Training in progress, step 2000

nohup.out

@@ -70307,3 +70307,65 @@ If your task is similar to the task the model of the checkpoint was trained on,
 [INFO|modeling_utils.py:1693] 2023-12-29 16:26:10,749 >> Model weights saved in ./checkpoint-1000/pytorch_model.bin
 [INFO|feature_extraction_utils.py:368] 2023-12-29 16:26:10,755 >> Feature extractor saved in ./checkpoint-1000/preprocessor_config.json
 [INFO|feature_extraction_utils.py:368] 2023-12-29 16:26:14,474 >> Feature extractor saved in ./preprocessor_config.json
+
 20%|██        | 1001/5000 [1:37:48<587:25:31, 528.82s/it]
 20%|██        | 1002/5000 [1:37:53<412:45:20, 371.67s/it]
 20%|██        | 1003/5000 [1:37:57<290:04:45, 261.27s/it]
 20%|██        | 1004/5000 [1:38:01<204:29:07, 184.22s/it]
 20%|██        | 1005/5000 [1:38:05<144:19:15, 130.05s/it]
 20%|██        | 1006/5000 [1:38:09<102:20:01, 92.24s/it] 
 20%|██        | 1007/5000 [1:38:13<72:50:10, 65.67s/it] 
 20%|██        | 1008/5000 [1:38:16<52:11:33, 47.07s/it]
 20%|██        | 1009/5000 [1:38:20<37:45:05, 34.05s/it]
 20%|██        | 1010/5000 [1:38:25<27:57:19, 25.22s/it]
 20%|██        | 1011/5000 [1:38:28<20:49:01, 18.79s/it]
 20%|██        | 1012/5000 [1:38:32<15:47:03, 14.25s/it]
 20%|██        | 1013/5000 [1:38:38<12:51:47, 11.61s/it]
 20%|██        | 1014/5000 [1:38:42<10:31:44,  9.51s/it]
 20%|██        | 1015/5000 [1:38:46<8:41:11,  7.85s/it] 
 20%|██        | 1016/5000 [1:38:50<7:18:49,  6.61s/it]
 20%|██        | 1017/5000 [1:38:54<6:21:29,  5.75s/it]
 20%|██        | 1018/5000 [1:38:58<5:53:04,  5.32s/it]
 20%|██        | 1019/5000 [1:39:03<5:43:10,  5.17s/it]
 20%|██        | 1020/5000 [1:39:06<5:13:58,  4.73s/it]
 20%|██        | 1021/5000 [1:39:11<5:07:33,  4.64s/it]
 20%|██        | 1022/5000 [1:39:15<4:56:32,  4.47s/it]
 20%|██        | 1023/5000 [1:39:19<4:42:33,  4.26s/it]
 20%|██        | 1024/5000 [1:39:23<4:32:55,  4.12s/it]
 20%|██        | 1025/5000 [1:39:27<4:38:48,  4.21s/it]
                                                       
 20%|██        | 1025/5000 [1:39:27<4:38:48,  4.21s/it]
 21%|██        | 1026/5000 [1:39:31<4:29:24,  4.07s/it]
 21%|██        | 1027/5000 [1:39:34<4:21:27,  3.95s/it]
 21%|██        | 1028/5000 [1:39:39<4:34:58,  4.15s/it]
 21%|██        | 1029/5000 [1:39:43<4:26:07,  4.02s/it]
 21%|██        | 1030/5000 [1:39:47<4:37:18,  4.19s/it]
 21%|██        | 1031/5000 [1:39:51<4:27:20,  4.04s/it]
 21%|██        | 1032/5000 [1:39:55<4:21:00,  3.95s/it]
 21%|██        | 1033/5000 [1:39:58<4:17:22,  3.89s/it]
 21%|██        | 1034/5000 [1:40:02<4:18:29,  3.91s/it]
 21%|██        | 1035/5000 [1:40:08<4:44:43,  4.31s/it]
 21%|██        | 1036/5000 [1:40:11<4:32:23,  4.12s/it]
 21%|██        | 1037/5000 [1:40:15<4:22:56,  3.98s/it]
 21%|██        | 1038/5000 [1:40:20<4:34:51,  4.16s/it]
 21%|██        | 1039/5000 [1:40:24<4:36:24,  4.19s/it]
 21%|██        | 1040/5000 [1:40:27<4:26:01,  4.03s/it]
 21%|██        | 1041/5000 [1:40:32<4:39:11,  4.23s/it]
 21%|██        | 1042/5000 [1:40:36<4:27:59,  4.06s/it]
 21%|██        | 1043/5000 [1:40:39<4:19:40,  3.94s/it]
 21%|██        | 1044/5000 [1:40:44<4:38:09,  4.22s/it]
 21%|██        | 1045/5000 [1:40:48<4:28:27,  4.07s/it]
 21%|██        | 1046/5000 [1:40:52<4:21:51,  3.97s/it]
 21%|██        | 1047/5000 [1:40:56<4:31:21,  4.12s/it]
 21%|██        | 1048/5000 [1:41:00<4:21:36,  3.97s/it]
 21%|██        | 1049/5000 [1:41:04<4:15:56,  3.89s/it]
 21%|██        | 1050/5000 [1:41:07<4:12:38,  3.84s/it]
                                                       
 21%|██        | 1050/5000 [1:41:07<4:12:38,  3.84s/it]
 21%|██        | 1051/5000 [1:41:11<4:10:32,  3.81s/it]
 21%|██        | 1052/5000 [1:41:15<4:09:18,  3.79s/it]
 21%|██        | 1053/5000 [1:41:20<4:27:27,  4.07s/it]
 21%|██        | 1054/5000 [1:41:23<4:20:29,  3.96s/it]
 21%|██        | 1055/5000 [1:41:28<4:43:50,  4.32s/it]
 21%|██        | 1056/5000 [1:41:32<4:31:01,  4.12s/it]
 21%|██        | 1057/5000 [1:41:36<4:21:47,  3.98s/it]
 21%|██        | 1058/5000 [1:41:39<4:15:18,  3.89s/it]
 21%|██        | 1059/5000 [1:41:43<4:12:44,  3.85s/it]
 21%|██        | 1060/5000 [1:41:47<4:18:28,  3.94s/it]
 21%|██        | 1061/5000 [1:41:52<4:32:32,  4.15s/it]
 21%|██        | 1062/5000 [1:41:56<4:23:32,  4.02s/it]
 21%|██▏       | 1063/5000 [1:41:59<4:17:07,  3.92s/it]
 21%|██▏       | 1064/5000 [1:42:04<4:39:17,  4.26s/it]
 21%|██▏       | 1065/5000 [1:42:08<4:27:36,  4.08s/it]
 21%|██▏       | 1066/5000 [1:42:12<4:19:53,  3.96s/it]
 21%|██▏       | 1067/5000 [1:42:15<4:13:59,  3.87s/it]
 21%|██▏       | 1068/5000 [1:42:19<4:10:37,  3.82s/it]
 21%|██▏       | 1069/5000 [1:42:23<4:07:39,  3.78s/it]
 21%|██▏       | 1070/5000 [1:42:28<4:35:10,  4.20s/it]
 21%|██▏       | 1071/5000 [1:42:32<4:25:07,  4.05s/it]
 21%|██▏       | 1072/5000 [1:42:36<4:34:11,  4.19s/it]
 21%|██▏       | 1073/5000 [1:42:40<4:24:20,  4.04s/it]
 21%|██▏       | 1074/5000 [1:42:44<4:17:34,  3.94s/it]
 22%|██▏       | 1075/5000 [1:42:47<4:12:39,  3.86s/it]
                                                       
 22%|██▏       | 1075/5000 [1:42:47<4:12:39,  3.86s/it]
 22%|██▏       | 1076/5000 [1:42:51<4:10:23,  3.83s/it]
 22%|██▏       | 1077/5000 [1:42:55<4:06:59,  3.78s/it]
 22%|██▏       | 1078/5000 [1:43:00<4:30:50,  4.14s/it]
 22%|██▏       | 1079/5000 [1:43:04<4:30:01,  4.13s/it]
 22%|██▏       | 1080/5000 [1:43:07<4:21:34,  4.00s/it]
 22%|██▏       | 1081/5000 [1:43:12<4:35:05,  4.21s/it]
 22%|██▏       | 1082/5000 [1:43:16<4:24:35,  4.05s/it]
 22%|██▏       | 1083/5000 [1:43:20<4:17:25,  3.94s/it]
 22%|██▏       | 1084/5000 [1:43:23<4:12:54,  3.88s/it]
 22%|██▏       | 1085/5000 [1:43:27<4:09:48,  3.83s/it]
 22%|██▏       | 1086/5000 [1:43:31<4:08:51,  3.81s/it]
 22%|██▏       | 1087/5000 [1:43:36<4:27:13,  4.10s/it]
 22%|██▏       | 1088/5000 [1:43:39<4:19:28,  3.98s/it]
 22%|██▏       | 1089/5000 [1:43:44<4:33:17,  4.19s/it]
 22%|██▏       | 1090/5000 [1:43:49<4:49:30,  4.44s/it]
 22%|██▏       | 1091/5000 [1:43:53<4:34:12,  4.21s/it]
 22%|██▏       | 1092/5000 [1:43:56<4:22:46,  4.03s/it]
 22%|██▏       | 1093/5000 [1:44:00<4:15:47,  3.93s/it]
 22%|██▏       | 1094/5000 [1:44:04<4:15:40,  3.93s/it]
 22%|██▏       | 1095/5000 [1:44:08<4:11:12,  3.86s/it]
 22%|██▏       | 1096/5000 [1:44:13<4:33:06,  4.20s/it]
 22%|██▏       | 1097/5000 [1:44:16<4:23:29,  4.05s/it]
 22%|██▏       | 1098/5000 [1:44:21<4:32:50,  4.20s/it]
 22%|██▏       | 1099/5000 [1:44:24<4:22:40,  4.04s/it]
 22%|██▏       | 1100/5000 [1:44:28<4:15:45,  3.93s/it]
                                                       
 22%|██▏       | 1100/5000 [1:44:28<4:15:45,  3.93s/it]
 22%|██▏       | 1101/5000 [1:44:32<4:11:14,  3.87s/it]
 22%|██▏       | 1102/5000 [1:44:36<4:07:35,  3.81s/it]
 22%|██▏       | 1103/5000 [1:44:39<4:05:06,  3.77s/it]
 22%|██▏       | 1104/5000 [1:44:43<4:03:11,  3.75s/it]
 22%|██▏       | 1105/5000 [1:44:48<4:23:33,  4.06s/it]
 22%|██▏       | 1106/5000 [1:44:52<4:31:56,  4.19s/it]
 22%|██▏       | 1107/5000 [1:44:56<4:22:50,  4.05s/it]
 22%|██▏       | 1108/5000 [1:45:00<4:30:17,  4.17s/it]
 22%|██▏       | 1109/5000 [1:45:05<4:36:42,  4.27s/it]
 22%|██▏       | 1110/5000 [1:45:09<4:26:00,  4.10s/it]
 22%|██▏       | 1111/5000 [1:45:12<4:18:02,  3.98s/it]
 22%|██▏       | 1112/5000 [1:45:16<4:12:50,  3.90s/it]
 22%|██▏       | 1113/5000 [1:45:21<4:26:45,  4.12s/it]
 22%|██▏       | 1114/5000 [1:45:25<4:35:03,  4.25s/it]
 22%|██▏       | 1115/5000 [1:45:29<4:24:53,  4.09s/it]
 22%|██▏       | 1116/5000 [1:45:33<4:17:17,  3.97s/it]
 22%|██▏       | 1117/5000 [1:45:36<4:12:19,  3.90s/it]
 22%|██▏       | 1118/5000 [1:45:40<4:08:14,  3.84s/it]
 22%|██▏       | 1119/5000 [1:45:44<4:04:47,  3.78s/it]
 22%|██▏       | 1120/5000 [1:45:47<4:03:41,  3.77s/it]
 22%|██▏       | 1121/5000 [1:45:51<4:08:27,  3.84s/it]
 22%|██▏       | 1122/5000 [1:45:57<4:39:48,  4.33s/it]
 22%|██▏       | 1123/5000 [1:46:01<4:32:47,  4.22s/it]
 22%|██▏       | 1124/5000 [1:46:05<4:22:21,  4.06s/it]
 22%|██▎       | 1125/5000 [1:46:08<4:14:27,  3.94s/it]
                                                       
 22%|██▎       | 1125/5000 [1:46:08<4:14:27,  3.94s/it]
 23%|██▎       | 1126/5000 [1:46:12<4:09:13,  3.86s/it]
 23%|██▎       | 1127/5000 [1:46:16<4:05:41,  3.81s/it]
 23%|██▎       | 1128/5000 [1:46:19<4:03:39,  3.78s/it]
 23%|██▎       | 1129/5000 [1:46:23<4:01:22,  3.74s/it]
 23%|██▎       | 1130/5000 [1:46:27<4:01:55,  3.75s/it]
 23%|██▎       | 1131/5000 [1:46:33<4:46:41,  4.45s/it]
 23%|██▎       | 1132/5000 [1:46:37<4:43:29,  4.40s/it]
 23%|██▎       | 1133/5000 [1:46:41<4:29:52,  4.19s/it]
 23%|██▎       | 1134/5000 [1:46:44<4:20:59,  4.05s/it]
 23%|██▎       | 1135/5000 [1:46:48<4:14:47,  3.96s/it]
 23%|██▎       | 1136/5000 [1:46:52<4:10:10,  3.88s/it]
 23%|██▎       | 1137/5000 [1:46:56<4:07:44,  3.85s/it]
 23%|██▎       | 1138/5000 [1:46:59<4:04:14,  3.79s/it]
 23%|██▎       | 1139/5000 [1:47:04<4:22:05,  4.07s/it]
 23%|██▎       | 1140/5000 [1:47:09<4:30:06,  4.20s/it]
 23%|██▎       | 1141/5000 [1:47:12<4:20:16,  4.05s/it]
 23%|██▎       | 1142/5000 [1:47:16<4:13:37,  3.94s/it]
 23%|██▎       | 1143/5000 [1:47:20<4:07:27,  3.85s/it]
 23%|██▎       | 1144/5000 [1:47:23<4:03:59,  3.80s/it]
 23%|██▎       | 1145/5000 [1:47:27<4:01:16,  3.76s/it]
 23%|██▎       | 1146/5000 [1:47:31<3:59:19,  3.73s/it]
 23%|██▎       | 1147/5000 [1:47:35<4:06:15,  3.83s/it]
 23%|██▎       | 1148/5000 [1:47:40<4:36:35,  4.31s/it]
 23%|██▎       | 1149/5000 [1:47:44<4:24:58,  4.13s/it]
 23%|██▎       | 1150/5000 [1:47:47<4:16:43,  4.00s/it]
                                                       
 23%|██▎       | 1150/5000 [1:47:47<4:16:43,  4.00s/it]
 23%|██▎       | 1151/5000 [1:47:51<4:13:56,  3.96s/it]
 23%|██▎       | 1152/5000 [1:47:55<4:13:30,  3.95s/it]
 23%|██▎       | 1153/5000 [1:47:59<4:07:57,  3.87s/it]
 23%|██▎       | 1154/5000 [1:48:03<4:04:12,  3.81s/it]
 23%|██▎       | 1155/5000 [1:48:06<4:02:28,  3.78s/it]
 23%|██▎       | 1156/5000 [1:48:10<4:05:42,  3.84s/it]
 23%|██▎       | 1157/5000 [1:48:16<4:38:41,  4.35s/it]
 23%|██▎       | 1158/5000 [1:48:20<4:35:12,  4.30s/it]
 23%|██▎       | 1159/5000 [1:48:24<4:31:11,  4.24s/it]
 23%|██▎       | 1160/5000 [1:48:28<4:21:07,  4.08s/it]
 23%|██▎       | 1161/5000 [1:48:32<4:13:45,  3.97s/it]
 23%|██▎       | 1162/5000 [1:48:35<4:09:31,  3.90s/it]
 23%|██▎       | 1163/5000 [1:48:39<4:05:36,  3.84s/it]
 23%|██▎       | 1164/5000 [1:48:43<4:02:51,  3.80s/it]
 23%|██▎       | 1165/5000 [1:48:47<4:20:09,  4.07s/it]
 23%|██▎       | 1166/5000 [1:48:52<4:32:17,  4.26s/it]
 23%|██▎       | 1167/5000 [1:48:56<4:21:19,  4.09s/it]
 23%|██▎       | 1168/5000 [1:49:00<4:20:36,  4.08s/it]
 23%|██▎       | 1169/5000 [1:49:03<4:12:26,  3.95s/it]
 23%|██▎       | 1170/5000 [1:49:07<4:12:55,  3.96s/it]
 23%|██▎       | 1171/5000 [1:49:11<4:08:41,  3.90s/it]
 23%|██▎       | 1172/5000 [1:49:15<4:03:56,  3.82s/it]
 23%|██▎       | 1173/5000 [1:49:19<4:01:06,  3.78s/it]
 23%|██▎       | 1174/5000 [1:49:23<4:19:38,  4.07s/it]
 24%|██▎       | 1175/5000 [1:49:28<4:26:39,  4.18s/it]
                                                       
 24%|██▎       | 1175/5000 [1:49:28<4:26:39,  4.18s/it]
 24%|██▎       | 1176/5000 [1:49:32<4:36:20,  4.34s/it]
 24%|██▎       | 1177/5000 [1:49:36<4:30:33,  4.25s/it]
 24%|██▎       | 1178/5000 [1:49:40<4:19:50,  4.08s/it]
 24%|██▎       | 1179/5000 [1:49:44<4:11:42,  3.95s/it]
 24%|██▎       | 1180/5000 [1:49:47<4:06:14,  3.87s/it]
 24%|██▎       | 1181/5000 [1:49:51<4:02:59,  3.82s/it]
 24%|██▎       | 1182/5000 [1:49:55<4:00:47,  3.78s/it]
 24%|██▎       | 1183/5000 [1:49:59<3:59:30,  3.76s/it]
 24%|██▎       | 1184/5000 [1:50:04<4:30:59,  4.26s/it]
 24%|██▎       | 1185/5000 [1:50:08<4:21:43,  4.12s/it]
 24%|██▎       | 1186/5000 [1:50:12<4:29:08,  4.23s/it]
 24%|██▎       | 1187/5000 [1:50:16<4:19:38,  4.09s/it]
 24%|██▍       | 1188/5000 [1:50:20<4:22:08,  4.13s/it]
 24%|██▍       | 1189/5000 [1:50:25<4:38:03,  4.38s/it]
 24%|██▍       | 1190/5000 [1:50:30<4:37:07,  4.36s/it]
 24%|██▍       | 1191/5000 [1:50:33<4:24:11,  4.16s/it]
 24%|██▍       | 1192/5000 [1:50:38<4:34:02,  4.32s/it]
 24%|██▍       | 1193/5000 [1:50:43<4:43:07,  4.46s/it]
 24%|██▍       | 1194/5000 [1:50:46<4:27:56,  4.22s/it]
 24%|██▍       | 1195/5000 [1:50:51<4:38:05,  4.39s/it]
 24%|██▍       | 1196/5000 [1:50:55<4:25:41,  4.19s/it]
 24%|██▍       | 1197/5000 [1:50:59<4:16:29,  4.05s/it]
 24%|██▍       | 1198/5000 [1:51:02<4:10:12,  3.95s/it]
 24%|██▍       | 1199/5000 [1:51:06<4:05:49,  3.88s/it]
 24%|██▍       | 1200/5000 [1:51:10<4:04:00,  3.85s/it]
                                                       
 24%|██▍       | 1200/5000 [1:51:10<4:04:00,  3.85s/it]
 24%|██▍       | 1201/5000 [1:51:16<4:38:34,  4.40s/it]
 24%|██▍       | 1202/5000 [1:51:19<4:25:40,  4.20s/it]
 24%|██▍       | 1203/5000 [1:51:23<4:17:08,  4.06s/it]
 24%|██▍       | 1204/5000 [1:51:27<4:10:21,  3.96s/it]
 24%|██▍       | 1205/5000 [1:51:30<4:05:27,  3.88s/it]
 24%|██▍       | 1206/5000 [1:51:34<4:01:52,  3.83s/it]
 24%|██▍       | 1207/5000 [1:51:38<4:00:09,  3.80s/it]
 24%|██▍       | 1208/5000 [1:51:42<3:58:33,  3.77s/it]
 24%|██▍       | 1209/5000 [1:51:47<4:24:45,  4.19s/it]
 24%|██▍       | 1210/5000 [1:51:52<4:42:49,  4.48s/it]
 24%|██▍       | 1211/5000 [1:51:56<4:27:53,  4.24s/it]
 24%|██▍       | 1212/5000 [1:51:59<4:17:15,  4.07s/it]
 24%|██▍       | 1213/5000 [1:52:03<4:09:51,  3.96s/it]
 24%|██▍       | 1214/5000 [1:52:07<4:06:27,  3.91s/it]
 24%|██▍       | 1215/5000 [1:52:10<4:03:36,  3.86s/it]
 24%|██▍       | 1216/5000 [1:52:14<4:03:34,  3.86s/it]
 24%|██▍       | 1217/5000 [1:52:18<4:00:49,  3.82s/it]
 24%|██▍       | 1218/5000 [1:52:23<4:15:57,  4.06s/it]
 24%|██▍       | 1219/5000 [1:52:28<4:40:06,  4.44s/it]
 24%|██▍       | 1220/5000 [1:52:32<4:25:20,  4.21s/it]
 24%|██▍       | 1221/5000 [1:52:36<4:33:04,  4.34s/it]
 24%|██▍       | 1222/5000 [1:52:40<4:21:22,  4.15s/it]
 24%|██▍       | 1223/5000 [1:52:44<4:12:28,  4.01s/it]
 24%|██▍       | 1224/5000 [1:52:47<4:06:34,  3.92s/it]
 24%|██▍       | 1225/5000 [1:52:51<4:02:37,  3.86s/it]
                                                       
 24%|██▍       | 1225/5000 [1:52:51<4:02:37,  3.86s/it]
 25%|██▍       | 1226/5000 [1:52:55<4:00:30,  3.82s/it]
 25%|██▍       | 1227/5000 [1:53:00<4:18:05,  4.10s/it]
 25%|██▍       | 1228/5000 [1:53:05<4:40:16,  4.46s/it]
 25%|██▍       | 1229/5000 [1:53:09<4:26:24,  4.24s/it]
 25%|██▍       | 1230/5000 [1:53:12<4:16:15,  4.08s/it]
 25%|██▍       | 1231/5000 [1:53:16<4:09:22,  3.97s/it]
 25%|██▍       | 1232/5000 [1:53:20<4:15:42,  4.07s/it]
 25%|██▍       | 1233/5000 [1:53:24<4:08:43,  3.96s/it]
 25%|██▍       | 1234/5000 [1:53:28<4:04:07,  3.89s/it]
 25%|██▍       | 1235/5000 [1:53:32<4:01:37,  3.85s/it]
 25%|██▍       | 1236/5000 [1:53:37<4:35:15,  4.39s/it]
 25%|██▍       | 1237/5000 [1:53:41<4:21:13,  4.17s/it]
 25%|██▍       | 1238/5000 [1:53:45<4:12:13,  4.02s/it]
 25%|██▍       | 1239/5000 [1:53:48<4:05:50,  3.92s/it]
 25%|██▍       | 1240/5000 [1:53:52<4:01:57,  3.86s/it]
 25%|██▍       | 1241/5000 [1:53:56<3:59:02,  3.82s/it]
 25%|██▍       | 1242/5000 [1:53:59<3:57:22,  3.79s/it]
 25%|██▍       | 1243/5000 [1:54:04<4:18:17,  4.12s/it]
 25%|██▍       | 1244/5000 [1:54:09<4:25:00,  4.23s/it]
 25%|██▍       | 1245/5000 [1:54:13<4:32:56,  4.36s/it]
 25%|██▍       | 1246/5000 [1:54:18<4:35:52,  4.41s/it]
 25%|██▍       | 1247/5000 [1:54:22<4:22:37,  4.20s/it]
 25%|██▍       | 1248/5000 [1:54:25<4:13:55,  4.06s/it]
 25%|██▍       | 1249/5000 [1:54:29<4:07:59,  3.97s/it]
 25%|██▌       | 1250/5000 [1:54:33<4:03:15,  3.89s/it]
                                                       
 25%|██▌       | 1250/5000 [1:54:33<4:03:15,  3.89s/it]
 25%|██▌       | 1251/5000 [1:54:37<3:59:29,  3.83s/it]
 25%|██▌       | 1252/5000 [1:54:40<3:56:07,  3.78s/it]
 25%|██▌       | 1253/5000 [1:54:44<3:53:47,  3.74s/it]
 25%|██▌       | 1254/5000 [1:54:49<4:11:02,  4.02s/it]
 25%|██▌       | 1255/5000 [1:54:53<4:26:09,  4.26s/it]
 25%|██▌       | 1256/5000 [1:54:57<4:15:49,  4.10s/it]
 25%|██▌       | 1257/5000 [1:55:01<4:09:02,  3.99s/it]
 25%|██▌       | 1258/5000 [1:55:05<4:03:41,  3.91s/it]
 25%|██▌       | 1259/5000 [1:55:08<4:00:04,  3.85s/it]
 25%|██▌       | 1260/5000 [1:55:12<3:57:21,  3.81s/it]
 25%|██▌       | 1261/5000 [1:55:16<3:55:33,  3.78s/it]
 25%|██▌       | 1262/5000 [1:55:21<4:19:17,  4.16s/it]
 25%|██▌       | 1263/5000 [1:55:24<4:11:07,  4.03s/it]
 25%|██▌       | 1264/5000 [1:55:29<4:20:52,  4.19s/it]
 25%|██▌       | 1265/5000 [1:55:33<4:12:28,  4.06s/it]
 25%|██▌       | 1266/5000 [1:55:37<4:06:35,  3.96s/it]
 25%|██▌       | 1267/5000 [1:55:40<4:02:25,  3.90s/it]
 25%|██▌       | 1268/5000 [1:55:44<4:02:13,  3.89s/it]
 25%|██▌       | 1269/5000 [1:55:48<4:07:17,  3.98s/it]
 25%|██▌       | 1270/5000 [1:55:54<4:39:10,  4.49s/it]
 25%|██▌       | 1271/5000 [1:55:58<4:24:51,  4.26s/it]
 25%|██▌       | 1272/5000 [1:56:02<4:33:09,  4.40s/it]
 25%|██▌       | 1273/5000 [1:56:06<4:25:00,  4.27s/it]
 25%|██▌       | 1274/5000 [1:56:10<4:15:12,  4.11s/it]
 26%|██▌       | 1275/5000 [1:56:14<4:09:07,  4.01s/it]
                                                       
 26%|██▌       | 1275/5000 [1:56:14<4:09:07,  4.01s/it]
 26%|██▌       | 1276/5000 [1:56:19<4:19:09,  4.18s/it]
 26%|██▌       | 1277/5000 [1:56:22<4:11:00,  4.05s/it]
 26%|██▌       | 1278/5000 [1:56:26<4:05:30,  3.96s/it]
 26%|██▌       | 1279/5000 [1:56:32<4:49:27,  4.67s/it]
 26%|██▌       | 1280/5000 [1:56:36<4:31:50,  4.38s/it]
 26%|██▌       | 1281/5000 [1:56:41<4:50:15,  4.68s/it]
 26%|██▌       | 1282/5000 [1:56:45<4:32:34,  4.40s/it]
 26%|██▌       | 1283/5000 [1:56:49<4:21:26,  4.22s/it]
 26%|██▌       | 1284/5000 [1:56:53<4:13:08,  4.09s/it]
 26%|██▌       | 1285/5000 [1:56:56<4:06:25,  3.98s/it]
 26%|██▌       | 1286/5000 [1:57:00<4:01:05,  3.89s/it]
 26%|██▌       | 1287/5000 [1:57:04<3:58:25,  3.85s/it]
 26%|██▌       | 1288/5000 [1:57:09<4:15:02,  4.12s/it]
 26%|██▌       | 1289/5000 [1:57:12<4:07:34,  4.00s/it]
 26%|██▌       | 1290/5000 [1:57:16<4:02:36,  3.92s/it]
 26%|██▌       | 1291/5000 [1:57:21<4:17:24,  4.16s/it]
 26%|██▌       | 1292/5000 [1:57:25<4:09:19,  4.03s/it]
 26%|██▌       | 1293/5000 [1:57:28<4:02:49,  3.93s/it]
 26%|██▌       | 1294/5000 [1:57:32<3:58:51,  3.87s/it]
 26%|██▌       | 1295/5000 [1:57:36<3:56:13,  3.83s/it]
 26%|██▌       | 1296/5000 [1:57:39<3:54:55,  3.81s/it]
 26%|██▌       | 1297/5000 [1:57:45<4:18:15,  4.18s/it]
 26%|██▌       | 1298/5000 [1:57:49<4:22:57,  4.26s/it]
 26%|██▌       | 1299/5000 [1:57:53<4:12:36,  4.10s/it]
 26%|██▌       | 1300/5000 [1:57:57<4:11:47,  4.08s/it]
                                                       
 26%|██▌       | 1300/5000 [1:57:57<4:11:47,  4.08s/it]
 26%|██▌       | 1301/5000 [1:58:00<4:04:59,  3.97s/it]
 26%|██▌       | 1302/5000 [1:58:04<3:59:39,  3.89s/it]
 26%|██▌       | 1303/5000 [1:58:08<3:55:21,  3.82s/it]
 26%|██▌       | 1304/5000 [1:58:12<3:52:40,  3.78s/it]
 26%|██▌       | 1305/5000 [1:58:15<3:50:47,  3.75s/it]
 26%|██▌       | 1306/5000 [1:58:20<4:07:13,  4.02s/it]
 26%|██▌       | 1307/5000 [1:58:24<4:01:12,  3.92s/it]
 26%|██▌       | 1308/5000 [1:58:29<4:26:32,  4.33s/it]
 26%|██▌       | 1309/5000 [1:58:33<4:18:45,  4.21s/it]
 26%|██▌       | 1310/5000 [1:58:36<4:09:53,  4.06s/it]
 26%|██▌       | 1311/5000 [1:58:40<4:03:49,  3.97s/it]
 26%|██▌       | 1312/5000 [1:58:44<3:59:28,  3.90s/it]
 26%|██▋       | 1313/5000 [1:58:48<3:56:32,  3.85s/it]
 26%|██▋       | 1314/5000 [1:58:52<4:13:23,  4.12s/it]
 26%|██▋       | 1315/5000 [1:58:56<4:06:04,  4.01s/it]
 26%|██▋       | 1316/5000 [1:59:00<4:00:57,  3.92s/it]
 26%|██▋       | 1317/5000 [1:59:04<4:12:11,  4.11s/it]
 26%|██▋       | 1318/5000 [1:59:08<4:05:19,  4.00s/it]
 26%|██▋       | 1319/5000 [1:59:12<4:01:06,  3.93s/it]
 26%|██▋       | 1320/5000 [1:59:16<3:56:50,  3.86s/it]
 26%|██▋       | 1321/5000 [1:59:21<4:15:56,  4.17s/it]
 26%|██▋       | 1322/5000 [1:59:24<4:08:34,  4.06s/it]
 26%|██▋       | 1323/5000 [1:59:28<4:02:40,  3.96s/it]
 26%|██▋       | 1324/5000 [1:59:32<3:58:04,  3.89s/it]
 26%|██▋       | 1325/5000 [1:59:37<4:16:11,  4.18s/it]
                                                       
 26%|██▋       | 1325/5000 [1:59:37<4:16:11,  4.18s/it]
 27%|██▋       | 1326/5000 [1:59:40<4:07:37,  4.04s/it]
 27%|██▋       | 1327/5000 [1:59:44<4:01:21,  3.94s/it]
 27%|██▋       | 1328/5000 [1:59:48<3:56:40,  3.87s/it]
 27%|██▋       | 1329/5000 [1:59:52<4:00:33,  3.93s/it]
 27%|██▋       | 1330/5000 [1:59:57<4:16:24,  4.19s/it]
 27%|██▋       | 1331/5000 [2:00:00<4:08:20,  4.06s/it]
 27%|██▋       | 1332/5000 [2:00:04<4:01:53,  3.96s/it]
 27%|██▋       | 1333/5000 [2:00:08<3:58:17,  3.90s/it]
 27%|██▋       | 1334/5000 [2:00:13<4:15:14,  4.18s/it]
 27%|██▋       | 1335/5000 [2:00:16<4:06:37,  4.04s/it]
 27%|██▋       | 1336/5000 [2:00:20<4:01:03,  3.95s/it]
 27%|██▋       | 1337/5000 [2:00:24<4:01:09,  3.95s/it]
 27%|██▋       | 1338/5000 [2:00:29<4:18:20,  4.23s/it]
 27%|██▋       | 1339/5000 [2:00:33<4:09:03,  4.08s/it]
 27%|██▋       | 1340/5000 [2:00:37<4:02:50,  3.98s/it]
 27%|██▋       | 1341/5000 [2:00:40<3:58:12,  3.91s/it]
 27%|██▋       | 1342/5000 [2:00:44<3:55:35,  3.86s/it]
 27%|██▋       | 1343/5000 [2:00:49<4:10:02,  4.10s/it]
 27%|██▋       | 1344/5000 [2:00:52<4:03:33,  4.00s/it]
 27%|██▋       | 1345/5000 [2:00:57<4:21:21,  4.29s/it]
 27%|██▋       | 1346/5000 [2:01:01<4:10:58,  4.12s/it]
 27%|██▋       | 1347/5000 [2:01:05<4:03:27,  4.00s/it]
 27%|██▋       | 1348/5000 [2:01:09<3:57:56,  3.91s/it]
 27%|██▋       | 1349/5000 [2:01:12<3:53:44,  3.84s/it]
 27%|██▋       | 1350/5000 [2:01:16<3:50:13,  3.78s/it]
                                                       
 27%|██▋       | 1350/5000 [2:01:16<3:50:13,  3.78s/it]
 27%|██▋       | 1351/5000 [2:01:20<3:48:31,  3.76s/it]
 27%|██▋       | 1352/5000 [2:01:24<4:06:18,  4.05s/it]
 27%|██▋       | 1353/5000 [2:01:28<3:59:16,  3.94s/it]
 27%|██▋       | 1354/5000 [2:01:33<4:14:17,  4.18s/it]
 27%|██▋       | 1355/5000 [2:01:36<4:06:09,  4.05s/it]
 27%|██▋       | 1356/5000 [2:01:40<4:00:12,  3.96s/it]
 27%|██▋       | 1357/5000 [2:01:44<3:55:50,  3.88s/it]
 27%|██▋       | 1358/5000 [2:01:48<3:51:59,  3.82s/it]
 27%|██▋       | 1359/5000 [2:01:51<3:49:26,  3.78s/it]
 27%|██▋       | 1360/5000 [2:01:56<4:15:27,  4.21s/it]
 27%|██▋       | 1361/5000 [2:02:00<4:06:16,  4.06s/it]
 27%|██▋       | 1362/5000 [2:02:05<4:24:41,  4.37s/it]
 27%|██▋       | 1363/5000 [2:02:09<4:12:42,  4.17s/it]
 27%|██▋       | 1364/5000 [2:02:13<4:03:42,  4.02s/it]
 27%|██▋       | 1365/5000 [2:02:16<3:58:40,  3.94s/it]
 27%|██▋       | 1366/5000 [2:02:20<3:54:12,  3.87s/it]
 27%|██▋       | 1367/5000 [2:02:24<3:51:26,  3.82s/it]
 27%|██▋       | 1368/5000 [2:02:28<3:49:06,  3.78s/it]
 27%|██▋       | 1369/5000 [2:02:31<3:47:54,  3.77s/it]
 27%|██▋       | 1370/5000 [2:02:37<4:15:40,  4.23s/it]
 27%|██▋       | 1371/5000 [2:02:41<4:21:35,  4.33s/it]
 27%|██▋       | 1372/5000 [2:02:45<4:10:34,  4.14s/it]
 27%|██▋       | 1373/5000 [2:02:49<4:02:45,  4.02s/it]
 27%|██▋       | 1374/5000 [2:02:52<3:57:27,  3.93s/it]
 28%|██▊       | 1375/5000 [2:02:56<3:53:38,  3.87s/it]
                                                       
 28%|██▊       | 1375/5000 [2:02:56<3:53:38,  3.87s/it]
 28%|██▊       | 1376/5000 [2:03:00<3:49:50,  3.81s/it]
 28%|██▊       | 1377/5000 [2:03:03<3:48:42,  3.79s/it]
 28%|██▊       | 1378/5000 [2:03:07<3:47:14,  3.76s/it]
 28%|██▊       | 1379/5000 [2:03:12<4:06:55,  4.09s/it]
 28%|██▊       | 1380/5000 [2:03:17<4:27:31,  4.43s/it]
 28%|██▊       | 1381/5000 [2:03:21<4:14:16,  4.22s/it]
 28%|██▊       | 1382/5000 [2:03:25<4:05:52,  4.08s/it]
 28%|██▊       | 1383/5000 [2:03:28<3:59:25,  3.97s/it]
 28%|██▊       | 1384/5000 [2:03:32<3:54:38,  3.89s/it]
 28%|██▊       | 1385/5000 [2:03:36<3:51:31,  3.84s/it]
 28%|██▊       | 1386/5000 [2:03:40<3:49:13,  3.81s/it]
 28%|██▊       | 1387/5000 [2:03:45<4:14:30,  4.23s/it]
 28%|██▊       | 1388/5000 [2:03:48<4:05:14,  4.07s/it]
 28%|██▊       | 1389/5000 [2:03:53<4:13:12,  4.21s/it]
 28%|██▊       | 1390/5000 [2:03:57<4:04:53,  4.07s/it]
 28%|██▊       | 1391/5000 [2:04:01<4:08:45,  4.14s/it]
 28%|██▊       | 1392/5000 [2:04:06<4:16:05,  4.26s/it]
 28%|██▊       | 1393/5000 [2:04:09<4:06:12,  4.10s/it]
 28%|██▊       | 1394/5000 [2:04:13<3:59:32,  3.99s/it]
 28%|██▊       | 1395/5000 [2:04:18<4:13:35,  4.22s/it]
 28%|██▊       | 1396/5000 [2:04:22<4:05:17,  4.08s/it]
 28%|██▊       | 1397/5000 [2:04:25<3:59:15,  3.98s/it]
 28%|██▊       | 1398/5000 [2:04:30<4:16:37,  4.27s/it]
 28%|██▊       | 1399/5000 [2:04:34<4:06:29,  4.11s/it]
 28%|██▊       | 1400/5000 [2:04:38<3:59:35,  3.99s/it]
                                                       
 28%|██▊       | 1400/5000 [2:04:38<3:59:35,  3.99s/it]
 28%|██▊       | 1401/5000 [2:04:41<3:54:11,  3.90s/it]
 28%|██▊       | 1402/5000 [2:04:45<3:51:05,  3.85s/it]
 28%|██▊       | 1403/5000 [2:04:49<3:48:51,  3.82s/it]
 28%|██▊       | 1404/5000 [2:04:54<4:06:23,  4.11s/it]
 28%|██▊       | 1405/5000 [2:04:58<4:13:35,  4.23s/it]
 28%|██▊       | 1406/5000 [2:05:02<4:03:26,  4.06s/it]
 28%|██▊       | 1407/5000 [2:05:06<3:57:00,  3.96s/it]
 28%|██▊       | 1408/5000 [2:05:09<3:52:28,  3.88s/it]
 28%|██▊       | 1409/5000 [2:05:13<3:50:21,  3.85s/it]
 28%|██▊       | 1410/5000 [2:05:17<3:47:46,  3.81s/it]
 28%|██▊       | 1411/5000 [2:05:20<3:45:57,  3.78s/it]
 28%|██▊       | 1412/5000 [2:05:24<3:43:33,  3.74s/it]
 28%|██▊       | 1413/5000 [2:05:29<4:01:05,  4.03s/it]
 28%|██▊       | 1414/5000 [2:05:34<4:12:51,  4.23s/it]
 28%|██▊       | 1415/5000 [2:05:37<4:02:46,  4.06s/it]
 28%|██▊       | 1416/5000 [2:05:41<3:56:15,  3.96s/it]
 28%|██▊       | 1417/5000 [2:05:45<3:52:01,  3.89s/it]
 28%|██▊       | 1418/5000 [2:05:48<3:49:02,  3.84s/it]
 28%|██▊       | 1419/5000 [2:05:52<3:48:08,  3.82s/it]
 28%|██▊       | 1420/5000 [2:05:57<4:06:24,  4.13s/it]
 28%|██▊       | 1421/5000 [2:06:01<3:57:52,  3.99s/it]
 28%|██▊       | 1422/5000 [2:06:06<4:15:34,  4.29s/it]
 28%|██▊       | 1423/5000 [2:06:09<4:06:00,  4.13s/it]
 28%|██▊       | 1424/5000 [2:06:13<3:58:34,  4.00s/it]
 28%|██▊       | 1425/5000 [2:06:17<3:53:03,  3.91s/it]
                                                       
 28%|██▊       | 1425/5000 [2:06:17<3:53:03,  3.91s/it]
 29%|██▊       | 1426/5000 [2:06:21<3:50:47,  3.87s/it]
 29%|██▊       | 1427/5000 [2:06:24<3:47:05,  3.81s/it]
 29%|██▊       | 1428/5000 [2:06:28<3:44:13,  3.77s/it]
 29%|██▊       | 1429/5000 [2:06:32<3:41:41,  3.72s/it]
 29%|██▊       | 1430/5000 [2:06:37<4:09:53,  4.20s/it]
 29%|██▊       | 1431/5000 [2:06:41<4:15:19,  4.29s/it]
 29%|██▊       | 1432/5000 [2:06:45<4:04:54,  4.12s/it]
 29%|██▊       | 1433/5000 [2:06:49<3:58:17,  4.01s/it]
 29%|██▊       | 1434/5000 [2:06:53<3:53:52,  3.94s/it]
 29%|██▊       | 1435/5000 [2:06:56<3:50:30,  3.88s/it]
 29%|██▊       | 1436/5000 [2:07:00<3:48:04,  3.84s/it]
 29%|██▊       | 1437/5000 [2:07:04<3:55:39,  3.97s/it]
 29%|██▉       | 1438/5000 [2:07:09<4:13:53,  4.28s/it]
 29%|██▉       | 1439/5000 [2:07:14<4:18:14,  4.35s/it]
 29%|██▉       | 1440/5000 [2:07:18<4:07:41,  4.17s/it]
 29%|██▉       | 1441/5000 [2:07:21<4:01:09,  4.07s/it]
 29%|██▉       | 1442/5000 [2:07:26<4:02:09,  4.08s/it]
 29%|██▉       | 1443/5000 [2:07:29<3:54:46,  3.96s/it]
 29%|██▉       | 1444/5000 [2:07:33<3:50:01,  3.88s/it]
 29%|██▉       | 1445/5000 [2:07:37<3:47:09,  3.83s/it]
 29%|██▉       | 1446/5000 [2:07:41<4:02:45,  4.10s/it]
 29%|██▉       | 1447/5000 [2:07:46<4:13:34,  4.28s/it]
 29%|██▉       | 1448/5000 [2:07:50<4:02:44,  4.10s/it]
 29%|██▉       | 1449/5000 [2:07:53<3:56:39,  4.00s/it]
 29%|██▉       | 1450/5000 [2:07:57<3:52:23,  3.93s/it]
                                                       
 29%|██▉       | 1450/5000 [2:07:57<3:52:23,  3.93s/it]
 29%|██▉       | 1451/5000 [2:08:01<3:48:48,  3.87s/it]
 29%|██▉       | 1452/5000 [2:08:05<3:45:36,  3.82s/it]
 29%|██▉       | 1453/5000 [2:08:08<3:43:52,  3.79s/it]
 29%|██▉       | 1454/5000 [2:08:12<3:42:21,  3.76s/it]
 29%|██▉       | 1455/5000 [2:08:16<3:41:13,  3.74s/it]
 29%|██▉       | 1456/5000 [2:08:22<4:16:18,  4.34s/it]
 29%|██▉       | 1457/5000 [2:08:26<4:19:16,  4.39s/it]
 29%|██▉       | 1458/5000 [2:08:30<4:06:53,  4.18s/it]
 29%|██▉       | 1459/5000 [2:08:34<4:00:00,  4.07s/it]
 29%|██▉       | 1460/5000 [2:08:38<4:06:33,  4.18s/it]
 29%|██▉       | 1461/5000 [2:08:42<3:58:52,  4.05s/it]
 29%|██▉       | 1462/5000 [2:08:45<3:53:47,  3.96s/it]
 29%|██▉       | 1463/5000 [2:08:50<4:07:45,  4.20s/it]
 29%|██▉       | 1464/5000 [2:08:55<4:15:49,  4.34s/it]
 29%|██▉       | 1465/5000 [2:08:59<4:04:49,  4.16s/it]
 29%|██▉       | 1466/5000 [2:09:02<3:57:25,  4.03s/it]
 29%|██▉       | 1467/5000 [2:09:06<3:51:40,  3.93s/it]
 29%|██▉       | 1468/5000 [2:09:10<3:47:54,  3.87s/it]
 29%|██▉       | 1469/5000 [2:09:14<3:45:24,  3.83s/it]
 29%|██▉       | 1470/5000 [2:09:17<3:43:45,  3.80s/it]
 29%|██▉       | 1471/5000 [2:09:21<3:43:25,  3.80s/it]
 29%|██▉       | 1472/5000 [2:09:26<3:59:33,  4.07s/it]
 29%|██▉       | 1473/5000 [2:09:30<4:07:21,  4.21s/it]
 29%|██▉       | 1474/5000 [2:09:34<3:58:54,  4.07s/it]
 30%|██▉       | 1475/5000 [2:09:38<4:01:24,  4.11s/it]
                                                       
 30%|██▉       | 1475/5000 [2:09:38<4:01:24,  4.11s/it]
 30%|██▉       | 1476/5000 [2:09:43<4:15:29,  4.35s/it]
 30%|██▉       | 1477/5000 [2:09:47<4:04:28,  4.16s/it]
 30%|██▉       | 1478/5000 [2:09:51<3:56:43,  4.03s/it]
 30%|██▉       | 1479/5000 [2:09:54<3:51:39,  3.95s/it]
 30%|██▉       | 1480/5000 [2:09:59<4:11:28,  4.29s/it]
 30%|██▉       | 1481/5000 [2:10:03<4:01:21,  4.12s/it]
 30%|██▉       | 1482/5000 [2:10:08<4:08:40,  4.24s/it]
 30%|██▉       | 1483/5000 [2:10:11<3:59:41,  4.09s/it]
 30%|██▉       | 1484/5000 [2:10:15<3:52:57,  3.98s/it]
 30%|██▉       | 1485/5000 [2:10:19<3:48:04,  3.89s/it]
 30%|██▉       | 1486/5000 [2:10:23<3:45:00,  3.84s/it]
 30%|██▉       | 1487/5000 [2:10:26<3:43:15,  3.81s/it]
 30%|██▉       | 1488/5000 [2:10:30<3:42:03,  3.79s/it]
 30%|██▉       | 1489/5000 [2:10:35<4:01:28,  4.13s/it]
 30%|██▉       | 1490/5000 [2:10:40<4:11:40,  4.30s/it]
 30%|██▉       | 1491/5000 [2:10:43<4:02:03,  4.14s/it]
 30%|██▉       | 1492/5000 [2:10:47<3:55:49,  4.03s/it]
 30%|██▉       | 1493/5000 [2:10:51<3:51:08,  3.95s/it]
 30%|██▉       | 1494/5000 [2:10:55<3:48:01,  3.90s/it]
 30%|██▉       | 1495/5000 [2:10:59<3:45:50,  3.87s/it]
 30%|██▉       | 1496/5000 [2:11:02<3:43:48,  3.83s/it]
 30%|██▉       | 1497/5000 [2:11:07<4:00:00,  4.11s/it]
 30%|██▉       | 1498/5000 [2:11:12<4:07:08,  4.23s/it]
 30%|██▉       | 1499/5000 [2:11:15<3:58:30,  4.09s/it]
 30%|███       | 1500/5000 [2:11:19<3:50:33,  3.95s/it]
                                                       
 30%|███       | 1500/5000 [2:11:19<3:50:33,  3.95s/it]
 30%|███       | 1501/5000 [2:11:23<3:45:34,  3.87s/it]
 30%|███       | 1502/5000 [2:11:26<3:44:11,  3.85s/it]
 30%|███       | 1503/5000 [2:11:30<3:42:53,  3.82s/it]
 30%|███       | 1504/5000 [2:11:34<3:46:20,  3.88s/it]
 30%|███       | 1505/5000 [2:11:38<3:43:25,  3.84s/it]
 30%|███       | 1506/5000 [2:11:44<4:18:41,  4.44s/it]
 30%|███       | 1507/5000 [2:11:48<4:06:10,  4.23s/it]
 30%|███       | 1508/5000 [2:11:52<4:02:23,  4.16s/it]
 30%|███       | 1509/5000 [2:11:55<3:55:55,  4.05s/it]
 30%|███       | 1510/5000 [2:11:59<3:49:54,  3.95s/it]
 30%|███       | 1511/5000 [2:12:03<3:46:14,  3.89s/it]
 30%|███       | 1512/5000 [2:12:07<3:43:19,  3.84s/it]
 30%|███       | 1513/5000 [2:12:10<3:40:26,  3.79s/it]
 30%|███       | 1514/5000 [2:12:15<4:03:08,  4.18s/it]
 30%|███       | 1515/5000 [2:12:20<4:12:31,  4.35s/it]
 30%|███       | 1516/5000 [2:12:24<4:02:01,  4.17s/it]
 30%|███       | 1517/5000 [2:12:28<3:54:14,  4.04s/it]
 30%|███       | 1518/5000 [2:12:32<3:57:25,  4.09s/it]
 30%|███       | 1519/5000 [2:12:36<4:05:45,  4.24s/it]
 30%|███       | 1520/5000 [2:12:40<3:57:07,  4.09s/it]
 30%|███       | 1521/5000 [2:12:44<3:51:31,  3.99s/it]
 30%|███       | 1522/5000 [2:12:48<3:46:10,  3.90s/it]
 30%|███       | 1523/5000 [2:12:54<4:33:15,  4.72s/it]
 30%|███       | 1524/5000 [2:12:58<4:23:36,  4.55s/it]
 30%|███       | 1525/5000 [2:13:02<4:08:15,  4.29s/it]
                                                       
 30%|███       | 1525/5000 [2:13:02<4:08:15,  4.29s/it]
 31%|███       | 1526/5000 [2:13:06<3:57:35,  4.10s/it]
 31%|███       | 1527/5000 [2:13:09<3:51:22,  4.00s/it]
 31%|███       | 1528/5000 [2:13:13<3:46:32,  3.91s/it]
 31%|███       | 1529/5000 [2:13:17<3:42:55,  3.85s/it]
 31%|███       | 1530/5000 [2:13:21<3:40:06,  3.81s/it]
 31%|███       | 1531/5000 [2:13:24<3:38:19,  3.78s/it]
 31%|███       | 1532/5000 [2:13:30<4:12:02,  4.36s/it]
 31%|███       | 1533/5000 [2:13:34<3:59:52,  4.15s/it]
 31%|███       | 1534/5000 [2:13:37<3:51:50,  4.01s/it]
 31%|███       | 1535/5000 [2:13:41<3:47:18,  3.94s/it]
 31%|███       | 1536/5000 [2:13:45<3:43:18,  3.87s/it]
 31%|███       | 1537/5000 [2:13:49<3:40:49,  3.83s/it]
 31%|███       | 1538/5000 [2:13:52<3:39:21,  3.80s/it]
 31%|███       | 1539/5000 [2:13:56<3:39:27,  3.80s/it]
 31%|███       | 1540/5000 [2:14:01<3:55:38,  4.09s/it]
 31%|███       | 1541/5000 [2:14:06<4:09:40,  4.33s/it]
 31%|███       | 1542/5000 [2:14:09<3:57:29,  4.12s/it]
 31%|███       | 1543/5000 [2:14:13<3:49:15,  3.98s/it]
 31%|███       | 1544/5000 [2:14:17<3:44:51,  3.90s/it]
 31%|███       | 1545/5000 [2:14:21<3:44:27,  3.90s/it]
 31%|███       | 1546/5000 [2:14:24<3:41:12,  3.84s/it]
 31%|███       | 1547/5000 [2:14:28<3:37:32,  3.78s/it]
 31%|███       | 1548/5000 [2:14:33<3:52:03,  4.03s/it]
 31%|███       | 1549/5000 [2:14:38<4:12:30,  4.39s/it]
 31%|███       | 1550/5000 [2:14:41<3:48:40,  3.98s/it]
                                                       
 31%|███       | 1550/5000 [2:14:41<3:48:40,  3.98s/it]
 31%|███       | 1551/5000 [2:14:43<3:15:23,  3.40s/it]
 31%|███       | 1552/5000 [2:14:45<2:51:53,  2.99s/it]
 31%|███       | 1553/5000 [2:14:47<2:35:35,  2.71s/it]
 31%|███       | 1554/5000 [2:14:49<2:24:00,  2.51s/it]
 31%|███       | 1555/5000 [2:14:51<2:15:58,  2.37s/it]
 31%|███       | 1556/5000 [2:14:53<2:10:33,  2.27s/it]
 31%|███       | 1557/5000 [2:14:55<2:06:39,  2.21s/it]
 31%|███       | 1558/5000 [2:14:57<2:03:45,  2.16s/it]
 31%|███       | 1559/5000 [2:14:59<2:01:57,  2.13s/it]
 31%|███       | 1560/5000 [2:15:01<2:00:38,  2.10s/it]
 31%|███       | 1561/5000 [2:15:03<1:59:31,  2.09s/it]
 31%|███       | 1562/5000 [2:15:05<1:58:50,  2.07s/it]
 31%|███▏      | 1563/5000 [2:15:07<1:58:24,  2.07s/it]
 31%|███▏      | 1564/5000 [2:15:09<1:58:05,  2.06s/it]
 31%|███▏      | 1565/5000 [2:15:12<1:57:56,  2.06s/it]
 31%|███▏      | 1566/5000 [2:15:12<1:30:09,  1.58s/it]{'eval_loss': 0.24461345374584198, 'eval_wer': 17.688063892927563, 'eval_runtime': 1705.6758, 'eval_samples_per_second': 7.337, 'eval_steps_per_second': 0.459, 'epoch': 1.04}
+{'loss': 0.196, 'learning_rate': 8.84e-06, 'epoch': 1.05}
+{'loss': 0.2057, 'learning_rate': 8.784444444444446e-06, 'epoch': 1.05}
+{'loss': 0.2115, 'learning_rate': 8.72888888888889e-06, 'epoch': 1.06}
+{'loss': 0.1891, 'learning_rate': 8.673333333333334e-06, 'epoch': 1.06}
+{'loss': 0.1985, 'learning_rate': 8.617777777777778e-06, 'epoch': 1.07}
+{'loss': 0.184, 'learning_rate': 8.562222222222224e-06, 'epoch': 1.07}
+{'loss': 0.1581, 'learning_rate': 8.506666666666668e-06, 'epoch': 1.08}
+{'loss': 0.1609, 'learning_rate': 8.451111111111112e-06, 'epoch': 1.08}
+{'loss': 0.1528, 'learning_rate': 8.395555555555557e-06, 'epoch': 1.09}
+{'loss': 0.1387, 'learning_rate': 8.34e-06, 'epoch': 1.09}
+{'loss': 0.1312, 'learning_rate': 8.284444444444446e-06, 'epoch': 1.1}
+{'loss': 0.1471, 'learning_rate': 8.22888888888889e-06, 'epoch': 1.1}
+{'loss': 0.1208, 'learning_rate': 8.173333333333334e-06, 'epoch': 1.11}
+{'loss': 0.1387, 'learning_rate': 8.11777777777778e-06, 'epoch': 1.11}
+{'loss': 0.1393, 'learning_rate': 8.062222222222222e-06, 'epoch': 1.12}
+{'loss': 0.1347, 'learning_rate': 8.006666666666667e-06, 'epoch': 1.12}
+{'loss': 0.1278, 'learning_rate': 7.951111111111111e-06, 'epoch': 1.13}
+{'loss': 0.1528, 'learning_rate': 7.895555555555557e-06, 'epoch': 1.13}
+{'loss': 0.1614, 'learning_rate': 7.840000000000001e-06, 'epoch': 1.14}
+{'loss': 0.1255, 'learning_rate': 7.784444444444445e-06, 'epoch': 1.14}
+{'loss': 0.138, 'learning_rate': 7.72888888888889e-06, 'epoch': 1.15}
+{'loss': 0.1341, 'learning_rate': 7.673333333333333e-06, 'epoch': 1.15}
+
+
+
+
+
+
+
+
+
+
 31%|███▏      | 1567/5000 [2:15:56<13:38:49, 14.31s/it]
 31%|███▏      | 1568/5000 [2:16:01<10:57:38, 11.50s/it]
 31%|███▏      | 1569/5000 [2:16:05<8:44:59,  9.18s/it] 
 31%|███▏      | 1570/5000 [2:16:08<7:11:38,  7.55s/it]
 31%|███▏      | 1571/5000 [2:16:12<6:06:21,  6.41s/it]
 31%|███▏      | 1572/5000 [2:16:16<5:19:49,  5.60s/it]
 31%|███▏      | 1573/5000 [2:16:20<4:47:04,  5.03s/it]
 31%|███▏      | 1574/5000 [2:16:24<4:29:09,  4.71s/it]
 32%|███▏      | 1575/5000 [2:16:27<4:10:45,  4.39s/it]
                                                       
 32%|███���      | 1575/5000 [2:16:27<4:10:45,  4.39s/it]
 32%|███▏      | 1576/5000 [2:16:32<4:16:33,  4.50s/it]
 32%|███▏      | 1577/5000 [2:16:36<4:17:01,  4.51s/it]
 32%|███▏      | 1578/5000 [2:16:40<4:03:07,  4.26s/it]
 32%|███▏      | 1579/5000 [2:16:44<3:53:43,  4.10s/it]
 32%|███▏      | 1580/5000 [2:16:48<3:48:04,  4.00s/it]
 32%|███▏      | 1581/5000 [2:16:51<3:44:01,  3.93s/it]
 32%|███▏      | 1582/5000 [2:16:55<3:40:07,  3.86s/it]
 32%|███▏      | 1583/5000 [2:16:59<3:37:22,  3.82s/it]
 32%|███▏      | 1584/5000 [2:17:03<3:35:42,  3.79s/it]
 32%|███▏      | 1585/5000 [2:17:08<4:07:56,  4.36s/it]
 32%|███▏      | 1586/5000 [2:17:12<3:57:50,  4.18s/it]
 32%|███▏      | 1587/5000 [2:17:16<3:49:43,  4.04s/it]
 32%|███▏      | 1588/5000 [2:17:20<3:44:50,  3.95s/it]
 32%|███▏      | 1589/5000 [2:17:23<3:40:59,  3.89s/it]
 32%|███▏      | 1590/5000 [2:17:27<3:38:09,  3.84s/it]
 32%|███▏      | 1591/5000 [2:17:31<3:37:29,  3.83s/it]
 32%|███▏      | 1592/5000 [2:17:36<3:53:37,  4.11s/it]
 32%|███▏      | 1593/5000 [2:17:40<4:04:11,  4.30s/it]
 32%|███▏      | 1594/5000 [2:17:45<4:09:30,  4.40s/it]
 32%|███▏      | 1595/5000 [2:17:49<3:57:27,  4.18s/it]
 32%|███▏      | 1596/5000 [2:17:52<3:48:31,  4.03s/it]
 32%|███▏      | 1597/5000 [2:17:56<3:42:35,  3.92s/it]
 32%|███▏      | 1598/5000 [2:18:00<3:38:28,  3.85s/it]
 32%|███▏      | 1599/5000 [2:18:03<3:35:39,  3.80s/it]
 32%|███▏      | 1600/5000 [2:18:08<3:49:17,  4.05s/it]
                                                       
 32%|███▏      | 1600/5000 [2:18:08<3:49:17,  4.05s/it]
 32%|███▏      | 1601/5000 [2:18:12<3:43:27,  3.94s/it]
 32%|███▏      | 1602/5000 [2:18:16<3:51:51,  4.09s/it]
 32%|███▏      | 1603/5000 [2:18:20<3:52:25,  4.11s/it]
 32%|███▏      | 1604/5000 [2:18:24<3:45:50,  3.99s/it]
 32%|███▏      | 1605/5000 [2:18:28<3:40:37,  3.90s/it]
 32%|███▏      | 1606/5000 [2:18:31<3:36:41,  3.83s/it]
 32%|███▏      | 1607/5000 [2:18:35<3:34:10,  3.79s/it]
 32%|███▏      | 1608/5000 [2:18:40<3:54:27,  4.15s/it]
 32%|███▏      | 1609/5000 [2:18:44<3:59:39,  4.24s/it]
 32%|███▏      | 1610/5000 [2:18:48<3:50:37,  4.08s/it]
 32%|███▏      | 1611/5000 [2:18:53<3:57:57,  4.21s/it]
 32%|███▏      | 1612/5000 [2:18:56<3:49:44,  4.07s/it]
 32%|███▏      | 1613/5000 [2:19:00<3:44:12,  3.97s/it]
 32%|███▏      | 1614/5000 [2:19:04<3:40:22,  3.91s/it]
 32%|███▏      | 1615/5000 [2:19:08<3:37:31,  3.86s/it]
 32%|███▏      | 1616/5000 [2:19:12<3:50:10,  4.08s/it]
 32%|███▏      | 1617/5000 [2:19:16<3:44:49,  3.99s/it]
 32%|███▏      | 1618/5000 [2:19:20<3:40:45,  3.92s/it]
 32%|███▏      | 1619/5000 [2:19:24<3:53:32,  4.14s/it]
 32%|███▏      | 1620/5000 [2:19:28<3:45:49,  4.01s/it]
 32%|███▏      | 1621/5000 [2:19:32<3:40:37,  3.92s/it]
 32%|███▏      | 1622/5000 [2:19:35<3:36:31,  3.85s/it]
 32%|███▏      | 1623/5000 [2:19:40<3:50:55,  4.10s/it]
 32%|███▏      | 1624/5000 [2:19:44<3:53:35,  4.15s/it]
 32%|███▎      | 1625/5000 [2:19:48<3:46:01,  4.02s/it]
                                                       
 32%|███▎      | 1625/5000 [2:19:48<3:46:01,  4.02s/it]
 33%|███▎      | 1626/5000 [2:19:52<3:41:36,  3.94s/it]
 33%|███▎      | 1627/5000 [2:19:57<4:00:22,  4.28s/it]
 33%|███▎      | 1628/5000 [2:20:01<3:59:39,  4.26s/it]
 33%|███▎      | 1629/5000 [2:20:05<3:50:28,  4.10s/it]
 33%|███▎      | 1630/5000 [2:20:09<3:44:18,  3.99s/it]
 33%|███▎      | 1631/5000 [2:20:13<3:55:29,  4.19s/it]
 33%|███▎      | 1632/5000 [2:20:17<3:47:35,  4.05s/it]
 33%|███▎      | 1633/5000 [2:20:21<3:42:06,  3.96s/it]
 33%|███▎      | 1634/5000 [2:20:25<3:37:35,  3.88s/it]
 33%|███▎      | 1635/5000 [2:20:28<3:34:20,  3.82s/it]
 33%|███▎      | 1636/5000 [2:20:33<3:48:20,  4.07s/it]
 33%|███▎      | 1637/5000 [2:20:37<3:42:43,  3.97s/it]
 33%|███▎      | 1638/5000 [2:20:40<3:38:43,  3.90s/it]
 33%|███▎      | 1639/5000 [2:20:45<3:55:32,  4.20s/it]
 33%|███▎      | 1640/5000 [2:20:49<3:49:50,  4.10s/it]
 33%|███▎      | 1641/5000 [2:20:53<3:43:28,  3.99s/it]
 33%|███▎      | 1642/5000 [2:20:57<3:40:58,  3.95s/it]
 33%|███▎      | 1643/5000 [2:21:00<3:37:24,  3.89s/it]
 33%|███▎      | 1644/5000 [2:21:04<3:33:14,  3.81s/it]
 33%|███▎      | 1645/5000 [2:21:09<3:47:28,  4.07s/it]
 33%|███▎      | 1646/5000 [2:21:13<3:43:12,  3.99s/it]
 33%|███▎      | 1647/5000 [2:21:16<3:39:49,  3.93s/it]
 33%|███▎      | 1648/5000 [2:21:21<3:56:20,  4.23s/it]
 33%|███▎      | 1649/5000 [2:21:25<3:55:25,  4.22s/it]
 33%|███▎      | 1650/5000 [2:21:29<3:46:20,  4.05s/it]
                                                       
 33%|███▎      | 1650/5000 [2:21:29<3:46:20,  4.05s/it]
 33%|███▎      | 1651/5000 [2:21:33<3:45:30,  4.04s/it]
 33%|███▎      | 1652/5000 [2:21:37<3:39:21,  3.93s/it]
 33%|███▎      | 1653/5000 [2:21:41<3:51:59,  4.16s/it]
 33%|███▎      | 1654/5000 [2:21:45<3:44:03,  4.02s/it]
 33%|███▎      | 1655/5000 [2:21:49<3:39:06,  3.93s/it]
 33%|███▎      | 1656/5000 [2:21:54<3:53:15,  4.19s/it]
 33%|███▎      | 1657/5000 [2:21:58<3:53:35,  4.19s/it]
 33%|███▎      | 1658/5000 [2:22:02<3:45:38,  4.05s/it]
 33%|███▎      | 1659/5000 [2:22:06<3:45:28,  4.05s/it]
 33%|███▎      | 1660/5000 [2:22:09<3:40:06,  3.95s/it]
 33%|███▎      | 1661/5000 [2:22:14<3:53:25,  4.19s/it]
 33%|███▎      | 1662/5000 [2:22:18<3:49:08,  4.12s/it]
 33%|███▎      | 1663/5000 [2:22:22<3:42:04,  3.99s/it]
 33%|███▎      | 1664/5000 [2:22:26<3:49:40,  4.13s/it]
 33%|███▎      | 1665/5000 [2:22:30<3:45:09,  4.05s/it]
 33%|███▎      | 1666/5000 [2:22:34<3:39:52,  3.96s/it]
 33%|███▎      | 1667/5000 [2:22:38<3:40:41,  3.97s/it]
 33%|███▎      | 1668/5000 [2:22:42<3:47:13,  4.09s/it]
 33%|███▎      | 1669/5000 [2:22:47<4:06:05,  4.43s/it]
 33%|███▎      | 1670/5000 [2:22:51<3:53:26,  4.21s/it]
 33%|███▎      | 1671/5000 [2:22:55<3:45:53,  4.07s/it]
 33%|███▎      | 1672/5000 [2:22:59<3:40:13,  3.97s/it]
 33%|███▎      | 1673/5000 [2:23:03<3:52:04,  4.19s/it]
 33%|███▎      | 1674/5000 [2:23:07<3:43:33,  4.03s/it]
 34%|███▎      | 1675/5000 [2:23:11<3:40:46,  3.98s/it]
                                                       
 34%|███▎      | 1675/5000 [2:23:11<3:40:46,  3.98s/it]
 34%|███▎      | 1676/5000 [2:23:15<3:45:49,  4.08s/it]
 34%|███▎      | 1677/5000 [2:23:19<3:40:04,  3.97s/it]
 34%|███▎      | 1678/5000 [2:23:24<3:52:21,  4.20s/it]
 34%|███▎      | 1679/5000 [2:23:27<3:43:52,  4.04s/it]
 34%|███▎      | 1680/5000 [2:23:31<3:37:38,  3.93s/it]
 34%|███▎      | 1681/5000 [2:23:35<3:33:49,  3.87s/it]
 34%|███▎      | 1682/5000 [2:23:40<4:00:58,  4.36s/it]
 34%|███▎      | 1683/5000 [2:23:44<3:53:59,  4.23s/it]
 34%|███▎      | 1684/5000 [2:23:48<3:45:22,  4.08s/it]
 34%|███▎      | 1685/5000 [2:23:52<3:38:52,  3.96s/it]
 34%|███▎      | 1686/5000 [2:23:56<3:50:56,  4.18s/it]
 34%|███▎      | 1687/5000 [2:24:00<3:43:44,  4.05s/it]
 34%|███▍      | 1688/5000 [2:24:04<3:38:10,  3.95s/it]
 34%|███▍      | 1689/5000 [2:24:07<3:34:03,  3.88s/it]
 34%|███▍      | 1690/5000 [2:24:11<3:31:35,  3.84s/it]
 34%|███▍      | 1691/5000 [2:24:16<3:48:21,  4.14s/it]
 34%|███▍      | 1692/5000 [2:24:20<3:41:17,  4.01s/it]
 34%|███▍      | 1693/5000 [2:24:23<3:36:03,  3.92s/it]
 34%|███▍      | 1694/5000 [2:24:27<3:32:32,  3.86s/it]
 34%|███▍      | 1695/5000 [2:24:31<3:29:58,  3.81s/it]
 34%|███▍      | 1696/5000 [2:24:36<3:46:57,  4.12s/it]
 34%|███▍      | 1697/5000 [2:24:39<3:39:21,  3.98s/it]
 34%|███▍      | 1698/5000 [2:24:43<3:33:26,  3.88s/it]
 34%|███▍      | 1699/5000 [2:24:47<3:30:12,  3.82s/it]
 34%|███▍      | 1700/5000 [2:24:51<3:43:49,  4.07s/it]
                                                       
 34%|███▍      | 1700/5000 [2:24:51<3:43:49,  4.07s/it]
 34%|███▍      | 1701/5000 [2:24:55<3:45:46,  4.11s/it]
 34%|███▍      | 1702/5000 [2:24:59<3:38:50,  3.98s/it]
 34%|███▍      | 1703/5000 [2:25:03<3:34:30,  3.90s/it]
 34%|███▍      | 1704/5000 [2:25:08<3:50:19,  4.19s/it]
 34%|███▍      | 1705/5000 [2:25:11<3:41:41,  4.04s/it]
 34%|███▍      | 1706/5000 [2:25:15<3:36:21,  3.94s/it]
 34%|███▍      | 1707/5000 [2:25:19<3:32:18,  3.87s/it]
 34%|███▍      | 1708/5000 [2:25:23<3:37:25,  3.96s/it]
 34%|███▍      | 1709/5000 [2:25:28<3:53:15,  4.25s/it]
 34%|███▍      | 1710/5000 [2:25:32<3:43:30,  4.08s/it]
 34%|███▍      | 1711/5000 [2:25:35<3:37:31,  3.97s/it]
 34%|███▍      | 1712/5000 [2:25:39<3:33:28,  3.90s/it]
 34%|███▍      | 1713/5000 [2:25:43<3:30:02,  3.83s/it]
 34%|███▍      | 1714/5000 [2:25:48<3:48:59,  4.18s/it]
 34%|███▍      | 1715/5000 [2:25:51<3:40:31,  4.03s/it]
 34%|███▍      | 1716/5000 [2:25:55<3:37:21,  3.97s/it]
 34%|███▍      | 1717/5000 [2:25:59<3:31:48,  3.87s/it]
 34%|███▍      | 1718/5000 [2:26:04<3:54:51,  4.29s/it]
 34%|███▍      | 1719/5000 [2:26:08<3:45:15,  4.12s/it]
 34%|███▍      | 1720/5000 [2:26:12<3:38:14,  3.99s/it]
 34%|███▍      | 1721/5000 [2:26:15<3:33:50,  3.91s/it]
 34%|███▍      | 1722/5000 [2:26:19<3:30:41,  3.86s/it]
 34%|███▍      | 1723/5000 [2:26:24<3:46:46,  4.15s/it]
 34%|███▍      | 1724/5000 [2:26:28<3:47:58,  4.18s/it]
 34%|███▍      | 1725/5000 [2:26:32<3:39:59,  4.03s/it]
                                                       
 34%|███▍      | 1725/5000 [2:26:32<3:39:59,  4.03s/it]
 35%|███▍      | 1726/5000 [2:26:36<3:48:10,  4.18s/it]
 35%|███▍      | 1727/5000 [2:26:40<3:41:09,  4.05s/it]
 35%|███▍      | 1728/5000 [2:26:44<3:36:09,  3.96s/it]
 35%|███▍      | 1729/5000 [2:26:48<3:31:49,  3.89s/it]
 35%|███▍      | 1730/5000 [2:26:51<3:28:45,  3.83s/it]
 35%|███▍      | 1731/5000 [2:26:55<3:26:25,  3.79s/it]
 35%|███▍      | 1732/5000 [2:27:00<3:49:03,  4.21s/it]
 35%|███▍      | 1733/5000 [2:27:04<3:40:20,  4.05s/it]
 35%|███▍      | 1734/5000 [2:27:08<3:34:54,  3.95s/it]
 35%|███▍      | 1735/5000 [2:27:13<3:52:55,  4.28s/it]
 35%|███▍      | 1736/5000 [2:27:16<3:43:00,  4.10s/it]
 35%|███▍      | 1737/5000 [2:27:20<3:35:37,  3.96s/it]
 35%|███▍      | 1738/5000 [2:27:24<3:31:57,  3.90s/it]
 35%|███▍      | 1739/5000 [2:27:27<3:29:05,  3.85s/it]
 35%|███▍      | 1740/5000 [2:27:31<3:26:59,  3.81s/it]
 35%|███▍      | 1741/5000 [2:27:36<3:47:52,  4.20s/it]
 35%|███▍      | 1742/5000 [2:27:40<3:40:01,  4.05s/it]
 35%|███▍      | 1743/5000 [2:27:44<3:34:14,  3.95s/it]
 35%|███▍      | 1744/5000 [2:27:48<3:43:30,  4.12s/it]
 35%|███▍      | 1745/5000 [2:27:52<3:37:11,  4.00s/it]
 35%|███▍      | 1746/5000 [2:27:56<3:32:15,  3.91s/it]
 35%|███▍      | 1747/5000 [2:27:59<3:29:29,  3.86s/it]
 35%|███▍      | 1748/5000 [2:28:03<3:27:51,  3.83s/it]
 35%|███▍      | 1749/5000 [2:28:07<3:25:44,  3.80s/it]
 35%|███▌      | 1750/5000 [2:28:12<3:44:22,  4.14s/it]
                                                       
 35%|███▌      | 1750/5000 [2:28:12<3:44:22,  4.14s/it]
 35%|███▌      | 1751/5000 [2:28:16<3:52:21,  4.29s/it]
 35%|███▌      | 1752/5000 [2:28:21<3:54:22,  4.33s/it]
 35%|███▌      | 1753/5000 [2:28:26<4:13:26,  4.68s/it]
 35%|███▌      | 1754/5000 [2:28:31<4:17:49,  4.77s/it]
 35%|███▌      | 1755/5000 [2:28:35<4:01:38,  4.47s/it]
 35%|███▌      | 1756/5000 [2:28:39<3:52:45,  4.30s/it]
 35%|███▌      | 1757/5000 [2:28:43<3:43:00,  4.13s/it]
 35%|███▌      | 1758/5000 [2:28:48<3:55:27,  4.36s/it]
 35%|███▌      | 1759/5000 [2:28:51<3:45:28,  4.17s/it]
 35%|███▌      | 1760/5000 [2:28:55<3:37:48,  4.03s/it]
 35%|███▌      | 1761/5000 [2:28:59<3:32:42,  3.94s/it]
 35%|███▌      | 1762/5000 [2:29:03<3:45:27,  4.18s/it]
 35%|███▌      | 1763/5000 [2:29:07<3:37:57,  4.04s/it]
 35%|███▌      | 1764/5000 [2:29:11<3:36:12,  4.01s/it]
 35%|███▌      | 1765/5000 [2:29:15<3:31:08,  3.92s/it]
 35%|███▌      | 1766/5000 [2:29:19<3:34:52,  3.99s/it]
 35%|███▌      | 1767/5000 [2:29:24<3:47:08,  4.22s/it]
 35%|███▌      | 1768/5000 [2:29:28<3:39:50,  4.08s/it]
 35%|███▌      | 1769/5000 [2:29:31<3:34:14,  3.98s/it]
 35%|███▌      | 1770/5000 [2:29:36<3:51:44,  4.30s/it]
 35%|███▌      | 1771/5000 [2:29:40<3:41:54,  4.12s/it]
 35%|███▌      | 1772/5000 [2:29:44<3:35:48,  4.01s/it]
 35%|███▌      | 1773/5000 [2:29:47<3:31:01,  3.92s/it]
 35%|███▌      | 1774/5000 [2:29:51<3:27:14,  3.85s/it]
 36%|███▌      | 1775/5000 [2:29:55<3:25:14,  3.82s/it]
                                                       
 36%|███▌      | 1775/5000 [2:29:55<3:25:14,  3.82s/it]
 36%|███▌      | 1776/5000 [2:30:00<3:39:56,  4.09s/it]
 36%|███▌      | 1777/5000 [2:30:03<3:34:03,  3.98s/it]
 36%|███▌      | 1778/5000 [2:30:08<3:44:22,  4.18s/it]
 36%|███▌      | 1779/5000 [2:30:12<3:38:23,  4.07s/it]
 36%|███▌      | 1780/5000 [2:30:16<3:32:18,  3.96s/it]
 36%|███▌      | 1781/5000 [2:30:19<3:27:57,  3.88s/it]
 36%|███▌      | 1782/5000 [2:30:23<3:24:21,  3.81s/it]
 36%|███▌      | 1783/5000 [2:30:27<3:22:52,  3.78s/it]
 36%|███▌      | 1784/5000 [2:30:30<3:22:03,  3.77s/it]
 36%|███▌      | 1785/5000 [2:30:35<3:37:24,  4.06s/it]
 36%|███▌      | 1786/5000 [2:30:39<3:31:16,  3.94s/it]
 36%|███▌      | 1787/5000 [2:30:44<3:52:58,  4.35s/it]
 36%|███▌      | 1788/5000 [2:30:48<3:43:02,  4.17s/it]
 36%|███▌      | 1789/5000 [2:30:51<3:35:28,  4.03s/it]
 36%|███▌      | 1790/5000 [2:30:55<3:32:42,  3.98s/it]
 36%|███▌      | 1791/5000 [2:30:59<3:29:08,  3.91s/it]
 36%|███▌      | 1792/5000 [2:31:03<3:25:02,  3.83s/it]
 36%|███▌      | 1793/5000 [2:31:07<3:37:41,  4.07s/it]
 36%|███▌      | 1794/5000 [2:31:11<3:31:48,  3.96s/it]
 36%|███▌      | 1795/5000 [2:31:15<3:27:39,  3.89s/it]
 36%|███▌      | 1796/5000 [2:31:19<3:37:30,  4.07s/it]
 36%|███▌      | 1797/5000 [2:31:23<3:33:10,  3.99s/it]
 36%|███▌      | 1798/5000 [2:31:27<3:29:45,  3.93s/it]
 36%|███▌      | 1799/5000 [2:31:31<3:26:36,  3.87s/it]
 36%|��██▌      | 1800/5000 [2:31:34<3:24:21,  3.83s/it]
                                                       
 36%|███▌      | 1800/5000 [2:31:34<3:24:21,  3.83s/it]
 36%|███▌      | 1801/5000 [2:31:38<3:22:19,  3.79s/it]
 36%|███▌      | 1802/5000 [2:31:43<3:38:42,  4.10s/it]
 36%|███▌      | 1803/5000 [2:31:47<3:35:20,  4.04s/it]
 36%|███▌      | 1804/5000 [2:31:51<3:44:58,  4.22s/it]
 36%|███▌      | 1805/5000 [2:31:55<3:37:59,  4.09s/it]
 36%|███▌      | 1806/5000 [2:31:59<3:32:11,  3.99s/it]
 36%|███▌      | 1807/5000 [2:32:04<3:47:33,  4.28s/it]
 36%|███▌      | 1808/5000 [2:32:09<3:58:18,  4.48s/it]
 36%|███▌      | 1809/5000 [2:32:13<3:53:00,  4.38s/it]
 36%|███▌      | 1810/5000 [2:32:17<3:42:12,  4.18s/it]
 36%|███▌      | 1811/5000 [2:32:21<3:49:26,  4.32s/it]
 36%|███▌      | 1812/5000 [2:32:26<3:56:10,  4.44s/it]
 36%|███▋      | 1813/5000 [2:32:31<4:07:52,  4.67s/it]
 36%|███▋      | 1814/5000 [2:32:35<3:53:21,  4.39s/it]
 36%|███▋      | 1815/5000 [2:32:39<3:42:39,  4.19s/it]
 36%|███▋      | 1816/5000 [2:32:42<3:34:49,  4.05s/it]
 36%|███▋      | 1817/5000 [2:32:46<3:30:03,  3.96s/it]
 36%|███▋      | 1818/5000 [2:32:51<3:43:19,  4.21s/it]
 36%|███▋      | 1819/5000 [2:32:55<3:35:26,  4.06s/it]
 36%|███▋      | 1820/5000 [2:32:58<3:30:01,  3.96s/it]
 36%|███▋      | 1821/5000 [2:33:03<3:46:05,  4.27s/it]
 36%|███▋      | 1822/5000 [2:33:07<3:38:36,  4.13s/it]
 36%|███▋      | 1823/5000 [2:33:11<3:31:23,  3.99s/it]
 36%|███▋      | 1824/5000 [2:33:15<3:25:38,  3.88s/it]
 36%|███▋      | 1825/5000 [2:33:18<3:21:27,  3.81s/it]
                                                       
 36%|███▋      | 1825/5000 [2:33:18<3:21:27,  3.81s/it]
 37%|███▋      | 1826/5000 [2:33:22<3:19:19,  3.77s/it]
 37%|███▋      | 1827/5000 [2:33:27<3:40:32,  4.17s/it]
 37%|███▋      | 1828/5000 [2:33:31<3:33:56,  4.05s/it]
 37%|███▋      | 1829/5000 [2:33:35<3:40:26,  4.17s/it]
 37%|███▋      | 1830/5000 [2:33:40<3:45:43,  4.27s/it]
 37%|███▋      | 1831/5000 [2:33:44<3:42:35,  4.21s/it]
 37%|███▋      | 1832/5000 [2:33:47<3:34:27,  4.06s/it]
 37%|███▋      | 1833/5000 [2:33:51<3:29:47,  3.97s/it]
 37%|███▋      | 1834/5000 [2:33:55<3:28:42,  3.96s/it]
 37%|███▋      | 1835/5000 [2:33:59<3:27:50,  3.94s/it]
 37%|███▋      | 1836/5000 [2:34:04<3:40:52,  4.19s/it]
 37%|███▋      | 1837/5000 [2:34:08<3:33:32,  4.05s/it]
 37%|███▋      | 1838/5000 [2:34:13<3:50:11,  4.37s/it]
 37%|███▋      | 1839/5000 [2:34:16<3:40:35,  4.19s/it]
 37%|███▋      | 1840/5000 [2:34:20<3:33:18,  4.05s/it]
 37%|███▋      | 1841/5000 [2:34:24<3:27:29,  3.94s/it]
 37%|███▋      | 1842/5000 [2:34:28<3:23:35,  3.87s/it]
 37%|███▋      | 1843/5000 [2:34:31<3:21:32,  3.83s/it]
 37%|███▋      | 1844/5000 [2:34:36<3:34:22,  4.08s/it]
 37%|███▋      | 1845/5000 [2:34:40<3:31:41,  4.03s/it]
 37%|███▋      | 1846/5000 [2:34:44<3:26:28,  3.93s/it]
 37%|███▋      | 1847/5000 [2:34:48<3:35:22,  4.10s/it]
 37%|███▋      | 1848/5000 [2:34:52<3:28:40,  3.97s/it]
 37%|███▋      | 1849/5000 [2:34:55<3:23:45,  3.88s/it]
 37%|███▋      | 1850/5000 [2:34:59<3:20:19,  3.82s/it]
                                                       
 37%|███▋      | 1850/5000 [2:34:59<3:20:19,  3.82s/it]
 37%|███▋      | 1851/5000 [2:35:03<3:19:13,  3.80s/it]
 37%|███▋      | 1852/5000 [2:35:07<3:25:11,  3.91s/it]
 37%|███▋      | 1853/5000 [2:35:12<3:46:20,  4.32s/it]
 37%|███▋      | 1854/5000 [2:35:16<3:35:59,  4.12s/it]
 37%|███▋      | 1855/5000 [2:35:21<3:46:14,  4.32s/it]
 37%|███▋      | 1856/5000 [2:35:24<3:36:53,  4.14s/it]
 37%|███▋      | 1857/5000 [2:35:28<3:30:14,  4.01s/it]
 37%|███▋      | 1858/5000 [2:35:32<3:25:13,  3.92s/it]
 37%|███▋      | 1859/5000 [2:35:36<3:22:19,  3.86s/it]
 37%|███▋      | 1860/5000 [2:35:39<3:20:16,  3.83s/it]
 37%|███▋      | 1861/5000 [2:35:44<3:37:51,  4.16s/it]
 37%|███▋      | 1862/5000 [2:35:48<3:37:17,  4.15s/it]
 37%|███▋      | 1863/5000 [2:35:52<3:30:56,  4.03s/it]
 37%|███▋      | 1864/5000 [2:35:57<3:39:46,  4.20s/it]
 37%|███▋      | 1865/5000 [2:36:00<3:32:16,  4.06s/it]
 37%|███▋      | 1866/5000 [2:36:05<3:33:22,  4.08s/it]
 37%|███▋      | 1867/5000 [2:36:08<3:27:28,  3.97s/it]
 37%|███▋      | 1868/5000 [2:36:12<3:23:19,  3.90s/it]
 37%|███▋      | 1869/5000 [2:36:17<3:34:55,  4.12s/it]
 37%|███▋      | 1870/5000 [2:36:22<3:49:18,  4.40s/it]
 37%|███▋      | 1871/5000 [2:36:25<3:38:36,  4.19s/it]
 37%|███▋      | 1872/5000 [2:36:29<3:31:16,  4.05s/it]
 37%|███▋      | 1873/5000 [2:36:34<3:45:12,  4.32s/it]
 37%|███▋      | 1874/5000 [2:36:39<3:54:15,  4.50s/it]
 38%|███▊      | 1875/5000 [2:36:43<3:42:31,  4.27s/it]
                                                       
 38%|███▊      | 1875/5000 [2:36:43<3:42:31,  4.27s/it]
 38%|███▊      | 1876/5000 [2:36:47<3:43:39,  4.30s/it]
 38%|███▊      | 1877/5000 [2:36:52<3:44:48,  4.32s/it]
 38%|███▊      | 1878/5000 [2:36:55<3:35:42,  4.15s/it]
 38%|███▊      | 1879/5000 [2:37:00<3:43:38,  4.30s/it]
 38%|███▊      | 1880/5000 [2:37:04<3:34:57,  4.13s/it]
 38%|███▊      | 1881/5000 [2:37:08<3:40:27,  4.24s/it]
 38%|███▊      | 1882/5000 [2:37:12<3:31:40,  4.07s/it]
 38%|███▊      | 1883/5000 [2:37:16<3:26:00,  3.97s/it]
 38%|███▊      | 1884/5000 [2:37:19<3:21:46,  3.89s/it]
 38%|███▊      | 1885/5000 [2:37:23<3:21:37,  3.88s/it]
 38%|███▊      | 1886/5000 [2:37:27<3:23:09,  3.91s/it]
 38%|███▊      | 1887/5000 [2:37:31<3:20:43,  3.87s/it]
 38%|███▊      | 1888/5000 [2:37:36<3:38:50,  4.22s/it]
 38%|███▊      | 1889/5000 [2:37:41<3:45:41,  4.35s/it]
 38%|███▊      | 1890/5000 [2:37:44<3:35:15,  4.15s/it]
 38%|███▊      | 1891/5000 [2:37:48<3:29:15,  4.04s/it]
 38%|███▊      | 1892/5000 [2:37:52<3:24:48,  3.95s/it]
 38%|███▊      | 1893/5000 [2:37:56<3:24:37,  3.95s/it]
 38%|███▊      | 1894/5000 [2:37:59<3:20:47,  3.88s/it]
 38%|███▊      | 1895/5000 [2:38:03<3:18:14,  3.83s/it]
 38%|███▊      | 1896/5000 [2:38:08<3:30:51,  4.08s/it]
 38%|███▊      | 1897/5000 [2:38:12<3:37:49,  4.21s/it]
 38%|███▊      | 1898/5000 [2:38:16<3:30:30,  4.07s/it]
 38%|███▊      | 1899/5000 [2:38:20<3:29:12,  4.05s/it]
 38%|███▊      | 1900/5000 [2:38:24<3:24:40,  3.96s/it]
                                                       
 38%|███▊      | 1900/5000 [2:38:24<3:24:40,  3.96s/it]
 38%|███▊      | 1901/5000 [2:38:28<3:23:31,  3.94s/it]
 38%|███▊      | 1902/5000 [2:38:31<3:20:08,  3.88s/it]
 38%|███▊      | 1903/5000 [2:38:35<3:18:26,  3.84s/it]
 38%|███▊      | 1904/5000 [2:38:39<3:16:57,  3.82s/it]
 38%|███▊      | 1905/5000 [2:38:45<3:46:28,  4.39s/it]
 38%|███▊      | 1906/5000 [2:38:48<3:35:56,  4.19s/it]
 38%|███▊      | 1907/5000 [2:38:52<3:28:10,  4.04s/it]
 38%|███▊      | 1908/5000 [2:38:56<3:30:05,  4.08s/it]
 38%|███▊      | 1909/5000 [2:39:00<3:23:43,  3.95s/it]
 38%|███▊      | 1910/5000 [2:39:04<3:19:31,  3.87s/it]
 38%|███▊      | 1911/5000 [2:39:08<3:21:09,  3.91s/it]
 38%|███▊      | 1912/5000 [2:39:11<3:16:52,  3.83s/it]
 38%|███▊      | 1913/5000 [2:39:15<3:14:59,  3.79s/it]
 38%|███▊      | 1914/5000 [2:39:21<3:49:00,  4.45s/it]
 38%|███▊      | 1915/5000 [2:39:25<3:46:53,  4.41s/it]
 38%|███▊      | 1916/5000 [2:39:29<3:36:00,  4.20s/it]
 38%|███▊      | 1917/5000 [2:39:33<3:29:00,  4.07s/it]
 38%|███▊      | 1918/5000 [2:39:36<3:23:41,  3.97s/it]
 38%|███▊      | 1919/5000 [2:39:40<3:20:12,  3.90s/it]
 38%|███▊      | 1920/5000 [2:39:44<3:17:40,  3.85s/it]
 38%|███▊      | 1921/5000 [2:39:48<3:15:15,  3.81s/it]
 38%|███▊      | 1922/5000 [2:39:53<3:37:03,  4.23s/it]
 38%|███▊      | 1923/5000 [2:39:57<3:41:01,  4.31s/it]
 38%|███▊      | 1924/5000 [2:40:01<3:33:50,  4.17s/it]
 38%|███▊      | 1925/5000 [2:40:05<3:25:50,  4.02s/it]
                                                       
 38%|███▊      | 1925/5000 [2:40:05<3:25:50,  4.02s/it]
 39%|███▊      | 1926/5000 [2:40:09<3:29:13,  4.08s/it]
 39%|███▊      | 1927/5000 [2:40:13<3:26:30,  4.03s/it]
 39%|███▊      | 1928/5000 [2:40:17<3:20:48,  3.92s/it]
 39%|███▊      | 1929/5000 [2:40:20<3:17:45,  3.86s/it]
 39%|███▊      | 1930/5000 [2:40:24<3:15:30,  3.82s/it]
 39%|███▊      | 1931/5000 [2:40:30<3:39:54,  4.30s/it]
 39%|███▊      | 1932/5000 [2:40:34<3:42:07,  4.34s/it]
 39%|███▊      | 1933/5000 [2:40:38<3:32:29,  4.16s/it]
 39%|███▊      | 1934/5000 [2:40:41<3:24:30,  4.00s/it]
 39%|███▊      | 1935/5000 [2:40:45<3:20:21,  3.92s/it]
 39%|███▊      | 1936/5000 [2:40:49<3:16:29,  3.85s/it]
 39%|███▊      | 1937/5000 [2:40:52<3:13:30,  3.79s/it]
 39%|███▉      | 1938/5000 [2:40:56<3:15:40,  3.83s/it]
 39%|███▉      | 1939/5000 [2:41:00<3:13:59,  3.80s/it]
 39%|███▉      | 1940/5000 [2:41:06<3:40:29,  4.32s/it]
 39%|███▉      | 1941/5000 [2:41:09<3:31:37,  4.15s/it]
 39%|███▉      | 1942/5000 [2:41:13<3:27:17,  4.07s/it]
 39%|███▉      | 1943/5000 [2:41:17<3:21:45,  3.96s/it]
 39%|███▉      | 1944/5000 [2:41:21<3:18:16,  3.89s/it]
 39%|███▉      | 1945/5000 [2:41:24<3:15:25,  3.84s/it]
 39%|███▉      | 1946/5000 [2:41:28<3:13:22,  3.80s/it]
 39%|███▉      | 1947/5000 [2:41:32<3:11:17,  3.76s/it]
 39%|███▉      | 1948/5000 [2:41:37<3:28:03,  4.09s/it]
 39%|███▉      | 1949/5000 [2:41:41<3:35:08,  4.23s/it]
 39%|███▉      | 1950/5000 [2:41:45<3:34:59,  4.23s/it]
                                                       
 39%|███▉      | 1950/5000 [2:41:45<3:34:59,  4.23s/it]
 39%|███▉      | 1951/5000 [2:41:49<3:26:49,  4.07s/it]
 39%|███▉      | 1952/5000 [2:41:53<3:20:40,  3.95s/it]
 39%|███▉      | 1953/5000 [2:41:57<3:17:31,  3.89s/it]
 39%|███▉      | 1954/5000 [2:42:00<3:15:03,  3.84s/it]
 39%|███▉      | 1955/5000 [2:42:04<3:15:51,  3.86s/it]
 39%|███▉      | 1956/5000 [2:42:08<3:16:17,  3.87s/it]
 39%|███▉      | 1957/5000 [2:42:13<3:31:22,  4.17s/it]
 39%|███▉      | 1958/5000 [2:42:18<3:42:32,  4.39s/it]
 39%|███▉      | 1959/5000 [2:42:22<3:32:18,  4.19s/it]
 39%|███▉      | 1960/5000 [2:42:25<3:24:00,  4.03s/it]
 39%|███▉      | 1961/5000 [2:42:29<3:19:06,  3.93s/it]
 39%|███▉      | 1962/5000 [2:42:33<3:14:41,  3.85s/it]
 39%|███▉      | 1963/5000 [2:42:36<3:11:53,  3.79s/it]
 39%|███▉      | 1964/5000 [2:42:40<3:10:29,  3.76s/it]
 39%|███▉      | 1965/5000 [2:42:44<3:15:35,  3.87s/it]
 39%|███▉      | 1966/5000 [2:42:48<3:13:54,  3.83s/it]
 39%|███▉      | 1967/5000 [2:42:54<3:45:15,  4.46s/it]
 39%|███▉      | 1968/5000 [2:42:59<3:51:49,  4.59s/it]
 39%|███▉      | 1969/5000 [2:43:02<3:38:53,  4.33s/it]
 39%|███▉      | 1970/5000 [2:43:06<3:30:20,  4.17s/it]
 39%|███▉      | 1971/5000 [2:43:10<3:24:05,  4.04s/it]
 39%|███▉      | 1972/5000 [2:43:14<3:25:28,  4.07s/it]
 39%|███▉      | 1973/5000 [2:43:18<3:20:04,  3.97s/it]
 39%|███▉      | 1974/5000 [2:43:21<3:16:18,  3.89s/it]
 40%|███▉      | 1975/5000 [2:43:26<3:29:35,  4.16s/it]
                                                       
 40%|███▉      | 1975/5000 [2:43:26<3:29:35,  4.16s/it]
 40%|███▉      | 1976/5000 [2:43:31<3:36:01,  4.29s/it]
 40%|███▉      | 1977/5000 [2:43:34<3:26:51,  4.11s/it]
 40%|███▉      | 1978/5000 [2:43:38<3:20:54,  3.99s/it]
 40%|███▉      | 1979/5000 [2:43:42<3:16:38,  3.91s/it]
 40%|███▉      | 1980/5000 [2:43:46<3:14:12,  3.86s/it]
 40%|███▉      | 1981/5000 [2:43:49<3:12:45,  3.83s/it]
 40%|███▉      | 1982/5000 [2:43:53<3:11:54,  3.82s/it]
 40%|███▉      | 1983/5000 [2:43:57<3:13:07,  3.84s/it]
 40%|███▉      | 1984/5000 [2:44:03<3:41:04,  4.40s/it]
 40%|███▉      | 1985/5000 [2:44:07<3:31:00,  4.20s/it]
 40%|███▉      | 1986/5000 [2:44:10<3:23:50,  4.06s/it]
 40%|███▉      | 1987/5000 [2:44:14<3:18:32,  3.95s/it]
 40%|███▉      | 1988/5000 [2:44:18<3:15:50,  3.90s/it]
 40%|███▉      | 1989/5000 [2:44:21<3:11:57,  3.83s/it]
 40%|███▉      | 1990/5000 [2:44:25<3:10:52,  3.80s/it]
 40%|███▉      | 1991/5000 [2:44:29<3:12:12,  3.83s/it]
 40%|███▉      | 1992/5000 [2:44:34<3:26:08,  4.11s/it]
 40%|███▉      | 1993/5000 [2:44:38<3:30:50,  4.21s/it]
 40%|███▉      | 1994/5000 [2:44:42<3:22:26,  4.04s/it]
 40%|███▉      | 1995/5000 [2:44:46<3:16:25,  3.92s/it]
 40%|███▉      | 1996/5000 [2:44:49<3:11:56,  3.83s/it]
 40%|███▉      | 1997/5000 [2:44:53<3:09:44,  3.79s/it]
 40%|███▉      | 1998/5000 [2:44:57<3:09:20,  3.78s/it]
 40%|███▉      | 1999/5000 [2:45:00<3:08:14,  3.76s/it]
 40%|████      | 2000/5000 [2:45:04<3:07:12,  3.74s/it]
                                                       
 40%|████      | 2000/5000 [2:45:04<3:07:12,  3.74s/it][INFO|trainer.py:2955] 2023-12-29 17:34:13,420 >> ***** Running Evaluation *****
+[INFO|trainer.py:2959] 2023-12-29 17:34:13,420 >>   Num examples: Unknown
+[INFO|trainer.py:2960] 2023-12-29 17:34:13,420 >>   Batch size = 16
+{'loss': 0.1223, 'learning_rate': 7.617777777777778e-06, 'epoch': 2.0}
+{'loss': 0.1272, 'learning_rate': 7.562222222222223e-06, 'epoch': 2.01}
+{'loss': 0.1324, 'learning_rate': 7.506666666666668e-06, 'epoch': 2.01}
+{'loss': 0.1277, 'learning_rate': 7.451111111111111e-06, 'epoch': 2.02}
+{'loss': 0.1184, 'learning_rate': 7.395555555555556e-06, 'epoch': 2.02}
+{'loss': 0.1117, 'learning_rate': 7.340000000000001e-06, 'epoch': 2.03}
+{'loss': 0.1092, 'learning_rate': 7.284444444444445e-06, 'epoch': 2.03}
+{'loss': 0.1027, 'learning_rate': 7.22888888888889e-06, 'epoch': 2.04}
+{'loss': 0.1018, 'learning_rate': 7.173333333333335e-06, 'epoch': 2.04}
+{'loss': 0.0909, 'learning_rate': 7.117777777777778e-06, 'epoch': 2.05}
+{'loss': 0.104, 'learning_rate': 7.062222222222223e-06, 'epoch': 2.05}
+{'loss': 0.1002, 'learning_rate': 7.006666666666667e-06, 'epoch': 2.06}
+{'loss': 0.0964, 'learning_rate': 6.951111111111112e-06, 'epoch': 2.06}
+{'loss': 0.0874, 'learning_rate': 6.8955555555555565e-06, 'epoch': 2.07}
+{'loss': 0.0885, 'learning_rate': 6.8400000000000014e-06, 'epoch': 2.07}
+{'loss': 0.084, 'learning_rate': 6.784444444444445e-06, 'epoch': 2.08}
+{'loss': 0.0766, 'learning_rate': 6.7288888888888895e-06, 'epoch': 2.08}
+{'loss': 0.0759, 'learning_rate': 6.6733333333333335e-06, 'epoch': 2.09}
+
+
+
+[INFO|trainer_utils.py:689] 2023-12-29 17:34:17,301 >> 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 [3:13:13<3:07:12,  3.74s/it][INFO|trainer.py:2700] 2023-12-29 18:02:22,593 >> Saving model checkpoint to ./checkpoint-2000
+[INFO|configuration_utils.py:447] 2023-12-29 18:02:22,594 >> Configuration saved in ./checkpoint-2000/config.json
+[INFO|modeling_utils.py:1693] 2023-12-29 18:02:23,729 >> Model weights saved in ./checkpoint-2000/pytorch_model.bin
+[INFO|feature_extraction_utils.py:368] 2023-12-29 18:02:23,735 >> Feature extractor saved in ./checkpoint-2000/preprocessor_config.json
+[INFO|feature_extraction_utils.py:368] 2023-12-29 18:02:29,350 >> Feature extractor saved in ./preprocessor_config.json

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a4639d60d8256b82e332d9df35a0adffad1db19eaca1e9aaa2bf73b9aee50ce
+oid sha256:ebf74bca481eb47c34f57ea400c690c4790c09983af00a6e6583d6b2002b9d31
 size 967102601

runs/Dec29_14-48-47_tknadmin-System-Product-Name/events.out.tfevents.1703857748.tknadmin-System-Product-Name.1211770.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:280ad4d33ef5194632c0a1558212191f6ce000aea5a2e015270644da50fb4dbc
-size 10864
+oid sha256:e37c9b39de887fd5bde9febfc52960fda87a83aeb3ba3a43be247141f5a7a6aa
+size 17462