Training in progress, step 5000

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:656ad65a0efd016b92be9b27dc8dca4b6485147fc7a287642049ae5aaf68cffa
+oid sha256:150f83b8191e1a4f4e821ec0df33eeef4c1a64217230609ef8841169e7ed474c
 size 967102601

training.log

@@ -1495,3 +1495,161 @@ Adding files tracked by Git LFS: ['wandb/run-20230509_115211-hq92t8sj/run-hq92t8
 [INFO|modeling_utils.py:1855] 2023-05-11 21:45:15,833 >> Model weights saved in ./checkpoint-4000/pytorch_model.bin
 [INFO|feature_extraction_utils.py:369] 2023-05-11 21:45:15,837 >> Feature extractor saved in ./checkpoint-4000/preprocessor_config.json
 [INFO|feature_extraction_utils.py:369] 2023-05-11 21:45:26,357 >> Feature extractor saved in ./preprocessor_config.json
+/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 '
+
 80%|████████  | 4001/5000 [36:05:04<276:31:36, 996.49s/it]
 80%|████████  | 4002/5000 [36:05:32<195:43:22, 706.01s/it]
 80%|████████  | 4003/5000 [36:06:04<139:31:57, 503.83s/it]
 80%|████████  | 4004/5000 [36:06:31<99:48:00, 360.72s/it] 
 80%|████████  | 4005/5000 [36:07:06<72:38:55, 262.85s/it]
 80%|████████  | 4006/5000 [36:07:34<53:10:57, 192.61s/it]
 80%|████████  | 4007/5000 [36:08:03<39:35:50, 143.56s/it]
 80%|████████  | 4008/5000 [36:08:33<30:06:13, 109.25s/it]
 80%|████████  | 4009/5000 [36:09:03<23:32:57, 85.55s/it] 
 80%|████████  | 4010/5000 [36:09:31<18:48:01, 68.36s/it]
 80%|████████  | 4011/5000 [36:10:03<15:47:00, 57.45s/it]
 80%|████████  | 4012/5000 [36:10:35<13:40:07, 49.80s/it]
 80%|████████  | 4013/5000 [36:11:03<11:51:20, 43.24s/it]
 80%|████████  | 4014/5000 [36:11:33<10:45:54, 39.30s/it]
 80%|████████  | 4015/5000 [36:12:01<9:48:40, 35.86s/it] 
 80%|████████  | 4016/5000 [36:12:31<9:20:23, 34.17s/it]
 80%|████████  | 4017/5000 [36:12:58<8:45:39, 32.09s/it]
 80%|████████  | 4018/5000 [36:13:30<8:44:40, 32.06s/it]
 80%|████████  | 4019/5000 [36:13:58<8:20:36, 30.62s/it]
 80%|████████  | 4020/5000 [36:14:29<8:21:45, 30.72s/it]
 80%|████████  | 4021/5000 [36:14:57<8:11:49, 30.14s/it]
 80%|████████  | 4022/5000 [36:15:28<8:13:17, 30.26s/it]
 80%|████████  | 4023/5000 [36:15:56<8:04:14, 29.74s/it]
 80%|████████  | 4024/5000 [36:16:27<8:09:20, 30.08s/it]
 80%|████████  | 4025/5000 [36:16:55<7:56:53, 29.35s/it]
                                                        
 80%|████████  | 4025/5000 [36:16:55<7:56:53, 29.35s/it]
 81%|████████  | 4026/5000 [36:17:26<8:06:38, 29.98s/it]
 81%|████████  | 4027/5000 [36:17:54<7:53:10, 29.18s/it]
 81%|████████  | 4028/5000 [36:18:25<8:00:52, 29.68s/it]
 81%|████████  | 4029/5000 [36:18:52<7:47:52, 28.91s/it]
 81%|████████  | 4030/5000 [36:19:31<8:35:59, 31.92s/it]
 81%|████████  | 4031/5000 [36:19:59<8:17:27, 30.80s/it]
 81%|████████  | 4032/5000 [36:20:29<8:16:13, 30.76s/it]
 81%|████████  | 4033/5000 [36:21:01<8:17:26, 30.86s/it]
 81%|████████  | 4034/5000 [36:21:28<8:02:26, 29.97s/it]
 81%|████████  | 4035/5000 [36:21:59<8:03:38, 30.07s/it]
 81%|████████  | 4036/5000 [36:22:27<7:56:28, 29.66s/it]
 81%|████████  | 4037/5000 [36:22:57<7:57:09, 29.73s/it]
 81%|████████  | 4038/5000 [36:23:25<7:44:33, 28.97s/it]
 81%|████████  | 4039/5000 [36:23:55<7:53:40, 29.57s/it]
 81%|████████  | 4040/5000 [36:24:22<7:39:26, 28.72s/it]
 81%|████████  | 4041/5000 [36:24:53<7:50:23, 29.43s/it]
 81%|████████  | 4042/5000 [36:25:21<7:40:02, 28.81s/it]
 81%|████████  | 4043/5000 [36:25:52<7:53:23, 29.68s/it]
 81%|████████  | 4044/5000 [36:26:21<7:46:08, 29.26s/it]
 81%|████████  | 4045/5000 [36:26:51<7:51:52, 29.65s/it]
 81%|████████  | 4046/5000 [36:27:21<7:50:31, 29.59s/it]
 81%|████████  | 4047/5000 [36:27:51<7:54:25, 29.87s/it]
 81%|████████  | 4048/5000 [36:28:24<8:06:50, 30.68s/it]
 81%|████████  | 4049/5000 [36:28:51<7:49:18, 29.61s/it]
 81%|████████  | 4050/5000 [36:29:22<7:57:29, 30.16s/it]
                                                        
 81%|████████  | 4050/5000 [36:29:22<7:57:29, 30.16s/it]
 81%|████████  | 4051/5000 [36:29:51<7:50:55, 29.77s/it]
 81%|████████  | 4052/5000 [36:30:22<7:55:38, 30.10s/it]
 81%|████████  | 4053/5000 [36:30:51<7:48:21, 29.67s/it]
 81%|████████  | 4054/5000 [36:31:21<7:50:49, 29.86s/it]
 81%|████████  | 4055/5000 [36:31:50<7:45:21, 29.55s/it]
 81%|█████���██  | 4056/5000 [36:32:22<7:57:05, 30.32s/it]
 81%|████████  | 4057/5000 [36:32:54<8:04:39, 30.84s/it]
 81%|████████  | 4058/5000 [36:33:22<7:51:43, 30.05s/it]
 81%|████████  | 4059/5000 [36:33:53<7:54:46, 30.27s/it]
 81%|████████  | 4060/5000 [36:34:21<7:44:52, 29.67s/it]
 81%|████████  | 4061/5000 [36:34:53<7:52:21, 30.18s/it]
 81%|████████  | 4062/5000 [36:35:20<7:38:33, 29.33s/it]
 81%|████████▏ | 4063/5000 [36:35:50<7:43:24, 29.67s/it]
 81%|████████▏ | 4064/5000 [36:36:18<7:31:10, 28.92s/it]
 81%|████████▏ | 4065/5000 [36:36:49<7:44:21, 29.80s/it]
 81%|████████▏ | 4066/5000 [36:37:18<7:35:59, 29.29s/it]
 81%|████████▏ | 4067/5000 [36:37:47<7:34:58, 29.26s/it]
 81%|████████▏ | 4068/5000 [36:38:17<7:37:52, 29.48s/it]
 81%|████████▏ | 4069/5000 [36:38:44<7:26:37, 28.78s/it]
 81%|████████▏ | 4070/5000 [36:39:15<7:38:01, 29.55s/it]
 81%|████████▏ | 4071/5000 [36:39:42<7:25:57, 28.80s/it]
 81%|████████▏ | 4072/5000 [36:40:13<7:33:07, 29.30s/it]
 81%|████████▏ | 4073/5000 [36:40:41<7:27:27, 28.96s/it]
 81%|████████▏ | 4074/5000 [36:41:15<7:52:01, 30.58s/it]
 82%|████████▏ | 4075/5000 [36:41:46<7:53:07, 30.69s/it]
                                                        
 82%|████████▏ | 4075/5000 [36:41:46<7:53:07, 30.69s/it]
 82%|████████▏ | 4076/5000 [36:42:13<7:36:21, 29.63s/it]
 82%|████████▏ | 4077/5000 [36:42:45<7:45:27, 30.26s/it]
 82%|████████▏ | 4078/5000 [36:43:14<7:38:13, 29.82s/it]
 82%|████████▏ | 4079/5000 [36:43:44<7:39:48, 29.95s/it]
 82%|████████▏ | 4080/5000 [36:44:12<7:30:57, 29.41s/it]
 82%|████████▏ | 4081/5000 [36:44:43<7:35:50, 29.76s/it]
 82%|████████▏ | 4082/5000 [36:45:11<7:28:36, 29.32s/it]
 82%|████████▏ | 4083/5000 [36:45:42<7:32:50, 29.63s/it]
 82%|████████▏ | 4084/5000 [36:46:10<7:25:13, 29.16s/it]
 82%|████████▏ | 4085/5000 [36:46:41<7:35:16, 29.85s/it]
 82%|████████▏ | 4086/5000 [36:47:08<7:20:29, 28.92s/it]
 82%|████████▏ | 4087/5000 [36:47:39<7:29:21, 29.53s/it]
 82%|████████▏ | 4088/5000 [36:48:06<7:17:40, 28.79s/it]
 82%|████████▏ | 4089/5000 [36:48:38<7:30:52, 29.70s/it]
 82%|████████▏ | 4090/5000 [36:49:09<7:38:15, 30.22s/it]
 82%|████████▏ | 4091/5000 [36:49:36<7:23:41, 29.29s/it]
 82%|████████▏ | 4092/5000 [36:50:07<7:31:39, 29.85s/it]
 82%|████████▏ | 4093/5000 [36:50:35<7:19:08, 29.05s/it]
 82%|████████▏ | 4094/5000 [36:51:05<7:26:27, 29.57s/it]
 82%|████████▏ | 4095/5000 [36:51:32<7:14:42, 28.82s/it]
 82%|████████▏ | 4096/5000 [36:52:04<7:28:10, 29.75s/it]
 82%|████████▏ | 4097/5000 [36:52:32<7:16:15, 28.99s/it]
 82%|████████▏ | 4098/5000 [36:53:03<7:26:39, 29.71s/it]
 82%|████████▏ | 4099/5000 [36:53:31<7:17:29, 29.13s/it]
 82%|████████▏ | 4100/5000 [36:54:01<7:20:09, 29.34s/it]
                                                        
 82%|████████▏ | 4100/5000 [36:54:01<7:20:09, 29.34s/it]
 82%|████████▏ | 4101/5000 [36:54:29<7:15:48, 29.09s/it]
 82%|████████▏ | 4102/5000 [36:55:00<7:21:51, 29.52s/it]
 82%|████████▏ | 4103/5000 [36:55:28<7:15:47, 29.15s/it]
 82%|████████▏ | 4104/5000 [36:56:00<7:27:54, 29.99s/it]
 82%|████████▏ | 4105/5000 [36:56:30<7:26:21, 29.92s/it]
 82%|████████▏ | 4106/5000 [36:56:58<7:17:54, 29.39s/it]
 82%|████████▏ | 4107/5000 [36:57:28<7:22:57, 29.76s/it]
 82%|████████▏ | 4108/5000 [36:57:56<7:13:05, 29.13s/it]
 82%|████████▏ | 4109/5000 [36:58:26<7:18:08, 29.50s/it]
 82%|████████▏ | 4110/5000 [36:58:55<7:13:56, 29.26s/it]
 82%|████████▏ | 4111/5000 [36:59:26<7:21:19, 29.79s/it]
 82%|████████▏ | 4112/5000 [36:59:53<7:09:13, 29.00s/it]
 82%|████████▏ | 4113/5000 [37:00:24<7:14:26, 29.39s/it]
 82%|████████▏ | 4114/5000 [37:00:51<7:03:17, 28.67s/it]
 82%|████████▏ | 4115/5000 [37:01:22<7:14:52, 29.48s/it]
 82%|████████▏ | 4116/5000 [37:01:49<7:03:40, 28.76s/it]
 82%|████████▏ | 4117/5000 [37:02:20<7:12:55, 29.42s/it]
 82%|████████▏ | 4118/5000 [37:02:50<7:16:55, 29.72s/it]
 82%|████████▏ | 4119/5000 [37:03:11<6:36:14, 26.99s/it]
 82%|████████▏ | 4120/5000 [37:03:21<5:23:09, 22.03s/it]
 82%|████████▏ | 4121/5000 [37:03:32<4:31:50, 18.56s/it]
 82%|████████▏ | 4122/5000 [37:03:42<3:56:29, 16.16s/it]{'eval_loss': 0.22095343470573425, 'eval_wer': 8.212281066472636, 'eval_runtime': 3161.6276, 'eval_samples_per_second': 4.909, 'eval_steps_per_second': 0.077, 'epoch': 16.02}
+{'loss': 0.1083, 'learning_rate': 2.168888888888889e-06, 'epoch': 16.03}
+{'loss': 0.1099, 'learning_rate': 2.1133333333333336e-06, 'epoch': 16.03}
+{'loss': 0.0948, 'learning_rate': 2.057777777777778e-06, 'epoch': 16.04}
+{'loss': 0.0966, 'learning_rate': 2.0022222222222225e-06, 'epoch': 16.04}
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
 82%|████████▏ | 4123/5000 [37:05:25<10:16:39, 42.19s/it]
 82%|████████▏ | 4124/5000 [37:05:54<9:16:59, 38.15s/it] 
 82%|████████▎ | 4125/5000 [37:06:21<8:27:37, 34.81s/it]
                                                        
 82%|████████▎ | 4125/5000 [37:06:21<8:27:37, 34.81s/it]
 83%|████████▎ | 4126/5000 [37:06:49<7:55:50, 32.67s/it]
 83%|████████▎ | 4127/5000 [37:07:17<7:35:24, 31.30s/it]
 83%|████████▎ | 4128/5000 [37:07:45<7:18:44, 30.19s/it]
 83%|████████▎ | 4129/5000 [37:08:14<7:16:11, 30.05s/it]
 83%|████████▎ | 4130/5000 [37:08:42<7:04:01, 29.24s/it]
 83%|████████▎ | 4131/5000 [37:09:11<7:05:34, 29.38s/it]
 83%|████████▎ | 4132/5000 [37:09:37<6:49:30, 28.31s/it]
 83%|████████▎ | 4133/5000 [37:10:04<6:44:45, 28.01s/it]
 83%|████████▎ | 4134/5000 [37:10:34<6:50:05, 28.41s/it]
 83%|████████▎ | 4135/5000 [37:11:01<6:45:24, 28.12s/it]
 83%|████████▎ | 4136/5000 [37:11:31<6:54:02, 28.75s/it]
 83%|████████▎ | 4137/5000 [37:11:59<6:48:00, 28.37s/it]
 83%|████████▎ | 4138/5000 [37:12:29<6:57:08, 29.04s/it]
 83%|████████▎ | 4139/5000 [37:12:58<6:53:52, 28.84s/it]
 83%|████████▎ | 4140/5000 [37:13:26<6:48:29, 28.50s/it]
 83%|████████▎ | 4141/5000 [37:13:54<6:48:55, 28.56s/it]
 83%|████████▎ | 4142/5000 [37:14:23<6:48:19, 28.55s/it]
 83%|████████▎ | 4143/5000 [37:14:51<6:47:59, 28.56s/it]
 83%|████████▎ | 4144/5000 [37:15:20<6:48:47, 28.65s/it]
 83%|████████▎ | 4145/5000 [37:15:48<6:45:43, 28.47s/it]
 83%|████████▎ | 4146/5000 [37:16:17<6:44:16, 28.40s/it]
 83%|████████▎ | 4147/5000 [37:16:45<6:45:44, 28.54s/it]
 83%|████████▎ | 4148/5000 [37:17:13<6:39:16, 28.12s/it]
 83%|████████▎ | 4149/5000 [37:17:41<6:41:18, 28.29s/it]
 83%|████████▎ | 4150/5000 [37:18:09<6:39:47, 28.22s/it]
                                                        
 83%|████████▎ | 4150/5000 [37:18:09<6:39:47, 28.22s/it]
 83%|████████▎ | 4151/5000 [37:18:39<6:43:58, 28.55s/it]
 83%|████████▎ | 4152/5000 [37:19:09<6:50:12, 29.02s/it]
 83%|████████▎ | 4153/5000 [37:19:37<6:44:58, 28.69s/it]
 83%|████████▎ | 4154/5000 [37:20:06<6:45:43, 28.77s/it]
 83%|████████▎ | 4155/5000 [37:20:34<6:42:57, 28.61s/it]
 83%|████████▎ | 4156/5000 [37:21:02<6:38:34, 28.34s/it]
 83%|████████▎ | 4157/5000 [37:21:31<6:43:54, 28.75s/it]
 83%|████████▎ | 4158/5000 [37:21:59<6:40:45, 28.56s/it]
 83%|████████▎ | 4159/5000 [37:22:28<6:40:39, 28.58s/it]
 83%|████████▎ | 4160/5000 [37:22:56<6:39:12, 28.51s/it]
 83%|████████▎ | 4161/5000 [37:23:25<6:37:35, 28.43s/it]
 83%|████████▎ | 4162/5000 [37:23:54<6:41:53, 28.78s/it]
 83%|████████▎ | 4163/5000 [37:24:23<6:39:26, 28.63s/it]
 83%|████████▎ | 4164/5000 [37:24:51<6:38:40, 28.61s/it]
 83%|████████▎ | 4165/5000 [37:25:19<6:34:43, 28.36s/it]
 83%|████████▎ | 4166/5000 [37:25:47<6:32:33, 28.24s/it]
 83%|████████▎ | 4167/5000 [37:26:16<6:37:42, 28.65s/it]
 83%|████████▎ | 4168/5000 [37:26:44<6:31:04, 28.20s/it]
 83%|████████▎ | 4169/5000 [37:27:12<6:31:38, 28.28s/it]
 83%|████████▎ | 4170/5000 [37:27:41<6:33:50, 28.47s/it]
 83%|████████▎ | 4171/5000 [37:28:09<6:33:30, 28.48s/it]
 83%|████████▎ | 4172/5000 [37:28:37<6:30:45, 28.32s/it]
 83%|████████▎ | 4173/5000 [37:29:05<6:26:21, 28.03s/it]
 83%|████████▎ | 4174/5000 [37:29:33<6:28:07, 28.19s/it]
 84%|████████▎ | 4175/5000 [37:30:03<6:34:17, 28.68s/it]
                                                        
 84%|████████▎ | 4175/5000 [37:30:03<6:34:17, 28.68s/it]
 84%|████████▎ | 4176/5000 [37:30:30<6:27:52, 28.24s/it]
 84%|████████▎ | 4177/5000 [37:30:59<6:27:15, 28.23s/it]
 84%|████████▎ | 4178/5000 [37:31:26<6:22:59, 27.96s/it]
 84%|████████▎ | 4179/5000 [37:31:54<6:23:47, 28.05s/it]
 84%|████████▎ | 4180/5000 [37:32:22<6:22:39, 28.00s/it]
 84%|████████▎ | 4181/5000 [37:32:50<6:23:56, 28.13s/it]
 84%|████████▎ | 4182/5000 [37:33:19<6:27:16, 28.41s/it]
 84%|████████▎ | 4183/5000 [37:33:47<6:21:40, 28.03s/it]
 84%|████████▎ | 4184/5000 [37:34:15<6:24:31, 28.27s/it]
 84%|████████▎ | 4185/5000 [37:34:44<6:24:44, 28.32s/it]
 84%|████████▎ | 4186/5000 [37:35:12<6:24:15, 28.32s/it]
 84%|████████▎ | 4187/5000 [37:35:40<6:21:55, 28.19s/it]
 84%|████████▍ | 4188/5000 [37:36:07<6:17:59, 27.93s/it]
 84%|████████▍ | 4189/5000 [37:36:37<6:25:03, 28.49s/it]
 84%|████████▍ | 4190/5000 [37:37:04<6:19:22, 28.10s/it]
 84%|████████▍ | 4191/5000 [37:37:32<6:18:38, 28.08s/it]
 84%|████████▍ | 4192/5000 [37:38:01<6:18:37, 28.12s/it]
 84%|████████▍ | 4193/5000 [37:38:28<6:15:06, 27.89s/it]
 84%|████████▍ | 4194/5000 [37:38:57<6:20:13, 28.30s/it]
 84%|████████▍ | 4195/5000 [37:39:24<6:14:37, 27.92s/it]
 84%|████████▍ | 4196/5000 [37:39:53<6:17:59, 28.21s/it]
 84%|████████▍ | 4197/5000 [37:40:20<6:13:46, 27.93s/it]
 84%|████████▍ | 4198/5000 [37:40:51<6:25:14, 28.82s/it]
 84%|████████▍ | 4199/5000 [37:41:20<6:25:45, 28.90s/it]
 84%|████████▍ | 4200/5000 [37:41:48<6:19:51, 28.49s/it]
                                                        
 84%|████████▍ | 4200/5000 [37:41:48<6:19:51, 28.49s/it]
 84%|████████▍ | 4201/5000 [37:42:17<6:23:00, 28.76s/it]
 84%|████████▍ | 4202/5000 [37:42:45<6:19:31, 28.54s/it]
 84%|████████▍ | 4203/5000 [37:43:13<6:15:21, 28.26s/it]
 84%|████████▍ | 4204/5000 [37:43:42<6:18:58, 28.57s/it]
 84%|████████▍ | 4205/5000 [37:44:11<6:18:07, 28.54s/it]
 84%|████████▍ | 4206/5000 [37:44:40<6:19:23, 28.67s/it]
 84%|████████▍ | 4207/5000 [37:45:08<6:17:54, 28.59s/it]
 84%|████████▍ | 4208/5000 [37:45:37<6:17:31, 28.60s/it]
 84%|████████▍ | 4209/5000 [37:46:05<6:14:58, 28.44s/it]
 84%|████████▍ | 4210/5000 [37:46:33<6:12:05, 28.26s/it]
 84%|████████▍ | 4211/5000 [37:47:01<6:12:31, 28.33s/it]
 84%|████████▍ | 4212/5000 [37:47:30<6:15:02, 28.56s/it]
 84%|████████▍ | 4213/5000 [37:47:58<6:11:53, 28.35s/it]
 84%|████████▍ | 4214/5000 [37:48:27<6:12:04, 28.40s/it]
 84%|████████▍ | 4215/5000 [37:48:55<6:11:15, 28.38s/it]
 84%|████████▍ | 4216/5000 [37:49:23<6:07:39, 28.14s/it]
 84%|████████▍ | 4217/5000 [37:49:51<6:09:43, 28.33s/it]
 84%|████████▍ | 4218/5000 [37:50:18<6:04:01, 27.93s/it]
 84%|████████▍ | 4219/5000 [37:50:46<6:03:41, 27.94s/it]
 84%|████████▍ | 4220/5000 [37:51:14<6:01:26, 27.80s/it]
 84%|████████▍ | 4221/5000 [37:51:41<5:59:13, 27.67s/it]
 84%|████████▍ | 4222/5000 [37:52:11<6:06:13, 28.24s/it]
 84%|████████▍ | 4223/5000 [37:52:38<6:01:25, 27.91s/it]
 84%|████████▍ | 4224/5000 [37:53:06<6:02:22, 28.02s/it]
 84%|████████▍ | 4225/5000 [37:53:33<5:58:48, 27.78s/it]
                                                        
 84%|████████▍ | 4225/5000 [37:53:33<5:58:48, 27.78s/it]
 85%|████████▍ | 4226/5000 [37:54:03<6:03:40, 28.19s/it]
 85%|████████▍ | 4227/5000 [37:54:31<6:03:54, 28.25s/it]
 85%|████████▍ | 4228/5000 [37:54:58<6:00:13, 28.00s/it]
 85%|████████▍ | 4229/5000 [37:55:26<5:59:07, 27.95s/it]
 85%|████████▍ | 4230/5000 [37:55:53<5:55:30, 27.70s/it]
 85%|████████▍ | 4231/5000 [37:56:22<5:57:11, 27.87s/it]
 85%|████████▍ | 4232/5000 [37:56:49<5:56:02, 27.82s/it]
 85%|████████▍ | 4233/5000 [37:57:18<5:57:29, 27.97s/it]
 85%|████████▍ | 4234/5000 [37:57:47<6:02:09, 28.37s/it]
 85%|████████▍ | 4235/5000 [37:58:14<5:57:25, 28.03s/it]
 85%|████████▍ | 4236/5000 [37:58:43<6:00:01, 28.27s/it]
 85%|████████▍ | 4237/5000 [37:59:11<5:59:56, 28.30s/it]
 85%|████████▍ | 4238/5000 [37:59:39<5:58:45, 28.25s/it]
 85%|████████▍ | 4239/5000 [38:00:08<6:00:44, 28.44s/it]
 85%|████████▍ | 4240/5000 [38:00:37<5:59:59, 28.42s/it]
 85%|████████▍ | 4241/5000 [38:01:07<6:08:18, 29.12s/it]
 85%|████████▍ | 4242/5000 [38:01:35<6:03:46, 28.79s/it]
 85%|████████▍ | 4243/5000 [38:02:05<6:05:46, 28.99s/it]
 85%|████████▍ | 4244/5000 [38:02:33<6:02:13, 28.75s/it]
 85%|████████▍ | 4245/5000 [38:03:01<6:00:01, 28.61s/it]
 85%|████████▍ | 4246/5000 [38:03:30<5:58:21, 28.52s/it]
 85%|████████▍ | 4247/5000 [38:03:59<6:01:58, 28.84s/it]
 85%|████████▍ | 4248/5000 [38:04:28<5:59:36, 28.69s/it]
 85%|████████▍ | 4249/5000 [38:04:56<5:57:04, 28.53s/it]
 85%|████████▌ | 4250/5000 [38:05:24<5:55:21, 28.43s/it]
                                                        
 85%|████████▌ | 4250/5000 [38:05:24<5:55:21, 28.43s/it]
 85%|████████▌ | 4251/5000 [38:05:52<5:53:40, 28.33s/it]
 85%|████████▌ | 4252/5000 [38:06:21<5:56:59, 28.64s/it]
 85%|████████▌ | 4253/5000 [38:06:48<5:50:32, 28.16s/it]
 85%|████████▌ | 4254/5000 [38:07:18<5:53:35, 28.44s/it]
 85%|████████▌ | 4255/5000 [38:07:47<5:56:36, 28.72s/it]
 85%|████████▌ | 4256/5000 [38:08:14<5:50:20, 28.25s/it]
 85%|████████▌ | 4257/5000 [38:08:43<5:54:07, 28.60s/it]
 85%|████████▌ | 4258/5000 [38:09:11<5:48:39, 28.19s/it]
 85%|████████▌ | 4259/5000 [38:09:40<5:53:17, 28.61s/it]
 85%|████████▌ | 4260/5000 [38:10:10<5:58:00, 29.03s/it]
 85%|████████▌ | 4261/5000 [38:10:38<5:50:57, 28.49s/it]
 85%|████████▌ | 4262/5000 [38:11:07<5:53:48, 28.77s/it]
 85%|████████▌ | 4263/5000 [38:11:34<5:47:09, 28.26s/it]
 85%|████████▌ | 4264/5000 [38:12:03<5:50:07, 28.54s/it]
 85%|████████▌ | 4265/5000 [38:12:30<5:44:32, 28.13s/it]
 85%|████████▌ | 4266/5000 [38:12:59<5:47:12, 28.38s/it]
 85%|████████▌ | 4267/5000 [38:13:27<5:44:05, 28.17s/it]
 85%|████████▌ | 4268/5000 [38:13:55<5:43:42, 28.17s/it]
 85%|████████▌ | 4269/5000 [38:14:24<5:44:42, 28.29s/it]
 85%|████████▌ | 4270/5000 [38:14:52<5:42:21, 28.14s/it]
 85%|████████▌ | 4271/5000 [38:15:20<5:41:08, 28.08s/it]
 85%|████████▌ | 4272/5000 [38:15:48<5:40:43, 28.08s/it]
 85%|████████▌ | 4273/5000 [38:16:15<5:38:03, 27.90s/it]
 85%|████████▌ | 4274/5000 [38:16:43<5:37:24, 27.89s/it]
 86%|████████▌ | 4275/5000 [38:17:12<5:41:43, 28.28s/it]
                                                        
 86%|████████▌ | 4275/5000 [38:17:12<5:41:43, 28.28s/it]
 86%|████████▌ | 4276/5000 [38:17:39<5:37:20, 27.96s/it]
 86%|████████▌ | 4277/5000 [38:18:10<5:45:03, 28.64s/it]
 86%|████████▌ | 4278/5000 [38:18:38<5:43:06, 28.51s/it]
 86%|████████▌ | 4279/5000 [38:19:06<5:39:59, 28.29s/it]
 86%|████████▌ | 4280/5000 [38:19:36<5:46:52, 28.91s/it]
 86%|████████▌ | 4281/5000 [38:20:03<5:40:49, 28.44s/it]
 86%|████████▌ | 4282/5000 [38:20:33<5:43:52, 28.74s/it]
 86%|████████▌ | 4283/5000 [38:21:00<5:38:52, 28.36s/it]
 86%|████████▌ | 4284/5000 [38:21:30<5:42:20, 28.69s/it]
 86%|████████▌ | 4285/5000 [38:21:58<5:39:00, 28.45s/it]
 86%|████████▌ | 4286/5000 [38:22:26<5:38:23, 28.44s/it]
 86%|████████▌ | 4287/5000 [38:22:55<5:39:10, 28.54s/it]
 86%|████████▌ | 4288/5000 [38:23:22<5:34:04, 28.15s/it]
 86%|████████▌ | 4289/5000 [38:23:53<5:44:06, 29.04s/it]
 86%|████████▌ | 4290/5000 [38:24:24<5:49:48, 29.56s/it]
 86%|████████▌ | 4291/5000 [38:24:52<5:43:59, 29.11s/it]
 86%|████████▌ | 4292/5000 [38:25:22<5:47:16, 29.43s/it]
 86%|████████▌ | 4293/5000 [38:25:50<5:43:03, 29.11s/it]
 86%|████████▌ | 4294/5000 [38:26:24<5:58:27, 30.46s/it]
 86%|████████▌ | 4295/5000 [38:26:55<5:58:56, 30.55s/it]
 86%|████████▌ | 4296/5000 [38:27:23<5:49:40, 29.80s/it]
 86%|████████▌ | 4297/5000 [38:27:53<5:51:39, 30.01s/it]
 86%|████████▌ | 4298/5000 [38:28:22<5:46:56, 29.65s/it]
 86%|████████▌ | 4299/5000 [38:28:53<5:49:00, 29.87s/it]
 86%|████████▌ | 4300/5000 [38:29:22<5:47:26, 29.78s/it]
                                                        
 86%|████████▌ | 4300/5000 [38:29:22<5:47:26, 29.78s/it]
 86%|████████▌ | 4301/5000 [38:29:50<5:41:51, 29.34s/it]
 86%|████████▌ | 4302/5000 [38:30:18<5:35:23, 28.83s/it]
 86%|████████▌ | 4303/5000 [38:30:46<5:31:54, 28.57s/it]
 86%|████████▌ | 4304/5000 [38:31:14<5:28:35, 28.33s/it]
 86%|████████▌ | 4305/5000 [38:31:43<5:31:56, 28.66s/it]
 86%|████████▌ | 4306/5000 [38:32:10<5:26:00, 28.18s/it]
 86%|████████▌ | 4307/5000 [38:32:39<5:26:33, 28.27s/it]
 86%|████████▌ | 4308/5000 [38:33:07<5:26:08, 28.28s/it]
 86%|████████▌ | 4309/5000 [38:33:35<5:25:05, 28.23s/it]
 86%|████████▌ | 4310/5000 [38:34:04<5:24:58, 28.26s/it]
 86%|████████▌ | 4311/5000 [38:34:32<5:25:22, 28.33s/it]
 86%|████████▌ | 4312/5000 [38:35:02<5:30:56, 28.86s/it]
 86%|████████▋ | 4313/5000 [38:35:29<5:24:31, 28.34s/it]
 86%|████████▋ | 4314/5000 [38:35:58<5:26:42, 28.58s/it]
 86%|████████▋ | 4315/5000 [38:36:26<5:21:15, 28.14s/it]
 86%|████████▋ | 4316/5000 [38:36:55<5:25:21, 28.54s/it]
 86%|████████▋ | 4317/5000 [38:37:25<5:28:45, 28.88s/it]
 86%|████████▋ | 4318/5000 [38:37:52<5:22:30, 28.37s/it]
 86%|████████▋ | 4319/5000 [38:38:21<5:23:04, 28.46s/it]
 86%|████████▋ | 4320/5000 [38:38:48<5:18:36, 28.11s/it]
 86%|████████▋ | 4321/5000 [38:39:16<5:19:58, 28.27s/it]
 86%|████████▋ | 4322/5000 [38:39:45<5:19:24, 28.27s/it]
 86%|████████▋ | 4323/5000 [38:40:12<5:16:43, 28.07s/it]
 86%|████████▋ | 4324/5000 [38:40:42<5:20:05, 28.41s/it]
 86%|████████▋ | 4325/5000 [38:41:09<5:15:39, 28.06s/it]
                                                        
 86%|████████▋ | 4325/5000 [38:41:09<5:15:39, 28.06s/it]
 87%|████████▋ | 4326/5000 [38:41:37<5:17:13, 28.24s/it]
 87%|████████▋ | 4327/5000 [38:42:05<5:13:27, 27.95s/it]
 87%|████████▋ | 4328/5000 [38:42:34<5:16:53, 28.29s/it]
 87%|████████▋ | 4329/5000 [38:43:02<5:16:46, 28.33s/it]
 87%|████████▋ | 4330/5000 [38:43:30<5:15:57, 28.30s/it]
 87%|████████▋ | 4331/5000 [38:44:00<5:18:23, 28.55s/it]
 87%|████████▋ | 4332/5000 [38:44:27<5:13:47, 28.19s/it]
 87%|████████▋ | 4333/5000 [38:44:55<5:13:04, 28.16s/it]
 87%|████████▋ | 4334/5000 [38:45:22<5:09:05, 27.85s/it]
 87%|████████▋ | 4335/5000 [38:45:51<5:12:37, 28.21s/it]
 87%|████████▋ | 4336/5000 [38:46:18<5:08:39, 27.89s/it]
 87%|████████▋ | 4337/5000 [38:46:48<5:13:27, 28.37s/it]
 87%|████████▋ | 4338/5000 [38:47:17<5:14:08, 28.47s/it]
 87%|████████▋ | 4339/5000 [38:47:45<5:12:11, 28.34s/it]
 87%|████████▋ | 4340/5000 [38:48:13<5:12:22, 28.40s/it]
 87%|████████▋ | 4341/5000 [38:48:40<5:08:35, 28.10s/it]
 87%|████████▋ | 4342/5000 [38:49:10<5:12:18, 28.48s/it]
 87%|████████▋ | 4343/5000 [38:49:38<5:11:43, 28.47s/it]
 87%|████████▋ | 4344/5000 [38:50:07<5:11:04, 28.45s/it]
 87%|████████▋ | 4345/5000 [38:50:34<5:08:05, 28.22s/it]
 87%|████████▋ | 4346/5000 [38:51:02<5:04:41, 27.95s/it]
 87%|████████▋ | 4347/5000 [38:51:31<5:09:32, 28.44s/it]
 87%|████████▋ | 4348/5000 [38:51:58<5:04:49, 28.05s/it]
 87%|████████▋ | 4349/5000 [38:52:28<5:08:55, 28.47s/it]
 87%|████████▋ | 4350/5000 [38:52:57<5:10:15, 28.64s/it]
                                                        
 87%|████████▋ | 4350/5000 [38:52:57<5:10:15, 28.64s/it]
 87%|████████▋ | 4351/5000 [38:53:25<5:08:41, 28.54s/it]
 87%|████████▋ | 4352/5000 [38:53:54<5:08:24, 28.56s/it]
 87%|████████▋ | 4353/5000 [38:54:21<5:03:48, 28.17s/it]
 87%|████████▋ | 4354/5000 [38:54:52<5:11:27, 28.93s/it]
 87%|████████▋ | 4355/5000 [38:55:19<5:05:27, 28.41s/it]
 87%|████████▋ | 4356/5000 [38:55:48<5:08:06, 28.71s/it]
 87%|████████▋ | 4357/5000 [38:56:17<5:06:39, 28.62s/it]
 87%|████████▋ | 4358/5000 [38:56:45<5:04:34, 28.47s/it]
 87%|████████▋ | 4359/5000 [38:57:13<5:02:31, 28.32s/it]
 87%|████████▋ | 4360/5000 [38:57:40<4:58:56, 28.03s/it]
 87%|████████▋ | 4361/5000 [38:58:11<5:06:43, 28.80s/it]
 87%|████████▋ | 4362/5000 [38:58:23<4:12:54, 23.78s/it]
 87%|████████▋ | 4363/5000 [38:58:33<3:29:59, 19.78s/it]
 87%|████████▋ | 4364/5000 [38:58:44<2:59:54, 16.97s/it]
 87%|████████▋ | 4365/5000 [38:58:54<2:39:16, 15.05s/it]{'loss': 0.094, 'learning_rate': 1.9466666666666665e-06, 'epoch': 17.0}
+{'loss': 0.0338, 'learning_rate': 1.8911111111111114e-06, 'epoch': 17.01}
+{'loss': 0.0257, 'learning_rate': 1.8355555555555557e-06, 'epoch': 17.01}
+{'loss': 0.0258, 'learning_rate': 1.7800000000000001e-06, 'epoch': 17.02}
+{'loss': 0.0241, 'learning_rate': 1.7244444444444448e-06, 'epoch': 17.02}
+{'loss': 0.0246, 'learning_rate': 1.668888888888889e-06, 'epoch': 17.03}
+{'loss': 0.0216, 'learning_rate': 1.6133333333333335e-06, 'epoch': 17.03}
+{'loss': 0.0252, 'learning_rate': 1.5577777777777777e-06, 'epoch': 17.04}
+{'loss': 0.0239, 'learning_rate': 1.5022222222222224e-06, 'epoch': 17.04}
+{'loss': 0.024, 'learning_rate': 1.4466666666666669e-06, 'epoch': 17.05}
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
 87%|████████▋ | 4366/5000 [39:00:48<7:52:14, 44.69s/it]
 87%|████████▋ | 4367/5000 [39:01:18<7:04:00, 40.19s/it]
 87%|████████▋ | 4368/5000 [39:01:46<6:26:25, 36.69s/it]
 87%|████████▋ | 4369/5000 [39:02:15<5:59:38, 34.20s/it]
 87%|████████▋ | 4370/5000 [39:02:44<5:42:26, 32.61s/it]
 87%|████████▋ | 4371/5000 [39:03:11<5:26:36, 31.15s/it]
 87%|████████▋ | 4372/5000 [39:03:41<5:21:10, 30.69s/it]
 87%|████████▋ | 4373/5000 [39:04:10<5:15:19, 30.17s/it]
 87%|████████▋ | 4374/5000 [39:04:38<5:06:41, 29.40s/it]
 88%|████████▊ | 4375/5000 [39:05:06<5:03:20, 29.12s/it]
                                                        
 88%|████████▊ | 4375/5000 [39:05:06<5:03:20, 29.12s/it]
 88%|████████▊ | 4376/5000 [39:05:34<5:00:11, 28.86s/it]
 88%|████████▊ | 4377/5000 [39:06:03<4:57:30, 28.65s/it]
 88%|████████▊ | 4378/5000 [39:06:31<4:55:53, 28.54s/it]
 88%|████████▊ | 4379/5000 [39:06:58<4:51:05, 28.13s/it]
 88%|████████▊ | 4380/5000 [39:07:26<4:50:55, 28.15s/it]
 88%|████████▊ | 4381/5000 [39:07:55<4:51:49, 28.29s/it]
 88%|████████▊ | 4382/5000 [39:08:23<4:50:55, 28.25s/it]
 88%|████████▊ | 4383/5000 [39:08:53<4:56:13, 28.81s/it]
 88%|████████▊ | 4384/5000 [39:09:20<4:50:17, 28.28s/it]
 88%|████████▊ | 4385/5000 [39:09:49<4:53:18, 28.62s/it]
 88%|████████▊ | 4386/5000 [39:10:17<4:48:31, 28.20s/it]
 88%|████████▊ | 4387/5000 [39:10:46<4:52:03, 28.59s/it]
 88%|████████▊ | 4388/5000 [39:11:15<4:52:21, 28.66s/it]
 88%|████████▊ | 4389/5000 [39:11:43<4:48:28, 28.33s/it]
 88%|████████▊ | 4390/5000 [39:12:10<4:44:39, 28.00s/it]
 88%|████████▊ | 4391/5000 [39:12:38<4:43:17, 27.91s/it]
 88%|████████▊ | 4392/5000 [39:13:06<4:45:56, 28.22s/it]
 88%|████████▊ | 4393/5000 [39:13:36<4:49:18, 28.60s/it]
 88%|████████▊ | 4394/5000 [39:14:04<4:48:27, 28.56s/it]
 88%|████████▊ | 4395/5000 [39:14:32<4:44:58, 28.26s/it]
 88%|████████▊ | 4396/5000 [39:15:00<4:43:36, 28.17s/it]
 88%|████████▊ | 4397/5000 [39:15:27<4:40:33, 27.92s/it]
 88%|████████▊ | 4398/5000 [39:15:56<4:42:49, 28.19s/it]
 88%|████████▊ | 4399/5000 [39:16:23<4:38:03, 27.76s/it]
 88%|████████▊ | 4400/5000 [39:16:52<4:41:42, 28.17s/it]
                                                        
 88%|████████▊ | 4400/5000 [39:16:52<4:41:42, 28.17s/it]
 88%|████████▊ | 4401/5000 [39:17:19<4:38:07, 27.86s/it]
 88%|████████▊ | 4402/5000 [39:17:48<4:41:20, 28.23s/it]
 88%|████████▊ | 4403/5000 [39:18:17<4:41:57, 28.34s/it]
 88%|████████▊ | 4404/5000 [39:18:44<4:38:18, 28.02s/it]
 88%|████████▊ | 4405/5000 [39:19:12<4:38:46, 28.11s/it]
 88%|████████▊ | 4406/5000 [39:19:41<4:40:03, 28.29s/it]
 88%|████████▊ | 4407/5000 [39:20:09<4:39:44, 28.31s/it]
 88%|████████▊ | 4408/5000 [39:20:40<4:46:21, 29.02s/it]
 88%|████████▊ | 4409/5000 [39:21:08<4:43:01, 28.73s/it]
 88%|████████▊ | 4410/5000 [39:21:36<4:41:02, 28.58s/it]
 88%|████████▊ | 4411/5000 [39:22:07<4:45:57, 29.13s/it]
 88%|████████▊ | 4412/5000 [39:22:34<4:39:51, 28.56s/it]
 88%|████████▊ | 4413/5000 [39:23:03<4:41:33, 28.78s/it]
 88%|████████▊ | 4414/5000 [39:23:32<4:40:33, 28.73s/it]
 88%|████████▊ | 4415/5000 [39:24:00<4:37:31, 28.46s/it]
 88%|████████▊ | 4416/5000 [39:24:30<4:40:53, 28.86s/it]
 88%|████████▊ | 4417/5000 [39:24:57<4:35:19, 28.34s/it]
 88%|████████▊ | 4418/5000 [39:25:27<4:40:06, 28.88s/it]
 88%|████████▊ | 4419/5000 [39:25:54<4:34:38, 28.36s/it]
 88%|████████▊ | 4420/5000 [39:26:23<4:36:39, 28.62s/it]
 88%|████████▊ | 4421/5000 [39:26:52<4:36:11, 28.62s/it]
 88%|████████▊ | 4422/5000 [39:27:21<4:35:54, 28.64s/it]
 88%|████████▊ | 4423/5000 [39:27:48<4:33:11, 28.41s/it]
 88%|████████▊ | 4424/5000 [39:28:16<4:31:50, 28.32s/it]
 88%|████████▊ | 4425/5000 [39:28:44<4:30:24, 28.22s/it]
                                                        
 88%|████████▊ | 4425/5000 [39:28:44<4:30:24, 28.22s/it]
 89%|████████▊ | 4426/5000 [39:29:14<4:33:06, 28.55s/it]
 89%|████████▊ | 4427/5000 [39:29:42<4:31:18, 28.41s/it]
 89%|████████▊ | 4428/5000 [39:30:09<4:28:15, 28.14s/it]
 89%|████████▊ | 4429/5000 [39:30:38<4:28:32, 28.22s/it]
 89%|████████▊ | 4430/5000 [39:31:06<4:28:30, 28.26s/it]
 89%|████████▊ | 4431/5000 [39:31:34<4:27:11, 28.17s/it]
 89%|████████▊ | 4432/5000 [39:32:01<4:24:12, 27.91s/it]
 89%|████████▊ | 4433/5000 [39:32:31<4:27:20, 28.29s/it]
 89%|████████▊ | 4434/5000 [39:32:57<4:22:52, 27.87s/it]
 89%|████████▊ | 4435/5000 [39:33:28<4:29:41, 28.64s/it]
 89%|████████▊ | 4436/5000 [39:33:56<4:26:33, 28.36s/it]
 89%|████████▊ | 4437/5000 [39:34:23<4:23:31, 28.08s/it]
 89%|████████▉ | 4438/5000 [39:34:51<4:23:43, 28.16s/it]
 89%|████████▉ | 4439/5000 [39:35:19<4:22:42, 28.10s/it]
 89%|████████▉ | 4440/5000 [39:35:47<4:20:38, 27.93s/it]
 89%|████████▉ | 4441/5000 [39:36:15<4:21:39, 28.08s/it]
 89%|████████▉ | 4442/5000 [39:36:44<4:21:50, 28.15s/it]
 89%|████████▉ | 4443/5000 [39:37:12<4:20:46, 28.09s/it]
 89%|████████▉ | 4444/5000 [39:37:39<4:17:54, 27.83s/it]
 89%|████████▉ | 4445/5000 [39:38:07<4:18:04, 27.90s/it]
 89%|████████▉ | 4446/5000 [39:38:34<4:15:55, 27.72s/it]
 89%|████████▉ | 4447/5000 [39:39:04<4:21:37, 28.39s/it]
 89%|████████▉ | 4448/5000 [39:39:32<4:19:19, 28.19s/it]
 89%|████████▉ | 4449/5000 [39:39:59<4:16:06, 27.89s/it]
 89%|████████▉ | 4450/5000 [39:40:29<4:20:45, 28.45s/it]
                                                        
 89%|████████▉ | 4450/5000 [39:40:29<4:20:45, 28.45s/it]
 89%|████████▉ | 4451/5000 [39:40:56<4:16:29, 28.03s/it]
 89%|████████▉ | 4452/5000 [39:41:24<4:17:12, 28.16s/it]
 89%|████████▉ | 4453/5000 [39:41:52<4:16:12, 28.10s/it]
 89%|████████▉ | 4454/5000 [39:42:20<4:14:05, 27.92s/it]
 89%|████████▉ | 4455/5000 [39:42:48<4:15:01, 28.08s/it]
 89%|████████▉ | 4456/5000 [39:43:17<4:17:22, 28.39s/it]
 89%|████████▉ | 4457/5000 [39:43:46<4:18:48, 28.60s/it]
 89%|████████▉ | 4458/5000 [39:44:15<4:17:01, 28.45s/it]
 89%|████████▉ | 4459/5000 [39:44:43<4:16:20, 28.43s/it]
 89%|████████▉ | 4460/5000 [39:45:11<4:15:55, 28.44s/it]
 89%|████████▉ | 4461/5000 [39:45:40<4:15:20, 28.42s/it]
 89%|████████▉ | 4462/5000 [39:46:08<4:14:07, 28.34s/it]
 89%|████████▉ | 4463/5000 [39:46:36<4:13:54, 28.37s/it]
 89%|████████▉ | 4464/5000 [39:47:04<4:10:27, 28.04s/it]
 89%|████████▉ | 4465/5000 [39:47:32<4:11:19, 28.19s/it]
 89%|████████▉ | 4466/5000 [39:48:00<4:09:23, 28.02s/it]
 89%|████████▉ | 4467/5000 [39:48:28<4:08:48, 28.01s/it]
 89%|████████▉ | 4468/5000 [39:48:56<4:09:52, 28.18s/it]
 89%|████████▉ | 4469/5000 [39:49:23<4:05:09, 27.70s/it]
 89%|████████▉ | 4470/5000 [39:49:52<4:09:15, 28.22s/it]
 89%|████████▉ | 4471/5000 [39:50:21<4:10:49, 28.45s/it]
 89%|████████▉ | 4472/5000 [39:50:48<4:06:35, 28.02s/it]
 89%|████████▉ | 4473/5000 [39:51:18<4:10:16, 28.49s/it]
 89%|████████▉ | 4474/5000 [39:51:45<4:06:18, 28.10s/it]
 90%|████████▉ | 4475/5000 [39:52:15<4:09:40, 28.53s/it]
                                                        
 90%|████████▉ | 4475/5000 [39:52:15<4:09:40, 28.53s/it]
 90%|████████▉ | 4476/5000 [39:52:42<4:06:27, 28.22s/it]
 90%|████████▉ | 4477/5000 [39:53:12<4:09:32, 28.63s/it]
 90%|████████▉ | 4478/5000 [39:53:40<4:08:15, 28.53s/it]
 90%|████████▉ | 4479/5000 [39:54:08<4:07:16, 28.48s/it]
 90%|████████▉ | 4480/5000 [39:54:37<4:06:12, 28.41s/it]
 90%|████████▉ | 4481/5000 [39:55:06<4:08:33, 28.74s/it]
 90%|████████▉ | 4482/5000 [39:55:34<4:07:06, 28.62s/it]
 90%|████████▉ | 4483/5000 [39:56:02<4:04:18, 28.35s/it]
 90%|████████▉ | 4484/5000 [39:56:31<4:05:35, 28.56s/it]
 90%|████████▉ | 4485/5000 [39:57:00<4:05:37, 28.62s/it]
 90%|████████▉ | 4486/5000 [39:57:29<4:05:19, 28.64s/it]
 90%|████████▉ | 4487/5000 [39:57:56<4:02:16, 28.34s/it]
 90%|████████▉ | 4488/5000 [39:58:26<4:05:27, 28.76s/it]
 90%|████████▉ | 4489/5000 [39:58:53<4:00:48, 28.28s/it]
 90%|████████▉ | 4490/5000 [39:59:22<4:00:41, 28.32s/it]
 90%|████████▉ | 4491/5000 [39:59:50<4:01:23, 28.46s/it]
 90%|████████▉ | 4492/5000 [40:00:18<3:59:55, 28.34s/it]
 90%|████████▉ | 4493/5000 [40:00:46<3:57:39, 28.12s/it]
 90%|████████▉ | 4494/5000 [40:01:15<3:57:56, 28.21s/it]
 90%|████████▉ | 4495/5000 [40:01:43<3:57:58, 28.27s/it]
 90%|████████▉ | 4496/5000 [40:02:12<4:00:09, 28.59s/it]
 90%|████████▉ | 4497/5000 [40:02:41<3:59:59, 28.63s/it]
 90%|████████▉ | 4498/5000 [40:03:09<3:58:57, 28.56s/it]
 90%|████████▉ | 4499/5000 [40:03:38<3:57:22, 28.43s/it]
 90%|█████████ | 4500/5000 [40:04:06<3:56:12, 28.35s/it]
                                                        
 90%|█████████ | 4500/5000 [40:04:06<3:56:12, 28.35s/it]
 90%|█████████ | 4501/5000 [40:04:35<3:58:16, 28.65s/it]
 90%|█████████ | 4502/5000 [40:05:02<3:53:33, 28.14s/it]
 90%|█████████ | 4503/5000 [40:05:32<3:56:43, 28.58s/it]
 90%|█████████ | 4504/5000 [40:05:59<3:52:44, 28.15s/it]
 90%|█████████ | 4505/5000 [40:06:27<3:53:40, 28.32s/it]
 90%|█████████ | 4506/5000 [40:06:56<3:54:12, 28.45s/it]
 90%|█████████ | 4507/5000 [40:07:24<3:52:51, 28.34s/it]
 90%|█████████ | 4508/5000 [40:07:52<3:50:52, 28.16s/it]
 90%|█████████ | 4509/5000 [40:08:21<3:53:19, 28.51s/it]
 90%|█████████ | 4510/5000 [40:08:49<3:50:53, 28.27s/it]
 90%|█████████ | 4511/5000 [40:09:19<3:54:41, 28.80s/it]
 90%|█████████ | 4512/5000 [40:09:46<3:50:39, 28.36s/it]
 90%|█████████ | 4513/5000 [40:10:16<3:52:07, 28.60s/it]
 90%|█████████ | 4514/5000 [40:10:43<3:48:04, 28.16s/it]
 90%|█████████ | 4515/5000 [40:11:12<3:49:46, 28.43s/it]
 90%|█████████ | 4516/5000 [40:11:40<3:49:17, 28.42s/it]
 90%|█████████ | 4517/5000 [40:12:09<3:48:48, 28.42s/it]
 90%|█████████ | 4518/5000 [40:12:39<3:53:23, 29.05s/it]
 90%|█████████ | 4519/5000 [40:13:07<3:49:12, 28.59s/it]
 90%|█████████ | 4520/5000 [40:13:35<3:47:00, 28.38s/it]
 90%|█████████ | 4521/5000 [40:14:03<3:46:25, 28.36s/it]
 90%|█████████ | 4522/5000 [40:14:31<3:45:36, 28.32s/it]
 90%|█████████ | 4523/5000 [40:14:59<3:45:05, 28.31s/it]
 90%|█████████ | 4524/5000 [40:15:28<3:46:29, 28.55s/it]
 90%|█████████ | 4525/5000 [40:15:56<3:42:38, 28.12s/it]
                                                        
 90%|█████████ | 4525/5000 [40:15:56<3:42:38, 28.12s/it]
 91%|█████████ | 4526/5000 [40:16:25<3:44:30, 28.42s/it]
 91%|█████████ | 4527/5000 [40:16:52<3:41:23, 28.08s/it]
 91%|█████████ | 4528/5000 [40:17:20<3:41:05, 28.10s/it]
 91%|█████████ | 4529/5000 [40:17:48<3:40:39, 28.11s/it]
 91%|█████████ | 4530/5000 [40:18:16<3:38:59, 27.96s/it]
 91%|█████████ | 4531/5000 [40:18:43<3:37:38, 27.84s/it]
 91%|█████████ | 4532/5000 [40:19:11<3:36:59, 27.82s/it]
 91%|█████████ | 4533/5000 [40:19:40<3:39:48, 28.24s/it]
 91%|█████████ | 4534/5000 [40:20:08<3:37:09, 27.96s/it]
 91%|█████████ | 4535/5000 [40:20:37<3:38:42, 28.22s/it]
 91%|█████████ | 4536/5000 [40:21:04<3:36:57, 28.05s/it]
 91%|█████████ | 4537/5000 [40:21:32<3:36:30, 28.06s/it]
 91%|█████████ | 4538/5000 [40:22:01<3:36:41, 28.14s/it]
 91%|█████████ | 4539/5000 [40:22:29<3:37:00, 28.24s/it]
 91%|█████████ | 4540/5000 [40:22:57<3:35:34, 28.12s/it]
 91%|█████████ | 4541/5000 [40:23:26<3:36:29, 28.30s/it]
 91%|█████████ | 4542/5000 [40:23:54<3:35:42, 28.26s/it]
 91%|█████████ | 4543/5000 [40:24:22<3:35:17, 28.27s/it]
 91%|█████████ | 4544/5000 [40:24:51<3:35:07, 28.31s/it]
 91%|█████████ | 4545/5000 [40:25:19<3:34:29, 28.28s/it]
 91%|█████████ | 4546/5000 [40:25:48<3:35:27, 28.47s/it]
 91%|█████████ | 4547/5000 [40:26:15<3:31:57, 28.07s/it]
 91%|█████████ | 4548/5000 [40:26:44<3:34:10, 28.43s/it]
 91%|█████████ | 4549/5000 [40:27:11<3:29:50, 27.92s/it]
 91%|█████████ | 4550/5000 [40:27:40<3:31:12, 28.16s/it]
                                                        
 91%|█████████ | 4550/5000 [40:27:40<3:31:12, 28.16s/it]
 91%|█████████ | 4551/5000 [40:28:08<3:31:11, 28.22s/it]
 91%|█████████ | 4552/5000 [40:28:36<3:30:02, 28.13s/it]
 91%|█████████ | 4553/5000 [40:29:05<3:32:25, 28.51s/it]
 91%|█████████ | 4554/5000 [40:29:32<3:29:03, 28.12s/it]
 91%|█████████ | 4555/5000 [40:30:06<3:41:10, 29.82s/it]
 91%|█████████ | 4556/5000 [40:30:34<3:35:23, 29.11s/it]
 91%|█████████ | 4557/5000 [40:31:02<3:32:15, 28.75s/it]
 91%|█████████ | 4558/5000 [40:31:29<3:29:01, 28.37s/it]
 91%|█████████ | 4559/5000 [40:31:57<3:27:40, 28.25s/it]
 91%|█████████ | 4560/5000 [40:32:27<3:30:13, 28.67s/it]
 91%|█████████ | 4561/5000 [40:32:54<3:26:30, 28.23s/it]
 91%|█████████ | 4562/5000 [40:33:22<3:26:39, 28.31s/it]
 91%|█████████▏| 4563/5000 [40:33:51<3:27:05, 28.43s/it]
 91%|█████████▏| 4564/5000 [40:34:19<3:26:08, 28.37s/it]
 91%|█████████▏| 4565/5000 [40:34:57<3:44:59, 31.03s/it]
 91%|█████████▏| 4566/5000 [40:35:24<3:36:16, 29.90s/it]
 91%|█████████▏| 4567/5000 [40:35:52<3:31:57, 29.37s/it]
 91%|█████████▏| 4568/5000 [40:36:20<3:28:59, 29.03s/it]
 91%|█████████▏| 4569/5000 [40:36:48<3:26:29, 28.75s/it]
 91%|█████████▏| 4570/5000 [40:37:21<3:35:05, 30.01s/it]
 91%|█████████▏| 4571/5000 [40:37:48<3:28:34, 29.17s/it]
 91%|█████████▏| 4572/5000 [40:38:18<3:28:50, 29.28s/it]
 91%|█████████▏| 4573/5000 [40:38:45<3:24:14, 28.70s/it]
 91%|█████████▏| 4574/5000 [40:39:14<3:24:41, 28.83s/it]
 92%|█████████▏| 4575/5000 [40:39:44<3:25:11, 28.97s/it]
                                                        
 92%|█████████▏| 4575/5000 [40:39:44<3:25:11, 28.97s/it]
 92%|█████████▏| 4576/5000 [40:40:11<3:20:41, 28.40s/it]
 92%|█████████▏| 4577/5000 [40:40:39<3:20:44, 28.47s/it]
 92%|█████████▏| 4578/5000 [40:41:07<3:17:30, 28.08s/it]
 92%|█████████▏| 4579/5000 [40:41:40<3:28:15, 29.68s/it]
 92%|█████████▏| 4580/5000 [40:42:07<3:22:39, 28.95s/it]
 92%|█████████▏| 4581/5000 [40:42:37<3:22:44, 29.03s/it]
 92%|█████████▏| 4582/5000 [40:43:04<3:18:40, 28.52s/it]
 92%|█████████▏| 4583/5000 [40:43:33<3:20:13, 28.81s/it]
 92%|█████████▏| 4584/5000 [40:44:02<3:19:13, 28.73s/it]
 92%|█████████▏| 4585/5000 [40:44:29<3:15:26, 28.26s/it]
 92%|█████████▏| 4586/5000 [40:44:58<3:15:29, 28.33s/it]
 92%|█████████▏| 4587/5000 [40:45:25<3:14:09, 28.21s/it]
 92%|█████████▏| 4588/5000 [40:45:57<3:21:30, 29.35s/it]
 92%|█████████▏| 4589/5000 [40:46:29<3:26:34, 30.16s/it]
 92%|█████████▏| 4590/5000 [40:46:58<3:21:57, 29.56s/it]
 92%|█████████▏| 4591/5000 [40:47:30<3:26:36, 30.31s/it]
 92%|█████████▏| 4592/5000 [40:47:58<3:22:18, 29.75s/it]
 92%|█████████▏| 4593/5000 [40:48:26<3:17:40, 29.14s/it]
 92%|█████████▏| 4594/5000 [40:48:54<3:15:10, 28.84s/it]
 92%|█████████▏| 4595/5000 [40:49:27<3:22:42, 30.03s/it]
 92%|█████████▏| 4596/5000 [40:49:57<3:22:13, 30.03s/it]
 92%|█████████▏| 4597/5000 [40:50:24<3:15:53, 29.17s/it]
 92%|█████████▏| 4598/5000 [40:50:57<3:23:51, 30.43s/it]
 92%|█████████▏| 4599/5000 [40:51:25<3:16:51, 29.45s/it]
 92%|█████████▏| 4600/5000 [40:51:53<3:14:15, 29.14s/it]
                                                        
 92%|█████████▏| 4600/5000 [40:51:53<3:14:15, 29.14s/it]
 92%|█████████▏| 4601/5000 [40:52:20<3:09:55, 28.56s/it]
 92%|█████████▏| 4602/5000 [40:52:49<3:10:26, 28.71s/it]
 92%|█████████▏| 4603/5000 [40:53:17<3:08:58, 28.56s/it]
 92%|█████████▏| 4604/5000 [40:53:38<2:52:24, 26.12s/it]
 92%|█████████▏| 4605/5000 [40:53:48<2:20:56, 21.41s/it]
 92%|█████████▏| 4606/5000 [40:53:59<1:58:51, 18.10s/it]
 92%|█████████▏| 4607/5000 [40:54:09<1:43:41, 15.83s/it]{'loss': 0.0424, 'learning_rate': 1.3911111111111111e-06, 'epoch': 18.0}
+{'loss': 0.0826, 'learning_rate': 1.3355555555555558e-06, 'epoch': 18.01}
+{'loss': 0.0711, 'learning_rate': 1.28e-06, 'epoch': 18.01}
+{'loss': 0.0866, 'learning_rate': 1.2244444444444445e-06, 'epoch': 18.02}
+{'loss': 0.0783, 'learning_rate': 1.168888888888889e-06, 'epoch': 18.02}
+{'loss': 0.0822, 'learning_rate': 1.1133333333333334e-06, 'epoch': 18.03}
+{'loss': 0.0853, 'learning_rate': 1.0577777777777779e-06, 'epoch': 18.03}
+{'loss': 0.0806, 'learning_rate': 1.0022222222222223e-06, 'epoch': 18.04}
+{'loss': 0.0697, 'learning_rate': 9.466666666666667e-07, 'epoch': 18.04}
+{'loss': 0.0781, 'learning_rate': 8.911111111111112e-07, 'epoch': 18.05}
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
 92%|█████████▏| 4608/5000 [40:56:01<4:52:23, 44.75s/it]
 92%|█████████▏| 4609/5000 [40:56:31<4:21:54, 40.19s/it]
 92%|█████████▏| 4610/5000 [40:56:58<3:56:25, 36.37s/it]
 92%|█████████▏| 4611/5000 [40:57:28<3:42:30, 34.32s/it]
 92%|█████████▏| 4612/5000 [40:57:58<3:33:00, 32.94s/it]
 92%|█████████▏| 4613/5000 [40:58:27<3:24:28, 31.70s/it]
 92%|█████████▏| 4614/5000 [40:58:56<3:19:25, 31.00s/it]
 92%|█████████▏| 4615/5000 [40:59:23<3:11:44, 29.88s/it]
 92%|█████��███▏| 4616/5000 [40:59:53<3:11:23, 29.90s/it]
 92%|█████████▏| 4617/5000 [41:00:20<3:05:39, 29.08s/it]
 92%|█████████▏| 4618/5000 [41:00:50<3:07:17, 29.42s/it]
 92%|█████████▏| 4619/5000 [41:01:20<3:07:11, 29.48s/it]
 92%|█████████▏| 4620/5000 [41:01:49<3:06:26, 29.44s/it]
 92%|█████████▏| 4621/5000 [41:02:19<3:06:46, 29.57s/it]
 92%|█████████▏| 4622/5000 [41:02:47<3:01:51, 28.87s/it]
 92%|█████████▏| 4623/5000 [41:03:16<3:01:41, 28.92s/it]
 92%|█████████▏| 4624/5000 [41:03:44<3:00:13, 28.76s/it]
 92%|█████████▎| 4625/5000 [41:04:12<2:59:01, 28.65s/it]
                                                        
 92%|█████████▎| 4625/5000 [41:04:12<2:59:01, 28.65s/it]
 93%|█████████▎| 4626/5000 [41:04:40<2:57:18, 28.45s/it]
 93%|█████████▎| 4627/5000 [41:05:10<2:58:55, 28.78s/it]
 93%|█████████▎| 4628/5000 [41:05:45<3:09:19, 30.54s/it]
 93%|█████████▎| 4629/5000 [41:06:13<3:04:03, 29.77s/it]
 93%|█████████▎| 4630/5000 [41:06:42<3:02:28, 29.59s/it]
 93%|█████████▎| 4631/5000 [41:07:10<2:59:39, 29.21s/it]
 93%|█████████▎| 4632/5000 [41:07:41<3:02:55, 29.82s/it]
 93%|█████████▎| 4633/5000 [41:08:08<2:57:22, 29.00s/it]
 93%|█████████▎| 4634/5000 [41:08:38<2:58:51, 29.32s/it]
 93%|█████████▎| 4635/5000 [41:09:08<2:58:18, 29.31s/it]
 93%|█████████▎| 4636/5000 [41:09:36<2:55:39, 28.95s/it]
 93%|█████████▎| 4637/5000 [41:10:06<2:57:23, 29.32s/it]
 93%|█████████▎| 4638/5000 [41:10:34<2:54:37, 28.94s/it]
 93%|█████████▎| 4639/5000 [41:11:02<2:52:55, 28.74s/it]
 93%|█████████▎| 4640/5000 [41:11:31<2:52:05, 28.68s/it]
 93%|█████████▎| 4641/5000 [41:11:59<2:49:48, 28.38s/it]
 93%|█████████▎| 4642/5000 [41:12:29<2:52:55, 28.98s/it]
 93%|█████████▎| 4643/5000 [41:12:58<2:52:51, 29.05s/it]
 93%|█████████▎| 4644/5000 [41:13:26<2:51:04, 28.83s/it]
 93%|█████████▎| 4645/5000 [41:13:56<2:51:07, 28.92s/it]
 93%|█████████▎| 4646/5000 [41:14:24<2:49:44, 28.77s/it]
 93%|█████████▎| 4647/5000 [41:14:55<2:52:19, 29.29s/it]
 93%|█████████▎| 4648/5000 [41:15:23<2:50:18, 29.03s/it]
 93%|█████████▎| 4649/5000 [41:15:51<2:48:39, 28.83s/it]
 93%|█████████▎| 4650/5000 [41:16:21<2:49:13, 29.01s/it]
                                                        
 93%|█████████▎| 4650/5000 [41:16:21<2:49:13, 29.01s/it]
 93%|█████████▎| 4651/5000 [41:16:49<2:47:30, 28.80s/it]
 93%|█████████▎| 4652/5000 [41:17:20<2:49:58, 29.31s/it]
 93%|█████████▎| 4653/5000 [41:17:47<2:45:44, 28.66s/it]
 93%|█████████▎| 4654/5000 [41:18:17<2:48:00, 29.14s/it]
 93%|█████████▎| 4655/5000 [41:18:46<2:48:10, 29.25s/it]
 93%|█████████▎| 4656/5000 [41:19:15<2:45:54, 28.94s/it]
 93%|█████████▎| 4657/5000 [41:19:45<2:47:48, 29.35s/it]
 93%|█████████▎| 4658/5000 [41:20:12<2:43:34, 28.70s/it]
 93%|█████████▎| 4659/5000 [41:20:42<2:45:19, 29.09s/it]
 93%|█████████▎| 4660/5000 [41:21:17<2:54:09, 30.73s/it]
 93%|█████████▎| 4661/5000 [41:21:44<2:48:13, 29.77s/it]
 93%|█████████▎| 4662/5000 [41:22:15<2:49:04, 30.01s/it]
 93%|█████████▎| 4663/5000 [41:22:42<2:43:47, 29.16s/it]
 93%|█████████▎| 4664/5000 [41:23:11<2:42:58, 29.10s/it]
 93%|█████████▎| 4665/5000 [41:23:39<2:39:59, 28.65s/it]
 93%|█████████▎| 4666/5000 [41:24:07<2:38:52, 28.54s/it]
 93%|█████████▎| 4667/5000 [41:24:37<2:41:26, 29.09s/it]
 93%|█████████▎| 4668/5000 [41:25:04<2:36:40, 28.32s/it]
 93%|█████████▎| 4669/5000 [41:25:33<2:37:08, 28.48s/it]
 93%|█████████▎| 4670/5000 [41:26:01<2:36:33, 28.47s/it]
 93%|█████████▎| 4671/5000 [41:26:29<2:35:30, 28.36s/it]
 93%|█████████▎| 4672/5000 [41:26:58<2:35:57, 28.53s/it]
 93%|█████████▎| 4673/5000 [41:27:27<2:35:37, 28.55s/it]
 93%|█████████▎| 4674/5000 [41:27:56<2:36:09, 28.74s/it]
 94%|█████████▎| 4675/5000 [41:28:23<2:33:11, 28.28s/it]
                                                        
 94%|█████████▎| 4675/5000 [41:28:23<2:33:11, 28.28s/it]
 94%|█████████▎| 4676/5000 [41:28:52<2:34:34, 28.62s/it]
 94%|█████████▎| 4677/5000 [41:29:25<2:40:30, 29.82s/it]
 94%|█████████▎| 4678/5000 [41:29:54<2:37:54, 29.43s/it]
 94%|█████████▎| 4679/5000 [41:30:22<2:35:55, 29.15s/it]
 94%|█████████▎| 4680/5000 [41:30:49<2:32:03, 28.51s/it]
 94%|█████████▎| 4681/5000 [41:31:18<2:31:44, 28.54s/it]
 94%|█████████▎| 4682/5000 [41:31:45<2:29:14, 28.16s/it]
 94%|█████████▎| 4683/5000 [41:32:14<2:29:45, 28.34s/it]
 94%|█████████▎| 4684/5000 [41:32:43<2:30:07, 28.51s/it]
 94%|█████████▎| 4685/5000 [41:33:10<2:27:57, 28.18s/it]
 94%|█████████▎| 4686/5000 [41:33:42<2:32:50, 29.20s/it]
 94%|█████████▎| 4687/5000 [41:34:10<2:31:01, 28.95s/it]
 94%|█████████▍| 4688/5000 [41:34:38<2:28:42, 28.60s/it]
 94%|█████████▍| 4689/5000 [41:35:06<2:27:57, 28.55s/it]
 94%|█████████▍| 4690/5000 [41:35:35<2:27:09, 28.48s/it]
 94%|█████████▍| 4691/5000 [41:36:03<2:26:28, 28.44s/it]
 94%|█████████▍| 4692/5000 [41:36:30<2:23:55, 28.04s/it]
 94%|█████████▍| 4693/5000 [41:36:58<2:22:41, 27.89s/it]
 94%|█████████▍| 4694/5000 [41:37:25<2:22:09, 27.87s/it]
 94%|█████████▍| 4695/5000 [41:37:53<2:21:42, 27.88s/it]
 94%|█████████▍| 4696/5000 [41:38:21<2:21:30, 27.93s/it]
 94%|█████████▍| 4697/5000 [41:38:50<2:22:09, 28.15s/it]
 94%|█████████▍| 4698/5000 [41:39:19<2:22:53, 28.39s/it]
 94%|█████████▍| 4699/5000 [41:39:47<2:21:59, 28.30s/it]
 94%|█████████▍| 4700/5000 [41:40:15<2:20:32, 28.11s/it]
                                                        
 94%|█████████▍| 4700/5000 [41:40:15<2:20:32, 28.11s/it]
 94%|█████████▍| 4701/5000 [41:40:42<2:19:28, 27.99s/it]
 94%|█████████▍| 4702/5000 [41:41:12<2:20:56, 28.38s/it]
 94%|█████████▍| 4703/5000 [41:41:39<2:18:37, 28.01s/it]
 94%|█████████▍| 4704/5000 [41:42:08<2:20:05, 28.40s/it]
 94%|█████████▍| 4705/5000 [41:42:37<2:19:49, 28.44s/it]
 94%|█████████▍| 4706/5000 [41:43:05<2:18:53, 28.35s/it]
 94%|█████████▍| 4707/5000 [41:43:33<2:18:30, 28.36s/it]
 94%|█████████▍| 4708/5000 [41:44:00<2:16:14, 27.99s/it]
 94%|█████████▍| 4709/5000 [41:44:33<2:22:26, 29.37s/it]
 94%|█████████▍| 4710/5000 [41:45:00<2:18:45, 28.71s/it]
 94%|█████████▍| 4711/5000 [41:45:29<2:18:25, 28.74s/it]
 94%|█████████▍| 4712/5000 [41:45:57<2:17:32, 28.66s/it]
 94%|█████████▍| 4713/5000 [41:46:26<2:16:42, 28.58s/it]
 94%|█████████▍| 4714/5000 [41:46:54<2:16:25, 28.62s/it]
 94%|█████████▍| 4715/5000 [41:47:22<2:13:49, 28.17s/it]
 94%|█████████▍| 4716/5000 [41:47:50<2:13:49, 28.27s/it]
 94%|█████████▍| 4717/5000 [41:48:21<2:16:24, 28.92s/it]
 94%|█████████▍| 4718/5000 [41:48:48<2:14:06, 28.53s/it]
 94%|█████████▍| 4719/5000 [41:49:21<2:20:22, 29.97s/it]
 94%|█████████▍| 4720/5000 [41:49:49<2:16:11, 29.18s/it]
 94%|█████████▍| 4721/5000 [41:50:23<2:22:09, 30.57s/it]
 94%|█████████▍| 4722/5000 [41:50:55<2:23:43, 31.02s/it]
 94%|█████████▍| 4723/5000 [41:51:22<2:18:19, 29.96s/it]
 94%|█████████▍| 4724/5000 [41:51:50<2:14:44, 29.29s/it]
 94%|█████████▍| 4725/5000 [41:52:18<2:12:43, 28.96s/it]
                                                        
 94%|█████████▍| 4725/5000 [41:52:18<2:12:43, 28.96s/it]
 95%|█████████▍| 4726/5000 [41:52:48<2:13:32, 29.24s/it]
 95%|█████████▍| 4727/5000 [41:53:16<2:11:47, 28.97s/it]
 95%|█████████▍| 4728/5000 [41:53:45<2:10:35, 28.81s/it]
 95%|█████████▍| 4729/5000 [41:54:14<2:10:06, 28.81s/it]
 95%|█████████▍| 4730/5000 [41:54:41<2:08:03, 28.46s/it]
 95%|█████████▍| 4731/5000 [41:55:10<2:07:20, 28.40s/it]
 95%|█████████▍| 4732/5000 [41:55:42<2:12:41, 29.71s/it]
 95%|█████████▍| 4733/5000 [41:56:11<2:10:37, 29.35s/it]
 95%|█████████▍| 4734/5000 [41:56:39<2:08:07, 28.90s/it]
 95%|█████████▍| 4735/5000 [41:57:07<2:07:13, 28.81s/it]
 95%|█████████▍| 4736/5000 [41:57:35<2:05:59, 28.64s/it]
 95%|█████████▍| 4737/5000 [41:58:08<2:11:01, 29.89s/it]
 95%|█████████▍| 4738/5000 [41:58:35<2:07:00, 29.09s/it]
 95%|█████████▍| 4739/5000 [41:59:05<2:07:16, 29.26s/it]
 95%|█████████▍| 4740/5000 [41:59:34<2:06:07, 29.10s/it]
 95%|█████████▍| 4741/5000 [42:00:01<2:03:21, 28.58s/it]
 95%|█████████▍| 4742/5000 [42:00:32<2:05:24, 29.17s/it]
 95%|█████████▍| 4743/5000 [42:00:59<2:02:22, 28.57s/it]
 95%|█████████▍| 4744/5000 [42:01:29<2:03:33, 28.96s/it]
 95%|█████████▍| 4745/5000 [42:01:58<2:03:42, 29.11s/it]
 95%|█████████▍| 4746/5000 [42:02:25<2:00:25, 28.45s/it]
 95%|█████████▍| 4747/5000 [42:02:52<1:58:21, 28.07s/it]
 95%|█████████▍| 4748/5000 [42:03:20<1:56:43, 27.79s/it]
 95%|█████████▍| 4749/5000 [42:03:48<1:57:29, 28.08s/it]
 95%|█████████▌| 4750/5000 [42:04:15<1:55:43, 27.77s/it]
                                                        
 95%|█████████▌| 4750/5000 [42:04:15<1:55:43, 27.77s/it]
 95%|█████████▌| 4751/5000 [42:04:45<1:57:01, 28.20s/it]
 95%|█████████▌| 4752/5000 [42:05:12<1:56:07, 28.10s/it]
 95%|█████████▌| 4753/5000 [42:05:40<1:54:59, 27.93s/it]
 95%|█████████▌| 4754/5000 [42:06:08<1:54:52, 28.02s/it]
 95%|█████████▌| 4755/5000 [42:06:37<1:55:05, 28.19s/it]
 95%|█████████▌| 4756/5000 [42:07:05<1:54:34, 28.17s/it]
 95%|█████████▌| 4757/5000 [42:07:36<1:58:04, 29.16s/it]
 95%|█████████▌| 4758/5000 [42:08:05<1:56:43, 28.94s/it]
 95%|█████████▌| 4759/5000 [42:08:32<1:54:24, 28.49s/it]
 95%|█████████▌| 4760/5000 [42:09:01<1:54:21, 28.59s/it]
 95%|█████████▌| 4761/5000 [42:09:28<1:52:33, 28.26s/it]
 95%|█████████▌| 4762/5000 [42:09:57<1:52:42, 28.41s/it]
 95%|█████████▌| 4763/5000 [42:10:25<1:51:55, 28.34s/it]
 95%|█████████▌| 4764/5000 [42:10:54<1:51:18, 28.30s/it]
 95%|█████████▌| 4765/5000 [42:11:23<1:51:41, 28.52s/it]
 95%|█████████▌| 4766/5000 [42:11:50<1:49:19, 28.03s/it]
 95%|█████████▌| 4767/5000 [42:12:19<1:50:46, 28.53s/it]
 95%|█████████▌| 4768/5000 [42:12:46<1:48:35, 28.08s/it]
 95%|█████████▌| 4769/5000 [42:13:16<1:50:24, 28.68s/it]
 95%|█████████▌| 4770/5000 [42:13:45<1:49:20, 28.52s/it]
 95%|█████████▌| 4771/5000 [42:14:12<1:48:12, 28.35s/it]
 95%|█████████▌| 4772/5000 [42:14:42<1:48:31, 28.56s/it]
 95%|█████████▌| 4773/5000 [42:15:09<1:46:27, 28.14s/it]
 95%|█████████▌| 4774/5000 [42:15:42<1:51:26, 29.58s/it]
 96%|█████████▌| 4775/5000 [42:16:10<1:49:25, 29.18s/it]
                                                        
 96%|█████████▌| 4775/5000 [42:16:10<1:49:25, 29.18s/it]
 96%|█████████▌| 4776/5000 [42:16:38<1:47:18, 28.74s/it]
 96%|█████████▌| 4777/5000 [42:17:06<1:45:59, 28.52s/it]
 96%|█████████▌| 4778/5000 [42:17:33<1:44:13, 28.17s/it]
 96%|█████████▌| 4779/5000 [42:18:02<1:44:44, 28.44s/it]
 96%|█████████▌| 4780/5000 [42:18:31<1:44:28, 28.49s/it]
 96%|█████████▌| 4781/5000 [42:18:59<1:43:21, 28.32s/it]
 96%|█████████▌| 4782/5000 [42:19:26<1:41:48, 28.02s/it]
 96%|█████████▌| 4783/5000 [42:19:54<1:41:24, 28.04s/it]
 96%|█████████▌| 4784/5000 [42:20:22<1:40:59, 28.05s/it]
 96%|█████████▌| 4785/5000 [42:20:54<1:45:05, 29.33s/it]
 96%|█████████▌| 4786/5000 [42:21:23<1:43:47, 29.10s/it]
 96%|█████████▌| 4787/5000 [42:21:52<1:42:48, 28.96s/it]
 96%|█████████▌| 4788/5000 [42:22:20<1:41:29, 28.73s/it]
 96%|█████████▌| 4789/5000 [42:22:48<1:40:51, 28.68s/it]
 96%|█████████▌| 4790/5000 [42:23:17<1:40:56, 28.84s/it]
 96%|█████████▌| 4791/5000 [42:23:45<1:38:44, 28.35s/it]
 96%|█████████▌| 4792/5000 [42:24:14<1:38:50, 28.51s/it]
 96%|█████████▌| 4793/5000 [42:24:42<1:38:04, 28.43s/it]
 96%|█████████▌| 4794/5000 [42:25:13<1:40:53, 29.39s/it]
 96%|█████████▌| 4795/5000 [42:25:41<1:38:50, 28.93s/it]
 96%|█████████▌| 4796/5000 [42:26:09<1:37:14, 28.60s/it]
 96%|█████████▌| 4797/5000 [42:26:37<1:35:41, 28.28s/it]
 96%|█████████▌| 4798/5000 [42:27:04<1:34:05, 27.95s/it]
 96%|█████████▌| 4799/5000 [42:27:32<1:33:50, 28.01s/it]
 96%|█████████▌| 4800/5000 [42:27:59<1:32:36, 27.78s/it]
                                                        
 96%|█████████▌| 4800/5000 [42:27:59<1:32:36, 27.78s/it]
 96%|█████████▌| 4801/5000 [42:28:28<1:32:55, 28.02s/it]
 96%|█████████▌| 4802/5000 [42:28:57<1:33:31, 28.34s/it]
 96%|█████████▌| 4803/5000 [42:29:24<1:31:49, 27.97s/it]
 96%|█████████▌| 4804/5000 [42:29:54<1:33:00, 28.47s/it]
 96%|█████████▌| 4805/5000 [42:30:20<1:30:48, 27.94s/it]
 96%|█████████▌| 4806/5000 [42:30:48<1:29:50, 27.79s/it]
 96%|█████████▌| 4807/5000 [42:31:15<1:29:05, 27.69s/it]
 96%|█████████▌| 4808/5000 [42:31:43<1:28:54, 27.78s/it]
 96%|█████████▌| 4809/5000 [42:32:11<1:28:38, 27.84s/it]
 96%|█████████▌| 4810/5000 [42:32:38<1:27:19, 27.57s/it]
 96%|█████████▌| 4811/5000 [42:33:07<1:27:54, 27.91s/it]
 96%|█████████▌| 4812/5000 [42:33:34<1:26:45, 27.69s/it]
 96%|█████████▋| 4813/5000 [42:34:03<1:27:20, 28.03s/it]
 96%|█████████▋| 4814/5000 [42:34:31<1:27:11, 28.13s/it]
 96%|█████████▋| 4815/5000 [42:34:59<1:26:15, 27.98s/it]
 96%|█████████▋| 4816/5000 [42:35:28<1:26:48, 28.30s/it]
 96%|█████████▋| 4817/5000 [42:35:55<1:25:30, 28.03s/it]
 96%|█████████▋| 4818/5000 [42:36:29<1:29:56, 29.65s/it]
 96%|█████████▋| 4819/5000 [42:36:56<1:27:07, 28.88s/it]
 96%|█████████▋| 4820/5000 [42:37:24<1:26:24, 28.80s/it]
 96%|█████████▋| 4821/5000 [42:37:52<1:24:27, 28.31s/it]
 96%|█████████▋| 4822/5000 [42:38:21<1:24:48, 28.59s/it]
 96%|█████████▋| 4823/5000 [42:38:49<1:24:16, 28.57s/it]
 96%|█████████▋| 4824/5000 [42:39:17<1:22:49, 28.24s/it]
 96%|█████████▋| 4825/5000 [42:39:49<1:25:24, 29.28s/it]
                                                        
 96%|█████████▋| 4825/5000 [42:39:49<1:25:24, 29.28s/it]
 97%|█████████▋| 4826/5000 [42:40:16<1:23:12, 28.69s/it]
 97%|█████████▋| 4827/5000 [42:40:45<1:23:21, 28.91s/it]
 97%|█████████▋| 4828/5000 [42:41:13<1:21:46, 28.52s/it]
 97%|█████████▋| 4829/5000 [42:41:41<1:20:56, 28.40s/it]
 97%|█████████▋| 4830/5000 [42:42:10<1:20:32, 28.43s/it]
 97%|█████████▋| 4831/5000 [42:42:37<1:19:04, 28.07s/it]
 97%|█████████▋| 4832/5000 [42:43:07<1:20:35, 28.78s/it]
 97%|█████████▋| 4833/5000 [42:43:34<1:18:45, 28.30s/it]
 97%|█████████▋| 4834/5000 [42:44:03<1:18:47, 28.48s/it]
 97%|█████████▋| 4835/5000 [42:44:32<1:18:16, 28.46s/it]
 97%|█████████▋| 4836/5000 [42:45:00<1:17:37, 28.40s/it]
 97%|█████████▋| 4837/5000 [42:45:28<1:16:34, 28.19s/it]
 97%|█████████▋| 4838/5000 [42:45:55<1:15:19, 27.90s/it]
 97%|█████████▋| 4839/5000 [42:46:24<1:16:14, 28.41s/it]
 97%|█████████▋| 4840/5000 [42:46:52<1:14:45, 28.04s/it]
 97%|█████████▋| 4841/5000 [42:47:19<1:13:57, 27.91s/it]
 97%|█████████▋| 4842/5000 [42:47:52<1:17:23, 29.39s/it]
 97%|█████████▋| 4843/5000 [42:48:20<1:15:54, 29.01s/it]
 97%|█████████▋| 4844/5000 [42:48:48<1:14:19, 28.59s/it]
 97%|█████████▋| 4845/5000 [42:49:16<1:13:16, 28.36s/it]
 97%|█████████▋| 4846/5000 [42:49:44<1:12:30, 28.25s/it]
 97%|█████████▋| 4847/5000 [42:49:56<59:44, 23.43s/it]  
 97%|█████████▋| 4848/5000 [42:50:06<49:27, 19.52s/it]
 97%|█████████▋| 4849/5000 [42:50:17<42:16, 16.80s/it]
 97%|█████████▋| 4850/5000 [42:50:27<37:12, 14.89s/it]
                                                      
 97%|█████████▋| 4850/5000 [42:50:27<37:12, 14.89s/it]{'loss': 0.0437, 'learning_rate': 8.355555555555556e-07, 'epoch': 19.0}
+{'loss': 0.0221, 'learning_rate': 7.8e-07, 'epoch': 19.01}
+{'loss': 0.0193, 'learning_rate': 7.244444444444446e-07, 'epoch': 19.01}
+{'loss': 0.0189, 'learning_rate': 6.68888888888889e-07, 'epoch': 19.02}
+{'loss': 0.02, 'learning_rate': 6.133333333333333e-07, 'epoch': 19.02}
+{'loss': 0.0174, 'learning_rate': 5.577777777777779e-07, 'epoch': 19.03}
+{'loss': 0.0191, 'learning_rate': 5.022222222222222e-07, 'epoch': 19.03}
+{'loss': 0.0192, 'learning_rate': 4.466666666666667e-07, 'epoch': 19.04}
+{'loss': 0.0183, 'learning_rate': 3.9111111111111115e-07, 'epoch': 19.04}
+{'loss': 0.0184, 'learning_rate': 3.3555555555555556e-07, 'epoch': 19.05}
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
 97%|█████████▋| 4851/5000 [42:52:35<2:01:26, 48.90s/it]
 97%|█████████▋| 4852/5000 [42:53:06<1:46:47, 43.29s/it]
 97%|█████████▋| 4853/5000 [42:53:34<1:35:02, 38.79s/it]
 97%|█████████▋| 4854/5000 [42:54:04<1:27:59, 36.16s/it]
 97%|█████████▋| 4855/5000 [42:54:32<1:21:38, 33.78s/it]
 97%|█████████▋| 4856/5000 [42:55:03<1:18:58, 32.91s/it]
 97%|█████████▋| 4857/5000 [42:55:31<1:14:59, 31.47s/it]
 97%|█████████▋| 4858/5000 [42:56:00<1:12:38, 30.69s/it]
 97%|█████████▋| 4859/5000 [42:56:27<1:09:43, 29.67s/it]
 97%|█████████▋| 4860/5000 [42:56:59<1:10:49, 30.35s/it]
 97%|█████████▋| 4861/5000 [42:57:26<1:08:10, 29.43s/it]
 97%|█████████▋| 4862/5000 [42:57:58<1:09:03, 30.03s/it]
 97%|█████████▋| 4863/5000 [42:58:30<1:10:01, 30.67s/it]
 97%|█████████▋| 4864/5000 [42:58:57<1:07:12, 29.65s/it]
 97%|█████████▋| 4865/5000 [42:59:29<1:07:51, 30.16s/it]
 97%|█████████▋| 4866/5000 [42:59:56<1:05:33, 29.35s/it]
 97%|█████████▋| 4867/5000 [43:00:26<1:05:38, 29.61s/it]
 97%|█████████▋| 4868/5000 [43:00:58<1:06:18, 30.14s/it]
 97%|█████████▋| 4869/5000 [43:01:25<1:03:50, 29.24s/it]
 97%|█████████▋| 4870/5000 [43:01:54<1:03:32, 29.33s/it]
 97%|█████████▋| 4871/5000 [43:02:22<1:01:42, 28.70s/it]
 97%|█████████▋| 4872/5000 [43:02:52<1:02:13, 29.17s/it]
 97%|█████████▋| 4873/5000 [43:03:24<1:03:38, 30.07s/it]
 97%|█████████▋| 4874/5000 [43:03:54<1:03:08, 30.07s/it]
 98%|█████████▊| 4875/5000 [43:04:23<1:01:39, 29.60s/it]
                                                        
 98%|█████████▊| 4875/5000 [43:04:23<1:01:39, 29.60s/it]
 98%|█████████▊| 4876/5000 [43:04:51<1:00:37, 29.34s/it]
 98%|█████████▊| 4877/5000 [43:05:23<1:01:27, 29.98s/it]
 98%|█████████▊| 4878/5000 [43:05:51<59:43, 29.37s/it]  
 98%|█████████▊| 4879/5000 [43:06:19<58:40, 29.10s/it]
 98%|█████████▊| 4880/5000 [43:06:48<57:49, 28.91s/it]
 98%|█████████▊| 4881/5000 [43:07:17<57:36, 29.05s/it]
 98%|█████████▊| 4882/5000 [43:07:50<59:38, 30.33s/it]
 98%|█████████▊| 4883/5000 [43:08:18<57:45, 29.62s/it]
 98%|█████████▊| 4884/5000 [43:08:50<58:24, 30.21s/it]
 98%|█████████▊| 4885/5000 [43:09:26<1:01:21, 32.01s/it]
 98%|█████████▊| 4886/5000 [43:09:53<57:48, 30.42s/it]  
 98%|█████████▊| 4887/5000 [43:10:22<56:40, 30.09s/it]
 98%|█████████▊| 4888/5000 [43:10:50<55:01, 29.48s/it]
 98%|█████████▊| 4889/5000 [43:11:17<53:09, 28.73s/it]
 98%|█████████▊| 4890/5000 [43:11:47<53:04, 28.95s/it]
 98%|█████████▊| 4891/5000 [43:12:15<52:02, 28.65s/it]
 98%|█████████▊| 4892/5000 [43:12:42<50:38, 28.13s/it]
 98%|█████████▊| 4893/5000 [43:13:13<51:43, 29.01s/it]
 98%|█████████▊| 4894/5000 [43:13:40<50:14, 28.44s/it]
 98%|█████████▊| 4895/5000 [43:14:08<49:31, 28.30s/it]
 98%|█████████▊| 4896/5000 [43:14:35<48:41, 28.09s/it]
 98%|█████████▊| 4897/5000 [43:15:06<49:21, 28.75s/it]
 98%|█████████▊| 4898/5000 [43:15:34<48:32, 28.55s/it]
 98%|█████████▊| 4899/5000 [43:16:03<48:36, 28.88s/it]
 98%|█████████▊| 4900/5000 [43:16:36<50:05, 30.05s/it]
                                                      
 98%|█████████▊| 4900/5000 [43:16:36<50:05, 30.05s/it]
 98%|████��████▊| 4901/5000 [43:17:04<48:30, 29.40s/it]
 98%|█████████▊| 4902/5000 [43:17:34<48:26, 29.66s/it]
 98%|█████████▊| 4903/5000 [43:18:03<47:23, 29.32s/it]
 98%|█████████▊| 4904/5000 [43:18:33<47:22, 29.61s/it]
 98%|█████████▊| 4905/5000 [43:19:02<46:23, 29.30s/it]
 98%|█████████▊| 4906/5000 [43:19:37<48:34, 31.01s/it]
 98%|█████████▊| 4907/5000 [43:20:04<46:16, 29.85s/it]
 98%|█████████▊| 4908/5000 [43:20:35<46:16, 30.18s/it]
 98%|█████████▊| 4909/5000 [43:21:02<44:25, 29.29s/it]
 98%|█████████▊| 4910/5000 [43:21:32<44:08, 29.43s/it]
 98%|█████████▊| 4911/5000 [43:22:00<43:09, 29.10s/it]
 98%|█████████▊| 4912/5000 [43:22:29<42:40, 29.10s/it]
 98%|█████████▊| 4913/5000 [43:22:57<41:40, 28.74s/it]
 98%|█████████▊| 4914/5000 [43:23:24<40:24, 28.20s/it]
 98%|█████████▊| 4915/5000 [43:23:54<40:46, 28.78s/it]
 98%|█████████▊| 4916/5000 [43:24:22<39:52, 28.48s/it]
 98%|█████████▊| 4917/5000 [43:24:53<40:15, 29.10s/it]
 98%|█████████▊| 4918/5000 [43:25:21<39:31, 28.92s/it]
 98%|█████████▊| 4919/5000 [43:25:51<39:19, 29.13s/it]
 98%|█████████▊| 4920/5000 [43:26:19<38:34, 28.93s/it]
 98%|█████████▊| 4921/5000 [43:26:52<39:46, 30.21s/it]
 98%|█████████▊| 4922/5000 [43:27:25<40:16, 30.99s/it]
 98%|█████████▊| 4923/5000 [43:27:53<38:27, 29.97s/it]
 98%|█████████▊| 4924/5000 [43:28:22<37:46, 29.82s/it]
 98%|█████████▊| 4925/5000 [43:28:51<36:44, 29.40s/it]
                                                      
 98%|█████████▊| 4925/5000 [43:28:51<36:44, 29.40s/it]
 99%|█████████▊| 4926/5000 [43:29:18<35:31, 28.81s/it]
 99%|█████████▊| 4927/5000 [43:29:46<34:41, 28.52s/it]
 99%|█████████▊| 4928/5000 [43:30:16<34:56, 29.12s/it]
 99%|█████████▊| 4929/5000 [43:30:46<34:32, 29.20s/it]
 99%|█████████▊| 4930/5000 [43:31:13<33:14, 28.50s/it]
 99%|█████████▊| 4931/5000 [43:31:43<33:24, 29.05s/it]
 99%|█████████▊| 4932/5000 [43:32:11<32:38, 28.80s/it]
 99%|█████████▊| 4933/5000 [43:32:42<32:58, 29.52s/it]
 99%|█████████▊| 4934/5000 [43:33:10<31:44, 28.86s/it]
 99%|█████████▊| 4935/5000 [43:33:41<32:12, 29.74s/it]
 99%|█████████▊| 4936/5000 [43:34:09<30:54, 28.97s/it]
 99%|█████████▊| 4937/5000 [43:34:40<31:18, 29.82s/it]
 99%|█████████▉| 4938/5000 [43:35:11<31:10, 30.17s/it]
 99%|█████████▉| 4939/5000 [43:35:39<29:47, 29.31s/it]
 99%|█████████▉| 4940/5000 [43:36:11<30:08, 30.14s/it]
 99%|█████████▉| 4941/5000 [43:36:38<28:46, 29.27s/it]
 99%|█████████▉| 4942/5000 [43:37:10<29:01, 30.02s/it]
 99%|█████████▉| 4943/5000 [43:37:42<29:02, 30.57s/it]
 99%|█████████▉| 4944/5000 [43:38:09<27:37, 29.60s/it]
 99%|█████████▉| 4945/5000 [43:38:40<27:28, 29.98s/it]
 99%|█████████▉| 4946/5000 [43:39:07<26:17, 29.22s/it]
 99%|█████████▉| 4947/5000 [43:39:38<26:14, 29.70s/it]
 99%|█████████▉| 4948/5000 [43:40:07<25:30, 29.44s/it]
 99%|█████████▉| 4949/5000 [43:40:37<25:13, 29.67s/it]
 99%|█████████▉| 4950/5000 [43:41:06<24:26, 29.33s/it]
                                                      
 99%|█████████▉| 4950/5000 [43:41:06<24:26, 29.33s/it]
 99%|█████████▉| 4951/5000 [43:41:36<24:16, 29.73s/it]
 99%|█████████▉| 4952/5000 [43:42:04<23:17, 29.12s/it]
 99%|█████████▉| 4953/5000 [43:42:34<23:05, 29.47s/it]
 99%|█████████▉| 4954/5000 [43:43:02<22:07, 28.86s/it]
 99%|█████████▉| 4955/5000 [43:43:34<22:20, 29.79s/it]
 99%|█████████▉| 4956/5000 [43:44:02<21:26, 29.25s/it]
 99%|█████████▉| 4957/5000 [43:44:33<21:18, 29.73s/it]
 99%|█████████▉| 4958/5000 [43:45:00<20:19, 29.04s/it]
 99%|█████████▉| 4959/5000 [43:45:30<20:01, 29.29s/it]
 99%|█████████▉| 4960/5000 [43:45:59<19:23, 29.09s/it]
 99%|█████████▉| 4961/5000 [43:46:29<19:05, 29.37s/it]
 99%|█████████▉| 4962/5000 [43:46:56<18:15, 28.82s/it]
 99%|█████████▉| 4963/5000 [43:47:27<18:13, 29.55s/it]
 99%|█████████▉| 4964/5000 [43:47:55<17:18, 28.84s/it]
 99%|█████████▉| 4965/5000 [43:48:26<17:15, 29.60s/it]
 99%|█████████▉| 4966/5000 [43:48:54<16:33, 29.23s/it]
 99%|█████████▉| 4967/5000 [43:49:23<16:03, 29.20s/it]
 99%|█████████▉| 4968/5000 [43:49:51<15:18, 28.70s/it]
 99%|█████████▉| 4969/5000 [43:50:21<15:02, 29.12s/it]
 99%|█████████▉| 4970/5000 [43:50:53<14:59, 29.97s/it]
 99%|█████████▉| 4971/5000 [43:51:23<14:32, 30.09s/it]
 99%|█████████▉| 4972/5000 [43:51:56<14:25, 30.90s/it]
 99%|█████████▉| 4973/5000 [43:52:26<13:48, 30.70s/it]
 99%|█████████▉| 4974/5000 [43:52:53<12:50, 29.63s/it]
                                                      
                                                      
+[INFO|trainer.py:3142] 2023-05-12 05:47:19,195 >>   Num examples: Unknown
+[INFO|trainer.py:3143] 2023-05-12 05:47:19,195 >>   Batch size = 64
+{'loss': 0.0261, 'learning_rate': 2.8e-07, 'epoch': 20.0}
+{'loss': 0.0187, 'learning_rate': 2.2444444444444445e-07, 'epoch': 20.01}
+{'loss': 0.0238, 'learning_rate': 1.6888888888888888e-07, 'epoch': 20.02}
+{'loss': 0.0177, 'learning_rate': 1.1333333333333336e-07, 'epoch': 20.02}
+{'loss': 0.021, 'learning_rate': 5.777777777777778e-08, 'epoch': 20.02}
+{'loss': 0.0189, 'learning_rate': 2.2222222222222225e-09, 'epoch': 20.03}
+
+
+
+[INFO|trainer_utils.py:693] 2023-05-12 05:47:34,127 >> 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.
+
                                                      
+[INFO|configuration_utils.py:458] 2023-05-12 06:44:01,605 >> Configuration saved in ./checkpoint-5000/config.json
+[INFO|configuration_utils.py:364] 2023-05-12 06:44:01,609 >> Configuration saved in ./checkpoint-5000/generation_config.json
+[INFO|modeling_utils.py:1855] 2023-05-12 06:44:04,688 >> Model weights saved in ./checkpoint-5000/pytorch_model.bin
+[INFO|feature_extraction_utils.py:369] 2023-05-12 06:44:04,692 >> Feature extractor saved in ./checkpoint-5000/preprocessor_config.json
+[INFO|feature_extraction_utils.py:369] 2023-05-12 06:44:15,555 >> Feature extractor saved in ./preprocessor_config.json

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

@@ -4380,3 +4380,1083 @@ Reading metadata...: 15520it [00:00, 34879.19it/s]
 {'eval_loss': 0.22095343470573425, 'eval_wer': 8.212281066472636, 'eval_runtime': 3161.6276, 'eval_samples_per_second': 4.909, 'eval_steps_per_second': 0.077, 'epoch': 16.02}
 [INFO|modeling_utils.py:1855] 2023-05-11 21:45:15,833 >> Model weights saved in ./checkpoint-4000/pytorch_model.bin
 [INFO|feature_extraction_utils.py:369] 2023-05-11 21:45:15,837 >> Feature extractor saved in ./checkpoint-4000/preprocessor_config.json
+[INFO|feature_extraction_utils.py:369] 2023-05-11 21:45:26,357 >> Feature extractor saved in ./preprocessor_config.json
+/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 '
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 80%|████████  | 4024/5000 [36:16:27<8:09:20, 30.08s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 81%|████████  | 4050/5000 [36:29:22<7:57:29, 30.16s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 82%|████████▏ | 4075/5000 [36:41:46<7:53:07, 30.69s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 82%|████████▏ | 4100/5000 [36:54:01<7:20:09, 29.34s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 82%|████████▏ | 4122/5000 [37:03:42<3:56:29, 16.16s/it]
+
+
+
+
+
+
+Reading metadata...: 15520it [00:00, 36696.34it/s]]
+
+
+
+ 82%|████████▎ | 4125/5000 [37:06:21<8:27:37, 34.81s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 83%|████████▎ | 4149/5000 [37:17:41<6:41:18, 28.29s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 84%|████████▎ | 4175/5000 [37:30:03<6:34:17, 28.68s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 84%|████████▍ | 4200/5000 [37:41:48<6:19:51, 28.49s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 84%|████████▍ | 4224/5000 [37:53:06<6:02:22, 28.02s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 85%|████████▌ | 4250/5000 [38:05:24<5:55:21, 28.43s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 86%|████████▌ | 4275/5000 [38:17:12<5:41:43, 28.28s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 86%|████████▌ | 4300/5000 [38:29:22<5:47:26, 29.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 86%|████████▋ | 4325/5000 [38:41:09<5:15:39, 28.06s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 87%|████████▋ | 4350/5000 [38:52:57<5:10:15, 28.64s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 87%|████████▋ | 4365/5000 [38:58:54<2:39:16, 15.05s/it]
+
+
+
+
+
+Reading metadata...: 15520it [00:00, 35578.75it/s]]
+
+
+
+
+
+
+
+
+
+
+ 88%|████████▊ | 4375/5000 [39:05:06<5:03:20, 29.12s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 88%|████████▊ | 4399/5000 [39:16:23<4:38:03, 27.76s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 88%|████████▊ | 4424/5000 [39:28:16<4:31:50, 28.32s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 89%|████████▉ | 4449/5000 [39:39:59<4:16:06, 27.89s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 89%|████████▉ | 4474/5000 [39:51:45<4:06:18, 28.10s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 90%|█████████ | 4500/5000 [40:04:06<3:56:12, 28.35s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 90%|█████████ | 4524/5000 [40:15:28<3:46:29, 28.55s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 91%|█████████ | 4550/5000 [40:27:40<3:31:12, 28.16s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 91%|█████████▏| 4574/5000 [40:39:14<3:24:41, 28.83s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 92%|█████████▏| 4599/5000 [40:51:25<3:16:51, 29.45s/it]
+
+
+
+
+
+
+
+
+ 92%|█████████▏| 4607/5000 [40:54:09<1:43:41, 15.83s/it]
+
+
+
+
+
+
+Reading metadata...: 15520it [00:00, 38951.85it/s]]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 92%|█████████▏| 4624/5000 [41:03:44<3:00:13, 28.76s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 93%|█████████▎| 4649/5000 [41:15:51<2:48:39, 28.83s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 93%|█████████▎| 4674/5000 [41:27:56<2:36:09, 28.74s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 94%|█████████▍| 4699/5000 [41:39:47<2:21:59, 28.30s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 94%|█████████▍| 4724/5000 [41:51:50<2:14:44, 29.29s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 95%|█████████▍| 4749/5000 [42:03:48<1:57:29, 28.08s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 95%|█████████▌| 4774/5000 [42:15:42<1:51:26, 29.58s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 96%|█████████▌| 4799/5000 [42:27:32<1:33:50, 28.01s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 96%|█████████▋| 4824/5000 [42:39:17<1:22:49, 28.24s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 97%|█████████▋| 4849/5000 [42:50:17<42:16, 16.80s/it]
+ 97%|█████████▋| 4850/5000 [42:50:27<37:12, 14.89s/it]
+
+
+
+
+
+
+
+Reading metadata...: 15520it [00:00, 34946.75it/s]]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 97%|█████████▋| 4874/5000 [43:03:54<1:03:08, 30.07s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 98%|█████████▊| 4900/5000 [43:16:36<50:05, 30.05s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 98%|█████████▊| 4924/5000 [43:28:22<37:46, 29.82s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 99%|█████████▉| 4950/5000 [43:41:06<24:26, 29.33s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+100%|█████████▉| 4975/5000 [43:53:24<12:30, 30.03s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+100%|█████████▉| 4999/5000 [44:05:11<00:29, 29.50s/it]
+100%|██████████| 5000/5000 [44:05:38<00:00, 28.81s/it][INFO|trainer.py:3138] 2023-05-12 05:47:19,194 >> ***** Running Evaluation *****
+[INFO|trainer.py:3142] 2023-05-12 05:47:19,195 >>   Num examples: Unknown
+[INFO|trainer.py:3143] 2023-05-12 05:47:19,195 >>   Batch size = 64
+Reading metadata...: 1it [00:01,  1.78s/it]
+[INFO|trainer_utils.py:693] 2023-05-12 05:47:34,127 >> 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.
+[INFO|configuration_utils.py:458] 2023-05-12 06:44:01,605 >> Configuration saved in ./checkpoint-5000/config.jsonorresponding 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.
+[INFO|configuration_utils.py:458] 2023-05-12 06:44:01,605 >> Configuration saved in ./checkpoint-5000/config.jsonorresponding 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.
+[INFO|modeling_utils.py:1855] 2023-05-12 06:44:04,688 >> Model weights saved in ./checkpoint-5000/pytorch_model.binresponding 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.
+[INFO|feature_extraction_utils.py:369] 2023-05-12 06:44:15,555 >> Feature extractor saved in ./preprocessor_config.jsononding 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.

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

@@ -1 +1 @@
-{"eval/loss": 0.22095343470573425, "eval/wer": 8.212281066472636, "eval/runtime": 3161.6276, "eval/samples_per_second": 4.909, "eval/steps_per_second": 0.077, "_timestamp": 1683830712.87446, "_runtime": 129820.17990994453, "_step": 163}
+{"eval/loss": 0.25196951627731323, "eval/wer": 8.44550699028117, "eval/runtime": 3402.3954, "eval/samples_per_second": 4.561, "eval/steps_per_second": 0.071, "_timestamp": 1683863041.5903704, "_runtime": 162148.89582037926, "_step": 204}

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c468e9b711e38b3400f6ef0efe4b2d44110679aa553d9d74488445634973d2a
-size 12027825
+oid sha256:3f08aa83a82456665be01ab2653f2de187bb975aed5d59b77492442519c41c69
+size 15040842