diff --git "a/run-2024-10-28T03:01:14+00:00.log" "b/run-2024-10-28T03:01:14+00:00.log" --- "a/run-2024-10-28T03:01:14+00:00.log" +++ "b/run-2024-10-28T03:01:14+00:00.log" @@ -2175,4 +2175,1071 @@ Non-default generation parameters: {'max_length': 200, 'early_stopping': True, ' self.pid = os.fork() 44%|████▍ | 27085/61904 [3:37:53<2857:28:59, 295.44s/it] 44%|████▍ | 27086/61904 [3:37:55<2004:28:46, 207.25s/it] 44%|████▍ | 27087/61904 [3:37:56<1407:50:39, 145.57s/it] 44%|████▍ | 27088/61904 [3:37:58<989:26:33, 102.31s/it] 44%|████▍ | 27089/61904 [3:37:59<696:22:38, 72.01s/it] 44%|████▍ | 27090/61904 [3:38:00<491:43:59, 50.85s/it] 44%|████▍ | 27091/61904 [3:38:02<348:18:32, 36.02s/it] 44%|████▍ | 27092/61904 [3:38:03<248:10:32, 25.66s/it] 44%|████▍ | 27093/61904 [3:38:05<178:13:52, 18.43s/it] 44%|████▍ | 27094/61904 [3:38:06<129:21:49, 13.38s/it] 44%|████▍ | 27095/61904 [3:38:08<94:16:47, 9.75s/it] 44%|████▍ | 27096/61904 [3:38:09<69:56:48, 7.23s/it] 44%|████▍ | 27097/61904 [3:38:10<52:56:02, 5.47s/it] 44%|████▍ | 27098/61904 [3:38:12<41:11:24, 4.26s/it] 44%|████▍ | 27099/61904 [3:38:13<32:54:53, 3.40s/it] 44%|████▍ | 27100/61904 [3:38:15<26:57:11, 2.79s/it] {'loss': 2.5946, 'learning_rate': 1.5640477116556463e-07, 'epoch': 7.0} 44%|████▍ | 27100/61904 [3:38:15<26:57:11, 2.79s/it] 44%|████▍ | 27101/61904 [3:38:16<23:16:18, 2.41s/it] 44%|████▍ | 27102/61904 [3:38:18<20:31:31, 2.12s/it] 44%|████▍ | 27103/61904 [3:38:19<18:15:45, 1.89s/it] 44%|████▍ | 27104/61904 [3:38:20<16:56:09, 1.75s/it] 44%|████▍ | 27105/61904 [3:38:22<15:39:52, 1.62s/it] 44%|████▍ | 27106/61904 [3:38:23<15:14:02, 1.58s/it] 44%|████▍ | 27107/61904 [3:38:25<15:10:19, 1.57s/it] 44%|████▍ | 27108/61904 [3:38:26<14:57:27, 1.55s/it] 44%|████▍ | 27109/61904 [3:38:28<14:45:04, 1.53s/it] 44%|████▍ | 27110/61904 [3:38:29<14:49:20, 1.53s/it] 44%|████▍ | 27111/61904 [3:38:31<14:20:05, 1.48s/it] 44%|████▍ | 27112/61904 [3:38:32<14:52:46, 1.54s/it] 44%|████▍ | 27113/61904 [3:38:34<14:52:45, 1.54s/it] 44%|████▍ | 27114/61904 [3:38:35<14:38:30, 1.52s/it] 44%|████▍ | 27115/61904 [3:38:37<14:13:24, 1.47s/it] 44%|████▍ | 27116/61904 [3:38:38<13:48:49, 1.43s/it] 44%|████▍ | 27117/61904 [3:38:39<14:09:28, 1.47s/it] 44%|████▍ | 27118/61904 [3:38:41<14:01:29, 1.45s/it] 44%|████▍ | 27119/61904 [3:38:42<14:17:23, 1.48s/it] 44%|████▍ | 27120/61904 [3:38:44<14:35:04, 1.51s/it] {'loss': 2.5941, 'learning_rate': 1.563723583560223e-07, 'epoch': 7.01} - 44%|████▍ | 27120/61904 [3:38:44<14:35:04, 1.51s/it] 44%|████▍ | 27121/61904 [3:38:45<14:09:07, 1.46s/it] 44%|████▍ | 27122/61904 [3:38:47<13:57:14, 1.44s/it] 44%|████▍ | 27123/61904 [3:38:48<13:34:48, 1.41s/it] 44%|████▍ | 27124/61904 [3:38:50<13:38:20, 1.41s/it] 44%|████▍ | 27125/61904 [3:38:51<13:40:00, 1.41s/it] 44%|████▍ | 27126/61904 [3:38:52<13:49:56, 1.43s/it] 44%|████▍ | 27127/61904 [3:38:54<13:45:40, 1.42s/it] \ No newline at end of file + 44%|████▍ | 27120/61904 [3:38:44<14:35:04, 1.51s/it] 44%|████▍ | 27121/61904 [3:38:45<14:09:07, 1.46s/it] 44%|████▍ | 27122/61904 [3:38:47<13:57:14, 1.44s/it] 44%|████▍ | 27123/61904 [3:38:48<13:34:48, 1.41s/it] 44%|████▍ | 27124/61904 [3:38:50<13:38:20, 1.41s/it] 44%|████▍ | 27125/61904 [3:38:51<13:40:00, 1.41s/it] 44%|████▍ | 27126/61904 [3:38:52<13:49:56, 1.43s/it] 44%|████▍ | 27127/61904 [3:38:54<13:45:40, 1.42s/it] 44%|████▍ | 27128/61904 [3:38:55<13:48:35, 1.43s/it] 44%|████▍ | 27129/61904 [3:38:57<13:39:53, 1.41s/it] 44%|████▍ | 27130/61904 [3:38:58<13:53:30, 1.44s/it] 44%|████▍ | 27131/61904 [3:39:00<14:18:11, 1.48s/it] 44%|████▍ | 27132/61904 [3:39:01<14:14:25, 1.47s/it] 44%|████▍ | 27133/61904 [3:39:03<13:49:32, 1.43s/it] 44%|████▍ | 27134/61904 [3:39:04<13:51:20, 1.43s/it] 44%|████▍ | 27135/61904 [3:39:06<14:17:37, 1.48s/it] 44%|████▍ | 27136/61904 [3:39:07<14:14:21, 1.47s/it] 44%|████▍ | 27137/61904 [3:39:08<13:57:29, 1.45s/it] 44%|████▍ | 27138/61904 [3:39:10<14:06:20, 1.46s/it] 44%|████▍ | 27139/61904 [3:39:11<13:53:49, 1.44s/it] 44%|████▍ | 27140/61904 [3:39:13<14:24:43, 1.49s/it] {'loss': 2.5895, 'learning_rate': 1.5633994554647995e-07, 'epoch': 7.01} + 44%|████▍ | 27140/61904 [3:39:13<14:24:43, 1.49s/it] 44%|████▍ | 27141/61904 [3:39:14<14:13:13, 1.47s/it] 44%|████▍ | 27142/61904 [3:39:16<14:18:57, 1.48s/it] 44%|████▍ | 27143/61904 [3:39:17<13:56:36, 1.44s/it] 44%|████▍ | 27144/61904 [3:39:19<13:45:33, 1.43s/it] 44%|████▍ | 27145/61904 [3:39:20<14:12:53, 1.47s/it] 44%|████▍ | 27146/61904 [3:39:21<13:45:49, 1.43s/it] 44%|████▍ | 27147/61904 [3:39:23<13:33:03, 1.40s/it] 44%|████▍ | 27148/61904 [3:39:24<13:32:15, 1.40s/it] 44%|████▍ | 27149/61904 [3:39:26<13:24:11, 1.39s/it] 44%|████▍ | 27150/61904 [3:39:27<14:02:46, 1.45s/it] 44%|████▍ | 27151/61904 [3:39:28<13:33:23, 1.40s/it] 44%|████▍ | 27152/61904 [3:39:30<13:32:27, 1.40s/it] 44%|████▍ | 27153/61904 [3:39:31<13:56:06, 1.44s/it] 44%|████▍ | 27154/61904 [3:39:33<13:44:08, 1.42s/it] 44%|████▍ | 27155/61904 [3:39:34<13:43:09, 1.42s/it] 44%|████▍ | 27156/61904 [3:39:36<13:57:53, 1.45s/it] 44%|████▍ | 27157/61904 [3:39:37<14:05:07, 1.46s/it] 44%|████▍ | 27158/61904 [3:39:39<13:55:04, 1.44s/it] 44%|████▍ | 27159/61904 [3:39:40<14:05:45, 1.46s/it] 44%|████▍ | 27160/61904 [3:39:42<14:04:09, 1.46s/it] {'loss': 2.5711, 'learning_rate': 1.5630753273693764e-07, 'epoch': 7.02} + 44%|████▍ | 27160/61904 [3:39:42<14:04:09, 1.46s/it] 44%|████▍ | 27161/61904 [3:39:43<14:36:49, 1.51s/it] 44%|████▍ | 27162/61904 [3:39:45<14:21:19, 1.49s/it] 44%|████▍ | 27163/61904 [3:39:46<14:01:41, 1.45s/it] 44%|████▍ | 27164/61904 [3:39:47<14:10:11, 1.47s/it] 44%|████▍ | 27165/61904 [3:39:49<13:49:24, 1.43s/it] 44%|████▍ | 27166/61904 [3:39:50<14:04:14, 1.46s/it] 44%|████▍ | 27167/61904 [3:39:52<13:44:18, 1.42s/it] 44%|████▍ | 27168/61904 [3:39:53<13:34:55, 1.41s/it] 44%|████▍ | 27169/61904 [3:39:54<13:22:20, 1.39s/it] 44%|████▍ | 27170/61904 [3:39:56<13:30:11, 1.40s/it] 44%|████▍ | 27171/61904 [3:39:57<13:35:04, 1.41s/it] 44%|████▍ | 27172/61904 [3:39:59<13:21:37, 1.38s/it] 44%|████▍ | 27173/61904 [3:40:00<13:17:39, 1.38s/it] 44%|████▍ | 27174/61904 [3:40:01<13:36:16, 1.41s/it] 44%|████▍ | 27175/61904 [3:40:03<13:52:00, 1.44s/it] 44%|████▍ | 27176/61904 [3:40:04<13:39:15, 1.42s/it] 44%|████▍ | 27177/61904 [3:40:06<13:50:22, 1.43s/it] 44%|████▍ | 27178/61904 [3:40:07<13:25:03, 1.39s/it] 44%|████▍ | 27179/61904 [3:40:08<13:25:19, 1.39s/it] 44%|████▍ | 27180/61904 [3:40:10<13:30:16, 1.40s/it] {'loss': 2.6074, 'learning_rate': 1.562751199273953e-07, 'epoch': 7.02} + 44%|████▍ | 27180/61904 [3:40:10<13:30:16, 1.40s/it] 44%|████▍ | 27181/61904 [3:40:11<13:57:10, 1.45s/it] 44%|████▍ | 27182/61904 [3:40:13<13:41:09, 1.42s/it] 44%|████▍ | 27183/61904 [3:40:14<14:00:37, 1.45s/it] 44%|████▍ | 27184/61904 [3:40:16<13:42:16, 1.42s/it] 44%|████▍ | 27185/61904 [3:40:17<13:53:43, 1.44s/it] 44%|████▍ | 27186/61904 [3:40:19<13:56:30, 1.45s/it] 44%|████▍ | 27187/61904 [3:40:20<13:20:31, 1.38s/it] 44%|████▍ | 27188/61904 [3:40:21<13:20:25, 1.38s/it] 44%|████▍ | 27189/61904 [3:40:23<13:18:01, 1.38s/it] 44%|████▍ | 27190/61904 [3:40:24<13:19:59, 1.38s/it] 44%|████▍ | 27191/61904 [3:40:26<13:47:57, 1.43s/it] 44%|████▍ | 27192/61904 [3:40:27<13:51:47, 1.44s/it] 44%|████▍ | 27193/61904 [3:40:29<14:09:31, 1.47s/it] 44%|████▍ | 27194/61904 [3:40:30<14:23:00, 1.49s/it] 44%|████▍ | 27195/61904 [3:40:31<14:07:12, 1.46s/it] 44%|████▍ | 27196/61904 [3:40:33<14:09:13, 1.47s/it] 44%|████▍ | 27197/61904 [3:40:34<14:18:43, 1.48s/it] 44%|████▍ | 27198/61904 [3:40:36<13:58:47, 1.45s/it] 44%|████▍ | 27199/61904 [3:40:37<14:01:41, 1.46s/it] 44%|████▍ | 27200/61904 [3:40:39<13:43:33, 1.42s/it] {'loss': 2.5763, 'learning_rate': 1.5624270711785296e-07, 'epoch': 7.03} + 44%|████▍ | 27200/61904 [3:40:39<13:43:33, 1.42s/it] 44%|████▍ | 27201/61904 [3:40:40<13:28:43, 1.40s/it] 44%|████▍ | 27202/61904 [3:40:41<13:30:45, 1.40s/it] 44%|████▍ | 27203/61904 [3:40:43<13:37:47, 1.41s/it] 44%|████▍ | 27204/61904 [3:40:44<13:21:35, 1.39s/it] 44%|████▍ | 27205/61904 [3:40:46<13:21:41, 1.39s/it] 44%|████▍ | 27206/61904 [3:40:47<13:14:23, 1.37s/it] 44%|████▍ | 27207/61904 [3:40:48<13:16:28, 1.38s/it] 44%|████▍ | 27208/61904 [3:40:50<13:33:36, 1.41s/it] 44%|████▍ | 27209/61904 [3:40:51<13:26:14, 1.39s/it] 44%|████▍ | 27210/61904 [3:40:53<13:44:21, 1.43s/it] 44%|████▍ | 27211/61904 [3:40:54<13:44:54, 1.43s/it] 44%|████▍ | 27212/61904 [3:40:55<13:33:36, 1.41s/it] 44%|████▍ | 27213/61904 [3:40:57<13:29:26, 1.40s/it] 44%|████▍ | 27214/61904 [3:40:58<13:25:45, 1.39s/it] 44%|████▍ | 27215/61904 [3:40:59<13:01:04, 1.35s/it] 44%|████▍ | 27216/61904 [3:41:01<13:30:15, 1.40s/it] 44%|████▍ | 27217/61904 [3:41:02<13:29:39, 1.40s/it] 44%|████▍ | 27218/61904 [3:41:04<13:51:18, 1.44s/it] 44%|████▍ | 27219/61904 [3:41:05<14:02:49, 1.46s/it] 44%|████▍ | 27220/61904 [3:41:07<13:51:58, 1.44s/it] {'loss': 2.5656, 'learning_rate': 1.5621029430831062e-07, 'epoch': 7.04} + 44%|████▍ | 27220/61904 [3:41:07<13:51:58, 1.44s/it] 44%|████▍ | 27221/61904 [3:41:08<13:45:21, 1.43s/it] 44%|████▍ | 27222/61904 [3:41:10<13:36:27, 1.41s/it] 44%|████▍ | 27223/61904 [3:41:11<13:37:26, 1.41s/it] 44%|████▍ | 27224/61904 [3:41:12<13:15:48, 1.38s/it] 44%|████▍ | 27225/61904 [3:41:14<13:23:29, 1.39s/it] 44%|████▍ | 27226/61904 [3:41:15<13:17:00, 1.38s/it] 44%|████▍ | 27227/61904 [3:41:16<13:11:09, 1.37s/it] 44%|████▍ | 27228/61904 [3:41:18<13:15:09, 1.38s/it] 44%|████▍ | 27229/61904 [3:41:19<13:19:42, 1.38s/it] 44%|████▍ | 27230/61904 [3:41:20<13:05:28, 1.36s/it] 44%|████▍ | 27231/61904 [3:41:22<13:04:34, 1.36s/it] 44%|████▍ | 27232/61904 [3:41:23<13:13:26, 1.37s/it] 44%|████▍ | 27233/61904 [3:41:25<13:35:52, 1.41s/it] 44%|████▍ | 27234/61904 [3:41:26<13:16:43, 1.38s/it] 44%|████▍ | 27235/61904 [3:41:27<13:07:01, 1.36s/it] 44%|████▍ | 27236/61904 [3:41:29<13:08:20, 1.36s/it] 44%|████▍ | 27237/61904 [3:41:30<13:43:40, 1.43s/it] 44%|████▍ | 27238/61904 [3:41:32<13:36:03, 1.41s/it] 44%|████▍ | 27239/61904 [3:41:33<13:31:14, 1.40s/it] 44%|████▍ | 27240/61904 [3:41:34<13:23:15, 1.39s/it] {'loss': 2.576, 'learning_rate': 1.561778814987683e-07, 'epoch': 7.04} + 44%|████▍ | 27240/61904 [3:41:34<13:23:15, 1.39s/it] 44%|████▍ | 27241/61904 [3:41:36<13:04:29, 1.36s/it] 44%|████▍ | 27242/61904 [3:41:37<12:38:02, 1.31s/it] 44%|████▍ | 27243/61904 [3:41:39<13:30:12, 1.40s/it] 44%|████▍ | 27244/61904 [3:41:40<13:37:33, 1.42s/it] 44%|████▍ | 27245/61904 [3:41:41<13:27:26, 1.40s/it] 44%|████▍ | 27246/61904 [3:41:43<13:26:51, 1.40s/it] 44%|████▍ | 27247/61904 [3:41:44<13:29:01, 1.40s/it] 44%|████▍ | 27248/61904 [3:41:46<13:37:45, 1.42s/it] 44%|████▍ | 27249/61904 [3:41:47<13:21:36, 1.39s/it] 44%|████▍ | 27250/61904 [3:41:48<13:23:21, 1.39s/it] 44%|████▍ | 27251/61904 [3:41:50<13:20:15, 1.39s/it] 44%|████▍ | 27252/61904 [3:41:51<13:13:22, 1.37s/it] 44%|████▍ | 27253/61904 [3:41:52<13:14:40, 1.38s/it] 44%|████▍ | 27254/61904 [3:41:54<12:58:07, 1.35s/it] 44%|████▍ | 27255/61904 [3:41:55<13:07:28, 1.36s/it] 44%|████▍ | 27256/61904 [3:41:57<13:21:40, 1.39s/it] 44%|████▍ | 27257/61904 [3:41:58<13:27:14, 1.40s/it] 44%|████▍ | 27258/61904 [3:41:59<13:38:00, 1.42s/it] 44%|████▍ | 27259/61904 [3:42:01<13:22:57, 1.39s/it] 44%|████▍ | 27260/61904 [3:42:02<13:42:44, 1.42s/it] {'loss': 2.6323, 'learning_rate': 1.5614546868922597e-07, 'epoch': 7.05} + 44%|████▍ | 27260/61904 [3:42:02<13:42:44, 1.42s/it] 44%|████▍ | 27261/61904 [3:42:04<13:15:06, 1.38s/it] 44%|████▍ | 27262/61904 [3:42:05<13:03:04, 1.36s/it] 44%|████▍ | 27263/61904 [3:42:06<13:02:15, 1.35s/it] 44%|████▍ | 27264/61904 [3:42:08<13:06:04, 1.36s/it] 44%|████▍ | 27265/61904 [3:42:09<13:38:38, 1.42s/it] 44%|████▍ | 27266/61904 [3:42:11<13:39:14, 1.42s/it] 44%|████▍ | 27267/61904 [3:42:12<13:31:54, 1.41s/it] 44%|████▍ | 27268/61904 [3:42:13<13:02:09, 1.35s/it] 44%|████▍ | 27269/61904 [3:42:14<12:46:20, 1.33s/it] 44%|████▍ | 27270/61904 [3:42:16<12:29:46, 1.30s/it] 44%|████▍ | 27271/61904 [3:42:17<12:54:40, 1.34s/it] 44%|████▍ | 27272/61904 [3:42:18<12:44:34, 1.32s/it] 44%|████▍ | 27273/61904 [3:42:20<12:47:13, 1.33s/it] 44%|████▍ | 27274/61904 [3:42:21<13:03:52, 1.36s/it] 44%|████▍ | 27275/61904 [3:42:23<13:13:41, 1.38s/it] 44%|████▍ | 27276/61904 [3:42:24<13:04:50, 1.36s/it] 44%|████▍ | 27277/61904 [3:42:25<13:06:31, 1.36s/it] 44%|████▍ | 27278/61904 [3:42:27<13:34:13, 1.41s/it] 44%|████▍ | 27279/61904 [3:42:28<13:10:37, 1.37s/it] 44%|████▍ | 27280/61904 [3:42:29<12:55:28, 1.34s/it] {'loss': 2.6121, 'learning_rate': 1.5611305587968364e-07, 'epoch': 7.05} + 44%|████▍ | 27280/61904 [3:42:29<12:55:28, 1.34s/it] 44%|████▍ | 27281/61904 [3:42:31<13:18:38, 1.38s/it] 44%|████▍ | 27282/61904 [3:42:32<13:11:50, 1.37s/it] 44%|████▍ | 27283/61904 [3:42:34<13:27:47, 1.40s/it] 44%|████▍ | 27284/61904 [3:42:35<13:13:21, 1.37s/it] 44%|████▍ | 27285/61904 [3:42:36<12:54:47, 1.34s/it] 44%|████▍ | 27286/61904 [3:42:38<13:49:28, 1.44s/it] 44%|████▍ | 27287/61904 [3:42:39<13:36:54, 1.42s/it] 44%|████▍ | 27288/61904 [3:42:41<14:05:14, 1.47s/it] 44%|████▍ | 27289/61904 [3:42:42<13:26:55, 1.40s/it] 44%|████▍ | 27290/61904 [3:42:43<13:18:53, 1.38s/it] 44%|████▍ | 27291/61904 [3:42:45<13:33:42, 1.41s/it] 44%|████▍ | 27292/61904 [3:42:46<13:16:51, 1.38s/it] 44%|████▍ | 27293/61904 [3:42:48<13:18:07, 1.38s/it] 44%|████▍ | 27294/61904 [3:42:49<13:05:06, 1.36s/it] 44%|████▍ | 27295/61904 [3:42:51<14:03:20, 1.46s/it] 44%|████▍ | 27296/61904 [3:42:52<14:28:53, 1.51s/it] 44%|████▍ | 27297/61904 [3:42:54<14:29:11, 1.51s/it] 44%|████▍ | 27298/61904 [3:42:55<13:56:16, 1.45s/it] 44%|████▍ | 27299/61904 [3:42:56<13:28:08, 1.40s/it] 44%|████▍ | 27300/61904 [3:42:58<13:09:44, 1.37s/it] {'loss': 2.5962, 'learning_rate': 1.560806430701413e-07, 'epoch': 7.06} + 44%|████▍ | 27300/61904 [3:42:58<13:09:44, 1.37s/it] 44%|████▍ | 27301/61904 [3:42:59<13:02:38, 1.36s/it] 44%|████▍ | 27302/61904 [3:43:00<13:05:09, 1.36s/it] 44%|████▍ | 27303/61904 [3:43:02<13:12:33, 1.37s/it] 44%|████▍ | 27304/61904 [3:43:03<13:08:25, 1.37s/it] 44%|████▍ | 27305/61904 [3:43:04<13:00:11, 1.35s/it] 44%|████▍ | 27306/61904 [3:43:06<12:56:26, 1.35s/it] 44%|████▍ | 27307/61904 [3:43:07<12:53:57, 1.34s/it] 44%|████▍ | 27308/61904 [3:43:08<13:10:04, 1.37s/it] 44%|████▍ | 27309/61904 [3:43:10<13:18:43, 1.39s/it] 44%|████▍ | 27310/61904 [3:43:11<13:42:20, 1.43s/it] 44%|████▍ | 27311/61904 [3:43:13<13:30:40, 1.41s/it] 44%|████▍ | 27312/61904 [3:43:14<13:13:32, 1.38s/it] 44%|████▍ | 27313/61904 [3:43:15<13:01:25, 1.36s/it] 44%|████▍ | 27314/61904 [3:43:17<12:58:38, 1.35s/it] 44%|████▍ | 27315/61904 [3:43:18<13:00:09, 1.35s/it] 44%|████▍ | 27316/61904 [3:43:19<12:48:04, 1.33s/it] 44%|████▍ | 27317/61904 [3:43:21<12:51:17, 1.34s/it] 44%|████▍ | 27318/61904 [3:43:22<12:51:00, 1.34s/it] 44%|████▍ | 27319/61904 [3:43:24<13:19:43, 1.39s/it] 44%|████▍ | 27320/61904 [3:43:25<13:24:38, 1.40s/it] {'loss': 2.614, 'learning_rate': 1.5604823026059899e-07, 'epoch': 7.06} + 44%|████▍ | 27320/61904 [3:43:25<13:24:38, 1.40s/it] 44%|████▍ | 27321/61904 [3:43:26<13:24:17, 1.40s/it] 44%|████▍ | 27322/61904 [3:43:28<13:18:30, 1.39s/it] 44%|████▍ | 27323/61904 [3:43:29<13:22:54, 1.39s/it] 44%|████▍ | 27324/61904 [3:43:30<13:13:29, 1.38s/it] 44%|████▍ | 27325/61904 [3:43:32<13:13:23, 1.38s/it] 44%|████▍ | 27326/61904 [3:43:33<12:50:50, 1.34s/it] 44%|████▍ | 27327/61904 [3:43:35<13:09:22, 1.37s/it] 44%|████▍ | 27328/61904 [3:43:36<13:04:20, 1.36s/it] 44%|████▍ | 27329/61904 [3:43:37<12:42:57, 1.32s/it] 44%|████▍ | 27330/61904 [3:43:38<12:42:16, 1.32s/it] 44%|████▍ | 27331/61904 [3:43:40<13:01:46, 1.36s/it] 44%|████▍ | 27332/61904 [3:43:41<13:26:48, 1.40s/it] 44%|████▍ | 27333/61904 [3:43:43<13:13:58, 1.38s/it] 44%|████▍ | 27334/61904 [3:43:44<13:41:54, 1.43s/it] 44%|████▍ | 27335/61904 [3:43:46<13:12:17, 1.38s/it] 44%|████▍ | 27336/61904 [3:43:47<12:46:54, 1.33s/it] 44%|████▍ | 27337/61904 [3:43:48<12:42:44, 1.32s/it] 44%|████▍ | 27338/61904 [3:43:49<12:46:43, 1.33s/it] 44%|████▍ | 27339/61904 [3:43:51<13:21:39, 1.39s/it] 44%|████▍ | 27340/61904 [3:43:52<13:11:45, 1.37s/it] {'loss': 2.5828, 'learning_rate': 1.5601581745105665e-07, 'epoch': 7.07} + 44%|████▍ | 27340/61904 [3:43:52<13:11:45, 1.37s/it] 44%|████▍ | 27341/61904 [3:43:54<13:17:06, 1.38s/it] 44%|████▍ | 27342/61904 [3:43:55<13:04:52, 1.36s/it] 44%|████▍ | 27343/61904 [3:43:56<13:01:24, 1.36s/it] 44%|████▍ | 27344/61904 [3:43:58<13:03:02, 1.36s/it] 44%|████▍ | 27345/61904 [3:43:59<12:50:24, 1.34s/it] 44%|████▍ | 27346/61904 [3:44:00<12:38:08, 1.32s/it] 44%|████▍ | 27347/61904 [3:44:02<12:34:45, 1.31s/it] 44%|████▍ | 27348/61904 [3:44:03<12:45:02, 1.33s/it] 44%|████▍ | 27349/61904 [3:44:04<12:53:45, 1.34s/it] 44%|████▍ | 27350/61904 [3:44:06<12:44:18, 1.33s/it] 44%|████▍ | 27351/61904 [3:44:07<12:41:00, 1.32s/it] 44%|████▍ | 27352/61904 [3:44:08<12:42:25, 1.32s/it] 44%|████▍ | 27353/61904 [3:44:10<12:48:04, 1.33s/it] 44%|████▍ | 27354/61904 [3:44:11<12:47:46, 1.33s/it] 44%|████▍ | 27355/61904 [3:44:12<12:39:58, 1.32s/it] 44%|████▍ | 27356/61904 [3:44:14<12:46:23, 1.33s/it] 44%|████▍ | 27357/61904 [3:44:15<13:00:11, 1.36s/it] 44%|████▍ | 27358/61904 [3:44:16<13:30:30, 1.41s/it] 44%|████▍ | 27359/61904 [3:44:18<13:03:51, 1.36s/it] 44%|████▍ | 27360/61904 [3:44:19<12:54:43, 1.35s/it] {'loss': 2.6366, 'learning_rate': 1.559834046415143e-07, 'epoch': 7.07} + 44%|████▍ | 27360/61904 [3:44:19<12:54:43, 1.35s/it] 44%|████▍ | 27361/61904 [3:44:21<13:23:19, 1.40s/it] 44%|████▍ | 27362/61904 [3:44:22<13:32:17, 1.41s/it] 44%|████▍ | 27363/61904 [3:44:23<13:34:50, 1.42s/it] 44%|████▍ | 27364/61904 [3:44:25<13:29:09, 1.41s/it] 44%|████▍ | 27365/61904 [3:44:26<13:14:36, 1.38s/it] 44%|████▍ | 27366/61904 [3:44:27<12:56:28, 1.35s/it] 44%|████▍ | 27367/61904 [3:44:29<12:53:34, 1.34s/it] 44%|████▍ | 27368/61904 [3:44:30<12:54:14, 1.35s/it] 44%|████▍ | 27369/61904 [3:44:31<12:55:37, 1.35s/it] 44%|████▍ | 27370/61904 [3:44:33<12:44:29, 1.33s/it] 44%|████▍ | 27371/61904 [3:44:34<12:56:21, 1.35s/it] 44%|████▍ | 27372/61904 [3:44:35<12:50:43, 1.34s/it] 44%|████▍ | 27373/61904 [3:44:37<12:50:31, 1.34s/it] 44%|████▍ | 27374/61904 [3:44:38<13:23:16, 1.40s/it] 44%|████▍ | 27375/61904 [3:44:40<13:05:26, 1.36s/it] 44%|████▍ | 27376/61904 [3:44:41<13:42:24, 1.43s/it] 44%|████▍ | 27377/61904 [3:44:43<13:30:31, 1.41s/it] 44%|████▍ | 27378/61904 [3:44:44<13:20:15, 1.39s/it] 44%|████▍ | 27379/61904 [3:44:45<13:04:44, 1.36s/it] 44%|████▍ | 27380/61904 [3:44:47<13:27:05, 1.40s/it] {'loss': 2.5704, 'learning_rate': 1.55950991831972e-07, 'epoch': 7.08} + 44%|████▍ | 27380/61904 [3:44:47<13:27:05, 1.40s/it] 44%|████▍ | 27381/61904 [3:44:48<13:18:39, 1.39s/it] 44%|████▍ | 27382/61904 [3:44:49<13:25:41, 1.40s/it] 44%|████▍ | 27383/61904 [3:44:51<13:36:27, 1.42s/it] 44%|████▍ | 27384/61904 [3:44:52<13:19:58, 1.39s/it] 44%|████▍ | 27385/61904 [3:44:54<13:00:18, 1.36s/it] 44%|████▍ | 27386/61904 [3:44:55<12:57:43, 1.35s/it] 44%|████▍ | 27387/61904 [3:44:56<12:45:45, 1.33s/it] 44%|████▍ | 27388/61904 [3:44:58<13:04:38, 1.36s/it] 44%|████▍ | 27389/61904 [3:44:59<13:22:32, 1.40s/it] 44%|████▍ | 27390/61904 [3:45:00<13:15:58, 1.38s/it] 44%|████▍ | 27391/61904 [3:45:02<13:11:33, 1.38s/it] 44%|████▍ | 27392/61904 [3:45:03<12:51:07, 1.34s/it] 44%|████▍ | 27393/61904 [3:45:04<13:01:36, 1.36s/it] 44%|████▍ | 27394/61904 [3:45:06<12:46:59, 1.33s/it] 44%|████▍ | 27395/61904 [3:45:07<12:38:37, 1.32s/it] 44%|████▍ | 27396/61904 [3:45:08<12:34:13, 1.31s/it] 44%|████▍ | 27397/61904 [3:45:10<12:58:08, 1.35s/it] 44%|████▍ | 27398/61904 [3:45:11<13:19:00, 1.39s/it] 44%|████▍ | 27399/61904 [3:45:12<12:52:34, 1.34s/it] 44%|████▍ | 27400/61904 [3:45:14<12:55:52, 1.35s/it] {'loss': 2.6038, 'learning_rate': 1.5591857902242966e-07, 'epoch': 7.08} + 44%|████▍ | 27400/61904 [3:45:14<12:55:52, 1.35s/it] 44%|████▍ | 27401/61904 [3:45:15<13:14:42, 1.38s/it] 44%|████▍ | 27402/61904 [3:45:17<13:21:59, 1.39s/it] 44%|████▍ | 27403/61904 [3:45:18<13:22:19, 1.40s/it] 44%|████▍ | 27404/61904 [3:45:19<13:19:01, 1.39s/it] 44%|████▍ | 27405/61904 [3:45:21<13:09:07, 1.37s/it] 44%|████▍ | 27406/61904 [3:45:22<12:51:21, 1.34s/it] 44%|████▍ | 27407/61904 [3:45:23<12:45:33, 1.33s/it] 44%|████▍ | 27408/61904 [3:45:25<13:09:45, 1.37s/it] 44%|████▍ | 27409/61904 [3:45:26<13:30:48, 1.41s/it] 44%|████▍ | 27410/61904 [3:45:28<13:44:20, 1.43s/it] 44%|████▍ | 27411/61904 [3:45:29<13:54:35, 1.45s/it] 44%|████▍ | 27412/61904 [3:45:31<13:44:09, 1.43s/it] 44%|████▍ | 27413/61904 [3:45:32<13:46:11, 1.44s/it] 44%|████▍ | 27414/61904 [3:45:33<13:24:18, 1.40s/it] 44%|████▍ | 27415/61904 [3:45:35<13:18:15, 1.39s/it] 44%|████▍ | 27416/61904 [3:45:36<13:22:47, 1.40s/it] 44%|████▍ | 27417/61904 [3:45:38<13:36:00, 1.42s/it] 44%|████▍ | 27418/61904 [3:45:39<14:06:39, 1.47s/it] 44%|████▍ | 27419/61904 [3:45:41<14:03:41, 1.47s/it] 44%|████▍ | 27420/61904 [3:45:42<13:49:27, 1.44s/it] {'loss': 2.5829, 'learning_rate': 1.5588616621288732e-07, 'epoch': 7.09} + 44%|████▍ | 27420/61904 [3:45:42<13:49:27, 1.44s/it] 44%|████▍ | 27421/61904 [3:45:44<13:43:59, 1.43s/it] 44%|████▍ | 27422/61904 [3:45:45<13:50:43, 1.45s/it] 44%|████▍ | 27423/61904 [3:45:46<13:31:54, 1.41s/it] 44%|████▍ | 27424/61904 [3:45:48<13:27:12, 1.40s/it] 44%|████▍ | 27425/61904 [3:45:49<13:32:48, 1.41s/it] 44%|████▍ | 27426/61904 [3:45:51<13:26:37, 1.40s/it] 44%|████▍ | 27427/61904 [3:45:52<13:48:38, 1.44s/it] 44%|████▍ | 27428/61904 [3:45:53<13:14:45, 1.38s/it] 44%|████▍ | 27429/61904 [3:45:55<12:45:29, 1.33s/it] 44%|████▍ | 27430/61904 [3:45:56<12:33:03, 1.31s/it] 44%|████▍ | 27431/61904 [3:45:58<13:56:14, 1.46s/it] 44%|████▍ | 27432/61904 [3:45:59<13:53:49, 1.45s/it] 44%|████▍ | 27433/61904 [3:46:00<13:37:05, 1.42s/it] 44%|████▍ | 27434/61904 [3:46:02<13:11:37, 1.38s/it] 44%|████▍ | 27435/61904 [3:46:03<12:49:17, 1.34s/it] 44%|████▍ | 27436/61904 [3:46:04<12:47:16, 1.34s/it] 44%|████▍ | 27437/61904 [3:46:06<12:46:59, 1.34s/it] 44%|████▍ | 27438/61904 [3:46:07<12:44:55, 1.33s/it] 44%|████▍ | 27439/61904 [3:46:08<12:50:04, 1.34s/it] 44%|████▍ | 27440/61904 [3:46:10<12:55:20, 1.35s/it] {'loss': 2.5535, 'learning_rate': 1.5585375340334498e-07, 'epoch': 7.09} + 44%|████▍ | 27440/61904 [3:46:10<12:55:20, 1.35s/it] 44%|████▍ | 27441/61904 [3:46:11<12:56:06, 1.35s/it] 44%|████▍ | 27442/61904 [3:46:12<13:08:55, 1.37s/it] 44%|████▍ | 27443/61904 [3:46:14<13:14:13, 1.38s/it] 44%|████▍ | 27444/61904 [3:46:15<13:02:35, 1.36s/it] 44%|████▍ | 27445/61904 [3:46:17<12:56:59, 1.35s/it] 44%|████▍ | 27446/61904 [3:46:18<12:55:55, 1.35s/it] 44%|████▍ | 27447/61904 [3:46:19<13:02:54, 1.36s/it] 44%|████▍ | 27448/61904 [3:46:21<13:06:04, 1.37s/it] 44%|████▍ | 27449/61904 [3:46:22<13:12:16, 1.38s/it] 44%|████▍ | 27450/61904 [3:46:23<13:11:11, 1.38s/it] 44%|████▍ | 27451/61904 [3:46:25<13:29:52, 1.41s/it] 44%|████▍ | 27452/61904 [3:46:27<14:08:22, 1.48s/it] 44%|████▍ | 27453/61904 [3:46:28<14:12:41, 1.49s/it] 44%|████▍ | 27454/61904 [3:46:29<13:59:05, 1.46s/it] 44%|████▍ | 27455/61904 [3:46:31<14:05:27, 1.47s/it] 44%|████▍ | 27456/61904 [3:46:33<14:36:43, 1.53s/it] 44%|████▍ | 27457/61904 [3:46:34<13:51:43, 1.45s/it] 44%|████▍ | 27458/61904 [3:46:35<13:20:14, 1.39s/it] 44%|████▍ | 27459/61904 [3:46:36<13:04:11, 1.37s/it] 44%|████▍ | 27460/61904 [3:46:38<13:03:22, 1.36s/it] {'loss': 2.6527, 'learning_rate': 1.5582134059380267e-07, 'epoch': 7.1} + 44%|████▍ | 27460/61904 [3:46:38<13:03:22, 1.36s/it] 44%|████▍ | 27461/61904 [3:46:39<13:23:19, 1.40s/it] 44%|████▍ | 27462/61904 [3:46:41<13:26:44, 1.41s/it] 44%|████▍ | 27463/61904 [3:46:42<13:09:32, 1.38s/it] 44%|████▍ | 27464/61904 [3:46:43<13:17:55, 1.39s/it] 44%|████▍ | 27465/61904 [3:46:45<13:26:17, 1.40s/it] 44%|████▍ | 27466/61904 [3:46:46<13:15:25, 1.39s/it] 44%|████▍ | 27467/61904 [3:46:48<13:23:57, 1.40s/it] 44%|████▍ | 27468/61904 [3:46:49<13:27:30, 1.41s/it] 44%|████▍ | 27469/61904 [3:46:50<13:12:19, 1.38s/it] 44%|████▍ | 27470/61904 [3:46:52<13:12:23, 1.38s/it] 44%|████▍ | 27471/61904 [3:46:53<13:15:09, 1.39s/it] 44%|████▍ | 27472/61904 [3:46:54<13:05:10, 1.37s/it] 44%|████▍ | 27473/61904 [3:46:56<13:10:45, 1.38s/it] 44%|████▍ | 27474/61904 [3:46:57<13:21:30, 1.40s/it] 44%|████▍ | 27475/61904 [3:46:59<13:33:31, 1.42s/it] 44%|████▍ | 27476/61904 [3:47:00<13:28:18, 1.41s/it] 44%|████▍ | 27477/61904 [3:47:01<13:14:21, 1.38s/it] 44%|████▍ | 27478/61904 [3:47:03<13:23:56, 1.40s/it] 44%|████▍ | 27479/61904 [3:47:04<12:59:53, 1.36s/it] 44%|████▍ | 27480/61904 [3:47:06<13:05:21, 1.37s/it] {'loss': 2.5602, 'learning_rate': 1.5578892778426033e-07, 'epoch': 7.1} + 44%|████▍ | 27480/61904 [3:47:06<13:05:21, 1.37s/it] 44%|████▍ | 27481/61904 [3:47:07<12:58:55, 1.36s/it] 44%|████▍ | 27482/61904 [3:47:08<13:16:51, 1.39s/it] 44%|████▍ | 27483/61904 [3:47:10<13:17:15, 1.39s/it] 44%|████▍ | 27484/61904 [3:47:11<13:05:05, 1.37s/it] 44%|████▍ | 27485/61904 [3:47:12<13:11:38, 1.38s/it] 44%|████▍ | 27486/61904 [3:47:14<13:15:22, 1.39s/it] 44%|████▍ | 27487/61904 [3:47:15<13:22:29, 1.40s/it] 44%|████▍ | 27488/61904 [3:47:17<13:14:01, 1.38s/it] 44%|████▍ | 27489/61904 [3:47:18<13:09:03, 1.38s/it] 44%|████▍ | 27490/61904 [3:47:20<13:35:41, 1.42s/it] 44%|████▍ | 27491/61904 [3:47:21<13:10:41, 1.38s/it] 44%|████▍ | 27492/61904 [3:47:22<13:11:15, 1.38s/it] 44%|████▍ | 27493/61904 [3:47:24<13:33:21, 1.42s/it] 44%|████▍ | 27494/61904 [3:47:25<14:09:24, 1.48s/it] 44%|████▍ | 27495/61904 [3:47:27<13:39:41, 1.43s/it] 44%|████▍ | 27496/61904 [3:47:28<13:47:14, 1.44s/it] 44%|████▍ | 27497/61904 [3:47:29<13:33:09, 1.42s/it] 44%|████▍ | 27498/61904 [3:47:31<13:33:43, 1.42s/it] 44%|████▍ | 27499/61904 [3:47:32<13:20:59, 1.40s/it] 44%|████▍ | 27500/61904 [3:47:34<13:08:42, 1.38s/it] {'loss': 2.5519, 'learning_rate': 1.55756514974718e-07, 'epoch': 7.11} + 44%|████▍ | 27500/61904 [3:47:34<13:08:42, 1.38s/it] 44%|████▍ | 27501/61904 [3:47:35<13:24:12, 1.40s/it] 44%|████▍ | 27502/61904 [3:47:36<12:56:17, 1.35s/it] 44%|████▍ | 27503/61904 [3:47:38<13:04:04, 1.37s/it] 44%|████▍ | 27504/61904 [3:47:39<13:10:23, 1.38s/it] 44%|████▍ | 27505/61904 [3:47:41<13:18:56, 1.39s/it] 44%|████▍ | 27506/61904 [3:47:42<12:55:24, 1.35s/it] 44%|████▍ | 27507/61904 [3:47:43<12:59:23, 1.36s/it] 44%|████▍ | 27508/61904 [3:47:45<12:56:04, 1.35s/it] 44%|████▍ | 27509/61904 [3:47:46<13:26:03, 1.41s/it] 44%|████▍ | 27510/61904 [3:47:47<13:07:34, 1.37s/it] 44%|████▍ | 27511/61904 [3:47:49<13:05:08, 1.37s/it] 44%|████▍ | 27512/61904 [3:47:50<13:22:27, 1.40s/it] 44%|████▍ | 27513/61904 [3:47:52<13:25:46, 1.41s/it] 44%|████▍ | 27514/61904 [3:47:53<13:14:13, 1.39s/it] 44%|████▍ | 27515/61904 [3:47:54<13:34:33, 1.42s/it] 44%|████▍ | 27516/61904 [3:47:56<13:28:49, 1.41s/it] 44%|████▍ | 27517/61904 [3:47:57<13:59:35, 1.46s/it] 44%|████▍ | 27518/61904 [3:47:59<13:21:46, 1.40s/it] 44%|████▍ | 27519/61904 [3:48:00<12:45:55, 1.34s/it] 44%|████▍ | 27520/61904 [3:48:01<13:08:35, 1.38s/it] {'loss': 2.6072, 'learning_rate': 1.5572410216517566e-07, 'epoch': 7.11} + 44%|████▍ | 27520/61904 [3:48:01<13:08:35, 1.38s/it] 44%|████▍ | 27521/61904 [3:48:03<13:05:19, 1.37s/it] 44%|████▍ | 27522/61904 [3:48:04<12:48:08, 1.34s/it] 44%|████▍ | 27523/61904 [3:48:05<12:39:47, 1.33s/it] 44%|████▍ | 27524/61904 [3:48:07<12:50:47, 1.35s/it] 44%|████▍ | 27525/61904 [3:48:08<12:37:38, 1.32s/it] 44%|████▍ | 27526/61904 [3:48:09<12:44:34, 1.33s/it] 44%|████▍ | 27527/61904 [3:48:11<13:17:29, 1.39s/it] 44%|████▍ | 27528/61904 [3:48:12<13:17:31, 1.39s/it] 44%|████��� | 27529/61904 [3:48:13<13:06:01, 1.37s/it] 44%|████▍ | 27530/61904 [3:48:15<12:53:15, 1.35s/it] 44%|████▍ | 27531/61904 [3:48:16<12:56:53, 1.36s/it] 44%|████▍ | 27532/61904 [3:48:18<13:07:25, 1.37s/it] 44%|████▍ | 27533/61904 [3:48:19<12:44:24, 1.33s/it] 44%|████▍ | 27534/61904 [3:48:20<12:50:22, 1.34s/it] 44%|████▍ | 27535/61904 [3:48:22<12:59:22, 1.36s/it] 44%|████▍ | 27536/61904 [3:48:23<13:23:58, 1.40s/it] 44%|████▍ | 27537/61904 [3:48:24<13:14:47, 1.39s/it] 44%|████▍ | 27538/61904 [3:48:26<13:11:43, 1.38s/it] 44%|████▍ | 27539/61904 [3:48:27<13:27:47, 1.41s/it] 44%|████▍ | 27540/61904 [3:48:29<13:38:44, 1.43s/it] {'loss': 2.5692, 'learning_rate': 1.5569168935563335e-07, 'epoch': 7.12} + 44%|████▍ | 27540/61904 [3:48:29<13:38:44, 1.43s/it] 44%|████▍ | 27541/61904 [3:48:30<13:44:59, 1.44s/it] 44%|████▍ | 27542/61904 [3:48:32<13:49:33, 1.45s/it] 44%|████▍ | 27543/61904 [3:48:33<13:36:37, 1.43s/it] 44%|████▍ | 27544/61904 [3:48:34<13:09:33, 1.38s/it] 44%|████▍ | 27545/61904 [3:48:36<13:18:06, 1.39s/it] 44%|████▍ | 27546/61904 [3:48:37<13:48:15, 1.45s/it] 44%|████▍ | 27547/61904 [3:48:39<13:32:11, 1.42s/it] 45%|████▍ | 27548/61904 [3:48:40<13:23:45, 1.40s/it] 45%|████▍ | 27549/61904 [3:48:41<13:18:03, 1.39s/it] 45%|████▍ | 27550/61904 [3:48:43<13:25:57, 1.41s/it] 45%|████▍ | 27551/61904 [3:48:44<13:15:52, 1.39s/it] 45%|████▍ | 27552/61904 [3:48:46<13:00:12, 1.36s/it] 45%|████▍ | 27553/61904 [3:48:47<12:46:38, 1.34s/it] 45%|████▍ | 27554/61904 [3:48:48<12:47:27, 1.34s/it] 45%|████▍ | 27555/61904 [3:48:50<13:15:44, 1.39s/it] 45%|████▍ | 27556/61904 [3:48:51<14:30:21, 1.52s/it] 45%|████▍ | 27557/61904 [3:48:53<14:00:45, 1.47s/it] 45%|████▍ | 27558/61904 [3:48:54<13:54:20, 1.46s/it] 45%|████▍ | 27559/61904 [3:48:56<13:47:39, 1.45s/it] 45%|████▍ | 27560/61904 [3:48:57<13:06:48, 1.37s/it] {'loss': 2.5865, 'learning_rate': 1.55659276546091e-07, 'epoch': 7.12} + 45%|████▍ | 27560/61904 [3:48:57<13:06:48, 1.37s/it] 45%|████▍ | 27561/61904 [3:48:58<13:30:08, 1.42s/it] 45%|████▍ | 27562/61904 [3:49:00<13:29:14, 1.41s/it] 45%|████▍ | 27563/61904 [3:49:01<13:17:37, 1.39s/it] 45%|████▍ | 27564/61904 [3:49:03<13:15:54, 1.39s/it] 45%|████▍ | 27565/61904 [3:49:04<12:41:17, 1.33s/it] 45%|████▍ | 27566/61904 [3:49:05<12:34:11, 1.32s/it] 45%|████▍ | 27567/61904 [3:49:06<12:30:25, 1.31s/it] 45%|████▍ | 27568/61904 [3:49:08<12:51:28, 1.35s/it] 45%|████▍ | 27569/61904 [3:49:09<12:46:53, 1.34s/it] 45%|████▍ | 27570/61904 [3:49:11<13:04:47, 1.37s/it] 45%|████▍ | 27571/61904 [3:49:12<13:02:33, 1.37s/it] 45%|████▍ | 27572/61904 [3:49:13<12:49:19, 1.34s/it] 45%|████▍ | 27573/61904 [3:49:15<13:13:03, 1.39s/it] 45%|████▍ | 27574/61904 [3:49:16<13:12:52, 1.39s/it] 45%|████▍ | 27575/61904 [3:49:17<13:28:31, 1.41s/it] 45%|████▍ | 27576/61904 [3:49:19<13:13:16, 1.39s/it] 45%|████▍ | 27577/61904 [3:49:20<13:26:27, 1.41s/it] 45%|████▍ | 27578/61904 [3:49:22<13:24:18, 1.41s/it] 45%|████▍ | 27579/61904 [3:49:23<13:13:29, 1.39s/it] 45%|████▍ | 27580/61904 [3:49:24<13:16:28, 1.39s/it] {'loss': 2.5513, 'learning_rate': 1.5562686373654867e-07, 'epoch': 7.13} + 45%|████▍ | 27580/61904 [3:49:24<13:16:28, 1.39s/it] 45%|████▍ | 27581/61904 [3:49:26<12:59:43, 1.36s/it] 45%|████▍ | 27582/61904 [3:49:27<13:32:19, 1.42s/it] 45%|████▍ | 27583/61904 [3:49:29<13:43:14, 1.44s/it] 45%|████▍ | 27584/61904 [3:49:30<13:38:27, 1.43s/it] 45%|████▍ | 27585/61904 [3:49:32<13:21:42, 1.40s/it] 45%|████▍ | 27586/61904 [3:49:33<13:15:36, 1.39s/it] 45%|████▍ | 27587/61904 [3:49:34<13:10:59, 1.38s/it] 45%|████▍ | 27588/61904 [3:49:35<12:44:41, 1.34s/it] 45%|████▍ | 27589/61904 [3:49:37<12:38:52, 1.33s/it] 45%|████▍ | 27590/61904 [3:49:38<12:59:16, 1.36s/it] 45%|████▍ | 27591/61904 [3:49:40<13:05:23, 1.37s/it] 45%|████▍ | 27592/61904 [3:49:41<13:35:55, 1.43s/it] 45%|████▍ | 27593/61904 [3:49:43<13:25:27, 1.41s/it] 45%|████▍ | 27594/61904 [3:49:44<13:30:27, 1.42s/it] 45%|████▍ | 27595/61904 [3:49:45<13:14:48, 1.39s/it] 45%|████▍ | 27596/61904 [3:49:47<13:01:32, 1.37s/it] 45%|████▍ | 27597/61904 [3:49:48<13:07:56, 1.38s/it] 45%|████▍ | 27598/61904 [3:49:49<12:54:38, 1.35s/it] 45%|████▍ | 27599/61904 [3:49:51<13:10:10, 1.38s/it] 45%|████▍ | 27600/61904 [3:49:52<12:58:35, 1.36s/it] {'loss': 2.5622, 'learning_rate': 1.5559445092700633e-07, 'epoch': 7.13} + 45%|████▍ | 27600/61904 [3:49:52<12:58:35, 1.36s/it] 45%|████▍ | 27601/61904 [3:49:53<12:44:59, 1.34s/it] 45%|████▍ | 27602/61904 [3:49:55<12:35:04, 1.32s/it] 45%|████▍ | 27603/61904 [3:49:56<12:47:49, 1.34s/it] 45%|████▍ | 27604/61904 [3:49:57<12:40:09, 1.33s/it] 45%|████▍ | 27605/61904 [3:49:59<13:09:47, 1.38s/it] 45%|████▍ | 27606/61904 [3:50:00<13:07:38, 1.38s/it] 45%|████▍ | 27607/61904 [3:50:02<13:21:16, 1.40s/it] 45%|████▍ | 27608/61904 [3:50:03<13:39:33, 1.43s/it] 45%|████▍ | 27609/61904 [3:50:05<13:42:11, 1.44s/it] 45%|████▍ | 27610/61904 [3:50:06<13:35:30, 1.43s/it] 45%|████▍ | 27611/61904 [3:50:07<13:22:40, 1.40s/it] 45%|████▍ | 27612/61904 [3:50:09<13:06:54, 1.38s/it] 45%|████▍ | 27613/61904 [3:50:10<12:54:39, 1.36s/it] 45%|████▍ | 27614/61904 [3:50:11<13:13:14, 1.39s/it] 45%|████▍ | 27615/61904 [3:50:13<12:52:36, 1.35s/it] 45%|████▍ | 27616/61904 [3:50:14<13:10:57, 1.38s/it] 45%|████▍ | 27617/61904 [3:50:15<12:36:18, 1.32s/it] 45%|████▍ | 27618/61904 [3:50:17<12:52:14, 1.35s/it] 45%|████▍ | 27619/61904 [3:50:18<12:51:11, 1.35s/it] 45%|████▍ | 27620/61904 [3:50:19<12:41:19, 1.33s/it] {'loss': 2.5787, 'learning_rate': 1.5556203811746402e-07, 'epoch': 7.14} + 45%|████▍ | 27620/61904 [3:50:19<12:41:19, 1.33s/it] 45%|████▍ | 27621/61904 [3:50:21<12:51:39, 1.35s/it] 45%|████▍ | 27622/61904 [3:50:22<13:17:24, 1.40s/it] 45%|████▍ | 27623/61904 [3:50:24<13:11:11, 1.38s/it] 45%|████▍ | 27624/61904 [3:50:25<13:22:56, 1.41s/it] 45%|████▍ | 27625/61904 [3:50:26<12:58:43, 1.36s/it] 45%|████▍ | 27626/61904 [3:50:28<13:12:33, 1.39s/it] 45%|████▍ | 27627/61904 [3:50:29<13:01:10, 1.37s/it] 45%|████▍ | 27628/61904 [3:50:31<13:16:21, 1.39s/it] 45%|████▍ | 27629/61904 [3:50:32<13:43:36, 1.44s/it] 45%|████▍ | 27630/61904 [3:50:34<13:58:52, 1.47s/it] 45%|████▍ | 27631/61904 [3:50:35<13:49:01, 1.45s/it] 45%|████▍ | 27632/61904 [3:50:36<13:31:24, 1.42s/it] 45%|████▍ | 27633/61904 [3:50:38<13:47:29, 1.45s/it] 45%|████▍ | 27634/61904 [3:50:39<13:25:36, 1.41s/it] 45%|████▍ | 27635/61904 [3:50:41<13:00:47, 1.37s/it] 45%|████▍ | 27636/61904 [3:50:42<13:58:28, 1.47s/it] 45%|████▍ | 27637/61904 [3:50:44<13:49:49, 1.45s/it] 45%|████▍ | 27638/61904 [3:50:45<13:16:52, 1.40s/it] 45%|████▍ | 27639/61904 [3:50:46<13:16:20, 1.39s/it] 45%|████▍ | 27640/61904 [3:50:48<13:04:42, 1.37s/it] {'loss': 2.5697, 'learning_rate': 1.5552962530792168e-07, 'epoch': 7.14} + 45%|████▍ | 27640/61904 [3:50:48<13:04:42, 1.37s/it] 45%|████▍ | 27641/61904 [3:50:49<12:47:53, 1.34s/it] 45%|████▍ | 27642/61904 [3:50:50<12:54:37, 1.36s/it] 45%|████▍ | 27643/61904 [3:50:52<13:03:34, 1.37s/it] 45%|████▍ | 27644/61904 [3:50:53<13:09:07, 1.38s/it] 45%|████▍ | 27645/61904 [3:50:54<13:02:02, 1.37s/it] 45%|████▍ | 27646/61904 [3:50:56<13:08:20, 1.38s/it] 45%|████▍ | 27647/61904 [3:50:57<13:05:49, 1.38s/it] 45%|████▍ | 27648/61904 [3:50:59<13:10:20, 1.38s/it] 45%|████▍ | 27649/61904 [3:51:00<12:51:23, 1.35s/it] 45%|████▍ | 27650/61904 [3:51:01<12:55:32, 1.36s/it] 45%|████▍ | 27651/61904 [3:51:03<13:00:26, 1.37s/it] 45%|████▍ | 27652/61904 [3:51:04<12:55:57, 1.36s/it] 45%|████▍ | 27653/61904 [3:51:06<13:25:35, 1.41s/it] 45%|████▍ | 27654/61904 [3:51:07<12:55:12, 1.36s/it] 45%|████▍ | 27655/61904 [3:51:08<12:46:56, 1.34s/it] 45%|████▍ | 27656/61904 [3:51:09<12:31:55, 1.32s/it] 45%|████▍ | 27657/61904 [3:51:11<13:07:29, 1.38s/it] 45%|████▍ | 27658/61904 [3:51:12<13:32:19, 1.42s/it] 45%|████▍ | 27659/61904 [3:51:14<13:01:57, 1.37s/it] 45%|████▍ | 27660/61904 [3:51:15<12:54:41, 1.36s/it] {'loss': 2.5477, 'learning_rate': 1.5549721249837934e-07, 'epoch': 7.15} + 45%|████▍ | 27660/61904 [3:51:15<12:54:41, 1.36s/it] 45%|████▍ | 27661/61904 [3:51:16<12:27:47, 1.31s/it] 45%|████▍ | 27662/61904 [3:51:17<12:28:04, 1.31s/it] 45%|████▍ | 27663/61904 [3:51:19<12:25:01, 1.31s/it] 45%|████▍ | 27664/61904 [3:51:20<12:14:19, 1.29s/it] 45%|████▍ | 27665/61904 [3:51:21<12:42:29, 1.34s/it] 45%|████▍ | 27666/61904 [3:51:23<12:42:55, 1.34s/it] 45%|████▍ | 27667/61904 [3:51:24<13:00:42, 1.37s/it] 45%|████▍ | 27668/61904 [3:51:26<13:09:50, 1.38s/it] 45%|████▍ | 27669/61904 [3:51:27<13:00:37, 1.37s/it] 45%|████▍ | 27670/61904 [3:51:28<12:50:37, 1.35s/it] 45%|████▍ | 27671/61904 [3:51:30<12:52:57, 1.35s/it] 45%|████▍ | 27672/61904 [3:51:31<12:41:37, 1.33s/it] 45%|████▍ | 27673/61904 [3:51:32<12:42:42, 1.34s/it] 45%|████▍ | 27674/61904 [3:51:34<12:29:31, 1.31s/it] 45%|████▍ | 27675/61904 [3:51:35<12:14:51, 1.29s/it] 45%|████▍ | 27676/61904 [3:51:36<12:20:20, 1.30s/it] 45%|████▍ | 27677/61904 [3:51:38<12:49:51, 1.35s/it] 45%|████▍ | 27678/61904 [3:51:39<12:51:12, 1.35s/it] 45%|████▍ | 27679/61904 [3:51:40<12:55:05, 1.36s/it] 45%|████▍ | 27680/61904 [3:51:42<12:38:11, 1.33s/it] {'loss': 2.5206, 'learning_rate': 1.5546479968883703e-07, 'epoch': 7.15} + 45%|████▍ | 27680/61904 [3:51:42<12:38:11, 1.33s/it] 45%|████▍ | 27681/61904 [3:51:43<13:12:03, 1.39s/it] 45%|████▍ | 27682/61904 [3:51:44<13:11:15, 1.39s/it] 45%|████▍ | 27683/61904 [3:51:46<13:12:33, 1.39s/it] 45%|████▍ | 27684/61904 [3:51:47<13:12:34, 1.39s/it] 45%|████▍ | 27685/61904 [3:51:49<13:14:23, 1.39s/it] 45%|████▍ | 27686/61904 [3:51:50<13:03:13, 1.37s/it] 45%|████▍ | 27687/61904 [3:51:51<13:20:31, 1.40s/it] 45%|████▍ | 27688/61904 [3:51:53<13:12:22, 1.39s/it] 45%|████▍ | 27689/61904 [3:51:54<13:17:46, 1.40s/it] 45%|████▍ | 27690/61904 [3:51:56<13:06:01, 1.38s/it] 45%|████▍ | 27691/61904 [3:51:57<13:04:28, 1.38s/it] 45%|████▍ | 27692/61904 [3:51:58<13:10:15, 1.39s/it] 45%|████▍ | 27693/61904 [3:52:00<12:54:02, 1.36s/it] 45%|████▍ | 27694/61904 [3:52:01<13:12:56, 1.39s/it] 45%|████▍ | 27695/61904 [3:52:03<13:19:37, 1.40s/it] 45%|████▍ | 27696/61904 [3:52:04<13:24:16, 1.41s/it] 45%|████▍ | 27697/61904 [3:52:05<12:53:37, 1.36s/it] 45%|████▍ | 27698/61904 [3:52:07<12:57:55, 1.36s/it] 45%|████▍ | 27699/61904 [3:52:08<12:48:08, 1.35s/it] 45%|████▍ | 27700/61904 [3:52:09<13:19:56, 1.40s/it] {'loss': 2.6325, 'learning_rate': 1.554323868792947e-07, 'epoch': 7.16} + 45%|████▍ | 27700/61904 [3:52:09<13:19:56, 1.40s/it] 45%|████▍ | 27701/61904 [3:52:11<13:15:34, 1.40s/it] 45%|████▍ | 27702/61904 [3:52:12<13:44:47, 1.45s/it] 45%|████▍ | 27703/61904 [3:52:14<13:45:56, 1.45s/it] 45%|████▍ | 27704/61904 [3:52:15<14:04:18, 1.48s/it] 45%|████▍ | 27705/61904 [3:52:17<14:03:49, 1.48s/it] 45%|████▍ | 27706/61904 [3:52:18<14:18:58, 1.51s/it] 45%|████▍ | 27707/61904 [3:52:20<14:07:04, 1.49s/it] 45%|████▍ | 27708/61904 [3:52:21<14:16:34, 1.50s/it] 45%|████▍ | 27709/61904 [3:52:23<13:46:19, 1.45s/it] 45%|████▍ | 27710/61904 [3:52:24<13:20:04, 1.40s/it] 45%|████▍ | 27711/61904 [3:52:25<13:16:16, 1.40s/it] 45%|████▍ | 27712/61904 [3:52:27<13:20:30, 1.40s/it] 45%|████▍ | 27713/61904 [3:52:28<12:43:25, 1.34s/it] 45%|████▍ | 27714/61904 [3:52:30<13:08:27, 1.38s/it] 45%|████▍ | 27715/61904 [3:52:31<13:09:49, 1.39s/it] 45%|████▍ | 27716/61904 [3:52:32<12:56:43, 1.36s/it] 45%|████▍ | 27717/61904 [3:52:34<12:43:40, 1.34s/it] 45%|████▍ | 27718/61904 [3:52:35<13:03:09, 1.37s/it] 45%|████▍ | 27719/61904 [3:52:36<13:17:03, 1.40s/it] 45%|████▍ | 27720/61904 [3:52:38<13:14:29, 1.39s/it] {'loss': 2.5897, 'learning_rate': 1.5539997406975236e-07, 'epoch': 7.16} + 45%|████▍ | 27720/61904 [3:52:38<13:14:29, 1.39s/it] 45%|████▍ | 27721/61904 [3:52:39<13:19:33, 1.40s/it] 45%|████▍ | 27722/61904 [3:52:41<13:37:36, 1.44s/it] 45%|████▍ | 27723/61904 [3:52:42<13:26:35, 1.42s/it] 45%|████▍ | 27724/61904 [3:52:43<13:18:34, 1.40s/it] 45%|████▍ | 27725/61904 [3:52:45<12:55:24, 1.36s/it] 45%|████▍ | 27726/61904 [3:52:46<12:51:36, 1.35s/it] 45%|████▍ | 27727/61904 [3:52:47<12:47:28, 1.35s/it] 45%|████▍ | 27728/61904 [3:52:49<12:53:11, 1.36s/it] 45%|████▍ | 27729/61904 [3:52:50<12:55:50, 1.36s/it] 45%|████▍ | 27730/61904 [3:52:52<13:37:50, 1.44s/it] 45%|████▍ | 27731/61904 [3:52:53<13:43:15, 1.45s/it] 45%|████▍ | 27732/61904 [3:52:55<13:26:50, 1.42s/it] 45%|████▍ | 27733/61904 [3:52:56<13:08:49, 1.39s/it] 45%|████▍ | 27734/61904 [3:52:57<12:59:21, 1.37s/it] 45%|████▍ | 27735/61904 [3:52:59<13:25:35, 1.41s/it] 45%|████▍ | 27736/61904 [3:53:00<13:12:13, 1.39s/it] 45%|████▍ | 27737/61904 [3:53:01<13:09:40, 1.39s/it] 45%|████▍ | 27738/61904 [3:53:03<13:08:51, 1.39s/it] 45%|████▍ | 27739/61904 [3:53:04<13:11:11, 1.39s/it] 45%|████▍ | 27740/61904 [3:53:06<13:09:10, 1.39s/it] {'loss': 2.5669, 'learning_rate': 1.5536756126021002e-07, 'epoch': 7.17} + 45%|████▍ | 27740/61904 [3:53:06<13:09:10, 1.39s/it] 45%|████▍ | 27741/61904 [3:53:07<13:10:01, 1.39s/it] 45%|████▍ | 27742/61904 [3:53:08<12:53:55, 1.36s/it] 45%|████▍ | 27743/61904 [3:53:10<12:55:38, 1.36s/it] 45%|████▍ | 27744/61904 [3:53:11<13:07:05, 1.38s/it] 45%|████▍ | 27745/61904 [3:53:12<12:56:57, 1.36s/it] 45%|████▍ | 27746/61904 [3:53:14<13:11:09, 1.39s/it] 45%|████▍ | 27747/61904 [3:53:15<12:42:26, 1.34s/it] 45%|████▍ | 27748/61904 [3:53:16<12:33:41, 1.32s/it] 45%|████▍ | 27749/61904 [3:53:18<13:11:41, 1.39s/it] 45%|████▍ | 27750/61904 [3:53:19<13:03:28, 1.38s/it] 45%|████▍ | 27751/61904 [3:53:21<12:57:56, 1.37s/it] 45%|████▍ | 27752/61904 [3:53:22<13:18:03, 1.40s/it] 45%|████▍ | 27753/61904 [3:53:23<13:03:10, 1.38s/it] 45%|████▍ | 27754/61904 [3:53:25<12:59:39, 1.37s/it] 45%|████▍ | 27755/61904 [3:53:26<13:19:33, 1.40s/it] 45%|████▍ | 27756/61904 [3:53:28<13:30:26, 1.42s/it] 45%|████▍ | 27757/61904 [3:53:29<13:34:21, 1.43s/it] 45%|████▍ | 27758/61904 [3:53:31<13:48:01, 1.45s/it] 45%|████▍ | 27759/61904 [3:53:32<13:28:31, 1.42s/it] 45%|████▍ | 27760/61904 [3:53:33<13:16:33, 1.40s/it] {'loss': 2.5391, 'learning_rate': 1.553351484506677e-07, 'epoch': 7.17} + 45%|████▍ | 27760/61904 [3:53:33<13:16:33, 1.40s/it] 45%|████▍ | 27761/61904 [3:53:35<13:23:43, 1.41s/it] 45%|████▍ | 27762/61904 [3:53:36<13:04:06, 1.38s/it] 45%|████▍ | 27763/61904 [3:53:38<13:36:21, 1.43s/it] 45%|████▍ | 27764/61904 [3:53:39<14:09:44, 1.49s/it] 45%|████▍ | 27765/61904 [3:53:41<13:40:09, 1.44s/it] 45%|████▍ | 27766/61904 [3:53:42<13:46:40, 1.45s/it] 45%|████▍ | 27767/61904 [3:53:43<13:32:02, 1.43s/it] 45%|████▍ | 27768/61904 [3:53:45<13:32:22, 1.43s/it] 45%|████▍ | 27769/61904 [3:53:46<13:22:17, 1.41s/it] 45%|████▍ | 27770/61904 [3:53:48<12:59:00, 1.37s/it] 45%|████▍ | 27771/61904 [3:53:49<12:43:23, 1.34s/it] 45%|████▍ | 27772/61904 [3:53:50<12:40:00, 1.34s/it] 45%|████▍ | 27773/61904 [3:53:52<12:45:49, 1.35s/it] 45%|████▍ | 27774/61904 [3:53:53<13:36:59, 1.44s/it] 45%|████▍ | 27775/61904 [3:53:55<13:16:59, 1.40s/it] 45%|████▍ | 27776/61904 [3:53:56<13:14:18, 1.40s/it] 45%|████▍ | 27777/61904 [3:53:57<12:53:16, 1.36s/it] 45%|████▍ | 27778/61904 [3:53:58<12:45:57, 1.35s/it] 45%|████▍ | 27779/61904 [3:54:00<12:51:13, 1.36s/it] 45%|████▍ | 27780/61904 [3:54:01<12:37:28, 1.33s/it] {'loss': 2.5715, 'learning_rate': 1.5530273564112537e-07, 'epoch': 7.18} + 45%|████▍ | 27780/61904 [3:54:01<12:37:28, 1.33s/it] 45%|████▍ | 27781/61904 [3:54:02<12:42:37, 1.34s/it] 45%|████▍ | 27782/61904 [3:54:04<12:28:45, 1.32s/it] 45%|████▍ | 27783/61904 [3:54:05<12:28:59, 1.32s/it] 45%|████▍ | 27784/61904 [3:54:06<12:42:13, 1.34s/it] 45%|████▍ | 27785/61904 [3:54:08<12:20:58, 1.30s/it] 45%|████▍ | 27786/61904 [3:54:09<12:30:35, 1.32s/it] 45%|████▍ | 27787/61904 [3:54:10<12:46:22, 1.35s/it] 45%|████▍ | 27788/61904 [3:54:12<13:17:37, 1.40s/it] 45%|████▍ | 27789/61904 [3:54:13<13:05:41, 1.38s/it] 45%|████▍ | 27790/61904 [3:54:15<13:01:09, 1.37s/it] 45%|████▍ | 27791/61904 [3:54:16<12:54:33, 1.36s/it] 45%|████▍ | 27792/61904 [3:54:17<12:41:45, 1.34s/it] 45%|████▍ | 27793/61904 [3:54:19<12:50:01, 1.35s/it] 45%|████▍ | 27794/61904 [3:54:20<12:42:49, 1.34s/it] 45%|████▍ | 27795/61904 [3:54:21<12:58:30, 1.37s/it] 45%|████▍ | 27796/61904 [3:54:23<12:52:13, 1.36s/it] 45%|████▍ | 27797/61904 [3:54:24<13:17:41, 1.40s/it] 45%|████▍ | 27798/61904 [3:54:26<13:42:11, 1.45s/it] 45%|████▍ | 27799/61904 [3:54:27<13:07:15, 1.39s/it] 45%|████▍ | 27800/61904 [3:54:28<12:55:16, 1.36s/it] {'loss': 2.6015, 'learning_rate': 1.5527032283158303e-07, 'epoch': 7.19} + 45%|████▍ | 27800/61904 [3:54:28<12:55:16, 1.36s/it] 45%|████▍ | 27801/61904 [3:54:30<12:38:59, 1.34s/it] 45%|████▍ | 27802/61904 [3:54:31<12:40:14, 1.34s/it] 45%|████▍ | 27803/61904 [3:54:32<12:32:58, 1.32s/it] 45%|████▍ | 27804/61904 [3:54:34<12:29:58, 1.32s/it] 45%|████▍ | 27805/61904 [3:54:35<12:44:04, 1.34s/it] 45%|████▍ | 27806/61904 [3:54:36<12:45:25, 1.35s/it] 45%|████▍ | 27807/61904 [3:54:38<13:17:02, 1.40s/it] 45%|████▍ | 27808/61904 [3:54:39<13:37:14, 1.44s/it] 45%|████▍ | 27809/61904 [3:54:41<14:02:03, 1.48s/it] 45%|████▍ | 27810/61904 [3:54:42<13:21:08, 1.41s/it] 45%|████▍ | 27811/61904 [3:54:44<13:29:08, 1.42s/it] 45%|████▍ | 27812/61904 [3:54:45<13:16:02, 1.40s/it] 45%|████▍ | 27813/61904 [3:54:46<13:13:19, 1.40s/it] 45%|████▍ | 27814/61904 [3:54:48<13:05:31, 1.38s/it] 45%|████▍ | 27815/61904 [3:54:49<13:02:03, 1.38s/it] 45%|████▍ | 27816/61904 [3:54:51<13:03:45, 1.38s/it] 45%|████▍ | 27817/61904 [3:54:52<12:47:54, 1.35s/it] 45%|████▍ | 27818/61904 [3:54:53<13:40:50, 1.44s/it] 45%|████▍ | 27819/61904 [3:54:55<13:47:02, 1.46s/it] 45%|████▍ | 27820/61904 [3:54:56<13:34:04, 1.43s/it] {'loss': 2.6043, 'learning_rate': 1.552379100220407e-07, 'epoch': 7.19} + 45%|████▍ | 27820/61904 [3:54:56<13:34:04, 1.43s/it] 45%|████▍ | 27821/61904 [3:54:58<13:33:12, 1.43s/it] 45%|████▍ | 27822/61904 [3:54:59<13:22:10, 1.41s/it] 45%|████▍ | 27823/61904 [3:55:01<13:21:52, 1.41s/it] 45%|████▍ | 27824/61904 [3:55:02<13:24:50, 1.42s/it] 45%|████▍ | 27825/61904 [3:55:03<13:05:14, 1.38s/it] 45%|████▍ | 27826/61904 [3:55:05<12:50:43, 1.36s/it] 45%|████▍ | 27827/61904 [3:55:06<12:59:08, 1.37s/it] 45%|████▍ | 27828/61904 [3:55:07<13:07:53, 1.39s/it] 45%|████▍ | 27829/61904 [3:55:09<13:10:37, 1.39s/it] 45%|████▍ | 27830/61904 [3:55:10<13:01:47, 1.38s/it] 45%|████▍ | 27831/61904 [3:55:11<12:39:46, 1.34s/it] 45%|████▍ | 27832/61904 [3:55:13<12:53:55, 1.36s/it] 45%|████▍ | 27833/61904 [3:55:14<13:14:02, 1.40s/it] 45%|████▍ | 27834/61904 [3:55:16<13:30:40, 1.43s/it] 45%|████▍ | 27835/61904 [3:55:17<13:31:12, 1.43s/it] 45%|████▍ | 27836/61904 [3:55:19<13:28:49, 1.42s/it] 45%|████▍ | 27837/61904 [3:55:20<13:33:32, 1.43s/it] 45%|████▍ | 27838/61904 [3:55:21<13:16:13, 1.40s/it] 45%|████▍ | 27839/61904 [3:55:23<13:06:10, 1.38s/it] 45%|████▍ | 27840/61904 [3:55:24<13:34:20, 1.43s/it] {'loss': 2.5723, 'learning_rate': 1.5520549721249838e-07, 'epoch': 7.2} + 45%|████▍ | 27840/61904 [3:55:24<13:34:20, 1.43s/it] 45%|████▍ | 27841/61904 [3:55:26<14:13:01, 1.50s/it] 45%|████▍ | 27842/61904 [3:55:27<13:49:15, 1.46s/it] 45%|████▍ | 27843/61904 [3:55:29<13:37:03, 1.44s/it] 45%|████▍ | 27844/61904 [3:55:30<13:45:35, 1.45s/it] 45%|████▍ | 27845/61904 [3:55:32<13:45:37, 1.45s/it] 45%|████▍ | 27846/61904 [3:55:33<13:22:03, 1.41s/it] 45%|████▍ | 27847/61904 [3:55:34<13:20:08, 1.41s/it] 45%|████▍ | 27848/61904 [3:55:36<13:03:35, 1.38s/it] 45%|████▍ | 27849/61904 [3:55:37<13:17:23, 1.40s/it] 45%|████▍ | 27850/61904 [3:55:39<13:19:20, 1.41s/it] 45%|████▍ | 27851/61904 [3:55:40<13:02:44, 1.38s/it] 45%|████▍ | 27852/61904 [3:55:41<13:11:33, 1.39s/it] 45%|████▍ | 27853/61904 [3:55:43<13:21:59, 1.41s/it] 45%|████▍ | 27854/61904 [3:55:44<13:21:08, 1.41s/it] 45%|████▍ | 27855/61904 [3:55:46<13:09:35, 1.39s/it] 45%|████▍ | 27856/61904 [3:55:47<12:51:55, 1.36s/it] 45%|████▌ | 27857/61904 [3:55:48<13:11:38, 1.40s/it] 45%|████▌ | 27858/61904 [3:55:50<13:20:33, 1.41s/it] 45%|████▌ | 27859/61904 [3:55:51<13:12:12, 1.40s/it] 45%|████▌ | 27860/61904 [3:55:52<12:37:33, 1.34s/it] {'loss': 2.5877, 'learning_rate': 1.5517308440295604e-07, 'epoch': 7.2} + 45%|████▌ | 27860/61904 [3:55:52<12:37:33, 1.34s/it] 45%|████▌ | 27861/61904 [3:55:54<12:46:41, 1.35s/it] 45%|████▌ | 27862/61904 [3:55:55<12:54:30, 1.37s/it] 45%|████▌ | 27863/61904 [3:55:56<12:50:43, 1.36s/it] 45%|████▌ | 27864/61904 [3:55:58<12:48:25, 1.35s/it] 45%|████▌ | 27865/61904 [3:55:59<13:19:16, 1.41s/it] 45%|████▌ | 27866/61904 [3:56:01<13:27:57, 1.42s/it] 45%|████▌ | 27867/61904 [3:56:02<13:14:52, 1.40s/it] 45%|████▌ | 27868/61904 [3:56:03<13:06:24, 1.39s/it] 45%|████▌ | 27869/61904 [3:56:05<12:44:15, 1.35s/it] 45%|████▌ | 27870/61904 [3:56:06<13:00:24, 1.38s/it] 45%|████▌ | 27871/61904 [3:56:08<13:28:50, 1.43s/it] 45%|████▌ | 27872/61904 [3:56:09<13:43:20, 1.45s/it] 45%|████▌ | 27873/61904 [3:56:10<13:15:56, 1.40s/it] 45%|████▌ | 27874/61904 [3:56:12<13:21:52, 1.41s/it] 45%|████▌ | 27875/61904 [3:56:13<13:05:24, 1.38s/it] 45%|████▌ | 27876/61904 [3:56:15<12:57:02, 1.37s/it] 45%|████▌ | 27877/61904 [3:56:16<13:36:48, 1.44s/it] 45%|████▌ | 27878/61904 [3:56:18<13:35:46, 1.44s/it] 45%|████▌ | 27879/61904 [3:56:19<13:18:00, 1.41s/it] 45%|████▌ | 27880/61904 [3:56:20<13:24:06, 1.42s/it] {'loss': 2.5823, 'learning_rate': 1.551406715934137e-07, 'epoch': 7.21} + 45%|████▌ | 27880/61904 [3:56:20<13:24:06, 1.42s/it] 45%|████▌ | 27881/61904 [3:56:22<13:38:28, 1.44s/it] 45%|████▌ | 27882/61904 [3:56:23<13:16:46, 1.41s/it] 45%|████▌ | 27883/61904 [3:56:25<13:14:45, 1.40s/it] 45%|████▌ | 27884/61904 [3:56:26<13:07:12, 1.39s/it] 45%|████▌ | 27885/61904 [3:56:27<13:19:00, 1.41s/it] 45%|████▌ | 27886/61904 [3:56:29<13:40:35, 1.45s/it] 45%|████▌ | 27887/61904 [3:56:30<12:59:29, 1.37s/it] 45%|████▌ | 27888/61904 [3:56:32<12:58:22, 1.37s/it] 45%|████▌ | 27889/61904 [3:56:33<13:42:36, 1.45s/it] 45%|████▌ | 27890/61904 [3:56:35<13:27:31, 1.42s/it] 45%|████▌ | 27891/61904 [3:56:36<13:27:22, 1.42s/it] 45%|████▌ | 27892/61904 [3:56:37<13:07:17, 1.39s/it] 45%|████▌ | 27893/61904 [3:56:39<12:48:04, 1.35s/it] 45%|████▌ | 27894/61904 [3:56:40<12:54:40, 1.37s/it] 45%|████▌ | 27895/61904 [3:56:41<12:46:48, 1.35s/it] 45%|████▌ | 27896/61904 [3:56:43<12:49:30, 1.36s/it] 45%|████▌ | 27897/61904 [3:56:44<12:50:45, 1.36s/it] 45%|████▌ | 27898/61904 [3:56:45<12:59:32, 1.38s/it] 45%|████▌ | 27899/61904 [3:56:47<12:53:58, 1.37s/it] 45%|████▌ | 27900/61904 [3:56:48<12:59:12, 1.37s/it] {'loss': 2.5435, 'learning_rate': 1.5510825878387137e-07, 'epoch': 7.21} + 45%|████▌ | 27900/61904 [3:56:48<12:59:12, 1.37s/it] 45%|████▌ | 27901/61904 [3:56:50<13:17:35, 1.41s/it] 45%|████▌ | 27902/61904 [3:56:51<13:07:36, 1.39s/it] 45%|████▌ | 27903/61904 [3:56:52<13:10:59, 1.40s/it] 45%|████▌ | 27904/61904 [3:56:54<13:24:04, 1.42s/it] 45%|████▌ | 27905/61904 [3:56:55<13:40:02, 1.45s/it] 45%|████▌ | 27906/61904 [3:56:57<13:15:01, 1.40s/it] 45%|████▌ | 27907/61904 [3:56:58<13:07:31, 1.39s/it] 45%|████▌ | 27908/61904 [3:56:59<13:10:56, 1.40s/it] 45%|████▌ | 27909/61904 [3:57:01<12:53:53, 1.37s/it] 45%|████▌ | 27910/61904 [3:57:02<13:00:29, 1.38s/it] 45%|████▌ | 27911/61904 [3:57:04<13:07:29, 1.39s/it] 45%|████▌ | 27912/61904 [3:57:05<13:10:41, 1.40s/it] 45%|████▌ | 27913/61904 [3:57:06<12:51:08, 1.36s/it] 45%|████▌ | 27914/61904 [3:57:08<12:50:44, 1.36s/it] 45%|████▌ | 27915/61904 [3:57:09<13:11:04, 1.40s/it] 45%|████▌ | 27916/61904 [3:57:10<12:55:35, 1.37s/it] 45%|████▌ | 27917/61904 [3:57:12<12:45:57, 1.35s/it] 45%|████▌ | 27918/61904 [3:57:13<13:17:28, 1.41s/it] 45%|████▌ | 27919/61904 [3:57:15<13:01:07, 1.38s/it] 45%|████▌ | 27920/61904 [3:57:16<12:50:21, 1.36s/it] {'loss': 2.5416, 'learning_rate': 1.5507584597432905e-07, 'epoch': 7.22} + 45%|████▌ | 27920/61904 [3:57:16<12:50:21, 1.36s/it] 45%|████▌ | 27921/61904 [3:57:17<13:00:50, 1.38s/it] 45%|████▌ | 27922/61904 [3:57:19<12:53:15, 1.37s/it] 45%|████▌ | 27923/61904 [3:57:20<12:39:58, 1.34s/it] 45%|████▌ | 27924/61904 [3:57:21<12:38:25, 1.34s/it] 45%|████▌ | 27925/61904 [3:57:23<12:31:53, 1.33s/it] 45%|████▌ | 27926/61904 [3:57:24<12:49:11, 1.36s/it] 45%|████▌ | 27927/61904 [3:57:25<13:08:09, 1.39s/it] 45%|████▌ | 27928/61904 [3:57:27<13:08:22, 1.39s/it] 45%|████▌ | 27929/61904 [3:57:28<13:11:58, 1.40s/it] 45%|████▌ | 27930/61904 [3:57:30<12:48:36, 1.36s/it] 45%|████▌ | 27931/61904 [3:57:31<12:45:39, 1.35s/it] 45%|████▌ | 27932/61904 [3:57:32<12:43:20, 1.35s/it] 45%|████▌ | 27933/61904 [3:57:33<12:23:58, 1.31s/it] 45%|████▌ | 27934/61904 [3:57:35<13:01:30, 1.38s/it] 45%|████▌ | 27935/61904 [3:57:36<12:50:00, 1.36s/it] 45%|████▌ | 27936/61904 [3:57:38<13:07:13, 1.39s/it] 45%|████▌ | 27937/61904 [3:57:39<13:05:18, 1.39s/it] 45%|████▌ | 27938/61904 [3:57:40<12:57:20, 1.37s/it] 45%|████▌ | 27939/61904 [3:57:42<12:43:22, 1.35s/it] 45%|████▌ | 27940/61904 [3:57:43<12:44:35, 1.35s/it] {'loss': 2.6001, 'learning_rate': 1.5504343316478672e-07, 'epoch': 7.22} + 45%|████▌ | 27940/61904 [3:57:43<12:44:35, 1.35s/it] 45%|████▌ | 27941/61904 [3:57:45<13:03:43, 1.38s/it] 45%|████▌ | 27942/61904 [3:57:46<13:45:57, 1.46s/it] 45%|████▌ | 27943/61904 [3:57:47<13:08:06, 1.39s/it] 45%|████▌ | 27944/61904 [3:57:49<13:25:50, 1.42s/it] 45%|████▌ | 27945/61904 [3:57:50<13:42:53, 1.45s/it] 45%|████▌ | 27946/61904 [3:57:52<13:31:23, 1.43s/it] 45%|████▌ | 27947/61904 [3:57:53<13:25:57, 1.42s/it] 45%|████▌ | 27948/61904 [3:57:55<13:25:58, 1.42s/it] 45%|████▌ | 27949/61904 [3:57:56<13:15:58, 1.41s/it] 45%|████▌ | 27950/61904 [3:57:58<13:26:54, 1.43s/it] 45%|████▌ | 27951/61904 [3:57:59<13:28:38, 1.43s/it] 45%|████▌ | 27952/61904 [3:58:00<13:36:26, 1.44s/it] 45%|████▌ | 27953/61904 [3:58:02<13:24:38, 1.42s/it] 45%|████▌ | 27954/61904 [3:58:03<12:59:00, 1.38s/it] 45%|████▌ | 27955/61904 [3:58:04<12:52:13, 1.36s/it] 45%|████▌ | 27956/61904 [3:58:06<12:33:15, 1.33s/it] 45%|████▌ | 27957/61904 [3:58:07<12:33:04, 1.33s/it] 45%|████▌ | 27958/61904 [3:58:08<12:48:10, 1.36s/it] 45%|████▌ | 27959/61904 [3:58:10<13:01:20, 1.38s/it] 45%|████▌ | 27960/61904 [3:58:11<13:03:33, 1.39s/it] {'loss': 2.6136, 'learning_rate': 1.5501102035524438e-07, 'epoch': 7.23} + 45%|████▌ | 27960/61904 [3:58:11<13:03:33, 1.39s/it] 45%|████▌ | 27961/61904 [3:58:13<13:02:23, 1.38s/it] 45%|████▌ | 27962/61904 [3:58:14<13:27:38, 1.43s/it] 45%|████▌ | 27963/61904 [3:58:15<13:04:10, 1.39s/it] 45%|████▌ | 27964/61904 [3:58:17<12:53:29, 1.37s/it] 45%|████▌ | 27965/61904 [3:58:18<12:53:04, 1.37s/it] 45%|████▌ | 27966/61904 [3:58:19<12:50:13, 1.36s/it] 45%|████▌ | 27967/61904 [3:58:21<12:41:54, 1.35s/it] 45%|████▌ | 27968/61904 [3:58:22<13:28:40, 1.43s/it] 45%|████▌ | 27969/61904 [3:58:24<13:31:34, 1.43s/it] 45%|████▌ | 27970/61904 [3:58:25<13:34:01, 1.44s/it] 45%|████▌ | 27971/61904 [3:58:27<13:10:22, 1.40s/it] 45%|████▌ | 27972/61904 [3:58:28<13:27:23, 1.43s/it] 45%|████▌ | 27973/61904 [3:58:30<13:40:26, 1.45s/it] 45%|████▌ | 27974/61904 [3:58:31<13:55:26, 1.48s/it] 45%|████▌ | 27975/61904 [3:58:33<13:51:37, 1.47s/it] 45%|████▌ | 27976/61904 [3:58:34<13:22:27, 1.42s/it] 45%|████▌ | 27977/61904 [3:58:35<13:27:39, 1.43s/it] 45%|████▌ | 27978/61904 [3:58:37<13:16:55, 1.41s/it] 45%|████▌ | 27979/61904 [3:58:38<13:19:23, 1.41s/it] 45%|████▌ | 27980/61904 [3:58:39<13:08:11, 1.39s/it] {'loss': 2.6079, 'learning_rate': 1.5497860754570204e-07, 'epoch': 7.23} + 45%|████▌ | 27980/61904 [3:58:39<13:08:11, 1.39s/it] 45%|█���██▌ | 27981/61904 [3:58:41<13:08:35, 1.39s/it] 45%|████▌ | 27982/61904 [3:58:42<12:58:19, 1.38s/it] 45%|████▌ | 27983/61904 [3:58:44<12:52:42, 1.37s/it] 45%|████▌ | 27984/61904 [3:58:45<12:35:49, 1.34s/it] 45%|████▌ | 27985/61904 [3:58:46<12:46:54, 1.36s/it] 45%|████▌ | 27986/61904 [3:58:48<12:48:30, 1.36s/it] 45%|████▌ | 27987/61904 [3:58:49<12:35:22, 1.34s/it] 45%|████▌ | 27988/61904 [3:58:50<12:32:34, 1.33s/it] 45%|████▌ | 27989/61904 [3:58:52<12:33:19, 1.33s/it] 45%|████▌ | 27990/61904 [3:58:53<12:37:47, 1.34s/it] 45%|████▌ | 27991/61904 [3:58:54<12:45:42, 1.35s/it] 45%|████▌ | 27992/61904 [3:58:56<12:47:38, 1.36s/it] 45%|████▌ | 27993/61904 [3:58:57<12:38:58, 1.34s/it] 45%|████▌ | 27994/61904 [3:58:59<13:15:06, 1.41s/it] 45%|████▌ | 27995/61904 [3:59:00<13:23:31, 1.42s/it] 45%|████▌ | 27996/61904 [3:59:01<13:01:07, 1.38s/it] 45%|████▌ | 27997/61904 [3:59:03<13:07:19, 1.39s/it] 45%|████▌ | 27998/61904 [3:59:04<13:03:40, 1.39s/it] 45%|████▌ | 27999/61904 [3:59:05<12:58:13, 1.38s/it] 45%|████▌ | 28000/61904 [3:59:07<13:12:59, 1.40s/it] {'loss': 2.6051, 'learning_rate': 1.5494619473615973e-07, 'epoch': 7.24} + 45%|████▌ | 28000/61904 [3:59:07<13:12:59, 1.40s/it] 45%|████▌ | 28001/61904 [3:59:08<12:54:27, 1.37s/it] 45%|████▌ | 28002/61904 [3:59:10<12:59:58, 1.38s/it] 45%|████▌ | 28003/61904 [3:59:11<12:48:19, 1.36s/it] 45%|████▌ | 28004/61904 [3:59:12<13:09:45, 1.40s/it] 45%|████▌ | 28005/61904 [3:59:14<13:08:33, 1.40s/it] 45%|████▌ | 28006/61904 [3:59:15<13:17:20, 1.41s/it] 45%|████▌ | 28007/61904 [3:59:17<12:58:27, 1.38s/it] 45%|████▌ | 28008/61904 [3:59:18<12:59:17, 1.38s/it] 45%|████▌ | 28009/61904 [3:59:19<12:58:02, 1.38s/it] 45%|████▌ | 28010/61904 [3:59:21<12:48:34, 1.36s/it] 45%|████▌ | 28011/61904 [3:59:22<12:36:59, 1.34s/it] 45%|████▌ | 28012/61904 [3:59:23<12:37:46, 1.34s/it] 45%|████▌ | 28013/61904 [3:59:25<12:30:31, 1.33s/it] 45%|████▌ | 28014/61904 [3:59:26<12:20:40, 1.31s/it] 45%|████▌ | 28015/61904 [3:59:27<12:52:28, 1.37s/it] 45%|████▌ | 28016/61904 [3:59:29<12:42:54, 1.35s/it] 45%|████▌ | 28017/61904 [3:59:30<12:27:44, 1.32s/it] 45%|████▌ | 28018/61904 [3:59:31<12:58:03, 1.38s/it] 45%|████▌ | 28019/61904 [3:59:33<12:47:21, 1.36s/it] 45%|████▌ | 28020/61904 [3:59:34<13:23:58, 1.42s/it] {'loss': 2.6275, 'learning_rate': 1.549137819266174e-07, 'epoch': 7.24} + 45%|████▌ | 28020/61904 [3:59:34<13:23:58, 1.42s/it] 45%|████▌ | 28021/61904 [3:59:36<13:05:35, 1.39s/it] 45%|████▌ | 28022/61904 [3:59:37<12:41:51, 1.35s/it] 45%|████▌ | 28023/61904 [3:59:38<12:28:15, 1.33s/it] 45%|████▌ | 28024/61904 [3:59:40<12:49:22, 1.36s/it] 45%|████▌ | 28025/61904 [3:59:41<12:36:18, 1.34s/it] 45%|████▌ | 28026/61904 [3:59:42<12:26:10, 1.32s/it] 45%|████▌ | 28027/61904 [3:59:43<12:27:43, 1.32s/it] 45%|████▌ | 28028/61904 [3:59:45<12:22:49, 1.32s/it] 45%|████▌ | 28029/61904 [3:59:46<12:33:55, 1.34s/it] 45%|████▌ | 28030/61904 [3:59:48<13:40:18, 1.45s/it] 45%|████▌ | 28031/61904 [3:59:49<13:23:59, 1.42s/it] 45%|████▌ | 28032/61904 [3:59:51<13:19:12, 1.42s/it] 45%|████▌ | 28033/61904 [3:59:52<13:25:18, 1.43s/it] 45%|████▌ | 28034/61904 [3:59:53<13:14:20, 1.41s/it] 45%|████▌ | 28035/61904 [3:59:55<13:19:32, 1.42s/it] 45%|████▌ | 28036/61904 [3:59:56<13:17:20, 1.41s/it] 45%|████▌ | 28037/61904 [3:59:58<13:24:18, 1.42s/it] 45%|████▌ | 28038/61904 [3:59:59<13:06:24, 1.39s/it] 45%|████▌ | 28039/61904 [4:00:00<13:06:54, 1.39s/it] 45%|████▌ | 28040/61904 [4:00:02<13:03:31, 1.39s/it] {'loss': 2.6114, 'learning_rate': 1.5488136911707505e-07, 'epoch': 7.25} + 45%|████▌ | 28040/61904 [4:00:02<13:03:31, 1.39s/it] 45%|████▌ | 28041/61904 [4:00:03<12:44:12, 1.35s/it] 45%|████▌ | 28042/61904 [4:00:05<13:27:57, 1.43s/it] 45%|████▌ | 28043/61904 [4:00:06<13:01:55, 1.39s/it] 45%|████▌ | 28044/61904 [4:00:07<13:02:52, 1.39s/it] 45%|████▌ | 28045/61904 [4:00:09<12:49:47, 1.36s/it] 45%|████▌ | 28046/61904 [4:00:10<12:30:20, 1.33s/it] 45%|████▌ | 28047/61904 [4:00:11<12:35:10, 1.34s/it] 45%|████▌ | 28048/61904 [4:00:13<12:21:37, 1.31s/it] 45%|████▌ | 28049/61904 [4:00:14<11:57:35, 1.27s/it] 45%|████▌ | 28050/61904 [4:00:15<12:34:38, 1.34s/it] 45%|████▌ | 28051/61904 [4:00:16<12:25:34, 1.32s/it] 45%|████▌ | 28052/61904 [4:00:18<12:17:08, 1.31s/it] 45%|████▌ | 28053/61904 [4:00:19<12:21:10, 1.31s/it] 45%|████▌ | 28054/61904 [4:00:20<12:10:50, 1.30s/it] 45%|████▌ | 28055/61904 [4:00:22<12:20:21, 1.31s/it] 45%|████▌ | 28056/61904 [4:00:23<12:24:10, 1.32s/it] 45%|████▌ | 28057/61904 [4:00:24<12:32:21, 1.33s/it] 45%|████▌ | 28058/61904 [4:00:26<12:37:49, 1.34s/it] 45%|████▌ | 28059/61904 [4:00:27<13:25:10, 1.43s/it] 45%|████▌ | 28060/61904 [4:00:29<13:10:48, 1.40s/it] {'loss': 2.6532, 'learning_rate': 1.5484895630753274e-07, 'epoch': 7.25} + 45%|████▌ | 28060/61904 [4:00:29<13:10:48, 1.40s/it] 45%|████▌ | 28061/61904 [4:00:30<13:05:58, 1.39s/it] 45%|████▌ | 28062/61904 [4:00:32<13:30:01, 1.44s/it] 45%|████▌ | 28063/61904 [4:00:33<13:11:28, 1.40s/it] 45%|████▌ | 28064/61904 [4:00:34<13:21:14, 1.42s/it] 45%|████▌ | 28065/61904 [4:00:36<13:34:17, 1.44s/it] 45%|████▌ | 28066/61904 [4:00:37<13:19:19, 1.42s/it] 45%|████▌ | 28067/61904 [4:00:39<12:52:04, 1.37s/it] 45%|████▌ | 28068/61904 [4:00:40<12:48:34, 1.36s/it] 45%|████▌ | 28069/61904 [4:00:41<12:42:55, 1.35s/it] 45%|████▌ | 28070/61904 [4:00:43<12:47:50, 1.36s/it] 45%|████▌ | 28071/61904 [4:00:44<13:15:46, 1.41s/it] 45%|████▌ | 28072/61904 [4:00:45<13:07:33, 1.40s/it] 45%|████▌ | 28073/61904 [4:00:47<13:04:51, 1.39s/it] 45%|████▌ | 28074/61904 [4:00:48<13:06:42, 1.40s/it] 45%|████▌ | 28075/61904 [4:00:49<12:37:09, 1.34s/it] 45%|████▌ | 28076/61904 [4:00:51<12:54:05, 1.37s/it] 45%|████▌ | 28077/61904 [4:00:52<12:56:36, 1.38s/it] 45%|████▌ | 28078/61904 [4:00:54<12:50:48, 1.37s/it] 45%|████▌ | 28079/61904 [4:00:55<12:51:55, 1.37s/it] 45%|████▌ | 28080/61904 [4:00:56<12:49:55, 1.37s/it] {'loss': 2.5954, 'learning_rate': 1.548165434979904e-07, 'epoch': 7.26} + 45%|████▌ | 28080/61904 [4:00:56<12:49:55, 1.37s/it] 45%|████▌ | 28081/61904 [4:00:58<12:56:20, 1.38s/it] 45%|████▌ | 28082/61904 [4:00:59<12:50:54, 1.37s/it] 45%|████▌ | 28083/61904 [4:01:01<12:57:34, 1.38s/it] 45%|████▌ | 28084/61904 [4:01:02<12:52:02, 1.37s/it] 45%|████▌ | 28085/61904 [4:01:03<12:38:01, 1.34s/it] 45%|████▌ | 28086/61904 [4:01:05<12:42:02, 1.35s/it] 45%|████▌ | 28087/61904 [4:01:06<12:49:31, 1.37s/it] 45%|████▌ | 28088/61904 [4:01:07<12:58:10, 1.38s/it] 45%|████▌ | 28089/61904 [4:01:09<13:00:12, 1.38s/it] 45%|████▌ | 28090/61904 [4:01:10<12:57:18, 1.38s/it] 45%|████▌ | 28091/61904 [4:01:12<12:59:35, 1.38s/it] 45%|████▌ | 28092/61904 [4:01:13<12:53:48, 1.37s/it] 45%|████▌ | 28093/61904 [4:01:14<12:46:57, 1.36s/it] 45%|████▌ | 28094/61904 [4:01:15<12:33:41, 1.34s/it] 45%|████▌ | 28095/61904 [4:01:17<12:59:37, 1.38s/it] 45%|████▌ | 28096/61904 [4:01:18<12:54:52, 1.38s/it] 45%|████▌ | 28097/61904 [4:01:20<12:55:30, 1.38s/it] 45%|████▌ | 28098/61904 [4:01:21<13:00:35, 1.39s/it] 45%|████▌ | 28099/61904 [4:01:23<13:20:16, 1.42s/it] 45%|████▌ | 28100/61904 [4:01:24<13:17:49, 1.42s/it] {'loss': 2.555, 'learning_rate': 1.5478413068844806e-07, 'epoch': 7.26} + 45%|████▌ | 28100/61904 [4:01:24<13:17:49, 1.42s/it] 45%|████▌ | 28101/61904 [4:01:25<13:03:50, 1.39s/it] 45%|████▌ | 28102/61904 [4:01:27<12:32:39, 1.34s/it] 45%|████▌ | 28103/61904 [4:01:28<12:07:49, 1.29s/it] 45%|████▌ | 28104/61904 [4:01:29<12:37:09, 1.34s/it] 45%|████▌ | 28105/61904 [4:01:31<12:38:34, 1.35s/it] 45%|████▌ | 28106/61904 [4:01:32<12:34:46, 1.34s/it] 45%|████▌ | 28107/61904 [4:01:33<12:40:27, 1.35s/it] 45%|████▌ | 28108/61904 [4:01:35<12:58:26, 1.38s/it] 45%|████▌ | 28109/61904 [4:01:36<13:00:20, 1.39s/it] 45%|████▌ | 28110/61904 [4:01:38<13:03:04, 1.39s/it] 45%|████▌ | 28111/61904 [4:01:39<12:52:25, 1.37s/it] 45%|████▌ | 28112/61904 [4:01:40<13:11:25, 1.41s/it] 45%|████▌ | 28113/61904 [4:01:42<12:55:32, 1.38s/it] 45%|████▌ | 28114/61904 [4:01:43<12:38:56, 1.35s/it] 45%|████▌ | 28115/61904 [4:01:44<12:21:59, 1.32s/it] 45%|████▌ | 28116/61904 [4:01:45<12:15:18, 1.31s/it] 45%|████▌ | 28117/61904 [4:01:47<12:12:03, 1.30s/it] 45%|████▌ | 28118/61904 [4:01:48<12:43:59, 1.36s/it] 45%|████▌ | 28119/61904 [4:01:50<12:39:38, 1.35s/it] 45%|████▌ | 28120/61904 [4:01:51<12:54:59, 1.38s/it] {'loss': 2.601, 'learning_rate': 1.5475171787890573e-07, 'epoch': 7.27} + 45%|████▌ | 28120/61904 [4:01:51<12:54:59, 1.38s/it] 45%|████▌ | 28121/61904 [4:01:53<13:21:16, 1.42s/it] 45%|████▌ | 28122/61904 [4:01:54<13:07:16, 1.40s/it] 45%|████▌ | 28123/61904 [4:01:55<13:21:36, 1.42s/it] 45%|████▌ | 28124/61904 [4:01:57<12:57:49, 1.38s/it] 45%|████▌ | 28125/61904 [4:01:58<13:13:31, 1.41s/it] 45%|████▌ | 28126/61904 [4:02:00<13:30:39, 1.44s/it] 45%|████▌ | 28127/61904 [4:02:01<13:20:12, 1.42s/it] 45%|████▌ | 28128/61904 [4:02:02<13:05:16, 1.39s/it] 45%|████▌ | 28129/61904 [4:02:04<12:54:10, 1.38s/it] 45%|████▌ | 28130/61904 [4:02:05<12:46:26, 1.36s/it] 45%|████▌ | 28131/61904 [4:02:06<12:39:40, 1.35s/it] 45%|████▌ | 28132/61904 [4:02:08<12:29:55, 1.33s/it] 45%|████▌ | 28133/61904 [4:02:09<12:29:55, 1.33s/it] 45%|████▌ | 28134/61904 [4:02:10<12:46:00, 1.36s/it] 45%|████▌ | 28135/61904 [4:02:12<12:27:09, 1.33s/it] 45%|████▌ | 28136/61904 [4:02:13<12:26:15, 1.33s/it] 45%|████▌ | 28137/61904 [4:02:14<12:10:03, 1.30s/it] 45%|████▌ | 28138/61904 [4:02:16<12:32:40, 1.34s/it] 45%|████▌ | 28139/61904 [4:02:17<12:41:15, 1.35s/it] 45%|████▌ | 28140/61904 [4:02:18<12:44:02, 1.36s/it] {'loss': 2.5666, 'learning_rate': 1.547193050693634e-07, 'epoch': 7.27} + 45%|████▌ | 28140/61904 [4:02:18<12:44:02, 1.36s/it] 45%|████▌ | 28141/61904 [4:02:20<12:58:24, 1.38s/it] 45%|████▌ | 28142/61904 [4:02:21<13:12:49, 1.41s/it] 45%|████▌ | 28143/61904 [4:02:23<13:08:55, 1.40s/it] 45%|████▌ | 28144/61904 [4:02:24<12:50:48, 1.37s/it] 45%|████▌ | 28145/61904 [4:02:25<13:00:11, 1.39s/it] 45%|████▌ | 28146/61904 [4:02:27<12:45:44, 1.36s/it] 45%|████▌ | 28147/61904 [4:02:28<12:55:19, 1.38s/it] 45%|████▌ | 28148/61904 [4:02:30<13:08:34, 1.40s/it] 45%|████▌ | 28149/61904 [4:02:31<12:58:44, 1.38s/it] 45%|████▌ | 28150/61904 [4:02:32<12:45:40, 1.36s/it] 45%|████▌ | 28151/61904 [4:02:34<13:07:27, 1.40s/it] 45%|████▌ | 28152/61904 [4:02:35<12:44:13, 1.36s/it] 45%|████▌ | 28153/61904 [4:02:36<12:37:02, 1.35s/it] 45%|████▌ | 28154/61904 [4:02:38<12:20:54, 1.32s/it] 45%|████▌ | 28155/61904 [4:02:39<12:47:30, 1.36s/it] 45%|████▌ | 28156/61904 [4:02:40<13:01:50, 1.39s/it] 45%|████▌ | 28157/61904 [4:02:42<12:55:32, 1.38s/it] 45%|████▌ | 28158/61904 [4:02:43<13:16:15, 1.42s/it] 45%|████▌ | 28159/61904 [4:02:45<12:58:50, 1.38s/it] 45%|████▌ | 28160/61904 [4:02:46<12:49:52, 1.37s/it] {'loss': 2.563, 'learning_rate': 1.5468689225982108e-07, 'epoch': 7.28} + 45%|████▌ | 28160/61904 [4:02:46<12:49:52, 1.37s/it] 45%|████▌ | 28161/61904 [4:02:47<12:43:04, 1.36s/it] 45%|████▌ | 28162/61904 [4:02:49<12:57:43, 1.38s/it] 45%|████▌ | 28163/61904 [4:02:50<13:07:13, 1.40s/it] 45%|████▌ | 28164/61904 [4:02:52<13:06:46, 1.40s/it] 45%|████▌ | 28165/61904 [4:02:53<13:02:19, 1.39s/it] 45%|████▌ | 28166/61904 [4:02:54<13:11:09, 1.41s/it] 46%|████▌ | 28167/61904 [4:02:56<12:48:59, 1.37s/it] 46%|████▌ | 28168/61904 [4:02:57<12:45:13, 1.36s/it] 46%|████▌ | 28169/61904 [4:02:58<12:27:06, 1.33s/it] 46%|████▌ | 28170/61904 [4:03:00<12:32:02, 1.34s/it] 46%|████▌ | 28171/61904 [4:03:01<12:44:22, 1.36s/it] 46%|████▌ | 28172/61904 [4:03:02<12:48:51, 1.37s/it] 46%|████▌ | 28173/61904 [4:03:04<13:13:03, 1.41s/it] 46%|████▌ | 28174/61904 [4:03:05<13:06:06, 1.40s/it] 46%|████▌ | 28175/61904 [4:03:07<13:11:14, 1.41s/it] 46%|████▌ | 28176/61904 [4:03:08<13:10:19, 1.41s/it] 46%|████▌ | 28177/61904 [4:03:09<12:57:52, 1.38s/it] 46%|████▌ | 28178/61904 [4:03:11<13:02:26, 1.39s/it] 46%|████▌ | 28179/61904 [4:03:12<13:24:24, 1.43s/it] 46%|████▌ | 28180/61904 [4:03:14<13:16:52, 1.42s/it] {'loss': 2.5919, 'learning_rate': 1.5465447945027874e-07, 'epoch': 7.28} + 46%|████▌ | 28180/61904 [4:03:14<13:16:52, 1.42s/it] 46%|████▌ | 28181/61904 [4:03:15<13:07:24, 1.40s/it] 46%|████▌ | 28182/61904 [4:03:16<12:59:11, 1.39s/it] 46%|████▌ | 28183/61904 [4:03:18<13:00:10, 1.39s/it] 46%|████▌ | 28184/61904 [4:03:19<13:06:36, 1.40s/it] 46%|████▌ | 28185/61904 [4:03:21<13:22:07, 1.43s/it] 46%|████▌ | 28186/61904 [4:03:22<13:12:43, 1.41s/it] 46%|████▌ | 28187/61904 [4:03:24<13:11:50, 1.41s/it] 46%|████▌ | 28188/61904 [4:03:25<13:02:16, 1.39s/it] 46%|████▌ | 28189/61904 [4:03:26<13:19:17, 1.42s/it] 46%|████▌ | 28190/61904 [4:03:28<13:28:17, 1.44s/it] 46%|████▌ | 28191/61904 [4:03:29<13:11:59, 1.41s/it] 46%|████▌ | 28192/61904 [4:03:31<12:53:09, 1.38s/it] 46%|████▌ | 28193/61904 [4:03:32<12:47:33, 1.37s/it] 46%|████▌ | 28194/61904 [4:03:33<12:52:02, 1.37s/it] 46%|████▌ | 28195/61904 [4:03:35<12:56:30, 1.38s/it] 46%|████▌ | 28196/61904 [4:03:36<12:31:00, 1.34s/it] 46%|████▌ | 28197/61904 [4:03:37<12:30:17, 1.34s/it] 46%|████▌ | 28198/61904 [4:03:39<12:25:54, 1.33s/it] 46%|████▌ | 28199/61904 [4:03:40<12:25:45, 1.33s/it] 46%|████▌ | 28200/61904 [4:03:41<12:30:35, 1.34s/it] {'loss': 2.5042, 'learning_rate': 1.546220666407364e-07, 'epoch': 7.29} + 46%|████▌ | 28200/61904 [4:03:41<12:30:35, 1.34s/it] 46%|████▌ | 28201/61904 [4:03:43<12:50:04, 1.37s/it] 46%|████▌ | 28202/61904 [4:03:44<13:03:05, 1.39s/it] 46%|████▌ | 28203/61904 [4:03:46<13:14:53, 1.42s/it] 46%|████▌ | 28204/61904 [4:03:47<13:45:19, 1.47s/it] 46%|████▌ | 28205/61904 [4:03:48<13:14:28, 1.41s/it] 46%|████▌ | 28206/61904 [4:03:50<13:21:53, 1.43s/it] 46%|████▌ | 28207/61904 [4:03:51<13:06:42, 1.40s/it] 46%|████▌ | 28208/61904 [4:03:53<12:57:16, 1.38s/it] 46%|████▌ | 28209/61904 [4:03:54<13:03:33, 1.40s/it] 46%|████▌ | 28210/61904 [4:03:55<12:46:01, 1.36s/it] 46%|████▌ | 28211/61904 [4:03:57<12:38:00, 1.35s/it] 46%|████▌ | 28212/61904 [4:03:58<13:20:20, 1.43s/it] 46%|████▌ | 28213/61904 [4:04:00<13:15:35, 1.42s/it] 46%|████▌ | 28214/61904 [4:04:01<12:54:31, 1.38s/it] 46%|████▌ | 28215/61904 [4:04:02<12:41:13, 1.36s/it] 46%|████▌ | 28216/61904 [4:04:04<12:58:59, 1.39s/it] 46%|████▌ | 28217/61904 [4:04:05<13:05:06, 1.40s/it] 46%|████▌ | 28218/61904 [4:04:06<12:45:27, 1.36s/it] 46%|████▌ | 28219/61904 [4:04:08<12:45:03, 1.36s/it] 46%|████▌ | 28220/61904 [4:04:09<12:46:52, 1.37s/it] {'loss': 2.614, 'learning_rate': 1.545896538311941e-07, 'epoch': 7.29} + 46%|████▌ | 28220/61904 [4:04:09<12:46:52, 1.37s/it] 46%|████▌ | 28221/61904 [4:04:10<12:38:10, 1.35s/it] 46%|████▌ | 28222/61904 [4:04:12<12:35:26, 1.35s/it] 46%|████▌ | 28223/61904 [4:04:13<13:00:19, 1.39s/it] 46%|████▌ | 28224/61904 [4:04:15<12:49:44, 1.37s/it] 46%|████▌ | 28225/61904 [4:04:16<13:04:52, 1.40s/it] 46%|████▌ | 28226/61904 [4:04:17<13:05:14, 1.40s/it] 46%|████▌ | 28227/61904 [4:04:19<13:29:44, 1.44s/it] 46%|████▌ | 28228/61904 [4:04:20<13:24:39, 1.43s/it] 46%|████▌ | 28229/61904 [4:04:22<13:06:23, 1.40s/it] 46%|████▌ | 28230/61904 [4:04:23<13:01:06, 1.39s/it] 46%|████▌ | 28231/61904 [4:04:24<12:27:14, 1.33s/it] 46%|████▌ | 28232/61904 [4:04:26<12:23:38, 1.33s/it] 46%|████▌ | 28233/61904 [4:04:27<12:24:26, 1.33s/it] 46%|████▌ | 28234/61904 [4:04:28<12:30:24, 1.34s/it] 46%|████▌ | 28235/61904 [4:04:30<12:26:40, 1.33s/it] 46%|████▌ | 28236/61904 [4:04:31<12:38:04, 1.35s/it] 46%|████▌ | 28237/61904 [4:04:32<12:47:40, 1.37s/it] 46%|████▌ | 28238/61904 [4:04:34<12:34:06, 1.34s/it] 46%|████▌ | 28239/61904 [4:04:35<12:25:10, 1.33s/it] 46%|████▌ | 28240/61904 [4:04:36<12:32:00, 1.34s/it] {'loss': 2.5763, 'learning_rate': 1.5455724102165175e-07, 'epoch': 7.3} + 46%|████▌ | 28240/61904 [4:04:36<12:32:00, 1.34s/it] 46%|████▌ | 28241/61904 [4:04:38<12:15:59, 1.31s/it] 46%|████▌ | 28242/61904 [4:04:39<12:25:42, 1.33s/it] 46%|████▌ | 28243/61904 [4:04:40<12:42:51, 1.36s/it] 46%|████▌ | 28244/61904 [4:04:42<12:24:33, 1.33s/it] 46%|████▌ | 28245/61904 [4:04:43<12:30:16, 1.34s/it] 46%|████▌ | 28246/61904 [4:04:44<12:10:10, 1.30s/it] 46%|████▌ | 28247/61904 [4:04:45<11:54:45, 1.27s/it] 46%|████▌ | 28248/61904 [4:04:47<12:27:35, 1.33s/it] 46%|████▌ | 28249/61904 [4:04:48<12:48:18, 1.37s/it] 46%|████▌ | 28250/61904 [4:04:50<12:36:24, 1.35s/it] 46%|████▌ | 28251/61904 [4:04:51<13:04:07, 1.40s/it] 46%|████▌ | 28252/61904 [4:04:53<13:05:06, 1.40s/it] 46%|████▌ | 28253/61904 [4:04:54<13:15:30, 1.42s/it] 46%|████▌ | 28254/61904 [4:04:55<12:48:51, 1.37s/it] 46%|████▌ | 28255/61904 [4:04:57<13:06:07, 1.40s/it] 46%|████▌ | 28256/61904 [4:04:58<13:08:45, 1.41s/it] 46%|████▌ | 28257/61904 [4:05:00<12:54:52, 1.38s/it] 46%|████▌ | 28258/61904 [4:05:01<13:01:26, 1.39s/it] 46%|████▌ | 28259/61904 [4:05:02<12:32:35, 1.34s/it] 46%|████▌ | 28260/61904 [4:05:04<12:48:40, 1.37s/it] {'loss': 2.5852, 'learning_rate': 1.545248282121094e-07, 'epoch': 7.3} + 46%|████▌ | 28260/61904 [4:05:04<12:48:40, 1.37s/it] 46%|████▌ | 28261/61904 [4:05:05<12:39:21, 1.35s/it] 46%|████▌ | 28262/61904 [4:05:06<12:47:08, 1.37s/it] 46%|████▌ | 28263/61904 [4:05:08<12:39:01, 1.35s/it] 46%|████▌ | 28264/61904 [4:05:09<12:50:10, 1.37s/it] 46%|████▌ | 28265/61904 [4:05:10<12:47:13, 1.37s/it] 46%|████▌ | 28266/61904 [4:05:12<12:54:28, 1.38s/it] 46%|████▌ | 28267/61904 [4:05:13<13:22:37, 1.43s/it] 46%|████▌ | 28268/61904 [4:05:15<13:00:02, 1.39s/it] 46%|████▌ | 28269/61904 [4:05:16<13:10:14, 1.41s/it] 46%|████▌ | 28270/61904 [4:05:18<13:02:44, 1.40s/it] 46%|████▌ | 28271/61904 [4:05:19<13:14:11, 1.42s/it] 46%|████▌ | 28272/61904 [4:05:21<13:38:15, 1.46s/it] 46%|████▌ | 28273/61904 [4:05:22<14:02:40, 1.50s/it] 46%|████▌ | 28274/61904 [4:05:24<15:28:27, 1.66s/it] 46%|████▌ | 28275/61904 [4:05:25<14:34:19, 1.56s/it] 46%|████▌ | 28276/61904 [4:05:27<14:06:18, 1.51s/it] 46%|████▌ | 28277/61904 [4:05:28<13:31:00, 1.45s/it] 46%|████▌ | 28278/61904 [4:05:30<13:44:46, 1.47s/it] 46%|████▌ | 28279/61904 [4:05:31<13:31:50, 1.45s/it] 46%|████▌ | 28280/61904 [4:05:32<13:11:47, 1.41s/it] {'loss': 2.638, 'learning_rate': 1.544924154025671e-07, 'epoch': 7.31} + 46%|████▌ | 28280/61904 [4:05:32<13:11:47, 1.41s/it] 46%|████▌ | 28281/61904 [4:05:34<12:55:55, 1.38s/it] 46%|████▌ | 28282/61904 [4:05:35<13:06:13, 1.40s/it] 46%|████▌ | 28283/61904 [4:05:36<12:43:17, 1.36s/it] 46%|████▌ | 28284/61904 [4:05:38<12:36:35, 1.35s/it] 46%|████▌ | 28285/61904 [4:05:39<12:41:31, 1.36s/it] 46%|████▌ | 28286/61904 [4:05:41<12:46:24, 1.37s/it] 46%|████▌ | 28287/61904 [4:05:42<12:43:30, 1.36s/it] 46%|████▌ | 28288/61904 [4:05:43<12:46:42, 1.37s/it] 46%|████▌ | 28289/61904 [4:05:45<12:32:12, 1.34s/it] 46%|████▌ | 28290/61904 [4:05:46<12:43:02, 1.36s/it] 46%|████▌ | 28291/61904 [4:05:47<12:30:27, 1.34s/it] 46%|████▌ | 28292/61904 [4:05:49<12:32:54, 1.34s/it] 46%|████▌ | 28293/61904 [4:05:50<12:50:30, 1.38s/it] 46%|████▌ | 28294/61904 [4:05:51<12:50:19, 1.38s/it] 46%|████▌ | 28295/61904 [4:05:53<13:24:47, 1.44s/it] 46%|████▌ | 28296/61904 [4:05:54<13:23:19, 1.43s/it] 46%|████▌ | 28297/61904 [4:05:56<13:49:59, 1.48s/it] 46%|████▌ | 28298/61904 [4:05:57<13:28:07, 1.44s/it] 46%|████▌ | 28299/61904 [4:05:59<13:09:35, 1.41s/it] 46%|████▌ | 28300/61904 [4:06:00<13:10:34, 1.41s/it] {'loss': 2.5642, 'learning_rate': 1.5446000259302476e-07, 'epoch': 7.31} + 46%|████▌ | 28300/61904 [4:06:00<13:10:34, 1.41s/it] 46%|████▌ | 28301/61904 [4:06:01<12:52:41, 1.38s/it] 46%|████▌ | 28302/61904 [4:06:03<13:07:16, 1.41s/it] 46%|████▌ | 28303/61904 [4:06:04<13:10:01, 1.41s/it] 46%|████▌ | 28304/61904 [4:06:06<12:49:07, 1.37s/it] 46%|████�� | 28305/61904 [4:06:07<13:00:27, 1.39s/it] 46%|████▌ | 28306/61904 [4:06:08<12:56:46, 1.39s/it] 46%|████▌ | 28307/61904 [4:06:10<12:40:47, 1.36s/it] 46%|████▌ | 28308/61904 [4:06:11<12:38:28, 1.35s/it] 46%|████▌ | 28309/61904 [4:06:12<12:48:10, 1.37s/it] 46%|████▌ | 28310/61904 [4:06:14<12:22:49, 1.33s/it] 46%|████▌ | 28311/61904 [4:06:15<12:43:51, 1.36s/it] 46%|████▌ | 28312/61904 [4:06:17<12:47:36, 1.37s/it] 46%|████▌ | 28313/61904 [4:06:18<12:38:40, 1.36s/it] 46%|████▌ | 28314/61904 [4:06:19<12:26:13, 1.33s/it] 46%|████▌ | 28315/61904 [4:06:20<12:27:57, 1.34s/it] 46%|████▌ | 28316/61904 [4:06:22<12:26:12, 1.33s/it] 46%|████▌ | 28317/61904 [4:06:23<12:28:19, 1.34s/it] 46%|████▌ | 28318/61904 [4:06:25<12:30:23, 1.34s/it] 46%|████▌ | 28319/61904 [4:06:26<12:31:19, 1.34s/it] 46%|████▌ | 28320/61904 [4:06:27<12:18:41, 1.32s/it] {'loss': 2.5905, 'learning_rate': 1.5442758978348242e-07, 'epoch': 7.32} + 46%|████▌ | 28320/61904 [4:06:27<12:18:41, 1.32s/it] 46%|████▌ | 28321/61904 [4:06:28<12:22:09, 1.33s/it] 46%|████▌ | 28322/61904 [4:06:30<12:30:27, 1.34s/it] 46%|████▌ | 28323/61904 [4:06:31<12:33:25, 1.35s/it] 46%|████▌ | 28324/61904 [4:06:33<12:33:02, 1.35s/it] 46%|████▌ | 28325/61904 [4:06:34<12:46:01, 1.37s/it] 46%|████▌ | 28326/61904 [4:06:35<12:38:29, 1.36s/it] 46%|████▌ | 28327/61904 [4:06:37<13:22:29, 1.43s/it] 46%|████▌ | 28328/61904 [4:06:38<12:58:39, 1.39s/it] 46%|████▌ | 28329/61904 [4:06:40<13:05:14, 1.40s/it] 46%|████▌ | 28330/61904 [4:06:41<12:50:52, 1.38s/it] 46%|████▌ | 28331/61904 [4:06:42<12:54:28, 1.38s/it] 46%|████▌ | 28332/61904 [4:06:44<12:57:37, 1.39s/it] 46%|████▌ | 28333/61904 [4:06:45<13:18:34, 1.43s/it] 46%|████▌ | 28334/61904 [4:06:47<12:50:43, 1.38s/it] 46%|████▌ | 28335/61904 [4:06:48<12:54:53, 1.39s/it] 46%|████▌ | 28336/61904 [4:06:49<12:45:12, 1.37s/it] 46%|████▌ | 28337/61904 [4:06:51<12:43:42, 1.37s/it] 46%|████▌ | 28338/61904 [4:06:52<13:13:26, 1.42s/it] 46%|████▌ | 28339/61904 [4:06:54<13:29:36, 1.45s/it] 46%|████▌ | 28340/61904 [4:06:55<13:32:47, 1.45s/it] {'loss': 2.5641, 'learning_rate': 1.5439517697394009e-07, 'epoch': 7.32} + 46%|████▌ | 28340/61904 [4:06:55<13:32:47, 1.45s/it] 46%|████▌ | 28341/61904 [4:06:57<13:27:31, 1.44s/it] 46%|████▌ | 28342/61904 [4:06:58<13:12:08, 1.42s/it] 46%|████▌ | 28343/61904 [4:06:59<12:50:06, 1.38s/it] 46%|████▌ | 28344/61904 [4:07:01<13:40:06, 1.47s/it] 46%|████▌ | 28345/61904 [4:07:02<13:16:39, 1.42s/it] 46%|████▌ | 28346/61904 [4:07:04<13:34:26, 1.46s/it] 46%|████▌ | 28347/61904 [4:07:05<13:10:59, 1.41s/it] 46%|████▌ | 28348/61904 [4:07:07<13:28:23, 1.45s/it] 46%|████▌ | 28349/61904 [4:07:08<13:23:46, 1.44s/it] 46%|████▌ | 28350/61904 [4:07:09<13:20:02, 1.43s/it] 46%|████▌ | 28351/61904 [4:07:11<13:21:13, 1.43s/it] 46%|████▌ | 28352/61904 [4:07:12<13:01:18, 1.40s/it] 46%|████▌ | 28353/61904 [4:07:13<12:50:45, 1.38s/it] 46%|████▌ | 28354/61904 [4:07:15<12:56:30, 1.39s/it] 46%|████▌ | 28355/61904 [4:07:16<13:18:36, 1.43s/it] 46%|████▌ | 28356/61904 [4:07:18<13:06:03, 1.41s/it] 46%|████▌ | 28357/61904 [4:07:19<12:56:53, 1.39s/it] 46%|████▌ | 28358/61904 [4:07:20<12:41:22, 1.36s/it] 46%|████▌ | 28359/61904 [4:07:22<13:03:02, 1.40s/it] 46%|████▌ | 28360/61904 [4:07:23<13:16:50, 1.43s/it] {'loss': 2.5369, 'learning_rate': 1.5436276416439775e-07, 'epoch': 7.33} + 46%|████▌ | 28360/61904 [4:07:23<13:16:50, 1.43s/it] 46%|████▌ | 28361/61904 [4:07:25<13:22:30, 1.44s/it] 46%|████▌ | 28362/61904 [4:07:26<13:26:44, 1.44s/it] 46%|████▌ | 28363/61904 [4:07:28<13:08:00, 1.41s/it] 46%|████▌ | 28364/61904 [4:07:29<13:07:42, 1.41s/it] 46%|████▌ | 28365/61904 [4:07:30<12:55:55, 1.39s/it] 46%|████▌ | 28366/61904 [4:07:32<12:56:20, 1.39s/it] 46%|████▌ | 28367/61904 [4:07:33<12:37:56, 1.36s/it] 46%|████▌ | 28368/61904 [4:07:35<12:53:41, 1.38s/it] 46%|████▌ | 28369/61904 [4:07:36<13:04:46, 1.40s/it] 46%|████▌ | 28370/61904 [4:07:38<13:30:23, 1.45s/it] 46%|████▌ | 28371/61904 [4:07:39<13:09:31, 1.41s/it] 46%|████▌ | 28372/61904 [4:07:40<13:26:48, 1.44s/it] 46%|████▌ | 28373/61904 [4:07:42<13:06:32, 1.41s/it] 46%|████▌ | 28374/61904 [4:07:43<13:01:35, 1.40s/it] 46%|████▌ | 28375/61904 [4:07:44<12:46:36, 1.37s/it] 46%|████▌ | 28376/61904 [4:07:46<12:49:42, 1.38s/it] 46%|████▌ | 28377/61904 [4:07:47<13:07:38, 1.41s/it] 46%|████▌ | 28378/61904 [4:07:49<12:51:39, 1.38s/it] 46%|████▌ | 28379/61904 [4:07:50<12:33:49, 1.35s/it] 46%|████▌ | 28380/61904 [4:07:51<12:38:00, 1.36s/it] {'loss': 2.5828, 'learning_rate': 1.5433035135485544e-07, 'epoch': 7.33} + 46%|████▌ | 28380/61904 [4:07:51<12:38:00, 1.36s/it] 46%|████▌ | 28381/61904 [4:07:53<13:06:59, 1.41s/it] 46%|████▌ | 28382/61904 [4:07:54<13:06:39, 1.41s/it] 46%|████▌ | 28383/61904 [4:07:55<12:58:02, 1.39s/it] 46%|████▌ | 28384/61904 [4:07:57<12:57:29, 1.39s/it] 46%|████▌ | 28385/61904 [4:07:58<13:13:28, 1.42s/it] 46%|████▌ | 28386/61904 [4:08:00<13:15:00, 1.42s/it] 46%|████▌ | 28387/61904 [4:08:01<12:58:29, 1.39s/it] 46%|████▌ | 28388/61904 [4:08:03<13:01:25, 1.40s/it] 46%|████▌ | 28389/61904 [4:08:04<13:21:19, 1.43s/it] 46%|████▌ | 28390/61904 [4:08:05<13:03:55, 1.40s/it] 46%|████▌ | 28391/61904 [4:08:07<13:09:13, 1.41s/it] 46%|████▌ | 28392/61904 [4:08:08<12:58:50, 1.39s/it] 46%|████▌ | 28393/61904 [4:08:10<13:31:22, 1.45s/it] 46%|████▌ | 28394/61904 [4:08:11<13:01:09, 1.40s/it] 46%|████▌ | 28395/61904 [4:08:12<12:39:26, 1.36s/it] 46%|████▌ | 28396/61904 [4:08:14<13:11:54, 1.42s/it] 46%|████▌ | 28397/61904 [4:08:15<13:03:53, 1.40s/it] 46%|████▌ | 28398/61904 [4:08:17<13:20:52, 1.43s/it] 46%|████▌ | 28399/61904 [4:08:18<13:10:37, 1.42s/it] 46%|████▌ | 28400/61904 [4:08:20<13:31:50, 1.45s/it] {'loss': 2.6183, 'learning_rate': 1.542979385453131e-07, 'epoch': 7.34} + 46%|████▌ | 28400/61904 [4:08:20<13:31:50, 1.45s/it] 46%|████▌ | 28401/61904 [4:08:21<13:35:45, 1.46s/it] 46%|████▌ | 28402/61904 [4:08:23<13:25:49, 1.44s/it] 46%|████▌ | 28403/61904 [4:08:24<13:33:32, 1.46s/it] 46%|████▌ | 28404/61904 [4:08:25<13:34:33, 1.46s/it] 46%|████▌ | 28405/61904 [4:08:27<13:29:02, 1.45s/it] 46%|████▌ | 28406/61904 [4:08:28<13:38:40, 1.47s/it] 46%|████▌ | 28407/61904 [4:08:30<13:36:15, 1.46s/it] 46%|████▌ | 28408/61904 [4:08:31<13:32:56, 1.46s/it] 46%|████▌ | 28409/61904 [4:08:33<13:16:11, 1.43s/it] 46%|████▌ | 28410/61904 [4:08:34<13:16:46, 1.43s/it] 46%|████▌ | 28411/61904 [4:08:36<13:15:24, 1.42s/it] 46%|████▌ | 28412/61904 [4:08:37<13:43:40, 1.48s/it] 46%|████▌ | 28413/61904 [4:08:38<13:13:00, 1.42s/it] 46%|████▌ | 28414/61904 [4:08:40<13:07:08, 1.41s/it] 46%|████▌ | 28415/61904 [4:08:41<12:52:54, 1.38s/it] 46%|████▌ | 28416/61904 [4:08:43<13:20:39, 1.43s/it] 46%|████▌ | 28417/61904 [4:08:44<13:05:57, 1.41s/it] 46%|████▌ | 28418/61904 [4:08:45<13:14:15, 1.42s/it] 46%|████▌ | 28419/61904 [4:08:47<13:18:00, 1.43s/it] 46%|████▌ | 28420/61904 [4:08:48<12:51:52, 1.38s/it] {'loss': 2.5041, 'learning_rate': 1.5426552573577076e-07, 'epoch': 7.35} + 46%|████▌ | 28420/61904 [4:08:48<12:51:52, 1.38s/it] 46%|████▌ | 28421/61904 [4:08:50<12:41:59, 1.37s/it] 46%|████▌ | 28422/61904 [4:08:51<12:39:01, 1.36s/it] 46%|████▌ | 28423/61904 [4:08:52<12:38:58, 1.36s/it] 46%|████▌ | 28424/61904 [4:08:54<13:04:33, 1.41s/it] 46%|████▌ | 28425/61904 [4:08:55<13:02:03, 1.40s/it] 46%|████▌ | 28426/61904 [4:08:57<13:01:59, 1.40s/it] 46%|████▌ | 28427/61904 [4:08:58<13:33:05, 1.46s/it] 46%|████▌ | 28428/61904 [4:08:59<13:14:47, 1.42s/it] 46%|████▌ | 28429/61904 [4:09:01<13:06:59, 1.41s/it] 46%|████▌ | 28430/61904 [4:09:02<12:52:57, 1.39s/it] 46%|████▌ | 28431/61904 [4:09:04<13:03:07, 1.40s/it] 46%|████▌ | 28432/61904 [4:09:05<12:45:26, 1.37s/it] 46%|████▌ | 28433/61904 [4:09:06<12:56:17, 1.39s/it] 46%|████▌ | 28434/61904 [4:09:08<12:51:22, 1.38s/it] 46%|████▌ | 28435/61904 [4:09:09<13:07:37, 1.41s/it] 46%|████▌ | 28436/61904 [4:09:11<13:01:00, 1.40s/it] 46%|████▌ | 28437/61904 [4:09:12<12:40:04, 1.36s/it] 46%|████▌ | 28438/61904 [4:09:13<12:40:06, 1.36s/it] 46%|████▌ | 28439/61904 [4:09:15<12:54:18, 1.39s/it] 46%|████▌ | 28440/61904 [4:09:16<12:56:18, 1.39s/it] {'loss': 2.6381, 'learning_rate': 1.5423311292622845e-07, 'epoch': 7.35} + 46%|████▌ | 28440/61904 [4:09:16<12:56:18, 1.39s/it] 46%|████▌ | 28441/61904 [4:09:17<12:28:15, 1.34s/it] 46%|████▌ | 28442/61904 [4:09:19<12:24:21, 1.33s/it] 46%|████▌ | 28443/61904 [4:09:20<12:44:47, 1.37s/it] 46%|████▌ | 28444/61904 [4:09:22<13:26:27, 1.45s/it] 46%|████▌ | 28445/61904 [4:09:23<13:06:19, 1.41s/it] 46%|████▌ | 28446/61904 [4:09:24<12:55:24, 1.39s/it] 46%|████▌ | 28447/61904 [4:09:26<12:43:46, 1.37s/it] 46%|████▌ | 28448/61904 [4:09:27<12:58:37, 1.40s/it] 46%|████▌ | 28449/61904 [4:09:28<12:50:29, 1.38s/it] 46%|████▌ | 28450/61904 [4:09:30<13:07:49, 1.41s/it] 46%|████▌ | 28451/61904 [4:09:31<13:25:11, 1.44s/it] 46%|████▌ | 28452/61904 [4:09:33<13:23:45, 1.44s/it] 46%|████▌ | 28453/61904 [4:09:34<12:59:19, 1.40s/it] 46%|████▌ | 28454/61904 [4:09:36<12:47:29, 1.38s/it] 46%|████▌ | 28455/61904 [4:09:37<12:40:37, 1.36s/it] 46%|████▌ | 28456/61904 [4:09:38<13:00:12, 1.40s/it] 46%|████▌ | 28457/61904 [4:09:40<13:18:01, 1.43s/it] 46%|████▌ | 28458/61904 [4:09:41<13:16:11, 1.43s/it] 46%|████▌ | 28459/61904 [4:09:43<13:39:11, 1.47s/it] 46%|████▌ | 28460/61904 [4:09:44<13:29:07, 1.45s/it] {'loss': 2.607, 'learning_rate': 1.542007001166861e-07, 'epoch': 7.36} + 46%|████▌ | 28460/61904 [4:09:44<13:29:07, 1.45s/it] 46%|████▌ | 28461/61904 [4:09:46<13:13:51, 1.42s/it] 46%|████▌ | 28462/61904 [4:09:47<12:57:57, 1.40s/it] 46%|████▌ | 28463/61904 [4:09:48<12:53:48, 1.39s/it] 46%|████▌ | 28464/61904 [4:09:50<12:39:11, 1.36s/it] 46%|████▌ | 28465/61904 [4:09:51<12:37:46, 1.36s/it] 46%|████▌ | 28466/61904 [4:09:52<12:29:13, 1.34s/it] 46%|████▌ | 28467/61904 [4:09:54<12:28:21, 1.34s/it] 46%|████▌ | 28468/61904 [4:09:55<12:42:36, 1.37s/it] 46%|████▌ | 28469/61904 [4:09:57<13:09:08, 1.42s/it] 46%|████▌ | 28470/61904 [4:09:58<12:54:32, 1.39s/it] 46%|████▌ | 28471/61904 [4:09:59<12:49:04, 1.38s/it] 46%|████▌ | 28472/61904 [4:10:01<12:52:01, 1.39s/it] 46%|████▌ | 28473/61904 [4:10:02<12:59:11, 1.40s/it] 46%|████▌ | 28474/61904 [4:10:04<13:29:54, 1.45s/it] 46%|████▌ | 28475/61904 [4:10:05<13:21:24, 1.44s/it] 46%|████▌ | 28476/61904 [4:10:06<12:52:13, 1.39s/it] 46%|████▌ | 28477/61904 [4:10:08<12:54:23, 1.39s/it] 46%|████▌ | 28478/61904 [4:10:09<12:42:24, 1.37s/it] 46%|████▌ | 28479/61904 [4:10:11<13:06:06, 1.41s/it] 46%|████▌ | 28480/61904 [4:10:12<13:01:59, 1.40s/it] {'loss': 2.5654, 'learning_rate': 1.5416828730714377e-07, 'epoch': 7.36} + 46%|████▌ | 28480/61904 [4:10:12<13:01:59, 1.40s/it] 46%|████▌ | 28481/61904 [4:10:13<13:01:45, 1.40s/it] 46%|████▌ | 28482/61904 [4:10:15<12:37:54, 1.36s/it] 46%|████▌ | 28483/61904 [4:10:16<13:05:47, 1.41s/it] 46%|████▌ | 28484/61904 [4:10:18<13:00:01, 1.40s/it] 46%|████▌ | 28485/61904 [4:10:19<12:51:57, 1.39s/it] 46%|████▌ | 28486/61904 [4:10:20<12:37:12, 1.36s/it] 46%|████▌ | 28487/61904 [4:10:22<12:51:28, 1.39s/it] 46%|████▌ | 28488/61904 [4:10:23<14:01:17, 1.51s/it] 46%|████▌ | 28489/61904 [4:10:25<14:07:11, 1.52s/it] 46%|████▌ | 28490/61904 [4:10:26<13:40:09, 1.47s/it] 46%|████▌ | 28491/61904 [4:10:28<13:22:40, 1.44s/it] 46%|████▌ | 28492/61904 [4:10:29<13:54:29, 1.50s/it] 46%|████▌ | 28493/61904 [4:10:31<13:30:42, 1.46s/it] 46%|████▌ | 28494/61904 [4:10:32<13:34:34, 1.46s/it] 46%|████▌ | 28495/61904 [4:10:34<13:26:28, 1.45s/it] 46%|████▌ | 28496/61904 [4:10:35<13:27:28, 1.45s/it] 46%|████▌ | 28497/61904 [4:10:36<12:57:13, 1.40s/it] 46%|████▌ | 28498/61904 [4:10:38<12:48:49, 1.38s/it] 46%|████▌ | 28499/61904 [4:10:39<12:41:18, 1.37s/it] 46%|████▌ | 28500/61904 [4:10:40<12:59:06, 1.40s/it] {'loss': 2.5333, 'learning_rate': 1.5413587449760143e-07, 'epoch': 7.37} + 46%|████▌ | 28500/61904 [4:10:40<12:59:06, 1.40s/it] 46%|████▌ | 28501/61904 [4:10:42<12:41:52, 1.37s/it] 46%|████▌ | 28502/61904 [4:10:43<12:58:53, 1.40s/it] 46%|████▌ | 28503/61904 [4:10:45<13:06:06, 1.41s/it] 46%|████▌ | 28504/61904 [4:10:46<13:22:03, 1.44s/it] 46%|████▌ | 28505/61904 [4:10:47<13:04:04, 1.41s/it] 46%|████▌ | 28506/61904 [4:10:49<13:12:09, 1.42s/it] 46%|████▌ | 28507/61904 [4:10:50<13:01:48, 1.40s/it] 46%|████▌ | 28508/61904 [4:10:52<13:06:44, 1.41s/it] 46%|████▌ | 28509/61904 [4:10:53<12:54:23, 1.39s/it] 46%|████▌ | 28510/61904 [4:10:54<12:48:56, 1.38s/it] 46%|████▌ | 28511/61904 [4:10:56<13:00:36, 1.40s/it] 46%|████▌ | 28512/61904 [4:10:57<12:56:32, 1.40s/it] 46%|████▌ | 28513/61904 [4:10:59<13:04:23, 1.41s/it] 46%|████▌ | 28514/61904 [4:11:00<12:41:34, 1.37s/it] 46%|████▌ | 28515/61904 [4:11:01<12:39:14, 1.36s/it] 46%|████▌ | 28516/61904 [4:11:03<12:35:59, 1.36s/it] 46%|████▌ | 28517/61904 [4:11:04<12:31:28, 1.35s/it] 46%|████▌ | 28518/61904 [4:11:06<13:10:15, 1.42s/it] 46%|████▌ | 28519/61904 [4:11:07<12:47:20, 1.38s/it] 46%|████▌ | 28520/61904 [4:11:08<12:45:46, 1.38s/it] {'loss': 2.5771, 'learning_rate': 1.5410346168805912e-07, 'epoch': 7.37} + 46%|████▌ | 28520/61904 [4:11:08<12:45:46, 1.38s/it] 46%|████▌ | 28521/61904 [4:11:09<12:21:27, 1.33s/it] 46%|████▌ | 28522/61904 [4:11:11<12:27:28, 1.34s/it] 46%|████▌ | 28523/61904 [4:11:12<13:00:16, 1.40s/it] 46%|████▌ | 28524/61904 [4:11:14<12:52:59, 1.39s/it] 46%|████▌ | 28525/61904 [4:11:15<13:02:36, 1.41s/it] 46%|████▌ | 28526/61904 [4:11:17<12:49:50, 1.38s/it] 46%|████▌ | 28527/61904 [4:11:18<12:55:35, 1.39s/it] 46%|████▌ | 28528/61904 [4:11:19<12:48:26, 1.38s/it] 46%|████▌ | 28529/61904 [4:11:21<13:13:01, 1.43s/it] 46%|████▌ | 28530/61904 [4:11:22<12:47:50, 1.38s/it] 46%|████▌ | 28531/61904 [4:11:23<12:39:42, 1.37s/it] 46%|████▌ | 28532/61904 [4:11:25<12:36:48, 1.36s/it] 46%|████▌ | 28533/61904 [4:11:26<13:22:41, 1.44s/it] 46%|████▌ | 28534/61904 [4:11:28<12:50:47, 1.39s/it] 46%|████▌ | 28535/61904 [4:11:29<12:37:43, 1.36s/it] 46%|████▌ | 28536/61904 [4:11:31<13:10:21, 1.42s/it] 46%|████▌ | 28537/61904 [4:11:32<13:01:20, 1.40s/it] 46%|████▌ | 28538/61904 [4:11:33<12:45:39, 1.38s/it] 46%|████▌ | 28539/61904 [4:11:35<12:53:33, 1.39s/it] 46%|████▌ | 28540/61904 [4:11:36<13:17:54, 1.43s/it] {'loss': 2.5225, 'learning_rate': 1.5407104887851678e-07, 'epoch': 7.38} + 46%|████▌ | 28540/61904 [4:11:36<13:17:54, 1.43s/it] 46%|████▌ | 28541/61904 [4:11:38<13:11:00, 1.42s/it] 46%|████▌ | 28542/61904 [4:11:39<14:10:04, 1.53s/it] 46%|████▌ | 28543/61904 [4:11:41<13:29:56, 1.46s/it] 46%|████▌ | 28544/61904 [4:11:42<13:28:51, 1.45s/it] 46%|████▌ | 28545/61904 [4:11:43<13:15:30, 1.43s/it] 46%|████▌ | 28546/61904 [4:11:45<13:30:34, 1.46s/it] 46%|████▌ | 28547/61904 [4:11:46<13:25:40, 1.45s/it] 46%|████▌ | 28548/61904 [4:11:48<12:57:45, 1.40s/it] 46%|████▌ | 28549/61904 [4:11:49<12:40:54, 1.37s/it] 46%|████▌ | 28550/61904 [4:11:50<12:50:25, 1.39s/it] 46%|████▌ | 28551/61904 [4:11:52<12:52:04, 1.39s/it] 46%|████▌ | 28552/61904 [4:11:53<13:01:29, 1.41s/it] 46%|████▌ | 28553/61904 [4:11:55<13:43:51, 1.48s/it] 46%|████▌ | 28554/61904 [4:11:56<13:56:53, 1.51s/it] 46%|████▌ | 28555/61904 [4:11:58<13:09:17, 1.42s/it] 46%|████▌ | 28556/61904 [4:11:59<12:55:33, 1.40s/it] 46%|████▌ | 28557/61904 [4:12:01<13:26:10, 1.45s/it] 46%|████▌ | 28558/61904 [4:12:02<12:52:30, 1.39s/it] 46%|████▌ | 28559/61904 [4:12:03<12:30:55, 1.35s/it] 46%|████▌ | 28560/61904 [4:12:04<12:31:59, 1.35s/it] {'loss': 2.6159, 'learning_rate': 1.5403863606897445e-07, 'epoch': 7.38} + 46%|████▌ | 28560/61904 [4:12:04<12:31:59, 1.35s/it] 46%|████▌ | 28561/61904 [4:12:06<12:29:45, 1.35s/it] 46%|████▌ | 28562/61904 [4:12:07<12:40:34, 1.37s/it] 46%|████▌ | 28563/61904 [4:12:09<13:04:44, 1.41s/it] 46%|████▌ | 28564/61904 [4:12:10<13:04:22, 1.41s/it] 46%|████▌ | 28565/61904 [4:12:12<13:00:19, 1.40s/it] 46%|████▌ | 28566/61904 [4:12:13<12:51:17, 1.39s/it] 46%|████▌ | 28567/61904 [4:12:14<12:38:59, 1.37s/it] 46%|████▌ | 28568/61904 [4:12:15<12:21:09, 1.33s/it] 46%|████▌ | 28569/61904 [4:12:17<12:24:17, 1.34s/it] 46%|████▌ | 28570/61904 [4:12:18<12:23:55, 1.34s/it] 46%|████▌ | 28571/61904 [4:12:20<12:30:52, 1.35s/it] 46%|████▌ | 28572/61904 [4:12:21<12:43:17, 1.37s/it] 46%|████▌ | 28573/61904 [4:12:22<13:05:51, 1.41s/it] 46%|████▌ | 28574/61904 [4:12:24<13:29:41, 1.46s/it] 46%|████▌ | 28575/61904 [4:12:25<13:11:58, 1.43s/it] 46%|████▌ | 28576/61904 [4:12:27<13:19:26, 1.44s/it] 46%|████▌ | 28577/61904 [4:12:28<13:03:52, 1.41s/it] 46%|████▌ | 28578/61904 [4:12:30<13:19:54, 1.44s/it] 46%|████▌ | 28579/61904 [4:12:31<12:45:52, 1.38s/it] 46%|████▌ | 28580/61904 [4:12:32<12:44:27, 1.38s/it] {'loss': 2.6229, 'learning_rate': 1.540062232594321e-07, 'epoch': 7.39} + 46%|████▌ | 28580/61904 [4:12:32<12:44:27, 1.38s/it] 46%|████▌ | 28581/61904 [4:12:34<12:43:56, 1.38s/it] 46%|████▌ | 28582/61904 [4:12:35<12:38:11, 1.37s/it] 46%|████▌ | 28583/61904 [4:12:36<12:24:12, 1.34s/it] 46%|████▌ | 28584/61904 [4:12:38<12:22:37, 1.34s/it] 46%|████▌ | 28585/61904 [4:12:39<12:41:34, 1.37s/it] 46%|████▌ | 28586/61904 [4:12:40<12:42:10, 1.37s/it] 46%|████▌ | 28587/61904 [4:12:42<12:45:16, 1.38s/it] 46%|████▌ | 28588/61904 [4:12:43<12:29:06, 1.35s/it] 46%|████▌ | 28589/61904 [4:12:44<12:27:46, 1.35s/it] 46%|████▌ | 28590/61904 [4:12:46<12:20:26, 1.33s/it] 46%|████▌ | 28591/61904 [4:12:47<12:26:11, 1.34s/it] 46%|████▌ | 28592/61904 [4:12:48<12:21:18, 1.34s/it] 46%|████▌ | 28593/61904 [4:12:50<12:51:23, 1.39s/it] 46%|████▌ | 28594/61904 [4:12:51<12:21:38, 1.34s/it] 46%|████▌ | 28595/61904 [4:12:53<12:42:51, 1.37s/it] 46%|████▌ | 28596/61904 [4:12:54<12:54:19, 1.39s/it] 46%|████▌ | 28597/61904 [4:12:55<12:42:22, 1.37s/it] 46%|████▌ | 28598/61904 [4:12:57<12:16:03, 1.33s/it] 46%|████▌ | 28599/61904 [4:12:58<12:14:59, 1.32s/it] 46%|████▌ | 28600/61904 [4:12:59<12:28:55, 1.35s/it] {'loss': 2.5326, 'learning_rate': 1.539738104498898e-07, 'epoch': 7.39} + 46%|████▌ | 28600/61904 [4:12:59<12:28:55, 1.35s/it] 46%|████▌ | 28601/61904 [4:13:01<12:51:56, 1.39s/it] 46%|████▌ | 28602/61904 [4:13:02<12:49:13, 1.39s/it] 46%|████▌ | 28603/61904 [4:13:04<12:56:01, 1.40s/it] 46%|████▌ | 28604/61904 [4:13:05<12:49:28, 1.39s/it] 46%|████▌ | 28605/61904 [4:13:06<12:48:52, 1.39s/it] 46%|████▌ | 28606/61904 [4:13:08<13:16:24, 1.44s/it] 46%|████▌ | 28607/61904 [4:13:09<12:56:31, 1.40s/it] 46%|████▌ | 28608/61904 [4:13:11<12:51:02, 1.39s/it] 46%|████▌ | 28609/61904 [4:13:12<12:50:53, 1.39s/it] 46%|████▌ | 28610/61904 [4:13:13<12:45:55, 1.38s/it] 46%|████▌ | 28611/61904 [4:13:15<12:49:51, 1.39s/it] 46%|████▌ | 28612/61904 [4:13:16<12:37:38, 1.37s/it] 46%|████▌ | 28613/61904 [4:13:17<12:22:47, 1.34s/it] 46%|████▌ | 28614/61904 [4:13:19<12:22:19, 1.34s/it] 46%|████▌ | 28615/61904 [4:13:20<12:20:35, 1.33s/it] 46%|████▌ | 28616/61904 [4:13:22<12:44:15, 1.38s/it] 46%|████▌ | 28617/61904 [4:13:23<12:29:28, 1.35s/it] 46%|████▌ | 28618/61904 [4:13:24<12:36:57, 1.36s/it] 46%|████▌ | 28619/61904 [4:13:26<12:57:16, 1.40s/it] 46%|████▌ | 28620/61904 [4:13:27<12:44:26, 1.38s/it] {'loss': 2.5116, 'learning_rate': 1.5394139764034746e-07, 'epoch': 7.4} + 46%|████▌ | 28620/61904 [4:13:27<12:44:26, 1.38s/it] 46%|████▌ | 28621/61904 [4:13:28<12:51:14, 1.39s/it] 46%|████▌ | 28622/61904 [4:13:30<12:48:46, 1.39s/it] 46%|████▌ | 28623/61904 [4:13:31<12:52:09, 1.39s/it] 46%|████▌ | 28624/61904 [4:13:33<12:45:51, 1.38s/it] 46%|████▌ | 28625/61904 [4:13:34<13:02:29, 1.41s/it] 46%|████▌ | 28626/61904 [4:13:36<13:08:54, 1.42s/it] 46%|████▌ | 28627/61904 [4:13:37<13:21:33, 1.45s/it] 46%|████▌ | 28628/61904 [4:13:39<13:31:13, 1.46s/it] 46%|████▌ | 28629/61904 [4:13:40<13:33:25, 1.47s/it] 46%|████▌ | 28630/61904 [4:13:41<13:17:30, 1.44s/it] 46%|████▋ | 28631/61904 [4:13:43<13:08:46, 1.42s/it] 46%|████▋ | 28632/61904 [4:13:44<13:18:35, 1.44s/it] 46%|████▋ | 28633/61904 [4:13:46<13:00:58, 1.41s/it] 46%|████▋ | 28634/61904 [4:13:47<13:07:39, 1.42s/it] 46%|████▋ | 28635/61904 [4:13:48<12:47:22, 1.38s/it] 46%|████▋ | 28636/61904 [4:13:50<13:06:32, 1.42s/it] 46%|████▋ | 28637/61904 [4:13:51<12:50:01, 1.39s/it] 46%|████▋ | 28638/61904 [4:13:53<12:48:33, 1.39s/it] 46%|████▋ | 28639/61904 [4:13:54<12:57:51, 1.40s/it] 46%|████▋ | 28640/61904 [4:13:55<12:44:23, 1.38s/it] {'loss': 2.5276, 'learning_rate': 1.5390898483080512e-07, 'epoch': 7.4} + 46%|████▋ | 28640/61904 [4:13:55<12:44:23, 1.38s/it] 46%|████▋ | 28641/61904 [4:13:57<12:55:59, 1.40s/it] 46%|████▋ | 28642/61904 [4:13:58<13:26:17, 1.45s/it] 46%|████▋ | 28643/61904 [4:14:00<13:00:35, 1.41s/it] 46%|████▋ | 28644/61904 [4:14:01<12:57:49, 1.40s/it] 46%|████▋ | 28645/61904 [4:14:02<12:33:58, 1.36s/it] 46%|████▋ | 28646/61904 [4:14:04<12:48:26, 1.39s/it] 46%|████▋ | 28647/61904 [4:14:05<12:50:24, 1.39s/it] 46%|████▋ | 28648/61904 [4:14:06<12:40:25, 1.37s/it] 46%|████▋ | 28649/61904 [4:14:08<12:44:32, 1.38s/it] 46%|████▋ | 28650/61904 [4:14:09<12:30:25, 1.35s/it] 46%|████▋ | 28651/61904 [4:14:11<12:39:51, 1.37s/it] 46%|████▋ | 28652/61904 [4:14:12<12:59:10, 1.41s/it] 46%|████▋ | 28653/61904 [4:14:13<12:52:50, 1.39s/it] 46%|████▋ | 28654/61904 [4:14:15<12:36:21, 1.36s/it] 46%|████▋ | 28655/61904 [4:14:16<12:44:21, 1.38s/it] 46%|████▋ | 28656/61904 [4:14:17<12:30:54, 1.36s/it] 46%|████▋ | 28657/61904 [4:14:19<12:48:50, 1.39s/it] 46%|████▋ | 28658/61904 [4:14:20<12:38:44, 1.37s/it] 46%|████▋ | 28659/61904 [4:14:22<12:39:40, 1.37s/it] 46%|████▋ | 28660/61904 [4:14:23<12:33:43, 1.36s/it] {'loss': 2.5662, 'learning_rate': 1.538765720212628e-07, 'epoch': 7.41} + 46%|████▋ | 28660/61904 [4:14:23<12:33:43, 1.36s/it] 46%|████▋ | 28661/61904 [4:14:24<12:33:56, 1.36s/it] 46%|████▋ | 28662/61904 [4:14:26<12:47:59, 1.39s/it] 46%|████▋ | 28663/61904 [4:14:27<13:15:22, 1.44s/it] 46%|████▋ | 28664/61904 [4:14:29<12:47:01, 1.38s/it] 46%|████▋ | 28665/61904 [4:14:30<13:01:56, 1.41s/it] 46%|████▋ | 28666/61904 [4:14:31<12:47:17, 1.39s/it] 46%|████▋ | 28667/61904 [4:14:33<12:27:23, 1.35s/it] 46%|████▋ | 28668/61904 [4:14:34<12:12:47, 1.32s/it] 46%|████▋ | 28669/61904 [4:14:35<12:20:59, 1.34s/it] 46%|████▋ | 28670/61904 [4:14:37<12:25:16, 1.35s/it] 46%|████▋ | 28671/61904 [4:14:38<12:20:44, 1.34s/it] 46%|████▋ | 28672/61904 [4:14:39<12:45:14, 1.38s/it] 46%|████▋ | 28673/61904 [4:14:41<12:47:18, 1.39s/it] 46%|████▋ | 28674/61904 [4:14:42<12:57:51, 1.40s/it] 46%|████▋ | 28675/61904 [4:14:43<12:35:13, 1.36s/it] 46%|████▋ | 28676/61904 [4:14:45<12:28:43, 1.35s/it] 46%|████▋ | 28677/61904 [4:14:46<12:39:54, 1.37s/it] 46%|████▋ | 28678/61904 [4:14:48<12:53:22, 1.40s/it] 46%|████▋ | 28679/61904 [4:14:49<12:41:44, 1.38s/it] 46%|████▋ | 28680/61904 [4:14:50<12:51:48, 1.39s/it] {'loss': 2.5843, 'learning_rate': 1.5384415921172047e-07, 'epoch': 7.41} + 46%|████▋ | 28680/61904 [4:14:50<12:51:48, 1.39s/it] 46%|████▋ | 28681/61904 [4:14:52<12:28:59, 1.35s/it] 46%|████▋ | 28682/61904 [4:14:53<12:29:40, 1.35s/it] 46%|████▋ | 28683/61904 [4:14:54<12:32:36, 1.36s/it] 46%|████▋ | 28684/61904 [4:14:56<13:04:45, 1.42s/it] 46%|████▋ | 28685/61904 [4:14:57<12:55:07, 1.40s/it] 46%|████▋ | 28686/61904 [4:14:59<12:55:44, 1.40s/it] 46%|████▋ | 28687/61904 [4:15:00<13:01:05, 1.41s/it] 46%|████▋ | 28688/61904 [4:15:01<12:41:22, 1.38s/it] 46%|████▋ | 28689/61904 [4:15:03<12:45:39, 1.38s/it] 46%|████▋ | 28690/61904 [4:15:04<12:56:28, 1.40s/it] 46%|████▋ | 28691/61904 [4:15:06<12:38:08, 1.37s/it] 46%|████▋ | 28692/61904 [4:15:07<12:27:22, 1.35s/it] 46%|████▋ | 28693/61904 [4:15:08<12:20:41, 1.34s/it] 46%|████▋ | 28694/61904 [4:15:10<12:14:17, 1.33s/it] 46%|████▋ | 28695/61904 [4:15:11<12:10:14, 1.32s/it] 46%|████▋ | 28696/61904 [4:15:12<12:25:15, 1.35s/it] 46%|████▋ | 28697/61904 [4:15:14<12:32:05, 1.36s/it] 46%|████▋ | 28698/61904 [4:15:15<12:21:29, 1.34s/it] 46%|████▋ | 28699/61904 [4:15:16<12:40:20, 1.37s/it] 46%|████▋ | 28700/61904 [4:15:18<12:42:35, 1.38s/it] {'loss': 2.6341, 'learning_rate': 1.5381174640217813e-07, 'epoch': 7.42} + 46%|████▋ | 28700/61904 [4:15:18<12:42:35, 1.38s/it] 46%|████▋ | 28701/61904 [4:15:19<13:09:08, 1.43s/it] 46%|████▋ | 28702/61904 [4:15:21<12:44:54, 1.38s/it] 46%|████▋ | 28703/61904 [4:15:22<12:39:10, 1.37s/it] 46%|████▋ | 28704/61904 [4:15:24<13:24:34, 1.45s/it] 46%|████▋ | 28705/61904 [4:15:25<13:45:24, 1.49s/it] 46%|████▋ | 28706/61904 [4:15:26<13:17:10, 1.44s/it] 46%|████▋ | 28707/61904 [4:15:28<13:35:08, 1.47s/it] 46%|████▋ | 28708/61904 [4:15:29<13:03:45, 1.42s/it] 46%|████▋ | 28709/61904 [4:15:31<13:22:38, 1.45s/it] 46%|████▋ | 28710/61904 [4:15:32<13:11:11, 1.43s/it] 46%|████▋ | 28711/61904 [4:15:34<12:45:24, 1.38s/it] 46%|████▋ | 28712/61904 [4:15:35<12:27:13, 1.35s/it] 46%|████▋ | 28713/61904 [4:15:36<12:37:38, 1.37s/it] 46%|████▋ | 28714/61904 [4:15:37<12:24:58, 1.35s/it] 46%|████▋ | 28715/61904 [4:15:39<12:15:30, 1.33s/it] 46%|████▋ | 28716/61904 [4:15:40<12:08:37, 1.32s/it] 46%|████▋ | 28717/61904 [4:15:41<12:25:19, 1.35s/it] 46%|████▋ | 28718/61904 [4:15:43<12:37:09, 1.37s/it] 46%|████▋ | 28719/61904 [4:15:44<12:30:19, 1.36s/it] 46%|████▋ | 28720/61904 [4:15:46<12:46:37, 1.39s/it] {'loss': 2.5741, 'learning_rate': 1.537793335926358e-07, 'epoch': 7.42} + 46%|████▋ | 28720/61904 [4:15:46<12:46:37, 1.39s/it] 46%|████▋ | 28721/61904 [4:15:47<12:49:32, 1.39s/it] 46%|████▋ | 28722/61904 [4:15:49<13:17:49, 1.44s/it] 46%|████▋ | 28723/61904 [4:15:50<13:07:29, 1.42s/it] 46%|████▋ | 28724/61904 [4:15:52<13:14:34, 1.44s/it] 46%|████▋ | 28725/61904 [4:15:53<13:11:35, 1.43s/it] 46%|████▋ | 28726/61904 [4:15:54<13:22:47, 1.45s/it] 46%|████▋ | 28727/61904 [4:15:56<13:46:13, 1.49s/it] 46%|████▋ | 28728/61904 [4:15:57<13:35:07, 1.47s/it] 46%|████▋ | 28729/61904 [4:15:59<13:17:34, 1.44s/it] 46%|████▋ | 28730/61904 [4:16:00<13:37:10, 1.48s/it] 46%|████▋ | 28731/61904 [4:16:02<13:05:15, 1.42s/it] 46%|████▋ | 28732/61904 [4:16:03<13:05:48, 1.42s/it] 46%|████▋ | 28733/61904 [4:16:04<13:00:08, 1.41s/it] 46%|████▋ | 28734/61904 [4:16:06<13:44:31, 1.49s/it] 46%|████▋ | 28735/61904 [4:16:08<13:24:28, 1.46s/it] 46%|████▋ | 28736/61904 [4:16:09<13:15:08, 1.44s/it] 46%|████▋ | 28737/61904 [4:16:10<12:49:40, 1.39s/it] 46%|████▋ | 28738/61904 [4:16:12<13:10:00, 1.43s/it] 46%|████▋ | 28739/61904 [4:16:13<12:41:46, 1.38s/it] 46%|████▋ | 28740/61904 [4:16:14<12:53:35, 1.40s/it] {'loss': 2.5658, 'learning_rate': 1.5374692078309346e-07, 'epoch': 7.43} + 46%|████▋ | 28740/61904 [4:16:14<12:53:35, 1.40s/it] 46%|████▋ | 28741/61904 [4:16:16<12:35:41, 1.37s/it] 46%|████▋ | 28742/61904 [4:16:17<12:38:57, 1.37s/it] 46%|████▋ | 28743/61904 [4:16:18<12:18:31, 1.34s/it] 46%|████▋ | 28744/61904 [4:16:20<12:12:57, 1.33s/it] 46%|████▋ | 28745/61904 [4:16:21<12:51:02, 1.40s/it] 46%|████▋ | 28746/61904 [4:16:23<12:42:42, 1.38s/it] 46%|████▋ | 28747/61904 [4:16:24<12:36:59, 1.37s/it] 46%|████▋ | 28748/61904 [4:16:25<12:18:29, 1.34s/it] 46%|████▋ | 28749/61904 [4:16:27<13:08:09, 1.43s/it] 46%|████▋ | 28750/61904 [4:16:28<12:38:07, 1.37s/it] 46%|████▋ | 28751/61904 [4:16:29<12:35:08, 1.37s/it] 46%|████▋ | 28752/61904 [4:16:31<12:40:35, 1.38s/it] 46%|████▋ | 28753/61904 [4:16:32<12:39:36, 1.37s/it] 46%|████▋ | 28754/61904 [4:16:34<12:40:34, 1.38s/it] 46%|████▋ | 28755/61904 [4:16:35<13:08:27, 1.43s/it] 46%|████▋ | 28756/61904 [4:16:37<13:13:19, 1.44s/it] 46%|████▋ | 28757/61904 [4:16:38<13:32:58, 1.47s/it] 46%|████▋ | 28758/61904 [4:16:39<13:04:17, 1.42s/it] 46%|████▋ | 28759/61904 [4:16:41<13:02:27, 1.42s/it] 46%|��███▋ | 28760/61904 [4:16:42<12:49:31, 1.39s/it] {'loss': 2.5909, 'learning_rate': 1.5371450797355114e-07, 'epoch': 7.43} + 46%|████▋ | 28760/61904 [4:16:42<12:49:31, 1.39s/it] 46%|████▋ | 28761/61904 [4:16:43<12:39:59, 1.38s/it] 46%|████▋ | 28762/61904 [4:16:45<13:14:49, 1.44s/it] 46%|████▋ | 28763/61904 [4:16:46<13:01:53, 1.42s/it] 46%|████▋ | 28764/61904 [4:16:48<12:49:08, 1.39s/it] 46%|████▋ | 28765/61904 [4:16:49<12:53:20, 1.40s/it] 46%|████▋ | 28766/61904 [4:16:51<12:57:20, 1.41s/it] 46%|████▋ | 28767/61904 [4:16:52<12:46:36, 1.39s/it] 46%|████▋ | 28768/61904 [4:16:53<12:42:33, 1.38s/it] 46%|████▋ | 28769/61904 [4:16:55<12:34:03, 1.37s/it] 46%|████▋ | 28770/61904 [4:16:56<12:42:26, 1.38s/it] 46%|████▋ | 28771/61904 [4:16:58<12:58:59, 1.41s/it] 46%|████▋ | 28772/61904 [4:16:59<13:12:22, 1.43s/it] 46%|████▋ | 28773/61904 [4:17:00<12:55:21, 1.40s/it] 46%|████▋ | 28774/61904 [4:17:02<12:45:34, 1.39s/it] 46%|████▋ | 28775/61904 [4:17:03<12:57:18, 1.41s/it] 46%|████▋ | 28776/61904 [4:17:04<12:36:30, 1.37s/it] 46%|████▋ | 28777/61904 [4:17:06<12:47:47, 1.39s/it] 46%|████▋ | 28778/61904 [4:17:07<12:45:36, 1.39s/it] 46%|████▋ | 28779/61904 [4:17:09<12:46:26, 1.39s/it] 46%|████▋ | 28780/61904 [4:17:10<12:32:25, 1.36s/it] {'loss': 2.5543, 'learning_rate': 1.536820951640088e-07, 'epoch': 7.44} + 46%|████▋ | 28780/61904 [4:17:10<12:32:25, 1.36s/it] 46%|████▋ | 28781/61904 [4:17:12<13:12:17, 1.44s/it] 46%|████▋ | 28782/61904 [4:17:13<12:50:18, 1.40s/it] 46%|████▋ | 28783/61904 [4:17:14<12:35:54, 1.37s/it] 46%|████▋ | 28784/61904 [4:17:15<12:25:25, 1.35s/it] 46%|████▋ | 28785/61904 [4:17:17<12:20:20, 1.34s/it] 47%|████▋ | 28786/61904 [4:17:18<12:13:05, 1.33s/it] 47%|████▋ | 28787/61904 [4:17:20<12:27:19, 1.35s/it] 47%|████▋ | 28788/61904 [4:17:21<12:41:31, 1.38s/it] 47%|████▋ | 28789/61904 [4:17:22<12:41:39, 1.38s/it] 47%|████▋ | 28790/61904 [4:17:24<13:10:28, 1.43s/it] 47%|████▋ | 28791/61904 [4:17:25<13:02:17, 1.42s/it] 47%|████▋ | 28792/61904 [4:17:27<12:34:45, 1.37s/it] 47%|████▋ | 28793/61904 [4:17:28<12:27:24, 1.35s/it] 47%|████▋ | 28794/61904 [4:17:29<12:35:18, 1.37s/it] 47%|████▋ | 28795/61904 [4:17:31<12:44:37, 1.39s/it] 47%|████▋ | 28796/61904 [4:17:32<12:32:16, 1.36s/it] 47%|████▋ | 28797/61904 [4:17:33<12:35:02, 1.37s/it] 47%|████▋ | 28798/61904 [4:17:35<12:47:26, 1.39s/it] 47%|████▋ | 28799/61904 [4:17:36<12:32:57, 1.36s/it] 47%|████▋ | 28800/61904 [4:17:37<12:33:31, 1.37s/it] {'loss': 2.5546, 'learning_rate': 1.5364968235446647e-07, 'epoch': 7.44} + 47%|████▋ | 28800/61904 [4:17:37<12:33:31, 1.37s/it] 47%|████▋ | 28801/61904 [4:17:39<12:37:21, 1.37s/it] 47%|████▋ | 28802/61904 [4:17:40<13:04:28, 1.42s/it] 47%|████▋ | 28803/61904 [4:17:42<13:24:22, 1.46s/it] 47%|████▋ | 28804/61904 [4:17:43<13:34:13, 1.48s/it] 47%|████▋ | 28805/61904 [4:17:45<13:32:01, 1.47s/it] 47%|████▋ | 28806/61904 [4:17:46<13:18:52, 1.45s/it] 47%|████▋ | 28807/61904 [4:17:48<13:22:36, 1.46s/it] 47%|████▋ | 28808/61904 [4:17:49<13:12:30, 1.44s/it] 47%|████▋ | 28809/61904 [4:17:51<13:22:43, 1.46s/it] 47%|████▋ | 28810/61904 [4:17:52<13:10:59, 1.43s/it] 47%|████▋ | 28811/61904 [4:17:53<12:57:31, 1.41s/it] 47%|████▋ | 28812/61904 [4:17:55<13:12:25, 1.44s/it] 47%|████▋ | 28813/61904 [4:17:56<12:55:18, 1.41s/it] 47%|████▋ | 28814/61904 [4:17:58<13:23:48, 1.46s/it] 47%|████▋ | 28815/61904 [4:17:59<13:47:10, 1.50s/it] 47%|████▋ | 28816/61904 [4:18:01<13:11:54, 1.44s/it] 47%|████▋ | 28817/61904 [4:18:02<13:00:19, 1.42s/it] 47%|████▋ | 28818/61904 [4:18:03<12:31:29, 1.36s/it] 47%|████▋ | 28819/61904 [4:18:05<12:38:39, 1.38s/it] 47%|████▋ | 28820/61904 [4:18:06<12:51:12, 1.40s/it] {'loss': 2.5236, 'learning_rate': 1.5361726954492416e-07, 'epoch': 7.45} + 47%|████▋ | 28820/61904 [4:18:06<12:51:12, 1.40s/it] 47%|████▋ | 28821/61904 [4:18:08<12:47:23, 1.39s/it] 47%|████▋ | 28822/61904 [4:18:09<12:40:05, 1.38s/it] 47%|████▋ | 28823/61904 [4:18:10<12:43:21, 1.38s/it] 47%|████▋ | 28824/61904 [4:18:12<12:34:04, 1.37s/it] 47%|████▋ | 28825/61904 [4:18:13<12:28:04, 1.36s/it] 47%|████▋ | 28826/61904 [4:18:14<12:54:33, 1.40s/it] 47%|████▋ | 28827/61904 [4:18:16<12:42:18, 1.38s/it] 47%|████▋ | 28828/61904 [4:18:17<12:43:40, 1.39s/it] 47%|████▋ | 28829/61904 [4:18:19<12:34:35, 1.37s/it] 47%|████▋ | 28830/61904 [4:18:20<12:48:39, 1.39s/it] 47%|████▋ | 28831/61904 [4:18:21<12:43:05, 1.38s/it] 47%|████▋ | 28832/61904 [4:18:23<12:49:10, 1.40s/it] 47%|████▋ | 28833/61904 [4:18:24<13:05:03, 1.42s/it] 47%|████▋ | 28834/61904 [4:18:26<12:43:29, 1.39s/it] 47%|████▋ | 28835/61904 [4:18:27<12:55:28, 1.41s/it] 47%|████▋ | 28836/61904 [4:18:28<12:53:58, 1.40s/it] 47%|████▋ | 28837/61904 [4:18:30<12:55:52, 1.41s/it] 47%|████▋ | 28838/61904 [4:18:31<12:53:17, 1.40s/it] 47%|████▋ | 28839/61904 [4:18:33<12:46:11, 1.39s/it] 47%|████▋ | 28840/61904 [4:18:34<12:49:54, 1.40s/it] {'loss': 2.5981, 'learning_rate': 1.5358485673538182e-07, 'epoch': 7.45} + 47%|████▋ | 28840/61904 [4:18:34<12:49:54, 1.40s/it] 47%|████▋ | 28841/61904 [4:18:35<12:59:20, 1.41s/it] 47%|████▋ | 28842/61904 [4:18:37<12:32:07, 1.36s/it] 47%|████▋ | 28843/61904 [4:18:38<12:33:28, 1.37s/it] 47%|████▋ | 28844/61904 [4:18:40<12:51:18, 1.40s/it] 47%|████▋ | 28845/61904 [4:18:41<12:46:12, 1.39s/it] 47%|████▋ | 28846/61904 [4:18:42<12:26:57, 1.36s/it] 47%|████▋ | 28847/61904 [4:18:44<12:38:11, 1.38s/it] 47%|████▋ | 28848/61904 [4:18:45<12:49:40, 1.40s/it] 47%|████▋ | 28849/61904 [4:18:47<13:13:31, 1.44s/it] 47%|████▋ | 28850/61904 [4:18:48<13:20:32, 1.45s/it] 47%|████▋ | 28851/61904 [4:18:49<13:00:37, 1.42s/it] 47%|████▋ | 28852/61904 [4:18:51<12:48:48, 1.40s/it] 47%|████▋ | 28853/61904 [4:18:52<12:30:00, 1.36s/it] 47%|████▋ | 28854/61904 [4:18:53<12:09:15, 1.32s/it] 47%|████▋ | 28855/61904 [4:18:55<12:12:48, 1.33s/it] 47%|████▋ | 28856/61904 [4:18:56<12:36:59, 1.37s/it] 47%|████▋ | 28857/61904 [4:18:57<12:38:39, 1.38s/it] 47%|████▋ | 28858/61904 [4:18:59<12:52:11, 1.40s/it] 47%|████▋ | 28859/61904 [4:19:00<12:47:50, 1.39s/it] 47%|████▋ | 28860/61904 [4:19:02<12:44:25, 1.39s/it] {'loss': 2.5322, 'learning_rate': 1.5355244392583948e-07, 'epoch': 7.46} + 47%|████▋ | 28860/61904 [4:19:02<12:44:25, 1.39s/it] 47%|████▋ | 28861/61904 [4:19:03<13:01:10, 1.42s/it] 47%|████▋ | 28862/61904 [4:19:05<12:50:47, 1.40s/it] 47%|████▋ | 28863/61904 [4:19:06<12:51:28, 1.40s/it] 47%|████▋ | 28864/61904 [4:19:07<12:51:29, 1.40s/it] 47%|████▋ | 28865/61904 [4:19:09<12:55:15, 1.41s/it] 47%|████▋ | 28866/61904 [4:19:10<12:40:46, 1.38s/it] 47%|████▋ | 28867/61904 [4:19:12<12:47:18, 1.39s/it] 47%|████▋ | 28868/61904 [4:19:13<12:51:43, 1.40s/it] 47%|████▋ | 28869/61904 [4:19:14<13:11:26, 1.44s/it] 47%|████▋ | 28870/61904 [4:19:16<12:40:55, 1.38s/it] 47%|████▋ | 28871/61904 [4:19:17<12:32:35, 1.37s/it] 47%|████▋ | 28872/61904 [4:19:18<12:09:19, 1.32s/it] 47%|████▋ | 28873/61904 [4:19:20<12:10:04, 1.33s/it] 47%|████▋ | 28874/61904 [4:19:21<12:04:10, 1.32s/it] 47%|████▋ | 28875/61904 [4:19:22<12:13:33, 1.33s/it] 47%|████▋ | 28876/61904 [4:19:24<12:14:11, 1.33s/it] 47%|████▋ | 28877/61904 [4:19:25<12:35:20, 1.37s/it] 47%|████▋ | 28878/61904 [4:19:26<12:43:07, 1.39s/it] 47%|████▋ | 28879/61904 [4:19:28<12:26:20, 1.36s/it] 47%|████▋ | 28880/61904 [4:19:29<12:07:51, 1.32s/it] {'loss': 2.6326, 'learning_rate': 1.5352003111629717e-07, 'epoch': 7.46} + 47%|████▋ | 28880/61904 [4:19:29<12:07:51, 1.32s/it] 47%|████▋ | 28881/61904 [4:19:31<12:37:37, 1.38s/it] 47%|████▋ | 28882/61904 [4:19:32<12:37:54, 1.38s/it] 47%|████▋ | 28883/61904 [4:19:33<12:48:05, 1.40s/it] 47%|████▋ | 28884/61904 [4:19:35<12:51:03, 1.40s/it] 47%|████▋ | 28885/61904 [4:19:36<12:44:58, 1.39s/it] 47%|████▋ | 28886/61904 [4:19:38<12:57:45, 1.41s/it] 47%|████▋ | 28887/61904 [4:19:39<13:01:18, 1.42s/it] 47%|████▋ | 28888/61904 [4:19:41<13:13:57, 1.44s/it] 47%|████▋ | 28889/61904 [4:19:42<12:47:55, 1.40s/it] 47%|████▋ | 28890/61904 [4:19:43<12:48:31, 1.40s/it] 47%|████▋ | 28891/61904 [4:19:45<12:58:12, 1.41s/it] 47%|████▋ | 28892/61904 [4:19:46<13:08:50, 1.43s/it] 47%|████▋ | 28893/61904 [4:19:47<12:50:56, 1.40s/it] 47%|████▋ | 28894/61904 [4:19:49<12:46:27, 1.39s/it] 47%|████▋ | 28895/61904 [4:19:50<12:39:54, 1.38s/it] 47%|████▋ | 28896/61904 [4:19:52<12:45:30, 1.39s/it] 47%|████▋ | 28897/61904 [4:19:53<12:45:53, 1.39s/it] 47%|████▋ | 28898/61904 [4:19:54<12:40:15, 1.38s/it] 47%|████▋ | 28899/61904 [4:19:56<12:18:01, 1.34s/it] 47%|████▋ | 28900/61904 [4:19:57<12:36:06, 1.37s/it] {'loss': 2.5647, 'learning_rate': 1.5348761830675483e-07, 'epoch': 7.47} + 47%|████▋ | 28900/61904 [4:19:57<12:36:06, 1.37s/it] 47%|████▋ | 28901/61904 [4:19:58<12:44:19, 1.39s/it] 47%|████▋ | 28902/61904 [4:20:00<12:43:53, 1.39s/it] 47%|████▋ | 28903/61904 [4:20:01<12:52:13, 1.40s/it] 47%|████▋ | 28904/61904 [4:20:03<13:15:55, 1.45s/it] 47%|████▋ | 28905/61904 [4:20:04<12:48:15, 1.40s/it] 47%|████▋ | 28906/61904 [4:20:05<12:38:39, 1.38s/it] 47%|████▋ | 28907/61904 [4:20:07<12:29:48, 1.36s/it] 47%|████▋ | 28908/61904 [4:20:08<12:21:59, 1.35s/it] 47%|████▋ | 28909/61904 [4:20:09<12:21:23, 1.35s/it] 47%|████▋ | 28910/61904 [4:20:11<12:24:51, 1.35s/it] 47%|████▋ | 28911/61904 [4:20:12<12:44:35, 1.39s/it] 47%|████▋ | 28912/61904 [4:20:14<12:39:27, 1.38s/it] 47%|████▋ | 28913/61904 [4:20:15<12:29:46, 1.36s/it] 47%|████▋ | 28914/61904 [4:20:16<12:41:06, 1.38s/it] 47%|████▋ | 28915/61904 [4:20:18<12:32:34, 1.37s/it] 47%|████▋ | 28916/61904 [4:20:19<12:59:21, 1.42s/it] 47%|████▋ | 28917/61904 [4:20:21<12:57:50, 1.41s/it] 47%|████▋ | 28918/61904 [4:20:22<12:40:16, 1.38s/it] 47%|████▋ | 28919/61904 [4:20:23<12:43:18, 1.39s/it] 47%|████▋ | 28920/61904 [4:20:25<12:25:21, 1.36s/it] {'loss': 2.6036, 'learning_rate': 1.534552054972125e-07, 'epoch': 7.47} + 47%|████▋ | 28920/61904 [4:20:25<12:25:21, 1.36s/it] 47%|████▋ | 28921/61904 [4:20:26<12:43:36, 1.39s/it] 47%|████▋ | 28922/61904 [4:20:27<12:37:21, 1.38s/it] 47%|████▋ | 28923/61904 [4:20:29<12:26:23, 1.36s/it] 47%|████▋ | 28924/61904 [4:20:30<12:26:11, 1.36s/it] 47%|████▋ | 28925/61904 [4:20:32<12:25:27, 1.36s/it] 47%|████▋ | 28926/61904 [4:20:33<12:12:10, 1.33s/it] 47%|████▋ | 28927/61904 [4:20:34<12:27:34, 1.36s/it] 47%|████▋ | 28928/61904 [4:20:36<12:47:37, 1.40s/it] 47%|████▋ | 28929/61904 [4:20:37<13:10:45, 1.44s/it] 47%|████▋ | 28930/61904 [4:20:39<13:10:08, 1.44s/it] 47%|████▋ | 28931/61904 [4:20:40<13:06:22, 1.43s/it] 47%|████▋ | 28932/61904 [4:20:42<13:14:16, 1.45s/it] 47%|████▋ | 28933/61904 [4:20:43<12:53:58, 1.41s/it] 47%|████▋ | 28934/61904 [4:20:44<12:57:26, 1.41s/it] 47%|████▋ | 28935/61904 [4:20:46<12:58:06, 1.42s/it] 47%|████▋ | 28936/61904 [4:20:47<13:08:59, 1.44s/it] 47%|████▋ | 28937/61904 [4:20:48<12:38:49, 1.38s/it] 47%|████▋ | 28938/61904 [4:20:50<12:10:27, 1.33s/it] 47%|████▋ | 28939/61904 [4:20:51<12:22:46, 1.35s/it] 47%|████▋ | 28940/61904 [4:20:52<12:29:10, 1.36s/it] {'loss': 2.5672, 'learning_rate': 1.5342279268767015e-07, 'epoch': 7.48} + 47%|████▋ | 28940/61904 [4:20:52<12:29:10, 1.36s/it] 47%|████▋ | 28941/61904 [4:20:54<12:25:40, 1.36s/it] 47%|████▋ | 28942/61904 [4:20:55<12:40:08, 1.38s/it] 47%|████▋ | 28943/61904 [4:20:57<13:17:52, 1.45s/it] 47%|████▋ | 28944/61904 [4:20:58<13:04:47, 1.43s/it] 47%|████▋ | 28945/61904 [4:21:00<12:50:07, 1.40s/it] 47%|████▋ | 28946/61904 [4:21:01<12:31:54, 1.37s/it] 47%|████▋ | 28947/61904 [4:21:02<13:00:19, 1.42s/it] 47%|████▋ | 28948/61904 [4:21:04<12:54:31, 1.41s/it] 47%|████▋ | 28949/61904 [4:21:05<13:09:21, 1.44s/it] 47%|████▋ | 28950/61904 [4:21:07<12:41:22, 1.39s/it] 47%|████▋ | 28951/61904 [4:21:08<12:45:15, 1.39s/it] 47%|████▋ | 28952/61904 [4:21:09<12:34:55, 1.37s/it] 47%|████▋ | 28953/61904 [4:21:11<12:32:29, 1.37s/it] 47%|████▋ | 28954/61904 [4:21:12<12:42:44, 1.39s/it] 47%|████▋ | 28955/61904 [4:21:14<12:45:41, 1.39s/it] 47%|████▋ | 28956/61904 [4:21:15<12:40:48, 1.39s/it] 47%|████▋ | 28957/61904 [4:21:16<12:41:04, 1.39s/it] 47%|████▋ | 28958/61904 [4:21:18<12:34:45, 1.37s/it] 47%|████▋ | 28959/61904 [4:21:19<12:37:18, 1.38s/it] 47%|████▋ | 28960/61904 [4:21:20<12:44:37, 1.39s/it] {'loss': 2.5102, 'learning_rate': 1.5339037987812782e-07, 'epoch': 7.48} + 47%|████▋ | 28960/61904 [4:21:20<12:44:37, 1.39s/it] 47%|████▋ | 28961/61904 [4:21:22<12:53:00, 1.41s/it] 47%|████▋ | 28962/61904 [4:21:23<13:04:34, 1.43s/it] 47%|████▋ | 28963/61904 [4:21:25<12:47:44, 1.40s/it] 47%|████▋ | 28964/61904 [4:21:26<12:49:26, 1.40s/it] 47%|████▋ | 28965/61904 [4:21:28<12:57:14, 1.42s/it] 47%|████▋ | 28966/61904 [4:21:29<12:46:26, 1.40s/it] 47%|████▋ | 28967/61904 [4:21:30<12:34:39, 1.37s/it] 47%|████▋ | 28968/61904 [4:21:32<12:35:10, 1.38s/it] 47%|████▋ | 28969/61904 [4:21:33<12:43:12, 1.39s/it] 47%|████▋ | 28970/61904 [4:21:34<12:54:26, 1.41s/it] 47%|████▋ | 28971/61904 [4:21:36<12:42:17, 1.39s/it] 47%|████▋ | 28972/61904 [4:21:37<13:03:19, 1.43s/it] 47%|████▋ | 28973/61904 [4:21:39<12:44:59, 1.39s/it] 47%|████▋ | 28974/61904 [4:21:40<12:23:31, 1.35s/it] 47%|████▋ | 28975/61904 [4:21:41<12:28:00, 1.36s/it] 47%|████▋ | 28976/61904 [4:21:43<12:27:39, 1.36s/it] 47%|████▋ | 28977/61904 [4:21:44<12:47:59, 1.40s/it] 47%|████▋ | 28978/61904 [4:21:46<12:47:04, 1.40s/it] 47%|████▋ | 28979/61904 [4:21:47<12:24:09, 1.36s/it] 47%|████▋ | 28980/61904 [4:21:48<12:06:56, 1.32s/it] {'loss': 2.6278, 'learning_rate': 1.533579670685855e-07, 'epoch': 7.49} + 47%|████▋ | 28980/61904 [4:21:48<12:06:56, 1.32s/it] 47%|████▋ | 28981/61904 [4:21:49<12:24:58, 1.36s/it] 47%|████▋ | 28982/61904 [4:21:51<12:53:54, 1.41s/it] 47%|████▋ | 28983/61904 [4:21:52<12:43:54, 1.39s/it] 47%|████▋ | 28984/61904 [4:21:54<13:02:05, 1.43s/it] 47%|████▋ | 28985/61904 [4:21:55<13:12:10, 1.44s/it] 47%|████▋ | 28986/61904 [4:21:57<13:24:40, 1.47s/it] 47%|████▋ | 28987/61904 [4:21:58<13:03:31, 1.43s/it] 47%|████▋ | 28988/61904 [4:22:00<12:50:30, 1.40s/it] 47%|████▋ | 28989/61904 [4:22:01<12:51:12, 1.41s/it] 47%|████▋ | 28990/61904 [4:22:02<12:51:29, 1.41s/it] 47%|████▋ | 28991/61904 [4:22:04<12:43:46, 1.39s/it] 47%|████▋ | 28992/61904 [4:22:05<12:32:12, 1.37s/it] 47%|████▋ | 28993/61904 [4:22:06<12:13:31, 1.34s/it] 47%|████▋ | 28994/61904 [4:22:08<12:34:17, 1.38s/it] 47%|████▋ | 28995/61904 [4:22:09<12:31:45, 1.37s/it] 47%|████▋ | 28996/61904 [4:22:10<12:17:08, 1.34s/it] 47%|████▋ | 28997/61904 [4:22:12<12:45:03, 1.39s/it] 47%|████▋ | 28998/61904 [4:22:14<13:31:29, 1.48s/it] 47%|████▋ | 28999/61904 [4:22:15<12:59:54, 1.42s/it] 47%|████▋ | 29000/61904 [4:22:16<13:28:08, 1.47s/it] {'loss': 2.6092, 'learning_rate': 1.5332555425904317e-07, 'epoch': 7.5} + 47%|████▋ | 29000/61904 [4:22:16<13:28:08, 1.47s/it] 47%|████▋ | 29001/61904 [4:22:18<13:02:18, 1.43s/it] 47%|████▋ | 29002/61904 [4:22:19<12:45:27, 1.40s/it] 47%|████▋ | 29003/61904 [4:22:21<13:00:45, 1.42s/it] 47%|████▋ | 29004/61904 [4:22:22<12:50:44, 1.41s/it] 47%|████▋ | 29005/61904 [4:22:23<12:59:13, 1.42s/it] 47%|████▋ | 29006/61904 [4:22:25<12:47:44, 1.40s/it] 47%|████▋ | 29007/61904 [4:22:26<12:39:47, 1.39s/it] 47%|████▋ | 29008/61904 [4:22:28<12:46:43, 1.40s/it] 47%|████▋ | 29009/61904 [4:22:29<12:31:44, 1.37s/it] 47%|████▋ | 29010/61904 [4:22:30<13:03:30, 1.43s/it] 47%|████▋ | 29011/61904 [4:22:32<12:43:09, 1.39s/it] 47%|████▋ | 29012/61904 [4:22:33<12:13:03, 1.34s/it] 47%|████▋ | 29013/61904 [4:22:34<12:08:23, 1.33s/it] 47%|████▋ | 29014/61904 [4:22:36<12:08:29, 1.33s/it] 47%|████▋ | 29015/61904 [4:22:37<12:13:21, 1.34s/it] 47%|████▋ | 29016/61904 [4:22:38<12:25:37, 1.36s/it] 47%|████▋ | 29017/61904 [4:22:40<12:49:29, 1.40s/it] 47%|████▋ | 29018/61904 [4:22:41<12:42:40, 1.39s/it] 47%|████▋ | 29019/61904 [4:22:43<12:41:02, 1.39s/it] 47%|████▋ | 29020/61904 [4:22:44<12:27:06, 1.36s/it] {'loss': 2.5685, 'learning_rate': 1.5329314144950083e-07, 'epoch': 7.5} + 47%|████▋ | 29020/61904 [4:22:44<12:27:06, 1.36s/it] 47%|████▋ | 29021/61904 [4:22:45<12:18:12, 1.35s/it] 47%|████▋ | 29022/61904 [4:22:47<12:30:00, 1.37s/it] 47%|████▋ | 29023/61904 [4:22:48<12:54:40, 1.41s/it] 47%|████▋ | 29024/61904 [4:22:50<12:47:22, 1.40s/it] 47%|████▋ | 29025/61904 [4:22:51<13:02:13, 1.43s/it] 47%|████▋ | 29026/61904 [4:22:52<13:02:26, 1.43s/it] 47%|████▋ | 29027/61904 [4:22:54<12:43:47, 1.39s/it] 47%|████▋ | 29028/61904 [4:22:55<12:36:58, 1.38s/it] 47%|████▋ | 29029/61904 [4:22:57<12:46:17, 1.40s/it] 47%|████▋ | 29030/61904 [4:22:58<12:38:49, 1.38s/it] 47%|████▋ | 29031/61904 [4:22:59<12:38:20, 1.38s/it] 47%|████▋ | 29032/61904 [4:23:01<12:35:16, 1.38s/it] 47%|████▋ | 29033/61904 [4:23:02<12:39:14, 1.39s/it] 47%|████▋ | 29034/61904 [4:23:04<13:10:34, 1.44s/it] 47%|████▋ | 29035/61904 [4:23:05<12:54:30, 1.41s/it] 47%|████▋ | 29036/61904 [4:23:06<12:26:23, 1.36s/it] 47%|████▋ | 29037/61904 [4:23:08<12:18:12, 1.35s/it] 47%|████▋ | 29038/61904 [4:23:09<12:12:23, 1.34s/it] 47%|████▋ | 29039/61904 [4:23:10<12:14:46, 1.34s/it] 47%|████▋ | 29040/61904 [4:23:12<12:18:18, 1.35s/it] {'loss': 2.5203, 'learning_rate': 1.5326072863995852e-07, 'epoch': 7.51} + 47%|████▋ | 29040/61904 [4:23:12<12:18:18, 1.35s/it] 47%|████▋ | 29041/61904 [4:23:13<12:24:40, 1.36s/it] 47%|████▋ | 29042/61904 [4:23:14<12:18:22, 1.35s/it] 47%|████▋ | 29043/61904 [4:23:16<12:28:59, 1.37s/it] 47%|████▋ | 29044/61904 [4:23:17<12:36:35, 1.38s/it] 47%|████▋ | 29045/61904 [4:23:19<12:39:17, 1.39s/it] 47%|████▋ | 29046/61904 [4:23:20<12:29:43, 1.37s/it] 47%|████▋ | 29047/61904 [4:23:21<12:30:04, 1.37s/it] 47%|████▋ | 29048/61904 [4:23:23<12:19:49, 1.35s/it] 47%|████▋ | 29049/61904 [4:23:24<12:13:30, 1.34s/it] 47%|████▋ | 29050/61904 [4:23:25<11:51:33, 1.30s/it] 47%|████▋ | 29051/61904 [4:23:26<12:09:00, 1.33s/it] 47%|████▋ | 29052/61904 [4:23:28<11:51:29, 1.30s/it] 47%|████▋ | 29053/61904 [4:23:29<12:08:50, 1.33s/it] 47%|████▋ | 29054/61904 [4:23:30<12:19:28, 1.35s/it] 47%|████▋ | 29055/61904 [4:23:32<11:59:54, 1.31s/it] 47%|████▋ | 29056/61904 [4:23:33<12:21:27, 1.35s/it] 47%|████▋ | 29057/61904 [4:23:35<13:11:31, 1.45s/it] 47%|████▋ | 29058/61904 [4:23:36<12:54:33, 1.41s/it] 47%|████▋ | 29059/61904 [4:23:38<12:53:23, 1.41s/it] 47%|████▋ | 29060/61904 [4:23:39<12:44:54, 1.40s/it] {'loss': 2.6086, 'learning_rate': 1.5322831583041618e-07, 'epoch': 7.51} + 47%|████▋ | 29060/61904 [4:23:39<12:44:54, 1.40s/it] 47%|████▋ | 29061/61904 [4:23:40<12:44:37, 1.40s/it] 47%|████▋ | 29062/61904 [4:23:42<12:45:51, 1.40s/it] 47%|████▋ | 29063/61904 [4:23:43<12:55:24, 1.42s/it] 47%|████▋ | 29064/61904 [4:23:45<12:54:46, 1.42s/it] 47%|████▋ | 29065/61904 [4:23:46<12:36:26, 1.38s/it] 47%|████▋ | 29066/61904 [4:23:47<12:51:25, 1.41s/it] 47%|████▋ | 29067/61904 [4:23:49<12:38:28, 1.39s/it] 47%|████▋ | 29068/61904 [4:23:50<12:36:24, 1.38s/it] 47%|████▋ | 29069/61904 [4:23:52<12:52:52, 1.41s/it] 47%|████▋ | 29070/61904 [4:23:53<12:45:56, 1.40s/it] 47%|████▋ | 29071/61904 [4:23:54<12:50:17, 1.41s/it] 47%|████▋ | 29072/61904 [4:23:56<12:44:28, 1.40s/it] 47%|████▋ | 29073/61904 [4:23:57<12:15:40, 1.34s/it] 47%|████▋ | 29074/61904 [4:23:58<12:08:36, 1.33s/it] 47%|████▋ | 29075/61904 [4:24:00<12:16:22, 1.35s/it] 47%|████▋ | 29076/61904 [4:24:01<12:25:21, 1.36s/it] 47%|████▋ | 29077/61904 [4:24:02<12:36:19, 1.38s/it] 47%|████▋ | 29078/61904 [4:24:04<12:11:54, 1.34s/it] 47%|████▋ | 29079/61904 [4:24:05<12:53:33, 1.41s/it] 47%|████▋ | 29080/61904 [4:24:07<12:53:22, 1.41s/it] {'loss': 2.556, 'learning_rate': 1.5319590302087384e-07, 'epoch': 7.52} + 47%|████▋ | 29080/61904 [4:24:07<12:53:22, 1.41s/it] 47%|██��█▋ | 29081/61904 [4:24:08<12:33:17, 1.38s/it] 47%|████▋ | 29082/61904 [4:24:09<12:22:02, 1.36s/it] 47%|████▋ | 29083/61904 [4:24:11<12:09:48, 1.33s/it] 47%|████▋ | 29084/61904 [4:24:12<12:07:55, 1.33s/it] 47%|████▋ | 29085/61904 [4:24:13<12:12:49, 1.34s/it] 47%|████▋ | 29086/61904 [4:24:15<12:13:30, 1.34s/it] 47%|████▋ | 29087/61904 [4:24:16<12:13:17, 1.34s/it] 47%|████▋ | 29088/61904 [4:24:17<12:28:23, 1.37s/it] 47%|████▋ | 29089/61904 [4:24:19<12:26:04, 1.36s/it] 47%|████▋ | 29090/61904 [4:24:20<12:13:59, 1.34s/it] 47%|████▋ | 29091/61904 [4:24:21<12:17:18, 1.35s/it] 47%|████▋ | 29092/61904 [4:24:23<12:14:03, 1.34s/it] 47%|████▋ | 29093/61904 [4:24:24<12:12:36, 1.34s/it] 47%|████▋ | 29094/61904 [4:24:25<12:06:14, 1.33s/it] 47%|████▋ | 29095/61904 [4:24:27<12:25:58, 1.36s/it] 47%|████▋ | 29096/61904 [4:24:28<12:51:43, 1.41s/it] 47%|████▋ | 29097/61904 [4:24:30<13:09:43, 1.44s/it] 47%|████▋ | 29098/61904 [4:24:31<13:01:11, 1.43s/it] 47%|████▋ | 29099/61904 [4:24:33<12:48:24, 1.41s/it] 47%|████▋ | 29100/61904 [4:24:34<12:52:54, 1.41s/it] {'loss': 2.6068, 'learning_rate': 1.531634902113315e-07, 'epoch': 7.52} + 47%|████▋ | 29100/61904 [4:24:34<12:52:54, 1.41s/it] 47%|████▋ | 29101/61904 [4:24:35<12:39:55, 1.39s/it] 47%|████▋ | 29102/61904 [4:24:37<12:31:21, 1.37s/it] 47%|████▋ | 29103/61904 [4:24:38<12:32:19, 1.38s/it] 47%|████▋ | 29104/61904 [4:24:39<12:41:44, 1.39s/it] 47%|████▋ | 29105/61904 [4:24:41<12:48:28, 1.41s/it] 47%|████▋ | 29106/61904 [4:24:42<13:04:15, 1.43s/it] 47%|████▋ | 29107/61904 [4:24:44<12:45:34, 1.40s/it] 47%|████▋ | 29108/61904 [4:24:45<12:48:48, 1.41s/it] 47%|████▋ | 29109/61904 [4:24:47<12:59:57, 1.43s/it] 47%|████▋ | 29110/61904 [4:24:48<12:43:04, 1.40s/it] 47%|████▋ | 29111/61904 [4:24:49<12:51:03, 1.41s/it] 47%|████▋ | 29112/61904 [4:24:51<13:03:21, 1.43s/it] 47%|████▋ | 29113/61904 [4:24:52<12:30:47, 1.37s/it] 47%|████▋ | 29114/61904 [4:24:54<12:41:26, 1.39s/it] 47%|████▋ | 29115/61904 [4:24:55<12:59:18, 1.43s/it] 47%|████▋ | 29116/61904 [4:24:56<12:49:23, 1.41s/it] 47%|████▋ | 29117/61904 [4:24:58<12:39:38, 1.39s/it] 47%|████▋ | 29118/61904 [4:24:59<12:56:44, 1.42s/it] 47%|████▋ | 29119/61904 [4:25:01<12:51:03, 1.41s/it] 47%|████▋ | 29120/61904 [4:25:02<12:50:08, 1.41s/it] {'loss': 2.5915, 'learning_rate': 1.531310774017892e-07, 'epoch': 7.53} + 47%|████▋ | 29120/61904 [4:25:02<12:50:08, 1.41s/it] 47%|████▋ | 29121/61904 [4:25:03<12:50:16, 1.41s/it] 47%|████▋ | 29122/61904 [4:25:05<12:41:40, 1.39s/it] 47%|████▋ | 29123/61904 [4:25:06<12:46:21, 1.40s/it] 47%|████▋ | 29124/61904 [4:25:08<12:30:47, 1.37s/it] 47%|████▋ | 29125/61904 [4:25:09<12:55:55, 1.42s/it] 47%|████▋ | 29126/61904 [4:25:11<13:02:47, 1.43s/it] 47%|████▋ | 29127/61904 [4:25:12<13:20:43, 1.47s/it] 47%|████▋ | 29128/61904 [4:25:14<13:12:38, 1.45s/it] 47%|████▋ | 29129/61904 [4:25:15<12:56:51, 1.42s/it] 47%|████▋ | 29130/61904 [4:25:16<12:27:13, 1.37s/it] 47%|████▋ | 29131/61904 [4:25:17<12:25:13, 1.36s/it] 47%|████▋ | 29132/61904 [4:25:19<12:22:53, 1.36s/it] 47%|████▋ | 29133/61904 [4:25:20<12:57:05, 1.42s/it] 47%|████▋ | 29134/61904 [4:25:22<12:50:34, 1.41s/it] 47%|████▋ | 29135/61904 [4:25:23<12:29:37, 1.37s/it] 47%|████▋ | 29136/61904 [4:25:24<12:09:15, 1.34s/it] 47%|████▋ | 29137/61904 [4:25:26<12:05:05, 1.33s/it] 47%|████▋ | 29138/61904 [4:25:27<12:37:28, 1.39s/it] 47%|████▋ | 29139/61904 [4:25:28<12:14:51, 1.35s/it] 47%|████▋ | 29140/61904 [4:25:30<12:35:19, 1.38s/it] {'loss': 2.5853, 'learning_rate': 1.5309866459224685e-07, 'epoch': 7.53} + 47%|████▋ | 29140/61904 [4:25:30<12:35:19, 1.38s/it] 47%|████▋ | 29141/61904 [4:25:31<13:06:08, 1.44s/it] 47%|████▋ | 29142/61904 [4:25:33<13:25:07, 1.47s/it] 47%|████▋ | 29143/61904 [4:25:34<13:10:52, 1.45s/it] 47%|████▋ | 29144/61904 [4:25:36<12:49:52, 1.41s/it] 47%|████▋ | 29145/61904 [4:25:37<12:52:13, 1.41s/it] 47%|████▋ | 29146/61904 [4:25:39<12:53:37, 1.42s/it] 47%|████▋ | 29147/61904 [4:25:40<12:40:47, 1.39s/it] 47%|████▋ | 29148/61904 [4:25:41<12:51:46, 1.41s/it] 47%|████▋ | 29149/61904 [4:25:43<12:28:53, 1.37s/it] 47%|████▋ | 29150/61904 [4:25:44<12:41:19, 1.39s/it] 47%|████▋ | 29151/61904 [4:25:45<12:35:21, 1.38s/it] 47%|████▋ | 29152/61904 [4:25:47<12:16:34, 1.35s/it] 47%|████▋ | 29153/61904 [4:25:48<12:19:39, 1.36s/it] 47%|████▋ | 29154/61904 [4:25:49<12:31:49, 1.38s/it] 47%|████▋ | 29155/61904 [4:25:51<13:05:24, 1.44s/it] 47%|████▋ | 29156/61904 [4:25:52<12:52:18, 1.41s/it] 47%|████▋ | 29157/61904 [4:25:54<12:18:51, 1.35s/it] 47%|████▋ | 29158/61904 [4:25:55<12:33:59, 1.38s/it] 47%|████▋ | 29159/61904 [4:25:57<12:50:33, 1.41s/it] 47%|████▋ | 29160/61904 [4:25:58<12:27:36, 1.37s/it] {'loss': 2.5933, 'learning_rate': 1.5306625178270451e-07, 'epoch': 7.54} + 47%|████▋ | 29160/61904 [4:25:58<12:27:36, 1.37s/it] 47%|████▋ | 29161/61904 [4:25:59<12:26:14, 1.37s/it] 47%|████▋ | 29162/61904 [4:26:01<12:38:40, 1.39s/it] 47%|████▋ | 29163/61904 [4:26:02<13:03:39, 1.44s/it] 47%|████▋ | 29164/61904 [4:26:04<13:15:31, 1.46s/it] 47%|████▋ | 29165/61904 [4:26:05<13:14:27, 1.46s/it] 47%|████▋ | 29166/61904 [4:26:06<12:43:50, 1.40s/it] 47%|████▋ | 29167/61904 [4:26:08<12:58:36, 1.43s/it] 47%|████▋ | 29168/61904 [4:26:09<12:49:50, 1.41s/it] 47%|████▋ | 29169/61904 [4:26:11<12:49:19, 1.41s/it] 47%|████▋ | 29170/61904 [4:26:12<12:36:00, 1.39s/it] 47%|████▋ | 29171/61904 [4:26:13<12:07:10, 1.33s/it] 47%|████▋ | 29172/61904 [4:26:15<12:43:43, 1.40s/it] 47%|████▋ | 29173/61904 [4:26:16<13:12:59, 1.45s/it] 47%|████▋ | 29174/61904 [4:26:18<12:47:22, 1.41s/it] 47%|████▋ | 29175/61904 [4:26:19<12:36:08, 1.39s/it] 47%|████▋ | 29176/61904 [4:26:20<12:50:12, 1.41s/it] 47%|████▋ | 29177/61904 [4:26:22<12:55:23, 1.42s/it] 47%|████▋ | 29178/61904 [4:26:23<12:39:17, 1.39s/it] 47%|████▋ | 29179/61904 [4:26:25<12:25:15, 1.37s/it] 47%|████▋ | 29180/61904 [4:26:26<12:30:47, 1.38s/it] {'loss': 2.5732, 'learning_rate': 1.5303383897316218e-07, 'epoch': 7.54} + 47%|████▋ | 29180/61904 [4:26:26<12:30:47, 1.38s/it] 47%|████▋ | 29181/61904 [4:26:27<12:35:08, 1.38s/it] 47%|████▋ | 29182/61904 [4:26:29<12:24:34, 1.37s/it] 47%|████▋ | 29183/61904 [4:26:30<12:37:42, 1.39s/it] 47%|████▋ | 29184/61904 [4:26:31<12:14:12, 1.35s/it] 47%|████▋ | 29185/61904 [4:26:33<12:10:49, 1.34s/it] 47%|████▋ | 29186/61904 [4:26:34<12:28:42, 1.37s/it] 47%|████▋ | 29187/61904 [4:26:36<12:26:17, 1.37s/it] 47%|████▋ | 29188/61904 [4:26:37<12:22:38, 1.36s/it] 47%|████▋ | 29189/61904 [4:26:38<12:31:39, 1.38s/it] 47%|████▋ | 29190/61904 [4:26:40<12:38:48, 1.39s/it] 47%|████▋ | 29191/61904 [4:26:41<13:03:25, 1.44s/it] 47%|████▋ | 29192/61904 [4:26:43<13:28:25, 1.48s/it] 47%|████▋ | 29193/61904 [4:26:44<13:19:11, 1.47s/it] 47%|████▋ | 29194/61904 [4:26:46<13:26:53, 1.48s/it] 47%|████▋ | 29195/61904 [4:26:47<13:09:47, 1.45s/it] 47%|████▋ | 29196/61904 [4:26:49<13:25:36, 1.48s/it] 47%|████▋ | 29197/61904 [4:26:50<13:06:11, 1.44s/it] 47%|████▋ | 29198/61904 [4:26:51<13:03:37, 1.44s/it] 47%|████▋ | 29199/61904 [4:26:53<13:09:21, 1.45s/it] 47%|████▋ | 29200/61904 [4:26:54<12:52:05, 1.42s/it] {'loss': 2.5925, 'learning_rate': 1.5300142616361986e-07, 'epoch': 7.55} + 47%|████▋ | 29200/61904 [4:26:54<12:52:05, 1.42s/it] 47%|████▋ | 29201/61904 [4:26:56<12:36:45, 1.39s/it] 47%|████▋ | 29202/61904 [4:26:57<12:26:09, 1.37s/it] 47%|████▋ | 29203/61904 [4:26:58<12:38:52, 1.39s/it] 47%|████▋ | 29204/61904 [4:27:00<12:26:18, 1.37s/it] 47%|████▋ | 29205/61904 [4:27:01<12:49:38, 1.41s/it] 47%|████▋ | 29206/61904 [4:27:03<12:39:36, 1.39s/it] 47%|████▋ | 29207/61904 [4:27:04<12:39:15, 1.39s/it] 47%|████▋ | 29208/61904 [4:27:05<12:28:13, 1.37s/it] 47%|████▋ | 29209/61904 [4:27:07<12:23:32, 1.36s/it] 47%|████▋ | 29210/61904 [4:27:08<12:22:03, 1.36s/it] 47%|████▋ | 29211/61904 [4:27:10<12:59:48, 1.43s/it] 47%|████▋ | 29212/61904 [4:27:11<12:48:04, 1.41s/it] 47%|████▋ | 29213/61904 [4:27:12<12:51:55, 1.42s/it] 47%|████▋ | 29214/61904 [4:27:14<12:21:07, 1.36s/it] 47%|████▋ | 29215/61904 [4:27:15<12:32:58, 1.38s/it] 47%|████▋ | 29216/61904 [4:27:16<12:28:48, 1.37s/it] 47%|████▋ | 29217/61904 [4:27:18<12:30:39, 1.38s/it] 47%|████▋ | 29218/61904 [4:27:19<12:41:35, 1.40s/it] 47%|████▋ | 29219/61904 [4:27:21<12:34:00, 1.38s/it] 47%|████▋ | 29220/61904 [4:27:22<13:00:00, 1.43s/it] {'loss': 2.6029, 'learning_rate': 1.5296901335407753e-07, 'epoch': 7.55} + 47%|████▋ | 29220/61904 [4:27:22<13:00:00, 1.43s/it] 47%|████▋ | 29221/61904 [4:27:24<12:56:15, 1.43s/it] 47%|████▋ | 29222/61904 [4:27:25<12:54:42, 1.42s/it] 47%|████▋ | 29223/61904 [4:27:26<12:35:26, 1.39s/it] 47%|████▋ | 29224/61904 [4:27:28<12:49:14, 1.41s/it] 47%|████▋ | 29225/61904 [4:27:29<12:24:19, 1.37s/it] 47%|████▋ | 29226/61904 [4:27:30<12:26:22, 1.37s/it] 47%|████▋ | 29227/61904 [4:27:32<12:12:12, 1.34s/it] 47%|████▋ | 29228/61904 [4:27:33<12:17:25, 1.35s/it] 47%|████▋ | 29229/61904 [4:27:34<12:25:01, 1.37s/it] 47%|████▋ | 29230/61904 [4:27:36<12:17:40, 1.35s/it] 47%|████▋ | 29231/61904 [4:27:37<12:37:25, 1.39s/it] 47%|████▋ | 29232/61904 [4:27:38<12:14:26, 1.35s/it] 47%|████▋ | 29233/61904 [4:27:40<12:11:39, 1.34s/it] 47%|████▋ | 29234/61904 [4:27:41<12:33:24, 1.38s/it] 47%|████▋ | 29235/61904 [4:27:43<12:30:10, 1.38s/it] 47%|████▋ | 29236/61904 [4:27:44<12:21:20, 1.36s/it] 47%|████▋ | 29237/61904 [4:27:45<12:29:32, 1.38s/it] 47%|████▋ | 29238/61904 [4:27:47<13:21:18, 1.47s/it] 47%|████▋ | 29239/61904 [4:27:48<12:36:44, 1.39s/it] 47%|████▋ | 29240/61904 [4:27:50<12:21:05, 1.36s/it] {'loss': 2.6053, 'learning_rate': 1.529366005445352e-07, 'epoch': 7.56} + 47%|████▋ | 29240/61904 [4:27:50<12:21:05, 1.36s/it] 47%|████▋ | 29241/61904 [4:27:51<12:17:36, 1.35s/it] 47%|████▋ | 29242/61904 [4:27:52<12:24:32, 1.37s/it] 47%|████▋ | 29243/61904 [4:27:54<12:26:31, 1.37s/it] 47%|████▋ | 29244/61904 [4:27:55<12:41:37, 1.40s/it] 47%|████▋ | 29245/61904 [4:27:56<12:19:23, 1.36s/it] 47%|████▋ | 29246/61904 [4:27:58<12:16:39, 1.35s/it] 47%|████▋ | 29247/61904 [4:27:59<12:20:18, 1.36s/it] 47%|████▋ | 29248/61904 [4:28:00<12:21:18, 1.36s/it] 47%|████▋ | 29249/61904 [4:28:02<12:29:34, 1.38s/it] 47%|████▋ | 29250/61904 [4:28:04<13:24:33, 1.48s/it] 47%|████▋ | 29251/61904 [4:28:05<13:32:18, 1.49s/it] 47%|████▋ | 29252/61904 [4:28:06<13:02:44, 1.44s/it] 47%|████▋ | 29253/61904 [4:28:08<12:38:08, 1.39s/it] 47%|████▋ | 29254/61904 [4:28:09<12:38:28, 1.39s/it] 47%|████▋ | 29255/61904 [4:28:11<12:53:12, 1.42s/it] 47%|████▋ | 29256/61904 [4:28:12<12:45:41, 1.41s/it] 47%|████▋ | 29257/61904 [4:28:13<12:36:19, 1.39s/it] 47%|████▋ | 29258/61904 [4:28:15<12:47:38, 1.41s/it] 47%|████▋ | 29259/61904 [4:28:16<12:56:22, 1.43s/it] 47%|████▋ | 29260/61904 [4:28:18<12:48:30, 1.41s/it] {'loss': 2.5341, 'learning_rate': 1.5290418773499288e-07, 'epoch': 7.56} + 47%|████▋ | 29260/61904 [4:28:18<12:48:30, 1.41s/it] 47%|████▋ | 29261/61904 [4:28:19<12:29:38, 1.38s/it] 47%|████▋ | 29262/61904 [4:28:20<12:21:42, 1.36s/it] 47%|████▋ | 29263/61904 [4:28:22<12:19:35, 1.36s/it] 47%|████▋ | 29264/61904 [4:28:23<12:24:13, 1.37s/it] 47%|████▋ | 29265/61904 [4:28:24<12:38:57, 1.40s/it] 47%|████▋ | 29266/61904 [4:28:26<12:17:58, 1.36s/it] 47%|████▋ | 29267/61904 [4:28:27<12:37:42, 1.39s/it] 47%|████▋ | 29268/61904 [4:28:29<12:52:32, 1.42s/it] 47%|████▋ | 29269/61904 [4:28:30<13:01:29, 1.44s/it] 47%|████▋ | 29270/61904 [4:28:32<12:52:30, 1.42s/it] 47%|████▋ | 29271/61904 [4:28:33<12:40:06, 1.40s/it] 47%|████▋ | 29272/61904 [4:28:34<12:09:32, 1.34s/it] 47%|████▋ | 29273/61904 [4:28:35<12:16:42, 1.35s/it] 47%|████▋ | 29274/61904 [4:28:37<12:13:17, 1.35s/it] 47%|████▋ | 29275/61904 [4:28:38<12:15:09, 1.35s/it] 47%|████▋ | 29276/61904 [4:28:39<12:08:07, 1.34s/it] 47%|████▋ | 29277/61904 [4:28:41<12:25:34, 1.37s/it] 47%|████▋ | 29278/61904 [4:28:42<12:29:24, 1.38s/it] 47%|████▋ | 29279/61904 [4:28:44<12:20:25, 1.36s/it] 47%|████▋ | 29280/61904 [4:28:45<12:19:27, 1.36s/it] {'loss': 2.4981, 'learning_rate': 1.5287177492545054e-07, 'epoch': 7.57} + 47%|████▋ | 29280/61904 [4:28:45<12:19:27, 1.36s/it] 47%|████▋ | 29281/61904 [4:28:46<12:08:33, 1.34s/it] 47%|████▋ | 29282/61904 [4:28:48<12:29:40, 1.38s/it] 47%|████▋ | 29283/61904 [4:28:49<12:36:29, 1.39s/it] 47%|████▋ | 29284/61904 [4:28:51<12:30:23, 1.38s/it] 47%|████▋ | 29285/61904 [4:28:52<12:31:49, 1.38s/it] 47%|████▋ | 29286/61904 [4:28:53<12:30:58, 1.38s/it] 47%|████▋ | 29287/61904 [4:28:55<12:36:19, 1.39s/it] 47%|████▋ | 29288/61904 [4:28:56<13:01:10, 1.44s/it] 47%|████▋ | 29289/61904 [4:28:58<12:58:17, 1.43s/it] 47%|████▋ | 29290/61904 [4:28:59<12:53:38, 1.42s/it] 47%|████▋ | 29291/61904 [4:29:01<13:00:50, 1.44s/it] 47%|████▋ | 29292/61904 [4:29:02<12:40:19, 1.40s/it] 47%|████▋ | 29293/61904 [4:29:03<12:50:25, 1.42s/it] 47%|████▋ | 29294/61904 [4:29:05<12:41:13, 1.40s/it] 47%|████▋ | 29295/61904 [4:29:06<12:27:29, 1.38s/it] 47%|████▋ | 29296/61904 [4:29:07<12:26:46, 1.37s/it] 47%|████▋ | 29297/61904 [4:29:09<12:15:19, 1.35s/it] 47%|████▋ | 29298/61904 [4:29:10<12:16:32, 1.36s/it] 47%|████▋ | 29299/61904 [4:29:11<12:20:47, 1.36s/it] 47%|████▋ | 29300/61904 [4:29:13<12:35:17, 1.39s/it] {'loss': 2.5551, 'learning_rate': 1.528393621159082e-07, 'epoch': 7.57} + 47%|████▋ | 29300/61904 [4:29:13<12:35:17, 1.39s/it] 47%|████▋ | 29301/61904 [4:29:14<12:58:43, 1.43s/it] 47%|████▋ | 29302/61904 [4:29:16<12:30:04, 1.38s/it] 47%|████▋ | 29303/61904 [4:29:17<12:23:47, 1.37s/it] 47%|████▋ | 29304/61904 [4:29:18<12:25:28, 1.37s/it] 47%|████▋ | 29305/61904 [4:29:20<12:07:41, 1.34s/it] 47%|████▋ | 29306/61904 [4:29:21<11:59:25, 1.32s/it] 47%|████▋ | 29307/61904 [4:29:22<12:10:53, 1.35s/it] 47%|████▋ | 29308/61904 [4:29:24<12:25:56, 1.37s/it] 47%|████▋ | 29309/61904 [4:29:25<12:24:45, 1.37s/it] 47%|████▋ | 29310/61904 [4:29:26<12:17:46, 1.36s/it] 47%|████▋ | 29311/61904 [4:29:28<12:27:34, 1.38s/it] 47%|████▋ | 29312/61904 [4:29:29<12:25:36, 1.37s/it] 47%|████▋ | 29313/61904 [4:29:31<12:55:07, 1.43s/it] 47%|████▋ | 29314/61904 [4:29:32<12:51:42, 1.42s/it] 47%|████▋ | 29315/61904 [4:29:34<12:58:10, 1.43s/it] 47%|████▋ | 29316/61904 [4:29:35<12:58:15, 1.43s/it] 47%|████▋ | 29317/61904 [4:29:37<12:54:29, 1.43s/it] 47%|████▋ | 29318/61904 [4:29:38<13:20:19, 1.47s/it] 47%|████▋ | 29319/61904 [4:29:40<13:10:26, 1.46s/it] 47%|████▋ | 29320/61904 [4:29:41<12:46:58, 1.41s/it] {'loss': 2.5029, 'learning_rate': 1.5280694930636586e-07, 'epoch': 7.58} + 47%|████▋ | 29320/61904 [4:29:41<12:46:58, 1.41s/it] 47%|████▋ | 29321/61904 [4:29:42<12:59:58, 1.44s/it] 47%|████▋ | 29322/61904 [4:29:44<12:48:14, 1.41s/it] 47%|████▋ | 29323/61904 [4:29:45<12:37:17, 1.39s/it] 47%|████▋ | 29324/61904 [4:29:46<12:19:02, 1.36s/it] 47%|████▋ | 29325/61904 [4:29:48<12:26:03, 1.37s/it] 47%|████▋ | 29326/61904 [4:29:49<12:15:11, 1.35s/it] 47%|████▋ | 29327/61904 [4:29:50<12:21:30, 1.37s/it] 47%|████▋ | 29328/61904 [4:29:52<12:19:58, 1.36s/it] 47%|████▋ | 29329/61904 [4:29:53<12:35:18, 1.39s/it] 47%|████▋ | 29330/61904 [4:29:55<12:41:05, 1.40s/it] 47%|████▋ | 29331/61904 [4:29:56<12:32:42, 1.39s/it] 47%|████▋ | 29332/61904 [4:29:58<13:02:51, 1.44s/it] 47%|████▋ | 29333/61904 [4:29:59<12:43:09, 1.41s/it] 47%|████▋ | 29334/61904 [4:30:00<12:55:36, 1.43s/it] 47%|████▋ | 29335/61904 [4:30:02<12:54:59, 1.43s/it] 47%|████▋ | 29336/61904 [4:30:03<12:56:38, 1.43s/it] 47%|████▋ | 29337/61904 [4:30:05<13:14:36, 1.46s/it] 47%|████▋ | 29338/61904 [4:30:06<13:28:06, 1.49s/it] 47%|████▋ | 29339/61904 [4:30:08<13:15:21, 1.47s/it] 47%|████▋ | 29340/61904 [4:30:09<13:01:40, 1.44s/it] {'loss': 2.6108, 'learning_rate': 1.5277453649682352e-07, 'epoch': 7.58} + 47%|████▋ | 29340/61904 [4:30:09<13:01:40, 1.44s/it] 47%|████▋ | 29341/61904 [4:30:11<12:52:37, 1.42s/it] 47%|████▋ | 29342/61904 [4:30:12<12:35:51, 1.39s/it] 47%|████▋ | 29343/61904 [4:30:13<12:51:22, 1.42s/it] 47%|████▋ | 29344/61904 [4:30:15<12:37:06, 1.40s/it] 47%|████▋ | 29345/61904 [4:30:16<12:31:34, 1.39s/it] 47%|████▋ | 29346/61904 [4:30:17<12:31:38, 1.39s/it] 47%|████▋ | 29347/61904 [4:30:19<12:33:59, 1.39s/it] 47%|████▋ | 29348/61904 [4:30:20<12:39:22, 1.40s/it] 47%|████▋ | 29349/61904 [4:30:22<12:24:08, 1.37s/it] 47%|████▋ | 29350/61904 [4:30:23<12:51:34, 1.42s/it] 47%|████▋ | 29351/61904 [4:30:24<12:48:11, 1.42s/it] 47%|████▋ | 29352/61904 [4:30:26<12:58:58, 1.44s/it] 47%|████▋ | 29353/61904 [4:30:27<12:46:44, 1.41s/it] 47%|████▋ | 29354/61904 [4:30:29<12:31:35, 1.39s/it] 47%|████▋ | 29355/61904 [4:30:30<12:48:14, 1.42s/it] 47%|████▋ | 29356/61904 [4:30:31<12:29:42, 1.38s/it] 47%|████▋ | 29357/61904 [4:30:33<12:47:20, 1.41s/it] 47%|████▋ | 29358/61904 [4:30:34<12:45:19, 1.41s/it] 47%|████▋ | 29359/61904 [4:30:36<12:49:13, 1.42s/it] 47%|████▋ | 29360/61904 [4:30:37<12:52:44, 1.42s/it] {'loss': 2.5652, 'learning_rate': 1.527421236872812e-07, 'epoch': 7.59} + 47%|████▋ | 29360/61904 [4:30:37<12:52:44, 1.42s/it] 47%|████▋ | 29361/61904 [4:30:39<12:34:23, 1.39s/it] 47%|████▋ | 29362/61904 [4:30:40<12:31:35, 1.39s/it] 47%|████▋ | 29363/61904 [4:30:41<13:00:29, 1.44s/it] 47%|████▋ | 29364/61904 [4:30:43<12:50:23, 1.42s/it] 47%|████▋ | 29365/61904 [4:30:44<13:00:35, 1.44s/it] 47%|████▋ | 29366/61904 [4:30:46<12:37:17, 1.40s/it] 47%|████▋ | 29367/61904 [4:30:47<12:11:10, 1.35s/it] 47%|████▋ | 29368/61904 [4:30:48<12:34:19, 1.39s/it] 47%|████▋ | 29369/61904 [4:30:50<12:43:48, 1.41s/it] 47%|████▋ | 29370/61904 [4:30:51<12:32:22, 1.39s/it] 47%|████▋ | 29371/61904 [4:30:52<12:23:17, 1.37s/it] 47%|████▋ | 29372/61904 [4:30:54<12:34:30, 1.39s/it] 47%|████▋ | 29373/61904 [4:30:55<12:41:11, 1.40s/it] 47%|████▋ | 29374/61904 [4:30:57<12:52:12, 1.42s/it] 47%|████▋ | 29375/61904 [4:30:58<13:03:53, 1.45s/it] 47%|████▋ | 29376/61904 [4:31:00<13:11:48, 1.46s/it] 47%|████▋ | 29377/61904 [4:31:01<13:01:10, 1.44s/it] 47%|████▋ | 29378/61904 [4:31:02<12:26:05, 1.38s/it] 47%|████▋ | 29379/61904 [4:31:04<13:59:53, 1.55s/it] 47%|████▋ | 29380/61904 [4:31:06<13:12:34, 1.46s/it] {'loss': 2.5423, 'learning_rate': 1.5270971087773887e-07, 'epoch': 7.59} + 47%|████▋ | 29380/61904 [4:31:06<13:12:34, 1.46s/it] 47%|████▋ | 29381/61904 [4:31:07<12:59:02, 1.44s/it] 47%|████▋ | 29382/61904 [4:31:08<13:00:45, 1.44s/it] 47%|████▋ | 29383/61904 [4:31:10<13:20:23, 1.48s/it] 47%|████▋ | 29384/61904 [4:31:11<12:47:32, 1.42s/it] 47%|████▋ | 29385/61904 [4:31:13<12:25:09, 1.37s/it] 47%|████▋ | 29386/61904 [4:31:14<12:24:29, 1.37s/it] 47%|████▋ | 29387/61904 [4:31:15<12:24:05, 1.37s/it] 47%|████▋ | 29388/61904 [4:31:17<12:28:07, 1.38s/it] 47%|████▋ | 29389/61904 [4:31:18<12:27:55, 1.38s/it] 47%|████▋ | 29390/61904 [4:31:20<13:19:48, 1.48s/it] 47%|████▋ | 29391/61904 [4:31:21<13:10:42, 1.46s/it] 47%|████▋ | 29392/61904 [4:31:23<12:57:14, 1.43s/it] 47%|████▋ | 29393/61904 [4:31:24<12:35:23, 1.39s/it] 47%|████▋ | 29394/61904 [4:31:25<12:33:54, 1.39s/it] 47%|████▋ | 29395/61904 [4:31:27<12:36:37, 1.40s/it] 47%|████▋ | 29396/61904 [4:31:28<12:57:33, 1.44s/it] 47%|████▋ | 29397/61904 [4:31:30<13:38:11, 1.51s/it] 47%|████▋ | 29398/61904 [4:31:31<13:14:30, 1.47s/it] 47%|████▋ | 29399/61904 [4:31:33<12:58:11, 1.44s/it] 47%|████▋ | 29400/61904 [4:31:34<12:52:15, 1.43s/it] {'loss': 2.5123, 'learning_rate': 1.5267729806819654e-07, 'epoch': 7.6} + 47%|████▋ | 29400/61904 [4:31:34<12:52:15, 1.43s/it] 47%|████▋ | 29401/61904 [4:31:35<12:56:12, 1.43s/it] 47%|████▋ | 29402/61904 [4:31:37<12:52:12, 1.43s/it] 47%|████▋ | 29403/61904 [4:31:38<12:23:28, 1.37s/it] 47%|████▋ | 29404/61904 [4:31:39<11:58:44, 1.33s/it] 48%|███���▊ | 29405/61904 [4:31:41<12:12:16, 1.35s/it] 48%|████▊ | 29406/61904 [4:31:42<12:22:49, 1.37s/it] 48%|████▊ | 29407/61904 [4:31:44<12:25:36, 1.38s/it] 48%|████▊ | 29408/61904 [4:31:45<12:30:27, 1.39s/it] 48%|████▊ | 29409/61904 [4:31:46<12:53:03, 1.43s/it] 48%|████▊ | 29410/61904 [4:31:48<12:43:23, 1.41s/it] 48%|████▊ | 29411/61904 [4:31:49<12:28:20, 1.38s/it] 48%|████▊ | 29412/61904 [4:31:50<12:13:19, 1.35s/it] 48%|████▊ | 29413/61904 [4:31:52<12:20:50, 1.37s/it] 48%|████▊ | 29414/61904 [4:31:53<12:12:12, 1.35s/it] 48%|████▊ | 29415/61904 [4:31:54<12:04:00, 1.34s/it] 48%|████▊ | 29416/61904 [4:31:56<12:29:17, 1.38s/it] 48%|████▊ | 29417/61904 [4:31:57<12:19:44, 1.37s/it] 48%|████▊ | 29418/61904 [4:31:59<12:30:59, 1.39s/it] 48%|████▊ | 29419/61904 [4:32:00<12:09:33, 1.35s/it] 48%|████▊ | 29420/61904 [4:32:01<12:05:57, 1.34s/it] {'loss': 2.5787, 'learning_rate': 1.5264488525865422e-07, 'epoch': 7.6} + 48%|████▊ | 29420/61904 [4:32:01<12:05:57, 1.34s/it] 48%|████▊ | 29421/61904 [4:32:03<12:06:12, 1.34s/it] 48%|████▊ | 29422/61904 [4:32:04<11:52:55, 1.32s/it] 48%|████▊ | 29423/61904 [4:32:05<11:49:49, 1.31s/it] 48%|████▊ | 29424/61904 [4:32:06<11:41:21, 1.30s/it] 48%|████▊ | 29425/61904 [4:32:08<11:51:50, 1.32s/it] 48%|████▊ | 29426/61904 [4:32:09<11:54:43, 1.32s/it] 48%|████▊ | 29427/61904 [4:32:10<11:47:07, 1.31s/it] 48%|████▊ | 29428/61904 [4:32:12<11:50:27, 1.31s/it] 48%|████▊ | 29429/61904 [4:32:13<12:37:23, 1.40s/it] 48%|████▊ | 29430/61904 [4:32:15<12:25:14, 1.38s/it] 48%|████▊ | 29431/61904 [4:32:16<12:06:27, 1.34s/it] 48%|████▊ | 29432/61904 [4:32:17<11:55:17, 1.32s/it] 48%|████▊ | 29433/61904 [4:32:19<12:10:38, 1.35s/it] 48%|████▊ | 29434/61904 [4:32:20<12:38:50, 1.40s/it] 48%|████▊ | 29435/61904 [4:32:22<12:48:20, 1.42s/it] 48%|████▊ | 29436/61904 [4:32:23<12:41:39, 1.41s/it] 48%|████▊ | 29437/61904 [4:32:24<12:31:09, 1.39s/it] 48%|████▊ | 29438/61904 [4:32:26<12:26:30, 1.38s/it] 48%|████▊ | 29439/61904 [4:32:27<12:22:37, 1.37s/it] 48%|████▊ | 29440/61904 [4:32:28<12:04:08, 1.34s/it] {'loss': 2.5894, 'learning_rate': 1.5261247244911189e-07, 'epoch': 7.61} + 48%|████▊ | 29440/61904 [4:32:28<12:04:08, 1.34s/it] 48%|████▊ | 29441/61904 [4:32:30<11:54:10, 1.32s/it] 48%|████▊ | 29442/61904 [4:32:31<12:20:06, 1.37s/it] 48%|████▊ | 29443/61904 [4:32:32<12:06:21, 1.34s/it] 48%|████▊ | 29444/61904 [4:32:34<12:18:08, 1.36s/it] 48%|████▊ | 29445/61904 [4:32:35<12:46:09, 1.42s/it] 48%|████▊ | 29446/61904 [4:32:37<12:33:52, 1.39s/it] 48%|████▊ | 29447/61904 [4:32:38<12:38:27, 1.40s/it] 48%|████▊ | 29448/61904 [4:32:40<12:48:35, 1.42s/it] 48%|████▊ | 29449/61904 [4:32:41<12:37:04, 1.40s/it] 48%|████▊ | 29450/61904 [4:32:42<12:20:51, 1.37s/it] 48%|████▊ | 29451/61904 [4:32:44<12:36:28, 1.40s/it] 48%|████▊ | 29452/61904 [4:32:45<12:26:36, 1.38s/it] 48%|████▊ | 29453/61904 [4:32:46<12:17:37, 1.36s/it] 48%|████▊ | 29454/61904 [4:32:48<12:37:17, 1.40s/it] 48%|████▊ | 29455/61904 [4:32:49<12:58:35, 1.44s/it] 48%|████▊ | 29456/61904 [4:32:51<12:49:24, 1.42s/it] 48%|████▊ | 29457/61904 [4:32:52<13:07:35, 1.46s/it] 48%|████▊ | 29458/61904 [4:32:54<12:50:06, 1.42s/it] 48%|████▊ | 29459/61904 [4:32:55<13:04:28, 1.45s/it] 48%|████▊ | 29460/61904 [4:32:57<13:20:45, 1.48s/it] {'loss': 2.5427, 'learning_rate': 1.5258005963956955e-07, 'epoch': 7.61} + 48%|████▊ | 29460/61904 [4:32:57<13:20:45, 1.48s/it] 48%|████▊ | 29461/61904 [4:32:58<13:17:36, 1.48s/it] 48%|████▊ | 29462/61904 [4:33:00<13:02:04, 1.45s/it] 48%|████▊ | 29463/61904 [4:33:01<12:57:36, 1.44s/it] 48%|████▊ | 29464/61904 [4:33:02<12:34:16, 1.40s/it] 48%|████▊ | 29465/61904 [4:33:04<12:41:51, 1.41s/it] 48%|████▊ | 29466/61904 [4:33:05<12:48:01, 1.42s/it] 48%|████▊ | 29467/61904 [4:33:06<12:38:28, 1.40s/it] 48%|████▊ | 29468/61904 [4:33:08<12:26:05, 1.38s/it] 48%|████▊ | 29469/61904 [4:33:09<12:28:33, 1.38s/it] 48%|████▊ | 29470/61904 [4:33:11<12:45:10, 1.42s/it] 48%|████▊ | 29471/61904 [4:33:12<12:38:22, 1.40s/it] 48%|████▊ | 29472/61904 [4:33:13<12:16:26, 1.36s/it] 48%|████▊ | 29473/61904 [4:33:15<12:14:47, 1.36s/it] 48%|████▊ | 29474/61904 [4:33:16<12:32:10, 1.39s/it] 48%|████▊ | 29475/61904 [4:33:18<12:37:20, 1.40s/it] 48%|████▊ | 29476/61904 [4:33:19<12:13:20, 1.36s/it] 48%|████▊ | 29477/61904 [4:33:20<11:58:54, 1.33s/it] 48%|████▊ | 29478/61904 [4:33:21<12:00:46, 1.33s/it] 48%|████▊ | 29479/61904 [4:33:23<12:01:58, 1.34s/it] 48%|████▊ | 29480/61904 [4:33:24<11:46:34, 1.31s/it] {'loss': 2.6234, 'learning_rate': 1.5254764683002724e-07, 'epoch': 7.62} + 48%|████▊ | 29480/61904 [4:33:24<11:46:34, 1.31s/it] 48%|████▊ | 29481/61904 [4:33:25<11:56:32, 1.33s/it] 48%|████▊ | 29482/61904 [4:33:27<12:12:52, 1.36s/it] 48%|████▊ | 29483/61904 [4:33:28<12:17:16, 1.36s/it] 48%|████▊ | 29484/61904 [4:33:29<12:02:18, 1.34s/it] 48%|████▊ | 29485/61904 [4:33:31<12:06:54, 1.35s/it] 48%|████▊ | 29486/61904 [4:33:32<12:10:05, 1.35s/it] 48%|████▊ | 29487/61904 [4:33:34<12:27:25, 1.38s/it] 48%|████▊ | 29488/61904 [4:33:35<12:28:42, 1.39s/it] 48%|████▊ | 29489/61904 [4:33:36<12:22:27, 1.37s/it] 48%|████▊ | 29490/61904 [4:33:38<12:22:23, 1.37s/it] 48%|████▊ | 29491/61904 [4:33:39<12:05:49, 1.34s/it] 48%|████▊ | 29492/61904 [4:33:40<12:07:01, 1.35s/it] 48%|████▊ | 29493/61904 [4:33:42<12:03:23, 1.34s/it] 48%|████▊ | 29494/61904 [4:33:43<12:30:55, 1.39s/it] 48%|████▊ | 29495/61904 [4:33:45<12:30:32, 1.39s/it] 48%|████▊ | 29496/61904 [4:33:46<12:48:31, 1.42s/it] 48%|████▊ | 29497/61904 [4:33:48<13:02:53, 1.45s/it] 48%|████▊ | 29498/61904 [4:33:49<13:07:26, 1.46s/it] 48%|████▊ | 29499/61904 [4:33:50<12:52:37, 1.43s/it] 48%|████▊ | 29500/61904 [4:33:52<12:35:13, 1.40s/it] {'loss': 2.5201, 'learning_rate': 1.525152340204849e-07, 'epoch': 7.62} + 48%|████▊ | 29500/61904 [4:33:52<12:35:13, 1.40s/it] 48%|████▊ | 29501/61904 [4:33:53<12:24:15, 1.38s/it] 48%|████▊ | 29502/61904 [4:33:55<12:28:56, 1.39s/it] 48%|████▊ | 29503/61904 [4:33:56<12:21:56, 1.37s/it] 48%|████▊ | 29504/61904 [4:33:57<12:17:54, 1.37s/it] 48%|████▊ | 29505/61904 [4:33:59<12:27:34, 1.38s/it] 48%|████▊ | 29506/61904 [4:34:00<12:48:33, 1.42s/it] 48%|████▊ | 29507/61904 [4:34:02<12:50:10, 1.43s/it] 48%|████▊ | 29508/61904 [4:34:03<12:58:14, 1.44s/it] 48%|████▊ | 29509/61904 [4:34:04<12:34:16, 1.40s/it] 48%|████▊ | 29510/61904 [4:34:06<12:46:56, 1.42s/it] 48%|████▊ | 29511/61904 [4:34:07<12:43:42, 1.41s/it] 48%|████▊ | 29512/61904 [4:34:09<12:35:07, 1.40s/it] 48%|████▊ | 29513/61904 [4:34:10<12:13:36, 1.36s/it] 48%|████▊ | 29514/61904 [4:34:11<12:13:08, 1.36s/it] 48%|████▊ | 29515/61904 [4:34:13<12:05:58, 1.34s/it] 48%|████▊ | 29516/61904 [4:34:14<12:10:31, 1.35s/it] 48%|████▊ | 29517/61904 [4:34:15<11:54:52, 1.32s/it] 48%|████▊ | 29518/61904 [4:34:17<12:11:21, 1.35s/it] 48%|████▊ | 29519/61904 [4:34:18<12:36:03, 1.40s/it] 48%|████▊ | 29520/61904 [4:34:19<12:09:38, 1.35s/it] {'loss': 2.5933, 'learning_rate': 1.5248282121094256e-07, 'epoch': 7.63} + 48%|████▊ | 29520/61904 [4:34:19<12:09:38, 1.35s/it] 48%|████▊ | 29521/61904 [4:34:21<12:39:50, 1.41s/it] 48%|████▊ | 29522/61904 [4:34:22<12:48:00, 1.42s/it] 48%|████▊ | 29523/61904 [4:34:24<12:40:19, 1.41s/it] 48%|████▊ | 29524/61904 [4:34:25<12:32:37, 1.39s/it] 48%|████▊ | 29525/61904 [4:34:26<12:30:27, 1.39s/it] 48%|████▊ | 29526/61904 [4:34:28<12:53:31, 1.43s/it] 48%|████▊ | 29527/61904 [4:34:29<12:55:57, 1.44s/it] 48%|████▊ | 29528/61904 [4:34:31<12:50:19, 1.43s/it] 48%|████▊ | 29529/61904 [4:34:32<12:23:47, 1.38s/it] 48%|████▊ | 29530/61904 [4:34:33<12:22:09, 1.38s/it] 48%|████▊ | 29531/61904 [4:34:35<12:48:20, 1.42s/it] 48%|████▊ | 29532/61904 [4:34:37<13:21:51, 1.49s/it] 48%|████▊ | 29533/61904 [4:34:38<12:38:07, 1.41s/it] 48%|████▊ | 29534/61904 [4:34:39<12:36:17, 1.40s/it] 48%|████▊ | 29535/61904 [4:34:41<12:49:04, 1.43s/it] 48%|████▊ | 29536/61904 [4:34:42<13:00:27, 1.45s/it] 48%|████▊ | 29537/61904 [4:34:44<12:36:55, 1.40s/it] 48%|████▊ | 29538/61904 [4:34:45<12:57:25, 1.44s/it] 48%|████▊ | 29539/61904 [4:34:46<12:29:26, 1.39s/it] 48%|████▊ | 29540/61904 [4:34:48<12:16:01, 1.36s/it] {'loss': 2.555, 'learning_rate': 1.5245040840140022e-07, 'epoch': 7.63} + 48%|████▊ | 29540/61904 [4:34:48<12:16:01, 1.36s/it] 48%|████▊ | 29541/61904 [4:34:49<12:11:33, 1.36s/it] 48%|████▊ | 29542/61904 [4:34:50<12:14:34, 1.36s/it] 48%|████▊ | 29543/61904 [4:34:52<12:25:58, 1.38s/it] 48%|████▊ | 29544/61904 [4:34:53<12:00:27, 1.34s/it] 48%|████▊ | 29545/61904 [4:34:54<12:24:19, 1.38s/it] 48%|████▊ | 29546/61904 [4:34:56<12:06:00, 1.35s/it] 48%|████▊ | 29547/61904 [4:34:57<12:10:22, 1.35s/it] 48%|████▊ | 29548/61904 [4:34:58<12:10:12, 1.35s/it] 48%|████▊ | 29549/61904 [4:35:00<12:19:15, 1.37s/it] 48%|████▊ | 29550/61904 [4:35:01<12:34:03, 1.40s/it] 48%|████▊ | 29551/61904 [4:35:03<12:26:37, 1.38s/it] 48%|████▊ | 29552/61904 [4:35:04<12:22:15, 1.38s/it] 48%|████▊ | 29553/61904 [4:35:05<12:24:08, 1.38s/it] 48%|████▊ | 29554/61904 [4:35:07<12:24:16, 1.38s/it] 48%|████▊ | 29555/61904 [4:35:08<12:29:16, 1.39s/it] 48%|████▊ | 29556/61904 [4:35:10<12:32:58, 1.40s/it] 48%|████▊ | 29557/61904 [4:35:11<12:31:34, 1.39s/it] 48%|████▊ | 29558/61904 [4:35:12<12:15:33, 1.36s/it] 48%|████▊ | 29559/61904 [4:35:14<11:54:50, 1.33s/it] 48%|████▊ | 29560/61904 [4:35:15<11:44:17, 1.31s/it] {'loss': 2.5297, 'learning_rate': 1.5241799559185788e-07, 'epoch': 7.64} + 48%|████▊ | 29560/61904 [4:35:15<11:44:17, 1.31s/it] 48%|████▊ | 29561/61904 [4:35:16<11:35:50, 1.29s/it] 48%|████▊ | 29562/61904 [4:35:18<11:55:59, 1.33s/it] 48%|████▊ | 29563/61904 [4:35:19<12:20:50, 1.37s/it] 48%|████▊ | 29564/61904 [4:35:20<12:20:32, 1.37s/it] 48%|████▊ | 29565/61904 [4:35:22<12:11:45, 1.36s/it] 48%|████▊ | 29566/61904 [4:35:23<12:34:53, 1.40s/it] 48%|████▊ | 29567/61904 [4:35:25<12:39:38, 1.41s/it] 48%|████▊ | 29568/61904 [4:35:26<12:27:31, 1.39s/it] 48%|████▊ | 29569/61904 [4:35:27<12:25:13, 1.38s/it] 48%|████▊ | 29570/61904 [4:35:29<12:14:44, 1.36s/it] 48%|████▊ | 29571/61904 [4:35:30<12:13:56, 1.36s/it] 48%|████▊ | 29572/61904 [4:35:31<12:26:48, 1.39s/it] 48%|████▊ | 29573/61904 [4:35:33<12:09:04, 1.35s/it] 48%|████▊ | 29574/61904 [4:35:34<12:16:58, 1.37s/it] 48%|████▊ | 29575/61904 [4:35:36<12:41:46, 1.41s/it] 48%|████▊ | 29576/61904 [4:35:37<12:15:57, 1.37s/it] 48%|████▊ | 29577/61904 [4:35:38<11:55:15, 1.33s/it] 48%|████▊ | 29578/61904 [4:35:39<11:47:43, 1.31s/it] 48%|████▊ | 29579/61904 [4:35:41<12:02:36, 1.34s/it] 48%|████▊ | 29580/61904 [4:35:42<12:12:19, 1.36s/it] {'loss': 2.574, 'learning_rate': 1.5238558278231557e-07, 'epoch': 7.65} + 48%|████▊ | 29580/61904 [4:35:42<12:12:19, 1.36s/it] 48%|████▊ | 29581/61904 [4:35:44<12:49:11, 1.43s/it] 48%|████▊ | 29582/61904 [4:35:45<12:37:32, 1.41s/it] 48%|████▊ | 29583/61904 [4:35:46<12:19:28, 1.37s/it] 48%|████▊ | 29584/61904 [4:35:48<12:00:57, 1.34s/it] 48%|████▊ | 29585/61904 [4:35:49<12:14:24, 1.36s/it] 48%|████▊ | 29586/61904 [4:35:50<12:07:59, 1.35s/it] 48%|████▊ | 29587/61904 [4:35:52<12:05:12, 1.35s/it] 48%|████▊ | 29588/61904 [4:35:53<12:15:41, 1.37s/it] 48%|████▊ | 29589/61904 [4:35:55<12:19:33, 1.37s/it] 48%|████▊ | 29590/61904 [4:35:56<11:53:00, 1.32s/it] 48%|████▊ | 29591/61904 [4:35:57<11:48:08, 1.31s/it] 48%|████▊ | 29592/61904 [4:35:58<11:59:46, 1.34s/it] 48%|████▊ | 29593/61904 [4:36:00<11:54:38, 1.33s/it] 48%|████▊ | 29594/61904 [4:36:01<11:58:55, 1.34s/it] 48%|████▊ | 29595/61904 [4:36:03<12:11:26, 1.36s/it] 48%|████▊ | 29596/61904 [4:36:04<12:10:05, 1.36s/it] 48%|████▊ | 29597/61904 [4:36:05<12:15:15, 1.37s/it] 48%|████▊ | 29598/61904 [4:36:07<12:24:22, 1.38s/it] 48%|████▊ | 29599/61904 [4:36:08<12:09:41, 1.36s/it] 48%|████▊ | 29600/61904 [4:36:09<12:01:36, 1.34s/it] {'loss': 2.6062, 'learning_rate': 1.5235316997277323e-07, 'epoch': 7.65} + 48%|████▊ | 29600/61904 [4:36:09<12:01:36, 1.34s/it] 48%|████▊ | 29601/61904 [4:36:11<12:15:12, 1.37s/it] 48%|████▊ | 29602/61904 [4:36:12<12:03:20, 1.34s/it] 48%|████▊ | 29603/61904 [4:36:13<12:15:29, 1.37s/it] 48%|████▊ | 29604/61904 [4:36:15<11:58:03, 1.33s/it] 48%|████▊ | 29605/61904 [4:36:16<12:03:06, 1.34s/it] 48%|████▊ | 29606/61904 [4:36:18<12:23:08, 1.38s/it] 48%|████▊ | 29607/61904 [4:36:19<12:09:07, 1.35s/it] 48%|████▊ | 29608/61904 [4:36:20<12:26:19, 1.39s/it] 48%|████▊ | 29609/61904 [4:36:22<11:58:57, 1.34s/it] 48%|████▊ | 29610/61904 [4:36:23<12:07:01, 1.35s/it] 48%|████▊ | 29611/61904 [4:36:24<12:03:49, 1.34s/it] 48%|████▊ | 29612/61904 [4:36:26<11:59:52, 1.34s/it] 48%|████▊ | 29613/61904 [4:36:27<12:15:35, 1.37s/it] 48%|████▊ | 29614/61904 [4:36:28<12:20:42, 1.38s/it] 48%|████▊ | 29615/61904 [4:36:30<12:03:48, 1.34s/it] 48%|████▊ | 29616/61904 [4:36:31<12:16:53, 1.37s/it] 48%|████▊ | 29617/61904 [4:36:33<12:34:27, 1.40s/it] 48%|████▊ | 29618/61904 [4:36:34<12:49:13, 1.43s/it] 48%|████▊ | 29619/61904 [4:36:36<13:11:09, 1.47s/it] 48%|████▊ | 29620/61904 [4:36:37<13:00:47, 1.45s/it] {'loss': 2.5437, 'learning_rate': 1.523207571632309e-07, 'epoch': 7.66} + 48%|████▊ | 29620/61904 [4:36:37<13:00:47, 1.45s/it] 48%|████▊ | 29621/61904 [4:36:38<12:41:17, 1.41s/it] 48%|████▊ | 29622/61904 [4:36:40<12:22:01, 1.38s/it] 48%|████▊ | 29623/61904 [4:36:41<12:07:28, 1.35s/it] 48%|████▊ | 29624/61904 [4:36:42<12:18:29, 1.37s/it] 48%|████▊ | 29625/61904 [4:36:44<12:45:08, 1.42s/it] 48%|████▊ | 29626/61904 [4:36:45<12:48:48, 1.43s/it] 48%|████▊ | 29627/61904 [4:36:47<13:01:22, 1.45s/it] 48%|████▊ | 29628/61904 [4:36:48<12:50:09, 1.43s/it] 48%|████▊ | 29629/61904 [4:36:50<12:23:30, 1.38s/it] 48%|████▊ | 29630/61904 [4:36:51<12:24:07, 1.38s/it] 48%|████▊ | 29631/61904 [4:36:52<12:27:39, 1.39s/it] 48%|████▊ | 29632/61904 [4:36:54<12:26:03, 1.39s/it] 48%|████▊ | 29633/61904 [4:36:55<12:38:43, 1.41s/it] 48%|████▊ | 29634/61904 [4:36:57<12:30:23, 1.40s/it] 48%|████▊ | 29635/61904 [4:36:58<13:09:27, 1.47s/it] 48%|████▊ | 29636/61904 [4:37:00<13:04:00, 1.46s/it] 48%|████▊ | 29637/61904 [4:37:01<12:54:19, 1.44s/it] 48%|████▊ | 29638/61904 [4:37:02<12:46:17, 1.42s/it] 48%|████▊ | 29639/61904 [4:37:04<12:32:50, 1.40s/it] 48%|████▊ | 29640/61904 [4:37:05<12:28:17, 1.39s/it] {'loss': 2.599, 'learning_rate': 1.5228834435368858e-07, 'epoch': 7.66} + 48%|████▊ | 29640/61904 [4:37:05<12:28:17, 1.39s/it] 48%|████▊ | 29641/61904 [4:37:07<12:32:11, 1.40s/it] 48%|████▊ | 29642/61904 [4:37:08<12:27:05, 1.39s/it] 48%|████▊ | 29643/61904 [4:37:09<12:40:18, 1.41s/it] 48%|████▊ | 29644/61904 [4:37:11<12:56:43, 1.44s/it] 48%|████▊ | 29645/61904 [4:37:12<13:10:00, 1.47s/it] 48%|████▊ | 29646/61904 [4:37:14<13:15:41, 1.48s/it] 48%|████▊ | 29647/61904 [4:37:15<12:57:36, 1.45s/it] 48%|████▊ | 29648/61904 [4:37:17<12:35:23, 1.41s/it] 48%|████▊ | 29649/61904 [4:37:18<12:32:35, 1.40s/it] 48%|████▊ | 29650/61904 [4:37:19<12:42:45, 1.42s/it] 48%|████▊ | 29651/61904 [4:37:21<12:32:04, 1.40s/it] 48%|████▊ | 29652/61904 [4:37:22<12:09:54, 1.36s/it] 48%|████▊ | 29653/61904 [4:37:23<12:04:42, 1.35s/it] 48%|████▊ | 29654/61904 [4:37:25<12:25:01, 1.39s/it] 48%|████▊ | 29655/61904 [4:37:26<12:25:12, 1.39s/it] 48%|████▊ | 29656/61904 [4:37:28<12:11:05, 1.36s/it] 48%|████▊ | 29657/61904 [4:37:29<12:23:04, 1.38s/it] 48%|████▊ | 29658/61904 [4:37:30<12:38:41, 1.41s/it] 48%|████▊ | 29659/61904 [4:37:32<12:54:52, 1.44s/it] 48%|████▊ | 29660/61904 [4:37:33<12:43:30, 1.42s/it] {'loss': 2.5211, 'learning_rate': 1.5225593154414625e-07, 'epoch': 7.67} + 48%|████▊ | 29660/61904 [4:37:33<12:43:30, 1.42s/it] 48%|████▊ | 29661/61904 [4:37:35<12:38:29, 1.41s/it] 48%|████▊ | 29662/61904 [4:37:36<12:31:47, 1.40s/it] 48%|████▊ | 29663/61904 [4:37:37<12:19:18, 1.38s/it] 48%|████▊ | 29664/61904 [4:37:39<12:49:35, 1.43s/it] 48%|████▊ | 29665/61904 [4:37:40<13:02:31, 1.46s/it] 48%|████▊ | 29666/61904 [4:37:42<12:29:17, 1.39s/it] 48%|████▊ | 29667/61904 [4:37:43<11:57:26, 1.34s/it] 48%|████▊ | 29668/61904 [4:37:44<12:19:50, 1.38s/it] 48%|████▊ | 29669/61904 [4:37:46<11:56:42, 1.33s/it] 48%|████▊ | 29670/61904 [4:37:47<12:07:25, 1.35s/it] 48%|████▊ | 29671/61904 [4:37:48<11:55:32, 1.33s/it] 48%|████▊ | 29672/61904 [4:37:50<12:16:56, 1.37s/it] 48%|████▊ | 29673/61904 [4:37:51<12:15:05, 1.37s/it] 48%|████▊ | 29674/61904 [4:37:53<12:28:15, 1.39s/it] 48%|████▊ | 29675/61904 [4:37:54<12:56:53, 1.45s/it] 48%|████▊ | 29676/61904 [4:37:56<12:41:13, 1.42s/it] 48%|████▊ | 29677/61904 [4:37:57<12:40:32, 1.42s/it] 48%|████▊ | 29678/61904 [4:37:58<12:34:01, 1.40s/it] 48%|████▊ | 29679/61904 [4:38:00<12:36:54, 1.41s/it] 48%|████▊ | 29680/61904 [4:38:01<12:40:10, 1.42s/it] {'loss': 2.538, 'learning_rate': 1.522235187346039e-07, 'epoch': 7.67} + 48%|████▊ | 29680/61904 [4:38:01<12:40:10, 1.42s/it] 48%|████▊ | 29681/61904 [4:38:03<13:02:13, 1.46s/it] 48%|████▊ | 29682/61904 [4:38:04<12:50:09, 1.43s/it] 48%|████▊ | 29683/61904 [4:38:05<12:32:14, 1.40s/it] 48%|████▊ | 29684/61904 [4:38:07<12:18:02, 1.37s/it] 48%|████▊ | 29685/61904 [4:38:08<12:19:52, 1.38s/it] 48%|████▊ | 29686/61904 [4:38:10<12:29:16, 1.40s/it] 48%|████▊ | 29687/61904 [4:38:11<12:32:30, 1.40s/it] 48%|████▊ | 29688/61904 [4:38:13<13:13:12, 1.48s/it] 48%|████▊ | 29689/61904 [4:38:14<12:48:23, 1.43s/it] 48%|████▊ | 29690/61904 [4:38:15<13:07:34, 1.47s/it] 48%|████▊ | 29691/61904 [4:38:17<12:21:09, 1.38s/it] 48%|████▊ | 29692/61904 [4:38:18<12:48:40, 1.43s/it] 48%|████▊ | 29693/61904 [4:38:19<12:22:34, 1.38s/it] 48%|████▊ | 29694/61904 [4:38:21<12:23:17, 1.38s/it] 48%|████▊ | 29695/61904 [4:38:22<12:50:29, 1.44s/it] 48%|████▊ | 29696/61904 [4:38:24<12:29:08, 1.40s/it] 48%|████▊ | 29697/61904 [4:38:25<12:28:03, 1.39s/it] 48%|████▊ | 29698/61904 [4:38:27<12:30:31, 1.40s/it] 48%|████▊ | 29699/61904 [4:38:28<12:10:58, 1.36s/it] 48%|████▊ | 29700/61904 [4:38:29<12:29:23, 1.40s/it] {'loss': 2.5887, 'learning_rate': 1.5219110592506157e-07, 'epoch': 7.68} + 48%|████▊ | 29700/61904 [4:38:29<12:29:23, 1.40s/it] 48%|████▊ | 29701/61904 [4:38:31<12:40:53, 1.42s/it] 48%|████▊ | 29702/61904 [4:38:32<13:30:24, 1.51s/it] 48%|████▊ | 29703/61904 [4:38:34<13:20:26, 1.49s/it] 48%|████▊ | 29704/61904 [4:38:35<12:46:55, 1.43s/it] 48%|████▊ | 29705/61904 [4:38:37<13:03:14, 1.46s/it] 48%|████▊ | 29706/61904 [4:38:38<12:37:44, 1.41s/it] 48%|████▊ | 29707/61904 [4:38:39<12:28:45, 1.40s/it] 48%|████▊ | 29708/61904 [4:38:41<12:18:40, 1.38s/it] 48%|████▊ | 29709/61904 [4:38:42<13:06:38, 1.47s/it] 48%|████▊ | 29710/61904 [4:38:44<13:06:40, 1.47s/it] 48%|████▊ | 29711/61904 [4:38:45<12:41:44, 1.42s/it] 48%|████▊ | 29712/61904 [4:38:47<12:39:21, 1.42s/it] 48%|████▊ | 29713/61904 [4:38:48<13:10:14, 1.47s/it] 48%|████▊ | 29714/61904 [4:38:50<13:06:05, 1.47s/it] 48%|████▊ | 29715/61904 [4:38:51<13:17:08, 1.49s/it] 48%|████▊ | 29716/61904 [4:38:53<13:01:08, 1.46s/it] 48%|████▊ | 29717/61904 [4:38:54<12:37:39, 1.41s/it] 48%|████▊ | 29718/61904 [4:38:55<12:40:22, 1.42s/it] 48%|████▊ | 29719/61904 [4:38:57<12:32:44, 1.40s/it] 48%|████▊ | 29720/61904 [4:38:58<12:16:47, 1.37s/it] {'loss': 2.5519, 'learning_rate': 1.5215869311551926e-07, 'epoch': 7.68} + 48%|████▊ | 29720/61904 [4:38:58<12:16:47, 1.37s/it] 48%|████▊ | 29721/61904 [4:38:59<12:22:48, 1.38s/it] 48%|████▊ | 29722/61904 [4:39:01<12:24:58, 1.39s/it] 48%|████▊ | 29723/61904 [4:39:02<12:22:10, 1.38s/it] 48%|████▊ | 29724/61904 [4:39:04<12:47:30, 1.43s/it] 48%|████▊ | 29725/61904 [4:39:05<12:55:37, 1.45s/it] 48%|████▊ | 29726/61904 [4:39:07<13:00:10, 1.45s/it] 48%|████▊ | 29727/61904 [4:39:08<12:39:33, 1.42s/it] 48%|████▊ | 29728/61904 [4:39:09<12:28:28, 1.40s/it] 48%|████�� | 29729/61904 [4:39:11<12:30:43, 1.40s/it] 48%|████▊ | 29730/61904 [4:39:12<12:13:09, 1.37s/it] 48%|████▊ | 29731/61904 [4:39:14<12:40:49, 1.42s/it] 48%|████▊ | 29732/61904 [4:39:15<12:12:13, 1.37s/it] 48%|████▊ | 29733/61904 [4:39:16<12:18:58, 1.38s/it] 48%|████▊ | 29734/61904 [4:39:17<12:02:13, 1.35s/it] 48%|████▊ | 29735/61904 [4:39:19<12:00:10, 1.34s/it] 48%|████▊ | 29736/61904 [4:39:20<11:32:29, 1.29s/it] 48%|████▊ | 29737/61904 [4:39:21<11:50:39, 1.33s/it] 48%|████▊ | 29738/61904 [4:39:23<12:12:52, 1.37s/it] 48%|████▊ | 29739/61904 [4:39:24<12:09:02, 1.36s/it] 48%|████▊ | 29740/61904 [4:39:26<13:02:14, 1.46s/it] {'loss': 2.5509, 'learning_rate': 1.5212628030597692e-07, 'epoch': 7.69} + 48%|████▊ | 29740/61904 [4:39:26<13:02:14, 1.46s/it] 48%|████▊ | 29741/61904 [4:39:27<12:33:37, 1.41s/it] 48%|████▊ | 29742/61904 [4:39:29<12:25:16, 1.39s/it] 48%|████▊ | 29743/61904 [4:39:30<12:24:55, 1.39s/it] 48%|████▊ | 29744/61904 [4:39:31<12:28:16, 1.40s/it] 48%|████▊ | 29745/61904 [4:39:33<12:11:50, 1.37s/it] 48%|████▊ | 29746/61904 [4:39:34<12:34:15, 1.41s/it] 48%|████▊ | 29747/61904 [4:39:35<12:20:45, 1.38s/it] 48%|████▊ | 29748/61904 [4:39:37<12:39:52, 1.42s/it] 48%|████▊ | 29749/61904 [4:39:38<12:54:25, 1.45s/it] 48%|████▊ | 29750/61904 [4:39:40<12:31:27, 1.40s/it] 48%|████▊ | 29751/61904 [4:39:41<12:15:13, 1.37s/it] 48%|████▊ | 29752/61904 [4:39:43<12:30:33, 1.40s/it] 48%|████▊ | 29753/61904 [4:39:44<12:30:44, 1.40s/it] 48%|████▊ | 29754/61904 [4:39:45<12:14:34, 1.37s/it] 48%|████▊ | 29755/61904 [4:39:47<12:14:08, 1.37s/it] 48%|████▊ | 29756/61904 [4:39:48<11:55:38, 1.34s/it] 48%|████▊ | 29757/61904 [4:39:49<12:01:11, 1.35s/it] 48%|████▊ | 29758/61904 [4:39:51<12:24:00, 1.39s/it] 48%|████▊ | 29759/61904 [4:39:52<12:36:31, 1.41s/it] 48%|████▊ | 29760/61904 [4:39:54<12:25:56, 1.39s/it] {'loss': 2.5353, 'learning_rate': 1.5209386749643458e-07, 'epoch': 7.69} + 48%|████▊ | 29760/61904 [4:39:54<12:25:56, 1.39s/it] 48%|████▊ | 29761/61904 [4:39:55<12:30:39, 1.40s/it] 48%|████▊ | 29762/61904 [4:39:56<12:20:19, 1.38s/it] 48%|████▊ | 29763/61904 [4:39:58<12:04:11, 1.35s/it] 48%|████▊ | 29764/61904 [4:39:59<12:20:24, 1.38s/it] 48%|████▊ | 29765/61904 [4:40:01<13:48:29, 1.55s/it] 48%|████▊ | 29766/61904 [4:40:02<13:03:15, 1.46s/it] 48%|████▊ | 29767/61904 [4:40:04<12:46:17, 1.43s/it] 48%|████▊ | 29768/61904 [4:40:05<12:45:57, 1.43s/it] 48%|████▊ | 29769/61904 [4:40:06<12:32:31, 1.41s/it] 48%|████▊ | 29770/61904 [4:40:08<12:32:57, 1.41s/it] 48%|████▊ | 29771/61904 [4:40:09<12:35:48, 1.41s/it] 48%|████▊ | 29772/61904 [4:40:11<12:46:45, 1.43s/it] 48%|████▊ | 29773/61904 [4:40:12<12:55:33, 1.45s/it] 48%|████▊ | 29774/61904 [4:40:13<12:17:43, 1.38s/it] 48%|████▊ | 29775/61904 [4:40:15<12:00:54, 1.35s/it] 48%|████▊ | 29776/61904 [4:40:16<12:20:25, 1.38s/it] 48%|████▊ | 29777/61904 [4:40:17<12:19:38, 1.38s/it] 48%|████▊ | 29778/61904 [4:40:19<12:22:49, 1.39s/it] 48%|████▊ | 29779/61904 [4:40:20<12:15:30, 1.37s/it] 48%|████▊ | 29780/61904 [4:40:22<12:05:04, 1.35s/it] {'loss': 2.6387, 'learning_rate': 1.5206145468689224e-07, 'epoch': 7.7} + 48%|████▊ | 29780/61904 [4:40:22<12:05:04, 1.35s/it] 48%|████▊ | 29781/61904 [4:40:23<12:11:43, 1.37s/it] 48%|████▊ | 29782/61904 [4:40:24<12:04:03, 1.35s/it] 48%|████▊ | 29783/61904 [4:40:26<12:04:37, 1.35s/it] 48%|████▊ | 29784/61904 [4:40:27<11:59:20, 1.34s/it] 48%|████▊ | 29785/61904 [4:40:28<11:52:09, 1.33s/it] 48%|████▊ | 29786/61904 [4:40:30<12:31:14, 1.40s/it] 48%|████▊ | 29787/61904 [4:40:31<12:27:03, 1.40s/it] 48%|████▊ | 29788/61904 [4:40:33<12:52:43, 1.44s/it] 48%|████▊ | 29789/61904 [4:40:34<12:44:48, 1.43s/it] 48%|████▊ | 29790/61904 [4:40:35<12:21:16, 1.38s/it] 48%|████▊ | 29791/61904 [4:40:37<12:23:48, 1.39s/it] 48%|████▊ | 29792/61904 [4:40:38<12:45:04, 1.43s/it] 48%|████▊ | 29793/61904 [4:40:40<12:42:54, 1.43s/it] 48%|████▊ | 29794/61904 [4:40:41<12:12:29, 1.37s/it] 48%|████▊ | 29795/61904 [4:40:42<12:24:50, 1.39s/it] 48%|████▊ | 29796/61904 [4:40:44<12:44:06, 1.43s/it] 48%|████▊ | 29797/61904 [4:40:46<13:06:24, 1.47s/it] 48%|████▊ | 29798/61904 [4:40:47<13:06:08, 1.47s/it] 48%|████▊ | 29799/61904 [4:40:48<12:58:39, 1.46s/it] 48%|████▊ | 29800/61904 [4:40:50<12:55:54, 1.45s/it] {'loss': 2.5547, 'learning_rate': 1.5202904187734993e-07, 'epoch': 7.7} + 48%|████▊ | 29800/61904 [4:40:50<12:55:54, 1.45s/it] 48%|████▊ | 29801/61904 [4:40:51<12:36:48, 1.41s/it] 48%|████▊ | 29802/61904 [4:40:53<12:28:57, 1.40s/it] 48%|████▊ | 29803/61904 [4:40:54<12:31:13, 1.40s/it] 48%|████▊ | 29804/61904 [4:40:55<12:12:46, 1.37s/it] 48%|████▊ | 29805/61904 [4:40:57<12:30:27, 1.40s/it] 48%|████▊ | 29806/61904 [4:40:58<12:16:01, 1.38s/it] 48%|████▊ | 29807/61904 [4:40:59<12:00:19, 1.35s/it] 48%|████▊ | 29808/61904 [4:41:01<12:01:49, 1.35s/it] 48%|████▊ | 29809/61904 [4:41:02<12:14:24, 1.37s/it] 48%|████▊ | 29810/61904 [4:41:04<12:33:05, 1.41s/it] 48%|████▊ | 29811/61904 [4:41:05<12:21:01, 1.39s/it] 48%|████▊ | 29812/61904 [4:41:06<12:24:38, 1.39s/it] 48%|████▊ | 29813/61904 [4:41:08<12:26:21, 1.40s/it] 48%|████▊ | 29814/61904 [4:41:09<12:11:25, 1.37s/it] 48%|████▊ | 29815/61904 [4:41:11<12:29:32, 1.40s/it] 48%|████▊ | 29816/61904 [4:41:12<12:23:49, 1.39s/it] 48%|████▊ | 29817/61904 [4:41:13<12:33:30, 1.41s/it] 48%|████▊ | 29818/61904 [4:41:15<12:32:12, 1.41s/it] 48%|████▊ | 29819/61904 [4:41:16<12:32:48, 1.41s/it] 48%|████▊ | 29820/61904 [4:41:18<12:32:02, 1.41s/it] {'loss': 2.65, 'learning_rate': 1.519966290678076e-07, 'epoch': 7.71} + 48%|████▊ | 29820/61904 [4:41:18<12:32:02, 1.41s/it] 48%|████▊ | 29821/61904 [4:41:19<12:41:55, 1.42s/it] 48%|████▊ | 29822/61904 [4:41:20<12:11:18, 1.37s/it] 48%|████▊ | 29823/61904 [4:41:22<12:05:37, 1.36s/it] 48%|████▊ | 29824/61904 [4:41:23<11:52:34, 1.33s/it] 48%|████▊ | 29825/61904 [4:41:24<11:56:00, 1.34s/it] 48%|████▊ | 29826/61904 [4:41:26<11:48:54, 1.33s/it] 48%|████▊ | 29827/61904 [4:41:27<12:02:35, 1.35s/it] 48%|████▊ | 29828/61904 [4:41:28<12:21:59, 1.39s/it] 48%|████▊ | 29829/61904 [4:41:30<12:24:05, 1.39s/it] 48%|████▊ | 29830/61904 [4:41:31<12:39:29, 1.42s/it] 48%|████▊ | 29831/61904 [4:41:33<12:31:06, 1.41s/it] 48%|████▊ | 29832/61904 [4:41:34<12:44:40, 1.43s/it] 48%|████▊ | 29833/61904 [4:41:35<12:33:24, 1.41s/it] 48%|████▊ | 29834/61904 [4:41:37<12:22:48, 1.39s/it] 48%|████▊ | 29835/61904 [4:41:38<12:16:05, 1.38s/it] 48%|████▊ | 29836/61904 [4:41:40<12:07:21, 1.36s/it] 48%|████▊ | 29837/61904 [4:41:41<12:00:34, 1.35s/it] 48%|████▊ | 29838/61904 [4:41:42<12:03:14, 1.35s/it] 48%|████▊ | 29839/61904 [4:41:44<12:05:13, 1.36s/it] 48%|████▊ | 29840/61904 [4:41:45<11:45:43, 1.32s/it] {'loss': 2.5733, 'learning_rate': 1.5196421625826526e-07, 'epoch': 7.71} + 48%|████▊ | 29840/61904 [4:41:45<11:45:43, 1.32s/it] 48%|████▊ | 29841/61904 [4:41:46<11:46:12, 1.32s/it] 48%|████▊ | 29842/61904 [4:41:47<11:54:42, 1.34s/it] 48%|████▊ | 29843/61904 [4:41:49<11:39:59, 1.31s/it] 48%|████▊ | 29844/61904 [4:41:50<11:42:27, 1.31s/it] 48%|████▊ | 29845/61904 [4:41:52<12:07:48, 1.36s/it] 48%|████▊ | 29846/61904 [4:41:53<12:13:08, 1.37s/it] 48%|████▊ | 29847/61904 [4:41:54<12:05:37, 1.36s/it] 48%|████▊ | 29848/61904 [4:41:56<12:09:59, 1.37s/it] 48%|████▊ | 29849/61904 [4:41:57<12:15:09, 1.38s/it] 48%|████▊ | 29850/61904 [4:41:58<12:18:22, 1.38s/it] 48%|████▊ | 29851/61904 [4:42:00<12:19:17, 1.38s/it] 48%|████▊ | 29852/61904 [4:42:01<11:59:37, 1.35s/it] 48%|████▊ | 29853/61904 [4:42:03<12:19:22, 1.38s/it] 48%|████▊ | 29854/61904 [4:42:04<12:29:27, 1.40s/it] 48%|████▊ | 29855/61904 [4:42:06<12:53:24, 1.45s/it] 48%|████▊ | 29856/61904 [4:42:07<13:24:59, 1.51s/it] 48%|████▊ | 29857/61904 [4:42:09<13:18:56, 1.50s/it] 48%|████▊ | 29858/61904 [4:42:10<13:05:45, 1.47s/it] 48%|████▊ | 29859/61904 [4:42:11<12:42:43, 1.43s/it] 48%|��███▊ | 29860/61904 [4:42:13<12:45:10, 1.43s/it] {'loss': 2.5608, 'learning_rate': 1.5193180344872294e-07, 'epoch': 7.72} + 48%|████▊ | 29860/61904 [4:42:13<12:45:10, 1.43s/it] 48%|████▊ | 29861/61904 [4:42:14<12:48:37, 1.44s/it] 48%|████▊ | 29862/61904 [4:42:16<13:31:40, 1.52s/it] 48%|████▊ | 29863/61904 [4:42:17<13:08:46, 1.48s/it] 48%|████▊ | 29864/61904 [4:42:19<13:04:34, 1.47s/it] 48%|████▊ | 29865/61904 [4:42:20<12:56:29, 1.45s/it] 48%|████▊ | 29866/61904 [4:42:22<12:30:35, 1.41s/it] 48%|████▊ | 29867/61904 [4:42:23<12:33:18, 1.41s/it] 48%|████▊ | 29868/61904 [4:42:24<12:26:35, 1.40s/it] 48%|████▊ | 29869/61904 [4:42:26<12:14:30, 1.38s/it] 48%|████▊ | 29870/61904 [4:42:27<12:07:06, 1.36s/it] 48%|████▊ | 29871/61904 [4:42:28<12:06:07, 1.36s/it] 48%|████▊ | 29872/61904 [4:42:30<12:13:12, 1.37s/it] 48%|████▊ | 29873/61904 [4:42:31<12:19:05, 1.38s/it] 48%|████▊ | 29874/61904 [4:42:33<12:14:39, 1.38s/it] 48%|████▊ | 29875/61904 [4:42:34<12:33:14, 1.41s/it] 48%|████▊ | 29876/61904 [4:42:35<12:42:30, 1.43s/it] 48%|████▊ | 29877/61904 [4:42:37<13:08:30, 1.48s/it] 48%|████▊ | 29878/61904 [4:42:38<12:50:55, 1.44s/it] 48%|████▊ | 29879/61904 [4:42:40<12:45:17, 1.43s/it] 48%|████▊ | 29880/61904 [4:42:41<12:38:01, 1.42s/it] {'loss': 2.5819, 'learning_rate': 1.518993906391806e-07, 'epoch': 7.72} + 48%|████▊ | 29880/61904 [4:42:41<12:38:01, 1.42s/it] 48%|████▊ | 29881/61904 [4:42:43<12:27:24, 1.40s/it] 48%|████▊ | 29882/61904 [4:42:44<12:19:30, 1.39s/it] 48%|████▊ | 29883/61904 [4:42:45<11:55:47, 1.34s/it] 48%|████▊ | 29884/61904 [4:42:47<12:16:35, 1.38s/it] 48%|████▊ | 29885/61904 [4:42:48<12:32:02, 1.41s/it] 48%|████▊ | 29886/61904 [4:42:50<12:45:10, 1.43s/it] 48%|████▊ | 29887/61904 [4:42:51<12:33:10, 1.41s/it] 48%|████▊ | 29888/61904 [4:42:52<12:15:41, 1.38s/it] 48%|████▊ | 29889/61904 [4:42:54<12:16:58, 1.38s/it] 48%|████▊ | 29890/61904 [4:42:55<12:27:16, 1.40s/it] 48%|████▊ | 29891/61904 [4:42:56<12:19:08, 1.39s/it] 48%|████▊ | 29892/61904 [4:42:58<12:41:02, 1.43s/it] 48%|████▊ | 29893/61904 [4:42:59<12:34:47, 1.41s/it] 48%|████▊ | 29894/61904 [4:43:01<12:36:12, 1.42s/it] 48%|████▊ | 29895/61904 [4:43:02<12:14:52, 1.38s/it] 48%|████▊ | 29896/61904 [4:43:03<11:58:27, 1.35s/it] 48%|████▊ | 29897/61904 [4:43:05<12:05:41, 1.36s/it] 48%|████▊ | 29898/61904 [4:43:06<12:17:26, 1.38s/it] 48%|████▊ | 29899/61904 [4:43:08<12:14:26, 1.38s/it] 48%|████▊ | 29900/61904 [4:43:09<12:18:21, 1.38s/it] {'loss': 2.6017, 'learning_rate': 1.5186697782963827e-07, 'epoch': 7.73} + 48%|████▊ | 29900/61904 [4:43:09<12:18:21, 1.38s/it] 48%|████▊ | 29901/61904 [4:43:10<12:34:54, 1.42s/it] 48%|████▊ | 29902/61904 [4:43:12<12:17:58, 1.38s/it] 48%|████▊ | 29903/61904 [4:43:13<12:31:45, 1.41s/it] 48%|████▊ | 29904/61904 [4:43:15<12:49:39, 1.44s/it] 48%|████▊ | 29905/61904 [4:43:16<12:50:33, 1.44s/it] 48%|████▊ | 29906/61904 [4:43:18<12:38:33, 1.42s/it] 48%|████▊ | 29907/61904 [4:43:19<12:33:41, 1.41s/it] 48%|████▊ | 29908/61904 [4:43:20<12:23:08, 1.39s/it] 48%|████▊ | 29909/61904 [4:43:22<12:41:12, 1.43s/it] 48%|████▊ | 29910/61904 [4:43:23<12:29:47, 1.41s/it] 48%|████▊ | 29911/61904 [4:43:24<12:06:07, 1.36s/it] 48%|████▊ | 29912/61904 [4:43:26<12:21:51, 1.39s/it] 48%|████▊ | 29913/61904 [4:43:27<12:38:33, 1.42s/it] 48%|████▊ | 29914/61904 [4:43:29<12:18:28, 1.39s/it] 48%|████▊ | 29915/61904 [4:43:30<12:19:58, 1.39s/it] 48%|████▊ | 29916/61904 [4:43:31<12:21:14, 1.39s/it] 48%|████▊ | 29917/61904 [4:43:33<12:12:10, 1.37s/it] 48%|████▊ | 29918/61904 [4:43:34<12:11:52, 1.37s/it] 48%|████▊ | 29919/61904 [4:43:36<12:19:59, 1.39s/it] 48%|████▊ | 29920/61904 [4:43:37<12:28:43, 1.40s/it] {'loss': 2.5467, 'learning_rate': 1.5183456502009593e-07, 'epoch': 7.73} + 48%|████▊ | 29920/61904 [4:43:37<12:28:43, 1.40s/it] 48%|████▊ | 29921/61904 [4:43:38<12:31:24, 1.41s/it] 48%|████▊ | 29922/61904 [4:43:40<12:41:32, 1.43s/it] 48%|████▊ | 29923/61904 [4:43:41<12:57:46, 1.46s/it] 48%|████▊ | 29924/61904 [4:43:43<12:37:08, 1.42s/it] 48%|████▊ | 29925/61904 [4:43:44<12:29:19, 1.41s/it] 48%|████▊ | 29926/61904 [4:43:46<12:46:27, 1.44s/it] 48%|████▊ | 29927/61904 [4:43:47<12:42:39, 1.43s/it] 48%|████▊ | 29928/61904 [4:43:49<12:40:10, 1.43s/it] 48%|████▊ | 29929/61904 [4:43:50<13:24:20, 1.51s/it] 48%|████▊ | 29930/61904 [4:43:52<12:50:06, 1.45s/it] 48%|████▊ | 29931/61904 [4:43:53<12:45:49, 1.44s/it] 48%|████▊ | 29932/61904 [4:43:54<12:32:09, 1.41s/it] 48%|████▊ | 29933/61904 [4:43:56<12:40:05, 1.43s/it] 48%|████▊ | 29934/61904 [4:43:57<12:37:53, 1.42s/it] 48%|████▊ | 29935/61904 [4:43:59<12:46:54, 1.44s/it] 48%|████▊ | 29936/61904 [4:44:00<13:27:57, 1.52s/it] 48%|████▊ | 29937/61904 [4:44:02<13:21:36, 1.50s/it] 48%|████▊ | 29938/61904 [4:44:03<12:48:09, 1.44s/it] 48%|████▊ | 29939/61904 [4:44:04<12:30:08, 1.41s/it] 48%|████▊ | 29940/61904 [4:44:06<12:11:43, 1.37s/it] {'loss': 2.558, 'learning_rate': 1.518021522105536e-07, 'epoch': 7.74} + 48%|████▊ | 29940/61904 [4:44:06<12:11:43, 1.37s/it] 48%|████▊ | 29941/61904 [4:44:07<12:15:04, 1.38s/it] 48%|████▊ | 29942/61904 [4:44:09<12:29:45, 1.41s/it] 48%|████▊ | 29943/61904 [4:44:10<12:24:22, 1.40s/it] 48%|████▊ | 29944/61904 [4:44:11<12:29:20, 1.41s/it] 48%|████▊ | 29945/61904 [4:44:13<12:33:33, 1.41s/it] 48%|████▊ | 29946/61904 [4:44:14<12:28:45, 1.41s/it] 48%|████▊ | 29947/61904 [4:44:16<12:41:32, 1.43s/it] 48%|████▊ | 29948/61904 [4:44:17<12:38:59, 1.43s/it] 48%|████▊ | 29949/61904 [4:44:19<12:41:21, 1.43s/it] 48%|████▊ | 29950/61904 [4:44:20<12:33:15, 1.41s/it] 48%|████▊ | 29951/61904 [4:44:21<12:54:56, 1.46s/it] 48%|████▊ | 29952/61904 [4:44:23<13:24:39, 1.51s/it] 48%|████▊ | 29953/61904 [4:44:24<12:46:17, 1.44s/it] 48%|████▊ | 29954/61904 [4:44:26<12:53:49, 1.45s/it] 48%|████▊ | 29955/61904 [4:44:28<13:21:49, 1.51s/it] 48%|████▊ | 29956/61904 [4:44:29<13:07:23, 1.48s/it] 48%|████▊ | 29957/61904 [4:44:30<12:59:07, 1.46s/it] 48%|████▊ | 29958/61904 [4:44:32<12:43:16, 1.43s/it] 48%|████▊ | 29959/61904 [4:44:33<12:21:50, 1.39s/it] 48%|████▊ | 29960/61904 [4:44:34<12:15:38, 1.38s/it] {'loss': 2.5716, 'learning_rate': 1.5176973940101128e-07, 'epoch': 7.74} + 48%|████▊ | 29960/61904 [4:44:34<12:15:38, 1.38s/it] 48%|████▊ | 29961/61904 [4:44:36<12:17:52, 1.39s/it] 48%|████▊ | 29962/61904 [4:44:37<12:40:16, 1.43s/it] 48%|████▊ | 29963/61904 [4:44:39<12:49:52, 1.45s/it] 48%|████▊ | 29964/61904 [4:44:40<12:26:35, 1.40s/it] 48%|████▊ | 29965/61904 [4:44:41<12:20:37, 1.39s/it] 48%|████▊ | 29966/61904 [4:44:43<12:19:12, 1.39s/it] 48%|████▊ | 29967/61904 [4:44:44<12:17:54, 1.39s/it] 48%|████▊ | 29968/61904 [4:44:46<12:16:14, 1.38s/it] 48%|████▊ | 29969/61904 [4:44:47<12:07:05, 1.37s/it] 48%|████▊ | 29970/61904 [4:44:48<12:27:05, 1.40s/it] 48%|████▊ | 29971/61904 [4:44:50<12:35:39, 1.42s/it] 48%|████▊ | 29972/61904 [4:44:51<12:24:44, 1.40s/it] 48%|████▊ | 29973/61904 [4:44:53<12:20:37, 1.39s/it] 48%|████▊ | 29974/61904 [4:44:54<12:22:54, 1.40s/it] 48%|████▊ | 29975/61904 [4:44:55<12:27:19, 1.40s/it] 48%|████▊ | 29976/61904 [4:44:57<12:17:42, 1.39s/it] 48%|████▊ | 29977/61904 [4:44:58<12:01:54, 1.36s/it] 48%|████▊ | 29978/61904 [4:44:59<11:59:38, 1.35s/it] 48%|████▊ | 29979/61904 [4:45:01<11:57:26, 1.35s/it] 48%|████▊ | 29980/61904 [4:45:02<12:08:49, 1.37s/it] {'loss': 2.5765, 'learning_rate': 1.5173732659146894e-07, 'epoch': 7.75} + 48%|████▊ | 29980/61904 [4:45:02<12:08:49, 1.37s/it] 48%|████▊ | 29981/61904 [4:45:04<12:20:24, 1.39s/it] 48%|████▊ | 29982/61904 [4:45:05<12:05:24, 1.36s/it] 48%|████▊ | 29983/61904 [4:45:06<12:16:53, 1.39s/it] 48%|████▊ | 29984/61904 [4:45:08<12:01:26, 1.36s/it] 48%|████▊ | 29985/61904 [4:45:09<12:21:50, 1.39s/it] 48%|████▊ | 29986/61904 [4:45:10<12:19:16, 1.39s/it] 48%|████▊ | 29987/61904 [4:45:12<12:21:17, 1.39s/it] 48%|████▊ | 29988/61904 [4:45:13<12:12:22, 1.38s/it] 48%|████▊ | 29989/61904 [4:45:14<11:56:47, 1.35s/it] 48%|████▊ | 29990/61904 [4:45:16<12:07:30, 1.37s/it] 48%|████▊ | 29991/61904 [4:45:17<11:52:28, 1.34s/it] 48%|████▊ | 29992/61904 [4:45:19<12:47:00, 1.44s/it] 48%|████▊ | 29993/61904 [4:45:20<12:11:10, 1.37s/it] 48%|████▊ | 29994/61904 [4:45:21<12:05:50, 1.36s/it] 48%|████▊ | 29995/61904 [4:45:23<12:14:06, 1.38s/it] 48%|████▊ | 29996/61904 [4:45:24<12:32:00, 1.41s/it] 48%|████▊ | 29997/61904 [4:45:26<13:09:43, 1.49s/it] 48%|████▊ | 29998/61904 [4:45:27<12:41:58, 1.43s/it] 48%|████▊ | 29999/61904 [4:45:29<12:34:42, 1.42s/it] 48%|████▊ | 30000/61904 [4:45:30<12:26:07, 1.40s/it] {'loss': 2.6051, 'learning_rate': 1.517049137819266e-07, 'epoch': 7.75} + 48%|████▊ | 30000/61904 [4:45:30<12:26:07, 1.40s/it] 48%|████▊ | 30001/61904 [4:45:31<12:14:46, 1.38s/it] 48%|████▊ | 30002/61904 [4:45:33<12:14:12, 1.38s/it] 48%|████▊ | 30003/61904 [4:45:34<12:23:15, 1.40s/it] 48%|████▊ | 30004/61904 [4:45:36<12:12:26, 1.38s/it] 48%|████▊ | 30005/61904 [4:45:37<12:13:43, 1.38s/it] 48%|████▊ | 30006/61904 [4:45:38<12:09:51, 1.37s/it] 48%|████▊ | 30007/61904 [4:45:40<12:15:21, 1.38s/it] 48%|████▊ | 30008/61904 [4:45:41<12:29:35, 1.41s/it] 48%|████▊ | 30009/61904 [4:45:42<12:18:02, 1.39s/it] 48%|████▊ | 30010/61904 [4:45:44<12:04:11, 1.36s/it] 48%|████▊ | 30011/61904 [4:45:45<12:46:28, 1.44s/it] 48%|████▊ | 30012/61904 [4:45:47<12:38:08, 1.43s/it] 48%|████▊ | 30013/61904 [4:45:48<12:53:10, 1.45s/it] 48%|████▊ | 30014/61904 [4:45:50<12:55:37, 1.46s/it] 48%|████▊ | 30015/61904 [4:45:51<13:06:28, 1.48s/it] 48%|████▊ | 30016/61904 [4:45:53<12:47:31, 1.44s/it] 48%|████▊ | 30017/61904 [4:45:54<12:26:13, 1.40s/it] 48%|████▊ | 30018/61904 [4:45:55<12:13:38, 1.38s/it] 48%|████▊ | 30019/61904 [4:45:57<11:58:04, 1.35s/it] 48%|████▊ | 30020/61904 [4:45:58<11:58:40, 1.35s/it] {'loss': 2.6049, 'learning_rate': 1.516725009723843e-07, 'epoch': 7.76} + 48%|████▊ | 30020/61904 [4:45:58<11:58:40, 1.35s/it] 48%|████▊ | 30021/61904 [4:45:59<12:06:32, 1.37s/it] 48%|████▊ | 30022/61904 [4:46:01<12:05:36, 1.37s/it] 48%|████▊ | 30023/61904 [4:46:02<12:16:54, 1.39s/it] 49%|████▊ | 30024/61904 [4:46:04<12:17:11, 1.39s/it] 49%|████▊ | 30025/61904 [4:46:05<12:03:08, 1.36s/it] 49%|████▊ | 30026/61904 [4:46:06<11:55:12, 1.35s/it] 49%|████▊ | 30027/61904 [4:46:07<11:41:08, 1.32s/it] 49%|████▊ | 30028/61904 [4:46:09<12:21:05, 1.39s/it] 49%|████▊ | 30029/61904 [4:46:10<12:10:55, 1.38s/it] 49%|████▊ | 30030/61904 [4:46:12<12:19:42, 1.39s/it] 49%|████▊ | 30031/61904 [4:46:13<12:26:08, 1.40s/it] 49%|████▊ | 30032/61904 [4:46:15<12:54:27, 1.46s/it] 49%|████▊ | 30033/61904 [4:46:16<12:40:14, 1.43s/it] 49%|████▊ | 30034/61904 [4:46:18<12:42:43, 1.44s/it] 49%|████▊ | 30035/61904 [4:46:19<12:37:00, 1.43s/it] 49%|████▊ | 30036/61904 [4:46:20<12:38:15, 1.43s/it] 49%|████▊ | 30037/61904 [4:46:22<12:34:03, 1.42s/it] 49%|████▊ | 30038/61904 [4:46:23<12:23:57, 1.40s/it] 49%|████▊ | 30039/61904 [4:46:25<12:23:04, 1.40s/it] 49%|████▊ | 30040/61904 [4:46:26<12:09:28, 1.37s/it] {'loss': 2.5621, 'learning_rate': 1.5164008816284195e-07, 'epoch': 7.76} + 49%|████▊ | 30040/61904 [4:46:26<12:09:28, 1.37s/it] 49%|████▊ | 30041/61904 [4:46:27<12:14:02, 1.38s/it] 49%|████▊ | 30042/61904 [4:46:29<12:02:29, 1.36s/it] 49%|████▊ | 30043/61904 [4:46:30<12:07:12, 1.37s/it] 49%|████▊ | 30044/61904 [4:46:31<12:02:24, 1.36s/it] 49%|████▊ | 30045/61904 [4:46:33<12:17:49, 1.39s/it] 49%|████▊ | 30046/61904 [4:46:34<12:14:46, 1.38s/it] 49%|████▊ | 30047/61904 [4:46:35<12:05:51, 1.37s/it] 49%|████▊ | 30048/61904 [4:46:37<12:07:09, 1.37s/it] 49%|████▊ | 30049/61904 [4:46:38<12:10:41, 1.38s/it] 49%|████▊ | 30050/61904 [4:46:40<12:25:44, 1.40s/it] 49%|████▊ | 30051/61904 [4:46:41<12:43:39, 1.44s/it] 49%|████▊ | 30052/61904 [4:46:43<12:51:17, 1.45s/it] 49%|████▊ | 30053/61904 [4:46:44<12:48:44, 1.45s/it] 49%|████▊ | 30054/61904 [4:46:46<12:32:06, 1.42s/it] 49%|████▊ | 30055/61904 [4:46:47<12:25:42, 1.40s/it] 49%|████▊ | 30056/61904 [4:46:48<12:10:32, 1.38s/it] 49%|████▊ | 30057/61904 [4:46:50<12:32:22, 1.42s/it] 49%|████▊ | 30058/61904 [4:46:51<12:40:59, 1.43s/it] 49%|████▊ | 30059/61904 [4:46:53<12:46:50, 1.44s/it] 49%|████▊ | 30060/61904 [4:46:54<12:46:57, 1.45s/it] {'loss': 2.5449, 'learning_rate': 1.5160767535329962e-07, 'epoch': 7.77} + 49%|████▊ | 30060/61904 [4:46:54<12:46:57, 1.45s/it] 49%|████▊ | 30061/61904 [4:46:55<12:38:59, 1.43s/it] 49%|████▊ | 30062/61904 [4:46:57<12:31:16, 1.42s/it] 49%|████▊ | 30063/61904 [4:46:58<12:13:41, 1.38s/it] 49%|████▊ | 30064/61904 [4:46:59<11:52:26, 1.34s/it] 49%|████▊ | 30065/61904 [4:47:01<11:52:05, 1.34s/it] 49%|████▊ | 30066/61904 [4:47:02<12:10:12, 1.38s/it] 49%|████▊ | 30067/61904 [4:47:04<12:09:37, 1.38s/it] 49%|████▊ | 30068/61904 [4:47:05<11:51:59, 1.34s/it] 49%|████▊ | 30069/61904 [4:47:06<11:36:41, 1.31s/it] 49%|████▊ | 30070/61904 [4:47:08<11:57:03, 1.35s/it] 49%|████▊ | 30071/61904 [4:47:09<12:17:44, 1.39s/it] 49%|████▊ | 30072/61904 [4:47:11<12:36:39, 1.43s/it] 49%|████▊ | 30073/61904 [4:47:12<12:37:29, 1.43s/it] 49%|████▊ | 30074/61904 [4:47:13<12:45:38, 1.44s/it] 49%|████▊ | 30075/61904 [4:47:15<12:41:01, 1.43s/it] 49%|████▊ | 30076/61904 [4:47:16<12:40:15, 1.43s/it] 49%|████▊ | 30077/61904 [4:47:18<12:40:47, 1.43s/it] 49%|████▊ | 30078/61904 [4:47:19<12:24:54, 1.40s/it] 49%|████▊ | 30079/61904 [4:47:20<12:10:20, 1.38s/it] 49%|████▊ | 30080/61904 [4:47:22<12:46:13, 1.44s/it] {'loss': 2.5652, 'learning_rate': 1.515752625437573e-07, 'epoch': 7.77} + 49%|████▊ | 30080/61904 [4:47:22<12:46:13, 1.44s/it] 49%|████▊ | 30081/61904 [4:47:23<12:50:19, 1.45s/it] 49%|████▊ | 30082/61904 [4:47:25<13:07:33, 1.48s/it] 49%|████▊ | 30083/61904 [4:47:26<12:59:59, 1.47s/it] 49%|████▊ | 30084/61904 [4:47:28<12:34:48, 1.42s/it] 49%|████▊ | 30085/61904 [4:47:29<12:18:56, 1.39s/it] 49%|████▊ | 30086/61904 [4:47:30<12:07:25, 1.37s/it] 49%|████▊ | 30087/61904 [4:47:32<12:56:06, 1.46s/it] 49%|████▊ | 30088/61904 [4:47:33<12:43:35, 1.44s/it] 49%|████▊ | 30089/61904 [4:47:35<12:56:27, 1.46s/it] 49%|████▊ | 30090/61904 [4:47:36<12:58:33, 1.47s/it] 49%|████▊ | 30091/61904 [4:47:38<12:44:13, 1.44s/it] 49%|████▊ | 30092/61904 [4:47:39<12:30:24, 1.42s/it] 49%|████▊ | 30093/61904 [4:47:41<12:43:24, 1.44s/it] 49%|████▊ | 30094/61904 [4:47:42<12:35:21, 1.42s/it] 49%|████▊ | 30095/61904 [4:47:44<12:39:30, 1.43s/it] 49%|████▊ | 30096/61904 [4:47:45<12:46:28, 1.45s/it] 49%|████▊ | 30097/61904 [4:47:46<12:42:59, 1.44s/it] 49%|████▊ | 30098/61904 [4:47:48<12:42:36, 1.44s/it] 49%|████▊ | 30099/61904 [4:47:49<12:22:47, 1.40s/it] 49%|████▊ | 30100/61904 [4:47:51<12:09:59, 1.38s/it] {'loss': 2.5216, 'learning_rate': 1.5154284973421497e-07, 'epoch': 7.78} + 49%|████▊ | 30100/61904 [4:47:51<12:09:59, 1.38s/it] 49%|████▊ | 30101/61904 [4:47:52<12:28:52, 1.41s/it] 49%|████▊ | 30102/61904 [4:47:53<12:37:44, 1.43s/it] 49%|████▊ | 30103/61904 [4:47:55<12:29:52, 1.41s/it] 49%|████▊ | 30104/61904 [4:47:56<12:30:05, 1.42s/it] 49%|████▊ | 30105/61904 [4:47:58<12:42:51, 1.44s/it] 49%|████▊ | 30106/61904 [4:47:59<12:22:45, 1.40s/it] 49%|████▊ | 30107/61904 [4:48:01<12:39:27, 1.43s/it] 49%|████▊ | 30108/61904 [4:48:02<12:44:57, 1.44s/it] 49%|████▊ | 30109/61904 [4:48:03<12:35:47, 1.43s/it] 49%|████▊ | 30110/61904 [4:48:05<12:10:04, 1.38s/it] 49%|████▊ | 30111/61904 [4:48:06<12:18:57, 1.39s/it] 49%|████▊ | 30112/61904 [4:48:08<12:19:01, 1.39s/it] 49%|████▊ | 30113/61904 [4:48:09<12:12:38, 1.38s/it] 49%|████▊ | 30114/61904 [4:48:10<12:13:44, 1.38s/it] 49%|████▊ | 30115/61904 [4:48:12<12:27:51, 1.41s/it] 49%|████▊ | 30116/61904 [4:48:13<12:27:09, 1.41s/it] 49%|████▊ | 30117/61904 [4:48:15<12:16:52, 1.39s/it] 49%|████▊ | 30118/61904 [4:48:16<12:17:53, 1.39s/it] 49%|████▊ | 30119/61904 [4:48:17<12:41:19, 1.44s/it] 49%|████▊ | 30120/61904 [4:48:19<12:20:27, 1.40s/it] {'loss': 2.521, 'learning_rate': 1.5151043692467263e-07, 'epoch': 7.78} + 49%|████▊ | 30120/61904 [4:48:19<12:20:27, 1.40s/it] 49%|████▊ | 30121/61904 [4:48:20<12:42:42, 1.44s/it] 49%|████▊ | 30122/61904 [4:48:22<12:22:29, 1.40s/it] 49%|████▊ | 30123/61904 [4:48:23<12:21:11, 1.40s/it] 49%|████▊ | 30124/61904 [4:48:24<12:20:32, 1.40s/it] 49%|████▊ | 30125/61904 [4:48:26<12:05:17, 1.37s/it] 49%|████▊ | 30126/61904 [4:48:27<12:41:52, 1.44s/it] 49%|████▊ | 30127/61904 [4:48:29<12:43:19, 1.44s/it] 49%|████▊ | 30128/61904 [4:48:30<12:26:53, 1.41s/it] 49%|████▊ | 30129/61904 [4:48:32<12:29:41, 1.42s/it] 49%|████▊ | 30130/61904 [4:48:33<12:42:04, 1.44s/it] 49%|████▊ | 30131/61904 [4:48:34<12:21:09, 1.40s/it] 49%|████▊ | 30132/61904 [4:48:36<12:11:37, 1.38s/it] 49%|████▊ | 30133/61904 [4:48:37<11:56:08, 1.35s/it] 49%|████▊ | 30134/61904 [4:48:39<12:38:57, 1.43s/it] 49%|████▊ | 30135/61904 [4:48:40<12:35:32, 1.43s/it] 49%|████▊ | 30136/61904 [4:48:41<12:26:47, 1.41s/it] 49%|████▊ | 30137/61904 [4:48:43<12:08:53, 1.38s/it] 49%|████▊ | 30138/61904 [4:48:44<12:23:22, 1.40s/it] 49%|████▊ | 30139/61904 [4:48:45<12:21:50, 1.40s/it] 49%|████▊ | 30140/61904 [4:48:47<12:07:16, 1.37s/it] {'loss': 2.5561, 'learning_rate': 1.514780241151303e-07, 'epoch': 7.79} + 49%|████▊ | 30140/61904 [4:48:47<12:07:16, 1.37s/it] 49%|████▊ | 30141/61904 [4:48:48<11:55:55, 1.35s/it] 49%|████▊ | 30142/61904 [4:48:49<11:58:35, 1.36s/it] 49%|████▊ | 30143/61904 [4:48:51<12:30:57, 1.42s/it] 49%|████▊ | 30144/61904 [4:48:52<12:13:52, 1.39s/it] 49%|████▊ | 30145/61904 [4:48:54<12:21:57, 1.40s/it] 49%|████▊ | 30146/61904 [4:48:55<12:13:53, 1.39s/it] 49%|████▊ | 30147/61904 [4:48:56<12:05:59, 1.37s/it] 49%|████▊ | 30148/61904 [4:48:58<11:58:12, 1.36s/it] 49%|████▊ | 30149/61904 [4:48:59<12:09:54, 1.38s/it] 49%|████▊ | 30150/61904 [4:49:01<12:25:32, 1.41s/it] 49%|████▊ | 30151/61904 [4:49:02<12:31:18, 1.42s/it] 49%|████▊ | 30152/61904 [4:49:03<12:13:36, 1.39s/it] 49%|████▊ | 30153/61904 [4:49:05<12:34:21, 1.43s/it] 49%|████▊ | 30154/61904 [4:49:07<13:35:07, 1.54s/it] 49%|████▊ | 30155/61904 [4:49:08<12:58:26, 1.47s/it] 49%|████▊ | 30156/61904 [4:49:09<12:45:58, 1.45s/it] 49%|████▊ | 30157/61904 [4:49:11<12:37:00, 1.43s/it] 49%|████▊ | 30158/61904 [4:49:12<12:26:44, 1.41s/it] 49%|████▊ | 30159/61904 [4:49:14<12:35:20, 1.43s/it] 49%|████▊ | 30160/61904 [4:49:15<12:26:40, 1.41s/it] {'loss': 2.5601, 'learning_rate': 1.5144561130558795e-07, 'epoch': 7.79} + 49%|████▊ | 30160/61904 [4:49:15<12:26:40, 1.41s/it] 49%|████▊ | 30161/61904 [4:49:16<12:25:53, 1.41s/it] 49%|████▊ | 30162/61904 [4:49:18<12:17:02, 1.39s/it] 49%|████▊ | 30163/61904 [4:49:19<12:07:30, 1.38s/it] 49%|████▊ | 30164/61904 [4:49:20<11:54:27, 1.35s/it] 49%|████▊ | 30165/61904 [4:49:22<11:49:30, 1.34s/it] 49%|████▊ | 30166/61904 [4:49:23<12:34:49, 1.43s/it] 49%|████▊ | 30167/61904 [4:49:25<12:38:47, 1.43s/it] 49%|████▊ | 30168/61904 [4:49:26<12:42:00, 1.44s/it] 49%|████▊ | 30169/61904 [4:49:28<12:29:23, 1.42s/it] 49%|████▊ | 30170/61904 [4:49:29<12:45:02, 1.45s/it] 49%|████▊ | 30171/61904 [4:49:31<12:47:26, 1.45s/it] 49%|████▊ | 30172/61904 [4:49:32<12:56:26, 1.47s/it] 49%|████▊ | 30173/61904 [4:49:33<12:30:49, 1.42s/it] 49%|████▊ | 30174/61904 [4:49:35<12:25:38, 1.41s/it] 49%|████▊ | 30175/61904 [4:49:36<12:08:30, 1.38s/it] 49%|████▊ | 30176/61904 [4:49:38<12:24:54, 1.41s/it] 49%|████▊ | 30177/61904 [4:49:39<12:11:08, 1.38s/it] 49%|████▊ | 30178/61904 [4:49:40<12:22:57, 1.41s/it] 49%|████▉ | 30179/61904 [4:49:42<12:06:16, 1.37s/it] 49%|████▉ | 30180/61904 [4:49:43<12:18:18, 1.40s/it] {'loss': 2.5599, 'learning_rate': 1.5141319849604564e-07, 'epoch': 7.8} + 49%|████▉ | 30180/61904 [4:49:43<12:18:18, 1.40s/it] 49%|███��▉ | 30181/61904 [4:49:45<12:09:48, 1.38s/it] 49%|████▉ | 30182/61904 [4:49:46<11:58:31, 1.36s/it] 49%|████▉ | 30183/61904 [4:49:47<11:51:04, 1.34s/it] 49%|████▉ | 30184/61904 [4:49:49<11:53:19, 1.35s/it] 49%|████▉ | 30185/61904 [4:49:50<11:58:05, 1.36s/it] 49%|████▉ | 30186/61904 [4:49:51<11:55:46, 1.35s/it] 49%|████▉ | 30187/61904 [4:49:53<11:58:14, 1.36s/it] 49%|████▉ | 30188/61904 [4:49:54<12:20:04, 1.40s/it] 49%|████▉ | 30189/61904 [4:49:55<12:09:48, 1.38s/it] 49%|████▉ | 30190/61904 [4:49:57<12:14:21, 1.39s/it] 49%|████▉ | 30191/61904 [4:49:58<12:07:11, 1.38s/it] 49%|████▉ | 30192/61904 [4:50:00<12:04:59, 1.37s/it] 49%|████▉ | 30193/61904 [4:50:01<12:22:48, 1.41s/it] 49%|████▉ | 30194/61904 [4:50:02<12:26:57, 1.41s/it] 49%|████▉ | 30195/61904 [4:50:04<12:30:54, 1.42s/it] 49%|████▉ | 30196/61904 [4:50:05<12:04:59, 1.37s/it] 49%|████▉ | 30197/61904 [4:50:07<12:17:08, 1.39s/it] 49%|████▉ | 30198/61904 [4:50:08<12:11:30, 1.38s/it] 49%|████▉ | 30199/61904 [4:50:09<12:04:54, 1.37s/it] 49%|████▉ | 30200/61904 [4:50:11<12:08:17, 1.38s/it] {'loss': 2.6198, 'learning_rate': 1.513807856865033e-07, 'epoch': 7.81} + 49%|████▉ | 30200/61904 [4:50:11<12:08:17, 1.38s/it] 49%|████▉ | 30201/61904 [4:50:12<12:15:18, 1.39s/it] 49%|████▉ | 30202/61904 [4:50:13<12:11:12, 1.38s/it] 49%|████▉ | 30203/61904 [4:50:15<11:39:09, 1.32s/it] 49%|████▉ | 30204/61904 [4:50:16<11:27:28, 1.30s/it] 49%|████▉ | 30205/61904 [4:50:17<11:17:37, 1.28s/it] 49%|████▉ | 30206/61904 [4:50:18<11:14:44, 1.28s/it] 49%|████▉ | 30207/61904 [4:50:20<11:26:54, 1.30s/it] 49%|████▉ | 30208/61904 [4:50:21<11:48:21, 1.34s/it] 49%|████▉ | 30209/61904 [4:50:23<11:56:06, 1.36s/it] 49%|████▉ | 30210/61904 [4:50:24<12:10:59, 1.38s/it] 49%|████▉ | 30211/61904 [4:50:25<12:13:18, 1.39s/it] 49%|████▉ | 30212/61904 [4:50:27<12:17:28, 1.40s/it] 49%|████▉ | 30213/61904 [4:50:28<12:22:50, 1.41s/it] 49%|████▉ | 30214/61904 [4:50:30<12:21:14, 1.40s/it] 49%|████▉ | 30215/61904 [4:50:31<12:36:36, 1.43s/it] 49%|████▉ | 30216/61904 [4:50:32<12:03:52, 1.37s/it] 49%|████▉ | 30217/61904 [4:50:34<11:59:51, 1.36s/it] 49%|████▉ | 30218/61904 [4:50:35<11:59:00, 1.36s/it] 49%|████▉ | 30219/61904 [4:50:36<11:55:06, 1.35s/it] 49%|████▉ | 30220/61904 [4:50:38<11:44:16, 1.33s/it] {'loss': 2.6023, 'learning_rate': 1.5134837287696096e-07, 'epoch': 7.81} + 49%|████▉ | 30220/61904 [4:50:38<11:44:16, 1.33s/it] 49%|████▉ | 30221/61904 [4:50:39<11:58:08, 1.36s/it] 49%|████▉ | 30222/61904 [4:50:41<11:56:22, 1.36s/it] 49%|████▉ | 30223/61904 [4:50:42<12:02:15, 1.37s/it] 49%|████▉ | 30224/61904 [4:50:43<12:07:20, 1.38s/it] 49%|████▉ | 30225/61904 [4:50:45<12:00:25, 1.36s/it] 49%|████▉ | 30226/61904 [4:50:46<12:22:59, 1.41s/it] 49%|████▉ | 30227/61904 [4:50:48<12:16:11, 1.39s/it] 49%|████▉ | 30228/61904 [4:50:49<12:13:21, 1.39s/it] 49%|████▉ | 30229/61904 [4:50:50<12:00:00, 1.36s/it] 49%|████▉ | 30230/61904 [4:50:52<12:19:54, 1.40s/it] 49%|████▉ | 30231/61904 [4:50:53<12:23:08, 1.41s/it] 49%|████▉ | 30232/61904 [4:50:54<12:12:39, 1.39s/it] 49%|████▉ | 30233/61904 [4:50:56<12:19:31, 1.40s/it] 49%|████▉ | 30234/61904 [4:50:57<12:28:54, 1.42s/it] 49%|████▉ | 30235/61904 [4:50:59<12:55:17, 1.47s/it] 49%|████▉ | 30236/61904 [4:51:00<12:36:14, 1.43s/it] 49%|████▉ | 30237/61904 [4:51:01<12:01:58, 1.37s/it] 49%|████▉ | 30238/61904 [4:51:03<12:05:13, 1.37s/it] 49%|████▉ | 30239/61904 [4:51:04<11:56:37, 1.36s/it] 49%|████▉ | 30240/61904 [4:51:06<11:52:59, 1.35s/it] {'loss': 2.5248, 'learning_rate': 1.5131596006741865e-07, 'epoch': 7.82} + 49%|████▉ | 30240/61904 [4:51:06<11:52:59, 1.35s/it] 49%|████▉ | 30241/61904 [4:51:07<11:44:24, 1.33s/it] 49%|████▉ | 30242/61904 [4:51:08<12:02:08, 1.37s/it] 49%|████▉ | 30243/61904 [4:51:10<12:01:25, 1.37s/it] 49%|████▉ | 30244/61904 [4:51:11<12:12:23, 1.39s/it] 49%|████▉ | 30245/61904 [4:51:13<12:29:04, 1.42s/it] 49%|████▉ | 30246/61904 [4:51:14<12:05:06, 1.37s/it] 49%|████▉ | 30247/61904 [4:51:15<12:05:17, 1.37s/it] 49%|████▉ | 30248/61904 [4:51:16<11:40:59, 1.33s/it] 49%|████▉ | 30249/61904 [4:51:18<11:51:44, 1.35s/it] 49%|████▉ | 30250/61904 [4:51:19<12:10:58, 1.39s/it] 49%|████▉ | 30251/61904 [4:51:21<12:40:16, 1.44s/it] 49%|████▉ | 30252/61904 [4:51:22<12:25:58, 1.41s/it] 49%|████▉ | 30253/61904 [4:51:24<12:30:37, 1.42s/it] 49%|████▉ | 30254/61904 [4:51:25<12:11:11, 1.39s/it] 49%|████▉ | 30255/61904 [4:51:26<12:14:51, 1.39s/it] 49%|████▉ | 30256/61904 [4:51:28<12:25:08, 1.41s/it] 49%|████▉ | 30257/61904 [4:51:29<12:13:18, 1.39s/it] 49%|████▉ | 30258/61904 [4:51:31<12:03:51, 1.37s/it] 49%|████▉ | 30259/61904 [4:51:32<11:52:27, 1.35s/it] 49%|████▉ | 30260/61904 [4:51:33<11:57:26, 1.36s/it] {'loss': 2.5971, 'learning_rate': 1.5128354725787631e-07, 'epoch': 7.82} + 49%|████▉ | 30260/61904 [4:51:33<11:57:26, 1.36s/it] 49%|████▉ | 30261/61904 [4:51:34<11:44:13, 1.34s/it] 49%|████▉ | 30262/61904 [4:51:36<11:46:16, 1.34s/it] 49%|████▉ | 30263/61904 [4:51:37<11:42:55, 1.33s/it] 49%|████▉ | 30264/61904 [4:51:39<12:02:17, 1.37s/it] 49%|████▉ | 30265/61904 [4:51:40<11:59:42, 1.36s/it] 49%|████▉ | 30266/61904 [4:51:41<11:56:52, 1.36s/it] 49%|████▉ | 30267/61904 [4:51:43<12:16:51, 1.40s/it] 49%|████▉ | 30268/61904 [4:51:44<11:55:38, 1.36s/it] 49%|████▉ | 30269/61904 [4:51:45<11:56:14, 1.36s/it] 49%|████▉ | 30270/61904 [4:51:47<12:21:48, 1.41s/it] 49%|████▉ | 30271/61904 [4:51:48<12:15:42, 1.40s/it] 49%|████▉ | 30272/61904 [4:51:50<12:25:54, 1.41s/it] 49%|████▉ | 30273/61904 [4:51:51<12:13:47, 1.39s/it] 49%|████▉ | 30274/61904 [4:51:52<12:02:57, 1.37s/it] 49%|████▉ | 30275/61904 [4:51:54<12:21:57, 1.41s/it] 49%|████▉ | 30276/61904 [4:51:55<11:59:00, 1.36s/it] 49%|████▉ | 30277/61904 [4:51:57<12:09:25, 1.38s/it] 49%|████▉ | 30278/61904 [4:51:58<12:14:24, 1.39s/it] 49%|████▉ | 30279/61904 [4:52:00<12:34:49, 1.43s/it] 49%|████▉ | 30280/61904 [4:52:01<12:17:33, 1.40s/it] {'loss': 2.5428, 'learning_rate': 1.5125113444833398e-07, 'epoch': 7.83} + 49%|████▉ | 30280/61904 [4:52:01<12:17:33, 1.40s/it] 49%|████▉ | 30281/61904 [4:52:02<12:14:58, 1.39s/it] 49%|████▉ | 30282/61904 [4:52:04<12:05:59, 1.38s/it] 49%|████▉ | 30283/61904 [4:52:05<12:13:37, 1.39s/it] 49%|████▉ | 30284/61904 [4:52:06<12:13:53, 1.39s/it] 49%|████▉ | 30285/61904 [4:52:08<12:00:32, 1.37s/it] 49%|████▉ | 30286/61904 [4:52:09<12:07:07, 1.38s/it] 49%|████▉ | 30287/61904 [4:52:11<12:11:19, 1.39s/it] 49%|████▉ | 30288/61904 [4:52:12<12:20:04, 1.40s/it] 49%|████▉ | 30289/61904 [4:52:13<12:02:23, 1.37s/it] 49%|████▉ | 30290/61904 [4:52:15<11:52:45, 1.35s/it] 49%|████▉ | 30291/61904 [4:52:16<11:53:01, 1.35s/it] 49%|████▉ | 30292/61904 [4:52:17<11:50:01, 1.35s/it] 49%|████▉ | 30293/61904 [4:52:19<11:40:01, 1.33s/it] 49%|████▉ | 30294/61904 [4:52:20<11:48:21, 1.34s/it] 49%|████▉ | 30295/61904 [4:52:21<11:37:41, 1.32s/it] 49%|████▉ | 30296/61904 [4:52:22<11:26:18, 1.30s/it] 49%|████▉ | 30297/61904 [4:52:24<11:41:15, 1.33s/it] 49%|████▉ | 30298/61904 [4:52:25<12:01:44, 1.37s/it] 49%|████▉ | 30299/61904 [4:52:27<11:59:21, 1.37s/it] 49%|████▉ | 30300/61904 [4:52:28<12:05:46, 1.38s/it] {'loss': 2.5757, 'learning_rate': 1.5121872163879164e-07, 'epoch': 7.83} + 49%|████▉ | 30300/61904 [4:52:28<12:05:46, 1.38s/it] 49%|████▉ | 30301/61904 [4:52:29<11:52:58, 1.35s/it] 49%|████▉ | 30302/61904 [4:52:31<12:09:44, 1.39s/it] 49%|████▉ | 30303/61904 [4:52:32<12:18:16, 1.40s/it] 49%|████▉ | 30304/61904 [4:52:34<12:51:08, 1.46s/it] 49%|████▉ | 30305/61904 [4:52:35<12:39:24, 1.44s/it] 49%|████▉ | 30306/61904 [4:52:37<12:22:28, 1.41s/it] 49%|████▉ | 30307/61904 [4:52:38<11:59:48, 1.37s/it] 49%|████▉ | 30308/61904 [4:52:39<12:11:15, 1.39s/it] 49%|████▉ | 30309/61904 [4:52:41<12:02:20, 1.37s/it] 49%|████▉ | 30310/61904 [4:52:42<11:55:54, 1.36s/it] 49%|████▉ | 30311/61904 [4:52:43<12:08:01, 1.38s/it] 49%|████▉ | 30312/61904 [4:52:45<12:20:11, 1.41s/it] 49%|████▉ | 30313/61904 [4:52:46<12:08:21, 1.38s/it] 49%|████▉ | 30314/61904 [4:52:48<11:59:19, 1.37s/it] 49%|████▉ | 30315/61904 [4:52:49<11:37:52, 1.33s/it] 49%|████▉ | 30316/61904 [4:52:50<11:49:01, 1.35s/it] 49%|████▉ | 30317/61904 [4:52:51<11:36:24, 1.32s/it] 49%|████▉ | 30318/61904 [4:52:53<11:36:54, 1.32s/it] 49%|████▉ | 30319/61904 [4:52:54<12:00:10, 1.37s/it] 49%|████▉ | 30320/61904 [4:52:55<11:43:02, 1.34s/it] {'loss': 2.561, 'learning_rate': 1.5118630882924933e-07, 'epoch': 7.84} + 49%|████▉ | 30320/61904 [4:52:55<11:43:02, 1.34s/it] 49%|████▉ | 30321/61904 [4:52:57<11:50:56, 1.35s/it] 49%|████▉ | 30322/61904 [4:52:58<11:53:40, 1.36s/it] 49%|████▉ | 30323/61904 [4:53:00<11:56:07, 1.36s/it] 49%|████▉ | 30324/61904 [4:53:01<11:58:55, 1.37s/it] 49%|████▉ | 30325/61904 [4:53:02<12:07:18, 1.38s/it] 49%|████▉ | 30326/61904 [4:53:04<11:59:00, 1.37s/it] 49%|████▉ | 30327/61904 [4:53:05<12:12:44, 1.39s/it] 49%|████▉ | 30328/61904 [4:53:07<12:20:43, 1.41s/it] 49%|████▉ | 30329/61904 [4:53:08<12:09:43, 1.39s/it] 49%|████▉ | 30330/61904 [4:53:09<12:04:51, 1.38s/it] 49%|████▉ | 30331/61904 [4:53:11<11:51:51, 1.35s/it] 49%|████▉ | 30332/61904 [4:53:12<12:26:41, 1.42s/it] 49%|████▉ | 30333/61904 [4:53:14<12:21:49, 1.41s/it] 49%|████▉ | 30334/61904 [4:53:15<12:26:10, 1.42s/it] 49%|████▉ | 30335/61904 [4:53:16<12:14:01, 1.40s/it] 49%|████▉ | 30336/61904 [4:53:18<12:02:15, 1.37s/it] 49%|████▉ | 30337/61904 [4:53:19<12:05:54, 1.38s/it] 49%|████▉ | 30338/61904 [4:53:20<12:10:12, 1.39s/it] 49%|████▉ | 30339/61904 [4:53:22<11:57:08, 1.36s/it] 49%|████▉ | 30340/61904 [4:53:23<12:15:21, 1.40s/it] {'loss': 2.5586, 'learning_rate': 1.51153896019707e-07, 'epoch': 7.84} + 49%|████▉ | 30340/61904 [4:53:23<12:15:21, 1.40s/it] 49%|████▉ | 30341/61904 [4:53:25<12:07:48, 1.38s/it] 49%|████▉ | 30342/61904 [4:53:26<12:04:02, 1.38s/it] 49%|████▉ | 30343/61904 [4:53:27<11:56:51, 1.36s/it] 49%|████▉ | 30344/61904 [4:53:29<11:48:05, 1.35s/it] 49%|████▉ | 30345/61904 [4:53:30<12:04:10, 1.38s/it] 49%|████▉ | 30346/61904 [4:53:31<12:09:49, 1.39s/it] 49%|████▉ | 30347/61904 [4:53:33<12:21:49, 1.41s/it] 49%|████▉ | 30348/61904 [4:53:34<12:35:05, 1.44s/it] 49%|████▉ | 30349/61904 [4:53:36<12:21:41, 1.41s/it] 49%|████▉ | 30350/61904 [4:53:37<12:42:11, 1.45s/it] 49%|████▉ | 30351/61904 [4:53:39<12:54:45, 1.47s/it] 49%|████▉ | 30352/61904 [4:53:40<13:07:02, 1.50s/it] 49%|████▉ | 30353/61904 [4:53:42<13:16:35, 1.51s/it] 49%|████▉ | 30354/61904 [4:53:43<12:53:21, 1.47s/it] 49%|████▉ | 30355/61904 [4:53:45<12:24:11, 1.42s/it] 49%|████▉ | 30356/61904 [4:53:46<12:26:23, 1.42s/it] 49%|████▉ | 30357/61904 [4:53:47<12:00:02, 1.37s/it] 49%|████▉ | 30358/61904 [4:53:49<11:50:20, 1.35s/it] 49%|████▉ | 30359/61904 [4:53:50<11:53:52, 1.36s/it] 49%|████▉ | 30360/61904 [4:53:51<12:09:57, 1.39s/it] {'loss': 2.612, 'learning_rate': 1.5112148321016465e-07, 'epoch': 7.85} + 49%|████▉ | 30360/61904 [4:53:51<12:09:57, 1.39s/it] 49%|████▉ | 30361/61904 [4:53:53<12:08:35, 1.39s/it] 49%|████▉ | 30362/61904 [4:53:54<12:06:38, 1.38s/it] 49%|████▉ | 30363/61904 [4:53:55<11:51:30, 1.35s/it] 49%|████▉ | 30364/61904 [4:53:57<11:58:45, 1.37s/it] 49%|████▉ | 30365/61904 [4:53:58<12:06:24, 1.38s/it] 49%|████▉ | 30366/61904 [4:54:00<12:45:25, 1.46s/it] 49%|████▉ | 30367/61904 [4:54:01<12:48:10, 1.46s/it] 49%|████▉ | 30368/61904 [4:54:03<12:16:26, 1.40s/it] 49%|████▉ | 30369/61904 [4:54:04<12:01:38, 1.37s/it] 49%|████▉ | 30370/61904 [4:54:05<11:44:33, 1.34s/it] 49%|████▉ | 30371/61904 [4:54:07<11:49:07, 1.35s/it] 49%|████▉ | 30372/61904 [4:54:08<11:56:16, 1.36s/it] 49%|████▉ | 30373/61904 [4:54:09<11:56:53, 1.36s/it] 49%|████▉ | 30374/61904 [4:54:11<11:48:12, 1.35s/it] 49%|████▉ | 30375/61904 [4:54:12<12:05:17, 1.38s/it] 49%|████▉ | 30376/61904 [4:54:14<12:08:02, 1.39s/it] 49%|████▉ | 30377/61904 [4:54:15<12:21:50, 1.41s/it] 49%|████▉ | 30378/61904 [4:54:16<12:08:09, 1.39s/it] 49%|████▉ | 30379/61904 [4:54:18<11:57:22, 1.37s/it] 49%|████▉ | 30380/61904 [4:54:19<12:12:16, 1.39s/it] {'loss': 2.5565, 'learning_rate': 1.510890704006223e-07, 'epoch': 7.85} + 49%|████▉ | 30380/61904 [4:54:19<12:12:16, 1.39s/it] 49%|████▉ | 30381/61904 [4:54:21<12:17:56, 1.40s/it] 49%|████▉ | 30382/61904 [4:54:22<12:11:43, 1.39s/it] 49%|████▉ | 30383/61904 [4:54:23<12:05:22, 1.38s/it] 49%|████▉ | 30384/61904 [4:54:25<12:04:53, 1.38s/it] 49%|████▉ | 30385/61904 [4:54:26<11:37:58, 1.33s/it] 49%|████▉ | 30386/61904 [4:54:27<12:00:41, 1.37s/it] 49%|████▉ | 30387/61904 [4:54:29<11:54:34, 1.36s/it] 49%|████▉ | 30388/61904 [4:54:30<11:39:57, 1.33s/it] 49%|████▉ | 30389/61904 [4:54:31<12:04:09, 1.38s/it] 49%|████▉ | 30390/61904 [4:54:33<11:45:56, 1.34s/it] 49%|████▉ | 30391/61904 [4:54:34<11:45:23, 1.34s/it] 49%|████▉ | 30392/61904 [4:54:36<12:15:37, 1.40s/it] 49%|████▉ | 30393/61904 [4:54:37<12:13:13, 1.40s/it] 49%|████▉ | 30394/61904 [4:54:38<12:15:52, 1.40s/it] 49%|████▉ | 30395/61904 [4:54:40<12:36:28, 1.44s/it] 49%|████▉ | 30396/61904 [4:54:41<12:35:14, 1.44s/it] 49%|████▉ | 30397/61904 [4:54:43<12:50:14, 1.47s/it] 49%|████▉ | 30398/61904 [4:54:44<12:30:48, 1.43s/it] 49%|████▉ | 30399/61904 [4:54:45<11:58:57, 1.37s/it] 49%|████▉ | 30400/61904 [4:54:47<12:00:54, 1.37s/it] {'loss': 2.5571, 'learning_rate': 1.5105665759108e-07, 'epoch': 7.86} + 49%|████▉ | 30400/61904 [4:54:47<12:00:54, 1.37s/it] 49%|████▉ | 30401/61904 [4:54:48<11:54:38, 1.36s/it] 49%|████▉ | 30402/61904 [4:54:50<12:01:49, 1.37s/it] 49%|████▉ | 30403/61904 [4:54:51<12:08:16, 1.39s/it] 49%|████▉ | 30404/61904 [4:54:52<12:16:07, 1.40s/it] 49%|████▉ | 30405/61904 [4:54:54<12:25:48, 1.42s/it] 49%|████▉ | 30406/61904 [4:54:55<12:30:55, 1.43s/it] 49%|████▉ | 30407/61904 [4:54:57<12:15:31, 1.40s/it] 49%|████▉ | 30408/61904 [4:54:58<12:07:06, 1.39s/it] 49%|████▉ | 30409/61904 [4:54:59<11:56:56, 1.37s/it] 49%|████▉ | 30410/61904 [4:55:01<11:46:51, 1.35s/it] 49%|████▉ | 30411/61904 [4:55:02<11:50:05, 1.35s/it] 49%|████▉ | 30412/61904 [4:55:03<11:54:01, 1.36s/it] 49%|████▉ | 30413/61904 [4:55:05<11:57:12, 1.37s/it] 49%|████▉ | 30414/61904 [4:55:06<12:16:28, 1.40s/it] 49%|████▉ | 30415/61904 [4:55:08<12:33:23, 1.44s/it] 49%|████▉ | 30416/61904 [4:55:09<11:53:58, 1.36s/it] 49%|████▉ | 30417/61904 [4:55:10<11:51:21, 1.36s/it] 49%|████▉ | 30418/61904 [4:55:12<11:58:53, 1.37s/it] 49%|████▉ | 30419/61904 [4:55:13<11:43:13, 1.34s/it] 49%|████▉ | 30420/61904 [4:55:14<11:37:55, 1.33s/it] {'loss': 2.5895, 'learning_rate': 1.5102424478153766e-07, 'epoch': 7.86} + 49%|████▉ | 30420/61904 [4:55:14<11:37:55, 1.33s/it] 49%|████▉ | 30421/61904 [4:55:16<11:49:05, 1.35s/it] 49%|████▉ | 30422/61904 [4:55:17<11:39:12, 1.33s/it] 49%|████▉ | 30423/61904 [4:55:18<12:04:40, 1.38s/it] 49%|████▉ | 30424/61904 [4:55:20<12:09:15, 1.39s/it] 49%|████▉ | 30425/61904 [4:55:21<12:28:12, 1.43s/it] 49%|████▉ | 30426/61904 [4:55:23<12:26:13, 1.42s/it] 49%|████▉ | 30427/61904 [4:55:24<12:25:34, 1.42s/it] 49%|████▉ | 30428/61904 [4:55:26<12:46:38, 1.46s/it] 49%|████▉ | 30429/61904 [4:55:27<12:42:04, 1.45s/it] 49%|████▉ | 30430/61904 [4:55:29<12:25:50, 1.42s/it] 49%|████▉ | 30431/61904 [4:55:30<12:02:01, 1.38s/it] 49%|████▉ | 30432/61904 [4:55:31<11:47:45, 1.35s/it] 49%|████▉ | 30433/61904 [4:55:32<11:45:10, 1.34s/it] 49%|████▉ | 30434/61904 [4:55:34<11:46:13, 1.35s/it] 49%|████▉ | 30435/61904 [4:55:35<12:00:01, 1.37s/it] 49%|████▉ | 30436/61904 [4:55:37<12:02:08, 1.38s/it] 49%|████▉ | 30437/61904 [4:55:38<11:53:17, 1.36s/it] 49%|████▉ | 30438/61904 [4:55:39<11:54:11, 1.36s/it] 49%|████▉ | 30439/61904 [4:55:41<11:51:05, 1.36s/it] 49%|████▉ | 30440/61904 [4:55:42<11:51:30, 1.36s/it] {'loss': 2.5987, 'learning_rate': 1.5099183197199532e-07, 'epoch': 7.87} + 49%|████▉ | 30440/61904 [4:55:42<11:51:30, 1.36s/it] 49%|████▉ | 30441/61904 [4:55:43<11:55:12, 1.36s/it] 49%|████▉ | 30442/61904 [4:55:45<11:58:39, 1.37s/it] 49%|████▉ | 30443/61904 [4:55:46<11:44:48, 1.34s/it] 49%|████▉ | 30444/61904 [4:55:48<12:19:35, 1.41s/it] 49%|████▉ | 30445/61904 [4:55:49<12:07:08, 1.39s/it] 49%|████▉ | 30446/61904 [4:55:50<12:18:13, 1.41s/it] 49%|████▉ | 30447/61904 [4:55:52<12:12:56, 1.40s/it] 49%|████▉ | 30448/61904 [4:55:53<11:47:13, 1.35s/it] 49%|████▉ | 30449/61904 [4:55:54<11:51:49, 1.36s/it] 49%|████▉ | 30450/61904 [4:55:56<11:32:35, 1.32s/it] 49%|████▉ | 30451/61904 [4:55:57<12:01:47, 1.38s/it] 49%|████▉ | 30452/61904 [4:55:58<11:41:38, 1.34s/it] 49%|████▉ | 30453/61904 [4:56:00<11:48:46, 1.35s/it] 49%|████▉ | 30454/61904 [4:56:01<12:05:08, 1.38s/it] 49%|████▉ | 30455/61904 [4:56:03<12:06:55, 1.39s/it] 49%|████▉ | 30456/61904 [4:56:04<12:03:11, 1.38s/it] 49%|████▉ | 30457/61904 [4:56:05<11:56:52, 1.37s/it] 49%|████▉ | 30458/61904 [4:56:07<12:10:09, 1.39s/it] 49%|████▉ | 30459/61904 [4:56:08<12:15:27, 1.40s/it] 49%|████▉ | 30460/61904 [4:56:09<11:59:45, 1.37s/it] {'loss': 2.5516, 'learning_rate': 1.5095941916245298e-07, 'epoch': 7.87} + 49%|████▉ | 30460/61904 [4:56:09<11:59:45, 1.37s/it] 49%|████▉ | 30461/61904 [4:56:11<11:48:22, 1.35s/it] 49%|████▉ | 30462/61904 [4:56:12<12:00:31, 1.37s/it] 49%|████▉ | 30463/61904 [4:56:14<12:00:38, 1.38s/it] 49%|████▉ | 30464/61904 [4:56:15<11:53:59, 1.36s/it] 49%|████▉ | 30465/61904 [4:56:16<11:44:59, 1.35s/it] 49%|████▉ | 30466/61904 [4:56:17<11:32:12, 1.32s/it] 49%|████▉ | 30467/61904 [4:56:19<11:51:11, 1.36s/it] 49%|████▉ | 30468/61904 [4:56:20<11:56:32, 1.37s/it] 49%|████▉ | 30469/61904 [4:56:22<12:15:51, 1.40s/it] 49%|████▉ | 30470/61904 [4:56:23<12:30:43, 1.43s/it] 49%|████▉ | 30471/61904 [4:56:25<12:11:44, 1.40s/it] 49%|████▉ | 30472/61904 [4:56:26<11:48:35, 1.35s/it] 49%|████▉ | 30473/61904 [4:56:27<11:38:23, 1.33s/it] 49%|████▉ | 30474/61904 [4:56:29<11:50:23, 1.36s/it] 49%|████▉ | 30475/61904 [4:56:30<11:56:00, 1.37s/it] 49%|████▉ | 30476/61904 [4:56:31<12:10:42, 1.40s/it] 49%|████▉ | 30477/61904 [4:56:33<12:26:33, 1.43s/it] 49%|████▉ | 30478/61904 [4:56:34<12:24:17, 1.42s/it] 49%|████▉ | 30479/61904 [4:56:36<12:04:20, 1.38s/it] 49%|████▉ | 30480/61904 [4:56:37<12:05:52, 1.39s/it] {'loss': 2.5649, 'learning_rate': 1.5092700635291067e-07, 'epoch': 7.88} + 49%|████▉ | 30480/61904 [4:56:37<12:05:52, 1.39s/it] 49%|████▉ | 30481/61904 [4:56:39<12:23:29, 1.42s/it] 49%|████▉ | 30482/61904 [4:56:40<12:37:07, 1.45s/it] 49%|████▉ | 30483/61904 [4:56:41<12:27:56, 1.43s/it] 49%|████▉ | 30484/61904 [4:56:43<12:44:11, 1.46s/it] 49%|████▉ | 30485/61904 [4:56:44<12:29:30, 1.43s/it] 49%|████▉ | 30486/61904 [4:56:46<12:37:13, 1.45s/it] 49%|████▉ | 30487/61904 [4:56:47<12:29:55, 1.43s/it] 49%|████▉ | 30488/61904 [4:56:49<12:38:17, 1.45s/it] 49%|████▉ | 30489/61904 [4:56:50<12:22:22, 1.42s/it] 49%|████▉ | 30490/61904 [4:56:51<12:19:58, 1.41s/it] 49%|████▉ | 30491/61904 [4:56:53<12:07:09, 1.39s/it] 49%|████▉ | 30492/61904 [4:56:54<12:15:00, 1.40s/it] 49%|████▉ | 30493/61904 [4:56:56<12:04:21, 1.38s/it] 49%|████▉ | 30494/61904 [4:56:57<11:56:47, 1.37s/it] 49%|████▉ | 30495/61904 [4:56:58<12:06:22, 1.39s/it] 49%|████▉ | 30496/61904 [4:57:00<11:52:22, 1.36s/it] 49%|████▉ | 30497/61904 [4:57:01<11:30:25, 1.32s/it] 49%|████▉ | 30498/61904 [4:57:02<11:21:37, 1.30s/it] 49%|████▉ | 30499/61904 [4:57:03<11:30:17, 1.32s/it] 49%|████▉ | 30500/61904 [4:57:05<11:53:06, 1.36s/it] {'loss': 2.5498, 'learning_rate': 1.5089459354336834e-07, 'epoch': 7.88} + 49%|████▉ | 30500/61904 [4:57:05<11:53:06, 1.36s/it] 49%|████▉ | 30501/61904 [4:57:06<11:52:03, 1.36s/it] 49%|████▉ | 30502/61904 [4:57:08<12:08:19, 1.39s/it] 49%|████▉ | 30503/61904 [4:57:09<12:02:54, 1.38s/it] 49%|████▉ | 30504/61904 [4:57:11<12:16:51, 1.41s/it] 49%|████▉ | 30505/61904 [4:57:12<12:30:14, 1.43s/it] 49%|████▉ | 30506/61904 [4:57:13<12:31:04, 1.44s/it] 49%|████▉ | 30507/61904 [4:57:15<11:55:53, 1.37s/it] 49%|████▉ | 30508/61904 [4:57:16<11:43:50, 1.35s/it] 49%|████▉ | 30509/61904 [4:57:17<11:53:36, 1.36s/it] 49%|████▉ | 30510/61904 [4:57:19<11:47:02, 1.35s/it] 49%|████▉ | 30511/61904 [4:57:20<12:06:49, 1.39s/it] 49%|████▉ | 30512/61904 [4:57:22<12:39:38, 1.45s/it] 49%|████▉ | 30513/61904 [4:57:23<12:20:29, 1.42s/it] 49%|████▉ | 30514/61904 [4:57:24<11:56:06, 1.37s/it] 49%|████▉ | 30515/61904 [4:57:26<12:02:36, 1.38s/it] 49%|████▉ | 30516/61904 [4:57:27<12:02:23, 1.38s/it] 49%|████▉ | 30517/61904 [4:57:29<11:58:17, 1.37s/it] 49%|████▉ | 30518/61904 [4:57:30<12:16:51, 1.41s/it] 49%|████▉ | 30519/61904 [4:57:31<12:17:52, 1.41s/it] 49%|████▉ | 30520/61904 [4:57:33<11:48:33, 1.35s/it] {'loss': 2.6242, 'learning_rate': 1.50862180733826e-07, 'epoch': 7.89} + 49%|████▉ | 30520/61904 [4:57:33<11:48:33, 1.35s/it] 49%|████▉ | 30521/61904 [4:57:34<11:48:18, 1.35s/it] 49%|████▉ | 30522/61904 [4:57:36<12:17:55, 1.41s/it] 49%|████▉ | 30523/61904 [4:57:37<12:27:19, 1.43s/it] 49%|████▉ | 30524/61904 [4:57:38<12:20:04, 1.42s/it] 49%|████▉ | 30525/61904 [4:57:40<12:06:58, 1.39s/it] 49%|████▉ | 30526/61904 [4:57:41<11:47:44, 1.35s/it] 49%|████▉ | 30527/61904 [4:57:42<11:25:26, 1.31s/it] 49%|████▉ | 30528/61904 [4:57:43<11:16:21, 1.29s/it] 49%|████▉ | 30529/61904 [4:57:45<11:40:12, 1.34s/it] 49%|████▉ | 30530/61904 [4:57:46<11:31:39, 1.32s/it] 49%|████▉ | 30531/61904 [4:57:48<12:01:38, 1.38s/it] 49%|████▉ | 30532/61904 [4:57:49<11:43:49, 1.35s/it] 49%|████▉ | 30533/61904 [4:57:50<11:32:45, 1.32s/it] 49%|████▉ | 30534/61904 [4:57:52<11:44:35, 1.35s/it] 49%|████▉ | 30535/61904 [4:57:53<12:03:37, 1.38s/it] 49%|████▉ | 30536/61904 [4:57:54<11:50:28, 1.36s/it] 49%|████▉ | 30537/61904 [4:57:56<12:26:35, 1.43s/it] 49%|████▉ | 30538/61904 [4:57:57<12:05:19, 1.39s/it] 49%|████▉ | 30539/61904 [4:57:59<12:07:19, 1.39s/it] 49%|████▉ | 30540/61904 [4:58:00<11:49:19, 1.36s/it] {'loss': 2.5774, 'learning_rate': 1.5082976792428366e-07, 'epoch': 7.89} + 49%|████▉ | 30540/61904 [4:58:00<11:49:19, 1.36s/it] 49%|████▉ | 30541/61904 [4:58:01<11:40:41, 1.34s/it] 49%|████▉ | 30542/61904 [4:58:03<12:20:32, 1.42s/it] 49%|████▉ | 30543/61904 [4:58:04<11:59:15, 1.38s/it] 49%|████▉ | 30544/61904 [4:58:06<12:02:35, 1.38s/it] 49%|████▉ | 30545/61904 [4:58:07<12:15:35, 1.41s/it] 49%|████▉ | 30546/61904 [4:58:08<12:07:15, 1.39s/it] 49%|████▉ | 30547/61904 [4:58:10<12:12:13, 1.40s/it] 49%|████▉ | 30548/61904 [4:58:11<12:08:26, 1.39s/it] 49%|████▉ | 30549/61904 [4:58:13<12:09:34, 1.40s/it] 49%|████▉ | 30550/61904 [4:58:14<12:07:08, 1.39s/it] 49%|████▉ | 30551/61904 [4:58:15<11:55:19, 1.37s/it] 49%|████▉ | 30552/61904 [4:58:17<12:13:28, 1.40s/it] 49%|████▉ | 30553/61904 [4:58:18<11:49:21, 1.36s/it] 49%|████▉ | 30554/61904 [4:58:19<12:00:31, 1.38s/it] 49%|████▉ | 30555/61904 [4:58:21<11:52:52, 1.36s/it] 49%|████▉ | 30556/61904 [4:58:22<12:10:49, 1.40s/it] 49%|████▉ | 30557/61904 [4:58:24<12:01:26, 1.38s/it] 49%|████▉ | 30558/61904 [4:58:25<12:27:25, 1.43s/it] 49%|████▉ | 30559/61904 [4:58:27<12:39:59, 1.45s/it] 49%|████▉ | 30560/61904 [4:58:28<12:37:38, 1.45s/it] {'loss': 2.5298, 'learning_rate': 1.5079735511474135e-07, 'epoch': 7.9} + 49%|████▉ | 30560/61904 [4:58:28<12:37:38, 1.45s/it] 49%|████▉ | 30561/61904 [4:58:30<12:40:29, 1.46s/it] 49%|████▉ | 30562/61904 [4:58:31<12:47:25, 1.47s/it] 49%|████▉ | 30563/61904 [4:58:32<12:38:34, 1.45s/it] 49%|████▉ | 30564/61904 [4:58:34<12:36:34, 1.45s/it] 49%|████▉ | 30565/61904 [4:58:35<12:32:13, 1.44s/it] 49%|████▉ | 30566/61904 [4:58:37<12:33:20, 1.44s/it] 49%|████▉ | 30567/61904 [4:58:38<13:05:29, 1.50s/it] 49%|████▉ | 30568/61904 [4:58:40<12:56:30, 1.49s/it] 49%|████▉ | 30569/61904 [4:58:41<13:05:41, 1.50s/it] 49%|████▉ | 30570/61904 [4:58:43<12:38:32, 1.45s/it] 49%|████▉ | 30571/61904 [4:58:44<12:50:02, 1.47s/it] 49%|████▉ | 30572/61904 [4:58:46<12:44:55, 1.46s/it] 49%|████▉ | 30573/61904 [4:58:47<12:04:15, 1.39s/it] 49%|████▉ | 30574/61904 [4:58:48<12:30:40, 1.44s/it] 49%|████▉ | 30575/61904 [4:58:50<12:11:02, 1.40s/it] 49%|████▉ | 30576/61904 [4:58:51<12:02:25, 1.38s/it] 49%|████▉ | 30577/61904 [4:58:53<12:23:41, 1.42s/it] 49%|████▉ | 30578/61904 [4:58:54<12:10:04, 1.40s/it] 49%|████▉ | 30579/61904 [4:58:55<12:11:57, 1.40s/it] 49%|████▉ | 30580/61904 [4:58:57<12:01:37, 1.38s/it] {'loss': 2.55, 'learning_rate': 1.50764942305199e-07, 'epoch': 7.9} + 49%|████▉ | 30580/61904 [4:58:57<12:01:37, 1.38s/it] 49%|████▉ | 30581/61904 [4:58:58<11:51:31, 1.36s/it] 49%|████▉ | 30582/61904 [4:59:00<12:08:43, 1.40s/it] 49%|████▉ | 30583/61904 [4:59:01<12:09:45, 1.40s/it] 49%|████▉ | 30584/61904 [4:59:02<11:52:08, 1.36s/it] 49%|████▉ | 30585/61904 [4:59:03<11:31:16, 1.32s/it] 49%|████▉ | 30586/61904 [4:59:05<11:27:30, 1.32s/it] 49%|████▉ | 30587/61904 [4:59:06<11:38:15, 1.34s/it] 49%|████▉ | 30588/61904 [4:59:08<11:49:55, 1.36s/it] 49%|████▉ | 30589/61904 [4:59:09<11:35:32, 1.33s/it] 49%|████▉ | 30590/61904 [4:59:10<11:39:14, 1.34s/it] 49%|████▉ | 30591/61904 [4:59:12<11:49:45, 1.36s/it] 49%|████▉ | 30592/61904 [4:59:13<11:28:50, 1.32s/it] 49%|████▉ | 30593/61904 [4:59:14<11:50:34, 1.36s/it] 49%|████▉ | 30594/61904 [4:59:16<11:41:51, 1.34s/it] 49%|████▉ | 30595/61904 [4:59:17<11:48:21, 1.36s/it] 49%|████▉ | 30596/61904 [4:59:18<11:58:38, 1.38s/it] 49%|████▉ | 30597/61904 [4:59:20<11:52:17, 1.37s/it] 49%|████▉ | 30598/61904 [4:59:21<11:54:15, 1.37s/it] 49%|████▉ | 30599/61904 [4:59:22<11:51:51, 1.36s/it] 49%|████▉ | 30600/61904 [4:59:24<11:50:42, 1.36s/it] {'loss': 2.5924, 'learning_rate': 1.5073252949565667e-07, 'epoch': 7.91} + 49%|████▉ | 30600/61904 [4:59:24<11:50:42, 1.36s/it] 49%|████▉ | 30601/61904 [4:59:25<12:03:11, 1.39s/it] 49%|████▉ | 30602/61904 [4:59:27<11:51:19, 1.36s/it] 49%|████▉ | 30603/61904 [4:59:28<11:58:24, 1.38s/it] 49%|████▉ | 30604/61904 [4:59:30<12:28:38, 1.44s/it] 49%|████▉ | 30605/61904 [4:59:31<12:21:14, 1.42s/it] 49%|████▉ | 30606/61904 [4:59:32<12:12:35, 1.40s/it] 49%|████▉ | 30607/61904 [4:59:34<12:10:29, 1.40s/it] 49%|████▉ | 30608/61904 [4:59:35<12:19:53, 1.42s/it] 49%|████▉ | 30609/61904 [4:59:36<12:00:25, 1.38s/it] 49%|████▉ | 30610/61904 [4:59:38<12:20:13, 1.42s/it] 49%|████▉ | 30611/61904 [4:59:39<11:56:10, 1.37s/it] 49%|████▉ | 30612/61904 [4:59:41<11:53:15, 1.37s/it] 49%|████▉ | 30613/61904 [4:59:42<12:57:54, 1.49s/it] 49%|████▉ | 30614/61904 [4:59:44<13:01:14, 1.50s/it] 49%|████▉ | 30615/61904 [4:59:45<12:25:39, 1.43s/it] 49%|████▉ | 30616/61904 [4:59:47<12:18:35, 1.42s/it] 49%|████▉ | 30617/61904 [4:59:48<11:58:38, 1.38s/it] 49%|████▉ | 30618/61904 [4:59:49<12:12:38, 1.41s/it] 49%|████▉ | 30619/61904 [4:59:51<12:01:40, 1.38s/it] 49%|████▉ | 30620/61904 [4:59:52<12:37:27, 1.45s/it] {'loss': 2.515, 'learning_rate': 1.5070011668611436e-07, 'epoch': 7.91} + 49%|████▉ | 30620/61904 [4:59:52<12:37:27, 1.45s/it] 49%|████▉ | 30621/61904 [4:59:54<12:35:01, 1.45s/it] 49%|████▉ | 30622/61904 [4:59:55<12:18:52, 1.42s/it] 49%|████▉ | 30623/61904 [4:59:56<12:14:17, 1.41s/it] 49%|████▉ | 30624/61904 [4:59:58<12:13:40, 1.41s/it] 49%|████▉ | 30625/61904 [4:59:59<11:57:04, 1.38s/it] 49%|████▉ | 30626/61904 [5:00:00<11:41:03, 1.34s/it] 49%|████▉ | 30627/61904 [5:00:02<11:53:41, 1.37s/it] 49%|████▉ | 30628/61904 [5:00:03<11:49:56, 1.36s/it] 49%|████▉ | 30629/61904 [5:00:05<12:04:48, 1.39s/it] 49%|████▉ | 30630/61904 [5:00:06<12:22:45, 1.42s/it] 49%|████▉ | 30631/61904 [5:00:08<12:26:34, 1.43s/it] 49%|████▉ | 30632/61904 [5:00:09<12:04:36, 1.39s/it] 49%|████▉ | 30633/61904 [5:00:10<12:09:38, 1.40s/it] 49%|████▉ | 30634/61904 [5:00:12<12:42:14, 1.46s/it] 49%|████▉ | 30635/61904 [5:00:13<12:36:52, 1.45s/it] 49%|██��█▉ | 30636/61904 [5:00:15<12:00:31, 1.38s/it] 49%|████▉ | 30637/61904 [5:00:16<12:25:49, 1.43s/it] 49%|████▉ | 30638/61904 [5:00:17<12:21:39, 1.42s/it] 49%|████▉ | 30639/61904 [5:00:19<12:16:13, 1.41s/it] 49%|████▉ | 30640/61904 [5:00:20<12:20:01, 1.42s/it] {'loss': 2.5605, 'learning_rate': 1.5066770387657202e-07, 'epoch': 7.92} + 49%|████▉ | 30640/61904 [5:00:20<12:20:01, 1.42s/it] 49%|████▉ | 30641/61904 [5:00:22<12:13:05, 1.41s/it] 49%|████▉ | 30642/61904 [5:00:23<12:20:23, 1.42s/it] 50%|████▉ | 30643/61904 [5:00:24<12:08:18, 1.40s/it] 50%|████▉ | 30644/61904 [5:00:26<11:47:30, 1.36s/it] 50%|████▉ | 30645/61904 [5:00:27<11:52:03, 1.37s/it] 50%|████▉ | 30646/61904 [5:00:29<12:19:30, 1.42s/it] 50%|████▉ | 30647/61904 [5:00:30<12:27:41, 1.44s/it] 50%|████▉ | 30648/61904 [5:00:32<12:18:40, 1.42s/it] 50%|████▉ | 30649/61904 [5:00:33<11:55:05, 1.37s/it] 50%|████▉ | 30650/61904 [5:00:34<12:20:26, 1.42s/it] 50%|████▉ | 30651/61904 [5:00:36<12:22:00, 1.42s/it] 50%|████▉ | 30652/61904 [5:00:37<12:26:59, 1.43s/it] 50%|████▉ | 30653/61904 [5:00:39<12:25:22, 1.43s/it] 50%|████▉ | 30654/61904 [5:00:40<12:30:22, 1.44s/it] 50%|████▉ | 30655/61904 [5:00:41<12:24:28, 1.43s/it] 50%|████▉ | 30656/61904 [5:00:43<12:13:56, 1.41s/it] 50%|████▉ | 30657/61904 [5:00:44<11:52:16, 1.37s/it] 50%|████▉ | 30658/61904 [5:00:46<12:10:49, 1.40s/it] 50%|████▉ | 30659/61904 [5:00:47<11:58:00, 1.38s/it] 50%|████▉ | 30660/61904 [5:00:48<11:49:49, 1.36s/it] {'loss': 2.6101, 'learning_rate': 1.5063529106702968e-07, 'epoch': 7.92} + 50%|████▉ | 30660/61904 [5:00:48<11:49:49, 1.36s/it] 50%|████▉ | 30661/61904 [5:00:50<11:44:56, 1.35s/it] 50%|████▉ | 30662/61904 [5:00:51<11:49:39, 1.36s/it] 50%|████▉ | 30663/61904 [5:00:53<12:19:41, 1.42s/it] 50%|████▉ | 30664/61904 [5:00:54<12:17:40, 1.42s/it] 50%|████▉ | 30665/61904 [5:00:55<12:15:17, 1.41s/it] 50%|████▉ | 30666/61904 [5:00:57<12:20:06, 1.42s/it] 50%|████▉ | 30667/61904 [5:00:58<12:05:16, 1.39s/it] 50%|████▉ | 30668/61904 [5:01:00<12:23:58, 1.43s/it] 50%|████▉ | 30669/61904 [5:01:01<12:27:08, 1.44s/it] 50%|████▉ | 30670/61904 [5:01:02<12:06:55, 1.40s/it] 50%|████▉ | 30671/61904 [5:01:04<12:34:10, 1.45s/it] 50%|████▉ | 30672/61904 [5:01:05<12:33:46, 1.45s/it] 50%|████▉ | 30673/61904 [5:01:07<12:11:27, 1.41s/it] 50%|████▉ | 30674/61904 [5:01:08<12:21:56, 1.43s/it] 50%|████▉ | 30675/61904 [5:01:10<12:17:26, 1.42s/it] 50%|████▉ | 30676/61904 [5:01:11<12:07:32, 1.40s/it] 50%|████▉ | 30677/61904 [5:01:12<12:01:18, 1.39s/it] 50%|████▉ | 30678/61904 [5:01:14<12:08:08, 1.40s/it] 50%|████▉ | 30679/61904 [5:01:15<12:04:30, 1.39s/it] 50%|████▉ | 30680/61904 [5:01:17<12:20:11, 1.42s/it] {'loss': 2.5612, 'learning_rate': 1.5060287825748734e-07, 'epoch': 7.93} + 50%|████▉ | 30680/61904 [5:01:17<12:20:11, 1.42s/it] 50%|████▉ | 30681/61904 [5:01:18<12:33:51, 1.45s/it] 50%|████▉ | 30682/61904 [5:01:20<12:29:43, 1.44s/it] 50%|████▉ | 30683/61904 [5:01:21<12:10:48, 1.40s/it] 50%|████▉ | 30684/61904 [5:01:22<11:54:13, 1.37s/it] 50%|████▉ | 30685/61904 [5:01:24<11:57:28, 1.38s/it] 50%|████▉ | 30686/61904 [5:01:25<12:21:23, 1.42s/it] 50%|████▉ | 30687/61904 [5:01:26<11:59:08, 1.38s/it] 50%|████▉ | 30688/61904 [5:01:28<11:41:20, 1.35s/it] 50%|████▉ | 30689/61904 [5:01:29<12:04:38, 1.39s/it] 50%|████▉ | 30690/61904 [5:01:30<12:00:43, 1.39s/it] 50%|████▉ | 30691/61904 [5:01:32<12:01:39, 1.39s/it] 50%|████▉ | 30692/61904 [5:01:33<11:46:01, 1.36s/it] 50%|████▉ | 30693/61904 [5:01:35<11:44:22, 1.35s/it] 50%|████▉ | 30694/61904 [5:01:36<11:55:23, 1.38s/it] 50%|████▉ | 30695/61904 [5:01:37<12:02:33, 1.39s/it] 50%|████▉ | 30696/61904 [5:01:39<11:33:56, 1.33s/it] 50%|████▉ | 30697/61904 [5:01:40<11:25:44, 1.32s/it] 50%|████▉ | 30698/61904 [5:01:41<11:36:26, 1.34s/it] 50%|████▉ | 30699/61904 [5:01:43<11:48:44, 1.36s/it] 50%|████▉ | 30700/61904 [5:01:44<11:48:19, 1.36s/it] {'loss': 2.6157, 'learning_rate': 1.5057046544794503e-07, 'epoch': 7.93} + 50%|████▉ | 30700/61904 [5:01:44<11:48:19, 1.36s/it] 50%|████▉ | 30701/61904 [5:01:45<11:44:45, 1.36s/it] 50%|████▉ | 30702/61904 [5:01:47<11:58:18, 1.38s/it] 50%|████▉ | 30703/61904 [5:01:48<12:03:50, 1.39s/it] 50%|████▉ | 30704/61904 [5:01:50<11:50:07, 1.37s/it] 50%|████▉ | 30705/61904 [5:01:51<11:37:54, 1.34s/it] 50%|████▉ | 30706/61904 [5:01:52<11:44:21, 1.35s/it] 50%|████▉ | 30707/61904 [5:01:54<11:43:41, 1.35s/it] 50%|████▉ | 30708/61904 [5:01:55<11:57:51, 1.38s/it] 50%|████▉ | 30709/61904 [5:01:56<11:56:22, 1.38s/it] 50%|████▉ | 30710/61904 [5:01:58<11:45:19, 1.36s/it] 50%|████▉ | 30711/61904 [5:01:59<11:43:46, 1.35s/it] 50%|████▉ | 30712/61904 [5:02:00<11:52:08, 1.37s/it] 50%|████▉ | 30713/61904 [5:02:02<12:22:54, 1.43s/it] 50%|████▉ | 30714/61904 [5:02:03<12:11:39, 1.41s/it] 50%|████▉ | 30715/61904 [5:02:05<12:24:50, 1.43s/it] 50%|████▉ | 30716/61904 [5:02:06<12:18:54, 1.42s/it] 50%|████▉ | 30717/61904 [5:02:08<12:10:53, 1.41s/it] 50%|████▉ | 30718/61904 [5:02:09<12:15:13, 1.41s/it] 50%|████▉ | 30719/61904 [5:02:11<12:51:09, 1.48s/it] 50%|████▉ | 30720/61904 [5:02:12<13:06:31, 1.51s/it] {'loss': 2.5566, 'learning_rate': 1.505380526384027e-07, 'epoch': 7.94} + 50%|████▉ | 30720/61904 [5:02:12<13:06:31, 1.51s/it] 50%|████▉ | 30721/61904 [5:02:14<12:52:22, 1.49s/it] 50%|████▉ | 30722/61904 [5:02:15<12:49:10, 1.48s/it] 50%|████▉ | 30723/61904 [5:02:17<12:41:10, 1.46s/it] 50%|████▉ | 30724/61904 [5:02:18<12:34:36, 1.45s/it] 50%|████▉ | 30725/61904 [5:02:19<12:31:38, 1.45s/it] 50%|████▉ | 30726/61904 [5:02:21<12:21:56, 1.43s/it] 50%|████▉ | 30727/61904 [5:02:22<12:06:48, 1.40s/it] 50%|████▉ | 30728/61904 [5:02:24<12:05:33, 1.40s/it] 50%|████▉ | 30729/61904 [5:02:25<11:57:08, 1.38s/it] 50%|████▉ | 30730/61904 [5:02:26<11:45:41, 1.36s/it] 50%|████▉ | 30731/61904 [5:02:28<11:54:37, 1.38s/it] 50%|████▉ | 30732/61904 [5:02:29<11:37:35, 1.34s/it] 50%|████▉ | 30733/61904 [5:02:30<11:50:46, 1.37s/it] 50%|████▉ | 30734/61904 [5:02:32<11:51:53, 1.37s/it] 50%|████▉ | 30735/61904 [5:02:33<12:01:34, 1.39s/it] 50%|████▉ | 30736/61904 [5:02:35<12:19:55, 1.42s/it] 50%|████▉ | 30737/61904 [5:02:36<12:17:03, 1.42s/it] 50%|████▉ | 30738/61904 [5:02:37<12:06:20, 1.40s/it] 50%|████▉ | 30739/61904 [5:02:39<11:51:23, 1.37s/it] 50%|████▉ | 30740/61904 [5:02:40<12:35:46, 1.46s/it] {'loss': 2.5501, 'learning_rate': 1.5050563982886036e-07, 'epoch': 7.94} + 50%|████▉ | 30740/61904 [5:02:40<12:35:46, 1.46s/it] 50%|████▉ | 30741/61904 [5:02:42<12:25:23, 1.44s/it] 50%|████▉ | 30742/61904 [5:02:43<12:03:02, 1.39s/it] 50%|████▉ | 30743/61904 [5:02:44<12:13:35, 1.41s/it] 50%|████▉ | 30744/61904 [5:02:46<12:04:07, 1.39s/it] 50%|████▉ | 30745/61904 [5:02:47<11:51:31, 1.37s/it] 50%|████▉ | 30746/61904 [5:02:49<12:21:46, 1.43s/it] 50%|████▉ | 30747/61904 [5:02:50<12:10:05, 1.41s/it] 50%|████▉ | 30748/61904 [5:02:51<11:51:04, 1.37s/it] 50%|████▉ | 30749/61904 [5:02:53<11:40:16, 1.35s/it] 50%|████▉ | 30750/61904 [5:02:54<11:39:57, 1.35s/it] 50%|████▉ | 30751/61904 [5:02:55<11:35:23, 1.34s/it] 50%|████▉ | 30752/61904 [5:02:57<11:26:29, 1.32s/it] 50%|████▉ | 30753/61904 [5:02:58<11:41:05, 1.35s/it] 50%|████▉ | 30754/61904 [5:02:59<12:02:36, 1.39s/it] 50%|████▉ | 30755/61904 [5:03:01<11:52:53, 1.37s/it] 50%|████▉ | 30756/61904 [5:03:02<11:57:26, 1.38s/it] 50%|████▉ | 30757/61904 [5:03:04<12:03:39, 1.39s/it] 50%|████▉ | 30758/61904 [5:03:05<11:38:57, 1.35s/it] 50%|████▉ | 30759/61904 [5:03:06<11:41:12, 1.35s/it] 50%|████▉ | 30760/61904 [5:03:08<11:34:21, 1.34s/it] {'loss': 2.5918, 'learning_rate': 1.5047322701931802e-07, 'epoch': 7.95} + 50%|████▉ | 30760/61904 [5:03:08<11:34:21, 1.34s/it] 50%|████▉ | 30761/61904 [5:03:09<11:40:53, 1.35s/it] 50%|████▉ | 30762/61904 [5:03:10<11:35:21, 1.34s/it] 50%|████▉ | 30763/61904 [5:03:12<11:43:55, 1.36s/it] 50%|████▉ | 30764/61904 [5:03:13<11:37:34, 1.34s/it] 50%|████▉ | 30765/61904 [5:03:14<11:31:30, 1.33s/it] 50%|████▉ | 30766/61904 [5:03:16<11:50:49, 1.37s/it] 50%|████▉ | 30767/61904 [5:03:17<11:43:54, 1.36s/it] 50%|████▉ | 30768/61904 [5:03:18<11:54:16, 1.38s/it] 50%|████▉ | 30769/61904 [5:03:20<11:43:20, 1.36s/it] 50%|████▉ | 30770/61904 [5:03:21<11:59:15, 1.39s/it] 50%|████▉ | 30771/61904 [5:03:23<11:52:28, 1.37s/it] 50%|████▉ | 30772/61904 [5:03:24<11:58:11, 1.38s/it] 50%|████▉ | 30773/61904 [5:03:25<12:12:26, 1.41s/it] 50%|████▉ | 30774/61904 [5:03:27<12:05:06, 1.40s/it] 50%|████▉ | 30775/61904 [5:03:28<12:13:49, 1.41s/it] 50%|████▉ | 30776/61904 [5:03:30<12:08:03, 1.40s/it] 50%|████▉ | 30777/61904 [5:03:31<12:01:47, 1.39s/it] 50%|████▉ | 30778/61904 [5:03:32<11:45:52, 1.36s/it] 50%|████▉ | 30779/61904 [5:03:34<11:33:53, 1.34s/it] 50%|████▉ | 30780/61904 [5:03:35<11:25:40, 1.32s/it] {'loss': 2.5722, 'learning_rate': 1.504408142097757e-07, 'epoch': 7.96} + 50%|████▉ | 30780/61904 [5:03:35<11:25:40, 1.32s/it] 50%|████▉ | 30781/61904 [5:03:36<11:22:46, 1.32s/it] 50%|████▉ | 30782/61904 [5:03:38<11:28:06, 1.33s/it] 50%|████▉ | 30783/61904 [5:03:39<11:25:03, 1.32s/it] 50%|████▉ | 30784/61904 [5:03:40<11:20:02, 1.31s/it] 50%|████▉ | 30785/61904 [5:03:42<11:34:00, 1.34s/it] 50%|████▉ | 30786/61904 [5:03:43<11:41:01, 1.35s/it] 50%|████▉ | 30787/61904 [5:03:44<11:34:08, 1.34s/it] 50%|████▉ | 30788/61904 [5:03:46<11:48:11, 1.37s/it] 50%|████▉ | 30789/61904 [5:03:47<11:44:46, 1.36s/it] 50%|████▉ | 30790/61904 [5:03:48<11:57:41, 1.38s/it] 50%|████▉ | 30791/61904 [5:03:50<11:48:53, 1.37s/it] 50%|████▉ | 30792/61904 [5:03:51<12:03:01, 1.39s/it] 50%|████▉ | 30793/61904 [5:03:53<12:10:13, 1.41s/it] 50%|████▉ | 30794/61904 [5:03:54<12:05:16, 1.40s/it] 50%|████▉ | 30795/61904 [5:03:55<12:03:48, 1.40s/it] 50%|████▉ | 30796/61904 [5:03:57<11:58:41, 1.39s/it] 50%|████▉ | 30797/61904 [5:03:58<12:21:05, 1.43s/it] 50%|████▉ | 30798/61904 [5:04:00<12:15:14, 1.42s/it] 50%|████▉ | 30799/61904 [5:04:01<12:21:29, 1.43s/it] 50%|████▉ | 30800/61904 [5:04:02<11:47:26, 1.36s/it] {'loss': 2.5233, 'learning_rate': 1.5040840140023337e-07, 'epoch': 7.96} + 50%|████▉ | 30800/61904 [5:04:02<11:47:26, 1.36s/it] 50%|████▉ | 30801/61904 [5:04:04<11:33:34, 1.34s/it] 50%|████▉ | 30802/61904 [5:04:05<11:25:21, 1.32s/it] 50%|████▉ | 30803/61904 [5:04:06<11:56:09, 1.38s/it] 50%|████▉ | 30804/61904 [5:04:08<11:48:45, 1.37s/it] 50%|████▉ | 30805/61904 [5:04:09<11:56:07, 1.38s/it] 50%|████▉ | 30806/61904 [5:04:11<12:06:38, 1.40s/it] 50%|████▉ | 30807/61904 [5:04:12<11:58:39, 1.39s/it] 50%|████▉ | 30808/61904 [5:04:13<12:05:15, 1.40s/it] 50%|████▉ | 30809/61904 [5:04:15<12:20:16, 1.43s/it] 50%|████▉ | 30810/61904 [5:04:16<12:04:00, 1.40s/it] 50%|████▉ | 30811/61904 [5:04:18<11:53:08, 1.38s/it] 50%|████▉ | 30812/61904 [5:04:19<11:45:50, 1.36s/it] 50%|████▉ | 30813/61904 [5:04:20<11:31:58, 1.34s/it] 50%|████▉ | 30814/61904 [5:04:22<11:32:33, 1.34s/it] 50%|████▉ | 30815/61904 [5:04:23<11:21:32, 1.32s/it] 50%|████▉ | 30816/61904 [5:04:24<11:07:49, 1.29s/it] 50%|████▉ | 30817/61904 [5:04:25<11:32:01, 1.34s/it] 50%|████▉ | 30818/61904 [5:04:27<11:39:17, 1.35s/it] 50%|████▉ | 30819/61904 [5:04:28<11:28:13, 1.33s/it] 50%|████▉ | 30820/61904 [5:04:30<11:55:28, 1.38s/it] {'loss': 2.5999, 'learning_rate': 1.5037598859069103e-07, 'epoch': 7.97} + 50%|████▉ | 30820/61904 [5:04:30<11:55:28, 1.38s/it] 50%|████▉ | 30821/61904 [5:04:31<11:55:32, 1.38s/it] 50%|████▉ | 30822/61904 [5:04:32<12:09:16, 1.41s/it] 50%|████▉ | 30823/61904 [5:04:34<12:02:45, 1.40s/it] 50%|████▉ | 30824/61904 [5:04:35<12:10:29, 1.41s/it] 50%|████▉ | 30825/61904 [5:04:37<11:50:27, 1.37s/it] 50%|████▉ | 30826/61904 [5:04:38<11:37:34, 1.35s/it] 50%|████▉ | 30827/61904 [5:04:39<11:39:10, 1.35s/it] 50%|████▉ | 30828/61904 [5:04:41<11:38:09, 1.35s/it] 50%|████▉ | 30829/61904 [5:04:42<11:49:46, 1.37s/it] 50%|████▉ | 30830/61904 [5:04:43<11:38:53, 1.35s/it] 50%|████▉ | 30831/61904 [5:04:45<11:30:27, 1.33s/it] 50%|████▉ | 30832/61904 [5:04:46<11:32:17, 1.34s/it] 50%|████▉ | 30833/61904 [5:04:47<11:58:21, 1.39s/it] 50%|████▉ | 30834/61904 [5:04:49<11:59:27, 1.39s/it] 50%|████▉ | 30835/61904 [5:04:50<11:51:15, 1.37s/it] 50%|████▉ | 30836/61904 [5:04:52<11:49:13, 1.37s/it] 50%|████▉ | 30837/61904 [5:04:53<11:41:00, 1.35s/it] 50%|████▉ | 30838/61904 [5:04:54<11:28:49, 1.33s/it] 50%|████▉ | 30839/61904 [5:04:55<11:36:39, 1.35s/it] 50%|████▉ | 30840/61904 [5:04:57<11:58:19, 1.39s/it] {'loss': 2.5356, 'learning_rate': 1.503435757811487e-07, 'epoch': 7.97} + 50%|████▉ | 30840/61904 [5:04:57<11:58:19, 1.39s/it] 50%|████▉ | 30841/61904 [5:04:58<12:16:32, 1.42s/it] 50%|████▉ | 30842/61904 [5:05:00<12:34:29, 1.46s/it] 50%|████▉ | 30843/61904 [5:05:01<12:13:57, 1.42s/it] 50%|████▉ | 30844/61904 [5:05:03<12:21:11, 1.43s/it] 50%|████▉ | 30845/61904 [5:05:04<12:33:34, 1.46s/it] 50%|████▉ | 30846/61904 [5:05:06<12:16:03, 1.42s/it] 50%|████▉ | 30847/61904 [5:05:07<11:57:02, 1.39s/it] 50%|████▉ | 30848/61904 [5:05:08<11:56:08, 1.38s/it] 50%|████▉ | 30849/61904 [5:05:10<12:15:25, 1.42s/it] 50%|████▉ | 30850/61904 [5:05:11<12:38:54, 1.47s/it] 50%|████▉ | 30851/61904 [5:05:13<12:30:39, 1.45s/it] 50%|████▉ | 30852/61904 [5:05:14<12:22:05, 1.43s/it] 50%|████▉ | 30853/61904 [5:05:16<12:14:33, 1.42s/it] 50%|████▉ | 30854/61904 [5:05:17<12:31:00, 1.45s/it] 50%|████▉ | 30855/61904 [5:05:18<12:02:17, 1.40s/it] 50%|████▉ | 30856/61904 [5:05:20<11:50:39, 1.37s/it] 50%|████▉ | 30857/61904 [5:05:21<11:59:10, 1.39s/it] 50%|████▉ | 30858/61904 [5:05:22<11:51:44, 1.38s/it] 50%|████▉ | 30859/61904 [5:05:24<12:07:49, 1.41s/it] 50%|████▉ | 30860/61904 [5:05:25<12:17:06, 1.42s/it] {'loss': 2.5524, 'learning_rate': 1.5031116297160638e-07, 'epoch': 7.98} + 50%|████▉ | 30860/61904 [5:05:25<12:17:06, 1.42s/it] 50%|████▉ | 30861/61904 [5:05:27<12:24:07, 1.44s/it] 50%|████▉ | 30862/61904 [5:05:28<12:19:42, 1.43s/it] 50%|████▉ | 30863/61904 [5:05:30<12:02:51, 1.40s/it] 50%|████▉ | 30864/61904 [5:05:31<12:01:03, 1.39s/it] 50%|████▉ | 30865/61904 [5:05:33<12:20:53, 1.43s/it] 50%|████▉ | 30866/61904 [5:05:34<12:14:38, 1.42s/it] 50%|████▉ | 30867/61904 [5:05:35<12:07:57, 1.41s/it] 50%|████▉ | 30868/61904 [5:05:37<12:03:44, 1.40s/it] 50%|████▉ | 30869/61904 [5:05:38<11:47:52, 1.37s/it] 50%|████▉ | 30870/61904 [5:05:39<12:01:54, 1.40s/it] 50%|████▉ | 30871/61904 [5:05:41<12:20:51, 1.43s/it] 50%|████▉ | 30872/61904 [5:05:43<12:51:03, 1.49s/it] 50%|████▉ | 30873/61904 [5:05:44<12:48:29, 1.49s/it] 50%|████▉ | 30874/61904 [5:05:45<12:15:26, 1.42s/it] 50%|████▉ | 30875/61904 [5:05:47<12:05:42, 1.40s/it] 50%|████▉ | 30876/61904 [5:05:48<12:20:46, 1.43s/it] 50%|████▉ | 30877/61904 [5:05:50<12:20:56, 1.43s/it] 50%|████▉ | 30878/61904 [5:05:51<12:17:02, 1.43s/it] 50%|████▉ | 30879/61904 [5:05:52<12:09:39, 1.41s/it] 50%|████▉ | 30880/61904 [5:05:54<12:12:31, 1.42s/it] {'loss': 2.6066, 'learning_rate': 1.5027875016206404e-07, 'epoch': 7.98} + 50%|████▉ | 30880/61904 [5:05:54<12:12:31, 1.42s/it] 50%|████▉ | 30881/61904 [5:05:55<12:05:23, 1.40s/it] 50%|████▉ | 30882/61904 [5:05:57<11:50:34, 1.37s/it] 50%|████▉ | 30883/61904 [5:05:58<11:56:15, 1.39s/it] 50%|████▉ | 30884/61904 [5:05:59<11:54:08, 1.38s/it] 50%|████▉ | 30885/61904 [5:06:01<11:51:03, 1.38s/it] 50%|████▉ | 30886/61904 [5:06:02<11:33:17, 1.34s/it] 50%|████▉ | 30887/61904 [5:06:03<11:23:05, 1.32s/it] 50%|████▉ | 30888/61904 [5:06:05<11:30:18, 1.34s/it] 50%|████▉ | 30889/61904 [5:06:06<11:38:48, 1.35s/it] 50%|████▉ | 30890/61904 [5:06:07<11:54:25, 1.38s/it] 50%|████▉ | 30891/61904 [5:06:09<11:36:46, 1.35s/it] 50%|████▉ | 30892/61904 [5:06:10<11:48:31, 1.37s/it] 50%|████▉ | 30893/61904 [5:06:12<11:57:11, 1.39s/it] 50%|████▉ | 30894/61904 [5:06:13<11:42:06, 1.36s/it] 50%|████▉ | 30895/61904 [5:06:14<11:20:53, 1.32s/it] 50%|████▉ | 30896/61904 [5:06:15<11:35:40, 1.35s/it] 50%|████▉ | 30897/61904 [5:06:17<11:44:57, 1.36s/it] 50%|████▉ | 30898/61904 [5:06:18<11:46:24, 1.37s/it] 50%|████▉ | 30899/61904 [5:06:20<12:06:03, 1.41s/it] 50%|████▉ | 30900/61904 [5:06:21<12:09:45, 1.41s/it] {'loss': 2.5563, 'learning_rate': 1.502463373525217e-07, 'epoch': 7.99} + 50%|████▉ | 30900/61904 [5:06:21<12:09:45, 1.41s/it] 50%|████▉ | 30901/61904 [5:06:23<12:09:18, 1.41s/it] 50%|████▉ | 30902/61904 [5:06:24<11:51:49, 1.38s/it] 50%|████▉ | 30903/61904 [5:06:25<11:42:07, 1.36s/it] 50%|████▉ | 30904/61904 [5:06:27<11:48:39, 1.37s/it] 50%|████▉ | 30905/61904 [5:06:28<12:03:23, 1.40s/it] 50%|████▉ | 30906/61904 [5:06:30<12:28:58, 1.45s/it] 50%|████▉ | 30907/61904 [5:06:31<12:29:41, 1.45s/it] 50%|████▉ | 30908/61904 [5:06:32<11:59:34, 1.39s/it] 50%|████▉ | 30909/61904 [5:06:34<11:39:50, 1.35s/it] 50%|████▉ | 30910/61904 [5:06:35<11:54:13, 1.38s/it] 50%|████▉ | 30911/61904 [5:06:36<12:01:31, 1.40s/it] 50%|████▉ | 30912/61904 [5:06:38<12:06:41, 1.41s/it] 50%|████▉ | 30913/61904 [5:06:39<11:57:56, 1.39s/it] 50%|████▉ | 30914/61904 [5:06:41<12:07:29, 1.41s/it] 50%|████▉ | 30915/61904 [5:06:42<11:50:43, 1.38s/it] 50%|████▉ | 30916/61904 [5:06:43<11:40:55, 1.36s/it] 50%|████▉ | 30917/61904 [5:06:45<11:45:09, 1.37s/it] 50%|████▉ | 30918/61904 [5:06:46<11:47:30, 1.37s/it] 50%|████▉ | 30919/61904 [5:06:47<11:39:19, 1.35s/it] 50%|████▉ | 30920/61904 [5:06:49<11:44:20, 1.36s/it] {'loss': 2.5131, 'learning_rate': 1.502139245429794e-07, 'epoch': 7.99} + 50%|████▉ | 30920/61904 [5:06:49<11:44:20, 1.36s/it] 50%|████▉ | 30921/61904 [5:06:50<11:41:16, 1.36s/it] 50%|████▉ | 30922/61904 [5:06:52<11:51:00, 1.38s/it] 50%|████▉ | 30923/61904 [5:06:53<11:59:48, 1.39s/it] 50%|████▉ | 30924/61904 [5:06:54<11:52:41, 1.38s/it] 50%|████▉ | 30925/61904 [5:06:56<11:43:22, 1.36s/it] 50%|████▉ | 30926/61904 [5:06:57<11:41:33, 1.36s/it] 50%|████▉ | 30927/61904 [5:06:59<12:17:18, 1.43s/it] 50%|████▉ | 30928/61904 [5:07:00<12:11:53, 1.42s/it] 50%|████▉ | 30929/61904 [5:07:01<11:51:13, 1.38s/it] 50%|████▉ | 30930/61904 [5:07:03<11:40:29, 1.36s/it] 50%|████▉ | 30931/61904 [5:07:04<11:48:13, 1.37s/it] 50%|████▉ | 30932/61904 [5:07:05<12:00:56, 1.40s/it] 50%|████▉ | 30933/61904 [5:07:07<11:45:28, 1.37s/it] 50%|████▉ | 30934/61904 [5:07:08<11:38:19, 1.35s/it] 50%|████▉ | 30935/61904 [5:07:10<11:50:23, 1.38s/it] 50%|████▉ | 30936/61904 [5:07:11<12:11:40, 1.42s/it] 50%|████▉ | 30937/61904 [5:07:12<11:54:37, 1.38s/it] 50%|████▉ | 30938/61904 [5:07:14<11:40:00, 1.36s/it] 50%|████▉ | 30939/61904 [5:07:15<11:49:37, 1.38s/it] 50%|████▉ | 30940/61904 [5:07:16<11:39:08, 1.35s/it] {'loss': 2.5943, 'learning_rate': 1.5018151173343705e-07, 'epoch': 8.0} + 50%|████▉ | 30940/61904 [5:07:16<11:39:08, 1.35s/it] 50%|████▉ | 30941/61904 [5:07:18<11:42:38, 1.36s/it] 50%|████▉ | 30942/61904 [5:07:19<12:02:28, 1.40s/it] 50%|████▉ | 30943/61904 [5:07:21<12:22:02, 1.44s/it] 50%|████▉ | 30944/61904 [5:07:22<11:51:37, 1.38s/it] 50%|████▉ | 30945/61904 [5:07:23<11:50:51, 1.38s/it] 50%|████▉ | 30946/61904 [5:07:25<11:58:35, 1.39s/it] 50%|████▉ | 30947/61904 [5:07:26<11:57:53, 1.39s/it] 50%|████▉ | 30948/61904 [5:07:28<11:53:29, 1.38s/it] 50%|████▉ | 30949/61904 [5:07:29<12:02:46, 1.40s/it] 50%|████▉ | 30950/61904 [5:07:30<12:19:15, 1.43s/it] 50%|████▉ | 30951/61904 [5:07:32<12:13:42, 1.42s/it] 50%|█████ | 30952/61904 [5:07:33<12:13:45, 1.42s/it] 50%|█████ | 30953/61904 [5:07:35<12:14:02, 1.42s/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() + 50%|█████ | 30954/61904 [5:22:23<2299:41:27, 267.49s/it] 50%|█████ | 30955/61904 [5:22:25<1613:36:15, 187.70s/it] 50%|█████ | 30956/61904 [5:22:26<1133:12:55, 131.82s/it] 50%|█████ | 30957/61904 [5:22:27<796:53:58, 92.70s/it] 50%|█████ | 30958/61904 [5:22:29<561:31:31, 65.32s/it] 50%|█████ | 30959/61904 [5:22:30<396:45:44, 46.16s/it] 50%|█████ | 30960/61904 [5:22:32<281:09:52, 32.71s/it] {'loss': 2.5393, 'learning_rate': 1.5014909892389472e-07, 'epoch': 8.0} + 50%|█████ | 30960/61904 [5:22:32<281:09:52, 32.71s/it] 50%|█████ | 30961/61904 [5:22:33<200:43:11, 23.35s/it] 50%|█████ | 30962/61904 [5:22:35<144:24:49, 16.80s/it] 50%|█████ | 30963/61904 [5:22:36<104:50:31, 12.20s/it] 50%|█████ | 30964/61904 [5:22:38<77:22:38, 9.00s/it] 50%|█████ | 30965/61904 [5:22:39<58:19:59, 6.79s/it] 50%|█████ | 30966/61904 [5:22:41<44:23:15, 5.17s/it] 50%|█████ | 30967/61904 [5:22:42<34:30:23, 4.02s/it] 50%|█████ | 30968/61904 [5:22:43<27:47:31, 3.23s/it] 50%|█████ | 30969/61904 [5:22:45<23:01:29, 2.68s/it] 50%|█████ | 30970/61904 [5:22:46<19:54:01, 2.32s/it] 50%|█████ | 30971/61904 [5:22:48<17:29:59, 2.04s/it] 50%|█████ | 30972/61904 [5:22:49<15:31:05, 1.81s/it] 50%|█████ | 30973/61904 [5:22:50<14:20:00, 1.67s/it] 50%|█████ | 30974/61904 [5:22:52<13:39:47, 1.59s/it] 50%|█████ | 30975/61904 [5:22:53<13:22:46, 1.56s/it] 50%|█████ | 30976/61904 [5:22:55<13:04:29, 1.52s/it] 50%|█████ | 30977/61904 [5:22:56<12:47:49, 1.49s/it] 50%|█████ | 30978/61904 [5:22:58<13:09:08, 1.53s/it] 50%|█████ | 30979/61904 [5:22:59<12:22:39, 1.44s/it] 50%|█████ | 30980/61904 [5:23:00<12:23:44, 1.44s/it] {'loss': 2.4841, 'learning_rate': 1.5011668611435238e-07, 'epoch': 8.01} + 50%|█████ | 30980/61904 [5:23:00<12:23:44, 1.44s/it] 50%|█████ | 30981/61904 [5:23:02<12:00:53, 1.40s/it] 50%|█████ | 30982/61904 [5:23:03<12:22:37, 1.44s/it] 50%|█████ | 30983/61904 [5:23:05<12:14:19, 1.42s/it] 50%|█████ | 30984/61904 [5:23:06<12:22:05, 1.44s/it] 50%|█████ | 30985/61904 [5:23:07<12:07:21, 1.41s/it] 50%|█████ | 30986/61904 [5:23:09<11:50:09, 1.38s/it] 50%|█████ | 30987/61904 [5:23:10<12:30:36, 1.46s/it] 50%|█████ | 30988/61904 [5:23:12<12:11:29, 1.42s/it] 50%|█████ | 30989/61904 [5:23:13<12:04:46, 1.41s/it] 50%|█████ | 30990/61904 [5:23:14<11:54:39, 1.39s/it] 50%|█████ | 30991/61904 [5:23:16<11:44:11, 1.37s/it] 50%|█████ | 30992/61904 [5:23:17<11:45:10, 1.37s/it] 50%|█████ | 30993/61904 [5:23:18<11:28:33, 1.34s/it] 50%|█████ | 30994/61904 [5:23:20<11:43:57, 1.37s/it] 50%|█████ | 30995/61904 [5:23:21<11:48:06, 1.37s/it] 50%|█████ | 30996/61904 [5:23:22<11:25:44, 1.33s/it] 50%|█████ | 30997/61904 [5:23:24<11:51:11, 1.38s/it] 50%|█████ | 30998/61904 [5:23:25<11:42:41, 1.36s/it] 50%|█████ | 30999/61904 [5:23:27<11:50:04, 1.38s/it] 50%|█████ | 31000/61904 [5:23:28<11:39:06, 1.36s/it] {'loss': 2.5913, 'learning_rate': 1.5008427330481007e-07, 'epoch': 8.01} + 50%|███���█ | 31000/61904 [5:23:28<11:39:06, 1.36s/it] 50%|█████ | 31001/61904 [5:23:29<11:53:47, 1.39s/it] 50%|█████ | 31002/61904 [5:23:31<11:59:15, 1.40s/it] 50%|█████ | 31003/61904 [5:23:32<12:37:40, 1.47s/it] 50%|█████ | 31004/61904 [5:23:34<12:27:20, 1.45s/it] 50%|█████ | 31005/61904 [5:23:35<12:09:40, 1.42s/it] 50%|█████ | 31006/61904 [5:23:37<12:08:15, 1.41s/it] 50%|█████ | 31007/61904 [5:23:38<11:45:47, 1.37s/it] 50%|█████ | 31008/61904 [5:23:39<11:36:34, 1.35s/it] 50%|█████ | 31009/61904 [5:23:41<11:46:56, 1.37s/it] 50%|█████ | 31010/61904 [5:23:42<12:13:55, 1.43s/it] 50%|█████ | 31011/61904 [5:23:44<13:07:53, 1.53s/it] 50%|█████ | 31012/61904 [5:23:45<13:09:13, 1.53s/it] 50%|█████ | 31013/61904 [5:23:47<12:43:07, 1.48s/it] 50%|█████ | 31014/61904 [5:23:48<12:46:29, 1.49s/it] 50%|█████ | 31015/61904 [5:23:50<12:34:13, 1.47s/it] 50%|█████ | 31016/61904 [5:23:51<12:14:17, 1.43s/it] 50%|█████ | 31017/61904 [5:23:53<12:28:17, 1.45s/it] 50%|█████ | 31018/61904 [5:23:54<12:03:32, 1.41s/it] 50%|█████ | 31019/61904 [5:23:55<12:07:21, 1.41s/it] 50%|█████ | 31020/61904 [5:23:57<12:09:32, 1.42s/it] {'loss': 2.5053, 'learning_rate': 1.5005186049526773e-07, 'epoch': 8.02} + 50%|█████ | 31020/61904 [5:23:57<12:09:32, 1.42s/it] 50%|█████ | 31021/61904 [5:23:58<11:49:39, 1.38s/it] 50%|█████ | 31022/61904 [5:23:59<11:55:03, 1.39s/it] 50%|█████ | 31023/61904 [5:24:01<11:50:06, 1.38s/it] 50%|█████ | 31024/61904 [5:24:02<11:59:39, 1.40s/it] \ No newline at end of file