ | 52272/61904 [4:11:13<3:48:55, 1.43s/it] 84%|████████▍ | 52273/61904 [4:11:14<3:45:43, 1.41s/it] 84%|████████▍ | 52274/61904 [4:11:16<3:45:30, 1.41s/it] 84%|████████▍ | 52275/61904 [4:11:17<3:42:35, 1.39s/it] 84%|████████▍ | 52276/61904 [4:11:18<3:41:41, 1.38s/it] 84%|████████▍ | 52277/61904 [4:11:20<3:49:14, 1.43s/it] 84%|████████▍ | 52278/61904 [4:11:21<3:47:35, 1.42s/it] 84%|████████▍ | 52279/61904 [4:11:23<3:42:16, 1.39s/it] 84%|████████▍ | 52280/61904 [4:11:24<3:47:27, 1.42s/it] {'loss': 2.4274, 'learning_rate': 1.1559704395176972e-07, 'epoch': 13.51} + 84%|████████▍ | 52280/61904 [4:11:24<3:47:27, 1.42s/it] 84%|████████▍ | 52281/61904 [4:11:25<3:43:38, 1.39s/it] 84%|████████▍ | 52282/61904 [4:11:27<3:40:26, 1.37s/it] 84%|████████▍ | 52283/61904 [4:11:28<3:35:25, 1.34s/it] 84%|████████▍ | 52284/61904 [4:11:29<3:33:03, 1.33s/it] 84%|████████▍ | 52285/61904 [4:11:31<3:37:18, 1.36s/it] 84%|████████▍ | 52286/61904 [4:11:32<3:41:51, 1.38s/it] 84%|████████▍ | 52287/61904 [4:11:34<3:42:06, 1.39s/it] 84%|████████▍ | 52288/61904 [4:11:35<3:42:35, 1.39s/it] 84%|████████▍ | 52289/61904 [4:11:36<3:42:22, 1.39s/it] 84%|████████▍ | 52290/61904 [4:11:38<3:41:01, 1.38s/it] 84%|████████▍ | 52291/61904 [4:11:39<3:36:02, 1.35s/it] 84%|████████▍ | 52292/61904 [4:11:40<3:32:46, 1.33s/it] 84%|████████▍ | 52293/61904 [4:11:42<3:42:27, 1.39s/it] 84%|████████▍ | 52294/61904 [4:11:43<3:34:43, 1.34s/it] 84%|████████▍ | 52295/61904 [4:11:44<3:39:46, 1.37s/it] 84%|████████▍ | 52296/61904 [4:11:46<3:35:52, 1.35s/it] 84%|████████▍ | 52297/61904 [4:11:47<3:34:34, 1.34s/it] 84%|████████▍ | 52298/61904 [4:11:49<3:39:18, 1.37s/it] 84%|████████▍ | 52299/61904 [4:11:50<3:42:56, 1.39s/it] 84%|████████▍ | 52300/61904 [4:11:51<3:34:57, 1.34s/it] {'loss': 2.4509, 'learning_rate': 1.1556463114222738e-07, 'epoch': 13.52} + 84%|████████▍ | 52300/61904 [4:11:51<3:34:57, 1.34s/it] 84%|████████▍ | 52301/61904 [4:11:53<3:36:06, 1.35s/it] 84%|████████▍ | 52302/61904 [4:11:54<3:41:47, 1.39s/it] 84%|████████▍ | 52303/61904 [4:11:56<3:52:05, 1.45s/it] 84%|████████▍ | 52304/61904 [4:11:57<3:48:51, 1.43s/it] 84%|████████▍ | 52305/61904 [4:11:58<3:50:10, 1.44s/it] 84%|████████▍ | 52306/61904 [4:12:00<3:41:45, 1.39s/it] 84%|████████▍ | 52307/61904 [4:12:01<3:39:01, 1.37s/it] 84%|████████▍ | 52308/61904 [4:12:03<3:52:05, 1.45s/it] 85%|████████▍ | 52309/61904 [4:12:04<3:44:06, 1.40s/it] 85%|████████▍ | 52310/61904 [4:12:05<3:37:19, 1.36s/it] 85%|████████▍ | 52311/61904 [4:12:07<3:40:30, 1.38s/it] 85%|████████▍ | 52312/61904 [4:12:08<3:34:38, 1.34s/it] 85%|████████▍ | 52313/61904 [4:12:09<3:33:29, 1.34s/it] 85%|████████▍ | 52314/61904 [4:12:11<3:30:26, 1.32s/it] 85%|████████▍ | 52315/61904 [4:12:12<3:29:19, 1.31s/it] 85%|████████▍ | 52316/61904 [4:12:13<3:34:06, 1.34s/it] 85%|████████▍ | 52317/61904 [4:12:14<3:26:25, 1.29s/it] 85%|████████▍ | 52318/61904 [4:12:16<3:33:31, 1.34s/it] 85%|████████▍ | 52319/61904 [4:12:17<3:35:25, 1.35s/it] 85%|████████▍ | 52320/61904 [4:12:19<3:39:31, 1.37s/it] {'loss': 2.4466, 'learning_rate': 1.1553221833268507e-07, 'epoch': 13.52} + 85%|████████▍ | 52320/61904 [4:12:19<3:39:31, 1.37s/it] 85%|████████▍ | 52321/61904 [4:12:20<3:48:36, 1.43s/it] 85%|████████▍ | 52322/61904 [4:12:22<3:47:05, 1.42s/it] 85%|████████▍ | 52323/61904 [4:12:23<3:39:12, 1.37s/it] 85%|████████▍ | 52324/61904 [4:12:24<3:40:53, 1.38s/it] 85%|████████▍ | 52325/61904 [4:12:26<3:36:33, 1.36s/it] 85%|████████▍ | 52326/61904 [4:12:27<3:39:22, 1.37s/it] 85%|████████▍ | 52327/61904 [4:12:29<3:58:07, 1.49s/it] 85%|████████▍ | 52328/61904 [4:12:30<3:51:06, 1.45s/it] 85%|████████▍ | 52329/61904 [4:12:32<3:48:53, 1.43s/it] 85%|████████▍ | 52330/61904 [4:12:33<3:51:14, 1.45s/it] 85%|████████▍ | 52331/61904 [4:12:34<3:47:05, 1.42s/it] 85%|████████▍ | 52332/61904 [4:12:36<3:38:00, 1.37s/it] 85%|████████▍ | 52333/61904 [4:12:37<3:47:21, 1.43s/it] 85%|████████▍ | 52334/61904 [4:12:39<3:45:21, 1.41s/it] 85%|████████▍ | 52335/61904 [4:12:40<3:38:05, 1.37s/it] 85%|████████▍ | 52336/61904 [4:12:41<3:36:37, 1.36s/it] 85%|████████▍ | 52337/61904 [4:12:43<3:57:05, 1.49s/it] 85%|████████▍ | 52338/61904 [4:12:44<3:52:06, 1.46s/it] 85%|████████▍ | 52339/61904 [4:12:46<3:48:31, 1.43s/it] 85%|████████▍ | 52340/61904 [4:12:47<3:49:48, 1.44s/it] {'loss': 2.486, 'learning_rate': 1.1549980552314273e-07, 'epoch': 13.53} + 85%|████████▍ | 52340/61904 [4:12:47<3:49:48, 1.44s/it] 85%|████████▍ | 52341/61904 [4:12:49<3:52:42, 1.46s/it] 85%|████████▍ | 52342/61904 [4:12:50<3:51:33, 1.45s/it] 85%|████████▍ | 52343/61904 [4:12:51<3:45:25, 1.41s/it] 85%|████████▍ | 52344/61904 [4:12:53<3:43:22, 1.40s/it] 85%|████████▍ | 52345/61904 [4:12:54<3:41:15, 1.39s/it] 85%|████████▍ | 52346/61904 [4:12:56<3:41:41, 1.39s/it] 85%|████████▍ | 52347/61904 [4:12:57<3:45:46, 1.42s/it] 85%|████████▍ | 52348/61904 [4:12:58<3:43:56, 1.41s/it] 85%|████████▍ | 52349/61904 [4:13:00<3:43:13, 1.40s/it] 85%|████████▍ | 52350/61904 [4:13:01<3:38:33, 1.37s/it] 85%|████████▍ | 52351/61904 [4:13:02<3:35:56, 1.36s/it] 85%|████████▍ | 52352/61904 [4:13:04<3:37:38, 1.37s/it] 85%|████████▍ | 52353/61904 [4:13:05<3:41:07, 1.39s/it] 85%|████████▍ | 52354/61904 [4:13:07<3:37:00, 1.36s/it] 85%|████████▍ | 52355/61904 [4:13:08<3:38:42, 1.37s/it] 85%|████████▍ | 52356/61904 [4:13:09<3:33:20, 1.34s/it] 85%|████████▍ | 52357/61904 [4:13:11<3:33:50, 1.34s/it] 85%|████████▍ | 52358/61904 [4:13:12<3:39:41, 1.38s/it] 85%|████████▍ | 52359/61904 [4:13:13<3:35:17, 1.35s/it] 85%|████████▍ | 52360/61904 [4:13:15<3:40:01, 1.38s/it] {'loss': 2.4423, 'learning_rate': 1.1546739271360039e-07, 'epoch': 13.53} + 85%|████████▍ | 52360/61904 [4:13:15<3:40:01, 1.38s/it] 85%|████████▍ | 52361/61904 [4:13:16<3:37:45, 1.37s/it] 85%|████████▍ | 52362/61904 [4:13:18<3:43:00, 1.40s/it] 85%|████████▍ | 52363/61904 [4:13:19<3:39:43, 1.38s/it] 85%|████████▍ | 52364/61904 [4:13:20<3:32:26, 1.34s/it] 85%|████████▍ | 52365/61904 [4:13:22<3:33:10, 1.34s/it] 85%|████████▍ | 52366/61904 [4:13:23<3:41:24, 1.39s/it] 85%|████████▍ | 52367/61904 [4:13:24<3:40:13, 1.39s/it] 85%|████████▍ | 52368/61904 [4:13:26<3:38:18, 1.37s/it] 85%|████████▍ | 52369/61904 [4:13:27<3:37:08, 1.37s/it] 85%|████████▍ | 52370/61904 [4:13:28<3:32:43, 1.34s/it] 85%|████████▍ | 52371/61904 [4:13:30<3:37:17, 1.37s/it] 85%|████████▍ | 52372/61904 [4:13:31<3:32:57, 1.34s/it] 85%|████████▍ | 52373/61904 [4:13:32<3:28:41, 1.31s/it] 85%|████████▍ | 52374/61904 [4:13:34<3:37:35, 1.37s/it] 85%|████████▍ | 52375/61904 [4:13:35<3:39:51, 1.38s/it] 85%|████████▍ | 52376/61904 [4:13:37<3:41:53, 1.40s/it] 85%|████████▍ | 52377/61904 [4:13:38<3:41:38, 1.40s/it] 85%|████████▍ | 52378/61904 [4:13:39<3:43:22, 1.41s/it] 85%|████████▍ | 52379/61904 [4:13:41<3:35:33, 1.36s/it] 85%|████████▍ | 52380/61904 [4:13:42<3:35:22, 1.36s/it] {'loss': 2.3907, 'learning_rate': 1.1543497990405808e-07, 'epoch': 13.54} + 85%|████████▍ | 52380/61904 [4:13:42<3:35:22, 1.36s/it] 85%|████████▍ | 52381/61904 [4:13:43<3:34:31, 1.35s/it] 85%|████████▍ | 52382/61904 [4:13:45<3:35:30, 1.36s/it] 85%|████████▍ | 52383/61904 [4:13:46<3:43:32, 1.41s/it] 85%|████████▍ | 52384/61904 [4:13:48<3:38:28, 1.38s/it] 85%|████████▍ | 52385/61904 [4:13:49<3:37:01, 1.37s/it] 85%|████████▍ | 52386/61904 [4:13:50<3:44:13, 1.41s/it] 85%|████████▍ | 52387/61904 [4:13:52<3:43:53, 1.41s/it] 85%|████████▍ | 52388/61904 [4:13:53<3:39:56, 1.39s/it] 85%|████████▍ | 52389/61904 [4:13:55<3:50:11, 1.45s/it] 85%|████████▍ | 52390/61904 [4:13:56<3:48:35, 1.44s/it] 85%|████████▍ | 52391/61904 [4:13:58<3:39:24, 1.38s/it] 85%|████████▍ | 52392/61904 [4:13:59<3:42:58, 1.41s/it] 85%|████████▍ | 52393/61904 [4:14:00<3:44:03, 1.41s/it] 85%|████████▍ | 52394/61904 [4:14:02<3:37:24, 1.37s/it] 85%|████████▍ | 52395/61904 [4:14:03<3:37:06, 1.37s/it] 85%|████████▍ | 52396/61904 [4:14:04<3:31:02, 1.33s/it] 85%|████████▍ | 52397/61904 [4:14:06<3:29:36, 1.32s/it] 85%|████████▍ | 52398/61904 [4:14:07<3:28:02, 1.31s/it] 85%|████████▍ | 52399/61904 [4:14:08<3:30:49, 1.33s/it] 85%|████████▍ | 52400/61904 [4:14:10<3:46:45, 1.43s/it] {'loss': 2.4323, 'learning_rate': 1.1540256709451574e-07, 'epoch': 13.54} + 85%|████████▍ | 52400/61904 [4:14:10<3:46:45, 1.43s/it] 85%|████████▍ | 52401/61904 [4:14:11<3:39:37, 1.39s/it] 85%|████████▍ | 52402/61904 [4:14:13<3:37:05, 1.37s/it] 85%|████████▍ | 52403/61904 [4:14:14<3:39:08, 1.38s/it] 85%|████████▍ | 52404/61904 [4:14:15<3:33:26, 1.35s/it] 85%|████████▍ | 52405/61904 [4:14:17<3:36:29, 1.37s/it] 85%|████████▍ | 52406/61904 [4:14:18<3:30:43, 1.33s/it] 85%|████████▍ | 52407/61904 [4:14:19<3:32:56, 1.35s/it] 85%|████████▍ | 52408/61904 [4:14:21<3:29:42, 1.32s/it] 85%|████████▍ | 52409/61904 [4:14:22<3:27:59, 1.31s/it] 85%|████████▍ | 52410/61904 [4:14:23<3:29:20, 1.32s/it] 85%|████████▍ | 52411/61904 [4:14:24<3:29:22, 1.32s/it] 85%|████████▍ | 52412/61904 [4:14:26<3:31:17, 1.34s/it] 85%|████████▍ | 52413/61904 [4:14:27<3:38:40, 1.38s/it] 85%|████████▍ | 52414/61904 [4:14:29<3:36:04, 1.37s/it] 85%|████████▍ | 52415/61904 [4:14:30<3:36:01, 1.37s/it] 85%|████████▍ | 52416/61904 [4:14:31<3:31:05, 1.33s/it] 85%|████████▍ | 52417/61904 [4:14:33<3:32:54, 1.35s/it] 85%|████████▍ | 52418/61904 [4:14:34<3:39:03, 1.39s/it] 85%|████████▍ | 52419/61904 [4:14:35<3:33:30, 1.35s/it] 85%|████████▍ | 52420/61904 [4:14:37<3:36:47, 1.37s/it] {'loss': 2.4375, 'learning_rate': 1.153701542849734e-07, 'epoch': 13.55} + 85%|████████▍ | 52420/61904 [4:14:37<3:36:47, 1.37s/it] 85%|████████▍ | 52421/61904 [4:14:38<3:37:32, 1.38s/it] 85%|████████▍ | 52422/61904 [4:14:40<3:39:43, 1.39s/it] 85%|████████▍ | 52423/61904 [4:14:41<3:39:27, 1.39s/it] 85%|████████▍ | 52424/61904 [4:14:43<3:44:11, 1.42s/it] 85%|████████▍ | 52425/61904 [4:14:44<3:38:24, 1.38s/it] 85%|████████▍ | 52426/61904 [4:14:45<3:39:50, 1.39s/it] 85%|████████▍ | 52427/61904 [4:14:47<3:44:27, 1.42s/it] 85%|████████▍ | 52428/61904 [4:14:48<3:48:22, 1.45s/it] 85%|████████▍ | 52429/61904 [4:14:50<3:43:29, 1.42s/it] 85%|████████▍ | 52430/61904 [4:14:51<3:43:30, 1.42s/it] 85%|████████▍ | 52431/61904 [4:14:52<3:43:32, 1.42s/it] 85%|████████▍ | 52432/61904 [4:14:54<3:45:28, 1.43s/it] 85%|████████▍ | 52433/61904 [4:14:55<3:38:00, 1.38s/it] 85%|████████▍ | 52434/61904 [4:14:56<3:36:21, 1.37s/it] 85%|████████▍ | 52435/61904 [4:14:58<3:35:05, 1.36s/it] 85%|████████▍ | 52436/61904 [4:14:59<3:33:22, 1.35s/it] 85%|████████▍ | 52437/61904 [4:15:00<3:33:16, 1.35s/it] 85%|████████▍ | 52438/61904 [4:15:02<3:30:41, 1.34s/it] 85%|████████▍ | 52439/61904 [4:15:03<3:39:27, 1.39s/it] 85%|████████▍ | 52440/61904 [4:15:05<3:33:08, 1.35s/it] {'loss': 2.4197, 'learning_rate': 1.1533774147543107e-07, 'epoch': 13.55} + 85%|████████▍ | 52440/61904 [4:15:05<3:33:08, 1.35s/it] 85%|████████▍ | 52441/61904 [4:15:06<3:38:02, 1.38s/it] 85%|████████▍ | 52442/61904 [4:15:07<3:36:06, 1.37s/it] 85%|████████▍ | 52443/61904 [4:15:09<3:40:58, 1.40s/it] 85%|████████▍ | 52444/61904 [4:15:10<3:44:10, 1.42s/it] 85%|████████▍ | 52445/61904 [4:15:12<3:42:37, 1.41s/it] 85%|████████▍ | 52446/61904 [4:15:13<3:41:49, 1.41s/it] 85%|████████▍ | 52447/61904 [4:15:14<3:39:13, 1.39s/it] 85%|████████▍ | 52448/61904 [4:15:16<3:41:29, 1.41s/it] 85%|████████▍ | 52449/61904 [4:15:17<3:39:59, 1.40s/it] 85%|████████▍ | 52450/61904 [4:15:19<3:40:51, 1.40s/it] 85%|████████▍ | 52451/61904 [4:15:20<3:37:01, 1.38s/it] 85%|████████▍ | 52452/61904 [4:15:21<3:33:01, 1.35s/it] 85%|████████▍ | 52453/61904 [4:15:23<3:35:44, 1.37s/it] 85%|████████▍ | 52454/61904 [4:15:24<3:41:34, 1.41s/it] 85%|████████▍ | 52455/61904 [4:15:26<3:45:43, 1.43s/it] 85%|████████▍ | 52456/61904 [4:15:27<3:45:00, 1.43s/it] 85%|████████▍ | 52457/61904 [4:15:29<3:48:32, 1.45s/it] 85%|████████▍ | 52458/61904 [4:15:30<3:52:23, 1.48s/it] 85%|████████▍ | 52459/61904 [4:15:31<3:45:37, 1.43s/it] 85%|████████▍ | 52460/61904 [4:15:33<3:39:10, 1.39s/it] {'loss': 2.4902, 'learning_rate': 1.1530532866588876e-07, 'epoch': 13.56} + 85%|████████▍ | 52460/61904 [4:15:33<3:39:10, 1.39s/it] 85%|████████▍ | 52461/61904 [4:15:34<3:36:32, 1.38s/it] 85%|████████▍ | 52462/61904 [4:15:35<3:31:21, 1.34s/it] 85%|████████▍ | 52463/61904 [4:15:37<3:32:57, 1.35s/it] 85%|████████▍ | 52464/61904 [4:15:38<3:36:19, 1.37s/it] 85%|████████▍ | 52465/61904 [4:15:40<3:42:57, 1.42s/it] 85%|████████▍ | 52466/61904 [4:15:41<3:40:53, 1.40s/it] 85%|████████▍ | 52467/61904 [4:15:42<3:38:05, 1.39s/it] 85%|████████▍ | 52468/61904 [4:15:44<3:41:09, 1.41s/it] 85%|████████▍ | 52469/61904 [4:15:45<3:41:26, 1.41s/it] 85%|████████▍ | 52470/61904 [4:15:47<3:44:24, 1.43s/it] 85%|████████▍ | 52471/61904 [4:15:48<3:40:43, 1.40s/it] 85%|████████▍ | 52472/61904 [4:15:50<3:42:16, 1.41s/it] 85%|████████▍ | 52473/61904 [4:15:51<3:39:26, 1.40s/it] 85%|████████▍ | 52474/61904 [4:15:52<3:44:32, 1.43s/it] 85%|████████▍ | 52475/61904 [4:15:54<3:40:05, 1.40s/it] 85%|████████▍ | 52476/61904 [4:15:55<3:37:35, 1.38s/it] 85%|████████▍ | 52477/61904 [4:15:56<3:36:08, 1.38s/it] 85%|████████▍ | 52478/61904 [4:15:58<3:26:59, 1.32s/it] 85%|████████▍ | 52479/61904 [4:15:59<3:28:18, 1.33s/it] 85%|████████▍ | 52480/61904 [4:16:00<3:29:45, 1.34s/it] {'loss': 2.4065, 'learning_rate': 1.1527291585634642e-07, 'epoch': 13.56} + 85%|████████▍ | 52480/61904 [4:16:00<3:29:45, 1.34s/it] 85%|████████▍ | 52481/61904 [4:16:02<3:34:36, 1.37s/it] 85%|████████▍ | 52482/61904 [4:16:03<3:38:23, 1.39s/it] 85%|████████▍ | 52483/61904 [4:16:05<3:41:34, 1.41s/it] 85%|████████▍ | 52484/61904 [4:16:06<3:35:08, 1.37s/it] 85%|████████▍ | 52485/61904 [4:16:07<3:35:47, 1.37s/it] 85%|████████▍ | 52486/61904 [4:16:09<3:34:49, 1.37s/it] 85%|████████▍ | 52487/61904 [4:16:10<3:26:12, 1.31s/it] 85%|████████▍ | 52488/61904 [4:16:11<3:30:43, 1.34s/it] 85%|████████▍ | 52489/61904 [4:16:13<3:26:32, 1.32s/it] 85%|████████▍ | 52490/61904 [4:16:14<3:24:58, 1.31s/it] 85%|████████▍ | 52491/61904 [4:16:15<3:38:14, 1.39s/it] 85%|████████▍ | 52492/61904 [4:16:17<3:34:37, 1.37s/it] 85%|████████▍ | 52493/61904 [4:16:18<3:35:13, 1.37s/it] 85%|████████▍ | 52494/61904 [4:16:20<3:42:06, 1.42s/it] 85%|████████▍ | 52495/61904 [4:16:21<3:38:36, 1.39s/it] 85%|████████▍ | 52496/61904 [4:16:22<3:40:36, 1.41s/it] 85%|████████▍ | 52497/61904 [4:16:24<3:42:55, 1.42s/it] 85%|████████▍ | 52498/61904 [4:16:25<3:37:13, 1.39s/it] 85%|████████▍ | 52499/61904 [4:16:26<3:35:09, 1.37s/it] 85%|████████▍ | 52500/61904 [4:16:28<3:36:52, 1.38s/it] {'loss': 2.4606, 'learning_rate': 1.1524050304680408e-07, 'epoch': 13.57} + 85%|████████▍ | 52500/61904 [4:16:28<3:36:52, 1.38s/it] 85%|████████▍ | 52501/61904 [4:16:29<3:37:46, 1.39s/it] 85%|████████▍ | 52502/61904 [4:16:31<3:36:48, 1.38s/it] 85%|████████▍ | 52503/61904 [4:16:32<3:35:34, 1.38s/it] 85%|████████▍ | 52504/61904 [4:16:33<3:39:02, 1.40s/it] 85%|████████▍ | 52505/61904 [4:16:35<3:42:13, 1.42s/it] 85%|████████▍ | 52506/61904 [4:16:36<3:35:46, 1.38s/it] 85%|████████▍ | 52507/61904 [4:16:37<3:28:47, 1.33s/it] 85%|████████▍ | 52508/61904 [4:16:39<3:28:27, 1.33s/it] 85%|████████▍ | 52509/61904 [4:16:40<3:36:43, 1.38s/it] 85%|████████▍ | 52510/61904 [4:16:42<3:45:56, 1.44s/it] 85%|████████▍ | 52511/61904 [4:16:43<3:48:50, 1.46s/it] 85%|████████▍ | 52512/61904 [4:16:45<3:54:32, 1.50s/it] 85%|████████▍ | 52513/61904 [4:16:46<3:42:12, 1.42s/it] 85%|████████▍ | 52514/61904 [4:16:47<3:32:08, 1.36s/it] 85%|████████▍ | 52515/61904 [4:16:49<3:32:37, 1.36s/it] 85%|████████▍ | 52516/61904 [4:16:50<3:35:19, 1.38s/it] 85%|████████▍ | 52517/61904 [4:16:52<3:32:29, 1.36s/it] 85%|████████▍ | 52518/61904 [4:16:53<3:36:43, 1.39s/it] 85%|████████▍ | 52519/61904 [4:16:54<3:42:38, 1.42s/it] 85%|████████▍ | 52520/61904 [4:16:56<3:41:02, 1.41s/it] {'loss': 2.4576, 'learning_rate': 1.1520809023726174e-07, 'epoch': 13.57} + 85%|████████▍ | 52520/61904 [4:16:56<3:41:02, 1.41s/it] 85%|████████▍ | 52521/61904 [4:16:57<3:49:50, 1.47s/it] 85%|████████▍ | 52522/61904 [4:16:59<3:43:23, 1.43s/it] 85%|████████▍ | 52523/61904 [4:17:00<3:40:28, 1.41s/it] 85%|████████▍ | 52524/61904 [4:17:02<3:38:23, 1.40s/it] 85%|████████▍ | 52525/61904 [4:17:03<3:36:28, 1.38s/it] 85%|████████▍ | 52526/61904 [4:17:04<3:42:07, 1.42s/it] 85%|████████▍ | 52527/61904 [4:17:06<3:42:14, 1.42s/it] 85%|████████▍ | 52528/61904 [4:17:07<3:37:47, 1.39s/it] 85%|████████▍ | 52529/61904 [4:17:08<3:35:04, 1.38s/it] 85%|████████▍ | 52530/61904 [4:17:10<3:29:18, 1.34s/it] 85%|████████▍ | 52531/61904 [4:17:11<3:30:44, 1.35s/it] 85%|████████▍ | 52532/61904 [4:17:12<3:29:05, 1.34s/it] 85%|████████▍ | 52533/61904 [4:17:14<3:34:26, 1.37s/it] 85%|████████▍ | 52534/61904 [4:17:15<3:33:57, 1.37s/it] 85%|████████▍ | 52535/61904 [4:17:17<3:37:55, 1.40s/it] 85%|████████▍ | 52536/61904 [4:17:18<3:34:37, 1.37s/it] 85%|████████▍ | 52537/61904 [4:17:19<3:38:30, 1.40s/it] 85%|████████▍ | 52538/61904 [4:17:21<3:38:44, 1.40s/it] 85%|████████▍ | 52539/61904 [4:17:22<3:34:45, 1.38s/it] 85%|████████▍ | 52540/61904 [4:17:23<3:31:12, 1.35s/it] {'loss': 2.4596, 'learning_rate': 1.1517567742771943e-07, 'epoch': 13.58} + 85%|████████▍ | 52540/61904 [4:17:23<3:31:12, 1.35s/it] 85%|████████▍ | 52541/61904 [4:17:25<3:35:08, 1.38s/it] 85%|████████▍ | 52542/61904 [4:17:26<3:29:57, 1.35s/it] 85%|████████▍ | 52543/61904 [4:17:28<3:32:30, 1.36s/it] 85%|████████▍ | 52544/61904 [4:17:29<3:36:34, 1.39s/it] 85%|████████▍ | 52545/61904 [4:17:30<3:35:20, 1.38s/it] 85%|████████▍ | 52546/61904 [4:17:32<3:42:48, 1.43s/it] 85%|████████▍ | 52547/61904 [4:17:33<3:41:46, 1.42s/it] 85%|████████▍ | 52548/61904 [4:17:35<3:34:43, 1.38s/it] 85%|████████▍ | 52549/61904 [4:17:36<3:32:59, 1.37s/it] 85%|████████▍ | 52550/61904 [4:17:37<3:31:59, 1.36s/it] 85%|████████▍ | 52551/61904 [4:17:39<3:25:18, 1.32s/it] 85%|████████▍ | 52552/61904 [4:17:40<3:32:25, 1.36s/it] 85%|████████▍ | 52553/61904 [4:17:41<3:37:01, 1.39s/it] 85%|████████▍ | 52554/61904 [4:17:43<3:36:13, 1.39s/it] 85%|████████▍ | 52555/61904 [4:17:44<3:39:08, 1.41s/it] 85%|████████▍ | 52556/61904 [4:17:46<3:41:16, 1.42s/it] 85%|████████▍ | 52557/61904 [4:17:47<3:39:01, 1.41s/it] 85%|████████▍ | 52558/61904 [4:17:49<3:38:33, 1.40s/it] 85%|████████▍ | 52559/61904 [4:17:50<3:40:56, 1.42s/it] 85%|████████▍ | 52560/61904 [4:17:51<3:41:35, 1.42s/it] {'loss': 2.4678, 'learning_rate': 1.1514326461817709e-07, 'epoch': 13.58} + 85%|████████▍ | 52560/61904 [4:17:51<3:41:35, 1.42s/it] 85%|████████▍ | 52561/61904 [4:17:53<3:47:19, 1.46s/it] 85%|████████▍ | 52562/61904 [4:17:54<3:44:46, 1.44s/it] 85%|████████▍ | 52563/61904 [4:17:56<3:39:40, 1.41s/it] 85%|████████▍ | 52564/61904 [4:17:57<3:41:01, 1.42s/it] 85%|████████▍ | 52565/61904 [4:17:58<3:35:46, 1.39s/it] 85%|████████▍ | 52566/61904 [4:18:00<3:36:47, 1.39s/it] 85%|████████▍ | 52567/61904 [4:18:01<3:35:43, 1.39s/it] 85%|████████▍ | 52568/61904 [4:18:03<3:37:34, 1.40s/it] 85%|████████▍ | 52569/61904 [4:18:04<3:32:38, 1.37s/it] 85%|████████▍ | 52570/61904 [4:18:05<3:41:43, 1.43s/it] 85%|████████▍ | 52571/61904 [4:18:07<3:41:42, 1.43s/it] 85%|████████▍ | 52572/61904 [4:18:08<3:37:21, 1.40s/it] 85%|████████▍ | 52573/61904 [4:18:10<3:35:34, 1.39s/it] 85%|████████▍ | 52574/61904 [4:18:11<3:41:13, 1.42s/it] 85%|████████▍ | 52575/61904 [4:18:13<3:45:43, 1.45s/it] 85%|████████▍ | 52576/61904 [4:18:14<3:52:40, 1.50s/it] 85%|████████▍ | 52577/61904 [4:18:16<3:46:52, 1.46s/it] 85%|████████▍ | 52578/61904 [4:18:17<3:47:34, 1.46s/it] 85%|████████▍ | 52579/61904 [4:18:19<3:55:18, 1.51s/it] 85%|████████▍ | 52580/61904 [4:18:20<3:50:26, 1.48s/it] {'loss': 2.4333, 'learning_rate': 1.1511085180863475e-07, 'epoch': 13.59} + 85%|████████▍ | 52580/61904 [4:18:20<3:50:26, 1.48s/it] 85%|████████▍ | 52581/61904 [4:18:21<3:43:42, 1.44s/it] 85%|████████▍ | 52582/61904 [4:18:23<3:35:38, 1.39s/it] 85%|████████▍ | 52583/61904 [4:18:24<3:37:13, 1.40s/it] 85%|████████▍ | 52584/61904 [4:18:26<3:36:11, 1.39s/it] 85%|████████▍ | 52585/61904 [4:18:27<3:43:17, 1.44s/it] 85%|████████▍ | 52586/61904 [4:18:29<3:46:05, 1.46s/it] 85%|████████▍ | 52587/61904 [4:18:30<3:39:01, 1.41s/it] 85%|████████▍ | 52588/61904 [4:18:31<3:37:10, 1.40s/it] 85%|████████▍ | 52589/61904 [4:18:33<3:31:39, 1.36s/it] 85%|████████▍ | 52590/61904 [4:18:34<3:32:21, 1.37s/it] 85%|████████▍ | 52591/61904 [4:18:35<3:33:13, 1.37s/it] 85%|████████▍ | 52592/61904 [4:18:37<3:31:00, 1.36s/it] 85%|████████▍ | 52593/61904 [4:18:38<3:33:18, 1.37s/it] 85%|████████▍ | 52594/61904 [4:18:40<3:43:00, 1.44s/it] 85%|████████▍ | 52595/61904 [4:18:41<3:42:49, 1.44s/it] 85%|████████▍ | 52596/61904 [4:18:42<3:39:30, 1.41s/it] 85%|████████▍ | 52597/61904 [4:18:44<3:38:17, 1.41s/it] 85%|████████▍ | 52598/61904 [4:18:45<3:34:40, 1.38s/it] 85%|████████▍ | 52599/61904 [4:18:47<3:41:16, 1.43s/it] 85%|████████▍ | 52600/61904 [4:18:48<3:38:53, 1.41s/it] {'loss': 2.4255, 'learning_rate': 1.1507843899909241e-07, 'epoch': 13.59} + 85%|████████▍ | 52600/61904 [4:18:48<3:38:53, 1.41s/it] 85%|████████▍ | 52601/61904 [4:18:49<3:36:45, 1.40s/it] 85%|████████▍ | 52602/61904 [4:18:51<3:39:25, 1.42s/it] 85%|████████▍ | 52603/61904 [4:18:52<3:42:29, 1.44s/it] 85%|████████▍ | 52604/61904 [4:18:54<3:41:54, 1.43s/it] 85%|████████▍ | 52605/61904 [4:18:55<3:39:02, 1.41s/it] 85%|████████▍ | 52606/61904 [4:18:57<3:39:09, 1.41s/it] 85%|████████▍ | 52607/61904 [4:18:58<3:43:46, 1.44s/it] 85%|████████▍ | 52608/61904 [4:18:59<3:41:08, 1.43s/it] 85%|████████▍ | 52609/61904 [4:19:01<3:38:38, 1.41s/it] 85%|████████▍ | 52610/61904 [4:19:02<3:49:15, 1.48s/it] 85%|████████▍ | 52611/61904 [4:19:04<3:46:40, 1.46s/it] 85%|████████▍ | 52612/61904 [4:19:05<3:46:08, 1.46s/it] 85%|████████▍ | 52613/61904 [4:19:07<3:48:23, 1.47s/it] 85%|████████▍ | 52614/61904 [4:19:08<3:45:37, 1.46s/it] 85%|████████▍ | 52615/61904 [4:19:10<3:48:42, 1.48s/it] 85%|████████▍ | 52616/61904 [4:19:11<3:51:26, 1.50s/it] 85%|████████▍ | 52617/61904 [4:19:13<3:56:14, 1.53s/it] 85%|████████▍ | 52618/61904 [4:19:14<3:46:33, 1.46s/it] 85%|████████▌ | 52619/61904 [4:19:16<3:41:47, 1.43s/it] 85%|████████▌ | 52620/61904 [4:19:17<3:47:37, 1.47s/it] {'loss': 2.414, 'learning_rate': 1.150460261895501e-07, 'epoch': 13.6} + 85%|████████▌ | 52620/61904 [4:19:17<3:47:37, 1.47s/it] 85%|████████▌ | 52621/61904 [4:19:18<3:40:47, 1.43s/it] 85%|████████▌ | 52622/61904 [4:19:20<3:38:34, 1.41s/it] 85%|████████▌ | 52623/61904 [4:19:21<3:33:47, 1.38s/it] 85%|████████▌ | 52624/61904 [4:19:23<3:34:53, 1.39s/it] 85%|████████▌ | 52625/61904 [4:19:24<3:41:16, 1.43s/it] 85%|████████▌ | 52626/61904 [4:19:26<3:40:44, 1.43s/it] 85%|████████▌ | 52627/61904 [4:19:27<3:37:19, 1.41s/it] 85%|████████▌ | 52628/61904 [4:19:28<3:39:48, 1.42s/it] 85%|████████▌ | 52629/61904 [4:19:30<3:39:00, 1.42s/it] 85%|████████▌ | 52630/61904 [4:19:31<3:45:47, 1.46s/it] 85%|████████▌ | 52631/61904 [4:19:33<3:42:01, 1.44s/it] 85%|████████▌ | 52632/61904 [4:19:34<3:41:21, 1.43s/it] 85%|████████▌ | 52633/61904 [4:19:35<3:33:28, 1.38s/it] 85%|████████▌ | 52634/61904 [4:19:37<3:40:59, 1.43s/it] 85%|████████▌ | 52635/61904 [4:19:38<3:37:54, 1.41s/it] 85%|████████▌ | 52636/61904 [4:19:40<3:33:00, 1.38s/it] 85%|████████▌ | 52637/61904 [4:19:41<3:37:11, 1.41s/it] 85%|████████▌ | 52638/61904 [4:19:43<3:41:19, 1.43s/it] 85%|████████▌ | 52639/61904 [4:19:44<3:44:40, 1.46s/it] 85%|████████▌ | 52640/61904 [4:19:45<3:41:08, 1.43s/it] {'loss': 2.4667, 'learning_rate': 1.1501361338000777e-07, 'epoch': 13.61} + 85%|████████▌ | 52640/61904 [4:19:45<3:41:08, 1.43s/it] 85%|████████▌ | 52641/61904 [4:19:47<3:34:07, 1.39s/it] 85%|████████▌ | 52642/61904 [4:19:48<3:35:06, 1.39s/it] 85%|████████▌ | 52643/61904 [4:19:49<3:32:08, 1.37s/it] 85%|████████▌ | 52644/61904 [4:19:51<3:29:39, 1.36s/it] 85%|████████▌ | 52645/61904 [4:19:52<3:35:55, 1.40s/it] 85%|████████▌ | 52646/61904 [4:19:54<3:33:54, 1.39s/it] 85%|████████▌ | 52647/61904 [4:19:55<3:36:32, 1.40s/it] 85%|████████▌ | 52648/61904 [4:19:57<3:36:54, 1.41s/it] 85%|████████▌ | 52649/61904 [4:19:58<3:39:14, 1.42s/it] 85%|████████▌ | 52650/61904 [4:19:59<3:42:01, 1.44s/it] 85%|████████▌ | 52651/61904 [4:20:01<3:37:01, 1.41s/it] 85%|████████▌ | 52652/61904 [4:20:02<3:32:29, 1.38s/it] 85%|████████▌ | 52653/61904 [4:20:03<3:32:27, 1.38s/it] 85%|████████▌ | 52654/61904 [4:20:05<3:28:59, 1.36s/it] 85%|████████▌ | 52655/61904 [4:20:06<3:27:46, 1.35s/it] 85%|████████▌ | 52656/61904 [4:20:07<3:29:25, 1.36s/it] 85%|████████▌ | 52657/61904 [4:20:09<3:28:41, 1.35s/it] 85%|████████▌ | 52658/61904 [4:20:10<3:33:48, 1.39s/it] 85%|████████▌ | 52659/61904 [4:20:12<3:34:59, 1.40s/it] 85%|████████▌ | 52660/61904 [4:20:13<3:31:39, 1.37s/it] {'loss': 2.4574, 'learning_rate': 1.1498120057046543e-07, 'epoch': 13.61} + 85%|████████▌ | 52660/61904 [4:20:13<3:31:39, 1.37s/it] 85%|████████▌ | 52661/61904 [4:20:14<3:33:06, 1.38s/it] 85%|████████▌ | 52662/61904 [4:20:16<3:34:33, 1.39s/it] 85%|████████▌ | 52663/61904 [4:20:17<3:34:22, 1.39s/it] 85%|████████▌ | 52664/61904 [4:20:19<3:35:33, 1.40s/it] 85%|████████▌ | 52665/61904 [4:20:20<3:34:16, 1.39s/it] 85%|████████▌ | 52666/61904 [4:20:21<3:34:45, 1.39s/it] 85%|████████▌ | 52667/61904 [4:20:23<3:31:13, 1.37s/it] 85%|████████▌ | 52668/61904 [4:20:24<3:31:37, 1.37s/it] 85%|████████▌ | 52669/61904 [4:20:26<3:31:31, 1.37s/it] 85%|████████▌ | 52670/61904 [4:20:27<3:30:53, 1.37s/it] 85%|████████▌ | 52671/61904 [4:20:28<3:30:40, 1.37s/it] 85%|████████▌ | 52672/61904 [4:20:29<3:25:48, 1.34s/it] 85%|████████▌ | 52673/61904 [4:20:31<3:24:35, 1.33s/it] 85%|████████▌ | 52674/61904 [4:20:32<3:26:34, 1.34s/it] 85%|████████▌ | 52675/61904 [4:20:34<3:28:55, 1.36s/it] 85%|████████▌ | 52676/61904 [4:20:35<3:30:56, 1.37s/it] 85%|████████▌ | 52677/61904 [4:20:36<3:31:56, 1.38s/it] 85%|████████▌ | 52678/61904 [4:20:38<3:29:27, 1.36s/it] 85%|████████▌ | 52679/61904 [4:20:39<3:28:30, 1.36s/it] 85%|████████▌ | 52680/61904 [4:20:40<3:32:15, 1.38s/it] {'loss': 2.4472, 'learning_rate': 1.1494878776092312e-07, 'epoch': 13.62} + 85%|████████▌ | 52680/61904 [4:20:40<3:32:15, 1.38s/it] 85%|████████▌ | 52681/61904 [4:20:42<3:26:13, 1.34s/it] 85%|████████▌ | 52682/61904 [4:20:43<3:26:22, 1.34s/it] 85%|████████▌ | 52683/61904 [4:20:45<3:31:25, 1.38s/it] 85%|████████▌ | 52684/61904 [4:20:46<3:34:55, 1.40s/it] 85%|████████▌ | 52685/61904 [4:20:47<3:35:33, 1.40s/it] 85%|████████▌ | 52686/61904 [4:20:49<3:38:38, 1.42s/it] 85%|████████▌ | 52687/61904 [4:20:50<3:32:01, 1.38s/it] 85%|████████▌ | 52688/61904 [4:20:52<3:33:37, 1.39s/it] 85%|████████▌ | 52689/61904 [4:20:53<3:35:51, 1.41s/it] 85%|████████▌ | 52690/61904 [4:20:54<3:39:08, 1.43s/it] 85%|████████▌ | 52691/61904 [4:20:56<3:31:14, 1.38s/it] 85%|████████▌ | 52692/61904 [4:20:57<3:30:21, 1.37s/it] 85%|████████▌ | 52693/61904 [4:20:59<3:34:41, 1.40s/it] 85%|████████▌ | 52694/61904 [4:21:00<3:34:54, 1.40s/it] 85%|████████▌ | 52695/61904 [4:21:01<3:34:12, 1.40s/it] 85%|████████▌ | 52696/61904 [4:21:03<3:35:09, 1.40s/it] 85%|████████▌ | 52697/61904 [4:21:04<3:29:28, 1.37s/it] 85%|████████▌ | 52698/61904 [4:21:05<3:28:51, 1.36s/it] 85%|████████▌ | 52699/61904 [4:21:07<3:28:49, 1.36s/it] 85%|████████▌ | 52700/61904 [4:21:08<3:27:58, 1.36s/it] {'loss': 2.4838, 'learning_rate': 1.1491637495138078e-07, 'epoch': 13.62} + 85%|████████▌ | 52700/61904 [4:21:08<3:27:58, 1.36s/it] 85%|████████▌ | 52701/61904 [4:21:10<3:34:39, 1.40s/it] 85%|████████▌ | 52702/61904 [4:21:11<3:36:24, 1.41s/it] 85%|████████▌ | 52703/61904 [4:21:12<3:31:33, 1.38s/it] 85%|████████▌ | 52704/61904 [4:21:14<3:34:26, 1.40s/it] 85%|████████▌ | 52705/61904 [4:21:15<3:31:03, 1.38s/it] 85%|████████▌ | 52706/61904 [4:21:16<3:28:50, 1.36s/it] 85%|████████▌ | 52707/61904 [4:21:18<3:38:39, 1.43s/it] 85%|████████▌ | 52708/61904 [4:21:19<3:33:04, 1.39s/it] 85%|████████▌ | 52709/61904 [4:21:21<3:34:00, 1.40s/it] 85%|████████▌ | 52710/61904 [4:21:22<3:39:11, 1.43s/it] 85%|████████▌ | 52711/61904 [4:21:24<3:34:17, 1.40s/it] 85%|████████▌ | 52712/61904 [4:21:25<3:34:08, 1.40s/it] 85%|████████▌ | 52713/61904 [4:21:26<3:37:29, 1.42s/it] 85%|████████▌ | 52714/61904 [4:21:28<3:34:05, 1.40s/it] 85%|████████▌ | 52715/61904 [4:21:29<3:28:07, 1.36s/it] 85%|████████▌ | 52716/61904 [4:21:30<3:27:40, 1.36s/it] 85%|████████▌ | 52717/61904 [4:21:32<3:27:45, 1.36s/it] 85%|████████▌ | 52718/61904 [4:21:33<3:27:12, 1.35s/it] 85%|████████▌ | 52719/61904 [4:21:35<3:36:27, 1.41s/it] 85%|████████▌ | 52720/61904 [4:21:36<3:31:59, 1.38s/it] {'loss': 2.4244, 'learning_rate': 1.1488396214183844e-07, 'epoch': 13.63} + 85%|████████▌ | 52720/61904 [4:21:36<3:31:59, 1.38s/it] 85%|████████▌ | 52721/61904 [4:21:37<3:31:05, 1.38s/it] 85%|████████▌ | 52722/61904 [4:21:39<3:29:24, 1.37s/it] 85%|████████▌ | 52723/61904 [4:21:40<3:24:46, 1.34s/it] 85%|████████▌ | 52724/61904 [4:21:41<3:23:38, 1.33s/it] 85%|████████▌ | 52725/61904 [4:21:43<3:26:26, 1.35s/it] 85%|████████▌ | 52726/61904 [4:21:44<3:33:15, 1.39s/it] 85%|████████▌ | 52727/61904 [4:21:46<3:31:29, 1.38s/it] 85%|████████▌ | 52728/61904 [4:21:47<3:35:04, 1.41s/it] 85%|████████▌ | 52729/61904 [4:21:48<3:36:42, 1.42s/it] 85%|████████▌ | 52730/61904 [4:21:50<3:36:54, 1.42s/it] 85%|████████▌ | 52731/61904 [4:21:51<3:30:47, 1.38s/it] 85%|████████▌ | 52732/61904 [4:21:52<3:29:27, 1.37s/it] 85%|████████▌ | 52733/61904 [4:21:54<3:44:07, 1.47s/it] 85%|████████▌ | 52734/61904 [4:21:56<3:38:27, 1.43s/it] 85%|████████▌ | 52735/61904 [4:21:57<3:37:22, 1.42s/it] 85%|████████▌ | 52736/61904 [4:21:58<3:31:29, 1.38s/it] 85%|████████▌ | 52737/61904 [4:22:00<3:29:46, 1.37s/it] 85%|████████▌ | 52738/61904 [4:22:01<3:26:54, 1.35s/it] 85%|████████▌ | 52739/61904 [4:22:02<3:33:07, 1.40s/it] 85%|████████▌ | 52740/61904 [4:22:04<3:44:54, 1.47s/it] {'loss': 2.4486, 'learning_rate': 1.148515493322961e-07, 'epoch': 13.63} + 85%|████████▌ | 52740/61904 [4:22:04<3:44:54, 1.47s/it] 85%|████████▌ | 52741/61904 [4:22:05<3:45:55, 1.48s/it] 85%|████████▌ | 52742/61904 [4:22:07<3:43:32, 1.46s/it] 85%|████████▌ | 52743/61904 [4:22:08<3:44:14, 1.47s/it] 85%|████████▌ | 52744/61904 [4:22:10<3:45:31, 1.48s/it] 85%|████████▌ | 52745/61904 [4:22:11<3:36:19, 1.42s/it] 85%|████████▌ | 52746/61904 [4:22:13<3:35:25, 1.41s/it] 85%|████████▌ | 52747/61904 [4:22:14<3:33:23, 1.40s/it] 85%|████████▌ | 52748/61904 [4:22:15<3:24:00, 1.34s/it] 85%|████████▌ | 52749/61904 [4:22:16<3:20:45, 1.32s/it] 85%|████████▌ | 52750/61904 [4:22:18<3:22:25, 1.33s/it] 85%|████████▌ | 52751/61904 [4:22:19<3:24:53, 1.34s/it] 85%|████████▌ | 52752/61904 [4:22:21<3:27:23, 1.36s/it] 85%|████████▌ | 52753/61904 [4:22:22<3:25:51, 1.35s/it] 85%|████████▌ | 52754/61904 [4:22:23<3:22:28, 1.33s/it] 85%|████████▌ | 52755/61904 [4:22:25<3:28:05, 1.36s/it] 85%|████████▌ | 52756/61904 [4:22:26<3:24:26, 1.34s/it] 85%|████████▌ | 52757/61904 [4:22:27<3:24:39, 1.34s/it] 85%|████████▌ | 52758/61904 [4:22:29<3:21:55, 1.32s/it] 85%|████████▌ | 52759/61904 [4:22:30<3:23:40, 1.34s/it] 85%|████████▌ | 52760/61904 [4:22:31<3:23:18, 1.33s/it] {'loss': 2.4595, 'learning_rate': 1.1481913652275379e-07, 'epoch': 13.64} + 85%|████████▌ | 52760/61904 [4:22:31<3:23:18, 1.33s/it] 85%|████████▌ | 52761/61904 [4:22:33<3:21:55, 1.33s/it] 85%|████████▌ | 52762/61904 [4:22:34<3:23:59, 1.34s/it] 85%|████████▌ | 52763/61904 [4:22:35<3:24:54, 1.34s/it] 85%|████████▌ | 52764/61904 [4:22:37<3:22:24, 1.33s/it] 85%|████████▌ | 52765/61904 [4:22:38<3:30:55, 1.38s/it] 85%|████████▌ | 52766/61904 [4:22:39<3:26:46, 1.36s/it] 85%|████████▌ | 52767/61904 [4:22:41<3:30:06, 1.38s/it] 85%|████████▌ | 52768/61904 [4:22:42<3:30:19, 1.38s/it] 85%|████████▌ | 52769/61904 [4:22:44<3:32:12, 1.39s/it] 85%|████████▌ | 52770/61904 [4:22:45<3:33:41, 1.40s/it] 85%|████████▌ | 52771/61904 [4:22:46<3:35:33, 1.42s/it] 85%|████████▌ | 52772/61904 [4:22:48<3:39:25, 1.44s/it] 85%|████████▌ | 52773/61904 [4:22:49<3:35:44, 1.42s/it] 85%|████████▌ | 52774/61904 [4:22:51<3:29:33, 1.38s/it] 85%|████████▌ | 52775/61904 [4:22:52<3:30:15, 1.38s/it] 85%|████████▌ | 52776/61904 [4:22:53<3:28:24, 1.37s/it] 85%|████████▌ | 52777/61904 [4:22:55<3:29:02, 1.37s/it] 85%|████████▌ | 52778/61904 [4:22:56<3:32:31, 1.40s/it] 85%|██���█████▌ | 52779/61904 [4:22:58<3:32:43, 1.40s/it] 85%|████████▌ | 52780/61904 [4:22:59<3:30:26, 1.38s/it] {'loss': 2.4267, 'learning_rate': 1.1478672371321145e-07, 'epoch': 13.64} + 85%|████████▌ | 52780/61904 [4:22:59<3:30:26, 1.38s/it] 85%|████████▌ | 52781/61904 [4:23:00<3:35:49, 1.42s/it] 85%|████████▌ | 52782/61904 [4:23:02<3:32:31, 1.40s/it] 85%|████████▌ | 52783/61904 [4:23:03<3:29:43, 1.38s/it] 85%|████████▌ | 52784/61904 [4:23:04<3:28:10, 1.37s/it] 85%|████████▌ | 52785/61904 [4:23:06<3:28:33, 1.37s/it] 85%|████████▌ | 52786/61904 [4:23:07<3:24:03, 1.34s/it] 85%|████████▌ | 52787/61904 [4:23:08<3:26:28, 1.36s/it] 85%|████████▌ | 52788/61904 [4:23:10<3:22:57, 1.34s/it] 85%|████████▌ | 52789/61904 [4:23:11<3:34:36, 1.41s/it] 85%|████████▌ | 52790/61904 [4:23:13<3:28:41, 1.37s/it] 85%|████████▌ | 52791/61904 [4:23:14<3:27:52, 1.37s/it] 85%|████████▌ | 52792/61904 [4:23:16<3:34:23, 1.41s/it] 85%|████████▌ | 52793/61904 [4:23:17<3:34:07, 1.41s/it] 85%|████████▌ | 52794/61904 [4:23:18<3:33:02, 1.40s/it] 85%|████████▌ | 52795/61904 [4:23:20<3:34:20, 1.41s/it] 85%|████████▌ | 52796/61904 [4:23:21<3:33:26, 1.41s/it] 85%|████████▌ | 52797/61904 [4:23:23<3:35:50, 1.42s/it] 85%|████████▌ | 52798/61904 [4:23:24<3:36:12, 1.42s/it] 85%|████████▌ | 52799/61904 [4:23:25<3:31:09, 1.39s/it] 85%|████████▌ | 52800/61904 [4:23:27<3:36:55, 1.43s/it] {'loss': 2.4348, 'learning_rate': 1.1475431090366911e-07, 'epoch': 13.65} + 85%|████████▌ | 52800/61904 [4:23:27<3:36:55, 1.43s/it] 85%|████████▌ | 52801/61904 [4:23:28<3:28:07, 1.37s/it] 85%|████████▌ | 52802/61904 [4:23:29<3:27:34, 1.37s/it] 85%|████████▌ | 52803/61904 [4:23:31<3:26:59, 1.36s/it] 85%|████████▌ | 52804/61904 [4:23:32<3:31:03, 1.39s/it] 85%|████████▌ | 52805/61904 [4:23:34<3:39:34, 1.45s/it] 85%|████████▌ | 52806/61904 [4:23:35<3:33:30, 1.41s/it] 85%|████████▌ | 52807/61904 [4:23:37<3:38:23, 1.44s/it] 85%|████████▌ | 52808/61904 [4:23:38<3:35:53, 1.42s/it] 85%|████████▌ | 52809/61904 [4:23:39<3:35:53, 1.42s/it] 85%|████████▌ | 52810/61904 [4:23:41<3:36:41, 1.43s/it] 85%|████████▌ | 52811/61904 [4:23:42<3:31:59, 1.40s/it] 85%|████████▌ | 52812/61904 [4:23:44<3:27:21, 1.37s/it] 85%|████████▌ | 52813/61904 [4:23:45<3:32:43, 1.40s/it] 85%|████████▌ | 52814/61904 [4:23:46<3:29:09, 1.38s/it] 85%|████████▌ | 52815/61904 [4:23:48<3:31:48, 1.40s/it] 85%|████████▌ | 52816/61904 [4:23:49<3:29:06, 1.38s/it] 85%|████████▌ | 52817/61904 [4:23:50<3:25:48, 1.36s/it] 85%|████████▌ | 52818/61904 [4:23:52<3:23:57, 1.35s/it] 85%|████████▌ | 52819/61904 [4:23:53<3:24:33, 1.35s/it] 85%|████████▌ | 52820/61904 [4:23:54<3:22:12, 1.34s/it] {'loss': 2.4963, 'learning_rate': 1.1472189809412677e-07, 'epoch': 13.65} + 85%|████████▌ | 52820/61904 [4:23:54<3:22:12, 1.34s/it] 85%|████████▌ | 52821/61904 [4:23:56<3:30:38, 1.39s/it] 85%|████████▌ | 52822/61904 [4:23:57<3:34:24, 1.42s/it] 85%|████████▌ | 52823/61904 [4:23:59<3:33:44, 1.41s/it] 85%|████████▌ | 52824/61904 [4:24:00<3:27:47, 1.37s/it] 85%|████████▌ | 52825/61904 [4:24:02<3:33:43, 1.41s/it] 85%|████████▌ | 52826/61904 [4:24:03<3:36:08, 1.43s/it] 85%|████████▌ | 52827/61904 [4:24:04<3:33:41, 1.41s/it] 85%|████████▌ | 52828/61904 [4:24:06<3:29:02, 1.38s/it] 85%|████████▌ | 52829/61904 [4:24:07<3:35:08, 1.42s/it] 85%|████████▌ | 52830/61904 [4:24:09<3:41:28, 1.46s/it] 85%|████████▌ | 52831/61904 [4:24:10<3:38:38, 1.45s/it] 85%|████████▌ | 52832/61904 [4:24:12<3:40:19, 1.46s/it] 85%|████████▌ | 52833/61904 [4:24:13<3:35:49, 1.43s/it] 85%|████████▌ | 52834/61904 [4:24:14<3:26:43, 1.37s/it] 85%|████████▌ | 52835/61904 [4:24:16<3:24:50, 1.36s/it] 85%|████████▌ | 52836/61904 [4:24:17<3:23:30, 1.35s/it] 85%|████████▌ | 52837/61904 [4:24:18<3:19:08, 1.32s/it] 85%|████���███▌ | 52838/61904 [4:24:20<3:26:54, 1.37s/it] 85%|████████▌ | 52839/61904 [4:24:21<3:26:57, 1.37s/it] 85%|████████▌ | 52840/61904 [4:24:23<3:32:52, 1.41s/it] {'loss': 2.3726, 'learning_rate': 1.1468948528458446e-07, 'epoch': 13.66} + 85%|████████▌ | 52840/61904 [4:24:23<3:32:52, 1.41s/it] 85%|████████▌ | 52841/61904 [4:24:24<3:34:42, 1.42s/it] 85%|████████▌ | 52842/61904 [4:24:25<3:30:37, 1.39s/it] 85%|████████▌ | 52843/61904 [4:24:27<3:27:28, 1.37s/it] 85%|████████▌ | 52844/61904 [4:24:28<3:25:25, 1.36s/it] 85%|████████▌ | 52845/61904 [4:24:29<3:27:04, 1.37s/it] 85%|████████▌ | 52846/61904 [4:24:31<3:28:35, 1.38s/it] 85%|████████▌ | 52847/61904 [4:24:32<3:33:13, 1.41s/it] 85%|████████▌ | 52848/61904 [4:24:34<3:31:45, 1.40s/it] 85%|████████▌ | 52849/61904 [4:24:35<3:26:32, 1.37s/it] 85%|████████▌ | 52850/61904 [4:24:36<3:27:37, 1.38s/it] 85%|████████▌ | 52851/61904 [4:24:38<3:29:11, 1.39s/it] 85%|████████▌ | 52852/61904 [4:24:39<3:33:04, 1.41s/it] 85%|████████▌ | 52853/61904 [4:24:41<3:31:35, 1.40s/it] 85%|████████▌ | 52854/61904 [4:24:42<3:33:50, 1.42s/it] 85%|████████▌ | 52855/61904 [4:24:43<3:33:09, 1.41s/it] 85%|████████▌ | 52856/61904 [4:24:45<3:31:37, 1.40s/it] 85%|████████▌ | 52857/61904 [4:24:46<3:31:22, 1.40s/it] 85%|████████▌ | 52858/61904 [4:24:48<3:30:06, 1.39s/it] 85%|████████▌ | 52859/61904 [4:24:49<3:23:58, 1.35s/it] 85%|████████▌ | 52860/61904 [4:24:50<3:18:18, 1.32s/it] {'loss': 2.3944, 'learning_rate': 1.1465707247504213e-07, 'epoch': 13.66} + 85%|████████▌ | 52860/61904 [4:24:50<3:18:18, 1.32s/it] 85%|████████▌ | 52861/61904 [4:24:52<3:23:16, 1.35s/it] 85%|████████▌ | 52862/61904 [4:24:53<3:25:26, 1.36s/it] 85%|████████▌ | 52863/61904 [4:24:54<3:28:36, 1.38s/it] 85%|████████▌ | 52864/61904 [4:24:56<3:30:12, 1.40s/it] 85%|████████▌ | 52865/61904 [4:24:57<3:25:33, 1.36s/it] 85%|████████▌ | 52866/61904 [4:24:58<3:22:58, 1.35s/it] 85%|████████▌ | 52867/61904 [4:25:00<3:26:26, 1.37s/it] 85%|████████▌ | 52868/61904 [4:25:01<3:24:35, 1.36s/it] 85%|████████▌ | 52869/61904 [4:25:02<3:22:20, 1.34s/it] 85%|████████▌ | 52870/61904 [4:25:04<3:21:18, 1.34s/it] 85%|████████▌ | 52871/61904 [4:25:05<3:31:23, 1.40s/it] 85%|████████▌ | 52872/61904 [4:25:07<3:36:31, 1.44s/it] 85%|████████▌ | 52873/61904 [4:25:08<3:37:42, 1.45s/it] 85%|████████▌ | 52874/61904 [4:25:10<3:38:52, 1.45s/it] 85%|████████▌ | 52875/61904 [4:25:11<3:41:25, 1.47s/it] 85%|████████▌ | 52876/61904 [4:25:13<3:40:49, 1.47s/it] 85%|████████▌ | 52877/61904 [4:25:14<3:36:12, 1.44s/it] 85%|████████▌ | 52878/61904 [4:25:16<3:33:25, 1.42s/it] 85%|████████▌ | 52879/61904 [4:25:17<3:32:19, 1.41s/it] 85%|████████▌ | 52880/61904 [4:25:18<3:31:02, 1.40s/it] {'loss': 2.5007, 'learning_rate': 1.1462465966549979e-07, 'epoch': 13.67} + 85%|████████▌ | 52880/61904 [4:25:18<3:31:02, 1.40s/it] 85%|████████▌ | 52881/61904 [4:25:20<3:36:09, 1.44s/it] 85%|████████▌ | 52882/61904 [4:25:21<3:38:32, 1.45s/it] 85%|████████▌ | 52883/61904 [4:25:23<3:37:15, 1.45s/it] 85%|████████▌ | 52884/61904 [4:25:24<3:27:40, 1.38s/it] 85%|████████▌ | 52885/61904 [4:25:25<3:20:24, 1.33s/it] 85%|████████▌ | 52886/61904 [4:25:27<3:19:35, 1.33s/it] 85%|████████▌ | 52887/61904 [4:25:28<3:15:34, 1.30s/it] 85%|████████▌ | 52888/61904 [4:25:29<3:15:48, 1.30s/it] 85%|████████▌ | 52889/61904 [4:25:30<3:20:51, 1.34s/it] 85%|████████▌ | 52890/61904 [4:25:32<3:25:02, 1.36s/it] 85%|████████▌ | 52891/61904 [4:25:33<3:25:21, 1.37s/it] 85%|████████▌ | 52892/61904 [4:25:35<3:25:57, 1.37s/it] 85%|████████▌ | 52893/61904 [4:25:36<3:26:47, 1.38s/it] 85%|████████▌ | 52894/61904 [4:25:38<3:32:21, 1.41s/it] 85%|████████▌ | 52895/61904 [4:25:39<3:24:30, 1.36s/it] 85%|████████▌ | 52896/61904 [4:25:40<3:34:25, 1.43s/it] 85%|██████���█▌ | 52897/61904 [4:25:42<3:30:10, 1.40s/it] 85%|████████▌ | 52898/61904 [4:25:43<3:25:37, 1.37s/it] 85%|████████▌ | 52899/61904 [4:25:45<3:33:08, 1.42s/it] 85%|████████▌ | 52900/61904 [4:25:46<3:37:26, 1.45s/it] {'loss': 2.4834, 'learning_rate': 1.1459224685595745e-07, 'epoch': 13.67} + 85%|████████▌ | 52900/61904 [4:25:46<3:37:26, 1.45s/it] 85%|████████▌ | 52901/61904 [4:25:47<3:28:42, 1.39s/it] 85%|████████▌ | 52902/61904 [4:25:49<3:27:49, 1.39s/it] 85%|████████▌ | 52903/61904 [4:25:50<3:26:22, 1.38s/it] 85%|████████▌ | 52904/61904 [4:25:51<3:23:06, 1.35s/it] 85%|████████▌ | 52905/61904 [4:25:53<3:19:55, 1.33s/it] 85%|████████▌ | 52906/61904 [4:25:54<3:25:34, 1.37s/it] 85%|████████▌ | 52907/61904 [4:25:55<3:26:12, 1.38s/it] 85%|████████▌ | 52908/61904 [4:25:57<3:22:43, 1.35s/it] 85%|████████▌ | 52909/61904 [4:25:58<3:24:46, 1.37s/it] 85%|████████▌ | 52910/61904 [4:26:00<3:30:11, 1.40s/it] 85%|████████▌ | 52911/61904 [4:26:01<3:29:12, 1.40s/it] 85%|████████▌ | 52912/61904 [4:26:03<3:36:02, 1.44s/it] 85%|████████▌ | 52913/61904 [4:26:04<3:40:08, 1.47s/it] 85%|████████▌ | 52914/61904 [4:26:06<3:44:01, 1.50s/it] 85%|████████▌ | 52915/61904 [4:26:07<3:44:53, 1.50s/it] 85%|████████▌ | 52916/61904 [4:26:09<3:36:53, 1.45s/it] 85%|████████▌ | 52917/61904 [4:26:10<3:30:55, 1.41s/it] 85%|████████▌ | 52918/61904 [4:26:11<3:31:40, 1.41s/it] 85%|████████▌ | 52919/61904 [4:26:13<3:35:36, 1.44s/it] 85%|████████▌ | 52920/61904 [4:26:14<3:29:42, 1.40s/it] {'loss': 2.3963, 'learning_rate': 1.1455983404641514e-07, 'epoch': 13.68} + 85%|████████▌ | 52920/61904 [4:26:14<3:29:42, 1.40s/it] 85%|████████▌ | 52921/61904 [4:26:15<3:25:14, 1.37s/it] 85%|████████▌ | 52922/61904 [4:26:17<3:25:59, 1.38s/it] 85%|████████▌ | 52923/61904 [4:26:18<3:21:52, 1.35s/it] 85%|████████▌ | 52924/61904 [4:26:19<3:20:03, 1.34s/it] 85%|████████▌ | 52925/61904 [4:26:21<3:19:36, 1.33s/it] 85%|████████▌ | 52926/61904 [4:26:22<3:20:02, 1.34s/it] 85%|████████▌ | 52927/61904 [4:26:23<3:18:36, 1.33s/it] 86%|████████▌ | 52928/61904 [4:26:25<3:18:50, 1.33s/it] 86%|████████▌ | 52929/61904 [4:26:26<3:23:03, 1.36s/it] 86%|████████▌ | 52930/61904 [4:26:27<3:21:17, 1.35s/it] 86%|████████▌ | 52931/61904 [4:26:29<3:19:48, 1.34s/it] 86%|████████▌ | 52932/61904 [4:26:30<3:23:40, 1.36s/it] 86%|████████▌ | 52933/61904 [4:26:32<3:28:27, 1.39s/it] 86%|████████▌ | 52934/61904 [4:26:33<3:30:18, 1.41s/it] 86%|████████▌ | 52935/61904 [4:26:34<3:31:27, 1.41s/it] 86%|████████▌ | 52936/61904 [4:26:36<3:25:42, 1.38s/it] 86%|████████▌ | 52937/61904 [4:26:37<3:24:55, 1.37s/it] 86%|████████▌ | 52938/61904 [4:26:38<3:25:08, 1.37s/it] 86%|████████▌ | 52939/61904 [4:26:40<3:25:08, 1.37s/it] 86%|████████▌ | 52940/61904 [4:26:41<3:21:22, 1.35s/it] {'loss': 2.4304, 'learning_rate': 1.1452742123687283e-07, 'epoch': 13.68} + 86%|████████▌ | 52940/61904 [4:26:41<3:21:22, 1.35s/it] 86%|████████▌ | 52941/61904 [4:26:43<3:30:28, 1.41s/it] 86%|████████▌ | 52942/61904 [4:26:44<3:26:52, 1.39s/it] 86%|████████▌ | 52943/61904 [4:26:45<3:26:47, 1.38s/it] 86%|████████▌ | 52944/61904 [4:26:47<3:23:45, 1.36s/it] 86%|████████▌ | 52945/61904 [4:26:48<3:22:21, 1.36s/it] 86%|████████▌ | 52946/61904 [4:26:50<3:29:49, 1.41s/it] 86%|████████▌ | 52947/61904 [4:26:51<3:26:47, 1.39s/it] 86%|████████▌ | 52948/61904 [4:26:52<3:26:26, 1.38s/it] 86%|████████▌ | 52949/61904 [4:26:54<3:24:48, 1.37s/it] 86%|████████▌ | 52950/61904 [4:26:55<3:20:42, 1.34s/it] 86%|████████▌ | 52951/61904 [4:26:56<3:24:28, 1.37s/it] 86%|████████▌ | 52952/61904 [4:26:58<3:30:22, 1.41s/it] 86%|████████▌ | 52953/61904 [4:26:59<3:31:07, 1.42s/it] 86%|████████▌ | 52954/61904 [4:27:01<3:24:24, 1.37s/it] 86%|████████▌ | 52955/61904 [4:27:02<3:21:34, 1.35s/it] 86%|████████��� | 52956/61904 [4:27:03<3:20:56, 1.35s/it] 86%|████████▌ | 52957/61904 [4:27:05<3:30:52, 1.41s/it] 86%|████████▌ | 52958/61904 [4:27:06<3:35:00, 1.44s/it] 86%|████████▌ | 52959/61904 [4:27:08<3:33:04, 1.43s/it] 86%|████████▌ | 52960/61904 [4:27:09<3:24:43, 1.37s/it] {'loss': 2.4219, 'learning_rate': 1.1449500842733046e-07, 'epoch': 13.69} + 86%|████████▌ | 52960/61904 [4:27:09<3:24:43, 1.37s/it] 86%|████████▌ | 52961/61904 [4:27:10<3:23:19, 1.36s/it] 86%|████████▌ | 52962/61904 [4:27:12<3:19:27, 1.34s/it] 86%|████████▌ | 52963/61904 [4:27:13<3:17:44, 1.33s/it] 86%|████████▌ | 52964/61904 [4:27:14<3:17:26, 1.33s/it] 86%|████████▌ | 52965/61904 [4:27:16<3:19:54, 1.34s/it] 86%|████████▌ | 52966/61904 [4:27:17<3:24:38, 1.37s/it] 86%|████████▌ | 52967/61904 [4:27:18<3:20:23, 1.35s/it] 86%|████████▌ | 52968/61904 [4:27:20<3:22:38, 1.36s/it] 86%|████████▌ | 52969/61904 [4:27:21<3:21:14, 1.35s/it] 86%|████████▌ | 52970/61904 [4:27:22<3:24:50, 1.38s/it] 86%|████████▌ | 52971/61904 [4:27:24<3:21:51, 1.36s/it] 86%|████████▌ | 52972/61904 [4:27:25<3:19:31, 1.34s/it] 86%|████████▌ | 52973/61904 [4:27:26<3:23:15, 1.37s/it] 86%|████████▌ | 52974/61904 [4:27:28<3:28:46, 1.40s/it] 86%|████████▌ | 52975/61904 [4:27:30<3:35:49, 1.45s/it] 86%|████████▌ | 52976/61904 [4:27:31<3:41:29, 1.49s/it] 86%|████████▌ | 52977/61904 [4:27:32<3:34:21, 1.44s/it] 86%|████████▌ | 52978/61904 [4:27:34<3:30:06, 1.41s/it] 86%|████████▌ | 52979/61904 [4:27:35<3:26:00, 1.38s/it] 86%|████████▌ | 52980/61904 [4:27:36<3:22:27, 1.36s/it] {'loss': 2.5008, 'learning_rate': 1.1446259561778815e-07, 'epoch': 13.69} + 86%|████████▌ | 52980/61904 [4:27:36<3:22:27, 1.36s/it] 86%|████████▌ | 52981/61904 [4:27:38<3:22:12, 1.36s/it] 86%|████████▌ | 52982/61904 [4:27:39<3:19:44, 1.34s/it] 86%|████████▌ | 52983/61904 [4:27:40<3:22:38, 1.36s/it] 86%|████████▌ | 52984/61904 [4:27:42<3:20:14, 1.35s/it] 86%|████████▌ | 52985/61904 [4:27:43<3:19:19, 1.34s/it] 86%|████████▌ | 52986/61904 [4:27:45<3:26:05, 1.39s/it] 86%|████████▌ | 52987/61904 [4:27:46<3:27:00, 1.39s/it] 86%|████████▌ | 52988/61904 [4:27:47<3:25:14, 1.38s/it] 86%|████████▌ | 52989/61904 [4:27:49<3:23:47, 1.37s/it] 86%|████████▌ | 52990/61904 [4:27:50<3:23:38, 1.37s/it] 86%|████████▌ | 52991/61904 [4:27:51<3:21:25, 1.36s/it] 86%|████████▌ | 52992/61904 [4:27:53<3:19:37, 1.34s/it] 86%|████████▌ | 52993/61904 [4:27:54<3:24:05, 1.37s/it] 86%|████████▌ | 52994/61904 [4:27:56<3:27:37, 1.40s/it] 86%|████████▌ | 52995/61904 [4:27:57<3:27:01, 1.39s/it] 86%|████████▌ | 52996/61904 [4:27:58<3:28:26, 1.40s/it] 86%|████████▌ | 52997/61904 [4:28:00<3:24:35, 1.38s/it] 86%|████████▌ | 52998/61904 [4:28:01<3:23:35, 1.37s/it] 86%|████████▌ | 52999/61904 [4:28:02<3:20:57, 1.35s/it] 86%|████████▌ | 53000/61904 [4:28:04<3:26:16, 1.39s/it] {'loss': 2.4243, 'learning_rate': 1.1443018280824581e-07, 'epoch': 13.7} + 86%|████████▌ | 53000/61904 [4:28:04<3:26:16, 1.39s/it] 86%|████████▌ | 53001/61904 [4:28:05<3:27:01, 1.40s/it] 86%|████████▌ | 53002/61904 [4:28:07<3:25:05, 1.38s/it] 86%|████████▌ | 53003/61904 [4:28:08<3:23:25, 1.37s/it] 86%|████████▌ | 53004/61904 [4:28:09<3:27:51, 1.40s/it] 86%|████████▌ | 53005/61904 [4:28:11<3:31:48, 1.43s/it] 86%|████████▌ | 53006/61904 [4:28:12<3:25:50, 1.39s/it] 86%|████████▌ | 53007/61904 [4:28:14<3:23:20, 1.37s/it] 86%|████████▌ | 53008/61904 [4:28:15<3:29:36, 1.41s/it] 86%|████████▌ | 53009/61904 [4:28:16<3:27:54, 1.40s/it] 86%|████████▌ | 53010/61904 [4:28:18<3:23:02, 1.37s/it] 86%|████████▌ | 53011/61904 [4:28:19<3:32:10, 1.43s/it] 86%|████████▌ | 53012/61904 [4:28:21<3:33:43, 1.44s/it] 86%|████████▌ | 53013/61904 [4:28:22<3:30:07, 1.42s/it] 86%|████████▌ | 53014/61904 [4:28:24<3:27:11, 1.40s/it] 86%|████████▌ | 53015/61904 [4:28:25<3:27:09, 1.40s/it] 86%|████████▌ | 53016/61904 [4:28:26<3:23:09, 1.37s/it] 86%|████████▌ | 53017/61904 [4:28:28<3:23:46, 1.38s/it] 86%|████████▌ | 53018/61904 [4:28:29<3:28:01, 1.40s/it] 86%|████████▌ | 53019/61904 [4:28:30<3:26:46, 1.40s/it] 86%|████████▌ | 53020/61904 [4:28:32<3:23:01, 1.37s/it] {'loss': 2.462, 'learning_rate': 1.143977699987035e-07, 'epoch': 13.7} + 86%|████████▌ | 53020/61904 [4:28:32<3:23:01, 1.37s/it] 86%|████████▌ | 53021/61904 [4:28:33<3:21:29, 1.36s/it] 86%|████████▌ | 53022/61904 [4:28:35<3:26:14, 1.39s/it] 86%|████████▌ | 53023/61904 [4:28:36<3:27:39, 1.40s/it] 86%|████████▌ | 53024/61904 [4:28:37<3:28:42, 1.41s/it] 86%|████████▌ | 53025/61904 [4:28:39<3:26:08, 1.39s/it] 86%|████████▌ | 53026/61904 [4:28:40<3:29:19, 1.41s/it] 86%|████████▌ | 53027/61904 [4:28:42<3:22:44, 1.37s/it] 86%|████████▌ | 53028/61904 [4:28:43<3:22:48, 1.37s/it] 86%|████████▌ | 53029/61904 [4:28:44<3:31:02, 1.43s/it] 86%|████████▌ | 53030/61904 [4:28:46<3:29:40, 1.42s/it] 86%|████████▌ | 53031/61904 [4:28:47<3:24:30, 1.38s/it] 86%|████████▌ | 53032/61904 [4:28:48<3:22:58, 1.37s/it] 86%|████████▌ | 53033/61904 [4:28:50<3:28:04, 1.41s/it] 86%|████████▌ | 53034/61904 [4:28:51<3:22:26, 1.37s/it] 86%|████████▌ | 53035/61904 [4:28:53<3:28:31, 1.41s/it] 86%|████████▌ | 53036/61904 [4:28:54<3:27:19, 1.40s/it] 86%|████████▌ | 53037/61904 [4:28:56<3:25:15, 1.39s/it] 86%|████████▌ | 53038/61904 [4:28:57<3:22:15, 1.37s/it] 86%|████████▌ | 53039/61904 [4:28:58<3:31:37, 1.43s/it] 86%|████████▌ | 53040/61904 [4:29:00<3:24:10, 1.38s/it] {'loss': 2.4512, 'learning_rate': 1.1436535718916113e-07, 'epoch': 13.71} + 86%|████████▌ | 53040/61904 [4:29:00<3:24:10, 1.38s/it] 86%|████████▌ | 53041/61904 [4:29:01<3:19:41, 1.35s/it] 86%|████████▌ | 53042/61904 [4:29:03<3:37:48, 1.47s/it] 86%|████████▌ | 53043/61904 [4:29:04<3:31:18, 1.43s/it] 86%|████████▌ | 53044/61904 [4:29:05<3:28:50, 1.41s/it] 86%|████████▌ | 53045/61904 [4:29:07<3:30:36, 1.43s/it] 86%|████████▌ | 53046/61904 [4:29:08<3:21:29, 1.36s/it] 86%|████████▌ | 53047/61904 [4:29:09<3:20:09, 1.36s/it] 86%|████████▌ | 53048/61904 [4:29:11<3:23:38, 1.38s/it] 86%|████████▌ | 53049/61904 [4:29:12<3:32:45, 1.44s/it] 86%|████████▌ | 53050/61904 [4:29:14<3:30:09, 1.42s/it] 86%|████████▌ | 53051/61904 [4:29:15<3:25:57, 1.40s/it] 86%|████████▌ | 53052/61904 [4:29:16<3:20:26, 1.36s/it] 86%|████████▌ | 53053/61904 [4:29:18<3:31:16, 1.43s/it] 86%|████████▌ | 53054/61904 [4:29:20<3:38:08, 1.48s/it] 86%|████████▌ | 53055/61904 [4:29:21<3:36:57, 1.47s/it] 86%|████████▌ | 53056/61904 [4:29:23<3:35:41, 1.46s/it] 86%|████████▌ | 53057/61904 [4:29:24<3:44:54, 1.53s/it] 86%|████████▌ | 53058/61904 [4:29:26<3:40:20, 1.49s/it] 86%|████████▌ | 53059/61904 [4:29:27<3:37:19, 1.47s/it] 86%|████████▌ | 53060/61904 [4:29:29<3:36:34, 1.47s/it] {'loss': 2.508, 'learning_rate': 1.1433294437961882e-07, 'epoch': 13.71} + 86%|████████▌ | 53060/61904 [4:29:29<3:36:34, 1.47s/it] 86%|████████▌ | 53061/61904 [4:29:30<3:35:55, 1.47s/it] 86%|████████▌ | 53062/61904 [4:29:31<3:35:02, 1.46s/it] 86%|████████▌ | 53063/61904 [4:29:33<3:30:53, 1.43s/it] 86%|████████▌ | 53064/61904 [4:29:34<3:29:07, 1.42s/it] 86%|████████▌ | 53065/61904 [4:29:36<3:28:56, 1.42s/it] 86%|████████▌ | 53066/61904 [4:29:37<3:32:00, 1.44s/it] 86%|████████▌ | 53067/61904 [4:29:38<3:28:14, 1.41s/it] 86%|████████▌ | 53068/61904 [4:29:40<3:25:45, 1.40s/it] 86%|████████▌ | 53069/61904 [4:29:41<3:28:14, 1.41s/it] 86%|████████▌ | 53070/61904 [4:29:43<3:23:53, 1.38s/it] 86%|████████▌ | 53071/61904 [4:29:44<3:22:19, 1.37s/it] 86%|████████▌ | 53072/61904 [4:29:45<3:20:59, 1.37s/it] 86%|████████▌ | 53073/61904 [4:29:47<3:25:26, 1.40s/it] 86%|████████▌ | 53074/61904 [4:29:48<3:25:52, 1.40s/it] 86%|████████▌ | 53075/61904 [4:29:50<3:29:37, 1.42s/it] 86%|████████▌ | 53076/61904 [4:29:51<3:21:15, 1.37s/it] 86%|████████▌ | 53077/61904 [4:29:52<3:18:41, 1.35s/it] 86%|████████▌ | 53078/61904 [4:29:53<3:17:33, 1.34s/it] 86%|████████▌ | 53079/61904 [4:29:55<3:27:43, 1.41s/it] 86%|████████▌ | 53080/61904 [4:29:56<3:28:05, 1.41s/it] {'loss': 2.4558, 'learning_rate': 1.1430053157007649e-07, 'epoch': 13.72} + 86%|████████▌ | 53080/61904 [4:29:56<3:28:05, 1.41s/it] 86%|████████▌ | 53081/61904 [4:29:58<3:21:39, 1.37s/it] 86%|████████▌ | 53082/61904 [4:29:59<3:19:33, 1.36s/it] 86%|████████▌ | 53083/61904 [4:30:00<3:14:51, 1.33s/it] 86%|████████▌ | 53084/61904 [4:30:02<3:12:00, 1.31s/it] 86%|████████▌ | 53085/61904 [4:30:03<3:17:50, 1.35s/it] 86%|████████▌ | 53086/61904 [4:30:04<3:17:13, 1.34s/it] 86%|████████▌ | 53087/61904 [4:30:06<3:14:44, 1.33s/it] 86%|████████▌ | 53088/61904 [4:30:07<3:20:36, 1.37s/it] 86%|████████▌ | 53089/61904 [4:30:08<3:15:58, 1.33s/it] 86%|████████▌ | 53090/61904 [4:30:10<3:14:55, 1.33s/it] 86%|████████▌ | 53091/61904 [4:30:11<3:11:53, 1.31s/it] 86%|████████▌ | 53092/61904 [4:30:12<3:16:09, 1.34s/it] 86%|████████▌ | 53093/61904 [4:30:14<3:17:14, 1.34s/it] 86%|████████▌ | 53094/61904 [4:30:15<3:21:34, 1.37s/it] 86%|████████▌ | 53095/61904 [4:30:17<3:27:48, 1.42s/it] 86%|████████▌ | 53096/61904 [4:30:18<3:20:38, 1.37s/it] 86%|████████▌ | 53097/61904 [4:30:19<3:20:52, 1.37s/it] 86%|████████▌ | 53098/61904 [4:30:21<3:23:24, 1.39s/it] 86%|████████▌ | 53099/61904 [4:30:22<3:22:05, 1.38s/it] 86%|████████▌ | 53100/61904 [4:30:23<3:22:02, 1.38s/it] {'loss': 2.4658, 'learning_rate': 1.1426811876053417e-07, 'epoch': 13.72} + 86%|████████▌ | 53100/61904 [4:30:23<3:22:02, 1.38s/it] 86%|████████▌ | 53101/61904 [4:30:25<3:18:57, 1.36s/it] 86%|████████▌ | 53102/61904 [4:30:26<3:13:36, 1.32s/it] 86%|████████▌ | 53103/61904 [4:30:27<3:18:31, 1.35s/it] 86%|████████▌ | 53104/61904 [4:30:29<3:17:16, 1.35s/it] 86%|████████▌ | 53105/61904 [4:30:30<3:22:47, 1.38s/it] 86%|████████▌ | 53106/61904 [4:30:32<3:23:55, 1.39s/it] 86%|████████▌ | 53107/61904 [4:30:33<3:21:51, 1.38s/it] 86%|████████▌ | 53108/61904 [4:30:34<3:27:30, 1.42s/it] 86%|████████▌ | 53109/61904 [4:30:36<3:24:44, 1.40s/it] 86%|████████▌ | 53110/61904 [4:30:37<3:20:11, 1.37s/it] 86%|████████▌ | 53111/61904 [4:30:39<3:27:54, 1.42s/it] 86%|████████▌ | 53112/61904 [4:30:40<3:23:05, 1.39s/it] 86%|████████▌ | 53113/61904 [4:30:41<3:22:26, 1.38s/it] 86%|████████▌ | 53114/61904 [4:30:43<3:21:47, 1.38s/it] 86%|████████▌ | 53115/61904 [4:30:44<3:18:05, 1.35s/it] 86%|████████▌ | 53116/61904 [4:30:45<3:14:55, 1.33s/it] 86%|████████▌ | 53117/61904 [4:30:47<3:19:54, 1.37s/it] 86%|████████▌ | 53118/61904 [4:30:48<3:22:33, 1.38s/it] 86%|████████▌ | 53119/61904 [4:30:50<3:22:42, 1.38s/it] 86%|████████▌ | 53120/61904 [4:30:51<3:20:22, 1.37s/it] {'loss': 2.3885, 'learning_rate': 1.1423570595099181e-07, 'epoch': 13.73} + 86%|████████▌ | 53120/61904 [4:30:51<3:20:22, 1.37s/it] 86%|████████▌ | 53121/61904 [4:30:52<3:21:59, 1.38s/it] 86%|████████▌ | 53122/61904 [4:30:54<3:19:44, 1.36s/it] 86%|████████▌ | 53123/61904 [4:30:55<3:21:35, 1.38s/it] 86%|████████▌ | 53124/61904 [4:30:56<3:20:01, 1.37s/it] 86%|████████▌ | 53125/61904 [4:30:58<3:24:14, 1.40s/it] 86%|████████▌ | 53126/61904 [4:30:59<3:26:22, 1.41s/it] 86%|████████▌ | 53127/61904 [4:31:01<3:22:05, 1.38s/it] 86%|████████▌ | 53128/61904 [4:31:02<3:19:00, 1.36s/it] 86%|████████▌ | 53129/61904 [4:31:03<3:20:30, 1.37s/it] 86%|████████▌ | 53130/61904 [4:31:04<3:13:27, 1.32s/it] 86%|████████▌ | 53131/61904 [4:31:06<3:17:29, 1.35s/it] 86%|████████▌ | 53132/61904 [4:31:07<3:20:44, 1.37s/it] 86%|████████▌ | 53133/61904 [4:31:09<3:17:11, 1.35s/it] 86%|████████▌ | 53134/61904 [4:31:10<3:25:21, 1.40s/it] 86%|████████▌ | 53135/61904 [4:31:11<3:22:03, 1.38s/it] 86%|████████▌ | 53136/61904 [4:31:13<3:25:28, 1.41s/it] 86%|████████▌ | 53137/61904 [4:31:14<3:19:59, 1.37s/it] 86%|████████▌ | 53138/61904 [4:31:16<3:22:53, 1.39s/it] 86%|████████▌ | 53139/61904 [4:31:17<3:11:51, 1.31s/it] 86%|████████▌ | 53140/61904 [4:31:18<3:18:12, 1.36s/it] {'loss': 2.44, 'learning_rate': 1.142032931414495e-07, 'epoch': 13.73} + 86%|████████▌ | 53140/61904 [4:31:18<3:18:12, 1.36s/it] 86%|████████▌ | 53141/61904 [4:31:19<3:12:20, 1.32s/it] 86%|████████▌ | 53142/61904 [4:31:21<3:09:55, 1.30s/it] 86%|████████▌ | 53143/61904 [4:31:22<3:11:04, 1.31s/it] 86%|████████▌ | 53144/61904 [4:31:24<3:18:16, 1.36s/it] 86%|████████▌ | 53145/61904 [4:31:25<3:19:46, 1.37s/it] 86%|████████▌ | 53146/61904 [4:31:26<3:19:41, 1.37s/it] 86%|████████▌ | 53147/61904 [4:31:28<3:22:10, 1.39s/it] 86%|████████▌ | 53148/61904 [4:31:29<3:16:42, 1.35s/it] 86%|████████▌ | 53149/61904 [4:31:30<3:14:25, 1.33s/it] 86%|████████▌ | 53150/61904 [4:31:32<3:18:52, 1.36s/it] 86%|████████▌ | 53151/61904 [4:31:33<3:20:19, 1.37s/it] 86%|████████▌ | 53152/61904 [4:31:34<3:19:02, 1.36s/it] 86%|████████▌ | 53153/61904 [4:31:36<3:13:34, 1.33s/it] 86%|████████▌ | 53154/61904 [4:31:37<3:18:47, 1.36s/it] 86%|████████▌ | 53155/61904 [4:31:39<3:18:49, 1.36s/it] 86%|████████▌ | 53156/61904 [4:31:40<3:18:57, 1.36s/it] 86%|████████▌ | 53157/61904 [4:31:41<3:21:50, 1.38s/it] 86%|████████▌ | 53158/61904 [4:31:43<3:22:12, 1.39s/it] 86%|████████▌ | 53159/61904 [4:31:44<3:19:22, 1.37s/it] 86%|████████▌ | 53160/61904 [4:31:45<3:19:48, 1.37s/it] {'loss': 2.4517, 'learning_rate': 1.1417088033190716e-07, 'epoch': 13.74} + 86%|████████▌ | 53160/61904 [4:31:45<3:19:48, 1.37s/it] 86%|████████▌ | 53161/61904 [4:31:47<3:16:23, 1.35s/it] 86%|████████▌ | 53162/61904 [4:31:48<3:21:04, 1.38s/it] 86%|████████▌ | 53163/61904 [4:31:50<3:27:21, 1.42s/it] 86%|████████▌ | 53164/61904 [4:31:51<3:20:46, 1.38s/it] 86%|████████▌ | 53165/61904 [4:31:52<3:22:19, 1.39s/it] 86%|████████▌ | 53166/61904 [4:31:54<3:23:20, 1.40s/it] 86%|████████▌ | 53167/61904 [4:31:55<3:25:19, 1.41s/it] 86%|████████▌ | 53168/61904 [4:31:57<3:19:40, 1.37s/it] 86%|████████▌ | 53169/61904 [4:31:58<3:18:25, 1.36s/it] 86%|████████▌ | 53170/61904 [4:31:59<3:15:18, 1.34s/it] 86%|████████▌ | 53171/61904 [4:32:01<3:17:15, 1.36s/it] 86%|████████▌ | 53172/61904 [4:32:02<3:15:34, 1.34s/it] 86%|████████▌ | 53173/61904 [4:32:03<3:16:55, 1.35s/it] 86%|████████▌ | 53174/61904 [4:32:05<3:15:41, 1.34s/it] 86%|████████▌ | 53175/61904 [4:32:06<3:18:09, 1.36s/it] 86%|████████▌ | 53176/61904 [4:32:07<3:22:26, 1.39s/it] 86%|████████▌ | 53177/61904 [4:32:09<3:25:35, 1.41s/it] 86%|████████▌ | 53178/61904 [4:32:10<3:28:36, 1.43s/it] 86%|████████▌ | 53179/61904 [4:32:12<3:32:39, 1.46s/it] 86%|████████▌ | 53180/61904 [4:32:13<3:23:50, 1.40s/it] {'loss': 2.4766, 'learning_rate': 1.1413846752236485e-07, 'epoch': 13.74} + 86%|████████▌ | 53180/61904 [4:32:13<3:23:50, 1.40s/it] 86%|████████▌ | 53181/61904 [4:32:14<3:17:27, 1.36s/it] 86%|████████▌ | 53182/61904 [4:32:16<3:19:36, 1.37s/it] 86%|████████▌ | 53183/61904 [4:32:17<3:18:36, 1.37s/it] 86%|████████▌ | 53184/61904 [4:32:19<3:23:49, 1.40s/it] 86%|████████▌ | 53185/61904 [4:32:20<3:22:24, 1.39s/it] 86%|████████▌ | 53186/61904 [4:32:21<3:22:05, 1.39s/it] 86%|████████▌ | 53187/61904 [4:32:23<3:20:56, 1.38s/it] 86%|████████▌ | 53188/61904 [4:32:24<3:16:36, 1.35s/it] 86%|████████▌ | 53189/61904 [4:32:25<3:13:22, 1.33s/it] 86%|████████▌ | 53190/61904 [4:32:27<3:11:34, 1.32s/it] 86%|████████▌ | 53191/61904 [4:32:28<3:20:30, 1.38s/it] 86%|████████▌ | 53192/61904 [4:32:30<3:26:52, 1.42s/it] 86%|████████▌ | 53193/61904 [4:32:31<3:23:04, 1.40s/it] 86%|████████▌ | 53194/61904 [4:32:32<3:21:17, 1.39s/it] 86%|████████▌ | 53195/61904 [4:32:34<3:19:16, 1.37s/it] 86%|████████▌ | 53196/61904 [4:32:35<3:23:40, 1.40s/it] 86%|████████▌ | 53197/61904 [4:32:37<3:22:04, 1.39s/it] 86%|████████▌ | 53198/61904 [4:32:38<3:19:28, 1.37s/it] 86%|████████▌ | 53199/61904 [4:32:39<3:22:10, 1.39s/it] 86%|████████▌ | 53200/61904 [4:32:41<3:12:57, 1.33s/it] {'loss': 2.447, 'learning_rate': 1.1410605471282248e-07, 'epoch': 13.75} + 86%|████████▌ | 53200/61904 [4:32:41<3:12:57, 1.33s/it] 86%|████████▌ | 53201/61904 [4:32:42<3:08:43, 1.30s/it] 86%|████████▌ | 53202/61904 [4:32:43<3:06:42, 1.29s/it] 86%|████████▌ | 53203/61904 [4:32:44<3:07:18, 1.29s/it] 86%|████████▌ | 53204/61904 [4:32:46<3:08:39, 1.30s/it] 86%|████████▌ | 53205/61904 [4:32:47<3:13:17, 1.33s/it] 86%|████████▌ | 53206/61904 [4:32:48<3:14:56, 1.34s/it] 86%|████████▌ | 53207/61904 [4:32:50<3:18:11, 1.37s/it] 86%|████████▌ | 53208/61904 [4:32:51<3:13:25, 1.33s/it] 86%|████████▌ | 53209/61904 [4:32:53<3:20:34, 1.38s/it] 86%|████████▌ | 53210/61904 [4:32:54<3:21:48, 1.39s/it] 86%|████████▌ | 53211/61904 [4:32:55<3:19:49, 1.38s/it] 86%|████████▌ | 53212/61904 [4:32:57<3:22:51, 1.40s/it] 86%|████████▌ | 53213/61904 [4:32:58<3:23:17, 1.40s/it] 86%|████████▌ | 53214/61904 [4:33:00<3:22:19, 1.40s/it] 86%|████████▌ | 53215/61904 [4:33:01<3:15:54, 1.35s/it] 86%|████████▌ | 53216/61904 [4:33:02<3:18:26, 1.37s/it] 86%|████████▌ | 53217/61904 [4:33:04<3:15:09, 1.35s/it] 86%|████████▌ | 53218/61904 [4:33:05<3:14:01, 1.34s/it] 86%|████████▌ | 53219/61904 [4:33:06<3:13:32, 1.34s/it] 86%|████████▌ | 53220/61904 [4:33:08<3:28:01, 1.44s/it] {'loss': 2.4432, 'learning_rate': 1.1407364190328017e-07, 'epoch': 13.76} + 86%|████████▌ | 53220/61904 [4:33:08<3:28:01, 1.44s/it] 86%|████████▌ | 53221/61904 [4:33:09<3:23:01, 1.40s/it] 86%|████████▌ | 53222/61904 [4:33:11<3:23:37, 1.41s/it] 86%|████████▌ | 53223/61904 [4:33:12<3:20:46, 1.39s/it] 86%|████████▌ | 53224/61904 [4:33:13<3:27:14, 1.43s/it] 86%|████████▌ | 53225/61904 [4:33:15<3:24:35, 1.41s/it] 86%|████████▌ | 53226/61904 [4:33:16<3:27:52, 1.44s/it] 86%|████████▌ | 53227/61904 [4:33:18<3:19:20, 1.38s/it] 86%|████████▌ | 53228/61904 [4:33:19<3:12:25, 1.33s/it] 86%|████████▌ | 53229/61904 [4:33:20<3:16:59, 1.36s/it] 86%|████████▌ | 53230/61904 [4:33:21<3:11:15, 1.32s/it] 86%|████████▌ | 53231/61904 [4:33:23<3:15:54, 1.36s/it] 86%|████████▌ | 53232/61904 [4:33:24<3:14:30, 1.35s/it] 86%|████████▌ | 53233/61904 [4:33:26<3:15:52, 1.36s/it] 86%|████████▌ | 53234/61904 [4:33:27<3:15:01, 1.35s/it] 86%|████████▌ | 53235/61904 [4:33:28<3:12:46, 1.33s/it] 86%|████████▌ | 53236/61904 [4:33:30<3:09:27, 1.31s/it] 86%|████████▌ | 53237/61904 [4:33:31<3:12:23, 1.33s/it] 86%|████████▌ | 53238/61904 [4:33:32<3:14:41, 1.35s/it] 86%|████████▌ | 53239/61904 [4:33:34<3:11:33, 1.33s/it] 86%|████████▌ | 53240/61904 [4:33:35<3:19:12, 1.38s/it] {'loss': 2.4773, 'learning_rate': 1.1404122909373786e-07, 'epoch': 13.76} + 86%|████████▌ | 53240/61904 [4:33:35<3:19:12, 1.38s/it] 86%|████████▌ | 53241/61904 [4:33:37<3:36:28, 1.50s/it] 86%|████████▌ | 53242/61904 [4:33:38<3:33:03, 1.48s/it] 86%|████████▌ | 53243/61904 [4:33:40<3:30:27, 1.46s/it] 86%|████████▌ | 53244/61904 [4:33:41<3:27:22, 1.44s/it] 86%|████████▌ | 53245/61904 [4:33:43<3:29:46, 1.45s/it] 86%|████████▌ | 53246/61904 [4:33:44<3:30:13, 1.46s/it] 86%|████████▌ | 53247/61904 [4:33:45<3:24:38, 1.42s/it] 86%|████████▌ | 53248/61904 [4:33:47<3:34:02, 1.48s/it] 86%|████████▌ | 53249/61904 [4:33:48<3:23:08, 1.41s/it] 86%|████████▌ | 53250/61904 [4:33:50<3:19:07, 1.38s/it] 86%|████████▌ | 53251/61904 [4:33:51<3:20:14, 1.39s/it] 86%|████████▌ | 53252/61904 [4:33:53<3:29:19, 1.45s/it] 86%|████████▌ | 53253/61904 [4:33:54<3:25:09, 1.42s/it] 86%|████████▌ | 53254/61904 [4:33:55<3:22:27, 1.40s/it] 86%|████████▌ | 53255/61904 [4:33:57<3:26:15, 1.43s/it] 86%|████████▌ | 53256/61904 [4:33:58<3:21:35, 1.40s/it] 86%|████████▌ | 53257/61904 [4:33:59<3:15:26, 1.36s/it] 86%|████████▌ | 53258/61904 [4:34:01<3:10:48, 1.32s/it] 86%|████████▌ | 53259/61904 [4:34:02<3:14:36, 1.35s/it] 86%|████████▌ | 53260/61904 [4:34:03<3:18:56, 1.38s/it] {'loss': 2.455, 'learning_rate': 1.140088162841955e-07, 'epoch': 13.77} + 86%|████████▌ | 53260/61904 [4:34:03<3:18:56, 1.38s/it] 86%|████████▌ | 53261/61904 [4:34:05<3:21:31, 1.40s/it] 86%|████████▌ | 53262/61904 [4:34:06<3:13:23, 1.34s/it] 86%|████████▌ | 53263/61904 [4:34:07<3:12:45, 1.34s/it] 86%|████████▌ | 53264/61904 [4:34:09<3:14:01, 1.35s/it] 86%|████████▌ | 53265/61904 [4:34:10<3:15:48, 1.36s/it] 86%|████████▌ | 53266/61904 [4:34:12<3:17:01, 1.37s/it] 86%|████████▌ | 53267/61904 [4:34:13<3:17:58, 1.38s/it] 86%|████████▌ | 53268/61904 [4:34:14<3:13:33, 1.34s/it] 86%|████████▌ | 53269/61904 [4:34:16<3:20:52, 1.40s/it] 86%|████████▌ | 53270/61904 [4:34:17<3:21:58, 1.40s/it] 86%|████████▌ | 53271/61904 [4:34:18<3:15:51, 1.36s/it] 86%|████████▌ | 53272/61904 [4:34:20<3:18:12, 1.38s/it] 86%|████████▌ | 53273/61904 [4:34:21<3:16:09, 1.36s/it] 86%|████████▌ | 53274/61904 [4:34:23<3:18:28, 1.38s/it] 86%|████████▌ | 53275/61904 [4:34:24<3:17:08, 1.37s/it] 86%|████████▌ | 53276/61904 [4:34:25<3:16:43, 1.37s/it] 86%|████████▌ | 53277/61904 [4:34:27<3:16:17, 1.37s/it] 86%|████████▌ | 53278/61904 [4:34:28<3:19:26, 1.39s/it] 86%|████████▌ | 53279/61904 [4:34:29<3:15:37, 1.36s/it] 86%|████████▌ | 53280/61904 [4:34:31<3:16:46, 1.37s/it] {'loss': 2.4651, 'learning_rate': 1.1397640347465318e-07, 'epoch': 13.77} + 86%|████████▌ | 53280/61904 [4:34:31<3:16:46, 1.37s/it] 86%|████████▌ | 53281/61904 [4:34:32<3:20:22, 1.39s/it] 86%|████████▌ | 53282/61904 [4:34:34<3:17:27, 1.37s/it] 86%|████████▌ | 53283/61904 [4:34:35<3:17:11, 1.37s/it] 86%|████████▌ | 53284/61904 [4:34:36<3:18:53, 1.38s/it] 86%|████████▌ | 53285/61904 [4:34:38<3:12:04, 1.34s/it] 86%|████████▌ | 53286/61904 [4:34:39<3:10:17, 1.32s/it] 86%|████████▌ | 53287/61904 [4:34:40<3:16:01, 1.36s/it] 86%|████████▌ | 53288/61904 [4:34:42<3:11:27, 1.33s/it] 86%|████████▌ | 53289/61904 [4:34:43<3:23:29, 1.42s/it] 86%|████████▌ | 53290/61904 [4:34:45<3:22:42, 1.41s/it] 86%|████████▌ | 53291/61904 [4:34:46<3:18:54, 1.39s/it] 86%|████████▌ | 53292/61904 [4:34:47<3:22:33, 1.41s/it] 86%|████████▌ | 53293/61904 [4:34:49<3:21:01, 1.40s/it] 86%|████████▌ | 53294/61904 [4:34:50<3:22:03, 1.41s/it] 86%|████████▌ | 53295/61904 [4:34:51<3:15:12, 1.36s/it] 86%|████████▌ | 53296/61904 [4:34:53<3:16:10, 1.37s/it] 86%|████████▌ | 53297/61904 [4:34:54<3:18:23, 1.38s/it] 86%|████████▌ | 53298/61904 [4:34:56<3:23:29, 1.42s/it] 86%|████████▌ | 53299/61904 [4:34:57<3:16:34, 1.37s/it] 86%|████████▌ | 53300/61904 [4:34:58<3:14:23, 1.36s/it] {'loss': 2.4309, 'learning_rate': 1.1394399066511085e-07, 'epoch': 13.78} + 86%|████████▌ | 53300/61904 [4:34:58<3:14:23, 1.36s/it] 86%|████████▌ | 53301/61904 [4:35:00<3:14:41, 1.36s/it] 86%|████████▌ | 53302/61904 [4:35:01<3:13:27, 1.35s/it] 86%|████████▌ | 53303/61904 [4:35:02<3:11:33, 1.34s/it] 86%|████████▌ | 53304/61904 [4:35:04<3:10:41, 1.33s/it] 86%|████████▌ | 53305/61904 [4:35:05<3:13:53, 1.35s/it] 86%|████████▌ | 53306/61904 [4:35:06<3:15:11, 1.36s/it] 86%|████████▌ | 53307/61904 [4:35:08<3:14:50, 1.36s/it] 86%|████████▌ | 53308/61904 [4:35:09<3:14:38, 1.36s/it] 86%|████████▌ | 53309/61904 [4:35:11<3:24:29, 1.43s/it] 86%|████████▌ | 53310/61904 [4:35:12<3:18:19, 1.38s/it] 86%|████████▌ | 53311/61904 [4:35:13<3:10:10, 1.33s/it] 86%|████████▌ | 53312/61904 [4:35:15<3:14:23, 1.36s/it] 86%|████████▌ | 53313/61904 [4:35:16<3:15:11, 1.36s/it] 86%|████████▌ | 53314/61904 [4:35:18<3:22:19, 1.41s/it] 86%|████████▌ | 53315/61904 [4:35:19<3:12:25, 1.34s/it] 86%|████████▌ | 53316/61904 [4:35:20<3:12:59, 1.35s/it] 86%|████████▌ | 53317/61904 [4:35:21<3:09:43, 1.33s/it] 86%|████████▌ | 53318/61904 [4:35:23<3:09:05, 1.32s/it] 86%|████████▌ | 53319/61904 [4:35:24<3:10:44, 1.33s/it] 86%|████████▌ | 53320/61904 [4:35:25<3:14:05, 1.36s/it] {'loss': 2.4539, 'learning_rate': 1.1391157785556853e-07, 'epoch': 13.78} + 86%|████████▌ | 53320/61904 [4:35:25<3:14:05, 1.36s/it] 86%|████████▌ | 53321/61904 [4:35:27<3:10:10, 1.33s/it] 86%|████████▌ | 53322/61904 [4:35:28<3:09:33, 1.33s/it] 86%|████████▌ | 53323/61904 [4:35:29<3:10:17, 1.33s/it] 86%|████████▌ | 53324/61904 [4:35:31<3:08:19, 1.32s/it] 86%|████████▌ | 53325/61904 [4:35:32<3:12:32, 1.35s/it] 86%|████████▌ | 53326/61904 [4:35:33<3:15:48, 1.37s/it] 86%|████████▌ | 53327/61904 [4:35:35<3:19:41, 1.40s/it] 86%|████████▌ | 53328/61904 [4:35:36<3:14:52, 1.36s/it] 86%|████████▌ | 53329/61904 [4:35:38<3:13:40, 1.36s/it] 86%|████████▌ | 53330/61904 [4:35:39<3:10:46, 1.34s/it] 86%|████████▌ | 53331/61904 [4:35:40<3:09:20, 1.33s/it] 86%|████████▌ | 53332/61904 [4:35:42<3:11:46, 1.34s/it] 86%|████████▌ | 53333/61904 [4:35:43<3:15:03, 1.37s/it] 86%|████████▌ | 53334/61904 [4:35:44<3:17:23, 1.38s/it] 86%|████████▌ | 53335/61904 [4:35:46<3:18:26, 1.39s/it] 86%|████████▌ | 53336/61904 [4:35:47<3:16:49, 1.38s/it] 86%|████████▌ | 53337/61904 [4:35:48<3:15:12, 1.37s/it] 86%|████████▌ | 53338/61904 [4:35:50<3:19:29, 1.40s/it] 86%|████████▌ | 53339/61904 [4:35:51<3:15:14, 1.37s/it] 86%|████████▌ | 53340/61904 [4:35:53<3:21:22, 1.41s/it] {'loss': 2.4259, 'learning_rate': 1.1387916504602617e-07, 'epoch': 13.79} + 86%|████████▌ | 53340/61904 [4:35:53<3:21:22, 1.41s/it] 86%|████████▌ | 53341/61904 [4:35:54<3:19:53, 1.40s/it] 86%|████████▌ | 53342/61904 [4:35:56<3:19:33, 1.40s/it] 86%|████████▌ | 53343/61904 [4:35:57<3:17:49, 1.39s/it] 86%|████████▌ | 53344/61904 [4:35:58<3:13:34, 1.36s/it] 86%|████████▌ | 53345/61904 [4:36:00<3:15:50, 1.37s/it] 86%|████████▌ | 53346/61904 [4:36:01<3:18:06, 1.39s/it] 86%|████████▌ | 53347/61904 [4:36:03<3:22:30, 1.42s/it] 86%|████████▌ | 53348/61904 [4:36:04<3:21:39, 1.41s/it] 86%|████████▌ | 53349/61904 [4:36:05<3:15:51, 1.37s/it] 86%|████████▌ | 53350/61904 [4:36:07<3:15:17, 1.37s/it] 86%|████████▌ | 53351/61904 [4:36:08<3:14:08, 1.36s/it] 86%|████████▌ | 53352/61904 [4:36:09<3:18:01, 1.39s/it] 86%|████████▌ | 53353/61904 [4:36:11<3:24:50, 1.44s/it] 86%|████████▌ | 53354/61904 [4:36:12<3:29:21, 1.47s/it] 86%|████████▌ | 53355/61904 [4:36:14<3:24:13, 1.43s/it] 86%|████████▌ | 53356/61904 [4:36:15<3:24:41, 1.44s/it] 86%|████████▌ | 53357/61904 [4:36:17<3:21:42, 1.42s/it] 86%|████████▌ | 53358/61904 [4:36:18<3:15:44, 1.37s/it] 86%|████████▌ | 53359/61904 [4:36:19<3:14:19, 1.36s/it] 86%|████████▌ | 53360/61904 [4:36:21<3:12:14, 1.35s/it] {'loss': 2.357, 'learning_rate': 1.1384675223648386e-07, 'epoch': 13.79} + 86%|████████▌ | 53360/61904 [4:36:21<3:12:14, 1.35s/it] 86%|████████▌ | 53361/61904 [4:36:22<3:07:29, 1.32s/it] 86%|████████▌ | 53362/61904 [4:36:23<3:11:22, 1.34s/it] 86%|████████▌ | 53363/61904 [4:36:25<3:12:21, 1.35s/it] 86%|████████▌ | 53364/61904 [4:36:26<3:11:34, 1.35s/it] 86%|████████▌ | 53365/61904 [4:36:27<3:13:13, 1.36s/it] 86%|████████▌ | 53366/61904 [4:36:29<3:15:10, 1.37s/it] 86%|████████▌ | 53367/61904 [4:36:30<3:16:48, 1.38s/it] 86%|████████▌ | 53368/61904 [4:36:31<3:13:11, 1.36s/it] 86%|████████▌ | 53369/61904 [4:36:33<3:18:23, 1.39s/it] 86%|████████▌ | 53370/61904 [4:36:34<3:23:17, 1.43s/it] 86%|████████▌ | 53371/61904 [4:36:36<3:25:12, 1.44s/it] 86%|████████▌ | 53372/61904 [4:36:37<3:33:34, 1.50s/it] 86%|████████▌ | 53373/61904 [4:36:39<3:32:09, 1.49s/it] 86%|████████▌ | 53374/61904 [4:36:40<3:31:30, 1.49s/it] 86%|████████▌ | 53375/61904 [4:36:42<3:31:28, 1.49s/it] 86%|████████▌ | 53376/61904 [4:36:43<3:22:29, 1.42s/it] 86%|████████▌ | 53377/61904 [4:36:45<3:18:31, 1.40s/it] 86%|████████▌ | 53378/61904 [4:36:46<3:16:34, 1.38s/it] 86%|████████▌ | 53379/61904 [4:36:47<3:10:35, 1.34s/it] 86%|████████▌ | 53380/61904 [4:36:49<3:15:15, 1.37s/it] {'loss': 2.4122, 'learning_rate': 1.1381433942694152e-07, 'epoch': 13.8} + 86%|████████▌ | 53380/61904 [4:36:49<3:15:15, 1.37s/it] 86%|████████▌ | 53381/61904 [4:36:50<3:16:14, 1.38s/it] 86%|████████▌ | 53382/61904 [4:36:51<3:15:56, 1.38s/it] 86%|████████▌ | 53383/61904 [4:36:53<3:12:46, 1.36s/it] 86%|████████▌ | 53384/61904 [4:36:54<3:13:57, 1.37s/it] 86%|████████▌ | 53385/61904 [4:36:55<3:13:31, 1.36s/it] 86%|████████▌ | 53386/61904 [4:36:57<3:08:22, 1.33s/it] 86%|████████▌ | 53387/61904 [4:36:58<3:10:25, 1.34s/it] 86%|████████▌ | 53388/61904 [4:36:59<3:15:33, 1.38s/it] 86%|████████▌ | 53389/61904 [4:37:01<3:14:14, 1.37s/it] 86%|████████▌ | 53390/61904 [4:37:02<3:19:36, 1.41s/it] 86%|████████▌ | 53391/61904 [4:37:04<3:22:37, 1.43s/it] 86%|████████▌ | 53392/61904 [4:37:05<3:25:52, 1.45s/it] 86%|████████▋ | 53393/61904 [4:37:07<3:23:45, 1.44s/it] 86%|████████▋ | 53394/61904 [4:37:08<3:17:08, 1.39s/it] 86%|████████▋ | 53395/61904 [4:37:09<3:11:50, 1.35s/it] 86%|████████▋ | 53396/61904 [4:37:11<3:15:18, 1.38s/it] 86%|████████▋ | 53397/61904 [4:37:12<3:14:20, 1.37s/it] 86%|████████▋ | 53398/61904 [4:37:13<3:16:09, 1.38s/it] 86%|████████▋ | 53399/61904 [4:37:15<3:16:14, 1.38s/it] 86%|████████▋ | 53400/61904 [4:37:16<3:20:57, 1.42s/it] {'loss': 2.435, 'learning_rate': 1.1378192661739921e-07, 'epoch': 13.8} + 86%|████████▋ | 53400/61904 [4:37:16<3:20:57, 1.42s/it] 86%|████████▋ | 53401/61904 [4:37:18<3:17:23, 1.39s/it] 86%|████████▋ | 53402/61904 [4:37:19<3:12:55, 1.36s/it] 86%|████████▋ | 53403/61904 [4:37:21<3:24:27, 1.44s/it] 86%|████████▋ | 53404/61904 [4:37:22<3:17:47, 1.40s/it] 86%|████████▋ | 53405/61904 [4:37:23<3:14:14, 1.37s/it] 86%|████████▋ | 53406/61904 [4:37:25<3:12:42, 1.36s/it] 86%|████████▋ | 53407/61904 [4:37:26<3:10:48, 1.35s/it] 86%|████████▋ | 53408/61904 [4:37:27<3:11:07, 1.35s/it] 86%|████████▋ | 53409/61904 [4:37:29<3:10:55, 1.35s/it] 86%|████████▋ | 53410/61904 [4:37:30<3:15:32, 1.38s/it] 86%|████████▋ | 53411/61904 [4:37:31<3:13:51, 1.37s/it] 86%|████████▋ | 53412/61904 [4:37:33<3:12:23, 1.36s/it] 86%|████████▋ | 53413/61904 [4:37:34<3:10:06, 1.34s/it] 86%|████████▋ | 53414/61904 [4:37:35<3:08:14, 1.33s/it] 86%|████████▋ | 53415/61904 [4:37:37<3:12:24, 1.36s/it] 86%|████████▋ | 53416/61904 [4:37:38<3:24:34, 1.45s/it] 86%|████████▋ | 53417/61904 [4:37:40<3:23:51, 1.44s/it] 86%|████████▋ | 53418/61904 [4:37:41<3:19:31, 1.41s/it] 86%|████████▋ | 53419/61904 [4:37:43<3:21:36, 1.43s/it] 86%|████████▋ | 53420/61904 [4:37:44<3:19:15, 1.41s/it] {'loss': 2.4501, 'learning_rate': 1.1374951380785684e-07, 'epoch': 13.81} + 86%|████████▋ | 53420/61904 [4:37:44<3:19:15, 1.41s/it] 86%|████████▋ | 53421/61904 [4:37:45<3:16:08, 1.39s/it] 86%|████████▋ | 53422/61904 [4:37:47<3:12:51, 1.36s/it] 86%|████████▋ | 53423/61904 [4:37:48<3:15:56, 1.39s/it] 86%|████████▋ | 53424/61904 [4:37:49<3:15:36, 1.38s/it] 86%|████████▋ | 53425/61904 [4:37:51<3:17:07, 1.39s/it] 86%|████████▋ | 53426/61904 [4:37:52<3:16:37, 1.39s/it] 86%|████████▋ | 53427/61904 [4:37:54<3:18:34, 1.41s/it] 86%|████████▋ | 53428/61904 [4:37:55<3:19:58, 1.42s/it] 86%|████████▋ | 53429/61904 [4:37:57<3:20:06, 1.42s/it] 86%|████████▋ | 53430/61904 [4:37:58<3:23:35, 1.44s/it] 86%|████████▋ | 53431/61904 [4:37:59<3:14:58, 1.38s/it] 86%|████████▋ | 53432/61904 [4:38:01<3:16:24, 1.39s/it] 86%|████████▋ | 53433/61904 [4:38:02<3:14:57, 1.38s/it] 86%|████████▋ | 53434/61904 [4:38:04<3:19:31, 1.41s/it] 86%|████████▋ | 53435/61904 [4:38:05<3:23:25, 1.44s/it] 86%|████████▋ | 53436/61904 [4:38:06<3:20:54, 1.42s/it] 86%|████████▋ | 53437/61904 [4:38:08<3:18:05, 1.40s/it] 86%|████████▋ | 53438/61904 [4:38:09<3:20:36, 1.42s/it] 86%|████████▋ | 53439/61904 [4:38:11<3:19:49, 1.42s/it] 86%|████████▋ | 53440/61904 [4:38:12<3:15:40, 1.39s/it] {'loss': 2.4191, 'learning_rate': 1.1371710099831453e-07, 'epoch': 13.81} + 86%|████████▋ | 53440/61904 [4:38:12<3:15:40, 1.39s/it] 86%|████████▋ | 53441/61904 [4:38:13<3:20:18, 1.42s/it] 86%|████████▋ | 53442/61904 [4:38:15<3:20:34, 1.42s/it] 86%|████████▋ | 53443/61904 [4:38:16<3:26:47, 1.47s/it] 86%|████████▋ | 53444/61904 [4:38:18<3:32:31, 1.51s/it] 86%|████████▋ | 53445/61904 [4:38:20<3:30:08, 1.49s/it] 86%|████████▋ | 53446/61904 [4:38:21<3:24:45, 1.45s/it] 86%|████████▋ | 53447/61904 [4:38:22<3:18:03, 1.41s/it] 86%|████████▋ | 53448/61904 [4:38:24<3:16:08, 1.39s/it] 86%|████████▋ | 53449/61904 [4:38:25<3:15:39, 1.39s/it] 86%|████████▋ | 53450/61904 [4:38:26<3:12:35, 1.37s/it] 86%|████████▋ | 53451/61904 [4:38:28<3:15:26, 1.39s/it] 86%|████████▋ | 53452/61904 [4:38:29<3:12:36, 1.37s/it] 86%|████████▋ | 53453/61904 [4:38:30<3:11:04, 1.36s/it] 86%|████████▋ | 53454/61904 [4:38:32<3:10:16, 1.35s/it] 86%|████████▋ | 53455/61904 [4:38:33<3:15:20, 1.39s/it] 86%|████████▋ | 53456/61904 [4:38:34<3:10:45, 1.35s/it] 86%|████████▋ | 53457/61904 [4:38:36<3:14:55, 1.38s/it] 86%|████████▋ | 53458/61904 [4:38:37<3:19:08, 1.41s/it] 86%|████████▋ | 53459/61904 [4:38:39<3:12:03, 1.36s/it] 86%|████████▋ | 53460/61904 [4:38:40<3:13:56, 1.38s/it] {'loss': 2.4168, 'learning_rate': 1.1368468818877219e-07, 'epoch': 13.82} + 86%|████████▋ | 53460/61904 [4:38:40<3:13:56, 1.38s/it] 86%|████████▋ | 53461/61904 [4:38:41<3:15:28, 1.39s/it] 86%|████████▋ | 53462/61904 [4:38:43<3:07:48, 1.33s/it] 86%|████████▋ | 53463/61904 [4:38:44<3:07:31, 1.33s/it] 86%|████████▋ | 53464/61904 [4:38:45<3:09:58, 1.35s/it] 86%|████████▋ | 53465/61904 [4:38:47<3:11:55, 1.36s/it] 86%|████████▋ | 53466/61904 [4:38:48<3:12:11, 1.37s/it] 86%|████████▋ | 53467/61904 [4:38:50<3:14:05, 1.38s/it] 86%|████████▋ | 53468/61904 [4:38:51<3:14:10, 1.38s/it] 86%|████████▋ | 53469/61904 [4:38:52<3:20:50, 1.43s/it] 86%|████████▋ | 53470/61904 [4:38:54<3:13:15, 1.37s/it] 86%|████████▋ | 53471/61904 [4:38:55<3:19:05, 1.42s/it] 86%|████████▋ | 53472/61904 [4:38:57<3:16:43, 1.40s/it] 86%|████████▋ | 53473/61904 [4:38:58<3:12:54, 1.37s/it] 86%|████████▋ | 53474/61904 [4:38:59<3:20:18, 1.43s/it] 86%|████████▋ | 53475/61904 [4:39:01<3:17:20, 1.40s/it] 86%|████████▋ | 53476/61904 [4:39:02<3:11:19, 1.36s/it] 86%|████████▋ | 53477/61904 [4:39:04<3:15:53, 1.39s/it] 86%|████████▋ | 53478/61904 [4:39:05<3:13:20, 1.38s/it] 86%|████████▋ | 53479/61904 [4:39:06<3:09:22, 1.35s/it] 86%|████████▋ | 53480/61904 [4:39:08<3:10:29, 1.36s/it] {'loss': 2.4114, 'learning_rate': 1.1365227537922988e-07, 'epoch': 13.82} + 86%|████████▋ | 53480/61904 [4:39:08<3:10:29, 1.36s/it] 86%|████████▋ | 53481/61904 [4:39:09<3:04:22, 1.31s/it] 86%|████████▋ | 53482/61904 [4:39:10<3:05:24, 1.32s/it] 86%|████████▋ | 53483/61904 [4:39:12<3:10:32, 1.36s/it] 86%|████████▋ | 53484/61904 [4:39:13<3:11:36, 1.37s/it] 86%|████████▋ | 53485/61904 [4:39:14<3:17:49, 1.41s/it] 86%|████████▋ | 53486/61904 [4:39:16<3:15:58, 1.40s/it] 86%|████████▋ | 53487/61904 [4:39:17<3:11:04, 1.36s/it] 86%|████████▋ | 53488/61904 [4:39:19<3:31:17, 1.51s/it] 86%|████████▋ | 53489/61904 [4:39:20<3:24:32, 1.46s/it] 86%|████████▋ | 53490/61904 [4:39:22<3:18:09, 1.41s/it] 86%|████████▋ | 53491/61904 [4:39:23<3:19:04, 1.42s/it] 86%|████████▋ | 53492/61904 [4:39:24<3:20:18, 1.43s/it] 86%|████████▋ | 53493/61904 [4:39:26<3:18:49, 1.42s/it] 86%|████████▋ | 53494/61904 [4:39:27<3:14:18, 1.39s/it] 86%|████████▋ | 53495/61904 [4:39:29<3:14:21, 1.39s/it] 86%|████████▋ | 53496/61904 [4:39:30<3:11:24, 1.37s/it] 86%|████████▋ | 53497/61904 [4:39:31<3:14:03, 1.38s/it] 86%|████████▋ | 53498/61904 [4:39:33<3:12:55, 1.38s/it] 86%|████████▋ | 53499/61904 [4:39:34<3:16:18, 1.40s/it] 86%|████████▋ | 53500/61904 [4:39:35<3:10:18, 1.36s/it] {'loss': 2.4437, 'learning_rate': 1.1361986256968752e-07, 'epoch': 13.83} + 86%|████████▋ | 53500/61904 [4:39:35<3:10:18, 1.36s/it] 86%|████████▋ | 53501/61904 [4:39:37<3:09:15, 1.35s/it] 86%|████████▋ | 53502/61904 [4:39:38<3:09:23, 1.35s/it] 86%|████████▋ | 53503/61904 [4:39:39<3:10:58, 1.36s/it] 86%|████████▋ | 53504/61904 [4:39:41<3:10:28, 1.36s/it] 86%|████████▋ | 53505/61904 [4:39:42<3:07:04, 1.34s/it] 86%|████████▋ | 53506/61904 [4:39:44<3:12:43, 1.38s/it] 86%|████████▋ | 53507/61904 [4:39:45<3:14:04, 1.39s/it] 86%|████████▋ | 53508/61904 [4:39:46<3:12:40, 1.38s/it] 86%|████████▋ | 53509/61904 [4:39:48<3:13:24, 1.38s/it] 86%|████████▋ | 53510/61904 [4:39:49<3:17:21, 1.41s/it] 86%|████████▋ | 53511/61904 [4:39:51<3:15:47, 1.40s/it] 86%|████████▋ | 53512/61904 [4:39:52<3:14:25, 1.39s/it] 86%|████████▋ | 53513/61904 [4:39:53<3:12:32, 1.38s/it] 86%|████████▋ | 53514/61904 [4:39:55<3:12:31, 1.38s/it] 86%|████████▋ | 53515/61904 [4:39:56<3:08:58, 1.35s/it] 86%|████████▋ | 53516/61904 [4:39:57<3:09:25, 1.35s/it] 86%|████████▋ | 53517/61904 [4:39:59<3:11:39, 1.37s/it] 86%|████████▋ | 53518/61904 [4:40:00<3:11:04, 1.37s/it] 86%|████████▋ | 53519/61904 [4:40:01<3:07:12, 1.34s/it] 86%|████████▋ | 53520/61904 [4:40:03<3:08:38, 1.35s/it] {'loss': 2.5263, 'learning_rate': 1.135874497601452e-07, 'epoch': 13.83} + 86%|████████▋ | 53520/61904 [4:40:03<3:08:38, 1.35s/it] 86%|████████▋ | 53521/61904 [4:40:04<3:14:05, 1.39s/it] 86%|████████▋ | 53522/61904 [4:40:05<3:07:41, 1.34s/it] 86%|████████▋ | 53523/61904 [4:40:07<3:14:28, 1.39s/it] 86%|████████▋ | 53524/61904 [4:40:08<3:07:39, 1.34s/it] 86%|████████▋ | 53525/61904 [4:40:10<3:11:46, 1.37s/it] 86%|████████▋ | 53526/61904 [4:40:11<3:14:21, 1.39s/it] 86%|████████▋ | 53527/61904 [4:40:13<3:17:30, 1.41s/it] 86%|████████▋ | 53528/61904 [4:40:14<3:21:26, 1.44s/it] 86%|████████▋ | 53529/61904 [4:40:16<3:26:41, 1.48s/it] 86%|████████▋ | 53530/61904 [4:40:17<3:19:11, 1.43s/it] 86%|████████▋ | 53531/61904 [4:40:18<3:22:00, 1.45s/it] 86%|████████▋ | 53532/61904 [4:40:20<3:25:15, 1.47s/it] 86%|████████▋ | 53533/61904 [4:40:21<3:25:04, 1.47s/it] 86%|████████▋ | 53534/61904 [4:40:23<3:13:01, 1.38s/it] 86%|████████▋ | 53535/61904 [4:40:24<3:11:25, 1.37s/it] 86%|████████▋ | 53536/61904 [4:40:25<3:19:23, 1.43s/it] 86%|████████▋ | 53537/61904 [4:40:27<3:14:08, 1.39s/it] 86%|████████▋ | 53538/61904 [4:40:28<3:11:22, 1.37s/it] 86%|████████▋ | 53539/61904 [4:40:30<3:12:56, 1.38s/it] 86%|████████▋ | 53540/61904 [4:40:31<3:15:51, 1.41s/it] {'loss': 2.3909, 'learning_rate': 1.1355503695060289e-07, 'epoch': 13.84} + 86%|████████▋ | 53540/61904 [4:40:31<3:15:51, 1.41s/it] 86%|████████▋ | 53541/61904 [4:40:32<3:13:45, 1.39s/it] 86%|████████▋ | 53542/61904 [4:40:34<3:14:41, 1.40s/it] 86%|████████▋ | 53543/61904 [4:40:35<3:22:32, 1.45s/it] 86%|████████▋ | 53544/61904 [4:40:37<3:19:31, 1.43s/it] 86%|████████▋ | 53545/61904 [4:40:38<3:16:35, 1.41s/it] 86%|████████▋ | 53546/61904 [4:40:39<3:12:54, 1.38s/it] 87%|████████��� | 53547/61904 [4:40:41<3:07:45, 1.35s/it] 87%|████████▋ | 53548/61904 [4:40:42<3:06:31, 1.34s/it] 87%|████████▋ | 53549/61904 [4:40:43<3:05:07, 1.33s/it] 87%|████████▋ | 53550/61904 [4:40:45<3:05:43, 1.33s/it] 87%|████████▋ | 53551/61904 [4:40:46<3:05:01, 1.33s/it] 87%|████████▋ | 53552/61904 [4:40:47<3:12:50, 1.39s/it] 87%|████████▋ | 53553/61904 [4:40:49<3:17:19, 1.42s/it] 87%|████████▋ | 53554/61904 [4:40:50<3:12:17, 1.38s/it] 87%|████████▋ | 53555/61904 [4:40:52<3:16:45, 1.41s/it] 87%|████████▋ | 53556/61904 [4:40:53<3:18:07, 1.42s/it] 87%|████████▋ | 53557/61904 [4:40:55<3:15:52, 1.41s/it] 87%|████████▋ | 53558/61904 [4:40:56<3:11:10, 1.37s/it] 87%|████████▋ | 53559/61904 [4:40:57<3:12:55, 1.39s/it] 87%|████████▋ | 53560/61904 [4:40:59<3:22:42, 1.46s/it] {'loss': 2.4661, 'learning_rate': 1.1352262414106056e-07, 'epoch': 13.84} + 87%|████████▋ | 53560/61904 [4:40:59<3:22:42, 1.46s/it] 87%|████████▋ | 53561/61904 [4:41:00<3:17:47, 1.42s/it] 87%|████████▋ | 53562/61904 [4:41:02<3:15:36, 1.41s/it] 87%|████████▋ | 53563/61904 [4:41:03<3:18:40, 1.43s/it] 87%|████████▋ | 53564/61904 [4:41:04<3:16:09, 1.41s/it] 87%|████████▋ | 53565/61904 [4:41:06<3:13:28, 1.39s/it] 87%|████████▋ | 53566/61904 [4:41:07<3:24:23, 1.47s/it] 87%|████████▋ | 53567/61904 [4:41:09<3:22:15, 1.46s/it] 87%|████████▋ | 53568/61904 [4:41:10<3:18:19, 1.43s/it] 87%|████████▋ | 53569/61904 [4:41:12<3:19:56, 1.44s/it] 87%|████████▋ | 53570/61904 [4:41:13<3:18:43, 1.43s/it] 87%|████████▋ | 53571/61904 [4:41:14<3:15:04, 1.40s/it] 87%|████████▋ | 53572/61904 [4:41:16<3:10:24, 1.37s/it] 87%|████████▋ | 53573/61904 [4:41:17<3:12:04, 1.38s/it] 87%|████████▋ | 53574/61904 [4:41:19<3:14:11, 1.40s/it] 87%|████████▋ | 53575/61904 [4:41:20<3:19:47, 1.44s/it] 87%|████████▋ | 53576/61904 [4:41:21<3:13:09, 1.39s/it] 87%|████████▋ | 53577/61904 [4:41:23<3:11:05, 1.38s/it] 87%|████████▋ | 53578/61904 [4:41:24<3:15:46, 1.41s/it] 87%|████████▋ | 53579/61904 [4:41:26<3:12:58, 1.39s/it] 87%|████████▋ | 53580/61904 [4:41:27<3:14:21, 1.40s/it] {'loss': 2.3978, 'learning_rate': 1.1349021133151822e-07, 'epoch': 13.85} + 87%|████████▋ | 53580/61904 [4:41:27<3:14:21, 1.40s/it] 87%|████████▋ | 53581/61904 [4:41:28<3:15:10, 1.41s/it] 87%|████████▋ | 53582/61904 [4:41:30<3:10:31, 1.37s/it] 87%|████████▋ | 53583/61904 [4:41:31<3:05:35, 1.34s/it] 87%|████████▋ | 53584/61904 [4:41:32<3:09:20, 1.37s/it] 87%|████████▋ | 53585/61904 [4:41:34<3:07:23, 1.35s/it] 87%|████████▋ | 53586/61904 [4:41:35<3:11:09, 1.38s/it] 87%|████████▋ | 53587/61904 [4:41:37<3:19:36, 1.44s/it] 87%|████████▋ | 53588/61904 [4:41:38<3:19:12, 1.44s/it] 87%|████████▋ | 53589/61904 [4:41:39<3:13:07, 1.39s/it] 87%|████████▋ | 53590/61904 [4:41:41<3:07:43, 1.35s/it] 87%|████████▋ | 53591/61904 [4:41:42<3:11:46, 1.38s/it] 87%|████████▋ | 53592/61904 [4:41:44<3:09:03, 1.36s/it] 87%|████████▋ | 53593/61904 [4:41:45<3:07:48, 1.36s/it] 87%|████████▋ | 53594/61904 [4:41:46<3:06:19, 1.35s/it] 87%|████████▋ | 53595/61904 [4:41:47<3:02:25, 1.32s/it] 87%|████████▋ | 53596/61904 [4:41:49<3:05:46, 1.34s/it] 87%|████████▋ | 53597/61904 [4:41:50<3:10:37, 1.38s/it] 87%|████████▋ | 53598/61904 [4:41:52<3:06:24, 1.35s/it] 87%|████████▋ | 53599/61904 [4:41:53<3:11:15, 1.38s/it] 87%|████████▋ | 53600/61904 [4:41:54<3:10:42, 1.38s/it] {'loss': 2.4506, 'learning_rate': 1.1345779852197588e-07, 'epoch': 13.85} + 87%|████████▋ | 53600/61904 [4:41:54<3:10:42, 1.38s/it] 87%|████████▋ | 53601/61904 [4:41:56<3:10:44, 1.38s/it] 87%|████████▋ | 53602/61904 [4:41:57<3:07:22, 1.35s/it] 87%|████████▋ | 53603/61904 [4:41:58<3:02:21, 1.32s/it] 87%|████████▋ | 53604/61904 [4:42:00<3:02:23, 1.32s/it] 87%|████████▋ | 53605/61904 [4:42:01<3:07:42, 1.36s/it] 87%|████████▋ | 53606/61904 [4:42:02<3:10:24, 1.38s/it] 87%|████████▋ | 53607/61904 [4:42:04<3:10:51, 1.38s/it] 87%|████████▋ | 53608/61904 [4:42:06<3:21:24, 1.46s/it] 87%|████████▋ | 53609/61904 [4:42:07<3:26:22, 1.49s/it] 87%|████████▋ | 53610/61904 [4:42:08<3:15:06, 1.41s/it] 87%|████████▋ | 53611/61904 [4:42:10<3:08:30, 1.36s/it] 87%|████████▋ | 53612/61904 [4:42:11<3:14:12, 1.41s/it] 87%|████████▋ | 53613/61904 [4:42:13<3:17:57, 1.43s/it] 87%|████████▋ | 53614/61904 [4:42:14<3:19:05, 1.44s/it] 87%|████████▋ | 53615/61904 [4:42:15<3:20:30, 1.45s/it] 87%|████████▋ | 53616/61904 [4:42:17<3:15:56, 1.42s/it] 87%|████████▋ | 53617/61904 [4:42:18<3:19:58, 1.45s/it] 87%|████████▋ | 53618/61904 [4:42:20<3:15:58, 1.42s/it] 87%|████████▋ | 53619/61904 [4:42:21<3:13:34, 1.40s/it] 87%|████████▋ | 53620/61904 [4:42:22<3:13:21, 1.40s/it] {'loss': 2.4424, 'learning_rate': 1.1342538571243357e-07, 'epoch': 13.86} + 87%|████████▋ | 53620/61904 [4:42:22<3:13:21, 1.40s/it] 87%|████████▋ | 53621/61904 [4:42:24<3:14:03, 1.41s/it] 87%|████████▋ | 53622/61904 [4:42:26<3:25:29, 1.49s/it] 87%|████████▋ | 53623/61904 [4:42:27<3:19:36, 1.45s/it] 87%|████████▋ | 53624/61904 [4:42:28<3:16:02, 1.42s/it] 87%|████████▋ | 53625/61904 [4:42:30<3:12:55, 1.40s/it] 87%|████████▋ | 53626/61904 [4:42:31<3:11:36, 1.39s/it] 87%|████████▋ | 53627/61904 [4:42:32<3:08:02, 1.36s/it] 87%|████████▋ | 53628/61904 [4:42:34<3:16:43, 1.43s/it] 87%|████████▋ | 53629/61904 [4:42:35<3:17:01, 1.43s/it] 87%|████████▋ | 53630/61904 [4:42:37<3:16:50, 1.43s/it] 87%|████████▋ | 53631/61904 [4:42:38<3:13:25, 1.40s/it] 87%|████████▋ | 53632/61904 [4:42:40<3:18:24, 1.44s/it] 87%|████████▋ | 53633/61904 [4:42:41<3:18:30, 1.44s/it] 87%|████████▋ | 53634/61904 [4:42:43<3:21:28, 1.46s/it] 87%|████████▋ | 53635/61904 [4:42:44<3:14:43, 1.41s/it] 87%|████████▋ | 53636/61904 [4:42:45<3:14:01, 1.41s/it] 87%|████████▋ | 53637/61904 [4:42:47<3:16:10, 1.42s/it] 87%|████████▋ | 53638/61904 [4:42:48<3:11:15, 1.39s/it] 87%|████████▋ | 53639/61904 [4:42:50<3:17:32, 1.43s/it] 87%|████████▋ | 53640/61904 [4:42:51<3:17:17, 1.43s/it] {'loss': 2.4247, 'learning_rate': 1.1339297290289123e-07, 'epoch': 13.86} + 87%|████████▋ | 53640/61904 [4:42:51<3:17:17, 1.43s/it] 87%|████████▋ | 53641/61904 [4:42:52<3:11:33, 1.39s/it] 87%|████████▋ | 53642/61904 [4:42:54<3:17:10, 1.43s/it] 87%|████████▋ | 53643/61904 [4:42:55<3:21:31, 1.46s/it] 87%|████████▋ | 53644/61904 [4:42:57<3:22:04, 1.47s/it] 87%|████████▋ | 53645/61904 [4:42:58<3:16:01, 1.42s/it] 87%|████████▋ | 53646/61904 [4:42:59<3:13:38, 1.41s/it] 87%|████████▋ | 53647/61904 [4:43:01<3:10:47, 1.39s/it] 87%|████████▋ | 53648/61904 [4:43:02<3:09:28, 1.38s/it] 87%|████████▋ | 53649/61904 [4:43:04<3:11:02, 1.39s/it] 87%|████████▋ | 53650/61904 [4:43:05<3:06:01, 1.35s/it] 87%|████████▋ | 53651/61904 [4:43:06<3:05:14, 1.35s/it] 87%|████████▋ | 53652/61904 [4:43:08<3:03:57, 1.34s/it] 87%|████████▋ | 53653/61904 [4:43:09<3:04:24, 1.34s/it] 87%|████████▋ | 53654/61904 [4:43:10<3:11:29, 1.39s/it] 87%|████████▋ | 53655/61904 [4:43:12<3:13:45, 1.41s/it] 87%|████████▋ | 53656/61904 [4:43:13<3:13:46, 1.41s/it] 87%|████████▋ | 53657/61904 [4:43:15<3:17:36, 1.44s/it] 87%|████████▋ | 53658/61904 [4:43:16<3:14:14, 1.41s/it] 87%|████████▋ | 53659/61904 [4:43:17<3:08:28, 1.37s/it] 87%|████████▋ | 53660/61904 [4:43:19<3:11:21, 1.39s/it] {'loss': 2.4441, 'learning_rate': 1.1336056009334889e-07, 'epoch': 13.87} + 87%|████████▋ | 53660/61904 [4:43:19<3:11:21, 1.39s/it] 87%|████████▋ | 53661/61904 [4:43:20<3:14:43, 1.42s/it] 87%|████████▋ | 53662/61904 [4:43:22<3:13:14, 1.41s/it] 87%|████████▋ | 53663/61904 [4:43:23<3:08:04, 1.37s/it] 87%|████████▋ | 53664/61904 [4:43:24<3:05:32, 1.35s/it] 87%|████████▋ | 53665/61904 [4:43:25<2:59:45, 1.31s/it] 87%|████████▋ | 53666/61904 [4:43:27<2:57:39, 1.29s/it] 87%|████████▋ | 53667/61904 [4:43:28<3:01:50, 1.32s/it] 87%|████████▋ | 53668/61904 [4:43:30<3:09:27, 1.38s/it] 87%|████████▋ | 53669/61904 [4:43:31<3:09:47, 1.38s/it] 87%|████████▋ | 53670/61904 [4:43:32<3:10:24, 1.39s/it] 87%|████████▋ | 53671/61904 [4:43:34<3:13:54, 1.41s/it] 87%|████████▋ | 53672/61904 [4:43:35<3:09:13, 1.38s/it] 87%|████████▋ | 53673/61904 [4:43:37<3:10:23, 1.39s/it] 87%|████████▋ | 53674/61904 [4:43:38<3:12:26, 1.40s/it] 87%|████████▋ | 53675/61904 [4:43:40<3:15:36, 1.43s/it] 87%|████████▋ | 53676/61904 [4:43:41<3:11:27, 1.40s/it] 87%|████████▋ | 53677/61904 [4:43:42<3:09:05, 1.38s/it] 87%|████████▋ | 53678/61904 [4:43:44<3:08:45, 1.38s/it] 87%|████████▋ | 53679/61904 [4:43:45<3:09:39, 1.38s/it] 87%|████████▋ | 53680/61904 [4:43:46<3:11:43, 1.40s/it] {'loss': 2.4742, 'learning_rate': 1.1332814728380655e-07, 'epoch': 13.87} + 87%|████████▋ | 53680/61904 [4:43:46<3:11:43, 1.40s/it] 87%|████████▋ | 53681/61904 [4:43:48<3:06:30, 1.36s/it] 87%|████████▋ | 53682/61904 [4:43:49<3:07:31, 1.37s/it] 87%|████████▋ | 53683/61904 [4:43:50<3:08:16, 1.37s/it] 87%|████████▋ | 53684/61904 [4:43:52<3:07:30, 1.37s/it] 87%|████████▋ | 53685/61904 [4:43:53<3:05:15, 1.35s/it] 87%|████████▋ | 53686/61904 [4:43:54<3:06:13, 1.36s/it] 87%|████████▋ | 53687/61904 [4:43:56<3:08:03, 1.37s/it] 87%|████████▋ | 53688/61904 [4:43:57<3:06:09, 1.36s/it] 87%|████████▋ | 53689/61904 [4:43:59<3:05:05, 1.35s/it] 87%|████████▋ | 53690/61904 [4:44:00<3:03:35, 1.34s/it] 87%|████████▋ | 53691/61904 [4:44:01<3:04:38, 1.35s/it] 87%|████████▋ | 53692/61904 [4:44:03<3:03:11, 1.34s/it] 87%|████████▋ | 53693/61904 [4:44:04<3:07:57, 1.37s/it] 87%|████████▋ | 53694/61904 [4:44:05<3:07:37, 1.37s/it] 87%|████████▋ | 53695/61904 [4:44:07<3:05:03, 1.35s/it] 87%|████████▋ | 53696/61904 [4:44:08<3:01:44, 1.33s/it] 87%|████████▋ | 53697/61904 [4:44:09<3:02:31, 1.33s/it] 87%|████████▋ | 53698/61904 [4:44:11<3:07:09, 1.37s/it] 87%|████████▋ | 53699/61904 [4:44:12<3:07:11, 1.37s/it] 87%|████████▋ | 53700/61904 [4:44:14<3:08:03, 1.38s/it] {'loss': 2.4507, 'learning_rate': 1.1329573447426424e-07, 'epoch': 13.88} + 87%|████████▋ | 53700/61904 [4:44:14<3:08:03, 1.38s/it] 87%|████████▋ | 53701/61904 [4:44:15<3:09:12, 1.38s/it] 87%|████████▋ | 53702/61904 [4:44:16<3:10:18, 1.39s/it] 87%|████████▋ | 53703/61904 [4:44:18<3:07:00, 1.37s/it] 87%|████████▋ | 53704/61904 [4:44:19<3:06:15, 1.36s/it] 87%|████████▋ | 53705/61904 [4:44:20<3:07:18, 1.37s/it] 87%|████████▋ | 53706/61904 [4:44:22<3:07:47, 1.37s/it] 87%|████████▋ | 53707/61904 [4:44:23<3:10:34, 1.40s/it] 87%|████████▋ | 53708/61904 [4:44:25<3:10:45, 1.40s/it] 87%|████████▋ | 53709/61904 [4:44:26<3:15:05, 1.43s/it] 87%|████████▋ | 53710/61904 [4:44:28<3:17:00, 1.44s/it] 87%|████████▋ | 53711/61904 [4:44:29<3:16:57, 1.44s/it] 87%|████████▋ | 53712/61904 [4:44:30<3:11:42, 1.40s/it] 87%|████████▋ | 53713/61904 [4:44:32<3:10:08, 1.39s/it] 87%|████████▋ | 53714/61904 [4:44:33<3:10:17, 1.39s/it] 87%|████████▋ | 53715/61904 [4:44:34<3:07:44, 1.38s/it] 87%|████████▋ | 53716/61904 [4:44:36<3:04:47, 1.35s/it] 87%|████████▋ | 53717/61904 [4:44:37<3:05:31, 1.36s/it] 87%|████████▋ | 53718/61904 [4:44:38<3:01:13, 1.33s/it] 87%|████████▋ | 53719/61904 [4:44:40<3:01:31, 1.33s/it] 87%|████████▋ | 53720/61904 [4:44:41<2:59:28, 1.32s/it] {'loss': 2.4422, 'learning_rate': 1.132633216647219e-07, 'epoch': 13.88} + 87%|████████▋ | 53720/61904 [4:44:41<2:59:28, 1.32s/it] 87%|████████▋ | 53721/61904 [4:44:42<3:03:05, 1.34s/it] 87%|████████▋ | 53722/61904 [4:44:44<3:07:47, 1.38s/it] 87%|████████▋ | 53723/61904 [4:44:45<3:09:32, 1.39s/it] 87%|████████▋ | 53724/61904 [4:44:47<3:10:16, 1.40s/it] 87%|████████▋ | 53725/61904 [4:44:48<3:09:56, 1.39s/it] 87%|████████▋ | 53726/61904 [4:44:49<3:07:43, 1.38s/it] 87%|████████▋ | 53727/61904 [4:44:51<3:08:47, 1.39s/it] 87%|████████▋ | 53728/61904 [4:44:52<3:10:59, 1.40s/it] 87%|████████▋ | 53729/61904 [4:44:54<3:08:05, 1.38s/it] 87%|████████▋ | 53730/61904 [4:44:55<3:09:28, 1.39s/it] 87%|████████▋ | 53731/61904 [4:44:56<3:01:49, 1.33s/it] 87%|████████▋ | 53732/61904 [4:44:57<2:57:58, 1.31s/it] 87%|████████▋ | 53733/61904 [4:44:59<3:07:56, 1.38s/it] 87%|████████▋ | 53734/61904 [4:45:00<3:07:35, 1.38s/it] 87%|████████▋ | 53735/61904 [4:45:02<3:03:51, 1.35s/it] 87%|████████▋ | 53736/61904 [4:45:03<3:06:59, 1.37s/it] 87%|████████▋ | 53737/61904 [4:45:05<3:09:17, 1.39s/it] 87%|████████▋ | 53738/61904 [4:45:06<3:06:45, 1.37s/it] 87%|████████▋ | 53739/61904 [4:45:07<3:05:21, 1.36s/it] 87%|████████▋ | 53740/61904 [4:45:09<3:05:41, 1.36s/it] {'loss': 2.5032, 'learning_rate': 1.1323090885517956e-07, 'epoch': 13.89} + 87%|████████▋ | 53740/61904 [4:45:09<3:05:41, 1.36s/it] 87%|████████▋ | 53741/61904 [4:45:10<3:06:45, 1.37s/it] 87%|████████▋ | 53742/61904 [4:45:11<3:04:52, 1.36s/it] 87%|████████▋ | 53743/61904 [4:45:13<3:01:59, 1.34s/it] 87%|████████▋ | 53744/61904 [4:45:14<3:05:01, 1.36s/it] 87%|████████▋ | 53745/61904 [4:45:15<3:03:20, 1.35s/it] 87%|████████▋ | 53746/61904 [4:45:17<3:06:09, 1.37s/it] 87%|████████▋ | 53747/61904 [4:45:18<3:05:37, 1.37s/it] 87%|████████▋ | 53748/61904 [4:45:19<3:00:23, 1.33s/it] 87%|████████▋ | 53749/61904 [4:45:21<3:01:48, 1.34s/it] 87%|████████▋ | 53750/61904 [4:45:22<3:03:05, 1.35s/it] 87%|████████▋ | 53751/61904 [4:45:24<3:10:19, 1.40s/it] 87%|████████▋ | 53752/61904 [4:45:25<3:13:05, 1.42s/it] 87%|████████▋ | 53753/61904 [4:45:27<3:16:51, 1.45s/it] 87%|████████▋ | 53754/61904 [4:45:28<3:19:06, 1.47s/it] 87%|████████▋ | 53755/61904 [4:45:29<3:13:27, 1.42s/it] 87%|████████▋ | 53756/61904 [4:45:31<3:17:04, 1.45s/it] 87%|████████▋ | 53757/61904 [4:45:32<3:11:18, 1.41s/it] 87%|████████▋ | 53758/61904 [4:45:34<3:13:41, 1.43s/it] 87%|████████▋ | 53759/61904 [4:45:35<3:13:45, 1.43s/it] 87%|████████▋ | 53760/61904 [4:45:36<3:07:28, 1.38s/it] {'loss': 2.4601, 'learning_rate': 1.1319849604563723e-07, 'epoch': 13.89} + 87%|████████▋ | 53760/61904 [4:45:36<3:07:28, 1.38s/it] 87%|████████▋ | 53761/61904 [4:45:38<3:01:36, 1.34s/it] 87%|████████▋ | 53762/61904 [4:45:39<3:06:35, 1.38s/it] 87%|████████▋ | 53763/61904 [4:45:40<3:05:31, 1.37s/it] 87%|████████▋ | 53764/61904 [4:45:42<3:12:18, 1.42s/it] 87%|████████▋ | 53765/61904 [4:45:43<3:06:35, 1.38s/it] 87%|████████▋ | 53766/61904 [4:45:45<3:10:35, 1.41s/it] 87%|████████▋ | 53767/61904 [4:45:46<3:12:20, 1.42s/it] 87%|████████▋ | 53768/61904 [4:45:48<3:10:18, 1.40s/it] 87%|████████▋ | 53769/61904 [4:45:49<3:10:29, 1.40s/it] 87%|████████▋ | 53770/61904 [4:45:50<3:12:02, 1.42s/it] 87%|████████▋ | 53771/61904 [4:45:52<3:13:33, 1.43s/it] 87%|████████▋ | 53772/61904 [4:45:53<3:08:36, 1.39s/it] 87%|████████▋ | 53773/61904 [4:45:55<3:14:50, 1.44s/it] 87%|████████▋ | 53774/61904 [4:45:56<3:18:47, 1.47s/it] 87%|████████▋ | 53775/61904 [4:45:57<3:09:57, 1.40s/it] 87%|████████▋ | 53776/61904 [4:45:59<3:09:46, 1.40s/it] 87%|████████▋ | 53777/61904 [4:46:00<3:06:27, 1.38s/it] 87%|████████▋ | 53778/61904 [4:46:02<3:04:14, 1.36s/it] 87%|████████▋ | 53779/61904 [4:46:03<3:09:00, 1.40s/it] 87%|████████▋ | 53780/61904 [4:46:04<3:08:49, 1.39s/it] {'loss': 2.3983, 'learning_rate': 1.1316608323609492e-07, 'epoch': 13.9} + 87%|████████▋ | 53780/61904 [4:46:04<3:08:49, 1.39s/it] 87%|████████▋ | 53781/61904 [4:46:06<3:06:12, 1.38s/it] 87%|████████▋ | 53782/61904 [4:46:07<3:02:21, 1.35s/it] 87%|████████▋ | 53783/61904 [4:46:08<3:06:41, 1.38s/it] 87%|████████▋ | 53784/61904 [4:46:10<3:06:02, 1.37s/it] 87%|████████▋ | 53785/61904 [4:46:11<3:09:59, 1.40s/it] 87%|████████▋ | 53786/61904 [4:46:13<3:09:35, 1.40s/it] 87%|████████▋ | 53787/61904 [4:46:14<3:08:20, 1.39s/it] 87%|████████▋ | 53788/61904 [4:46:15<3:10:28, 1.41s/it] 87%|████████▋ | 53789/61904 [4:46:17<3:05:32, 1.37s/it] 87%|████████▋ | 53790/61904 [4:46:18<3:08:20, 1.39s/it] 87%|████████▋ | 53791/61904 [4:46:20<3:04:15, 1.36s/it] 87%|████████▋ | 53792/61904 [4:46:21<3:02:21, 1.35s/it] 87%|████████▋ | 53793/61904 [4:46:22<3:06:21, 1.38s/it] 87%|████████▋ | 53794/61904 [4:46:24<3:10:54, 1.41s/it] 87%|████████▋ | 53795/61904 [4:46:25<3:07:04, 1.38s/it] 87%|████████▋ | 53796/61904 [4:46:26<3:05:03, 1.37s/it] 87%|████████▋ | 53797/61904 [4:46:28<3:06:45, 1.38s/it] 87%|████████▋ | 53798/61904 [4:46:29<3:09:44, 1.40s/it] 87%|████████▋ | 53799/61904 [4:46:31<3:10:51, 1.41s/it] 87%|████████▋ | 53800/61904 [4:46:32<3:06:12, 1.38s/it] {'loss': 2.3913, 'learning_rate': 1.1313367042655258e-07, 'epoch': 13.91} + 87%|████████▋ | 53800/61904 [4:46:32<3:06:12, 1.38s/it] 87%|████████▋ | 53801/61904 [4:46:33<3:06:20, 1.38s/it] 87%|████████▋ | 53802/61904 [4:46:35<3:05:35, 1.37s/it] 87%|████████▋ | 53803/61904 [4:46:36<3:01:36, 1.35s/it] 87%|████████▋ | 53804/61904 [4:46:37<3:01:13, 1.34s/it] 87%|████████▋ | 53805/61904 [4:46:39<3:00:45, 1.34s/it] 87%|████████▋ | 53806/61904 [4:46:40<3:03:18, 1.36s/it] 87%|████████▋ | 53807/61904 [4:46:41<3:02:31, 1.35s/it] 87%|████████▋ | 53808/61904 [4:46:43<3:05:56, 1.38s/it] 87%|████████▋ | 53809/61904 [4:46:44<3:03:47, 1.36s/it] 87%|████████▋ | 53810/61904 [4:46:46<3:04:03, 1.36s/it] 87%|████████▋ | 53811/61904 [4:46:47<3:06:21, 1.38s/it] 87%|████████▋ | 53812/61904 [4:46:48<3:01:29, 1.35s/it] 87%|████████▋ | 53813/61904 [4:46:50<2:58:19, 1.32s/it] 87%|████████▋ | 53814/61904 [4:46:51<3:02:30, 1.35s/it] 87%|████████▋ | 53815/61904 [4:46:52<3:02:52, 1.36s/it] 87%|████████▋ | 53816/61904 [4:46:54<3:03:29, 1.36s/it] 87%|████████▋ | 53817/61904 [4:46:55<3:01:08, 1.34s/it] 87%|████████▋ | 53818/61904 [4:46:56<3:02:29, 1.35s/it] 87%|████████▋ | 53819/61904 [4:46:58<3:07:24, 1.39s/it] 87%|████████▋ | 53820/61904 [4:46:59<3:06:51, 1.39s/it] {'loss': 2.4417, 'learning_rate': 1.1310125761701024e-07, 'epoch': 13.91} + 87%|████████▋ | 53820/61904 [4:46:59<3:06:51, 1.39s/it] 87%|████████▋ | 53821/61904 [4:47:01<3:05:02, 1.37s/it] 87%|████████▋ | 53822/61904 [4:47:02<3:03:53, 1.37s/it] 87%|████████▋ | 53823/61904 [4:47:03<2:58:08, 1.32s/it] 87%|████████▋ | 53824/61904 [4:47:05<2:59:31, 1.33s/it] 87%|████████▋ | 53825/61904 [4:47:06<2:57:24, 1.32s/it] 87%|████████▋ | 53826/61904 [4:47:07<3:05:38, 1.38s/it] 87%|████████▋ | 53827/61904 [4:47:09<3:10:44, 1.42s/it] 87%|████████▋ | 53828/61904 [4:47:10<3:19:24, 1.48s/it] 87%|████████▋ | 53829/61904 [4:47:12<3:10:43, 1.42s/it] 87%|████████▋ | 53830/61904 [4:47:13<3:10:12, 1.41s/it] 87%|████████▋ | 53831/61904 [4:47:14<3:05:22, 1.38s/it] 87%|████████▋ | 53832/61904 [4:47:16<3:08:21, 1.40s/it] 87%|████████▋ | 53833/61904 [4:47:17<3:02:27, 1.36s/it] 87%|████████▋ | 53834/61904 [4:47:18<3:02:55, 1.36s/it] 87%|████████▋ | 53835/61904 [4:47:20<3:08:36, 1.40s/it] 87%|████████▋ | 53836/61904 [4:47:22<3:22:25, 1.51s/it] 87%|████████▋ | 53837/61904 [4:47:23<3:16:57, 1.46s/it] 87%|████████▋ | 53838/61904 [4:47:25<3:19:52, 1.49s/it] 87%|████████▋ | 53839/61904 [4:47:26<3:11:39, 1.43s/it] 87%|████████▋ | 53840/61904 [4:47:27<3:15:57, 1.46s/it] {'loss': 2.422, 'learning_rate': 1.1306884480746793e-07, 'epoch': 13.92} + 87%|████████▋ | 53840/61904 [4:47:27<3:15:57, 1.46s/it] 87%|████████▋ | 53841/61904 [4:47:29<3:12:53, 1.44s/it] 87%|████████▋ | 53842/61904 [4:47:30<3:10:37, 1.42s/it] 87%|████████▋ | 53843/61904 [4:47:32<3:07:17, 1.39s/it] 87%|████████▋ | 53844/61904 [4:47:33<3:07:49, 1.40s/it] 87%|████████▋ | 53845/61904 [4:47:34<3:10:38, 1.42s/it] 87%|████████▋ | 53846/61904 [4:47:36<3:04:17, 1.37s/it] 87%|████████▋ | 53847/61904 [4:47:37<3:07:30, 1.40s/it] 87%|████████▋ | 53848/61904 [4:47:39<3:05:56, 1.38s/it] 87%|████████▋ | 53849/61904 [4:47:40<3:01:05, 1.35s/it] 87%|████████▋ | 53850/61904 [4:47:41<3:02:55, 1.36s/it] 87%|████████▋ | 53851/61904 [4:47:43<3:10:09, 1.42s/it] 87%|████████▋ | 53852/61904 [4:47:44<3:11:47, 1.43s/it] 87%|████████▋ | 53853/61904 [4:47:46<3:20:51, 1.50s/it] 87%|████████▋ | 53854/61904 [4:47:47<3:11:34, 1.43s/it] 87%|████████▋ | 53855/61904 [4:47:48<3:06:02, 1.39s/it] 87%|████████▋ | 53856/61904 [4:47:50<3:03:56, 1.37s/it] 87%|████████▋ | 53857/61904 [4:47:51<3:02:32, 1.36s/it] 87%|████████▋ | 53858/61904 [4:47:52<3:03:44, 1.37s/it] 87%|████████▋ | 53859/61904 [4:47:54<3:05:07, 1.38s/it] 87%|████████▋ | 53860/61904 [4:47:55<3:01:58, 1.36s/it] {'loss': 2.4629, 'learning_rate': 1.1303643199792559e-07, 'epoch': 13.92} + 87%|████████▋ | 53860/61904 [4:47:55<3:01:58, 1.36s/it] 87%|████████▋ | 53861/61904 [4:47:57<3:02:35, 1.36s/it] 87%|████████▋ | 53862/61904 [4:47:58<3:03:09, 1.37s/it] 87%|████████▋ | 53863/61904 [4:47:59<3:05:45, 1.39s/it] 87%|████████▋ | 53864/61904 [4:48:01<3:09:47, 1.42s/it] 87%|████████▋ | 53865/61904 [4:48:02<3:10:56, 1.43s/it] 87%|████████▋ | 53866/61904 [4:48:04<3:11:24, 1.43s/it] 87%|████████▋ | 53867/61904 [4:48:05<3:09:14, 1.41s/it] 87%|████████▋ | 53868/61904 [4:48:06<3:03:35, 1.37s/it] 87%|████████▋ | 53869/61904 [4:48:08<3:05:51, 1.39s/it] 87%|████████▋ | 53870/61904 [4:48:09<3:05:37, 1.39s/it] 87%|████████▋ | 53871/61904 [4:48:11<3:10:14, 1.42s/it] 87%|████████▋ | 53872/61904 [4:48:12<3:15:02, 1.46s/it] 87%|████████▋ | 53873/61904 [4:48:14<3:32:11, 1.59s/it] 87%|████████▋ | 53874/61904 [4:48:15<3:20:42, 1.50s/it] 87%|████████▋ | 53875/61904 [4:48:17<3:13:39, 1.45s/it] 87%|████████▋ | 53876/61904 [4:48:18<3:07:25, 1.40s/it] 87%|████████▋ | 53877/61904 [4:48:19<3:05:49, 1.39s/it] 87%|████████▋ | 53878/61904 [4:48:21<3:00:39, 1.35s/it] 87%|████████▋ | 53879/61904 [4:48:22<3:00:23, 1.35s/it] 87%|████████▋ | 53880/61904 [4:48:23<3:03:42, 1.37s/it] {'loss': 2.4489, 'learning_rate': 1.1300401918838325e-07, 'epoch': 13.93} + 87%|████████▋ | 53880/61904 [4:48:23<3:03:42, 1.37s/it] 87%|████████▋ | 53881/61904 [4:48:25<3:01:15, 1.36s/it] 87%|████████▋ | 53882/61904 [4:48:26<2:59:53, 1.35s/it] 87%|████████▋ | 53883/61904 [4:48:27<3:00:01, 1.35s/it] 87%|████████▋ | 53884/61904 [4:48:29<3:00:44, 1.35s/it] 87%|████████▋ | 53885/61904 [4:48:30<3:01:26, 1.36s/it] 87%|████████▋ | 53886/61904 [4:48:32<3:03:00, 1.37s/it] 87%|████████▋ | 53887/61904 [4:48:33<3:05:21, 1.39s/it] 87%|████████▋ | 53888/61904 [4:48:34<3:04:44, 1.38s/it] 87%|████████▋ | 53889/61904 [4:48:36<3:01:26, 1.36s/it] 87%|████████▋ | 53890/61904 [4:48:37<3:01:48, 1.36s/it] 87%|████████▋ | 53891/61904 [4:48:38<2:59:46, 1.35s/it] 87%|████████▋ | 53892/61904 [4:48:40<2:58:33, 1.34s/it] 87%|████████▋ | 53893/61904 [4:48:41<3:01:47, 1.36s/it] 87%|████████▋ | 53894/61904 [4:48:42<2:59:26, 1.34s/it] 87%|████████▋ | 53895/61904 [4:48:44<3:01:46, 1.36s/it] 87%|████████▋ | 53896/61904 [4:48:45<3:04:44, 1.38s/it] 87%|████████▋ | 53897/61904 [4:48:46<3:00:14, 1.35s/it] 87%|████████▋ | 53898/61904 [4:48:48<3:01:01, 1.36s/it] 87%|████████▋ | 53899/61904 [4:48:49<3:03:43, 1.38s/it] 87%|████████▋ | 53900/61904 [4:48:51<3:02:29, 1.37s/it] {'loss': 2.4243, 'learning_rate': 1.1297160637884091e-07, 'epoch': 13.93} + 87%|████████▋ | 53900/61904 [4:48:51<3:02:29, 1.37s/it] 87%|████████▋ | 53901/61904 [4:48:52<3:01:53, 1.36s/it] 87%|████████▋ | 53902/61904 [4:48:53<3:01:40, 1.36s/it] 87%|████████▋ | 53903/61904 [4:48:55<3:00:32, 1.35s/it] 87%|████████▋ | 53904/61904 [4:48:56<3:11:28, 1.44s/it] 87%|████████▋ | 53905/61904 [4:48:58<3:11:15, 1.43s/it] 87%|████████▋ | 53906/61904 [4:48:59<3:08:36, 1.41s/it] 87%|████████▋ | 53907/61904 [4:49:00<3:07:51, 1.41s/it] 87%|████████▋ | 53908/61904 [4:49:02<3:13:50, 1.45s/it] 87%|████████▋ | 53909/61904 [4:49:03<3:10:40, 1.43s/it] 87%|████████▋ | 53910/61904 [4:49:05<3:05:52, 1.40s/it] 87%|████████▋ | 53911/61904 [4:49:06<3:10:22, 1.43s/it] 87%|████████▋ | 53912/61904 [4:49:08<3:06:29, 1.40s/it] 87%|████████▋ | 53913/61904 [4:49:09<3:05:40, 1.39s/it] 87%|████████▋ | 53914/61904 [4:49:10<3:04:49, 1.39s/it] 87%|████████▋ | 53915/61904 [4:49:12<3:01:55, 1.37s/it] 87%|████████▋ | 53916/61904 [4:49:13<2:58:40, 1.34s/it] 87%|████████▋ | 53917/61904 [4:49:14<3:01:47, 1.37s/it] 87%|████████▋ | 53918/61904 [4:49:16<2:59:09, 1.35s/it] 87%|████████▋ | 53919/61904 [4:49:17<3:01:01, 1.36s/it] 87%|████████▋ | 53920/61904 [4:49:18<2:58:17, 1.34s/it] {'loss': 2.4241, 'learning_rate': 1.129391935692986e-07, 'epoch': 13.94} + 87%|████████▋ | 53920/61904 [4:49:18<2:58:17, 1.34s/it] 87%|████████▋ | 53921/61904 [4:49:20<2:55:46, 1.32s/it] 87%|████████▋ | 53922/61904 [4:49:21<2:59:36, 1.35s/it] 87%|████████▋ | 53923/61904 [4:49:22<3:00:02, 1.35s/it] 87%|████████▋ | 53924/61904 [4:49:24<2:59:16, 1.35s/it] 87%|████████▋ | 53925/61904 [4:49:25<2:59:13, 1.35s/it] 87%|████████▋ | 53926/61904 [4:49:27<3:03:51, 1.38s/it] 87%|████████▋ | 53927/61904 [4:49:28<3:07:22, 1.41s/it] 87%|████████▋ | 53928/61904 [4:49:29<3:03:22, 1.38s/it] 87%|████████▋ | 53929/61904 [4:49:31<3:03:43, 1.38s/it] 87%|████████▋ | 53930/61904 [4:49:32<3:03:18, 1.38s/it] 87%|████████▋ | 53931/61904 [4:49:33<3:03:30, 1.38s/it] 87%|████████▋ | 53932/61904 [4:49:35<3:05:41, 1.40s/it] 87%|████████▋ | 53933/61904 [4:49:36<3:00:36, 1.36s/it] 87%|████████▋ | 53934/61904 [4:49:37<2:57:15, 1.33s/it] 87%|████████▋ | 53935/61904 [4:49:39<2:58:31, 1.34s/it] 87%|████████▋ | 53936/61904 [4:49:40<2:54:48, 1.32s/it] 87%|████████▋ | 53937/61904 [4:49:41<2:54:32, 1.31s/it] 87%|████████▋ | 53938/61904 [4:49:43<2:55:36, 1.32s/it] 87%|████████▋ | 53939/61904 [4:49:44<2:57:13, 1.34s/it] 87%|████████▋ | 53940/61904 [4:49:46<3:07:53, 1.42s/it] {'loss': 2.4386, 'learning_rate': 1.1290678075975626e-07, 'epoch': 13.94} + 87%|████████▋ | 53940/61904 [4:49:46<3:07:53, 1.42s/it] 87%|████████▋ | 53941/61904 [4:49:47<3:07:45, 1.41s/it] 87%|████████▋ | 53942/61904 [4:49:48<3:03:56, 1.39s/it] 87%|████████▋ | 53943/61904 [4:49:50<3:04:28, 1.39s/it] 87%|████████▋ | 53944/61904 [4:49:51<3:10:48, 1.44s/it] 87%|████████▋ | 53945/61904 [4:49:53<3:06:45, 1.41s/it] 87%|████████▋ | 53946/61904 [4:49:54<3:04:07, 1.39s/it] 87%|████████▋ | 53947/61904 [4:49:56<3:11:52, 1.45s/it] 87%|████████▋ | 53948/61904 [4:49:57<3:06:33, 1.41s/it] 87%|████████▋ | 53949/61904 [4:49:58<3:08:04, 1.42s/it] 87%|████████▋ | 53950/61904 [4:50:00<3:06:34, 1.41s/it] 87%|████████▋ | 53951/61904 [4:50:01<3:08:27, 1.42s/it] 87%|████████▋ | 53952/61904 [4:50:03<3:11:43, 1.45s/it] 87%|████████▋ | 53953/61904 [4:50:04<3:06:37, 1.41s/it] 87%|████████▋ | 53954/61904 [4:50:05<3:07:29, 1.41s/it] 87%|████████▋ | 53955/61904 [4:50:07<3:07:19, 1.41s/it] 87%|████████▋ | 53956/61904 [4:50:08<3:00:07, 1.36s/it] 87%|████████▋ | 53957/61904 [4:50:10<3:10:08, 1.44s/it] 87%|████████▋ | 53958/61904 [4:50:11<3:04:28, 1.39s/it] 87%|████████▋ | 53959/61904 [4:50:12<3:01:00, 1.37s/it] 87%|████████▋ | 53960/61904 [4:50:14<3:07:14, 1.41s/it] {'loss': 2.4117, 'learning_rate': 1.1287436795021392e-07, 'epoch': 13.95} + 87%|████████▋ | 53960/61904 [4:50:14<3:07:14, 1.41s/it] 87%|████████▋ | 53961/61904 [4:50:15<3:07:28, 1.42s/it] 87%|████████▋ | 53962/61904 [4:50:17<3:01:54, 1.37s/it] 87%|████████▋ | 53963/61904 [4:50:18<3:04:52, 1.40s/it] 87%|████████▋ | 53964/61904 [4:50:19<3:01:21, 1.37s/it] 87%|████████▋ | 53965/61904 [4:50:21<3:00:42, 1.37s/it] 87%|████████▋ | 53966/61904 [4:50:22<2:58:59, 1.35s/it] 87%|████████▋ | 53967/61904 [4:50:23<2:54:38, 1.32s/it] 87%|████████▋ | 53968/61904 [4:50:25<2:53:59, 1.32s/it] 87%|████████▋ | 53969/61904 [4:50:26<2:51:40, 1.30s/it] 87%|████████▋ | 53970/61904 [4:50:27<2:51:18, 1.30s/it] 87%|████████▋ | 53971/61904 [4:50:28<2:56:09, 1.33s/it] 87%|████████▋ | 53972/61904 [4:50:30<2:54:27, 1.32s/it] 87%|████████▋ | 53973/61904 [4:50:31<2:49:49, 1.28s/it] 87%|████████▋ | 53974/61904 [4:50:32<2:54:00, 1.32s/it] 87%|████████▋ | 53975/61904 [4:50:34<3:03:14, 1.39s/it] 87%|████████▋ | 53976/61904 [4:50:36<3:13:12, 1.46s/it] 87%|████████▋ | 53977/61904 [4:50:37<3:14:00, 1.47s/it] 87%|████████▋ | 53978/61904 [4:50:38<3:06:30, 1.41s/it] 87%|████████▋ | 53979/61904 [4:50:40<3:09:45, 1.44s/it] 87%|████████▋ | 53980/61904 [4:50:41<3:06:58, 1.42s/it] {'loss': 2.4356, 'learning_rate': 1.1284195514067159e-07, 'epoch': 13.95} + 87%|████████▋ | 53980/61904 [4:50:41<3:06:58, 1.42s/it] 87%|████████▋ | 53981/61904 [4:50:43<3:02:55, 1.39s/it] 87%|████████▋ | 53982/61904 [4:50:44<2:59:48, 1.36s/it] 87%|████████▋ | 53983/61904 [4:50:45<3:04:17, 1.40s/it] 87%|████████▋ | 53984/61904 [4:50:47<3:02:21, 1.38s/it] 87%|████████▋ | 53985/61904 [4:50:48<2:59:07, 1.36s/it] 87%|████████▋ | 53986/61904 [4:50:49<3:02:43, 1.38s/it] 87%|████████▋ | 53987/61904 [4:50:51<3:04:20, 1.40s/it] 87%|████████▋ | 53988/61904 [4:50:52<3:02:44, 1.39s/it] 87%|████████▋ | 53989/61904 [4:50:54<3:04:23, 1.40s/it] 87%|████████▋ | 53990/61904 [4:50:55<3:04:35, 1.40s/it] 87%|████████▋ | 53991/61904 [4:50:56<3:03:12, 1.39s/it] 87%|████████▋ | 53992/61904 [4:50:58<3:01:20, 1.38s/it] 87%|████████▋ | 53993/61904 [4:50:59<3:06:06, 1.41s/it] 87%|████████▋ | 53994/61904 [4:51:01<3:04:39, 1.40s/it] 87%|████████▋ | 53995/61904 [4:51:02<3:01:00, 1.37s/it] 87%|████████▋ | 53996/61904 [4:51:03<3:05:38, 1.41s/it] 87%|████████▋ | 53997/61904 [4:51:05<3:05:35, 1.41s/it] 87%|████████▋ | 53998/61904 [4:51:06<3:07:14, 1.42s/it] 87%|████████▋ | 53999/61904 [4:51:08<3:01:30, 1.38s/it] 87%|████████▋ | 54000/61904 [4:51:09<3:11:08, 1.45s/it] {'loss': 2.4823, 'learning_rate': 1.1280954233112928e-07, 'epoch': 13.96} + 87%|████████▋ | 54000/61904 [4:51:09<3:11:08, 1.45s/it] 87%|████████▋ | 54001/61904 [4:51:11<3:10:31, 1.45s/it] 87%|████████▋ | 54002/61904 [4:51:12<3:09:46, 1.44s/it] 87%|████████▋ | 54003/61904 [4:51:13<3:03:30, 1.39s/it] 87%|████████▋ | 54004/61904 [4:51:15<3:04:54, 1.40s/it] 87%|████████▋ | 54005/61904 [4:51:16<3:05:47, 1.41s/it] 87%|████████▋ | 54006/61904 [4:51:17<3:02:30, 1.39s/it] 87%|████████▋ | 54007/61904 [4:51:19<3:04:40, 1.40s/it] 87%|████████▋ | 54008/61904 [4:51:20<3:01:36, 1.38s/it] 87%|████████▋ | 54009/61904 [4:51:22<2:58:08, 1.35s/it] 87%|████████▋ | 54010/61904 [4:51:23<3:01:04, 1.38s/it] 87%|████████▋ | 54011/61904 [4:51:24<3:02:46, 1.39s/it] 87%|████████▋ | 54012/61904 [4:51:26<2:59:56, 1.37s/it] 87%|████████▋ | 54013/61904 [4:51:27<2:55:34, 1.33s/it] 87%|████████▋ | 54014/61904 [4:51:28<2:53:46, 1.32s/it] 87%|████████▋ | 54015/61904 [4:51:30<2:55:00, 1.33s/it] 87%|████████▋ | 54016/61904 [4:51:31<2:57:03, 1.35s/it] 87%|████████▋ | 54017/61904 [4:51:32<2:59:57, 1.37s/it] 87%|████████▋ | 54018/61904 [4:51:34<2:56:31, 1.34s/it] 87%|████████▋ | 54019/61904 [4:51:35<3:02:25, 1.39s/it] 87%|████████▋ | 54020/61904 [4:51:37<3:03:48, 1.40s/it] {'loss': 2.4368, 'learning_rate': 1.1277712952158694e-07, 'epoch': 13.96} + 87%|���███████▋ | 54020/61904 [4:51:37<3:03:48, 1.40s/it] 87%|████████▋ | 54021/61904 [4:51:38<3:05:41, 1.41s/it] 87%|████████▋ | 54022/61904 [4:51:39<3:05:23, 1.41s/it] 87%|████████▋ | 54023/61904 [4:51:41<3:07:13, 1.43s/it] 87%|████████▋ | 54024/61904 [4:51:42<3:08:15, 1.43s/it] 87%|████████▋ | 54025/61904 [4:51:44<3:04:38, 1.41s/it] 87%|████████▋ | 54026/61904 [4:51:45<3:10:12, 1.45s/it] 87%|████████▋ | 54027/61904 [4:51:47<3:05:43, 1.41s/it] 87%|████████▋ | 54028/61904 [4:51:48<3:02:47, 1.39s/it] 87%|████████▋ | 54029/61904 [4:51:49<3:02:01, 1.39s/it] 87%|████████▋ | 54030/61904 [4:51:51<3:02:52, 1.39s/it] 87%|████████▋ | 54031/61904 [4:51:52<3:03:18, 1.40s/it] 87%|████████▋ | 54032/61904 [4:51:53<3:01:16, 1.38s/it] 87%|████████▋ | 54033/61904 [4:51:55<2:58:20, 1.36s/it] 87%|████████▋ | 54034/61904 [4:51:56<3:00:29, 1.38s/it] 87%|████████▋ | 54035/61904 [4:51:57<2:55:34, 1.34s/it] 87%|████████▋ | 54036/61904 [4:51:59<2:51:02, 1.30s/it] 87%|████████▋ | 54037/61904 [4:52:00<2:57:15, 1.35s/it] 87%|████████▋ | 54038/61904 [4:52:02<2:58:32, 1.36s/it] 87%|████████▋ | 54039/61904 [4:52:03<2:57:35, 1.35s/it] 87%|████████▋ | 54040/61904 [4:52:04<2:55:42, 1.34s/it] {'loss': 2.4806, 'learning_rate': 1.127447167120446e-07, 'epoch': 13.97} + 87%|████████▋ | 54040/61904 [4:52:04<2:55:42, 1.34s/it] 87%|████████▋ | 54041/61904 [4:52:06<3:02:04, 1.39s/it] 87%|████████▋ | 54042/61904 [4:52:07<2:58:25, 1.36s/it] 87%|████████▋ | 54043/61904 [4:52:08<3:01:07, 1.38s/it] 87%|████████▋ | 54044/61904 [4:52:10<2:58:40, 1.36s/it] 87%|████████▋ | 54045/61904 [4:52:11<2:57:20, 1.35s/it] 87%|████████▋ | 54046/61904 [4:52:13<3:03:54, 1.40s/it] 87%|████████▋ | 54047/61904 [4:52:14<3:01:54, 1.39s/it] 87%|████████▋ | 54048/61904 [4:52:15<3:00:23, 1.38s/it] 87%|████████▋ | 54049/61904 [4:52:17<3:05:11, 1.41s/it] 87%|████████▋ | 54050/61904 [4:52:18<3:07:03, 1.43s/it] 87%|████████▋ | 54051/61904 [4:52:20<3:03:38, 1.40s/it] 87%|████████▋ | 54052/61904 [4:52:21<3:10:31, 1.46s/it] 87%|████████▋ | 54053/61904 [4:52:22<3:04:44, 1.41s/it] 87%|████████▋ | 54054/61904 [4:52:24<3:06:25, 1.42s/it] 87%|████████▋ | 54055/61904 [4:52:25<3:05:01, 1.41s/it] 87%|████████▋ | 54056/61904 [4:52:27<3:02:42, 1.40s/it] 87%|████████▋ | 54057/61904 [4:52:28<3:06:29, 1.43s/it] 87%|████████▋ | 54058/61904 [4:52:30<3:05:34, 1.42s/it] 87%|████████▋ | 54059/61904 [4:52:31<2:59:43, 1.37s/it] 87%|████████▋ | 54060/61904 [4:52:32<3:02:04, 1.39s/it] {'loss': 2.3614, 'learning_rate': 1.1271230390250226e-07, 'epoch': 13.97} + 87%|████████▋ | 54060/61904 [4:52:32<3:02:04, 1.39s/it] 87%|████████▋ | 54061/61904 [4:52:34<3:05:58, 1.42s/it] 87%|████████▋ | 54062/61904 [4:52:35<3:03:06, 1.40s/it] 87%|████████▋ | 54063/61904 [4:52:36<3:02:23, 1.40s/it] 87%|████████▋ | 54064/61904 [4:52:38<3:01:02, 1.39s/it] 87%|████████▋ | 54065/61904 [4:52:39<2:57:47, 1.36s/it] 87%|████████▋ | 54066/61904 [4:52:40<2:56:51, 1.35s/it] 87%|████████▋ | 54067/61904 [4:52:42<2:54:54, 1.34s/it] 87%|████████▋ | 54068/61904 [4:52:43<2:56:15, 1.35s/it] 87%|████████▋ | 54069/61904 [4:52:45<3:12:40, 1.48s/it] 87%|████████▋ | 54070/61904 [4:52:46<3:13:26, 1.48s/it] 87%|████████▋ | 54071/61904 [4:52:48<3:12:05, 1.47s/it] 87%|████████▋ | 54072/61904 [4:52:49<3:04:48, 1.42s/it] 87%|████████▋ | 54073/61904 [4:52:50<2:57:52, 1.36s/it] 87%|████████▋ | 54074/61904 [4:52:52<2:57:16, 1.36s/it] 87%|████████▋ | 54075/61904 [4:52:53<2:56:13, 1.35s/it] 87%|████████▋ | 54076/61904 [4:52:55<3:02:51, 1.40s/it] 87%|████████▋ | 54077/61904 [4:52:56<2:56:38, 1.35s/it] 87%|████████▋ | 54078/61904 [4:52:57<3:00:06, 1.38s/it] 87%|████████▋ | 54079/61904 [4:52:59<3:07:17, 1.44s/it] 87%|████████▋ | 54080/61904 [4:53:00<2:58:14, 1.37s/it] {'loss': 2.4549, 'learning_rate': 1.1267989109295995e-07, 'epoch': 13.98} + 87%|████████▋ | 54080/61904 [4:53:00<2:58:14, 1.37s/it] 87%|████████▋ | 54081/61904 [4:53:01<2:56:56, 1.36s/it] 87%|████████▋ | 54082/61904 [4:53:03<3:01:29, 1.39s/it] 87%|████████▋ | 54083/61904 [4:53:04<2:53:51, 1.33s/it] 87%|████████▋ | 54084/61904 [4:53:05<2:53:55, 1.33s/it] 87%|████████▋ | 54085/61904 [4:53:07<2:54:54, 1.34s/it] 87%|████████▋ | 54086/61904 [4:53:08<2:54:58, 1.34s/it] 87%|████████▋ | 54087/61904 [4:53:09<2:55:50, 1.35s/it] 87%|████████▋ | 54088/61904 [4:53:11<2:55:26, 1.35s/it] 87%|████████▋ | 54089/61904 [4:53:12<2:57:13, 1.36s/it] 87%|████████▋ | 54090/61904 [4:53:13<2:53:18, 1.33s/it] 87%|████████▋ | 54091/61904 [4:53:15<2:59:45, 1.38s/it] 87%|████████▋ | 54092/61904 [4:53:16<3:02:59, 1.41s/it] 87%|████████▋ | 54093/61904 [4:53:18<2:57:46, 1.37s/it] 87%|████████▋ | 54094/61904 [4:53:19<3:03:46, 1.41s/it] 87%|████████▋ | 54095/61904 [4:53:21<2:59:05, 1.38s/it] 87%|████████▋ | 54096/61904 [4:53:22<2:58:43, 1.37s/it] 87%|████████▋ | 54097/61904 [4:53:23<3:01:05, 1.39s/it] 87%|████████▋ | 54098/61904 [4:53:25<3:01:59, 1.40s/it] 87%|████████▋ | 54099/61904 [4:53:26<3:00:35, 1.39s/it] 87%|████████▋ | 54100/61904 [4:53:27<2:53:42, 1.34s/it] {'loss': 2.4648, 'learning_rate': 1.1264747828341761e-07, 'epoch': 13.98} + 87%|████████▋ | 54100/61904 [4:53:27<2:53:42, 1.34s/it] 87%|████████▋ | 54101/61904 [4:53:29<2:52:09, 1.32s/it] 87%|████████▋ | 54102/61904 [4:53:30<2:53:00, 1.33s/it] 87%|████████▋ | 54103/61904 [4:53:31<2:52:37, 1.33s/it] 87%|████████▋ | 54104/61904 [4:53:33<2:59:36, 1.38s/it] 87%|████████▋ | 54105/61904 [4:53:34<3:04:21, 1.42s/it] 87%|████████▋ | 54106/61904 [4:53:36<3:00:08, 1.39s/it] 87%|████████▋ | 54107/61904 [4:53:37<3:02:36, 1.41s/it] 87%|████████▋ | 54108/61904 [4:53:38<2:59:42, 1.38s/it] 87%|████████▋ | 54109/61904 [4:53:40<3:00:34, 1.39s/it] 87%|████████▋ | 54110/61904 [4:53:41<2:56:01, 1.36s/it] 87%|████████▋ | 54111/61904 [4:53:42<2:55:59, 1.35s/it] 87%|████████▋ | 54112/61904 [4:53:44<2:54:21, 1.34s/it] 87%|████████▋ | 54113/61904 [4:53:45<2:55:41, 1.35s/it] 87%|████████▋ | 54114/61904 [4:53:47<3:00:00, 1.39s/it] 87%|████████▋ | 54115/61904 [4:53:48<3:03:51, 1.42s/it] 87%|████████▋ | 54116/61904 [4:53:49<2:58:26, 1.37s/it] 87%|████████▋ | 54117/61904 [4:53:51<2:57:18, 1.37s/it] 87%|████████▋ | 54118/61904 [4:53:52<2:55:55, 1.36s/it] 87%|████████▋ | 54119/61904 [4:53:53<2:54:51, 1.35s/it] 87%|████████▋ | 54120/61904 [4:53:55<2:55:53, 1.36s/it] {'loss': 2.482, 'learning_rate': 1.1261506547387527e-07, 'epoch': 13.99} + 87%|████████▋ | 54120/61904 [4:53:55<2:55:53, 1.36s/it] 87%|████████▋ | 54121/61904 [4:53:56<2:58:24, 1.38s/it] 87%|████████▋ | 54122/61904 [4:53:58<2:59:47, 1.39s/it] 87%|████████▋ | 54123/61904 [4:53:59<2:58:55, 1.38s/it] 87%|████████▋ | 54124/61904 [4:54:00<2:53:18, 1.34s/it] 87%|████████▋ | 54125/61904 [4:54:02<2:59:21, 1.38s/it] 87%|████████▋ | 54126/61904 [4:54:03<2:59:10, 1.38s/it] 87%|████████▋ | 54127/61904 [4:54:04<2:57:55, 1.37s/it] 87%|████████▋ | 54128/61904 [4:54:06<3:01:03, 1.40s/it] 87%|████████▋ | 54129/61904 [4:54:07<3:00:44, 1.39s/it] 87%|████████▋ | 54130/61904 [4:54:09<2:56:58, 1.37s/it] 87%|████████▋ | 54131/61904 [4:54:10<2:52:59, 1.34s/it] 87%|████████▋ | 54132/61904 [4:54:11<2:51:34, 1.32s/it] 87%|████████▋ | 54133/61904 [4:54:12<2:48:58, 1.30s/it] 87%|████████▋ | 54134/61904 [4:54:14<2:53:01, 1.34s/it] 87%|████████▋ | 54135/61904 [4:54:15<2:57:50, 1.37s/it] 87%|████████▋ | 54136/61904 [4:54:17<2:59:59, 1.39s/it] 87%|████████▋ | 54137/61904 [4:54:18<2:55:50, 1.36s/it] 87%|████████▋ | 54138/61904 [4:54:19<2:57:45, 1.37s/it] 87%|████████▋ | 54139/61904 [4:54:21<2:54:21, 1.35s/it] 87%|████████▋ | 54140/61904 [4:54:22<2:53:36, 1.34s/it] {'loss': 2.4405, 'learning_rate': 1.1258265266433296e-07, 'epoch': 13.99} + 87%|████████▋ | 54140/61904 [4:54:22<2:53:36, 1.34s/it] 87%|████████▋ | 54141/61904 [4:54:23<2:53:02, 1.34s/it] 87%|████████▋ | 54142/61904 [4:54:25<2:53:36, 1.34s/it] 87%|████████▋ | 54143/61904 [4:54:26<2:51:01, 1.32s/it] 87%|████████▋ | 54144/61904 [4:54:27<2:49:02, 1.31s/it] 87%|████████▋ | 54145/61904 [4:54:29<2:53:25, 1.34s/it] 87%|████████▋ | 54146/61904 [4:54:30<2:53:26, 1.34s/it] 87%|████████▋ | 54147/61904 [4:54:31<2:57:44, 1.37s/it] 87%|████████▋ | 54148/61904 [4:54:33<2:55:47, 1.36s/it] 87%|████████▋ | 54149/61904 [4:54:34<2:58:12, 1.38s/it] 87%|████████▋ | 54150/61904 [4:54:36<3:00:04, 1.39s/it] 87%|████████▋ | 54151/61904 [4:54:37<2:56:18, 1.36s/it] 87%|████████▋ | 54152/61904 [4:54:38<2:54:03, 1.35s/it] 87%|████████▋ | 54153/61904 [4:54:40<2:55:03, 1.36s/it] 87%|████████▋ | 54154/61904 [4:54:41<2:55:54, 1.36s/it] 87%|████████▋ | 54155/61904 [4:54:42<2:57:20, 1.37s/it] 87%|████████▋ | 54156/61904 [4:54:44<2:56:18, 1.37s/it] 87%|████████▋ | 54157/61904 [4:54:45<2:53:19, 1.34s/it] 87%|████████▋ | 54158/61904 [4:54:46<2:52:09, 1.33s/it] 87%|████████▋ | 54159/61904 [4:54:48<2:52:16, 1.33s/it] 87%|████████▋ | 54160/61904 [4:54:49<2:59:48, 1.39s/it] {'loss': 2.4125, 'learning_rate': 1.1255023985479062e-07, 'epoch': 14.0} + 87%|████████▋ | 54160/61904 [4:54:49<2:59:48, 1.39s/it] 87%|████████▋ | 54161/61904 [4:54:51<3:02:34, 1.41s/it] 87%|████████▋ | 54162/61904 [4:54:52<2:57:35, 1.38s/it] 87%|████████▋ | 54163/61904 [4:54:53<2:56:21, 1.37s/it] 87%|████████▋ | 54164/61904 [4:54:55<2:55:32, 1.36s/it] 87%|████████▋ | 54165/61904 [4:54:56<2:54:50, 1.36s/it] 88%|████████▊ | 54166/61904 [4:54:57<2:58:49, 1.39s/it] 88%|████████▊ | 54167/61904 [4:54:59<3:04:07, 1.43s/it]Generation Kwargs: +{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5} + + 0%| | 0/861 [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} +/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() + 88%|████████▊ | 54168/61904 [5:08:44<534:04:07, 248.53s/it] 88%|████████▊ | 54169/61904 [5:08:46<374:48:53, 174.45s/it] 88%|████████▊ | 54170/61904 [5:08:47<263:14:41, 122.53s/it] 88%|████████▊ | 54171/61904 [5:08:49<185:15:09, 86.24s/it] 88%|████████▊ | 54172/61904 [5:08:50<130:38:14, 60.82s/it] 88%|████████▊ | 54173/61904 [5:08:51<92:19:45, 42.99s/it] 88%|████████▊ | 54174/61904 [5:08:53<65:32:20, 30.52s/it] 88%|████████▊ | 54175/61904 [5:08:54<46:50:58, 21.82s/it] 88%|████████▊ | 54176/61904 [5:08:56<33:38:28, 15.67s/it] 88%|████████▊ | 54177/61904 [5:08:57<24:28:27, 11.40s/it] 88%|████████▊ | 54178/61904 [5:08:59<18:07:15, 8.44s/it] 88%|████████▊ | 54179/61904 [5:09:00<13:40:09, 6.37s/it] 88%|████████▊ | 54180/61904 [5:09:02<10:42:22, 4.99s/it] {'loss': 2.497, 'learning_rate': 1.1251782704524828e-07, 'epoch': 14.0} + 88%|████████▊ | 54180/61904 [5:09:02<10:42:22, 4.99s/it] 88%|████████▊ | 54181/61904 [5:09:03<8:25:20, 3.93s/it] 88%|████████▊ | 54182/61904 [5:09:05<6:49:32, 3.18s/it] 88%|████████▊ | 54183/61904 [5:09:06<5:42:11, 2.66s/it] 88%|████████▊ | 54184/61904 [5:09:08<5:06:09, 2.38s/it] 88%|████████▊ | 54185/61904 [5:09:10<4:33:41, 2.13s/it] 88%|████████▊ | 54186/61904 [5:09:11<4:11:36, 1.96s/it] 88%|████████▊ | 54187/61904 [5:09:13<3:55:33, 1.83s/it] 88%|████████▊ | 54188/61904 [5:09:14<3:39:33, 1.71s/it] 88%|████████▊ | 54189/61904 [5:09:16<3:30:47, 1.64s/it] 88%|████████▊ | 54190/61904 [5:09:17<3:27:39, 1.62s/it] 88%|████████▊ | 54191/61904 [5:09:19<3:22:56, 1.58s/it] 88%|████████▊ | 54192/61904 [5:09:20<3:15:02, 1.52s/it] 88%|████████▊ | 54193/61904 [5:09:21<3:12:42, 1.50s/it] 88%|████████▊ | 54194/61904 [5:09:23<3:09:46, 1.48s/it] 88%|████████▊ | 54195/61904 [5:09:24<3:10:43, 1.48s/it] 88%|████████▊ | 54196/61904 [5:09:26<3:18:27, 1.54s/it] 88%|████████▊ | 54197/61904 [5:09:28<3:20:10, 1.56s/it] 88%|████████▊ | 54198/61904 [5:09:29<3:14:42, 1.52s/it] 88%|████████▊ | 54199/61904 [5:09:30<3:06:05, 1.45s/it] 88%|████████▊ | 54200/61904 [5:09:32<3:05:54, 1.45s/it] {'loss': 2.4448, 'learning_rate': 1.1248541423570595e-07, 'epoch': 14.01} + 88%|████████▊ | 54200/61904 [5:09:32<3:05:54, 1.45s/it] 88%|████████▊ | 54201/61904 [5:09:33<3:05:20, 1.44s/it] 88%|████████▊ | 54202/61904 [5:09:35<3:03:01, 1.43s/it] 88%|████████▊ | 54203/61904 [5:09:36<3:02:41, 1.42s/it] 88%|████████▊ | 54204/61904 [5:09:38<3:05:54, 1.45s/it] 88%|████████▊ | 54205/61904 [5:09:39<3:12:12, 1.50s/it] 88%|████████▊ | 54206/61904 [5:09:41<3:05:05, 1.44s/it] 88%|████████▊ | 54207/61904 [5:09:42<3:06:32, 1.45s/it] 88%|████████▊ | 54208/61904 [5:09:43<3:07:56, 1.47s/it] 88%|████████▊ | 54209/61904 [5:09:45<3:09:16, 1.48s/it] 88%|████████▊ | 54210/61904 [5:09:47<3:11:24, 1.49s/it] 88%|████████▊ | 54211/61904 [5:09:48<3:08:58, 1.47s/it] 88%|████████▊ | 54212/61904 [5:09:49<3:08:25, 1.47s/it] 88%|████████▊ | 54213/61904 [5:09:51<3:08:12, 1.47s/it] 88%|████████▊ | 54214/61904 [5:09:52<3:09:40, 1.48s/it] \ No newline at end of file