Training in progress, step 2000

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd612903095a65f07dd99040b0e39e361bd86d9b463b47ab9a3633b1b266dd23
+oid sha256:4bfa1ab908dab46b89366a1db97b311ae26c44da936561eaf5c9ef2be1315a21
 size 967102601

training.log

@@ -994,3 +994,167 @@ wandb: 🚀 View run at https://wandb.ai/danielizham/huggingface/runs/lvsln7ks
 Adding files tracked by Git LFS: ['wandb/run-20230509_115211-hq92t8sj/run-hq92t8sj.wandb', 'wandb/run-20230510_094132-lvsln7ks/run-lvsln7ks.wandb']. This may take a bit of time if the files are large.
 {'eval_loss': 0.24644243717193604, 'eval_wer': 9.800036380645496, 'eval_runtime': 3384.9122, 'eval_samples_per_second': 4.585, 'eval_steps_per_second': 0.072, 'epoch': 4.01}
 05/10/2023 18:44:21 - WARNING - huggingface_hub.repository - Adding files tracked by Git LFS: ['wandb/run-20230509_115211-hq92t8sj/run-hq92t8sj.wandb', 'wandb/run-20230510_094132-lvsln7ks/run-lvsln7ks.wandb']. This may take a bit of time if the files are large.
+/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.
+  warnings.warn('Was asked to gather along dimension 0, but all '
+
 20%|██        | 1001/5000 [9:03:19<1170:39:51, 1053.86s/it]
 20%|██        | 1002/5000 [9:03:48<828:45:04, 746.25s/it]  
 20%|██        | 1003/5000 [9:04:17<589:34:20, 531.01s/it]
 20%|██        | 1004/5000 [9:04:45<421:56:45, 380.13s/it]
 20%|██        | 1005/5000 [9:05:13<304:41:43, 274.57s/it]
 20%|██        | 1006/5000 [9:05:40<222:16:53, 200.35s/it]
 20%|██        | 1007/5000 [9:06:10<165:22:17, 149.10s/it]
 20%|██        | 1008/5000 [9:06:37<124:54:48, 112.65s/it]
 20%|██        | 1009/5000 [9:07:04<96:24:16, 86.96s/it]  
 20%|██        | 1010/5000 [9:07:33<76:59:46, 69.47s/it]
 20%|██        | 1011/5000 [9:08:01<63:08:00, 56.98s/it]
 20%|██        | 1012/5000 [9:08:28<53:10:01, 47.99s/it]
 20%|██        | 1013/5000 [9:08:56<46:31:43, 42.01s/it]
 20%|██        | 1014/5000 [9:09:23<41:34:57, 37.56s/it]
 20%|██        | 1015/5000 [9:09:52<38:43:41, 34.99s/it]
 20%|██        | 1016/5000 [9:10:20<36:23:19, 32.88s/it]
 20%|██        | 1017/5000 [9:10:49<35:00:41, 31.64s/it]
 20%|██        | 1018/5000 [9:11:18<34:03:53, 30.80s/it]
 20%|██        | 1019/5000 [9:11:45<32:58:46, 29.82s/it]
 20%|██        | 1020/5000 [9:12:15<32:50:09, 29.70s/it]
 20%|██        | 1021/5000 [9:12:43<32:17:24, 29.21s/it]
 20%|██        | 1022/5000 [9:13:10<31:48:15, 28.78s/it]
 20%|██        | 1023/5000 [9:13:39<31:40:38, 28.67s/it]
 20%|██        | 1024/5000 [9:14:08<31:48:32, 28.80s/it]
 20%|██        | 1025/5000 [9:14:35<31:09:01, 28.21s/it]
                                                        
 20%|██        | 1025/5000 [9:14:35<31:09:01, 28.21s/it]
 21%|██        | 1026/5000 [9:15:05<31:44:49, 28.76s/it]
 21%|██        | 1027/5000 [9:15:32<31:07:57, 28.21s/it]
 21%|██        | 1028/5000 [9:16:02<31:45:25, 28.78s/it]
 21%|██        | 1029/5000 [9:16:29<31:11:13, 28.27s/it]
 21%|██        | 1030/5000 [9:17:01<32:17:18, 29.28s/it]
 21%|██        | 1031/5000 [9:17:29<31:57:19, 28.98s/it]
 21%|██        | 1032/5000 [9:17:57<31:44:06, 28.79s/it]
 21%|██        | 1033/5000 [9:18:25<31:16:27, 28.38s/it]
 21%|██        | 1034/5000 [9:18:52<30:46:58, 27.94s/it]
 21%|██        | 1035/5000 [9:19:20<31:02:35, 28.19s/it]
 21%|██        | 1036/5000 [9:19:49<31:04:00, 28.21s/it]
 21%|██        | 1037/5000 [9:20:18<31:36:11, 28.71s/it]
 21%|██        | 1038/5000 [9:20:46<31:06:32, 28.27s/it]
 21%|██        | 1039/5000 [9:21:16<31:45:50, 28.87s/it]
 21%|██        | 1040/5000 [9:21:45<31:55:46, 29.03s/it]
 21%|██        | 1041/5000 [9:22:17<32:48:28, 29.83s/it]
 21%|██        | 1042/5000 [9:22:47<32:58:15, 29.99s/it]
 21%|██        | 1043/5000 [9:23:17<32:52:43, 29.91s/it]
 21%|██        | 1044/5000 [9:23:47<32:42:19, 29.76s/it]
 21%|██        | 1045/5000 [9:24:17<32:52:05, 29.92s/it]
 21%|██        | 1046/5000 [9:24:47<32:52:58, 29.94s/it]
 21%|██        | 1047/5000 [9:25:15<32:26:30, 29.54s/it]
 21%|██        | 1048/5000 [9:25:46<32:41:54, 29.79s/it]
 21%|██        | 1049/5000 [9:26:14<32:13:26, 29.36s/it]
 21%|██        | 1050/5000 [9:26:42<31:40:07, 28.86s/it]
                                                        
 21%|██        | 1050/5000 [9:26:42<31:40:07, 28.86s/it]
 21%|██        | 1051/5000 [9:27:09<31:13:29, 28.47s/it]
 21%|██        | 1052/5000 [9:27:37<30:59:26, 28.26s/it]
 21%|██        | 1053/5000 [9:28:06<31:14:32, 28.50s/it]
 21%|██        | 1054/5000 [9:28:34<30:50:26, 28.14s/it]
 21%|██        | 1055/5000 [9:29:02<30:49:40, 28.13s/it]
 21%|██        | 1056/5000 [9:29:29<30:33:56, 27.90s/it]
 21%|██        | 1057/5000 [9:29:58<30:49:15, 28.14s/it]
 21%|██        | 1058/5000 [9:30:27<31:06:36, 28.41s/it]
 21%|██        | 1059/5000 [9:30:54<30:45:45, 28.10s/it]
 21%|██        | 1060/5000 [9:31:22<30:50:42, 28.18s/it]
 21%|██        | 1061/5000 [9:31:50<30:31:20, 27.90s/it]
 21%|██        | 1062/5000 [9:32:17<30:18:14, 27.70s/it]
 21%|██▏       | 1063/5000 [9:32:44<30:11:33, 27.61s/it]
 21%|██▏       | 1064/5000 [9:33:11<29:44:56, 27.21s/it]
 21%|██▏       | 1065/5000 [9:33:39<30:06:51, 27.55s/it]
 21%|██▏       | 1066/5000 [9:34:05<29:41:50, 27.18s/it]
 21%|██▏       | 1067/5000 [9:34:34<30:19:16, 27.75s/it]
 21%|██▏       | 1068/5000 [9:35:03<30:33:43, 27.98s/it]
 21%|██▏       | 1069/5000 [9:35:30<30:23:41, 27.84s/it]
 21%|██▏       | 1070/5000 [9:35:58<30:24:31, 27.86s/it]
 21%|██▏       | 1071/5000 [9:36:26<30:20:39, 27.80s/it]
 21%|██▏       | 1072/5000 [9:36:54<30:34:05, 28.02s/it]
 21%|██▏       | 1073/5000 [9:37:22<30:29:22, 27.95s/it]
 21%|██▏       | 1074/5000 [9:37:49<30:00:13, 27.51s/it]
 22%|██▏       | 1075/5000 [9:38:18<30:32:50, 28.02s/it]
                                                        
 22%|██▏       | 1075/5000 [9:38:18<30:32:50, 28.02s/it]
 22%|██▏       | 1076/5000 [9:38:46<30:23:00, 27.87s/it]
 22%|██▏       | 1077/5000 [9:39:14<30:24:39, 27.91s/it]
 22%|██▏       | 1078/5000 [9:39:41<30:19:45, 27.84s/it]
 22%|██▏       | 1079/5000 [9:40:09<30:14:07, 27.76s/it]
 22%|██▏       | 1080/5000 [9:40:36<30:12:26, 27.74s/it]
 22%|██▏       | 1081/5000 [9:41:05<30:18:27, 27.84s/it]
 22%|██▏       | 1082/5000 [9:41:32<30:15:30, 27.80s/it]
 22%|██▏       | 1083/5000 [9:42:01<30:42:35, 28.22s/it]
 22%|██▏       | 1084/5000 [9:42:29<30:21:54, 27.91s/it]
 22%|██▏       | 1085/5000 [9:42:57<30:24:33, 27.96s/it]
 22%|██▏       | 1086/5000 [9:43:26<30:46:06, 28.30s/it]
 22%|██▏       | 1087/5000 [9:43:55<30:58:04, 28.49s/it]
 22%|██▏       | 1088/5000 [9:44:23<30:48:14, 28.35s/it]
 22%|██▏       | 1089/5000 [9:44:50<30:25:17, 28.00s/it]
 22%|██▏       | 1090/5000 [9:45:19<30:37:14, 28.19s/it]
 22%|██▏       | 1091/5000 [9:45:46<30:28:55, 28.07s/it]
 22%|██▏       | 1092/5000 [9:46:14<30:20:22, 27.95s/it]
 22%|██▏       | 1093/5000 [9:46:44<30:54:33, 28.48s/it]
 22%|██▏       | 1094/5000 [9:47:11<30:25:16, 28.04s/it]
 22%|██▏       | 1095/5000 [9:47:40<30:51:22, 28.45s/it]
 22%|██▏       | 1096/5000 [9:48:08<30:42:11, 28.31s/it]
 22%|██▏       | 1097/5000 [9:48:36<30:27:26, 28.09s/it]
 22%|██▏       | 1098/5000 [9:49:04<30:24:16, 28.05s/it]
 22%|██▏       | 1099/5000 [9:49:32<30:20:56, 28.01s/it]
 22%|██▏       | 1100/5000 [9:50:01<30:41:56, 28.34s/it]
                                                        
 22%|██▏       | 1100/5000 [9:50:01<30:41:56, 28.34s/it]
 22%|██▏       | 1101/5000 [9:50:29<30:36:17, 28.26s/it]
 22%|██▏       | 1102/5000 [9:50:58<30:46:01, 28.41s/it]
 22%|██▏       | 1103/5000 [9:51:26<30:53:07, 28.53s/it]
 22%|██▏       | 1104/5000 [9:51:55<31:01:08, 28.66s/it]
 22%|██▏       | 1105/5000 [9:52:24<30:51:01, 28.51s/it]
 22%|██▏       | 1106/5000 [9:52:53<31:05:04, 28.74s/it]
 22%|██▏       | 1107/5000 [9:53:20<30:36:54, 28.31s/it]
 22%|██▏       | 1108/5000 [9:53:49<30:55:08, 28.60s/it]
 22%|██▏       | 1109/5000 [9:54:18<30:47:13, 28.48s/it]
 22%|██▏       | 1110/5000 [9:54:47<30:56:00, 28.63s/it]
 22%|██▏       | 1111/5000 [9:55:15<30:47:19, 28.50s/it]
 22%|██▏       | 1112/5000 [9:55:42<30:24:08, 28.15s/it]
 22%|██▏       | 1113/5000 [9:56:11<30:42:10, 28.44s/it]
 22%|██▏       | 1114/5000 [9:56:38<30:16:34, 28.05s/it]
 22%|██▏       | 1115/5000 [9:57:07<30:19:40, 28.10s/it]
 22%|██▏       | 1116/5000 [9:57:35<30:18:56, 28.10s/it]
 22%|██▏       | 1117/5000 [9:58:03<30:25:33, 28.21s/it]
 22%|██▏       | 1118/5000 [9:58:31<30:21:25, 28.15s/it]
 22%|██▏       | 1119/5000 [9:58:59<30:24:44, 28.21s/it]
 22%|██▏       | 1120/5000 [9:59:27<30:13:15, 28.04s/it]
 22%|██▏       | 1121/5000 [9:59:55<30:12:07, 28.03s/it]
 22%|██▏       | 1122/5000 [10:00:23<30:15:38, 28.09s/it]
 22%|██▏       | 1123/5000 [10:00:51<30:07:11, 27.97s/it]
 22%|██▏       | 1124/5000 [10:01:20<30:33:44, 28.39s/it]
 22%|██▎       | 1125/5000 [10:01:47<30:08:21, 28.00s/it]
                                                         
 22%|██▎       | 1125/5000 [10:01:47<30:08:21, 28.00s/it]
 23%|██▎       | 1126/5000 [10:02:15<30:06:41, 27.98s/it]
 23%|██▎       | 1127/5000 [10:02:44<30:10:13, 28.04s/it]
 23%|██▎       | 1128/5000 [10:03:12<30:10:54, 28.06s/it]
 23%|██▎       | 1129/5000 [10:03:40<30:05:04, 27.98s/it]
 23%|██▎       | 1130/5000 [10:04:07<30:03:25, 27.96s/it]
 23%|██▎       | 1131/5000 [10:04:35<29:53:21, 27.81s/it]
 23%|██▎       | 1132/5000 [10:05:01<29:23:39, 27.36s/it]
 23%|██▎       | 1133/5000 [10:05:29<29:35:17, 27.55s/it]
 23%|██▎       | 1134/5000 [10:05:57<29:46:16, 27.72s/it]
 23%|██▎       | 1135/5000 [10:06:24<29:31:36, 27.50s/it]
 23%|██▎       | 1136/5000 [10:06:55<30:24:45, 28.33s/it]
 23%|██▎       | 1137/5000 [10:07:22<29:59:16, 27.95s/it]
 23%|██▎       | 1138/5000 [10:07:53<31:09:11, 29.04s/it]
 23%|██▎       | 1139/5000 [10:08:20<30:31:19, 28.46s/it]
 23%|██▎       | 1140/5000 [10:08:51<31:08:21, 29.04s/it]
 23%|██▎       | 1141/5000 [10:09:25<32:48:14, 30.60s/it]
 23%|██▎       | 1142/5000 [10:09:53<32:04:58, 29.94s/it]
 23%|██▎       | 1143/5000 [10:10:22<31:48:52, 29.69s/it]
 23%|██▎       | 1144/5000 [10:10:50<31:15:16, 29.18s/it]
 23%|██▎       | 1145/5000 [10:11:21<31:49:40, 29.72s/it]
 23%|██▎       | 1146/5000 [10:11:51<31:45:12, 29.66s/it]
 23%|██▎       | 1147/5000 [10:12:19<31:17:33, 29.24s/it]
 23%|██▎       | 1148/5000 [10:12:47<30:53:55, 28.88s/it]
 23%|██▎       | 1149/5000 [10:13:14<30:16:44, 28.31s/it]
 23%|██▎       | 1150/5000 [10:13:42<30:15:19, 28.29s/it]
                                                         
 23%|██▎       | 1150/5000 [10:13:42<30:15:19, 28.29s/it]
 23%|██▎       | 1151/5000 [10:14:16<31:59:28, 29.92s/it]
 23%|██▎       | 1152/5000 [10:14:43<31:05:52, 29.09s/it]
 23%|██▎       | 1153/5000 [10:15:13<31:08:29, 29.14s/it]
 23%|██▎       | 1154/5000 [10:15:41<30:52:25, 28.90s/it]
 23%|██▎       | 1155/5000 [10:16:09<30:29:03, 28.54s/it]
 23%|██▎       | 1156/5000 [10:16:39<30:56:50, 28.98s/it]
 23%|██▎       | 1157/5000 [10:17:06<30:32:49, 28.62s/it]
 23%|██▎       | 1158/5000 [10:17:34<30:20:39, 28.43s/it]
 23%|██▎       | 1159/5000 [10:18:02<30:02:32, 28.16s/it]
 23%|██▎       | 1160/5000 [10:18:30<30:09:17, 28.27s/it]
 23%|██▎       | 1161/5000 [10:18:57<29:38:42, 27.80s/it]
 23%|██▎       | 1162/5000 [10:19:26<29:59:21, 28.13s/it]
 23%|██▎       | 1163/5000 [10:19:54<29:52:06, 28.02s/it]
 23%|██▎       | 1164/5000 [10:20:21<29:42:42, 27.88s/it]
 23%|██▎       | 1165/5000 [10:20:50<29:59:36, 28.16s/it]
 23%|██▎       | 1166/5000 [10:21:17<29:39:48, 27.85s/it]
 23%|██▎       | 1167/5000 [10:21:46<29:47:06, 27.97s/it]
 23%|██▎       | 1168/5000 [10:22:15<30:13:09, 28.39s/it]
 23%|██▎       | 1169/5000 [10:22:42<29:48:02, 28.00s/it]
 23%|██▎       | 1170/5000 [10:23:11<29:59:31, 28.19s/it]
 23%|██▎       | 1171/5000 [10:23:38<29:41:55, 27.92s/it]
 23%|██▎       | 1172/5000 [10:24:07<29:56:05, 28.15s/it]
 23%|██▎       | 1173/5000 [10:24:34<29:36:59, 27.86s/it]
 23%|██▎       | 1174/5000 [10:25:04<30:12:39, 28.43s/it]
 24%|██▎       | 1175/5000 [10:25:32<30:11:55, 28.42s/it]
                                                         
 24%|██▎       | 1175/5000 [10:25:32<30:11:55, 28.42s/it]
 24%|██▎       | 1176/5000 [10:26:00<30:07:35, 28.36s/it]
 24%|██▎       | 1177/5000 [10:26:29<30:11:09, 28.43s/it]
 24%|██▎       | 1178/5000 [10:26:57<30:01:53, 28.29s/it]
 24%|██▎       | 1179/5000 [10:27:25<29:58:55, 28.25s/it]
 24%|██▎       | 1180/5000 [10:27:55<30:24:32, 28.66s/it]
 24%|██▎       | 1181/5000 [10:28:22<29:55:23, 28.21s/it]
 24%|██▎       | 1182/5000 [10:28:50<29:54:08, 28.19s/it]
 24%|██▎       | 1183/5000 [10:29:17<29:30:38, 27.83s/it]
 24%|██▎       | 1184/5000 [10:29:45<29:41:18, 28.01s/it]
 24%|██▎       | 1185/5000 [10:30:12<29:21:47, 27.71s/it]
 24%|██▎       | 1186/5000 [10:30:41<29:41:45, 28.03s/it]
 24%|██▎       | 1187/5000 [10:31:08<29:16:01, 27.63s/it]
 24%|██▍       | 1188/5000 [10:31:35<29:16:48, 27.65s/it]
 24%|██▍       | 1189/5000 [10:32:05<29:45:25, 28.11s/it]
 24%|██▍       | 1190/5000 [10:32:31<29:18:47, 27.70s/it]
 24%|██▍       | 1191/5000 [10:33:00<29:29:28, 27.87s/it]
 24%|██▍       | 1192/5000 [10:33:27<29:13:02, 27.62s/it]
 24%|██▍       | 1193/5000 [10:33:55<29:26:26, 27.84s/it]
 24%|██▍       | 1194/5000 [10:34:23<29:29:45, 27.90s/it]
 24%|██▍       | 1195/5000 [10:34:51<29:20:20, 27.76s/it]
 24%|██▍       | 1196/5000 [10:35:20<30:02:10, 28.43s/it]
 24%|██▍       | 1197/5000 [10:35:48<29:37:08, 28.04s/it]
 24%|██▍       | 1198/5000 [10:36:16<29:38:26, 28.07s/it]
 24%|██▍       | 1199/5000 [10:36:43<29:16:57, 27.73s/it]
 24%|██▍       | 1200/5000 [10:37:12<29:47:54, 28.23s/it]
                                                         
 24%|██▍       | 1200/5000 [10:37:12<29:47:54, 28.23s/it]
 24%|██▍       | 1201/5000 [10:37:40<29:43:02, 28.16s/it]
 24%|██▍       | 1202/5000 [10:38:07<29:20:26, 27.81s/it]
 24%|██▍       | 1203/5000 [10:38:38<30:16:47, 28.71s/it]
 24%|██▍       | 1204/5000 [10:39:05<29:43:03, 28.18s/it]
 24%|██▍       | 1205/5000 [10:39:34<30:00:32, 28.47s/it]
 24%|██▍       | 1206/5000 [10:40:02<29:54:34, 28.38s/it]
 24%|██▍       | 1207/5000 [10:40:30<29:46:16, 28.26s/it]
 24%|██▍       | 1208/5000 [10:41:00<30:24:41, 28.87s/it]
 24%|██▍       | 1209/5000 [10:41:23<28:19:20, 26.90s/it]
 24%|██▍       | 1210/5000 [10:41:33<23:10:35, 22.01s/it]
 24%|██▍       | 1211/5000 [10:41:44<19:31:58, 18.56s/it]
 24%|██▍       | 1212/5000 [10:41:54<16:58:24, 16.13s/it]{'loss': 0.1262, 'learning_rate': 8.835555555555557e-06, 'epoch': 4.01}
+{'loss': 0.1261, 'learning_rate': 8.78e-06, 'epoch': 4.02}
+{'loss': 0.1084, 'learning_rate': 8.724444444444445e-06, 'epoch': 4.02}
+{'loss': 0.1237, 'learning_rate': 8.66888888888889e-06, 'epoch': 4.03}
+{'loss': 0.1078, 'learning_rate': 8.613333333333333e-06, 'epoch': 4.03}
+{'loss': 0.0952, 'learning_rate': 8.557777777777778e-06, 'epoch': 4.04}
+{'loss': 0.0921, 'learning_rate': 8.502222222222223e-06, 'epoch': 4.04}
+{'loss': 0.0994, 'learning_rate': 8.446666666666668e-06, 'epoch': 4.05}
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
 24%|██▍       | 1213/5000 [10:43:47<47:21:42, 45.02s/it]
 24%|██▍       | 1214/5000 [10:44:16<42:29:57, 40.41s/it]
 24%|██▍       | 1215/5000 [10:44:46<39:11:38, 37.28s/it]
 24%|██▍       | 1216/5000 [10:45:14<36:11:56, 34.44s/it]
 24%|██▍       | 1217/5000 [10:45:45<35:08:13, 33.44s/it]
 24%|██▍       | 1218/5000 [10:46:13<33:10:38, 31.58s/it]
 24%|██▍       | 1219/5000 [10:46:43<32:52:23, 31.30s/it]
 24%|██▍       | 1220/5000 [10:47:13<32:22:00, 30.83s/it]
 24%|██▍       | 1221/5000 [10:47:40<31:17:17, 29.81s/it]
 24%|██▍       | 1222/5000 [10:48:10<31:07:41, 29.66s/it]
 24%|██▍       | 1223/5000 [10:48:37<30:31:58, 29.10s/it]
 24%|██▍       | 1224/5000 [10:49:07<30:36:03, 29.17s/it]
 24%|██▍       | 1225/5000 [10:49:34<29:56:46, 28.56s/it]
                                                         
 24%|██▍       | 1225/5000 [10:49:34<29:56:46, 28.56s/it]
 25%|██▍       | 1226/5000 [10:50:06<30:57:00, 29.52s/it]
 25%|██▍       | 1227/5000 [10:50:33<30:12:54, 28.83s/it]
 25%|██▍       | 1228/5000 [10:51:03<30:34:53, 29.19s/it]
 25%|██▍       | 1229/5000 [10:51:31<30:12:18, 28.84s/it]
 25%|██▍       | 1230/5000 [10:52:00<30:21:47, 28.99s/it]
 25%|██▍       | 1231/5000 [10:52:32<31:13:06, 29.82s/it]
 25%|██▍       | 1232/5000 [10:52:59<30:11:05, 28.84s/it]
 25%|██▍       | 1233/5000 [10:53:29<30:33:24, 29.20s/it]
 25%|██▍       | 1234/5000 [10:53:57<30:09:09, 28.82s/it]
 25%|██▍       | 1235/5000 [10:54:26<30:27:55, 29.13s/it]
 25%|██▍       | 1236/5000 [10:54:54<29:56:16, 28.63s/it]
 25%|██▍       | 1237/5000 [10:55:24<30:29:39, 29.17s/it]
 25%|██▍       | 1238/5000 [10:55:54<30:43:45, 29.41s/it]
 25%|██▍       | 1239/5000 [10:56:22<30:16:04, 28.97s/it]
 25%|██▍       | 1240/5000 [10:56:52<30:34:52, 29.28s/it]
 25%|██▍       | 1241/5000 [10:57:20<30:13:53, 28.95s/it]
 25%|██▍       | 1242/5000 [10:57:51<30:45:26, 29.46s/it]
 25%|██▍       | 1243/5000 [10:58:18<30:03:56, 28.81s/it]
 25%|██▍       | 1244/5000 [10:58:50<30:48:27, 29.53s/it]
 25%|██▍       | 1245/5000 [10:59:20<30:59:20, 29.71s/it]
 25%|██▍       | 1246/5000 [10:59:48<30:33:14, 29.30s/it]
 25%|██▍       | 1247/5000 [11:00:18<30:45:28, 29.50s/it]
 25%|██▍       | 1248/5000 [11:00:45<30:03:40, 28.84s/it]
 25%|██▍       | 1249/5000 [11:01:16<30:35:12, 29.36s/it]
 25%|██▌       | 1250/5000 [11:01:43<29:58:55, 28.78s/it]
                                                         
 25%|██▌       | 1250/5000 [11:01:43<29:58:55, 28.78s/it]
 25%|██▌       | 1251/5000 [11:02:15<30:43:18, 29.50s/it]
 25%|██▌       | 1252/5000 [11:02:43<30:24:58, 29.22s/it]
 25%|██▌       | 1253/5000 [11:03:13<30:39:42, 29.46s/it]
 25%|██▌       | 1254/5000 [11:03:41<30:18:17, 29.12s/it]
 25%|██▌       | 1255/5000 [11:04:11<30:35:26, 29.41s/it]
 25%|██▌       | 1256/5000 [11:04:40<30:10:34, 29.02s/it]
 25%|██▌       | 1257/5000 [11:05:10<30:41:58, 29.53s/it]
 25%|██▌       | 1258/5000 [11:05:38<29:58:15, 28.83s/it]
 25%|██▌       | 1259/5000 [11:06:07<30:15:08, 29.11s/it]
 25%|██▌       | 1260/5000 [11:06:34<29:38:33, 28.53s/it]
 25%|██▌       | 1261/5000 [11:07:05<30:09:32, 29.04s/it]
 25%|██▌       | 1262/5000 [11:07:33<29:49:16, 28.72s/it]
 25%|██▌       | 1263/5000 [11:08:02<30:03:21, 28.95s/it]
 25%|██▌       | 1264/5000 [11:08:33<30:44:24, 29.62s/it]
 25%|██▌       | 1265/5000 [11:09:01<30:04:57, 29.00s/it]
 25%|██▌       | 1266/5000 [11:09:31<30:26:59, 29.36s/it]
 25%|██▌       | 1267/5000 [11:09:59<29:53:07, 28.82s/it]
 25%|██▌       | 1268/5000 [11:10:28<30:11:18, 29.12s/it]
 25%|██▌       | 1269/5000 [11:10:57<29:56:48, 28.90s/it]
 25%|██▌       | 1270/5000 [11:11:28<30:37:32, 29.56s/it]
 25%|██▌       | 1271/5000 [11:11:55<29:57:06, 28.92s/it]
 25%|██▌       | 1272/5000 [11:12:33<32:34:52, 31.46s/it]
 25%|██▌       | 1273/5000 [11:13:00<31:21:53, 30.30s/it]
 25%|██▌       | 1274/5000 [11:13:32<31:53:31, 30.81s/it]
 26%|██▌       | 1275/5000 [11:14:00<30:57:42, 29.92s/it]
                                                         
 26%|██▌       | 1275/5000 [11:14:00<30:57:42, 29.92s/it]
 26%|██▌       | 1276/5000 [11:14:30<31:01:39, 29.99s/it]
 26%|██▌       | 1277/5000 [11:14:59<30:35:14, 29.58s/it]
 26%|██▌       | 1278/5000 [11:15:30<30:54:05, 29.89s/it]
 26%|██▌       | 1279/5000 [11:15:59<30:52:32, 29.87s/it]
 26%|██▌       | 1280/5000 [11:16:29<30:48:56, 29.82s/it]
 26%|██▌       | 1281/5000 [11:16:57<30:16:49, 29.31s/it]
 26%|██▌       | 1282/5000 [11:17:27<30:32:25, 29.57s/it]
 26%|██▌       | 1283/5000 [11:17:57<30:28:53, 29.52s/it]
 26%|██▌       | 1284/5000 [11:18:25<30:00:59, 29.08s/it]
 26%|██▌       | 1285/5000 [11:18:55<30:12:39, 29.28s/it]
 26%|██▌       | 1286/5000 [11:19:22<29:40:18, 28.76s/it]
 26%|██▌       | 1287/5000 [11:19:52<29:54:58, 29.01s/it]
 26%|██▌       | 1288/5000 [11:20:20<29:39:55, 28.77s/it]
 26%|██▌       | 1289/5000 [11:20:51<30:18:41, 29.40s/it]
 26%|██▌       | 1290/5000 [11:21:18<29:37:19, 28.74s/it]
 26%|██▌       | 1291/5000 [11:21:55<31:59:59, 31.06s/it]
 26%|██▌       | 1292/5000 [11:22:23<31:07:54, 30.23s/it]
 26%|██▌       | 1293/5000 [11:22:55<31:35:18, 30.68s/it]
 26%|██▌       | 1294/5000 [11:23:24<31:14:42, 30.35s/it]
 26%|██▌       | 1295/5000 [11:24:01<33:07:29, 32.19s/it]
 26%|██▌       | 1296/5000 [11:24:29<31:52:33, 30.98s/it]
 26%|██▌       | 1297/5000 [11:25:00<31:51:34, 30.97s/it]
 26%|██▌       | 1298/5000 [11:25:27<30:39:43, 29.82s/it]
 26%|██▌       | 1299/5000 [11:25:56<30:36:10, 29.77s/it]
 26%|██▌       | 1300/5000 [11:26:24<29:52:50, 29.07s/it]
                                                         
 26%|██▌       | 1300/5000 [11:26:24<29:52:50, 29.07s/it]
 26%|██▌       | 1301/5000 [11:26:54<30:18:55, 29.50s/it]
 26%|██▌       | 1302/5000 [11:27:23<29:53:07, 29.09s/it]
 26%|██▌       | 1303/5000 [11:27:52<30:01:53, 29.24s/it]
 26%|██▌       | 1304/5000 [11:28:20<29:40:47, 28.91s/it]
 26%|██▌       | 1305/5000 [11:28:54<31:12:37, 30.41s/it]
 26%|██▌       | 1306/5000 [11:29:22<30:32:25, 29.76s/it]
 26%|██▌       | 1307/5000 [11:29:53<30:42:48, 29.94s/it]
 26%|██▌       | 1308/5000 [11:30:20<29:51:44, 29.12s/it]
 26%|██▌       | 1309/5000 [11:30:52<30:49:19, 30.06s/it]
 26%|██▌       | 1310/5000 [11:31:19<29:52:54, 29.15s/it]
 26%|██▌       | 1311/5000 [11:31:52<30:54:14, 30.16s/it]
 26%|██▌       | 1312/5000 [11:32:23<31:08:18, 30.40s/it]
 26%|██▋       | 1313/5000 [11:32:50<30:09:34, 29.45s/it]
 26%|██▋       | 1314/5000 [11:33:20<30:12:57, 29.51s/it]
 26%|██▋       | 1315/5000 [11:33:47<29:33:12, 28.87s/it]
 26%|██▋       | 1316/5000 [11:34:18<30:13:06, 29.53s/it]
 26%|██▋       | 1317/5000 [11:34:46<29:37:11, 28.95s/it]
 26%|██▋       | 1318/5000 [11:35:16<29:55:41, 29.26s/it]
 26%|██▋       | 1319/5000 [11:35:44<29:35:58, 28.95s/it]
 26%|██▋       | 1320/5000 [11:36:14<29:51:19, 29.21s/it]
 26%|██▋       | 1321/5000 [11:36:45<30:21:42, 29.71s/it]
 26%|██▋       | 1322/5000 [11:37:13<29:56:35, 29.31s/it]
 26%|██▋       | 1323/5000 [11:37:43<30:04:04, 29.44s/it]
 26%|██▋       | 1324/5000 [11:38:11<29:45:49, 29.15s/it]
 26%|██▋       | 1325/5000 [11:38:41<29:56:14, 29.33s/it]
                                                         
 26%|██▋       | 1325/5000 [11:38:41<29:56:14, 29.33s/it]
 27%|██▋       | 1326/5000 [11:39:09<29:31:26, 28.93s/it]
 27%|██▋       | 1327/5000 [11:39:40<30:09:20, 29.56s/it]
 27%|██▋       | 1328/5000 [11:40:09<30:06:38, 29.52s/it]
 27%|██▋       | 1329/5000 [11:40:38<29:56:53, 29.37s/it]
 27%|██▋       | 1330/5000 [11:41:06<29:15:14, 28.70s/it]
 27%|██▋       | 1331/5000 [11:41:37<29:57:26, 29.39s/it]
 27%|██▋       | 1332/5000 [11:42:05<29:34:11, 29.02s/it]
 27%|██▋       | 1333/5000 [11:42:35<29:53:12, 29.34s/it]
 27%|██▋       | 1334/5000 [11:43:04<29:59:20, 29.45s/it]
 27%|██▋       | 1335/5000 [11:43:31<29:13:21, 28.70s/it]
 27%|██▋       | 1336/5000 [11:44:01<29:33:04, 29.04s/it]
 27%|██▋       | 1337/5000 [11:44:29<29:17:06, 28.78s/it]
 27%|██▋       | 1338/5000 [11:44:59<29:32:37, 29.04s/it]
 27%|██▋       | 1339/5000 [11:45:28<29:20:06, 28.85s/it]
 27%|██▋       | 1340/5000 [11:45:58<29:46:54, 29.29s/it]
 27%|██▋       | 1341/5000 [11:46:26<29:24:01, 28.93s/it]
 27%|██▋       | 1342/5000 [11:46:56<29:41:07, 29.21s/it]
 27%|██▋       | 1343/5000 [11:47:23<29:07:18, 28.67s/it]
 27%|██▋       | 1344/5000 [11:47:54<29:46:03, 29.31s/it]
 27%|██▋       | 1345/5000 [11:48:23<29:37:08, 29.17s/it]
 27%|██▋       | 1346/5000 [11:48:52<29:43:21, 29.28s/it]
 27%|██▋       | 1347/5000 [11:49:21<29:23:16, 28.96s/it]
 27%|██▋       | 1348/5000 [11:49:50<29:29:58, 29.08s/it]
 27%|██▋       | 1349/5000 [11:50:21<29:59:29, 29.57s/it]
 27%|██▋       | 1350/5000 [11:50:51<30:10:19, 29.76s/it]
                                                         
 27%|██▋       | 1350/5000 [11:50:51<30:10:19, 29.76s/it]
 27%|██▋       | 1351/5000 [11:51:22<30:34:13, 30.16s/it]
 27%|██▋       | 1352/5000 [11:51:50<29:56:12, 29.54s/it]
 27%|██▋       | 1353/5000 [11:52:20<30:01:33, 29.64s/it]
 27%|██▋       | 1354/5000 [11:52:48<29:36:37, 29.24s/it]
 27%|██▋       | 1355/5000 [11:53:25<31:45:45, 31.37s/it]
 27%|██▋       | 1356/5000 [11:53:53<30:47:11, 30.41s/it]
 27%|██▋       | 1357/5000 [11:54:24<31:01:19, 30.66s/it]
 27%|██▋       | 1358/5000 [11:54:51<29:56:30, 29.60s/it]
 27%|██▋       | 1359/5000 [11:55:21<29:54:03, 29.56s/it]
 27%|██▋       | 1360/5000 [11:55:48<29:21:45, 29.04s/it]
 27%|██▋       | 1361/5000 [11:56:18<29:26:42, 29.13s/it]
 27%|██▋       | 1362/5000 [11:56:45<28:58:12, 28.67s/it]
 27%|██▋       | 1363/5000 [11:57:15<29:20:37, 29.05s/it]
 27%|██▋       | 1364/5000 [11:57:43<28:54:12, 28.62s/it]
 27%|██▋       | 1365/5000 [11:58:11<28:46:12, 28.49s/it]
 27%|██▋       | 1366/5000 [11:58:40<28:58:45, 28.71s/it]
 27%|██▋       | 1367/5000 [11:59:08<28:48:42, 28.55s/it]
 27%|██▋       | 1368/5000 [11:59:38<29:13:04, 28.96s/it]
 27%|██▋       | 1369/5000 [12:00:07<28:56:55, 28.70s/it]
 27%|██▋       | 1370/5000 [12:00:37<29:20:50, 29.10s/it]
 27%|██▋       | 1371/5000 [12:01:04<28:46:14, 28.54s/it]
 27%|██▋       | 1372/5000 [12:01:35<29:31:20, 29.29s/it]
 27%|██▋       | 1373/5000 [12:02:02<28:52:51, 28.67s/it]
 27%|██▋       | 1374/5000 [12:02:32<29:13:55, 29.02s/it]
 28%|██▊       | 1375/5000 [12:03:00<29:03:49, 28.86s/it]
                                                         
 28%|██▊       | 1375/5000 [12:03:00<29:03:49, 28.86s/it]
 28%|██▊       | 1376/5000 [12:03:30<29:17:05, 29.09s/it]
 28%|██▊       | 1377/5000 [12:03:57<28:43:43, 28.55s/it]
 28%|██▊       | 1378/5000 [12:04:26<28:45:04, 28.58s/it]
 28%|██▊       | 1379/5000 [12:04:57<29:30:41, 29.34s/it]
 28%|██▊       | 1380/5000 [12:05:25<28:57:03, 28.79s/it]
 28%|██▊       | 1381/5000 [12:05:54<29:06:37, 28.96s/it]
 28%|██▊       | 1382/5000 [12:06:21<28:34:04, 28.43s/it]
 28%|██▊       | 1383/5000 [12:06:51<29:03:37, 28.92s/it]
 28%|██▊       | 1384/5000 [12:07:19<28:37:02, 28.49s/it]
 28%|██▊       | 1385/5000 [12:07:50<29:19:44, 29.21s/it]
 28%|██▊       | 1386/5000 [12:08:17<28:42:50, 28.60s/it]
 28%|██▊       | 1387/5000 [12:08:47<29:12:18, 29.10s/it]
 28%|██▊       | 1388/5000 [12:09:17<29:34:34, 29.48s/it]
 28%|██▊       | 1389/5000 [12:09:45<29:09:21, 29.07s/it]
 28%|██▊       | 1390/5000 [12:10:15<29:15:45, 29.18s/it]
 28%|██▊       | 1391/5000 [12:10:41<28:25:10, 28.35s/it]
 28%|██▊       | 1392/5000 [12:11:13<29:32:01, 29.47s/it]
 28%|██▊       | 1393/5000 [12:11:40<28:48:09, 28.75s/it]
 28%|██▊       | 1394/5000 [12:12:10<29:06:59, 29.07s/it]
 28%|██▊       | 1395/5000 [12:12:40<29:17:19, 29.25s/it]
 28%|██▊       | 1396/5000 [12:13:07<28:40:51, 28.65s/it]
 28%|██▊       | 1397/5000 [12:13:35<28:30:57, 28.49s/it]
 28%|██▊       | 1398/5000 [12:14:05<28:53:32, 28.88s/it]
 28%|██▊       | 1399/5000 [12:14:34<28:48:51, 28.81s/it]
 28%|██▊       | 1400/5000 [12:15:04<29:12:43, 29.21s/it]
                                                         
 28%|██▊       | 1400/5000 [12:15:04<29:12:43, 29.21s/it]
 28%|██▊       | 1401/5000 [12:15:32<28:53:52, 28.91s/it]
 28%|██▊       | 1402/5000 [12:16:09<31:16:18, 31.29s/it]
 28%|██▊       | 1403/5000 [12:16:37<30:10:29, 30.20s/it]
 28%|██▊       | 1404/5000 [12:17:07<30:08:30, 30.18s/it]
 28%|██▊       | 1405/5000 [12:17:34<29:16:52, 29.32s/it]
 28%|██▊       | 1406/5000 [12:18:02<28:53:49, 28.95s/it]
 28%|██▊       | 1407/5000 [12:18:34<29:41:20, 29.75s/it]
 28%|██▊       | 1408/5000 [12:19:01<28:52:39, 28.94s/it]
 28%|██▊       | 1409/5000 [12:19:31<29:17:49, 29.37s/it]
 28%|██▊       | 1410/5000 [12:20:07<31:12:06, 31.29s/it]
 28%|██▊       | 1411/5000 [12:20:35<30:17:30, 30.38s/it]
 28%|██▊       | 1412/5000 [12:21:06<30:27:16, 30.56s/it]
 28%|██▊       | 1413/5000 [12:21:34<29:31:35, 29.63s/it]
 28%|██▊       | 1414/5000 [12:22:05<30:05:30, 30.21s/it]
 28%|██▊       | 1415/5000 [12:22:32<29:11:18, 29.31s/it]
 28%|██▊       | 1416/5000 [12:23:03<29:36:20, 29.74s/it]
 28%|██▊       | 1417/5000 [12:23:30<28:37:36, 28.76s/it]
 28%|██▊       | 1418/5000 [12:24:02<29:34:39, 29.73s/it]
 28%|██▊       | 1419/5000 [12:24:30<29:11:10, 29.34s/it]
 28%|██▊       | 1420/5000 [12:25:00<29:20:38, 29.51s/it]
 28%|██▊       | 1421/5000 [12:25:28<28:50:57, 29.02s/it]
 28%|██▊       | 1422/5000 [12:25:58<29:06:47, 29.29s/it]
 28%|██▊       | 1423/5000 [12:26:26<28:49:29, 29.01s/it]
 28%|██▊       | 1424/5000 [12:26:58<29:36:49, 29.81s/it]
 28%|██▊       | 1425/5000 [12:27:26<29:14:04, 29.44s/it]
                                                         
 28%|██▊       | 1425/5000 [12:27:26<29:14:04, 29.44s/it]
 29%|██▊       | 1426/5000 [12:27:56<29:24:35, 29.62s/it]
 29%|██▊       | 1427/5000 [12:28:26<29:27:08, 29.68s/it]
 29%|██▊       | 1428/5000 [12:28:56<29:25:18, 29.65s/it]
 29%|██▊       | 1429/5000 [12:29:23<28:44:45, 28.98s/it]
 29%|██▊       | 1430/5000 [12:29:53<28:56:47, 29.19s/it]
 29%|██▊       | 1431/5000 [12:30:20<28:20:11, 28.58s/it]
 29%|██▊       | 1432/5000 [12:30:51<29:01:55, 29.29s/it]
 29%|██▊       | 1433/5000 [12:31:21<29:10:23, 29.44s/it]
 29%|██▊       | 1434/5000 [12:31:49<28:42:47, 28.99s/it]
 29%|██▊       | 1435/5000 [12:32:20<29:20:46, 29.63s/it]
 29%|██▊       | 1436/5000 [12:32:47<28:38:08, 28.92s/it]
 29%|██▊       | 1437/5000 [12:33:23<30:36:15, 30.92s/it]
 29%|██▉       | 1438/5000 [12:33:53<30:24:06, 30.73s/it]
 29%|██▉       | 1439/5000 [12:34:21<29:28:12, 29.79s/it]
 29%|██▉       | 1440/5000 [12:34:49<28:55:38, 29.25s/it]
 29%|██▉       | 1441/5000 [12:35:17<28:44:12, 29.07s/it]
 29%|██▉       | 1442/5000 [12:35:47<28:52:34, 29.22s/it]
 29%|██▉       | 1443/5000 [12:36:14<28:16:40, 28.62s/it]
 29%|██▉       | 1444/5000 [12:36:45<28:53:06, 29.24s/it]
 29%|██▉       | 1445/5000 [12:37:15<29:06:27, 29.48s/it]
 29%|██▉       | 1446/5000 [12:37:43<28:40:25, 29.05s/it]
 29%|██▉       | 1447/5000 [12:38:14<29:24:27, 29.80s/it]
 29%|██▉       | 1448/5000 [12:38:42<28:39:08, 29.04s/it]
 29%|██▉       | 1449/5000 [12:39:11<28:48:24, 29.20s/it]
 29%|██▉       | 1450/5000 [12:39:38<28:05:33, 28.49s/it]
                                                         
 29%|██▉       | 1450/5000 [12:39:38<28:05:33, 28.49s/it]
 29%|██▉       | 1451/5000 [12:40:08<28:38:09, 29.05s/it]
 29%|██▉       | 1452/5000 [12:40:20<23:36:38, 23.96s/it]
 29%|██▉       | 1453/5000 [12:40:31<19:40:18, 19.97s/it]
 29%|██▉       | 1454/5000 [12:40:42<16:51:57, 17.12s/it]
 29%|██▉       | 1455/5000 [12:40:52<14:54:16, 15.14s/it]{'loss': 0.125, 'learning_rate': 8.391111111111112e-06, 'epoch': 5.0}
+{'loss': 0.1309, 'learning_rate': 8.335555555555556e-06, 'epoch': 5.01}
+{'loss': 0.1241, 'learning_rate': 8.28e-06, 'epoch': 5.01}
+{'loss': 0.1299, 'learning_rate': 8.224444444444444e-06, 'epoch': 5.02}
+{'loss': 0.1249, 'learning_rate': 8.16888888888889e-06, 'epoch': 5.02}
+{'loss': 0.1199, 'learning_rate': 8.113333333333334e-06, 'epoch': 5.03}
+{'loss': 0.1405, 'learning_rate': 8.057777777777778e-06, 'epoch': 5.03}
+{'loss': 0.1291, 'learning_rate': 8.002222222222222e-06, 'epoch': 5.04}
+{'loss': 0.1359, 'learning_rate': 7.946666666666666e-06, 'epoch': 5.04}
+{'loss': 0.1306, 'learning_rate': 7.891111111111112e-06, 'epoch': 5.05}
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
 29%|██▉       | 1456/5000 [12:42:51<45:29:33, 46.21s/it]
 29%|██▉       | 1457/5000 [12:43:19<40:05:43, 40.74s/it]
 29%|██▉       | 1458/5000 [12:43:50<37:17:53, 37.91s/it]
 29%|██▉       | 1459/5000 [12:44:17<34:03:03, 34.62s/it]
 29%|██▉       | 1460/5000 [12:44:47<32:41:56, 33.25s/it]
 29%|██▉       | 1461/5000 [12:45:14<30:49:38, 31.36s/it]
 29%|██▉       | 1462/5000 [12:45:42<29:57:01, 30.48s/it]
 29%|██▉       | 1463/5000 [12:46:13<29:57:30, 30.49s/it]
 29%|██▉       | 1464/5000 [12:46:40<28:53:50, 29.42s/it]
 29%|██▉       | 1465/5000 [12:47:10<29:04:17, 29.61s/it]
 29%|██▉       | 1466/5000 [12:47:36<28:06:06, 28.63s/it]
 29%|██▉       | 1467/5000 [12:48:07<28:35:01, 29.13s/it]
 29%|██▉       | 1468/5000 [12:48:35<28:22:16, 28.92s/it]
 29%|██▉       | 1469/5000 [12:49:05<28:43:10, 29.28s/it]
 29%|██▉       | 1470/5000 [12:49:33<28:20:46, 28.91s/it]
 29%|██▉       | 1471/5000 [12:50:04<28:47:15, 29.37s/it]
 29%|██▉       | 1472/5000 [12:50:32<28:22:51, 28.96s/it]
 29%|██▉       | 1473/5000 [12:51:04<29:14:59, 29.86s/it]
 29%|██▉       | 1474/5000 [12:51:31<28:26:53, 29.05s/it]
 30%|██▉       | 1475/5000 [12:51:59<28:05:07, 28.68s/it]
                                                         
 30%|██▉       | 1475/5000 [12:51:59<28:05:07, 28.68s/it]
 30%|██▉       | 1476/5000 [12:52:31<29:09:09, 29.78s/it]
 30%|██▉       | 1477/5000 [12:52:59<28:40:21, 29.30s/it]
 30%|██▉       | 1478/5000 [12:53:37<31:08:37, 31.83s/it]
 30%|██▉       | 1479/5000 [12:54:04<29:45:47, 30.43s/it]
 30%|██▉       | 1480/5000 [12:54:34<29:30:29, 30.18s/it]
 30%|██▉       | 1481/5000 [12:55:01<28:37:14, 29.28s/it]
 30%|██▉       | 1482/5000 [12:55:29<28:21:15, 29.02s/it]
 30%|██▉       | 1483/5000 [12:55:59<28:36:13, 29.28s/it]
 30%|██▉       | 1484/5000 [12:56:25<27:45:07, 28.42s/it]
 30%|██▉       | 1485/5000 [12:57:02<30:10:50, 30.91s/it]
 30%|██▉       | 1486/5000 [12:57:29<29:04:27, 29.79s/it]
 30%|██▉       | 1487/5000 [12:58:01<29:37:57, 30.37s/it]
 30%|██▉       | 1488/5000 [12:58:29<28:54:27, 29.63s/it]
 30%|██▉       | 1489/5000 [12:58:57<28:32:15, 29.26s/it]
 30%|██▉       | 1490/5000 [12:59:25<27:59:09, 28.70s/it]
 30%|██▉       | 1491/5000 [12:59:52<27:28:44, 28.19s/it]
 30%|██▉       | 1492/5000 [13:00:23<28:26:23, 29.19s/it]
 30%|██▉       | 1493/5000 [13:00:51<28:06:45, 28.86s/it]
 30%|██▉       | 1494/5000 [13:01:22<28:43:43, 29.50s/it]
 30%|██▉       | 1495/5000 [13:01:50<28:12:36, 28.97s/it]
 30%|██▉       | 1496/5000 [13:02:22<28:54:58, 29.71s/it]
 30%|██▉       | 1497/5000 [13:02:48<28:05:18, 28.87s/it]
 30%|██▉       | 1498/5000 [13:03:17<27:53:11, 28.67s/it]
 30%|██▉       | 1499/5000 [13:03:47<28:14:46, 29.05s/it]
 30%|███       | 1500/5000 [13:04:14<27:52:11, 28.67s/it]
                                                         
 30%|███       | 1500/5000 [13:04:14<27:52:11, 28.67s/it]
 30%|███       | 1501/5000 [13:04:45<28:32:09, 29.36s/it]
 30%|███       | 1502/5000 [13:05:12<27:51:10, 28.66s/it]
 30%|███       | 1503/5000 [13:05:43<28:33:17, 29.40s/it]
 30%|███       | 1504/5000 [13:06:11<27:56:37, 28.78s/it]
 30%|███       | 1505/5000 [13:06:42<28:37:46, 29.49s/it]
 30%|███       | 1506/5000 [13:07:10<28:12:37, 29.07s/it]
 30%|███       | 1507/5000 [13:07:37<27:42:54, 28.56s/it]
 30%|███       | 1508/5000 [13:08:08<28:22:58, 29.26s/it]
 30%|███       | 1509/5000 [13:08:36<27:47:34, 28.66s/it]
 30%|███       | 1510/5000 [13:09:06<28:16:45, 29.17s/it]
 30%|███       | 1511/5000 [13:09:34<28:03:18, 28.95s/it]
 30%|███       | 1512/5000 [13:10:05<28:23:54, 29.31s/it]
 30%|███       | 1513/5000 [13:10:33<28:05:51, 29.01s/it]
 30%|███       | 1514/5000 [13:11:03<28:25:50, 29.36s/it]
 30%|███       | 1515/5000 [13:11:31<28:03:22, 28.98s/it]
 30%|███       | 1516/5000 [13:11:59<27:35:53, 28.52s/it]
 30%|███       | 1517/5000 [13:12:28<27:56:20, 28.88s/it]
 30%|███       | 1518/5000 [13:12:57<28:00:31, 28.96s/it]
 30%|███       | 1519/5000 [13:13:27<28:20:06, 29.30s/it]
 30%|███       | 1520/5000 [13:13:56<27:57:58, 28.93s/it]
 30%|███       | 1521/5000 [13:14:26<28:23:28, 29.38s/it]
 30%|███       | 1522/5000 [13:14:56<28:35:27, 29.59s/it]
 30%|███       | 1523/5000 [13:15:24<28:07:36, 29.12s/it]
 30%|███       | 1524/5000 [13:15:55<28:31:59, 29.55s/it]
 30%|███       | 1525/5000 [13:16:23<28:06:45, 29.12s/it]
                                                         
 30%|███       | 1525/5000 [13:16:23<28:06:45, 29.12s/it]
 31%|███       | 1526/5000 [13:16:53<28:26:37, 29.48s/it]
 31%|███       | 1527/5000 [13:17:23<28:37:37, 29.67s/it]
 31%|███       | 1528/5000 [13:17:51<28:06:14, 29.14s/it]
 31%|███       | 1529/5000 [13:18:21<28:10:20, 29.22s/it]
 31%|███       | 1530/5000 [13:18:49<28:02:22, 29.09s/it]
 31%|███       | 1531/5000 [13:19:24<29:40:09, 30.79s/it]
 31%|███       | 1532/5000 [13:19:55<29:37:30, 30.75s/it]
 31%|███       | 1533/5000 [13:20:23<28:50:26, 29.95s/it]
 31%|███       | 1534/5000 [13:20:53<28:49:29, 29.94s/it]
 31%|███       | 1535/5000 [13:21:22<28:30:39, 29.62s/it]
 31%|███       | 1536/5000 [13:21:51<28:29:09, 29.60s/it]
 31%|███       | 1537/5000 [13:22:19<28:03:50, 29.17s/it]
 31%|███       | 1538/5000 [13:22:50<28:34:58, 29.72s/it]
 31%|███       | 1539/5000 [13:23:17<27:44:59, 28.86s/it]
 31%|███       | 1540/5000 [13:23:48<28:16:25, 29.42s/it]
 31%|███       | 1541/5000 [13:24:17<28:18:35, 29.46s/it]
 31%|███       | 1542/5000 [13:24:44<27:34:49, 28.71s/it]
 31%|███       | 1543/5000 [13:25:14<27:53:37, 29.05s/it]
 31%|███       | 1544/5000 [13:25:41<27:18:50, 28.45s/it]
 31%|███       | 1545/5000 [13:26:12<27:50:00, 29.00s/it]
 31%|███       | 1546/5000 [13:26:39<27:16:09, 28.42s/it]
 31%|███       | 1547/5000 [13:27:09<27:52:25, 29.06s/it]
 31%|███       | 1548/5000 [13:27:37<27:37:58, 28.82s/it]
 31%|███       | 1549/5000 [13:28:12<29:23:48, 30.67s/it]
 31%|███       | 1550/5000 [13:28:41<28:46:01, 30.02s/it]
                                                         
 31%|███       | 1550/5000 [13:28:41<28:46:01, 30.02s/it]
 31%|███       | 1551/5000 [13:29:10<28:36:18, 29.86s/it]
 31%|███       | 1552/5000 [13:29:41<28:42:43, 29.98s/it]
 31%|███       | 1553/5000 [13:30:09<28:08:29, 29.39s/it]
 31%|███       | 1554/5000 [13:30:38<28:09:31, 29.42s/it]
 31%|███       | 1555/5000 [13:31:06<27:39:22, 28.90s/it]
 31%|███       | 1556/5000 [13:31:35<27:48:32, 29.07s/it]
 31%|███       | 1557/5000 [13:32:03<27:25:24, 28.67s/it]
 31%|███       | 1558/5000 [13:32:34<27:57:23, 29.24s/it]
 31%|███       | 1559/5000 [13:33:01<27:22:29, 28.64s/it]
 31%|███       | 1560/5000 [13:33:32<28:00:41, 29.31s/it]
 31%|███       | 1561/5000 [13:34:01<27:50:32, 29.15s/it]
 31%|███       | 1562/5000 [13:34:29<27:42:44, 29.02s/it]
 31%|███▏      | 1563/5000 [13:34:58<27:31:12, 28.83s/it]
 31%|███▏      | 1564/5000 [13:35:28<27:56:31, 29.28s/it]
 31%|███▏      | 1565/5000 [13:35:58<28:07:32, 29.48s/it]
 31%|███▏      | 1566/5000 [13:36:25<27:24:18, 28.73s/it]
 31%|███▏      | 1567/5000 [13:36:56<27:59:24, 29.35s/it]
 31%|███▏      | 1568/5000 [13:37:24<27:36:28, 28.96s/it]
 31%|███▏      | 1569/5000 [13:37:54<27:50:25, 29.21s/it]
 31%|███▏      | 1570/5000 [13:38:21<27:27:54, 28.83s/it]
 31%|███▏      | 1571/5000 [13:38:53<28:08:47, 29.55s/it]
 31%|███▏      | 1572/5000 [13:39:22<28:07:05, 29.53s/it]
 31%|███▏      | 1573/5000 [13:39:51<27:56:24, 29.35s/it]
 31%|███▏      | 1574/5000 [13:40:21<28:01:26, 29.45s/it]
 32%|███▏      | 1575/5000 [13:40:49<27:37:42, 29.04s/it]
                                                         
 32%|███▏      | 1575/5000 [13:40:49<27:37:42, 29.04s/it]
 32%|███▏      | 1576/5000 [13:41:19<27:55:28, 29.36s/it]
 32%|███▏      | 1577/5000 [13:41:46<27:19:27, 28.74s/it]
 32%|███▏      | 1578/5000 [13:42:16<27:43:37, 29.17s/it]
 32%|███▏      | 1579/5000 [13:42:44<27:09:31, 28.58s/it]
 32%|███▏      | 1580/5000 [13:43:15<27:52:14, 29.34s/it]
 32%|███▏      | 1581/5000 [13:43:44<27:56:43, 29.42s/it]
 32%|███▏      | 1582/5000 [13:44:13<27:50:16, 29.32s/it]
 32%|███▏      | 1583/5000 [13:44:43<27:57:35, 29.46s/it]
 32%|███▏      | 1584/5000 [13:45:13<27:53:49, 29.40s/it]
 32%|███▏      | 1585/5000 [13:45:40<27:26:47, 28.93s/it]
 32%|███▏      | 1586/5000 [13:46:12<28:20:56, 29.89s/it]
 32%|███▏      | 1587/5000 [13:46:48<30:03:40, 31.71s/it]
 32%|███▏      | 1588/5000 [13:47:17<29:08:57, 30.76s/it]
 32%|███▏      | 1589/5000 [13:47:47<29:01:41, 30.64s/it]
 32%|███▏      | 1590/5000 [13:48:15<28:15:37, 29.84s/it]
 32%|███▏      | 1591/5000 [13:48:45<28:19:49, 29.92s/it]
 32%|███▏      | 1592/5000 [13:49:13<27:31:28, 29.08s/it]
 32%|███▏      | 1593/5000 [13:49:43<27:59:23, 29.58s/it]
 32%|███▏      | 1594/5000 [13:50:11<27:22:09, 28.93s/it]
 32%|███▏      | 1595/5000 [13:50:41<27:48:33, 29.40s/it]
 32%|███▏      | 1596/5000 [13:51:10<27:36:56, 29.21s/it]
 32%|███▏      | 1597/5000 [13:51:46<29:37:28, 31.34s/it]
 32%|███▏      | 1598/5000 [13:52:15<28:46:37, 30.45s/it]
 32%|███▏      | 1599/5000 [13:52:44<28:31:27, 30.19s/it]
 32%|███▏      | 1600/5000 [13:53:15<28:38:52, 30.33s/it]
                                                         
 32%|███▏      | 1600/5000 [13:53:15<28:38:52, 30.33s/it]
 32%|███▏      | 1601/5000 [13:53:43<28:03:42, 29.72s/it]
 32%|███▏      | 1602/5000 [13:54:13<28:07:04, 29.79s/it]
 32%|███▏      | 1603/5000 [13:54:41<27:36:55, 29.27s/it]
 32%|███▏      | 1604/5000 [13:55:14<28:40:58, 30.41s/it]
 32%|███▏      | 1605/5000 [13:55:43<28:06:53, 29.81s/it]
 32%|███▏      | 1606/5000 [13:56:20<30:13:09, 32.05s/it]
 32%|███▏      | 1607/5000 [13:56:47<28:54:03, 30.66s/it]
 32%|███▏      | 1608/5000 [13:57:18<28:48:22, 30.57s/it]
 32%|███▏      | 1609/5000 [13:57:46<28:13:36, 29.97s/it]
 32%|███▏      | 1610/5000 [13:58:16<28:07:26, 29.87s/it]
 32%|███▏      | 1611/5000 [13:58:46<28:14:32, 30.00s/it]
 32%|███▏      | 1612/5000 [13:59:13<27:26:12, 29.15s/it]
 32%|███▏      | 1613/5000 [13:59:45<28:02:40, 29.81s/it]
 32%|███▏      | 1614/5000 [14:00:13<27:38:58, 29.40s/it]
 32%|███▏      | 1615/5000 [14:00:43<27:46:37, 29.54s/it]
 32%|███▏      | 1616/5000 [14:01:11<27:16:57, 29.02s/it]
 32%|███▏      | 1617/5000 [14:01:40<27:22:12, 29.13s/it]
 32%|███▏      | 1618/5000 [14:02:10<27:35:40, 29.37s/it]
 32%|███▏      | 1619/5000 [14:02:38<27:13:03, 28.98s/it]
 32%|███▏      | 1620/5000 [14:03:10<27:51:10, 29.67s/it]
 32%|███▏      | 1621/5000 [14:03:37<27:18:02, 29.09s/it]
 32%|███▏      | 1622/5000 [14:04:06<27:19:01, 29.11s/it]
 32%|███▏      | 1623/5000 [14:04:35<27:01:39, 28.81s/it]
 32%|███▏      | 1624/5000 [14:05:04<27:12:58, 29.02s/it]
 32%|███▎      | 1625/5000 [14:05:32<26:57:46, 28.76s/it]
                                                         
 32%|███▎      | 1625/5000 [14:05:32<26:57:46, 28.76s/it]
 33%|███▎      | 1626/5000 [14:06:03<27:30:51, 29.36s/it]
 33%|███▎      | 1627/5000 [14:06:29<26:41:03, 28.48s/it]
 33%|███▎      | 1628/5000 [14:06:59<26:57:17, 28.78s/it]
 33%|███▎      | 1629/5000 [14:07:26<26:31:08, 28.32s/it]
 33%|███▎      | 1630/5000 [14:07:57<27:15:22, 29.12s/it]
 33%|███▎      | 1631/5000 [14:08:25<27:01:48, 28.88s/it]
 33%|███▎      | 1632/5000 [14:08:55<27:18:31, 29.19s/it]
 33%|███▎      | 1633/5000 [14:09:25<27:24:23, 29.30s/it]
 33%|███▎      | 1634/5000 [14:09:55<27:35:35, 29.51s/it]
 33%|███▎      | 1635/5000 [14:10:26<27:59:10, 29.94s/it]
 33%|███▎      | 1636/5000 [14:10:54<27:30:44, 29.44s/it]
 33%|███▎      | 1637/5000 [14:11:24<27:38:18, 29.59s/it]
 33%|███▎      | 1638/5000 [14:11:52<27:11:14, 29.11s/it]
 33%|███▎      | 1639/5000 [14:12:22<27:25:27, 29.37s/it]
 33%|███▎      | 1640/5000 [14:12:50<26:59:40, 28.92s/it]
 33%|███▎      | 1641/5000 [14:13:20<27:26:34, 29.41s/it]
 33%|███▎      | 1642/5000 [14:13:48<26:48:15, 28.74s/it]
 33%|███▎      | 1643/5000 [14:14:18<27:19:34, 29.30s/it]
 33%|███▎      | 1644/5000 [14:14:45<26:44:41, 28.69s/it]
 33%|███▎      | 1645/5000 [14:15:23<29:10:53, 31.31s/it]
 33%|███▎      | 1646/5000 [14:15:50<28:01:55, 30.09s/it]
 33%|███▎      | 1647/5000 [14:16:21<28:10:59, 30.26s/it]
 33%|███▎      | 1648/5000 [14:16:49<27:31:52, 29.57s/it]
 33%|███▎      | 1649/5000 [14:17:21<28:17:23, 30.39s/it]
 33%|███▎      | 1650/5000 [14:17:49<27:35:28, 29.65s/it]
                                                         
 33%|███▎      | 1650/5000 [14:17:49<27:35:28, 29.65s/it]
 33%|███▎      | 1651/5000 [14:18:19<27:39:32, 29.73s/it]
 33%|███▎      | 1652/5000 [14:18:47<27:07:02, 29.16s/it]
 33%|███▎      | 1653/5000 [14:19:18<27:43:59, 29.83s/it]
 33%|███▎      | 1654/5000 [14:19:45<27:01:39, 29.08s/it]
 33%|███▎      | 1655/5000 [14:20:16<27:29:29, 29.59s/it]
 33%|███▎      | 1656/5000 [14:20:44<26:50:17, 28.89s/it]
 33%|███▎      | 1657/5000 [14:21:15<27:27:37, 29.57s/it]
 33%|███▎      | 1658/5000 [14:21:42<26:46:42, 28.85s/it]
 33%|███▎      | 1659/5000 [14:22:12<27:15:06, 29.36s/it]
 33%|███▎      | 1660/5000 [14:22:41<26:55:09, 29.01s/it]
 33%|███▎      | 1661/5000 [14:23:10<27:06:17, 29.22s/it]
 33%|███▎      | 1662/5000 [14:23:39<26:54:03, 29.01s/it]
 33%|███▎      | 1663/5000 [14:24:08<27:01:16, 29.15s/it]
 33%|███▎      | 1664/5000 [14:24:37<26:49:00, 28.94s/it]
 33%|███▎      | 1665/5000 [14:25:08<27:20:58, 29.52s/it]
 33%|███▎      | 1666/5000 [14:25:35<26:42:53, 28.85s/it]
 33%|███▎      | 1667/5000 [14:26:06<27:16:58, 29.47s/it]
 33%|███▎      | 1668/5000 [14:26:33<26:43:12, 28.87s/it]
 33%|███▎      | 1669/5000 [14:27:04<27:15:17, 29.46s/it]
 33%|███▎      | 1670/5000 [14:27:32<26:40:50, 28.84s/it]
 33%|███▎      | 1671/5000 [14:28:04<27:40:33, 29.93s/it]
 33%|███▎      | 1672/5000 [14:28:31<26:57:50, 29.17s/it]
 33%|███▎      | 1673/5000 [14:29:01<27:07:50, 29.36s/it]
 33%|███▎      | 1674/5000 [14:29:30<26:52:46, 29.09s/it]
 34%|███▎      | 1675/5000 [14:29:59<27:04:36, 29.32s/it]
                                                         
 34%|███▎      | 1675/5000 [14:29:59<27:04:36, 29.32s/it]
 34%|███▎      | 1676/5000 [14:30:31<27:35:42, 29.89s/it]
 34%|███▎      | 1677/5000 [14:30:58<26:49:12, 29.06s/it]
 34%|███▎      | 1678/5000 [14:31:28<27:09:04, 29.42s/it]
 34%|███▎      | 1679/5000 [14:31:56<26:46:46, 29.03s/it]
 34%|███▎      | 1680/5000 [14:32:24<26:32:17, 28.78s/it]
 34%|███▎      | 1681/5000 [14:32:53<26:22:22, 28.61s/it]
 34%|███▎      | 1682/5000 [14:33:23<26:45:49, 29.04s/it]
 34%|███▎      | 1683/5000 [14:33:50<26:24:37, 28.66s/it]
 34%|███▎      | 1684/5000 [14:34:26<28:22:55, 30.81s/it]
 34%|███▎      | 1685/5000 [14:34:55<27:44:35, 30.13s/it]
 34%|███▎      | 1686/5000 [14:35:27<28:14:51, 30.69s/it]
 34%|███▎      | 1687/5000 [14:35:54<27:19:14, 29.69s/it]
 34%|███▍      | 1688/5000 [14:36:25<27:35:42, 29.99s/it]
 34%|███▍      | 1689/5000 [14:36:52<26:44:09, 29.07s/it]
 34%|███▍      | 1690/5000 [14:37:22<27:05:49, 29.47s/it]
 34%|███▍      | 1691/5000 [14:37:49<26:22:53, 28.70s/it]
 34%|███▍      | 1692/5000 [14:38:19<26:37:37, 28.98s/it]
 34%|███▍      | 1693/5000 [14:38:49<27:01:40, 29.42s/it]
 34%|███▍      | 1694/5000 [14:39:10<24:34:24, 26.76s/it]
 34%|███▍      | 1695/5000 [14:39:20<20:05:02, 21.88s/it]
 34%|███▍      | 1696/5000 [14:39:31<16:56:42, 18.46s/it]
 34%|███▍      | 1697/5000 [14:39:41<14:46:59, 16.11s/it]{'loss': 0.19, 'learning_rate': 7.835555555555556e-06, 'epoch': 6.0}
+{'loss': 0.2177, 'learning_rate': 7.78e-06, 'epoch': 6.01}
+{'loss': 0.1542, 'learning_rate': 7.724444444444446e-06, 'epoch': 6.01}
+{'loss': 0.0816, 'learning_rate': 7.66888888888889e-06, 'epoch': 6.02}
+{'loss': 0.0775, 'learning_rate': 7.613333333333334e-06, 'epoch': 6.02}
+{'loss': 0.0816, 'learning_rate': 7.557777777777779e-06, 'epoch': 6.03}
+{'loss': 0.0829, 'learning_rate': 7.502222222222223e-06, 'epoch': 6.03}
+{'loss': 0.0837, 'learning_rate': 7.446666666666668e-06, 'epoch': 6.04}
+{'loss': 0.0863, 'learning_rate': 7.3911111111111125e-06, 'epoch': 6.04}
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
 34%|███▍      | 1698/5000 [14:41:21<37:45:45, 41.17s/it]
 34%|███▍      | 1699/5000 [14:41:50<34:31:48, 37.66s/it]
 34%|███▍      | 1700/5000 [14:42:18<31:39:14, 34.53s/it]
                                                         
 34%|███▍      | 1700/5000 [14:42:18<31:39:14, 34.53s/it]
 34%|███▍      | 1701/5000 [14:42:46<30:02:40, 32.79s/it]
 34%|███▍      | 1702/5000 [14:43:15<28:46:01, 31.40s/it]
 34%|███▍      | 1703/5000 [14:43:42<27:40:38, 30.22s/it]
 34%|███▍      | 1704/5000 [14:44:10<27:07:31, 29.63s/it]
 34%|███▍      | 1705/5000 [14:44:40<27:11:28, 29.71s/it]
 34%|███▍      | 1706/5000 [14:45:08<26:45:34, 29.25s/it]
 34%|███▍      | 1707/5000 [14:45:35<26:07:57, 28.57s/it]
 34%|███▍      | 1708/5000 [14:46:04<26:16:42, 28.74s/it]
 34%|█��█▍      | 1709/5000 [14:46:34<26:22:17, 28.85s/it]
 34%|███▍      | 1710/5000 [14:47:01<25:57:18, 28.40s/it]
 34%|███▍      | 1711/5000 [14:47:29<25:57:18, 28.41s/it]
 34%|███▍      | 1712/5000 [14:47:58<25:53:55, 28.36s/it]
 34%|███▍      | 1713/5000 [14:48:26<25:51:03, 28.31s/it]
 34%|███▍      | 1714/5000 [14:48:57<26:34:29, 29.11s/it]
 34%|███▍      | 1715/5000 [14:49:24<26:02:29, 28.54s/it]
 34%|███▍      | 1716/5000 [14:49:53<26:14:58, 28.78s/it]
 34%|███▍      | 1717/5000 [14:50:22<26:21:00, 28.89s/it]
 34%|███▍      | 1718/5000 [14:50:51<26:09:39, 28.70s/it]
 34%|███▍      | 1719/5000 [14:51:20<26:19:24, 28.88s/it]
 34%|███▍      | 1720/5000 [14:51:47<25:54:43, 28.44s/it]
 34%|███▍      | 1721/5000 [14:52:16<25:54:13, 28.44s/it]
 34%|███▍      | 1722/5000 [14:52:44<25:52:38, 28.42s/it]
 34%|███▍      | 1723/5000 [14:53:19<27:35:00, 30.30s/it]
 34%|███▍      | 1724/5000 [14:53:46<26:46:59, 29.43s/it]
 34%|███▍      | 1725/5000 [14:54:15<26:30:49, 29.14s/it]
                                                         
 34%|███▍      | 1725/5000 [14:54:15<26:30:49, 29.14s/it]
 35%|███▍      | 1726/5000 [14:54:44<26:34:49, 29.23s/it]
 35%|███▍      | 1727/5000 [14:55:19<27:59:41, 30.79s/it]
 35%|███▍      | 1728/5000 [14:55:47<27:16:05, 30.00s/it]
 35%|███▍      | 1729/5000 [14:56:15<26:49:20, 29.52s/it]
 35%|███▍      | 1730/5000 [14:56:45<27:00:43, 29.74s/it]
 35%|███▍      | 1731/5000 [14:57:15<26:55:08, 29.64s/it]
 35%|███▍      | 1732/5000 [14:57:43<26:32:55, 29.25s/it]
 35%|███▍      | 1733/5000 [14:58:12<26:17:40, 28.97s/it]
 35%|███▍      | 1734/5000 [14:58:42<26:40:26, 29.40s/it]
 35%|███▍      | 1735/5000 [14:59:09<26:04:46, 28.76s/it]
 35%|███▍      | 1736/5000 [14:59:37<25:50:36, 28.50s/it]
 35%|███▍      | 1737/5000 [15:00:08<26:31:06, 29.26s/it]
 35%|███▍      | 1738/5000 [15:00:35<25:58:16, 28.66s/it]
 35%|███▍      | 1739/5000 [15:01:03<25:44:14, 28.41s/it]
 35%|███▍      | 1740/5000 [15:01:30<25:23:21, 28.04s/it]
 35%|███▍      | 1741/5000 [15:02:00<25:42:23, 28.40s/it]
 35%|███▍      | 1742/5000 [15:02:28<25:39:49, 28.36s/it]
 35%|███▍      | 1743/5000 [15:02:55<25:17:45, 27.96s/it]
 35%|███▍      | 1744/5000 [15:03:33<28:04:55, 31.05s/it]
 35%|███▍      | 1745/5000 [15:04:00<26:56:29, 29.80s/it]
 35%|███▍      | 1746/5000 [15:04:29<26:37:49, 29.46s/it]
 35%|███▍      | 1747/5000 [15:04:58<26:27:04, 29.27s/it]
 35%|███▍      | 1748/5000 [15:05:28<26:37:39, 29.48s/it]
 35%|███▍      | 1749/5000 [15:05:56<26:15:21, 29.07s/it]
 35%|███▌      | 1750/5000 [15:06:24<26:10:07, 28.99s/it]
                                                         
 35%|███▌      | 1750/5000 [15:06:24<26:10:07, 28.99s/it]
 35%|███▌      | 1751/5000 [15:06:55<26:29:17, 29.35s/it]
 35%|███▌      | 1752/5000 [15:07:23<26:06:38, 28.94s/it]
 35%|███▌      | 1753/5000 [15:07:52<26:07:43, 28.97s/it]
 35%|███▌      | 1754/5000 [15:08:20<25:56:12, 28.77s/it]
 35%|███▌      | 1755/5000 [15:08:48<25:49:07, 28.64s/it]
 35%|███▌      | 1756/5000 [15:09:15<25:12:15, 27.97s/it]
 35%|███▌      | 1757/5000 [15:09:43<25:13:24, 28.00s/it]
 35%|███▌      | 1758/5000 [15:10:13<25:46:07, 28.61s/it]
 35%|███▌      | 1759/5000 [15:10:41<25:38:16, 28.48s/it]
 35%|███▌      | 1760/5000 [15:11:12<26:17:01, 29.20s/it]
 35%|███▌      | 1761/5000 [15:11:39<25:45:09, 28.62s/it]
 35%|███▌      | 1762/5000 [15:12:09<26:07:48, 29.05s/it]
 35%|███▌      | 1763/5000 [15:12:36<25:35:06, 28.45s/it]
 35%|███▌      | 1764/5000 [15:13:04<25:28:41, 28.34s/it]
 35%|███▌      | 1765/5000 [15:13:35<26:00:01, 28.93s/it]
 35%|███▌      | 1766/5000 [15:14:04<26:00:46, 28.96s/it]
 35%|███▌      | 1767/5000 [15:14:32<25:43:02, 28.64s/it]
 35%|███▌      | 1768/5000 [15:15:01<25:47:38, 28.73s/it]
 35%|███▌      | 1769/5000 [15:15:29<25:36:00, 28.52s/it]
 35%|███▌      | 1770/5000 [15:15:57<25:27:37, 28.38s/it]
 35%|███▌      | 1771/5000 [15:16:25<25:25:28, 28.35s/it]
 35%|███▌      | 1772/5000 [15:16:53<25:16:50, 28.19s/it]
 35%|███▌      | 1773/5000 [15:17:23<25:46:21, 28.75s/it]
 35%|███▌      | 1774/5000 [15:17:51<25:42:35, 28.69s/it]
 36%|███▌      | 1775/5000 [15:18:20<25:35:23, 28.57s/it]
                                                         
 36%|███▌      | 1775/5000 [15:18:20<25:35:23, 28.57s/it]
 36%|███▌      | 1776/5000 [15:18:48<25:31:15, 28.50s/it]
 36%|███▌      | 1777/5000 [15:19:16<25:29:16, 28.47s/it]
 36%|███▌      | 1778/5000 [15:19:44<25:08:27, 28.09s/it]
 36%|███▌      | 1779/5000 [15:20:12<25:16:39, 28.25s/it]
 36%|███▌      | 1780/5000 [15:20:39<24:58:11, 27.92s/it]
 36%|███▌      | 1781/5000 [15:21:07<25:02:09, 28.00s/it]
 36%|███▌      | 1782/5000 [15:21:36<25:04:41, 28.06s/it]
 36%|███▌      | 1783/5000 [15:22:02<24:39:57, 27.60s/it]
 36%|███▌      | 1784/5000 [15:22:33<25:23:19, 28.42s/it]
 36%|███▌      | 1785/5000 [15:23:00<25:06:40, 28.12s/it]
 36%|███▌      | 1786/5000 [15:23:29<25:14:45, 28.28s/it]
 36%|███▌      | 1787/5000 [15:23:57<25:19:01, 28.37s/it]
 36%|███▌      | 1788/5000 [15:24:24<25:00:04, 28.02s/it]
 36%|███▌      | 1789/5000 [15:24:54<25:27:32, 28.54s/it]
 36%|███▌      | 1790/5000 [15:25:21<25:05:19, 28.14s/it]
 36%|███▌      | 1791/5000 [15:25:50<25:19:54, 28.42s/it]
 36%|███▌      | 1792/5000 [15:26:18<25:07:14, 28.19s/it]
 36%|███▌      | 1793/5000 [15:26:45<24:48:17, 27.84s/it]
 36%|███▌      | 1794/5000 [15:27:13<24:50:16, 27.89s/it]
 36%|███▌      | 1795/5000 [15:27:40<24:32:47, 27.57s/it]
 36%|███▌      | 1796/5000 [15:28:09<24:54:46, 27.99s/it]
 36%|███▌      | 1797/5000 [15:28:37<24:57:59, 28.06s/it]
 36%|███▌      | 1798/5000 [15:29:05<25:01:57, 28.14s/it]
 36%|███▌      | 1799/5000 [15:29:33<24:50:30, 27.94s/it]
 36%|███▌      | 1800/5000 [15:30:01<24:55:32, 28.04s/it]
                                                         
 36%|███▌      | 1800/5000 [15:30:01<24:55:32, 28.04s/it]
 36%|███▌      | 1801/5000 [15:30:30<25:00:54, 28.15s/it]
 36%|███▌      | 1802/5000 [15:30:58<24:58:25, 28.11s/it]
 36%|███▌      | 1803/5000 [15:31:25<24:48:17, 27.93s/it]
 36%|███▌      | 1804/5000 [15:31:53<24:48:08, 27.94s/it]
 36%|███▌      | 1805/5000 [15:32:21<24:48:32, 27.95s/it]
 36%|███▌      | 1806/5000 [15:32:49<24:54:00, 28.07s/it]
 36%|███▌      | 1807/5000 [15:33:18<25:05:12, 28.28s/it]
 36%|███▌      | 1808/5000 [15:33:45<24:43:19, 27.88s/it]
 36%|███▌      | 1809/5000 [15:34:14<25:04:47, 28.29s/it]
 36%|███▌      | 1810/5000 [15:34:42<24:48:47, 28.00s/it]
 36%|███▌      | 1811/5000 [15:35:11<25:06:24, 28.34s/it]
 36%|███▌      | 1812/5000 [15:35:40<25:18:34, 28.58s/it]
 36%|███▋      | 1813/5000 [15:36:07<24:55:49, 28.16s/it]
 36%|███▋      | 1814/5000 [15:36:35<24:55:15, 28.16s/it]
 36%|███▋      | 1815/5000 [15:37:05<25:20:18, 28.64s/it]
 36%|███▋      | 1816/5000 [15:37:33<25:07:00, 28.40s/it]
 36%|███▋      | 1817/5000 [15:38:02<25:11:10, 28.49s/it]
 36%|███▋      | 1818/5000 [15:38:28<24:38:17, 27.87s/it]
 36%|███▋      | 1819/5000 [15:38:57<24:55:53, 28.22s/it]
 36%|███▋      | 1820/5000 [15:39:28<25:37:02, 29.00s/it]
 36%|███▋      | 1821/5000 [15:39:56<25:19:35, 28.68s/it]
 36%|███▋      | 1822/5000 [15:40:25<25:26:04, 28.81s/it]
 36%|███▋      | 1823/5000 [15:40:52<25:00:14, 28.33s/it]
 36%|███▋      | 1824/5000 [15:41:20<24:58:11, 28.30s/it]
 36%|███▋      | 1825/5000 [15:41:48<24:40:17, 27.97s/it]
                                                         
 36%|███▋      | 1825/5000 [15:41:48<24:40:17, 27.97s/it]
 37%|███▋      | 1826/5000 [15:42:16<24:53:23, 28.23s/it]
 37%|███▋      | 1827/5000 [15:42:46<25:09:03, 28.54s/it]
 37%|███▋      | 1828/5000 [15:43:15<25:26:48, 28.88s/it]
 37%|███▋      | 1829/5000 [15:43:43<25:13:57, 28.65s/it]
 37%|███▋      | 1830/5000 [15:44:14<25:47:45, 29.30s/it]
 37%|███▋      | 1831/5000 [15:44:41<25:14:01, 28.67s/it]
 37%|███▋      | 1832/5000 [15:45:14<26:17:36, 29.88s/it]
 37%|███▋      | 1833/5000 [15:45:41<25:36:04, 29.10s/it]
 37%|███▋      | 1834/5000 [15:46:13<26:07:34, 29.71s/it]
 37%|███▋      | 1835/5000 [15:46:41<25:42:34, 29.24s/it]
 37%|███▋      | 1836/5000 [15:47:09<25:26:33, 28.95s/it]
 37%|███▋      | 1837/5000 [15:47:37<25:06:26, 28.58s/it]
 37%|███▋      | 1838/5000 [15:48:05<24:57:56, 28.42s/it]
 37%|███▋      | 1839/5000 [15:48:33<24:53:11, 28.34s/it]
 37%|███▋      | 1840/5000 [15:49:01<24:43:26, 28.17s/it]
 37%|███▋      | 1841/5000 [15:49:28<24:35:46, 28.03s/it]
 37%|███▋      | 1842/5000 [15:49:57<24:41:27, 28.15s/it]
 37%|███▋      | 1843/5000 [15:50:23<24:12:04, 27.60s/it]
 37%|███▋      | 1844/5000 [15:50:53<24:53:59, 28.40s/it]
 37%|███▋      | 1845/5000 [15:51:21<24:43:57, 28.22s/it]
 37%|███▋      | 1846/5000 [15:51:48<24:19:14, 27.76s/it]
 37%|███▋      | 1847/5000 [15:52:17<24:33:04, 28.03s/it]
 37%|███▋      | 1848/5000 [15:52:44<24:18:53, 27.77s/it]
 37%|███▋      | 1849/5000 [15:53:12<24:19:41, 27.79s/it]
 37%|███▋      | 1850/5000 [15:53:41<24:37:31, 28.14s/it]
                                                         
 37%|███▋      | 1850/5000 [15:53:41<24:37:31, 28.14s/it]
 37%|███▋      | 1851/5000 [15:54:08<24:20:37, 27.83s/it]
 37%|███▋      | 1852/5000 [15:54:38<25:00:06, 28.59s/it]
 37%|███▋      | 1853/5000 [15:55:05<24:35:50, 28.14s/it]
 37%|███▋      | 1854/5000 [15:55:35<24:56:11, 28.53s/it]
 37%|███▋      | 1855/5000 [15:56:02<24:40:51, 28.25s/it]
 37%|███▋      | 1856/5000 [15:56:29<24:22:08, 27.90s/it]
 37%|███▋      | 1857/5000 [15:56:58<24:31:21, 28.09s/it]
 37%|███▋      | 1858/5000 [15:57:25<24:15:44, 27.80s/it]
 37%|███▋      | 1859/5000 [15:57:53<24:24:00, 27.97s/it]
 37%|███▋      | 1860/5000 [15:58:24<25:09:44, 28.85s/it]
 37%|███▋      | 1861/5000 [15:58:51<24:41:46, 28.32s/it]
 37%|███▋      | 1862/5000 [15:59:19<24:39:00, 28.28s/it]
 37%|███▋      | 1863/5000 [15:59:49<25:05:34, 28.80s/it]
 37%|███▋      | 1864/5000 [16:00:17<24:49:12, 28.49s/it]
 37%|███▋      | 1865/5000 [16:00:45<24:43:37, 28.39s/it]
 37%|███▋      | 1866/5000 [16:01:15<24:54:59, 28.62s/it]
 37%|███▋      | 1867/5000 [16:01:42<24:42:43, 28.40s/it]
 37%|███▋      | 1868/5000 [16:02:09<24:19:22, 27.96s/it]
 37%|███▋      | 1869/5000 [16:02:38<24:35:35, 28.28s/it]
 37%|███▋      | 1870/5000 [16:03:06<24:32:10, 28.22s/it]
 37%|███▋      | 1871/5000 [16:03:35<24:29:39, 28.18s/it]
 37%|███▋      | 1872/5000 [16:04:03<24:32:06, 28.24s/it]
 37%|███▋      | 1873/5000 [16:04:34<25:13:59, 29.05s/it]
 37%|███▋      | 1874/5000 [16:05:05<25:39:29, 29.55s/it]
 38%|███▊      | 1875/5000 [16:05:33<25:22:21, 29.23s/it]
                                                         
 38%|███▊      | 1875/5000 [16:05:33<25:22:21, 29.23s/it]
 38%|███▊      | 1876/5000 [16:06:01<25:06:19, 28.93s/it]
 38%|███▊      | 1877/5000 [16:06:30<25:09:46, 29.01s/it]
 38%|███▊      | 1878/5000 [16:06:58<24:46:19, 28.56s/it]
 38%|███▊      | 1879/5000 [16:07:27<24:53:55, 28.72s/it]
 38%|███▊      | 1880/5000 [16:07:55<24:41:18, 28.49s/it]
 38%|███▊      | 1881/5000 [16:08:22<24:11:37, 27.92s/it]
 38%|███▊      | 1882/5000 [16:08:50<24:24:05, 28.17s/it]
 38%|███▊      | 1883/5000 [16:09:20<24:43:30, 28.56s/it]
 38%|███▊      | 1884/5000 [16:09:48<24:31:59, 28.34s/it]
 38%|███▊      | 1885/5000 [16:10:16<24:24:57, 28.22s/it]
 38%|███▊      | 1886/5000 [16:10:44<24:31:49, 28.36s/it]
 38%|███▊      | 1887/5000 [16:11:12<24:26:43, 28.27s/it]
 38%|███▊      | 1888/5000 [16:11:41<24:30:18, 28.35s/it]
 38%|███▊      | 1889/5000 [16:12:09<24:26:38, 28.29s/it]
 38%|███▊      | 1890/5000 [16:12:37<24:16:34, 28.10s/it]
 38%|███▊      | 1891/5000 [16:13:06<24:29:26, 28.36s/it]
 38%|███▊      | 1892/5000 [16:13:34<24:21:03, 28.21s/it]
 38%|███▊      | 1893/5000 [16:14:01<24:10:22, 28.01s/it]
 38%|███▊      | 1894/5000 [16:14:29<24:13:59, 28.09s/it]
 38%|███▊      | 1895/5000 [16:14:58<24:16:44, 28.15s/it]
 38%|███▊      | 1896/5000 [16:15:26<24:21:55, 28.26s/it]
 38%|███▊      | 1897/5000 [16:15:54<24:11:47, 28.07s/it]
 38%|███▊      | 1898/5000 [16:16:21<24:00:12, 27.86s/it]
 38%|███▊      | 1899/5000 [16:16:50<24:08:46, 28.03s/it]
 38%|███▊      | 1900/5000 [16:17:16<23:40:33, 27.49s/it]
                                                         
 38%|███▊      | 1900/5000 [16:17:16<23:40:33, 27.49s/it]
 38%|███▊      | 1901/5000 [16:17:45<23:59:19, 27.87s/it]
 38%|███▊      | 1902/5000 [16:18:12<23:51:51, 27.73s/it]
 38%|███▊      | 1903/5000 [16:18:41<24:15:07, 28.19s/it]
 38%|███▊      | 1904/5000 [16:19:10<24:18:53, 28.27s/it]
 38%|███▊      | 1905/5000 [16:19:38<24:18:17, 28.27s/it]
 38%|███▊      | 1906/5000 [16:20:06<24:10:34, 28.13s/it]
 38%|███▊      | 1907/5000 [16:20:34<24:11:02, 28.15s/it]
 38%|███▊      | 1908/5000 [16:21:02<24:09:14, 28.12s/it]
 38%|███▊      | 1909/5000 [16:21:30<24:05:13, 28.05s/it]
 38%|███▊      | 1910/5000 [16:21:58<24:09:08, 28.14s/it]
 38%|███▊      | 1911/5000 [16:22:26<24:02:51, 28.03s/it]
 38%|███▊      | 1912/5000 [16:22:54<24:01:25, 28.01s/it]
 38%|███▊      | 1913/5000 [16:23:22<24:02:16, 28.03s/it]
 38%|███▊      | 1914/5000 [16:23:50<23:57:06, 27.94s/it]
 38%|███▊      | 1915/5000 [16:24:18<23:57:11, 27.95s/it]
 38%|███▊      | 1916/5000 [16:24:46<24:00:10, 28.02s/it]
 38%|███▊      | 1917/5000 [16:25:14<24:01:27, 28.05s/it]
 38%|███▊      | 1918/5000 [16:25:42<24:01:44, 28.07s/it]
 38%|███▊      | 1919/5000 [16:26:10<23:58:40, 28.02s/it]
 38%|███▊      | 1920/5000 [16:26:38<23:59:53, 28.05s/it]
 38%|███▊      | 1921/5000 [16:27:06<23:59:47, 28.06s/it]
 38%|███▊      | 1922/5000 [16:27:34<23:59:06, 28.05s/it]
 38%|███▊      | 1923/5000 [16:28:02<24:00:02, 28.08s/it]
 38%|███▊      | 1924/5000 [16:28:30<23:58:24, 28.06s/it]
 38%|███▊      | 1925/5000 [16:28:59<24:12:37, 28.34s/it]
                                                         
 38%|███▊      | 1925/5000 [16:28:59<24:12:37, 28.34s/it]
 39%|███▊      | 1926/5000 [16:29:27<23:54:02, 27.99s/it]
 39%|███▊      | 1927/5000 [16:29:55<23:54:51, 28.02s/it]
 39%|███▊      | 1928/5000 [16:30:23<23:56:14, 28.05s/it]
 39%|███▊      | 1929/5000 [16:30:51<23:58:15, 28.10s/it]
 39%|███▊      | 1930/5000 [16:31:18<23:42:35, 27.80s/it]
 39%|███▊      | 1931/5000 [16:31:47<23:56:23, 28.08s/it]
 39%|███▊      | 1932/5000 [16:32:14<23:46:46, 27.90s/it]
 39%|███▊      | 1933/5000 [16:32:43<23:52:30, 28.02s/it]
 39%|███▊      | 1934/5000 [16:33:17<25:20:34, 29.76s/it]
 39%|███▊      | 1935/5000 [16:33:44<24:40:30, 28.98s/it]
 39%|███▊      | 1936/5000 [16:34:14<25:07:27, 29.52s/it]
 39%|███▊      | 1937/5000 [16:34:27<20:41:32, 24.32s/it]
 39%|███▉      | 1938/5000 [16:34:37<17:09:12, 20.17s/it]
 39%|███▉      | 1939/5000 [16:34:48<14:40:32, 17.26s/it]
 39%|███▉      | 1940/5000 [16:34:58<12:58:19, 15.26s/it]{'loss': 0.0933, 'learning_rate': 7.335555555555556e-06, 'epoch': 7.0}
+{'loss': 0.0797, 'learning_rate': 7.280000000000001e-06, 'epoch': 7.01}
+{'loss': 0.0638, 'learning_rate': 7.224444444444445e-06, 'epoch': 7.01}
+{'loss': 0.0693, 'learning_rate': 7.1688888888888895e-06, 'epoch': 7.02}
+{'loss': 0.0553, 'learning_rate': 7.113333333333334e-06, 'epoch': 7.02}
+{'loss': 0.0637, 'learning_rate': 7.057777777777778e-06, 'epoch': 7.03}
+{'loss': 0.0556, 'learning_rate': 7.0022222222222225e-06, 'epoch': 7.03}
+{'loss': 0.0514, 'learning_rate': 6.946666666666667e-06, 'epoch': 7.04}
+{'loss': 0.0454, 'learning_rate': 6.891111111111111e-06, 'epoch': 7.04}
+{'loss': 0.0505, 'learning_rate': 6.835555555555556e-06, 'epoch': 7.05}
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
 39%|███▉      | 1941/5000 [16:36:56<39:14:02, 46.17s/it]
 39%|███▉      | 1942/5000 [16:37:27<35:18:22, 41.56s/it]
 39%|███▉      | 1943/5000 [16:37:57<32:17:04, 38.02s/it]
 39%|███▉      | 1944/5000 [16:38:24<29:31:16, 34.78s/it]
 39%|███▉      | 1945/5000 [16:38:55<28:33:12, 33.65s/it]
 39%|███▉      | 1946/5000 [16:39:22<26:45:43, 31.55s/it]
 39%|███▉      | 1947/5000 [16:39:53<26:33:50, 31.32s/it]
 39%|███▉      | 1948/5000 [16:40:25<26:48:55, 31.63s/it]
 39%|███▉      | 1949/5000 [16:40:55<26:18:21, 31.04s/it]
 39%|███▉      | 1950/5000 [16:41:26<26:21:14, 31.11s/it]
                                                         
 39%|███▉      | 1950/5000 [16:41:26<26:21:14, 31.11s/it]
 39%|███▉      | 1951/5000 [16:41:53<25:20:56, 29.93s/it]
 39%|███▉      | 1952/5000 [16:42:27<26:12:15, 30.95s/it]
 39%|███▉      | 1953/5000 [16:42:55<25:32:57, 30.19s/it]
 39%|███▉      | 1954/5000 [16:43:24<25:13:56, 29.82s/it]
 39%|███▉      | 1955/5000 [16:43:55<25:26:29, 30.08s/it]
 39%|███▉      | 1956/5000 [16:44:22<24:40:56, 29.19s/it]
 39%|███▉      | 1957/5000 [16:44:52<25:03:56, 29.65s/it]
 39%|███▉      | 1958/5000 [16:45:20<24:39:07, 29.17s/it]
 39%|███▉      | 1959/5000 [16:45:50<24:40:56, 29.22s/it]
 39%|███▉      | 1960/5000 [16:46:18<24:19:42, 28.81s/it]
 39%|███▉      | 1961/5000 [16:46:47<24:34:22, 29.11s/it]
 39%|███▉      | 1962/5000 [16:47:16<24:19:49, 28.83s/it]
 39%|███▉      | 1963/5000 [16:47:46<24:48:03, 29.40s/it]
 39%|███▉      | 1964/5000 [16:48:22<26:27:41, 31.38s/it]
 39%|███▉      | 1965/5000 [16:48:50<25:36:23, 30.37s/it]
 39%|███▉      | 1966/5000 [16:49:21<25:46:20, 30.58s/it]
 39%|███▉      | 1967/5000 [16:49:50<25:12:33, 29.92s/it]
 39%|███▉      | 1968/5000 [16:50:20<25:20:18, 30.09s/it]
 39%|███▉      | 1969/5000 [16:50:50<25:16:00, 30.01s/it]
 39%|███▉      | 1970/5000 [16:51:18<24:39:12, 29.29s/it]
 39%|███▉      | 1971/5000 [16:51:48<24:53:08, 29.58s/it]
 39%|███▉      | 1972/5000 [16:52:16<24:27:24, 29.08s/it]
 39%|███▉      | 1973/5000 [16:52:49<25:23:38, 30.20s/it]
 39%|███▉      | 1974/5000 [16:53:19<25:18:27, 30.11s/it]
 40%|███▉      | 1975/5000 [16:53:46<24:39:45, 29.35s/it]
                                                         
 40%|███▉      | 1975/5000 [16:53:46<24:39:45, 29.35s/it]
 40%|███▉      | 1976/5000 [16:54:17<25:02:41, 29.82s/it]
 40%|███▉      | 1977/5000 [16:54:45<24:26:36, 29.11s/it]
 40%|███▉      | 1978/5000 [16:55:15<24:41:51, 29.42s/it]
 40%|███▉      | 1979/5000 [16:55:44<24:40:58, 29.41s/it]
 40%|███▉      | 1980/5000 [16:56:11<24:09:35, 28.80s/it]
 40%|███▉      | 1981/5000 [16:56:41<24:27:15, 29.16s/it]
 40%|███▉      | 1982/5000 [16:57:09<23:56:28, 28.56s/it]
 40%|███▉      | 1983/5000 [16:57:38<24:14:09, 28.92s/it]
 40%|███▉      | 1984/5000 [16:58:13<25:36:00, 30.56s/it]
 40%|███▉      | 1985/5000 [16:58:41<24:56:31, 29.78s/it]
 40%|███▉      | 1986/5000 [16:59:10<24:53:44, 29.74s/it]
 40%|███▉      | 1987/5000 [16:59:38<24:14:16, 28.96s/it]
 40%|███▉      | 1988/5000 [17:00:08<24:30:13, 29.29s/it]
 40%|███▉      | 1989/5000 [17:00:35<23:55:31, 28.61s/it]
 40%|███▉      | 1990/5000 [17:01:04<24:13:53, 28.98s/it]
 40%|███▉      | 1991/5000 [17:01:35<24:32:30, 29.36s/it]
 40%|███▉      | 1992/5000 [17:02:02<23:59:43, 28.72s/it]
 40%|███▉      | 1993/5000 [17:02:31<24:12:15, 28.98s/it]
 40%|███▉      | 1994/5000 [17:02:58<23:39:35, 28.34s/it]
 40%|███▉      | 1995/5000 [17:03:36<26:03:43, 31.22s/it]
 40%|███▉      | 1996/5000 [17:04:06<25:33:23, 30.63s/it]
 40%|███▉      | 1997/5000 [17:04:33<24:44:30, 29.66s/it]
 40%|███▉      | 1998/5000 [17:05:03<24:47:59, 29.74s/it]
 40%|███▉      | 1999/5000 [17:05:30<24:09:55, 28.99s/it]
 40%|████      | 2000/5000 [17:06:00<24:20:42, 29.21s/it]
                                                         
 40%|████      | 2000/5000 [17:06:00<24:20:42, 29.21s/it][INFO|trainer.py:3138] 2023-05-11 02:47:40,879 >> ***** Running Evaluation *****
+[INFO|trainer.py:3142] 2023-05-11 02:47:40,879 >>   Num examples: Unknown
+[INFO|trainer.py:3143] 2023-05-11 02:47:40,879 >>   Batch size = 64
+{'loss': 0.0866, 'learning_rate': 6.780000000000001e-06, 'epoch': 8.0}
+{'loss': 0.128, 'learning_rate': 6.724444444444444e-06, 'epoch': 8.01}
+{'loss': 0.1098, 'learning_rate': 6.668888888888889e-06, 'epoch': 8.01}
+
+
+
+[INFO|trainer_utils.py:693] 2023-05-11 02:47:55,714 >> The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`,  you can safely ignore this message.
+
                                                         
 40%|████      | 2000/5000 [17:58:10<24:20:42, 29.21s/it][INFO|trainer.py:2877] 2023-05-11 03:39:50,770 >> Saving model checkpoint to ./checkpoint-2000
+[INFO|configuration_utils.py:458] 2023-05-11 03:39:50,774 >> Configuration saved in ./checkpoint-2000/config.json
+[INFO|configuration_utils.py:364] 2023-05-11 03:39:50,778 >> Configuration saved in ./checkpoint-2000/generation_config.json
+[INFO|modeling_utils.py:1855] 2023-05-11 03:39:54,336 >> Model weights saved in ./checkpoint-2000/pytorch_model.bin
+[INFO|feature_extraction_utils.py:369] 2023-05-11 03:39:54,340 >> Feature extractor saved in ./checkpoint-2000/preprocessor_config.json
+[INFO|feature_extraction_utils.py:369] 2023-05-11 03:40:05,259 >> Feature extractor saved in ./preprocessor_config.json

wandb/run-20230510_094132-lvsln7ks/files/config.yaml

@@ -53,6 +53,26 @@ _wandb:
       5: 1
       6:
       - 1
+    - 1: eval/loss
+      5: 1
+      6:
+      - 1
+    - 1: eval/wer
+      5: 1
+      6:
+      - 1
+    - 1: eval/runtime
+      5: 1
+      6:
+      - 1
+    - 1: eval/samples_per_second
+      5: 1
+      6:
+      - 1
+    - 1: eval/steps_per_second
+      5: 1
+      6:
+      - 1
 vocab_size:
   desc: null
   value: 51865

wandb/run-20230510_094132-lvsln7ks/files/output.log

@@ -1109,3 +1109,1083 @@ Reading metadata...: 221914it [00:33, 6083.09it/s]
 [INFO|feature_extraction_utils.py:369] 2023-05-10 18:44:03,173 >> Feature extractor saved in ./checkpoint-1000/preprocessor_config.json
 [INFO|feature_extraction_utils.py:369] 2023-05-10 18:44:11,165 >> Feature extractor saved in ./preprocessor_config.json
 Adding files tracked by Git LFS: ['wandb/run-20230509_115211-hq92t8sj/run-hq92t8sj.wandb', 'wandb/run-20230510_094132-lvsln7ks/run-lvsln7ks.wandb']. This may take a bit of time if the files are large.
+05/10/2023 18:44:21 - WARNING - huggingface_hub.repository - Adding files tracked by Git LFS: ['wandb/run-20230509_115211-hq92t8sj/run-hq92t8sj.wandb', 'wandb/run-20230510_094132-lvsln7ks/run-lvsln7ks.wandb']. This may take a bit of time if the files are large.
+/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.
+  warnings.warn('Was asked to gather along dimension 0, but all '
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 20%|██        | 1025/5000 [9:14:35<31:09:01, 28.21s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 21%|██        | 1049/5000 [9:26:14<32:13:26, 29.36s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 22%|██▏       | 1075/5000 [9:38:18<30:32:50, 28.02s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 22%|██▏       | 1100/5000 [9:50:01<30:41:56, 28.34s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 22%|██▎       | 1125/5000 [10:01:47<30:08:21, 28.00s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 23%|██▎       | 1150/5000 [10:13:42<30:15:19, 28.29s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 23%|██▎       | 1174/5000 [10:25:04<30:12:39, 28.43s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 24%|██▍       | 1200/5000 [10:37:12<29:47:54, 28.23s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+ 24%|██▍       | 1212/5000 [10:41:54<16:58:24, 16.13s/it]
+
+
+
+
+
+Reading metadata...: 15520it [00:00, 39430.04it/s]]
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 24%|██▍       | 1225/5000 [10:49:34<29:56:46, 28.56s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 25%|██▌       | 1250/5000 [11:01:43<29:58:55, 28.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 26%|██▌       | 1275/5000 [11:14:00<30:57:42, 29.92s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 26%|██▌       | 1300/5000 [11:26:24<29:52:50, 29.07s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 26%|██▋       | 1325/5000 [11:38:41<29:56:14, 29.33s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 27%|██▋       | 1350/5000 [11:50:51<30:10:19, 29.76s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 28%|██▊       | 1375/5000 [12:03:00<29:03:49, 28.86s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 28%|██▊       | 1400/5000 [12:15:04<29:12:43, 29.21s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 28%|██▊       | 1425/5000 [12:27:26<29:14:04, 29.44s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 29%|██▉       | 1450/5000 [12:39:38<28:05:33, 28.49s/it]
+
+
+
+
+
+ 29%|██▉       | 1455/5000 [12:40:52<14:54:16, 15.14s/it]
+
+
+
+
+
+Reading metadata...: 221914it [00:11, 21050.24it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 30%|██▉       | 1475/5000 [12:51:59<28:05:07, 28.68s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 30%|███       | 1500/5000 [13:04:14<27:52:11, 28.67s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 30%|███       | 1524/5000 [13:15:55<28:31:59, 29.55s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 31%|███       | 1550/5000 [13:28:41<28:46:01, 30.02s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 32%|███▏      | 1575/5000 [13:40:49<27:37:42, 29.04s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 32%|███▏      | 1600/5000 [13:53:15<28:38:52, 30.33s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 32%|███▎      | 1625/5000 [14:05:32<26:57:46, 28.76s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 33%|███▎      | 1650/5000 [14:17:49<27:35:28, 29.65s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 34%|███▎      | 1675/5000 [14:29:59<27:04:36, 29.32s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 34%|███▍      | 1697/5000 [14:39:41<14:46:59, 16.11s/it]
+
+
+
+
+Reading metadata...: 15520it [00:00, 37994.72it/s]]
+
+
+
+ 34%|███▍      | 1700/5000 [14:42:18<31:39:14, 34.53s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 34%|███▍      | 1725/5000 [14:54:15<26:30:49, 29.14s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 35%|███▌      | 1750/5000 [15:06:24<26:10:07, 28.99s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 36%|███▌      | 1775/5000 [15:18:20<25:35:23, 28.57s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 36%|███▌      | 1799/5000 [15:29:33<24:50:30, 27.94s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 36%|███▋      | 1825/5000 [15:41:48<24:40:17, 27.97s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 37%|███▋      | 1850/5000 [15:53:41<24:37:31, 28.14s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 38%|███▊      | 1875/5000 [16:05:33<25:22:21, 29.23s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 38%|███▊      | 1900/5000 [16:17:16<23:40:33, 27.49s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 38%|███▊      | 1925/5000 [16:28:59<24:12:37, 28.34s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 39%|███▉      | 1940/5000 [16:34:58<12:58:19, 15.26s/it]
+
+
+
+
+
+Reading metadata...: 15520it [00:00, 41429.23it/s]]
+
+
+
+
+
+
+
+
+
+
+ 39%|███▉      | 1950/5000 [16:41:26<26:21:14, 31.11s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 40%|███▉      | 1975/5000 [16:53:46<24:39:45, 29.35s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 40%|████      | 2000/5000 [17:06:00<24:20:42, 29.21s/it][INFO|trainer.py:3138] 2023-05-11 02:47:40,879 >> ***** Running Evaluation *****
+[INFO|trainer.py:3142] 2023-05-11 02:47:40,879 >>   Num examples: Unknown
+[INFO|trainer.py:3143] 2023-05-11 02:47:40,879 >>   Batch size = 64
+Reading metadata...: 0it [00:00, ?it/s]
+
+
+[INFO|trainer_utils.py:693] 2023-05-11 02:47:55,714 >> The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`,  you can safely ignore this message.
+ 40%|████      | 2000/5000 [17:58:10<24:20:42, 29.21s/it][INFO|trainer.py:2877] 2023-05-11 03:39:50,770 >> Saving model checkpoint to ./checkpoint-2000
+[INFO|configuration_utils.py:458] 2023-05-11 03:39:50,774 >> Configuration saved in ./checkpoint-2000/config.json
+[INFO|configuration_utils.py:364] 2023-05-11 03:39:50,778 >> Configuration saved in ./checkpoint-2000/generation_config.json
+{'eval_loss': 0.2271677553653717, 'eval_wer': 8.622862637077075, 'eval_runtime': 3129.8829, 'eval_samples_per_second': 4.959, 'eval_steps_per_second': 0.078, 'epoch': 8.01}
+[INFO|modeling_utils.py:1855] 2023-05-11 03:39:54,336 >> Model weights saved in ./checkpoint-2000/pytorch_model.bin
+[INFO|feature_extraction_utils.py:369] 2023-05-11 03:39:54,340 >> Feature extractor saved in ./checkpoint-2000/preprocessor_config.json

wandb/run-20230510_094132-lvsln7ks/files/wandb-summary.json

@@ -1 +1 @@
-{"eval/loss": 0.24644243717193604, "eval/wer": 9.800036380645496, "eval/runtime": 3384.9122, "eval/samples_per_second": 4.585, "eval/steps_per_second": 0.072, "_timestamp": 1683733439.7217376, "_runtime": 32547.02718758583, "_step": 40}
+{"eval/loss": 0.2271677553653717, "eval/wer": 8.622862637077075, "eval/runtime": 3129.8829, "eval/samples_per_second": 4.959, "eval/steps_per_second": 0.078, "_timestamp": 1683765590.7620673, "_runtime": 64698.06751728058, "_step": 81}

wandb/run-20230510_094132-lvsln7ks/run-lvsln7ks.wandb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f609cebcb2556eb362db7a3183df0883f15973830c811569a65ac946da2f844e
-size 2982800
+oid sha256:21a79200307ea1c47cedc383f577661a583925df8f10c30824145756da71c81d
+size 5963995