diff --git "a/run-2024-07-15T17:00:53+00:00.log" "b/run-2024-07-15T17:00:53+00:00.log"
--- "a/run-2024-07-15T17:00:53+00:00.log"
+++ "b/run-2024-07-15T17:00:53+00:00.log"
@@ -1210,4 +1210,1168 @@ Non-default generation parameters: {'max_length': 200, 'early_stopping': True, '
 
 44%|████▍     | 162600/371472 [1:57:52<18:45:45,  3.09it/s]
 44%|████▍     | 162601/371472 [1:57:53<19:20:06,  3.00it/s]
 44%|████▍     | 162602/371472 [1:57:53<18:08:06,  3.20it/s]
 44%|████▍     | 162603/371472 [1:57:53<17:24:19,  3.33it/s]
 44%|████▍     | 162604/371472 [1:57:53<17:07:34,  3.39it/s]
 44%|████▍     | 162605/371472 [1:57:54<17:03:03,  3.40it/s]
 44%|████▍     | 162606/371472 [1:57:54<16:56:38,  3.42it/s]
 44%|████▍     | 162607/371472 [1:57:54<18:15:01,  3.18it/s]
 44%|████▍     | 162608/371472 [1:57:55<18:34:43,  3.12it/s]
 44%|████▍     | 162609/371472 [1:57:55<18:44:45,  3.09it/s]
 44%|████▍     | 162610/371472 [1:57:55<18:23:13,  3.16it/s]
 44%|████▍     | 162611/371472 [1:57:56<18:00:16,  3.22it/s]
 44%|████▍     | 162612/371472 [1:57:56<17:41:15,  3.28it/s]
 44%|████▍     | 162613/371472 [1:57:56<17:56:20,  3.23it/s]
 44%|████▍     | 162614/371472 [1:57:57<18:07:59,  3.20it/s]
 44%|████▍     | 162615/371472 [1:57:57<17:49:05,  3.26it/s]
 44%|████▍     | 162616/371472 [1:57:57<19:26:07,  2.99it/s]
 44%|████▍     | 162617/371472 [1:57:58<19:55:23,  2.91it/s]
 44%|████▍     | 162618/371472 [1:57:58<19:06:19,  3.04it/s]
 44%|████▍     | 162619/371472 [1:57:58<18:38:39,  3.11it/s]
 44%|████▍     | 162620/371472 [1:57:59<17:45:00,  3.27it/s]
                                                            
{'loss': 3.0512, 'learning_rate': 6.062778771359002e-07, 'epoch': 7.0}
 
 44%|████▍     | 162620/371472 [1:57:59<17:45:00,  3.27it/s]
 44%|████▍     | 162621/371472 [1:57:59<18:47:58,  3.09it/s]
 44%|████▍     | 162622/371472 [1:57:59<18:48:27,  3.08it/s]
 44%|████▍     | 162623/371472 [1:58:00<18:43:23,  3.10it/s]
 44%|████▍     | 162624/371472 [1:58:00<18:14:48,  3.18it/s]
 44%|████▍     | 162625/371472 [1:58:00<18:12:59,  3.18it/s]
 44%|████▍     | 162626/371472 [1:58:01<19:19:54,  3.00it/s]
 44%|████▍     | 162627/371472 [1:58:01<19:32:01,  2.97it/s]
 44%|████▍     | 162628/371472 [1:58:01<18:28:47,  3.14it/s]
 44%|████▍     | 162629/371472 [1:58:02<18:48:22,  3.08it/s]
 44%|████▍     | 162630/371472 [1:58:02<18:19:37,  3.17it/s]
 44%|████▍     | 162631/371472 [1:58:02<19:08:05,  3.03it/s]
 44%|████▍     | 162632/371472 [1:58:03<19:22:54,  2.99it/s]
 44%|████▍     | 162633/371472 [1:58:03<20:10:48,  2.87it/s]
 44%|████▍     | 162634/371472 [1:58:03<19:58:31,  2.90it/s]
 44%|████▍     | 162635/371472 [1:58:04<20:47:42,  2.79it/s]
 44%|████▍     | 162636/371472 [1:58:04<20:16:51,  2.86it/s]
 44%|████▍     | 162637/371472 [1:58:04<19:26:14,  2.98it/s]
 44%|████▍     | 162638/371472 [1:58:05<19:04:18,  3.04it/s]
 44%|████▍     | 162639/371472 [1:58:05<18:47:09,  3.09it/s]
 44%|████▍     | 162640/371472 [1:58:05<18:21:51,  3.16it/s]
                                                            
{'loss': 2.9536, 'learning_rate': 6.062293951604214e-07, 'epoch': 7.01}
 
 44%|████▍     | 162640/371472 [1:58:05<18:21:51,  3.16it/s]
 44%|████▍     | 162641/371472 [1:58:05<17:53:33,  3.24it/s]
 44%|████▍     | 162642/371472 [1:58:06<17:32:54,  3.31it/s]
 44%|████▍     | 162643/371472 [1:58:06<17:19:34,  3.35it/s]
 44%|████▍     | 162644/371472 [1:58:06<18:05:34,  3.21it/s]
 44%|████▍     | 162645/371472 [1:58:07<17:52:29,  3.25it/s]
 44%|████▍     | 162646/371472 [1:58:07<17:37:08,  3.29it/s]
 44%|████▍     | 162647/371472 [1:58:07<17:40:02,  3.28it/s]
 44%|████▍     | 162648/371472 [1:58:08<17:37:19,  3.29it/s]
 44%|████▍     | 162649/371472 [1:58:08<17:23:29,  3.34it/s]
 44%|████▍     | 162650/371472 [1:58:08<17:58:32,  3.23it/s]
 44%|████▍     | 162651/371472 [1:58:09<18:37:55,  3.11it/s]
 44%|████▍     | 162652/371472 [1:58:09<18:14:18,  3.18it/s]
 44%|████▍     | 162653/371472 [1:58:09<18:43:48,  3.10it/s]
 44%|████▍     | 162654/371472 [1:58:10<18:52:43,  3.07it/s]
 44%|████▍     | 162655/371472 [1:58:10<18:25:22,  3.15it/s]
 44%|████▍     | 162656/371472 [1:58:10<18:40:29,  3.11it/s]
 44%|████▍     | 162657/371472 [1:58:10<18:42:13,  3.10it/s]
 44%|████▍     | 162658/371472 [1:58:11<18:29:00,  3.14it/s]
 44%|████▍     | 162659/371472 [1:58:11<19:00:02,  3.05it/s]
 44%|████▍     | 162660/371472 [1:58:11<18:26:29,  3.15it/s]
                                                            
{'loss': 3.1112, 'learning_rate': 6.061809131849426e-07, 'epoch': 7.01}
-
 44%|████▍     | 162660/371472 [1:58:11<18:26:29,  3.15it/s]
 44%|████▍     | 162661/371472 [1:58:12<18:17:26,  3.17it/s]
 44%|████▍     | 162662/371472 [1:58:12<18:49:07,  3.08it/s]
 44%|████▍     | 162663/371472 [1:58:12<19:07:49,  3.03it/s]
 44%|████▍     | 162664/371472 [1:58:13<18:10:33,  3.19it/s]
\ No newline at end of file
+
 44%|████▍     | 162660/371472 [1:58:11<18:26:29,  3.15it/s]
 44%|████▍     | 162661/371472 [1:58:12<18:17:26,  3.17it/s]
 44%|████▍     | 162662/371472 [1:58:12<18:49:07,  3.08it/s]
 44%|████▍     | 162663/371472 [1:58:12<19:07:49,  3.03it/s]
 44%|████▍     | 162664/371472 [1:58:13<18:10:33,  3.19it/s]
 44%|████▍     | 162665/371472 [1:58:13<20:37:39,  2.81it/s]
 44%|████▍     | 162666/371472 [1:58:13<19:30:38,  2.97it/s]
 44%|████▍     | 162667/371472 [1:58:14<18:24:29,  3.15it/s]
 44%|████▍     | 162668/371472 [1:58:14<18:40:54,  3.10it/s]
 44%|████▍     | 162669/371472 [1:58:14<17:49:57,  3.25it/s]
 44%|████▍     | 162670/371472 [1:58:15<17:47:35,  3.26it/s]
 44%|████▍     | 162671/371472 [1:58:15<17:41:14,  3.28it/s]
 44%|████▍     | 162672/371472 [1:58:15<17:26:26,  3.33it/s]
 44%|████▍     | 162673/371472 [1:58:16<17:08:27,  3.38it/s]
 44%|████▍     | 162674/371472 [1:58:16<18:31:56,  3.13it/s]
 44%|████▍     | 162675/371472 [1:58:16<18:26:39,  3.14it/s]
 44%|████▍     | 162676/371472 [1:58:17<18:40:43,  3.11it/s]
 44%|████▍     | 162677/371472 [1:58:17<18:00:45,  3.22it/s]
 44%|████▍     | 162678/371472 [1:58:17<17:39:21,  3.28it/s]
 44%|████▍     | 162679/371472 [1:58:17<17:28:44,  3.32it/s]
 44%|████▍     | 162680/371472 [1:58:18<16:50:12,  3.44it/s]
                                                            
{'loss': 3.034, 'learning_rate': 6.061324312094636e-07, 'epoch': 7.01}
+
 44%|████▍     | 162680/371472 [1:58:18<16:50:12,  3.44it/s]
 44%|████▍     | 162681/371472 [1:58:18<16:50:14,  3.44it/s]
 44%|████▍     | 162682/371472 [1:58:18<19:50:14,  2.92it/s]
 44%|████▍     | 162683/371472 [1:58:19<19:18:44,  3.00it/s]
 44%|████▍     | 162684/371472 [1:58:19<19:10:49,  3.02it/s]
 44%|████▍     | 162685/371472 [1:58:19<19:37:24,  2.96it/s]
 44%|████▍     | 162686/371472 [1:58:20<19:31:00,  2.97it/s]
 44%|████▍     | 162687/371472 [1:58:20<18:35:39,  3.12it/s]
 44%|████▍     | 162688/371472 [1:58:20<18:10:12,  3.19it/s]
 44%|████▍     | 162689/371472 [1:58:21<18:07:37,  3.20it/s]
 44%|████▍     | 162690/371472 [1:58:21<18:01:17,  3.22it/s]
 44%|████▍     | 162691/371472 [1:58:21<19:38:20,  2.95it/s]
 44%|████▍     | 162692/371472 [1:58:22<18:57:24,  3.06it/s]
 44%|████▍     | 162693/371472 [1:58:22<18:21:17,  3.16it/s]
 44%|████▍     | 162694/371472 [1:58:22<17:53:29,  3.24it/s]
 44%|████▍     | 162695/371472 [1:58:23<18:40:44,  3.10it/s]
 44%|████▍     | 162696/371472 [1:58:23<18:10:04,  3.19it/s]
 44%|████▍     | 162697/371472 [1:58:23<18:01:13,  3.22it/s]
 44%|████▍     | 162698/371472 [1:58:23<17:26:39,  3.32it/s]
 44%|████▍     | 162699/371472 [1:58:24<16:58:26,  3.42it/s]
 44%|████▍     | 162700/371472 [1:58:24<17:23:13,  3.34it/s]
                                                            
{'loss': 2.8783, 'learning_rate': 6.060839492339847e-07, 'epoch': 7.01}
+
 44%|████▍     | 162700/371472 [1:58:24<17:23:13,  3.34it/s]
 44%|████▍     | 162701/371472 [1:58:24<17:01:51,  3.41it/s]
 44%|████▍     | 162702/371472 [1:58:25<16:55:52,  3.43it/s]
 44%|████▍     | 162703/371472 [1:58:25<16:39:42,  3.48it/s]
 44%|████▍     | 162704/371472 [1:58:25<17:30:39,  3.31it/s]
 44%|████▍     | 162705/371472 [1:58:26<17:17:46,  3.35it/s]
 44%|████▍     | 162706/371472 [1:58:26<16:56:59,  3.42it/s]
 44%|████▍     | 162707/371472 [1:58:26<17:35:16,  3.30it/s]
 44%|████▍     | 162708/371472 [1:58:26<17:11:49,  3.37it/s]
 44%|████▍     | 162709/371472 [1:58:27<16:40:38,  3.48it/s]
 44%|████▍     | 162710/371472 [1:58:27<16:31:28,  3.51it/s]
 44%|████▍     | 162711/371472 [1:58:27<17:42:19,  3.28it/s]
 44%|████▍     | 162712/371472 [1:58:28<18:20:28,  3.16it/s]
 44%|████▍     | 162713/371472 [1:58:28<17:22:04,  3.34it/s]
 44%|████▍     | 162714/371472 [1:58:28<17:20:04,  3.35it/s]
 44%|████▍     | 162715/371472 [1:58:29<18:01:45,  3.22it/s]
 44%|████▍     | 162716/371472 [1:58:29<17:50:38,  3.25it/s]
 44%|████▍     | 162717/371472 [1:58:29<19:31:20,  2.97it/s]
 44%|████▍     | 162718/371472 [1:58:30<18:37:11,  3.11it/s]
 44%|████▍     | 162719/371472 [1:58:30<18:05:10,  3.21it/s]
 44%|████▍     | 162720/371472 [1:58:30<19:14:20,  3.01it/s]
                                                            
{'loss': 2.9961, 'learning_rate': 6.060354672585059e-07, 'epoch': 7.01}
+
 44%|████▍     | 162720/371472 [1:58:30<19:14:20,  3.01it/s]
 44%|████▍     | 162721/371472 [1:58:31<18:36:13,  3.12it/s]
 44%|████▍     | 162722/371472 [1:58:31<18:26:07,  3.15it/s]
 44%|████▍     | 162723/371472 [1:58:31<17:39:55,  3.28it/s]
 44%|████▍     | 162724/371472 [1:58:31<17:44:16,  3.27it/s]
 44%|████▍     | 162725/371472 [1:58:32<17:39:19,  3.28it/s]
 44%|████▍     | 162726/371472 [1:58:32<17:40:16,  3.28it/s]
 44%|████▍     | 162727/371472 [1:58:33<20:58:24,  2.76it/s]
 44%|████▍     | 162728/371472 [1:58:33<19:54:41,  2.91it/s]
 44%|████▍     | 162729/371472 [1:58:33<19:16:08,  3.01it/s]
 44%|████▍     | 162730/371472 [1:58:33<18:42:51,  3.10it/s]
 44%|████▍     | 162731/371472 [1:58:34<18:36:49,  3.12it/s]
 44%|████▍     | 162732/371472 [1:58:34<18:14:56,  3.18it/s]
 44%|████▍     | 162733/371472 [1:58:34<18:52:30,  3.07it/s]
 44%|████▍     | 162734/371472 [1:58:35<19:38:21,  2.95it/s]
 44%|████▍     | 162735/371472 [1:58:35<19:26:11,  2.98it/s]
 44%|████▍     | 162736/371472 [1:58:35<20:02:14,  2.89it/s]
 44%|████▍     | 162737/371472 [1:58:36<20:23:13,  2.84it/s]
 44%|████▍     | 162738/371472 [1:58:36<19:35:42,  2.96it/s]
 44%|████▍     | 162739/371472 [1:58:36<18:47:16,  3.09it/s]
 44%|████▍     | 162740/371472 [1:58:37<18:44:19,  3.09it/s]
                                                            
{'loss': 2.9377, 'learning_rate': 6.05986985283027e-07, 'epoch': 7.01}
+
 44%|████▍     | 162740/371472 [1:58:37<18:44:19,  3.09it/s]
 44%|████▍     | 162741/371472 [1:58:37<18:13:57,  3.18it/s]
 44%|████▍     | 162742/371472 [1:58:37<18:30:54,  3.13it/s]
 44%|████▍     | 162743/371472 [1:58:38<18:36:10,  3.12it/s]
 44%|████▍     | 162744/371472 [1:58:38<18:35:40,  3.12it/s]
 44%|████▍     | 162745/371472 [1:58:38<19:00:43,  3.05it/s]
 44%|████▍     | 162746/371472 [1:58:39<18:04:19,  3.21it/s]
 44%|████▍     | 162747/371472 [1:58:39<17:25:36,  3.33it/s]
 44%|████▍     | 162748/371472 [1:58:39<17:04:41,  3.39it/s]
 44%|████▍     | 162749/371472 [1:58:39<16:43:15,  3.47it/s]
 44%|████▍     | 162750/371472 [1:58:40<17:17:04,  3.35it/s]
 44%|████▍     | 162751/371472 [1:58:40<17:20:57,  3.34it/s]
 44%|████▍     | 162752/371472 [1:58:40<17:25:54,  3.33it/s]
 44%|████▍     | 162753/371472 [1:58:41<17:01:37,  3.41it/s]
 44%|████▍     | 162754/371472 [1:58:41<17:22:38,  3.34it/s]
 44%|████▍     | 162755/371472 [1:58:41<18:27:20,  3.14it/s]
 44%|████▍     | 162756/371472 [1:58:42<18:21:52,  3.16it/s]
 44%|████▍     | 162757/371472 [1:58:42<17:44:59,  3.27it/s]
 44%|████▍     | 162758/371472 [1:58:42<18:06:18,  3.20it/s]
 44%|████▍     | 162759/371472 [1:58:43<18:33:33,  3.12it/s]
 44%|████▍     | 162760/371472 [1:58:43<17:51:58,  3.24it/s]
                                                            
{'loss': 2.9542, 'learning_rate': 6.05938503307548e-07, 'epoch': 7.01}
+
 44%|████▍     | 162760/371472 [1:58:43<17:51:58,  3.24it/s]
 44%|████▍     | 162761/371472 [1:58:43<18:38:19,  3.11it/s]
 44%|████▍     | 162762/371472 [1:58:43<17:55:28,  3.23it/s]
 44%|████▍     | 162763/371472 [1:58:44<18:19:16,  3.16it/s]
 44%|████▍     | 162764/371472 [1:58:44<18:20:31,  3.16it/s]
 44%|████▍     | 162765/371472 [1:58:44<17:39:53,  3.28it/s]
 44%|████▍     | 162766/371472 [1:58:45<18:31:06,  3.13it/s]
 44%|████▍     | 162767/371472 [1:58:45<18:18:30,  3.17it/s]
 44%|████▍     | 162768/371472 [1:58:45<18:48:26,  3.08it/s]
 44%|████▍     | 162769/371472 [1:58:46<18:40:42,  3.10it/s]
 44%|████▍     | 162770/371472 [1:58:46<18:47:23,  3.09it/s]
 44%|████▍     | 162771/371472 [1:58:46<18:46:34,  3.09it/s]
 44%|████▍     | 162772/371472 [1:58:47<18:31:03,  3.13it/s]
 44%|████▍     | 162773/371472 [1:58:47<19:02:00,  3.05it/s]
 44%|████▍     | 162774/371472 [1:58:47<19:17:33,  3.00it/s]
 44%|████▍     | 162775/371472 [1:58:48<20:02:40,  2.89it/s]
 44%|████▍     | 162776/371472 [1:58:48<19:20:16,  3.00it/s]
 44%|████▍     | 162777/371472 [1:58:48<18:41:51,  3.10it/s]
 44%|████▍     | 162778/371472 [1:58:49<17:55:09,  3.24it/s]
 44%|████▍     | 162779/371472 [1:58:49<19:13:47,  3.01it/s]
 44%|████▍     | 162780/371472 [1:58:49<19:05:44,  3.04it/s]
                                                            
{'loss': 3.0192, 'learning_rate': 6.058900213320691e-07, 'epoch': 7.01}
+
 44%|████▍     | 162780/371472 [1:58:49<19:05:44,  3.04it/s]
 44%|████▍     | 162781/371472 [1:58:50<18:30:59,  3.13it/s]
 44%|████▍     | 162782/371472 [1:58:50<17:55:52,  3.23it/s]
 44%|████▍     | 162783/371472 [1:58:50<17:52:07,  3.24it/s]
 44%|████▍     | 162784/371472 [1:58:51<17:39:44,  3.28it/s]
 44%|████▍     | 162785/371472 [1:58:51<17:03:40,  3.40it/s]
 44%|████▍     | 162786/371472 [1:58:51<17:21:30,  3.34it/s]
 44%|████▍     | 162787/371472 [1:58:51<17:15:29,  3.36it/s]
 44%|████▍     | 162788/371472 [1:58:52<16:58:49,  3.41it/s]
 44%|████▍     | 162789/371472 [1:58:52<18:42:05,  3.10it/s]
 44%|████▍     | 162790/371472 [1:58:52<19:07:16,  3.03it/s]
 44%|████▍     | 162791/371472 [1:58:53<19:55:16,  2.91it/s]
 44%|████▍     | 162792/371472 [1:58:53<19:18:41,  3.00it/s]
 44%|████▍     | 162793/371472 [1:58:53<19:32:48,  2.97it/s]
 44%|████▍     | 162794/371472 [1:58:54<19:45:05,  2.93it/s]
 44%|████▍     | 162795/371472 [1:58:54<19:15:05,  3.01it/s]
 44%|████▍     | 162796/371472 [1:58:54<19:18:20,  3.00it/s]
 44%|████▍     | 162797/371472 [1:58:55<18:59:42,  3.05it/s]
 44%|████▍     | 162798/371472 [1:58:55<19:17:07,  3.01it/s]
 44%|████▍     | 162799/371472 [1:58:55<19:04:56,  3.04it/s]
 44%|████▍     | 162800/371472 [1:58:56<20:05:54,  2.88it/s]
                                                            
{'loss': 2.9397, 'learning_rate': 6.058415393565903e-07, 'epoch': 7.01}
+
 44%|████▍     | 162800/371472 [1:58:56<20:05:54,  2.88it/s]
 44%|████▍     | 162801/371472 [1:58:56<20:20:12,  2.85it/s]
 44%|████▍     | 162802/371472 [1:58:57<19:42:19,  2.94it/s]
 44%|████▍     | 162803/371472 [1:58:57<19:24:48,  2.99it/s]
 44%|████▍     | 162804/371472 [1:58:57<19:02:52,  3.04it/s]
 44%|████▍     | 162805/371472 [1:58:57<19:11:28,  3.02it/s]
 44%|████▍     | 162806/371472 [1:58:58<19:46:43,  2.93it/s]
 44%|████▍     | 162807/371472 [1:58:58<19:21:08,  3.00it/s]
 44%|████▍     | 162808/371472 [1:58:58<18:38:24,  3.11it/s]
 44%|████▍     | 162809/371472 [1:58:59<18:41:30,  3.10it/s]
 44%|████▍     | 162810/371472 [1:58:59<18:24:22,  3.15it/s]
 44%|████▍     | 162811/371472 [1:58:59<18:17:13,  3.17it/s]
 44%|████▍     | 162812/371472 [1:59:00<18:20:20,  3.16it/s]
 44%|████▍     | 162813/371472 [1:59:00<18:07:47,  3.20it/s]
 44%|████▍     | 162814/371472 [1:59:00<18:15:56,  3.17it/s]
 44%|████▍     | 162815/371472 [1:59:01<17:32:26,  3.30it/s]
 44%|████▍     | 162816/371472 [1:59:01<17:19:09,  3.35it/s]
 44%|████▍     | 162817/371472 [1:59:01<17:28:12,  3.32it/s]
 44%|████▍     | 162818/371472 [1:59:02<17:28:10,  3.32it/s]
 44%|████▍     | 162819/371472 [1:59:02<18:44:26,  3.09it/s]
 44%|████▍     | 162820/371472 [1:59:02<18:23:23,  3.15it/s]
                                                            
{'loss': 3.0397, 'learning_rate': 6.057930573811115e-07, 'epoch': 7.01}
+
 44%|████▍     | 162820/371472 [1:59:02<18:23:23,  3.15it/s]
 44%|████▍     | 162821/371472 [1:59:03<20:10:34,  2.87it/s]
 44%|████▍     | 162822/371472 [1:59:03<21:11:19,  2.74it/s]
 44%|████▍     | 162823/371472 [1:59:03<21:14:06,  2.73it/s]
 44%|████▍     | 162824/371472 [1:59:04<20:16:44,  2.86it/s]
 44%|████▍     | 162825/371472 [1:59:04<20:30:25,  2.83it/s]
 44%|████▍     | 162826/371472 [1:59:04<20:43:31,  2.80it/s]
 44%|████▍     | 162827/371472 [1:59:05<20:46:15,  2.79it/s]
 44%|████▍     | 162828/371472 [1:59:05<19:45:37,  2.93it/s]
 44%|████▍     | 162829/371472 [1:59:05<19:37:55,  2.95it/s]
 44%|████▍     | 162830/371472 [1:59:06<19:07:39,  3.03it/s]
 44%|████▍     | 162831/371472 [1:59:06<18:23:23,  3.15it/s]
 44%|████▍     | 162832/371472 [1:59:06<17:46:05,  3.26it/s]
 44%|████▍     | 162833/371472 [1:59:07<17:21:45,  3.34it/s]
 44%|████▍     | 162834/371472 [1:59:07<17:50:59,  3.25it/s]
 44%|████▍     | 162835/371472 [1:59:07<18:30:23,  3.13it/s]
 44%|████▍     | 162836/371472 [1:59:08<19:33:09,  2.96it/s]
 44%|████▍     | 162837/371472 [1:59:08<19:36:12,  2.96it/s]
 44%|████▍     | 162838/371472 [1:59:08<18:49:23,  3.08it/s]
 44%|████▍     | 162839/371472 [1:59:09<18:53:39,  3.07it/s]
 44%|████▍     | 162840/371472 [1:59:09<20:02:16,  2.89it/s]
                                                            
{'loss': 2.8082, 'learning_rate': 6.057445754056325e-07, 'epoch': 7.01}
+
 44%|████▍     | 162840/371472 [1:59:09<20:02:16,  2.89it/s]
 44%|████▍     | 162841/371472 [1:59:09<19:46:38,  2.93it/s]
 44%|████▍     | 162842/371472 [1:59:10<19:06:53,  3.03it/s]
 44%|████▍     | 162843/371472 [1:59:10<20:21:37,  2.85it/s]
 44%|████▍     | 162844/371472 [1:59:10<19:46:28,  2.93it/s]
 44%|████▍     | 162845/371472 [1:59:11<18:32:02,  3.13it/s]
 44%|████▍     | 162846/371472 [1:59:11<18:03:28,  3.21it/s]
 44%|████▍     | 162847/371472 [1:59:11<18:50:42,  3.08it/s]
 44%|████▍     | 162848/371472 [1:59:12<18:10:06,  3.19it/s]
 44%|████▍     | 162849/371472 [1:59:12<17:25:17,  3.33it/s]
 44%|████▍     | 162850/371472 [1:59:12<18:03:01,  3.21it/s]
 44%|████▍     | 162851/371472 [1:59:12<17:39:29,  3.28it/s]
 44%|████▍     | 162852/371472 [1:59:13<18:19:08,  3.16it/s]
 44%|████▍     | 162853/371472 [1:59:13<18:00:25,  3.22it/s]
 44%|████▍     | 162854/371472 [1:59:13<19:09:39,  3.02it/s]
 44%|████▍     | 162855/371472 [1:59:14<21:48:34,  2.66it/s]
 44%|████▍     | 162856/371472 [1:59:14<21:11:54,  2.73it/s]
 44%|████▍     | 162857/371472 [1:59:15<20:12:19,  2.87it/s]
 44%|████▍     | 162858/371472 [1:59:15<20:39:39,  2.80it/s]
 44%|████▍     | 162859/371472 [1:59:15<19:34:22,  2.96it/s]
 44%|████▍     | 162860/371472 [1:59:16<19:27:04,  2.98it/s]
                                                            
{'loss': 2.9747, 'learning_rate': 6.056960934301536e-07, 'epoch': 7.01}
+
 44%|████▍     | 162860/371472 [1:59:16<19:27:04,  2.98it/s]
 44%|████▍     | 162861/371472 [1:59:16<18:49:44,  3.08it/s]
 44%|████▍     | 162862/371472 [1:59:16<18:10:47,  3.19it/s]
 44%|████▍     | 162863/371472 [1:59:17<18:13:38,  3.18it/s]
 44%|████▍     | 162864/371472 [1:59:17<17:57:26,  3.23it/s]
 44%|████▍     | 162865/371472 [1:59:17<19:32:03,  2.97it/s]
 44%|████▍     | 162866/371472 [1:59:18<19:38:38,  2.95it/s]
 44%|████▍     | 162867/371472 [1:59:18<20:13:18,  2.87it/s]
 44%|████▍     | 162868/371472 [1:59:18<19:43:58,  2.94it/s]
 44%|████▍     | 162869/371472 [1:59:19<18:51:48,  3.07it/s]
 44%|████▍     | 162870/371472 [1:59:19<18:30:53,  3.13it/s]
 44%|████▍     | 162871/371472 [1:59:19<17:58:31,  3.22it/s]
 44%|████▍     | 162872/371472 [1:59:19<18:27:09,  3.14it/s]
 44%|████▍     | 162873/371472 [1:59:20<18:17:02,  3.17it/s]
 44%|████▍     | 162874/371472 [1:59:20<17:38:56,  3.28it/s]
 44%|████▍     | 162875/371472 [1:59:20<17:53:13,  3.24it/s]
 44%|████▍     | 162876/371472 [1:59:21<17:45:56,  3.26it/s]
 44%|████▍     | 162877/371472 [1:59:21<17:32:57,  3.30it/s]
 44%|████▍     | 162878/371472 [1:59:21<17:55:27,  3.23it/s]
 44%|████▍     | 162879/371472 [1:59:22<17:52:23,  3.24it/s]
 44%|████▍     | 162880/371472 [1:59:22<18:20:55,  3.16it/s]
                                                            
{'loss': 2.8268, 'learning_rate': 6.056476114546747e-07, 'epoch': 7.02}
+
 44%|████▍     | 162880/371472 [1:59:22<18:20:55,  3.16it/s]
 44%|████▍     | 162881/371472 [1:59:22<17:51:34,  3.24it/s]
 44%|████▍     | 162882/371472 [1:59:23<17:40:48,  3.28it/s]
 44%|████▍     | 162883/371472 [1:59:23<18:20:24,  3.16it/s]
 44%|████▍     | 162884/371472 [1:59:23<18:25:31,  3.14it/s]
 44%|████▍     | 162885/371472 [1:59:24<20:29:40,  2.83it/s]
 44%|████▍     | 162886/371472 [1:59:24<19:54:53,  2.91it/s]
 44%|████▍     | 162887/371472 [1:59:24<18:31:24,  3.13it/s]
 44%|████▍     | 162888/371472 [1:59:25<18:21:20,  3.16it/s]
 44%|████▍     | 162889/371472 [1:59:25<18:43:12,  3.10it/s]
 44%|████▍     | 162890/371472 [1:59:25<18:38:25,  3.11it/s]
 44%|████▍     | 162891/371472 [1:59:25<18:26:16,  3.14it/s]
 44%|████▍     | 162892/371472 [1:59:26<18:40:32,  3.10it/s]
 44%|████▍     | 162893/371472 [1:59:26<18:56:18,  3.06it/s]
 44%|████▍     | 162894/371472 [1:59:26<18:37:18,  3.11it/s]
 44%|████▍     | 162895/371472 [1:59:27<18:29:34,  3.13it/s]
 44%|████▍     | 162896/371472 [1:59:27<18:56:16,  3.06it/s]
 44%|████▍     | 162897/371472 [1:59:27<19:26:59,  2.98it/s]
 44%|████▍     | 162898/371472 [1:59:28<18:39:03,  3.11it/s]
 44%|████▍     | 162899/371472 [1:59:28<19:24:00,  2.99it/s]
 44%|████▍     | 162900/371472 [1:59:28<19:01:22,  3.05it/s]
                                                            
{'loss': 3.1277, 'learning_rate': 6.055991294791959e-07, 'epoch': 7.02}
+
 44%|████▍     | 162900/371472 [1:59:28<19:01:22,  3.05it/s]
 44%|████▍     | 162901/371472 [1:59:29<18:45:00,  3.09it/s]
 44%|████▍     | 162902/371472 [1:59:29<18:54:38,  3.06it/s]
 44%|████▍     | 162903/371472 [1:59:29<18:29:53,  3.13it/s]
 44%|████▍     | 162904/371472 [1:59:30<18:29:38,  3.13it/s]
 44%|████▍     | 162905/371472 [1:59:30<18:27:26,  3.14it/s]
 44%|████▍     | 162906/371472 [1:59:30<17:38:38,  3.28it/s]
 44%|████▍     | 162907/371472 [1:59:31<16:53:41,  3.43it/s]
 44%|████▍     | 162908/371472 [1:59:31<17:12:41,  3.37it/s]
 44%|████▍     | 162909/371472 [1:59:31<17:42:51,  3.27it/s]
 44%|████▍     | 162910/371472 [1:59:32<18:09:52,  3.19it/s]
 44%|████▍     | 162911/371472 [1:59:32<18:15:33,  3.17it/s]
 44%|████▍     | 162912/371472 [1:59:32<17:53:56,  3.24it/s]
 44%|████▍     | 162913/371472 [1:59:33<20:54:39,  2.77it/s]
 44%|████▍     | 162914/371472 [1:59:33<20:35:10,  2.81it/s]
 44%|████▍     | 162915/371472 [1:59:33<19:52:47,  2.91it/s]
 44%|████▍     | 162916/371472 [1:59:34<18:50:57,  3.07it/s]
 44%|████▍     | 162917/371472 [1:59:34<18:19:08,  3.16it/s]
 44%|████▍     | 162918/371472 [1:59:34<17:53:10,  3.24it/s]
 44%|████▍     | 162919/371472 [1:59:34<17:59:22,  3.22it/s]
 44%|████▍     | 162920/371472 [1:59:35<17:18:25,  3.35it/s]
                                                            
{'loss': 3.0074, 'learning_rate': 6.055506475037168e-07, 'epoch': 7.02}
+
 44%|████▍     | 162920/371472 [1:59:35<17:18:25,  3.35it/s]
 44%|████▍     | 162921/371472 [1:59:35<18:03:53,  3.21it/s]
 44%|████▍     | 162922/371472 [1:59:35<19:46:09,  2.93it/s]
 44%|████▍     | 162923/371472 [1:59:36<19:00:41,  3.05it/s]
 44%|████▍     | 162924/371472 [1:59:36<17:59:57,  3.22it/s]
 44%|████▍     | 162925/371472 [1:59:36<17:21:39,  3.34it/s]
 44%|████▍     | 162926/371472 [1:59:37<17:02:41,  3.40it/s]
 44%|████▍     | 162927/371472 [1:59:37<17:02:45,  3.40it/s]
 44%|████▍     | 162928/371472 [1:59:37<16:34:18,  3.50it/s]
 44%|████▍     | 162929/371472 [1:59:37<16:44:08,  3.46it/s]
 44%|████▍     | 162930/371472 [1:59:38<17:02:50,  3.40it/s]
 44%|████▍     | 162931/371472 [1:59:38<17:05:42,  3.39it/s]
 44%|████▍     | 162932/371472 [1:59:38<17:28:14,  3.32it/s]
 44%|████▍     | 162933/371472 [1:59:39<17:05:08,  3.39it/s]
 44%|████▍     | 162934/371472 [1:59:39<16:37:03,  3.49it/s]
 44%|████▍     | 162935/371472 [1:59:39<17:29:10,  3.31it/s]
 44%|████▍     | 162936/371472 [1:59:40<17:28:08,  3.32it/s]
 44%|████▍     | 162937/371472 [1:59:40<17:32:23,  3.30it/s]
 44%|████▍     | 162938/371472 [1:59:40<17:25:48,  3.32it/s]
 44%|████▍     | 162939/371472 [1:59:40<17:27:58,  3.32it/s]
 44%|████▍     | 162940/371472 [1:59:41<17:57:21,  3.23it/s]
                                                            
{'loss': 2.8977, 'learning_rate': 6.05502165528238e-07, 'epoch': 7.02}
+
 44%|████▍     | 162940/371472 [1:59:41<17:57:21,  3.23it/s]
 44%|████▍     | 162941/371472 [1:59:41<17:38:57,  3.28it/s]
 44%|████▍     | 162942/371472 [1:59:41<17:30:00,  3.31it/s]
 44%|████▍     | 162943/371472 [1:59:42<17:17:51,  3.35it/s]
 44%|████▍     | 162944/371472 [1:59:42<17:23:55,  3.33it/s]
 44%|████▍     | 162945/371472 [1:59:42<16:46:24,  3.45it/s]
 44%|████▍     | 162946/371472 [1:59:43<17:19:53,  3.34it/s]
 44%|████▍     | 162947/371472 [1:59:43<17:16:01,  3.35it/s]
 44%|████▍     | 162948/371472 [1:59:43<17:20:27,  3.34it/s]
 44%|████▍     | 162949/371472 [1:59:43<17:16:33,  3.35it/s]
 44%|████▍     | 162950/371472 [1:59:44<18:10:11,  3.19it/s]
 44%|████▍     | 162951/371472 [1:59:44<17:27:17,  3.32it/s]
 44%|████▍     | 162952/371472 [1:59:44<17:09:12,  3.38it/s]
 44%|████▍     | 162953/371472 [1:59:45<18:07:55,  3.19it/s]
 44%|████▍     | 162954/371472 [1:59:45<17:47:34,  3.26it/s]
 44%|████▍     | 162955/371472 [1:59:45<17:32:48,  3.30it/s]
 44%|████▍     | 162956/371472 [1:59:46<17:11:03,  3.37it/s]
 44%|████▍     | 162957/371472 [1:59:46<17:09:39,  3.38it/s]
 44%|████▍     | 162958/371472 [1:59:46<17:18:03,  3.35it/s]
 44%|████▍     | 162959/371472 [1:59:46<16:51:50,  3.43it/s]
 44%|████▍     | 162960/371472 [1:59:47<16:39:20,  3.48it/s]
                                                            
{'loss': 2.8764, 'learning_rate': 6.054536835527592e-07, 'epoch': 7.02}
+
 44%|████▍     | 162960/371472 [1:59:47<16:39:20,  3.48it/s]
 44%|████▍     | 162961/371472 [1:59:47<17:22:43,  3.33it/s]
 44%|████▍     | 162962/371472 [1:59:47<17:34:39,  3.30it/s]
 44%|████▍     | 162963/371472 [1:59:48<17:10:03,  3.37it/s]
 44%|████▍     | 162964/371472 [1:59:48<16:57:27,  3.42it/s]
 44%|████▍     | 162965/371472 [1:59:48<16:56:43,  3.42it/s]
 44%|████▍     | 162966/371472 [1:59:49<17:03:57,  3.39it/s]
 44%|████▍     | 162967/371472 [1:59:49<16:35:03,  3.49it/s]
 44%|████▍     | 162968/371472 [1:59:49<16:50:59,  3.44it/s]
 44%|████▍     | 162969/371472 [1:59:50<18:45:06,  3.09it/s]
 44%|████▍     | 162970/371472 [1:59:50<18:32:07,  3.12it/s]
 44%|████▍     | 162971/371472 [1:59:50<18:26:15,  3.14it/s]
 44%|████▍     | 162972/371472 [1:59:50<18:22:05,  3.15it/s]
 44%|████▍     | 162973/371472 [1:59:51<17:48:39,  3.25it/s]
 44%|████▍     | 162974/371472 [1:59:51<17:36:48,  3.29it/s]
 44%|████▍     | 162975/371472 [1:59:51<16:57:22,  3.42it/s]
 44%|████▍     | 162976/371472 [1:59:52<17:08:58,  3.38it/s]
 44%|████▍     | 162977/371472 [1:59:52<18:03:15,  3.21it/s]
 44%|████▍     | 162978/371472 [1:59:52<17:34:03,  3.30it/s]
 44%|████▍     | 162979/371472 [1:59:53<17:52:48,  3.24it/s]
 44%|████▍     | 162980/371472 [1:59:53<19:02:20,  3.04it/s]
                                                            
{'loss': 2.9158, 'learning_rate': 6.054052015772804e-07, 'epoch': 7.02}
+
 44%|████▍     | 162980/371472 [1:59:53<19:02:20,  3.04it/s]
 44%|████▍     | 162981/371472 [1:59:53<19:17:16,  3.00it/s]
 44%|████▍     | 162982/371472 [1:59:54<18:50:35,  3.07it/s]
 44%|████▍     | 162983/371472 [1:59:54<18:28:27,  3.13it/s]
 44%|████▍     | 162984/371472 [1:59:54<17:59:30,  3.22it/s]
 44%|████▍     | 162985/371472 [1:59:54<17:28:12,  3.31it/s]
 44%|████▍     | 162986/371472 [1:59:55<16:53:23,  3.43it/s]
 44%|████▍     | 162987/371472 [1:59:55<17:50:28,  3.25it/s]
 44%|████▍     | 162988/371472 [1:59:55<17:34:51,  3.29it/s]
 44%|████▍     | 162989/371472 [1:59:56<17:50:57,  3.24it/s]
 44%|████▍     | 162990/371472 [1:59:56<17:11:00,  3.37it/s]
 44%|████▍     | 162991/371472 [1:59:56<17:07:43,  3.38it/s]
 44%|████▍     | 162992/371472 [1:59:57<17:26:51,  3.32it/s]
 44%|████▍     | 162993/371472 [1:59:57<17:17:11,  3.35it/s]
 44%|████▍     | 162994/371472 [1:59:57<17:06:16,  3.39it/s]
 44%|████▍     | 162995/371472 [1:59:57<17:52:28,  3.24it/s]
 44%|████▍     | 162996/371472 [1:59:58<18:41:48,  3.10it/s]
 44%|████▍     | 162997/371472 [1:59:58<18:01:30,  3.21it/s]
 44%|████▍     | 162998/371472 [1:59:58<18:00:16,  3.22it/s]
 44%|████▍     | 162999/371472 [1:59:59<18:11:33,  3.18it/s]
 44%|████▍     | 163000/371472 [1:59:59<17:44:59,  3.26it/s]
                                                            
{'loss': 2.7917, 'learning_rate': 6.053567196018013e-07, 'epoch': 7.02}
+
 44%|████▍     | 163000/371472 [1:59:59<17:44:59,  3.26it/s]
 44%|████▍     | 163001/371472 [1:59:59<17:26:05,  3.32it/s]
 44%|████▍     | 163002/371472 [2:00:00<17:10:06,  3.37it/s]
 44%|████▍     | 163003/371472 [2:00:00<17:01:31,  3.40it/s]
 44%|████▍     | 163004/371472 [2:00:00<16:53:28,  3.43it/s]
 44%|████▍     | 163005/371472 [2:00:00<16:43:47,  3.46it/s]
 44%|████▍     | 163006/371472 [2:00:01<17:07:54,  3.38it/s]
 44%|████▍     | 163007/371472 [2:00:01<16:52:05,  3.43it/s]
 44%|████▍     | 163008/371472 [2:00:01<16:42:48,  3.46it/s]
 44%|████▍     | 163009/371472 [2:00:02<18:02:51,  3.21it/s]
 44%|████▍     | 163010/371472 [2:00:02<18:05:51,  3.20it/s]
 44%|████▍     | 163011/371472 [2:00:02<18:29:33,  3.13it/s]
 44%|████▍     | 163012/371472 [2:00:03<17:46:37,  3.26it/s]
 44%|████▍     | 163013/371472 [2:00:03<17:24:18,  3.33it/s]
 44%|████▍     | 163014/371472 [2:00:03<17:29:51,  3.31it/s]
 44%|████▍     | 163015/371472 [2:00:04<17:19:32,  3.34it/s]
 44%|████▍     | 163016/371472 [2:00:04<17:01:22,  3.40it/s]
 44%|████▍     | 163017/371472 [2:00:04<16:38:11,  3.48it/s]
 44%|████▍     | 163018/371472 [2:00:04<16:39:07,  3.48it/s]
 44%|████▍     | 163019/371472 [2:00:05<17:02:03,  3.40it/s]
 44%|████▍     | 163020/371472 [2:00:05<17:02:25,  3.40it/s]
                                                            
{'loss': 3.0121, 'learning_rate': 6.053082376263224e-07, 'epoch': 7.02}
+
 44%|████▍     | 163020/371472 [2:00:05<17:02:25,  3.40it/s]
 44%|████▍     | 163021/371472 [2:00:05<17:04:46,  3.39it/s]
 44%|████▍     | 163022/371472 [2:00:06<16:50:24,  3.44it/s]
 44%|████▍     | 163023/371472 [2:00:06<16:53:02,  3.43it/s]
 44%|████▍     | 163024/371472 [2:00:06<17:04:27,  3.39it/s]
 44%|████▍     | 163025/371472 [2:00:06<17:11:52,  3.37it/s]
 44%|████▍     | 163026/371472 [2:00:07<17:53:16,  3.24it/s]
 44%|████▍     | 163027/371472 [2:00:07<17:42:02,  3.27it/s]
 44%|████▍     | 163028/371472 [2:00:07<17:36:37,  3.29it/s]
 44%|████▍     | 163029/371472 [2:00:08<17:22:41,  3.33it/s]
 44%|████▍     | 163030/371472 [2:00:08<17:14:59,  3.36it/s]
 44%|████▍     | 163031/371472 [2:00:08<17:13:51,  3.36it/s]
 44%|████▍     | 163032/371472 [2:00:09<16:45:00,  3.46it/s]
 44%|████▍     | 163033/371472 [2:00:09<16:50:49,  3.44it/s]
 44%|████▍     | 163034/371472 [2:00:09<17:23:04,  3.33it/s]
 44%|████▍     | 163035/371472 [2:00:10<18:45:57,  3.09it/s]
 44%|████▍     | 163036/371472 [2:00:10<19:06:59,  3.03it/s]
 44%|████▍     | 163037/371472 [2:00:10<18:45:25,  3.09it/s]
 44%|████▍     | 163038/371472 [2:00:10<18:11:58,  3.18it/s]
 44%|████▍     | 163039/371472 [2:00:11<17:42:09,  3.27it/s]
 44%|████▍     | 163040/371472 [2:00:11<17:17:44,  3.35it/s]
                                                            
{'loss': 2.9799, 'learning_rate': 6.052597556508436e-07, 'epoch': 7.02}
+
 44%|████▍     | 163040/371472 [2:00:11<17:17:44,  3.35it/s]
 44%|████▍     | 163041/371472 [2:00:11<17:24:47,  3.32it/s]
 44%|████▍     | 163042/371472 [2:00:12<16:57:13,  3.42it/s]
 44%|████▍     | 163043/371472 [2:00:12<16:51:45,  3.43it/s]
 44%|████▍     | 163044/371472 [2:00:12<16:59:13,  3.41it/s]
 44%|████▍     | 163045/371472 [2:00:13<17:21:00,  3.34it/s]
 44%|████▍     | 163046/371472 [2:00:13<17:29:17,  3.31it/s]
 44%|████▍     | 163047/371472 [2:00:13<16:45:28,  3.45it/s]
 44%|████▍     | 163048/371472 [2:00:13<16:46:31,  3.45it/s]
 44%|████▍     | 163049/371472 [2:00:14<16:54:43,  3.42it/s]
 44%|████▍     | 163050/371472 [2:00:14<17:18:26,  3.35it/s]
 44%|████▍     | 163051/371472 [2:00:14<17:06:58,  3.38it/s]
 44%|████▍     | 163052/371472 [2:00:15<17:08:23,  3.38it/s]
 44%|████▍     | 163053/371472 [2:00:15<17:00:54,  3.40it/s]
 44%|████▍     | 163054/371472 [2:00:15<16:40:34,  3.47it/s]
 44%|████▍     | 163055/371472 [2:00:15<17:05:54,  3.39it/s]
 44%|████▍     | 163056/371472 [2:00:16<17:17:17,  3.35it/s]
 44%|████▍     | 163057/371472 [2:00:16<17:48:15,  3.25it/s]
 44%|████▍     | 163058/371472 [2:00:16<18:34:35,  3.12it/s]
 44%|████▍     | 163059/371472 [2:00:17<17:37:58,  3.28it/s]
 44%|████▍     | 163060/371472 [2:00:17<17:06:52,  3.38it/s]
                                                            
{'loss': 2.8608, 'learning_rate': 6.052112736753647e-07, 'epoch': 7.02}
+
 44%|████▍     | 163060/371472 [2:00:17<17:06:52,  3.38it/s]
 44%|████▍     | 163061/371472 [2:00:17<17:41:56,  3.27it/s]
 44%|████▍     | 163062/371472 [2:00:18<17:44:58,  3.26it/s]
 44%|████▍     | 163063/371472 [2:00:18<17:34:11,  3.29it/s]
 44%|████▍     | 163064/371472 [2:00:18<17:29:30,  3.31it/s]
 44%|████▍     | 163065/371472 [2:00:19<17:43:21,  3.27it/s]
 44%|████▍     | 163066/371472 [2:00:19<17:21:00,  3.34it/s]
 44%|████▍     | 163067/371472 [2:00:19<17:20:47,  3.34it/s]
 44%|████▍     | 163068/371472 [2:00:19<17:12:46,  3.36it/s]
 44%|████▍     | 163069/371472 [2:00:20<16:57:14,  3.41it/s]
 44%|████▍     | 163070/371472 [2:00:20<17:05:33,  3.39it/s]
 44%|████▍     | 163071/371472 [2:00:20<17:05:49,  3.39it/s]
 44%|████▍     | 163072/371472 [2:00:21<17:34:57,  3.29it/s]
 44%|████▍     | 163073/371472 [2:00:21<18:28:24,  3.13it/s]
 44%|████▍     | 163074/371472 [2:00:21<18:06:55,  3.20it/s]
 44%|████▍     | 163075/371472 [2:00:22<17:46:13,  3.26it/s]
 44%|████▍     | 163076/371472 [2:00:22<17:32:21,  3.30it/s]
 44%|████▍     | 163077/371472 [2:00:22<17:32:56,  3.30it/s]
 44%|████▍     | 163078/371472 [2:00:22<17:06:00,  3.39it/s]
 44%|████▍     | 163079/371472 [2:00:23<16:59:11,  3.41it/s]
 44%|████▍     | 163080/371472 [2:00:23<16:53:00,  3.43it/s]
                                                            
{'loss': 3.0588, 'learning_rate': 6.051627916998858e-07, 'epoch': 7.02}
+
 44%|████▍     | 163080/371472 [2:00:23<16:53:00,  3.43it/s]
 44%|████▍     | 163081/371472 [2:00:23<16:47:12,  3.45it/s]
 44%|████▍     | 163082/371472 [2:00:24<16:21:11,  3.54it/s]
 44%|████▍     | 163083/371472 [2:00:24<16:18:47,  3.55it/s]
 44%|████▍     | 163084/371472 [2:00:24<16:43:23,  3.46it/s]
 44%|████▍     | 163085/371472 [2:00:25<18:08:23,  3.19it/s]
 44%|████▍     | 163086/371472 [2:00:25<17:40:59,  3.27it/s]
 44%|████▍     | 163087/371472 [2:00:25<17:20:48,  3.34it/s]
 44%|████▍     | 163088/371472 [2:00:25<17:03:58,  3.39it/s]
 44%|████▍     | 163089/371472 [2:00:26<17:06:53,  3.38it/s]
 44%|████▍     | 163090/371472 [2:00:26<17:10:52,  3.37it/s]
 44%|████▍     | 163091/371472 [2:00:26<16:49:40,  3.44it/s]
 44%|████▍     | 163092/371472 [2:00:27<16:33:00,  3.50it/s]
 44%|████▍     | 163093/371472 [2:00:27<16:27:31,  3.52it/s]
 44%|████▍     | 163094/371472 [2:00:27<17:34:49,  3.29it/s]
 44%|████▍     | 163095/371472 [2:00:27<17:20:06,  3.34it/s]
 44%|████▍     | 163096/371472 [2:00:28<18:05:33,  3.20it/s]
 44%|████▍     | 163097/371472 [2:00:28<17:37:55,  3.28it/s]
 44%|████▍     | 163098/371472 [2:00:28<17:10:37,  3.37it/s]
 44%|████▍     | 163099/371472 [2:00:29<17:03:54,  3.39it/s]
 44%|████▍     | 163100/371472 [2:00:29<17:41:14,  3.27it/s]
                                                            
{'loss': 3.0159, 'learning_rate': 6.051143097244069e-07, 'epoch': 7.03}
+
 44%|████▍     | 163100/371472 [2:00:29<17:41:14,  3.27it/s]
 44%|████▍     | 163101/371472 [2:00:29<19:47:02,  2.93it/s]
 44%|████▍     | 163102/371472 [2:00:30<19:45:06,  2.93it/s]
 44%|████▍     | 163103/371472 [2:00:30<19:02:24,  3.04it/s]
 44%|████▍     | 163104/371472 [2:00:30<17:56:00,  3.23it/s]
 44%|████▍     | 163105/371472 [2:00:31<17:21:25,  3.33it/s]
 44%|████▍     | 163106/371472 [2:00:31<17:21:16,  3.34it/s]
 44%|████▍     | 163107/371472 [2:00:31<17:04:49,  3.39it/s]
 44%|████▍     | 163108/371472 [2:00:31<17:04:45,  3.39it/s]
 44%|████▍     | 163109/371472 [2:00:32<16:50:26,  3.44it/s]
 44%|████▍     | 163110/371472 [2:00:32<17:06:46,  3.38it/s]
 44%|████▍     | 163111/371472 [2:00:32<17:09:32,  3.37it/s]
 44%|████▍     | 163112/371472 [2:00:33<18:31:55,  3.12it/s]
 44%|████▍     | 163113/371472 [2:00:33<19:11:06,  3.02it/s]
 44%|████▍     | 163114/371472 [2:00:33<18:21:56,  3.15it/s]
 44%|████▍     | 163115/371472 [2:00:34<17:52:19,  3.24it/s]
 44%|████▍     | 163116/371472 [2:00:34<17:13:04,  3.36it/s]
 44%|████▍     | 163117/371472 [2:00:34<17:09:50,  3.37it/s]
 44%|████▍     | 163118/371472 [2:00:35<17:06:17,  3.38it/s]
 44%|████▍     | 163119/371472 [2:00:35<17:59:03,  3.22it/s]
 44%|████▍     | 163120/371472 [2:00:35<17:37:05,  3.29it/s]
                                                            
{'loss': 2.9035, 'learning_rate': 6.05065827748928e-07, 'epoch': 7.03}
+
 44%|████▍     | 163120/371472 [2:00:35<17:37:05,  3.29it/s]
 44%|████▍     | 163121/371472 [2:00:35<17:53:32,  3.23it/s]
 44%|████▍     | 163122/371472 [2:00:36<17:46:37,  3.26it/s]
 44%|████▍     | 163123/371472 [2:00:36<19:13:20,  3.01it/s]
 44%|████▍     | 163124/371472 [2:00:36<18:48:22,  3.08it/s]
 44%|████▍     | 163125/371472 [2:00:37<18:04:01,  3.20it/s]
 44%|████▍     | 163126/371472 [2:00:37<18:42:34,  3.09it/s]
 44%|████▍     | 163127/371472 [2:00:37<18:47:50,  3.08it/s]
 44%|████▍     | 163128/371472 [2:00:38<18:32:05,  3.12it/s]
 44%|████▍     | 163129/371472 [2:00:38<18:41:19,  3.10it/s]
 44%|████▍     | 163130/371472 [2:00:38<18:44:50,  3.09it/s]
 44%|████▍     | 163131/371472 [2:00:39<18:22:23,  3.15it/s]
 44%|████▍     | 163132/371472 [2:00:39<17:55:46,  3.23it/s]
 44%|████▍     | 163133/371472 [2:00:39<17:35:59,  3.29it/s]
 44%|████▍     | 163134/371472 [2:00:40<16:57:26,  3.41it/s]
 44%|████▍     | 163135/371472 [2:00:40<16:54:47,  3.42it/s]
 44%|████▍     | 163136/371472 [2:00:40<16:41:06,  3.47it/s]
 44%|████▍     | 163137/371472 [2:00:40<16:43:40,  3.46it/s]
 44%|████▍     | 163138/371472 [2:00:41<16:23:33,  3.53it/s]
 44%|████▍     | 163139/371472 [2:00:41<16:06:41,  3.59it/s]
 44%|████▍     | 163140/371472 [2:00:41<16:12:40,  3.57it/s]
                                                            
{'loss': 2.8273, 'learning_rate': 6.050173457734491e-07, 'epoch': 7.03}
+
 44%|████▍     | 163140/371472 [2:00:41<16:12:40,  3.57it/s]
 44%|████▍     | 163141/371472 [2:00:42<16:31:57,  3.50it/s]
 44%|████▍     | 163142/371472 [2:00:42<16:53:59,  3.42it/s]
 44%|████▍     | 163143/371472 [2:00:42<17:10:28,  3.37it/s]
 44%|████▍     | 163144/371472 [2:00:42<16:41:23,  3.47it/s]
 44%|████▍     | 163145/371472 [2:00:43<17:20:50,  3.34it/s]
 44%|████▍     | 163146/371472 [2:00:43<17:02:29,  3.40it/s]
 44%|████▍     | 163147/371472 [2:00:43<17:08:18,  3.38it/s]
 44%|████▍     | 163148/371472 [2:00:44<17:09:42,  3.37it/s]
 44%|████▍     | 163149/371472 [2:00:44<17:07:26,  3.38it/s]
 44%|████▍     | 163150/371472 [2:00:44<17:06:09,  3.38it/s]
 44%|████▍     | 163151/371472 [2:00:45<17:31:15,  3.30it/s]
 44%|████▍     | 163152/371472 [2:00:45<17:11:17,  3.37it/s]
 44%|████▍     | 163153/371472 [2:00:45<17:37:03,  3.28it/s]
 44%|████▍     | 163154/371472 [2:00:45<17:26:02,  3.32it/s]
 44%|████▍     | 163155/371472 [2:00:46<17:22:38,  3.33it/s]
 44%|████▍     | 163156/371472 [2:00:46<18:14:27,  3.17it/s]
 44%|████▍     | 163157/371472 [2:00:46<18:13:26,  3.18it/s]
 44%|████▍     | 163158/371472 [2:00:47<18:49:49,  3.07it/s]
 44%|████▍     | 163159/371472 [2:00:47<19:11:45,  3.01it/s]
 44%|████▍     | 163160/371472 [2:00:47<18:52:13,  3.07it/s]
                                                            
{'loss': 2.9879, 'learning_rate': 6.049688637979701e-07, 'epoch': 7.03}
+
 44%|████▍     | 163160/371472 [2:00:47<18:52:13,  3.07it/s]
 44%|████▍     | 163161/371472 [2:00:48<18:01:25,  3.21it/s]
 44%|████▍     | 163162/371472 [2:00:48<18:32:51,  3.12it/s]
 44%|████▍     | 163163/371472 [2:00:48<17:43:58,  3.26it/s]
 44%|████▍     | 163164/371472 [2:00:49<17:39:22,  3.28it/s]
 44%|████▍     | 163165/371472 [2:00:49<17:18:30,  3.34it/s]
 44%|████▍     | 163166/371472 [2:00:49<17:52:06,  3.24it/s]
 44%|████▍     | 163167/371472 [2:00:50<18:08:37,  3.19it/s]
 44%|████▍     | 163168/371472 [2:00:50<19:42:27,  2.94it/s]
 44%|████▍     | 163169/371472 [2:00:50<19:23:12,  2.98it/s]
 44%|████▍     | 163170/371472 [2:00:51<18:47:38,  3.08it/s]
 44%|████▍     | 163171/371472 [2:00:51<18:26:17,  3.14it/s]
 44%|████▍     | 163172/371472 [2:00:51<18:05:38,  3.20it/s]
 44%|████▍     | 163173/371472 [2:00:51<18:04:14,  3.20it/s]
 44%|████▍     | 163174/371472 [2:00:52<20:41:51,  2.80it/s]
 44%|████▍     | 163175/371472 [2:00:52<19:29:10,  2.97it/s]
 44%|████▍     | 163176/371472 [2:00:53<19:20:42,  2.99it/s]
 44%|████▍     | 163177/371472 [2:00:53<18:20:26,  3.15it/s]
 44%|████▍     | 163178/371472 [2:00:53<17:49:46,  3.25it/s]
 44%|████▍     | 163179/371472 [2:00:53<17:26:13,  3.32it/s]
 44%|████▍     | 163180/371472 [2:00:54<16:47:23,  3.45it/s]
                                                            
{'loss': 2.8966, 'learning_rate': 6.049203818224913e-07, 'epoch': 7.03}
+
 44%|████▍     | 163180/371472 [2:00:54<16:47:23,  3.45it/s]
 44%|████▍     | 163181/371472 [2:00:54<16:21:30,  3.54it/s]
 44%|████▍     | 163182/371472 [2:00:54<16:17:35,  3.55it/s]
 44%|████▍     | 163183/371472 [2:00:55<16:36:54,  3.48it/s]
 44%|████▍     | 163184/371472 [2:00:55<16:33:21,  3.49it/s]
 44%|████▍     | 163185/371472 [2:00:55<17:41:02,  3.27it/s]
 44%|████▍     | 163186/371472 [2:00:55<18:07:40,  3.19it/s]
 44%|████▍     | 163187/371472 [2:00:56<17:46:52,  3.25it/s]
 44%|████▍     | 163188/371472 [2:00:56<17:14:21,  3.36it/s]
 44%|████▍     | 163189/371472 [2:00:56<18:49:31,  3.07it/s]
 44%|████▍     | 163190/371472 [2:00:57<18:14:27,  3.17it/s]
 44%|████▍     | 163191/371472 [2:00:57<17:35:43,  3.29it/s]
 44%|████▍     | 163192/371472 [2:00:57<17:27:17,  3.31it/s]
 44%|████▍     | 163193/371472 [2:00:58<17:40:12,  3.27it/s]
 44%|████▍     | 163194/371472 [2:00:58<17:05:38,  3.38it/s]
 44%|████▍     | 163195/371472 [2:00:58<17:52:04,  3.24it/s]
 44%|████▍     | 163196/371472 [2:00:59<17:29:51,  3.31it/s]
 44%|████▍     | 163197/371472 [2:00:59<18:36:44,  3.11it/s]
 44%|████▍     | 163198/371472 [2:00:59<17:48:05,  3.25it/s]
 44%|████▍     | 163199/371472 [2:00:59<17:43:53,  3.26it/s]
 44%|████▍     | 163200/371472 [2:01:00<17:14:04,  3.36it/s]
                                                            
{'loss': 3.0789, 'learning_rate': 6.048718998470125e-07, 'epoch': 7.03}
+
 44%|████▍     | 163200/371472 [2:01:00<17:14:04,  3.36it/s]
 44%|████▍     | 163201/371472 [2:01:00<18:21:14,  3.15it/s]
 44%|████▍     | 163202/371472 [2:01:00<17:45:37,  3.26it/s]
 44%|████▍     | 163203/371472 [2:01:01<17:59:07,  3.22it/s]
 44%|████▍     | 163204/371472 [2:01:01<17:42:47,  3.27it/s]
 44%|████▍     | 163205/371472 [2:01:01<17:42:31,  3.27it/s]
 44%|████▍     | 163206/371472 [2:01:02<18:06:50,  3.19it/s]
 44%|████▍     | 163207/371472 [2:01:02<18:17:22,  3.16it/s]
 44%|████▍     | 163208/371472 [2:01:02<18:15:10,  3.17it/s]
 44%|████▍     | 163209/371472 [2:01:03<18:12:50,  3.18it/s]
 44%|████▍     | 163210/371472 [2:01:03<17:48:47,  3.25it/s]
 44%|████▍     | 163211/371472 [2:01:03<17:22:00,  3.33it/s]
 44%|████▍     | 163212/371472 [2:01:03<17:03:18,  3.39it/s]
 44%|████▍     | 163213/371472 [2:01:04<16:47:26,  3.45it/s]
 44%|████▍     | 163214/371472 [2:01:04<16:59:47,  3.40it/s]
 44%|████▍     | 163215/371472 [2:01:04<17:53:04,  3.23it/s]
 44%|████▍     | 163216/371472 [2:01:05<17:34:44,  3.29it/s]
 44%|████▍     | 163217/371472 [2:01:05<17:41:42,  3.27it/s]
 44%|████▍     | 163218/371472 [2:01:05<17:38:47,  3.28it/s]
 44%|████▍     | 163219/371472 [2:01:06<17:18:57,  3.34it/s]
 44%|████▍     | 163220/371472 [2:01:06<17:17:37,  3.35it/s]
                                                            
{'loss': 2.9414, 'learning_rate': 6.048234178715335e-07, 'epoch': 7.03}
+
 44%|████▍     | 163220/371472 [2:01:06<17:17:37,  3.35it/s]
 44%|████▍     | 163221/371472 [2:01:06<16:51:57,  3.43it/s]
 44%|████▍     | 163222/371472 [2:01:06<16:25:56,  3.52it/s]
 44%|████▍     | 163223/371472 [2:01:07<16:09:49,  3.58it/s]
 44%|████▍     | 163224/371472 [2:01:07<16:31:04,  3.50it/s]
 44%|████▍     | 163225/371472 [2:01:07<16:38:05,  3.48it/s]
 44%|████▍     | 163226/371472 [2:01:08<17:49:09,  3.25it/s]
 44%|████▍     | 163227/371472 [2:01:08<17:44:42,  3.26it/s]
 44%|████▍     | 163228/371472 [2:01:08<17:55:02,  3.23it/s]
 44%|████▍     | 163229/371472 [2:01:09<17:44:55,  3.26it/s]
 44%|████▍     | 163230/371472 [2:01:09<18:32:00,  3.12it/s]
 44%|████▍     | 163231/371472 [2:01:09<18:38:27,  3.10it/s]
 44%|████▍     | 163232/371472 [2:01:10<18:03:07,  3.20it/s]
 44%|████▍     | 163233/371472 [2:01:10<17:50:07,  3.24it/s]
 44%|████▍     | 163234/371472 [2:01:10<17:52:39,  3.24it/s]
 44%|████▍     | 163235/371472 [2:01:10<17:44:43,  3.26it/s]
 44%|████▍     | 163236/371472 [2:01:11<17:05:36,  3.38it/s]
 44%|████▍     | 163237/371472 [2:01:11<16:48:20,  3.44it/s]
 44%|████▍     | 163238/371472 [2:01:11<16:57:09,  3.41it/s]
 44%|████▍     | 163239/371472 [2:01:12<17:10:50,  3.37it/s]
 44%|████▍     | 163240/371472 [2:01:12<16:44:20,  3.46it/s]
                                                            
{'loss': 2.9182, 'learning_rate': 6.047749358960546e-07, 'epoch': 7.03}
+
 44%|████▍     | 163240/371472 [2:01:12<16:44:20,  3.46it/s]
 44%|████▍     | 163241/371472 [2:01:12<16:26:33,  3.52it/s]
 44%|████▍     | 163242/371472 [2:01:12<16:50:24,  3.43it/s]
 44%|████▍     | 163243/371472 [2:01:13<16:52:36,  3.43it/s]
 44%|████▍     | 163244/371472 [2:01:13<16:47:34,  3.44it/s]
 44%|████▍     | 163245/371472 [2:01:13<18:13:04,  3.17it/s]
 44%|████▍     | 163246/371472 [2:01:14<18:12:51,  3.18it/s]
 44%|████▍     | 163247/371472 [2:01:14<17:51:26,  3.24it/s]
 44%|████▍     | 163248/371472 [2:01:14<17:21:30,  3.33it/s]
 44%|████▍     | 163249/371472 [2:01:15<17:07:35,  3.38it/s]
 44%|████▍     | 163250/371472 [2:01:15<17:21:57,  3.33it/s]
 44%|████▍     | 163251/371472 [2:01:15<17:13:50,  3.36it/s]
 44%|████▍     | 163252/371472 [2:01:16<18:37:10,  3.11it/s]
 44%|████▍     | 163253/371472 [2:01:16<17:43:56,  3.26it/s]
 44%|████▍     | 163254/371472 [2:01:16<17:22:06,  3.33it/s]
 44%|████▍     | 163255/371472 [2:01:16<17:05:58,  3.38it/s]
 44%|████▍     | 163256/371472 [2:01:17<17:13:18,  3.36it/s]
 44%|████▍     | 163257/371472 [2:01:17<17:04:20,  3.39it/s]
 44%|████▍     | 163258/371472 [2:01:17<17:57:35,  3.22it/s]
 44%|████▍     | 163259/371472 [2:01:18<18:26:53,  3.14it/s]
 44%|████▍     | 163260/371472 [2:01:18<17:53:24,  3.23it/s]
                                                            
{'loss': 2.8845, 'learning_rate': 6.047264539205757e-07, 'epoch': 7.03}
+
 44%|████▍     | 163260/371472 [2:01:18<17:53:24,  3.23it/s]
 44%|████▍     | 163261/371472 [2:01:18<18:46:29,  3.08it/s]
 44%|████▍     | 163262/371472 [2:01:19<18:31:04,  3.12it/s]
 44%|████▍     | 163263/371472 [2:01:19<18:12:32,  3.18it/s]
 44%|████▍     | 163264/371472 [2:01:19<17:48:33,  3.25it/s]
 44%|████▍     | 163265/371472 [2:01:19<17:08:15,  3.37it/s]
 44%|████▍     | 163266/371472 [2:01:20<17:13:52,  3.36it/s]
 44%|████▍     | 163267/371472 [2:01:20<17:49:34,  3.24it/s]
 44%|████▍     | 163268/371472 [2:01:20<17:13:21,  3.36it/s]
 44%|████▍     | 163269/371472 [2:01:21<17:08:26,  3.37it/s]
 44%|████▍     | 163270/371472 [2:01:21<17:17:18,  3.35it/s]
 44%|████▍     | 163271/371472 [2:01:21<16:36:07,  3.48it/s]
 44%|████▍     | 163272/371472 [2:01:22<20:16:29,  2.85it/s]
 44%|████▍     | 163273/371472 [2:01:22<19:27:44,  2.97it/s]
 44%|████▍     | 163274/371472 [2:01:22<18:36:25,  3.11it/s]
 44%|████▍     | 163275/371472 [2:01:23<17:58:18,  3.22it/s]
 44%|████▍     | 163276/371472 [2:01:23<18:53:02,  3.06it/s]
 44%|████▍     | 163277/371472 [2:01:23<18:00:27,  3.21it/s]
 44%|████▍     | 163278/371472 [2:01:24<18:21:07,  3.15it/s]
 44%|████▍     | 163279/371472 [2:01:24<18:01:00,  3.21it/s]
 44%|████▍     | 163280/371472 [2:01:24<17:40:27,  3.27it/s]
                                                            
{'loss': 2.9894, 'learning_rate': 6.046779719450968e-07, 'epoch': 7.03}
+
 44%|████▍     | 163280/371472 [2:01:24<17:40:27,  3.27it/s]
 44%|████▍     | 163281/371472 [2:01:24<17:35:51,  3.29it/s]
 44%|████▍     | 163282/371472 [2:01:25<17:16:39,  3.35it/s]
 44%|████▍     | 163283/371472 [2:01:25<17:43:55,  3.26it/s]
 44%|████▍     | 163284/371472 [2:01:25<17:25:15,  3.32it/s]
 44%|████▍     | 163285/371472 [2:01:26<17:19:34,  3.34it/s]
 44%|████▍     | 163286/371472 [2:01:26<17:54:18,  3.23it/s]
 44%|████▍     | 163287/371472 [2:01:26<17:21:09,  3.33it/s]
 44%|████▍     | 163288/371472 [2:01:27<17:36:17,  3.28it/s]
 44%|████▍     | 163289/371472 [2:01:27<19:15:15,  3.00it/s]
 44%|████▍     | 163290/371472 [2:01:27<18:19:43,  3.16it/s]
 44%|████▍     | 163291/371472 [2:01:28<18:04:49,  3.20it/s]
 44%|████▍     | 163292/371472 [2:01:28<17:37:50,  3.28it/s]
 44%|████▍     | 163293/371472 [2:01:28<17:10:33,  3.37it/s]
 44%|████▍     | 163294/371472 [2:01:28<17:12:04,  3.36it/s]
 44%|████▍     | 163295/371472 [2:01:29<18:14:37,  3.17it/s]
 44%|████▍     | 163296/371472 [2:01:29<17:55:25,  3.23it/s]
 44%|████▍     | 163297/371472 [2:01:29<17:14:08,  3.36it/s]
 44%|████▍     | 163298/371472 [2:01:30<17:09:59,  3.37it/s]
 44%|████▍     | 163299/371472 [2:01:30<17:01:40,  3.40it/s]
 44%|████▍     | 163300/371472 [2:01:30<16:58:36,  3.41it/s]
                                                            
{'loss': 2.981, 'learning_rate': 6.046294899696179e-07, 'epoch': 7.03}
+
 44%|████▍     | 163300/371472 [2:01:30<16:58:36,  3.41it/s]
 44%|████▍     | 163301/371472 [2:01:31<17:16:55,  3.35it/s]
 44%|████▍     | 163302/371472 [2:01:31<16:41:27,  3.46it/s]
 44%|████▍     | 163303/371472 [2:01:31<16:33:53,  3.49it/s]
 44%|████▍     | 163304/371472 [2:01:31<16:28:17,  3.51it/s]
 44%|████▍     | 163305/371472 [2:01:32<16:24:20,  3.52it/s]
 44%|████▍     | 163306/371472 [2:01:32<16:30:24,  3.50it/s]
 44%|████▍     | 163307/371472 [2:01:32<17:57:35,  3.22it/s]
 44%|████▍     | 163308/371472 [2:01:33<17:15:10,  3.35it/s]
 44%|████▍     | 163309/371472 [2:01:33<17:46:02,  3.25it/s]
 44%|████▍     | 163310/371472 [2:01:33<18:48:24,  3.07it/s]
 44%|████▍     | 163311/371472 [2:01:34<18:17:56,  3.16it/s]
 44%|████▍     | 163312/371472 [2:01:34<17:57:46,  3.22it/s]
 44%|████▍     | 163313/371472 [2:01:34<18:31:31,  3.12it/s]
 44%|████▍     | 163314/371472 [2:01:34<17:38:32,  3.28it/s]
 44%|████▍     | 163315/371472 [2:01:35<18:37:48,  3.10it/s]
 44%|████▍     | 163316/371472 [2:01:35<17:34:33,  3.29it/s]
 44%|████▍     | 163317/371472 [2:01:35<17:23:19,  3.33it/s]
 44%|████▍     | 163318/371472 [2:01:36<18:11:26,  3.18it/s]
 44%|████▍     | 163319/371472 [2:01:36<19:55:07,  2.90it/s]
 44%|████▍     | 163320/371472 [2:01:36<18:50:26,  3.07it/s]
                                                            
{'loss': 3.0679, 'learning_rate': 6.04581007994139e-07, 'epoch': 7.03}
+
 44%|████▍     | 163320/371472 [2:01:36<18:50:26,  3.07it/s]
 44%|████▍     | 163321/371472 [2:01:37<18:14:01,  3.17it/s]
 44%|████▍     | 163322/371472 [2:01:37<18:01:16,  3.21it/s]
 44%|████▍     | 163323/371472 [2:01:37<17:49:09,  3.24it/s]
 44%|████▍     | 163324/371472 [2:01:38<18:32:15,  3.12it/s]
 44%|████▍     | 163325/371472 [2:01:38<18:11:35,  3.18it/s]
 44%|████▍     | 163326/371472 [2:01:38<17:54:11,  3.23it/s]
 44%|████▍     | 163327/371472 [2:01:39<17:27:11,  3.31it/s]
 44%|████▍     | 163328/371472 [2:01:39<17:50:36,  3.24it/s]
 44%|████▍     | 163329/371472 [2:01:39<18:01:02,  3.21it/s]
 44%|████▍     | 163330/371472 [2:01:39<17:29:21,  3.31it/s]
 44%|████▍     | 163331/371472 [2:01:40<17:16:25,  3.35it/s]
 44%|████▍     | 163332/371472 [2:01:40<17:45:25,  3.26it/s]
 44%|████▍     | 163333/371472 [2:01:40<17:19:16,  3.34it/s]
 44%|████▍     | 163334/371472 [2:01:41<17:30:25,  3.30it/s]
 44%|████▍     | 163335/371472 [2:01:41<17:44:14,  3.26it/s]
 44%|████▍     | 163336/371472 [2:01:41<17:11:26,  3.36it/s]
 44%|████▍     | 163337/371472 [2:01:42<17:17:16,  3.34it/s]
 44%|████▍     | 163338/371472 [2:01:42<17:19:47,  3.34it/s]
 44%|████▍     | 163339/371472 [2:01:42<18:06:58,  3.19it/s]
 44%|████▍     | 163340/371472 [2:01:43<18:35:17,  3.11it/s]
                                                            
{'loss': 2.7753, 'learning_rate': 6.045325260186602e-07, 'epoch': 7.04}
+
 44%|████▍     | 163340/371472 [2:01:43<18:35:17,  3.11it/s]
 44%|████▍     | 163341/371472 [2:01:43<18:43:53,  3.09it/s]
 44%|████▍     | 163342/371472 [2:01:43<18:37:41,  3.10it/s]
 44%|████▍     | 163343/371472 [2:01:44<18:04:00,  3.20it/s]
 44%|████▍     | 163344/371472 [2:01:44<17:52:03,  3.24it/s]
 44%|████▍     | 163345/371472 [2:01:44<18:18:26,  3.16it/s]
 44%|████▍     | 163346/371472 [2:01:44<17:34:19,  3.29it/s]
 44%|████▍     | 163347/371472 [2:01:45<17:13:05,  3.36it/s]
 44%|████▍     | 163348/371472 [2:01:45<18:17:01,  3.16it/s]
 44%|████▍     | 163349/371472 [2:01:45<17:21:35,  3.33it/s]
 44%|████▍     | 163350/371472 [2:01:46<17:11:15,  3.36it/s]
 44%|██���█▍     | 163351/371472 [2:01:46<16:45:24,  3.45it/s]
 44%|████▍     | 163352/371472 [2:01:46<17:24:09,  3.32it/s]
 44%|████▍     | 163353/371472 [2:01:47<17:36:35,  3.28it/s]
 44%|████▍     | 163354/371472 [2:01:47<17:13:45,  3.36it/s]
 44%|████▍     | 163355/371472 [2:01:47<16:59:49,  3.40it/s]
 44%|████▍     | 163356/371472 [2:01:47<17:01:35,  3.40it/s]
 44%|████▍     | 163357/371472 [2:01:48<16:35:48,  3.48it/s]
 44%|████▍     | 163358/371472 [2:01:48<17:09:53,  3.37it/s]
 44%|████▍     | 163359/371472 [2:01:48<16:51:20,  3.43it/s]
 44%|████▍     | 163360/371472 [2:01:49<17:38:23,  3.28it/s]
                                                            
{'loss': 2.8831, 'learning_rate': 6.044840440431813e-07, 'epoch': 7.04}
+
 44%|████▍     | 163360/371472 [2:01:49<17:38:23,  3.28it/s]
 44%|████▍     | 163361/371472 [2:01:49<17:05:56,  3.38it/s]
 44%|████▍     | 163362/371472 [2:01:49<17:41:00,  3.27it/s]
 44%|████▍     | 163363/371472 [2:01:49<17:18:32,  3.34it/s]
 44%|████▍     | 163364/371472 [2:01:50<17:33:51,  3.29it/s]
 44%|████▍     | 163365/371472 [2:01:50<17:46:21,  3.25it/s]
 44%|████▍     | 163366/371472 [2:01:50<18:40:37,  3.10it/s]
 44%|████▍     | 163367/371472 [2:01:51<17:56:37,  3.22it/s]
 44%|████▍     | 163368/371472 [2:01:51<18:03:17,  3.20it/s]
 44%|████▍     | 163369/371472 [2:01:51<17:22:26,  3.33it/s]
 44%|████▍     | 163370/371472 [2:01:52<17:04:58,  3.38it/s]
 44%|████▍     | 163371/371472 [2:01:52<17:04:16,  3.39it/s]
 44%|████▍     | 163372/371472 [2:01:52<17:08:14,  3.37it/s]
 44%|████▍     | 163373/371472 [2:01:53<17:07:26,  3.38it/s]
 44%|████▍     | 163374/371472 [2:01:53<16:49:56,  3.43it/s]
 44%|████▍     | 163375/371472 [2:01:53<16:58:02,  3.41it/s]
 44%|████▍     | 163376/371472 [2:01:53<17:33:58,  3.29it/s]
 44%|████▍     | 163377/371472 [2:01:54<17:03:23,  3.39it/s]
 44%|████▍     | 163378/371472 [2:01:54<16:50:54,  3.43it/s]
 44%|████▍     | 163379/371472 [2:01:54<16:52:48,  3.42it/s]
 44%|████▍     | 163380/371472 [2:01:55<17:31:41,  3.30it/s]
                                                            
{'loss': 3.0505, 'learning_rate': 6.044355620677023e-07, 'epoch': 7.04}
+
 44%|████▍     | 163380/371472 [2:01:55<17:31:41,  3.30it/s]
 44%|████▍     | 163381/371472 [2:01:55<17:17:02,  3.34it/s]
 44%|████▍     | 163382/371472 [2:01:55<17:23:38,  3.32it/s]
 44%|████▍     | 163383/371472 [2:01:56<17:28:46,  3.31it/s]
 44%|████▍     | 163384/371472 [2:01:56<17:15:22,  3.35it/s]
 44%|████▍     | 163385/371472 [2:01:56<16:39:34,  3.47it/s]
 44%|████▍     | 163386/371472 [2:01:56<17:06:00,  3.38it/s]
 44%|████▍     | 163387/371472 [2:01:57<17:16:17,  3.35it/s]
 44%|████▍     | 163388/371472 [2:01:57<18:04:47,  3.20it/s]
 44%|████▍     | 163389/371472 [2:01:57<18:01:08,  3.21it/s]
 44%|████▍     | 163390/371472 [2:01:58<17:52:39,  3.23it/s]
 44%|████▍     | 163391/371472 [2:01:58<18:45:06,  3.08it/s]
 44%|████▍     | 163392/371472 [2:01:58<17:34:26,  3.29it/s]
 44%|████▍     | 163393/371472 [2:01:59<17:01:16,  3.40it/s]
 44%|████▍     | 163394/371472 [2:01:59<16:40:13,  3.47it/s]
 44%|████▍     | 163395/371472 [2:01:59<16:36:45,  3.48it/s]
 44%|████▍     | 163396/371472 [2:01:59<16:46:26,  3.45it/s]
 44%|████▍     | 163397/371472 [2:02:00<17:06:04,  3.38it/s]
 44%|████▍     | 163398/371472 [2:02:00<17:19:15,  3.34it/s]
 44%|████▍     | 163399/371472 [2:02:00<17:22:43,  3.33it/s]
 44%|████▍     | 163400/371472 [2:02:01<16:59:47,  3.40it/s]
                                                            
{'loss': 3.0424, 'learning_rate': 6.043870800922234e-07, 'epoch': 7.04}
+
 44%|████▍     | 163400/371472 [2:02:01<16:59:47,  3.40it/s]
 44%|████▍     | 163401/371472 [2:02:01<16:56:09,  3.41it/s]
 44%|████▍     | 163402/371472 [2:02:01<17:39:04,  3.27it/s]
 44%|████▍     | 163403/371472 [2:02:01<17:00:26,  3.40it/s]
 44%|████▍     | 163404/371472 [2:02:02<18:14:29,  3.17it/s]
 44%|████▍     | 163405/371472 [2:02:02<17:27:48,  3.31it/s]
 44%|████▍     | 163406/371472 [2:02:02<17:14:48,  3.35it/s]
 44%|████▍     | 163407/371472 [2:02:03<17:20:15,  3.33it/s]
 44%|████▍     | 163408/371472 [2:02:03<18:56:58,  3.05it/s]
 44%|████▍     | 163409/371472 [2:02:03<19:34:55,  2.95it/s]
 44%|████▍     | 163410/371472 [2:02:04<18:57:50,  3.05it/s]
 44%|████▍     | 163411/371472 [2:02:04<18:06:52,  3.19it/s]
 44%|████▍     | 163412/371472 [2:02:04<17:37:20,  3.28it/s]
 44%|████▍     | 163413/371472 [2:02:05<17:23:25,  3.32it/s]
 44%|████▍     | 163414/371472 [2:02:05<17:58:45,  3.21it/s]
 44%|████▍     | 163415/371472 [2:02:05<17:37:21,  3.28it/s]
 44%|████▍     | 163416/371472 [2:02:06<17:10:36,  3.36it/s]
 44%|████▍     | 163417/371472 [2:02:06<16:38:24,  3.47it/s]
 44%|████▍     | 163418/371472 [2:02:06<16:49:47,  3.43it/s]
 44%|████▍     | 163419/371472 [2:02:06<16:28:10,  3.51it/s]
 44%|████▍     | 163420/371472 [2:02:07<16:44:06,  3.45it/s]
                                                            
{'loss': 2.8949, 'learning_rate': 6.043385981167446e-07, 'epoch': 7.04}
+
 44%|████▍     | 163420/371472 [2:02:07<16:44:06,  3.45it/s]
 44%|████▍     | 163421/371472 [2:02:07<16:50:47,  3.43it/s]
 44%|████▍     | 163422/371472 [2:02:07<16:52:26,  3.42it/s]
 44%|████▍     | 163423/371472 [2:02:08<17:19:26,  3.34it/s]
 44%|████▍     | 163424/371472 [2:02:08<17:17:48,  3.34it/s]
 44%|████▍     | 163425/371472 [2:02:08<16:48:20,  3.44it/s]
 44%|████▍     | 163426/371472 [2:02:08<16:52:27,  3.42it/s]
 44%|████▍     | 163427/371472 [2:02:09<16:32:41,  3.49it/s]
 44%|████▍     | 163428/371472 [2:02:09<16:26:01,  3.52it/s]
 44%|████▍     | 163429/371472 [2:02:09<16:51:25,  3.43it/s]
 44%|████▍     | 163430/371472 [2:02:10<18:19:50,  3.15it/s]
 44%|████▍     | 163431/371472 [2:02:10<17:49:12,  3.24it/s]
 44%|████▍     | 163432/371472 [2:02:10<17:21:53,  3.33it/s]
 44%|████▍     | 163433/371472 [2:02:11<17:37:24,  3.28it/s]
 44%|████▍     | 163434/371472 [2:02:11<17:15:52,  3.35it/s]
 44%|████▍     | 163435/371472 [2:02:11<17:11:20,  3.36it/s]
 44%|████▍     | 163436/371472 [2:02:12<21:23:25,  2.70it/s]
 44%|████▍     | 163437/371472 [2:02:12<19:39:19,  2.94it/s]
 44%|████▍     | 163438/371472 [2:02:12<18:35:05,  3.11it/s]
 44%|████▍     | 163439/371472 [2:02:13<18:12:08,  3.17it/s]
 44%|████▍     | 163440/371472 [2:02:13<18:15:50,  3.16it/s]
                                                            
{'loss': 2.8069, 'learning_rate': 6.042901161412656e-07, 'epoch': 7.04}
+
 44%|████▍     | 163440/371472 [2:02:13<18:15:50,  3.16it/s]
 44%|████▍     | 163441/371472 [2:02:13<18:37:19,  3.10it/s]
 44%|████▍     | 163442/371472 [2:02:13<18:06:59,  3.19it/s]
 44%|████▍     | 163443/371472 [2:02:14<18:09:52,  3.18it/s]
 44%|████▍     | 163444/371472 [2:02:14<17:25:41,  3.32it/s]
 44%|████▍     | 163445/371472 [2:02:14<17:28:17,  3.31it/s]
 44%|████▍     | 163446/371472 [2:02:15<17:29:32,  3.30it/s]
 44%|████▍     | 163447/371472 [2:02:15<18:04:21,  3.20it/s]
 44%|████▍     | 163448/371472 [2:02:15<18:01:52,  3.20it/s]
 44%|████▍     | 163449/371472 [2:02:16<17:35:48,  3.28it/s]
 44%|████▍     | 163450/371472 [2:02:16<18:15:59,  3.16it/s]
 44%|████▍     | 163451/371472 [2:02:16<17:44:19,  3.26it/s]
 44%|████▍     | 163452/371472 [2:02:17<17:15:20,  3.35it/s]
 44%|████▍     | 163453/371472 [2:02:17<17:11:06,  3.36it/s]
 44%|████▍     | 163454/371472 [2:02:17<17:16:33,  3.34it/s]
 44%|████▍     | 163455/371472 [2:02:17<17:27:33,  3.31it/s]
 44%|████▍     | 163456/371472 [2:02:18<17:18:13,  3.34it/s]
 44%|████▍     | 163457/371472 [2:02:18<16:57:55,  3.41it/s]
 44%|████▍     | 163458/371472 [2:02:18<17:14:19,  3.35it/s]
 44%|████▍     | 163459/371472 [2:02:19<16:58:38,  3.40it/s]
 44%|████▍     | 163460/371472 [2:02:19<16:46:58,  3.44it/s]
                                                            
{'loss': 3.0025, 'learning_rate': 6.042416341657868e-07, 'epoch': 7.04}
+
 44%|████▍     | 163460/371472 [2:02:19<16:46:58,  3.44it/s]
 44%|████▍     | 163461/371472 [2:02:19<16:36:05,  3.48it/s]
 44%|████▍     | 163462/371472 [2:02:19<16:19:53,  3.54it/s]
 44%|████▍     | 163463/371472 [2:02:20<16:05:11,  3.59it/s]
 44%|████▍     | 163464/371472 [2:02:20<15:48:19,  3.66it/s]
 44%|████▍     | 163465/371472 [2:02:20<15:45:38,  3.67it/s]
 44%|████▍     | 163466/371472 [2:02:21<15:54:34,  3.63it/s]
 44%|████▍     | 163467/371472 [2:02:21<15:53:35,  3.64it/s]
 44%|████▍     | 163468/371472 [2:02:21<17:12:59,  3.36it/s]
 44%|████▍     | 163469/371472 [2:02:21<17:01:08,  3.39it/s]
 44%|████▍     | 163470/371472 [2:02:22<16:51:08,  3.43it/s]
 44%|████▍     | 163471/371472 [2:02:22<19:40:21,  2.94it/s]
 44%|████▍     | 163472/371472 [2:02:23<20:10:39,  2.86it/s]
 44%|████▍     | 163473/371472 [2:02:23<19:04:51,  3.03it/s]
 44%|████▍     | 163474/371472 [2:02:23<18:42:42,  3.09it/s]
 44%|████▍     | 163475/371472 [2:02:23<18:36:48,  3.10it/s]
 44%|████▍     | 163476/371472 [2:02:24<19:36:16,  2.95it/s]
 44%|████▍     | 163477/371472 [2:02:24<18:47:10,  3.08it/s]
 44%|████▍     | 163478/371472 [2:02:24<18:03:10,  3.20it/s]
 44%|████▍     | 163479/371472 [2:02:25<18:11:55,  3.17it/s]
 44%|████▍     | 163480/371472 [2:02:25<17:42:28,  3.26it/s]
                                                            
{'loss': 2.962, 'learning_rate': 6.041931521903079e-07, 'epoch': 7.04}
+
 44%|████▍     | 163480/371472 [2:02:25<17:42:28,  3.26it/s]
 44%|████▍     | 163481/371472 [2:02:25<17:16:14,  3.35it/s]
 44%|████▍     | 163482/371472 [2:02:26<16:45:03,  3.45it/s]
 44%|████▍     | 163483/371472 [2:02:26<16:39:23,  3.47it/s]
 44%|████▍     | 163484/371472 [2:02:26<16:43:09,  3.46it/s]
 44%|████▍     | 163485/371472 [2:02:27<18:05:07,  3.19it/s]
 44%|████▍     | 163486/371472 [2:02:27<17:45:07,  3.25it/s]
 44%|████▍     | 163487/371472 [2:02:27<17:23:42,  3.32it/s]
 44%|████▍     | 163488/371472 [2:02:27<17:29:56,  3.30it/s]
 44%|████▍     | 163489/371472 [2:02:28<19:04:48,  3.03it/s]
 44%|████▍     | 163490/371472 [2:02:28<17:59:25,  3.21it/s]
 44%|████▍     | 163491/371472 [2:02:28<17:22:42,  3.32it/s]
 44%|████▍     | 163492/371472 [2:02:29<16:56:18,  3.41it/s]
 44%|████▍     | 163493/371472 [2:02:29<16:48:11,  3.44it/s]
 44%|████▍     | 163494/371472 [2:02:29<16:47:52,  3.44it/s]
 44%|████▍     | 163495/371472 [2:02:29<17:09:14,  3.37it/s]
 44%|████▍     | 163496/371472 [2:02:30<17:56:16,  3.22it/s]
 44%|████▍     | 163497/371472 [2:02:30<18:00:43,  3.21it/s]
 44%|████▍     | 163498/371472 [2:02:30<18:40:15,  3.09it/s]
 44%|████▍     | 163499/371472 [2:02:31<17:49:19,  3.24it/s]
 44%|████▍     | 163500/371472 [2:02:31<17:16:25,  3.34it/s]
                                                            
{'loss': 3.0152, 'learning_rate': 6.04144670214829e-07, 'epoch': 7.04}
+
 44%|████▍     | 163500/371472 [2:02:31<17:16:25,  3.34it/s]
 44%|████▍     | 163501/371472 [2:02:31<17:39:04,  3.27it/s]
 44%|████▍     | 163502/371472 [2:02:32<17:37:48,  3.28it/s]
 44%|████▍     | 163503/371472 [2:02:32<17:50:17,  3.24it/s]
 44%|████▍     | 163504/371472 [2:02:32<18:26:14,  3.13it/s]
 44%|████▍     | 163505/371472 [2:02:33<18:11:05,  3.18it/s]
 44%|████▍     | 163506/371472 [2:02:33<17:16:53,  3.34it/s]
 44%|████▍     | 163507/371472 [2:02:33<17:12:24,  3.36it/s]
 44%|████▍     | 163508/371472 [2:02:33<16:49:10,  3.43it/s]
 44%|████▍     | 163509/371472 [2:02:34<16:29:39,  3.50it/s]
 44%|████▍     | 163510/371472 [2:02:34<16:43:26,  3.45it/s]
 44%|████▍     | 163511/371472 [2:02:34<16:36:02,  3.48it/s]
 44%|████▍     | 163512/371472 [2:02:35<17:07:21,  3.37it/s]
 44%|████▍     | 163513/371472 [2:02:35<17:07:37,  3.37it/s]
 44%|████▍     | 163514/371472 [2:02:35<17:56:47,  3.22it/s]
 44%|████▍     | 163515/371472 [2:02:36<17:35:03,  3.29it/s]
 44%|████▍     | 163516/371472 [2:02:36<17:06:20,  3.38it/s]
 44%|████▍     | 163517/371472 [2:02:36<17:08:59,  3.37it/s]
 44%|████▍     | 163518/371472 [2:02:37<18:25:17,  3.14it/s]
 44%|████▍     | 163519/371472 [2:02:37<17:33:40,  3.29it/s]
 44%|████▍     | 163520/371472 [2:02:37<17:25:14,  3.32it/s]
                                                            
{'loss': 2.8635, 'learning_rate': 6.040961882393501e-07, 'epoch': 7.04}
+
 44%|████▍     | 163520/371472 [2:02:37<17:25:14,  3.32it/s]
 44%|████▍     | 163521/371472 [2:02:37<17:56:04,  3.22it/s]
 44%|████▍     | 163522/371472 [2:02:38<17:16:14,  3.34it/s]
 44%|████▍     | 163523/371472 [2:02:38<17:06:54,  3.38it/s]
 44%|████▍     | 163524/371472 [2:02:38<17:01:14,  3.39it/s]
 44%|████▍     | 163525/371472 [2:02:39<16:48:24,  3.44it/s]
 44%|████▍     | 163526/371472 [2:02:39<17:49:17,  3.24it/s]
 44%|████▍     | 163527/371472 [2:02:39<17:30:14,  3.30it/s]
 44%|████▍     | 163528/371472 [2:02:39<17:02:34,  3.39it/s]
 44%|████▍     | 163529/371472 [2:02:40<17:02:52,  3.39it/s]
 44%|████▍     | 163530/371472 [2:02:40<16:49:23,  3.43it/s]
 44%|████▍     | 163531/371472 [2:02:40<17:49:03,  3.24it/s]
 44%|████▍     | 163532/371472 [2:02:41<18:20:49,  3.15it/s]
 44%|████▍     | 163533/371472 [2:02:41<17:48:03,  3.24it/s]
 44%|████▍     | 163534/371472 [2:02:41<17:44:04,  3.26it/s]
 44%|████▍     | 163535/371472 [2:02:42<17:14:46,  3.35it/s]
 44%|████▍     | 163536/371472 [2:02:42<16:37:41,  3.47it/s]
 44%|████▍     | 163537/371472 [2:02:42<16:29:26,  3.50it/s]
 44%|████▍     | 163538/371472 [2:02:42<16:38:01,  3.47it/s]
 44%|████▍     | 163539/371472 [2:02:43<16:42:30,  3.46it/s]
 44%|████▍     | 163540/371472 [2:02:43<16:56:17,  3.41it/s]
                                                            
{'loss': 2.9724, 'learning_rate': 6.040477062638712e-07, 'epoch': 7.04}
+
 44%|████▍     | 163540/371472 [2:02:43<16:56:17,  3.41it/s]
 44%|████▍     | 163541/371472 [2:02:43<16:54:04,  3.42it/s]
 44%|████▍     | 163542/371472 [2:02:44<18:04:10,  3.20it/s]
 44%|████▍     | 163543/371472 [2:02:44<17:37:19,  3.28it/s]
 44%|████▍     | 163544/371472 [2:02:44<18:22:19,  3.14it/s]
 44%|████▍     | 163545/371472 [2:02:45<18:18:21,  3.16it/s]
 44%|████▍     | 163546/371472 [2:02:45<18:20:13,  3.15it/s]
 44%|████▍     | 163547/371472 [2:02:45<18:46:49,  3.08it/s]
 44%|████▍     | 163548/371472 [2:02:46<18:00:32,  3.21it/s]
 44%|████▍     | 163549/371472 [2:02:46<17:29:19,  3.30it/s]
 44%|████▍     | 163550/371472 [2:02:46<18:08:57,  3.18it/s]
 44%|████▍     | 163551/371472 [2:02:47<18:04:17,  3.20it/s]
 44%|████▍     | 163552/371472 [2:02:47<18:17:49,  3.16it/s]
 44%|████▍     | 163553/371472 [2:02:47<18:12:03,  3.17it/s]
 44%|████▍     | 163554/371472 [2:02:47<17:54:07,  3.23it/s]
 44%|████▍     | 163555/371472 [2:02:48<18:03:34,  3.20it/s]
 44%|████▍     | 163556/371472 [2:02:48<17:40:46,  3.27it/s]
 44%|████▍     | 163557/371472 [2:02:48<17:17:22,  3.34it/s]
 44%|████▍     | 163558/371472 [2:02:49<18:07:24,  3.19it/s]
 44%|████▍     | 163559/371472 [2:02:49<17:45:46,  3.25it/s]
 44%|████▍     | 163560/371472 [2:02:49<17:22:39,  3.32it/s]
                                                            
{'loss': 2.9637, 'learning_rate': 6.039992242883923e-07, 'epoch': 7.04}
+
 44%|████▍     | 163560/371472 [2:02:49<17:22:39,  3.32it/s]
 44%|████▍     | 163561/371472 [2:02:50<17:12:00,  3.36it/s]
 44%|████▍     | 163562/371472 [2:02:50<17:55:26,  3.22it/s]
 44%|████▍     | 163563/371472 [2:02:50<18:17:42,  3.16it/s]
 44%|████▍     | 163564/371472 [2:02:51<17:43:00,  3.26it/s]
 44%|████▍     | 163565/371472 [2:02:51<17:26:50,  3.31it/s]
 44%|████▍     | 163566/371472 [2:02:51<17:05:01,  3.38it/s]
 44%|████▍     | 163567/371472 [2:02:51<17:32:28,  3.29it/s]
 44%|████▍     | 163568/371472 [2:02:52<17:02:59,  3.39it/s]
 44%|████▍     | 163569/371472 [2:02:52<17:01:17,  3.39it/s]
 44%|████▍     | 163570/371472 [2:02:52<17:51:31,  3.23it/s]
 44%|████▍     | 163571/371472 [2:02:53<18:00:40,  3.21it/s]
 44%|████▍     | 163572/371472 [2:02:53<17:09:58,  3.36it/s]
 44%|████▍     | 163573/371472 [2:02:53<18:30:47,  3.12it/s]
 44%|████▍     | 163574/371472 [2:02:54<18:06:16,  3.19it/s]
 44%|████▍     | 163575/371472 [2:02:54<18:02:36,  3.20it/s]
 44%|████▍     | 163576/371472 [2:02:54<17:45:25,  3.25it/s]
 44%|████▍     | 163577/371472 [2:02:54<16:54:44,  3.41it/s]
 44%|████▍     | 163578/371472 [2:02:55<16:54:03,  3.42it/s]
 44%|████▍     | 163579/371472 [2:02:55<16:49:15,  3.43it/s]
 44%|████▍     | 163580/371472 [2:02:55<16:42:47,  3.46it/s]
                                                            
{'loss': 3.1147, 'learning_rate': 6.039507423129134e-07, 'epoch': 7.05}
+
 44%|████▍     | 163580/371472 [2:02:55<16:42:47,  3.46it/s]
 44%|████▍     | 163581/371472 [2:02:56<16:50:15,  3.43it/s]
 44%|████▍     | 163582/371472 [2:02:56<16:38:46,  3.47it/s]
 44%|████▍     | 163583/371472 [2:02:56<16:29:22,  3.50it/s]
 44%|████▍     | 163584/371472 [2:02:56<16:37:51,  3.47it/s]
 44%|████▍     | 163585/371472 [2:02:57<17:08:41,  3.37it/s]
 44%|████▍     | 163586/371472 [2:02:57<16:55:52,  3.41it/s]
 44%|████▍     | 163587/371472 [2:02:57<17:13:38,  3.35it/s]
 44%|████▍     | 163588/371472 [2:02:58<18:12:41,  3.17it/s]
 44%|████▍     | 163589/371472 [2:02:58<17:42:09,  3.26it/s]
 44%|████▍     | 163590/371472 [2:02:58<17:16:01,  3.34it/s]
 44%|████▍     | 163591/371472 [2:02:59<17:35:52,  3.28it/s]
 44%|████▍     | 163592/371472 [2:02:59<16:59:40,  3.40it/s]
 44%|████▍     | 163593/371472 [2:02:59<16:44:37,  3.45it/s]
 44%|████▍     | 163594/371472 [2:02:59<16:44:21,  3.45it/s]
 44%|████▍     | 163595/371472 [2:03:00<16:34:34,  3.48it/s]
 44%|████▍     | 163596/371472 [2:03:00<16:30:30,  3.50it/s]
 44%|████▍     | 163597/371472 [2:03:00<16:53:59,  3.42it/s]
 44%|████▍     | 163598/371472 [2:03:01<17:39:02,  3.27it/s]
 44%|████▍     | 163599/371472 [2:03:01<17:56:22,  3.22it/s]
 44%|████▍     | 163600/371472 [2:03:01<17:41:05,  3.27it/s]
                                                            
{'loss': 3.136, 'learning_rate': 6.039022603374346e-07, 'epoch': 7.05}
+
 44%|████▍     | 163600/371472 [2:03:01<17:41:05,  3.27it/s]
 44%|████▍     | 163601/371472 [2:03:02<17:10:40,  3.36it/s]
 44%|████▍     | 163602/371472 [2:03:02<18:59:53,  3.04it/s]
 44%|████▍     | 163603/371472 [2:03:02<18:07:29,  3.19it/s]
 44%|████▍     | 163604/371472 [2:03:03<18:50:31,  3.06it/s]
 44%|████▍     | 163605/371472 [2:03:03<18:58:38,  3.04it/s]
 44%|████▍     | 163606/371472 [2:03:03<18:18:37,  3.15it/s]
 44%|████▍     | 163607/371472 [2:03:04<18:00:32,  3.21it/s]
 44%|████▍     | 163608/371472 [2:03:04<18:02:33,  3.20it/s]
 44%|████▍     | 163609/371472 [2:03:04<17:32:32,  3.29it/s]
 44%|████▍     | 163610/371472 [2:03:04<18:57:20,  3.05it/s]
 44%|████▍     | 163611/371472 [2:03:05<18:05:23,  3.19it/s]
 44%|████▍     | 163612/371472 [2:03:05<17:54:51,  3.22it/s]
 44%|████▍     | 163613/371472 [2:03:05<19:23:32,  2.98it/s]
 44%|████▍     | 163614/371472 [2:03:06<18:37:17,  3.10it/s]
 44%|████▍     | 163615/371472 [2:03:06<17:44:05,  3.26it/s]
 44%|████▍     | 163616/371472 [2:03:06<17:11:49,  3.36it/s]
 44%|████▍     | 163617/371472 [2:03:07<17:00:35,  3.39it/s]
 44%|████▍     | 163618/371472 [2:03:07<16:44:51,  3.45it/s]
 44%|████▍     | 163619/371472 [2:03:07<16:47:01,  3.44it/s]
 44%|████▍     | 163620/371472 [2:03:07<17:10:02,  3.36it/s]
                                                            
{'loss': 2.9028, 'learning_rate': 6.038537783619557e-07, 'epoch': 7.05}
+
 44%|████▍     | 163620/371472 [2:03:07<17:10:02,  3.36it/s]
 44%|████▍     | 163621/371472 [2:03:08<16:40:36,  3.46it/s]
 44%|████▍     | 163622/371472 [2:03:08<16:32:33,  3.49it/s]
 44%|████▍     | 163623/371472 [2:03:08<16:44:07,  3.45it/s]
 44%|████▍     | 163624/371472 [2:03:09<16:45:38,  3.44it/s]
 44%|████▍     | 163625/371472 [2:03:09<16:34:02,  3.48it/s]
 44%|████▍     | 163626/371472 [2:03:09<16:29:03,  3.50it/s]
 44%|████▍     | 163627/371472 [2:03:09<16:44:33,  3.45it/s]
 44%|████▍     | 163628/371472 [2:03:10<16:40:49,  3.46it/s]
 44%|████▍     | 163629/371472 [2:03:10<16:49:25,  3.43it/s]
 44%|████▍     | 163630/371472 [2:03:10<16:49:08,  3.43it/s]
 44%|████▍     | 163631/371472 [2:03:11<16:31:00,  3.50it/s]
 44%|████▍     | 163632/371472 [2:03:11<16:18:51,  3.54it/s]
 44%|████▍     | 163633/371472 [2:03:11<16:27:14,  3.51it/s]
 44%|████▍     | 163634/371472 [2:03:11<16:00:51,  3.61it/s]
 44%|████▍     | 163635/371472 [2:03:12<16:29:01,  3.50it/s]
 44%|████▍     | 163636/371472 [2:03:12<17:13:40,  3.35it/s]
 44%|████▍     | 163637/371472 [2:03:12<16:46:03,  3.44it/s]
 44%|████▍     | 163638/371472 [2:03:13<16:36:40,  3.48it/s]
 44%|████▍     | 163639/371472 [2:03:13<16:31:04,  3.50it/s]
 44%|████▍     | 163640/371472 [2:03:13<19:08:26,  3.02it/s]
                                                            
{'loss': 3.1695, 'learning_rate': 6.038052963864767e-07, 'epoch': 7.05}
+
 44%|████▍     | 163640/371472 [2:03:13<19:08:26,  3.02it/s]
 44%|████▍     | 163641/371472 [2:03:14<18:22:15,  3.14it/s]
 44%|████▍     | 163642/371472 [2:03:14<17:47:18,  3.25it/s]
 44%|████▍     | 163643/371472 [2:03:14<17:25:45,  3.31it/s]
 44%|████▍     | 163644/371472 [2:03:14<16:52:14,  3.42it/s]
 44%|████▍     | 163645/371472 [2:03:15<16:58:48,  3.40it/s]
 44%|████▍     | 163646/371472 [2:03:15<16:36:52,  3.47it/s]
 44%|████▍     | 163647/371472 [2:03:15<17:04:29,  3.38it/s]
 44%|████▍     | 163648/371472 [2:03:16<17:51:00,  3.23it/s]
 44%|████▍     | 163649/371472 [2:03:16<17:31:12,  3.29it/s]
 44%|████▍     | 163650/371472 [2:03:16<17:31:59,  3.29it/s]
 44%|████▍     | 163651/371472 [2:03:17<18:09:45,  3.18it/s]
 44%|████▍     | 163652/371472 [2:03:17<18:00:34,  3.21it/s]
 44%|████▍     | 163653/371472 [2:03:17<17:20:50,  3.33it/s]
 44%|████▍     | 163654/371472 [2:03:18<17:47:35,  3.24it/s]
 44%|████▍     | 163655/371472 [2:03:18<18:12:18,  3.17it/s]
 44%|████▍     | 163656/371472 [2:03:18<18:17:24,  3.16it/s]
 44%|████▍     | 163657/371472 [2:03:18<17:38:36,  3.27it/s]
 44%|████▍     | 163658/371472 [2:03:19<17:06:34,  3.37it/s]
 44%|████▍     | 163659/371472 [2:03:19<17:32:48,  3.29it/s]
 44%|████▍     | 163660/371472 [2:03:19<17:14:33,  3.35it/s]
                                                            
{'loss': 2.964, 'learning_rate': 6.037568144109978e-07, 'epoch': 7.05}
+
 44%|████▍     | 163660/371472 [2:03:19<17:14:33,  3.35it/s]
 44%|████▍     | 163661/371472 [2:03:20<18:43:45,  3.08it/s]
 44%|████▍     | 163662/371472 [2:03:20<17:54:53,  3.22it/s]
 44%|████▍     | 163663/371472 [2:03:20<17:52:20,  3.23it/s]
 44%|████▍     | 163664/371472 [2:03:21<17:55:24,  3.22it/s]
 44%|████▍     | 163665/371472 [2:03:21<17:32:19,  3.29it/s]
 44%|████▍     | 163666/371472 [2:03:21<17:25:34,  3.31it/s]
 44%|████▍     | 163667/371472 [2:03:22<18:53:17,  3.06it/s]
 44%|████▍     | 163668/371472 [2:03:22<17:59:22,  3.21it/s]
 44%|████▍     | 163669/371472 [2:03:22<17:26:15,  3.31it/s]
 44%|████▍     | 163670/371472 [2:03:22<16:47:29,  3.44it/s]
 44%|████▍     | 163671/371472 [2:03:23<16:28:42,  3.50it/s]
 44%|████▍     | 163672/371472 [2:03:23<16:56:54,  3.41it/s]
 44%|████▍     | 163673/371472 [2:03:23<17:05:21,  3.38it/s]
 44%|████▍     | 163674/371472 [2:03:24<16:57:21,  3.40it/s]
 44%|████▍     | 163675/371472 [2:03:24<16:54:43,  3.41it/s]
 44%|████▍     | 163676/371472 [2:03:24<17:03:36,  3.38it/s]
 44%|████▍     | 163677/371472 [2:03:25<17:24:43,  3.31it/s]
 44%|████▍     | 163678/371472 [2:03:25<17:10:21,  3.36it/s]
 44%|████▍     | 163679/371472 [2:03:25<17:55:18,  3.22it/s]
 44%|████▍     | 163680/371472 [2:03:26<19:25:00,  2.97it/s]
                                                            
{'loss': 2.9293, 'learning_rate': 6.03708332435519e-07, 'epoch': 7.05}
+
 44%|████▍     | 163680/371472 [2:03:26<19:25:00,  2.97it/s]
 44%|████▍     | 163681/371472 [2:03:26<18:46:24,  3.07it/s]
 44%|████▍     | 163682/371472 [2:03:26<18:36:52,  3.10it/s]
 44%|████▍     | 163683/371472 [2:03:26<18:12:50,  3.17it/s]
 44%|████▍     | 163684/371472 [2:03:27<17:28:56,  3.30it/s]
 44%|████▍     | 163685/371472 [2:03:27<17:36:46,  3.28it/s]
 44%|████▍     | 163686/371472 [2:03:27<17:34:12,  3.29it/s]
 44%|████▍     | 163687/371472 [2:03:28<17:52:16,  3.23it/s]
 44%|████▍     | 163688/371472 [2:03:28<17:31:50,  3.29it/s]
 44%|████▍     | 163689/371472 [2:03:28<17:14:45,  3.35it/s]
 44%|████▍     | 163690/371472 [2:03:29<17:16:00,  3.34it/s]
 44%|████▍     | 163691/371472 [2:03:29<17:03:52,  3.38it/s]
 44%|████▍     | 163692/371472 [2:03:29<16:55:42,  3.41it/s]
 44%|████▍     | 163693/371472 [2:03:29<17:01:54,  3.39it/s]
 44%|████▍     | 163694/371472 [2:03:30<17:13:51,  3.35it/s]
 44%|████▍     | 163695/371472 [2:03:30<17:34:22,  3.28it/s]
 44%|████▍     | 163696/371472 [2:03:30<17:27:06,  3.31it/s]
 44%|████▍     | 163697/371472 [2:03:31<17:40:45,  3.26it/s]
 44%|████▍     | 163698/371472 [2:03:31<18:35:06,  3.11it/s]
 44%|████▍     | 163699/371472 [2:03:31<17:55:58,  3.22it/s]
 44%|████▍     | 163700/371472 [2:03:32<18:28:32,  3.12it/s]
                                                            
{'loss': 2.844, 'learning_rate': 6.0365985046004e-07, 'epoch': 7.05}
+
 44%|████▍     | 163700/371472 [2:03:32<18:28:32,  3.12it/s]
 44%|████▍     | 163701/371472 [2:03:32<18:07:06,  3.19it/s]
 44%|████▍     | 163702/371472 [2:03:32<17:43:10,  3.26it/s]
 44%|████▍     | 163703/371472 [2:03:33<17:12:12,  3.35it/s]
 44%|████▍     | 163704/371472 [2:03:33<16:53:10,  3.42it/s]
 44%|████▍     | 163705/371472 [2:03:33<16:49:24,  3.43it/s]
 44%|████▍     | 163706/371472 [2:03:33<17:38:02,  3.27it/s]
 44%|████▍     | 163707/371472 [2:03:34<17:39:10,  3.27it/s]
 44%|████▍     | 163708/371472 [2:03:34<18:43:19,  3.08it/s]
 44%|████▍     | 163709/371472 [2:03:34<18:41:45,  3.09it/s]
 44%|████▍     | 163710/371472 [2:03:35<18:06:21,  3.19it/s]
 44%|████▍     | 163711/371472 [2:03:35<18:08:21,  3.18it/s]
 44%|████▍     | 163712/371472 [2:03:35<17:54:17,  3.22it/s]
 44%|████▍     | 163713/371472 [2:03:36<17:50:13,  3.24it/s]
 44%|████▍     | 163714/371472 [2:03:36<17:39:43,  3.27it/s]
 44%|████▍     | 163715/371472 [2:03:36<17:01:44,  3.39it/s]
 44%|████▍     | 163716/371472 [2:03:36<16:56:33,  3.41it/s]
 44%|████▍     | 163717/371472 [2:03:37<16:39:02,  3.47it/s]
 44%|████▍     | 163718/371472 [2:03:37<16:53:52,  3.42it/s]
 44%|████▍     | 163719/371472 [2:03:37<17:46:30,  3.25it/s]
 44%|████▍     | 163720/371472 [2:03:38<17:16:23,  3.34it/s]
                                                            
{'loss': 2.9406, 'learning_rate': 6.036113684845612e-07, 'epoch': 7.05}
+
 44%|████▍     | 163720/371472 [2:03:38<17:16:23,  3.34it/s]
 44%|████▍     | 163721/371472 [2:03:38<17:32:18,  3.29it/s]
 44%|████▍     | 163722/371472 [2:03:38<17:14:18,  3.35it/s]
 44%|████▍     | 163723/371472 [2:03:39<17:09:01,  3.36it/s]
 44%|████▍     | 163724/371472 [2:03:39<16:53:11,  3.42it/s]
 44%|████▍     | 163725/371472 [2:03:39<16:52:19,  3.42it/s]
 44%|████▍     | 163726/371472 [2:03:39<16:53:06,  3.42it/s]
 44%|████▍     | 163727/371472 [2:03:40<18:19:32,  3.15it/s]
 44%|████▍     | 163728/371472 [2:03:40<17:47:25,  3.24it/s]
 44%|████▍     | 163729/371472 [2:03:40<17:43:07,  3.26it/s]
 44%|████▍     | 163730/371472 [2:03:41<21:00:27,  2.75it/s]
 44%|████▍     | 163731/371472 [2:03:41<20:40:00,  2.79it/s]
 44%|████▍     | 163732/371472 [2:03:42<19:46:35,  2.92it/s]
 44%|████▍     | 163733/371472 [2:03:42<19:02:25,  3.03it/s]
 44%|████▍     | 163734/371472 [2:03:42<18:19:43,  3.15it/s]
 44%|████▍     | 163735/371472 [2:03:42<17:49:34,  3.24it/s]
 44%|████▍     | 163736/371472 [2:03:43<17:57:23,  3.21it/s]
 44%|████▍     | 163737/371472 [2:03:43<17:41:25,  3.26it/s]
 44%|████▍     | 163738/371472 [2:03:43<17:38:44,  3.27it/s]
 44%|████▍     | 163739/371472 [2:03:44<17:25:16,  3.31it/s]
 44%|████▍     | 163740/371472 [2:03:44<17:35:18,  3.28it/s]
                                                            
{'loss': 2.8727, 'learning_rate': 6.035628865090823e-07, 'epoch': 7.05}
+
 44%|████▍     | 163740/371472 [2:03:44<17:35:18,  3.28it/s]
 44%|████▍     | 163741/371472 [2:03:44<17:38:19,  3.27it/s]
 44%|████▍     | 163742/371472 [2:03:45<19:10:36,  3.01it/s]
 44%|████▍     | 163743/371472 [2:03:45<18:56:00,  3.05it/s]
 44%|████▍     | 163744/371472 [2:03:45<18:21:20,  3.14it/s]
 44%|████▍     | 163745/371472 [2:03:46<17:59:14,  3.21it/s]
 44%|████▍     | 163746/371472 [2:03:46<17:26:14,  3.31it/s]
 44%|████▍     | 163747/371472 [2:03:46<17:08:58,  3.36it/s]
 44%|████▍     | 163748/371472 [2:03:46<16:49:57,  3.43it/s]
 44%|████▍     | 163749/371472 [2:03:47<16:54:43,  3.41it/s]
 44%|████▍     | 163750/371472 [2:03:47<17:26:21,  3.31it/s]
 44%|████▍     | 163751/371472 [2:03:47<18:15:50,  3.16it/s]
 44%|████▍     | 163752/371472 [2:03:48<18:21:28,  3.14it/s]
 44%|████▍     | 163753/371472 [2:03:48<17:38:20,  3.27it/s]
 44%|████▍     | 163754/371472 [2:03:48<18:14:45,  3.16it/s]
 44%|████▍     | 163755/371472 [2:03:49<17:41:53,  3.26it/s]
 44%|████▍     | 163756/371472 [2:03:49<17:39:26,  3.27it/s]
 44%|████▍     | 163757/371472 [2:03:49<17:33:54,  3.28it/s]
 44%|████▍     | 163758/371472 [2:03:50<17:42:57,  3.26it/s]
 44%|████▍     | 163759/371472 [2:03:50<18:24:17,  3.13it/s]
 44%|████▍     | 163760/371472 [2:03:50<18:30:07,  3.12it/s]
                                                            
{'loss': 3.0454, 'learning_rate': 6.035144045336032e-07, 'epoch': 7.05}
+
 44%|████▍     | 163760/371472 [2:03:50<18:30:07,  3.12it/s]
 44%|████▍     | 163761/371472 [2:03:51<18:20:06,  3.15it/s]
 44%|████▍     | 163762/371472 [2:03:51<18:13:48,  3.16it/s]
 44%|████▍     | 163763/371472 [2:03:51<17:58:00,  3.21it/s]
 44%|████▍     | 163764/371472 [2:03:51<17:53:32,  3.22it/s]
 44%|████▍     | 163765/371472 [2:03:52<17:12:49,  3.35it/s]
 44%|████▍     | 163766/371472 [2:03:52<17:02:01,  3.39it/s]
 44%|████▍     | 163767/371472 [2:03:52<17:17:15,  3.34it/s]
 44%|████▍     | 163768/371472 [2:03:53<17:45:53,  3.25it/s]
 44%|████▍     | 163769/371472 [2:03:53<18:24:26,  3.13it/s]
 44%|████▍     | 163770/371472 [2:03:53<17:53:05,  3.23it/s]
 44%|████▍     | 163771/371472 [2:03:54<17:27:22,  3.31it/s]
 44%|████▍     | 163772/371472 [2:03:54<17:26:12,  3.31it/s]
 44%|████▍     | 163773/371472 [2:03:54<17:12:50,  3.35it/s]
 44%|████▍     | 163774/371472 [2:03:54<16:44:21,  3.45it/s]
 44%|████▍     | 163775/371472 [2:03:55<17:04:04,  3.38it/s]
 44%|████▍     | 163776/371472 [2:03:55<17:06:14,  3.37it/s]
 44%|████▍     | 163777/371472 [2:03:55<17:16:27,  3.34it/s]
 44%|████▍     | 163778/371472 [2:03:56<16:49:28,  3.43it/s]
 44%|████▍     | 163779/371472 [2:03:56<17:07:15,  3.37it/s]
 44%|████▍     | 163780/371472 [2:03:56<20:16:09,  2.85it/s]
                                                            
{'loss': 2.9611, 'learning_rate': 6.034659225581244e-07, 'epoch': 7.05}
+
 44%|████▍     | 163780/371472 [2:03:56<20:16:09,  2.85it/s]
 44%|████▍     | 163781/371472 [2:03:57<19:38:40,  2.94it/s]
 44%|████▍     | 163782/371472 [2:03:57<19:31:32,  2.95it/s]
 44%|████▍     | 163783/371472 [2:03:57<20:01:21,  2.88it/s]
 44%|████▍     | 163784/371472 [2:03:58<18:51:47,  3.06it/s]
 44%|████▍     | 163785/371472 [2:03:58<18:45:31,  3.08it/s]
 44%|████▍     | 163786/371472 [2:03:58<18:37:33,  3.10it/s]
 44%|████▍     | 163787/371472 [2:03:59<18:01:09,  3.20it/s]
 44%|████▍     | 163788/371472 [2:03:59<21:24:52,  2.69it/s]
 44%|████▍     | 163789/371472 [2:03:59<20:35:36,  2.80it/s]
 44%|████▍     | 163790/371472 [2:04:00<20:06:04,  2.87it/s]
 44%|████▍     | 163791/371472 [2:04:00<19:07:21,  3.02it/s]
 44%|████▍     | 163792/371472 [2:04:00<18:43:16,  3.08it/s]
 44%|████▍     | 163793/371472 [2:04:01<18:30:52,  3.12it/s]
 44%|████▍     | 163794/371472 [2:04:01<18:53:44,  3.05it/s]
 44%|████▍     | 163795/371472 [2:04:01<19:13:37,  3.00it/s]
 44%|████▍     | 163796/371472 [2:04:02<19:44:31,  2.92it/s]
 44%|████▍     | 163797/371472 [2:04:02<18:43:08,  3.08it/s]
 44%|████▍     | 163798/371472 [2:04:02<18:01:41,  3.20it/s]
 44%|████▍     | 163799/371472 [2:04:03<17:44:38,  3.25it/s]
 44%|████▍     | 163800/371472 [2:04:03<17:01:10,  3.39it/s]
                                                            
{'loss': 3.0298, 'learning_rate': 6.034174405826456e-07, 'epoch': 7.06}
+
 44%|████▍     | 163800/371472 [2:04:03<17:01:10,  3.39it/s]
 44%|████▍     | 163801/371472 [2:04:03<17:05:09,  3.38it/s]
 44%|████▍     | 163802/371472 [2:04:03<16:48:36,  3.43it/s]
 44%|████▍     | 163803/371472 [2:04:04<17:44:09,  3.25it/s]
 44%|████▍     | 163804/371472 [2:04:04<17:16:24,  3.34it/s]
 44%|████▍     | 163805/371472 [2:04:04<16:57:30,  3.40it/s]
 44%|████▍     | 163806/371472 [2:04:05<16:33:27,  3.48it/s]
 44%|████▍     | 163807/371472 [2:04:05<16:37:55,  3.47it/s]
 44%|████▍     | 163808/371472 [2:04:05<17:18:26,  3.33it/s]
 44%|████▍     | 163809/371472 [2:04:06<17:11:22,  3.36it/s]
 44%|████▍     | 163810/371472 [2:04:06<16:57:00,  3.40it/s]
 44%|████▍     | 163811/371472 [2:04:06<17:05:13,  3.38it/s]
 44%|████▍     | 163812/371472 [2:04:06<17:12:26,  3.35it/s]
 44%|████▍     | 163813/371472 [2:04:07<17:01:57,  3.39it/s]
 44%|████▍     | 163814/371472 [2:04:07<16:45:26,  3.44it/s]
 44%|████▍     | 163815/371472 [2:04:07<17:06:00,  3.37it/s]
 44%|████▍     | 163816/371472 [2:04:08<17:08:07,  3.37it/s]
 44%|████▍     | 163817/371472 [2:04:08<17:25:25,  3.31it/s]
 44%|████▍     | 163818/371472 [2:04:08<17:34:25,  3.28it/s]
 44%|████▍     | 163819/371472 [2:04:09<17:07:52,  3.37it/s]
 44%|████▍     | 163820/371472 [2:04:09<17:01:13,  3.39it/s]
                                                            
{'loss': 2.9875, 'learning_rate': 6.033689586071667e-07, 'epoch': 7.06}
+
 44%|████▍     | 163820/371472 [2:04:09<17:01:13,  3.39it/s]
 44%|████▍     | 163821/371472 [2:04:09<17:38:42,  3.27it/s]
 44%|████▍     | 163822/371472 [2:04:09<17:59:39,  3.21it/s]
 44%|████▍     | 163823/371472 [2:04:10<17:30:03,  3.30it/s]
 44%|████▍     | 163824/371472 [2:04:10<17:36:09,  3.28it/s]
 44%|████▍     | 163825/371472 [2:04:10<16:58:46,  3.40it/s]
 44%|████▍     | 163826/371472 [2:04:11<17:25:59,  3.31it/s]
 44%|████▍     | 163827/371472 [2:04:11<17:25:00,  3.31it/s]
 44%|████▍     | 163828/371472 [2:04:11<17:29:25,  3.30it/s]
 44%|████▍     | 163829/371472 [2:04:12<18:03:55,  3.19it/s]
 44%|████▍     | 163830/371472 [2:04:12<17:57:46,  3.21it/s]
 44%|████▍     | 163831/371472 [2:04:12<17:21:03,  3.32it/s]
 44%|████▍     | 163832/371472 [2:04:12<17:30:12,  3.30it/s]
 44%|████▍     | 163833/371472 [2:04:13<17:37:08,  3.27it/s]
 44%|████▍     | 163834/371472 [2:04:13<17:02:21,  3.38it/s]
 44%|████▍     | 163835/371472 [2:04:13<17:16:42,  3.34it/s]
 44%|████▍     | 163836/371472 [2:04:14<16:39:59,  3.46it/s]
 44%|████▍     | 163837/371472 [2:04:14<17:15:38,  3.34it/s]
 44%|████▍     | 163838/371472 [2:04:14<17:27:43,  3.30it/s]
 44%|████▍     | 163839/371472 [2:04:15<17:50:20,  3.23it/s]
 44%|████▍     | 163840/371472 [2:04:15<17:37:45,  3.27it/s]
                                                            
{'loss': 2.964, 'learning_rate': 6.033204766316878e-07, 'epoch': 7.06}
+
 44%|████▍     | 163840/371472 [2:04:15<17:37:45,  3.27it/s]
 44%|████▍     | 163841/371472 [2:04:15<17:26:43,  3.31it/s]
 44%|████▍     | 163842/371472 [2:04:15<17:03:37,  3.38it/s]
 44%|████▍     | 163843/371472 [2:04:16<17:22:31,  3.32it/s]
 44%|████▍     | 163844/371472 [2:04:16<17:08:21,  3.37it/s]
 44%|████▍     | 163845/371472 [2:04:16<17:17:48,  3.33it/s]
 44%|████▍     | 163846/371472 [2:04:17<17:36:35,  3.28it/s]
 44%|████▍     | 163847/371472 [2:04:17<17:16:47,  3.34it/s]
 44%|████▍     | 163848/371472 [2:04:17<17:38:31,  3.27it/s]
 44%|████▍     | 163849/371472 [2:04:18<17:51:13,  3.23it/s]
 44%|████▍     | 163850/371472 [2:04:18<17:40:12,  3.26it/s]
 44%|████▍     | 163851/371472 [2:04:18<17:24:20,  3.31it/s]
 44%|████▍     | 163852/371472 [2:04:19<17:56:44,  3.21it/s]
 44%|████▍     | 163853/371472 [2:04:19<18:13:41,  3.16it/s]
 44%|████▍     | 163854/371472 [2:04:19<17:48:07,  3.24it/s]
 44%|████▍     | 163855/371472 [2:04:19<17:53:50,  3.22it/s]
 44%|████▍     | 163856/371472 [2:04:20<17:34:03,  3.28it/s]
 44%|████▍     | 163857/371472 [2:04:20<18:01:36,  3.20it/s]
 44%|████▍     | 163858/371472 [2:04:20<18:20:49,  3.14it/s]
 44%|████▍     | 163859/371472 [2:04:21<19:00:35,  3.03it/s]
 44%|████▍     | 163860/371472 [2:04:21<18:15:03,  3.16it/s]
                                                            
{'loss': 2.9821, 'learning_rate': 6.03271994656209e-07, 'epoch': 7.06}
+
 44%|████▍     | 163860/371472 [2:04:21<18:15:03,  3.16it/s]
 44%|████▍     | 163861/371472 [2:04:21<17:48:30,  3.24it/s]
 44%|████▍     | 163862/371472 [2:04:22<18:26:55,  3.13it/s]
 44%|████▍     | 163863/371472 [2:04:22<17:41:04,  3.26it/s]
 44%|████▍     | 163864/371472 [2:04:22<17:21:48,  3.32it/s]
 44%|████▍     | 163865/371472 [2:04:23<17:47:32,  3.24it/s]
 44%|████▍     | 163866/371472 [2:04:23<18:45:26,  3.07it/s]
 44%|████▍     | 163867/371472 [2:04:23<18:04:42,  3.19it/s]
 44%|████▍     | 163868/371472 [2:04:24<17:54:32,  3.22it/s]
 44%|████▍     | 163869/371472 [2:04:24<17:40:00,  3.26it/s]
 44%|████▍     | 163870/371472 [2:04:24<17:30:03,  3.30it/s]
 44%|████▍     | 163871/371472 [2:04:24<18:32:56,  3.11it/s]
 44%|████▍     | 163872/371472 [2:04:25<18:28:52,  3.12it/s]
 44%|████▍     | 163873/371472 [2:04:25<18:54:12,  3.05it/s]
 44%|████▍     | 163874/371472 [2:04:25<18:32:55,  3.11it/s]
 44%|████▍     | 163875/371472 [2:04:26<18:05:37,  3.19it/s]
 44%|████▍     | 163876/371472 [2:04:26<17:14:06,  3.35it/s]
 44%|████▍     | 163877/371472 [2:04:26<17:32:32,  3.29it/s]
 44%|████▍     | 163878/371472 [2:04:27<18:20:18,  3.14it/s]
 44%|████▍     | 163879/371472 [2:04:27<18:08:57,  3.18it/s]
 44%|████▍     | 163880/371472 [2:04:27<17:40:42,  3.26it/s]
                                                            
{'loss': 2.9721, 'learning_rate': 6.032235126807299e-07, 'epoch': 7.06}
+
 44%|████▍     | 163880/371472 [2:04:27<17:40:42,  3.26it/s]
 44%|████▍     | 163881/371472 [2:04:28<17:53:06,  3.22it/s]
 44%|████▍     | 163882/371472 [2:04:28<17:51:43,  3.23it/s]
 44%|████▍     | 163883/371472 [2:04:28<17:41:32,  3.26it/s]
 44%|████▍     | 163884/371472 [2:04:28<17:14:13,  3.35it/s]
 44%|████▍     | 163885/371472 [2:04:29<17:21:59,  3.32it/s]
 44%|████▍     | 163886/371472 [2:04:29<17:10:51,  3.36it/s]
 44%|████▍     | 163887/371472 [2:04:29<17:11:38,  3.35it/s]
 44%|████▍     | 163888/371472 [2:04:30<17:53:49,  3.22it/s]
 44%|████▍     | 163889/371472 [2:04:30<17:18:43,  3.33it/s]
 44%|████▍     | 163890/371472 [2:04:30<17:16:37,  3.34it/s]
 44%|████▍     | 163891/371472 [2:04:31<16:58:00,  3.40it/s]
 44%|████▍     | 163892/371472 [2:04:31<17:01:09,  3.39it/s]
 44%|████▍     | 163893/371472 [2:04:31<16:51:49,  3.42it/s]
 44%|████▍     | 163894/371472 [2:04:32<17:52:05,  3.23it/s]
 44%|████▍     | 163895/371472 [2:04:32<17:19:48,  3.33it/s]
 44%|████▍     | 163896/371472 [2:04:32<17:39:26,  3.27it/s]
 44%|████▍     | 163897/371472 [2:04:32<17:34:18,  3.28it/s]
 44%|████▍     | 163898/371472 [2:04:33<17:29:59,  3.29it/s]
 44%|████▍     | 163899/371472 [2:04:33<17:05:56,  3.37it/s]
 44%|████▍     | 163900/371472 [2:04:33<17:59:17,  3.21it/s]
                                                            
{'loss': 3.0335, 'learning_rate': 6.031750307052511e-07, 'epoch': 7.06}
+
 44%|████▍     | 163900/371472 [2:04:33<17:59:17,  3.21it/s]
 44%|████▍     | 163901/371472 [2:04:34<17:41:28,  3.26it/s]
 44%|████▍     | 163902/371472 [2:04:34<18:30:10,  3.12it/s]
 44%|████▍     | 163903/371472 [2:04:34<17:46:56,  3.24it/s]
 44%|████▍     | 163904/371472 [2:04:35<17:02:45,  3.38it/s]
 44%|████▍     | 163905/371472 [2:04:35<17:05:07,  3.37it/s]
 44%|████▍     | 163906/371472 [2:04:35<17:02:52,  3.38it/s]
 44%|████▍     | 163907/371472 [2:04:35<16:41:40,  3.45it/s]
 44%|████▍     | 163908/371472 [2:04:36<16:29:31,  3.50it/s]
 44%|████▍     | 163909/371472 [2:04:36<16:24:44,  3.51it/s]
 44%|████▍     | 163910/371472 [2:04:36<16:48:30,  3.43it/s]
 44%|████▍     | 163911/371472 [2:04:37<16:32:06,  3.49it/s]
 44%|████▍     | 163912/371472 [2:04:37<16:56:43,  3.40it/s]
 44%|████▍     | 163913/371472 [2:04:37<17:05:04,  3.37it/s]
 44%|████▍     | 163914/371472 [2:04:37<17:17:29,  3.33it/s]
 44%|████▍     | 163915/371472 [2:04:38<17:49:07,  3.24it/s]
 44%|████▍     | 163916/371472 [2:04:38<17:37:59,  3.27it/s]
 44%|████▍     | 163917/371472 [2:04:38<17:19:50,  3.33it/s]
 44%|████▍     | 163918/371472 [2:04:39<17:13:06,  3.35it/s]
 44%|���███▍     | 163919/371472 [2:04:39<17:22:56,  3.32it/s]
 44%|████▍     | 163920/371472 [2:04:39<18:05:52,  3.19it/s]
                                                            
{'loss': 3.0767, 'learning_rate': 6.031265487297722e-07, 'epoch': 7.06}
+
 44%|████▍     | 163920/371472 [2:04:39<18:05:52,  3.19it/s]
 44%|████▍     | 163921/371472 [2:04:40<17:40:01,  3.26it/s]
 44%|████▍     | 163922/371472 [2:04:40<17:07:57,  3.37it/s]
 44%|████▍     | 163923/371472 [2:04:40<16:57:11,  3.40it/s]
 44%|████▍     | 163924/371472 [2:04:41<20:00:13,  2.88it/s]
 44%|████▍     | 163925/371472 [2:04:41<18:48:47,  3.06it/s]
 44%|████▍     | 163926/371472 [2:04:41<18:12:01,  3.17it/s]
 44%|████▍     | 163927/371472 [2:04:42<17:44:52,  3.25it/s]
 44%|████▍     | 163928/371472 [2:04:42<17:02:00,  3.38it/s]
 44%|████▍     | 163929/371472 [2:04:42<18:14:24,  3.16it/s]
 44%|████▍     | 163930/371472 [2:04:42<18:17:45,  3.15it/s]
 44%|████▍     | 163931/371472 [2:04:43<18:31:12,  3.11it/s]
 44%|████▍     | 163932/371472 [2:04:43<18:11:32,  3.17it/s]
 44%|████▍     | 163933/371472 [2:04:43<17:50:11,  3.23it/s]
 44%|████▍     | 163934/371472 [2:04:44<17:23:39,  3.31it/s]
 44%|████▍     | 163935/371472 [2:04:44<17:32:01,  3.29it/s]
 44%|████▍     | 163936/371472 [2:04:44<17:24:15,  3.31it/s]
 44%|████▍     | 163937/371472 [2:04:45<17:34:35,  3.28it/s]
 44%|████▍     | 163938/371472 [2:04:45<17:45:43,  3.25it/s]
 44%|████▍     | 163939/371472 [2:04:45<17:51:12,  3.23it/s]
 44%|████▍     | 163940/371472 [2:04:46<17:30:57,  3.29it/s]
                                                            
{'loss': 2.8802, 'learning_rate': 6.030780667542933e-07, 'epoch': 7.06}
+
 44%|████▍     | 163940/371472 [2:04:46<17:30:57,  3.29it/s]
 44%|████▍     | 163941/371472 [2:04:46<17:33:22,  3.28it/s]
 44%|████▍     | 163942/371472 [2:04:46<18:16:52,  3.15it/s]
 44%|████▍     | 163943/371472 [2:04:46<18:00:32,  3.20it/s]
 44%|████▍     | 163944/371472 [2:04:47<17:39:38,  3.26it/s]
 44%|████▍     | 163945/371472 [2:04:47<17:53:33,  3.22it/s]
 44%|████▍     | 163946/371472 [2:04:47<17:30:02,  3.29it/s]
 44%|████▍     | 163947/371472 [2:04:48<17:27:37,  3.30it/s]
 44%|████▍     | 163948/371472 [2:04:48<18:36:49,  3.10it/s]
 44%|████▍     | 163949/371472 [2:04:48<18:58:54,  3.04it/s]
 44%|████▍     | 163950/371472 [2:04:49<18:50:09,  3.06it/s]
 44%|████▍     | 163951/371472 [2:04:49<18:02:42,  3.19it/s]
 44%|████▍     | 163952/371472 [2:04:49<17:24:37,  3.31it/s]
 44%|████▍     | 163953/371472 [2:04:50<17:02:31,  3.38it/s]
 44%|████▍     | 163954/371472 [2:04:50<16:53:06,  3.41it/s]
 44%|████▍     | 163955/371472 [2:04:50<17:47:29,  3.24it/s]
 44%|████▍     | 163956/371472 [2:04:50<17:22:37,  3.32it/s]
 44%|████▍     | 163957/371472 [2:04:51<17:36:59,  3.27it/s]
 44%|████▍     | 163958/371472 [2:04:51<17:25:46,  3.31it/s]
 44%|████▍     | 163959/371472 [2:04:51<17:39:59,  3.26it/s]
 44%|████▍     | 163960/371472 [2:04:52<17:21:32,  3.32it/s]
                                                            
{'loss': 2.9003, 'learning_rate': 6.030295847788144e-07, 'epoch': 7.06}
+
 44%|████▍     | 163960/371472 [2:04:52<17:21:32,  3.32it/s]
 44%|████▍     | 163961/371472 [2:04:52<17:51:21,  3.23it/s]
 44%|████▍     | 163962/371472 [2:04:52<17:15:54,  3.34it/s]
 44%|████▍     | 163963/371472 [2:04:53<17:44:51,  3.25it/s]
 44%|████▍     | 163964/371472 [2:04:53<17:46:41,  3.24it/s]
 44%|████▍     | 163965/371472 [2:04:53<17:29:04,  3.30it/s]
 44%|████▍     | 163966/371472 [2:04:54<17:26:36,  3.30it/s]
 44%|████▍     | 163967/371472 [2:04:54<17:30:38,  3.29it/s]
 44%|████▍     | 163968/371472 [2:04:54<17:22:12,  3.32it/s]
 44%|████▍     | 163969/371472 [2:04:54<16:48:17,  3.43it/s]
 44%|████▍     | 163970/371472 [2:04:55<16:44:29,  3.44it/s]
 44%|████▍     | 163971/371472 [2:04:55<16:20:59,  3.53it/s]
 44%|████▍     | 163972/371472 [2:04:55<16:08:22,  3.57it/s]
 44%|████▍     | 163973/371472 [2:04:56<16:47:56,  3.43it/s]
 44%|████▍     | 163974/371472 [2:04:56<16:59:09,  3.39it/s]
 44%|████▍     | 163975/371472 [2:04:56<18:07:29,  3.18it/s]
 44%|████▍     | 163976/371472 [2:04:56<17:56:04,  3.21it/s]
 44%|████▍     | 163977/371472 [2:04:57<18:12:15,  3.17it/s]
 44%|████▍     | 163978/371472 [2:04:57<18:04:03,  3.19it/s]
 44%|████▍     | 163979/371472 [2:04:57<17:42:34,  3.25it/s]
 44%|████▍     | 163980/371472 [2:04:58<17:55:38,  3.22it/s]
                                                            
{'loss': 2.973, 'learning_rate': 6.029811028033356e-07, 'epoch': 7.06}
+
 44%|████▍     | 163980/371472 [2:04:58<17:55:38,  3.22it/s]
 44%|████▍     | 163981/371472 [2:04:58<17:41:51,  3.26it/s]
 44%|████▍     | 163982/371472 [2:04:58<17:18:15,  3.33it/s]
 44%|████▍     | 163983/371472 [2:04:59<17:33:57,  3.28it/s]
 44%|████▍     | 163984/371472 [2:04:59<17:05:56,  3.37it/s]
 44%|████▍     | 163985/371472 [2:04:59<16:57:03,  3.40it/s]
 44%|████▍     | 163986/371472 [2:05:00<17:21:08,  3.32it/s]
 44%|████▍     | 163987/371472 [2:05:00<16:57:44,  3.40it/s]
 44%|████▍     | 163988/371472 [2:05:00<16:41:47,  3.45it/s]
 44%|████▍     | 163989/371472 [2:05:00<16:35:23,  3.47it/s]
 44%|████▍     | 163990/371472 [2:05:01<17:05:55,  3.37it/s]
 44%|████▍     | 163991/371472 [2:05:01<17:03:44,  3.38it/s]
 44%|████▍     | 163992/371472 [2:05:01<16:42:58,  3.45it/s]
 44%|████▍     | 163993/371472 [2:05:02<16:47:57,  3.43it/s]
 44%|████▍     | 163994/371472 [2:05:02<17:02:14,  3.38it/s]
 44%|████▍     | 163995/371472 [2:05:02<17:03:24,  3.38it/s]
 44%|████▍     | 163996/371472 [2:05:02<17:05:10,  3.37it/s]
 44%|████▍     | 163997/371472 [2:05:03<16:50:09,  3.42it/s]
 44%|████▍     | 163998/371472 [2:05:03<18:29:48,  3.12it/s]
 44%|████▍     | 163999/371472 [2:05:03<17:49:30,  3.23it/s]
 44%|████▍     | 164000/371472 [2:05:04<17:23:20,  3.31it/s]
                                                            
{'loss': 2.9174, 'learning_rate': 6.029326208278567e-07, 'epoch': 7.06}
+
 44%|████▍     | 164000/371472 [2:05:04<17:23:20,  3.31it/s]
 44%|████▍     | 164001/371472 [2:05:04<18:07:00,  3.18it/s]
 44%|████▍     | 164002/371472 [2:05:04<18:50:49,  3.06it/s]
 44%|████▍     | 164003/371472 [2:05:05<17:58:56,  3.20it/s]
 44%|████▍     | 164004/371472 [2:05:05<17:37:14,  3.27it/s]
 44%|████▍     | 164005/371472 [2:05:05<19:33:14,  2.95it/s]
 44%|████▍     | 164006/371472 [2:05:06<19:00:57,  3.03it/s]
 44%|████▍     | 164007/371472 [2:05:06<18:15:52,  3.16it/s]
 44%|████▍     | 164008/371472 [2:05:06<17:59:04,  3.20it/s]
 44%|████▍     | 164009/371472 [2:05:07<17:52:19,  3.22it/s]
 44%|████▍     | 164010/371472 [2:05:07<18:11:51,  3.17it/s]
 44%|████▍     | 164011/371472 [2:05:07<18:08:22,  3.18it/s]
 44%|████▍     | 164012/371472 [2:05:08<18:27:49,  3.12it/s]
 44%|████▍     | 164013/371472 [2:05:08<18:10:38,  3.17it/s]
 44%|████▍     | 164014/371472 [2:05:08<18:52:28,  3.05it/s]
 44%|████▍     | 164015/371472 [2:05:09<19:27:59,  2.96it/s]
 44%|████▍     | 164016/371472 [2:05:09<18:46:16,  3.07it/s]
 44%|████▍     | 164017/371472 [2:05:09<19:25:20,  2.97it/s]
 44%|████▍     | 164018/371472 [2:05:10<18:24:17,  3.13it/s]
 44%|████▍     | 164019/371472 [2:05:10<17:56:21,  3.21it/s]
 44%|████▍     | 164020/371472 [2:05:10<18:05:46,  3.18it/s]
                                                            
{'loss': 2.9363, 'learning_rate': 6.028841388523777e-07, 'epoch': 7.06}
+
 44%|████▍     | 164020/371472 [2:05:10<18:05:46,  3.18it/s]
 44%|████▍     | 164021/371472 [2:05:10<17:38:12,  3.27it/s]
 44%|████▍     | 164022/371472 [2:05:11<17:42:59,  3.25it/s]
 44%|████▍     | 164023/371472 [2:05:11<17:11:30,  3.35it/s]
 44%|████▍     | 164024/371472 [2:05:11<16:44:23,  3.44it/s]
 44%|████▍     | 164025/371472 [2:05:12<16:28:45,  3.50it/s]
 44%|████▍     | 164026/371472 [2:05:12<16:50:05,  3.42it/s]
 44%|████▍     | 164027/371472 [2:05:12<16:35:29,  3.47it/s]
 44%|████▍     | 164028/371472 [2:05:12<16:46:33,  3.43it/s]
 44%|████▍     | 164029/371472 [2:05:13<16:14:15,  3.55it/s]
 44%|████▍     | 164030/371472 [2:05:13<16:09:21,  3.57it/s]
 44%|████▍     | 164031/371472 [2:05:13<16:18:56,  3.53it/s]
 44%|████▍     | 164032/371472 [2:05:14<16:46:55,  3.43it/s]
 44%|████▍     | 164033/371472 [2:05:14<17:39:34,  3.26it/s]
 44%|████▍     | 164034/371472 [2:05:14<17:20:28,  3.32it/s]
 44%|████▍     | 164035/371472 [2:05:14<17:11:29,  3.35it/s]
 44%|████▍     | 164036/371472 [2:05:15<17:01:55,  3.38it/s]
 44%|████▍     | 164037/371472 [2:05:15<16:32:02,  3.48it/s]
 44%|████▍     | 164038/371472 [2:05:15<16:23:16,  3.52it/s]
 44%|████▍     | 164039/371472 [2:05:16<16:23:38,  3.51it/s]
 44%|████▍     | 164040/371472 [2:05:16<16:16:28,  3.54it/s]
                                                            
{'loss': 2.9845, 'learning_rate': 6.028356568768988e-07, 'epoch': 7.07}
+
 44%|████▍     | 164040/371472 [2:05:16<16:16:28,  3.54it/s]
 44%|████▍     | 164041/371472 [2:05:16<16:48:32,  3.43it/s]
 44%|████▍     | 164042/371472 [2:05:17<17:17:33,  3.33it/s]
 44%|████▍     | 164043/371472 [2:05:17<18:01:42,  3.20it/s]
 44%|████▍     | 164044/371472 [2:05:17<17:29:01,  3.30it/s]
 44%|████▍     | 164045/371472 [2:05:18<18:44:16,  3.07it/s]
 44%|████▍     | 164046/371472 [2:05:18<20:07:43,  2.86it/s]
 44%|████▍     | 164047/371472 [2:05:18<19:16:55,  2.99it/s]
 44%|████▍     | 164048/371472 [2:05:19<18:43:36,  3.08it/s]
 44%|████▍     | 164049/371472 [2:05:19<18:22:57,  3.13it/s]
 44%|████▍     | 164050/371472 [2:05:19<17:26:14,  3.30it/s]
 44%|████▍     | 164051/371472 [2:05:19<17:10:59,  3.35it/s]
 44%|████▍     | 164052/371472 [2:05:20<17:50:54,  3.23it/s]
 44%|████▍     | 164053/371472 [2:05:20<17:35:06,  3.28it/s]
 44%|████▍     | 164054/371472 [2:05:20<17:21:46,  3.32it/s]
 44%|████▍     | 164055/371472 [2:05:21<17:40:54,  3.26it/s]
 44%|████▍     | 164056/371472 [2:05:21<17:27:02,  3.30it/s]
 44%|████▍     | 164057/371472 [2:05:21<17:47:10,  3.24it/s]
 44%|████▍     | 164058/371472 [2:05:22<17:19:23,  3.33it/s]
 44%|████▍     | 164059/371472 [2:05:22<18:43:09,  3.08it/s]
 44%|████▍     | 164060/371472 [2:05:22<18:12:19,  3.16it/s]
                                                            
{'loss': 3.1542, 'learning_rate': 6.0278717490142e-07, 'epoch': 7.07}
+
 44%|████▍     | 164060/371472 [2:05:22<18:12:19,  3.16it/s]
 44%|████▍     | 164061/371472 [2:05:22<17:52:14,  3.22it/s]
 44%|████▍     | 164062/371472 [2:05:23<17:35:37,  3.27it/s]
 44%|████▍     | 164063/371472 [2:05:23<17:40:19,  3.26it/s]
 44%|████▍     | 164064/371472 [2:05:23<16:55:39,  3.40it/s]
 44%|████▍     | 164065/371472 [2:05:24<16:51:37,  3.42it/s]
 44%|████▍     | 164066/371472 [2:05:24<17:20:24,  3.32it/s]
 44%|████▍     | 164067/371472 [2:05:24<17:17:58,  3.33it/s]
 44%|████▍     | 164068/371472 [2:05:25<17:06:35,  3.37it/s]
 44%|████▍     | 164069/371472 [2:05:25<17:07:57,  3.36it/s]
 44%|████▍     | 164070/371472 [2:05:25<16:57:59,  3.40it/s]
 44%|████▍     | 164071/371472 [2:05:25<16:47:46,  3.43it/s]
 44%|████▍     | 164072/371472 [2:05:26<16:55:08,  3.41it/s]
 44%|████▍     | 164073/371472 [2:05:26<17:36:17,  3.27it/s]
 44%|████▍     | 164074/371472 [2:05:26<17:34:34,  3.28it/s]
 44%|████▍     | 164075/371472 [2:05:27<16:52:25,  3.41it/s]
 44%|████▍     | 164076/371472 [2:05:27<16:55:12,  3.40it/s]
 44%|████▍     | 164077/371472 [2:05:27<18:10:57,  3.17it/s]
 44%|████▍     | 164078/371472 [2:05:28<18:15:14,  3.16it/s]
 44%|████▍     | 164079/371472 [2:05:28<18:05:52,  3.18it/s]
 44%|████▍     | 164080/371472 [2:05:28<17:45:27,  3.24it/s]
                                                            
{'loss': 3.1543, 'learning_rate': 6.027386929259411e-07, 'epoch': 7.07}
+
 44%|████▍     | 164080/371472 [2:05:28<17:45:27,  3.24it/s]
 44%|████▍     | 164081/371472 [2:05:29<17:34:59,  3.28it/s]
 44%|████▍     | 164082/371472 [2:05:29<17:25:22,  3.31it/s]
 44%|████▍     | 164083/371472 [2:05:29<17:06:00,  3.37it/s]
 44%|████▍     | 164084/371472 [2:05:29<16:54:47,  3.41it/s]
 44%|████▍     | 164085/371472 [2:05:30<17:16:37,  3.33it/s]
 44%|████▍     | 164086/371472 [2:05:30<17:13:13,  3.35it/s]
 44%|████▍     | 164087/371472 [2:05:30<16:40:12,  3.46it/s]
 44%|████▍     | 164088/371472 [2:05:31<17:04:44,  3.37it/s]
 44%|████▍     | 164089/371472 [2:05:31<16:59:13,  3.39it/s]
 44%|████▍     | 164090/371472 [2:05:31<16:56:39,  3.40it/s]
 44%|████▍     | 164091/371472 [2:05:31<16:41:39,  3.45it/s]
 44%|████▍     | 164092/371472 [2:05:32<17:01:50,  3.38it/s]
 44%|████▍     | 164093/371472 [2:05:32<16:43:58,  3.44it/s]
 44%|████▍     | 164094/371472 [2:05:32<16:49:26,  3.42it/s]
 44%|████▍     | 164095/371472 [2:05:33<17:23:52,  3.31it/s]
 44%|████▍     | 164096/371472 [2:05:33<16:57:17,  3.40it/s]
 44%|████▍     | 164097/371472 [2:05:33<16:42:22,  3.45it/s]
 44%|████▍     | 164098/371472 [2:05:34<17:13:27,  3.34it/s]
 44%|████▍     | 164099/371472 [2:05:34<17:31:49,  3.29it/s]
 44%|████▍     | 164100/371472 [2:05:34<18:01:46,  3.19it/s]
                                                            
{'loss': 2.9746, 'learning_rate': 6.026902109504622e-07, 'epoch': 7.07}
+
 44%|████▍     | 164100/371472 [2:05:34<18:01:46,  3.19it/s]
 44%|████▍     | 164101/371472 [2:05:34<17:14:57,  3.34it/s]
 44%|████▍     | 164102/371472 [2:05:35<17:09:20,  3.36it/s]
 44%|████▍     | 164103/371472 [2:05:35<17:09:20,  3.36it/s]
 44%|████▍     | 164104/371472 [2:05:35<17:12:03,  3.35it/s]
 44%|████▍     | 164105/371472 [2:05:36<17:22:50,  3.31it/s]
 44%|████▍     | 164106/371472 [2:05:36<17:17:08,  3.33it/s]
 44%|████▍     | 164107/371472 [2:05:36<17:14:53,  3.34it/s]
 44%|████▍     | 164108/371472 [2:05:37<17:50:04,  3.23it/s]
 44%|████▍     | 164109/371472 [2:05:37<17:30:59,  3.29it/s]
 44%|████▍     | 164110/371472 [2:05:37<17:39:06,  3.26it/s]
 44%|████▍     | 164111/371472 [2:05:37<17:43:27,  3.25it/s]
 44%|████▍     | 164112/371472 [2:05:38<17:21:42,  3.32it/s]
 44%|████▍     | 164113/371472 [2:05:38<17:22:59,  3.31it/s]
 44%|████▍     | 164114/371472 [2:05:38<17:20:29,  3.32it/s]
 44%|████▍     | 164115/371472 [2:05:39<17:20:06,  3.32it/s]
 44%|████▍     | 164116/371472 [2:05:39<17:41:36,  3.26it/s]
 44%|████▍     | 164117/371472 [2:05:39<17:23:17,  3.31it/s]
 44%|████▍     | 164118/371472 [2:05:40<17:08:37,  3.36it/s]
 44%|████▍     | 164119/371472 [2:05:40<17:18:11,  3.33it/s]
 44%|████▍     | 164120/371472 [2:05:40<17:13:39,  3.34it/s]
                                                            
{'loss': 2.9436, 'learning_rate': 6.026417289749833e-07, 'epoch': 7.07}
+
 44%|████▍     | 164120/371472 [2:05:40<17:13:39,  3.34it/s]
 44%|████▍     | 164121/371472 [2:05:40<17:00:26,  3.39it/s]
 44%|████▍     | 164122/371472 [2:05:41<16:51:55,  3.42it/s]
 44%|████▍     | 164123/371472 [2:05:41<17:00:17,  3.39it/s]
 44%|████▍     | 164124/371472 [2:05:41<16:42:13,  3.45it/s]
 44%|████▍     | 164125/371472 [2:05:42<17:45:10,  3.24it/s]
 44%|████▍     | 164126/371472 [2:05:42<18:05:31,  3.18it/s]
 44%|████▍     | 164127/371472 [2:05:42<17:40:43,  3.26it/s]
 44%|████▍     | 164128/371472 [2:05:43<17:24:53,  3.31it/s]
 44%|████▍     | 164129/371472 [2:05:43<17:14:12,  3.34it/s]
 44%|████▍     | 164130/371472 [2:05:43<17:45:09,  3.24it/s]
 44%|████▍     | 164131/371472 [2:05:44<18:30:25,  3.11it/s]
 44%|████▍     | 164132/371472 [2:05:44<17:50:55,  3.23it/s]
 44%|████▍     | 164133/371472 [2:05:44<17:21:24,  3.32it/s]
 44%|████▍     | 164134/371472 [2:05:44<17:15:13,  3.34it/s]
 44%|████▍     | 164135/371472 [2:05:45<17:59:11,  3.20it/s]
 44%|████▍     | 164136/371472 [2:05:45<17:42:58,  3.25it/s]
 44%|████▍     | 164137/371472 [2:05:45<17:12:36,  3.35it/s]
 44%|████▍     | 164138/371472 [2:05:46<16:51:50,  3.42it/s]
 44%|████▍     | 164139/371472 [2:05:46<16:52:55,  3.41it/s]
 44%|████▍     | 164140/371472 [2:05:46<16:42:30,  3.45it/s]
                                                            
{'loss': 3.0228, 'learning_rate': 6.025932469995044e-07, 'epoch': 7.07}
+
 44%|████▍     | 164140/371472 [2:05:46<16:42:30,  3.45it/s]
 44%|████▍     | 164141/371472 [2:05:47<17:05:24,  3.37it/s]
 44%|████▍     | 164142/371472 [2:05:47<16:58:25,  3.39it/s]
 44%|████▍     | 164143/371472 [2:05:47<16:55:06,  3.40it/s]
 44%|████▍     | 164144/371472 [2:05:47<16:56:18,  3.40it/s]
 44%|████▍     | 164145/371472 [2:05:48<17:00:07,  3.39it/s]
 44%|████▍     | 164146/371472 [2:05:48<18:59:45,  3.03it/s]
 44%|████▍     | 164147/371472 [2:05:48<18:09:42,  3.17it/s]
 44%|████▍     | 164148/371472 [2:05:49<17:24:07,  3.31it/s]
 44%|████▍     | 164149/371472 [2:05:49<17:16:08,  3.33it/s]
 44%|████▍     | 164150/371472 [2:05:49<17:00:32,  3.39it/s]
 44%|████▍     | 164151/371472 [2:05:50<16:46:29,  3.43it/s]
 44%|████▍     | 164152/371472 [2:05:50<16:30:47,  3.49it/s]
 44%|████▍     | 164153/371472 [2:05:50<17:33:45,  3.28it/s]
 44%|████▍     | 164154/371472 [2:05:50<17:07:13,  3.36it/s]
 44%|████▍     | 164155/371472 [2:05:51<17:30:15,  3.29it/s]
 44%|████▍     | 164156/371472 [2:05:51<17:02:19,  3.38it/s]
 44%|████▍     | 164157/371472 [2:05:51<16:47:07,  3.43it/s]
 44%|████▍     | 164158/371472 [2:05:52<16:34:02,  3.48it/s]
 44%|████▍     | 164159/371472 [2:05:52<16:40:14,  3.45it/s]
 44%|████▍     | 164160/371472 [2:05:52<17:14:22,  3.34it/s]
                                                            
{'loss': 3.046, 'learning_rate': 6.025447650240255e-07, 'epoch': 7.07}
+
 44%|████▍     | 164160/371472 [2:05:52<17:14:22,  3.34it/s]
 44%|████▍     | 164161/371472 [2:05:53<20:46:08,  2.77it/s]
 44%|████▍     | 164162/371472 [2:05:53<19:35:20,  2.94it/s]
 44%|████▍     | 164163/371472 [2:05:53<18:52:46,  3.05it/s]
 44%|████▍     | 164164/371472 [2:05:54<18:47:45,  3.06it/s]
 44%|████▍     | 164165/371472 [2:05:54<18:44:10,  3.07it/s]
 44%|████▍     | 164166/371472 [2:05:54<18:08:23,  3.17it/s]
 44%|████▍     | 164167/371472 [2:05:54<17:35:47,  3.27it/s]
 44%|████▍     | 164168/371472 [2:05:55<17:30:28,  3.29it/s]
 44%|████▍     | 164169/371472 [2:05:55<17:10:08,  3.35it/s]
 44%|████▍     | 164170/371472 [2:05:55<18:02:31,  3.19it/s]
 44%|████▍     | 164171/371472 [2:05:56<17:30:25,  3.29it/s]
 44%|████▍     | 164172/371472 [2:05:56<17:08:43,  3.36it/s]
 44%|████▍     | 164173/371472 [2:05:56<16:49:20,  3.42it/s]
 44%|████▍     | 164174/371472 [2:05:57<16:55:20,  3.40it/s]
 44%|████▍     | 164175/371472 [2:05:57<16:42:19,  3.45it/s]
 44%|████▍     | 164176/371472 [2:05:57<16:53:47,  3.41it/s]
 44%|████▍     | 164177/371472 [2:05:57<17:00:15,  3.39it/s]
 44%|████▍     | 164178/371472 [2:05:58<17:00:51,  3.38it/s]
 44%|████▍     | 164179/371472 [2:05:58<17:10:18,  3.35it/s]
 44%|████▍     | 164180/371472 [2:05:58<17:19:53,  3.32it/s]
                                                            
{'loss': 2.9359, 'learning_rate': 6.024962830485465e-07, 'epoch': 7.07}
+
 44%|████▍     | 164180/371472 [2:05:58<17:19:53,  3.32it/s]
 44%|████▍     | 164181/371472 [2:05:59<19:50:12,  2.90it/s]
 44%|████▍     | 164182/371472 [2:05:59<18:37:16,  3.09it/s]
 44%|████▍     | 164183/371472 [2:05:59<18:34:52,  3.10it/s]
 44%|████▍     | 164184/371472 [2:06:00<20:51:06,  2.76it/s]
 44%|████▍     | 164185/371472 [2:06:00<19:28:16,  2.96it/s]
 44%|████▍     | 164186/371472 [2:06:00<18:40:49,  3.08it/s]
 44%|████▍     | 164187/371472 [2:06:01<17:34:21,  3.28it/s]
 44%|████▍     | 164188/371472 [2:06:01<17:41:57,  3.25it/s]
 44%|████▍     | 164189/371472 [2:06:01<17:27:38,  3.30it/s]
 44%|████▍     | 164190/371472 [2:06:02<17:03:46,  3.37it/s]
 44%|████▍     | 164191/371472 [2:06:02<16:52:31,  3.41it/s]
 44%|████▍     | 164192/371472 [2:06:02<16:42:30,  3.45it/s]
 44%|████▍     | 164193/371472 [2:06:03<18:54:01,  3.05it/s]
 44%|████▍     | 164194/371472 [2:06:03<18:48:41,  3.06it/s]
 44%|████▍     | 164195/371472 [2:06:03<18:01:03,  3.20it/s]
 44%|████▍     | 164196/371472 [2:06:03<17:25:54,  3.30it/s]
 44%|████▍     | 164197/371472 [2:06:04<18:04:46,  3.18it/s]
 44%|████▍     | 164198/371472 [2:06:04<17:45:46,  3.24it/s]
 44%|████▍     | 164199/371472 [2:06:04<17:43:47,  3.25it/s]
 44%|████▍     | 164200/371472 [2:06:05<17:38:30,  3.26it/s]
                                                            
{'loss': 2.9893, 'learning_rate': 6.024478010730677e-07, 'epoch': 7.07}
+
 44%|████▍     | 164200/371472 [2:06:05<17:38:30,  3.26it/s]
 44%|████▍     | 164201/371472 [2:06:05<17:34:38,  3.28it/s]
 44%|████▍     | 164202/371472 [2:06:05<17:22:41,  3.31it/s]
 44%|████▍     | 164203/371472 [2:06:06<17:18:39,  3.33it/s]
 44%|████▍     | 164204/371472 [2:06:06<17:17:15,  3.33it/s]
 44%|████▍     | 164205/371472 [2:06:06<17:06:49,  3.36it/s]
 44%|████▍     | 164206/371472 [2:06:06<17:10:17,  3.35it/s]
 44%|████▍     | 164207/371472 [2:06:07<17:13:25,  3.34it/s]
 44%|████▍     | 164208/371472 [2:06:07<17:44:03,  3.25it/s]
 44%|████▍     | 164209/371472 [2:06:07<17:21:55,  3.32it/s]
 44%|████▍     | 164210/371472 [2:06:08<16:53:28,  3.41it/s]
 44%|████▍     | 164211/371472 [2:06:08<16:43:23,  3.44it/s]
 44%|████▍     | 164212/371472 [2:06:08<17:11:35,  3.35it/s]
 44%|████▍     | 164213/371472 [2:06:09<16:47:34,  3.43it/s]
 44%|████▍     | 164214/371472 [2:06:09<16:57:50,  3.39it/s]
 44%|████▍     | 164215/371472 [2:06:09<16:42:47,  3.44it/s]
 44%|████▍     | 164216/371472 [2:06:09<17:18:37,  3.33it/s]
 44%|████▍     | 164217/371472 [2:06:10<17:04:25,  3.37it/s]
 44%|████▍     | 164218/371472 [2:06:10<17:16:57,  3.33it/s]
 44%|████▍     | 164219/371472 [2:06:10<17:07:37,  3.36it/s]
 44%|████▍     | 164220/371472 [2:06:11<17:57:12,  3.21it/s]
                                                            
{'loss': 3.0916, 'learning_rate': 6.023993190975889e-07, 'epoch': 7.07}
+
 44%|████▍     | 164220/371472 [2:06:11<17:57:12,  3.21it/s]
 44%|████▍     | 164221/371472 [2:06:11<17:28:04,  3.30it/s]
 44%|████▍     | 164222/371472 [2:06:11<17:40:01,  3.26it/s]
 44%|████▍     | 164223/371472 [2:06:12<17:07:01,  3.36it/s]
 44%|████▍     | 164224/371472 [2:06:12<18:35:26,  3.10it/s]
 44%|████▍     | 164225/371472 [2:06:12<18:10:07,  3.17it/s]
 44%|████▍     | 164226/371472 [2:06:13<17:34:47,  3.27it/s]
 44%|████▍     | 164227/371472 [2:06:13<17:13:10,  3.34it/s]
 44%|████▍     | 164228/371472 [2:06:13<17:04:52,  3.37it/s]
 44%|████▍     | 164229/371472 [2:06:13<16:55:35,  3.40it/s]
 44%|████▍     | 164230/371472 [2:06:14<17:04:13,  3.37it/s]
 44%|████▍     | 164231/371472 [2:06:14<16:42:26,  3.45it/s]
 44%|████▍     | 164232/371472 [2:06:14<17:16:41,  3.33it/s]
 44%|████▍     | 164233/371472 [2:06:15<16:56:36,  3.40it/s]
 44%|████▍     | 164234/371472 [2:06:15<16:56:34,  3.40it/s]
 44%|████▍     | 164235/371472 [2:06:15<16:53:18,  3.41it/s]
 44%|████▍     | 164236/371472 [2:06:15<17:03:07,  3.38it/s]
 44%|████▍     | 164237/371472 [2:06:16<17:07:01,  3.36it/s]
 44%|████▍     | 164238/371472 [2:06:16<17:14:41,  3.34it/s]
 44%|████▍     | 164239/371472 [2:06:16<17:06:16,  3.37it/s]
 44%|████▍     | 164240/371472 [2:06:17<17:24:22,  3.31it/s]
                                                            
{'loss': 2.8421, 'learning_rate': 6.023508371221099e-07, 'epoch': 7.07}
+
 44%|████▍     | 164240/371472 [2:06:17<17:24:22,  3.31it/s]
 44%|████▍     | 164241/371472 [2:06:17<17:35:10,  3.27it/s]
 44%|████▍     | 164242/371472 [2:06:17<17:43:20,  3.25it/s]
 44%|████▍     | 164243/371472 [2:06:18<17:38:49,  3.26it/s]
 44%|████▍     | 164244/371472 [2:06:18<16:57:22,  3.39it/s]
 44%|████▍     | 164245/371472 [2:06:18<17:07:42,  3.36it/s]
 44%|████▍     | 164246/371472 [2:06:18<17:12:29,  3.35it/s]
 44%|████▍     | 164247/371472 [2:06:19<17:16:06,  3.33it/s]
 44%|████▍     | 164248/371472 [2:06:19<17:25:56,  3.30it/s]
 44%|████▍     | 164249/371472 [2:06:19<16:52:56,  3.41it/s]
 44%|████▍     | 164250/371472 [2:06:20<16:35:24,  3.47it/s]
 44%|████▍     | 164251/371472 [2:06:20<17:25:26,  3.30it/s]
 44%|████▍     | 164252/371472 [2:06:20<17:28:34,  3.29it/s]
 44%|████▍     | 164253/371472 [2:06:21<17:26:46,  3.30it/s]
 44%|████▍     | 164254/371472 [2:06:21<17:02:56,  3.38it/s]
 44%|████▍     | 164255/371472 [2:06:21<18:07:21,  3.18it/s]
 44%|████▍     | 164256/371472 [2:06:22<18:43:12,  3.07it/s]
 44%|████▍     | 164257/371472 [2:06:22<19:57:26,  2.88it/s]
 44%|████▍     | 164258/371472 [2:06:22<19:08:32,  3.01it/s]
 44%|████▍     | 164259/371472 [2:06:23<18:34:38,  3.10it/s]
 44%|████▍     | 164260/371472 [2:06:23<17:57:06,  3.21it/s]
                                                            
{'loss': 2.7733, 'learning_rate': 6.02302355146631e-07, 'epoch': 7.07}
+
 44%|████▍     | 164260/371472 [2:06:23<17:57:06,  3.21it/s]
 44%|████▍     | 164261/371472 [2:06:23<17:40:57,  3.26it/s]
 44%|████▍     | 164262/371472 [2:06:23<17:17:40,  3.33it/s]
 44%|████▍     | 164263/371472 [2:06:24<17:12:00,  3.35it/s]
 44%|████▍     | 164264/371472 [2:06:24<16:56:39,  3.40it/s]
 44%|████▍     | 164265/371472 [2:06:24<17:32:45,  3.28it/s]
 44%|████▍     | 164266/371472 [2:06:25<17:42:33,  3.25it/s]
 44%|████▍     | 164267/371472 [2:06:25<18:25:06,  3.12it/s]
 44%|████▍     | 164268/371472 [2:06:25<18:34:15,  3.10it/s]
 44%|████▍     | 164269/371472 [2:06:26<18:50:53,  3.05it/s]
 44%|████▍     | 164270/371472 [2:06:26<19:00:51,  3.03it/s]
 44%|████▍     | 164271/371472 [2:06:26<19:50:33,  2.90it/s]
 44%|████▍     | 164272/371472 [2:06:27<18:58:12,  3.03it/s]
 44%|████▍     | 164273/371472 [2:06:27<18:05:37,  3.18it/s]
 44%|████▍     | 164274/371472 [2:06:27<17:50:40,  3.23it/s]
 44%|████▍     | 164275/371472 [2:06:28<18:07:01,  3.18it/s]
 44%|████▍     | 164276/371472 [2:06:28<17:48:55,  3.23it/s]
 44%|████▍     | 164277/371472 [2:06:28<18:05:00,  3.18it/s]
 44%|████▍     | 164278/371472 [2:06:28<17:39:46,  3.26it/s]
 44%|████▍     | 164279/371472 [2:06:29<17:09:42,  3.35it/s]
 44%|████▍     | 164280/371472 [2:06:29<17:10:22,  3.35it/s]
                                                            
{'loss': 2.9088, 'learning_rate': 6.022538731711522e-07, 'epoch': 7.08}
+
 44%|████▍     | 164280/371472 [2:06:29<17:10:22,  3.35it/s]
 44%|████▍     | 164281/371472 [2:06:29<18:16:11,  3.15it/s]
 44%|████▍     | 164282/371472 [2:06:30<18:06:01,  3.18it/s]
 44%|████▍     | 164283/371472 [2:06:30<17:35:51,  3.27it/s]
 44%|████▍     | 164284/371472 [2:06:30<17:07:44,  3.36it/s]
 44%|████▍     | 164285/371472 [2:06:31<16:55:33,  3.40it/s]
 44%|████▍     | 164286/371472 [2:06:31<16:51:14,  3.41it/s]
 44%|████▍     | 164287/371472 [2:06:31<17:13:49,  3.34it/s]
 44%|████▍     | 164288/371472 [2:06:31<17:17:24,  3.33it/s]
 44%|████▍     | 164289/371472 [2:06:32<17:07:25,  3.36it/s]
 44%|████▍     | 164290/371472 [2:06:32<17:02:51,  3.38it/s]
 44%|████▍     | 164291/371472 [2:06:32<17:41:57,  3.25it/s]
 44%|████▍     | 164292/371472 [2:06:33<17:41:28,  3.25it/s]
 44%|████▍     | 164293/371472 [2:06:33<17:10:33,  3.35it/s]
 44%|████▍     | 164294/371472 [2:06:33<16:50:39,  3.42it/s]
 44%|████▍     | 164295/371472 [2:06:34<18:41:41,  3.08it/s]
 44%|████▍     | 164296/371472 [2:06:34<18:00:24,  3.20it/s]
 44%|████▍     | 164297/371472 [2:06:34<18:36:55,  3.09it/s]
 44%|████▍     | 164298/371472 [2:06:35<18:05:56,  3.18it/s]
 44%|████▍     | 164299/371472 [2:06:35<17:48:11,  3.23it/s]
 44%|████▍     | 164300/371472 [2:06:35<17:16:43,  3.33it/s]
                                                            
{'loss': 3.0312, 'learning_rate': 6.022053911956732e-07, 'epoch': 7.08}
+
 44%|████▍     | 164300/371472 [2:06:35<17:16:43,  3.33it/s]
 44%|████▍     | 164301/371472 [2:06:35<17:10:01,  3.35it/s]
 44%|████▍     | 164302/371472 [2:06:36<18:00:07,  3.20it/s]
 44%|████▍     | 164303/371472 [2:06:36<19:12:26,  3.00it/s]
 44%|████▍     | 164304/371472 [2:06:36<18:22:59,  3.13it/s]
 44%|████▍     | 164305/371472 [2:06:37<18:09:38,  3.17it/s]
 44%|████▍     | 164306/371472 [2:06:37<17:21:16,  3.32it/s]
 44%|████▍     | 164307/371472 [2:06:37<17:32:56,  3.28it/s]
 44%|████▍     | 164308/371472 [2:06:38<17:28:22,  3.29it/s]
 44%|████▍     | 164309/371472 [2:06:38<17:06:52,  3.36it/s]
 44%|████▍     | 164310/371472 [2:06:38<18:07:27,  3.18it/s]
 44%|████▍     | 164311/371472 [2:06:39<17:37:51,  3.26it/s]
 44%|████▍     | 164312/371472 [2:06:39<18:57:05,  3.04it/s]
 44%|████▍     | 164313/371472 [2:06:39<18:26:37,  3.12it/s]
 44%|████▍     | 164314/371472 [2:06:40<17:48:02,  3.23it/s]
 44%|████▍     | 164315/371472 [2:06:40<17:16:20,  3.33it/s]
 44%|████▍     | 164316/371472 [2:06:40<17:09:34,  3.35it/s]
 44%|████▍     | 164317/371472 [2:06:40<17:29:25,  3.29it/s]
 44%|████▍     | 164318/371472 [2:06:41<17:26:43,  3.30it/s]
 44%|████▍     | 164319/371472 [2:06:41<17:36:30,  3.27it/s]
 44%|████▍     | 164320/371472 [2:06:41<17:13:00,  3.34it/s]
                                                            
{'loss': 2.8864, 'learning_rate': 6.021569092201943e-07, 'epoch': 7.08}
+
 44%|████▍     | 164320/371472 [2:06:41<17:13:00,  3.34it/s]
 44%|████▍     | 164321/371472 [2:06:42<16:54:34,  3.40it/s]
 44%|████▍     | 164322/371472 [2:06:42<16:37:27,  3.46it/s]
 44%|████▍     | 164323/371472 [2:06:42<16:39:27,  3.45it/s]
 44%|████▍     | 164324/371472 [2:06:43<17:07:42,  3.36it/s]
 44%|████▍     | 164325/371472 [2:06:43<17:00:30,  3.38it/s]
 44%|████▍     | 164326/371472 [2:06:43<16:51:05,  3.41it/s]
 44%|████▍     | 164327/371472 [2:06:43<17:52:14,  3.22it/s]
 44%|████▍     | 164328/371472 [2:06:44<17:50:37,  3.22it/s]
 44%|████▍     | 164329/371472 [2:06:44<17:35:02,  3.27it/s]
 44%|████▍     | 164330/371472 [2:06:44<17:04:16,  3.37it/s]
 44%|████▍     | 164331/371472 [2:06:45<17:07:07,  3.36it/s]
 44%|████▍     | 164332/371472 [2:06:45<17:10:00,  3.35it/s]
 44%|████▍     | 164333/371472 [2:06:45<17:43:40,  3.25it/s]
 44%|████▍     | 164334/371472 [2:06:46<17:45:32,  3.24it/s]
 44%|████▍     | 164335/371472 [2:06:46<17:26:35,  3.30it/s]
 44%|████▍     | 164336/371472 [2:06:46<18:00:30,  3.20it/s]
 44%|████▍     | 164337/371472 [2:06:46<17:22:31,  3.31it/s]
 44%|████▍     | 164338/371472 [2:06:47<17:17:30,  3.33it/s]
 44%|████▍     | 164339/371472 [2:06:47<17:22:15,  3.31it/s]
 44%|████▍     | 164340/371472 [2:06:47<17:23:21,  3.31it/s]
                                                            
{'loss': 3.0425, 'learning_rate': 6.021084272447154e-07, 'epoch': 7.08}
+
 44%|████▍     | 164340/371472 [2:06:47<17:23:21,  3.31it/s]
 44%|████▍     | 164341/371472 [2:06:48<17:11:23,  3.35it/s]
 44%|████▍     | 164342/371472 [2:06:48<17:27:05,  3.30it/s]
 44%|████▍     | 164343/371472 [2:06:48<18:41:04,  3.08it/s]
 44%|████▍     | 164344/371472 [2:06:49<18:08:25,  3.17it/s]
 44%|████▍     | 164345/371472 [2:06:49<17:44:11,  3.24it/s]
 44%|████▍     | 164346/371472 [2:06:49<18:31:32,  3.11it/s]
 44%|████▍     | 164347/371472 [2:06:50<18:23:42,  3.13it/s]
 44%|████▍     | 164348/371472 [2:06:50<17:39:43,  3.26it/s]
 44%|████▍     | 164349/371472 [2:06:50<17:10:43,  3.35it/s]
 44%|████▍     | 164350/371472 [2:06:50<17:26:01,  3.30it/s]
 44%|████▍     | 164351/371472 [2:06:51<17:08:39,  3.36it/s]
 44%|████▍     | 164352/371472 [2:06:51<16:59:51,  3.38it/s]
 44%|████▍     | 164353/371472 [2:06:51<17:14:33,  3.34it/s]
 44%|████▍     | 164354/371472 [2:06:52<17:09:12,  3.35it/s]
 44%|████▍     | 164355/371472 [2:06:52<17:12:18,  3.34it/s]
 44%|████▍     | 164356/371472 [2:06:52<16:55:51,  3.40it/s]
 44%|████▍     | 164357/371472 [2:06:53<16:54:41,  3.40it/s]
 44%|████▍     | 164358/371472 [2:06:53<16:41:39,  3.45it/s]
 44%|████▍     | 164359/371472 [2:06:53<16:59:11,  3.39it/s]
 44%|████▍     | 164360/371472 [2:06:53<18:06:27,  3.18it/s]
                                                            
{'loss': 3.0696, 'learning_rate': 6.020599452692366e-07, 'epoch': 7.08}
+
 44%|████▍     | 164360/371472 [2:06:53<18:06:27,  3.18it/s]
 44%|████▍     | 164361/371472 [2:06:54<17:44:28,  3.24it/s]
 44%|████▍     | 164362/371472 [2:06:54<17:21:09,  3.32it/s]
 44%|████▍     | 164363/371472 [2:06:54<16:50:37,  3.42it/s]
 44%|████▍     | 164364/371472 [2:06:55<16:37:56,  3.46it/s]
 44%|████▍     | 164365/371472 [2:06:55<16:57:35,  3.39it/s]
 44%|████▍     | 164366/371472 [2:06:55<16:52:20,  3.41it/s]
 44%|████▍     | 164367/371472 [2:06:56<16:49:55,  3.42it/s]
 44%|████▍     | 164368/371472 [2:06:56<16:46:00,  3.43it/s]
 44%|████▍     | 164369/371472 [2:06:56<18:12:11,  3.16it/s]
 44%|████▍     | 164370/371472 [2:06:56<18:27:58,  3.12it/s]
 44%|████▍     | 164371/371472 [2:06:57<18:15:14,  3.15it/s]
 44%|████▍     | 164372/371472 [2:06:57<18:01:00,  3.19it/s]
 44%|████▍     | 164373/371472 [2:06:57<17:38:26,  3.26it/s]
 44%|████▍     | 164374/371472 [2:06:58<17:32:11,  3.28it/s]
 44%|████▍     | 164375/371472 [2:06:58<17:02:31,  3.38it/s]
 44%|████▍     | 164376/371472 [2:06:58<16:57:52,  3.39it/s]
 44%|████▍     | 164377/371472 [2:06:59<17:06:07,  3.36it/s]
 44%|████▍     | 164378/371472 [2:06:59<16:47:43,  3.43it/s]
 44%|████▍     | 164379/371472 [2:06:59<16:50:16,  3.42it/s]
 44%|████▍     | 164380/371472 [2:06:59<16:25:51,  3.50it/s]
                                                            
{'loss': 3.0198, 'learning_rate': 6.020114632937577e-07, 'epoch': 7.08}
+
 44%|████▍     | 164380/371472 [2:06:59<16:25:51,  3.50it/s]
 44%|████▍     | 164381/371472 [2:07:00<16:34:36,  3.47it/s]
 44%|████▍     | 164382/371472 [2:07:00<16:27:05,  3.50it/s]
 44%|████▍     | 164383/371472 [2:07:00<17:35:23,  3.27it/s]
 44%|████▍     | 164384/371472 [2:07:01<16:59:17,  3.39it/s]
 44%|████▍     | 164385/371472 [2:07:01<17:02:23,  3.38it/s]
 44%|████▍     | 164386/371472 [2:07:01<16:49:52,  3.42it/s]
 44%|████▍     | 164387/371472 [2:07:01<16:49:01,  3.42it/s]
 44%|████▍     | 164388/371472 [2:07:02<16:58:34,  3.39it/s]
 44%|████▍     | 164389/371472 [2:07:02<16:58:17,  3.39it/s]
 44%|████▍     | 164390/371472 [2:07:02<16:52:41,  3.41it/s]
 44%|████▍     | 164391/371472 [2:07:03<16:43:43,  3.44it/s]
 44%|████▍     | 164392/371472 [2:07:03<16:51:11,  3.41it/s]
 44%|████▍     | 164393/371472 [2:07:03<17:01:01,  3.38it/s]
 44%|████▍     | 164394/371472 [2:07:04<16:55:46,  3.40it/s]
 44%|████▍     | 164395/371472 [2:07:04<17:50:09,  3.23it/s]
 44%|████▍     | 164396/371472 [2:07:04<17:45:04,  3.24it/s]
 44%|████▍     | 164397/371472 [2:07:05<18:02:32,  3.19it/s]
 44%|████▍     | 164398/371472 [2:07:05<17:36:15,  3.27it/s]
 44%|████▍     | 164399/371472 [2:07:05<18:11:18,  3.16it/s]
 44%|████▍     | 164400/371472 [2:07:05<17:42:26,  3.25it/s]
                                                            
{'loss': 2.9285, 'learning_rate': 6.019629813182787e-07, 'epoch': 7.08}
+
 44%|████▍     | 164400/371472 [2:07:05<17:42:26,  3.25it/s]
 44%|████▍     | 164401/371472 [2:07:06<17:41:34,  3.25it/s]
 44%|████▍     | 164402/371472 [2:07:06<18:51:06,  3.05it/s]
 44%|████▍     | 164403/371472 [2:07:06<18:13:00,  3.16it/s]
 44%|████▍     | 164404/371472 [2:07:07<17:33:13,  3.28it/s]
 44%|████▍     | 164405/371472 [2:07:07<17:18:37,  3.32it/s]
 44%|████▍     | 164406/371472 [2:07:07<17:01:14,  3.38it/s]
 44%|████▍     | 164407/371472 [2:07:08<17:03:27,  3.37it/s]
 44%|████▍     | 164408/371472 [2:07:08<16:40:35,  3.45it/s]
 44%|████▍     | 164409/371472 [2:07:08<16:47:32,  3.43it/s]
 44%|████▍     | 164410/371472 [2:07:08<16:45:05,  3.43it/s]
 44%|████▍     | 164411/371472 [2:07:09<16:34:01,  3.47it/s]
 44%|████▍     | 164412/371472 [2:07:09<16:38:46,  3.46it/s]
 44%|████▍     | 164413/371472 [2:07:09<17:41:20,  3.25it/s]
 44%|████▍     | 164414/371472 [2:07:10<17:13:10,  3.34it/s]
 44%|████▍     | 164415/371472 [2:07:10<17:12:01,  3.34it/s]
 44%|████▍     | 164416/371472 [2:07:10<17:53:12,  3.22it/s]
 44%|████▍     | 164417/371472 [2:07:11<17:44:35,  3.24it/s]
 44%|████▍     | 164418/371472 [2:07:11<17:15:10,  3.33it/s]
 44%|████▍     | 164419/371472 [2:07:11<17:37:00,  3.26it/s]
 44%|████▍     | 164420/371472 [2:07:11<17:43:49,  3.24it/s]
                                                            
{'loss': 3.0015, 'learning_rate': 6.019144993427998e-07, 'epoch': 7.08}
+
 44%|████▍     | 164420/371472 [2:07:11<17:43:49,  3.24it/s]
 44%|████▍     | 164421/371472 [2:07:12<17:43:50,  3.24it/s]
 44%|████▍     | 164422/371472 [2:07:12<17:15:21,  3.33it/s]
 44%|████▍     | 164423/371472 [2:07:12<16:41:23,  3.45it/s]
 44%|████▍     | 164424/371472 [2:07:13<16:52:05,  3.41it/s]
 44%|████▍     | 164425/371472 [2:07:13<16:33:49,  3.47it/s]
 44%|████▍     | 164426/371472 [2:07:13<18:26:35,  3.12it/s]
 44%|████▍     | 164427/371472 [2:07:14<18:48:13,  3.06it/s]
 44%|████▍     | 164428/371472 [2:07:14<18:19:19,  3.14it/s]
 44%|████▍     | 164429/371472 [2:07:14<17:49:19,  3.23it/s]
 44%|████▍     | 164430/371472 [2:07:15<17:23:53,  3.31it/s]
 44%|████▍     | 164431/371472 [2:07:15<17:33:45,  3.27it/s]
 44%|████▍     | 164432/371472 [2:07:15<17:06:54,  3.36it/s]
 44%|████▍     | 164433/371472 [2:07:15<17:23:18,  3.31it/s]
 44%|████▍     | 164434/371472 [2:07:16<16:42:15,  3.44it/s]
 44%|████▍     | 164435/371472 [2:07:16<17:19:00,  3.32it/s]
 44%|████▍     | 164436/371472 [2:07:16<17:21:46,  3.31it/s]
 44%|████▍     | 164437/371472 [2:07:17<18:01:09,  3.19it/s]
 44%|████▍     | 164438/371472 [2:07:17<17:44:04,  3.24it/s]
 44%|████▍     | 164439/371472 [2:07:17<17:29:13,  3.29it/s]
 44%|████▍     | 164440/371472 [2:07:18<17:50:40,  3.22it/s]
                                                            
{'loss': 3.0201, 'learning_rate': 6.01866017367321e-07, 'epoch': 7.08}
+
 44%|████▍     | 164440/371472 [2:07:18<17:50:40,  3.22it/s]
 44%|████▍     | 164441/371472 [2:07:18<17:48:30,  3.23it/s]
 44%|████▍     | 164442/371472 [2:07:18<17:09:46,  3.35it/s]
 44%|████▍     | 164443/371472 [2:07:18<16:54:14,  3.40it/s]
 44%|████▍     | 164444/371472 [2:07:19<16:53:21,  3.40it/s]
 44%|████▍     | 164445/371472 [2:07:19<16:55:44,  3.40it/s]
 44%|████▍     | 164446/371472 [2:07:19<17:35:51,  3.27it/s]
 44%|████▍     | 164447/371472 [2:07:20<17:25:49,  3.30it/s]
 44%|████▍     | 164448/371472 [2:07:20<16:59:54,  3.38it/s]
 44%|████▍     | 164449/371472 [2:07:20<16:45:01,  3.43it/s]
 44%|████▍     | 164450/371472 [2:07:21<16:28:09,  3.49it/s]
 44%|████▍     | 164451/371472 [2:07:21<16:24:35,  3.50it/s]
 44%|████▍     | 164452/371472 [2:07:21<17:45:16,  3.24it/s]
 44%|████▍     | 164453/371472 [2:07:21<16:51:42,  3.41it/s]
 44%|████▍     | 164454/371472 [2:07:22<16:32:26,  3.48it/s]
 44%|████▍     | 164455/371472 [2:07:22<16:53:58,  3.40it/s]
 44%|████▍     | 164456/371472 [2:07:22<16:42:59,  3.44it/s]
 44%|████▍     | 164457/371472 [2:07:23<16:14:36,  3.54it/s]
 44%|████▍     | 164458/371472 [2:07:23<17:52:19,  3.22it/s]
 44%|████▍     | 164459/371472 [2:07:23<17:25:30,  3.30it/s]
 44%|████▍     | 164460/371472 [2:07:23<17:06:32,  3.36it/s]
                                                            
{'loss': 3.0112, 'learning_rate': 6.018175353918421e-07, 'epoch': 7.08}
+
 44%|████▍     | 164460/371472 [2:07:23<17:06:32,  3.36it/s]
 44%|████▍     | 164461/371472 [2:07:24<18:07:25,  3.17it/s]
 44%|████▍     | 164462/371472 [2:07:24<17:56:07,  3.21it/s]
 44%|████▍     | 164463/371472 [2:07:24<17:40:52,  3.25it/s]
 44%|████▍     | 164464/371472 [2:07:25<18:13:48,  3.15it/s]
 44%|████▍     | 164465/371472 [2:07:25<17:59:38,  3.20it/s]
 44%|████▍     | 164466/371472 [2:07:25<17:54:53,  3.21it/s]
 44%|████▍     | 164467/371472 [2:07:26<18:04:07,  3.18it/s]
 44%|████▍     | 164468/371472 [2:07:26<18:20:28,  3.14it/s]
 44%|████▍     | 164469/371472 [2:07:26<18:05:21,  3.18it/s]
 44%|████▍     | 164470/371472 [2:07:27<17:43:53,  3.24it/s]
 44%|████▍     | 164471/371472 [2:07:27<17:33:17,  3.28it/s]
 44%|████▍     | 164472/371472 [2:07:27<17:19:59,  3.32it/s]
 44%|████▍     | 164473/371472 [2:07:28<18:48:14,  3.06it/s]
 44%|████▍     | 164474/371472 [2:07:28<18:48:02,  3.06it/s]
 44%|████▍     | 164475/371472 [2:07:28<19:35:25,  2.94it/s]
 44%|████▍     | 164476/371472 [2:07:29<19:51:07,  2.90it/s]
 44%|████▍     | 164477/371472 [2:07:29<18:55:21,  3.04it/s]
 44%|████▍     | 164478/371472 [2:07:29<19:10:30,  3.00it/s]
 44%|████▍     | 164479/371472 [2:07:30<18:57:28,  3.03it/s]
 44%|████▍     | 164480/371472 [2:07:30<18:37:48,  3.09it/s]
                                                            
{'loss': 2.8393, 'learning_rate': 6.017690534163631e-07, 'epoch': 7.08}
+
 44%|████▍     | 164480/371472 [2:07:30<18:37:48,  3.09it/s]
 44%|████▍     | 164481/371472 [2:07:30<18:22:26,  3.13it/s]
 44%|████▍     | 164482/371472 [2:07:31<18:14:23,  3.15it/s]
 44%|████▍     | 164483/371472 [2:07:31<18:49:49,  3.05it/s]
 44%|████▍     | 164484/371472 [2:07:31<17:48:29,  3.23it/s]
 44%|████▍     | 164485/371472 [2:07:31<17:32:21,  3.28it/s]
 44%|████▍     | 164486/371472 [2:07:32<17:19:06,  3.32it/s]
 44%|████▍     | 164487/371472 [2:07:32<17:23:20,  3.31it/s]
 44%|████▍     | 164488/371472 [2:07:32<18:24:55,  3.12it/s]
 44%|████▍     | 164489/371472 [2:07:33<17:56:53,  3.20it/s]
 44%|████▍     | 164490/371472 [2:07:33<17:22:27,  3.31it/s]
 44%|████▍     | 164491/371472 [2:07:33<17:24:05,  3.30it/s]
 44%|████▍     | 164492/371472 [2:07:34<16:58:07,  3.39it/s]
 44%|████▍     | 164493/371472 [2:07:34<18:07:24,  3.17it/s]
 44%|████▍     | 164494/371472 [2:07:34<17:16:06,  3.33it/s]
 44%|████▍     | 164495/371472 [2:07:35<17:48:54,  3.23it/s]
 44%|████▍     | 164496/371472 [2:07:35<16:56:54,  3.39it/s]
 44%|████▍     | 164497/371472 [2:07:35<17:30:00,  3.29it/s]
 44%|████▍     | 164498/371472 [2:07:35<17:27:15,  3.29it/s]
 44%|████▍     | 164499/371472 [2:07:36<17:00:09,  3.38it/s]
 44%|████▍     | 164500/371472 [2:07:36<17:00:41,  3.38it/s]
                                                            
{'loss': 2.9475, 'learning_rate': 6.017205714408843e-07, 'epoch': 7.09}
+
 44%|████▍     | 164500/371472 [2:07:36<17:00:41,  3.38it/s]
 44%|████▍     | 164501/371472 [2:07:36<17:12:49,  3.34it/s]
 44%|████▍     | 164502/371472 [2:07:37<16:45:13,  3.43it/s]
 44%|████▍     | 164503/371472 [2:07:37<16:31:42,  3.48it/s]
 44%|████▍     | 164504/371472 [2:07:37<16:44:02,  3.44it/s]
 44%|████▍     | 164505/371472 [2:07:38<17:56:41,  3.20it/s]
 44%|████▍     | 164506/371472 [2:07:38<17:27:55,  3.29it/s]
 44%|████▍     | 164507/371472 [2:07:38<17:11:07,  3.35it/s]
 44%|████▍     | 164508/371472 [2:07:38<16:53:58,  3.40it/s]
 44%|████▍     | 164509/371472 [2:07:39<17:05:20,  3.36it/s]
 44%|████▍     | 164510/371472 [2:07:39<16:55:15,  3.40it/s]
 44%|████▍     | 164511/371472 [2:07:39<18:32:15,  3.10it/s]
 44%|████▍     | 164512/371472 [2:07:40<18:04:22,  3.18it/s]
 44%|████▍     | 164513/371472 [2:07:40<18:53:21,  3.04it/s]
 44%|████▍     | 164514/371472 [2:07:40<20:24:34,  2.82it/s]
 44%|████▍     | 164515/371472 [2:07:41<18:59:05,  3.03it/s]
 44%|████▍     | 164516/371472 [2:07:41<18:15:23,  3.15it/s]
 44%|████▍     | 164517/371472 [2:07:41<17:36:26,  3.26it/s]
 44%|████▍     | 164518/371472 [2:07:42<17:01:59,  3.38it/s]
 44%|████▍     | 164519/371472 [2:07:42<17:04:54,  3.37it/s]
 44%|████▍     | 164520/371472 [2:07:42<19:30:20,  2.95it/s]
                                                            
{'loss': 2.8907, 'learning_rate': 6.016720894654054e-07, 'epoch': 7.09}
+
 44%|████▍     | 164520/371472 [2:07:42<19:30:20,  2.95it/s]
 44%|████▍     | 164521/371472 [2:07:43<19:43:06,  2.92it/s]
 44%|████▍     | 164522/371472 [2:07:43<19:01:49,  3.02it/s]
 44%|████▍     | 164523/371472 [2:07:43<19:27:41,  2.95it/s]
 44%|████▍     | 164524/371472 [2:07:44<20:04:31,  2.86it/s]
 44%|████▍     | 164525/371472 [2:07:44<19:02:51,  3.02it/s]
 44%|████▍     | 164526/371472 [2:07:44<18:58:35,  3.03it/s]
 44%|████▍     | 164527/371472 [2:07:45<17:51:25,  3.22it/s]
 44%|████▍     | 164528/371472 [2:07:45<17:47:21,  3.23it/s]
 44%|████▍     | 164529/371472 [2:07:45<17:47:24,  3.23it/s]
 44%|████▍     | 164530/371472 [2:07:45<17:48:13,  3.23it/s]
 44%|████▍     | 164531/371472 [2:07:46<18:42:05,  3.07it/s]
 44%|████▍     | 164532/371472 [2:07:46<17:53:58,  3.21it/s]
 44%|████▍     | 164533/371472 [2:07:46<17:29:18,  3.29it/s]
 44%|████▍     | 164534/371472 [2:07:47<17:14:56,  3.33it/s]
 44%|████▍     | 164535/371472 [2:07:47<16:52:40,  3.41it/s]
 44%|████▍     | 164536/371472 [2:07:47<17:07:35,  3.36it/s]
 44%|████▍     | 164537/371472 [2:07:48<18:31:35,  3.10it/s]
 44%|████▍     | 164538/371472 [2:07:48<17:57:39,  3.20it/s]
 44%|████▍     | 164539/371472 [2:07:48<17:17:13,  3.33it/s]
 44%|████▍     | 164540/371472 [2:07:49<17:34:46,  3.27it/s]
                                                            
{'loss': 2.8161, 'learning_rate': 6.016236074899265e-07, 'epoch': 7.09}
+
 44%|████▍     | 164540/371472 [2:07:49<17:34:46,  3.27it/s]
 44%|████▍     | 164541/371472 [2:07:49<17:03:01,  3.37it/s]
 44%|████▍     | 164542/371472 [2:07:49<16:49:17,  3.42it/s]
 44%|████▍     | 164543/371472 [2:07:49<17:16:01,  3.33it/s]
 44%|████▍     | 164544/371472 [2:07:50<18:12:51,  3.16it/s]
 44%|████▍     | 164545/371472 [2:07:50<17:56:59,  3.20it/s]
 44%|████▍     | 164546/371472 [2:07:50<18:08:50,  3.17it/s]
 44%|████▍     | 164547/371472 [2:07:51<18:19:56,  3.14it/s]
 44%|████▍     | 164548/371472 [2:07:51<17:45:02,  3.24it/s]
 44%|████▍     | 164549/371472 [2:07:51<17:46:46,  3.23it/s]
 44%|████▍     | 164550/371472 [2:07:52<17:45:13,  3.24it/s]
 44%|████▍     | 164551/371472 [2:07:52<17:40:35,  3.25it/s]
 44%|████▍     | 164552/371472 [2:07:52<16:56:43,  3.39it/s]
 44%|████▍     | 164553/371472 [2:07:53<17:17:47,  3.32it/s]
 44%|████▍     | 164554/371472 [2:07:53<17:05:41,  3.36it/s]
 44%|████▍     | 164555/371472 [2:07:53<17:12:13,  3.34it/s]
 44%|████▍     | 164556/371472 [2:07:53<17:18:33,  3.32it/s]
 44%|████▍     | 164557/371472 [2:07:54<17:08:01,  3.35it/s]
 44%|████▍     | 164558/371472 [2:07:54<17:35:39,  3.27it/s]
 44%|████▍     | 164559/371472 [2:07:54<17:44:18,  3.24it/s]
 44%|████▍     | 164560/371472 [2:07:55<17:26:36,  3.29it/s]
                                                            
{'loss': 3.0204, 'learning_rate': 6.015751255144475e-07, 'epoch': 7.09}
+
 44%|████▍     | 164560/371472 [2:07:55<17:26:36,  3.29it/s]
 44%|████▍     | 164561/371472 [2:07:55<17:23:27,  3.30it/s]
 44%|████▍     | 164562/371472 [2:07:55<17:22:36,  3.31it/s]
 44%|████▍     | 164563/371472 [2:07:56<17:24:58,  3.30it/s]
 44%|████▍     | 164564/371472 [2:07:56<18:19:58,  3.14it/s]
 44%|████▍     | 164565/371472 [2:07:56<17:43:16,  3.24it/s]
 44%|████▍     | 164566/371472 [2:07:56<17:35:44,  3.27it/s]
 44%|████▍     | 164567/371472 [2:07:57<17:58:25,  3.20it/s]
 44%|████▍     | 164568/371472 [2:07:57<17:42:53,  3.24it/s]
 44%|████▍     | 164569/371472 [2:07:57<17:24:05,  3.30it/s]
 44%|████▍     | 164570/371472 [2:07:58<17:07:38,  3.36it/s]
 44%|████▍     | 164571/371472 [2:07:58<16:34:36,  3.47it/s]
 44%|████▍     | 164572/371472 [2:07:58<17:36:07,  3.27it/s]
 44%|████▍     | 164573/371472 [2:07:59<17:34:15,  3.27it/s]
 44%|████▍     | 164574/371472 [2:07:59<18:36:27,  3.09it/s]
 44%|████▍     | 164575/371472 [2:07:59<18:31:27,  3.10it/s]
 44%|████▍     | 164576/371472 [2:08:00<18:04:54,  3.18it/s]
 44%|████▍     | 164577/371472 [2:08:00<18:57:59,  3.03it/s]
 44%|████▍     | 164578/371472 [2:08:00<18:10:56,  3.16it/s]
 44%|████▍     | 164579/371472 [2:08:01<17:39:12,  3.26it/s]
 44%|████▍     | 164580/371472 [2:08:01<17:25:31,  3.30it/s]
                                                            
{'loss': 2.9281, 'learning_rate': 6.015266435389687e-07, 'epoch': 7.09}
+
 44%|████▍     | 164580/371472 [2:08:01<17:25:31,  3.30it/s]
 44%|████▍     | 164581/371472 [2:08:01<17:14:33,  3.33it/s]
 44%|████▍     | 164582/371472 [2:08:01<16:56:33,  3.39it/s]
 44%|████▍     | 164583/371472 [2:08:02<16:43:02,  3.44it/s]
 44%|████▍     | 164584/371472 [2:08:02<16:14:27,  3.54it/s]
 44%|████▍     | 164585/371472 [2:08:02<16:01:12,  3.59it/s]
 44%|████▍     | 164586/371472 [2:08:03<16:16:41,  3.53it/s]
 44%|████▍     | 164587/371472 [2:08:03<16:26:31,  3.50it/s]
 44%|████▍     | 164588/371472 [2:08:03<16:43:09,  3.44it/s]
 44%|████▍     | 164589/371472 [2:08:03<16:14:21,  3.54it/s]
 44%|████▍     | 164590/371472 [2:08:04<16:11:47,  3.55it/s]
 44%|████▍     | 164591/371472 [2:08:04<15:56:04,  3.61it/s]
 44%|████▍     | 164592/371472 [2:08:04<16:24:02,  3.50it/s]
 44%|████▍     | 164593/371472 [2:08:04<16:25:00,  3.50it/s]
 44%|████▍     | 164594/371472 [2:08:05<16:30:02,  3.48it/s]
 44%|████▍     | 164595/371472 [2:08:05<16:38:46,  3.45it/s]
 44%|████▍     | 164596/371472 [2:08:05<16:38:54,  3.45it/s]
 44%|████▍     | 164597/371472 [2:08:06<17:00:37,  3.38it/s]
 44%|████▍     | 164598/371472 [2:08:06<17:54:40,  3.21it/s]
 44%|████▍     | 164599/371472 [2:08:07<24:00:23,  2.39it/s]
 44%|████▍     | 164600/371472 [2:08:07<21:52:02,  2.63it/s]
                                                            
{'loss': 2.9017, 'learning_rate': 6.014781615634899e-07, 'epoch': 7.09}
+
 44%|████▍     | 164600/371472 [2:08:07<21:52:02,  2.63it/s]
 44%|████▍     | 164601/371472 [2:08:07<20:36:13,  2.79it/s]
 44%|████▍     | 164602/371472 [2:08:08<21:27:52,  2.68it/s]
 44%|████▍     | 164603/371472 [2:08:08<20:31:21,  2.80it/s]
 44%|████▍     | 164604/371472 [2:08:08<19:19:02,  2.97it/s]
 44%|████▍     | 164605/371472 [2:08:09<18:24:25,  3.12it/s]
 44%|████▍     | 164606/371472 [2:08:09<18:04:48,  3.18it/s]
 44%|████▍     | 164607/371472 [2:08:09<17:32:32,  3.28it/s]
 44%|████▍     | 164608/371472 [2:08:09<17:22:10,  3.31it/s]
 44%|████▍     | 164609/371472 [2:08:10<16:54:25,  3.40it/s]
 44%|████▍     | 164610/371472 [2:08:10<17:10:08,  3.35it/s]
 44%|████▍     | 164611/371472 [2:08:10<17:42:22,  3.25it/s]
 44%|████▍     | 164612/371472 [2:08:11<17:18:38,  3.32it/s]
 44%|████▍     | 164613/371472 [2:08:11<16:54:09,  3.40it/s]
 44%|████▍     | 164614/371472 [2:08:11<16:52:00,  3.41it/s]
 44%|████▍     | 164615/371472 [2:08:12<17:01:44,  3.37it/s]
 44%|████▍     | 164616/371472 [2:08:12<16:49:20,  3.42it/s]
 44%|████▍     | 164617/371472 [2:08:12<16:41:47,  3.44it/s]
 44%|████▍     | 164618/371472 [2:08:12<16:36:13,  3.46it/s]
 44%|████▍     | 164619/371472 [2:08:13<16:31:29,  3.48it/s]
 44%|████▍     | 164620/371472 [2:08:13<16:31:12,  3.48it/s]
                                                            
{'loss': 2.8945, 'learning_rate': 6.01429679588011e-07, 'epoch': 7.09}
+
 44%|████▍     | 164620/371472 [2:08:13<16:31:12,  3.48it/s]
 44%|████▍     | 164621/371472 [2:08:13<16:16:00,  3.53it/s]
 44%|████▍     | 164622/371472 [2:08:14<16:04:17,  3.58it/s]
 44%|████▍     | 164623/371472 [2:08:14<16:33:05,  3.47it/s]
 44%|████▍     | 164624/371472 [2:08:14<16:40:09,  3.45it/s]
 44%|████▍     | 164625/371472 [2:08:14<16:31:31,  3.48it/s]
 44%|████▍     | 164626/371472 [2:08:15<16:19:23,  3.52it/s]
 44%|████▍     | 164627/371472 [2:08:15<16:34:53,  3.47it/s]
 44%|████▍     | 164628/371472 [2:08:15<16:25:03,  3.50it/s]
 44%|████▍     | 164629/371472 [2:08:16<16:27:03,  3.49it/s]
 44%|████▍     | 164630/371472 [2:08:16<17:52:03,  3.22it/s]
 44%|████▍     | 164631/371472 [2:08:16<17:17:10,  3.32it/s]
 44%|████▍     | 164632/371472 [2:08:16<16:58:56,  3.38it/s]
 44%|████▍     | 164633/371472 [2:08:17<17:41:06,  3.25it/s]
 44%|████▍     | 164634/371472 [2:08:17<17:22:49,  3.31it/s]
 44%|████▍     | 164635/371472 [2:08:17<17:19:42,  3.32it/s]
 44%|████▍     | 164636/371472 [2:08:18<17:02:32,  3.37it/s]
 44%|████▍     | 164637/371472 [2:08:18<16:57:54,  3.39it/s]
 44%|████▍     | 164638/371472 [2:08:18<16:37:00,  3.46it/s]
 44%|████▍     | 164639/371472 [2:08:19<16:50:08,  3.41it/s]
 44%|████▍     | 164640/371472 [2:08:19<17:04:51,  3.36it/s]
                                                            
{'loss': 2.972, 'learning_rate': 6.01381197612532e-07, 'epoch': 7.09}
+
 44%|████▍     | 164640/371472 [2:08:19<17:04:51,  3.36it/s]
 44%|████▍     | 164641/371472 [2:08:19<17:36:06,  3.26it/s]
 44%|████▍     | 164642/371472 [2:08:19<16:54:27,  3.40it/s]
 44%|████▍     | 164643/371472 [2:08:20<16:49:02,  3.42it/s]
 44%|████▍     | 164644/371472 [2:08:20<16:43:17,  3.44it/s]
 44%|████▍     | 164645/371472 [2:08:20<16:23:31,  3.50it/s]
 44%|████▍     | 164646/371472 [2:08:21<16:50:08,  3.41it/s]
 44%|████▍     | 164647/371472 [2:08:21<17:07:06,  3.36it/s]
 44%|████▍     | 164648/371472 [2:08:21<17:01:06,  3.38it/s]
 44%|████▍     | 164649/371472 [2:08:22<17:40:10,  3.25it/s]
 44%|████▍     | 164650/371472 [2:08:22<17:48:31,  3.23it/s]
 44%|████▍     | 164651/371472 [2:08:22<17:44:39,  3.24it/s]
 44%|████▍     | 164652/371472 [2:08:22<17:26:56,  3.29it/s]
 44%|████▍     | 164653/371472 [2:08:23<17:19:35,  3.32it/s]
 44%|████▍     | 164654/371472 [2:08:23<17:21:49,  3.31it/s]
 44%|████▍     | 164655/371472 [2:08:23<17:19:20,  3.32it/s]
 44%|████▍     | 164656/371472 [2:08:24<17:32:12,  3.28it/s]
 44%|████▍     | 164657/371472 [2:08:24<16:57:26,  3.39it/s]
 44%|████▍     | 164658/371472 [2:08:24<17:21:58,  3.31it/s]
 44%|████▍     | 164659/371472 [2:08:25<16:58:25,  3.38it/s]
 44%|████▍     | 164660/371472 [2:08:25<17:18:48,  3.32it/s]
                                                            
{'loss': 2.8434, 'learning_rate': 6.013327156370531e-07, 'epoch': 7.09}
+
 44%|████▍     | 164660/371472 [2:08:25<17:18:48,  3.32it/s]
 44%|████▍     | 164661/371472 [2:08:25<16:53:50,  3.40it/s]
 44%|████▍     | 164662/371472 [2:08:25<16:51:01,  3.41it/s]
 44%|████▍     | 164663/371472 [2:08:26<17:32:16,  3.28it/s]
 44%|████▍     | 164664/371472 [2:08:26<17:14:21,  3.33it/s]
 44%|████▍     | 164665/371472 [2:08:26<16:39:49,  3.45it/s]
 44%|████▍     | 164666/371472 [2:08:27<18:00:47,  3.19it/s]
 44%|████▍     | 164667/371472 [2:08:27<17:49:05,  3.22it/s]
 44%|████▍     | 164668/371472 [2:08:27<19:08:21,  3.00it/s]
 44%|████▍     | 164669/371472 [2:08:28<18:36:19,  3.09it/s]
 44%|████▍     | 164670/371472 [2:08:28<17:40:33,  3.25it/s]
 44%|████▍     | 164671/371472 [2:08:28<17:18:53,  3.32it/s]
 44%|████▍     | 164672/371472 [2:08:29<17:56:59,  3.20it/s]
 44%|████▍     | 164673/371472 [2:08:29<17:06:31,  3.36it/s]
 44%|████▍     | 164674/371472 [2:08:29<16:57:49,  3.39it/s]
 44%|████▍     | 164675/371472 [2:08:29<17:35:50,  3.26it/s]
 44%|████▍     | 164676/371472 [2:08:30<17:20:59,  3.31it/s]
 44%|████▍     | 164677/371472 [2:08:30<17:06:23,  3.36it/s]
 44%|████▍     | 164678/371472 [2:08:30<17:03:56,  3.37it/s]
 44%|████▍     | 164679/371472 [2:08:31<16:38:26,  3.45it/s]
 44%|████▍     | 164680/371472 [2:08:31<17:06:08,  3.36it/s]
                                                            
{'loss': 2.9673, 'learning_rate': 6.012842336615743e-07, 'epoch': 7.09}
+
 44%|████▍     | 164680/371472 [2:08:31<17:06:08,  3.36it/s]
 44%|████▍     | 164681/371472 [2:08:31<17:10:16,  3.35it/s]
 44%|████▍     | 164682/371472 [2:08:32<18:16:52,  3.14it/s]
 44%|████▍     | 164683/371472 [2:08:32<17:41:35,  3.25it/s]
 44%|████▍     | 164684/371472 [2:08:32<17:20:39,  3.31it/s]
 44%|████▍     | 164685/371472 [2:08:32<16:53:27,  3.40it/s]
 44%|████▍     | 164686/371472 [2:08:33<16:35:59,  3.46it/s]
 44%|████▍     | 164687/371472 [2:08:33<16:59:20,  3.38it/s]
 44%|████▍     | 164688/371472 [2:08:33<16:32:11,  3.47it/s]
 44%|████▍     | 164689/371472 [2:08:34<17:27:43,  3.29it/s]
 44%|████▍     | 164690/371472 [2:08:34<17:21:12,  3.31it/s]
 44%|████▍     | 164691/371472 [2:08:34<16:55:19,  3.39it/s]
 44%|████▍     | 164692/371472 [2:08:35<16:48:55,  3.42it/s]
 44%|████▍     | 164693/371472 [2:08:35<16:39:30,  3.45it/s]
 44%|████▍     | 164694/371472 [2:08:35<17:01:57,  3.37it/s]
 44%|████▍     | 164695/371472 [2:08:35<16:51:55,  3.41it/s]
 44%|████▍     | 164696/371472 [2:08:36<17:56:39,  3.20it/s]
 44%|████▍     | 164697/371472 [2:08:36<17:31:35,  3.28it/s]
 44%|████▍     | 164698/371472 [2:08:36<17:20:59,  3.31it/s]
 44%|████▍     | 164699/371472 [2:08:37<16:50:22,  3.41it/s]
 44%|████▍     | 164700/371472 [2:08:37<16:41:16,  3.44it/s]
                                                            
{'loss': 2.9604, 'learning_rate': 6.012357516860953e-07, 'epoch': 7.09}
+
 44%|████▍     | 164700/371472 [2:08:37<16:41:16,  3.44it/s]
 44%|████▍     | 164701/371472 [2:08:37<16:54:16,  3.40it/s]
 44%|████▍     | 164702/371472 [2:08:38<17:48:24,  3.23it/s]
 44%|████▍     | 164703/371472 [2:08:38<17:19:35,  3.31it/s]
 44%|████▍     | 164704/371472 [2:08:38<16:56:33,  3.39it/s]
 44%|████▍     | 164705/371472 [2:08:38<17:17:01,  3.32it/s]
 44%|████▍     | 164706/371472 [2:08:39<17:23:18,  3.30it/s]
 44%|████▍     | 164707/371472 [2:08:39<17:16:32,  3.32it/s]
 44%|████▍     | 164708/371472 [2:08:39<17:14:26,  3.33it/s]
 44%|████▍     | 164709/371472 [2:08:40<17:19:53,  3.31it/s]
 44%|████▍     | 164710/371472 [2:08:40<18:08:48,  3.16it/s]
 44%|████▍     | 164711/371472 [2:08:40<17:28:45,  3.29it/s]
 44%|████▍     | 164712/371472 [2:08:41<17:26:59,  3.29it/s]
 44%|████▍     | 164713/371472 [2:08:41<17:16:51,  3.32it/s]
 44%|████▍     | 164714/371472 [2:08:41<16:48:09,  3.42it/s]
 44%|████▍     | 164715/371472 [2:08:41<17:26:54,  3.29it/s]
 44%|████▍     | 164716/371472 [2:08:42<17:10:56,  3.34it/s]
 44%|████▍     | 164717/371472 [2:08:42<18:04:08,  3.18it/s]
 44%|████▍     | 164718/371472 [2:08:42<17:18:41,  3.32it/s]
 44%|████▍     | 164719/371472 [2:08:43<17:51:12,  3.22it/s]
 44%|████▍     | 164720/371472 [2:08:43<17:56:54,  3.20it/s]
                                                            
{'loss': 3.1189, 'learning_rate': 6.011872697106164e-07, 'epoch': 7.09}
+
 44%|████▍     | 164720/371472 [2:08:43<17:56:54,  3.20it/s]
 44%|████▍     | 164721/371472 [2:08:43<18:26:58,  3.11it/s]
 44%|████▍     | 164722/371472 [2:08:44<18:53:11,  3.04it/s]
 44%|████▍     | 164723/371472 [2:08:44<18:20:04,  3.13it/s]
 44%|████▍     | 164724/371472 [2:08:44<17:32:39,  3.27it/s]
 44%|████▍     | 164725/371472 [2:08:45<18:01:49,  3.19it/s]
 44%|████▍     | 164726/371472 [2:08:45<18:54:11,  3.04it/s]
 44%|████▍     | 164727/371472 [2:08:45<20:17:14,  2.83it/s]
 44%|████▍     | 164728/371472 [2:08:46<19:00:41,  3.02it/s]
 44%|████▍     | 164729/371472 [2:08:46<18:19:55,  3.13it/s]
 44%|████▍     | 164730/371472 [2:08:46<18:44:29,  3.06it/s]
 44%|████▍     | 164731/371472 [2:08:47<17:45:41,  3.23it/s]
 44%|████▍     | 164732/371472 [2:08:47<18:25:54,  3.12it/s]
 44%|████▍     | 164733/371472 [2:08:47<18:44:40,  3.06it/s]
 44%|████▍     | 164734/371472 [2:08:48<18:37:41,  3.08it/s]
 44%|████▍     | 164735/371472 [2:08:48<18:27:55,  3.11it/s]
 44%|████▍     | 164736/371472 [2:08:48<17:49:05,  3.22it/s]
 44%|████▍     | 164737/371472 [2:08:49<18:59:20,  3.02it/s]
 44%|████▍     | 164738/371472 [2:08:49<18:14:04,  3.15it/s]
 44%|████▍     | 164739/371472 [2:08:49<17:12:57,  3.34it/s]
 44%|████▍     | 164740/371472 [2:08:49<17:27:37,  3.29it/s]
                                                            
{'loss': 3.0591, 'learning_rate': 6.011387877351376e-07, 'epoch': 7.1}
+
 44%|████▍     | 164740/371472 [2:08:49<17:27:37,  3.29it/s]
 44%|████▍     | 164741/371472 [2:08:50<17:38:09,  3.26it/s]
 44%|████▍     | 164742/371472 [2:08:50<19:28:34,  2.95it/s]
 44%|████▍     | 164743/371472 [2:08:50<18:52:46,  3.04it/s]
 44%|████▍     | 164744/371472 [2:08:51<18:15:11,  3.15it/s]
 44%|████▍     | 164745/371472 [2:08:51<17:42:07,  3.24it/s]
 44%|████▍     | 164746/371472 [2:08:51<17:15:18,  3.33it/s]
 44%|████▍     | 164747/371472 [2:08:52<20:07:44,  2.85it/s]
 44%|████▍     | 164748/371472 [2:08:52<20:22:18,  2.82it/s]
 44%|████▍     | 164749/371472 [2:08:52<19:17:22,  2.98it/s]
 44%|████▍     | 164750/371472 [2:08:53<18:35:50,  3.09it/s]
 44%|████▍     | 164751/371472 [2:08:53<18:55:35,  3.03it/s]
 44%|████▍     | 164752/371472 [2:08:53<17:58:22,  3.19it/s]
 44%|████▍     | 164753/371472 [2:08:54<17:20:32,  3.31it/s]
 44%|████▍     | 164754/371472 [2:08:54<17:01:22,  3.37it/s]
 44%|████▍     | 164755/371472 [2:08:54<17:09:01,  3.35it/s]
 44%|████▍     | 164756/371472 [2:08:54<16:57:19,  3.39it/s]
 44%|████▍     | 164757/371472 [2:08:55<16:48:57,  3.41it/s]
 44%|████▍     | 164758/371472 [2:08:55<16:56:28,  3.39it/s]
 44%|████▍     | 164759/371472 [2:08:55<17:21:10,  3.31it/s]
 44%|████▍     | 164760/371472 [2:08:56<16:55:08,  3.39it/s]
                                                            
{'loss': 3.0443, 'learning_rate': 6.010903057596588e-07, 'epoch': 7.1}
+
 44%|████▍     | 164760/371472 [2:08:56<16:55:08,  3.39it/s]
 44%|████▍     | 164761/371472 [2:08:56<16:29:22,  3.48it/s]
 44%|████▍     | 164762/371472 [2:08:56<16:09:04,  3.56it/s]
 44%|████▍     | 164763/371472 [2:08:56<16:12:06,  3.54it/s]
 44%|████▍     | 164764/371472 [2:08:57<16:47:19,  3.42it/s]
 44%|████▍     | 164765/371472 [2:08:57<16:37:23,  3.45it/s]
 44%|████▍     | 164766/371472 [2:08:57<16:42:15,  3.44it/s]
 44%|████▍     | 164767/371472 [2:08:58<16:40:45,  3.44it/s]
 44%|████▍     | 164768/371472 [2:08:58<16:30:08,  3.48it/s]
 44%|████▍     | 164769/371472 [2:08:58<16:34:35,  3.46it/s]
 44%|████▍     | 164770/371472 [2:08:59<17:11:18,  3.34it/s]
 44%|████▍     | 164771/371472 [2:08:59<17:11:26,  3.34it/s]
 44%|████▍     | 164772/371472 [2:08:59<17:11:33,  3.34it/s]
 44%|████▍     | 164773/371472 [2:08:59<16:53:07,  3.40it/s]
 44%|████▍     | 164774/371472 [2:09:00<17:11:48,  3.34it/s]
 44%|████▍     | 164775/371472 [2:09:00<16:51:05,  3.41it/s]
 44%|████▍     | 164776/371472 [2:09:00<17:52:03,  3.21it/s]
 44%|████▍     | 164777/371472 [2:09:01<17:11:51,  3.34it/s]
 44%|████▍     | 164778/371472 [2:09:01<17:02:46,  3.37it/s]
 44%|████▍     | 164779/371472 [2:09:01<17:08:04,  3.35it/s]
 44%|████▍     | 164780/371472 [2:09:02<18:16:59,  3.14it/s]
                                                            
{'loss': 3.0799, 'learning_rate': 6.010418237841796e-07, 'epoch': 7.1}
+
 44%|████▍     | 164780/371472 [2:09:02<18:16:59,  3.14it/s]
 44%|████▍     | 164781/371472 [2:09:02<18:05:42,  3.17it/s]
 44%|████▍     | 164782/371472 [2:09:02<17:34:56,  3.27it/s]
 44%|████▍     | 164783/371472 [2:09:03<18:20:19,  3.13it/s]
 44%|████▍     | 164784/371472 [2:09:03<18:13:08,  3.15it/s]
 44%|████▍     | 164785/371472 [2:09:03<18:06:47,  3.17it/s]
 44%|████▍     | 164786/371472 [2:09:04<18:18:26,  3.14it/s]
 44%|████▍     | 164787/371472 [2:09:04<17:41:15,  3.25it/s]
 44%|████▍     | 164788/371472 [2:09:04<17:10:41,  3.34it/s]
 44%|████▍     | 164789/371472 [2:09:04<17:03:53,  3.36it/s]
 44%|████▍     | 164790/371472 [2:09:05<16:46:09,  3.42it/s]
 44%|████▍     | 164791/371472 [2:09:05<16:26:18,  3.49it/s]
 44%|████▍     | 164792/371472 [2:09:05<16:25:23,  3.50it/s]
 44%|████▍     | 164793/371472 [2:09:06<16:47:00,  3.42it/s]
 44%|████▍     | 164794/371472 [2:09:06<16:56:31,  3.39it/s]
 44%|████▍     | 164795/371472 [2:09:06<16:37:10,  3.45it/s]
 44%|████▍     | 164796/371472 [2:09:07<19:01:21,  3.02it/s]
 44%|████▍     | 164797/371472 [2:09:07<18:18:15,  3.14it/s]
 44%|████▍     | 164798/371472 [2:09:07<17:37:29,  3.26it/s]
 44%|████▍     | 164799/371472 [2:09:07<17:46:44,  3.23it/s]
 44%|████▍     | 164800/371472 [2:09:08<17:26:02,  3.29it/s]
                                                            
{'loss': 3.0805, 'learning_rate': 6.009933418087008e-07, 'epoch': 7.1}
+
 44%|████▍     | 164800/371472 [2:09:08<17:26:02,  3.29it/s]
 44%|████▍     | 164801/371472 [2:09:08<18:38:31,  3.08it/s]
 44%|████▍     | 164802/371472 [2:09:08<18:08:54,  3.16it/s]
 44%|████▍     | 164803/371472 [2:09:09<18:04:10,  3.18it/s]
 44%|████▍     | 164804/371472 [2:09:09<17:46:33,  3.23it/s]
 44%|████▍     | 164805/371472 [2:09:09<17:35:24,  3.26it/s]
 44%|████▍     | 164806/371472 [2:09:10<17:46:37,  3.23it/s]
 44%|████▍     | 164807/371472 [2:09:10<17:29:21,  3.28it/s]
 44%|████▍     | 164808/371472 [2:09:10<17:49:51,  3.22it/s]
 44%|████▍     | 164809/371472 [2:09:11<17:48:21,  3.22it/s]
 44%|████▍     | 164810/371472 [2:09:11<17:12:48,  3.33it/s]
 44%|████▍     | 164811/371472 [2:09:11<16:50:46,  3.41it/s]
 44%|████▍     | 164812/371472 [2:09:11<16:53:41,  3.40it/s]
 44%|████▍     | 164813/371472 [2:09:12<16:42:39,  3.44it/s]
 44%|████▍     | 164814/371472 [2:09:12<17:41:37,  3.24it/s]
 44%|████▍     | 164815/371472 [2:09:12<17:30:25,  3.28it/s]
 44%|████▍     | 164816/371472 [2:09:13<17:32:39,  3.27it/s]
 44%|████▍     | 164817/371472 [2:09:13<17:57:13,  3.20it/s]
 44%|████▍     | 164818/371472 [2:09:13<17:32:09,  3.27it/s]
 44%|████▍     | 164819/371472 [2:09:13<17:12:30,  3.34it/s]
 44%|████▍     | 164820/371472 [2:09:14<17:13:29,  3.33it/s]
                                                            
{'loss': 3.0189, 'learning_rate': 6.00944859833222e-07, 'epoch': 7.1}
+
 44%|████▍     | 164820/371472 [2:09:14<17:13:29,  3.33it/s]
 44%|████▍     | 164821/371472 [2:09:14<16:52:46,  3.40it/s]
 44%|████▍     | 164822/371472 [2:09:14<18:02:56,  3.18it/s]
 44%|████▍     | 164823/371472 [2:09:15<17:59:51,  3.19it/s]
 44%|████▍     | 164824/371472 [2:09:15<17:17:55,  3.32it/s]
 44%|████▍     | 164825/371472 [2:09:15<16:56:36,  3.39it/s]
 44%|████▍     | 164826/371472 [2:09:16<16:32:27,  3.47it/s]
 44%|████▍     | 164827/371472 [2:09:16<17:30:39,  3.28it/s]
 44%|████▍     | 164828/371472 [2:09:16<17:13:58,  3.33it/s]
 44%|████▍     | 164829/371472 [2:09:17<17:16:32,  3.32it/s]
 44%|████▍     | 164830/371472 [2:09:17<17:35:53,  3.26it/s]
 44%|████▍     | 164831/371472 [2:09:17<18:01:36,  3.18it/s]
 44%|████▍     | 164832/371472 [2:09:17<17:49:06,  3.22it/s]
 44%|████▍     | 164833/371472 [2:09:18<17:46:17,  3.23it/s]
 44%|████▍     | 164834/371472 [2:09:18<17:33:32,  3.27it/s]
 44%|████▍     | 164835/371472 [2:09:18<17:10:13,  3.34it/s]
 44%|████▍     | 164836/371472 [2:09:19<17:08:29,  3.35it/s]
 44%|████▍     | 164837/371472 [2:09:19<16:53:43,  3.40it/s]
 44%|████▍     | 164838/371472 [2:09:19<16:37:49,  3.45it/s]
 44%|████▍     | 164839/371472 [2:09:20<16:37:46,  3.45it/s]
 44%|████▍     | 164840/371472 [2:09:20<17:30:08,  3.28it/s]
                                                            
{'loss': 2.9508, 'learning_rate': 6.008963778577431e-07, 'epoch': 7.1}
+
 44%|████▍     | 164840/371472 [2:09:20<17:30:08,  3.28it/s]
 44%|████▍     | 164841/371472 [2:09:20<17:05:42,  3.36it/s]
 44%|████▍     | 164842/371472 [2:09:20<16:47:45,  3.42it/s]
 44%|████▍     | 164843/371472 [2:09:21<16:51:58,  3.40it/s]
 44%|████▍     | 164844/371472 [2:09:21<17:23:47,  3.30it/s]
 44%|████▍     | 164845/371472 [2:09:21<16:54:20,  3.40it/s]
 44%|████▍     | 164846/371472 [2:09:22<16:46:01,  3.42it/s]
 44%|████▍     | 164847/371472 [2:09:22<17:00:57,  3.37it/s]
 44%|████▍     | 164848/371472 [2:09:22<16:40:59,  3.44it/s]
 44%|████▍     | 164849/371472 [2:09:22<16:55:27,  3.39it/s]
 44%|████▍     | 164850/371472 [2:09:23<16:34:58,  3.46it/s]
 44%|████▍     | 164851/371472 [2:09:23<17:16:35,  3.32it/s]
 44%|████▍     | 164852/371472 [2:09:23<17:48:07,  3.22it/s]
 44%|████▍     | 164853/371472 [2:09:24<17:41:37,  3.24it/s]
 44%|████▍     | 164854/371472 [2:09:24<17:24:08,  3.30it/s]
 44%|████▍     | 164855/371472 [2:09:24<18:27:29,  3.11it/s]
 44%|████▍     | 164856/371472 [2:09:25<17:56:44,  3.20it/s]
 44%|████▍     | 164857/371472 [2:09:25<17:31:05,  3.28it/s]
 44%|████▍     | 164858/371472 [2:09:25<17:15:16,  3.33it/s]
 44%|████▍     | 164859/371472 [2:09:26<17:28:33,  3.28it/s]
 44%|████▍     | 164860/371472 [2:09:26<18:17:53,  3.14it/s]
                                                            
{'loss': 2.7667, 'learning_rate': 6.008478958822641e-07, 'epoch': 7.1}
+
 44%|████▍     | 164860/371472 [2:09:26<18:17:53,  3.14it/s]
 44%|████▍     | 164861/371472 [2:09:26<18:07:30,  3.17it/s]
 44%|████▍     | 164862/371472 [2:09:27<18:22:29,  3.12it/s]
 44%|████▍     | 164863/371472 [2:09:27<18:22:34,  3.12it/s]
 44%|████▍     | 164864/371472 [2:09:27<17:37:33,  3.26it/s]
 44%|████▍     | 164865/371472 [2:09:27<17:44:44,  3.23it/s]
 44%|████▍     | 164866/371472 [2:09:28<17:31:52,  3.27it/s]
 44%|████▍     | 164867/371472 [2:09:28<17:20:22,  3.31it/s]
 44%|████▍     | 164868/371472 [2:09:28<17:09:14,  3.35it/s]
 44%|████▍     | 164869/371472 [2:09:29<17:43:53,  3.24it/s]
 44%|████▍     | 164870/371472 [2:09:29<17:34:09,  3.27it/s]
 44%|████▍     | 164871/371472 [2:09:29<17:25:25,  3.29it/s]
 44%|████▍     | 164872/371472 [2:09:30<18:01:38,  3.18it/s]
 44%|████▍     | 164873/371472 [2:09:30<18:06:45,  3.17it/s]
 44%|████▍     | 164874/371472 [2:09:30<17:56:59,  3.20it/s]
 44%|████▍     | 164875/371472 [2:09:31<18:02:45,  3.18it/s]
 44%|████▍     | 164876/371472 [2:09:31<17:28:31,  3.28it/s]
 44%|████▍     | 164877/371472 [2:09:31<16:50:55,  3.41it/s]
 44%|████▍     | 164878/371472 [2:09:31<18:06:35,  3.17it/s]
 44%|████▍     | 164879/371472 [2:09:32<17:34:46,  3.26it/s]
 44%|████▍     | 164880/371472 [2:09:32<17:58:56,  3.19it/s]
                                                            
{'loss': 2.8482, 'learning_rate': 6.007994139067853e-07, 'epoch': 7.1}
+
 44%|████▍     | 164880/371472 [2:09:32<17:58:56,  3.19it/s]
 44%|████▍     | 164881/371472 [2:09:32<17:35:33,  3.26it/s]
 44%|████▍     | 164882/371472 [2:09:33<17:31:40,  3.27it/s]
 44%|████▍     | 164883/371472 [2:09:33<17:10:53,  3.34it/s]
 44%|████▍     | 164884/371472 [2:09:33<16:59:17,  3.38it/s]
 44%|████▍     | 164885/371472 [2:09:34<16:33:36,  3.47it/s]
 44%|████▍     | 164886/371472 [2:09:34<16:47:30,  3.42it/s]
 44%|████▍     | 164887/371472 [2:09:34<16:50:20,  3.41it/s]
 44%|████▍     | 164888/371472 [2:09:34<17:30:26,  3.28it/s]
 44%|████▍     | 164889/371472 [2:09:35<17:02:19,  3.37it/s]
 44%|████▍     | 164890/371472 [2:09:35<16:51:43,  3.40it/s]
 44%|████▍     | 164891/371472 [2:09:35<16:49:00,  3.41it/s]
 44%|████▍     | 164892/371472 [2:09:36<18:56:37,  3.03it/s]
 44%|████▍     | 164893/371472 [2:09:36<18:02:53,  3.18it/s]
 44%|████▍     | 164894/371472 [2:09:36<17:37:42,  3.26it/s]
 44%|████▍     | 164895/371472 [2:09:37<17:10:46,  3.34it/s]
 44%|████▍     | 164896/371472 [2:09:37<17:27:49,  3.29it/s]
 44%|████▍     | 164897/371472 [2:09:37<17:09:34,  3.34it/s]
 44%|████▍     | 164898/371472 [2:09:37<17:01:38,  3.37it/s]
 44%|████▍     | 164899/371472 [2:09:38<17:16:45,  3.32it/s]
 44%|████▍     | 164900/371472 [2:09:38<17:04:19,  3.36it/s]
                                                            
{'loss': 2.8236, 'learning_rate': 6.007509319313064e-07, 'epoch': 7.1}
+
 44%|████▍     | 164900/371472 [2:09:38<17:04:19,  3.36it/s]
 44%|████▍     | 164901/371472 [2:09:38<16:56:36,  3.39it/s]
 44%|████▍     | 164902/371472 [2:09:39<18:13:25,  3.15it/s]
 44%|████▍     | 164903/371472 [2:09:39<17:49:55,  3.22it/s]
 44%|████▍     | 164904/371472 [2:09:39<17:44:36,  3.23it/s]
 44%|████▍     | 164905/371472 [2:09:40<18:01:00,  3.18it/s]
 44%|████▍     | 164906/371472 [2:09:40<17:27:52,  3.29it/s]
 44%|████▍     | 164907/371472 [2:09:40<17:14:05,  3.33it/s]
 44%|████▍     | 164908/371472 [2:09:41<17:23:11,  3.30it/s]
 44%|████▍     | 164909/371472 [2:09:41<16:59:18,  3.38it/s]
 44%|████▍     | 164910/371472 [2:09:41<17:50:34,  3.22it/s]
 44%|████▍     | 164911/371472 [2:09:41<17:18:59,  3.31it/s]
 44%|████▍     | 164912/371472 [2:09:42<17:33:59,  3.27it/s]
 44%|████▍     | 164913/371472 [2:09:42<17:38:57,  3.25it/s]
 44%|████▍     | 164914/371472 [2:09:42<17:47:05,  3.23it/s]
 44%|████▍     | 164915/371472 [2:09:43<17:56:59,  3.20it/s]
 44%|████▍     | 164916/371472 [2:09:43<17:20:18,  3.31it/s]
 44%|████▍     | 164917/371472 [2:09:43<17:17:00,  3.32it/s]
 44%|████▍     | 164918/371472 [2:09:44<16:59:00,  3.38it/s]
 44%|████▍     | 164919/371472 [2:09:44<16:31:05,  3.47it/s]
 44%|████▍     | 164920/371472 [2:09:44<16:16:56,  3.52it/s]
                                                            
{'loss': 2.962, 'learning_rate': 6.007024499558275e-07, 'epoch': 7.1}
+
 44%|████▍     | 164920/371472 [2:09:44<16:16:56,  3.52it/s]
 44%|████▍     | 164921/371472 [2:09:44<15:52:35,  3.61it/s]
 44%|████▍     | 164922/371472 [2:09:45<16:01:09,  3.58it/s]
 44%|████▍     | 164923/371472 [2:09:45<15:44:36,  3.64it/s]
 44%|████▍     | 164924/371472 [2:09:45<19:23:13,  2.96it/s]
 44%|███���▍     | 164925/371472 [2:09:46<18:28:49,  3.10it/s]
 44%|████▍     | 164926/371472 [2:09:46<17:29:18,  3.28it/s]
 44%|████▍     | 164927/371472 [2:09:46<17:23:44,  3.30it/s]
 44%|████▍     | 164928/371472 [2:09:47<17:26:47,  3.29it/s]
 44%|████▍     | 164929/371472 [2:09:47<18:09:43,  3.16it/s]
 44%|████▍     | 164930/371472 [2:09:47<17:41:49,  3.24it/s]
 44%|████▍     | 164931/371472 [2:09:48<18:09:15,  3.16it/s]
 44%|████▍     | 164932/371472 [2:09:48<18:06:36,  3.17it/s]
 44%|████▍     | 164933/371472 [2:09:48<17:42:53,  3.24it/s]
 44%|████▍     | 164934/371472 [2:09:49<19:04:50,  3.01it/s]
 44%|████▍     | 164935/371472 [2:09:49<18:02:13,  3.18it/s]
 44%|████▍     | 164936/371472 [2:09:49<17:01:34,  3.37it/s]
 44%|████▍     | 164937/371472 [2:09:49<17:49:56,  3.22it/s]
 44%|████▍     | 164938/371472 [2:09:50<18:00:06,  3.19it/s]
 44%|████▍     | 164939/371472 [2:09:50<17:29:19,  3.28it/s]
 44%|████▍     | 164940/371472 [2:09:50<17:27:42,  3.29it/s]
                                                            
{'loss': 3.0985, 'learning_rate': 6.006539679803485e-07, 'epoch': 7.1}
+
 44%|████▍     | 164940/371472 [2:09:50<17:27:42,  3.29it/s]
 44%|████▍     | 164941/371472 [2:09:51<17:17:45,  3.32it/s]
 44%|████▍     | 164942/371472 [2:09:51<17:27:21,  3.29it/s]
 44%|████▍     | 164943/371472 [2:09:51<16:59:08,  3.38it/s]
 44%|████▍     | 164944/371472 [2:09:51<16:46:06,  3.42it/s]
 44%|████▍     | 164945/371472 [2:09:52<16:49:55,  3.41it/s]
 44%|████▍     | 164946/371472 [2:09:52<16:45:11,  3.42it/s]
 44%|████▍     | 164947/371472 [2:09:52<17:04:46,  3.36it/s]
 44%|████▍     | 164948/371472 [2:09:53<17:12:40,  3.33it/s]
 44%|████▍     | 164949/371472 [2:09:53<17:02:52,  3.37it/s]
 44%|████▍     | 164950/371472 [2:09:53<17:24:54,  3.29it/s]
 44%|████▍     | 164951/371472 [2:09:54<16:50:24,  3.41it/s]
 44%|████▍     | 164952/371472 [2:09:54<16:41:43,  3.44it/s]
 44%|████▍     | 164953/371472 [2:09:54<18:40:59,  3.07it/s]
 44%|████▍     | 164954/371472 [2:09:55<18:02:27,  3.18it/s]
 44%|████▍     | 164955/371472 [2:09:55<18:44:12,  3.06it/s]
 44%|████▍     | 164956/371472 [2:09:55<18:00:26,  3.19it/s]
 44%|████▍     | 164957/371472 [2:09:55<17:15:13,  3.32it/s]
 44%|████▍     | 164958/371472 [2:09:56<17:19:35,  3.31it/s]
 44%|████▍     | 164959/371472 [2:09:56<16:59:17,  3.38it/s]
 44%|████▍     | 164960/371472 [2:09:56<16:52:26,  3.40it/s]
                                                            
{'loss': 3.0049, 'learning_rate': 6.006054860048697e-07, 'epoch': 7.11}
+
 44%|████▍     | 164960/371472 [2:09:56<16:52:26,  3.40it/s]
 44%|████▍     | 164961/371472 [2:09:57<17:07:53,  3.35it/s]
 44%|████▍     | 164962/371472 [2:09:57<16:51:25,  3.40it/s]
 44%|████▍     | 164963/371472 [2:09:57<16:50:00,  3.41it/s]
 44%|████▍     | 164964/371472 [2:09:58<17:58:15,  3.19it/s]
 44%|████▍     | 164965/371472 [2:09:58<18:19:37,  3.13it/s]
 44%|████▍     | 164966/371472 [2:09:58<17:41:46,  3.24it/s]
 44%|████▍     | 164967/371472 [2:09:58<16:57:48,  3.38it/s]
 44%|████▍     | 164968/371472 [2:09:59<17:23:46,  3.30it/s]
 44%|████▍     | 164969/371472 [2:09:59<17:34:50,  3.26it/s]
 44%|████▍     | 164970/371472 [2:09:59<16:53:22,  3.40it/s]
 44%|████▍     | 164971/371472 [2:10:00<17:12:32,  3.33it/s]
 44%|████▍     | 164972/371472 [2:10:00<18:37:42,  3.08it/s]
 44%|████▍     | 164973/371472 [2:10:00<18:53:52,  3.04it/s]
 44%|████▍     | 164974/371472 [2:10:01<19:24:47,  2.95it/s]
 44%|████▍     | 164975/371472 [2:10:01<18:30:59,  3.10it/s]
 44%|████▍     | 164976/371472 [2:10:01<19:37:35,  2.92it/s]
 44%|████▍     | 164977/371472 [2:10:02<19:21:30,  2.96it/s]
 44%|████▍     | 164978/371472 [2:10:02<18:57:39,  3.03it/s]
 44%|████▍     | 164979/371472 [2:10:02<19:06:44,  3.00it/s]
 44%|████▍     | 164980/371472 [2:10:03<18:31:04,  3.10it/s]
                                                            
{'loss': 2.7876, 'learning_rate': 6.005570040293909e-07, 'epoch': 7.11}
+
 44%|████▍     | 164980/371472 [2:10:03<18:31:04,  3.10it/s]
 44%|████▍     | 164981/371472 [2:10:03<17:57:18,  3.19it/s]
 44%|████▍     | 164982/371472 [2:10:03<17:30:56,  3.27it/s]
 44%|████▍     | 164983/371472 [2:10:04<17:20:37,  3.31it/s]
 44%|████▍     | 164984/371472 [2:10:04<17:13:32,  3.33it/s]
 44%|████▍     | 164985/371472 [2:10:04<17:13:44,  3.33it/s]
 44%|████▍     | 164986/371472 [2:10:04<17:08:56,  3.34it/s]
 44%|████▍     | 164987/371472 [2:10:05<17:38:51,  3.25it/s]
 44%|████▍     | 164988/371472 [2:10:05<17:40:19,  3.25it/s]
 44%|████▍     | 164989/371472 [2:10:05<17:15:09,  3.32it/s]
 44%|████▍     | 164990/371472 [2:10:06<18:19:57,  3.13it/s]
 44%|████▍     | 164991/371472 [2:10:06<18:24:36,  3.12it/s]
 44%|████▍     | 164992/371472 [2:10:06<18:07:57,  3.16it/s]
 44%|████▍     | 164993/371472 [2:10:07<18:23:11,  3.12it/s]
 44%|████▍     | 164994/371472 [2:10:07<18:22:41,  3.12it/s]
 44%|████▍     | 164995/371472 [2:10:07<17:33:40,  3.27it/s]
 44%|████▍     | 164996/371472 [2:10:08<17:41:24,  3.24it/s]
 44%|████▍     | 164997/371472 [2:10:08<17:08:27,  3.35it/s]
 44%|████▍     | 164998/371472 [2:10:08<16:51:18,  3.40it/s]
 44%|████▍     | 164999/371472 [2:10:08<17:11:36,  3.34it/s]
 44%|████▍     | 165000/371472 [2:10:09<17:01:49,  3.37it/s]
                                                            
{'loss': 2.6748, 'learning_rate': 6.00508522053912e-07, 'epoch': 7.11}
+
 44%|████▍     | 165000/371472 [2:10:09<17:01:49,  3.37it/s]
 44%|████▍     | 165001/371472 [2:10:09<16:50:36,  3.41it/s]
 44%|████▍     | 165002/371472 [2:10:09<17:25:07,  3.29it/s]
 44%|████▍     | 165003/371472 [2:10:10<17:42:15,  3.24it/s]
 44%|████▍     | 165004/371472 [2:10:10<18:12:10,  3.15it/s]
 44%|████▍     | 165005/371472 [2:10:10<17:46:24,  3.23it/s]
 44%|████▍     | 165006/371472 [2:10:11<17:34:23,  3.26it/s]
 44%|████▍     | 165007/371472 [2:10:11<17:31:11,  3.27it/s]
 44%|████▍     | 165008/371472 [2:10:11<16:48:08,  3.41it/s]
 44%|████▍     | 165009/371472 [2:10:11<16:26:53,  3.49it/s]
 44%|████▍     | 165010/371472 [2:10:12<16:42:48,  3.43it/s]
 44%|████▍     | 165011/371472 [2:10:12<16:23:14,  3.50it/s]
 44%|████▍     | 165012/371472 [2:10:12<16:26:15,  3.49it/s]
 44%|████▍     | 165013/371472 [2:10:13<16:09:23,  3.55it/s]
 44%|████▍     | 165014/371472 [2:10:13<16:45:51,  3.42it/s]
 44%|████▍     | 165015/371472 [2:10:13<16:51:20,  3.40it/s]
 44%|████▍     | 165016/371472 [2:10:13<16:26:01,  3.49it/s]
 44%|████▍     | 165017/371472 [2:10:14<16:53:42,  3.39it/s]
 44%|████▍     | 165018/371472 [2:10:14<19:00:48,  3.02it/s]
 44%|████▍     | 165019/371472 [2:10:14<18:03:50,  3.17it/s]
 44%|████▍     | 165020/371472 [2:10:15<18:00:37,  3.18it/s]
                                                            
{'loss': 2.9568, 'learning_rate': 6.00460040078433e-07, 'epoch': 7.11}
+
 44%|████▍     | 165020/371472 [2:10:15<18:00:37,  3.18it/s]
 44%|████▍     | 165021/371472 [2:10:15<17:52:24,  3.21it/s]
 44%|████▍     | 165022/371472 [2:10:15<17:18:58,  3.31it/s]
 44%|████▍     | 165023/371472 [2:10:16<17:10:42,  3.34it/s]
 44%|████▍     | 165024/371472 [2:10:16<17:08:45,  3.34it/s]
 44%|████▍     | 165025/371472 [2:10:16<16:45:42,  3.42it/s]
 44%|████▍     | 165026/371472 [2:10:17<16:45:27,  3.42it/s]
 44%|████▍     | 165027/371472 [2:10:17<16:29:52,  3.48it/s]
 44%|████▍     | 165028/371472 [2:10:17<16:32:29,  3.47it/s]
 44%|████▍     | 165029/371472 [2:10:17<16:29:04,  3.48it/s]
 44%|████▍     | 165030/371472 [2:10:18<15:56:07,  3.60it/s]
 44%|████▍     | 165031/371472 [2:10:18<18:01:55,  3.18it/s]
 44%|████▍     | 165032/371472 [2:10:18<17:43:35,  3.23it/s]
 44%|████▍     | 165033/371472 [2:10:19<17:57:45,  3.19it/s]
 44%|████▍     | 165034/371472 [2:10:19<18:07:14,  3.16it/s]
 44%|████▍     | 165035/371472 [2:10:19<17:30:50,  3.27it/s]
 44%|████▍     | 165036/371472 [2:10:20<17:03:37,  3.36it/s]
 44%|████▍     | 165037/371472 [2:10:20<17:13:07,  3.33it/s]
 44%|████▍     | 165038/371472 [2:10:20<17:13:09,  3.33it/s]
 44%|████▍     | 165039/371472 [2:10:21<18:10:29,  3.16it/s]
 44%|████▍     | 165040/371472 [2:10:21<18:09:13,  3.16it/s]
                                                            
{'loss': 2.9358, 'learning_rate': 6.004115581029541e-07, 'epoch': 7.11}
+
 44%|████▍     | 165040/371472 [2:10:21<18:09:13,  3.16it/s]
 44%|████▍     | 165041/371472 [2:10:21<17:47:49,  3.22it/s]
 44%|████▍     | 165042/371472 [2:10:21<17:39:27,  3.25it/s]
 44%|████▍     | 165043/371472 [2:10:22<17:55:57,  3.20it/s]
 44%|████▍     | 165044/371472 [2:10:22<17:52:05,  3.21it/s]
 44%|████▍     | 165045/371472 [2:10:22<17:33:15,  3.27it/s]
 44%|████▍     | 165046/371472 [2:10:23<17:08:35,  3.34it/s]
 44%|████▍     | 165047/371472 [2:10:23<17:08:35,  3.34it/s]
 44%|████▍     | 165048/371472 [2:10:23<16:49:16,  3.41it/s]
 44%|████▍     | 165049/371472 [2:10:24<16:45:09,  3.42it/s]
 44%|████▍     | 165050/371472 [2:10:24<17:06:16,  3.35it/s]
 44%|████▍     | 165051/371472 [2:10:24<16:30:10,  3.47it/s]
 44%|████▍     | 165052/371472 [2:10:24<17:56:46,  3.20it/s]
 44%|████▍     | 165053/371472 [2:10:25<17:28:34,  3.28it/s]
 44%|████▍     | 165054/371472 [2:10:25<16:43:42,  3.43it/s]
 44%|████▍     | 165055/371472 [2:10:25<16:31:41,  3.47it/s]
 44%|████▍     | 165056/371472 [2:10:26<16:32:25,  3.47it/s]
 44%|████▍     | 165057/371472 [2:10:26<17:03:08,  3.36it/s]
 44%|████▍     | 165058/371472 [2:10:26<17:25:27,  3.29it/s]
 44%|████▍     | 165059/371472 [2:10:27<17:03:04,  3.36it/s]
 44%|████▍     | 165060/371472 [2:10:27<16:24:30,  3.49it/s]
                                                            
{'loss': 3.0014, 'learning_rate': 6.003630761274753e-07, 'epoch': 7.11}
+
 44%|████▍     | 165060/371472 [2:10:27<16:24:30,  3.49it/s]
 44%|████▍     | 165061/371472 [2:10:27<17:01:26,  3.37it/s]
 44%|████▍     | 165062/371472 [2:10:27<17:04:58,  3.36it/s]
 44%|████▍     | 165063/371472 [2:10:28<17:40:37,  3.24it/s]
 44%|████▍     | 165064/371472 [2:10:28<17:19:13,  3.31it/s]
 44%|████▍     | 165065/371472 [2:10:28<18:54:45,  3.03it/s]
 44%|████▍     | 165066/371472 [2:10:29<18:43:28,  3.06it/s]
 44%|████▍     | 165067/371472 [2:10:29<18:30:57,  3.10it/s]
 44%|████▍     | 165068/371472 [2:10:29<18:54:57,  3.03it/s]
 44%|████▍     | 165069/371472 [2:10:30<18:11:17,  3.15it/s]
 44%|████▍     | 165070/371472 [2:10:30<17:50:26,  3.21it/s]
 44%|████▍     | 165071/371472 [2:10:30<17:21:23,  3.30it/s]
 44%|████▍     | 165072/371472 [2:10:31<17:17:59,  3.31it/s]
 44%|████▍     | 165073/371472 [2:10:31<17:09:49,  3.34it/s]
 44%|████▍     | 165074/371472 [2:10:31<16:50:23,  3.40it/s]
 44%|████▍     | 165075/371472 [2:10:31<16:43:00,  3.43it/s]
 44%|████▍     | 165076/371472 [2:10:32<16:39:42,  3.44it/s]
 44%|████▍     | 165077/371472 [2:10:32<16:56:02,  3.39it/s]
 44%|████▍     | 165078/371472 [2:10:32<17:16:54,  3.32it/s]
 44%|████▍     | 165079/371472 [2:10:33<17:06:25,  3.35it/s]
 44%|████▍     | 165080/371472 [2:10:33<17:30:56,  3.27it/s]
                                                            
{'loss': 3.124, 'learning_rate': 6.003145941519964e-07, 'epoch': 7.11}
+
 44%|████▍     | 165080/371472 [2:10:33<17:30:56,  3.27it/s]
 44%|████▍     | 165081/371472 [2:10:33<17:06:00,  3.35it/s]
 44%|████▍     | 165082/371472 [2:10:34<18:25:30,  3.11it/s]
 44%|████▍     | 165083/371472 [2:10:34<17:27:40,  3.28it/s]
 44%|████▍     | 165084/371472 [2:10:34<17:13:58,  3.33it/s]
 44%|████▍     | 165085/371472 [2:10:34<17:42:26,  3.24it/s]
 44%|████▍     | 165086/371472 [2:10:35<17:39:59,  3.25it/s]
 44%|████▍     | 165087/371472 [2:10:35<17:58:05,  3.19it/s]
 44%|████▍     | 165088/371472 [2:10:35<17:49:49,  3.22it/s]
 44%|████▍     | 165089/371472 [2:10:36<17:20:48,  3.30it/s]
 44%|████▍     | 165090/371472 [2:10:36<17:31:03,  3.27it/s]
 44%|████▍     | 165091/371472 [2:10:36<17:23:35,  3.30it/s]
 44%|████▍     | 165092/371472 [2:10:37<18:59:53,  3.02it/s]
 44%|████▍     | 165093/371472 [2:10:37<18:37:07,  3.08it/s]
 44%|████▍     | 165094/371472 [2:10:37<18:50:46,  3.04it/s]
 44%|████▍     | 165095/371472 [2:10:38<18:32:24,  3.09it/s]
 44%|████▍     | 165096/371472 [2:10:38<17:56:06,  3.20it/s]
 44%|████▍     | 165097/371472 [2:10:38<17:48:31,  3.22it/s]
 44%|████▍     | 165098/371472 [2:10:39<18:27:02,  3.11it/s]
 44%|████▍     | 165099/371472 [2:10:39<17:29:45,  3.28it/s]
 44%|████▍     | 165100/371472 [2:10:39<17:36:35,  3.26it/s]
                                                            
{'loss': 3.0466, 'learning_rate': 6.002661121765174e-07, 'epoch': 7.11}
+
 44%|████▍     | 165100/371472 [2:10:39<17:36:35,  3.26it/s]
 44%|████▍     | 165101/371472 [2:10:40<18:11:21,  3.15it/s]
 44%|████▍     | 165102/371472 [2:10:40<18:09:51,  3.16it/s]
 44%|████▍     | 165103/371472 [2:10:40<17:58:12,  3.19it/s]
 44%|████▍     | 165104/371472 [2:10:40<17:53:04,  3.21it/s]
 44%|████▍     | 165105/371472 [2:10:41<18:04:14,  3.17it/s]
 44%|████▍     | 165106/371472 [2:10:41<17:11:22,  3.33it/s]
 44%|████▍     | 165107/371472 [2:10:41<18:36:31,  3.08it/s]
 44%|████▍     | 165108/371472 [2:10:42<18:02:07,  3.18it/s]
 44%|████▍     | 165109/371472 [2:10:42<17:10:33,  3.34it/s]
 44%|████▍     | 165110/371472 [2:10:42<16:56:51,  3.38it/s]
 44%|████▍     | 165111/371472 [2:10:43<16:54:17,  3.39it/s]
 44%|████▍     | 165112/371472 [2:10:43<18:54:59,  3.03it/s]
 44%|████▍     | 165113/371472 [2:10:43<18:37:07,  3.08it/s]
 44%|████▍     | 165114/371472 [2:10:44<18:01:16,  3.18it/s]
 44%|████▍     | 165115/371472 [2:10:44<17:59:06,  3.19it/s]
 44%|████▍     | 165116/371472 [2:10:44<17:49:05,  3.22it/s]
 44%|████▍     | 165117/371472 [2:10:45<18:06:27,  3.17it/s]
 44%|████▍     | 165118/371472 [2:10:45<17:13:57,  3.33it/s]
 44%|████▍     | 165119/371472 [2:10:45<17:16:18,  3.32it/s]
 44%|████▍     | 165120/371472 [2:10:45<17:02:43,  3.36it/s]
                                                            
{'loss': 2.8176, 'learning_rate': 6.002176302010386e-07, 'epoch': 7.11}
+
 44%|████▍     | 165120/371472 [2:10:45<17:02:43,  3.36it/s]
 44%|████▍     | 165121/371472 [2:10:46<16:43:58,  3.43it/s]
 44%|████▍     | 165122/371472 [2:10:46<16:39:23,  3.44it/s]
 44%|████▍     | 165123/371472 [2:10:46<16:28:51,  3.48it/s]
 44%|████▍     | 165124/371472 [2:10:46<16:13:24,  3.53it/s]
 44%|████▍     | 165125/371472 [2:10:47<16:21:29,  3.50it/s]
 44%|████▍     | 165126/371472 [2:10:47<15:49:05,  3.62it/s]
 44%|████▍     | 165127/371472 [2:10:47<15:46:42,  3.63it/s]
 44%|████▍     | 165128/371472 [2:10:48<16:24:53,  3.49it/s]
 44%|████▍     | 165129/371472 [2:10:48<16:20:42,  3.51it/s]
 44%|████▍     | 165130/371472 [2:10:48<16:08:50,  3.55it/s]
 44%|████▍     | 165131/371472 [2:10:49<17:13:31,  3.33it/s]
 44%|████▍     | 165132/371472 [2:10:49<18:06:26,  3.17it/s]
 44%|████▍     | 165133/371472 [2:10:49<18:05:29,  3.17it/s]
 44%|████▍     | 165134/371472 [2:10:49<17:27:47,  3.28it/s]
 44%|████▍     | 165135/371472 [2:10:50<17:45:25,  3.23it/s]
 44%|████▍     | 165136/371472 [2:10:50<17:30:49,  3.27it/s]
 44%|████▍     | 165137/371472 [2:10:50<17:54:59,  3.20it/s]
 44%|████▍     | 165138/371472 [2:10:51<17:44:45,  3.23it/s]
 44%|████▍     | 165139/371472 [2:10:51<16:59:01,  3.37it/s]
 44%|████▍     | 165140/371472 [2:10:51<16:57:00,  3.38it/s]
                                                            
{'loss': 2.9513, 'learning_rate': 6.001691482255598e-07, 'epoch': 7.11}
+
 44%|████▍     | 165140/371472 [2:10:51<16:57:00,  3.38it/s]
 44%|████▍     | 165141/371472 [2:10:52<17:13:24,  3.33it/s]
 44%|████▍     | 165142/371472 [2:10:52<16:45:05,  3.42it/s]
 44%|████▍     | 165143/371472 [2:10:52<16:32:25,  3.47it/s]
 44%|████▍     | 165144/371472 [2:10:52<16:44:22,  3.42it/s]
 44%|████▍     | 165145/371472 [2:10:53<16:40:00,  3.44it/s]
 44%|████▍     | 165146/371472 [2:10:53<16:49:24,  3.41it/s]
 44%|████▍     | 165147/371472 [2:10:53<16:26:17,  3.49it/s]
 44%|████▍     | 165148/371472 [2:10:54<16:24:12,  3.49it/s]
 44%|████▍     | 165149/371472 [2:10:54<16:10:16,  3.54it/s]
 44%|████▍     | 165150/371472 [2:10:54<16:36:55,  3.45it/s]
 44%|████▍     | 165151/371472 [2:10:54<16:31:00,  3.47it/s]
 44%|████▍     | 165152/371472 [2:10:55<17:10:53,  3.34it/s]
 44%|████▍     | 165153/371472 [2:10:55<16:37:18,  3.45it/s]
 44%|████▍     | 165154/371472 [2:10:55<16:55:10,  3.39it/s]
 44%|████▍     | 165155/371472 [2:10:56<17:03:50,  3.36it/s]
 44%|████▍     | 165156/371472 [2:10:56<17:11:39,  3.33it/s]
 44%|████▍     | 165157/371472 [2:10:56<17:06:02,  3.35it/s]
 44%|████▍     | 165158/371472 [2:10:57<17:27:52,  3.28it/s]
 44%|████▍     | 165159/371472 [2:10:57<17:05:22,  3.35it/s]
 44%|████▍     | 165160/371472 [2:10:57<16:52:54,  3.39it/s]
                                                            
{'loss': 3.0868, 'learning_rate': 6.001206662500807e-07, 'epoch': 7.11}
+
 44%|████▍     | 165160/371472 [2:10:57<16:52:54,  3.39it/s]
 44%|████▍     | 165161/371472 [2:10:57<16:22:20,  3.50it/s]
 44%|████▍     | 165162/371472 [2:10:58<16:20:39,  3.51it/s]
 44%|████▍     | 165163/371472 [2:10:58<16:09:27,  3.55it/s]
 44%|████▍     | 165164/371472 [2:10:58<16:22:34,  3.50it/s]
 44%|████▍     | 165165/371472 [2:10:59<17:15:34,  3.32it/s]
 44%|████▍     | 165166/371472 [2:10:59<17:16:34,  3.32it/s]
 44%|████▍     | 165167/371472 [2:10:59<17:10:39,  3.34it/s]
 44%|████▍     | 165168/371472 [2:10:59<16:55:19,  3.39it/s]
 44%|████▍     | 165169/371472 [2:11:00<16:43:13,  3.43it/s]
 44%|████▍     | 165170/371472 [2:11:00<16:39:11,  3.44it/s]
 44%|████▍     | 165171/371472 [2:11:00<17:50:11,  3.21it/s]
 44%|████▍     | 165172/371472 [2:11:01<17:44:37,  3.23it/s]
 44%|████▍     | 165173/371472 [2:11:01<17:52:17,  3.21it/s]
 44%|████▍     | 165174/371472 [2:11:01<17:22:22,  3.30it/s]
 44%|████▍     | 165175/371472 [2:11:02<17:52:27,  3.21it/s]
 44%|████▍     | 165176/371472 [2:11:02<18:47:53,  3.05it/s]
 44%|████▍     | 165177/371472 [2:11:02<18:51:22,  3.04it/s]
 44%|████▍     | 165178/371472 [2:11:03<18:03:17,  3.17it/s]
 44%|████▍     | 165179/371472 [2:11:03<18:02:37,  3.18it/s]
 44%|████▍     | 165180/371472 [2:11:03<17:52:17,  3.21it/s]
                                                            
{'loss': 2.8789, 'learning_rate': 6.000721842746018e-07, 'epoch': 7.11}
+
 44%|████▍     | 165180/371472 [2:11:03<17:52:17,  3.21it/s]
 44%|████▍     | 165181/371472 [2:11:04<17:28:32,  3.28it/s]
 44%|████▍     | 165182/371472 [2:11:04<17:18:35,  3.31it/s]
 44%|████▍     | 165183/371472 [2:11:04<17:46:25,  3.22it/s]
 44%|████▍     | 165184/371472 [2:11:04<17:06:48,  3.35it/s]
 44%|████▍     | 165185/371472 [2:11:05<16:52:09,  3.40it/s]
 44%|████▍     | 165186/371472 [2:11:05<17:52:01,  3.21it/s]
 44%|████▍     | 165187/371472 [2:11:05<17:40:03,  3.24it/s]
 44%|████▍     | 165188/371472 [2:11:06<17:16:26,  3.32it/s]
 44%|████▍     | 165189/371472 [2:11:06<16:58:25,  3.38it/s]
 44%|████▍     | 165190/371472 [2:11:06<17:06:48,  3.35it/s]
 44%|████▍     | 165191/371472 [2:11:07<17:08:28,  3.34it/s]
 44%|████▍     | 165192/371472 [2:11:07<17:13:17,  3.33it/s]
 44%|████▍     | 165193/371472 [2:11:07<17:10:35,  3.34it/s]
 44%|████▍     | 165194/371472 [2:11:07<17:14:12,  3.32it/s]
 44%|████▍     | 165195/371472 [2:11:08<16:49:31,  3.41it/s]
 44%|████▍     | 165196/371472 [2:11:08<16:56:32,  3.38it/s]
 44%|████▍     | 165197/371472 [2:11:08<17:45:59,  3.23it/s]
 44%|████▍     | 165198/371472 [2:11:09<18:09:54,  3.15it/s]
 44%|████▍     | 165199/371472 [2:11:09<18:06:17,  3.16it/s]
 44%|████▍     | 165200/371472 [2:11:09<17:36:50,  3.25it/s]
                                                            
{'loss': 2.9039, 'learning_rate': 6.00023702299123e-07, 'epoch': 7.12}
+
 44%|████▍     | 165200/371472 [2:11:09<17:36:50,  3.25it/s]
 44%|████▍     | 165201/371472 [2:11:10<17:54:55,  3.20it/s]
 44%|████▍     | 165202/371472 [2:11:10<17:42:58,  3.23it/s]
 44%|████▍     | 165203/371472 [2:11:10<17:21:30,  3.30it/s]
 44%|████▍     | 165204/371472 [2:11:11<17:57:14,  3.19it/s]
 44%|████▍     | 165205/371472 [2:11:11<18:01:35,  3.18it/s]
 44%|████▍     | 165206/371472 [2:11:11<18:01:56,  3.18it/s]
 44%|████▍     | 165207/371472 [2:11:11<17:08:52,  3.34it/s]
 44%|████▍     | 165208/371472 [2:11:12<16:56:48,  3.38it/s]
 44%|████▍     | 165209/371472 [2:11:12<16:48:47,  3.41it/s]
 44%|████▍     | 165210/371472 [2:11:12<16:21:15,  3.50it/s]
 44%|████▍     | 165211/371472 [2:11:13<16:10:25,  3.54it/s]
 44%|████▍     | 165212/371472 [2:11:13<16:11:34,  3.54it/s]
 44%|████▍     | 165213/371472 [2:11:13<16:22:21,  3.50it/s]
 44%|████▍     | 165214/371472 [2:11:13<16:28:48,  3.48it/s]
 44%|████▍     | 165215/371472 [2:11:14<16:34:29,  3.46it/s]
 44%|████▍     | 165216/371472 [2:11:14<16:07:16,  3.55it/s]
 44%|████▍     | 165217/371472 [2:11:14<17:24:29,  3.29it/s]
 44%|████▍     | 165218/371472 [2:11:15<17:14:10,  3.32it/s]
 44%|████▍     | 165219/371472 [2:11:15<17:18:19,  3.31it/s]
 44%|████▍     | 165220/371472 [2:11:15<17:24:00,  3.29it/s]
                                                            
{'loss': 3.0421, 'learning_rate': 5.999752203236441e-07, 'epoch': 7.12}
+
 44%|████▍     | 165220/371472 [2:11:15<17:24:00,  3.29it/s]
 44%|████▍     | 165221/371472 [2:11:16<17:21:30,  3.30it/s]
 44%|████▍     | 165222/371472 [2:11:16<17:22:19,  3.30it/s]
 44%|████▍     | 165223/371472 [2:11:16<17:10:38,  3.34it/s]
 44%|████▍     | 165224/371472 [2:11:16<16:53:55,  3.39it/s]
 44%|████▍     | 165225/371472 [2:11:17<17:45:55,  3.22it/s]
 44%|████▍     | 165226/371472 [2:11:17<17:45:50,  3.23it/s]
 44%|████▍     | 165227/371472 [2:11:17<17:27:42,  3.28it/s]
 44%|████▍     | 165228/371472 [2:11:18<17:01:25,  3.37it/s]
 44%|████▍     | 165229/371472 [2:11:18<16:48:58,  3.41it/s]
 44%|████▍     | 165230/371472 [2:11:18<18:50:31,  3.04it/s]
 44%|████▍     | 165231/371472 [2:11:19<19:24:04,  2.95it/s]
 44%|████▍     | 165232/371472 [2:11:19<19:37:22,  2.92it/s]
 44%|████▍     | 165233/371472 [2:11:19<18:38:54,  3.07it/s]
 44%|████▍     | 165234/371472 [2:11:20<18:10:33,  3.15it/s]
 44%|████▍     | 165235/371472 [2:11:20<17:29:29,  3.28it/s]
 44%|████▍     | 165236/371472 [2:11:20<17:06:43,  3.35it/s]
 44%|████▍     | 165237/371472 [2:11:21<17:17:59,  3.31it/s]
 44%|████▍     | 165238/371472 [2:11:21<16:47:22,  3.41it/s]
 44%|████▍     | 165239/371472 [2:11:21<16:58:03,  3.38it/s]
 44%|████▍     | 165240/371472 [2:11:21<16:51:35,  3.40it/s]
                                                            
{'loss': 2.7671, 'learning_rate': 5.999267383481652e-07, 'epoch': 7.12}
+
 44%|████▍     | 165240/371472 [2:11:21<16:51:35,  3.40it/s]
 44%|████▍     | 165241/371472 [2:11:22<18:03:40,  3.17it/s]
 44%|████▍     | 165242/371472 [2:11:22<17:25:50,  3.29it/s]
 44%|████▍     | 165243/371472 [2:11:22<17:38:44,  3.25it/s]
 44%|████▍     | 165244/371472 [2:11:23<17:47:31,  3.22it/s]
 44%|████▍     | 165245/371472 [2:11:23<18:38:16,  3.07it/s]
 44%|████▍     | 165246/371472 [2:11:23<18:14:06,  3.14it/s]
 44%|████▍     | 165247/371472 [2:11:24<18:35:13,  3.08it/s]
 44%|████▍     | 165248/371472 [2:11:24<18:00:02,  3.18it/s]
 44%|████▍     | 165249/371472 [2:11:24<17:35:07,  3.26it/s]
 44%|████▍     | 165250/371472 [2:11:25<19:23:41,  2.95it/s]
 44%|████▍     | 165251/371472 [2:11:25<19:06:51,  3.00it/s]
 44%|████▍     | 165252/371472 [2:11:25<18:21:21,  3.12it/s]
 44%|████▍     | 165253/371472 [2:11:26<17:58:38,  3.19it/s]
 44%|████▍     | 165254/371472 [2:11:26<17:43:19,  3.23it/s]
 44%|████▍     | 165255/371472 [2:11:26<17:25:34,  3.29it/s]
 44%|████▍     | 165256/371472 [2:11:26<17:00:00,  3.37it/s]
 44%|████▍     | 165257/371472 [2:11:27<16:45:17,  3.42it/s]
 44%|████▍     | 165258/371472 [2:11:27<16:34:38,  3.46it/s]
 44%|████▍     | 165259/371472 [2:11:27<17:48:43,  3.22it/s]
 44%|████▍     | 165260/371472 [2:11:28<18:54:20,  3.03it/s]
                                                            
{'loss': 2.997, 'learning_rate': 5.998782563726863e-07, 'epoch': 7.12}
+
 44%|████▍     | 165260/371472 [2:11:28<18:54:20,  3.03it/s]
 44%|████▍     | 165261/371472 [2:11:28<18:55:44,  3.03it/s]
 44%|████▍     | 165262/371472 [2:11:28<18:30:54,  3.09it/s]
 44%|████▍     | 165263/371472 [2:11:29<19:13:52,  2.98it/s]
 44%|████▍     | 165264/371472 [2:11:29<17:55:44,  3.19it/s]
 44%|████▍     | 165265/371472 [2:11:29<17:20:23,  3.30it/s]
 44%|████▍     | 165266/371472 [2:11:30<17:15:54,  3.32it/s]
 44%|████▍     | 165267/371472 [2:11:30<18:36:54,  3.08it/s]
 44%|████▍     | 165268/371472 [2:11:30<19:05:21,  3.00it/s]
 44%|████▍     | 165269/371472 [2:11:31<18:24:54,  3.11it/s]
 44%|████▍     | 165270/371472 [2:11:31<17:46:28,  3.22it/s]
 44%|████▍     | 165271/371472 [2:11:31<17:33:50,  3.26it/s]
 44%|████▍     | 165272/371472 [2:11:31<17:24:19,  3.29it/s]
 44%|████▍     | 165273/371472 [2:11:32<17:06:31,  3.35it/s]
 44%|████▍     | 165274/371472 [2:11:32<16:47:37,  3.41it/s]
 44%|████▍     | 165275/371472 [2:11:32<16:27:50,  3.48it/s]
 44%|████▍     | 165276/371472 [2:11:33<16:53:07,  3.39it/s]
 44%|████▍     | 165277/371472 [2:11:33<16:44:38,  3.42it/s]
 44%|████▍     | 165278/371472 [2:11:33<16:54:44,  3.39it/s]
 44%|████▍     | 165279/371472 [2:11:34<16:34:11,  3.46it/s]
 44%|████▍     | 165280/371472 [2:11:34<16:57:17,  3.38it/s]
                                                            
{'loss': 2.8864, 'learning_rate': 5.998297743972074e-07, 'epoch': 7.12}
+
 44%|████▍     | 165280/371472 [2:11:34<16:57:17,  3.38it/s]
 44%|████▍     | 165281/371472 [2:11:34<16:28:39,  3.48it/s]
 44%|████▍     | 165282/371472 [2:11:34<17:10:54,  3.33it/s]
 44%|████▍     | 165283/371472 [2:11:35<17:46:15,  3.22it/s]
 44%|████▍     | 165284/371472 [2:11:35<17:29:25,  3.27it/s]
 44%|████▍     | 165285/371472 [2:11:35<17:25:18,  3.29it/s]
 44%|████▍     | 165286/371472 [2:11:36<18:13:10,  3.14it/s]
 44%|████▍     | 165287/371472 [2:11:36<17:45:47,  3.22it/s]
 44%|████▍     | 165288/371472 [2:11:36<17:22:08,  3.30it/s]
 44%|████▍     | 165289/371472 [2:11:37<19:36:57,  2.92it/s]
 44%|████▍     | 165290/371472 [2:11:37<19:42:41,  2.91it/s]
 44%|████▍     | 165291/371472 [2:11:37<19:13:14,  2.98it/s]
 44%|████▍     | 165292/371472 [2:11:38<18:48:51,  3.04it/s]
 44%|████▍     | 165293/371472 [2:11:38<18:17:00,  3.13it/s]
 44%|████▍     | 165294/371472 [2:11:38<18:00:40,  3.18it/s]
 44%|████▍     | 165295/371472 [2:11:39<17:52:02,  3.21it/s]
 44%|████▍     | 165296/371472 [2:11:39<17:30:00,  3.27it/s]
 44%|████▍     | 165297/371472 [2:11:39<17:09:11,  3.34it/s]
 44%|████▍     | 165298/371472 [2:11:39<16:58:17,  3.37it/s]
 44%|████▍     | 165299/371472 [2:11:40<17:24:44,  3.29it/s]
 44%|████▍     | 165300/371472 [2:11:40<18:13:30,  3.14it/s]
                                                            
{'loss': 3.011, 'learning_rate': 5.997812924217286e-07, 'epoch': 7.12}
+
 44%|████▍     | 165300/371472 [2:11:40<18:13:30,  3.14it/s]
 44%|████▍     | 165301/371472 [2:11:41<19:29:00,  2.94it/s]
 44%|████▍     | 165302/371472 [2:11:41<18:54:57,  3.03it/s]
 44%|████▍     | 165303/371472 [2:11:41<18:33:37,  3.09it/s]
 44%|████▍     | 165304/371472 [2:11:41<18:27:38,  3.10it/s]
 44%|████▍     | 165305/371472 [2:11:42<19:09:25,  2.99it/s]
 45%|████▍     | 165306/371472 [2:11:42<18:14:52,  3.14it/s]
 45%|████▍     | 165307/371472 [2:11:42<17:38:10,  3.25it/s]
 45%|████▍     | 165308/371472 [2:11:43<17:21:13,  3.30it/s]
 45%|████▍     | 165309/371472 [2:11:43<17:12:18,  3.33it/s]
 45%|████▍     | 165310/371472 [2:11:43<16:55:39,  3.38it/s]
 45%|████▍     | 165311/371472 [2:11:44<17:55:41,  3.19it/s]
 45%|████▍     | 165312/371472 [2:11:44<17:31:32,  3.27it/s]
 45%|████▍     | 165313/371472 [2:11:44<17:49:29,  3.21it/s]
 45%|████▍     | 165314/371472 [2:11:45<19:04:51,  3.00it/s]
 45%|████▍     | 165315/371472 [2:11:45<17:57:40,  3.19it/s]
 45%|████▍     | 165316/371472 [2:11:45<18:22:38,  3.12it/s]
 45%|████▍     | 165317/371472 [2:11:46<18:03:02,  3.17it/s]
 45%|████▍     | 165318/371472 [2:11:46<17:22:49,  3.29it/s]
 45%|████▍     | 165319/371472 [2:11:46<17:02:49,  3.36it/s]
 45%|████▍     | 165320/371472 [2:11:46<17:06:32,  3.35it/s]
                                                            
{'loss': 2.8793, 'learning_rate': 5.997328104462495e-07, 'epoch': 7.12}
+
 45%|████▍     | 165320/371472 [2:11:46<17:06:32,  3.35it/s]
 45%|████▍     | 165321/371472 [2:11:47<17:13:03,  3.33it/s]
 45%|████▍     | 165322/371472 [2:11:47<17:00:21,  3.37it/s]
 45%|████▍     | 165323/371472 [2:11:47<17:03:37,  3.36it/s]
 45%|████▍     | 165324/371472 [2:11:48<17:33:01,  3.26it/s]
 45%|████▍     | 165325/371472 [2:11:48<16:54:01,  3.39it/s]
 45%|████▍     | 165326/371472 [2:11:48<16:59:38,  3.37it/s]
 45%|████▍     | 165327/371472 [2:11:48<16:44:45,  3.42it/s]
 45%|████▍     | 165328/371472 [2:11:49<17:25:24,  3.29it/s]
 45%|████▍     | 165329/371472 [2:11:49<16:50:21,  3.40it/s]
 45%|████▍     | 165330/371472 [2:11:49<16:39:05,  3.44it/s]
 45%|████▍     | 165331/371472 [2:11:50<16:13:47,  3.53it/s]
 45%|████▍     | 165332/371472 [2:11:50<16:29:23,  3.47it/s]
 45%|████▍     | 165333/371472 [2:11:50<17:03:38,  3.36it/s]
 45%|████▍     | 165334/371472 [2:11:50<16:34:46,  3.45it/s]
 45%|████▍     | 165335/371472 [2:11:51<16:42:25,  3.43it/s]
 45%|████▍     | 165336/371472 [2:11:51<17:21:26,  3.30it/s]
 45%|████▍     | 165337/371472 [2:11:51<17:30:33,  3.27it/s]
 45%|████▍     | 165338/371472 [2:11:52<17:25:24,  3.29it/s]
 45%|████▍     | 165339/371472 [2:11:52<17:09:38,  3.34it/s]
 45%|████▍     | 165340/371472 [2:11:52<16:54:52,  3.39it/s]
                                                            
{'loss': 2.9767, 'learning_rate': 5.996843284707707e-07, 'epoch': 7.12}
+
 45%|████▍     | 165340/371472 [2:11:52<16:54:52,  3.39it/s]
 45%|████▍     | 165341/371472 [2:11:53<16:50:58,  3.40it/s]
 45%|████▍     | 165342/371472 [2:11:53<18:22:42,  3.12it/s]
 45%|████▍     | 165343/371472 [2:11:53<18:17:40,  3.13it/s]
 45%|████▍     | 165344/371472 [2:11:54<18:06:46,  3.16it/s]
 45%|████▍     | 165345/371472 [2:11:54<18:32:42,  3.09it/s]
 45%|████▍     | 165346/371472 [2:11:54<20:09:31,  2.84it/s]
 45%|████▍     | 165347/371472 [2:11:55<19:20:28,  2.96it/s]
 45%|████▍     | 165348/371472 [2:11:55<18:59:24,  3.02it/s]
 45%|████▍     | 165349/371472 [2:11:55<19:13:29,  2.98it/s]
 45%|████▍     | 165350/371472 [2:11:56<21:12:02,  2.70it/s]
 45%|████▍     | 165351/371472 [2:11:56<20:43:53,  2.76it/s]
 45%|████▍     | 165352/371472 [2:11:56<20:10:09,  2.84it/s]
 45%|████▍     | 165353/371472 [2:11:57<19:00:36,  3.01it/s]
 45%|████▍     | 165354/371472 [2:11:57<18:12:59,  3.14it/s]
 45%|████▍     | 165355/371472 [2:11:57<17:44:49,  3.23it/s]
 45%|████▍     | 165356/371472 [2:11:58<18:08:23,  3.16it/s]
 45%|████▍     | 165357/371472 [2:11:58<17:39:25,  3.24it/s]
 45%|████▍     | 165358/371472 [2:11:58<17:48:19,  3.22it/s]
 45%|████▍     | 165359/371472 [2:11:59<19:35:17,  2.92it/s]
 45%|████▍     | 165360/371472 [2:11:59<18:36:13,  3.08it/s]
                                                            
{'loss': 2.9329, 'learning_rate': 5.996358464952919e-07, 'epoch': 7.12}
+
 45%|████▍     | 165360/371472 [2:11:59<18:36:13,  3.08it/s]
 45%|████▍     | 165361/371472 [2:11:59<18:03:06,  3.17it/s]
 45%|████▍     | 165362/371472 [2:12:00<17:24:34,  3.29it/s]
 45%|████▍     | 165363/371472 [2:12:00<17:13:05,  3.33it/s]
 45%|████▍     | 165364/371472 [2:12:00<17:11:07,  3.33it/s]
 45%|████▍     | 165365/371472 [2:12:00<17:07:47,  3.34it/s]
 45%|████��     | 165366/371472 [2:12:01<17:13:43,  3.32it/s]
 45%|████▍     | 165367/371472 [2:12:01<17:37:38,  3.25it/s]
 45%|████▍     | 165368/371472 [2:12:01<18:19:56,  3.12it/s]
 45%|████▍     | 165369/371472 [2:12:02<17:23:02,  3.29it/s]
 45%|████▍     | 165370/371472 [2:12:02<16:37:04,  3.45it/s]
 45%|████▍     | 165371/371472 [2:12:02<16:35:38,  3.45it/s]
 45%|████▍     | 165372/371472 [2:12:03<16:44:36,  3.42it/s]
 45%|████▍     | 165373/371472 [2:12:03<16:36:19,  3.45it/s]
 45%|████▍     | 165374/371472 [2:12:03<16:16:47,  3.52it/s]
 45%|████▍     | 165375/371472 [2:12:03<16:22:00,  3.50it/s]
 45%|████▍     | 165376/371472 [2:12:04<17:43:15,  3.23it/s]
 45%|████▍     | 165377/371472 [2:12:04<17:41:19,  3.24it/s]
 45%|████▍     | 165378/371472 [2:12:04<17:16:25,  3.31it/s]
 45%|████▍     | 165379/371472 [2:12:05<16:47:32,  3.41it/s]
 45%|████▍     | 165380/371472 [2:12:05<19:12:53,  2.98it/s]
                                                            
{'loss': 2.949, 'learning_rate': 5.99587364519813e-07, 'epoch': 7.12}
+
 45%|████▍     | 165380/371472 [2:12:05<19:12:53,  2.98it/s]
 45%|████▍     | 165381/371472 [2:12:05<18:09:50,  3.15it/s]
 45%|████▍     | 165382/371472 [2:12:06<18:33:35,  3.08it/s]
 45%|████▍     | 165383/371472 [2:12:06<17:52:32,  3.20it/s]
 45%|████▍     | 165384/371472 [2:12:06<17:45:06,  3.22it/s]
 45%|████▍     | 165385/371472 [2:12:06<17:03:37,  3.36it/s]
 45%|████▍     | 165386/371472 [2:12:07<16:45:59,  3.41it/s]
 45%|████▍     | 165387/371472 [2:12:07<17:21:26,  3.30it/s]
 45%|████▍     | 165388/371472 [2:12:07<17:42:45,  3.23it/s]
 45%|████▍     | 165389/371472 [2:12:08<17:13:50,  3.32it/s]
 45%|████▍     | 165390/371472 [2:12:08<16:47:17,  3.41it/s]
 45%|████▍     | 165391/371472 [2:12:08<16:50:00,  3.40it/s]
 45%|████▍     | 165392/371472 [2:12:09<16:52:50,  3.39it/s]
 45%|████▍     | 165393/371472 [2:12:09<17:04:01,  3.35it/s]
 45%|████▍     | 165394/371472 [2:12:09<16:57:24,  3.38it/s]
 45%|████▍     | 165395/371472 [2:12:09<16:55:10,  3.38it/s]
 45%|████▍     | 165396/371472 [2:12:10<16:39:52,  3.44it/s]
 45%|████▍     | 165397/371472 [2:12:10<16:31:16,  3.46it/s]
 45%|████▍     | 165398/371472 [2:12:10<16:41:32,  3.43it/s]
 45%|████▍     | 165399/371472 [2:12:11<18:10:05,  3.15it/s]
 45%|████▍     | 165400/371472 [2:12:11<17:20:10,  3.30it/s]
                                                            
{'loss': 2.8001, 'learning_rate': 5.99538882544334e-07, 'epoch': 7.12}
+
 45%|████▍     | 165400/371472 [2:12:11<17:20:10,  3.30it/s]
 45%|████▍     | 165401/371472 [2:12:11<16:34:11,  3.45it/s]
 45%|████▍     | 165402/371472 [2:12:12<16:26:02,  3.48it/s]
 45%|████▍     | 165403/371472 [2:12:12<16:42:49,  3.42it/s]
 45%|████▍     | 165404/371472 [2:12:12<17:05:06,  3.35it/s]
 45%|████▍     | 165405/371472 [2:12:12<17:14:08,  3.32it/s]
 45%|████▍     | 165406/371472 [2:12:13<18:14:15,  3.14it/s]
 45%|████▍     | 165407/371472 [2:12:13<19:01:09,  3.01it/s]
 45%|████▍     | 165408/371472 [2:12:14<19:26:04,  2.95it/s]
 45%|████▍     | 165409/371472 [2:12:14<18:16:55,  3.13it/s]
 45%|████▍     | 165410/371472 [2:12:14<17:40:46,  3.24it/s]
 45%|████▍     | 165411/371472 [2:12:14<17:27:37,  3.28it/s]
 45%|████▍     | 165412/371472 [2:12:15<16:58:57,  3.37it/s]
 45%|████▍     | 165413/371472 [2:12:15<16:54:47,  3.38it/s]
 45%|████▍     | 165414/371472 [2:12:15<16:53:50,  3.39it/s]
 45%|████▍     | 165415/371472 [2:12:16<16:45:39,  3.41it/s]
 45%|████▍     | 165416/371472 [2:12:16<16:47:10,  3.41it/s]
 45%|████▍     | 165417/371472 [2:12:16<16:42:08,  3.43it/s]
 45%|████▍     | 165418/371472 [2:12:16<17:00:07,  3.37it/s]
 45%|████▍     | 165419/371472 [2:12:17<17:04:06,  3.35it/s]
 45%|████▍     | 165420/371472 [2:12:17<17:36:27,  3.25it/s]
                                                            
{'loss': 2.9253, 'learning_rate': 5.994904005688551e-07, 'epoch': 7.12}
+
 45%|████▍     | 165420/371472 [2:12:17<17:36:27,  3.25it/s]
 45%|████▍     | 165421/371472 [2:12:17<17:24:20,  3.29it/s]
 45%|████▍     | 165422/371472 [2:12:18<17:22:32,  3.29it/s]
 45%|████▍     | 165423/371472 [2:12:18<17:08:11,  3.34it/s]
 45%|████▍     | 165424/371472 [2:12:18<16:43:52,  3.42it/s]
 45%|████▍     | 165425/371472 [2:12:19<17:28:45,  3.27it/s]
 45%|████▍     | 165426/371472 [2:12:19<17:10:34,  3.33it/s]
 45%|████▍     | 165427/371472 [2:12:19<16:48:54,  3.40it/s]
 45%|████▍     | 165428/371472 [2:12:19<16:47:07,  3.41it/s]
 45%|████▍     | 165429/371472 [2:12:20<16:30:55,  3.47it/s]
 45%|████▍     | 165430/371472 [2:12:20<16:39:36,  3.44it/s]
 45%|████▍     | 165431/371472 [2:12:20<18:14:25,  3.14it/s]
 45%|████▍     | 165432/371472 [2:12:21<17:35:55,  3.25it/s]
 45%|████▍     | 165433/371472 [2:12:21<17:45:21,  3.22it/s]
 45%|████▍     | 165434/371472 [2:12:21<17:18:14,  3.31it/s]
 45%|████▍     | 165435/371472 [2:12:22<17:16:48,  3.31it/s]
 45%|████▍     | 165436/371472 [2:12:22<17:25:12,  3.29it/s]
 45%|████▍     | 165437/371472 [2:12:22<16:59:23,  3.37it/s]
 45%|████▍     | 165438/371472 [2:12:22<17:04:19,  3.35it/s]
 45%|████▍     | 165439/371472 [2:12:23<16:44:14,  3.42it/s]
 45%|████▍     | 165440/371472 [2:12:23<16:42:14,  3.43it/s]
                                                            
{'loss': 2.9064, 'learning_rate': 5.994419185933763e-07, 'epoch': 7.13}
+
 45%|████▍     | 165440/371472 [2:12:23<16:42:14,  3.43it/s]
 45%|████▍     | 165441/371472 [2:12:23<17:07:51,  3.34it/s]
 45%|████▍     | 165442/371472 [2:12:24<17:20:31,  3.30it/s]
 45%|████▍     | 165443/371472 [2:12:24<17:14:13,  3.32it/s]
 45%|████▍     | 165444/371472 [2:12:24<16:46:38,  3.41it/s]
 45%|████▍     | 165445/371472 [2:12:24<16:38:38,  3.44it/s]
 45%|████▍     | 165446/371472 [2:12:25<16:43:04,  3.42it/s]
 45%|████▍     | 165447/371472 [2:12:25<16:28:09,  3.47it/s]
 45%|████▍     | 165448/371472 [2:12:25<17:10:22,  3.33it/s]
 45%|████▍     | 165449/371472 [2:12:26<17:15:50,  3.31it/s]
 45%|████▍     | 165450/371472 [2:12:26<17:25:08,  3.29it/s]
 45%|████▍     | 165451/371472 [2:12:26<17:31:24,  3.27it/s]
 45%|████▍     | 165452/371472 [2:12:27<18:55:27,  3.02it/s]
 45%|████▍     | 165453/371472 [2:12:27<17:49:34,  3.21it/s]
 45%|████▍     | 165454/371472 [2:12:27<17:56:50,  3.19it/s]
 45%|████▍     | 165455/371472 [2:12:28<18:26:13,  3.10it/s]
 45%|████▍     | 165456/371472 [2:12:28<17:54:56,  3.19it/s]
 45%|████▍     | 165457/371472 [2:12:28<17:16:52,  3.31it/s]
 45%|████▍     | 165458/371472 [2:12:28<17:09:19,  3.34it/s]
 45%|████▍     | 165459/371472 [2:12:29<17:15:11,  3.32it/s]
 45%|████▍     | 165460/371472 [2:12:29<18:00:49,  3.18it/s]
                                                            
{'loss': 2.9482, 'learning_rate': 5.993934366178973e-07, 'epoch': 7.13}
+
 45%|████▍     | 165460/371472 [2:12:29<18:00:49,  3.18it/s]
 45%|████▍     | 165461/371472 [2:12:29<18:38:30,  3.07it/s]
 45%|████▍     | 165462/371472 [2:12:30<18:16:47,  3.13it/s]
 45%|████▍     | 165463/371472 [2:12:30<18:58:12,  3.02it/s]
 45%|████▍     | 165464/371472 [2:12:30<18:10:01,  3.15it/s]
 45%|████▍     | 165465/371472 [2:12:31<17:14:12,  3.32it/s]
 45%|████▍     | 165466/371472 [2:12:31<16:49:00,  3.40it/s]
 45%|████▍     | 165467/371472 [2:12:31<16:42:08,  3.43it/s]
 45%|████▍     | 165468/371472 [2:12:32<16:46:28,  3.41it/s]
 45%|████▍     | 165469/371472 [2:12:32<17:10:27,  3.33it/s]
 45%|████▍     | 165470/371472 [2:12:32<17:19:10,  3.30it/s]
 45%|████▍     | 165471/371472 [2:12:32<17:09:01,  3.34it/s]
 45%|████▍     | 165472/371472 [2:12:33<16:36:15,  3.45it/s]
 45%|████▍     | 165473/371472 [2:12:33<16:30:21,  3.47it/s]
 45%|████▍     | 165474/371472 [2:12:33<16:32:20,  3.46it/s]
 45%|████▍     | 165475/371472 [2:12:34<18:20:49,  3.12it/s]
 45%|████▍     | 165476/371472 [2:12:34<18:44:40,  3.05it/s]
 45%|████▍     | 165477/371472 [2:12:34<18:36:05,  3.08it/s]
 45%|████▍     | 165478/371472 [2:12:35<17:33:56,  3.26it/s]
 45%|████▍     | 165479/371472 [2:12:35<17:12:37,  3.32it/s]
 45%|████▍     | 165480/371472 [2:12:35<17:57:12,  3.19it/s]
                                                            
{'loss': 3.1369, 'learning_rate': 5.993449546424184e-07, 'epoch': 7.13}
+
 45%|████▍     | 165480/371472 [2:12:35<17:57:12,  3.19it/s]
 45%|████▍     | 165481/371472 [2:12:36<18:32:28,  3.09it/s]
 45%|████▍     | 165482/371472 [2:12:36<17:48:08,  3.21it/s]
 45%|████▍     | 165483/371472 [2:12:36<18:08:29,  3.15it/s]
 45%|████▍     | 165484/371472 [2:12:37<18:24:17,  3.11it/s]
 45%|████▍     | 165485/371472 [2:12:37<18:47:25,  3.05it/s]
 45%|████▍     | 165486/371472 [2:12:37<18:04:51,  3.16it/s]
 45%|████▍     | 165487/371472 [2:12:38<17:59:25,  3.18it/s]
 45%|████▍     | 165488/371472 [2:12:38<17:11:50,  3.33it/s]
 45%|████▍     | 165489/371472 [2:12:38<16:44:53,  3.42it/s]
 45%|████▍     | 165490/371472 [2:12:38<18:00:19,  3.18it/s]
 45%|████▍     | 165491/371472 [2:12:39<18:21:57,  3.12it/s]
 45%|████▍     | 165492/371472 [2:12:39<18:15:25,  3.13it/s]
 45%|█���██▍     | 165493/371472 [2:12:39<17:44:40,  3.22it/s]
 45%|████▍     | 165494/371472 [2:12:40<16:57:58,  3.37it/s]
 45%|████▍     | 165495/371472 [2:12:40<16:35:27,  3.45it/s]
 45%|████▍     | 165496/371472 [2:12:40<16:16:29,  3.52it/s]
 45%|████▍     | 165497/371472 [2:12:40<16:36:40,  3.44it/s]
 45%|████▍     | 165498/371472 [2:12:41<17:13:46,  3.32it/s]
 45%|████▍     | 165499/371472 [2:12:41<17:07:03,  3.34it/s]
 45%|████▍     | 165500/371472 [2:12:41<16:54:55,  3.38it/s]
                                                            
{'loss': 2.9048, 'learning_rate': 5.992964726669396e-07, 'epoch': 7.13}
+
 45%|████▍     | 165500/371472 [2:12:41<16:54:55,  3.38it/s]
 45%|████▍     | 165501/371472 [2:12:42<16:32:08,  3.46it/s]
 45%|████▍     | 165502/371472 [2:12:42<16:35:39,  3.45it/s]
 45%|████▍     | 165503/371472 [2:12:42<17:45:57,  3.22it/s]
 45%|████▍     | 165504/371472 [2:12:43<17:29:54,  3.27it/s]
 45%|████▍     | 165505/371472 [2:12:43<17:23:56,  3.29it/s]
 45%|████▍     | 165506/371472 [2:12:43<18:55:16,  3.02it/s]
 45%|████▍     | 165507/371472 [2:12:44<18:38:27,  3.07it/s]
 45%|████▍     | 165508/371472 [2:12:44<18:55:33,  3.02it/s]
 45%|████▍     | 165509/371472 [2:12:44<18:30:24,  3.09it/s]
 45%|████▍     | 165510/371472 [2:12:45<18:18:24,  3.13it/s]
 45%|████▍     | 165511/371472 [2:12:45<19:51:05,  2.88it/s]
 45%|████▍     | 165512/371472 [2:12:45<20:02:53,  2.85it/s]
 45%|████▍     | 165513/371472 [2:12:46<19:54:27,  2.87it/s]
 45%|████▍     | 165514/371472 [2:12:46<18:56:35,  3.02it/s]
 45%|████▍     | 165515/371472 [2:12:46<18:58:12,  3.02it/s]
 45%|████▍     | 165516/371472 [2:12:47<18:23:46,  3.11it/s]
 45%|████▍     | 165517/371472 [2:12:47<18:25:04,  3.11it/s]
 45%|████▍     | 165518/371472 [2:12:47<17:51:20,  3.20it/s]
 45%|████▍     | 165519/371472 [2:12:48<18:04:30,  3.17it/s]
 45%|████▍     | 165520/371472 [2:12:48<18:01:08,  3.17it/s]
                                                            
{'loss': 2.9847, 'learning_rate': 5.992479906914608e-07, 'epoch': 7.13}
+
 45%|████▍     | 165520/371472 [2:12:48<18:01:08,  3.17it/s]
 45%|████▍     | 165521/371472 [2:12:48<17:33:48,  3.26it/s]
 45%|████▍     | 165522/371472 [2:12:48<17:08:29,  3.34it/s]
 45%|████▍     | 165523/371472 [2:12:49<17:14:39,  3.32it/s]
 45%|████▍     | 165524/371472 [2:12:49<16:43:41,  3.42it/s]
 45%|████▍     | 165525/371472 [2:12:49<16:47:05,  3.41it/s]
 45%|████▍     | 165526/371472 [2:12:50<17:14:58,  3.32it/s]
 45%|████▍     | 165527/371472 [2:12:50<18:14:25,  3.14it/s]
 45%|████▍     | 165528/371472 [2:12:50<17:40:08,  3.24it/s]
 45%|████▍     | 165529/371472 [2:12:51<17:42:58,  3.23it/s]
 45%|████▍     | 165530/371472 [2:12:51<17:16:48,  3.31it/s]
 45%|████▍     | 165531/371472 [2:12:51<16:47:16,  3.41it/s]
 45%|████▍     | 165532/371472 [2:12:51<17:15:34,  3.31it/s]
 45%|████▍     | 165533/371472 [2:12:52<16:52:36,  3.39it/s]
 45%|████▍     | 165534/371472 [2:12:52<17:08:26,  3.34it/s]
 45%|████▍     | 165535/371472 [2:12:52<17:13:09,  3.32it/s]
 45%|████▍     | 165536/371472 [2:12:53<17:03:53,  3.35it/s]
 45%|████▍     | 165537/371472 [2:12:53<17:07:29,  3.34it/s]
 45%|████▍     | 165538/371472 [2:12:53<16:53:46,  3.39it/s]
 45%|████▍     | 165539/371472 [2:12:53<16:31:35,  3.46it/s]
 45%|████▍     | 165540/371472 [2:12:54<16:52:28,  3.39it/s]
                                                            
{'loss': 2.8901, 'learning_rate': 5.991995087159816e-07, 'epoch': 7.13}
+
 45%|████▍     | 165540/371472 [2:12:54<16:52:28,  3.39it/s]
 45%|████▍     | 165541/371472 [2:12:54<16:49:55,  3.40it/s]
 45%|████▍     | 165542/371472 [2:12:54<16:45:06,  3.41it/s]
 45%|████▍     | 165543/371472 [2:12:55<16:28:49,  3.47it/s]
 45%|████▍     | 165544/371472 [2:12:55<16:36:27,  3.44it/s]
 45%|████▍     | 165545/371472 [2:12:55<16:19:36,  3.50it/s]
 45%|████▍     | 165546/371472 [2:12:56<16:29:45,  3.47it/s]
 45%|████▍     | 165547/371472 [2:12:56<16:27:02,  3.48it/s]
 45%|████▍     | 165548/371472 [2:12:56<16:51:18,  3.39it/s]
 45%|████▍     | 165549/371472 [2:12:56<17:01:27,  3.36it/s]
 45%|████▍     | 165550/371472 [2:12:57<16:56:14,  3.38it/s]
 45%|████▍     | 165551/371472 [2:12:57<18:57:39,  3.02it/s]
 45%|████▍     | 165552/371472 [2:12:57<18:44:04,  3.05it/s]
 45%|████▍     | 165553/371472 [2:12:58<18:02:08,  3.17it/s]
 45%|████▍     | 165554/371472 [2:12:58<17:18:14,  3.31it/s]
 45%|████▍     | 165555/371472 [2:12:58<17:19:56,  3.30it/s]
 45%|████▍     | 165556/371472 [2:12:59<17:50:15,  3.21it/s]
 45%|████▍     | 165557/371472 [2:12:59<17:46:30,  3.22it/s]
 45%|████▍     | 165558/371472 [2:12:59<17:15:32,  3.31it/s]
 45%|████▍     | 165559/371472 [2:13:00<17:18:22,  3.31it/s]
 45%|████▍     | 165560/371472 [2:13:00<17:51:00,  3.20it/s]
                                                            
{'loss': 2.866, 'learning_rate': 5.991510267405028e-07, 'epoch': 7.13}
+
 45%|████▍     | 165560/371472 [2:13:00<17:51:00,  3.20it/s]
 45%|████▍     | 165561/371472 [2:13:00<17:15:29,  3.31it/s]
 45%|████▍     | 165562/371472 [2:13:00<17:02:51,  3.36it/s]
 45%|████▍     | 165563/371472 [2:13:01<21:03:55,  2.72it/s]
 45%|████▍     | 165564/371472 [2:13:01<19:56:28,  2.87it/s]
 45%|████▍     | 165565/371472 [2:13:02<19:07:49,  2.99it/s]
 45%|████▍     | 165566/371472 [2:13:02<18:33:05,  3.08it/s]
 45%|████▍     | 165567/371472 [2:13:02<17:49:20,  3.21it/s]
 45%|████▍     | 165568/371472 [2:13:02<17:49:07,  3.21it/s]
 45%|████▍     | 165569/371472 [2:13:03<17:27:30,  3.28it/s]
 45%|████▍     | 165570/371472 [2:13:03<17:08:23,  3.34it/s]
 45%|████▍     | 165571/371472 [2:13:03<16:42:38,  3.42it/s]
 45%|████▍     | 165572/371472 [2:13:04<16:49:59,  3.40it/s]
 45%|████▍     | 165573/371472 [2:13:04<17:42:33,  3.23it/s]
 45%|████▍     | 165574/371472 [2:13:04<17:09:09,  3.33it/s]
 45%|████▍     | 165575/371472 [2:13:05<17:08:16,  3.34it/s]
 45%|████▍     | 165576/371472 [2:13:05<16:48:41,  3.40it/s]
 45%|████▍     | 165577/371472 [2:13:05<17:57:15,  3.19it/s]
 45%|████▍     | 165578/371472 [2:13:05<17:48:00,  3.21it/s]
 45%|████▍     | 165579/371472 [2:13:06<18:09:35,  3.15it/s]
 45%|████▍     | 165580/371472 [2:13:06<18:02:37,  3.17it/s]
                                                            
{'loss': 2.9895, 'learning_rate': 5.99102544765024e-07, 'epoch': 7.13}
+
 45%|████▍     | 165580/371472 [2:13:06<18:02:37,  3.17it/s]
 45%|████▍     | 165581/371472 [2:13:06<17:19:45,  3.30it/s]
 45%|████▍     | 165582/371472 [2:13:07<16:49:37,  3.40it/s]
 45%|████▍     | 165583/371472 [2:13:07<17:00:44,  3.36it/s]
 45%|████▍     | 165584/371472 [2:13:07<17:30:37,  3.27it/s]
 45%|████▍     | 165585/371472 [2:13:08<18:04:37,  3.16it/s]
 45%|████▍     | 165586/371472 [2:13:08<17:39:33,  3.24it/s]
 45%|████▍     | 165587/371472 [2:13:08<16:54:20,  3.38it/s]
 45%|████▍     | 165588/371472 [2:13:09<17:55:03,  3.19it/s]
 45%|████▍     | 165589/371472 [2:13:09<17:28:44,  3.27it/s]
 45%|████▍     | 165590/371472 [2:13:09<17:20:09,  3.30it/s]
 45%|████▍     | 165591/371472 [2:13:09<16:49:12,  3.40it/s]
 45%|████▍     | 165592/371472 [2:13:10<17:31:04,  3.26it/s]
 45%|████▍     | 165593/371472 [2:13:10<17:04:18,  3.35it/s]
 45%|████▍     | 165594/371472 [2:13:10<17:23:48,  3.29it/s]
 45%|████▍     | 165595/371472 [2:13:11<17:12:09,  3.32it/s]
 45%|████▍     | 165596/371472 [2:13:11<17:48:50,  3.21it/s]
 45%|████▍     | 165597/371472 [2:13:11<17:10:30,  3.33it/s]
 45%|████▍     | 165598/371472 [2:13:12<17:00:26,  3.36it/s]
 45%|████▍     | 165599/371472 [2:13:12<17:00:49,  3.36it/s]
 45%|████▍     | 165600/371472 [2:13:12<16:52:40,  3.39it/s]
                                                            
{'loss': 2.8174, 'learning_rate': 5.990540627895452e-07, 'epoch': 7.13}
+
 45%|████▍     | 165600/371472 [2:13:12<16:52:40,  3.39it/s]
 45%|████▍     | 165601/371472 [2:13:12<16:36:08,  3.44it/s]
 45%|████▍     | 165602/371472 [2:13:13<17:12:05,  3.32it/s]
 45%|████▍     | 165603/371472 [2:13:13<16:53:09,  3.39it/s]
 45%|████▍     | 165604/371472 [2:13:13<16:38:14,  3.44it/s]
 45%|████▍     | 165605/371472 [2:13:14<16:55:09,  3.38it/s]
 45%|████▍     | 165606/371472 [2:13:14<17:30:38,  3.27it/s]
 45%|████▍     | 165607/371472 [2:13:14<17:21:35,  3.29it/s]
 45%|████▍     | 165608/371472 [2:13:15<17:18:49,  3.30it/s]
 45%|████▍     | 165609/371472 [2:13:15<17:58:14,  3.18it/s]
 45%|████▍     | 165610/371472 [2:13:15<17:47:31,  3.21it/s]
 45%|████▍     | 165611/371472 [2:13:15<17:36:36,  3.25it/s]
 45%|████▍     | 165612/371472 [2:13:16<17:41:17,  3.23it/s]
 45%|████▍     | 165613/371472 [2:13:16<17:23:02,  3.29it/s]
 45%|████▍     | 165614/371472 [2:13:16<17:48:26,  3.21it/s]
 45%|████▍     | 165615/371472 [2:13:17<17:25:18,  3.28it/s]
 45%|████▍     | 165616/371472 [2:13:17<17:04:04,  3.35it/s]
 45%|████▍     | 165617/371472 [2:13:17<17:01:46,  3.36it/s]
 45%|████▍     | 165618/371472 [2:13:18<17:50:23,  3.21it/s]
 45%|████▍     | 165619/371472 [2:13:18<17:39:00,  3.24it/s]
 45%|████▍     | 165620/371472 [2:13:18<17:40:34,  3.23it/s]
                                                            
{'loss': 2.9952, 'learning_rate': 5.990055808140662e-07, 'epoch': 7.13}
+
 45%|████▍     | 165620/371472 [2:13:18<17:40:34,  3.23it/s]
 45%|████▍     | 165621/371472 [2:13:19<17:28:59,  3.27it/s]
 45%|████▍     | 165622/371472 [2:13:19<17:18:07,  3.30it/s]
 45%|████▍     | 165623/371472 [2:13:19<17:07:38,  3.34it/s]
 45%|████▍     | 165624/371472 [2:13:19<16:44:48,  3.41it/s]
 45%|████▍     | 165625/371472 [2:13:20<16:37:15,  3.44it/s]
 45%|████▍     | 165626/371472 [2:13:20<16:46:15,  3.41it/s]
 45%|████▍     | 165627/371472 [2:13:20<16:48:35,  3.40it/s]
 45%|████▍     | 165628/371472 [2:13:21<17:00:07,  3.36it/s]
 45%|████▍     | 165629/371472 [2:13:21<17:32:07,  3.26it/s]
 45%|████▍     | 165630/371472 [2:13:21<18:03:53,  3.17it/s]
 45%|████▍     | 165631/371472 [2:13:22<17:21:41,  3.29it/s]
 45%|████▍     | 165632/371472 [2:13:22<17:23:57,  3.29it/s]
 45%|████▍     | 165633/371472 [2:13:22<17:00:10,  3.36it/s]
 45%|████▍     | 165634/371472 [2:13:22<16:52:27,  3.39it/s]
 45%|████▍     | 165635/371472 [2:13:23<16:53:01,  3.39it/s]
 45%|████▍     | 165636/371472 [2:13:23<16:40:49,  3.43it/s]
 45%|████▍     | 165637/371472 [2:13:23<16:30:04,  3.46it/s]
 45%|████▍     | 165638/371472 [2:13:24<16:36:43,  3.44it/s]
 45%|████▍     | 165639/371472 [2:13:24<16:41:24,  3.43it/s]
 45%|████▍     | 165640/371472 [2:13:24<16:26:20,  3.48it/s]
                                                            
{'loss': 2.8857, 'learning_rate': 5.989570988385874e-07, 'epoch': 7.13}
+
 45%|████▍     | 165640/371472 [2:13:24<16:26:20,  3.48it/s]
 45%|████▍     | 165641/371472 [2:13:25<17:47:48,  3.21it/s]
 45%|████▍     | 165642/371472 [2:13:25<17:38:39,  3.24it/s]
 45%|████▍     | 165643/371472 [2:13:25<17:14:52,  3.31it/s]
 45%|████▍     | 165644/371472 [2:13:25<17:00:50,  3.36it/s]
 45%|████▍     | 165645/371472 [2:13:26<18:35:18,  3.08it/s]
 45%|████▍     | 165646/371472 [2:13:26<17:49:54,  3.21it/s]
 45%|████▍     | 165647/371472 [2:13:26<18:22:26,  3.11it/s]
 45%|████▍     | 165648/371472 [2:13:27<18:01:45,  3.17it/s]
 45%|████▍     | 165649/371472 [2:13:27<17:52:36,  3.20it/s]
 45%|████▍     | 165650/371472 [2:13:27<17:15:43,  3.31it/s]
 45%|████▍     | 165651/371472 [2:13:28<17:35:19,  3.25it/s]
 45%|████▍     | 165652/371472 [2:13:28<17:07:46,  3.34it/s]
 45%|████▍     | 165653/371472 [2:13:28<18:20:56,  3.12it/s]
 45%|████▍     | 165654/371472 [2:13:29<18:24:31,  3.11it/s]
 45%|████▍     | 165655/371472 [2:13:29<17:52:42,  3.20it/s]
 45%|████▍     | 165656/371472 [2:13:29<17:41:42,  3.23it/s]
 45%|████▍     | 165657/371472 [2:13:29<17:11:23,  3.33it/s]
 45%|████▍     | 165658/371472 [2:13:30<17:23:09,  3.29it/s]
 45%|████▍     | 165659/371472 [2:13:30<17:01:01,  3.36it/s]
 45%|████▍     | 165660/371472 [2:13:30<18:38:29,  3.07it/s]
                                                            
{'loss': 2.9869, 'learning_rate': 5.989086168631084e-07, 'epoch': 7.14}
+
 45%|████▍     | 165660/371472 [2:13:30<18:38:29,  3.07it/s]
 45%|████▍     | 165661/371472 [2:13:31<17:51:27,  3.20it/s]
 45%|████▍     | 165662/371472 [2:13:31<17:57:30,  3.18it/s]
 45%|████▍     | 165663/371472 [2:13:31<18:02:46,  3.17it/s]
 45%|████▍     | 165664/371472 [2:13:32<17:22:15,  3.29it/s]
 45%|████▍     | 165665/371472 [2:13:32<17:27:55,  3.27it/s]
 45%|████▍     | 165666/371472 [2:13:32<18:13:10,  3.14it/s]
 45%|████▍     | 165667/371472 [2:13:33<17:38:46,  3.24it/s]
 45%|████▍     | 165668/371472 [2:13:33<18:37:35,  3.07it/s]
 45%|████▍     | 165669/371472 [2:13:33<17:56:50,  3.19it/s]
 45%|████▍     | 165670/371472 [2:13:34<18:10:54,  3.14it/s]
 45%|████▍     | 165671/371472 [2:13:34<18:00:48,  3.17it/s]
 45%|████▍     | 165672/371472 [2:13:34<18:08:12,  3.15it/s]
 45%|████▍     | 165673/371472 [2:13:34<17:32:08,  3.26it/s]
 45%|████▍     | 165674/371472 [2:13:35<17:16:18,  3.31it/s]
 45%|████▍     | 165675/371472 [2:13:35<16:49:18,  3.40it/s]
 45%|████▍     | 165676/371472 [2:13:35<17:43:44,  3.22it/s]
 45%|████▍     | 165677/371472 [2:13:36<17:11:36,  3.32it/s]
 45%|████▍     | 165678/371472 [2:13:36<16:59:56,  3.36it/s]
 45%|████▍     | 165679/371472 [2:13:36<17:12:19,  3.32it/s]
 45%|████▍     | 165680/371472 [2:13:37<17:07:39,  3.34it/s]
                                                            
{'loss': 2.816, 'learning_rate': 5.988601348876296e-07, 'epoch': 7.14}
+
 45%|████▍     | 165680/371472 [2:13:37<17:07:39,  3.34it/s]
 45%|████▍     | 165681/371472 [2:13:37<16:58:40,  3.37it/s]
 45%|████▍     | 165682/371472 [2:13:37<17:11:17,  3.33it/s]
 45%|████▍     | 165683/371472 [2:13:37<17:06:17,  3.34it/s]
 45%|████▍     | 165684/371472 [2:13:38<17:36:00,  3.25it/s]
 45%|████▍     | 165685/371472 [2:13:38<17:28:46,  3.27it/s]
 45%|████▍     | 165686/371472 [2:13:38<16:47:56,  3.40it/s]
 45%|████▍     | 165687/371472 [2:13:39<16:45:03,  3.41it/s]
 45%|████▍     | 165688/371472 [2:13:39<16:40:11,  3.43it/s]
 45%|████▍     | 165689/371472 [2:13:39<16:22:07,  3.49it/s]
 45%|████▍     | 165690/371472 [2:13:40<16:48:07,  3.40it/s]
 45%|████▍     | 165691/371472 [2:13:40<16:55:14,  3.38it/s]
 45%|████▍     | 165692/371472 [2:13:40<16:27:41,  3.47it/s]
 45%|████▍     | 165693/371472 [2:13:40<16:40:10,  3.43it/s]
 45%|████▍     | 165694/371472 [2:13:41<17:52:43,  3.20it/s]
 45%|████▍     | 165695/371472 [2:13:41<17:40:08,  3.24it/s]
 45%|████▍     | 165696/371472 [2:13:41<17:21:02,  3.29it/s]
 45%|████▍     | 165697/371472 [2:13:42<18:16:04,  3.13it/s]
 45%|████▍     | 165698/371472 [2:13:42<17:51:26,  3.20it/s]
 45%|████▍     | 165699/371472 [2:13:42<17:21:50,  3.29it/s]
 45%|████▍     | 165700/371472 [2:13:43<16:52:02,  3.39it/s]
                                                            
{'loss': 3.0321, 'learning_rate': 5.988116529121506e-07, 'epoch': 7.14}
+
 45%|████▍     | 165700/371472 [2:13:43<16:52:02,  3.39it/s]
 45%|████▍     | 165701/371472 [2:13:43<17:30:54,  3.26it/s]
 45%|████▍     | 165702/371472 [2:13:43<17:02:13,  3.35it/s]
 45%|████▍     | 165703/371472 [2:13:43<16:33:06,  3.45it/s]
 45%|████▍     | 165704/371472 [2:13:44<16:13:44,  3.52it/s]
 45%|████▍     | 165705/371472 [2:13:44<16:23:19,  3.49it/s]
 45%|████▍     | 165706/371472 [2:13:44<17:05:26,  3.34it/s]
 45%|████▍     | 165707/371472 [2:13:45<16:45:40,  3.41it/s]
 45%|████▍     | 165708/371472 [2:13:45<16:31:11,  3.46it/s]
 45%|████▍     | 165709/371472 [2:13:45<17:52:47,  3.20it/s]
 45%|████▍     | 165710/371472 [2:13:46<17:27:53,  3.27it/s]
 45%|████▍     | 165711/371472 [2:13:46<18:13:57,  3.13it/s]
 45%|████▍     | 165712/371472 [2:13:46<17:47:57,  3.21it/s]
 45%|████▍     | 165713/371472 [2:13:46<17:18:55,  3.30it/s]
 45%|████▍     | 165714/371472 [2:13:47<16:57:59,  3.37it/s]
 45%|████▍     | 165715/371472 [2:13:47<16:58:00,  3.37it/s]
 45%|████▍     | 165716/371472 [2:13:47<16:57:09,  3.37it/s]
 45%|████▍     | 165717/371472 [2:13:48<17:12:13,  3.32it/s]
 45%|████▍     | 165718/371472 [2:13:48<16:50:13,  3.39it/s]
 45%|████▍     | 165719/371472 [2:13:48<16:51:54,  3.39it/s]
 45%|████▍     | 165720/371472 [2:13:49<18:06:29,  3.16it/s]
                                                            
{'loss': 2.8562, 'learning_rate': 5.987631709366717e-07, 'epoch': 7.14}
+
 45%|████▍     | 165720/371472 [2:13:49<18:06:29,  3.16it/s]
 45%|████▍     | 165721/371472 [2:13:49<17:42:50,  3.23it/s]
 45%|████▍     | 165722/371472 [2:13:49<17:34:02,  3.25it/s]
 45%|████▍     | 165723/371472 [2:13:50<17:47:47,  3.21it/s]
 45%|████▍     | 165724/371472 [2:13:50<17:34:43,  3.25it/s]
 45%|████▍     | 165725/371472 [2:13:50<17:10:57,  3.33it/s]
 45%|████▍     | 165726/371472 [2:13:50<17:38:52,  3.24it/s]
 45%|████▍     | 165727/371472 [2:13:51<17:46:40,  3.21it/s]
 45%|████▍     | 165728/371472 [2:13:51<17:13:08,  3.32it/s]
 45%|████▍     | 165729/371472 [2:13:51<17:24:12,  3.28it/s]
 45%|████▍     | 165730/371472 [2:13:52<17:23:24,  3.29it/s]
 45%|████▍     | 165731/371472 [2:13:52<16:58:29,  3.37it/s]
 45%|████▍     | 165732/371472 [2:13:52<16:44:40,  3.41it/s]
 45%|████▍     | 165733/371472 [2:13:53<16:59:19,  3.36it/s]
 45%|████▍     | 165734/371472 [2:13:53<17:11:22,  3.32it/s]
 45%|████▍     | 165735/371472 [2:13:53<16:54:45,  3.38it/s]
 45%|████▍     | 165736/371472 [2:13:53<17:21:13,  3.29it/s]
 45%|████▍     | 165737/371472 [2:13:54<16:56:49,  3.37it/s]
 45%|████▍     | 165738/371472 [2:13:54<16:48:08,  3.40it/s]
 45%|████▍     | 165739/371472 [2:13:54<16:46:33,  3.41it/s]
 45%|████▍     | 165740/371472 [2:13:55<17:23:23,  3.29it/s]
                                                            
{'loss': 3.1286, 'learning_rate': 5.987146889611929e-07, 'epoch': 7.14}
+
 45%|████▍     | 165740/371472 [2:13:55<17:23:23,  3.29it/s]
 45%|████▍     | 165741/371472 [2:13:55<16:58:34,  3.37it/s]
 45%|████▍     | 165742/371472 [2:13:55<18:42:14,  3.06it/s]
 45%|████▍     | 165743/371472 [2:13:56<19:01:53,  3.00it/s]
 45%|████▍     | 165744/371472 [2:13:56<18:26:41,  3.10it/s]
 45%|████▍     | 165745/371472 [2:13:56<17:50:26,  3.20it/s]
 45%|████▍     | 165746/371472 [2:13:57<18:13:35,  3.14it/s]
 45%|████▍     | 165747/371472 [2:13:57<17:29:55,  3.27it/s]
 45%|████▍     | 165748/371472 [2:13:57<17:11:32,  3.32it/s]
 45%|████▍     | 165749/371472 [2:13:57<17:15:15,  3.31it/s]
 45%|████▍     | 165750/371472 [2:13:58<18:09:24,  3.15it/s]
 45%|████▍     | 165751/371472 [2:13:58<17:26:42,  3.28it/s]
 45%|████▍     | 165752/371472 [2:13:58<17:27:26,  3.27it/s]
 45%|████▍     | 165753/371472 [2:13:59<16:51:52,  3.39it/s]
 45%|████▍     | 165754/371472 [2:13:59<17:21:53,  3.29it/s]
 45%|████▍     | 165755/371472 [2:13:59<18:08:26,  3.15it/s]
 45%|████▍     | 165756/371472 [2:14:00<17:40:22,  3.23it/s]
 45%|████▍     | 165757/371472 [2:14:00<18:22:08,  3.11it/s]
 45%|████▍     | 165758/371472 [2:14:00<18:08:37,  3.15it/s]
 45%|████▍     | 165759/371472 [2:14:01<17:20:06,  3.30it/s]
 45%|████▍     | 165760/371472 [2:14:01<16:55:24,  3.38it/s]
                                                            
{'loss': 2.7627, 'learning_rate': 5.986662069857141e-07, 'epoch': 7.14}
+
 45%|████▍     | 165760/371472 [2:14:01<16:55:24,  3.38it/s]
 45%|████▍     | 165761/371472 [2:14:01<16:40:30,  3.43it/s]
 45%|████▍     | 165762/371472 [2:14:01<16:35:06,  3.45it/s]
 45%|████▍     | 165763/371472 [2:14:02<17:04:36,  3.35it/s]
 45%|████▍     | 165764/371472 [2:14:02<16:29:56,  3.46it/s]
 45%|████▍     | 165765/371472 [2:14:02<16:39:39,  3.43it/s]
 45%|████▍     | 165766/371472 [2:14:03<16:37:19,  3.44it/s]
 45%|████▍     | 165767/371472 [2:14:03<17:51:16,  3.20it/s]
 45%|████▍     | 165768/371472 [2:14:03<17:05:02,  3.34it/s]
 45%|████▍     | 165769/371472 [2:14:03<17:21:08,  3.29it/s]
 45%|████▍     | 165770/371472 [2:14:04<18:25:18,  3.10it/s]
 45%|████▍     | 165771/371472 [2:14:04<17:51:55,  3.20it/s]
 45%|████▍     | 165772/371472 [2:14:04<17:08:34,  3.33it/s]
 45%|████▍     | 165773/371472 [2:14:05<17:02:22,  3.35it/s]
 45%|████▍     | 165774/371472 [2:14:05<16:26:48,  3.47it/s]
 45%|████▍     | 165775/371472 [2:14:05<16:47:22,  3.40it/s]
 45%|████▍     | 165776/371472 [2:14:06<16:26:39,  3.47it/s]
 45%|████▍     | 165777/371472 [2:14:06<17:45:49,  3.22it/s]
 45%|████▍     | 165778/371472 [2:14:06<17:40:38,  3.23it/s]
 45%|████▍     | 165779/371472 [2:14:07<17:23:55,  3.28it/s]
 45%|████▍     | 165780/371472 [2:14:07<18:38:55,  3.06it/s]
                                                            
{'loss': 3.0709, 'learning_rate': 5.986177250102351e-07, 'epoch': 7.14}
+
 45%|████▍     | 165780/371472 [2:14:07<18:38:55,  3.06it/s]
 45%|████▍     | 165781/371472 [2:14:07<18:06:38,  3.15it/s]
 45%|████▍     | 165782/371472 [2:14:08<18:12:21,  3.14it/s]
 45%|████▍     | 165783/371472 [2:14:08<17:57:00,  3.18it/s]
 45%|████▍     | 165784/371472 [2:14:08<17:34:57,  3.25it/s]
 45%|████▍     | 165785/371472 [2:14:08<17:26:27,  3.28it/s]
 45%|████▍     | 165786/371472 [2:14:09<18:21:30,  3.11it/s]
 45%|████▍     | 165787/371472 [2:14:09<18:37:23,  3.07it/s]
 45%|████▍     | 165788/371472 [2:14:09<19:42:01,  2.90it/s]
 45%|████▍     | 165789/371472 [2:14:10<18:44:28,  3.05it/s]
 45%|████▍     | 165790/371472 [2:14:10<18:51:26,  3.03it/s]
 45%|████▍     | 165791/371472 [2:14:10<18:42:44,  3.05it/s]
 45%|████▍     | 165792/371472 [2:14:11<18:17:35,  3.12it/s]
 45%|████▍     | 165793/371472 [2:14:11<18:17:40,  3.12it/s]
 45%|████▍     | 165794/371472 [2:14:11<17:45:14,  3.22it/s]
 45%|████▍     | 165795/371472 [2:14:12<18:18:11,  3.12it/s]
 45%|████▍     | 165796/371472 [2:14:12<17:59:33,  3.18it/s]
 45%|████▍     | 165797/371472 [2:14:12<17:21:02,  3.29it/s]
 45%|████▍     | 165798/371472 [2:14:13<17:27:43,  3.27it/s]
 45%|████▍     | 165799/371472 [2:14:13<18:10:59,  3.14it/s]
 45%|████▍     | 165800/371472 [2:14:13<17:40:40,  3.23it/s]
                                                            
{'loss': 2.8484, 'learning_rate': 5.985692430347561e-07, 'epoch': 7.14}
+
 45%|████▍     | 165800/371472 [2:14:13<17:40:40,  3.23it/s]
 45%|████▍     | 165801/371472 [2:14:14<17:30:15,  3.26it/s]
 45%|████▍     | 165802/371472 [2:14:14<17:22:36,  3.29it/s]
 45%|████▍     | 165803/371472 [2:14:14<17:00:13,  3.36it/s]
 45%|████▍     | 165804/371472 [2:14:14<17:04:16,  3.35it/s]
 45%|████▍     | 165805/371472 [2:14:15<16:31:44,  3.46it/s]
 45%|████▍     | 165806/371472 [2:14:15<16:52:13,  3.39it/s]
 45%|████▍     | 165807/371472 [2:14:15<17:20:51,  3.29it/s]
 45%|████▍     | 165808/371472 [2:14:16<18:27:22,  3.10it/s]
 45%|████▍     | 165809/371472 [2:14:16<18:17:20,  3.12it/s]
 45%|████▍     | 165810/371472 [2:14:16<19:01:35,  3.00it/s]
 45%|████▍     | 165811/371472 [2:14:17<18:29:26,  3.09it/s]
 45%|████▍     | 165812/371472 [2:14:17<18:01:52,  3.17it/s]
 45%|████▍     | 165813/371472 [2:14:17<17:43:53,  3.22it/s]
 45%|████▍     | 165814/371472 [2:14:18<17:31:17,  3.26it/s]
 45%|████▍     | 165815/371472 [2:14:18<17:31:32,  3.26it/s]
 45%|████▍     | 165816/371472 [2:14:18<17:20:52,  3.29it/s]
 45%|████▍     | 165817/371472 [2:14:18<16:59:12,  3.36it/s]
 45%|████▍     | 165818/371472 [2:14:19<17:32:57,  3.26it/s]
 45%|████▍     | 165819/371472 [2:14:19<17:31:04,  3.26it/s]
 45%|████▍     | 165820/371472 [2:14:19<17:35:19,  3.25it/s]
                                                            
{'loss': 2.9155, 'learning_rate': 5.985207610592773e-07, 'epoch': 7.14}
+
 45%|████▍     | 165820/371472 [2:14:19<17:35:19,  3.25it/s]
 45%|████▍     | 165821/371472 [2:14:20<17:19:51,  3.30it/s]
 45%|████▍     | 165822/371472 [2:14:20<16:55:33,  3.37it/s]
 45%|████▍     | 165823/371472 [2:14:20<16:37:05,  3.44it/s]
 45%|████▍     | 165824/371472 [2:14:20<16:10:04,  3.53it/s]
 45%|████▍     | 165825/371472 [2:14:21<16:19:38,  3.50it/s]
 45%|████▍     | 165826/371472 [2:14:21<22:02:08,  2.59it/s]
 45%|████▍     | 165827/371472 [2:14:22<20:40:55,  2.76it/s]
 45%|████▍     | 165828/371472 [2:14:22<19:15:22,  2.97it/s]
 45%|████▍     | 165829/371472 [2:14:22<18:46:51,  3.04it/s]
 45%|████▍     | 165830/371472 [2:14:23<17:57:10,  3.18it/s]
 45%|████▍     | 165831/371472 [2:14:23<18:16:34,  3.13it/s]
 45%|████▍     | 165832/371472 [2:14:23<17:47:04,  3.21it/s]
 45%|████▍     | 165833/371472 [2:14:24<18:03:59,  3.16it/s]
 45%|████▍     | 165834/371472 [2:14:24<17:40:20,  3.23it/s]
 45%|████▍     | 165835/371472 [2:14:24<17:38:16,  3.24it/s]
 45%|████▍     | 165836/371472 [2:14:24<17:59:58,  3.17it/s]
 45%|████▍     | 165837/371472 [2:14:25<17:27:27,  3.27it/s]
 45%|████▍     | 165838/371472 [2:14:25<17:11:18,  3.32it/s]
 45%|████▍     | 165839/371472 [2:14:25<17:48:44,  3.21it/s]
 45%|████▍     | 165840/371472 [2:14:26<17:19:25,  3.30it/s]
                                                            
{'loss': 2.8336, 'learning_rate': 5.984722790837984e-07, 'epoch': 7.14}
+
 45%|████▍     | 165840/371472 [2:14:26<17:19:25,  3.30it/s]
 45%|████▍     | 165841/371472 [2:14:26<16:52:41,  3.38it/s]
 45%|████▍     | 165842/371472 [2:14:26<16:37:58,  3.43it/s]
 45%|████▍     | 165843/371472 [2:14:26<16:21:41,  3.49it/s]
 45%|████▍     | 165844/371472 [2:14:27<16:40:18,  3.43it/s]
 45%|████▍     | 165845/371472 [2:14:27<16:17:26,  3.51it/s]
 45%|████▍     | 165846/371472 [2:14:27<16:50:10,  3.39it/s]
 45%|████▍     | 165847/371472 [2:14:28<17:09:16,  3.33it/s]
 45%|████▍     | 165848/371472 [2:14:28<18:01:28,  3.17it/s]
 45%|████▍     | 165849/371472 [2:14:28<17:14:09,  3.31it/s]
 45%|████▍     | 165850/371472 [2:14:29<17:45:31,  3.22it/s]
 45%|████▍     | 165851/371472 [2:14:29<17:31:52,  3.26it/s]
 45%|████▍     | 165852/371472 [2:14:29<17:34:37,  3.25it/s]
 45%|████▍     | 165853/371472 [2:14:30<16:55:32,  3.37it/s]
 45%|████▍     | 165854/371472 [2:14:30<16:42:43,  3.42it/s]
 45%|████▍     | 165855/371472 [2:14:30<16:30:59,  3.46it/s]
 45%|████▍     | 165856/371472 [2:14:30<16:12:53,  3.52it/s]
 45%|████▍     | 165857/371472 [2:14:31<16:18:14,  3.50it/s]
 45%|████▍     | 165858/371472 [2:14:31<16:04:56,  3.55it/s]
 45%|████▍     | 165859/371472 [2:14:31<16:19:37,  3.50it/s]
 45%|████▍     | 165860/371472 [2:14:32<16:29:45,  3.46it/s]
                                                            
{'loss': 2.9144, 'learning_rate': 5.984237971083194e-07, 'epoch': 7.14}
+
 45%|████▍     | 165860/371472 [2:14:32<16:29:45,  3.46it/s]
 45%|████▍     | 165861/371472 [2:14:32<16:30:24,  3.46it/s]
 45%|████▍     | 165862/371472 [2:14:32<16:51:33,  3.39it/s]
 45%|████▍     | 165863/371472 [2:14:32<16:37:05,  3.44it/s]
 45%|████▍     | 165864/371472 [2:14:33<18:16:51,  3.12it/s]
 45%|████▍     | 165865/371472 [2:14:33<17:39:31,  3.23it/s]
 45%|████▍     | 165866/371472 [2:14:33<17:03:32,  3.35it/s]
 45%|████▍     | 165867/371472 [2:14:34<16:51:52,  3.39it/s]
 45%|████▍     | 165868/371472 [2:14:34<17:14:21,  3.31it/s]
 45%|████▍     | 165869/371472 [2:14:34<17:00:02,  3.36it/s]
 45%|████▍     | 165870/371472 [2:14:35<17:15:17,  3.31it/s]
 45%|████▍     | 165871/371472 [2:14:35<17:28:35,  3.27it/s]
 45%|████▍     | 165872/371472 [2:14:35<17:27:36,  3.27it/s]
 45%|████▍     | 165873/371472 [2:14:35<17:04:40,  3.34it/s]
 45%|████▍     | 165874/371472 [2:14:36<16:54:19,  3.38it/s]
 45%|████▍     | 165875/371472 [2:14:36<17:27:04,  3.27it/s]
 45%|████▍     | 165876/371472 [2:14:36<17:31:31,  3.26it/s]
 45%|████▍     | 165877/371472 [2:14:37<17:05:35,  3.34it/s]
 45%|████▍     | 165878/371472 [2:14:37<17:14:48,  3.31it/s]
 45%|████▍     | 165879/371472 [2:14:37<17:22:13,  3.29it/s]
 45%|████▍     | 165880/371472 [2:14:38<17:16:49,  3.30it/s]
                                                            
{'loss': 2.8718, 'learning_rate': 5.983753151328406e-07, 'epoch': 7.14}
+
 45%|████▍     | 165880/371472 [2:14:38<17:16:49,  3.30it/s]
 45%|████▍     | 165881/371472 [2:14:38<17:12:58,  3.32it/s]
 45%|████▍     | 165882/371472 [2:14:38<17:30:49,  3.26it/s]
 45%|████▍     | 165883/371472 [2:14:38<17:20:36,  3.29it/s]
 45%|████▍     | 165884/371472 [2:14:39<16:51:14,  3.39it/s]
 45%|████▍     | 165885/371472 [2:14:39<17:07:29,  3.33it/s]
 45%|████▍     | 165886/371472 [2:14:39<16:42:34,  3.42it/s]
 45%|████▍     | 165887/371472 [2:14:40<16:36:17,  3.44it/s]
 45%|████▍     | 165888/371472 [2:14:40<16:44:22,  3.41it/s]
 45%|████▍     | 165889/371472 [2:14:40<16:56:33,  3.37it/s]
 45%|████▍     | 165890/371472 [2:14:41<17:27:28,  3.27it/s]
 45%|████▍     | 165891/371472 [2:14:41<17:59:09,  3.18it/s]
 45%|████▍     | 165892/371472 [2:14:41<18:05:34,  3.16it/s]
 45%|████▍     | 165893/371472 [2:14:42<17:43:17,  3.22it/s]
 45%|████▍     | 165894/371472 [2:14:42<17:12:33,  3.32it/s]
 45%|████▍     | 165895/371472 [2:14:42<17:07:22,  3.33it/s]
 45%|████▍     | 165896/371472 [2:14:42<16:54:15,  3.38it/s]
 45%|████▍     | 165897/371472 [2:14:43<16:52:21,  3.38it/s]
 45%|████▍     | 165898/371472 [2:14:43<16:42:14,  3.42it/s]
 45%|████▍     | 165899/371472 [2:14:43<17:25:41,  3.28it/s]
 45%|████▍     | 165900/371472 [2:14:44<17:18:42,  3.30it/s]
                                                            
{'loss': 2.7754, 'learning_rate': 5.983268331573618e-07, 'epoch': 7.15}
+
 45%|████▍     | 165900/371472 [2:14:44<17:18:42,  3.30it/s]
 45%|████▍     | 165901/371472 [2:14:44<17:46:20,  3.21it/s]
 45%|████▍     | 165902/371472 [2:14:44<17:26:50,  3.27it/s]
 45%|████▍     | 165903/371472 [2:14:45<17:19:09,  3.30it/s]
 45%|████▍     | 165904/371472 [2:14:45<17:02:28,  3.35it/s]
 45%|████▍     | 165905/371472 [2:14:45<16:56:01,  3.37it/s]
 45%|████▍     | 165906/371472 [2:14:45<16:49:46,  3.39it/s]
 45%|████▍     | 165907/371472 [2:14:46<16:49:46,  3.39it/s]
 45%|████▍     | 165908/371472 [2:14:46<16:55:24,  3.37it/s]
 45%|████▍     | 165909/371472 [2:14:46<16:40:34,  3.42it/s]
 45%|████▍     | 165910/371472 [2:14:47<16:42:58,  3.42it/s]
 45%|████▍     | 165911/371472 [2:14:47<16:41:24,  3.42it/s]
 45%|████▍     | 165912/371472 [2:14:47<16:40:53,  3.42it/s]
 45%|████▍     | 165913/371472 [2:14:48<17:52:07,  3.20it/s]
 45%|████▍     | 165914/371472 [2:14:48<17:12:52,  3.32it/s]
 45%|████▍     | 165915/371472 [2:14:48<17:47:57,  3.21it/s]
 45%|████▍     | 165916/371472 [2:14:48<17:39:53,  3.23it/s]
 45%|████▍     | 165917/371472 [2:14:49<17:26:02,  3.28it/s]
 45%|████▍     | 165918/371472 [2:14:49<17:50:10,  3.20it/s]
 45%|████▍     | 165919/371472 [2:14:49<17:39:16,  3.23it/s]
 45%|████▍     | 165920/371472 [2:14:50<17:11:51,  3.32it/s]
                                                            
{'loss': 2.9541, 'learning_rate': 5.982783511818827e-07, 'epoch': 7.15}
+
 45%|████▍     | 165920/371472 [2:14:50<17:11:51,  3.32it/s]
 45%|████▍     | 165921/371472 [2:14:50<17:32:11,  3.26it/s]
 45%|████▍     | 165922/371472 [2:14:50<17:28:14,  3.27it/s]
 45%|████▍     | 165923/371472 [2:14:51<17:57:43,  3.18it/s]
 45%|████▍     | 165924/371472 [2:14:51<17:35:47,  3.24it/s]
 45%|████▍     | 165925/371472 [2:14:51<17:09:56,  3.33it/s]
 45%|████▍     | 165926/371472 [2:14:52<17:52:37,  3.19it/s]
 45%|████▍     | 165927/371472 [2:14:52<17:39:55,  3.23it/s]
 45%|████▍     | 165928/371472 [2:14:52<17:15:35,  3.31it/s]
 45%|████▍     | 165929/371472 [2:14:52<17:11:08,  3.32it/s]
 45%|████▍     | 165930/371472 [2:14:53<18:22:11,  3.11it/s]
 45%|████▍     | 165931/371472 [2:14:53<18:40:55,  3.06it/s]
 45%|████▍     | 165932/371472 [2:14:53<18:16:03,  3.13it/s]
 45%|████▍     | 165933/371472 [2:14:54<18:26:43,  3.10it/s]
 45%|█���██▍     | 165934/371472 [2:14:54<17:41:45,  3.23it/s]
 45%|████▍     | 165935/371472 [2:14:54<17:07:09,  3.34it/s]
 45%|████▍     | 165936/371472 [2:14:55<16:30:17,  3.46it/s]
 45%|████▍     | 165937/371472 [2:14:55<16:50:41,  3.39it/s]
 45%|████▍     | 165938/371472 [2:14:55<16:28:58,  3.46it/s]
 45%|████▍     | 165939/371472 [2:14:55<16:20:06,  3.50it/s]
 45%|████▍     | 165940/371472 [2:14:56<16:50:39,  3.39it/s]
                                                            
{'loss': 3.015, 'learning_rate': 5.982298692064038e-07, 'epoch': 7.15}
+
 45%|████▍     | 165940/371472 [2:14:56<16:50:39,  3.39it/s]
 45%|████▍     | 165941/371472 [2:14:56<16:50:38,  3.39it/s]
 45%|████▍     | 165942/371472 [2:14:56<18:16:49,  3.12it/s]
 45%|████▍     | 165943/371472 [2:14:57<17:49:53,  3.20it/s]
 45%|████▍     | 165944/371472 [2:14:57<17:36:27,  3.24it/s]
 45%|████▍     | 165945/371472 [2:14:57<17:41:45,  3.23it/s]
 45%|████▍     | 165946/371472 [2:14:58<17:51:19,  3.20it/s]
 45%|████▍     | 165947/371472 [2:14:58<17:17:09,  3.30it/s]
 45%|████▍     | 165948/371472 [2:14:58<16:43:21,  3.41it/s]
 45%|████▍     | 165949/371472 [2:14:58<16:25:00,  3.48it/s]
 45%|████▍     | 165950/371472 [2:14:59<17:42:03,  3.23it/s]
 45%|████▍     | 165951/371472 [2:14:59<17:08:21,  3.33it/s]
 45%|████▍     | 165952/371472 [2:14:59<18:54:00,  3.02it/s]
 45%|████▍     | 165953/371472 [2:15:00<18:14:32,  3.13it/s]
 45%|████▍     | 165954/371472 [2:15:00<17:50:04,  3.20it/s]
 45%|████▍     | 165955/371472 [2:15:00<17:26:30,  3.27it/s]
 45%|████▍     | 165956/371472 [2:15:01<17:41:28,  3.23it/s]
 45%|████▍     | 165957/371472 [2:15:01<18:11:20,  3.14it/s]
 45%|████▍     | 165958/371472 [2:15:01<18:05:32,  3.16it/s]
 45%|████▍     | 165959/371472 [2:15:02<18:36:48,  3.07it/s]
 45%|████▍     | 165960/371472 [2:15:02<18:06:18,  3.15it/s]
                                                            
{'loss': 2.849, 'learning_rate': 5.98181387230925e-07, 'epoch': 7.15}
+
 45%|████▍     | 165960/371472 [2:15:02<18:06:18,  3.15it/s]
 45%|████▍     | 165961/371472 [2:15:02<17:43:49,  3.22it/s]
 45%|████▍     | 165962/371472 [2:15:03<19:02:47,  3.00it/s]
 45%|████▍     | 165963/371472 [2:15:03<18:40:06,  3.06it/s]
 45%|████▍     | 165964/371472 [2:15:03<18:12:32,  3.13it/s]
 45%|████▍     | 165965/371472 [2:15:04<17:37:06,  3.24it/s]
 45%|████▍     | 165966/371472 [2:15:04<17:00:59,  3.35it/s]
 45%|████▍     | 165967/371472 [2:15:04<16:37:48,  3.43it/s]
 45%|████▍     | 165968/371472 [2:15:04<16:47:43,  3.40it/s]
 45%|████▍     | 165969/371472 [2:15:05<16:18:09,  3.50it/s]
 45%|████▍     | 165970/371472 [2:15:05<16:08:42,  3.54it/s]
 45%|████▍     | 165971/371472 [2:15:05<16:50:37,  3.39it/s]
 45%|████▍     | 165972/371472 [2:15:06<17:16:29,  3.30it/s]
 45%|████▍     | 165973/371472 [2:15:06<17:07:22,  3.33it/s]
 45%|████▍     | 165974/371472 [2:15:06<16:46:41,  3.40it/s]
 45%|████▍     | 165975/371472 [2:15:06<16:27:44,  3.47it/s]
 45%|████▍     | 165976/371472 [2:15:07<16:06:15,  3.54it/s]
 45%|████▍     | 165977/371472 [2:15:07<16:21:48,  3.49it/s]
 45%|████▍     | 165978/371472 [2:15:07<16:11:06,  3.53it/s]
 45%|████▍     | 165979/371472 [2:15:08<16:34:45,  3.44it/s]
 45%|████▍     | 165980/371472 [2:15:08<16:33:15,  3.45it/s]
                                                            
{'loss': 2.9698, 'learning_rate': 5.981329052554462e-07, 'epoch': 7.15}
+
 45%|████▍     | 165980/371472 [2:15:08<16:33:15,  3.45it/s]
 45%|████▍     | 165981/371472 [2:15:08<16:26:53,  3.47it/s]
 45%|████▍     | 165982/371472 [2:15:08<16:17:37,  3.50it/s]
 45%|████▍     | 165983/371472 [2:15:09<16:26:16,  3.47it/s]
 45%|████▍     | 165984/371472 [2:15:09<16:00:21,  3.57it/s]
 45%|████▍     | 165985/371472 [2:15:09<17:18:53,  3.30it/s]
 45%|████▍     | 165986/371472 [2:15:10<16:59:36,  3.36it/s]
 45%|████▍     | 165987/371472 [2:15:10<16:39:07,  3.43it/s]
 45%|████▍     | 165988/371472 [2:15:10<16:32:45,  3.45it/s]
 45%|████▍     | 165989/371472 [2:15:11<16:39:28,  3.43it/s]
 45%|████▍     | 165990/371472 [2:15:11<16:50:56,  3.39it/s]
 45%|████▍     | 165991/371472 [2:15:11<16:54:03,  3.38it/s]
 45%|████▍     | 165992/371472 [2:15:11<16:44:55,  3.41it/s]
 45%|████▍     | 165993/371472 [2:15:12<16:38:30,  3.43it/s]
 45%|████▍     | 165994/371472 [2:15:12<16:42:35,  3.42it/s]
 45%|████▍     | 165995/371472 [2:15:12<16:46:04,  3.40it/s]
 45%|████▍     | 165996/371472 [2:15:13<16:48:24,  3.40it/s]
 45%|████▍     | 165997/371472 [2:15:13<16:36:11,  3.44it/s]
 45%|████▍     | 165998/371472 [2:15:13<16:16:52,  3.51it/s]
 45%|████▍     | 165999/371472 [2:15:13<16:02:30,  3.56it/s]
 45%|████▍     | 166000/371472 [2:15:14<15:55:52,  3.58it/s]
                                                            
{'loss': 2.7705, 'learning_rate': 5.980844232799672e-07, 'epoch': 7.15}
+
 45%|████▍     | 166000/371472 [2:15:14<15:55:52,  3.58it/s]
 45%|████▍     | 166001/371472 [2:15:14<17:54:36,  3.19it/s]
 45%|████▍     | 166002/371472 [2:15:14<17:31:54,  3.26it/s]
 45%|████▍     | 166003/371472 [2:15:15<17:12:02,  3.32it/s]
 45%|████▍     | 166004/371472 [2:15:15<16:46:29,  3.40it/s]
 45%|████▍     | 166005/371472 [2:15:15<17:50:04,  3.20it/s]
 45%|████▍     | 166006/371472 [2:15:16<17:26:56,  3.27it/s]
 45%|████▍     | 166007/371472 [2:15:16<17:36:22,  3.24it/s]
 45%|████▍     | 166008/371472 [2:15:16<17:48:06,  3.21it/s]
 45%|████▍     | 166009/371472 [2:15:16<16:57:51,  3.36it/s]
 45%|████▍     | 166010/371472 [2:15:17<16:27:07,  3.47it/s]
 45%|████▍     | 166011/371472 [2:15:17<16:53:24,  3.38it/s]
 45%|████▍     | 166012/371472 [2:15:18<19:50:47,  2.88it/s]
 45%|████▍     | 166013/371472 [2:15:18<19:05:08,  2.99it/s]
 45%|████▍     | 166014/371472 [2:15:18<18:08:13,  3.15it/s]
 45%|████▍     | 166015/371472 [2:15:18<17:23:44,  3.28it/s]
 45%|████▍     | 166016/371472 [2:15:19<17:29:11,  3.26it/s]
 45%|████▍     | 166017/371472 [2:15:19<16:52:46,  3.38it/s]
 45%|████▍     | 166018/371472 [2:15:19<16:32:46,  3.45it/s]
 45%|████▍     | 166019/371472 [2:15:20<16:22:16,  3.49it/s]
 45%|████▍     | 166020/371472 [2:15:20<16:19:21,  3.50it/s]
                                                            
{'loss': 2.901, 'learning_rate': 5.980359413044883e-07, 'epoch': 7.15}
+
 45%|████▍     | 166020/371472 [2:15:20<16:19:21,  3.50it/s]
 45%|████▍     | 166021/371472 [2:15:20<17:39:12,  3.23it/s]
 45%|████▍     | 166022/371472 [2:15:20<18:05:56,  3.15it/s]
 45%|████▍     | 166023/371472 [2:15:21<18:11:13,  3.14it/s]
 45%|████▍     | 166024/371472 [2:15:21<17:45:41,  3.21it/s]
 45%|████▍     | 166025/371472 [2:15:21<17:23:29,  3.28it/s]
 45%|████▍     | 166026/371472 [2:15:22<17:26:22,  3.27it/s]
 45%|████▍     | 166027/371472 [2:15:22<17:36:01,  3.24it/s]
 45%|████▍     | 166028/371472 [2:15:22<17:36:48,  3.24it/s]
 45%|████▍     | 166029/371472 [2:15:23<18:21:15,  3.11it/s]
 45%|████▍     | 166030/371472 [2:15:23<18:06:34,  3.15it/s]
 45%|████▍     | 166031/371472 [2:15:23<17:24:23,  3.28it/s]
 45%|████▍     | 166032/371472 [2:15:24<17:03:24,  3.35it/s]
 45%|████▍     | 166033/371472 [2:15:24<16:54:09,  3.38it/s]
 45%|████▍     | 166034/371472 [2:15:24<17:00:16,  3.36it/s]
 45%|████▍     | 166035/371472 [2:15:24<16:56:31,  3.37it/s]
 45%|████▍     | 166036/371472 [2:15:25<17:06:23,  3.34it/s]
 45%|████▍     | 166037/371472 [2:15:25<16:48:19,  3.40it/s]
 45%|████▍     | 166038/371472 [2:15:25<16:27:03,  3.47it/s]
 45%|████▍     | 166039/371472 [2:15:26<16:24:43,  3.48it/s]
 45%|████▍     | 166040/371472 [2:15:26<18:01:49,  3.16it/s]
                                                            
{'loss': 2.876, 'learning_rate': 5.979874593290095e-07, 'epoch': 7.15}
+
 45%|████▍     | 166040/371472 [2:15:26<18:01:49,  3.16it/s]
 45%|████▍     | 166041/371472 [2:15:26<17:36:10,  3.24it/s]
 45%|████▍     | 166042/371472 [2:15:27<17:33:38,  3.25it/s]
 45%|████▍     | 166043/371472 [2:15:27<17:05:31,  3.34it/s]
 45%|████▍     | 166044/371472 [2:15:27<17:09:21,  3.33it/s]
 45%|████▍     | 166045/371472 [2:15:27<17:00:02,  3.36it/s]
 45%|████▍     | 166046/371472 [2:15:28<16:50:24,  3.39it/s]
 45%|████▍     | 166047/371472 [2:15:28<16:39:11,  3.43it/s]
 45%|████▍     | 166048/371472 [2:15:28<16:26:55,  3.47it/s]
 45%|████▍     | 166049/371472 [2:15:29<16:27:34,  3.47it/s]
 45%|████▍     | 166050/371472 [2:15:29<16:23:09,  3.48it/s]
 45%|████▍     | 166051/371472 [2:15:29<16:27:46,  3.47it/s]
 45%|████▍     | 166052/371472 [2:15:29<17:07:57,  3.33it/s]
 45%|████▍     | 166053/371472 [2:15:30<17:31:18,  3.26it/s]
 45%|████▍     | 166054/371472 [2:15:30<17:16:59,  3.30it/s]
 45%|████▍     | 166055/371472 [2:15:30<16:36:01,  3.44it/s]
 45%|████▍     | 166056/371472 [2:15:31<16:12:44,  3.52it/s]
 45%|████▍     | 166057/371472 [2:15:31<15:54:52,  3.59it/s]
 45%|████▍     | 166058/371472 [2:15:31<16:28:39,  3.46it/s]
 45%|████▍     | 166059/371472 [2:15:32<16:46:16,  3.40it/s]
 45%|████▍     | 166060/371472 [2:15:32<16:06:56,  3.54it/s]
                                                            
{'loss': 2.8266, 'learning_rate': 5.979389773535307e-07, 'epoch': 7.15}
+
 45%|████▍     | 166060/371472 [2:15:32<16:06:56,  3.54it/s]
 45%|████▍     | 166061/371472 [2:15:32<16:59:11,  3.36it/s]
 45%|████▍     | 166062/371472 [2:15:32<16:45:19,  3.41it/s]
 45%|████▍     | 166063/371472 [2:15:33<16:26:21,  3.47it/s]
 45%|████▍     | 166064/371472 [2:15:33<16:12:29,  3.52it/s]
 45%|████▍     | 166065/371472 [2:15:33<16:02:23,  3.56it/s]
 45%|████▍     | 166066/371472 [2:15:33<15:46:06,  3.62it/s]
 45%|████▍     | 166067/371472 [2:15:34<15:41:37,  3.64it/s]
 45%|████▍     | 166068/371472 [2:15:34<16:00:04,  3.57it/s]
 45%|████▍     | 166069/371472 [2:15:34<15:56:11,  3.58it/s]
 45%|████▍     | 166070/371472 [2:15:35<16:26:22,  3.47it/s]
 45%|████▍     | 166071/371472 [2:15:35<17:10:47,  3.32it/s]
 45%|████▍     | 166072/371472 [2:15:35<18:40:50,  3.05it/s]
 45%|████▍     | 166073/371472 [2:15:36<18:02:24,  3.16it/s]
 45%|████▍     | 166074/371472 [2:15:36<17:31:58,  3.25it/s]
 45%|████▍     | 166075/371472 [2:15:36<17:50:41,  3.20it/s]
 45%|████▍     | 166076/371472 [2:15:37<17:30:02,  3.26it/s]
 45%|████▍     | 166077/371472 [2:15:37<17:12:22,  3.32it/s]
 45%|████▍     | 166078/371472 [2:15:37<17:33:12,  3.25it/s]
 45%|████▍     | 166079/371472 [2:15:37<17:47:46,  3.21it/s]
 45%|████▍     | 166080/371472 [2:15:38<17:16:19,  3.30it/s]
                                                            
{'loss': 2.9199, 'learning_rate': 5.978904953780516e-07, 'epoch': 7.15}
+
 45%|████▍     | 166080/371472 [2:15:38<17:16:19,  3.30it/s]
 45%|████▍     | 166081/371472 [2:15:38<17:02:02,  3.35it/s]
 45%|████▍     | 166082/371472 [2:15:38<16:54:15,  3.38it/s]
 45%|████▍     | 166083/371472 [2:15:39<17:11:19,  3.32it/s]
 45%|████▍     | 166084/371472 [2:15:39<17:37:19,  3.24it/s]
 45%|████▍     | 166085/371472 [2:15:39<17:38:39,  3.23it/s]
 45%|████▍     | 166086/371472 [2:15:40<17:14:37,  3.31it/s]
 45%|████▍     | 166087/371472 [2:15:40<16:53:01,  3.38it/s]
 45%|████▍     | 166088/371472 [2:15:40<16:54:00,  3.38it/s]
 45%|████▍     | 166089/371472 [2:15:40<16:59:57,  3.36it/s]
 45%|████▍     | 166090/371472 [2:15:41<16:28:31,  3.46it/s]
 45%|████▍     | 166091/371472 [2:15:41<16:42:12,  3.42it/s]
 45%|████▍     | 166092/371472 [2:15:41<16:42:06,  3.42it/s]
 45%|████▍     | 166093/371472 [2:15:42<16:48:14,  3.40it/s]
 45%|████▍     | 166094/371472 [2:15:42<16:29:44,  3.46it/s]
 45%|████▍     | 166095/371472 [2:15:42<16:22:58,  3.48it/s]
 45%|████▍     | 166096/371472 [2:15:43<17:05:29,  3.34it/s]
 45%|████▍     | 166097/371472 [2:15:43<17:24:49,  3.28it/s]
 45%|████▍     | 166098/371472 [2:15:43<17:23:10,  3.28it/s]
 45%|████▍     | 166099/371472 [2:15:43<17:36:40,  3.24it/s]
 45%|████▍     | 166100/371472 [2:15:44<17:27:05,  3.27it/s]
                                                            
{'loss': 3.0151, 'learning_rate': 5.978420134025727e-07, 'epoch': 7.15}
+
 45%|████▍     | 166100/371472 [2:15:44<17:27:05,  3.27it/s]
 45%|████▍     | 166101/371472 [2:15:44<18:10:36,  3.14it/s]
 45%|████▍     | 166102/371472 [2:15:44<17:35:21,  3.24it/s]
 45%|████▍     | 166103/371472 [2:15:45<17:55:32,  3.18it/s]
 45%|████▍     | 166104/371472 [2:15:45<17:30:25,  3.26it/s]
 45%|████▍     | 166105/371472 [2:15:45<17:06:57,  3.33it/s]
 45%|████▍     | 166106/371472 [2:15:46<16:48:37,  3.39it/s]
 45%|████▍     | 166107/371472 [2:15:46<18:05:07,  3.15it/s]
 45%|████▍     | 166108/371472 [2:15:46<17:35:09,  3.24it/s]
 45%|████▍     | 166109/371472 [2:15:47<17:08:13,  3.33it/s]
 45%|████▍     | 166110/371472 [2:15:47<17:47:08,  3.21it/s]
 45%|████▍     | 166111/371472 [2:15:47<17:13:37,  3.31it/s]
 45%|████▍     | 166112/371472 [2:15:47<17:20:21,  3.29it/s]
 45%|████▍     | 166113/371472 [2:15:48<17:28:28,  3.26it/s]
 45%|████▍     | 166114/371472 [2:15:48<17:33:55,  3.25it/s]
 45%|████▍     | 166115/371472 [2:15:48<17:15:24,  3.31it/s]
 45%|████▍     | 166116/371472 [2:15:49<17:40:36,  3.23it/s]
 45%|████▍     | 166117/371472 [2:15:49<17:34:08,  3.25it/s]
 45%|████▍     | 166118/371472 [2:15:49<17:01:42,  3.35it/s]
 45%|████▍     | 166119/371472 [2:15:50<16:59:49,  3.36it/s]
 45%|████▍     | 166120/371472 [2:15:50<16:54:09,  3.37it/s]
                                                            
{'loss': 3.0024, 'learning_rate': 5.977935314270939e-07, 'epoch': 7.16}
+
 45%|████▍     | 166120/371472 [2:15:50<16:54:09,  3.37it/s]
 45%|████▍     | 166121/371472 [2:15:50<18:03:31,  3.16it/s]
 45%|████▍     | 166122/371472 [2:15:50<17:39:49,  3.23it/s]
 45%|████▍     | 166123/371472 [2:15:51<17:04:31,  3.34it/s]
 45%|████▍     | 166124/371472 [2:15:51<16:52:03,  3.38it/s]
 45%|████▍     | 166125/371472 [2:15:51<17:49:11,  3.20it/s]
 45%|████▍     | 166126/371472 [2:15:52<17:31:20,  3.26it/s]
 45%|████▍     | 166127/371472 [2:15:52<17:01:51,  3.35it/s]
 45%|████▍     | 166128/371472 [2:15:52<17:50:17,  3.20it/s]
 45%|████▍     | 166129/371472 [2:15:53<17:36:30,  3.24it/s]
 45%|████▍     | 166130/371472 [2:15:53<17:08:10,  3.33it/s]
 45%|████▍     | 166131/371472 [2:15:53<17:13:00,  3.31it/s]
 45%|████▍     | 166132/371472 [2:15:54<18:46:01,  3.04it/s]
 45%|████▍     | 166133/371472 [2:15:54<17:54:32,  3.18it/s]
 45%|████▍     | 166134/371472 [2:15:54<17:58:29,  3.17it/s]
 45%|████▍     | 166135/371472 [2:15:55<17:39:41,  3.23it/s]
 45%|████▍     | 166136/371472 [2:15:55<17:25:41,  3.27it/s]
 45%|████▍     | 166137/371472 [2:15:55<18:00:17,  3.17it/s]
 45%|████▍     | 166138/371472 [2:15:55<18:41:50,  3.05it/s]
 45%|████▍     | 166139/371472 [2:15:56<17:43:17,  3.22it/s]
 45%|████▍     | 166140/371472 [2:15:56<18:39:21,  3.06it/s]
                                                            
{'loss': 2.8695, 'learning_rate': 5.97745049451615e-07, 'epoch': 7.16}
+
 45%|████▍     | 166140/371472 [2:15:56<18:39:21,  3.06it/s]
 45%|████▍     | 166141/371472 [2:15:56<17:52:13,  3.19it/s]
 45%|████▍     | 166142/371472 [2:15:57<17:12:45,  3.31it/s]
 45%|████▍     | 166143/371472 [2:15:57<16:38:13,  3.43it/s]
 45%|████▍     | 166144/371472 [2:15:57<16:39:02,  3.43it/s]
 45%|████▍     | 166145/371472 [2:15:58<18:12:22,  3.13it/s]
 45%|████▍     | 166146/371472 [2:15:58<17:17:19,  3.30it/s]
 45%|████▍     | 166147/371472 [2:15:58<17:05:25,  3.34it/s]
 45%|████▍     | 166148/371472 [2:15:59<17:48:47,  3.20it/s]
 45%|████▍     | 166149/371472 [2:15:59<17:06:09,  3.33it/s]
 45%|████▍     | 166150/371472 [2:15:59<16:43:15,  3.41it/s]
 45%|████▍     | 166151/371472 [2:15:59<16:13:26,  3.52it/s]
 45%|████▍     | 166152/371472 [2:16:00<16:23:12,  3.48it/s]
 45%|████▍     | 166153/371472 [2:16:00<16:30:17,  3.46it/s]
 45%|████▍     | 166154/371472 [2:16:00<16:32:40,  3.45it/s]
 45%|████▍     | 166155/371472 [2:16:01<17:24:11,  3.28it/s]
 45%|████▍     | 166156/371472 [2:16:01<16:43:51,  3.41it/s]
 45%|████▍     | 166157/371472 [2:16:01<17:09:47,  3.32it/s]
 45%|████▍     | 166158/371472 [2:16:01<16:46:40,  3.40it/s]
 45%|████▍     | 166159/371472 [2:16:02<17:07:28,  3.33it/s]
 45%|████▍     | 166160/371472 [2:16:02<17:36:08,  3.24it/s]
                                                            
{'loss': 3.1322, 'learning_rate': 5.976965674761361e-07, 'epoch': 7.16}
+
 45%|████▍     | 166160/371472 [2:16:02<17:36:08,  3.24it/s]
 45%|████▍     | 166161/371472 [2:16:02<17:34:49,  3.24it/s]
 45%|████▍     | 166162/371472 [2:16:03<17:27:07,  3.27it/s]
 45%|████▍     | 166163/371472 [2:16:03<17:04:49,  3.34it/s]
 45%|████▍     | 166164/371472 [2:16:03<18:17:38,  3.12it/s]
 45%|████▍     | 166165/371472 [2:16:04<17:42:37,  3.22it/s]
 45%|████▍     | 166166/371472 [2:16:04<17:19:22,  3.29it/s]
 45%|████▍     | 166167/371472 [2:16:04<17:32:50,  3.25it/s]
 45%|████▍     | 166168/371472 [2:16:05<17:07:14,  3.33it/s]
 45%|████▍     | 166169/371472 [2:16:05<16:56:40,  3.37it/s]
 45%|████▍     | 166170/371472 [2:16:05<16:31:17,  3.45it/s]
 45%|████▍     | 166171/371472 [2:16:05<16:52:30,  3.38it/s]
 45%|████▍     | 166172/371472 [2:16:06<16:49:36,  3.39it/s]
 45%|████▍     | 166173/371472 [2:16:06<16:41:32,  3.42it/s]
 45%|████▍     | 166174/371472 [2:16:06<17:36:27,  3.24it/s]
 45%|████▍     | 166175/371472 [2:16:07<17:01:13,  3.35it/s]
 45%|████▍     | 166176/371472 [2:16:07<16:56:39,  3.37it/s]
 45%|████▍     | 166177/371472 [2:16:07<18:01:21,  3.16it/s]
 45%|████▍     | 166178/371472 [2:16:08<17:36:54,  3.24it/s]
 45%|████▍     | 166179/371472 [2:16:08<17:59:36,  3.17it/s]
 45%|████▍     | 166180/371472 [2:16:08<17:26:09,  3.27it/s]
                                                            
{'loss': 3.1076, 'learning_rate': 5.976480855006571e-07, 'epoch': 7.16}
+
 45%|████▍     | 166180/371472 [2:16:08<17:26:09,  3.27it/s]
 45%|████▍     | 166181/371472 [2:16:08<17:22:18,  3.28it/s]
 45%|████▍     | 166182/371472 [2:16:09<18:58:07,  3.01it/s]
 45%|████▍     | 166183/371472 [2:16:09<18:03:18,  3.16it/s]
 45%|████▍     | 166184/371472 [2:16:09<17:40:34,  3.23it/s]
 45%|████▍     | 166185/371472 [2:16:10<17:47:36,  3.20it/s]
 45%|████▍     | 166186/371472 [2:16:10<17:30:01,  3.26it/s]
 45%|████▍     | 166187/371472 [2:16:10<17:24:56,  3.27it/s]
 45%|████▍     | 166188/371472 [2:16:11<17:08:21,  3.33it/s]
 45%|████▍     | 166189/371472 [2:16:11<16:29:32,  3.46it/s]
 45%|████▍     | 166190/371472 [2:16:11<16:58:09,  3.36it/s]
 45%|████▍     | 166191/371472 [2:16:12<18:32:20,  3.08it/s]
 45%|████▍     | 166192/371472 [2:16:12<17:23:28,  3.28it/s]
 45%|████▍     | 166193/371472 [2:16:12<16:53:22,  3.38it/s]
 45%|████▍     | 166194/371472 [2:16:12<16:53:59,  3.37it/s]
 45%|████▍     | 166195/371472 [2:16:13<16:54:01,  3.37it/s]
 45%|████▍     | 166196/371472 [2:16:13<16:47:48,  3.39it/s]
 45%|████▍     | 166197/371472 [2:16:13<16:33:20,  3.44it/s]
 45%|████▍     | 166198/371472 [2:16:14<16:43:30,  3.41it/s]
 45%|████▍     | 166199/371472 [2:16:14<16:36:58,  3.43it/s]
 45%|████▍     | 166200/371472 [2:16:14<16:33:50,  3.44it/s]
                                                            
{'loss': 3.0057, 'learning_rate': 5.975996035251783e-07, 'epoch': 7.16}
+
 45%|████▍     | 166200/371472 [2:16:14<16:33:50,  3.44it/s]
 45%|████▍     | 166201/371472 [2:16:15<17:40:59,  3.22it/s]
 45%|████▍     | 166202/371472 [2:16:15<16:59:56,  3.35it/s]
 45%|████▍     | 166203/371472 [2:16:15<17:12:48,  3.31it/s]
 45%|████▍     | 166204/371472 [2:16:15<17:40:38,  3.23it/s]
 45%|████▍     | 166205/371472 [2:16:16<17:01:09,  3.35it/s]
 45%|████▍     | 166206/371472 [2:16:16<16:39:34,  3.42it/s]
 45%|████▍     | 166207/371472 [2:16:16<16:34:32,  3.44it/s]
 45%|████▍     | 166208/371472 [2:16:17<16:44:18,  3.41it/s]
 45%|████▍     | 166209/371472 [2:16:17<16:38:02,  3.43it/s]
 45%|████▍     | 166210/371472 [2:16:17<17:54:11,  3.18it/s]
 45%|████▍     | 166211/371472 [2:16:18<17:51:23,  3.19it/s]
 45%|████▍     | 166212/371472 [2:16:18<18:00:43,  3.17it/s]
 45%|████▍     | 166213/371472 [2:16:18<17:45:57,  3.21it/s]
 45%|████▍     | 166214/371472 [2:16:18<17:38:41,  3.23it/s]
 45%|████▍     | 166215/371472 [2:16:19<18:19:56,  3.11it/s]
 45%|████▍     | 166216/371472 [2:16:19<18:16:12,  3.12it/s]
 45%|████▍     | 166217/371472 [2:16:19<17:47:37,  3.20it/s]
 45%|████▍     | 166218/371472 [2:16:20<17:50:57,  3.19it/s]
 45%|████▍     | 166219/371472 [2:16:20<17:15:30,  3.30it/s]
 45%|████▍     | 166220/371472 [2:16:20<17:23:39,  3.28it/s]
                                                            
{'loss': 2.7869, 'learning_rate': 5.975511215496994e-07, 'epoch': 7.16}
+
 45%|████▍     | 166220/371472 [2:16:20<17:23:39,  3.28it/s]
 45%|████▍     | 166221/371472 [2:16:21<17:04:55,  3.34it/s]
 45%|████▍     | 166222/371472 [2:16:21<17:35:50,  3.24it/s]
 45%|████▍     | 166223/371472 [2:16:21<18:33:01,  3.07it/s]
 45%|████▍     | 166224/371472 [2:16:22<18:23:03,  3.10it/s]
 45%|████▍     | 166225/371472 [2:16:22<18:49:21,  3.03it/s]
 45%|████▍     | 166226/371472 [2:16:22<18:12:49,  3.13it/s]
 45%|████▍     | 166227/371472 [2:16:23<17:58:08,  3.17it/s]
 45%|████▍     | 166228/371472 [2:16:23<17:20:58,  3.29it/s]
 45%|████▍     | 166229/371472 [2:16:23<17:36:22,  3.24it/s]
 45%|████▍     | 166230/371472 [2:16:23<17:34:19,  3.24it/s]
 45%|████▍     | 166231/371472 [2:16:24<18:23:40,  3.10it/s]
 45%|████▍     | 166232/371472 [2:16:24<17:53:09,  3.19it/s]
 45%|████▍     | 166233/371472 [2:16:24<17:53:14,  3.19it/s]
 45%|████▍     | 166234/371472 [2:16:25<17:44:46,  3.21it/s]
 45%|████▍     | 166235/371472 [2:16:25<18:33:40,  3.07it/s]
 45%|████▍     | 166236/371472 [2:16:25<18:37:17,  3.06it/s]
 45%|████▍     | 166237/371472 [2:16:26<18:10:08,  3.14it/s]
 45%|████▍     | 166238/371472 [2:16:26<19:07:43,  2.98it/s]
 45%|████▍     | 166239/371472 [2:16:26<19:07:32,  2.98it/s]
 45%|████▍     | 166240/371472 [2:16:27<18:22:00,  3.10it/s]
                                                            
{'loss': 2.9718, 'learning_rate': 5.975026395742205e-07, 'epoch': 7.16}
+
 45%|████▍     | 166240/371472 [2:16:27<18:22:00,  3.10it/s]
 45%|████▍     | 166241/371472 [2:16:27<18:55:47,  3.01it/s]
 45%|████▍     | 166242/371472 [2:16:27<18:48:07,  3.03it/s]
 45%|████▍     | 166243/371472 [2:16:28<19:11:45,  2.97it/s]
 45%|████▍     | 166244/371472 [2:16:28<18:54:14,  3.02it/s]
 45%|████▍     | 166245/371472 [2:16:28<17:37:37,  3.23it/s]
 45%|████▍     | 166246/371472 [2:16:29<16:58:21,  3.36it/s]
 45%|████▍     | 166247/371472 [2:16:29<16:57:59,  3.36it/s]
 45%|████▍     | 166248/371472 [2:16:29<18:04:22,  3.15it/s]
 45%|████▍     | 166249/371472 [2:16:30<19:11:53,  2.97it/s]
 45%|████▍     | 166250/371472 [2:16:30<18:56:15,  3.01it/s]
 45%|████▍     | 166251/371472 [2:16:30<18:43:25,  3.04it/s]
 45%|████▍     | 166252/371472 [2:16:31<18:36:35,  3.06it/s]
 45%|████▍     | 166253/371472 [2:16:31<18:25:39,  3.09it/s]
 45%|████▍     | 166254/371472 [2:16:31<18:01:23,  3.16it/s]
 45%|████▍     | 166255/371472 [2:16:32<17:55:18,  3.18it/s]
 45%|████▍     | 166256/371472 [2:16:32<17:38:25,  3.23it/s]
 45%|████▍     | 166257/371472 [2:16:32<17:37:27,  3.23it/s]
 45%|████▍     | 166258/371472 [2:16:32<18:06:21,  3.15it/s]
 45%|████▍     | 166259/371472 [2:16:33<19:20:27,  2.95it/s]
 45%|████▍     | 166260/371472 [2:16:33<18:32:49,  3.07it/s]
                                                            
{'loss': 2.8379, 'learning_rate': 5.974541575987416e-07, 'epoch': 7.16}
+
 45%|████▍     | 166260/371472 [2:16:33<18:32:49,  3.07it/s]
 45%|████▍     | 166261/371472 [2:16:33<18:28:05,  3.09it/s]
 45%|████▍     | 166262/371472 [2:16:34<18:07:12,  3.15it/s]
 45%|████▍     | 166263/371472 [2:16:34<17:46:32,  3.21it/s]
 45%|████▍     | 166264/371472 [2:16:34<18:01:39,  3.16it/s]
 45%|████▍     | 166265/371472 [2:16:35<17:13:16,  3.31it/s]
 45%|████▍     | 166266/371472 [2:16:35<16:45:51,  3.40it/s]
 45%|████▍     | 166267/371472 [2:16:35<16:58:05,  3.36it/s]
 45%|████▍     | 166268/371472 [2:16:36<17:11:46,  3.31it/s]
 45%|████▍     | 166269/371472 [2:16:36<17:22:56,  3.28it/s]
 45%|████▍     | 166270/371472 [2:16:36<17:22:59,  3.28it/s]
 45%|████▍     | 166271/371472 [2:16:36<17:23:50,  3.28it/s]
 45%|████▍     | 166272/371472 [2:16:37<17:17:00,  3.30it/s]
 45%|████▍     | 166273/371472 [2:16:37<17:27:41,  3.26it/s]
 45%|████▍     | 166274/371472 [2:16:37<18:07:51,  3.14it/s]
 45%|████▍     | 166275/371472 [2:16:38<17:31:10,  3.25it/s]
 45%|████▍     | 166276/371472 [2:16:38<17:14:31,  3.31it/s]
 45%|████▍     | 166277/371472 [2:16:38<16:53:42,  3.37it/s]
 45%|████▍     | 166278/371472 [2:16:39<16:56:00,  3.37it/s]
 45%|████▍     | 166279/371472 [2:16:39<16:44:35,  3.40it/s]
 45%|████▍     | 166280/371472 [2:16:39<17:12:47,  3.31it/s]
                                                            
{'loss': 3.0159, 'learning_rate': 5.974056756232628e-07, 'epoch': 7.16}
+
 45%|████▍     | 166280/371472 [2:16:39<17:12:47,  3.31it/s]
 45%|████▍     | 166281/371472 [2:16:40<17:46:00,  3.21it/s]
 45%|████▍     | 166282/371472 [2:16:40<17:17:35,  3.30it/s]
 45%|████▍     | 166283/371472 [2:16:40<17:10:23,  3.32it/s]
 45%|████▍     | 166284/371472 [2:16:40<17:52:03,  3.19it/s]
 45%|████▍     | 166285/371472 [2:16:41<17:35:46,  3.24it/s]
 45%|████▍     | 166286/371472 [2:16:41<17:22:15,  3.28it/s]
 45%|████▍     | 166287/371472 [2:16:41<17:35:04,  3.24it/s]
 45%|████▍     | 166288/371472 [2:16:42<16:53:08,  3.38it/s]
 45%|████▍     | 166289/371472 [2:16:42<16:53:17,  3.37it/s]
 45%|████▍     | 166290/371472 [2:16:42<16:52:58,  3.38it/s]
 45%|████▍     | 166291/371472 [2:16:43<16:50:29,  3.38it/s]
 45%|████▍     | 166292/371472 [2:16:43<16:09:30,  3.53it/s]
 45%|████▍     | 166293/371472 [2:16:43<15:41:55,  3.63it/s]
 45%|████▍     | 166294/371472 [2:16:43<16:09:12,  3.53it/s]
 45%|████▍     | 166295/371472 [2:16:44<15:51:42,  3.59it/s]
 45%|████▍     | 166296/371472 [2:16:44<18:23:32,  3.10it/s]
 45%|████▍     | 166297/371472 [2:16:44<17:55:38,  3.18it/s]
 45%|████▍     | 166298/371472 [2:16:45<17:52:19,  3.19it/s]
 45%|████▍     | 166299/371472 [2:16:45<17:47:11,  3.20it/s]
 45%|████▍     | 166300/371472 [2:16:45<17:24:24,  3.27it/s]
                                                            
{'loss': 2.9229, 'learning_rate': 5.973571936477838e-07, 'epoch': 7.16}
+
 45%|████▍     | 166300/371472 [2:16:45<17:24:24,  3.27it/s]
 45%|████▍     | 166301/371472 [2:16:46<17:19:17,  3.29it/s]
 45%|████▍     | 166302/371472 [2:16:46<18:12:02,  3.13it/s]
 45%|████▍     | 166303/371472 [2:16:46<17:47:06,  3.20it/s]
 45%|████▍     | 166304/371472 [2:16:47<17:49:25,  3.20it/s]
 45%|████▍     | 166305/371472 [2:16:47<17:21:05,  3.28it/s]
 45%|████▍     | 166306/371472 [2:16:47<17:18:59,  3.29it/s]
 45%|████▍     | 166307/371472 [2:16:47<17:29:45,  3.26it/s]
 45%|████▍     | 166308/371472 [2:16:48<16:44:07,  3.41it/s]
 45%|████▍     | 166309/371472 [2:16:48<17:13:57,  3.31it/s]
 45%|████▍     | 166310/371472 [2:16:48<16:44:02,  3.41it/s]
 45%|████▍     | 166311/371472 [2:16:49<16:42:00,  3.41it/s]
 45%|████▍     | 166312/371472 [2:16:49<16:53:54,  3.37it/s]
 45%|████▍     | 166313/371472 [2:16:49<16:37:06,  3.43it/s]
 45%|████▍     | 166314/371472 [2:16:49<16:41:51,  3.41it/s]
 45%|████▍     | 166315/371472 [2:16:50<16:33:12,  3.44it/s]
 45%|████▍     | 166316/371472 [2:16:50<16:31:06,  3.45it/s]
 45%|████▍     | 166317/371472 [2:16:50<16:11:36,  3.52it/s]
 45%|████▍     | 166318/371472 [2:16:51<17:33:06,  3.25it/s]
 45%|████▍     | 166319/371472 [2:16:51<17:09:30,  3.32it/s]
 45%|████▍     | 166320/371472 [2:16:51<17:01:30,  3.35it/s]
                                                            
{'loss': 2.9966, 'learning_rate': 5.973087116723049e-07, 'epoch': 7.16}
+
 45%|████▍     | 166320/371472 [2:16:51<17:01:30,  3.35it/s]
 45%|████▍     | 166321/371472 [2:16:52<17:54:12,  3.18it/s]
 45%|████▍     | 166322/371472 [2:16:52<17:21:10,  3.28it/s]
 45%|████▍     | 166323/371472 [2:16:52<17:15:37,  3.30it/s]
 45%|████▍     | 166324/371472 [2:16:52<17:12:11,  3.31it/s]
 45%|████▍     | 166325/371472 [2:16:53<16:48:20,  3.39it/s]
 45%|████▍     | 166326/371472 [2:16:53<16:50:39,  3.38it/s]
 45%|████▍     | 166327/371472 [2:16:53<16:41:30,  3.41it/s]
 45%|████▍     | 166328/371472 [2:16:54<18:00:36,  3.16it/s]
 45%|████▍     | 166329/371472 [2:16:54<18:18:18,  3.11it/s]
 45%|████▍     | 166330/371472 [2:16:54<18:05:52,  3.15it/s]
 45%|████▍     | 166331/371472 [2:16:55<17:49:32,  3.20it/s]
 45%|████▍     | 166332/371472 [2:16:55<18:01:58,  3.16it/s]
 45%|████▍     | 166333/371472 [2:16:55<17:32:07,  3.25it/s]
 45%|████▍     | 166334/371472 [2:16:56<17:16:11,  3.30it/s]
 45%|████▍     | 166335/371472 [2:16:56<17:00:06,  3.35it/s]
 45%|████▍     | 166336/371472 [2:16:56<18:08:01,  3.14it/s]
 45%|████▍     | 166337/371472 [2:16:57<18:49:23,  3.03it/s]
 45%|████▍     | 166338/371472 [2:16:57<18:49:21,  3.03it/s]
 45%|████▍     | 166339/371472 [2:16:57<17:43:04,  3.22it/s]
 45%|████▍     | 166340/371472 [2:16:57<17:28:56,  3.26it/s]
                                                            
{'loss': 3.0938, 'learning_rate': 5.97260229696826e-07, 'epoch': 7.16}
+
 45%|████▍     | 166340/371472 [2:16:57<17:28:56,  3.26it/s]
 45%|████▍     | 166341/371472 [2:16:58<17:10:02,  3.32it/s]
 45%|████▍     | 166342/371472 [2:16:58<16:37:35,  3.43it/s]
 45%|████▍     | 166343/371472 [2:16:58<16:42:12,  3.41it/s]
 45%|████▍     | 166344/371472 [2:16:59<18:06:55,  3.15it/s]
 45%|████▍     | 166345/371472 [2:16:59<17:51:02,  3.19it/s]
 45%|████▍     | 166346/371472 [2:16:59<17:52:12,  3.19it/s]
 45%|████▍     | 166347/371472 [2:17:00<17:37:57,  3.23it/s]
 45%|████▍     | 166348/371472 [2:17:00<17:08:35,  3.32it/s]
 45%|████▍     | 166349/371472 [2:17:00<17:53:04,  3.19it/s]
 45%|████▍     | 166350/371472 [2:17:01<17:36:48,  3.23it/s]
 45%|████▍     | 166351/371472 [2:17:01<17:58:51,  3.17it/s]
 45%|████▍     | 166352/371472 [2:17:01<17:17:15,  3.30it/s]
 45%|████▍     | 166353/371472 [2:17:01<16:53:33,  3.37it/s]
 45%|████▍     | 166354/371472 [2:17:02<16:58:38,  3.36it/s]
 45%|████▍     | 166355/371472 [2:17:02<16:59:33,  3.35it/s]
 45%|████▍     | 166356/371472 [2:17:02<16:48:57,  3.39it/s]
 45%|████▍     | 166357/371472 [2:17:03<16:40:55,  3.42it/s]
 45%|████▍     | 166358/371472 [2:17:03<17:45:23,  3.21it/s]
 45%|████▍     | 166359/371472 [2:17:03<17:11:14,  3.31it/s]
 45%|████▍     | 166360/371472 [2:17:04<16:59:57,  3.35it/s]
                                                            
{'loss': 2.8535, 'learning_rate': 5.972117477213472e-07, 'epoch': 7.17}
+
 45%|████▍     | 166360/371472 [2:17:04<16:59:57,  3.35it/s]
 45%|████▍     | 166361/371472 [2:17:04<16:24:31,  3.47it/s]
 45%|████▍     | 166362/371472 [2:17:04<16:33:59,  3.44it/s]
 45%|████▍     | 166363/371472 [2:17:04<16:45:19,  3.40it/s]
 45%|████▍     | 166364/371472 [2:17:05<16:37:07,  3.43it/s]
 45%|████▍     | 166365/371472 [2:17:05<16:37:20,  3.43it/s]
 45%|████▍     | 166366/371472 [2:17:05<16:21:33,  3.48it/s]
 45%|████▍     | 166367/371472 [2:17:06<16:15:32,  3.50it/s]
 45%|████▍     | 166368/371472 [2:17:06<16:19:28,  3.49it/s]
 45%|████▍     | 166369/371472 [2:17:06<16:17:27,  3.50it/s]
 45%|████▍     | 166370/371472 [2:17:06<17:25:44,  3.27it/s]
 45%|████▍     | 166371/371472 [2:17:07<17:07:30,  3.33it/s]
 45%|████▍     | 166372/371472 [2:17:07<16:59:53,  3.35it/s]
 45%|████▍     | 166373/371472 [2:17:07<17:13:47,  3.31it/s]
 45%|████▍     | 166374/371472 [2:17:08<18:32:40,  3.07it/s]
 45%|██��█▍     | 166375/371472 [2:17:08<18:29:52,  3.08it/s]
 45%|████▍     | 166376/371472 [2:17:08<17:52:21,  3.19it/s]
 45%|████▍     | 166377/371472 [2:17:09<17:30:21,  3.25it/s]
 45%|████▍     | 166378/371472 [2:17:09<17:06:49,  3.33it/s]
 45%|████▍     | 166379/371472 [2:17:09<18:16:47,  3.12it/s]
 45%|████▍     | 166380/371472 [2:17:10<17:49:51,  3.19it/s]
                                                            
{'loss': 2.8759, 'learning_rate': 5.971632657458683e-07, 'epoch': 7.17}
+
 45%|████▍     | 166380/371472 [2:17:10<17:49:51,  3.19it/s]
 45%|████▍     | 166381/371472 [2:17:10<17:31:53,  3.25it/s]
 45%|████▍     | 166382/371472 [2:17:10<17:29:30,  3.26it/s]
 45%|████▍     | 166383/371472 [2:17:10<17:12:22,  3.31it/s]
 45%|████▍     | 166384/371472 [2:17:11<17:04:33,  3.34it/s]
 45%|████▍     | 166385/371472 [2:17:11<17:18:11,  3.29it/s]
 45%|████▍     | 166386/371472 [2:17:11<17:21:58,  3.28it/s]
 45%|████▍     | 166387/371472 [2:17:12<17:04:50,  3.34it/s]
 45%|████▍     | 166388/371472 [2:17:12<16:46:24,  3.40it/s]
 45%|████▍     | 166389/371472 [2:17:12<17:16:52,  3.30it/s]
 45%|████▍     | 166390/371472 [2:17:13<18:05:47,  3.15it/s]
 45%|████▍     | 166391/371472 [2:17:13<17:37:29,  3.23it/s]
 45%|████▍     | 166392/371472 [2:17:13<17:09:58,  3.32it/s]
 45%|████▍     | 166393/371472 [2:17:14<19:41:52,  2.89it/s]
 45%|████▍     | 166394/371472 [2:17:14<20:04:00,  2.84it/s]
 45%|████▍     | 166395/371472 [2:17:14<18:54:28,  3.01it/s]
 45%|████▍     | 166396/371472 [2:17:15<19:54:45,  2.86it/s]
 45%|████▍     | 166397/371472 [2:17:15<19:25:01,  2.93it/s]
 45%|████▍     | 166398/371472 [2:17:15<18:47:39,  3.03it/s]
 45%|████▍     | 166399/371472 [2:17:16<18:49:05,  3.03it/s]
 45%|████▍     | 166400/371472 [2:17:16<17:49:09,  3.20it/s]
                                                            
{'loss': 2.9628, 'learning_rate': 5.971147837703893e-07, 'epoch': 7.17}
+
 45%|████▍     | 166400/371472 [2:17:16<17:49:09,  3.20it/s]
 45%|████▍     | 166401/371472 [2:17:16<17:18:46,  3.29it/s]
 45%|████▍     | 166402/371472 [2:17:16<16:49:05,  3.39it/s]
 45%|████▍     | 166403/371472 [2:17:17<17:17:19,  3.29it/s]
 45%|████▍     | 166404/371472 [2:17:17<16:59:31,  3.35it/s]
 45%|████▍     | 166405/371472 [2:17:17<16:59:30,  3.35it/s]
 45%|████▍     | 166406/371472 [2:17:18<18:29:41,  3.08it/s]
 45%|████▍     | 166407/371472 [2:17:18<17:32:30,  3.25it/s]
 45%|████▍     | 166408/371472 [2:17:18<17:52:41,  3.19it/s]
 45%|████▍     | 166409/371472 [2:17:19<17:23:20,  3.28it/s]
 45%|████▍     | 166410/371472 [2:17:19<16:54:55,  3.37it/s]
 45%|████▍     | 166411/371472 [2:17:19<17:00:25,  3.35it/s]
 45%|████▍     | 166412/371472 [2:17:19<16:40:31,  3.42it/s]
 45%|████▍     | 166413/371472 [2:17:20<16:43:52,  3.40it/s]
 45%|████▍     | 166414/371472 [2:17:20<16:43:47,  3.40it/s]
 45%|████▍     | 166415/371472 [2:17:20<17:26:12,  3.27it/s]
 45%|████▍     | 166416/371472 [2:17:21<17:14:05,  3.30it/s]
 45%|████▍     | 166417/371472 [2:17:21<16:51:51,  3.38it/s]
 45%|████▍     | 166418/371472 [2:17:21<16:38:01,  3.42it/s]
 45%|████▍     | 166419/371472 [2:17:22<16:32:32,  3.44it/s]
 45%|████▍     | 166420/371472 [2:17:22<16:14:36,  3.51it/s]
                                                            
{'loss': 2.9814, 'learning_rate': 5.970663017949105e-07, 'epoch': 7.17}
+
 45%|████▍     | 166420/371472 [2:17:22<16:14:36,  3.51it/s]
 45%|████▍     | 166421/371472 [2:17:22<16:23:58,  3.47it/s]
 45%|████▍     | 166422/371472 [2:17:23<19:35:43,  2.91it/s]
 45%|████▍     | 166423/371472 [2:17:23<19:21:29,  2.94it/s]
 45%|████▍     | 166424/371472 [2:17:23<18:42:14,  3.05it/s]
 45%|████▍     | 166425/371472 [2:17:24<18:01:43,  3.16it/s]
 45%|████▍     | 166426/371472 [2:17:24<18:19:12,  3.11it/s]
 45%|████▍     | 166427/371472 [2:17:24<17:25:19,  3.27it/s]
 45%|████▍     | 166428/371472 [2:17:24<16:58:29,  3.36it/s]
 45%|████▍     | 166429/371472 [2:17:25<16:43:45,  3.40it/s]
 45%|████▍     | 166430/371472 [2:17:25<16:42:47,  3.41it/s]
 45%|████▍     | 166431/371472 [2:17:25<16:38:14,  3.42it/s]
 45%|████▍     | 166432/371472 [2:17:26<16:13:47,  3.51it/s]
 45%|████▍     | 166433/371472 [2:17:26<16:18:58,  3.49it/s]
 45%|████▍     | 166434/371472 [2:17:26<17:37:40,  3.23it/s]
 45%|████▍     | 166435/371472 [2:17:27<17:38:18,  3.23it/s]
 45%|████▍     | 166436/371472 [2:17:27<16:57:14,  3.36it/s]
 45%|████▍     | 166437/371472 [2:17:27<16:38:53,  3.42it/s]
 45%|████▍     | 166438/371472 [2:17:27<17:06:12,  3.33it/s]
 45%|████▍     | 166439/371472 [2:17:28<17:15:16,  3.30it/s]
 45%|████▍     | 166440/371472 [2:17:28<16:48:39,  3.39it/s]
                                                            
{'loss': 2.8651, 'learning_rate': 5.970178198194315e-07, 'epoch': 7.17}
+
 45%|████▍     | 166440/371472 [2:17:28<16:48:39,  3.39it/s]
 45%|████▍     | 166441/371472 [2:17:28<17:11:35,  3.31it/s]
 45%|████▍     | 166442/371472 [2:17:29<16:36:24,  3.43it/s]
 45%|████▍     | 166443/371472 [2:17:29<17:41:48,  3.22it/s]
 45%|████▍     | 166444/371472 [2:17:29<17:28:44,  3.26it/s]
 45%|████▍     | 166445/371472 [2:17:29<17:12:56,  3.31it/s]
 45%|████▍     | 166446/371472 [2:17:30<17:14:27,  3.30it/s]
 45%|████▍     | 166447/371472 [2:17:30<17:01:13,  3.35it/s]
 45%|████▍     | 166448/371472 [2:17:30<17:46:11,  3.20it/s]
 45%|████▍     | 166449/371472 [2:17:31<17:32:11,  3.25it/s]
 45%|████▍     | 166450/371472 [2:17:31<18:03:49,  3.15it/s]
 45%|████▍     | 166451/371472 [2:17:31<17:10:01,  3.32it/s]
 45%|████▍     | 166452/371472 [2:17:32<16:50:55,  3.38it/s]
 45%|████▍     | 166453/371472 [2:17:32<17:58:24,  3.17it/s]
 45%|████▍     | 166454/371472 [2:17:32<17:15:13,  3.30it/s]
 45%|████▍     | 166455/371472 [2:17:33<17:15:50,  3.30it/s]
 45%|████▍     | 166456/371472 [2:17:33<17:17:42,  3.29it/s]
 45%|████▍     | 166457/371472 [2:17:33<17:43:35,  3.21it/s]
 45%|████▍     | 166458/371472 [2:17:33<17:45:17,  3.21it/s]
 45%|████▍     | 166459/371472 [2:17:34<17:06:53,  3.33it/s]
 45%|████▍     | 166460/371472 [2:17:34<16:35:11,  3.43it/s]
                                                            
{'loss': 2.8922, 'learning_rate': 5.969693378439526e-07, 'epoch': 7.17}
+
 45%|████▍     | 166460/371472 [2:17:34<16:35:11,  3.43it/s]
 45%|████▍     | 166461/371472 [2:17:34<17:18:33,  3.29it/s]
 45%|████▍     | 166462/371472 [2:17:35<16:52:46,  3.37it/s]
 45%|████▍     | 166463/371472 [2:17:35<16:42:44,  3.41it/s]
 45%|████▍     | 166464/371472 [2:17:35<16:55:01,  3.37it/s]
 45%|████▍     | 166465/371472 [2:17:36<16:55:41,  3.36it/s]
 45%|████▍     | 166466/371472 [2:17:36<16:57:50,  3.36it/s]
 45%|████▍     | 166467/371472 [2:17:36<16:50:25,  3.38it/s]
 45%|████▍     | 166468/371472 [2:17:36<16:49:23,  3.38it/s]
 45%|████▍     | 166469/371472 [2:17:37<16:40:05,  3.42it/s]
 45%|████▍     | 166470/371472 [2:17:37<17:47:48,  3.20it/s]
 45%|████▍     | 166471/371472 [2:17:37<18:02:33,  3.16it/s]
 45%|████▍     | 166472/371472 [2:17:38<17:19:41,  3.29it/s]
 45%|████▍     | 166473/371472 [2:17:38<17:17:17,  3.29it/s]
 45%|████▍     | 166474/371472 [2:17:38<16:53:56,  3.37it/s]
 45%|████▍     | 166475/371472 [2:17:39<16:50:14,  3.38it/s]
 45%|████▍     | 166476/371472 [2:17:39<17:56:02,  3.18it/s]
 45%|████▍     | 166477/371472 [2:17:39<17:26:06,  3.27it/s]
 45%|████▍     | 166478/371472 [2:17:39<16:58:04,  3.36it/s]
 45%|████▍     | 166479/371472 [2:17:40<17:44:10,  3.21it/s]
 45%|████▍     | 166480/371472 [2:17:40<17:18:06,  3.29it/s]
                                                            
{'loss': 2.9063, 'learning_rate': 5.969208558684737e-07, 'epoch': 7.17}
+
 45%|████▍     | 166480/371472 [2:17:40<17:18:06,  3.29it/s]
 45%|████▍     | 166481/371472 [2:17:40<16:56:30,  3.36it/s]
 45%|████▍     | 166482/371472 [2:17:41<16:52:40,  3.37it/s]
 45%|████▍     | 166483/371472 [2:17:41<17:10:55,  3.31it/s]
 45%|████▍     | 166484/371472 [2:17:41<17:09:08,  3.32it/s]
 45%|████▍     | 166485/371472 [2:17:42<16:44:00,  3.40it/s]
 45%|████▍     | 166486/371472 [2:17:42<17:17:14,  3.29it/s]
 45%|████▍     | 166487/371472 [2:17:42<17:59:08,  3.17it/s]
 45%|████▍     | 166488/371472 [2:17:43<17:34:26,  3.24it/s]
 45%|████▍     | 166489/371472 [2:17:43<17:15:34,  3.30it/s]
 45%|████▍     | 166490/371472 [2:17:43<18:12:23,  3.13it/s]
 45%|████▍     | 166491/371472 [2:17:43<17:33:07,  3.24it/s]
 45%|████▍     | 166492/371472 [2:17:44<17:10:33,  3.32it/s]
 45%|████▍     | 166493/371472 [2:17:44<16:52:07,  3.38it/s]
 45%|████▍     | 166494/371472 [2:17:44<16:45:14,  3.40it/s]
 45%|████▍     | 166495/371472 [2:17:45<16:33:29,  3.44it/s]
 45%|████▍     | 166496/371472 [2:17:45<16:09:46,  3.52it/s]
 45%|████▍     | 166497/371472 [2:17:45<16:14:38,  3.51it/s]
 45%|████▍     | 166498/371472 [2:17:45<16:21:25,  3.48it/s]
 45%|████▍     | 166499/371472 [2:17:46<16:28:49,  3.45it/s]
 45%|████▍     | 166500/371472 [2:17:46<16:20:28,  3.48it/s]
                                                            
{'loss': 2.9269, 'learning_rate': 5.968723738929949e-07, 'epoch': 7.17}
+
 45%|████▍     | 166500/371472 [2:17:46<16:20:28,  3.48it/s]
 45%|████▍     | 166501/371472 [2:17:46<16:14:24,  3.51it/s]
 45%|████▍     | 166502/371472 [2:17:47<16:55:16,  3.36it/s]
 45%|████▍     | 166503/371472 [2:17:47<16:37:53,  3.42it/s]
 45%|████▍     | 166504/371472 [2:17:47<16:38:41,  3.42it/s]
 45%|████▍     | 166505/371472 [2:17:48<18:03:29,  3.15it/s]
 45%|████▍     | 166506/371472 [2:17:48<17:26:51,  3.26it/s]
 45%|████▍     | 166507/371472 [2:17:48<16:54:30,  3.37it/s]
 45%|████▍     | 166508/371472 [2:17:48<18:01:16,  3.16it/s]
 45%|████▍     | 166509/371472 [2:17:49<19:08:34,  2.97it/s]
 45%|████▍     | 166510/371472 [2:17:49<17:59:49,  3.16it/s]
 45%|████▍     | 166511/371472 [2:17:49<17:36:51,  3.23it/s]
 45%|████▍     | 166512/371472 [2:17:50<18:11:36,  3.13it/s]
 45%|████▍     | 166513/371472 [2:17:50<17:26:00,  3.27it/s]
 45%|████▍     | 166514/371472 [2:17:50<17:16:58,  3.29it/s]
 45%|████▍     | 166515/371472 [2:17:51<17:12:26,  3.31it/s]
 45%|████▍     | 166516/371472 [2:17:51<17:35:03,  3.24it/s]
 45%|████▍     | 166517/371472 [2:17:51<17:05:10,  3.33it/s]
 45%|████▍     | 166518/371472 [2:17:52<16:40:49,  3.41it/s]
 45%|████▍     | 166519/371472 [2:17:52<17:21:23,  3.28it/s]
 45%|████▍     | 166520/371472 [2:17:52<17:12:46,  3.31it/s]
                                                            
{'loss': 2.7926, 'learning_rate': 5.96823891917516e-07, 'epoch': 7.17}
+
 45%|████▍     | 166520/371472 [2:17:52<17:12:46,  3.31it/s]
 45%|████▍     | 166521/371472 [2:17:52<16:52:22,  3.37it/s]
 45%|████▍     | 166522/371472 [2:17:53<17:20:13,  3.28it/s]
 45%|████▍     | 166523/371472 [2:17:53<17:40:57,  3.22it/s]
 45%|████▍     | 166524/371472 [2:17:53<16:58:09,  3.35it/s]
 45%|████▍     | 166525/371472 [2:17:54<16:56:21,  3.36it/s]
 45%|████▍     | 166526/371472 [2:17:54<17:13:10,  3.31it/s]
 45%|████▍     | 166527/371472 [2:17:54<18:12:00,  3.13it/s]
 45%|████▍     | 166528/371472 [2:17:55<17:32:15,  3.25it/s]
 45%|████▍     | 166529/371472 [2:17:55<16:48:49,  3.39it/s]
 45%|████▍     | 166530/371472 [2:17:55<17:34:18,  3.24it/s]
 45%|████▍     | 166531/371472 [2:17:56<17:32:19,  3.25it/s]
 45%|████▍     | 166532/371472 [2:17:56<17:17:04,  3.29it/s]
 45%|████▍     | 166533/371472 [2:17:56<16:56:12,  3.36it/s]
 45%|████▍     | 166534/371472 [2:17:56<17:05:13,  3.33it/s]
 45%|████▍     | 166535/371472 [2:17:57<17:20:58,  3.28it/s]
 45%|████▍     | 166536/371472 [2:17:57<17:10:13,  3.32it/s]
 45%|████▍     | 166537/371472 [2:17:57<17:00:17,  3.35it/s]
 45%|████▍     | 166538/371472 [2:17:58<17:32:40,  3.24it/s]
 45%|████▍     | 166539/371472 [2:17:58<17:15:33,  3.30it/s]
 45%|████▍     | 166540/371472 [2:17:58<17:57:40,  3.17it/s]
                                                            
{'loss': 2.9786, 'learning_rate': 5.967754099420371e-07, 'epoch': 7.17}
+
 45%|████▍     | 166540/371472 [2:17:58<17:57:40,  3.17it/s]
 45%|████▍     | 166541/371472 [2:17:59<17:29:02,  3.26it/s]
 45%|████▍     | 166542/371472 [2:17:59<17:38:57,  3.23it/s]
 45%|████▍     | 166543/371472 [2:17:59<17:52:46,  3.18it/s]
 45%|████▍     | 166544/371472 [2:18:00<18:10:28,  3.13it/s]
 45%|████▍     | 166545/371472 [2:18:00<17:50:10,  3.19it/s]
 45%|████▍     | 166546/371472 [2:18:00<17:56:47,  3.17it/s]
 45%|████▍     | 166547/371472 [2:18:00<17:27:43,  3.26it/s]
 45%|████▍     | 166548/371472 [2:18:01<17:23:32,  3.27it/s]
 45%|████▍     | 166549/371472 [2:18:01<17:11:08,  3.31it/s]
 45%|████▍     | 166550/371472 [2:18:01<18:07:57,  3.14it/s]
 45%|████▍     | 166551/371472 [2:18:02<18:07:48,  3.14it/s]
 45%|████▍     | 166552/371472 [2:18:02<18:36:30,  3.06it/s]
 45%|████▍     | 166553/371472 [2:18:02<18:13:24,  3.12it/s]
 45%|████▍     | 166554/371472 [2:18:03<17:59:16,  3.16it/s]
 45%|████▍     | 166555/371472 [2:18:03<18:21:00,  3.10it/s]
 45%|████▍     | 166556/371472 [2:18:03<17:37:09,  3.23it/s]
 45%|████▍     | 166557/371472 [2:18:04<17:32:33,  3.24it/s]
 45%|████▍     | 166558/371472 [2:18:04<17:07:18,  3.32it/s]
 45%|████▍     | 166559/371472 [2:18:04<19:14:39,  2.96it/s]
 45%|████▍     | 166560/371472 [2:18:05<18:29:30,  3.08it/s]
                                                            
{'loss': 2.8454, 'learning_rate': 5.967269279665581e-07, 'epoch': 7.17}
+
 45%|████▍     | 166560/371472 [2:18:05<18:29:30,  3.08it/s]
 45%|████▍     | 166561/371472 [2:18:05<18:00:17,  3.16it/s]
 45%|████▍     | 166562/371472 [2:18:05<17:53:18,  3.18it/s]
 45%|████▍     | 166563/371472 [2:18:06<18:01:01,  3.16it/s]
 45%|████▍     | 166564/371472 [2:18:06<17:50:47,  3.19it/s]
 45%|████▍     | 166565/371472 [2:18:06<18:11:33,  3.13it/s]
 45%|████▍     | 166566/371472 [2:18:06<17:33:01,  3.24it/s]
 45%|████▍     | 166567/371472 [2:18:07<17:16:20,  3.30it/s]
 45%|████▍     | 166568/371472 [2:18:07<16:54:38,  3.37it/s]
 45%|████▍     | 166569/371472 [2:18:07<17:03:46,  3.34it/s]
 45%|████▍     | 166570/371472 [2:18:08<17:20:04,  3.28it/s]
 45%|████▍     | 166571/371472 [2:18:08<17:38:44,  3.23it/s]
 45%|████▍     | 166572/371472 [2:18:08<17:24:56,  3.27it/s]
 45%|████▍     | 166573/371472 [2:18:09<17:06:58,  3.33it/s]
 45%|████▍     | 166574/371472 [2:18:09<17:35:40,  3.23it/s]
 45%|████▍     | 166575/371472 [2:18:09<17:06:46,  3.33it/s]
 45%|████▍     | 166576/371472 [2:18:09<17:06:30,  3.33it/s]
 45%|████▍     | 166577/371472 [2:18:10<16:43:02,  3.40it/s]
 45%|████▍     | 166578/371472 [2:18:10<16:56:16,  3.36it/s]
 45%|████▍     | 166579/371472 [2:18:10<17:10:14,  3.31it/s]
 45%|████▍     | 166580/371472 [2:18:11<18:10:55,  3.13it/s]
                                                            
{'loss': 2.7862, 'learning_rate': 5.966784459910793e-07, 'epoch': 7.17}
+
 45%|████▍     | 166580/371472 [2:18:11<18:10:55,  3.13it/s]
 45%|████▍     | 166581/371472 [2:18:11<18:01:48,  3.16it/s]
 45%|████▍     | 166582/371472 [2:18:11<17:05:54,  3.33it/s]
 45%|████▍     | 166583/371472 [2:18:12<16:49:16,  3.38it/s]
 45%|████▍     | 166584/371472 [2:18:12<16:40:58,  3.41it/s]
 45%|████▍     | 166585/371472 [2:18:12<17:25:34,  3.27it/s]
 45%|████▍     | 166586/371472 [2:18:12<16:57:10,  3.36it/s]
 45%|████▍     | 166587/371472 [2:18:13<17:19:05,  3.29it/s]
 45%|████▍     | 166588/371472 [2:18:13<20:52:14,  2.73it/s]
 45%|████▍     | 166589/371472 [2:18:14<19:31:33,  2.91it/s]
 45%|████▍     | 166590/371472 [2:18:14<18:25:25,  3.09it/s]
 45%|████▍     | 166591/371472 [2:18:14<17:49:17,  3.19it/s]
 45%|████▍     | 166592/371472 [2:18:14<17:57:15,  3.17it/s]
 45%|████▍     | 166593/371472 [2:18:15<18:23:23,  3.09it/s]
 45%|████▍     | 166594/371472 [2:18:15<20:16:01,  2.81it/s]
 45%|████▍     | 166595/371472 [2:18:16<19:06:28,  2.98it/s]
 45%|████▍     | 166596/371472 [2:18:16<18:24:19,  3.09it/s]
 45%|████▍     | 166597/371472 [2:18:16<19:38:03,  2.90it/s]
 45%|████▍     | 166598/371472 [2:18:17<18:51:16,  3.02it/s]
 45%|████▍     | 166599/371472 [2:18:17<18:49:59,  3.02it/s]
 45%|████▍     | 166600/371472 [2:18:17<18:04:22,  3.15it/s]
                                                            
{'loss': 3.1183, 'learning_rate': 5.966299640156004e-07, 'epoch': 7.18}
+
 45%|████▍     | 166600/371472 [2:18:17<18:04:22,  3.15it/s]
 45%|████▍     | 166601/371472 [2:18:17<18:05:02,  3.15it/s]
 45%|████▍     | 166602/371472 [2:18:18<17:56:30,  3.17it/s]
 45%|████▍     | 166603/371472 [2:18:18<17:34:11,  3.24it/s]
 45%|████▍     | 166604/371472 [2:18:18<17:19:44,  3.28it/s]
 45%|████▍     | 166605/371472 [2:18:19<16:52:44,  3.37it/s]
 45%|████▍     | 166606/371472 [2:18:19<17:50:51,  3.19it/s]
 45%|████▍     | 166607/371472 [2:18:19<17:21:24,  3.28it/s]
 45%|████▍     | 166608/371472 [2:18:20<17:21:38,  3.28it/s]
 45%|████▍     | 166609/371472 [2:18:20<17:07:55,  3.32it/s]
 45%|████▍     | 166610/371472 [2:18:20<17:00:01,  3.35it/s]
 45%|████▍     | 166611/371472 [2:18:21<19:01:42,  2.99it/s]
 45%|████▍     | 166612/371472 [2:18:21<18:28:57,  3.08it/s]
 45%|████▍     | 166613/371472 [2:18:21<17:49:22,  3.19it/s]
 45%|████▍     | 166614/371472 [2:18:22<18:15:59,  3.12it/s]
 45%|████▍     | 166615/371472 [2:18:22<17:49:03,  3.19it/s]
 45%|████▍     | 166616/371472 [2:18:22<17:32:23,  3.24it/s]
 45%|████▍     | 166617/371472 [2:18:22<17:11:21,  3.31it/s]
 45%|████▍     | 166618/371472 [2:18:23<16:41:01,  3.41it/s]
 45%|████▍     | 166619/371472 [2:18:23<17:00:55,  3.34it/s]
 45%|████▍     | 166620/371472 [2:18:23<17:57:10,  3.17it/s]
                                                            
{'loss': 2.8224, 'learning_rate': 5.965814820401215e-07, 'epoch': 7.18}
+
 45%|████▍     | 166620/371472 [2:18:23<17:57:10,  3.17it/s]
 45%|████▍     | 166621/371472 [2:18:24<19:08:48,  2.97it/s]
 45%|████▍     | 166622/371472 [2:18:24<18:22:03,  3.10it/s]
 45%|████▍     | 166623/371472 [2:18:24<17:21:41,  3.28it/s]
 45%|████▍     | 166624/371472 [2:18:25<16:56:38,  3.36it/s]
 45%|████▍     | 166625/371472 [2:18:25<16:46:46,  3.39it/s]
 45%|████▍     | 166626/371472 [2:18:25<17:31:34,  3.25it/s]
 45%|████▍     | 166627/371472 [2:18:26<17:51:49,  3.19it/s]
 45%|████▍     | 166628/371472 [2:18:26<17:25:25,  3.27it/s]
 45%|████▍     | 166629/371472 [2:18:26<17:25:39,  3.26it/s]
 45%|████▍     | 166630/371472 [2:18:26<17:06:50,  3.32it/s]
 45%|████▍     | 166631/371472 [2:18:27<16:48:54,  3.38it/s]
 45%|████▍     | 166632/371472 [2:18:27<16:41:47,  3.41it/s]
 45%|████▍     | 166633/371472 [2:18:27<16:40:57,  3.41it/s]
 45%|████▍     | 166634/371472 [2:18:28<17:02:23,  3.34it/s]
 45%|████▍     | 166635/371472 [2:18:28<17:12:13,  3.31it/s]
 45%|████▍     | 166636/371472 [2:18:28<17:06:00,  3.33it/s]
 45%|████▍     | 166637/371472 [2:18:28<17:14:08,  3.30it/s]
 45%|████▍     | 166638/371472 [2:18:29<16:52:33,  3.37it/s]
 45%|████▍     | 166639/371472 [2:18:29<16:51:52,  3.37it/s]
 45%|████▍     | 166640/371472 [2:18:29<16:30:12,  3.45it/s]
                                                            
{'loss': 2.9662, 'learning_rate': 5.965330000646426e-07, 'epoch': 7.18}
+
 45%|████▍     | 166640/371472 [2:18:29<16:30:12,  3.45it/s]
 45%|████▍     | 166641/371472 [2:18:30<16:30:57,  3.44it/s]
 45%|████▍     | 166642/371472 [2:18:30<16:39:34,  3.42it/s]
 45%|████▍     | 166643/371472 [2:18:30<17:16:14,  3.29it/s]
 45%|████▍     | 166644/371472 [2:18:31<16:49:01,  3.38it/s]
 45%|████▍     | 166645/371472 [2:18:31<16:53:52,  3.37it/s]
 45%|████▍     | 166646/371472 [2:18:31<16:47:57,  3.39it/s]
 45%|████▍     | 166647/371472 [2:18:31<16:35:02,  3.43it/s]
 45%|████▍     | 166648/371472 [2:18:32<17:35:32,  3.23it/s]
 45%|████▍     | 166649/371472 [2:18:32<17:16:52,  3.29it/s]
 45%|████▍     | 166650/371472 [2:18:32<17:07:05,  3.32it/s]
 45%|████▍     | 166651/371472 [2:18:33<16:39:39,  3.41it/s]
 45%|████▍     | 166652/371472 [2:18:33<16:41:40,  3.41it/s]
 45%|████▍     | 166653/371472 [2:18:33<16:47:27,  3.39it/s]
 45%|████▍     | 166654/371472 [2:18:34<18:06:03,  3.14it/s]
 45%|████▍     | 166655/371472 [2:18:34<17:34:02,  3.24it/s]
 45%|████▍     | 166656/371472 [2:18:34<17:23:25,  3.27it/s]
 45%|████▍     | 166657/371472 [2:18:34<16:48:26,  3.38it/s]
 45%|████▍     | 166658/371472 [2:18:35<17:20:35,  3.28it/s]
 45%|████▍     | 166659/371472 [2:18:35<21:01:57,  2.70it/s]
 45%|████▍     | 166660/371472 [2:18:36<19:23:39,  2.93it/s]
                                                            
{'loss': 2.7401, 'learning_rate': 5.964845180891638e-07, 'epoch': 7.18}
+
 45%|████▍     | 166660/371472 [2:18:36<19:23:39,  2.93it/s]
 45%|████▍     | 166661/371472 [2:18:36<18:37:46,  3.05it/s]
 45%|████▍     | 166662/371472 [2:18:36<18:01:32,  3.16it/s]
 45%|████▍     | 166663/371472 [2:18:36<17:38:47,  3.22it/s]
 45%|████▍     | 166664/371472 [2:18:37<17:45:10,  3.20it/s]
 45%|████▍     | 166665/371472 [2:18:37<17:28:21,  3.26it/s]
 45%|████▍     | 166666/371472 [2:18:37<18:01:00,  3.16it/s]
 45%|████▍     | 166667/371472 [2:18:38<17:31:26,  3.25it/s]
 45%|████▍     | 166668/371472 [2:18:38<17:48:49,  3.19it/s]
 45%|████▍     | 166669/371472 [2:18:38<17:19:25,  3.28it/s]
 45%|████▍     | 166670/371472 [2:18:39<18:04:35,  3.15it/s]
 45%|████▍     | 166671/371472 [2:18:39<17:30:05,  3.25it/s]
 45%|████▍     | 166672/371472 [2:18:39<16:56:07,  3.36it/s]
 45%|████▍     | 166673/371472 [2:18:40<17:02:44,  3.34it/s]
 45%|████▍     | 166674/371472 [2:18:40<16:44:34,  3.40it/s]
 45%|████▍     | 166675/371472 [2:18:40<16:20:33,  3.48it/s]
 45%|████▍     | 166676/371472 [2:18:40<16:57:07,  3.36it/s]
 45%|████▍     | 166677/371472 [2:18:41<16:48:12,  3.39it/s]
 45%|████▍     | 166678/371472 [2:18:41<17:26:07,  3.26it/s]
 45%|████▍     | 166679/371472 [2:18:41<16:58:56,  3.35it/s]
 45%|████▍     | 166680/371472 [2:18:42<16:41:08,  3.41it/s]
                                                            
{'loss': 2.9522, 'learning_rate': 5.964360361136848e-07, 'epoch': 7.18}
+
 45%|████▍     | 166680/371472 [2:18:42<16:41:08,  3.41it/s]
 45%|████▍     | 166681/371472 [2:18:42<17:12:25,  3.31it/s]
 45%|████▍     | 166682/371472 [2:18:42<16:57:46,  3.35it/s]
 45%|████▍     | 166683/371472 [2:18:42<16:49:05,  3.38it/s]
 45%|████▍     | 166684/371472 [2:18:43<16:56:28,  3.36it/s]
 45%|████▍     | 166685/371472 [2:18:43<17:02:44,  3.34it/s]
 45%|████▍     | 166686/371472 [2:18:43<17:10:22,  3.31it/s]
 45%|████▍     | 166687/371472 [2:18:44<16:52:53,  3.37it/s]
 45%|████▍     | 166688/371472 [2:18:44<16:54:31,  3.36it/s]
 45%|████▍     | 166689/371472 [2:18:44<17:31:23,  3.25it/s]
 45%|████▍     | 166690/371472 [2:18:45<17:44:52,  3.21it/s]
 45%|████▍     | 166691/371472 [2:18:45<17:01:42,  3.34it/s]
 45%|████▍     | 166692/371472 [2:18:45<16:49:52,  3.38it/s]
 45%|████▍     | 166693/371472 [2:18:45<16:51:18,  3.37it/s]
 45%|████▍     | 166694/371472 [2:18:46<16:42:00,  3.41it/s]
 45%|████▍     | 166695/371472 [2:18:46<16:27:15,  3.46it/s]
 45%|████▍     | 166696/371472 [2:18:46<16:53:36,  3.37it/s]
 45%|████▍     | 166697/371472 [2:18:47<16:50:43,  3.38it/s]
 45%|████▍     | 166698/371472 [2:18:47<17:16:21,  3.29it/s]
 45%|████▍     | 166699/371472 [2:18:47<17:56:25,  3.17it/s]
 45%|████▍     | 166700/371472 [2:18:48<17:57:33,  3.17it/s]
                                                            
{'loss': 3.0052, 'learning_rate': 5.963875541382059e-07, 'epoch': 7.18}
+
 45%|████▍     | 166700/371472 [2:18:48<17:57:33,  3.17it/s]
 45%|████▍     | 166701/371472 [2:18:48<17:45:08,  3.20it/s]
 45%|████▍     | 166702/371472 [2:18:48<17:13:10,  3.30it/s]
 45%|████▍     | 166703/371472 [2:18:48<16:39:33,  3.41it/s]
 45%|████▍     | 166704/371472 [2:18:49<16:35:13,  3.43it/s]
 45%|████▍     | 166705/371472 [2:18:49<17:38:17,  3.22it/s]
 45%|████▍     | 166706/371472 [2:18:49<17:16:58,  3.29it/s]
 45%|████▍     | 166707/371472 [2:18:50<16:44:55,  3.40it/s]
 45%|████▍     | 166708/371472 [2:18:50<16:28:11,  3.45it/s]
 45%|████▍     | 166709/371472 [2:18:50<16:26:28,  3.46it/s]
 45%|████▍     | 166710/371472 [2:18:51<16:38:16,  3.42it/s]
 45%|████▍     | 166711/371472 [2:18:51<16:21:43,  3.48it/s]
 45%|████▍     | 166712/371472 [2:18:51<17:11:28,  3.31it/s]
 45%|████▍     | 166713/371472 [2:18:51<17:03:17,  3.33it/s]
 45%|████▍     | 166714/371472 [2:18:52<17:25:54,  3.26it/s]
 45%|████▍     | 166715/371472 [2:18:52<16:59:24,  3.35it/s]
 45%|████▍     | 166716/371472 [2:18:52<18:03:34,  3.15it/s]
 45%|████▍     | 166717/371472 [2:18:53<17:33:44,  3.24it/s]
 45%|████▍     | 166718/371472 [2:18:53<17:01:25,  3.34it/s]
 45%|████▍     | 166719/371472 [2:18:53<16:57:23,  3.35it/s]
 45%|████▍     | 166720/371472 [2:18:54<16:46:29,  3.39it/s]
                                                            
{'loss': 2.8316, 'learning_rate': 5.96339072162727e-07, 'epoch': 7.18}
+
 45%|████▍     | 166720/371472 [2:18:54<16:46:29,  3.39it/s]
 45%|████▍     | 166721/371472 [2:18:54<16:14:31,  3.50it/s]
 45%|████▍     | 166722/371472 [2:18:54<16:38:14,  3.42it/s]
 45%|████▍     | 166723/371472 [2:18:54<16:39:58,  3.41it/s]
 45%|████▍     | 166724/371472 [2:18:55<16:17:52,  3.49it/s]
 45%|████▍     | 166725/371472 [2:18:55<15:58:00,  3.56it/s]
 45%|████▍     | 166726/371472 [2:18:55<16:23:16,  3.47it/s]
 45%|████▍     | 166727/371472 [2:18:56<17:10:54,  3.31it/s]
 45%|████▍     | 166728/371472 [2:18:56<16:43:57,  3.40it/s]
 45%|████▍     | 166729/371472 [2:18:56<16:45:47,  3.39it/s]
 45%|████▍     | 166730/371472 [2:18:57<17:00:31,  3.34it/s]
 45%|████▍     | 166731/371472 [2:18:57<16:57:08,  3.35it/s]
 45%|████▍     | 166732/371472 [2:18:57<17:00:01,  3.35it/s]
 45%|████▍     | 166733/371472 [2:18:57<17:05:13,  3.33it/s]
 45%|████▍     | 166734/371472 [2:18:58<16:59:46,  3.35it/s]
 45%|████▍     | 166735/371472 [2:18:58<17:44:34,  3.21it/s]
 45%|████▍     | 166736/371472 [2:18:58<17:01:48,  3.34it/s]
 45%|████▍     | 166737/371472 [2:18:59<17:37:20,  3.23it/s]
 45%|████▍     | 166738/371472 [2:18:59<18:27:34,  3.08it/s]
 45%|████▍     | 166739/371472 [2:18:59<17:34:39,  3.24it/s]
 45%|████▍     | 166740/371472 [2:19:00<17:52:01,  3.18it/s]
                                                            
{'loss': 2.9772, 'learning_rate': 5.962905901872481e-07, 'epoch': 7.18}
+
 45%|████▍     | 166740/371472 [2:19:00<17:52:01,  3.18it/s]
 45%|████▍     | 166741/371472 [2:19:00<17:40:47,  3.22it/s]
 45%|████▍     | 166742/371472 [2:19:00<18:24:04,  3.09it/s]
 45%|████▍     | 166743/371472 [2:19:01<18:25:35,  3.09it/s]
 45%|████▍     | 166744/371472 [2:19:01<18:00:57,  3.16it/s]
 45%|████▍     | 166745/371472 [2:19:01<17:55:49,  3.17it/s]
 45%|████▍     | 166746/371472 [2:19:02<17:42:28,  3.21it/s]
 45%|████▍     | 166747/371472 [2:19:02<16:49:15,  3.38it/s]
 45%|████▍     | 166748/371472 [2:19:02<16:55:20,  3.36it/s]
 45%|████▍     | 166749/371472 [2:19:02<16:25:27,  3.46it/s]
 45%|████▍     | 166750/371472 [2:19:03<15:54:44,  3.57it/s]
 45%|████▍     | 166751/371472 [2:19:03<16:23:38,  3.47it/s]
 45%|████▍     | 166752/371472 [2:19:03<16:49:06,  3.38it/s]
 45%|████▍     | 166753/371472 [2:19:04<16:44:38,  3.40it/s]
 45%|████▍     | 166754/371472 [2:19:04<16:41:56,  3.41it/s]
 45%|████▍     | 166755/371472 [2:19:04<16:33:07,  3.44it/s]
 45%|████▍     | 166756/371472 [2:19:04<16:18:30,  3.49it/s]
 45%|████▍     | 166757/371472 [2:19:05<16:35:16,  3.43it/s]
 45%|████▍     | 166758/371472 [2:19:05<16:26:20,  3.46it/s]
 45%|████▍     | 166759/371472 [2:19:05<17:29:53,  3.25it/s]
 45%|████▍     | 166760/371472 [2:19:06<16:52:40,  3.37it/s]
                                                            
{'loss': 3.0082, 'learning_rate': 5.962421082117693e-07, 'epoch': 7.18}
+
 45%|████▍     | 166760/371472 [2:19:06<16:52:40,  3.37it/s]
 45%|████▍     | 166761/371472 [2:19:06<16:48:47,  3.38it/s]
 45%|████▍     | 166762/371472 [2:19:06<16:44:33,  3.40it/s]
 45%|████▍     | 166763/371472 [2:19:06<16:27:47,  3.45it/s]
 45%|████▍     | 166764/371472 [2:19:07<16:31:15,  3.44it/s]
 45%|████▍     | 166765/371472 [2:19:07<16:21:53,  3.47it/s]
 45%|████▍     | 166766/371472 [2:19:07<16:33:29,  3.43it/s]
 45%|████▍     | 166767/371472 [2:19:08<17:05:24,  3.33it/s]
 45%|████▍     | 166768/371472 [2:19:08<16:51:05,  3.37it/s]
 45%|████▍     | 166769/371472 [2:19:08<16:31:17,  3.44it/s]
 45%|████▍     | 166770/371472 [2:19:08<16:33:23,  3.43it/s]
 45%|████▍     | 166771/371472 [2:19:09<17:13:43,  3.30it/s]
 45%|████▍     | 166772/371472 [2:19:09<17:13:19,  3.30it/s]
 45%|████▍     | 166773/371472 [2:19:09<17:56:37,  3.17it/s]
 45%|████▍     | 166774/371472 [2:19:10<17:42:52,  3.21it/s]
 45%|████▍     | 166775/371472 [2:19:10<17:27:53,  3.26it/s]
 45%|████▍     | 166776/371472 [2:19:10<17:20:21,  3.28it/s]
 45%|████▍     | 166777/371472 [2:19:11<16:56:03,  3.36it/s]
 45%|████▍     | 166778/371472 [2:19:11<16:41:15,  3.41it/s]
 45%|████▍     | 166779/371472 [2:19:11<16:29:13,  3.45it/s]
 45%|████▍     | 166780/371472 [2:19:11<16:22:53,  3.47it/s]
                                                            
{'loss': 2.9295, 'learning_rate': 5.961936262362904e-07, 'epoch': 7.18}
+
 45%|████▍     | 166780/371472 [2:19:11<16:22:53,  3.47it/s]
 45%|████▍     | 166781/371472 [2:19:12<17:00:36,  3.34it/s]
 45%|████▍     | 166782/371472 [2:19:12<17:35:04,  3.23it/s]
 45%|████▍     | 166783/371472 [2:19:12<17:12:49,  3.30it/s]
 45%|████▍     | 166784/371472 [2:19:13<17:28:37,  3.25it/s]
 45%|████▍     | 166785/371472 [2:19:13<17:03:05,  3.33it/s]
 45%|████▍     | 166786/371472 [2:19:13<17:12:39,  3.30it/s]
 45%|████▍     | 166787/371472 [2:19:14<16:41:25,  3.41it/s]
 45%|████▍     | 166788/371472 [2:19:14<16:21:53,  3.47it/s]
 45%|████▍     | 166789/371472 [2:19:14<16:46:23,  3.39it/s]
 45%|████▍     | 166790/371472 [2:19:15<17:00:48,  3.34it/s]
 45%|████▍     | 166791/371472 [2:19:15<16:47:56,  3.38it/s]
 45%|████▍     | 166792/371472 [2:19:15<16:58:42,  3.35it/s]
 45%|████▍     | 166793/371472 [2:19:15<17:15:59,  3.29it/s]
 45%|████▍     | 166794/371472 [2:19:16<16:56:28,  3.36it/s]
 45%|████▍     | 166795/371472 [2:19:16<16:35:41,  3.43it/s]
 45%|████▍     | 166796/371472 [2:19:16<16:32:44,  3.44it/s]
 45%|████▍     | 166797/371472 [2:19:17<19:17:38,  2.95it/s]
 45%|████▍     | 166798/371472 [2:19:17<18:27:14,  3.08it/s]
 45%|████▍     | 166799/371472 [2:19:17<18:05:01,  3.14it/s]
 45%|████▍     | 166800/371472 [2:19:18<18:00:14,  3.16it/s]
                                                            
{'loss': 2.9893, 'learning_rate': 5.961451442608115e-07, 'epoch': 7.18}
+
 45%|████▍     | 166800/371472 [2:19:18<18:00:14,  3.16it/s]
 45%|████▍     | 166801/371472 [2:19:18<17:12:16,  3.30it/s]
 45%|████▍     | 166802/371472 [2:19:18<18:10:43,  3.13it/s]
 45%|████▍     | 166803/371472 [2:19:19<17:35:48,  3.23it/s]
 45%|████▍     | 166804/371472 [2:19:19<17:15:45,  3.29it/s]
 45%|████▍     | 166805/371472 [2:19:19<16:41:22,  3.41it/s]
 45%|████▍     | 166806/371472 [2:19:19<16:49:44,  3.38it/s]
 45%|████▍     | 166807/371472 [2:19:20<16:49:48,  3.38it/s]
 45%|████▍     | 166808/371472 [2:19:20<16:42:03,  3.40it/s]
 45%|████▍     | 166809/371472 [2:19:20<16:28:01,  3.45it/s]
 45%|████▍     | 166810/371472 [2:19:21<16:05:10,  3.53it/s]
 45%|████▍     | 166811/371472 [2:19:21<16:04:21,  3.54it/s]
 45%|████▍     | 166812/371472 [2:19:21<17:10:15,  3.31it/s]
 45%|████▍     | 166813/371472 [2:19:21<17:14:05,  3.30it/s]
 45%|████▍     | 166814/371472 [2:19:22<16:45:44,  3.39it/s]
 45%|████▍     | 166815/371472 [2:19:22<16:27:41,  3.45it/s]
 45%|██���█▍     | 166816/371472 [2:19:22<16:38:27,  3.42it/s]
 45%|████▍     | 166817/371472 [2:19:23<16:34:31,  3.43it/s]
 45%|████▍     | 166818/371472 [2:19:23<16:16:58,  3.49it/s]
 45%|████▍     | 166819/371472 [2:19:23<16:15:31,  3.50it/s]
 45%|████▍     | 166820/371472 [2:19:23<16:27:32,  3.45it/s]
                                                            
{'loss': 2.9769, 'learning_rate': 5.960966622853325e-07, 'epoch': 7.19}
+
 45%|████▍     | 166820/371472 [2:19:23<16:27:32,  3.45it/s]
 45%|████▍     | 166821/371472 [2:19:24<16:24:41,  3.46it/s]
 45%|████▍     | 166822/371472 [2:19:24<16:17:05,  3.49it/s]
 45%|████▍     | 166823/371472 [2:19:24<16:04:25,  3.54it/s]
 45%|████▍     | 166824/371472 [2:19:25<16:05:38,  3.53it/s]
 45%|████▍     | 166825/371472 [2:19:25<16:18:01,  3.49it/s]
 45%|████▍     | 166826/371472 [2:19:25<17:07:23,  3.32it/s]
 45%|████▍     | 166827/371472 [2:19:26<17:08:41,  3.32it/s]
 45%|████▍     | 166828/371472 [2:19:26<16:33:42,  3.43it/s]
 45%|████▍     | 166829/371472 [2:19:26<16:38:33,  3.42it/s]
 45%|████▍     | 166830/371472 [2:19:26<16:29:51,  3.45it/s]
 45%|████▍     | 166831/371472 [2:19:27<16:46:44,  3.39it/s]
 45%|████▍     | 166832/371472 [2:19:27<16:56:28,  3.36it/s]
 45%|████▍     | 166833/371472 [2:19:27<17:01:59,  3.34it/s]
 45%|████▍     | 166834/371472 [2:19:28<17:00:55,  3.34it/s]
 45%|████▍     | 166835/371472 [2:19:28<16:39:35,  3.41it/s]
 45%|████▍     | 166836/371472 [2:19:28<16:17:07,  3.49it/s]
 45%|████▍     | 166837/371472 [2:19:28<17:08:36,  3.32it/s]
 45%|████▍     | 166838/371472 [2:19:29<16:58:02,  3.35it/s]
 45%|████▍     | 166839/371472 [2:19:29<17:00:24,  3.34it/s]
 45%|████▍     | 166840/371472 [2:19:29<17:03:04,  3.33it/s]
                                                            
{'loss': 2.9779, 'learning_rate': 5.960481803098537e-07, 'epoch': 7.19}
+
 45%|████▍     | 166840/371472 [2:19:29<17:03:04,  3.33it/s]
 45%|████▍     | 166841/371472 [2:19:30<16:37:09,  3.42it/s]
 45%|████▍     | 166842/371472 [2:19:30<17:19:54,  3.28it/s]
 45%|████▍     | 166843/371472 [2:19:30<18:16:10,  3.11it/s]
 45%|████▍     | 166844/371472 [2:19:31<17:43:26,  3.21it/s]
 45%|████▍     | 166845/371472 [2:19:31<17:08:42,  3.32it/s]
 45%|████▍     | 166846/371472 [2:19:31<16:40:23,  3.41it/s]
 45%|████▍     | 166847/371472 [2:19:31<16:47:17,  3.39it/s]
 45%|████▍     | 166848/371472 [2:19:32<18:10:22,  3.13it/s]
 45%|████▍     | 166849/371472 [2:19:32<17:58:04,  3.16it/s]
 45%|████▍     | 166850/371472 [2:19:32<17:08:46,  3.31it/s]
 45%|████▍     | 166851/371472 [2:19:33<16:59:29,  3.35it/s]
 45%|████▍     | 166852/371472 [2:19:33<16:57:17,  3.35it/s]
 45%|████▍     | 166853/371472 [2:19:33<18:28:12,  3.08it/s]
 45%|████▍     | 166854/371472 [2:19:34<18:19:31,  3.10it/s]
 45%|████▍     | 166855/371472 [2:19:34<17:54:36,  3.17it/s]
 45%|████▍     | 166856/371472 [2:19:34<17:13:23,  3.30it/s]
 45%|████▍     | 166857/371472 [2:19:35<18:43:19,  3.04it/s]
 45%|████▍     | 166858/371472 [2:19:35<18:35:37,  3.06it/s]
 45%|████▍     | 166859/371472 [2:19:35<18:25:50,  3.08it/s]
 45%|████▍     | 166860/371472 [2:19:36<17:49:56,  3.19it/s]
                                                            
{'loss': 3.0604, 'learning_rate': 5.959996983343748e-07, 'epoch': 7.19}
+
 45%|████▍     | 166860/371472 [2:19:36<17:49:56,  3.19it/s]
 45%|████▍     | 166861/371472 [2:19:36<18:36:46,  3.05it/s]
 45%|████▍     | 166862/371472 [2:19:36<19:02:00,  2.99it/s]
 45%|████▍     | 166863/371472 [2:19:37<18:19:15,  3.10it/s]
 45%|████▍     | 166864/371472 [2:19:37<19:02:31,  2.98it/s]
 45%|████▍     | 166865/371472 [2:19:37<19:08:47,  2.97it/s]
 45%|████▍     | 166866/371472 [2:19:38<18:37:12,  3.05it/s]
 45%|████▍     | 166867/371472 [2:19:38<18:55:50,  3.00it/s]
 45%|████▍     | 166868/371472 [2:19:38<18:58:15,  3.00it/s]
 45%|████▍     | 166869/371472 [2:19:39<19:01:04,  2.99it/s]
 45%|████▍     | 166870/371472 [2:19:39<18:15:30,  3.11it/s]
 45%|████▍     | 166871/371472 [2:19:39<17:38:20,  3.22it/s]
 45%|████▍     | 166872/371472 [2:19:40<17:08:48,  3.31it/s]
 45%|████▍     | 166873/371472 [2:19:40<16:48:02,  3.38it/s]
 45%|████▍     | 166874/371472 [2:19:40<17:09:40,  3.31it/s]
 45%|████▍     | 166875/371472 [2:19:40<16:33:50,  3.43it/s]
 45%|████▍     | 166876/371472 [2:19:41<17:04:51,  3.33it/s]
 45%|████▍     | 166877/371472 [2:19:41<16:44:26,  3.39it/s]
 45%|████▍     | 166878/371472 [2:19:41<16:39:00,  3.41it/s]
 45%|████▍     | 166879/371472 [2:19:42<18:15:22,  3.11it/s]
 45%|████▍     | 166880/371472 [2:19:42<17:18:54,  3.28it/s]
                                                            
{'loss': 2.8288, 'learning_rate': 5.959512163588959e-07, 'epoch': 7.19}
+
 45%|████▍     | 166880/371472 [2:19:42<17:18:54,  3.28it/s]
 45%|████▍     | 166881/371472 [2:19:42<17:50:31,  3.19it/s]
 45%|████▍     | 166882/371472 [2:19:43<17:21:06,  3.28it/s]
 45%|████▍     | 166883/371472 [2:19:43<17:06:36,  3.32it/s]
 45%|████▍     | 166884/371472 [2:19:43<17:10:52,  3.31it/s]
 45%|████▍     | 166885/371472 [2:19:43<17:08:21,  3.32it/s]
 45%|████▍     | 166886/371472 [2:19:44<17:11:17,  3.31it/s]
 45%|████▍     | 166887/371472 [2:19:44<16:59:35,  3.34it/s]
 45%|████▍     | 166888/371472 [2:19:44<17:07:17,  3.32it/s]
 45%|████▍     | 166889/371472 [2:19:45<17:58:02,  3.16it/s]
 45%|████▍     | 166890/371472 [2:19:45<17:44:33,  3.20it/s]
 45%|████▍     | 166891/371472 [2:19:45<17:12:40,  3.30it/s]
 45%|████▍     | 166892/371472 [2:19:46<16:56:24,  3.35it/s]
 45%|████▍     | 166893/371472 [2:19:46<16:25:17,  3.46it/s]
 45%|████▍     | 166894/371472 [2:19:46<15:53:38,  3.58it/s]
 45%|████▍     | 166895/371472 [2:19:46<15:57:13,  3.56it/s]
 45%|████▍     | 166896/371472 [2:19:47<16:53:57,  3.36it/s]
 45%|████▍     | 166897/371472 [2:19:47<16:53:39,  3.36it/s]
 45%|████▍     | 166898/371472 [2:19:47<16:44:03,  3.40it/s]
 45%|████▍     | 166899/371472 [2:19:48<17:24:33,  3.26it/s]
 45%|████▍     | 166900/371472 [2:19:48<17:04:41,  3.33it/s]
                                                            
{'loss': 2.9687, 'learning_rate': 5.95902734383417e-07, 'epoch': 7.19}
+
 45%|████▍     | 166900/371472 [2:19:48<17:04:41,  3.33it/s]
 45%|████▍     | 166901/371472 [2:19:48<16:35:27,  3.43it/s]
 45%|████▍     | 166902/371472 [2:19:48<16:25:51,  3.46it/s]
 45%|████▍     | 166903/371472 [2:19:49<17:32:30,  3.24it/s]
 45%|████▍     | 166904/371472 [2:19:49<17:10:20,  3.31it/s]
 45%|████▍     | 166905/371472 [2:19:49<17:38:45,  3.22it/s]
 45%|████▍     | 166906/371472 [2:19:50<17:34:18,  3.23it/s]
 45%|████▍     | 166907/371472 [2:19:50<17:25:27,  3.26it/s]
 45%|████▍     | 166908/371472 [2:19:50<17:15:10,  3.29it/s]
 45%|████▍     | 166909/371472 [2:19:51<16:43:25,  3.40it/s]
 45%|████▍     | 166910/371472 [2:19:51<17:02:26,  3.33it/s]
 45%|████▍     | 166911/371472 [2:19:51<17:14:21,  3.30it/s]
 45%|████▍     | 166912/371472 [2:19:52<17:03:54,  3.33it/s]
 45%|████▍     | 166913/371472 [2:19:52<17:01:30,  3.34it/s]
 45%|████▍     | 166914/371472 [2:19:52<16:35:38,  3.42it/s]
 45%|████▍     | 166915/371472 [2:19:52<16:48:25,  3.38it/s]
 45%|████▍     | 166916/371472 [2:19:53<17:02:42,  3.33it/s]
 45%|████▍     | 166917/371472 [2:19:53<16:50:08,  3.38it/s]
 45%|████▍     | 166918/371472 [2:19:53<17:10:27,  3.31it/s]
 45%|████▍     | 166919/371472 [2:19:54<18:43:26,  3.03it/s]
 45%|████▍     | 166920/371472 [2:19:54<19:25:05,  2.93it/s]
                                                            
{'loss': 3.0262, 'learning_rate': 5.958542524079382e-07, 'epoch': 7.19}
+
 45%|████▍     | 166920/371472 [2:19:54<19:25:05,  2.93it/s]
 45%|████▍     | 166921/371472 [2:19:54<19:43:30,  2.88it/s]
 45%|████▍     | 166922/371472 [2:19:55<19:41:54,  2.88it/s]
 45%|████▍     | 166923/371472 [2:19:55<19:04:30,  2.98it/s]
 45%|████▍     | 166924/371472 [2:19:55<19:10:48,  2.96it/s]
 45%|████▍     | 166925/371472 [2:19:56<19:32:39,  2.91it/s]
 45%|████▍     | 166926/371472 [2:19:56<19:08:36,  2.97it/s]
 45%|████▍     | 166927/371472 [2:19:56<18:36:54,  3.05it/s]
 45%|████▍     | 166928/371472 [2:19:57<17:46:28,  3.20it/s]
 45%|████▍     | 166929/371472 [2:19:57<17:47:58,  3.19it/s]
 45%|████▍     | 166930/371472 [2:19:57<17:56:10,  3.17it/s]
 45%|████▍     | 166931/371472 [2:19:58<17:54:49,  3.17it/s]
 45%|████▍     | 166932/371472 [2:19:58<17:55:21,  3.17it/s]
 45%|████▍     | 166933/371472 [2:19:58<17:38:33,  3.22it/s]
 45%|████▍     | 166934/371472 [2:19:59<17:23:59,  3.27it/s]
 45%|████▍     | 166935/371472 [2:19:59<17:13:50,  3.30it/s]
 45%|████▍     | 166936/371472 [2:19:59<16:54:01,  3.36it/s]
 45%|████▍     | 166937/371472 [2:19:59<16:41:38,  3.40it/s]
 45%|████▍     | 166938/371472 [2:20:00<16:57:08,  3.35it/s]
 45%|████▍     | 166939/371472 [2:20:00<18:36:36,  3.05it/s]
 45%|████▍     | 166940/371472 [2:20:00<17:48:10,  3.19it/s]
                                                            
{'loss': 2.9214, 'learning_rate': 5.958057704324591e-07, 'epoch': 7.19}
+
 45%|��███▍     | 166940/371472 [2:20:00<17:48:10,  3.19it/s]
 45%|████▍     | 166941/371472 [2:20:01<17:59:47,  3.16it/s]
 45%|████▍     | 166942/371472 [2:20:01<18:47:16,  3.02it/s]
 45%|████▍     | 166943/371472 [2:20:01<18:24:38,  3.09it/s]
 45%|████▍     | 166944/371472 [2:20:02<17:29:17,  3.25it/s]
 45%|████▍     | 166945/371472 [2:20:02<17:03:21,  3.33it/s]
 45%|████▍     | 166946/371472 [2:20:02<17:26:22,  3.26it/s]
 45%|████▍     | 166947/371472 [2:20:03<16:46:50,  3.39it/s]
 45%|████▍     | 166948/371472 [2:20:03<17:33:12,  3.24it/s]
 45%|████▍     | 166949/371472 [2:20:03<17:27:41,  3.25it/s]
 45%|████▍     | 166950/371472 [2:20:03<17:06:35,  3.32it/s]
 45%|████▍     | 166951/371472 [2:20:04<17:36:33,  3.23it/s]
 45%|████▍     | 166952/371472 [2:20:04<17:15:53,  3.29it/s]
 45%|████▍     | 166953/371472 [2:20:04<17:04:53,  3.33it/s]
 45%|████▍     | 166954/371472 [2:20:05<17:04:18,  3.33it/s]
 45%|████▍     | 166955/371472 [2:20:05<16:57:08,  3.35it/s]
 45%|████▍     | 166956/371472 [2:20:05<16:57:34,  3.35it/s]
 45%|████▍     | 166957/371472 [2:20:06<18:46:38,  3.03it/s]
 45%|████▍     | 166958/371472 [2:20:06<18:06:11,  3.14it/s]
 45%|████▍     | 166959/371472 [2:20:06<17:47:06,  3.19it/s]
 45%|████▍     | 166960/371472 [2:20:07<18:04:05,  3.14it/s]
                                                            
{'loss': 2.9494, 'learning_rate': 5.957572884569802e-07, 'epoch': 7.19}
+
 45%|████▍     | 166960/371472 [2:20:07<18:04:05,  3.14it/s]
 45%|████▍     | 166961/371472 [2:20:07<17:26:13,  3.26it/s]
 45%|████▍     | 166962/371472 [2:20:07<16:52:37,  3.37it/s]
 45%|████▍     | 166963/371472 [2:20:07<16:53:54,  3.36it/s]
 45%|████▍     | 166964/371472 [2:20:08<16:55:49,  3.36it/s]
 45%|████▍     | 166965/371472 [2:20:08<16:50:03,  3.37it/s]
 45%|████▍     | 166966/371472 [2:20:08<17:54:16,  3.17it/s]
 45%|████▍     | 166967/371472 [2:20:09<17:26:23,  3.26it/s]
 45%|████▍     | 166968/371472 [2:20:09<17:07:15,  3.32it/s]
 45%|████▍     | 166969/371472 [2:20:09<16:45:17,  3.39it/s]
 45%|████▍     | 166970/371472 [2:20:10<16:27:24,  3.45it/s]
 45%|████▍     | 166971/371472 [2:20:10<16:04:19,  3.53it/s]
 45%|████▍     | 166972/371472 [2:20:10<15:52:50,  3.58it/s]
 45%|████▍     | 166973/371472 [2:20:10<16:09:06,  3.52it/s]
 45%|████▍     | 166974/371472 [2:20:11<16:49:21,  3.38it/s]
 45%|████▍     | 166975/371472 [2:20:11<17:45:22,  3.20it/s]
 45%|████▍     | 166976/371472 [2:20:11<17:00:38,  3.34it/s]
 45%|████▍     | 166977/371472 [2:20:12<17:17:32,  3.28it/s]
 45%|████▍     | 166978/371472 [2:20:12<17:34:05,  3.23it/s]
 45%|████▍     | 166979/371472 [2:20:12<18:24:13,  3.09it/s]
 45%|████▍     | 166980/371472 [2:20:13<17:40:53,  3.21it/s]
                                                            
{'loss': 2.7909, 'learning_rate': 5.957088064815014e-07, 'epoch': 7.19}
+
 45%|████▍     | 166980/371472 [2:20:13<17:40:53,  3.21it/s]
 45%|████▍     | 166981/371472 [2:20:13<17:23:27,  3.27it/s]
 45%|████▍     | 166982/371472 [2:20:13<17:14:52,  3.29it/s]
 45%|████▍     | 166983/371472 [2:20:13<16:59:58,  3.34it/s]
 45%|████▍     | 166984/371472 [2:20:14<17:37:42,  3.22it/s]
 45%|████▍     | 166985/371472 [2:20:14<17:54:45,  3.17it/s]
 45%|████▍     | 166986/371472 [2:20:14<17:28:13,  3.25it/s]
 45%|████▍     | 166987/371472 [2:20:15<16:41:35,  3.40it/s]
 45%|████▍     | 166988/371472 [2:20:15<17:18:26,  3.28it/s]
 45%|████▍     | 166989/371472 [2:20:15<17:13:24,  3.30it/s]
 45%|████▍     | 166990/371472 [2:20:16<16:40:09,  3.41it/s]
 45%|████▍     | 166991/371472 [2:20:16<16:24:32,  3.46it/s]
 45%|████▍     | 166992/371472 [2:20:16<16:28:06,  3.45it/s]
 45%|████▍     | 166993/371472 [2:20:17<18:21:05,  3.10it/s]
 45%|████▍     | 166994/371472 [2:20:17<17:23:08,  3.27it/s]
 45%|████▍     | 166995/371472 [2:20:17<17:16:11,  3.29it/s]
 45%|████▍     | 166996/371472 [2:20:17<16:43:32,  3.40it/s]
 45%|████▍     | 166997/371472 [2:20:18<16:13:56,  3.50it/s]
 45%|████▍     | 166998/371472 [2:20:18<16:33:33,  3.43it/s]
 45%|████▍     | 166999/371472 [2:20:18<16:21:17,  3.47it/s]
 45%|████▍     | 167000/371472 [2:20:19<16:44:51,  3.39it/s]
                                                            
{'loss': 2.9268, 'learning_rate': 5.956603245060225e-07, 'epoch': 7.19}
+
 45%|████▍     | 167000/371472 [2:20:19<16:44:51,  3.39it/s]
 45%|████▍     | 167001/371472 [2:20:19<16:42:30,  3.40it/s]
 45%|████▍     | 167002/371472 [2:20:19<16:44:37,  3.39it/s]
 45%|████▍     | 167003/371472 [2:20:19<17:19:05,  3.28it/s]
 45%|████▍     | 167004/371472 [2:20:20<17:11:32,  3.30it/s]
 45%|████▍     | 167005/371472 [2:20:20<17:11:19,  3.30it/s]
 45%|████▍     | 167006/371472 [2:20:20<17:36:57,  3.22it/s]
 45%|████▍     | 167007/371472 [2:20:21<17:37:37,  3.22it/s]
 45%|████▍     | 167008/371472 [2:20:21<18:11:44,  3.12it/s]
 45%|████▍     | 167009/371472 [2:20:21<17:32:20,  3.24it/s]
 45%|████▍     | 167010/371472 [2:20:22<17:24:58,  3.26it/s]
 45%|████▍     | 167011/371472 [2:20:22<19:47:00,  2.87it/s]
 45%|████▍     | 167012/371472 [2:20:22<18:42:37,  3.04it/s]
 45%|████▍     | 167013/371472 [2:20:23<17:51:51,  3.18it/s]
 45%|████▍     | 167014/371472 [2:20:23<17:08:30,  3.31it/s]
 45%|████▍     | 167015/371472 [2:20:23<18:15:40,  3.11it/s]
 45%|████▍     | 167016/371472 [2:20:24<17:27:26,  3.25it/s]
 45%|████▍     | 167017/371472 [2:20:24<18:04:50,  3.14it/s]
 45%|████▍     | 167018/371472 [2:20:24<18:43:26,  3.03it/s]
 45%|████▍     | 167019/371472 [2:20:25<18:29:31,  3.07it/s]
 45%|████▍     | 167020/371472 [2:20:25<18:44:09,  3.03it/s]
                                                            
{'loss': 2.8481, 'learning_rate': 5.956118425305436e-07, 'epoch': 7.19}
+
 45%|████▍     | 167020/371472 [2:20:25<18:44:09,  3.03it/s]
 45%|████▍     | 167021/371472 [2:20:25<18:06:30,  3.14it/s]
 45%|████▍     | 167022/371472 [2:20:26<18:59:04,  2.99it/s]
 45%|████▍     | 167023/371472 [2:20:26<18:43:02,  3.03it/s]
 45%|████▍     | 167024/371472 [2:20:26<18:21:42,  3.09it/s]
 45%|████▍     | 167025/371472 [2:20:27<18:09:04,  3.13it/s]
 45%|████▍     | 167026/371472 [2:20:27<18:34:21,  3.06it/s]
 45%|████▍     | 167027/371472 [2:20:27<17:49:33,  3.19it/s]
 45%|████▍     | 167028/371472 [2:20:27<18:00:45,  3.15it/s]
 45%|████▍     | 167029/371472 [2:20:28<17:54:24,  3.17it/s]
 45%|████▍     | 167030/371472 [2:20:28<18:04:29,  3.14it/s]
 45%|████▍     | 167031/371472 [2:20:28<17:38:49,  3.22it/s]
 45%|████▍     | 167032/371472 [2:20:29<17:01:52,  3.33it/s]
 45%|████▍     | 167033/371472 [2:20:29<16:56:01,  3.35it/s]
 45%|████▍     | 167034/371472 [2:20:29<16:50:55,  3.37it/s]
 45%|████▍     | 167035/371472 [2:20:30<17:33:07,  3.24it/s]
 45%|████▍     | 167036/371472 [2:20:30<17:18:10,  3.28it/s]
 45%|████▍     | 167037/371472 [2:20:30<18:51:42,  3.01it/s]
 45%|████▍     | 167038/371472 [2:20:31<17:52:46,  3.18it/s]
 45%|████▍     | 167039/371472 [2:20:31<18:09:26,  3.13it/s]
 45%|████▍     | 167040/371472 [2:20:31<17:31:57,  3.24it/s]
                                                            
{'loss': 3.02, 'learning_rate': 5.955633605550647e-07, 'epoch': 7.19}
+
 45%|████▍     | 167040/371472 [2:20:31<17:31:57,  3.24it/s]
 45%|████▍     | 167041/371472 [2:20:31<17:05:40,  3.32it/s]
 45%|████▍     | 167042/371472 [2:20:32<17:02:41,  3.33it/s]
 45%|████▍     | 167043/371472 [2:20:32<17:02:11,  3.33it/s]
 45%|████▍     | 167044/371472 [2:20:32<16:38:56,  3.41it/s]
 45%|████▍     | 167045/371472 [2:20:33<17:25:03,  3.26it/s]
 45%|████▍     | 167046/371472 [2:20:33<17:00:40,  3.34it/s]
 45%|████▍     | 167047/371472 [2:20:33<16:47:24,  3.38it/s]
 45%|████▍     | 167048/371472 [2:20:34<16:30:04,  3.44it/s]
 45%|████▍     | 167049/371472 [2:20:34<17:24:10,  3.26it/s]
 45%|████▍     | 167050/371472 [2:20:34<17:23:15,  3.27it/s]
 45%|████▍     | 167051/371472 [2:20:35<18:27:40,  3.08it/s]
 45%|████▍     | 167052/371472 [2:20:35<18:16:59,  3.11it/s]
 45%|████▍     | 167053/371472 [2:20:35<18:51:03,  3.01it/s]
 45%|████▍     | 167054/371472 [2:20:36<18:34:14,  3.06it/s]
 45%|████▍     | 167055/371472 [2:20:36<18:17:52,  3.10it/s]
 45%|████▍     | 167056/371472 [2:20:36<19:14:13,  2.95it/s]
 45%|████▍     | 167057/371472 [2:20:37<18:35:38,  3.05it/s]
 45%|████▍     | 167058/371472 [2:20:37<21:08:33,  2.69it/s]
 45%|████▍     | 167059/371472 [2:20:37<21:11:37,  2.68it/s]
 45%|████▍     | 167060/371472 [2:20:38<19:26:53,  2.92it/s]
                                                            
{'loss': 2.9193, 'learning_rate': 5.955148785795858e-07, 'epoch': 7.2}
+
 45%|████▍     | 167060/371472 [2:20:38<19:26:53,  2.92it/s]
 45%|████▍     | 167061/371472 [2:20:38<18:50:26,  3.01it/s]
 45%|████▍     | 167062/371472 [2:20:38<17:56:27,  3.16it/s]
 45%|████▍     | 167063/371472 [2:20:39<17:28:27,  3.25it/s]
 45%|████▍     | 167064/371472 [2:20:39<17:01:57,  3.33it/s]
 45%|████▍     | 167065/371472 [2:20:39<17:10:17,  3.31it/s]
 45%|████▍     | 167066/371472 [2:20:39<17:43:31,  3.20it/s]
 45%|████▍     | 167067/371472 [2:20:40<17:46:04,  3.20it/s]
 45%|████▍     | 167068/371472 [2:20:40<17:21:11,  3.27it/s]
 45%|████▍     | 167069/371472 [2:20:40<17:53:21,  3.17it/s]
 45%|████▍     | 167070/371472 [2:20:41<17:49:29,  3.19it/s]
 45%|████▍     | 167071/371472 [2:20:41<17:40:34,  3.21it/s]
 45%|████▍     | 167072/371472 [2:20:41<17:13:43,  3.30it/s]
 45%|████▍     | 167073/371472 [2:20:42<17:09:28,  3.31it/s]
 45%|████▍     | 167074/371472 [2:20:42<18:37:02,  3.05it/s]
 45%|████▍     | 167075/371472 [2:20:42<19:06:47,  2.97it/s]
 45%|████▍     | 167076/371472 [2:20:43<18:24:16,  3.08it/s]
 45%|████▍     | 167077/371472 [2:20:43<17:49:57,  3.18it/s]
 45%|████▍     | 167078/371472 [2:20:43<17:25:45,  3.26it/s]
 45%|████▍     | 167079/371472 [2:20:44<17:20:03,  3.28it/s]
 45%|████▍     | 167080/371472 [2:20:44<17:28:18,  3.25it/s]
                                                            
{'loss': 2.93, 'learning_rate': 5.954663966041069e-07, 'epoch': 7.2}
+
 45%|████▍     | 167080/371472 [2:20:44<17:28:18,  3.25it/s]
 45%|████▍     | 167081/371472 [2:20:44<18:05:49,  3.14it/s]
 45%|████▍     | 167082/371472 [2:20:45<18:14:22,  3.11it/s]
 45%|████▍     | 167083/371472 [2:20:45<18:36:54,  3.05it/s]
 45%|████▍     | 167084/371472 [2:20:45<17:51:29,  3.18it/s]
 45%|████▍     | 167085/371472 [2:20:45<17:32:15,  3.24it/s]
 45%|████▍     | 167086/371472 [2:20:46<17:17:21,  3.28it/s]
 45%|████▍     | 167087/371472 [2:20:46<16:48:24,  3.38it/s]
 45%|████▍     | 167088/371472 [2:20:46<17:03:59,  3.33it/s]
 45%|████▍     | 167089/371472 [2:20:47<17:03:33,  3.33it/s]
 45%|████▍     | 167090/371472 [2:20:47<16:56:45,  3.35it/s]
 45%|████▍     | 167091/371472 [2:20:47<17:08:46,  3.31it/s]
 45%|████▍     | 167092/371472 [2:20:48<17:38:25,  3.22it/s]
 45%|████▍     | 167093/371472 [2:20:48<17:15:23,  3.29it/s]
 45%|████▍     | 167094/371472 [2:20:48<17:07:53,  3.31it/s]
 45%|████▍     | 167095/371472 [2:20:48<17:54:14,  3.17it/s]
 45%|████▍     | 167096/371472 [2:20:49<18:11:07,  3.12it/s]
 45%|████▍     | 167097/371472 [2:20:49<17:53:27,  3.17it/s]
 45%|████▍     | 167098/371472 [2:20:49<17:41:44,  3.21it/s]
 45%|████▍     | 167099/371472 [2:20:50<17:27:35,  3.25it/s]
 45%|████▍     | 167100/371472 [2:20:50<17:05:34,  3.32it/s]
                                                            
{'loss': 2.9868, 'learning_rate': 5.95417914628628e-07, 'epoch': 7.2}
+
 45%|████▍     | 167100/371472 [2:20:50<17:05:34,  3.32it/s]
 45%|████▍     | 167101/371472 [2:20:50<17:01:47,  3.33it/s]
 45%|████▍     | 167102/371472 [2:20:51<17:33:51,  3.23it/s]
 45%|████▍     | 167103/371472 [2:20:51<17:02:01,  3.33it/s]
 45%|████▍     | 167104/371472 [2:20:51<17:48:28,  3.19it/s]
 45%|████▍     | 167105/371472 [2:20:52<18:43:30,  3.03it/s]
 45%|████▍     | 167106/371472 [2:20:52<18:55:12,  3.00it/s]
 45%|████▍     | 167107/371472 [2:20:52<17:58:46,  3.16it/s]
 45%|████▍     | 167108/371472 [2:20:53<17:33:58,  3.23it/s]
 45%|████▍     | 167109/371472 [2:20:53<17:17:59,  3.28it/s]
 45%|████▍     | 167110/371472 [2:20:53<17:41:08,  3.21it/s]
 45%|████▍     | 167111/371472 [2:20:53<17:15:49,  3.29it/s]
 45%|████▍     | 167112/371472 [2:20:54<17:13:02,  3.30it/s]
 45%|████▍     | 167113/371472 [2:20:54<17:53:29,  3.17it/s]
 45%|████▍     | 167114/371472 [2:20:54<17:44:26,  3.20it/s]
 45%|████▍     | 167115/371472 [2:20:55<17:35:03,  3.23it/s]
 45%|████▍     | 167116/371472 [2:20:55<18:18:01,  3.10it/s]
 45%|████▍     | 167117/371472 [2:20:55<17:54:05,  3.17it/s]
 45%|████▍     | 167118/371472 [2:20:56<17:33:09,  3.23it/s]
 45%|████▍     | 167119/371472 [2:20:56<17:00:23,  3.34it/s]
 45%|████▍     | 167120/371472 [2:20:56<16:35:45,  3.42it/s]
                                                            
{'loss': 2.8993, 'learning_rate': 5.953694326531491e-07, 'epoch': 7.2}
+
 45%|████▍     | 167120/371472 [2:20:56<16:35:45,  3.42it/s]
 45%|████▍     | 167121/371472 [2:20:57<16:51:59,  3.37it/s]
 45%|████▍     | 167122/371472 [2:20:57<16:49:17,  3.37it/s]
 45%|████▍     | 167123/371472 [2:20:57<16:41:29,  3.40it/s]
 45%|████▍     | 167124/371472 [2:20:57<16:35:27,  3.42it/s]
 45%|████▍     | 167125/371472 [2:20:58<18:53:44,  3.00it/s]
 45%|████▍     | 167126/371472 [2:20:58<18:20:26,  3.09it/s]
 45%|████▍     | 167127/371472 [2:20:58<17:38:20,  3.22it/s]
 45%|████▍     | 167128/371472 [2:20:59<17:12:00,  3.30it/s]
 45%|████▍     | 167129/371472 [2:20:59<17:51:21,  3.18it/s]
 45%|████▍     | 167130/371472 [2:20:59<17:15:52,  3.29it/s]
 45%|████▍     | 167131/371472 [2:21:00<16:40:25,  3.40it/s]
 45%|████▍     | 167132/371472 [2:21:00<16:56:41,  3.35it/s]
 45%|████▍     | 167133/371472 [2:21:00<19:38:12,  2.89it/s]
 45%|████▍     | 167134/371472 [2:21:01<18:53:52,  3.00it/s]
 45%|████▍     | 167135/371472 [2:21:01<18:23:54,  3.09it/s]
 45%|████▍     | 167136/371472 [2:21:01<17:54:09,  3.17it/s]
 45%|████▍     | 167137/371472 [2:21:02<17:51:22,  3.18it/s]
 45%|████▍     | 167138/371472 [2:21:02<17:42:06,  3.21it/s]
 45%|████▍     | 167139/371472 [2:21:02<17:58:07,  3.16it/s]
 45%|████▍     | 167140/371472 [2:21:02<17:57:16,  3.16it/s]
                                                            
{'loss': 2.9262, 'learning_rate': 5.953209506776703e-07, 'epoch': 7.2}
+
 45%|████▍     | 167140/371472 [2:21:02<17:57:16,  3.16it/s]
 45%|████▍     | 167141/371472 [2:21:03<17:29:39,  3.24it/s]
 45%|████▍     | 167142/371472 [2:21:03<18:07:14,  3.13it/s]
 45%|████▍     | 167143/371472 [2:21:03<17:40:02,  3.21it/s]
 45%|████▍     | 167144/371472 [2:21:04<17:28:01,  3.25it/s]
 45%|████▍     | 167145/371472 [2:21:04<17:07:48,  3.31it/s]
 45%|████▍     | 167146/371472 [2:21:04<16:53:21,  3.36it/s]
 45%|████▍     | 167147/371472 [2:21:05<16:51:10,  3.37it/s]
 45%|████▍     | 167148/371472 [2:21:05<17:11:15,  3.30it/s]
 45%|████▍     | 167149/371472 [2:21:05<16:46:14,  3.38it/s]
 45%|████▍     | 167150/371472 [2:21:05<16:54:13,  3.36it/s]
 45%|████▍     | 167151/371472 [2:21:06<16:39:28,  3.41it/s]
 45%|████▍     | 167152/371472 [2:21:06<16:53:28,  3.36it/s]
 45%|████▍     | 167153/371472 [2:21:06<16:54:55,  3.36it/s]
 45%|████▍     | 167154/371472 [2:21:07<16:25:19,  3.46it/s]
 45%|████▍     | 167155/371472 [2:21:07<16:27:06,  3.45it/s]
 45%|████▍     | 167156/371472 [2:21:07<16:33:48,  3.43it/s]
 45%|████▍     | 167157/371472 [2:21:08<19:12:48,  2.95it/s]
 45%|████▍     | 167158/371472 [2:21:08<18:34:05,  3.06it/s]
 45%|████▍     | 167159/371472 [2:21:08<18:23:02,  3.09it/s]
 45%|████▍     | 167160/371472 [2:21:09<17:43:43,  3.20it/s]
                                                            
{'loss': 3.0902, 'learning_rate': 5.952724687021914e-07, 'epoch': 7.2}
+
 45%|████▍     | 167160/371472 [2:21:09<17:43:43,  3.20it/s]
 45%|████▍     | 167161/371472 [2:21:09<17:34:22,  3.23it/s]
 45%|████▍     | 167162/371472 [2:21:09<17:16:34,  3.29it/s]
 45%|████▌     | 167163/371472 [2:21:09<17:14:36,  3.29it/s]
 45%|████▌     | 167164/371472 [2:21:10<18:08:18,  3.13it/s]
 45%|████▌     | 167165/371472 [2:21:10<17:34:53,  3.23it/s]
 45%|████▌     | 167166/371472 [2:21:10<17:06:47,  3.32it/s]
 45%|████▌     | 167167/371472 [2:21:11<16:31:19,  3.43it/s]
 45%|████▌     | 167168/371472 [2:21:11<16:32:48,  3.43it/s]
 45%|████▌     | 167169/371472 [2:21:11<16:44:52,  3.39it/s]
 45%|████▌     | 167170/371472 [2:21:12<16:41:00,  3.40it/s]
 45%|████▌     | 167171/371472 [2:21:12<16:31:04,  3.44it/s]
 45%|████▌     | 167172/371472 [2:21:12<16:37:26,  3.41it/s]
 45%|████▌     | 167173/371472 [2:21:12<16:06:19,  3.52it/s]
 45%|████▌     | 167174/371472 [2:21:13<16:05:20,  3.53it/s]
 45%|████▌     | 167175/371472 [2:21:13<15:40:41,  3.62it/s]
 45%|████▌     | 167176/371472 [2:21:13<16:38:45,  3.41it/s]
 45%|████▌     | 167177/371472 [2:21:14<16:34:16,  3.42it/s]
 45%|████▌     | 167178/371472 [2:21:14<16:37:49,  3.41it/s]
 45%|████▌     | 167179/371472 [2:21:14<16:24:51,  3.46it/s]
 45%|████▌     | 167180/371472 [2:21:14<16:18:02,  3.48it/s]
                                                            
{'loss': 3.0595, 'learning_rate': 5.952239867267125e-07, 'epoch': 7.2}
+
 45%|████▌     | 167180/371472 [2:21:14<16:18:02,  3.48it/s]
 45%|████▌     | 167181/371472 [2:21:15<17:26:47,  3.25it/s]
 45%|████▌     | 167182/371472 [2:21:15<16:55:34,  3.35it/s]
 45%|████▌     | 167183/371472 [2:21:15<17:18:49,  3.28it/s]
 45%|████▌     | 167184/371472 [2:21:16<17:36:21,  3.22it/s]
 45%|████▌     | 167185/371472 [2:21:16<17:13:59,  3.29it/s]
 45%|████▌     | 167186/371472 [2:21:16<17:38:02,  3.22it/s]
 45%|████▌     | 167187/371472 [2:21:17<17:20:18,  3.27it/s]
 45%|████▌     | 167188/371472 [2:21:17<17:02:34,  3.33it/s]
 45%|████▌     | 167189/371472 [2:21:17<16:54:57,  3.35it/s]
 45%|████▌     | 167190/371472 [2:21:18<17:43:05,  3.20it/s]
 45%|████▌     | 167191/371472 [2:21:18<17:15:22,  3.29it/s]
 45%|████▌     | 167192/371472 [2:21:18<17:00:48,  3.34it/s]
 45%|████▌     | 167193/371472 [2:21:18<17:14:13,  3.29it/s]
 45%|████▌     | 167194/371472 [2:21:19<17:02:56,  3.33it/s]
 45%|████▌     | 167195/371472 [2:21:19<17:05:12,  3.32it/s]
 45%|████▌     | 167196/371472 [2:21:19<16:57:14,  3.35it/s]
 45%|████▌     | 167197/371472 [2:21:20<17:05:39,  3.32it/s]
 45%|████▌     | 167198/371472 [2:21:20<17:25:09,  3.26it/s]
 45%|████▌     | 167199/371472 [2:21:20<16:59:31,  3.34it/s]
 45%|████▌     | 167200/371472 [2:21:21<17:00:41,  3.34it/s]
                                                            
{'loss': 2.8887, 'learning_rate': 5.951755047512335e-07, 'epoch': 7.2}
+
 45%|████▌     | 167200/371472 [2:21:21<17:00:41,  3.34it/s]
 45%|████▌     | 167201/371472 [2:21:21<17:13:16,  3.29it/s]
 45%|████▌     | 167202/371472 [2:21:21<18:01:43,  3.15it/s]
 45%|████▌     | 167203/371472 [2:21:21<17:31:02,  3.24it/s]
 45%|████▌     | 167204/371472 [2:21:22<18:16:33,  3.10it/s]
 45%|████▌     | 167205/371472 [2:21:22<18:42:04,  3.03it/s]
 45%|████▌     | 167206/371472 [2:21:23<18:38:31,  3.04it/s]
 45%|████▌     | 167207/371472 [2:21:23<17:54:21,  3.17it/s]
 45%|████▌     | 167208/371472 [2:21:23<17:28:26,  3.25it/s]
 45%|████▌     | 167209/371472 [2:21:23<17:25:50,  3.26it/s]
 45%|████▌     | 167210/371472 [2:21:24<17:31:55,  3.24it/s]
 45%|████▌     | 167211/371472 [2:21:24<17:34:44,  3.23it/s]
 45%|████▌     | 167212/371472 [2:21:24<17:24:26,  3.26it/s]
 45%|████▌     | 167213/371472 [2:21:25<17:14:06,  3.29it/s]
 45%|████▌     | 167214/371472 [2:21:25<16:52:15,  3.36it/s]
 45%|████▌     | 167215/371472 [2:21:25<17:19:59,  3.27it/s]
 45%|████▌     | 167216/371472 [2:21:26<17:23:16,  3.26it/s]
 45%|████▌     | 167217/371472 [2:21:26<17:06:48,  3.32it/s]
 45%|████▌     | 167218/371472 [2:21:26<16:53:10,  3.36it/s]
 45%|████▌     | 167219/371472 [2:21:26<17:54:21,  3.17it/s]
 45%|████▌     | 167220/371472 [2:21:27<17:45:46,  3.19it/s]
                                                            
{'loss': 2.8772, 'learning_rate': 5.951270227757547e-07, 'epoch': 7.2}
+
 45%|████▌     | 167220/371472 [2:21:27<17:45:46,  3.19it/s]
 45%|████▌     | 167221/371472 [2:21:27<17:12:14,  3.30it/s]
 45%|████▌     | 167222/371472 [2:21:27<16:52:26,  3.36it/s]
 45%|████▌     | 167223/371472 [2:21:28<17:14:33,  3.29it/s]
 45%|████▌     | 167224/371472 [2:21:28<17:07:20,  3.31it/s]
 45%|████▌     | 167225/371472 [2:21:28<17:01:55,  3.33it/s]
 45%|████▌     | 167226/371472 [2:21:29<16:39:08,  3.41it/s]
 45%|████▌     | 167227/371472 [2:21:29<16:35:57,  3.42it/s]
 45%|████▌     | 167228/371472 [2:21:29<16:29:20,  3.44it/s]
 45%|████▌     | 167229/371472 [2:21:29<16:05:10,  3.53it/s]
 45%|████▌     | 167230/371472 [2:21:30<16:06:20,  3.52it/s]
 45%|████▌     | 167231/371472 [2:21:30<16:24:24,  3.46it/s]
 45%|████▌     | 167232/371472 [2:21:30<16:44:05,  3.39it/s]
 45%|████▌     | 167233/371472 [2:21:31<17:27:56,  3.25it/s]
 45%|████▌     | 167234/371472 [2:21:31<17:16:09,  3.29it/s]
 45%|████▌     | 167235/371472 [2:21:31<17:51:40,  3.18it/s]
 45%|████▌     | 167236/371472 [2:21:32<17:34:19,  3.23it/s]
 45%|████▌     | 167237/371472 [2:21:32<17:41:48,  3.21it/s]
 45%|████▌     | 167238/371472 [2:21:32<17:20:53,  3.27it/s]
 45%|████▌     | 167239/371472 [2:21:33<18:17:49,  3.10it/s]
 45%|████▌     | 167240/371472 [2:21:33<18:31:42,  3.06it/s]
                                                            
{'loss': 3.1009, 'learning_rate': 5.950785408002758e-07, 'epoch': 7.2}
+
 45%|████▌     | 167240/371472 [2:21:33<18:31:42,  3.06it/s]
 45%|████▌     | 167241/371472 [2:21:33<19:03:07,  2.98it/s]
 45%|████▌     | 167242/371472 [2:21:34<18:40:25,  3.04it/s]
 45%|████▌     | 167243/371472 [2:21:34<19:21:20,  2.93it/s]
 45%|████▌     | 167244/371472 [2:21:34<19:08:08,  2.96it/s]
 45%|████▌     | 167245/371472 [2:21:35<19:27:45,  2.91it/s]
 45%|████▌     | 167246/371472 [2:21:35<18:23:03,  3.09it/s]
 45%|████▌     | 167247/371472 [2:21:35<17:55:36,  3.16it/s]
 45%|████▌     | 167248/371472 [2:21:35<17:42:59,  3.20it/s]
 45%|████▌     | 167249/371472 [2:21:36<17:17:48,  3.28it/s]
 45%|████▌     | 167250/371472 [2:21:36<16:59:38,  3.34it/s]
 45%|████▌     | 167251/371472 [2:21:36<17:05:55,  3.32it/s]
 45%|████▌     | 167252/371472 [2:21:37<16:54:51,  3.35it/s]
 45%|████▌     | 167253/371472 [2:21:37<16:44:03,  3.39it/s]
 45%|████▌     | 167254/371472 [2:21:37<16:53:13,  3.36it/s]
 45%|████▌     | 167255/371472 [2:21:38<17:16:27,  3.28it/s]
 45%|████▌     | 167256/371472 [2:21:38<17:23:13,  3.26it/s]
 45%|████▌     | 167257/371472 [2:21:38<17:29:50,  3.24it/s]
 45%|████▌     | 167258/371472 [2:21:38<17:22:01,  3.27it/s]
 45%|████▌     | 167259/371472 [2:21:39<18:19:13,  3.10it/s]
 45%|████▌     | 167260/371472 [2:21:39<17:43:05,  3.20it/s]
                                                            
{'loss': 2.9769, 'learning_rate': 5.950300588247969e-07, 'epoch': 7.2}
+
 45%|████▌     | 167260/371472 [2:21:39<17:43:05,  3.20it/s]
 45%|████▌     | 167261/371472 [2:21:39<17:09:03,  3.31it/s]
 45%|████▌     | 167262/371472 [2:21:40<17:02:09,  3.33it/s]
 45%|████▌     | 167263/371472 [2:21:40<17:31:45,  3.24it/s]
 45%|████▌     | 167264/371472 [2:21:40<17:29:35,  3.24it/s]
 45%|████▌     | 167265/371472 [2:21:41<17:16:38,  3.28it/s]
 45%|████▌     | 167266/371472 [2:21:41<16:37:41,  3.41it/s]
 45%|████▌     | 167267/371472 [2:21:41<16:43:01,  3.39it/s]
 45%|████▌     | 167268/371472 [2:21:41<16:40:32,  3.40it/s]
 45%|████▌     | 167269/371472 [2:21:42<16:56:10,  3.35it/s]
 45%|████▌     | 167270/371472 [2:21:42<17:35:18,  3.23it/s]
 45%|████▌     | 167271/371472 [2:21:42<17:00:27,  3.34it/s]
 45%|████▌     | 167272/371472 [2:21:43<17:13:01,  3.29it/s]
 45%|████▌     | 167273/371472 [2:21:43<16:54:12,  3.36it/s]
 45%|████▌     | 167274/371472 [2:21:43<17:36:58,  3.22it/s]
 45%|████▌     | 167275/371472 [2:21:44<18:32:27,  3.06it/s]
 45%|████▌     | 167276/371472 [2:21:44<18:51:40,  3.01it/s]
 45%|████▌     | 167277/371472 [2:21:44<19:42:47,  2.88it/s]
 45%|████▌     | 167278/371472 [2:21:45<18:51:30,  3.01it/s]
 45%|████▌     | 167279/371472 [2:21:45<18:01:25,  3.15it/s]
 45%|████▌     | 167280/371472 [2:21:45<18:58:17,  2.99it/s]
                                                            
{'loss': 2.7755, 'learning_rate': 5.94981576849318e-07, 'epoch': 7.21}
+
 45%|████▌     | 167280/371472 [2:21:45<18:58:17,  2.99it/s]
 45%|████▌     | 167281/371472 [2:21:46<18:52:53,  3.00it/s]
 45%|████▌     | 167282/371472 [2:21:46<18:10:27,  3.12it/s]
 45%|████▌     | 167283/371472 [2:21:46<17:54:16,  3.17it/s]
 45%|████▌     | 167284/371472 [2:21:47<17:28:48,  3.24it/s]
 45%|████▌     | 167285/371472 [2:21:47<17:34:00,  3.23it/s]
 45%|████▌     | 167286/371472 [2:21:47<18:10:10,  3.12it/s]
 45%|████▌     | 167287/371472 [2:21:48<17:56:39,  3.16it/s]
 45%|████▌     | 167288/371472 [2:21:48<17:18:52,  3.28it/s]
 45%|████▌     | 167289/371472 [2:21:48<16:50:18,  3.37it/s]
 45%|████▌     | 167290/371472 [2:21:48<16:37:21,  3.41it/s]
 45%|████▌     | 167291/371472 [2:21:49<16:36:18,  3.42it/s]
 45%|████▌     | 167292/371472 [2:21:49<16:23:01,  3.46it/s]
 45%|████▌     | 167293/371472 [2:21:49<17:52:18,  3.17it/s]
 45%|████▌     | 167294/371472 [2:21:50<18:14:40,  3.11it/s]
 45%|████▌     | 167295/371472 [2:21:50<17:57:23,  3.16it/s]
 45%|████▌     | 167296/371472 [2:21:50<17:36:17,  3.22it/s]
 45%|████▌     | 167297/371472 [2:21:51<18:09:33,  3.12it/s]
 45%|████▌     | 167298/371472 [2:21:51<17:58:27,  3.16it/s]
 45%|████▌     | 167299/371472 [2:21:51<17:45:20,  3.19it/s]
 45%|████▌     | 167300/371472 [2:21:52<17:23:51,  3.26it/s]
                                                            
{'loss': 2.9528, 'learning_rate': 5.949330948738392e-07, 'epoch': 7.21}
+
 45%|████▌     | 167300/371472 [2:21:52<17:23:51,  3.26it/s]
 45%|████▌     | 167301/371472 [2:21:52<17:50:09,  3.18it/s]
 45%|████▌     | 167302/371472 [2:21:52<17:05:09,  3.32it/s]
 45%|████▌     | 167303/371472 [2:21:52<17:36:40,  3.22it/s]
 45%|████▌     | 167304/371472 [2:21:53<17:50:51,  3.18it/s]
 45%|████▌     | 167305/371472 [2:21:53<17:24:01,  3.26it/s]
 45%|████▌     | 167306/371472 [2:21:53<17:02:43,  3.33it/s]
 45%|████▌     | 167307/371472 [2:21:54<16:47:54,  3.38it/s]
 45%|████▌     | 167308/371472 [2:21:54<16:27:16,  3.45it/s]
 45%|████▌     | 167309/371472 [2:21:54<17:10:02,  3.30it/s]
 45%|████▌     | 167310/371472 [2:21:55<16:56:52,  3.35it/s]
 45%|████▌     | 167311/371472 [2:21:55<16:41:45,  3.40it/s]
 45%|████▌     | 167312/371472 [2:21:55<17:54:47,  3.17it/s]
 45%|████▌     | 167313/371472 [2:21:55<17:31:19,  3.24it/s]
 45%|████▌     | 167314/371472 [2:21:56<16:58:31,  3.34it/s]
 45%|████▌     | 167315/371472 [2:21:56<17:20:47,  3.27it/s]
 45%|████▌     | 167316/371472 [2:21:56<17:10:48,  3.30it/s]
 45%|████▌     | 167317/371472 [2:21:57<17:07:42,  3.31it/s]
 45%|████▌     | 167318/371472 [2:21:57<17:24:31,  3.26it/s]
 45%|████▌     | 167319/371472 [2:21:57<17:16:07,  3.28it/s]
 45%|████▌     | 167320/371472 [2:21:58<17:54:17,  3.17it/s]
                                                            
{'loss': 3.1157, 'learning_rate': 5.948846128983601e-07, 'epoch': 7.21}
+
 45%|████▌     | 167320/371472 [2:21:58<17:54:17,  3.17it/s]
 45%|████▌     | 167321/371472 [2:21:58<17:15:52,  3.28it/s]
 45%|████▌     | 167322/371472 [2:21:58<17:17:24,  3.28it/s]
 45%|████▌     | 167323/371472 [2:21:59<16:57:13,  3.34it/s]
 45%|████▌     | 167324/371472 [2:21:59<17:03:58,  3.32it/s]
 45%|████▌     | 167325/371472 [2:21:59<18:54:55,  3.00it/s]
 45%|████▌     | 167326/371472 [2:22:00<18:04:23,  3.14it/s]
 45%|████▌     | 167327/371472 [2:22:00<19:06:19,  2.97it/s]
 45%|████▌     | 167328/371472 [2:22:00<18:22:45,  3.09it/s]
 45%|████▌     | 167329/371472 [2:22:01<18:50:40,  3.01it/s]
 45%|████▌     | 167330/371472 [2:22:01<18:59:06,  2.99it/s]
 45%|████▌     | 167331/371472 [2:22:01<18:46:02,  3.02it/s]
 45%|████▌     | 167332/371472 [2:22:01<17:57:42,  3.16it/s]
 45%|████▌     | 167333/371472 [2:22:02<17:40:19,  3.21it/s]
 45%|████▌     | 167334/371472 [2:22:02<17:13:50,  3.29it/s]
 45%|████▌     | 167335/371472 [2:22:02<17:01:46,  3.33it/s]
 45%|████▌     | 167336/371472 [2:22:03<16:42:06,  3.40it/s]
 45%|████▌     | 167337/371472 [2:22:03<16:31:02,  3.43it/s]
 45%|████▌     | 167338/371472 [2:22:03<17:01:33,  3.33it/s]
 45%|████▌     | 167339/371472 [2:22:04<17:30:28,  3.24it/s]
 45%|████▌     | 167340/371472 [2:22:04<17:11:32,  3.30it/s]
                                                            
{'loss': 2.7264, 'learning_rate': 5.948361309228812e-07, 'epoch': 7.21}
+
 45%|████▌     | 167340/371472 [2:22:04<17:11:32,  3.30it/s]
 45%|████▌     | 167341/371472 [2:22:04<17:22:43,  3.26it/s]
 45%|████▌     | 167342/371472 [2:22:04<17:17:41,  3.28it/s]
 45%|████▌     | 167343/371472 [2:22:05<17:00:01,  3.34it/s]
 45%|████▌     | 167344/371472 [2:22:05<17:26:55,  3.25it/s]
 45%|████▌     | 167345/371472 [2:22:05<17:13:36,  3.29it/s]
 45%|████▌     | 167346/371472 [2:22:06<20:25:26,  2.78it/s]
 45%|████▌     | 167347/371472 [2:22:06<19:46:02,  2.87it/s]
 45%|████▌     | 167348/371472 [2:22:07<20:52:32,  2.72it/s]
 45%|████▌     | 167349/371472 [2:22:07<20:18:59,  2.79it/s]
 45%|████▌     | 167350/371472 [2:22:07<20:54:26,  2.71it/s]
 45%|████▌     | 167351/371472 [2:22:08<20:58:07,  2.70it/s]
 45%|████▌     | 167352/371472 [2:22:08<19:43:30,  2.87it/s]
 45%|████▌     | 167353/371472 [2:22:08<19:02:02,  2.98it/s]
 45%|████▌     | 167354/371472 [2:22:09<18:35:54,  3.05it/s]
 45%|████▌     | 167355/371472 [2:22:09<18:09:08,  3.12it/s]
 45%|████▌     | 167356/371472 [2:22:09<18:17:33,  3.10it/s]
 45%|████▌     | 167357/371472 [2:22:10<17:47:24,  3.19it/s]
 45%|████▌     | 167358/371472 [2:22:10<17:47:15,  3.19it/s]
 45%|████▌     | 167359/371472 [2:22:10<18:40:37,  3.04it/s]
 45%|████▌     | 167360/371472 [2:22:11<17:51:48,  3.17it/s]
                                                            
{'loss': 2.9063, 'learning_rate': 5.947876489474024e-07, 'epoch': 7.21}
+
 45%|████▌     | 167360/371472 [2:22:11<17:51:48,  3.17it/s]
 45%|████▌     | 167361/371472 [2:22:11<17:35:05,  3.22it/s]
 45%|████▌     | 167362/371472 [2:22:11<17:11:56,  3.30it/s]
 45%|████▌     | 167363/371472 [2:22:11<17:00:18,  3.33it/s]
 45%|████▌     | 167364/371472 [2:22:12<17:15:39,  3.28it/s]
 45%|████▌     | 167365/371472 [2:22:12<17:19:28,  3.27it/s]
 45%|████▌     | 167366/371472 [2:22:12<16:57:59,  3.34it/s]
 45%|████▌     | 167367/371472 [2:22:13<17:02:05,  3.33it/s]
 45%|████▌     | 167368/371472 [2:22:13<16:56:06,  3.35it/s]
 45%|████▌     | 167369/371472 [2:22:13<17:01:00,  3.33it/s]
 45%|████▌     | 167370/371472 [2:22:14<17:03:30,  3.32it/s]
 45%|████▌     | 167371/371472 [2:22:14<17:11:24,  3.30it/s]
 45%|████▌     | 167372/371472 [2:22:14<16:49:52,  3.37it/s]
 45%|████▌     | 167373/371472 [2:22:14<16:29:51,  3.44it/s]
 45%|████▌     | 167374/371472 [2:22:15<16:51:50,  3.36it/s]
 45%|████▌     | 167375/371472 [2:22:15<16:33:11,  3.42it/s]
 45%|████▌     | 167376/371472 [2:22:15<16:47:15,  3.38it/s]
 45%|████▌     | 167377/371472 [2:22:16<16:50:19,  3.37it/s]
 45%|████▌     | 167378/371472 [2:22:16<17:46:10,  3.19it/s]
 45%|████▌     | 167379/371472 [2:22:16<17:31:49,  3.23it/s]
 45%|████▌     | 167380/371472 [2:22:17<17:19:18,  3.27it/s]
                                                            
{'loss': 2.9303, 'learning_rate': 5.947391669719236e-07, 'epoch': 7.21}
+
 45%|████▌     | 167380/371472 [2:22:17<17:19:18,  3.27it/s]
 45%|████▌     | 167381/371472 [2:22:17<17:04:27,  3.32it/s]
 45%|████▌     | 167382/371472 [2:22:17<17:49:08,  3.18it/s]
 45%|████▌     | 167383/371472 [2:22:17<17:09:10,  3.31it/s]
 45%|████▌     | 167384/371472 [2:22:18<17:07:44,  3.31it/s]
 45%|████▌     | 167385/371472 [2:22:18<16:52:03,  3.36it/s]
 45%|████▌     | 167386/371472 [2:22:18<16:47:04,  3.38it/s]
 45%|████▌     | 167387/371472 [2:22:19<17:27:48,  3.25it/s]
 45%|████▌     | 167388/371472 [2:22:19<17:11:54,  3.30it/s]
 45%|████▌     | 167389/371472 [2:22:19<17:05:26,  3.32it/s]
 45%|████▌     | 167390/371472 [2:22:20<17:36:45,  3.22it/s]
 45%|████▌     | 167391/371472 [2:22:20<17:07:21,  3.31it/s]
 45%|████▌     | 167392/371472 [2:22:20<17:07:53,  3.31it/s]
 45%|████▌     | 167393/371472 [2:22:20<16:50:02,  3.37it/s]
 45%|████▌     | 167394/371472 [2:22:21<16:48:50,  3.37it/s]
 45%|████▌     | 167395/371472 [2:22:21<17:19:32,  3.27it/s]
 45%|████▌     | 167396/371472 [2:22:21<17:01:02,  3.33it/s]
 45%|████▌     | 167397/371472 [2:22:22<17:31:01,  3.24it/s]
 45%|████▌     | 167398/371472 [2:22:22<17:41:11,  3.21it/s]
 45%|████▌     | 167399/371472 [2:22:22<17:42:03,  3.20it/s]
 45%|████▌     | 167400/371472 [2:22:23<18:20:13,  3.09it/s]
                                                            
{'loss': 2.9421, 'learning_rate': 5.946906849964447e-07, 'epoch': 7.21}
+
 45%|████▌     | 167400/371472 [2:22:23<18:20:13,  3.09it/s]
 45%|████▌     | 167401/371472 [2:22:23<18:14:03,  3.11it/s]
 45%|████▌     | 167402/371472 [2:22:23<17:36:12,  3.22it/s]
 45%|████▌     | 167403/371472 [2:22:24<17:14:14,  3.29it/s]
 45%|████▌     | 167404/371472 [2:22:24<17:25:24,  3.25it/s]
 45%|████▌     | 167405/371472 [2:22:24<17:15:08,  3.29it/s]
 45%|████▌     | 167406/371472 [2:22:24<16:59:21,  3.34it/s]
 45%|████▌     | 167407/371472 [2:22:25<17:04:55,  3.32it/s]
 45%|████▌     | 167408/371472 [2:22:25<17:06:52,  3.31it/s]
 45%|████▌     | 167409/371472 [2:22:25<16:59:21,  3.34it/s]
 45%|████▌     | 167410/371472 [2:22:26<16:19:57,  3.47it/s]
 45%|████▌     | 167411/371472 [2:22:26<16:22:22,  3.46it/s]
 45%|████▌     | 167412/371472 [2:22:26<18:00:02,  3.15it/s]
 45%|████▌     | 167413/371472 [2:22:27<17:22:14,  3.26it/s]
 45%|████▌     | 167414/371472 [2:22:27<18:25:25,  3.08it/s]
 45%|████▌     | 167415/371472 [2:22:27<17:35:19,  3.22it/s]
 45%|████▌     | 167416/371472 [2:22:28<17:55:10,  3.16it/s]
 45%|████▌     | 167417/371472 [2:22:28<17:45:26,  3.19it/s]
 45%|████▌     | 167418/371472 [2:22:28<17:43:15,  3.20it/s]
 45%|████▌     | 167419/371472 [2:22:28<17:43:09,  3.20it/s]
 45%|████▌     | 167420/371472 [2:22:29<17:41:25,  3.20it/s]
                                                            
{'loss': 2.8847, 'learning_rate': 5.946422030209658e-07, 'epoch': 7.21}
+
 45%|████▌     | 167420/371472 [2:22:29<17:41:25,  3.20it/s]
 45%|████▌     | 167421/371472 [2:22:29<18:16:38,  3.10it/s]
 45%|████▌     | 167422/371472 [2:22:29<17:43:47,  3.20it/s]
 45%|████▌     | 167423/371472 [2:22:30<17:27:45,  3.25it/s]
 45%|████▌     | 167424/371472 [2:22:30<17:12:59,  3.29it/s]
 45%|████▌     | 167425/371472 [2:22:30<17:31:42,  3.23it/s]
 45%|████▌     | 167426/371472 [2:22:31<17:03:47,  3.32it/s]
 45%|████▌     | 167427/371472 [2:22:31<17:05:34,  3.32it/s]
 45%|████▌     | 167428/371472 [2:22:31<17:04:08,  3.32it/s]
 45%|████▌     | 167429/371472 [2:22:32<16:55:14,  3.35it/s]
 45%|████▌     | 167430/371472 [2:22:32<18:25:23,  3.08it/s]
 45%|████▌     | 167431/371472 [2:22:32<17:49:38,  3.18it/s]
 45%|████▌     | 167432/371472 [2:22:32<17:28:34,  3.24it/s]
 45%|████▌     | 167433/371472 [2:22:33<16:58:04,  3.34it/s]
 45%|████▌     | 167434/371472 [2:22:33<16:59:36,  3.34it/s]
 45%|████▌     | 167435/371472 [2:22:33<16:53:17,  3.36it/s]
 45%|████▌     | 167436/371472 [2:22:34<18:45:36,  3.02it/s]
 45%|████▌     | 167437/371472 [2:22:34<17:55:03,  3.16it/s]
 45%|████▌     | 167438/371472 [2:22:34<18:10:59,  3.12it/s]
 45%|████▌     | 167439/371472 [2:22:35<17:30:59,  3.24it/s]
 45%|████▌     | 167440/371472 [2:22:35<18:10:52,  3.12it/s]
                                                            
{'loss': 2.8596, 'learning_rate': 5.945937210454868e-07, 'epoch': 7.21}
+
 45%|████▌     | 167440/371472 [2:22:35<18:10:52,  3.12it/s]
 45%|████▌     | 167441/371472 [2:22:35<19:18:01,  2.94it/s]
 45%|████▌     | 167442/371472 [2:22:36<18:38:51,  3.04it/s]
 45%|████▌     | 167443/371472 [2:22:36<17:46:58,  3.19it/s]
 45%|████▌     | 167444/371472 [2:22:36<18:17:54,  3.10it/s]
 45%|████▌     | 167445/371472 [2:22:37<17:55:31,  3.16it/s]
 45%|████▌     | 167446/371472 [2:22:37<17:21:27,  3.27it/s]
 45%|████▌     | 167447/371472 [2:22:37<17:17:04,  3.28it/s]
 45%|████▌     | 167448/371472 [2:22:38<17:36:31,  3.22it/s]
 45%|████▌     | 167449/371472 [2:22:38<17:42:02,  3.20it/s]
 45%|████▌     | 167450/371472 [2:22:38<16:53:16,  3.36it/s]
 45%|████▌     | 167451/371472 [2:22:38<16:54:52,  3.35it/s]
 45%|████▌     | 167452/371472 [2:22:39<18:38:59,  3.04it/s]
 45%|████▌     | 167453/371472 [2:22:39<19:45:01,  2.87it/s]
 45%|████▌     | 167454/371472 [2:22:40<20:36:32,  2.75it/s]
 45%|████▌     | 167455/371472 [2:22:40<19:57:54,  2.84it/s]
 45%|████▌     | 167456/371472 [2:22:40<19:06:57,  2.96it/s]
 45%|████▌     | 167457/371472 [2:22:41<18:18:53,  3.09it/s]
 45%|████▌     | 167458/371472 [2:22:41<17:48:48,  3.18it/s]
 45%|████▌     | 167459/371472 [2:22:41<17:54:58,  3.16it/s]
 45%|████▌     | 167460/371472 [2:22:42<18:52:30,  3.00it/s]
                                                            
{'loss': 2.9099, 'learning_rate': 5.94545239070008e-07, 'epoch': 7.21}
+
 45%|████▌     | 167460/371472 [2:22:42<18:52:30,  3.00it/s]
 45%|████▌     | 167461/371472 [2:22:42<18:06:46,  3.13it/s]
 45%|████▌     | 167462/371472 [2:22:42<17:23:40,  3.26it/s]
 45%|████▌     | 167463/371472 [2:22:42<17:22:54,  3.26it/s]
 45%|████▌     | 167464/371472 [2:22:43<17:00:28,  3.33it/s]
 45%|████▌     | 167465/371472 [2:22:43<16:38:37,  3.40it/s]
 45%|████▌     | 167466/371472 [2:22:43<16:28:17,  3.44it/s]
 45%|████▌     | 167467/371472 [2:22:44<16:49:24,  3.37it/s]
 45%|████▌     | 167468/371472 [2:22:44<16:51:28,  3.36it/s]
 45%|████▌     | 167469/371472 [2:22:44<16:56:09,  3.35it/s]
 45%|████▌     | 167470/371472 [2:22:44<17:35:58,  3.22it/s]
 45%|████▌     | 167471/371472 [2:22:45<17:35:41,  3.22it/s]
 45%|████▌     | 167472/371472 [2:22:45<17:05:55,  3.31it/s]
 45%|████▌     | 167473/371472 [2:22:45<17:53:40,  3.17it/s]
 45%|████▌     | 167474/371472 [2:22:46<17:20:31,  3.27it/s]
 45%|████▌     | 167475/371472 [2:22:46<17:23:45,  3.26it/s]
 45%|████▌     | 167476/371472 [2:22:46<17:01:48,  3.33it/s]
 45%|████▌     | 167477/371472 [2:22:47<17:15:23,  3.28it/s]
 45%|████▌     | 167478/371472 [2:22:47<18:40:52,  3.03it/s]
 45%|████▌     | 167479/371472 [2:22:47<18:36:12,  3.05it/s]
 45%|████▌     | 167480/371472 [2:22:48<18:15:51,  3.10it/s]
                                                            
{'loss': 2.8965, 'learning_rate': 5.94496757094529e-07, 'epoch': 7.21}
+
 45%|████▌     | 167480/371472 [2:22:48<18:15:51,  3.10it/s]
 45%|████▌     | 167481/371472 [2:22:48<17:37:53,  3.21it/s]
 45%|████▌     | 167482/371472 [2:22:48<17:12:08,  3.29it/s]
 45%|████▌     | 167483/371472 [2:22:49<17:47:43,  3.18it/s]
 45%|████▌     | 167484/371472 [2:22:49<17:13:14,  3.29it/s]
 45%|████▌     | 167485/371472 [2:22:49<16:33:28,  3.42it/s]
 45%|████▌     | 167486/371472 [2:22:49<17:15:40,  3.28it/s]
 45%|████▌     | 167487/371472 [2:22:50<17:12:35,  3.29it/s]
 45%|████▌     | 167488/371472 [2:22:50<17:03:50,  3.32it/s]
 45%|████▌     | 167489/371472 [2:22:50<16:47:24,  3.37it/s]
 45%|████▌     | 167490/371472 [2:22:51<17:45:31,  3.19it/s]
 45%|████▌     | 167491/371472 [2:22:51<17:00:13,  3.33it/s]
 45%|████▌     | 167492/371472 [2:22:51<16:40:38,  3.40it/s]
 45%|████▌     | 167493/371472 [2:22:51<16:26:10,  3.45it/s]
 45%|████▌     | 167494/371472 [2:22:52<16:38:22,  3.41it/s]
 45%|████▌     | 167495/371472 [2:22:52<16:36:06,  3.41it/s]
 45%|████▌     | 167496/371472 [2:22:52<16:57:37,  3.34it/s]
 45%|████▌     | 167497/371472 [2:22:53<16:58:19,  3.34it/s]
 45%|████▌     | 167498/371472 [2:22:53<16:37:23,  3.41it/s]
 45%|████▌     | 167499/371472 [2:22:53<17:29:09,  3.24it/s]
 45%|████▌     | 167500/371472 [2:22:54<18:19:32,  3.09it/s]
                                                            
{'loss': 2.7551, 'learning_rate': 5.944482751190501e-07, 'epoch': 7.21}
+
 45%|████▌     | 167500/371472 [2:22:54<18:19:32,  3.09it/s]
 45%|████▌     | 167501/371472 [2:22:54<18:08:05,  3.12it/s]
 45%|████▌     | 167502/371472 [2:22:54<17:53:42,  3.17it/s]
 45%|████▌     | 167503/371472 [2:22:55<17:48:06,  3.18it/s]
 45%|████▌     | 167504/371472 [2:22:55<18:03:46,  3.14it/s]
 45%|████▌     | 167505/371472 [2:22:55<17:54:13,  3.16it/s]
 45%|████▌     | 167506/371472 [2:22:56<18:39:15,  3.04it/s]
 45%|████▌     | 167507/371472 [2:22:56<17:56:30,  3.16it/s]
 45%|█��██▌     | 167508/371472 [2:22:56<17:23:10,  3.26it/s]
 45%|████▌     | 167509/371472 [2:22:56<17:03:02,  3.32it/s]
 45%|████▌     | 167510/371472 [2:22:57<16:49:26,  3.37it/s]
 45%|████▌     | 167511/371472 [2:22:57<16:35:16,  3.42it/s]
 45%|████▌     | 167512/371472 [2:22:57<16:58:04,  3.34it/s]
 45%|████▌     | 167513/371472 [2:22:58<17:07:25,  3.31it/s]
 45%|████▌     | 167514/371472 [2:22:58<17:01:21,  3.33it/s]
 45%|████▌     | 167515/371472 [2:22:58<17:00:05,  3.33it/s]
 45%|████▌     | 167516/371472 [2:22:59<16:57:09,  3.34it/s]
 45%|████▌     | 167517/371472 [2:22:59<16:36:48,  3.41it/s]
 45%|████▌     | 167518/371472 [2:22:59<16:53:23,  3.35it/s]
 45%|████▌     | 167519/371472 [2:22:59<17:06:58,  3.31it/s]
 45%|████▌     | 167520/371472 [2:23:00<17:57:55,  3.15it/s]
                                                            
{'loss': 2.9461, 'learning_rate': 5.943997931435713e-07, 'epoch': 7.22}
+
 45%|████▌     | 167520/371472 [2:23:00<17:57:55,  3.15it/s]
 45%|████▌     | 167521/371472 [2:23:00<17:47:26,  3.18it/s]
 45%|████▌     | 167522/371472 [2:23:00<17:46:41,  3.19it/s]
 45%|████▌     | 167523/371472 [2:23:01<18:55:36,  2.99it/s]
 45%|████▌     | 167524/371472 [2:23:01<18:17:06,  3.10it/s]
 45%|████▌     | 167525/371472 [2:23:01<18:17:52,  3.10it/s]
 45%|████▌     | 167526/371472 [2:23:02<18:19:25,  3.09it/s]
 45%|████▌     | 167527/371472 [2:23:02<17:51:54,  3.17it/s]
 45%|████▌     | 167528/371472 [2:23:02<17:11:48,  3.29it/s]
 45%|████▌     | 167529/371472 [2:23:03<17:02:29,  3.32it/s]
 45%|████▌     | 167530/371472 [2:23:03<16:49:44,  3.37it/s]
 45%|████▌     | 167531/371472 [2:23:03<17:08:14,  3.31it/s]
 45%|████▌     | 167532/371472 [2:23:04<17:06:37,  3.31it/s]
 45%|████▌     | 167533/371472 [2:23:04<17:21:26,  3.26it/s]
 45%|████▌     | 167534/371472 [2:23:04<16:56:21,  3.34it/s]
 45%|████▌     | 167535/371472 [2:23:04<16:26:21,  3.45it/s]
 45%|████▌     | 167536/371472 [2:23:05<16:36:12,  3.41it/s]
 45%|████▌     | 167537/371472 [2:23:05<17:14:30,  3.29it/s]
 45%|████▌     | 167538/371472 [2:23:05<17:25:08,  3.25it/s]
 45%|████▌     | 167539/371472 [2:23:06<17:50:03,  3.18it/s]
 45%|████▌     | 167540/371472 [2:23:06<17:26:19,  3.25it/s]
                                                            
{'loss': 2.8199, 'learning_rate': 5.943513111680924e-07, 'epoch': 7.22}
+
 45%|████▌     | 167540/371472 [2:23:06<17:26:19,  3.25it/s]
 45%|████▌     | 167541/371472 [2:23:06<17:22:16,  3.26it/s]
 45%|████▌     | 167542/371472 [2:23:07<16:29:07,  3.44it/s]
 45%|████▌     | 167543/371472 [2:23:07<16:55:59,  3.35it/s]
 45%|████▌     | 167544/371472 [2:23:07<16:47:27,  3.37it/s]
 45%|████▌     | 167545/371472 [2:23:07<18:14:06,  3.11it/s]
 45%|████▌     | 167546/371472 [2:23:08<17:55:26,  3.16it/s]
 45%|████▌     | 167547/371472 [2:23:08<17:30:45,  3.23it/s]
 45%|████▌     | 167548/371472 [2:23:08<17:17:19,  3.28it/s]
 45%|████▌     | 167549/371472 [2:23:09<16:50:46,  3.36it/s]
 45%|████▌     | 167550/371472 [2:23:09<16:44:13,  3.38it/s]
 45%|████▌     | 167551/371472 [2:23:09<16:35:40,  3.41it/s]
 45%|████▌     | 167552/371472 [2:23:10<16:45:11,  3.38it/s]
 45%|████▌     | 167553/371472 [2:23:10<16:35:08,  3.42it/s]
 45%|████▌     | 167554/371472 [2:23:10<17:31:02,  3.23it/s]
 45%|████▌     | 167555/371472 [2:23:10<17:31:09,  3.23it/s]
 45%|████▌     | 167556/371472 [2:23:11<17:09:05,  3.30it/s]
 45%|████▌     | 167557/371472 [2:23:11<17:33:24,  3.23it/s]
 45%|████▌     | 167558/371472 [2:23:11<17:15:03,  3.28it/s]
 45%|████▌     | 167559/371472 [2:23:12<17:04:11,  3.32it/s]
 45%|████▌     | 167560/371472 [2:23:12<17:36:35,  3.22it/s]
                                                            
{'loss': 3.1303, 'learning_rate': 5.943028291926135e-07, 'epoch': 7.22}
+
 45%|████▌     | 167560/371472 [2:23:12<17:36:35,  3.22it/s]
 45%|████▌     | 167561/371472 [2:23:12<17:48:23,  3.18it/s]
 45%|████▌     | 167562/371472 [2:23:13<18:03:27,  3.14it/s]
 45%|████▌     | 167563/371472 [2:23:13<17:53:22,  3.17it/s]
 45%|████▌     | 167564/371472 [2:23:13<17:07:57,  3.31it/s]
 45%|████▌     | 167565/371472 [2:23:14<16:48:12,  3.37it/s]
 45%|████▌     | 167566/371472 [2:23:14<17:06:24,  3.31it/s]
 45%|████▌     | 167567/371472 [2:23:14<18:42:41,  3.03it/s]
 45%|████▌     | 167568/371472 [2:23:15<17:59:31,  3.15it/s]
 45%|████▌     | 167569/371472 [2:23:15<17:31:05,  3.23it/s]
 45%|████▌     | 167570/371472 [2:23:15<17:17:18,  3.28it/s]
 45%|████▌     | 167571/371472 [2:23:15<17:02:42,  3.32it/s]
 45%|████▌     | 167572/371472 [2:23:16<17:01:04,  3.33it/s]
 45%|████▌     | 167573/371472 [2:23:16<17:00:37,  3.33it/s]
 45%|████▌     | 167574/371472 [2:23:16<17:14:05,  3.29it/s]
 45%|████▌     | 167575/371472 [2:23:17<17:10:42,  3.30it/s]
 45%|████▌     | 167576/371472 [2:23:17<17:03:12,  3.32it/s]
 45%|████▌     | 167577/371472 [2:23:17<17:49:14,  3.18it/s]
 45%|████▌     | 167578/371472 [2:23:18<18:04:32,  3.13it/s]
 45%|████▌     | 167579/371472 [2:23:18<18:24:44,  3.08it/s]
 45%|████▌     | 167580/371472 [2:23:18<17:52:57,  3.17it/s]
                                                            
{'loss': 3.0348, 'learning_rate': 5.942543472171345e-07, 'epoch': 7.22}
+
 45%|████▌     | 167580/371472 [2:23:18<17:52:57,  3.17it/s]
 45%|████▌     | 167581/371472 [2:23:19<18:22:43,  3.08it/s]
 45%|████▌     | 167582/371472 [2:23:19<17:51:36,  3.17it/s]
 45%|████▌     | 167583/371472 [2:23:19<17:08:40,  3.30it/s]
 45%|████▌     | 167584/371472 [2:23:19<17:23:03,  3.26it/s]
 45%|████▌     | 167585/371472 [2:23:20<17:12:47,  3.29it/s]
 45%|████▌     | 167586/371472 [2:23:20<16:48:08,  3.37it/s]
 45%|████▌     | 167587/371472 [2:23:20<16:44:27,  3.38it/s]
 45%|████▌     | 167588/371472 [2:23:21<17:18:26,  3.27it/s]
 45%|████▌     | 167589/371472 [2:23:21<18:16:10,  3.10it/s]
 45%|████▌     | 167590/371472 [2:23:21<17:50:52,  3.17it/s]
 45%|████▌     | 167591/371472 [2:23:22<17:13:28,  3.29it/s]
 45%|████▌     | 167592/371472 [2:23:22<17:04:53,  3.32it/s]
 45%|████▌     | 167593/371472 [2:23:22<16:56:59,  3.34it/s]
 45%|████▌     | 167594/371472 [2:23:22<16:45:32,  3.38it/s]
 45%|████▌     | 167595/371472 [2:23:23<16:31:54,  3.43it/s]
 45%|████▌     | 167596/371472 [2:23:23<16:35:30,  3.41it/s]
 45%|████▌     | 167597/371472 [2:23:23<16:20:15,  3.47it/s]
 45%|████▌     | 167598/371472 [2:23:24<16:12:22,  3.49it/s]
 45%|████▌     | 167599/371472 [2:23:24<16:39:56,  3.40it/s]
 45%|████▌     | 167600/371472 [2:23:24<17:05:55,  3.31it/s]
                                                            
{'loss': 2.9456, 'learning_rate': 5.942058652416557e-07, 'epoch': 7.22}
+
 45%|████▌     | 167600/371472 [2:23:24<17:05:55,  3.31it/s]
 45%|████▌     | 167601/371472 [2:23:25<17:01:31,  3.33it/s]
 45%|████▌     | 167602/371472 [2:23:25<17:00:31,  3.33it/s]
 45%|████▌     | 167603/371472 [2:23:25<17:14:15,  3.29it/s]
 45%|████▌     | 167604/371472 [2:23:25<16:58:18,  3.34it/s]
 45%|████▌     | 167605/371472 [2:23:26<16:50:14,  3.36it/s]
 45%|████▌     | 167606/371472 [2:23:26<17:05:52,  3.31it/s]
 45%|████▌     | 167607/371472 [2:23:26<16:38:27,  3.40it/s]
 45%|████▌     | 167608/371472 [2:23:27<16:45:55,  3.38it/s]
 45%|████▌     | 167609/371472 [2:23:27<16:29:28,  3.43it/s]
 45%|████▌     | 167610/371472 [2:23:27<16:43:14,  3.39it/s]
 45%|████▌     | 167611/371472 [2:23:28<16:59:53,  3.33it/s]
 45%|████▌     | 167612/371472 [2:23:28<16:36:42,  3.41it/s]
 45%|████▌     | 167613/371472 [2:23:28<16:32:52,  3.42it/s]
 45%|████▌     | 167614/371472 [2:23:28<16:51:56,  3.36it/s]
 45%|████▌     | 167615/371472 [2:23:29<17:51:09,  3.17it/s]
 45%|████▌     | 167616/371472 [2:23:29<17:55:01,  3.16it/s]
 45%|████▌     | 167617/371472 [2:23:29<17:28:11,  3.24it/s]
 45%|████▌     | 167618/371472 [2:23:30<17:49:27,  3.18it/s]
 45%|████▌     | 167619/371472 [2:23:30<18:26:06,  3.07it/s]
 45%|████▌     | 167620/371472 [2:23:30<17:55:16,  3.16it/s]
                                                            
{'loss': 2.7533, 'learning_rate': 5.941573832661768e-07, 'epoch': 7.22}
+
 45%|████▌     | 167620/371472 [2:23:30<17:55:16,  3.16it/s]
 45%|████▌     | 167621/371472 [2:23:31<17:16:38,  3.28it/s]
 45%|████▌     | 167622/371472 [2:23:31<17:32:29,  3.23it/s]
 45%|████▌     | 167623/371472 [2:23:31<17:03:35,  3.32it/s]
 45%|████▌     | 167624/371472 [2:23:32<16:46:45,  3.37it/s]
 45%|████▌     | 167625/371472 [2:23:32<17:02:36,  3.32it/s]
 45%|████▌     | 167626/371472 [2:23:32<17:22:13,  3.26it/s]
 45%|████▌     | 167627/371472 [2:23:32<16:41:31,  3.39it/s]
 45%|████▌     | 167628/371472 [2:23:33<17:07:29,  3.31it/s]
 45%|████▌     | 167629/371472 [2:23:33<17:48:39,  3.18it/s]
 45%|████▌     | 167630/371472 [2:23:33<18:30:02,  3.06it/s]
 45%|████▌     | 167631/371472 [2:23:34<18:01:39,  3.14it/s]
 45%|████▌     | 167632/371472 [2:23:34<18:04:26,  3.13it/s]
 45%|████▌     | 167633/371472 [2:23:34<18:14:28,  3.10it/s]
 45%|████▌     | 167634/371472 [2:23:35<17:51:21,  3.17it/s]
 45%|████▌     | 167635/371472 [2:23:35<17:25:43,  3.25it/s]
 45%|████▌     | 167636/371472 [2:23:35<16:53:12,  3.35it/s]
 45%|████▌     | 167637/371472 [2:23:36<16:47:23,  3.37it/s]
 45%|████▌     | 167638/371472 [2:23:36<16:47:57,  3.37it/s]
 45%|████▌     | 167639/371472 [2:23:36<16:39:37,  3.40it/s]
 45%|████▌     | 167640/371472 [2:23:36<16:24:44,  3.45it/s]
                                                            
{'loss': 2.9833, 'learning_rate': 5.941089012906978e-07, 'epoch': 7.22}
+
 45%|████▌     | 167640/371472 [2:23:36<16:24:44,  3.45it/s]
 45%|████▌     | 167641/371472 [2:23:37<16:43:51,  3.38it/s]
 45%|████▌     | 167642/371472 [2:23:37<17:17:21,  3.27it/s]
 45%|████▌     | 167643/371472 [2:23:37<17:25:18,  3.25it/s]
 45%|████▌     | 167644/371472 [2:23:38<17:20:32,  3.26it/s]
 45%|████▌     | 167645/371472 [2:23:38<17:24:29,  3.25it/s]
 45%|████▌     | 167646/371472 [2:23:38<16:53:11,  3.35it/s]
 45%|████▌     | 167647/371472 [2:23:39<17:26:03,  3.25it/s]
 45%|████▌     | 167648/371472 [2:23:39<17:04:27,  3.32it/s]
 45%|████▌     | 167649/371472 [2:23:39<16:38:51,  3.40it/s]
 45%|████▌     | 167650/371472 [2:23:39<16:43:25,  3.39it/s]
 45%|████▌     | 167651/371472 [2:23:40<16:50:35,  3.36it/s]
 45%|████▌     | 167652/371472 [2:23:40<16:46:00,  3.38it/s]
 45%|████▌     | 167653/371472 [2:23:40<17:13:54,  3.29it/s]
 45%|████▌     | 167654/371472 [2:23:41<17:13:02,  3.29it/s]
 45%|████▌     | 167655/371472 [2:23:41<16:49:29,  3.37it/s]
 45%|████▌     | 167656/371472 [2:23:41<16:44:26,  3.38it/s]
 45%|████▌     | 167657/371472 [2:23:42<16:58:08,  3.34it/s]
 45%|████▌     | 167658/371472 [2:23:42<17:47:41,  3.18it/s]
 45%|████▌     | 167659/371472 [2:23:42<17:23:11,  3.26it/s]
 45%|████▌     | 167660/371472 [2:23:43<18:30:24,  3.06it/s]
                                                            
{'loss': 2.7963, 'learning_rate': 5.94060419315219e-07, 'epoch': 7.22}
+
 45%|████▌     | 167660/371472 [2:23:43<18:30:24,  3.06it/s]
 45%|████▌     | 167661/371472 [2:23:43<18:42:04,  3.03it/s]
 45%|████▌     | 167662/371472 [2:23:43<19:21:43,  2.92it/s]
 45%|████▌     | 167663/371472 [2:23:44<18:18:06,  3.09it/s]
 45%|████▌     | 167664/371472 [2:23:44<19:50:57,  2.85it/s]
 45%|████▌     | 167665/371472 [2:23:44<19:08:20,  2.96it/s]
 45%|████▌     | 167666/371472 [2:23:45<19:13:56,  2.94it/s]
 45%|████▌     | 167667/371472 [2:23:45<19:12:51,  2.95it/s]
 45%|████▌     | 167668/371472 [2:23:45<18:35:10,  3.05it/s]
 45%|████▌     | 167669/371472 [2:23:46<18:28:14,  3.06it/s]
 45%|████▌     | 167670/371472 [2:23:46<17:37:04,  3.21it/s]
 45%|████▌     | 167671/371472 [2:23:46<17:16:15,  3.28it/s]
 45%|████▌     | 167672/371472 [2:23:46<16:32:23,  3.42it/s]
 45%|████▌     | 167673/371472 [2:23:47<16:16:38,  3.48it/s]
 45%|████▌     | 167674/371472 [2:23:47<17:26:50,  3.24it/s]
 45%|████▌     | 167675/371472 [2:23:47<18:10:56,  3.11it/s]
 45%|████▌     | 167676/371472 [2:23:48<18:06:17,  3.13it/s]
 45%|████▌     | 167677/371472 [2:23:48<18:27:34,  3.07it/s]
 45%|████▌     | 167678/371472 [2:23:48<18:11:24,  3.11it/s]
 45%|████▌     | 167679/371472 [2:23:49<17:28:13,  3.24it/s]
 45%|████▌     | 167680/371472 [2:23:49<18:28:32,  3.06it/s]
                                                            
{'loss': 2.9361, 'learning_rate': 5.940119373397402e-07, 'epoch': 7.22}
+
 45%|████▌     | 167680/371472 [2:23:49<18:28:32,  3.06it/s]
 45%|████▌     | 167681/371472 [2:23:49<17:56:30,  3.16it/s]
 45%|████▌     | 167682/371472 [2:23:50<18:32:54,  3.05it/s]
 45%|████▌     | 167683/371472 [2:23:50<18:20:12,  3.09it/s]
 45%|████▌     | 167684/371472 [2:23:50<17:30:34,  3.23it/s]
 45%|████▌     | 167685/371472 [2:23:51<18:01:28,  3.14it/s]
 45%|████▌     | 167686/371472 [2:23:51<17:59:41,  3.15it/s]
 45%|████▌     | 167687/371472 [2:23:51<17:32:39,  3.23it/s]
 45%|████▌     | 167688/371472 [2:23:51<17:30:54,  3.23it/s]
 45%|████▌     | 167689/371472 [2:23:52<17:16:52,  3.28it/s]
 45%|████▌     | 167690/371472 [2:23:52<16:57:36,  3.34it/s]
 45%|████▌     | 167691/371472 [2:23:52<17:09:04,  3.30it/s]
 45%|████▌     | 167692/371472 [2:23:53<16:39:39,  3.40it/s]
 45%|████▌     | 167693/371472 [2:23:53<16:53:24,  3.35it/s]
 45%|████▌     | 167694/371472 [2:23:53<17:11:19,  3.29it/s]
 45%|████▌     | 167695/371472 [2:23:54<16:53:11,  3.35it/s]
 45%|████▌     | 167696/371472 [2:23:54<18:33:22,  3.05it/s]
 45%|████▌     | 167697/371472 [2:23:54<17:55:41,  3.16it/s]
 45%|████▌     | 167698/371472 [2:23:55<17:46:00,  3.19it/s]
 45%|████▌     | 167699/371472 [2:23:55<17:43:38,  3.19it/s]
 45%|████▌     | 167700/371472 [2:23:55<17:55:10,  3.16it/s]
                                                            
{'loss': 3.0236, 'learning_rate': 5.939634553642612e-07, 'epoch': 7.22}
+
 45%|████▌     | 167700/371472 [2:23:55<17:55:10,  3.16it/s]
 45%|████▌     | 167701/371472 [2:23:55<17:35:14,  3.22it/s]
 45%|████▌     | 167702/371472 [2:23:56<18:15:47,  3.10it/s]
 45%|████▌     | 167703/371472 [2:23:56<17:28:20,  3.24it/s]
 45%|████▌     | 167704/371472 [2:23:56<17:16:10,  3.28it/s]
 45%|████▌     | 167705/371472 [2:23:57<16:57:35,  3.34it/s]
 45%|████▌     | 167706/371472 [2:23:57<16:30:09,  3.43it/s]
 45%|████▌     | 167707/371472 [2:23:57<17:11:53,  3.29it/s]
 45%|████▌     | 167708/371472 [2:23:58<17:29:00,  3.24it/s]
 45%|████▌     | 167709/371472 [2:23:58<16:51:27,  3.36it/s]
 45%|████▌     | 167710/371472 [2:23:58<18:35:06,  3.05it/s]
 45%|████▌     | 167711/371472 [2:23:59<17:41:08,  3.20it/s]
 45%|████▌     | 167712/371472 [2:23:59<17:40:01,  3.20it/s]
 45%|████▌     | 167713/371472 [2:23:59<17:16:25,  3.28it/s]
 45%|████▌     | 167714/371472 [2:24:00<17:51:05,  3.17it/s]
 45%|████▌     | 167715/371472 [2:24:00<17:27:54,  3.24it/s]
 45%|████▌     | 167716/371472 [2:24:00<17:17:14,  3.27it/s]
 45%|████▌     | 167717/371472 [2:24:00<17:11:58,  3.29it/s]
 45%|████▌     | 167718/371472 [2:24:01<19:28:11,  2.91it/s]
 45%|████▌     | 167719/371472 [2:24:01<18:27:48,  3.07it/s]
 45%|████▌     | 167720/371472 [2:24:01<17:57:17,  3.15it/s]
                                                            
{'loss': 3.0724, 'learning_rate': 5.939149733887822e-07, 'epoch': 7.22}
+
 45%|████▌     | 167720/371472 [2:24:01<17:57:17,  3.15it/s]
 45%|████▌     | 167721/371472 [2:24:02<17:04:33,  3.31it/s]
 45%|████▌     | 167722/371472 [2:24:02<17:07:52,  3.30it/s]
 45%|████▌     | 167723/371472 [2:24:02<17:06:18,  3.31it/s]
 45%|████▌     | 167724/371472 [2:24:03<16:54:36,  3.35it/s]
 45%|████▌     | 167725/371472 [2:24:03<17:45:47,  3.19it/s]
 45%|████▌     | 167726/371472 [2:24:03<18:32:34,  3.05it/s]
 45%|████▌     | 167727/371472 [2:24:04<18:06:30,  3.13it/s]
 45%|████▌     | 167728/371472 [2:24:04<17:55:15,  3.16it/s]
 45%|████▌     | 167729/371472 [2:24:04<17:16:03,  3.28it/s]
 45%|████▌     | 167730/371472 [2:24:05<17:28:26,  3.24it/s]
 45%|████▌     | 167731/371472 [2:24:05<16:59:31,  3.33it/s]
 45%|████▌     | 167732/371472 [2:24:05<17:16:43,  3.28it/s]
 45%|████▌     | 167733/371472 [2:24:05<17:23:40,  3.25it/s]
 45%|████▌     | 167734/371472 [2:24:06<16:54:15,  3.35it/s]
 45%|████▌     | 167735/371472 [2:24:06<17:02:16,  3.32it/s]
 45%|████▌     | 167736/371472 [2:24:06<17:01:42,  3.32it/s]
 45%|████▌     | 167737/371472 [2:24:07<16:51:35,  3.36it/s]
 45%|████▌     | 167738/371472 [2:24:07<16:45:35,  3.38it/s]
 45%|████▌     | 167739/371472 [2:24:07<16:24:27,  3.45it/s]
 45%|████▌     | 167740/371472 [2:24:07<16:47:33,  3.37it/s]
                                                            
{'loss': 2.9369, 'learning_rate': 5.938664914133034e-07, 'epoch': 7.22}
+
 45%|████▌     | 167740/371472 [2:24:07<16:47:33,  3.37it/s]
 45%|████▌     | 167741/371472 [2:24:08<16:48:17,  3.37it/s]
 45%|████▌     | 167742/371472 [2:24:08<17:01:50,  3.32it/s]
 45%|████▌     | 167743/371472 [2:24:08<16:51:39,  3.36it/s]
 45%|████▌     | 167744/371472 [2:24:09<16:32:03,  3.42it/s]
 45%|████▌     | 167745/371472 [2:24:09<16:50:22,  3.36it/s]
 45%|████▌     | 167746/371472 [2:24:09<16:39:11,  3.40it/s]
 45%|████▌     | 167747/371472 [2:24:10<16:35:04,  3.41it/s]
 45%|████▌     | 167748/371472 [2:24:10<16:22:23,  3.46it/s]
 45%|████▌     | 167749/371472 [2:24:10<16:31:56,  3.42it/s]
 45%|████▌     | 167750/371472 [2:24:10<16:17:23,  3.47it/s]
 45%|████▌     | 167751/371472 [2:24:11<16:27:59,  3.44it/s]
 45%|████▌     | 167752/371472 [2:24:11<16:15:21,  3.48it/s]
 45%|████▌     | 167753/371472 [2:24:11<16:28:04,  3.44it/s]
 45%|████▌     | 167754/371472 [2:24:12<16:06:08,  3.51it/s]
 45%|████▌     | 167755/371472 [2:24:12<16:17:38,  3.47it/s]
 45%|████▌     | 167756/371472 [2:24:12<16:51:32,  3.36it/s]
 45%|████▌     | 167757/371472 [2:24:12<17:06:02,  3.31it/s]
 45%|████▌     | 167758/371472 [2:24:13<17:43:12,  3.19it/s]
 45%|████▌     | 167759/371472 [2:24:13<19:31:19,  2.90it/s]
 45%|████▌     | 167760/371472 [2:24:14<18:47:15,  3.01it/s]
                                                            
{'loss': 3.022, 'learning_rate': 5.938180094378246e-07, 'epoch': 7.23}
+
 45%|████▌     | 167760/371472 [2:24:14<18:47:15,  3.01it/s]
 45%|████▌     | 167761/371472 [2:24:14<18:07:37,  3.12it/s]
 45%|████▌     | 167762/371472 [2:24:14<17:23:00,  3.26it/s]
 45%|████▌     | 167763/371472 [2:24:14<16:59:35,  3.33it/s]
 45%|████▌     | 167764/371472 [2:24:15<17:31:26,  3.23it/s]
 45%|████▌     | 167765/371472 [2:24:15<17:08:20,  3.30it/s]
 45%|████▌     | 167766/371472 [2:24:15<16:41:15,  3.39it/s]
 45%|████▌     | 167767/371472 [2:24:16<18:42:28,  3.02it/s]
 45%|████▌     | 167768/371472 [2:24:16<17:47:06,  3.18it/s]
 45%|████▌     | 167769/371472 [2:24:16<17:20:46,  3.26it/s]
 45%|████▌     | 167770/371472 [2:24:17<17:16:28,  3.28it/s]
 45%|████▌     | 167771/371472 [2:24:17<17:54:17,  3.16it/s]
 45%|████▌     | 167772/371472 [2:24:17<17:30:53,  3.23it/s]
 45%|████▌     | 167773/371472 [2:24:18<17:44:12,  3.19it/s]
 45%|████▌     | 167774/371472 [2:24:18<17:01:36,  3.32it/s]
 45%|████▌     | 167775/371472 [2:24:18<17:13:32,  3.28it/s]
 45%|████▌     | 167776/371472 [2:24:18<18:10:59,  3.11it/s]
 45%|████▌     | 167777/371472 [2:24:19<18:00:48,  3.14it/s]
 45%|████▌     | 167778/371472 [2:24:19<17:49:53,  3.17it/s]
 45%|████▌     | 167779/371472 [2:24:19<17:44:45,  3.19it/s]
 45%|████▌     | 167780/371472 [2:24:20<18:00:27,  3.14it/s]
                                                            
{'loss': 2.9464, 'learning_rate': 5.937695274623457e-07, 'epoch': 7.23}
+
 45%|████▌     | 167780/371472 [2:24:20<18:00:27,  3.14it/s]
 45%|████▌     | 167781/371472 [2:24:20<17:25:10,  3.25it/s]
 45%|████▌     | 167782/371472 [2:24:20<17:13:11,  3.29it/s]
 45%|████▌     | 167783/371472 [2:24:21<18:21:41,  3.08it/s]
 45%|████▌     | 167784/371472 [2:24:21<18:03:07,  3.13it/s]
 45%|████▌     | 167785/371472 [2:24:21<18:21:43,  3.08it/s]
 45%|████▌     | 167786/371472 [2:24:22<18:34:11,  3.05it/s]
 45%|████▌     | 167787/371472 [2:24:22<18:28:53,  3.06it/s]
 45%|████▌     | 167788/371472 [2:24:22<17:25:38,  3.25it/s]
 45%|████▌     | 167789/371472 [2:24:23<17:39:29,  3.20it/s]
 45%|████▌     | 167790/371472 [2:24:23<17:09:06,  3.30it/s]
 45%|████▌     | 167791/371472 [2:24:23<17:23:22,  3.25it/s]
 45%|████▌     | 167792/371472 [2:24:23<17:08:37,  3.30it/s]
 45%|████▌     | 167793/371472 [2:24:24<16:48:26,  3.37it/s]
 45%|████▌     | 167794/371472 [2:24:24<16:40:24,  3.39it/s]
 45%|████▌     | 167795/371472 [2:24:24<16:30:45,  3.43it/s]
 45%|████▌     | 167796/371472 [2:24:25<16:42:13,  3.39it/s]
 45%|████▌     | 167797/371472 [2:24:25<16:39:26,  3.40it/s]
 45%|████▌     | 167798/371472 [2:24:25<16:27:08,  3.44it/s]
 45%|████▌     | 167799/371472 [2:24:26<17:20:21,  3.26it/s]
 45%|████▌     | 167800/371472 [2:24:26<17:21:02,  3.26it/s]
                                                            
{'loss': 2.8952, 'learning_rate': 5.937210454868667e-07, 'epoch': 7.23}
+
 45%|████▌     | 167800/371472 [2:24:26<17:21:02,  3.26it/s]
 45%|████▌     | 167801/371472 [2:24:26<17:05:35,  3.31it/s]
 45%|████▌     | 167802/371472 [2:24:26<17:03:29,  3.32it/s]
 45%|████▌     | 167803/371472 [2:24:27<16:59:56,  3.33it/s]
 45%|████▌     | 167804/371472 [2:24:27<17:19:01,  3.27it/s]
 45%|████▌     | 167805/371472 [2:24:27<17:30:55,  3.23it/s]
 45%|████▌     | 167806/371472 [2:24:28<17:27:20,  3.24it/s]
 45%|████▌     | 167807/371472 [2:24:28<17:12:25,  3.29it/s]
 45%|████▌     | 167808/371472 [2:24:28<17:35:12,  3.22it/s]
 45%|████▌     | 167809/371472 [2:24:29<17:07:22,  3.30it/s]
 45%|████▌     | 167810/371472 [2:24:29<17:14:03,  3.28it/s]
 45%|████▌     | 167811/371472 [2:24:29<17:15:27,  3.28it/s]
 45%|████▌     | 167812/371472 [2:24:29<17:00:16,  3.33it/s]
 45%|████▌     | 167813/371472 [2:24:30<16:45:23,  3.38it/s]
 45%|████▌     | 167814/371472 [2:24:30<16:54:53,  3.34it/s]
 45%|████▌     | 167815/371472 [2:24:30<16:57:40,  3.34it/s]
 45%|████▌     | 167816/371472 [2:24:31<16:37:04,  3.40it/s]
 45%|████▌     | 167817/371472 [2:24:31<16:41:29,  3.39it/s]
 45%|████▌     | 167818/371472 [2:24:31<17:24:10,  3.25it/s]
 45%|████▌     | 167819/371472 [2:24:32<17:04:59,  3.31it/s]
 45%|████▌     | 167820/371472 [2:24:32<16:46:41,  3.37it/s]
                                                            
{'loss': 2.9995, 'learning_rate': 5.936725635113879e-07, 'epoch': 7.23}
+
 45%|████▌     | 167820/371472 [2:24:32<16:46:41,  3.37it/s]
 45%|████▌     | 167821/371472 [2:24:32<17:26:14,  3.24it/s]
 45%|████▌     | 167822/371472 [2:24:33<18:52:42,  3.00it/s]
 45%|████▌     | 167823/371472 [2:24:33<20:12:12,  2.80it/s]
 45%|████▌     | 167824/371472 [2:24:33<19:31:47,  2.90it/s]
 45%|████▌     | 167825/371472 [2:24:34<19:11:34,  2.95it/s]
 45%|████▌     | 167826/371472 [2:24:34<18:17:35,  3.09it/s]
 45%|████▌     | 167827/371472 [2:24:34<18:25:55,  3.07it/s]
 45%|████▌     | 167828/371472 [2:24:35<17:55:29,  3.16it/s]
 45%|████▌     | 167829/371472 [2:24:35<17:55:26,  3.16it/s]
 45%|████▌     | 167830/371472 [2:24:35<17:12:50,  3.29it/s]
 45%|████▌     | 167831/371472 [2:24:35<16:48:46,  3.36it/s]
 45%|████▌     | 167832/371472 [2:24:36<17:11:01,  3.29it/s]
 45%|████▌     | 167833/371472 [2:24:36<16:34:39,  3.41it/s]
 45%|████▌     | 167834/371472 [2:24:36<16:44:30,  3.38it/s]
 45%|████▌     | 167835/371472 [2:24:37<19:25:50,  2.91it/s]
 45%|████▌     | 167836/371472 [2:24:37<18:43:03,  3.02it/s]
 45%|████▌     | 167837/371472 [2:24:37<18:23:32,  3.08it/s]
 45%|████▌     | 167838/371472 [2:24:38<17:50:29,  3.17it/s]
 45%|████▌     | 167839/371472 [2:24:38<17:14:32,  3.28it/s]
 45%|████▌     | 167840/371472 [2:24:38<17:27:22,  3.24it/s]
                                                            
{'loss': 3.0927, 'learning_rate': 5.936240815359089e-07, 'epoch': 7.23}
+
 45%|████▌     | 167840/371472 [2:24:38<17:27:22,  3.24it/s]
 45%|████▌     | 167841/371472 [2:24:39<17:17:18,  3.27it/s]
 45%|████▌     | 167842/371472 [2:24:39<17:07:39,  3.30it/s]
 45%|████▌     | 167843/371472 [2:24:39<17:08:33,  3.30it/s]
 45%|████▌     | 167844/371472 [2:24:39<16:55:08,  3.34it/s]
 45%|████▌     | 167845/371472 [2:24:40<18:09:04,  3.12it/s]
 45%|████▌     | 167846/371472 [2:24:40<17:49:53,  3.17it/s]
 45%|████▌     | 167847/371472 [2:24:40<17:24:05,  3.25it/s]
 45%|████▌     | 167848/371472 [2:24:41<16:56:10,  3.34it/s]
 45%|████▌     | 167849/371472 [2:24:41<18:46:50,  3.01it/s]
 45%|████▌     | 167850/371472 [2:24:41<18:02:09,  3.14it/s]
 45%|████▌     | 167851/371472 [2:24:42<17:40:02,  3.20it/s]
 45%|████▌     | 167852/371472 [2:24:42<17:18:58,  3.27it/s]
 45%|████▌     | 167853/371472 [2:24:42<18:22:17,  3.08it/s]
 45%|████▌     | 167854/371472 [2:24:43<18:14:22,  3.10it/s]
 45%|████▌     | 167855/371472 [2:24:43<18:25:24,  3.07it/s]
 45%|████▌     | 167856/371472 [2:24:43<17:45:11,  3.19it/s]
 45%|████▌     | 167857/371472 [2:24:44<17:46:25,  3.18it/s]
 45%|████▌     | 167858/371472 [2:24:44<18:03:00,  3.13it/s]
 45%|████▌     | 167859/371472 [2:24:44<18:27:32,  3.06it/s]
 45%|████▌     | 167860/371472 [2:24:45<18:19:22,  3.09it/s]
                                                            
{'loss': 2.8791, 'learning_rate': 5.935755995604301e-07, 'epoch': 7.23}
+
 45%|████▌     | 167860/371472 [2:24:45<18:19:22,  3.09it/s]
 45%|████▌     | 167861/371472 [2:24:45<18:29:50,  3.06it/s]
 45%|████▌     | 167862/371472 [2:24:45<17:45:07,  3.19it/s]
 45%|████▌     | 167863/371472 [2:24:46<17:09:26,  3.30it/s]
 45%|████▌     | 167864/371472 [2:24:46<17:10:18,  3.29it/s]
 45%|████▌     | 167865/371472 [2:24:46<19:13:51,  2.94it/s]
 45%|████▌     | 167866/371472 [2:24:47<18:35:09,  3.04it/s]
 45%|████▌     | 167867/371472 [2:24:47<17:47:01,  3.18it/s]
 45%|████▌     | 167868/371472 [2:24:47<17:05:28,  3.31it/s]
 45%|████▌     | 167869/371472 [2:24:47<16:40:24,  3.39it/s]
 45%|████▌     | 167870/371472 [2:24:48<17:01:39,  3.32it/s]
 45%|████▌     | 167871/371472 [2:24:48<17:13:19,  3.28it/s]
 45%|████▌     | 167872/371472 [2:24:48<18:11:42,  3.11it/s]
 45%|████▌     | 167873/371472 [2:24:49<17:32:48,  3.22it/s]
 45%|████▌     | 167874/371472 [2:24:49<17:22:00,  3.26it/s]
 45%|████▌     | 167875/371472 [2:24:49<17:22:10,  3.26it/s]
 45%|████▌     | 167876/371472 [2:24:50<17:06:47,  3.30it/s]
 45%|████▌     | 167877/371472 [2:24:50<17:51:59,  3.17it/s]
 45%|████▌     | 167878/371472 [2:24:50<17:23:44,  3.25it/s]
 45%|████▌     | 167879/371472 [2:24:51<18:10:51,  3.11it/s]
 45%|████▌     | 167880/371472 [2:24:51<17:38:05,  3.21it/s]
                                                            
{'loss': 3.0313, 'learning_rate': 5.935271175849511e-07, 'epoch': 7.23}
+
 45%|████▌     | 167880/371472 [2:24:51<17:38:05,  3.21it/s]
 45%|████▌     | 167881/371472 [2:24:51<17:48:32,  3.18it/s]
 45%|████▌     | 167882/371472 [2:24:51<17:32:20,  3.22it/s]
 45%|████▌     | 167883/371472 [2:24:52<17:36:51,  3.21it/s]
 45%|████▌     | 167884/371472 [2:24:52<17:22:21,  3.26it/s]
 45%|████▌     | 167885/371472 [2:24:52<17:10:16,  3.29it/s]
 45%|████▌     | 167886/371472 [2:24:53<18:41:42,  3.02it/s]
 45%|████▌     | 167887/371472 [2:24:53<18:47:55,  3.01it/s]
 45%|████▌     | 167888/371472 [2:24:53<18:21:02,  3.08it/s]
 45%|████▌     | 167889/371472 [2:24:54<18:38:13,  3.03it/s]
 45%|████▌     | 167890/371472 [2:24:54<17:59:51,  3.14it/s]
 45%|████▌     | 167891/371472 [2:24:54<17:49:35,  3.17it/s]
 45%|████▌     | 167892/371472 [2:24:55<17:30:02,  3.23it/s]
 45%|████▌     | 167893/371472 [2:24:55<17:04:51,  3.31it/s]
 45%|████▌     | 167894/371472 [2:24:55<16:45:54,  3.37it/s]
 45%|████▌     | 167895/371472 [2:24:55<17:01:49,  3.32it/s]
 45%|████▌     | 167896/371472 [2:24:56<16:44:33,  3.38it/s]
 45%|████▌     | 167897/371472 [2:24:56<16:34:17,  3.41it/s]
 45%|████▌     | 167898/371472 [2:24:56<16:36:10,  3.41it/s]
 45%|████▌     | 167899/371472 [2:24:57<17:26:33,  3.24it/s]
 45%|████▌     | 167900/371472 [2:24:57<16:50:08,  3.36it/s]
                                                            
{'loss': 2.9859, 'learning_rate': 5.934786356094723e-07, 'epoch': 7.23}
+
 45%|████▌     | 167900/371472 [2:24:57<16:50:08,  3.36it/s]
 45%|████▌     | 167901/371472 [2:24:57<17:42:45,  3.19it/s]
 45%|████▌     | 167902/371472 [2:24:58<17:09:18,  3.30it/s]
 45%|████▌     | 167903/371472 [2:24:58<17:13:01,  3.28it/s]
 45%|████▌     | 167904/371472 [2:24:58<17:16:50,  3.27it/s]
 45%|████▌     | 167905/371472 [2:24:59<17:07:35,  3.30it/s]
 45%|████▌     | 167906/371472 [2:24:59<17:19:00,  3.27it/s]
 45%|████▌     | 167907/371472 [2:24:59<17:06:35,  3.30it/s]
 45%|████▌     | 167908/371472 [2:24:59<17:17:05,  3.27it/s]
 45%|████▌     | 167909/371472 [2:25:00<16:47:10,  3.37it/s]
 45%|████▌     | 167910/371472 [2:25:00<16:46:20,  3.37it/s]
 45%|████▌     | 167911/371472 [2:25:00<17:04:23,  3.31it/s]
 45%|████▌     | 167912/371472 [2:25:01<17:02:01,  3.32it/s]
 45%|████▌     | 167913/371472 [2:25:01<17:01:56,  3.32it/s]
 45%|████▌     | 167914/371472 [2:25:01<17:17:27,  3.27it/s]
 45%|████▌     | 167915/371472 [2:25:02<17:04:45,  3.31it/s]
 45%|████▌     | 167916/371472 [2:25:02<16:37:16,  3.40it/s]
 45%|████▌     | 167917/371472 [2:25:02<16:17:12,  3.47it/s]
 45%|████▌     | 167918/371472 [2:25:02<16:33:02,  3.42it/s]
 45%|████▌     | 167919/371472 [2:25:03<16:12:24,  3.49it/s]
 45%|████▌     | 167920/371472 [2:25:03<16:07:48,  3.51it/s]
                                                            
{'loss': 3.0214, 'learning_rate': 5.934301536339935e-07, 'epoch': 7.23}
+
 45%|████▌     | 167920/371472 [2:25:03<16:07:48,  3.51it/s]
 45%|████▌     | 167921/371472 [2:25:03<16:32:37,  3.42it/s]
 45%|████▌     | 167922/371472 [2:25:04<17:15:42,  3.28it/s]
 45%|████▌     | 167923/371472 [2:25:04<16:57:10,  3.34it/s]
 45%|████▌     | 167924/371472 [2:25:04<16:52:26,  3.35it/s]
 45%|████▌     | 167925/371472 [2:25:04<17:03:43,  3.31it/s]
 45%|████▌     | 167926/371472 [2:25:05<16:55:12,  3.34it/s]
 45%|████▌     | 167927/371472 [2:25:05<17:38:22,  3.21it/s]
 45%|████▌     | 167928/371472 [2:25:05<17:24:12,  3.25it/s]
 45%|████▌     | 167929/371472 [2:25:06<17:02:40,  3.32it/s]
 45%|████▌     | 167930/371472 [2:25:06<17:14:06,  3.28it/s]
 45%|████▌     | 167931/371472 [2:25:06<16:51:19,  3.35it/s]
 45%|████▌     | 167932/371472 [2:25:07<16:54:52,  3.34it/s]
 45%|████▌     | 167933/371472 [2:25:07<16:58:31,  3.33it/s]
 45%|████▌     | 167934/371472 [2:25:07<16:42:27,  3.38it/s]
 45%|████▌     | 167935/371472 [2:25:07<16:47:06,  3.37it/s]
 45%|████▌     | 167936/371472 [2:25:08<16:28:08,  3.43it/s]
 45%|████▌     | 167937/371472 [2:25:08<16:37:27,  3.40it/s]
 45%|████▌     | 167938/371472 [2:25:08<17:22:59,  3.25it/s]
 45%|████▌     | 167939/371472 [2:25:09<16:48:29,  3.36it/s]
 45%|████▌     | 167940/371472 [2:25:09<16:19:33,  3.46it/s]
                                                            
{'loss': 2.8827, 'learning_rate': 5.933816716585146e-07, 'epoch': 7.23}
+
 45%|████▌     | 167940/371472 [2:25:09<16:19:33,  3.46it/s]
 45%|████▌     | 167941/371472 [2:25:09<17:02:46,  3.32it/s]
 45%|████▌     | 167942/371472 [2:25:10<16:38:43,  3.40it/s]
 45%|████▌     | 167943/371472 [2:25:10<16:26:55,  3.44it/s]
 45%|████▌     | 167944/371472 [2:25:10<16:07:36,  3.51it/s]
 45%|████▌     | 167945/371472 [2:25:10<16:55:11,  3.34it/s]
 45%|████▌     | 167946/371472 [2:25:11<16:40:56,  3.39it/s]
 45%|████▌     | 167947/371472 [2:25:11<17:13:00,  3.28it/s]
 45%|████▌     | 167948/371472 [2:25:11<17:16:00,  3.27it/s]
 45%|█���██▌     | 167949/371472 [2:25:12<16:32:28,  3.42it/s]
 45%|████▌     | 167950/371472 [2:25:12<16:58:39,  3.33it/s]
 45%|████▌     | 167951/371472 [2:25:12<16:37:31,  3.40it/s]
 45%|████▌     | 167952/371472 [2:25:13<17:11:53,  3.29it/s]
 45%|████▌     | 167953/371472 [2:25:13<17:17:51,  3.27it/s]
 45%|████▌     | 167954/371472 [2:25:13<16:43:38,  3.38it/s]
 45%|████▌     | 167955/371472 [2:25:13<16:42:32,  3.38it/s]
 45%|████▌     | 167956/371472 [2:25:14<16:29:24,  3.43it/s]
 45%|████▌     | 167957/371472 [2:25:14<16:53:46,  3.35it/s]
 45%|████▌     | 167958/371472 [2:25:14<17:20:10,  3.26it/s]
 45%|████▌     | 167959/371472 [2:25:15<16:50:05,  3.36it/s]
 45%|████▌     | 167960/371472 [2:25:15<17:27:02,  3.24it/s]
                                                            
{'loss': 3.0012, 'learning_rate': 5.933331896830355e-07, 'epoch': 7.23}
+
 45%|████▌     | 167960/371472 [2:25:15<17:27:02,  3.24it/s]
 45%|████▌     | 167961/371472 [2:25:15<17:27:12,  3.24it/s]
 45%|████▌     | 167962/371472 [2:25:16<17:23:06,  3.25it/s]
 45%|████▌     | 167963/371472 [2:25:16<18:40:37,  3.03it/s]
 45%|████▌     | 167964/371472 [2:25:16<18:18:34,  3.09it/s]
 45%|████▌     | 167965/371472 [2:25:17<17:47:44,  3.18it/s]
 45%|████▌     | 167966/371472 [2:25:17<17:37:17,  3.21it/s]
 45%|████▌     | 167967/371472 [2:25:17<17:21:52,  3.26it/s]
 45%|████▌     | 167968/371472 [2:25:17<17:28:43,  3.23it/s]
 45%|████▌     | 167969/371472 [2:25:18<17:13:09,  3.28it/s]
 45%|████▌     | 167970/371472 [2:25:18<16:39:23,  3.39it/s]
 45%|████▌     | 167971/371472 [2:25:18<16:15:34,  3.48it/s]
 45%|████▌     | 167972/371472 [2:25:19<16:33:43,  3.41it/s]
 45%|████▌     | 167973/371472 [2:25:19<16:37:20,  3.40it/s]
 45%|████▌     | 167974/371472 [2:25:19<17:40:13,  3.20it/s]
 45%|████▌     | 167975/371472 [2:25:20<19:11:54,  2.94it/s]
 45%|████▌     | 167976/371472 [2:25:20<18:55:09,  2.99it/s]
 45%|████▌     | 167977/371472 [2:25:20<18:16:22,  3.09it/s]
 45%|████▌     | 167978/371472 [2:25:21<17:43:21,  3.19it/s]
 45%|████▌     | 167979/371472 [2:25:21<17:32:08,  3.22it/s]
 45%|████▌     | 167980/371472 [2:25:21<17:46:07,  3.18it/s]
                                                            
{'loss': 2.9237, 'learning_rate': 5.932847077075567e-07, 'epoch': 7.24}
+
 45%|████▌     | 167980/371472 [2:25:21<17:46:07,  3.18it/s]
 45%|████▌     | 167981/371472 [2:25:22<17:30:32,  3.23it/s]
 45%|████▌     | 167982/371472 [2:25:22<16:42:08,  3.38it/s]
 45%|████▌     | 167983/371472 [2:25:22<16:25:26,  3.44it/s]
 45%|████▌     | 167984/371472 [2:25:22<17:58:41,  3.14it/s]
 45%|████▌     | 167985/371472 [2:25:23<17:58:05,  3.15it/s]
 45%|████▌     | 167986/371472 [2:25:23<17:46:57,  3.18it/s]
 45%|████▌     | 167987/371472 [2:25:23<17:16:59,  3.27it/s]
 45%|████▌     | 167988/371472 [2:25:24<17:11:30,  3.29it/s]
 45%|████▌     | 167989/371472 [2:25:24<16:57:06,  3.33it/s]
 45%|████▌     | 167990/371472 [2:25:24<16:42:38,  3.38it/s]
 45%|████▌     | 167991/371472 [2:25:25<16:33:19,  3.41it/s]
 45%|████▌     | 167992/371472 [2:25:25<16:17:36,  3.47it/s]
 45%|████▌     | 167993/371472 [2:25:25<17:35:51,  3.21it/s]
 45%|████▌     | 167994/371472 [2:25:25<17:38:52,  3.20it/s]
 45%|████▌     | 167995/371472 [2:25:26<17:49:50,  3.17it/s]
 45%|████▌     | 167996/371472 [2:25:26<17:19:46,  3.26it/s]
 45%|████▌     | 167997/371472 [2:25:26<17:23:43,  3.25it/s]
 45%|████▌     | 167998/371472 [2:25:27<17:29:54,  3.23it/s]
 45%|████▌     | 167999/371472 [2:25:27<16:47:06,  3.37it/s]
 45%|████▌     | 168000/371472 [2:25:27<18:33:01,  3.05it/s]
                                                            
{'loss': 2.9389, 'learning_rate': 5.932362257320779e-07, 'epoch': 7.24}
+
 45%|████▌     | 168000/371472 [2:25:27<18:33:01,  3.05it/s]
 45%|████▌     | 168001/371472 [2:25:28<18:02:54,  3.13it/s]
 45%|████▌     | 168002/371472 [2:25:28<17:42:38,  3.19it/s]
 45%|████▌     | 168003/371472 [2:25:28<17:06:46,  3.30it/s]
 45%|████▌     | 168004/371472 [2:25:29<17:12:01,  3.29it/s]
 45%|████▌     | 168005/371472 [2:25:29<16:51:53,  3.35it/s]
 45%|████▌     | 168006/371472 [2:25:29<18:17:28,  3.09it/s]
 45%|████▌     | 168007/371472 [2:25:29<17:31:18,  3.23it/s]
 45%|████▌     | 168008/371472 [2:25:30<17:08:40,  3.30it/s]
 45%|████▌     | 168009/371472 [2:25:30<16:39:01,  3.39it/s]
 45%|████▌     | 168010/371472 [2:25:30<17:26:08,  3.24it/s]
 45%|████▌     | 168011/371472 [2:25:31<16:56:02,  3.34it/s]
 45%|████▌     | 168012/371472 [2:25:31<16:40:04,  3.39it/s]
 45%|████▌     | 168013/371472 [2:25:31<17:58:52,  3.14it/s]
 45%|████▌     | 168014/371472 [2:25:32<18:13:37,  3.10it/s]
 45%|████▌     | 168015/371472 [2:25:32<17:36:18,  3.21it/s]
 45%|████▌     | 168016/371472 [2:25:32<16:57:34,  3.33it/s]
 45%|████▌     | 168017/371472 [2:25:33<16:33:50,  3.41it/s]
 45%|████▌     | 168018/371472 [2:25:33<16:45:04,  3.37it/s]
 45%|████▌     | 168019/371472 [2:25:33<16:19:57,  3.46it/s]
 45%|████▌     | 168020/371472 [2:25:33<17:22:30,  3.25it/s]
                                                            
{'loss': 3.1977, 'learning_rate': 5.931877437565988e-07, 'epoch': 7.24}
+
 45%|████▌     | 168020/371472 [2:25:33<17:22:30,  3.25it/s]
 45%|████▌     | 168021/371472 [2:25:34<16:54:52,  3.34it/s]
 45%|████▌     | 168022/371472 [2:25:34<17:52:43,  3.16it/s]
 45%|████▌     | 168023/371472 [2:25:34<17:39:17,  3.20it/s]
 45%|████▌     | 168024/371472 [2:25:35<17:08:32,  3.30it/s]
 45%|████▌     | 168025/371472 [2:25:35<16:37:41,  3.40it/s]
 45%|████▌     | 168026/371472 [2:25:35<16:54:41,  3.34it/s]
 45%|████▌     | 168027/371472 [2:25:36<17:19:05,  3.26it/s]
 45%|████▌     | 168028/371472 [2:25:36<17:24:42,  3.25it/s]
 45%|████▌     | 168029/371472 [2:25:36<17:02:52,  3.31it/s]
 45%|████▌     | 168030/371472 [2:25:36<16:45:02,  3.37it/s]
 45%|████▌     | 168031/371472 [2:25:37<16:53:15,  3.35it/s]
 45%|████▌     | 168032/371472 [2:25:37<16:35:24,  3.41it/s]
 45%|████▌     | 168033/371472 [2:25:37<16:36:30,  3.40it/s]
 45%|████▌     | 168034/371472 [2:25:38<19:34:23,  2.89it/s]
 45%|████▌     | 168035/371472 [2:25:38<18:41:00,  3.02it/s]
 45%|████▌     | 168036/371472 [2:25:38<18:13:47,  3.10it/s]
 45%|████▌     | 168037/371472 [2:25:39<17:54:13,  3.16it/s]
 45%|████▌     | 168038/371472 [2:25:39<17:23:02,  3.25it/s]
 45%|████▌     | 168039/371472 [2:25:39<17:11:07,  3.29it/s]
 45%|████▌     | 168040/371472 [2:25:40<16:35:04,  3.41it/s]
                                                            
{'loss': 3.0234, 'learning_rate': 5.9313926178112e-07, 'epoch': 7.24}
+
 45%|████▌     | 168040/371472 [2:25:40<16:35:04,  3.41it/s]
 45%|████▌     | 168041/371472 [2:25:40<16:55:47,  3.34it/s]
 45%|████▌     | 168042/371472 [2:25:40<16:20:33,  3.46it/s]
 45%|████▌     | 168043/371472 [2:25:40<17:30:56,  3.23it/s]
 45%|████▌     | 168044/371472 [2:25:41<17:01:31,  3.32it/s]
 45%|████▌     | 168045/371472 [2:25:41<17:49:50,  3.17it/s]
 45%|████▌     | 168046/371472 [2:25:41<17:22:48,  3.25it/s]
 45%|████▌     | 168047/371472 [2:25:42<18:16:55,  3.09it/s]
 45%|████▌     | 168048/371472 [2:25:42<18:51:11,  3.00it/s]
 45%|████▌     | 168049/371472 [2:25:42<17:59:44,  3.14it/s]
 45%|████▌     | 168050/371472 [2:25:43<17:38:41,  3.20it/s]
 45%|████▌     | 168051/371472 [2:25:43<17:20:28,  3.26it/s]
 45%|████▌     | 168052/371472 [2:25:43<16:55:23,  3.34it/s]
 45%|████▌     | 168053/371472 [2:25:44<16:54:24,  3.34it/s]
 45%|████▌     | 168054/371472 [2:25:44<16:34:02,  3.41it/s]
 45%|████▌     | 168055/371472 [2:25:44<16:53:10,  3.35it/s]
 45%|████▌     | 168056/371472 [2:25:44<16:39:06,  3.39it/s]
 45%|████▌     | 168057/371472 [2:25:45<16:43:53,  3.38it/s]
 45%|████▌     | 168058/371472 [2:25:45<16:33:53,  3.41it/s]
 45%|████▌     | 168059/371472 [2:25:45<18:17:05,  3.09it/s]
 45%|████▌     | 168060/371472 [2:25:46<17:33:47,  3.22it/s]
                                                            
{'loss': 2.8896, 'learning_rate': 5.930907798056412e-07, 'epoch': 7.24}
+
 45%|████▌     | 168060/371472 [2:25:46<17:33:47,  3.22it/s]
 45%|████▌     | 168061/371472 [2:25:46<17:17:59,  3.27it/s]
 45%|████▌     | 168062/371472 [2:25:46<17:13:20,  3.28it/s]
 45%|████▌     | 168063/371472 [2:25:47<16:41:43,  3.38it/s]
 45%|████▌     | 168064/371472 [2:25:47<16:33:46,  3.41it/s]
 45%|████▌     | 168065/371472 [2:25:47<16:57:50,  3.33it/s]
 45%|████▌     | 168066/371472 [2:25:48<18:54:32,  2.99it/s]
 45%|████▌     | 168067/371472 [2:25:48<18:13:58,  3.10it/s]
 45%|████▌     | 168068/371472 [2:25:48<17:59:42,  3.14it/s]
 45%|████▌     | 168069/371472 [2:25:48<17:20:01,  3.26it/s]
 45%|████▌     | 168070/371472 [2:25:49<18:22:12,  3.08it/s]
 45%|████▌     | 168071/371472 [2:25:49<17:38:34,  3.20it/s]
 45%|████▌     | 168072/371472 [2:25:49<16:55:42,  3.34it/s]
 45%|████▌     | 168073/371472 [2:25:50<16:26:19,  3.44it/s]
 45%|████▌     | 168074/371472 [2:25:50<16:12:36,  3.49it/s]
 45%|████▌     | 168075/371472 [2:25:50<16:00:56,  3.53it/s]
 45%|████▌     | 168076/371472 [2:25:51<16:02:58,  3.52it/s]
 45%|████▌     | 168077/371472 [2:25:51<16:08:34,  3.50it/s]
 45%|████▌     | 168078/371472 [2:25:51<16:36:34,  3.40it/s]
 45%|████▌     | 168079/371472 [2:25:51<16:53:00,  3.35it/s]
 45%|████▌     | 168080/371472 [2:25:52<16:24:55,  3.44it/s]
                                                            
{'loss': 2.9428, 'learning_rate': 5.930422978301622e-07, 'epoch': 7.24}
+
 45%|████▌     | 168080/371472 [2:25:52<16:24:55,  3.44it/s]
 45%|████▌     | 168081/371472 [2:25:52<16:15:14,  3.48it/s]
 45%|████▌     | 168082/371472 [2:25:52<16:59:19,  3.33it/s]
 45%|████▌     | 168083/371472 [2:25:53<16:51:04,  3.35it/s]
 45%|████▌     | 168084/371472 [2:25:53<16:37:49,  3.40it/s]
 45%|████▌     | 168085/371472 [2:25:53<16:36:55,  3.40it/s]
 45%|████▌     | 168086/371472 [2:25:53<16:31:58,  3.42it/s]
 45%|████▌     | 168087/371472 [2:25:54<16:32:01,  3.42it/s]
 45%|████▌     | 168088/371472 [2:25:54<16:37:22,  3.40it/s]
 45%|████▌     | 168089/371472 [2:25:54<16:28:06,  3.43it/s]
 45%|████▌     | 168090/371472 [2:25:55<16:32:08,  3.42it/s]
 45%|████▌     | 168091/371472 [2:25:55<16:24:44,  3.44it/s]
 45%|████▌     | 168092/371472 [2:25:55<16:32:48,  3.41it/s]
 45%|████▌     | 168093/371472 [2:25:56<16:24:01,  3.44it/s]
 45%|████▌     | 168094/371472 [2:25:56<16:20:23,  3.46it/s]
 45%|████▌     | 168095/371472 [2:25:56<16:15:25,  3.48it/s]
 45%|████▌     | 168096/371472 [2:25:56<16:12:25,  3.49it/s]
 45%|████▌     | 168097/371472 [2:25:57<16:20:56,  3.46it/s]
 45%|████▌     | 168098/371472 [2:25:57<16:41:02,  3.39it/s]
 45%|████▌     | 168099/371472 [2:25:57<16:44:40,  3.37it/s]
 45%|████▌     | 168100/371472 [2:25:58<17:13:58,  3.28it/s]
                                                            
{'loss': 2.9208, 'learning_rate': 5.929938158546832e-07, 'epoch': 7.24}
+
 45%|████▌     | 168100/371472 [2:25:58<17:13:58,  3.28it/s]
 45%|████▌     | 168101/371472 [2:25:58<17:21:53,  3.25it/s]
 45%|████▌     | 168102/371472 [2:25:58<17:02:47,  3.31it/s]
 45%|████▌     | 168103/371472 [2:25:59<17:15:40,  3.27it/s]
 45%|████▌     | 168104/371472 [2:25:59<18:43:51,  3.02it/s]
 45%|████▌     | 168105/371472 [2:25:59<18:43:03,  3.02it/s]
 45%|████▌     | 168106/371472 [2:26:00<17:53:20,  3.16it/s]
 45%|████▌     | 168107/371472 [2:26:00<17:53:05,  3.16it/s]
 45%|████▌     | 168108/371472 [2:26:00<17:23:14,  3.25it/s]
 45%|████▌     | 168109/371472 [2:26:00<17:10:52,  3.29it/s]
 45%|████▌     | 168110/371472 [2:26:01<17:12:14,  3.28it/s]
 45%|████▌     | 168111/371472 [2:26:01<16:42:57,  3.38it/s]
 45%|████▌     | 168112/371472 [2:26:01<16:32:23,  3.42it/s]
 45%|████▌     | 168113/371472 [2:26:02<16:26:50,  3.43it/s]
 45%|████▌     | 168114/371472 [2:26:02<16:23:25,  3.45it/s]
 45%|████▌     | 168115/371472 [2:26:02<16:26:02,  3.44it/s]
 45%|████▌     | 168116/371472 [2:26:02<16:28:43,  3.43it/s]
 45%|████▌     | 168117/371472 [2:26:03<16:10:01,  3.49it/s]
 45%|████▌     | 168118/371472 [2:26:03<16:15:34,  3.47it/s]
 45%|████▌     | 168119/371472 [2:26:03<17:25:26,  3.24it/s]
 45%|████▌     | 168120/371472 [2:26:04<16:55:52,  3.34it/s]
                                                            
{'loss': 3.0968, 'learning_rate': 5.929453338792044e-07, 'epoch': 7.24}
+
 45%|████▌     | 168120/371472 [2:26:04<16:55:52,  3.34it/s]
 45%|████▌     | 168121/371472 [2:26:04<18:02:53,  3.13it/s]
 45%|████▌     | 168122/371472 [2:26:04<17:50:51,  3.16it/s]
 45%|████▌     | 168123/371472 [2:26:05<16:54:24,  3.34it/s]
 45%|████▌     | 168124/371472 [2:26:05<16:32:21,  3.42it/s]
 45%|████▌     | 168125/371472 [2:26:05<16:20:18,  3.46it/s]
 45%|████▌     | 168126/371472 [2:26:05<16:32:32,  3.41it/s]
 45%|████▌     | 168127/371472 [2:26:06<16:31:53,  3.42it/s]
 45%|████▌     | 168128/371472 [2:26:06<16:08:21,  3.50it/s]
 45%|████▌     | 168129/371472 [2:26:06<16:51:01,  3.35it/s]
 45%|████▌     | 168130/371472 [2:26:07<17:57:57,  3.14it/s]
 45%|████▌     | 168131/371472 [2:26:07<20:03:14,  2.82it/s]
 45%|████▌     | 168132/371472 [2:26:07<18:53:10,  2.99it/s]
 45%|████▌     | 168133/371472 [2:26:08<18:31:36,  3.05it/s]
 45%|████▌     | 168134/371472 [2:26:08<18:09:07,  3.11it/s]
 45%|████▌     | 168135/371472 [2:26:08<17:43:40,  3.19it/s]
 45%|████▌     | 168136/371472 [2:26:09<17:16:40,  3.27it/s]
 45%|████▌     | 168137/371472 [2:26:09<17:05:41,  3.30it/s]
 45%|████▌     | 168138/371472 [2:26:09<17:43:56,  3.19it/s]
 45%|████▌     | 168139/371472 [2:26:10<17:07:22,  3.30it/s]
 45%|████▌     | 168140/371472 [2:26:10<17:15:27,  3.27it/s]
                                                            
{'loss': 2.8931, 'learning_rate': 5.928968519037256e-07, 'epoch': 7.24}
+
 45%|████▌     | 168140/371472 [2:26:10<17:15:27,  3.27it/s]
 45%|████▌     | 168141/371472 [2:26:10<16:43:51,  3.38it/s]
 45%|████▌     | 168142/371472 [2:26:10<16:42:48,  3.38it/s]
 45%|████▌     | 168143/371472 [2:26:11<16:42:35,  3.38it/s]
 45%|████▌     | 168144/371472 [2:26:11<16:38:21,  3.39it/s]
 45%|████▌     | 168145/371472 [2:26:11<16:23:11,  3.45it/s]
 45%|████▌     | 168146/371472 [2:26:12<16:14:00,  3.48it/s]
 45%|████▌     | 168147/371472 [2:26:12<16:10:41,  3.49it/s]
 45%|████▌     | 168148/371472 [2:26:12<16:08:48,  3.50it/s]
 45%|████▌     | 168149/371472 [2:26:12<15:54:10,  3.55it/s]
 45%|████▌     | 168150/371472 [2:26:13<15:56:27,  3.54it/s]
 45%|████▌     | 168151/371472 [2:26:13<15:57:09,  3.54it/s]
 45%|████▌     | 168152/371472 [2:26:13<16:21:21,  3.45it/s]
 45%|████▌     | 168153/371472 [2:26:14<16:20:58,  3.45it/s]
 45%|████▌     | 168154/371472 [2:26:14<18:07:58,  3.11it/s]
 45%|████▌     | 168155/371472 [2:26:14<17:40:45,  3.19it/s]
 45%|████▌     | 168156/371472 [2:26:15<17:15:16,  3.27it/s]
 45%|████▌     | 168157/371472 [2:26:15<17:04:21,  3.31it/s]
 45%|████▌     | 168158/371472 [2:26:15<17:39:10,  3.20it/s]
 45%|████▌     | 168159/371472 [2:26:15<17:15:52,  3.27it/s]
 45%|████▌     | 168160/371472 [2:26:16<16:56:27,  3.33it/s]
                                                            
{'loss': 2.9136, 'learning_rate': 5.928483699282467e-07, 'epoch': 7.24}
+
 45%|████▌     | 168160/371472 [2:26:16<16:56:27,  3.33it/s]
 45%|████▌     | 168161/371472 [2:26:16<17:00:01,  3.32it/s]
 45%|████▌     | 168162/371472 [2:26:16<17:10:09,  3.29it/s]
 45%|████▌     | 168163/371472 [2:26:17<16:40:00,  3.39it/s]
 45%|████▌     | 168164/371472 [2:26:17<16:34:55,  3.41it/s]
 45%|████▌     | 168165/371472 [2:26:17<16:29:34,  3.42it/s]
 45%|████▌     | 168166/371472 [2:26:18<16:35:28,  3.40it/s]
 45%|████▌     | 168167/371472 [2:26:18<16:36:15,  3.40it/s]
 45%|████▌     | 168168/371472 [2:26:18<16:28:27,  3.43it/s]
 45%|████▌     | 168169/371472 [2:26:18<17:13:57,  3.28it/s]
 45%|████▌     | 168170/371472 [2:26:19<17:34:07,  3.21it/s]
 45%|████▌     | 168171/371472 [2:26:19<17:14:08,  3.28it/s]
 45%|████▌     | 168172/371472 [2:26:19<16:53:46,  3.34it/s]
 45%|████▌     | 168173/371472 [2:26:20<16:26:17,  3.44it/s]
 45%|████▌     | 168174/371472 [2:26:20<16:46:19,  3.37it/s]
 45%|████▌     | 168175/371472 [2:26:20<17:11:34,  3.28it/s]
 45%|████▌     | 168176/371472 [2:26:21<16:37:53,  3.40it/s]
 45%|████▌     | 168177/371472 [2:26:21<17:08:18,  3.29it/s]
 45%|████▌     | 168178/371472 [2:26:21<16:52:08,  3.35it/s]
 45%|████▌     | 168179/371472 [2:26:21<16:27:02,  3.43it/s]
 45%|████▌     | 168180/371472 [2:26:22<16:24:15,  3.44it/s]
                                                            
{'loss': 3.1429, 'learning_rate': 5.927998879527677e-07, 'epoch': 7.24}
+
 45%|████▌     | 168180/371472 [2:26:22<16:24:15,  3.44it/s]
 45%|████▌     | 168181/371472 [2:26:22<16:40:27,  3.39it/s]
 45%|████▌     | 168182/371472 [2:26:22<16:45:31,  3.37it/s]
 45%|████▌     | 168183/371472 [2:26:23<16:51:48,  3.35it/s]
 45%|████▌     | 168184/371472 [2:26:23<16:24:08,  3.44it/s]
 45%|████▌     | 168185/371472 [2:26:23<17:07:04,  3.30it/s]
 45%|████▌     | 168186/371472 [2:26:23<17:00:52,  3.32it/s]
 45%|████▌     | 168187/371472 [2:26:24<17:05:16,  3.30it/s]
 45%|████▌     | 168188/371472 [2:26:24<17:18:10,  3.26it/s]
 45%|████▌     | 168189/371472 [2:26:24<17:12:57,  3.28it/s]
 45%|████▌     | 168190/371472 [2:26:25<17:59:36,  3.14it/s]
 45%|████▌     | 168191/371472 [2:26:25<19:25:18,  2.91it/s]
 45%|████▌     | 168192/371472 [2:26:26<19:37:05,  2.88it/s]
 45%|████▌     | 168193/371472 [2:26:26<18:56:39,  2.98it/s]
 45%|████▌     | 168194/371472 [2:26:26<18:59:17,  2.97it/s]
 45%|████▌     | 168195/371472 [2:26:27<19:20:44,  2.92it/s]
 45%|████▌     | 168196/371472 [2:26:27<19:09:51,  2.95it/s]
 45%|████▌     | 168197/371472 [2:26:27<18:18:02,  3.09it/s]
 45%|████▌     | 168198/371472 [2:26:27<17:15:56,  3.27it/s]
 45%|████▌     | 168199/371472 [2:26:28<17:27:25,  3.23it/s]
 45%|████▌     | 168200/371472 [2:26:28<17:08:51,  3.29it/s]
                                                            
{'loss': 3.007, 'learning_rate': 5.927514059772889e-07, 'epoch': 7.24}
+
 45%|████▌     | 168200/371472 [2:26:28<17:08:51,  3.29it/s]
 45%|████▌     | 168201/371472 [2:26:28<16:54:20,  3.34it/s]
 45%|████▌     | 168202/371472 [2:26:29<17:05:49,  3.30it/s]
 45%|████▌     | 168203/371472 [2:26:29<17:40:55,  3.19it/s]
 45%|████▌     | 168204/371472 [2:26:29<17:22:37,  3.25it/s]
 45%|████▌     | 168205/371472 [2:26:30<17:19:10,  3.26it/s]
 45%|████▌     | 168206/371472 [2:26:30<17:07:10,  3.30it/s]
 45%|████▌     | 168207/371472 [2:26:30<16:58:13,  3.33it/s]
 45%|████▌     | 168208/371472 [2:26:30<16:50:30,  3.35it/s]
 45%|████▌     | 168209/371472 [2:26:31<16:28:41,  3.43it/s]
 45%|████▌     | 168210/371472 [2:26:31<16:23:46,  3.44it/s]
 45%|████▌     | 168211/371472 [2:26:31<19:16:41,  2.93it/s]
 45%|████▌     | 168212/371472 [2:26:32<18:27:13,  3.06it/s]
 45%|████▌     | 168213/371472 [2:26:32<18:16:00,  3.09it/s]
 45%|████▌     | 168214/371472 [2:26:32<18:43:26,  3.02it/s]
 45%|████▌     | 168215/371472 [2:26:33<18:00:41,  3.13it/s]
 45%|████▌     | 168216/371472 [2:26:33<17:18:09,  3.26it/s]
 45%|████▌     | 168217/371472 [2:26:33<17:52:39,  3.16it/s]
 45%|████▌     | 168218/371472 [2:26:34<17:41:00,  3.19it/s]
 45%|████▌     | 168219/371472 [2:26:34<17:10:01,  3.29it/s]
 45%|████▌     | 168220/371472 [2:26:34<17:38:45,  3.20it/s]
                                                            
{'loss': 2.9629, 'learning_rate': 5.9270292400181e-07, 'epoch': 7.25}
+
 45%|████▌     | 168220/371472 [2:26:34<17:38:45,  3.20it/s]
 45%|████▌     | 168221/371472 [2:26:35<17:13:37,  3.28it/s]
 45%|████▌     | 168222/371472 [2:26:35<16:55:13,  3.34it/s]
 45%|████▌     | 168223/371472 [2:26:35<16:53:11,  3.34it/s]
 45%|████▌     | 168224/371472 [2:26:35<17:23:00,  3.25it/s]
 45%|████▌     | 168225/371472 [2:26:36<18:27:58,  3.06it/s]
 45%|████▌     | 168226/371472 [2:26:36<18:07:37,  3.11it/s]
 45%|████▌     | 168227/371472 [2:26:36<17:26:16,  3.24it/s]
 45%|████▌     | 168228/371472 [2:26:37<17:02:47,  3.31it/s]
 45%|████▌     | 168229/371472 [2:26:37<16:29:24,  3.42it/s]
 45%|████▌     | 168230/371472 [2:26:37<18:40:25,  3.02it/s]
 45%|████▌     | 168231/371472 [2:26:38<18:10:45,  3.11it/s]
 45%|████▌     | 168232/371472 [2:26:38<17:43:25,  3.19it/s]
 45%|████▌     | 168233/371472 [2:26:38<17:21:32,  3.25it/s]
 45%|████▌     | 168234/371472 [2:26:39<18:23:59,  3.07it/s]
 45%|████▌     | 168235/371472 [2:26:39<17:45:15,  3.18it/s]
 45%|████▌     | 168236/371472 [2:26:39<17:53:24,  3.16it/s]
 45%|████▌     | 168237/371472 [2:26:40<17:59:06,  3.14it/s]
 45%|████▌     | 168238/371472 [2:26:40<17:37:37,  3.20it/s]
 45%|████▌     | 168239/371472 [2:26:40<17:11:07,  3.28it/s]
 45%|████▌     | 168240/371472 [2:26:40<16:51:01,  3.35it/s]
                                                            
{'loss': 2.9683, 'learning_rate': 5.92654442026331e-07, 'epoch': 7.25}
+
 45%|████▌     | 168240/371472 [2:26:40<16:51:01,  3.35it/s]
 45%|████▌     | 168241/371472 [2:26:41<16:29:05,  3.42it/s]
 45%|████▌     | 168242/371472 [2:26:41<17:02:35,  3.31it/s]
 45%|████▌     | 168243/371472 [2:26:41<17:18:48,  3.26it/s]
 45%|████▌     | 168244/371472 [2:26:42<16:58:42,  3.32it/s]
 45%|████▌     | 168245/371472 [2:26:42<16:56:54,  3.33it/s]
 45%|████▌     | 168246/371472 [2:26:42<16:45:20,  3.37it/s]
 45%|████▌     | 168247/371472 [2:26:43<17:02:06,  3.31it/s]
 45%|████▌     | 168248/371472 [2:26:43<16:56:41,  3.33it/s]
 45%|████▌     | 168249/371472 [2:26:43<17:29:02,  3.23it/s]
 45%|████▌     | 168250/371472 [2:26:44<17:53:47,  3.15it/s]
 45%|████▌     | 168251/371472 [2:26:44<17:45:02,  3.18it/s]
 45%|████▌     | 168252/371472 [2:26:44<17:05:48,  3.30it/s]
 45%|████▌     | 168253/371472 [2:26:44<17:02:29,  3.31it/s]
 45%|████▌     | 168254/371472 [2:26:45<16:48:08,  3.36it/s]
 45%|████▌     | 168255/371472 [2:26:45<16:44:50,  3.37it/s]
 45%|████▌     | 168256/371472 [2:26:45<16:14:26,  3.48it/s]
 45%|████▌     | 168257/371472 [2:26:46<16:09:10,  3.49it/s]
 45%|████▌     | 168258/371472 [2:26:46<16:09:35,  3.49it/s]
 45%|████▌     | 168259/371472 [2:26:46<15:55:55,  3.54it/s]
 45%|████▌     | 168260/371472 [2:26:46<16:45:58,  3.37it/s]
                                                            
{'loss': 3.0316, 'learning_rate': 5.926059600508521e-07, 'epoch': 7.25}
+
 45%|████▌     | 168260/371472 [2:26:46<16:45:58,  3.37it/s]
 45%|████▌     | 168261/371472 [2:26:47<16:25:00,  3.44it/s]
 45%|████▌     | 168262/371472 [2:26:47<17:15:23,  3.27it/s]
 45%|████▌     | 168263/371472 [2:26:47<18:14:47,  3.09it/s]
 45%|████▌     | 168264/371472 [2:26:48<17:21:12,  3.25it/s]
 45%|████▌     | 168265/371472 [2:26:48<18:20:47,  3.08it/s]
 45%|████▌     | 168266/371472 [2:26:48<18:21:17,  3.08it/s]
 45%|████▌     | 168267/371472 [2:26:49<18:58:15,  2.98it/s]
 45%|████▌     | 168268/371472 [2:26:49<17:48:41,  3.17it/s]
 45%|████▌     | 168269/371472 [2:26:49<17:18:15,  3.26it/s]
 45%|████▌     | 168270/371472 [2:26:50<17:42:23,  3.19it/s]
 45%|████▌     | 168271/371472 [2:26:50<17:38:51,  3.20it/s]
 45%|████▌     | 168272/371472 [2:26:50<17:41:25,  3.19it/s]
 45%|████▌     | 168273/371472 [2:26:51<17:30:43,  3.22it/s]
 45%|████▌     | 168274/371472 [2:26:51<18:00:31,  3.13it/s]
 45%|████▌     | 168275/371472 [2:26:51<18:21:28,  3.07it/s]
 45%|████▌     | 168276/371472 [2:26:51<17:29:23,  3.23it/s]
 45%|████▌     | 168277/371472 [2:26:52<17:22:41,  3.25it/s]
 45%|████▌     | 168278/371472 [2:26:52<17:01:08,  3.32it/s]
 45%|████▌     | 168279/371472 [2:26:52<16:49:27,  3.35it/s]
 45%|████▌     | 168280/371472 [2:26:53<16:22:24,  3.45it/s]
                                                            
{'loss': 2.954, 'learning_rate': 5.925574780753733e-07, 'epoch': 7.25}
+
 45%|████▌     | 168280/371472 [2:26:53<16:22:24,  3.45it/s]
 45%|████▌     | 168281/371472 [2:26:53<16:22:08,  3.45it/s]
 45%|████▌     | 168282/371472 [2:26:53<18:01:53,  3.13it/s]
 45%|████▌     | 168283/371472 [2:26:54<17:00:26,  3.32it/s]
 45%|████▌     | 168284/371472 [2:26:54<16:34:00,  3.41it/s]
 45%|████▌     | 168285/371472 [2:26:54<16:31:43,  3.41it/s]
 45%|████▌     | 168286/371472 [2:26:54<16:01:20,  3.52it/s]
 45%|████▌     | 168287/371472 [2:26:55<15:40:52,  3.60it/s]
 45%|████▌     | 168288/371472 [2:26:55<15:32:41,  3.63it/s]
 45%|████▌     | 168289/371472 [2:26:55<15:16:15,  3.70it/s]
 45%|████▌     | 168290/371472 [2:26:56<16:11:07,  3.49it/s]
 45%|████▌     | 168291/371472 [2:26:56<16:52:32,  3.34it/s]
 45%|████▌     | 168292/371472 [2:26:56<16:56:21,  3.33it/s]
 45%|████▌     | 168293/371472 [2:26:56<17:10:21,  3.29it/s]
 45%|████▌     | 168294/371472 [2:26:57<17:10:43,  3.29it/s]
 45%|████▌     | 168295/371472 [2:26:57<17:02:25,  3.31it/s]
 45%|████▌     | 168296/371472 [2:26:57<16:51:13,  3.35it/s]
 45%|████▌     | 168297/371472 [2:26:58<16:56:23,  3.33it/s]
 45%|████▌     | 168298/371472 [2:26:58<16:39:03,  3.39it/s]
 45%|████▌     | 168299/371472 [2:26:58<16:35:58,  3.40it/s]
 45%|████▌     | 168300/371472 [2:26:59<16:32:33,  3.41it/s]
                                                            
{'loss': 2.9693, 'learning_rate': 5.925089960998945e-07, 'epoch': 7.25}
+
 45%|████▌     | 168300/371472 [2:26:59<16:32:33,  3.41it/s]
 45%|████▌     | 168301/371472 [2:26:59<16:25:31,  3.44it/s]
 45%|████▌     | 168302/371472 [2:26:59<16:35:26,  3.40it/s]
 45%|████▌     | 168303/371472 [2:26:59<16:11:46,  3.48it/s]
 45%|████▌     | 168304/371472 [2:27:00<15:59:30,  3.53it/s]
 45%|████▌     | 168305/371472 [2:27:00<15:52:11,  3.56it/s]
 45%|████▌     | 168306/371472 [2:27:00<15:45:47,  3.58it/s]
 45%|████▌     | 168307/371472 [2:27:00<15:45:53,  3.58it/s]
 45%|████▌     | 168308/371472 [2:27:01<15:44:26,  3.59it/s]
 45%|████▌     | 168309/371472 [2:27:01<15:33:08,  3.63it/s]
 45%|████▌     | 168310/371472 [2:27:01<15:46:28,  3.58it/s]
 45%|████▌     | 168311/371472 [2:27:02<15:46:07,  3.58it/s]
 45%|████▌     | 168312/371472 [2:27:02<15:58:21,  3.53it/s]
 45%|████▌     | 168313/371472 [2:27:02<19:29:04,  2.90it/s]
 45%|████▌     | 168314/371472 [2:27:03<18:15:38,  3.09it/s]
 45%|████▌     | 168315/371472 [2:27:03<17:54:17,  3.15it/s]
 45%|████▌     | 168316/371472 [2:27:03<17:30:51,  3.22it/s]
 45%|████▌     | 168317/371472 [2:27:04<16:57:15,  3.33it/s]
 45%|████▌     | 168318/371472 [2:27:04<17:29:10,  3.23it/s]
 45%|████▌     | 168319/371472 [2:27:04<16:48:11,  3.36it/s]
 45%|████▌     | 168320/371472 [2:27:04<16:59:46,  3.32it/s]
                                                            
{'loss': 2.9614, 'learning_rate': 5.924605141244155e-07, 'epoch': 7.25}
+
 45%|████▌     | 168320/371472 [2:27:04<16:59:46,  3.32it/s]
 45%|████▌     | 168321/371472 [2:27:05<16:33:30,  3.41it/s]
 45%|████▌     | 168322/371472 [2:27:05<16:15:57,  3.47it/s]
 45%|████▌     | 168323/371472 [2:27:05<16:13:20,  3.48it/s]
 45%|████▌     | 168324/371472 [2:27:06<16:33:42,  3.41it/s]
 45%|████▌     | 168325/371472 [2:27:06<16:39:30,  3.39it/s]
 45%|████▌     | 168326/371472 [2:27:06<16:49:22,  3.35it/s]
 45%|████▌     | 168327/371472 [2:27:06<16:40:21,  3.38it/s]
 45%|████▌     | 168328/371472 [2:27:07<16:24:13,  3.44it/s]
 45%|████▌     | 168329/371472 [2:27:07<16:56:48,  3.33it/s]
 45%|████▌     | 168330/371472 [2:27:07<16:45:39,  3.37it/s]
 45%|████▌     | 168331/371472 [2:27:08<16:45:03,  3.37it/s]
 45%|████▌     | 168332/371472 [2:27:08<17:19:44,  3.26it/s]
 45%|████▌     | 168333/371472 [2:27:08<17:23:14,  3.25it/s]
 45%|████▌     | 168334/371472 [2:27:09<17:12:26,  3.28it/s]
 45%|████▌     | 168335/371472 [2:27:09<16:45:59,  3.37it/s]
 45%|████▌     | 168336/371472 [2:27:09<16:19:48,  3.46it/s]
 45%|████▌     | 168337/371472 [2:27:09<16:31:03,  3.42it/s]
 45%|████▌     | 168338/371472 [2:27:10<16:06:28,  3.50it/s]
 45%|████▌     | 168339/371472 [2:27:10<16:19:43,  3.46it/s]
 45%|████▌     | 168340/371472 [2:27:10<16:16:11,  3.47it/s]
                                                            
{'loss': 3.064, 'learning_rate': 5.924120321489365e-07, 'epoch': 7.25}
+
 45%|████▌     | 168340/371472 [2:27:10<16:16:11,  3.47it/s]
 45%|████▌     | 168341/371472 [2:27:11<16:05:01,  3.51it/s]
 45%|████▌     | 168342/371472 [2:27:11<16:03:37,  3.51it/s]
 45%|████▌     | 168343/371472 [2:27:11<16:13:51,  3.48it/s]
 45%|████▌     | 168344/371472 [2:27:12<16:56:00,  3.33it/s]
 45%|████▌     | 168345/371472 [2:27:12<17:30:41,  3.22it/s]
 45%|████▌     | 168346/371472 [2:27:12<17:19:01,  3.26it/s]
 45%|████▌     | 168347/371472 [2:27:12<16:46:44,  3.36it/s]
 45%|████▌     | 168348/371472 [2:27:13<16:28:17,  3.43it/s]
 45%|████▌     | 168349/371472 [2:27:13<16:40:17,  3.38it/s]
 45%|████▌     | 168350/371472 [2:27:13<16:41:27,  3.38it/s]
 45%|████▌     | 168351/371472 [2:27:14<17:28:51,  3.23it/s]
 45%|████▌     | 168352/371472 [2:27:14<16:59:26,  3.32it/s]
 45%|████▌     | 168353/371472 [2:27:14<16:32:10,  3.41it/s]
 45%|████▌     | 168354/371472 [2:27:14<16:33:34,  3.41it/s]
 45%|████▌     | 168355/371472 [2:27:15<17:56:08,  3.15it/s]
 45%|████▌     | 168356/371472 [2:27:15<17:24:48,  3.24it/s]
 45%|████▌     | 168357/371472 [2:27:15<17:34:37,  3.21it/s]
 45%|████▌     | 168358/371472 [2:27:16<17:24:18,  3.24it/s]
 45%|████▌     | 168359/371472 [2:27:16<17:13:45,  3.27it/s]
 45%|████▌     | 168360/371472 [2:27:16<18:10:54,  3.10it/s]
                                                            
{'loss': 3.0012, 'learning_rate': 5.923635501734577e-07, 'epoch': 7.25}
+
 45%|████▌     | 168360/371472 [2:27:16<18:10:54,  3.10it/s]
 45%|████▌     | 168361/371472 [2:27:17<18:06:46,  3.11it/s]
 45%|████▌     | 168362/371472 [2:27:17<17:19:03,  3.26it/s]
 45%|████▌     | 168363/371472 [2:27:17<17:08:48,  3.29it/s]
 45%|████▌     | 168364/371472 [2:27:18<20:19:58,  2.77it/s]
 45%|████▌     | 168365/371472 [2:27:18<20:09:12,  2.80it/s]
 45%|████▌     | 168366/371472 [2:27:18<19:13:13,  2.94it/s]
 45%|████▌     | 168367/371472 [2:27:19<18:49:03,  3.00it/s]
 45%|████▌     | 168368/371472 [2:27:19<18:19:48,  3.08it/s]
 45%|████▌     | 168369/371472 [2:27:19<17:45:25,  3.18it/s]
 45%|████▌     | 168370/371472 [2:27:20<17:18:07,  3.26it/s]
 45%|████▌     | 168371/371472 [2:27:20<16:46:35,  3.36it/s]
 45%|████▌     | 168372/371472 [2:27:20<16:41:27,  3.38it/s]
 45%|████▌     | 168373/371472 [2:27:21<17:22:39,  3.25it/s]
 45%|████▌     | 168374/371472 [2:27:21<17:25:44,  3.24it/s]
 45%|████▌     | 168375/371472 [2:27:21<17:12:25,  3.28it/s]
 45%|████▌     | 168376/371472 [2:27:21<17:28:50,  3.23it/s]
 45%|████▌     | 168377/371472 [2:27:22<17:19:57,  3.25it/s]
 45%|████▌     | 168378/371472 [2:27:22<17:23:06,  3.25it/s]
 45%|████▌     | 168379/371472 [2:27:22<17:11:17,  3.28it/s]
 45%|████▌     | 168380/371472 [2:27:23<17:16:32,  3.27it/s]
                                                            
{'loss': 2.952, 'learning_rate': 5.923150681979789e-07, 'epoch': 7.25}
+
 45%|████▌     | 168380/371472 [2:27:23<17:16:32,  3.27it/s]
 45%|████▌     | 168381/371472 [2:27:23<18:24:48,  3.06it/s]
 45%|████▌     | 168382/371472 [2:27:23<17:33:31,  3.21it/s]
 45%|████▌     | 168383/371472 [2:27:24<16:56:29,  3.33it/s]
 45%|████▌     | 168384/371472 [2:27:24<17:44:54,  3.18it/s]
 45%|████▌     | 168385/371472 [2:27:24<18:31:30,  3.05it/s]
 45%|████▌     | 168386/371472 [2:27:25<19:18:41,  2.92it/s]
 45%|████▌     | 168387/371472 [2:27:25<18:36:41,  3.03it/s]
 45%|████▌     | 168388/371472 [2:27:25<17:53:25,  3.15it/s]
 45%|████▌     | 168389/371472 [2:27:26<17:34:54,  3.21it/s]
 45%|███���▌     | 168390/371472 [2:27:26<16:51:25,  3.35it/s]
 45%|████▌     | 168391/371472 [2:27:26<17:09:09,  3.29it/s]
 45%|████▌     | 168392/371472 [2:27:26<16:56:27,  3.33it/s]
 45%|████▌     | 168393/371472 [2:27:27<17:34:34,  3.21it/s]
 45%|████▌     | 168394/371472 [2:27:27<18:30:36,  3.05it/s]
 45%|████▌     | 168395/371472 [2:27:27<17:58:40,  3.14it/s]
 45%|████▌     | 168396/371472 [2:27:28<18:28:41,  3.05it/s]
 45%|████▌     | 168397/371472 [2:27:28<18:06:30,  3.12it/s]
 45%|████▌     | 168398/371472 [2:27:28<17:39:48,  3.19it/s]
 45%|████▌     | 168399/371472 [2:27:29<17:27:35,  3.23it/s]
 45%|████▌     | 168400/371472 [2:27:29<16:57:28,  3.33it/s]
                                                            
{'loss': 2.9328, 'learning_rate': 5.922665862224999e-07, 'epoch': 7.25}
+
 45%|████▌     | 168400/371472 [2:27:29<16:57:28,  3.33it/s]
 45%|████▌     | 168401/371472 [2:27:29<18:48:51,  3.00it/s]
 45%|████▌     | 168402/371472 [2:27:30<18:07:11,  3.11it/s]
 45%|████▌     | 168403/371472 [2:27:30<19:04:08,  2.96it/s]
 45%|████▌     | 168404/371472 [2:27:30<18:04:23,  3.12it/s]
 45%|████▌     | 168405/371472 [2:27:31<17:42:35,  3.19it/s]
 45%|████▌     | 168406/371472 [2:27:31<17:41:49,  3.19it/s]
 45%|████▌     | 168407/371472 [2:27:31<17:35:12,  3.21it/s]
 45%|████▌     | 168408/371472 [2:27:32<17:26:30,  3.23it/s]
 45%|████▌     | 168409/371472 [2:27:32<16:40:26,  3.38it/s]
 45%|████▌     | 168410/371472 [2:27:32<17:02:03,  3.31it/s]
 45%|████▌     | 168411/371472 [2:27:32<17:01:44,  3.31it/s]
 45%|████▌     | 168412/371472 [2:27:33<16:39:11,  3.39it/s]
 45%|████▌     | 168413/371472 [2:27:33<16:16:11,  3.47it/s]
 45%|████▌     | 168414/371472 [2:27:33<16:02:44,  3.52it/s]
 45%|████▌     | 168415/371472 [2:27:34<16:43:09,  3.37it/s]
 45%|████▌     | 168416/371472 [2:27:34<16:45:02,  3.37it/s]
 45%|████▌     | 168417/371472 [2:27:34<16:16:14,  3.47it/s]
 45%|████▌     | 168418/371472 [2:27:34<16:02:44,  3.52it/s]
 45%|████▌     | 168419/371472 [2:27:35<15:45:22,  3.58it/s]
 45%|████▌     | 168420/371472 [2:27:35<17:08:04,  3.29it/s]
                                                            
{'loss': 2.9244, 'learning_rate': 5.92218104247021e-07, 'epoch': 7.25}
+
 45%|████▌     | 168420/371472 [2:27:35<17:08:04,  3.29it/s]
 45%|████▌     | 168421/371472 [2:27:35<17:53:19,  3.15it/s]
 45%|████▌     | 168422/371472 [2:27:36<17:12:39,  3.28it/s]
 45%|████▌     | 168423/371472 [2:27:36<17:03:02,  3.31it/s]
 45%|████▌     | 168424/371472 [2:27:36<17:05:14,  3.30it/s]
 45%|████▌     | 168425/371472 [2:27:37<17:06:58,  3.30it/s]
 45%|████▌     | 168426/371472 [2:27:37<17:04:40,  3.30it/s]
 45%|████▌     | 168427/371472 [2:27:37<17:00:31,  3.32it/s]
 45%|████▌     | 168428/371472 [2:27:38<17:23:13,  3.24it/s]
 45%|████▌     | 168429/371472 [2:27:38<17:13:27,  3.27it/s]
 45%|████▌     | 168430/371472 [2:27:38<16:54:19,  3.34it/s]
 45%|████▌     | 168431/371472 [2:27:38<17:30:40,  3.22it/s]
 45%|████▌     | 168432/371472 [2:27:39<17:17:55,  3.26it/s]
 45%|████▌     | 168433/371472 [2:27:39<17:23:13,  3.24it/s]
 45%|████▌     | 168434/371472 [2:27:39<17:05:15,  3.30it/s]
 45%|████▌     | 168435/371472 [2:27:40<17:43:11,  3.18it/s]
 45%|████▌     | 168436/371472 [2:27:40<17:43:59,  3.18it/s]
 45%|████▌     | 168437/371472 [2:27:40<17:45:22,  3.18it/s]
 45%|████▌     | 168438/371472 [2:27:41<17:27:28,  3.23it/s]
 45%|████▌     | 168439/371472 [2:27:41<17:42:29,  3.18it/s]
 45%|████▌     | 168440/371472 [2:27:41<17:19:55,  3.25it/s]
                                                            
{'loss': 2.996, 'learning_rate': 5.921696222715422e-07, 'epoch': 7.26}
+
 45%|████▌     | 168440/371472 [2:27:41<17:19:55,  3.25it/s]
 45%|████▌     | 168441/371472 [2:27:42<18:53:24,  2.99it/s]
 45%|████▌     | 168442/371472 [2:27:42<18:42:52,  3.01it/s]
 45%|████▌     | 168443/371472 [2:27:42<19:05:40,  2.95it/s]
 45%|████▌     | 168444/371472 [2:27:43<18:03:31,  3.12it/s]
 45%|████▌     | 168445/371472 [2:27:43<17:07:08,  3.29it/s]
 45%|████▌     | 168446/371472 [2:27:43<16:45:49,  3.36it/s]
 45%|████▌     | 168447/371472 [2:27:43<16:54:10,  3.34it/s]
 45%|████▌     | 168448/371472 [2:27:44<16:41:56,  3.38it/s]
 45%|████▌     | 168449/371472 [2:27:44<16:51:06,  3.35it/s]
 45%|████▌     | 168450/371472 [2:27:44<16:59:51,  3.32it/s]
 45%|████▌     | 168451/371472 [2:27:45<17:48:46,  3.17it/s]
 45%|████▌     | 168452/371472 [2:27:45<17:18:47,  3.26it/s]
 45%|████▌     | 168453/371472 [2:27:45<17:13:26,  3.27it/s]
 45%|████▌     | 168454/371472 [2:27:46<17:09:19,  3.29it/s]
 45%|████▌     | 168455/371472 [2:27:46<16:54:18,  3.34it/s]
 45%|████▌     | 168456/371472 [2:27:46<17:49:51,  3.16it/s]
 45%|████▌     | 168457/371472 [2:27:47<17:35:44,  3.20it/s]
 45%|████▌     | 168458/371472 [2:27:47<17:31:04,  3.22it/s]
 45%|████▌     | 168459/371472 [2:27:47<17:03:51,  3.30it/s]
 45%|████▌     | 168460/371472 [2:27:47<16:57:38,  3.32it/s]
                                                            
{'loss': 3.0186, 'learning_rate': 5.921211402960633e-07, 'epoch': 7.26}
+
 45%|████▌     | 168460/371472 [2:27:47<16:57:38,  3.32it/s]
 45%|████▌     | 168461/371472 [2:27:48<16:40:23,  3.38it/s]
 45%|████▌     | 168462/371472 [2:27:48<16:35:27,  3.40it/s]
 45%|████▌     | 168463/371472 [2:27:48<16:27:36,  3.43it/s]
 45%|████▌     | 168464/371472 [2:27:49<16:06:50,  3.50it/s]
 45%|████▌     | 168465/371472 [2:27:49<15:50:10,  3.56it/s]
 45%|████▌     | 168466/371472 [2:27:49<17:15:10,  3.27it/s]
 45%|████▌     | 168467/371472 [2:27:50<17:31:12,  3.22it/s]
 45%|████▌     | 168468/371472 [2:27:50<17:08:42,  3.29it/s]
 45%|████▌     | 168469/371472 [2:27:50<16:47:26,  3.36it/s]
 45%|████▌     | 168470/371472 [2:27:50<17:27:55,  3.23it/s]
 45%|████▌     | 168471/371472 [2:27:51<16:55:28,  3.33it/s]
 45%|████▌     | 168472/371472 [2:27:51<16:51:04,  3.35it/s]
 45%|████▌     | 168473/371472 [2:27:51<16:44:46,  3.37it/s]
 45%|████▌     | 168474/371472 [2:27:52<17:44:09,  3.18it/s]
 45%|████▌     | 168475/371472 [2:27:52<16:51:22,  3.35it/s]
 45%|████▌     | 168476/371472 [2:27:52<16:45:40,  3.36it/s]
 45%|████▌     | 168477/371472 [2:27:53<17:23:16,  3.24it/s]
 45%|████▌     | 168478/371472 [2:27:53<17:18:51,  3.26it/s]
 45%|████▌     | 168479/371472 [2:27:53<17:30:31,  3.22it/s]
 45%|████▌     | 168480/371472 [2:27:53<17:22:09,  3.25it/s]
                                                            
{'loss': 2.9952, 'learning_rate': 5.920726583205843e-07, 'epoch': 7.26}
+
 45%|████▌     | 168480/371472 [2:27:53<17:22:09,  3.25it/s]
 45%|████▌     | 168481/371472 [2:27:54<17:14:34,  3.27it/s]
 45%|████▌     | 168482/371472 [2:27:54<17:25:11,  3.24it/s]
 45%|████▌     | 168483/371472 [2:27:54<17:00:11,  3.32it/s]
 45%|████▌     | 168484/371472 [2:27:55<16:50:16,  3.35it/s]
 45%|████▌     | 168485/371472 [2:27:55<16:42:09,  3.38it/s]
 45%|████▌     | 168486/371472 [2:27:55<16:29:44,  3.42it/s]
 45%|████▌     | 168487/371472 [2:27:56<16:38:37,  3.39it/s]
 45%|████▌     | 168488/371472 [2:27:56<16:19:47,  3.45it/s]
 45%|████▌     | 168489/371472 [2:27:56<17:41:13,  3.19it/s]
 45%|████▌     | 168490/371472 [2:27:56<17:34:58,  3.21it/s]
 45%|████▌     | 168491/371472 [2:27:57<17:03:42,  3.30it/s]
 45%|████▌     | 168492/371472 [2:27:57<16:55:41,  3.33it/s]
 45%|████▌     | 168493/371472 [2:27:57<17:02:33,  3.31it/s]
 45%|████▌     | 168494/371472 [2:27:58<16:42:43,  3.37it/s]
 45%|████▌     | 168495/371472 [2:27:58<17:23:40,  3.24it/s]
 45%|████▌     | 168496/371472 [2:27:58<17:04:52,  3.30it/s]
 45%|████▌     | 168497/371472 [2:27:59<17:40:36,  3.19it/s]
 45%|████▌     | 168498/371472 [2:27:59<17:25:56,  3.23it/s]
 45%|████▌     | 168499/371472 [2:27:59<17:38:47,  3.20it/s]
 45%|████▌     | 168500/371472 [2:28:00<17:25:09,  3.24it/s]
                                                            
{'loss': 2.8745, 'learning_rate': 5.920241763451054e-07, 'epoch': 7.26}
+
 45%|████▌     | 168500/371472 [2:28:00<17:25:09,  3.24it/s]
 45%|████▌     | 168501/371472 [2:28:00<16:55:30,  3.33it/s]
 45%|████▌     | 168502/371472 [2:28:00<16:26:34,  3.43it/s]
 45%|████▌     | 168503/371472 [2:28:00<17:28:44,  3.23it/s]
 45%|████▌     | 168504/371472 [2:28:01<17:05:09,  3.30it/s]
 45%|████▌     | 168505/371472 [2:28:01<16:57:18,  3.33it/s]
 45%|████▌     | 168506/371472 [2:28:01<16:42:23,  3.37it/s]
 45%|████▌     | 168507/371472 [2:28:02<16:29:16,  3.42it/s]
 45%|████▌     | 168508/371472 [2:28:02<16:04:28,  3.51it/s]
 45%|████▌     | 168509/371472 [2:28:02<16:13:10,  3.48it/s]
 45%|████▌     | 168510/371472 [2:28:02<16:02:09,  3.52it/s]
 45%|████▌     | 168511/371472 [2:28:03<16:02:14,  3.52it/s]
 45%|████▌     | 168512/371472 [2:28:03<16:27:34,  3.43it/s]
 45%|████▌     | 168513/371472 [2:28:03<18:21:08,  3.07it/s]
 45%|████▌     | 168514/371472 [2:28:04<17:42:57,  3.18it/s]
 45%|████▌     | 168515/371472 [2:28:04<17:23:58,  3.24it/s]
 45%|████▌     | 168516/371472 [2:28:04<17:03:19,  3.31it/s]
 45%|████▌     | 168517/371472 [2:28:05<17:54:54,  3.15it/s]
 45%|████▌     | 168518/371472 [2:28:05<17:12:46,  3.28it/s]
 45%|████▌     | 168519/371472 [2:28:05<16:35:17,  3.40it/s]
 45%|████▌     | 168520/371472 [2:28:05<16:12:07,  3.48it/s]
                                                            
{'loss': 2.7985, 'learning_rate': 5.919756943696266e-07, 'epoch': 7.26}
+
 45%|████▌     | 168520/371472 [2:28:05<16:12:07,  3.48it/s]
 45%|████▌     | 168521/371472 [2:28:06<16:01:28,  3.52it/s]
 45%|████▌     | 168522/371472 [2:28:06<16:07:09,  3.50it/s]
 45%|████▌     | 168523/371472 [2:28:06<16:11:30,  3.48it/s]
 45%|████▌     | 168524/371472 [2:28:07<16:55:17,  3.33it/s]
 45%|████▌     | 168525/371472 [2:28:07<16:19:27,  3.45it/s]
 45%|████▌     | 168526/371472 [2:28:07<16:19:46,  3.45it/s]
 45%|████▌     | 168527/371472 [2:28:08<16:40:01,  3.38it/s]
 45%|████▌     | 168528/371472 [2:28:08<17:45:05,  3.18it/s]
 45%|████▌     | 168529/371472 [2:28:08<16:58:06,  3.32it/s]
 45%|████▌     | 168530/371472 [2:28:08<17:10:07,  3.28it/s]
 45%|████▌     | 168531/371472 [2:28:09<16:35:44,  3.40it/s]
 45%|████▌     | 168532/371472 [2:28:09<16:13:32,  3.47it/s]
 45%|████▌     | 168533/371472 [2:28:09<16:46:58,  3.36it/s]
 45%|████▌     | 168534/371472 [2:28:10<16:41:48,  3.38it/s]
 45%|████▌     | 168535/371472 [2:28:10<17:33:55,  3.21it/s]
 45%|████▌     | 168536/371472 [2:28:10<17:05:48,  3.30it/s]
 45%|████▌     | 168537/371472 [2:28:11<17:05:49,  3.30it/s]
 45%|████▌     | 168538/371472 [2:28:11<17:02:48,  3.31it/s]
 45%|████▌     | 168539/371472 [2:28:11<16:45:58,  3.36it/s]
 45%|████▌     | 168540/371472 [2:28:11<16:20:47,  3.45it/s]
                                                            
{'loss': 2.8791, 'learning_rate': 5.919272123941478e-07, 'epoch': 7.26}
+
 45%|████▌     | 168540/371472 [2:28:11<16:20:47,  3.45it/s]
 45%|████▌     | 168541/371472 [2:28:12<17:12:37,  3.28it/s]
 45%|████▌     | 168542/371472 [2:28:12<17:15:09,  3.27it/s]
 45%|████▌     | 168543/371472 [2:28:12<17:46:27,  3.17it/s]
 45%|████▌     | 168544/371472 [2:28:13<17:44:48,  3.18it/s]
 45%|████▌     | 168545/371472 [2:28:13<17:00:25,  3.31it/s]
 45%|████▌     | 168546/371472 [2:28:13<16:52:24,  3.34it/s]
 45%|████▌     | 168547/371472 [2:28:14<17:51:09,  3.16it/s]
 45%|████▌     | 168548/371472 [2:28:14<17:22:49,  3.24it/s]
 45%|████▌     | 168549/371472 [2:28:14<17:11:45,  3.28it/s]
 45%|████▌     | 168550/371472 [2:28:15<16:44:01,  3.37it/s]
 45%|████▌     | 168551/371472 [2:28:15<16:57:41,  3.32it/s]
 45%|████▌     | 168552/371472 [2:28:15<17:28:11,  3.23it/s]
 45%|████▌     | 168553/371472 [2:28:15<16:55:22,  3.33it/s]
 45%|████▌     | 168554/371472 [2:28:16<16:36:16,  3.39it/s]
 45%|████▌     | 168555/371472 [2:28:16<16:56:39,  3.33it/s]
 45%|████▌     | 168556/371472 [2:28:16<16:38:32,  3.39it/s]
 45%|████▌     | 168557/371472 [2:28:17<16:49:51,  3.35it/s]
 45%|████▌     | 168558/371472 [2:28:17<16:45:53,  3.36it/s]
 45%|████▌     | 168559/371472 [2:28:17<16:16:13,  3.46it/s]
 45%|████▌     | 168560/371472 [2:28:18<17:05:00,  3.30it/s]
                                                            
{'loss': 2.8099, 'learning_rate': 5.918787304186687e-07, 'epoch': 7.26}
+
 45%|████▌     | 168560/371472 [2:28:18<17:05:00,  3.30it/s]
 45%|████▌     | 168561/371472 [2:28:18<17:51:45,  3.16it/s]
 45%|████▌     | 168562/371472 [2:28:18<17:33:54,  3.21it/s]
 45%|████▌     | 168563/371472 [2:28:18<17:39:29,  3.19it/s]
 45%|████▌     | 168564/371472 [2:28:19<18:19:57,  3.07it/s]
 45%|████▌     | 168565/371472 [2:28:19<17:22:08,  3.25it/s]
 45%|████▌     | 168566/371472 [2:28:19<16:48:24,  3.35it/s]
 45%|████▌     | 168567/371472 [2:28:20<16:16:30,  3.46it/s]
 45%|████▌     | 168568/371472 [2:28:20<16:17:16,  3.46it/s]
 45%|████▌     | 168569/371472 [2:28:20<16:23:43,  3.44it/s]
 45%|████▌     | 168570/371472 [2:28:21<17:34:30,  3.21it/s]
 45%|████▌     | 168571/371472 [2:28:21<17:27:26,  3.23it/s]
 45%|████▌     | 168572/371472 [2:28:21<16:36:06,  3.39it/s]
 45%|████▌     | 168573/371472 [2:28:21<16:00:36,  3.52it/s]
 45%|████▌     | 168574/371472 [2:28:22<15:50:47,  3.56it/s]
 45%|████▌     | 168575/371472 [2:28:22<15:57:43,  3.53it/s]
 45%|████▌     | 168576/371472 [2:28:22<15:49:00,  3.56it/s]
 45%|████▌     | 168577/371472 [2:28:23<16:02:53,  3.51it/s]
 45%|████▌     | 168578/371472 [2:28:23<16:08:15,  3.49it/s]
 45%|████▌     | 168579/371472 [2:28:23<16:07:07,  3.50it/s]
 45%|████▌     | 168580/371472 [2:28:23<16:18:39,  3.46it/s]
                                                            
{'loss': 2.939, 'learning_rate': 5.918302484431899e-07, 'epoch': 7.26}
+
 45%|████▌     | 168580/371472 [2:28:23<16:18:39,  3.46it/s]
 45%|████▌     | 168581/371472 [2:28:24<16:21:31,  3.45it/s]
 45%|████▌     | 168582/371472 [2:28:24<18:11:42,  3.10it/s]
 45%|████▌     | 168583/371472 [2:28:24<18:00:26,  3.13it/s]
 45%|████▌     | 168584/371472 [2:28:25<17:37:24,  3.20it/s]
 45%|████▌     | 168585/371472 [2:28:25<17:50:24,  3.16it/s]
 45%|████▌     | 168586/371472 [2:28:25<17:22:58,  3.24it/s]
 45%|████▌     | 168587/371472 [2:28:26<17:14:36,  3.27it/s]
 45%|████▌     | 168588/371472 [2:28:26<16:40:59,  3.38it/s]
 45%|████▌     | 168589/371472 [2:28:26<17:00:13,  3.31it/s]
 45%|████▌     | 168590/371472 [2:28:26<16:36:09,  3.39it/s]
 45%|████▌     | 168591/371472 [2:28:27<16:49:17,  3.35it/s]
 45%|████▌     | 168592/371472 [2:28:27<16:08:37,  3.49it/s]
 45%|████▌     | 168593/371472 [2:28:27<16:40:00,  3.38it/s]
 45%|████▌     | 168594/371472 [2:28:28<16:27:32,  3.42it/s]
 45%|████▌     | 168595/371472 [2:28:28<17:28:34,  3.22it/s]
 45%|████▌     | 168596/371472 [2:28:28<17:23:20,  3.24it/s]
 45%|████▌     | 168597/371472 [2:28:29<17:29:49,  3.22it/s]
 45%|████▌     | 168598/371472 [2:28:29<16:59:04,  3.32it/s]
 45%|████▌     | 168599/371472 [2:28:29<17:31:22,  3.22it/s]
 45%|████▌     | 168600/371472 [2:28:30<17:28:18,  3.23it/s]
                                                            
{'loss': 2.9422, 'learning_rate': 5.91781766467711e-07, 'epoch': 7.26}
+
 45%|████▌     | 168600/371472 [2:28:30<17:28:18,  3.23it/s]
 45%|████▌     | 168601/371472 [2:28:30<17:20:44,  3.25it/s]
 45%|████▌     | 168602/371472 [2:28:30<16:52:03,  3.34it/s]
 45%|████▌     | 168603/371472 [2:28:30<16:57:35,  3.32it/s]
 45%|████▌     | 168604/371472 [2:28:31<17:20:41,  3.25it/s]
 45%|████▌     | 168605/371472 [2:28:31<16:47:51,  3.35it/s]
 45%|████▌     | 168606/371472 [2:28:31<17:19:05,  3.25it/s]
 45%|████▌     | 168607/371472 [2:28:32<18:32:18,  3.04it/s]
 45%|████▌     | 168608/371472 [2:28:32<18:03:42,  3.12it/s]
 45%|████▌     | 168609/371472 [2:28:32<17:25:05,  3.24it/s]
 45%|████▌     | 168610/371472 [2:28:33<16:48:10,  3.35it/s]
 45%|████▌     | 168611/371472 [2:28:33<17:27:51,  3.23it/s]
 45%|████▌     | 168612/371472 [2:28:33<17:15:57,  3.26it/s]
 45%|████▌     | 168613/371472 [2:28:34<16:42:42,  3.37it/s]
 45%|████▌     | 168614/371472 [2:28:34<16:41:19,  3.38it/s]
 45%|████▌     | 168615/371472 [2:28:34<17:25:36,  3.23it/s]
 45%|████▌     | 168616/371472 [2:28:34<16:51:30,  3.34it/s]
 45%|████▌     | 168617/371472 [2:28:35<17:18:35,  3.26it/s]
 45%|████▌     | 168618/371472 [2:28:35<16:38:52,  3.38it/s]
 45%|████▌     | 168619/371472 [2:28:35<16:45:42,  3.36it/s]
 45%|████▌     | 168620/371472 [2:28:36<16:25:28,  3.43it/s]
                                                            
{'loss': 2.9773, 'learning_rate': 5.91733284492232e-07, 'epoch': 7.26}
+
 45%|████▌     | 168620/371472 [2:28:36<16:25:28,  3.43it/s]
 45%|████▌     | 168621/371472 [2:28:36<16:30:22,  3.41it/s]
 45%|████▌     | 168622/371472 [2:28:36<16:32:46,  3.41it/s]
 45%|████▌     | 168623/371472 [2:28:37<16:50:23,  3.35it/s]
 45%|████▌     | 168624/371472 [2:28:37<16:16:20,  3.46it/s]
 45%|████▌     | 168625/371472 [2:28:37<15:44:29,  3.58it/s]
 45%|████▌     | 168626/371472 [2:28:37<16:15:51,  3.46it/s]
 45%|████▌     | 168627/371472 [2:28:38<16:13:02,  3.47it/s]
 45%|████▌     | 168628/371472 [2:28:38<15:44:20,  3.58it/s]
 45%|████▌     | 168629/371472 [2:28:38<15:57:05,  3.53it/s]
 45%|████▌     | 168630/371472 [2:28:38<15:50:04,  3.56it/s]
 45%|████▌     | 168631/371472 [2:28:39<15:43:02,  3.58it/s]
 45%|████▌     | 168632/371472 [2:28:39<15:55:09,  3.54it/s]
 45%|████▌     | 168633/371472 [2:28:39<15:54:08,  3.54it/s]
 45%|████▌     | 168634/371472 [2:28:40<16:02:46,  3.51it/s]
 45%|████▌     | 168635/371472 [2:28:40<16:15:56,  3.46it/s]
 45%|████▌     | 168636/371472 [2:28:40<16:36:54,  3.39it/s]
 45%|████▌     | 168637/371472 [2:28:41<17:10:33,  3.28it/s]
 45%|████▌     | 168638/371472 [2:28:41<18:28:26,  3.05it/s]
 45%|████▌     | 168639/371472 [2:28:41<17:31:21,  3.22it/s]
 45%|████▌     | 168640/371472 [2:28:41<17:03:46,  3.30it/s]
                                                            
{'loss': 2.9952, 'learning_rate': 5.916848025167531e-07, 'epoch': 7.26}
+
 45%|████▌     | 168640/371472 [2:28:41<17:03:46,  3.30it/s]
 45%|████▌     | 168641/371472 [2:28:42<16:36:05,  3.39it/s]
 45%|████▌     | 168642/371472 [2:28:42<16:57:40,  3.32it/s]
 45%|████▌     | 168643/371472 [2:28:42<16:31:40,  3.41it/s]
 45%|████▌     | 168644/371472 [2:28:43<17:20:09,  3.25it/s]
 45%|████▌     | 168645/371472 [2:28:43<17:15:09,  3.27it/s]
 45%|████▌     | 168646/371472 [2:28:43<16:51:27,  3.34it/s]
 45%|████▌     | 168647/371472 [2:28:44<16:24:56,  3.43it/s]
 45%|████▌     | 168648/371472 [2:28:44<16:20:58,  3.45it/s]
 45%|████▌     | 168649/371472 [2:28:44<16:31:26,  3.41it/s]
 45%|████▌     | 168650/371472 [2:28:44<16:57:09,  3.32it/s]
 45%|████▌     | 168651/371472 [2:28:45<16:37:51,  3.39it/s]
 45%|████▌     | 168652/371472 [2:28:45<15:58:57,  3.52it/s]
 45%|████▌     | 168653/371472 [2:28:45<16:07:56,  3.49it/s]
 45%|████▌     | 168654/371472 [2:28:46<16:36:17,  3.39it/s]
 45%|████▌     | 168655/371472 [2:28:46<16:45:55,  3.36it/s]
 45%|████▌     | 168656/371472 [2:28:46<17:13:14,  3.27it/s]
 45%|████▌     | 168657/371472 [2:28:46<16:53:55,  3.33it/s]
 45%|████▌     | 168658/371472 [2:28:47<16:26:34,  3.43it/s]
 45%|████▌     | 168659/371472 [2:28:47<17:06:31,  3.29it/s]
 45%|████▌     | 168660/371472 [2:28:48<18:51:34,  2.99it/s]
                                                            
{'loss': 2.95, 'learning_rate': 5.916363205412743e-07, 'epoch': 7.26}
+
 45%|████▌     | 168660/371472 [2:28:48<18:51:34,  2.99it/s]
 45%|████▌     | 168661/371472 [2:28:48<17:44:51,  3.17it/s]
 45%|████▌     | 168662/371472 [2:28:48<17:26:55,  3.23it/s]
 45%|████▌     | 168663/371472 [2:28:48<17:03:41,  3.30it/s]
 45%|████▌     | 168664/371472 [2:28:49<18:20:09,  3.07it/s]
 45%|████▌     | 168665/371472 [2:28:49<17:27:29,  3.23it/s]
 45%|████▌     | 168666/371472 [2:28:49<16:46:05,  3.36it/s]
 45%|████▌     | 168667/371472 [2:28:50<16:53:30,  3.34it/s]
 45%|████▌     | 168668/371472 [2:28:50<16:49:48,  3.35it/s]
 45%|████▌     | 168669/371472 [2:28:50<16:37:05,  3.39it/s]
 45%|████▌     | 168670/371472 [2:28:50<16:22:51,  3.44it/s]
 45%|████▌     | 168671/371472 [2:28:51<17:01:24,  3.31it/s]
 45%|████▌     | 168672/371472 [2:28:51<16:46:00,  3.36it/s]
 45%|████▌     | 168673/371472 [2:28:51<16:49:10,  3.35it/s]
 45%|████▌     | 168674/371472 [2:28:52<16:21:15,  3.44it/s]
 45%|████▌     | 168675/371472 [2:28:52<16:36:50,  3.39it/s]
 45%|████▌     | 168676/371472 [2:28:52<16:58:26,  3.32it/s]
 45%|████▌     | 168677/371472 [2:28:53<16:39:19,  3.38it/s]
 45%|████▌     | 168678/371472 [2:28:53<16:44:23,  3.37it/s]
 45%|████▌     | 168679/371472 [2:28:53<16:34:03,  3.40it/s]
 45%|████▌     | 168680/371472 [2:28:53<16:31:19,  3.41it/s]
                                                            
{'loss': 2.9477, 'learning_rate': 5.915878385657955e-07, 'epoch': 7.27}
+
 45%|████▌     | 168680/371472 [2:28:53<16:31:19,  3.41it/s]
 45%|████▌     | 168681/371472 [2:28:54<16:18:30,  3.45it/s]
 45%|████▌     | 168682/371472 [2:28:54<16:47:31,  3.35it/s]
 45%|████▌     | 168683/371472 [2:28:54<16:24:38,  3.43it/s]
 45%|████▌     | 168684/371472 [2:28:55<17:17:08,  3.26it/s]
 45%|████▌     | 168685/371472 [2:28:55<17:03:34,  3.30it/s]
 45%|████▌     | 168686/371472 [2:28:55<17:06:13,  3.29it/s]
 45%|████▌     | 168687/371472 [2:28:56<18:11:13,  3.10it/s]
 45%|████▌     | 168688/371472 [2:28:56<17:57:38,  3.14it/s]
 45%|████▌     | 168689/371472 [2:28:56<17:40:00,  3.19it/s]
 45%|████▌     | 168690/371472 [2:28:57<17:20:49,  3.25it/s]
 45%|████▌     | 168691/371472 [2:28:57<17:10:22,  3.28it/s]
 45%|████▌     | 168692/371472 [2:28:57<17:11:50,  3.28it/s]
 45%|████▌     | 168693/371472 [2:28:57<16:35:58,  3.39it/s]
 45%|████▌     | 168694/371472 [2:28:58<16:29:57,  3.41it/s]
 45%|████▌     | 168695/371472 [2:28:58<16:12:12,  3.48it/s]
 45%|████▌     | 168696/371472 [2:28:58<16:15:32,  3.46it/s]
 45%|████▌     | 168697/371472 [2:28:59<16:00:20,  3.52it/s]
 45%|████▌     | 168698/371472 [2:28:59<16:07:48,  3.49it/s]
 45%|████▌     | 168699/371472 [2:28:59<16:10:40,  3.48it/s]
 45%|████▌     | 168700/371472 [2:28:59<15:56:04,  3.53it/s]
                                                            
{'loss': 3.0112, 'learning_rate': 5.915393565903165e-07, 'epoch': 7.27}
+
 45%|████▌     | 168700/371472 [2:28:59<15:56:04,  3.53it/s]
 45%|████▌     | 168701/371472 [2:29:00<16:04:46,  3.50it/s]
 45%|████▌     | 168702/371472 [2:29:00<15:55:00,  3.54it/s]
 45%|████▌     | 168703/371472 [2:29:00<15:40:44,  3.59it/s]
 45%|████▌     | 168704/371472 [2:29:00<15:52:27,  3.55it/s]
 45%|████▌     | 168705/371472 [2:29:01<16:27:45,  3.42it/s]
 45%|████▌     | 168706/371472 [2:29:01<16:13:38,  3.47it/s]
 45%|████▌     | 168707/371472 [2:29:01<15:53:19,  3.54it/s]
 45%|████▌     | 168708/371472 [2:29:02<15:43:31,  3.58it/s]
 45%|████▌     | 168709/371472 [2:29:02<16:05:24,  3.50it/s]
 45%|████▌     | 168710/371472 [2:29:02<15:47:59,  3.56it/s]
 45%|████▌     | 168711/371472 [2:29:03<16:41:46,  3.37it/s]
 45%|████▌     | 168712/371472 [2:29:03<16:27:40,  3.42it/s]
 45%|████▌     | 168713/371472 [2:29:03<16:12:19,  3.48it/s]
 45%|████▌     | 168714/371472 [2:29:03<16:12:21,  3.48it/s]
 45%|████▌     | 168715/371472 [2:29:04<16:10:02,  3.48it/s]
 45%|████▌     | 168716/371472 [2:29:04<15:31:57,  3.63it/s]
 45%|████▌     | 168717/371472 [2:29:04<16:17:10,  3.46it/s]
 45%|████▌     | 168718/371472 [2:29:05<16:23:19,  3.44it/s]
 45%|████▌     | 168719/371472 [2:29:05<16:23:05,  3.44it/s]
 45%|████▌     | 168720/371472 [2:29:05<17:09:51,  3.28it/s]
                                                            
{'loss': 2.9472, 'learning_rate': 5.914908746148375e-07, 'epoch': 7.27}
+
 45%|████▌     | 168720/371472 [2:29:05<17:09:51,  3.28it/s]
 45%|████▌     | 168721/371472 [2:29:05<16:30:55,  3.41it/s]
 45%|████▌     | 168722/371472 [2:29:06<17:32:50,  3.21it/s]
 45%|████▌     | 168723/371472 [2:29:06<17:34:33,  3.20it/s]
 45%|████▌     | 168724/371472 [2:29:06<17:10:28,  3.28it/s]
 45%|████▌     | 168725/371472 [2:29:07<16:39:18,  3.38it/s]
 45%|████▌     | 168726/371472 [2:29:07<16:46:01,  3.36it/s]
 45%|████▌     | 168727/371472 [2:29:07<16:18:51,  3.45it/s]
 45%|████▌     | 168728/371472 [2:29:08<16:39:49,  3.38it/s]
 45%|████▌     | 168729/371472 [2:29:08<16:51:30,  3.34it/s]
 45%|████▌     | 168730/371472 [2:29:08<17:38:26,  3.19it/s]
 45%|████▌     | 168731/371472 [2:29:08<17:01:41,  3.31it/s]
 45%|████▌     | 168732/371472 [2:29:09<16:49:38,  3.35it/s]
 45%|████▌     | 168733/371472 [2:29:09<16:21:53,  3.44it/s]
 45%|████▌     | 168734/371472 [2:29:09<17:23:26,  3.24it/s]
 45%|████▌     | 168735/371472 [2:29:10<17:01:36,  3.31it/s]
 45%|████▌     | 168736/371472 [2:29:10<16:53:16,  3.33it/s]
 45%|████▌     | 168737/371472 [2:29:10<16:53:37,  3.33it/s]
 45%|████▌     | 168738/371472 [2:29:11<18:11:18,  3.10it/s]
 45%|████▌     | 168739/371472 [2:29:11<17:49:13,  3.16it/s]
 45%|████▌     | 168740/371472 [2:29:11<17:23:45,  3.24it/s]
                                                            
{'loss': 2.9012, 'learning_rate': 5.914423926393587e-07, 'epoch': 7.27}
+
 45%|████▌     | 168740/371472 [2:29:11<17:23:45,  3.24it/s]
 45%|████▌     | 168741/371472 [2:29:12<18:11:40,  3.10it/s]
 45%|████▌     | 168742/371472 [2:29:12<18:49:40,  2.99it/s]
 45%|████▌     | 168743/371472 [2:29:12<18:01:58,  3.12it/s]
 45%|████▌     | 168744/371472 [2:29:13<17:31:11,  3.21it/s]
 45%|████▌     | 168745/371472 [2:29:13<17:06:37,  3.29it/s]
 45%|████▌     | 168746/371472 [2:29:13<16:13:30,  3.47it/s]
 45%|████▌     | 168747/371472 [2:29:13<16:22:21,  3.44it/s]
 45%|████▌     | 168748/371472 [2:29:14<16:34:12,  3.40it/s]
 45%|████▌     | 168749/371472 [2:29:14<16:15:12,  3.46it/s]
 45%|████▌     | 168750/371472 [2:29:14<16:48:24,  3.35it/s]
 45%|████▌     | 168751/371472 [2:29:15<17:39:27,  3.19it/s]
 45%|████▌     | 168752/371472 [2:29:15<17:23:48,  3.24it/s]
 45%|████▌     | 168753/371472 [2:29:15<17:29:28,  3.22it/s]
 45%|████▌     | 168754/371472 [2:29:16<17:10:49,  3.28it/s]
 45%|████▌     | 168755/371472 [2:29:16<16:39:40,  3.38it/s]
 45%|████▌     | 168756/371472 [2:29:16<16:24:45,  3.43it/s]
 45%|████▌     | 168757/371472 [2:29:16<16:26:12,  3.43it/s]
 45%|████▌     | 168758/371472 [2:29:17<16:50:48,  3.34it/s]
 45%|████▌     | 168759/371472 [2:29:17<16:54:55,  3.33it/s]
 45%|████▌     | 168760/371472 [2:29:17<18:28:06,  3.05it/s]
                                                            
{'loss': 2.878, 'learning_rate': 5.913939106638799e-07, 'epoch': 7.27}
+
 45%|████▌     | 168760/371472 [2:29:17<18:28:06,  3.05it/s]
 45%|████▌     | 168761/371472 [2:29:18<18:32:00,  3.04it/s]
 45%|████▌     | 168762/371472 [2:29:18<17:39:46,  3.19it/s]
 45%|████▌     | 168763/371472 [2:29:18<17:22:54,  3.24it/s]
 45%|████▌     | 168764/371472 [2:29:19<17:42:31,  3.18it/s]
 45%|████▌     | 168765/371472 [2:29:19<17:27:06,  3.23it/s]
 45%|████▌     | 168766/371472 [2:29:19<17:07:23,  3.29it/s]
 45%|████▌     | 168767/371472 [2:29:20<17:24:53,  3.23it/s]
 45%|████▌     | 168768/371472 [2:29:20<17:05:18,  3.29it/s]
 45%|████▌     | 168769/371472 [2:29:20<16:36:00,  3.39it/s]
 45%|████▌     | 168770/371472 [2:29:20<17:28:38,  3.22it/s]
 45%|████▌     | 168771/371472 [2:29:21<19:13:20,  2.93it/s]
 45%|████▌     | 168772/371472 [2:29:21<18:20:04,  3.07it/s]
 45%|████▌     | 168773/371472 [2:29:21<18:03:06,  3.12it/s]
 45%|████▌     | 168774/371472 [2:29:22<17:29:27,  3.22it/s]
 45%|████▌     | 168775/371472 [2:29:22<17:17:56,  3.25it/s]
 45%|████▌     | 168776/371472 [2:29:22<17:01:37,  3.31it/s]
 45%|████▌     | 168777/371472 [2:29:23<16:53:03,  3.33it/s]
 45%|████▌     | 168778/371472 [2:29:23<16:31:17,  3.41it/s]
 45%|████▌     | 168779/371472 [2:29:23<16:32:12,  3.40it/s]
 45%|████▌     | 168780/371472 [2:29:23<16:17:55,  3.45it/s]
                                                            
{'loss': 3.0647, 'learning_rate': 5.913454286884009e-07, 'epoch': 7.27}
+
 45%|████▌     | 168780/371472 [2:29:23<16:17:55,  3.45it/s]
 45%|████▌     | 168781/371472 [2:29:24<16:23:13,  3.44it/s]
 45%|████▌     | 168782/371472 [2:29:24<16:08:20,  3.49it/s]
 45%|████▌     | 168783/371472 [2:29:24<17:05:32,  3.29it/s]
 45%|████▌     | 168784/371472 [2:29:25<17:44:09,  3.17it/s]
 45%|████▌     | 168785/371472 [2:29:25<17:24:48,  3.23it/s]
 45%|████▌     | 168786/371472 [2:29:25<16:55:45,  3.33it/s]
 45%|████▌     | 168787/371472 [2:29:26<16:27:55,  3.42it/s]
 45%|████▌     | 168788/371472 [2:29:26<16:29:33,  3.41it/s]
 45%|████▌     | 168789/371472 [2:29:26<16:00:42,  3.52it/s]
 45%|████▌     | 168790/371472 [2:29:26<15:56:42,  3.53it/s]
 45%|████▌     | 168791/371472 [2:29:27<16:25:19,  3.43it/s]
 45%|████▌     | 168792/371472 [2:29:27<16:44:09,  3.36it/s]
 45%|████▌     | 168793/371472 [2:29:27<16:43:46,  3.37it/s]
 45%|████▌     | 168794/371472 [2:29:28<17:54:00,  3.15it/s]
 45%|████▌     | 168795/371472 [2:29:28<17:13:14,  3.27it/s]
 45%|████▌     | 168796/371472 [2:29:28<16:53:47,  3.33it/s]
 45%|████▌     | 168797/371472 [2:29:29<17:09:26,  3.28it/s]
 45%|████▌     | 168798/371472 [2:29:29<16:34:02,  3.40it/s]
 45%|████▌     | 168799/371472 [2:29:29<16:23:50,  3.43it/s]
 45%|████▌     | 168800/371472 [2:29:29<16:16:13,  3.46it/s]
                                                            
{'loss': 2.8986, 'learning_rate': 5.91296946712922e-07, 'epoch': 7.27}
+
 45%|████▌     | 168800/371472 [2:29:29<16:16:13,  3.46it/s]
 45%|████▌     | 168801/371472 [2:29:30<16:38:40,  3.38it/s]
 45%|████▌     | 168802/371472 [2:29:30<16:26:52,  3.42it/s]
 45%|████▌     | 168803/371472 [2:29:30<17:08:10,  3.29it/s]
 45%|████▌     | 168804/371472 [2:29:31<17:03:44,  3.30it/s]
 45%|████▌     | 168805/371472 [2:29:31<16:33:18,  3.40it/s]
 45%|████▌     | 168806/371472 [2:29:31<16:24:01,  3.43it/s]
 45%|████▌     | 168807/371472 [2:29:31<15:50:09,  3.55it/s]
 45%|████▌     | 168808/371472 [2:29:32<16:38:45,  3.38it/s]
 45%|████▌     | 168809/371472 [2:29:32<16:18:23,  3.45it/s]
 45%|████▌     | 168810/371472 [2:29:32<15:53:22,  3.54it/s]
 45%|████▌     | 168811/371472 [2:29:33<15:58:37,  3.52it/s]
 45%|████▌     | 168812/371472 [2:29:33<15:56:11,  3.53it/s]
 45%|████▌     | 168813/371472 [2:29:33<15:35:13,  3.61it/s]
 45%|████▌     | 168814/371472 [2:29:33<16:13:29,  3.47it/s]
 45%|████▌     | 168815/371472 [2:29:34<15:54:08,  3.54it/s]
 45%|████▌     | 168816/371472 [2:29:34<16:52:06,  3.34it/s]
 45%|████▌     | 168817/371472 [2:29:34<17:19:04,  3.25it/s]
 45%|████▌     | 168818/371472 [2:29:35<16:50:41,  3.34it/s]
 45%|████▌     | 168819/371472 [2:29:35<16:12:23,  3.47it/s]
 45%|████▌     | 168820/371472 [2:29:35<15:59:49,  3.52it/s]
                                                            
{'loss': 2.9061, 'learning_rate': 5.912484647374432e-07, 'epoch': 7.27}
+
 45%|████▌     | 168820/371472 [2:29:35<15:59:49,  3.52it/s]
 45%|████▌     | 168821/371472 [2:29:36<16:06:44,  3.49it/s]
 45%|████▌     | 168822/371472 [2:29:36<15:58:30,  3.52it/s]
 45%|████▌     | 168823/371472 [2:29:36<15:53:48,  3.54it/s]
 45%|████▌     | 168824/371472 [2:29:36<16:05:11,  3.50it/s]
 45%|████▌     | 168825/371472 [2:29:37<16:07:51,  3.49it/s]
 45%|████▌     | 168826/371472 [2:29:37<16:13:28,  3.47it/s]
 45%|████▌     | 168827/371472 [2:29:37<16:22:33,  3.44it/s]
 45%|████▌     | 168828/371472 [2:29:38<16:34:41,  3.40it/s]
 45%|████▌     | 168829/371472 [2:29:38<16:33:19,  3.40it/s]
 45%|████▌     | 168830/371472 [2:29:38<16:22:24,  3.44it/s]
 45%|████▌     | 168831/371472 [2:29:38<16:36:22,  3.39it/s]
 45%|████▌     | 168832/371472 [2:29:39<16:09:30,  3.48it/s]
 45%|████▌     | 168833/371472 [2:29:39<15:43:01,  3.58it/s]
 45%|████▌     | 168834/371472 [2:29:39<15:36:58,  3.60it/s]
 45%|████▌     | 168835/371472 [2:29:40<16:00:13,  3.52it/s]
 45%|████▌     | 168836/371472 [2:29:40<15:50:18,  3.55it/s]
 45%|████▌     | 168837/371472 [2:29:40<16:12:23,  3.47it/s]
 45%|████▌     | 168838/371472 [2:29:40<16:33:48,  3.40it/s]
 45%|████▌     | 168839/371472 [2:29:41<16:59:45,  3.31it/s]
 45%|████▌     | 168840/371472 [2:29:41<17:28:42,  3.22it/s]
                                                            
{'loss': 2.9105, 'learning_rate': 5.911999827619643e-07, 'epoch': 7.27}
+
 45%|████▌     | 168840/371472 [2:29:41<17:28:42,  3.22it/s]
 45%|████▌     | 168841/371472 [2:29:41<17:10:04,  3.28it/s]
 45%|████▌     | 168842/371472 [2:29:42<17:21:59,  3.24it/s]
 45%|████▌     | 168843/371472 [2:29:42<16:54:17,  3.33it/s]
 45%|████▌     | 168844/371472 [2:29:42<17:01:34,  3.31it/s]
 45%|████▌     | 168845/371472 [2:29:43<16:46:54,  3.35it/s]
 45%|████▌     | 168846/371472 [2:29:43<16:41:13,  3.37it/s]
 45%|████▌     | 168847/371472 [2:29:43<16:50:48,  3.34it/s]
 45%|████▌     | 168848/371472 [2:29:43<17:16:30,  3.26it/s]
 45%|████▌     | 168849/371472 [2:29:44<16:57:14,  3.32it/s]
 45%|████▌     | 168850/371472 [2:29:44<16:20:57,  3.44it/s]
 45%|████▌     | 168851/371472 [2:29:44<16:13:08,  3.47it/s]
 45%|████▌     | 168852/371472 [2:29:45<15:55:40,  3.53it/s]
 45%|████▌     | 168853/371472 [2:29:45<16:59:42,  3.31it/s]
 45%|████▌     | 168854/371472 [2:29:45<16:58:55,  3.31it/s]
 45%|████▌     | 168855/371472 [2:29:46<17:41:39,  3.18it/s]
 45%|████▌     | 168856/371472 [2:29:46<17:27:11,  3.22it/s]
 45%|████▌     | 168857/371472 [2:29:46<18:06:30,  3.11it/s]
 45%|████▌     | 168858/371472 [2:29:47<17:53:38,  3.15it/s]
 45%|████▌     | 168859/371472 [2:29:47<17:05:33,  3.29it/s]
 45%|████▌     | 168860/371472 [2:29:47<16:38:30,  3.38it/s]
                                                            
{'loss': 2.9233, 'learning_rate': 5.911515007864853e-07, 'epoch': 7.27}
+
 45%|████▌     | 168860/371472 [2:29:47<16:38:30,  3.38it/s]
 45%|████▌     | 168861/371472 [2:29:47<16:52:32,  3.34it/s]
 45%|████▌     | 168862/371472 [2:29:48<16:46:59,  3.35it/s]
 45%|████▌     | 168863/371472 [2:29:48<18:58:08,  2.97it/s]
 45%|████▌     | 168864/371472 [2:29:48<17:58:36,  3.13it/s]
 45%|████▌     | 168865/371472 [2:29:49<17:53:34,  3.15it/s]
 45%|████▌     | 168866/371472 [2:29:49<17:39:38,  3.19it/s]
 45%|████▌     | 168867/371472 [2:29:49<17:06:45,  3.29it/s]
 45%|████▌     | 168868/371472 [2:29:50<16:58:28,  3.32it/s]
 45%|████▌     | 168869/371472 [2:29:50<16:54:25,  3.33it/s]
 45%|████▌     | 168870/371472 [2:29:50<17:45:45,  3.17it/s]
 45%|████▌     | 168871/371472 [2:29:51<17:17:29,  3.25it/s]
 45%|████▌     | 168872/371472 [2:29:51<17:05:22,  3.29it/s]
 45%|████▌     | 168873/371472 [2:29:51<17:05:00,  3.29it/s]
 45%|████▌     | 168874/371472 [2:29:51<16:32:24,  3.40it/s]
 45%|████▌     | 168875/371472 [2:29:52<16:06:10,  3.49it/s]
 45%|████▌     | 168876/371472 [2:29:52<16:34:38,  3.39it/s]
 45%|████▌     | 168877/371472 [2:29:52<16:13:19,  3.47it/s]
 45%|████▌     | 168878/371472 [2:29:53<15:59:36,  3.52it/s]
 45%|████▌     | 168879/371472 [2:29:53<16:47:06,  3.35it/s]
 45%|████▌     | 168880/371472 [2:29:53<16:50:32,  3.34it/s]
                                                            
{'loss': 2.8147, 'learning_rate': 5.911030188110064e-07, 'epoch': 7.27}
+
 45%|████▌     | 168880/371472 [2:29:53<16:50:32,  3.34it/s]
 45%|████▌     | 168881/371472 [2:29:53<16:52:08,  3.34it/s]
 45%|████▌     | 168882/371472 [2:29:54<18:22:02,  3.06it/s]
 45%|████▌     | 168883/371472 [2:29:54<17:42:21,  3.18it/s]
 45%|████▌     | 168884/371472 [2:29:54<17:31:36,  3.21it/s]
 45%|████▌     | 168885/371472 [2:29:55<16:49:07,  3.35it/s]
 45%|████▌     | 168886/371472 [2:29:55<17:22:30,  3.24it/s]
 45%|████▌     | 168887/371472 [2:29:55<17:20:06,  3.25it/s]
 45%|████▌     | 168888/371472 [2:29:56<16:45:48,  3.36it/s]
 45%|████▌     | 168889/371472 [2:29:56<16:23:08,  3.43it/s]
 45%|████▌     | 168890/371472 [2:29:56<16:16:09,  3.46it/s]
 45%|████▌     | 168891/371472 [2:29:56<16:15:58,  3.46it/s]
 45%|████▌     | 168892/371472 [2:29:57<16:27:20,  3.42it/s]
 45%|████▌     | 168893/371472 [2:29:57<16:08:32,  3.49it/s]
 45%|████▌     | 168894/371472 [2:29:57<16:26:52,  3.42it/s]
 45%|████▌     | 168895/371472 [2:29:58<17:35:49,  3.20it/s]
 45%|████▌     | 168896/371472 [2:29:58<18:13:14,  3.09it/s]
 45%|████▌     | 168897/371472 [2:29:58<17:38:48,  3.19it/s]
 45%|████▌     | 168898/371472 [2:29:59<17:41:30,  3.18it/s]
 45%|████▌     | 168899/371472 [2:29:59<18:12:44,  3.09it/s]
 45%|████▌     | 168900/371472 [2:29:59<17:36:48,  3.19it/s]
                                                            
{'loss': 2.9303, 'learning_rate': 5.910545368355276e-07, 'epoch': 7.27}
+
 45%|████▌     | 168900/371472 [2:29:59<17:36:48,  3.19it/s]
 45%|████▌     | 168901/371472 [2:30:00<17:07:09,  3.29it/s]
 45%|████▌     | 168902/371472 [2:30:00<17:54:03,  3.14it/s]
 45%|████▌     | 168903/371472 [2:30:00<18:57:16,  2.97it/s]
 45%|████▌     | 168904/371472 [2:30:01<17:53:57,  3.14it/s]
 45%|████▌     | 168905/371472 [2:30:01<17:09:28,  3.28it/s]
 45%|████▌     | 168906/371472 [2:30:01<17:26:13,  3.23it/s]
 45%|████▌     | 168907/371472 [2:30:01<16:56:47,  3.32it/s]
 45%|████▌     | 168908/371472 [2:30:02<17:30:38,  3.21it/s]
 45%|████▌     | 168909/371472 [2:30:02<17:15:40,  3.26it/s]
 45%|████▌     | 168910/371472 [2:30:02<17:01:17,  3.31it/s]
 45%|████▌     | 168911/371472 [2:30:03<16:53:39,  3.33it/s]
 45%|████▌     | 168912/371472 [2:30:03<16:34:13,  3.40it/s]
 45%|████▌     | 168913/371472 [2:30:03<16:07:38,  3.49it/s]
 45%|████▌     | 168914/371472 [2:30:04<16:45:15,  3.36it/s]
 45%|████▌     | 168915/371472 [2:30:04<16:22:53,  3.43it/s]
 45%|████▌     | 168916/371472 [2:30:04<17:01:51,  3.30it/s]
 45%|████▌     | 168917/371472 [2:30:04<16:43:00,  3.37it/s]
 45%|████▌     | 168918/371472 [2:30:05<17:44:54,  3.17it/s]
 45%|████▌     | 168919/371472 [2:30:05<17:03:27,  3.30it/s]
 45%|████▌     | 168920/371472 [2:30:05<16:46:23,  3.35it/s]
                                                            
{'loss': 2.9242, 'learning_rate': 5.910060548600487e-07, 'epoch': 7.28}
+
 45%|████▌     | 168920/371472 [2:30:05<16:46:23,  3.35it/s]
 45%|████▌     | 168921/371472 [2:30:06<18:07:45,  3.10it/s]
 45%|████▌     | 168922/371472 [2:30:06<17:33:46,  3.20it/s]
 45%|████▌     | 168923/371472 [2:30:06<17:21:18,  3.24it/s]
 45%|████▌     | 168924/371472 [2:30:07<16:42:34,  3.37it/s]
 45%|████▌     | 168925/371472 [2:30:07<16:45:24,  3.36it/s]
 45%|████▌     | 168926/371472 [2:30:07<16:36:30,  3.39it/s]
 45%|████▌     | 168927/371472 [2:30:07<16:35:17,  3.39it/s]
 45%|████▌     | 168928/371472 [2:30:08<16:20:38,  3.44it/s]
 45%|████▌     | 168929/371472 [2:30:08<16:50:40,  3.34it/s]
 45%|████▌     | 168930/371472 [2:30:08<16:25:04,  3.43it/s]
 45%|████▌     | 168931/371472 [2:30:09<16:09:55,  3.48it/s]
 45%|████▌     | 168932/371472 [2:30:09<16:23:28,  3.43it/s]
 45%|████▌     | 168933/371472 [2:30:09<16:27:18,  3.42it/s]
 45%|████▌     | 168934/371472 [2:30:09<16:03:17,  3.50it/s]
 45%|████▌     | 168935/371472 [2:30:10<15:57:47,  3.52it/s]
 45%|████▌     | 168936/371472 [2:30:10<16:07:09,  3.49it/s]
 45%|████▌     | 168937/371472 [2:30:10<15:57:58,  3.52it/s]
 45%|████▌     | 168938/371472 [2:30:11<16:14:18,  3.46it/s]
 45%|████▌     | 168939/371472 [2:30:11<16:07:29,  3.49it/s]
 45%|████▌     | 168940/371472 [2:30:11<17:26:06,  3.23it/s]
                                                            
{'loss': 3.0085, 'learning_rate': 5.909575728845698e-07, 'epoch': 7.28}
+
 45%|████▌     | 168940/371472 [2:30:11<17:26:06,  3.23it/s]
 45%|████▌     | 168941/371472 [2:30:12<17:08:50,  3.28it/s]
 45%|████▌     | 168942/371472 [2:30:12<17:06:59,  3.29it/s]
 45%|████▌     | 168943/371472 [2:30:12<16:51:22,  3.34it/s]
 45%|████▌     | 168944/371472 [2:30:12<16:36:35,  3.39it/s]
 45%|████▌     | 168945/371472 [2:30:13<17:51:26,  3.15it/s]
 45%|████▌     | 168946/371472 [2:30:13<17:58:54,  3.13it/s]
 45%|████▌     | 168947/371472 [2:30:13<17:49:16,  3.16it/s]
 45%|████▌     | 168948/371472 [2:30:14<17:30:33,  3.21it/s]
 45%|████▌     | 168949/371472 [2:30:14<17:08:09,  3.28it/s]
 45%|████▌     | 168950/371472 [2:30:14<16:36:27,  3.39it/s]
 45%|████▌     | 168951/371472 [2:30:15<17:03:23,  3.30it/s]
 45%|████▌     | 168952/371472 [2:30:15<16:45:44,  3.36it/s]
 45%|████▌     | 168953/371472 [2:30:15<16:40:38,  3.37it/s]
 45%|████▌     | 168954/371472 [2:30:16<16:34:05,  3.40it/s]
 45%|████▌     | 168955/371472 [2:30:16<16:29:00,  3.41it/s]
 45%|████▌     | 168956/371472 [2:30:16<16:14:57,  3.46it/s]
 45%|████▌     | 168957/371472 [2:30:16<16:57:54,  3.32it/s]
 45%|████▌     | 168958/371472 [2:30:17<17:05:03,  3.29it/s]
 45%|████▌     | 168959/371472 [2:30:17<18:30:10,  3.04it/s]
 45%|████▌     | 168960/371472 [2:30:17<18:52:03,  2.98it/s]
                                                            
{'loss': 2.872, 'learning_rate': 5.909090909090909e-07, 'epoch': 7.28}
+
 45%|████▌     | 168960/371472 [2:30:17<18:52:03,  2.98it/s]
 45%|████▌     | 168961/371472 [2:30:18<17:45:40,  3.17it/s]
 45%|████▌     | 168962/371472 [2:30:18<17:58:38,  3.13it/s]
 45%|████▌     | 168963/371472 [2:30:18<17:22:57,  3.24it/s]
 45%|████▌     | 168964/371472 [2:30:19<16:55:25,  3.32it/s]
 45%|████▌     | 168965/371472 [2:30:19<17:20:24,  3.24it/s]
 45%|████▌     | 168966/371472 [2:30:19<16:58:15,  3.31it/s]
 45%|████▌     | 168967/371472 [2:30:20<16:32:08,  3.40it/s]
 45%|████▌     | 168968/371472 [2:30:20<16:34:03,  3.40it/s]
 45%|████▌     | 168969/371472 [2:30:20<16:32:23,  3.40it/s]
 45%|████▌     | 168970/371472 [2:30:20<16:47:19,  3.35it/s]
 45%|████▌     | 168971/371472 [2:30:21<16:32:36,  3.40it/s]
 45%|████▌     | 168972/371472 [2:30:21<16:01:21,  3.51it/s]
 45%|████▌     | 168973/371472 [2:30:21<16:03:23,  3.50it/s]
 45%|████▌     | 168974/371472 [2:30:22<16:41:27,  3.37it/s]
 45%|████▌     | 168975/371472 [2:30:22<17:08:46,  3.28it/s]
 45%|████▌     | 168976/371472 [2:30:22<16:57:47,  3.32it/s]
 45%|████▌     | 168977/371472 [2:30:22<16:32:55,  3.40it/s]
 45%|████▌     | 168978/371472 [2:30:23<16:30:03,  3.41it/s]
 45%|████▌     | 168979/371472 [2:30:23<17:09:46,  3.28it/s]
 45%|████▌     | 168980/371472 [2:30:23<17:22:30,  3.24it/s]
                                                            
{'loss': 2.9409, 'learning_rate': 5.90860608933612e-07, 'epoch': 7.28}
+
 45%|████▌     | 168980/371472 [2:30:23<17:22:30,  3.24it/s]
 45%|████▌     | 168981/371472 [2:30:24<17:17:17,  3.25it/s]
 45%|████▌     | 168982/371472 [2:30:24<16:48:39,  3.35it/s]
 45%|████▌     | 168983/371472 [2:30:24<17:54:29,  3.14it/s]
 45%|████▌     | 168984/371472 [2:30:25<17:34:15,  3.20it/s]
 45%|████▌     | 168985/371472 [2:30:25<17:13:42,  3.26it/s]
 45%|████▌     | 168986/371472 [2:30:25<18:07:41,  3.10it/s]
 45%|████▌     | 168987/371472 [2:30:26<17:09:51,  3.28it/s]
 45%|████▌     | 168988/371472 [2:30:26<18:09:16,  3.10it/s]
 45%|████▌     | 168989/371472 [2:30:26<17:23:37,  3.23it/s]
 45%|████▌     | 168990/371472 [2:30:27<17:40:28,  3.18it/s]
 45%|████▌     | 168991/371472 [2:30:27<17:20:30,  3.24it/s]
 45%|████▌     | 168992/371472 [2:30:27<17:20:56,  3.24it/s]
 45%|████▌     | 168993/371472 [2:30:27<17:04:41,  3.29it/s]
 45%|████▌     | 168994/371472 [2:30:28<16:51:44,  3.34it/s]
 45%|████▌     | 168995/371472 [2:30:28<17:01:02,  3.31it/s]
 45%|████▌     | 168996/371472 [2:30:28<16:48:42,  3.35it/s]
 45%|████▌     | 168997/371472 [2:30:29<16:28:22,  3.41it/s]
 45%|████▌     | 168998/371472 [2:30:29<16:56:57,  3.32it/s]
 45%|████▌     | 168999/371472 [2:30:29<17:06:19,  3.29it/s]
 45%|████▌     | 169000/371472 [2:30:30<17:00:31,  3.31it/s]
                                                            
{'loss': 3.0711, 'learning_rate': 5.908121269581331e-07, 'epoch': 7.28}
+
 45%|████▌     | 169000/371472 [2:30:30<17:00:31,  3.31it/s]
 45%|████▌     | 169001/371472 [2:30:30<17:19:39,  3.25it/s]
 45%|████▌     | 169002/371472 [2:30:30<17:38:51,  3.19it/s]
 45%|████▌     | 169003/371472 [2:30:30<17:29:16,  3.22it/s]
 45%|████▌     | 169004/371472 [2:30:31<17:01:35,  3.30it/s]
 45%|████▌     | 169005/371472 [2:30:31<17:25:29,  3.23it/s]
 45%|████▌     | 169006/371472 [2:30:31<18:13:14,  3.09it/s]
 45%|████▌     | 169007/371472 [2:30:32<18:23:13,  3.06it/s]
 45%|████▌     | 169008/371472 [2:30:32<17:51:33,  3.15it/s]
 45%|████▌     | 169009/371472 [2:30:32<17:16:03,  3.26it/s]
 45%|████▌     | 169010/371472 [2:30:33<16:55:03,  3.32it/s]
 45%|████▌     | 169011/371472 [2:30:33<16:56:21,  3.32it/s]
 45%|████▌     | 169012/371472 [2:30:33<17:05:59,  3.29it/s]
 45%|████▌     | 169013/371472 [2:30:34<16:34:35,  3.39it/s]
 45%|████▌     | 169014/371472 [2:30:34<16:31:49,  3.40it/s]
 45%|████▌     | 169015/371472 [2:30:34<15:58:31,  3.52it/s]
 45%|████▌     | 169016/371472 [2:30:34<15:49:05,  3.56it/s]
 45%|████▌     | 169017/371472 [2:30:35<16:06:26,  3.49it/s]
 45%|████▌     | 169018/371472 [2:30:35<16:55:38,  3.32it/s]
 45%|████▌     | 169019/371472 [2:30:35<17:19:05,  3.25it/s]
 46%|████▌     | 169020/371472 [2:30:36<16:46:55,  3.35it/s]
                                                            
{'loss': 3.0192, 'learning_rate': 5.907636449826542e-07, 'epoch': 7.28}
+
 46%|████▌     | 169020/371472 [2:30:36<16:46:55,  3.35it/s]
 46%|████▌     | 169021/371472 [2:30:36<16:44:23,  3.36it/s]
 46%|████▌     | 169022/371472 [2:30:36<16:41:06,  3.37it/s]
 46%|████▌     | 169023/371472 [2:30:36<16:15:12,  3.46it/s]
 46%|████▌     | 169024/371472 [2:30:37<16:23:26,  3.43it/s]
 46%|████▌     | 169025/371472 [2:30:37<16:18:52,  3.45it/s]
 46%|████▌     | 169026/371472 [2:30:37<16:59:46,  3.31it/s]
 46%|████▌     | 169027/371472 [2:30:38<16:41:37,  3.37it/s]
 46%|████▌     | 169028/371472 [2:30:38<16:19:44,  3.44it/s]
 46%|████▌     | 169029/371472 [2:30:38<16:03:13,  3.50it/s]
 46%|████▌     | 169030/371472 [2:30:39<16:35:05,  3.39it/s]
 46%|████▌     | 169031/371472 [2:30:39<16:41:45,  3.37it/s]
 46%|████▌     | 169032/371472 [2:30:39<17:17:06,  3.25it/s]
 46%|████▌     | 169033/371472 [2:30:39<16:39:57,  3.37it/s]
 46%|████▌     | 169034/371472 [2:30:40<16:27:05,  3.42it/s]
 46%|████▌     | 169035/371472 [2:30:40<16:19:54,  3.44it/s]
 46%|████▌     | 169036/371472 [2:30:40<16:06:29,  3.49it/s]
 46%|████▌     | 169037/371472 [2:30:41<16:09:03,  3.48it/s]
 46%|████▌     | 169038/371472 [2:30:41<17:34:03,  3.20it/s]
 46%|████▌     | 169039/371472 [2:30:41<17:14:57,  3.26it/s]
 46%|████▌     | 169040/371472 [2:30:42<17:29:19,  3.22it/s]
                                                            
{'loss': 2.9171, 'learning_rate': 5.907151630071753e-07, 'epoch': 7.28}
+
 46%|████▌     | 169040/371472 [2:30:42<17:29:19,  3.22it/s]
 46%|████▌     | 169041/371472 [2:30:42<16:55:40,  3.32it/s]
 46%|████▌     | 169042/371472 [2:30:42<17:35:44,  3.20it/s]
 46%|████▌     | 169043/371472 [2:30:42<17:01:41,  3.30it/s]
 46%|████▌     | 169044/371472 [2:30:43<16:54:42,  3.32it/s]
 46%|████▌     | 169045/371472 [2:30:43<16:49:34,  3.34it/s]
 46%|████▌     | 169046/371472 [2:30:43<16:30:18,  3.41it/s]
 46%|████▌     | 169047/371472 [2:30:44<16:31:58,  3.40it/s]
 46%|████▌     | 169048/371472 [2:30:44<17:35:59,  3.19it/s]
 46%|████▌     | 169049/371472 [2:30:44<17:46:28,  3.16it/s]
 46%|████▌     | 169050/371472 [2:30:45<17:42:10,  3.18it/s]
 46%|████▌     | 169051/371472 [2:30:45<17:40:54,  3.18it/s]
 46%|████▌     | 169052/371472 [2:30:45<17:14:26,  3.26it/s]
 46%|████▌     | 169053/371472 [2:30:46<17:17:40,  3.25it/s]
 46%|████▌     | 169054/371472 [2:30:46<16:44:29,  3.36it/s]
 46%|████▌     | 169055/371472 [2:30:46<16:50:20,  3.34it/s]
 46%|████▌     | 169056/371472 [2:30:46<16:31:46,  3.40it/s]
 46%|████▌     | 169057/371472 [2:30:47<17:39:51,  3.18it/s]
 46%|████▌     | 169058/371472 [2:30:47<17:07:46,  3.28it/s]
 46%|████▌     | 169059/371472 [2:30:47<17:09:22,  3.28it/s]
 46%|████▌     | 169060/371472 [2:30:48<17:59:11,  3.13it/s]
                                                            
{'loss': 2.8123, 'learning_rate': 5.906666810316965e-07, 'epoch': 7.28}
+
 46%|████▌     | 169060/371472 [2:30:48<17:59:11,  3.13it/s]
 46%|████▌     | 169061/371472 [2:30:48<17:42:40,  3.17it/s]
 46%|████▌     | 169062/371472 [2:30:48<17:20:07,  3.24it/s]
 46%|████▌     | 169063/371472 [2:30:49<16:55:46,  3.32it/s]
 46%|████▌     | 169064/371472 [2:30:49<16:35:02,  3.39it/s]
 46%|████▌     | 169065/371472 [2:30:49<17:19:11,  3.25it/s]
 46%|████▌     | 169066/371472 [2:30:49<16:50:02,  3.34it/s]
 46%|████▌     | 169067/371472 [2:30:50<16:25:10,  3.42it/s]
 46%|████▌     | 169068/371472 [2:30:50<16:14:38,  3.46it/s]
 46%|████▌     | 169069/371472 [2:30:50<16:25:43,  3.42it/s]
 46%|████▌     | 169070/371472 [2:30:51<17:11:26,  3.27it/s]
 46%|████▌     | 169071/371472 [2:30:51<17:46:21,  3.16it/s]
 46%|████▌     | 169072/371472 [2:30:51<17:22:28,  3.24it/s]
 46%|████▌     | 169073/371472 [2:30:52<16:43:51,  3.36it/s]
 46%|████▌     | 169074/371472 [2:30:52<16:36:24,  3.39it/s]
 46%|████▌     | 169075/371472 [2:30:52<16:12:41,  3.47it/s]
 46%|████▌     | 169076/371472 [2:30:52<17:18:39,  3.25it/s]
 46%|████▌     | 169077/371472 [2:30:53<16:39:25,  3.38it/s]
 46%|████▌     | 169078/371472 [2:30:53<17:35:57,  3.19it/s]
 46%|████▌     | 169079/371472 [2:30:53<17:20:45,  3.24it/s]
 46%|████▌     | 169080/371472 [2:30:54<17:04:29,  3.29it/s]
                                                            
{'loss': 3.0775, 'learning_rate': 5.906181990562176e-07, 'epoch': 7.28}
+
 46%|████▌     | 169080/371472 [2:30:54<17:04:29,  3.29it/s]
 46%|████▌     | 169081/371472 [2:30:54<16:41:49,  3.37it/s]
 46%|████▌     | 169082/371472 [2:30:54<17:11:36,  3.27it/s]
 46%|████▌     | 169083/371472 [2:30:55<16:40:56,  3.37it/s]
 46%|████▌     | 169084/371472 [2:30:55<16:48:43,  3.34it/s]
 46%|████▌     | 169085/371472 [2:30:55<17:14:14,  3.26it/s]
 46%|████▌     | 169086/371472 [2:30:56<18:18:14,  3.07it/s]
 46%|████▌     | 169087/371472 [2:30:56<18:19:00,  3.07it/s]
 46%|████▌     | 169088/371472 [2:30:56<18:08:56,  3.10it/s]
 46%|████▌     | 169089/371472 [2:30:57<18:00:19,  3.12it/s]
 46%|████▌     | 169090/371472 [2:30:57<17:30:43,  3.21it/s]
 46%|████▌     | 169091/371472 [2:30:57<17:20:05,  3.24it/s]
 46%|████▌     | 169092/371472 [2:30:57<17:07:47,  3.28it/s]
 46%|████▌     | 169093/371472 [2:30:58<17:51:07,  3.15it/s]
 46%|████▌     | 169094/371472 [2:30:58<17:35:59,  3.19it/s]
 46%|████▌     | 169095/371472 [2:30:58<17:24:41,  3.23it/s]
 46%|████▌     | 169096/371472 [2:30:59<17:10:38,  3.27it/s]
 46%|████▌     | 169097/371472 [2:30:59<16:36:30,  3.38it/s]
 46%|████▌     | 169098/371472 [2:30:59<16:32:28,  3.40it/s]
 46%|████▌     | 169099/371472 [2:31:00<16:28:21,  3.41it/s]
 46%|████▌     | 169100/371472 [2:31:00<17:37:34,  3.19it/s]
                                                            
{'loss': 2.7945, 'learning_rate': 5.905697170807385e-07, 'epoch': 7.28}
+
 46%|████▌     | 169100/371472 [2:31:00<17:37:34,  3.19it/s]
 46%|████▌     | 169101/371472 [2:31:00<17:01:42,  3.30it/s]
 46%|████▌     | 169102/371472 [2:31:00<16:26:57,  3.42it/s]
 46%|████▌     | 169103/371472 [2:31:01<16:00:37,  3.51it/s]
 46%|████▌     | 169104/371472 [2:31:01<16:23:17,  3.43it/s]
 46%|████▌     | 169105/371472 [2:31:01<16:35:01,  3.39it/s]
 46%|████▌     | 169106/371472 [2:31:02<17:15:57,  3.26it/s]
 46%|████▌     | 169107/371472 [2:31:02<17:30:18,  3.21it/s]
 46%|████▌     | 169108/371472 [2:31:02<17:45:25,  3.17it/s]
 46%|████▌     | 169109/371472 [2:31:03<17:12:59,  3.27it/s]
 46%|████▌     | 169110/371472 [2:31:03<17:24:25,  3.23it/s]
 46%|████▌     | 169111/371472 [2:31:03<17:10:35,  3.27it/s]
 46%|████▌     | 169112/371472 [2:31:03<16:44:13,  3.36it/s]
 46%|████▌     | 169113/371472 [2:31:04<17:03:01,  3.30it/s]
 46%|████▌     | 169114/371472 [2:31:04<16:44:07,  3.36it/s]
 46%|████▌     | 169115/371472 [2:31:04<17:17:11,  3.25it/s]
 46%|████▌     | 169116/371472 [2:31:05<16:39:40,  3.37it/s]
 46%|████▌     | 169117/371472 [2:31:05<16:37:41,  3.38it/s]
 46%|████▌     | 169118/371472 [2:31:05<17:36:30,  3.19it/s]
 46%|████▌     | 169119/371472 [2:31:06<17:41:48,  3.18it/s]
 46%|████▌     | 169120/371472 [2:31:06<17:42:16,  3.17it/s]
                                                            
{'loss': 2.7648, 'learning_rate': 5.905212351052597e-07, 'epoch': 7.28}
+
 46%|████▌     | 169120/371472 [2:31:06<17:42:16,  3.17it/s]
 46%|████▌     | 169121/371472 [2:31:06<17:38:24,  3.19it/s]
 46%|████▌     | 169122/371472 [2:31:07<17:18:44,  3.25it/s]
 46%|████▌     | 169123/371472 [2:31:07<18:28:38,  3.04it/s]
 46%|████▌     | 169124/371472 [2:31:07<18:22:31,  3.06it/s]
 46%|████▌     | 169125/371472 [2:31:08<17:42:17,  3.17it/s]
 46%|████▌     | 169126/371472 [2:31:08<17:15:20,  3.26it/s]
 46%|████▌     | 169127/371472 [2:31:08<16:48:22,  3.34it/s]
 46%|████▌     | 169128/371472 [2:31:08<16:45:00,  3.36it/s]
 46%|████▌     | 169129/371472 [2:31:09<16:20:58,  3.44it/s]
 46%|████▌     | 169130/371472 [2:31:09<17:55:20,  3.14it/s]
 46%|████▌     | 169131/371472 [2:31:09<17:21:47,  3.24it/s]
 46%|████▌     | 169132/371472 [2:31:10<16:47:20,  3.35it/s]
 46%|████▌     | 169133/371472 [2:31:10<16:33:13,  3.40it/s]
 46%|████▌     | 169134/371472 [2:31:10<17:18:08,  3.25it/s]
 46%|████▌     | 169135/371472 [2:31:11<16:48:09,  3.35it/s]
 46%|████▌     | 169136/371472 [2:31:11<17:37:27,  3.19it/s]
 46%|████▌     | 169137/371472 [2:31:11<17:02:26,  3.30it/s]
 46%|████▌     | 169138/371472 [2:31:11<16:44:01,  3.36it/s]
 46%|████▌     | 169139/371472 [2:31:12<16:32:01,  3.40it/s]
 46%|████▌     | 169140/371472 [2:31:12<16:41:29,  3.37it/s]
                                                            
{'loss': 2.9796, 'learning_rate': 5.904727531297809e-07, 'epoch': 7.29}
+
 46%|████▌     | 169140/371472 [2:31:12<16:41:29,  3.37it/s]
 46%|████▌     | 169141/371472 [2:31:12<16:23:07,  3.43it/s]
 46%|████▌     | 169142/371472 [2:31:13<16:19:22,  3.44it/s]
 46%|████▌     | 169143/371472 [2:31:13<16:59:30,  3.31it/s]
 46%|████▌     | 169144/371472 [2:31:13<17:02:43,  3.30it/s]
 46%|████▌     | 169145/371472 [2:31:14<18:04:37,  3.11it/s]
 46%|████▌     | 169146/371472 [2:31:14<17:23:31,  3.23it/s]
 46%|████▌     | 169147/371472 [2:31:14<17:48:19,  3.16it/s]
 46%|████▌     | 169148/371472 [2:31:15<17:39:54,  3.18it/s]
 46%|████▌     | 169149/371472 [2:31:15<17:19:16,  3.24it/s]
 46%|████▌     | 169150/371472 [2:31:15<17:00:21,  3.30it/s]
 46%|████▌     | 169151/371472 [2:31:15<16:47:02,  3.35it/s]
 46%|████▌     | 169152/371472 [2:31:16<16:30:39,  3.40it/s]
 46%|████▌     | 169153/371472 [2:31:16<16:24:27,  3.43it/s]
 46%|████▌     | 169154/371472 [2:31:16<18:26:25,  3.05it/s]
 46%|████▌     | 169155/371472 [2:31:17<18:16:12,  3.08it/s]
 46%|████▌     | 169156/371472 [2:31:17<17:17:52,  3.25it/s]
 46%|████▌     | 169157/371472 [2:31:17<17:05:23,  3.29it/s]
 46%|████▌     | 169158/371472 [2:31:18<17:20:39,  3.24it/s]
 46%|████▌     | 169159/371472 [2:31:18<16:56:02,  3.32it/s]
 46%|████▌     | 169160/371472 [2:31:18<16:33:54,  3.39it/s]
                                                            
{'loss': 2.8709, 'learning_rate': 5.904242711543019e-07, 'epoch': 7.29}
+
 46%|████▌     | 169160/371472 [2:31:18<16:33:54,  3.39it/s]
 46%|████▌     | 169161/371472 [2:31:18<16:56:32,  3.32it/s]
 46%|████▌     | 169162/371472 [2:31:19<16:44:38,  3.36it/s]
 46%|████▌     | 169163/371472 [2:31:19<16:21:09,  3.44it/s]
 46%|████▌     | 169164/371472 [2:31:19<16:12:47,  3.47it/s]
 46%|████▌     | 169165/371472 [2:31:20<16:19:03,  3.44it/s]
 46%|████▌     | 169166/371472 [2:31:20<16:14:28,  3.46it/s]
 46%|████▌     | 169167/371472 [2:31:20<16:16:56,  3.45it/s]
 46%|████▌     | 169168/371472 [2:31:21<17:11:42,  3.27it/s]
 46%|████▌     | 169169/371472 [2:31:21<16:59:59,  3.31it/s]
 46%|████▌     | 169170/371472 [2:31:21<16:45:53,  3.35it/s]
 46%|████▌     | 169171/371472 [2:31:21<16:27:00,  3.42it/s]
 46%|████▌     | 169172/371472 [2:31:22<15:51:37,  3.54it/s]
 46%|████▌     | 169173/371472 [2:31:22<16:12:37,  3.47it/s]
 46%|████▌     | 169174/371472 [2:31:22<15:57:11,  3.52it/s]
 46%|████▌     | 169175/371472 [2:31:22<15:50:17,  3.55it/s]
 46%|████▌     | 169176/371472 [2:31:23<16:09:22,  3.48it/s]
 46%|████▌     | 169177/371472 [2:31:23<15:50:55,  3.55it/s]
 46%|████▌     | 169178/371472 [2:31:23<17:56:17,  3.13it/s]
 46%|████▌     | 169179/371472 [2:31:24<17:03:08,  3.30it/s]
 46%|████▌     | 169180/371472 [2:31:24<17:25:56,  3.22it/s]
                                                            
{'loss': 2.9439, 'learning_rate': 5.90375789178823e-07, 'epoch': 7.29}
+
 46%|████▌     | 169180/371472 [2:31:24<17:25:56,  3.22it/s]
 46%|████▌     | 169181/371472 [2:31:24<16:50:07,  3.34it/s]
 46%|████▌     | 169182/371472 [2:31:25<16:34:33,  3.39it/s]
 46%|████▌     | 169183/371472 [2:31:25<16:52:55,  3.33it/s]
 46%|████▌     | 169184/371472 [2:31:25<16:36:53,  3.38it/s]
 46%|████▌     | 169185/371472 [2:31:26<17:31:06,  3.21it/s]
 46%|████▌     | 169186/371472 [2:31:26<16:43:59,  3.36it/s]
 46%|████▌     | 169187/371472 [2:31:26<16:33:56,  3.39it/s]
 46%|████▌     | 169188/371472 [2:31:26<16:14:16,  3.46it/s]
 46%|████▌     | 169189/371472 [2:31:27<16:07:01,  3.49it/s]
 46%|████▌     | 169190/371472 [2:31:27<17:34:24,  3.20it/s]
 46%|████▌     | 169191/371472 [2:31:27<17:37:59,  3.19it/s]
 46%|████▌     | 169192/371472 [2:31:28<17:16:44,  3.25it/s]
 46%|████▌     | 169193/371472 [2:31:28<16:56:19,  3.32it/s]
 46%|████▌     | 169194/371472 [2:31:28<16:34:48,  3.39it/s]
 46%|████▌     | 169195/371472 [2:31:29<16:58:45,  3.31it/s]
 46%|████▌     | 169196/371472 [2:31:29<16:43:08,  3.36it/s]
 46%|████▌     | 169197/371472 [2:31:29<17:00:41,  3.30it/s]
 46%|████▌     | 169198/371472 [2:31:29<16:43:13,  3.36it/s]
 46%|████▌     | 169199/371472 [2:31:30<16:52:18,  3.33it/s]
 46%|████▌     | 169200/371472 [2:31:30<16:54:19,  3.32it/s]
                                                            
{'loss': 2.8146, 'learning_rate': 5.903273072033443e-07, 'epoch': 7.29}
+
 46%|████▌     | 169200/371472 [2:31:30<16:54:19,  3.32it/s]
 46%|████▌     | 169201/371472 [2:31:30<16:48:02,  3.34it/s]
 46%|████▌     | 169202/371472 [2:31:31<16:42:26,  3.36it/s]
 46%|████▌     | 169203/371472 [2:31:31<16:19:22,  3.44it/s]
 46%|████▌     | 169204/371472 [2:31:31<16:23:06,  3.43it/s]
 46%|████▌     | 169205/371472 [2:31:31<15:59:40,  3.51it/s]
 46%|████▌     | 169206/371472 [2:31:32<16:29:58,  3.41it/s]
 46%|████▌     | 169207/371472 [2:31:32<16:49:32,  3.34it/s]
 46%|████▌     | 169208/371472 [2:31:32<16:11:24,  3.47it/s]
 46%|████▌     | 169209/371472 [2:31:33<16:24:11,  3.43it/s]
 46%|████▌     | 169210/371472 [2:31:33<16:43:32,  3.36it/s]
 46%|████▌     | 169211/371472 [2:31:33<17:21:54,  3.24it/s]
 46%|████▌     | 169212/371472 [2:31:34<17:47:30,  3.16it/s]
 46%|████▌     | 169213/371472 [2:31:34<17:18:57,  3.24it/s]
 46%|████▌     | 169214/371472 [2:31:34<16:59:18,  3.31it/s]
 46%|████▌     | 169215/371472 [2:31:34<16:42:43,  3.36it/s]
 46%|████▌     | 169216/371472 [2:31:35<17:59:15,  3.12it/s]
 46%|████▌     | 169217/371472 [2:31:35<18:13:43,  3.08it/s]
 46%|████▌     | 169218/371472 [2:31:36<18:04:51,  3.11it/s]
 46%|████▌     | 169219/371472 [2:31:36<17:10:28,  3.27it/s]
 46%|████▌     | 169220/371472 [2:31:36<16:58:20,  3.31it/s]
                                                            
{'loss': 2.9144, 'learning_rate': 5.902788252278652e-07, 'epoch': 7.29}
+
 46%|████▌     | 169220/371472 [2:31:36<16:58:20,  3.31it/s]
 46%|████▌     | 169221/371472 [2:31:36<16:32:26,  3.40it/s]
 46%|████▌     | 169222/371472 [2:31:37<16:16:47,  3.45it/s]
 46%|████▌     | 169223/371472 [2:31:37<17:12:06,  3.27it/s]
 46%|████▌     | 169224/371472 [2:31:37<17:27:15,  3.22it/s]
 46%|████▌     | 169225/371472 [2:31:38<17:39:36,  3.18it/s]
 46%|████▌     | 169226/371472 [2:31:38<17:06:16,  3.28it/s]
 46%|████▌     | 169227/371472 [2:31:38<17:27:01,  3.22it/s]
 46%|████▌     | 169228/371472 [2:31:39<17:13:00,  3.26it/s]
 46%|████▌     | 169229/371472 [2:31:39<16:56:14,  3.32it/s]
 46%|████▌     | 169230/371472 [2:31:39<17:04:26,  3.29it/s]
 46%|████▌     | 169231/371472 [2:31:39<17:34:26,  3.20it/s]
 46%|████▌     | 169232/371472 [2:31:40<17:04:41,  3.29it/s]
 46%|████▌     | 169233/371472 [2:31:40<18:10:16,  3.09it/s]
 46%|████▌     | 169234/371472 [2:31:40<17:51:52,  3.14it/s]
 46%|████▌     | 169235/371472 [2:31:41<18:19:03,  3.07it/s]
 46%|████▌     | 169236/371472 [2:31:41<17:20:40,  3.24it/s]
 46%|████▌     | 169237/371472 [2:31:41<16:56:53,  3.31it/s]
 46%|████▌     | 169238/371472 [2:31:42<18:06:14,  3.10it/s]
 46%|████▌     | 169239/371472 [2:31:42<19:53:44,  2.82it/s]
 46%|████▌     | 169240/371472 [2:31:42<18:46:48,  2.99it/s]
                                                            
{'loss': 2.9881, 'learning_rate': 5.902303432523863e-07, 'epoch': 7.29}
+
 46%|████▌     | 169240/371472 [2:31:42<18:46:48,  2.99it/s]
 46%|████▌     | 169241/371472 [2:31:43<17:55:45,  3.13it/s]
 46%|████▌     | 169242/371472 [2:31:43<17:30:07,  3.21it/s]
 46%|████▌     | 169243/371472 [2:31:43<16:59:55,  3.30it/s]
 46%|████▌     | 169244/371472 [2:31:44<16:28:35,  3.41it/s]
 46%|████▌     | 169245/371472 [2:31:44<16:36:11,  3.38it/s]
 46%|████▌     | 169246/371472 [2:31:44<17:03:37,  3.29it/s]
 46%|████▌     | 169247/371472 [2:31:44<17:05:05,  3.29it/s]
 46%|████▌     | 169248/371472 [2:31:45<16:36:59,  3.38it/s]
 46%|████▌     | 169249/371472 [2:31:45<16:21:26,  3.43it/s]
 46%|████▌     | 169250/371472 [2:31:45<17:46:08,  3.16it/s]
 46%|████▌     | 169251/371472 [2:31:46<17:54:26,  3.14it/s]
 46%|████▌     | 169252/371472 [2:31:46<17:51:08,  3.15it/s]
 46%|████▌     | 169253/371472 [2:31:46<17:19:16,  3.24it/s]
 46%|████▌     | 169254/371472 [2:31:47<16:42:53,  3.36it/s]
 46%|████▌     | 169255/371472 [2:31:47<16:29:39,  3.41it/s]
 46%|████▌     | 169256/371472 [2:31:47<16:56:24,  3.32it/s]
 46%|████▌     | 169257/371472 [2:31:48<17:02:22,  3.30it/s]
 46%|████▌     | 169258/371472 [2:31:48<16:27:55,  3.41it/s]
 46%|████▌     | 169259/371472 [2:31:48<16:33:35,  3.39it/s]
 46%|████▌     | 169260/371472 [2:31:48<16:11:31,  3.47it/s]
                                                            
{'loss': 2.9816, 'learning_rate': 5.901818612769074e-07, 'epoch': 7.29}
+
 46%|████▌     | 169260/371472 [2:31:48<16:11:31,  3.47it/s]
 46%|████▌     | 169261/371472 [2:31:49<17:34:28,  3.20it/s]
 46%|████▌     | 169262/371472 [2:31:49<16:43:59,  3.36it/s]
 46%|████▌     | 169263/371472 [2:31:49<16:56:41,  3.31it/s]
 46%|████▌     | 169264/371472 [2:31:50<16:41:18,  3.37it/s]
 46%|████▌     | 169265/371472 [2:31:50<16:33:11,  3.39it/s]
 46%|████▌     | 169266/371472 [2:31:50<16:51:24,  3.33it/s]
 46%|████▌     | 169267/371472 [2:31:51<17:14:46,  3.26it/s]
 46%|████▌     | 169268/371472 [2:31:51<17:30:50,  3.21it/s]
 46%|████▌     | 169269/371472 [2:31:51<17:14:08,  3.26it/s]
 46%|████▌     | 169270/371472 [2:31:51<16:35:17,  3.39it/s]
 46%|████▌     | 169271/371472 [2:31:52<16:25:52,  3.42it/s]
 46%|████▌     | 169272/371472 [2:31:52<16:21:18,  3.43it/s]
 46%|████▌     | 169273/371472 [2:31:52<16:45:52,  3.35it/s]
 46%|████▌     | 169274/371472 [2:31:53<16:33:31,  3.39it/s]
 46%|████▌     | 169275/371472 [2:31:53<16:06:28,  3.49it/s]
 46%|████▌     | 169276/371472 [2:31:53<16:03:22,  3.50it/s]
 46%|████▌     | 169277/371472 [2:31:53<15:56:27,  3.52it/s]
 46%|████▌     | 169278/371472 [2:31:54<15:56:44,  3.52it/s]
 46%|████▌     | 169279/371472 [2:31:54<16:37:22,  3.38it/s]
 46%|████▌     | 169280/371472 [2:31:54<16:34:13,  3.39it/s]
                                                            
{'loss': 2.825, 'learning_rate': 5.901333793014286e-07, 'epoch': 7.29}
+
 46%|████▌     | 169280/371472 [2:31:54<16:34:13,  3.39it/s]
 46%|████▌     | 169281/371472 [2:31:55<16:51:05,  3.33it/s]
 46%|████▌     | 169282/371472 [2:31:55<18:35:05,  3.02it/s]
 46%|████▌     | 169283/371472 [2:31:55<17:51:32,  3.14it/s]
 46%|████▌     | 169284/371472 [2:31:56<17:52:02,  3.14it/s]
 46%|████▌     | 169285/371472 [2:31:56<17:50:05,  3.15it/s]
 46%|████▌     | 169286/371472 [2:31:56<17:54:41,  3.14it/s]
 46%|████▌     | 169287/371472 [2:31:57<18:38:53,  3.01it/s]
 46%|████▌     | 169288/371472 [2:31:57<17:38:02,  3.18it/s]
 46%|████▌     | 169289/371472 [2:31:57<17:20:49,  3.24it/s]
 46%|████▌     | 169290/371472 [2:31:58<18:07:21,  3.10it/s]
 46%|████▌     | 169291/371472 [2:31:58<17:31:17,  3.21it/s]
 46%|████▌     | 169292/371472 [2:31:58<17:14:14,  3.26it/s]
 46%|████▌     | 169293/371472 [2:31:58<17:17:59,  3.25it/s]
 46%|████▌     | 169294/371472 [2:31:59<17:25:08,  3.22it/s]
 46%|████▌     | 169295/371472 [2:31:59<17:06:28,  3.28it/s]
 46%|████▌     | 169296/371472 [2:31:59<16:57:20,  3.31it/s]
 46%|████▌     | 169297/371472 [2:32:00<16:38:38,  3.37it/s]
 46%|████▌     | 169298/371472 [2:32:00<16:19:15,  3.44it/s]
 46%|████▌     | 169299/371472 [2:32:00<15:47:51,  3.55it/s]
 46%|████▌     | 169300/371472 [2:32:00<15:36:07,  3.60it/s]
                                                            
{'loss': 3.0248, 'learning_rate': 5.900848973259497e-07, 'epoch': 7.29}
+
 46%|████▌     | 169300/371472 [2:32:00<15:36:07,  3.60it/s]
 46%|████▌     | 169301/371472 [2:32:01<15:51:45,  3.54it/s]
 46%|████▌     | 169302/371472 [2:32:01<16:17:10,  3.45it/s]
 46%|████▌     | 169303/371472 [2:32:01<16:50:11,  3.34it/s]
 46%|████▌     | 169304/371472 [2:32:02<16:39:48,  3.37it/s]
 46%|████▌     | 169305/371472 [2:32:02<16:39:28,  3.37it/s]
 46%|████▌     | 169306/371472 [2:32:02<16:58:56,  3.31it/s]
 46%|████▌     | 169307/371472 [2:32:03<16:58:15,  3.31it/s]
 46%|████▌     | 169308/371472 [2:32:03<18:24:32,  3.05it/s]
 46%|████▌     | 169309/371472 [2:32:03<18:04:54,  3.11it/s]
 46%|████▌     | 169310/371472 [2:32:04<18:18:52,  3.07it/s]
 46%|████▌     | 169311/371472 [2:32:04<17:47:14,  3.16it/s]
 46%|████▌     | 169312/371472 [2:32:04<17:10:39,  3.27it/s]
 46%|████▌     | 169313/371472 [2:32:05<18:57:36,  2.96it/s]
 46%|████▌     | 169314/371472 [2:32:05<18:12:18,  3.08it/s]
 46%|████▌     | 169315/371472 [2:32:05<17:47:39,  3.16it/s]
 46%|████▌     | 169316/371472 [2:32:05<17:36:00,  3.19it/s]
 46%|████▌     | 169317/371472 [2:32:06<17:34:35,  3.19it/s]
 46%|████▌     | 169318/371472 [2:32:06<17:33:50,  3.20it/s]
 46%|████▌     | 169319/371472 [2:32:06<17:06:53,  3.28it/s]
 46%|████▌     | 169320/371472 [2:32:07<16:27:05,  3.41it/s]
                                                            
{'loss': 2.9905, 'learning_rate': 5.900364153504708e-07, 'epoch': 7.29}
+
 46%|████▌     | 169320/371472 [2:32:07<16:27:05,  3.41it/s]
 46%|████▌     | 169321/371472 [2:32:07<16:08:23,  3.48it/s]
 46%|████▌     | 169322/371472 [2:32:07<16:35:42,  3.38it/s]
 46%|████▌     | 169323/371472 [2:32:08<16:39:51,  3.37it/s]
 46%|████▌     | 169324/371472 [2:32:08<16:38:49,  3.37it/s]
 46%|████▌     | 169325/371472 [2:32:08<16:45:30,  3.35it/s]
 46%|████▌     | 169326/371472 [2:32:08<16:24:54,  3.42it/s]
 46%|████▌     | 169327/371472 [2:32:09<16:54:30,  3.32it/s]
 46%|████▌     | 169328/371472 [2:32:09<17:13:18,  3.26it/s]
 46%|████▌     | 169329/371472 [2:32:09<16:50:18,  3.33it/s]
 46%|████▌     | 169330/371472 [2:32:10<16:16:51,  3.45it/s]
 46%|████▌     | 169331/371472 [2:32:10<16:13:24,  3.46it/s]
 46%|████▌     | 169332/371472 [2:32:10<16:52:36,  3.33it/s]
 46%|████▌     | 169333/371472 [2:32:10<16:27:54,  3.41it/s]
 46%|████▌     | 169334/371472 [2:32:11<17:12:19,  3.26it/s]
 46%|████▌     | 169335/371472 [2:32:11<17:14:22,  3.26it/s]
 46%|████▌     | 169336/371472 [2:32:11<17:08:38,  3.28it/s]
 46%|████▌     | 169337/371472 [2:32:12<16:27:31,  3.41it/s]
 46%|████▌     | 169338/371472 [2:32:12<16:44:11,  3.35it/s]
 46%|████▌     | 169339/371472 [2:32:12<16:46:13,  3.35it/s]
 46%|████▌     | 169340/371472 [2:32:13<16:07:03,  3.48it/s]
                                                            
{'loss': 2.9468, 'learning_rate': 5.899879333749919e-07, 'epoch': 7.29}
+
 46%|████▌     | 169340/371472 [2:32:13<16:07:03,  3.48it/s]
 46%|████▌     | 169341/371472 [2:32:13<16:01:26,  3.50it/s]
 46%|████▌     | 169342/371472 [2:32:13<17:14:15,  3.26it/s]
 46%|████▌     | 169343/371472 [2:32:14<16:51:27,  3.33it/s]
 46%|████▌     | 169344/371472 [2:32:14<16:17:23,  3.45it/s]
 46%|████▌     | 169345/371472 [2:32:14<16:01:26,  3.50it/s]
 46%|████▌     | 169346/371472 [2:32:14<16:16:24,  3.45it/s]
 46%|████▌     | 169347/371472 [2:32:15<16:01:46,  3.50it/s]
 46%|████▌     | 169348/371472 [2:32:15<16:22:25,  3.43it/s]
 46%|████▌     | 169349/371472 [2:32:15<16:13:19,  3.46it/s]
 46%|████▌     | 169350/371472 [2:32:15<16:12:51,  3.46it/s]
 46%|████▌     | 169351/371472 [2:32:16<15:41:55,  3.58it/s]
 46%|████▌     | 169352/371472 [2:32:16<17:54:50,  3.13it/s]
 46%|████▌     | 169353/371472 [2:32:17<18:25:03,  3.05it/s]
 46%|████▌     | 169354/371472 [2:32:17<17:41:48,  3.17it/s]
 46%|████▌     | 169355/371472 [2:32:17<17:15:27,  3.25it/s]
 46%|████▌     | 169356/371472 [2:32:17<16:55:26,  3.32it/s]
 46%|████▌     | 169357/371472 [2:32:18<16:22:25,  3.43it/s]
 46%|████▌     | 169358/371472 [2:32:18<16:30:01,  3.40it/s]
 46%|████▌     | 169359/371472 [2:32:18<16:37:56,  3.38it/s]
 46%|████▌     | 169360/371472 [2:32:19<16:20:07,  3.44it/s]
                                                            
{'loss': 2.9361, 'learning_rate': 5.89939451399513e-07, 'epoch': 7.29}
+
 46%|████▌     | 169360/371472 [2:32:19<16:20:07,  3.44it/s]
 46%|████▌     | 169361/371472 [2:32:19<16:41:15,  3.36it/s]
 46%|████▌     | 169362/371472 [2:32:19<17:03:28,  3.29it/s]
 46%|████▌     | 169363/371472 [2:32:19<17:11:20,  3.27it/s]
 46%|████▌     | 169364/371472 [2:32:20<17:00:56,  3.30it/s]
 46%|████▌     | 169365/371472 [2:32:20<17:40:46,  3.18it/s]
 46%|████▌     | 169366/371472 [2:32:20<17:27:03,  3.22it/s]
 46%|████▌     | 169367/371472 [2:32:21<17:05:12,  3.29it/s]
 46%|████▌     | 169368/371472 [2:32:21<17:53:16,  3.14it/s]
 46%|████▌     | 169369/371472 [2:32:21<17:00:05,  3.30it/s]
 46%|████▌     | 169370/371472 [2:32:22<17:02:31,  3.29it/s]
 46%|████▌     | 169371/371472 [2:32:22<17:06:31,  3.28it/s]
 46%|████▌     | 169372/371472 [2:32:22<17:08:22,  3.28it/s]
 46%|████▌     | 169373/371472 [2:32:23<17:06:45,  3.28it/s]
 46%|████▌     | 169374/371472 [2:32:23<17:42:59,  3.17it/s]
 46%|████▌     | 169375/371472 [2:32:23<17:18:00,  3.24it/s]
 46%|████▌     | 169376/371472 [2:32:24<17:51:31,  3.14it/s]
 46%|████▌     | 169377/371472 [2:32:24<18:20:59,  3.06it/s]
 46%|████▌     | 169378/371472 [2:32:24<17:34:08,  3.20it/s]
 46%|████▌     | 169379/371472 [2:32:24<18:02:51,  3.11it/s]
 46%|████▌     | 169380/371472 [2:32:25<17:23:24,  3.23it/s]
                                                            
{'loss': 3.002, 'learning_rate': 5.898909694240341e-07, 'epoch': 7.3}
+
 46%|████▌     | 169380/371472 [2:32:25<17:23:24,  3.23it/s]
 46%|████▌     | 169381/371472 [2:32:25<16:44:36,  3.35it/s]
 46%|████▌     | 169382/371472 [2:32:25<16:42:08,  3.36it/s]
 46%|████▌     | 169383/371472 [2:32:26<17:29:59,  3.21it/s]
 46%|████▌     | 169384/371472 [2:32:26<17:23:21,  3.23it/s]
 46%|████▌     | 169385/371472 [2:32:26<17:00:36,  3.30it/s]
 46%|████▌     | 169386/371472 [2:32:27<16:27:22,  3.41it/s]
 46%|████▌     | 169387/371472 [2:32:27<16:25:57,  3.42it/s]
 46%|████▌     | 169388/371472 [2:32:27<16:15:54,  3.45it/s]
 46%|████▌     | 169389/371472 [2:32:27<16:47:40,  3.34it/s]
 46%|████▌     | 169390/371472 [2:32:28<16:29:28,  3.40it/s]
 46%|████▌     | 169391/371472 [2:32:28<16:22:35,  3.43it/s]
 46%|████▌     | 169392/371472 [2:32:28<16:08:26,  3.48it/s]
 46%|████▌     | 169393/371472 [2:32:29<16:20:41,  3.43it/s]
 46%|████▌     | 169394/371472 [2:32:29<18:05:11,  3.10it/s]
 46%|████▌     | 169395/371472 [2:32:29<17:19:48,  3.24it/s]
 46%|████▌     | 169396/371472 [2:32:30<16:44:11,  3.35it/s]
 46%|████▌     | 169397/371472 [2:32:30<16:36:59,  3.38it/s]
 46%|████▌     | 169398/371472 [2:32:30<16:17:53,  3.44it/s]
 46%|██���█▌     | 169399/371472 [2:32:30<15:45:00,  3.56it/s]
 46%|████▌     | 169400/371472 [2:32:31<15:33:16,  3.61it/s]
                                                            
{'loss': 2.8868, 'learning_rate': 5.898424874485552e-07, 'epoch': 7.3}
+
 46%|████▌     | 169400/371472 [2:32:31<15:33:16,  3.61it/s]
 46%|████▌     | 169401/371472 [2:32:31<15:44:20,  3.57it/s]
 46%|████▌     | 169402/371472 [2:32:31<15:46:33,  3.56it/s]
 46%|████▌     | 169403/371472 [2:32:32<16:32:12,  3.39it/s]
 46%|████▌     | 169404/371472 [2:32:32<16:32:51,  3.39it/s]
 46%|████▌     | 169405/371472 [2:32:32<15:59:58,  3.51it/s]
 46%|████▌     | 169406/371472 [2:32:32<16:20:07,  3.44it/s]
 46%|████▌     | 169407/371472 [2:32:33<16:01:05,  3.50it/s]
 46%|████▌     | 169408/371472 [2:32:33<17:11:08,  3.27it/s]
 46%|████▌     | 169409/371472 [2:32:33<16:22:36,  3.43it/s]
 46%|████▌     | 169410/371472 [2:32:34<16:22:32,  3.43it/s]
 46%|████▌     | 169411/371472 [2:32:34<15:58:55,  3.51it/s]
 46%|████▌     | 169412/371472 [2:32:34<16:13:34,  3.46it/s]
 46%|████▌     | 169413/371472 [2:32:34<16:07:07,  3.48it/s]
 46%|████▌     | 169414/371472 [2:32:35<17:13:14,  3.26it/s]
 46%|████▌     | 169415/371472 [2:32:35<16:53:58,  3.32it/s]
 46%|████▌     | 169416/371472 [2:32:35<16:46:18,  3.35it/s]
 46%|████▌     | 169417/371472 [2:32:36<18:23:02,  3.05it/s]
 46%|████▌     | 169418/371472 [2:32:36<19:06:07,  2.94it/s]
 46%|████▌     | 169419/371472 [2:32:36<17:59:40,  3.12it/s]
 46%|████▌     | 169420/371472 [2:32:37<17:34:59,  3.19it/s]
                                                            
{'loss': 2.8819, 'learning_rate': 5.897940054730763e-07, 'epoch': 7.3}
+
 46%|████▌     | 169420/371472 [2:32:37<17:34:59,  3.19it/s]
 46%|████▌     | 169421/371472 [2:32:37<17:32:54,  3.20it/s]
 46%|████▌     | 169422/371472 [2:32:37<18:00:52,  3.12it/s]
 46%|████▌     | 169423/371472 [2:32:38<18:15:01,  3.08it/s]
 46%|████▌     | 169424/371472 [2:32:38<17:29:10,  3.21it/s]
 46%|████▌     | 169425/371472 [2:32:38<17:04:09,  3.29it/s]
 46%|████▌     | 169426/371472 [2:32:39<17:34:59,  3.19it/s]
 46%|████▌     | 169427/371472 [2:32:39<17:08:22,  3.27it/s]
 46%|████▌     | 169428/371472 [2:32:39<17:09:39,  3.27it/s]
 46%|████▌     | 169429/371472 [2:32:39<16:41:15,  3.36it/s]
 46%|████▌     | 169430/371472 [2:32:40<17:09:52,  3.27it/s]
 46%|████▌     | 169431/371472 [2:32:40<17:13:45,  3.26it/s]
 46%|████▌     | 169432/371472 [2:32:40<17:27:23,  3.21it/s]
 46%|████▌     | 169433/371472 [2:32:41<16:55:08,  3.32it/s]
 46%|████▌     | 169434/371472 [2:32:41<16:30:24,  3.40it/s]
 46%|████▌     | 169435/371472 [2:32:41<16:44:17,  3.35it/s]
 46%|████▌     | 169436/371472 [2:32:42<16:52:56,  3.32it/s]
 46%|████▌     | 169437/371472 [2:32:42<17:26:11,  3.22it/s]
 46%|████▌     | 169438/371472 [2:32:42<17:08:18,  3.27it/s]
 46%|████▌     | 169439/371472 [2:32:42<16:33:18,  3.39it/s]
 46%|████▌     | 169440/371472 [2:32:43<16:30:20,  3.40it/s]
                                                            
{'loss': 3.1066, 'learning_rate': 5.897455234975975e-07, 'epoch': 7.3}
+
 46%|████▌     | 169440/371472 [2:32:43<16:30:20,  3.40it/s]
 46%|████▌     | 169441/371472 [2:32:43<16:18:16,  3.44it/s]
 46%|████▌     | 169442/371472 [2:32:43<15:56:57,  3.52it/s]
 46%|████▌     | 169443/371472 [2:32:44<16:32:42,  3.39it/s]
 46%|████▌     | 169444/371472 [2:32:44<16:12:00,  3.46it/s]
 46%|████▌     | 169445/371472 [2:32:44<16:03:25,  3.49it/s]
 46%|████▌     | 169446/371472 [2:32:44<15:54:18,  3.53it/s]
 46%|████▌     | 169447/371472 [2:32:45<16:06:38,  3.48it/s]
 46%|████▌     | 169448/371472 [2:32:45<16:12:44,  3.46it/s]
 46%|████▌     | 169449/371472 [2:32:45<16:41:02,  3.36it/s]
 46%|████▌     | 169450/371472 [2:32:46<16:32:26,  3.39it/s]
 46%|████▌     | 169451/371472 [2:32:46<16:14:38,  3.45it/s]
 46%|████▌     | 169452/371472 [2:32:46<16:47:06,  3.34it/s]
 46%|████▌     | 169453/371472 [2:32:47<17:20:17,  3.24it/s]
 46%|████▌     | 169454/371472 [2:32:47<16:51:17,  3.33it/s]
 46%|████▌     | 169455/371472 [2:32:47<16:40:44,  3.36it/s]
 46%|████▌     | 169456/371472 [2:32:47<16:30:28,  3.40it/s]
 46%|████▌     | 169457/371472 [2:32:48<16:14:23,  3.46it/s]
 46%|████▌     | 169458/371472 [2:32:48<16:12:12,  3.46it/s]
 46%|████▌     | 169459/371472 [2:32:48<15:58:16,  3.51it/s]
 46%|████▌     | 169460/371472 [2:32:49<16:08:31,  3.48it/s]
                                                            
{'loss': 2.8859, 'learning_rate': 5.896970415221186e-07, 'epoch': 7.3}
+
 46%|████▌     | 169460/371472 [2:32:49<16:08:31,  3.48it/s]
 46%|████▌     | 169461/371472 [2:32:49<16:09:57,  3.47it/s]
 46%|████▌     | 169462/371472 [2:32:49<16:15:26,  3.45it/s]
 46%|████▌     | 169463/371472 [2:32:49<16:16:54,  3.45it/s]
 46%|████▌     | 169464/371472 [2:32:50<16:09:49,  3.47it/s]
 46%|████▌     | 169465/371472 [2:32:50<16:10:20,  3.47it/s]
 46%|████▌     | 169466/371472 [2:32:50<16:26:36,  3.41it/s]
 46%|████▌     | 169467/371472 [2:32:51<17:27:03,  3.22it/s]
 46%|████▌     | 169468/371472 [2:32:51<17:11:37,  3.26it/s]
 46%|████▌     | 169469/371472 [2:32:51<17:22:27,  3.23it/s]
 46%|████▌     | 169470/371472 [2:32:52<17:02:21,  3.29it/s]
 46%|████▌     | 169471/371472 [2:32:52<18:06:20,  3.10it/s]
 46%|████▌     | 169472/371472 [2:32:52<17:34:38,  3.19it/s]
 46%|████▌     | 169473/371472 [2:32:53<17:06:24,  3.28it/s]
 46%|████▌     | 169474/371472 [2:32:53<16:30:23,  3.40it/s]
 46%|████▌     | 169475/371472 [2:32:53<16:25:12,  3.42it/s]
 46%|████▌     | 169476/371472 [2:32:53<16:20:53,  3.43it/s]
 46%|████▌     | 169477/371472 [2:32:54<16:40:25,  3.37it/s]
 46%|████▌     | 169478/371472 [2:32:54<16:25:12,  3.42it/s]
 46%|████▌     | 169479/371472 [2:32:54<16:13:29,  3.46it/s]
 46%|████▌     | 169480/371472 [2:32:55<17:05:16,  3.28it/s]
                                                            
{'loss': 2.8926, 'learning_rate': 5.896485595466396e-07, 'epoch': 7.3}
+
 46%|████▌     | 169480/371472 [2:32:55<17:05:16,  3.28it/s]
 46%|████▌     | 169481/371472 [2:32:55<17:04:48,  3.29it/s]
 46%|████▌     | 169482/371472 [2:32:55<17:02:43,  3.29it/s]
 46%|████▌     | 169483/371472 [2:32:55<16:51:07,  3.33it/s]
 46%|████▌     | 169484/371472 [2:32:56<16:29:32,  3.40it/s]
 46%|████▌     | 169485/371472 [2:32:56<16:22:44,  3.43it/s]
 46%|████▌     | 169486/371472 [2:32:56<16:29:15,  3.40it/s]
 46%|████▌     | 169487/371472 [2:32:57<16:32:34,  3.39it/s]
 46%|████▌     | 169488/371472 [2:32:57<16:18:19,  3.44it/s]
 46%|████▌     | 169489/371472 [2:32:57<15:58:18,  3.51it/s]
 46%|████▌     | 169490/371472 [2:32:57<16:12:53,  3.46it/s]
 46%|████▌     | 169491/371472 [2:32:58<16:00:24,  3.51it/s]
 46%|████▌     | 169492/371472 [2:32:58<15:40:01,  3.58it/s]
 46%|████▌     | 169493/371472 [2:32:58<15:53:32,  3.53it/s]
 46%|████▌     | 169494/371472 [2:32:59<15:55:01,  3.52it/s]
 46%|████▌     | 169495/371472 [2:32:59<15:55:46,  3.52it/s]
 46%|████▌     | 169496/371472 [2:32:59<15:51:09,  3.54it/s]
 46%|████▌     | 169497/371472 [2:32:59<15:55:17,  3.52it/s]
 46%|████▌     | 169498/371472 [2:33:00<15:39:44,  3.58it/s]
 46%|████▌     | 169499/371472 [2:33:00<15:56:57,  3.52it/s]
 46%|████▌     | 169500/371472 [2:33:00<15:53:04,  3.53it/s]
                                                            
{'loss': 2.8052, 'learning_rate': 5.896000775711607e-07, 'epoch': 7.3}
+
 46%|████▌     | 169500/371472 [2:33:00<15:53:04,  3.53it/s]
 46%|████▌     | 169501/371472 [2:33:01<16:33:25,  3.39it/s]
 46%|████▌     | 169502/371472 [2:33:01<16:30:40,  3.40it/s]
 46%|████▌     | 169503/371472 [2:33:01<18:21:26,  3.06it/s]
 46%|████▌     | 169504/371472 [2:33:02<19:20:30,  2.90it/s]
 46%|████▌     | 169505/371472 [2:33:02<19:32:54,  2.87it/s]
 46%|████▌     | 169506/371472 [2:33:02<18:23:00,  3.05it/s]
 46%|████▌     | 169507/371472 [2:33:03<17:33:18,  3.20it/s]
 46%|████▌     | 169508/371472 [2:33:03<17:08:36,  3.27it/s]
 46%|████▌     | 169509/371472 [2:33:03<16:45:36,  3.35it/s]
 46%|████▌     | 169510/371472 [2:33:04<17:05:36,  3.28it/s]
 46%|████▌     | 169511/371472 [2:33:04<16:44:57,  3.35it/s]
 46%|████▌     | 169512/371472 [2:33:04<16:26:24,  3.41it/s]
 46%|████▌     | 169513/371472 [2:33:04<16:21:01,  3.43it/s]
 46%|████▌     | 169514/371472 [2:33:05<16:17:03,  3.44it/s]
 46%|████▌     | 169515/371472 [2:33:05<16:14:16,  3.45it/s]
 46%|████▌     | 169516/371472 [2:33:05<16:10:01,  3.47it/s]
 46%|████▌     | 169517/371472 [2:33:06<16:07:15,  3.48it/s]
 46%|████▌     | 169518/371472 [2:33:06<16:14:59,  3.45it/s]
 46%|████▌     | 169519/371472 [2:33:06<19:27:07,  2.88it/s]
 46%|████▌     | 169520/371472 [2:33:07<18:24:15,  3.05it/s]
                                                            
{'loss': 2.9299, 'learning_rate': 5.895515955956818e-07, 'epoch': 7.3}
+
 46%|████▌     | 169520/371472 [2:33:07<18:24:15,  3.05it/s]
 46%|████▌     | 169521/371472 [2:33:07<17:38:08,  3.18it/s]
 46%|████▌     | 169522/371472 [2:33:07<17:21:41,  3.23it/s]
 46%|██��█▌     | 169523/371472 [2:33:07<17:34:02,  3.19it/s]
 46%|████▌     | 169524/371472 [2:33:08<17:25:43,  3.22it/s]
 46%|████▌     | 169525/371472 [2:33:08<18:50:47,  2.98it/s]
 46%|████▌     | 169526/371472 [2:33:08<17:58:23,  3.12it/s]
 46%|████▌     | 169527/371472 [2:33:09<18:28:08,  3.04it/s]
 46%|████▌     | 169528/371472 [2:33:09<18:35:27,  3.02it/s]
 46%|████▌     | 169529/371472 [2:33:09<18:48:19,  2.98it/s]
 46%|████▌     | 169530/371472 [2:33:10<18:45:17,  2.99it/s]
 46%|████▌     | 169531/371472 [2:33:10<19:56:31,  2.81it/s]
 46%|████▌     | 169532/371472 [2:33:11<18:53:43,  2.97it/s]
 46%|████▌     | 169533/371472 [2:33:11<18:15:26,  3.07it/s]
 46%|████▌     | 169534/371472 [2:33:11<18:02:33,  3.11it/s]
 46%|████▌     | 169535/371472 [2:33:11<17:17:19,  3.24it/s]
 46%|████▌     | 169536/371472 [2:33:12<16:35:46,  3.38it/s]
 46%|████▌     | 169537/371472 [2:33:12<16:35:46,  3.38it/s]
 46%|████▌     | 169538/371472 [2:33:12<16:23:17,  3.42it/s]
 46%|████▌     | 169539/371472 [2:33:13<16:28:19,  3.41it/s]
 46%|████▌     | 169540/371472 [2:33:13<16:25:47,  3.41it/s]
                                                            
{'loss': 2.8855, 'learning_rate': 5.89503113620203e-07, 'epoch': 7.3}
+
 46%|████▌     | 169540/371472 [2:33:13<16:25:47,  3.41it/s]
 46%|████▌     | 169541/371472 [2:33:13<18:45:40,  2.99it/s]
 46%|████▌     | 169542/371472 [2:33:14<18:39:02,  3.01it/s]
 46%|████▌     | 169543/371472 [2:33:14<17:53:29,  3.14it/s]
 46%|████▌     | 169544/371472 [2:33:14<17:15:25,  3.25it/s]
 46%|████▌     | 169545/371472 [2:33:14<16:58:32,  3.30it/s]
 46%|████▌     | 169546/371472 [2:33:15<16:51:40,  3.33it/s]
 46%|████▌     | 169547/371472 [2:33:15<17:27:43,  3.21it/s]
 46%|████▌     | 169548/371472 [2:33:15<17:20:49,  3.23it/s]
 46%|████▌     | 169549/371472 [2:33:16<17:26:41,  3.22it/s]
 46%|████▌     | 169550/371472 [2:33:16<17:13:42,  3.26it/s]
 46%|████▌     | 169551/371472 [2:33:16<17:03:51,  3.29it/s]
 46%|████▌     | 169552/371472 [2:33:17<17:01:34,  3.29it/s]
 46%|████▌     | 169553/371472 [2:33:17<17:01:38,  3.29it/s]
 46%|████▌     | 169554/371472 [2:33:17<17:01:28,  3.29it/s]
 46%|████▌     | 169555/371472 [2:33:18<17:18:47,  3.24it/s]
 46%|████▌     | 169556/371472 [2:33:18<16:49:51,  3.33it/s]
 46%|████▌     | 169557/371472 [2:33:18<16:33:25,  3.39it/s]
 46%|████▌     | 169558/371472 [2:33:18<17:27:55,  3.21it/s]
 46%|████▌     | 169559/371472 [2:33:19<17:01:21,  3.29it/s]
 46%|████▌     | 169560/371472 [2:33:19<17:46:33,  3.16it/s]
                                                            
{'loss': 3.0999, 'learning_rate': 5.894546316447241e-07, 'epoch': 7.3}
+
 46%|████▌     | 169560/371472 [2:33:19<17:46:33,  3.16it/s]
 46%|████▌     | 169561/371472 [2:33:19<17:07:32,  3.27it/s]
 46%|████▌     | 169562/371472 [2:33:20<17:48:27,  3.15it/s]
 46%|████▌     | 169563/371472 [2:33:20<16:53:58,  3.32it/s]
 46%|████▌     | 169564/371472 [2:33:20<16:21:48,  3.43it/s]
 46%|████▌     | 169565/371472 [2:33:21<16:22:59,  3.42it/s]
 46%|████▌     | 169566/371472 [2:33:21<16:16:45,  3.45it/s]
 46%|████▌     | 169567/371472 [2:33:21<16:27:31,  3.41it/s]
 46%|████▌     | 169568/371472 [2:33:21<16:02:16,  3.50it/s]
 46%|████▌     | 169569/371472 [2:33:22<15:43:55,  3.56it/s]
 46%|████▌     | 169570/371472 [2:33:22<16:00:33,  3.50it/s]
 46%|████▌     | 169571/371472 [2:33:22<15:59:50,  3.51it/s]
 46%|████▌     | 169572/371472 [2:33:23<17:05:45,  3.28it/s]
 46%|████▌     | 169573/371472 [2:33:23<17:11:40,  3.26it/s]
 46%|████▌     | 169574/371472 [2:33:23<17:05:51,  3.28it/s]
 46%|████▌     | 169575/371472 [2:33:23<16:55:40,  3.31it/s]
 46%|████▌     | 169576/371472 [2:33:24<17:29:22,  3.21it/s]
 46%|████▌     | 169577/371472 [2:33:24<16:58:52,  3.30it/s]
 46%|████▌     | 169578/371472 [2:33:24<16:44:31,  3.35it/s]
 46%|████▌     | 169579/371472 [2:33:25<16:40:56,  3.36it/s]
 46%|████▌     | 169580/371472 [2:33:25<16:17:03,  3.44it/s]
                                                            
{'loss': 3.057, 'learning_rate': 5.894061496692452e-07, 'epoch': 7.3}
+
 46%|████▌     | 169580/371472 [2:33:25<16:17:03,  3.44it/s]
 46%|████▌     | 169581/371472 [2:33:25<16:03:03,  3.49it/s]
 46%|████▌     | 169582/371472 [2:33:26<16:17:14,  3.44it/s]
 46%|████▌     | 169583/371472 [2:33:26<16:38:28,  3.37it/s]
 46%|████▌     | 169584/371472 [2:33:26<16:39:57,  3.36it/s]
 46%|████▌     | 169585/371472 [2:33:27<17:33:39,  3.19it/s]
 46%|████▌     | 169586/371472 [2:33:27<16:41:47,  3.36it/s]
 46%|████▌     | 169587/371472 [2:33:27<16:32:53,  3.39it/s]
 46%|████▌     | 169588/371472 [2:33:27<16:47:36,  3.34it/s]
 46%|████▌     | 169589/371472 [2:33:28<16:36:14,  3.38it/s]
 46%|████▌     | 169590/371472 [2:33:28<16:41:54,  3.36it/s]
 46%|████▌     | 169591/371472 [2:33:28<16:18:57,  3.44it/s]
 46%|████▌     | 169592/371472 [2:33:29<17:09:47,  3.27it/s]
 46%|████▌     | 169593/371472 [2:33:29<16:39:25,  3.37it/s]
 46%|████▌     | 169594/371472 [2:33:29<16:15:01,  3.45it/s]
 46%|████▌     | 169595/371472 [2:33:29<16:05:55,  3.48it/s]
 46%|████▌     | 169596/371472 [2:33:30<17:25:12,  3.22it/s]
 46%|████▌     | 169597/371472 [2:33:30<17:09:03,  3.27it/s]
 46%|████▌     | 169598/371472 [2:33:30<17:57:01,  3.12it/s]
 46%|████▌     | 169599/371472 [2:33:31<17:19:18,  3.24it/s]
 46%|████▌     | 169600/371472 [2:33:31<16:57:15,  3.31it/s]
                                                            
{'loss': 3.0468, 'learning_rate': 5.893576676937663e-07, 'epoch': 7.3}
+
 46%|████▌     | 169600/371472 [2:33:31<16:57:15,  3.31it/s]
 46%|████▌     | 169601/371472 [2:33:31<16:34:07,  3.38it/s]
 46%|████▌     | 169602/371472 [2:33:32<16:12:40,  3.46it/s]
 46%|████▌     | 169603/371472 [2:33:32<17:27:08,  3.21it/s]
 46%|████▌     | 169604/371472 [2:33:32<16:44:14,  3.35it/s]
 46%|████▌     | 169605/371472 [2:33:32<16:15:21,  3.45it/s]
 46%|████▌     | 169606/371472 [2:33:33<17:21:16,  3.23it/s]
 46%|████▌     | 169607/371472 [2:33:33<17:31:15,  3.20it/s]
 46%|████▌     | 169608/371472 [2:33:33<17:04:03,  3.29it/s]
 46%|████▌     | 169609/371472 [2:33:34<16:30:51,  3.40it/s]
 46%|████▌     | 169610/371472 [2:33:34<15:58:53,  3.51it/s]
 46%|████▌     | 169611/371472 [2:33:34<16:32:28,  3.39it/s]
 46%|████▌     | 169612/371472 [2:33:35<17:16:50,  3.24it/s]
 46%|████▌     | 169613/371472 [2:33:35<17:41:51,  3.17it/s]
 46%|████▌     | 169614/371472 [2:33:35<17:41:26,  3.17it/s]
 46%|████▌     | 169615/371472 [2:33:36<17:38:07,  3.18it/s]
 46%|████▌     | 169616/371472 [2:33:36<18:01:51,  3.11it/s]
 46%|████▌     | 169617/371472 [2:33:36<17:41:33,  3.17it/s]
 46%|████▌     | 169618/371472 [2:33:36<17:06:28,  3.28it/s]
 46%|████▌     | 169619/371472 [2:33:37<16:43:22,  3.35it/s]
 46%|████▌     | 169620/371472 [2:33:37<16:31:56,  3.39it/s]
                                                            
{'loss': 3.1104, 'learning_rate': 5.893091857182873e-07, 'epoch': 7.31}
+
 46%|████▌     | 169620/371472 [2:33:37<16:31:56,  3.39it/s]
 46%|████▌     | 169621/371472 [2:33:37<17:01:47,  3.29it/s]
 46%|████▌     | 169622/371472 [2:33:38<16:33:44,  3.39it/s]
 46%|████▌     | 169623/371472 [2:33:38<16:37:15,  3.37it/s]
 46%|████▌     | 169624/371472 [2:33:38<16:40:40,  3.36it/s]
 46%|████▌     | 169625/371472 [2:33:39<16:19:01,  3.44it/s]
 46%|████▌     | 169626/371472 [2:33:39<17:45:02,  3.16it/s]
 46%|████▌     | 169627/371472 [2:33:39<18:34:34,  3.02it/s]
 46%|████▌     | 169628/371472 [2:33:40<18:26:07,  3.04it/s]
 46%|████▌     | 169629/371472 [2:33:40<17:59:29,  3.12it/s]
 46%|████▌     | 169630/371472 [2:33:40<17:24:20,  3.22it/s]
 46%|████▌     | 169631/371472 [2:33:40<17:31:49,  3.20it/s]
 46%|████▌     | 169632/371472 [2:33:41<16:54:22,  3.32it/s]
 46%|████▌     | 169633/371472 [2:33:41<16:29:58,  3.40it/s]
 46%|████▌     | 169634/371472 [2:33:41<16:48:40,  3.34it/s]
 46%|████▌     | 169635/371472 [2:33:42<17:24:45,  3.22it/s]
 46%|████▌     | 169636/371472 [2:33:42<17:31:30,  3.20it/s]
 46%|████▌     | 169637/371472 [2:33:42<17:34:18,  3.19it/s]
 46%|████▌     | 169638/371472 [2:33:43<17:25:54,  3.22it/s]
 46%|████▌     | 169639/371472 [2:33:43<18:14:26,  3.07it/s]
 46%|████▌     | 169640/371472 [2:33:43<17:58:10,  3.12it/s]
                                                            
{'loss': 2.8131, 'learning_rate': 5.892607037428084e-07, 'epoch': 7.31}
+
 46%|████▌     | 169640/371472 [2:33:43<17:58:10,  3.12it/s]
 46%|████▌     | 169641/371472 [2:33:44<18:04:10,  3.10it/s]
 46%|████▌     | 169642/371472 [2:33:44<18:26:16,  3.04it/s]
 46%|████▌     | 169643/371472 [2:33:44<18:11:31,  3.08it/s]
 46%|████▌     | 169644/371472 [2:33:45<18:46:45,  2.99it/s]
 46%|████▌     | 169645/371472 [2:33:45<17:52:07,  3.14it/s]
 46%|████▌     | 169646/371472 [2:33:45<17:15:26,  3.25it/s]
 46%|████▌     | 169647/371472 [2:33:46<17:26:41,  3.21it/s]
 46%|████▌     | 169648/371472 [2:33:46<17:43:55,  3.16it/s]
 46%|████▌     | 169649/371472 [2:33:46<17:25:01,  3.22it/s]
 46%|���███▌     | 169650/371472 [2:33:46<17:01:59,  3.29it/s]
 46%|████▌     | 169651/371472 [2:33:47<17:58:22,  3.12it/s]
 46%|████▌     | 169652/371472 [2:33:47<19:34:45,  2.86it/s]
 46%|████▌     | 169653/371472 [2:33:48<19:01:23,  2.95it/s]
 46%|████▌     | 169654/371472 [2:33:48<24:09:53,  2.32it/s]
 46%|████▌     | 169655/371472 [2:33:48<21:37:46,  2.59it/s]
 46%|████▌     | 169656/371472 [2:33:49<20:07:58,  2.78it/s]
 46%|████▌     | 169657/371472 [2:33:49<22:35:05,  2.48it/s]
 46%|████▌     | 169658/371472 [2:33:50<20:37:38,  2.72it/s]
 46%|████▌     | 169659/371472 [2:33:50<21:00:21,  2.67it/s]
 46%|████▌     | 169660/371472 [2:33:50<19:44:29,  2.84it/s]
                                                            
{'loss': 3.0096, 'learning_rate': 5.892122217673296e-07, 'epoch': 7.31}
+
 46%|████▌     | 169660/371472 [2:33:50<19:44:29,  2.84it/s]
 46%|████▌     | 169661/371472 [2:33:51<19:10:37,  2.92it/s]
 46%|████▌     | 169662/371472 [2:33:51<18:11:25,  3.08it/s]
 46%|████▌     | 169663/371472 [2:33:51<17:35:53,  3.19it/s]
 46%|████▌     | 169664/371472 [2:33:51<16:57:39,  3.31it/s]
 46%|████▌     | 169665/371472 [2:33:52<16:58:52,  3.30it/s]
 46%|████▌     | 169666/371472 [2:33:52<16:52:08,  3.32it/s]
 46%|████▌     | 169667/371472 [2:33:52<16:33:23,  3.39it/s]
 46%|████▌     | 169668/371472 [2:33:53<17:02:21,  3.29it/s]
 46%|████▌     | 169669/371472 [2:33:53<16:38:09,  3.37it/s]
 46%|████▌     | 169670/371472 [2:33:53<17:02:32,  3.29it/s]
 46%|████▌     | 169671/371472 [2:33:54<16:54:10,  3.32it/s]
 46%|████▌     | 169672/371472 [2:33:54<16:40:06,  3.36it/s]
 46%|████▌     | 169673/371472 [2:33:54<16:35:28,  3.38it/s]
 46%|████▌     | 169674/371472 [2:33:54<16:06:51,  3.48it/s]
 46%|████▌     | 169675/371472 [2:33:55<16:16:03,  3.45it/s]
 46%|████▌     | 169676/371472 [2:33:55<15:59:09,  3.51it/s]
 46%|████▌     | 169677/371472 [2:33:55<16:30:25,  3.40it/s]
 46%|████▌     | 169678/371472 [2:33:56<16:17:34,  3.44it/s]
 46%|████▌     | 169679/371472 [2:33:56<16:01:52,  3.50it/s]
 46%|████▌     | 169680/371472 [2:33:56<17:54:13,  3.13it/s]
                                                            
{'loss': 3.1009, 'learning_rate': 5.891637397918507e-07, 'epoch': 7.31}
+
 46%|████▌     | 169680/371472 [2:33:56<17:54:13,  3.13it/s]
 46%|████▌     | 169681/371472 [2:33:57<18:39:22,  3.00it/s]
 46%|████▌     | 169682/371472 [2:33:57<18:33:17,  3.02it/s]
 46%|████▌     | 169683/371472 [2:33:57<17:32:04,  3.20it/s]
 46%|████▌     | 169684/371472 [2:33:58<18:26:14,  3.04it/s]
 46%|████▌     | 169685/371472 [2:33:58<17:33:33,  3.19it/s]
 46%|████▌     | 169686/371472 [2:33:58<17:19:32,  3.24it/s]
 46%|████▌     | 169687/371472 [2:33:58<16:25:25,  3.41it/s]
 46%|████▌     | 169688/371472 [2:33:59<17:19:06,  3.24it/s]
 46%|████▌     | 169689/371472 [2:33:59<16:41:19,  3.36it/s]
 46%|████▌     | 169690/371472 [2:33:59<16:37:46,  3.37it/s]
 46%|████▌     | 169691/371472 [2:34:00<17:13:46,  3.25it/s]
 46%|████▌     | 169692/371472 [2:34:00<17:03:06,  3.29it/s]
 46%|████▌     | 169693/371472 [2:34:00<16:51:35,  3.32it/s]
 46%|████▌     | 169694/371472 [2:34:00<16:27:37,  3.41it/s]
 46%|████▌     | 169695/371472 [2:34:01<16:10:33,  3.46it/s]
 46%|████▌     | 169696/371472 [2:34:01<15:59:25,  3.51it/s]
 46%|████▌     | 169697/371472 [2:34:01<16:35:48,  3.38it/s]
 46%|████▌     | 169698/371472 [2:34:02<16:43:25,  3.35it/s]
 46%|████▌     | 169699/371472 [2:34:02<16:17:57,  3.44it/s]
 46%|████▌     | 169700/371472 [2:34:02<16:00:19,  3.50it/s]
                                                            
{'loss': 2.9723, 'learning_rate': 5.891152578163718e-07, 'epoch': 7.31}
+
 46%|████▌     | 169700/371472 [2:34:02<16:00:19,  3.50it/s]
 46%|████▌     | 169701/371472 [2:34:02<16:06:59,  3.48it/s]
 46%|████▌     | 169702/371472 [2:34:03<15:54:29,  3.52it/s]
 46%|████▌     | 169703/371472 [2:34:03<17:11:12,  3.26it/s]
 46%|████▌     | 169704/371472 [2:34:03<16:40:05,  3.36it/s]
 46%|████▌     | 169705/371472 [2:34:04<17:38:56,  3.18it/s]
 46%|████▌     | 169706/371472 [2:34:04<17:08:52,  3.27it/s]
 46%|████▌     | 169707/371472 [2:34:04<16:54:22,  3.32it/s]
 46%|████▌     | 169708/371472 [2:34:05<16:09:37,  3.47it/s]
 46%|████▌     | 169709/371472 [2:34:05<15:54:32,  3.52it/s]
 46%|████▌     | 169710/371472 [2:34:05<16:04:12,  3.49it/s]
 46%|████▌     | 169711/371472 [2:34:05<16:15:34,  3.45it/s]
 46%|████▌     | 169712/371472 [2:34:06<16:35:58,  3.38it/s]
 46%|████▌     | 169713/371472 [2:34:06<16:08:57,  3.47it/s]
 46%|████▌     | 169714/371472 [2:34:06<16:11:41,  3.46it/s]
 46%|████▌     | 169715/371472 [2:34:07<15:50:14,  3.54it/s]
 46%|████▌     | 169716/371472 [2:34:07<16:08:37,  3.47it/s]
 46%|████▌     | 169717/371472 [2:34:07<15:55:41,  3.52it/s]
 46%|████▌     | 169718/371472 [2:34:07<16:40:36,  3.36it/s]
 46%|████▌     | 169719/371472 [2:34:08<16:35:31,  3.38it/s]
 46%|████▌     | 169720/371472 [2:34:08<16:34:03,  3.38it/s]
                                                            
{'loss': 3.0135, 'learning_rate': 5.890667758408929e-07, 'epoch': 7.31}
+
 46%|████▌     | 169720/371472 [2:34:08<16:34:03,  3.38it/s]
 46%|████▌     | 169721/371472 [2:34:08<16:36:25,  3.37it/s]
 46%|████▌     | 169722/371472 [2:34:09<17:05:30,  3.28it/s]
 46%|████▌     | 169723/371472 [2:34:09<16:48:12,  3.34it/s]
 46%|████▌     | 169724/371472 [2:34:09<16:56:12,  3.31it/s]
 46%|████▌     | 169725/371472 [2:34:10<16:40:30,  3.36it/s]
 46%|████▌     | 169726/371472 [2:34:10<16:10:04,  3.47it/s]
 46%|████▌     | 169727/371472 [2:34:10<16:11:20,  3.46it/s]
 46%|████▌     | 169728/371472 [2:34:10<16:17:48,  3.44it/s]
 46%|████▌     | 169729/371472 [2:34:11<16:57:34,  3.30it/s]
 46%|████▌     | 169730/371472 [2:34:11<16:53:36,  3.32it/s]
 46%|████▌     | 169731/371472 [2:34:11<17:37:26,  3.18it/s]
 46%|████▌     | 169732/371472 [2:34:12<17:07:39,  3.27it/s]
 46%|████▌     | 169733/371472 [2:34:12<16:51:23,  3.32it/s]
 46%|████▌     | 169734/371472 [2:34:12<16:37:24,  3.37it/s]
 46%|████▌     | 169735/371472 [2:34:13<17:07:38,  3.27it/s]
 46%|████▌     | 169736/371472 [2:34:13<16:45:41,  3.34it/s]
 46%|████▌     | 169737/371472 [2:34:13<16:31:09,  3.39it/s]
 46%|████▌     | 169738/371472 [2:34:13<16:12:48,  3.46it/s]
 46%|████▌     | 169739/371472 [2:34:14<16:21:09,  3.43it/s]
 46%|████▌     | 169740/371472 [2:34:14<17:37:10,  3.18it/s]
                                                            
{'loss': 2.9477, 'learning_rate': 5.89018293865414e-07, 'epoch': 7.31}
+
 46%|████▌     | 169740/371472 [2:34:14<17:37:10,  3.18it/s]
 46%|████▌     | 169741/371472 [2:34:14<17:28:59,  3.21it/s]
 46%|████▌     | 169742/371472 [2:34:15<17:03:31,  3.28it/s]
 46%|████▌     | 169743/371472 [2:34:15<16:41:21,  3.36it/s]
 46%|████▌     | 169744/371472 [2:34:15<16:19:14,  3.43it/s]
 46%|████▌     | 169745/371472 [2:34:16<16:41:41,  3.36it/s]
 46%|████▌     | 169746/371472 [2:34:16<16:13:43,  3.45it/s]
 46%|████▌     | 169747/371472 [2:34:16<16:48:57,  3.33it/s]
 46%|████▌     | 169748/371472 [2:34:16<16:18:01,  3.44it/s]
 46%|████▌     | 169749/371472 [2:34:17<16:07:47,  3.47it/s]
 46%|████▌     | 169750/371472 [2:34:17<17:20:44,  3.23it/s]
 46%|████▌     | 169751/371472 [2:34:17<17:21:52,  3.23it/s]
 46%|████▌     | 169752/371472 [2:34:18<17:53:12,  3.13it/s]
 46%|████▌     | 169753/371472 [2:34:18<17:08:10,  3.27it/s]
 46%|████▌     | 169754/371472 [2:34:18<16:26:30,  3.41it/s]
 46%|████▌     | 169755/371472 [2:34:19<16:25:07,  3.41it/s]
 46%|████▌     | 169756/371472 [2:34:19<16:32:21,  3.39it/s]
 46%|████▌     | 169757/371472 [2:34:19<16:14:14,  3.45it/s]
 46%|████▌     | 169758/371472 [2:34:19<16:09:31,  3.47it/s]
 46%|████▌     | 169759/371472 [2:34:20<15:56:38,  3.51it/s]
 46%|████▌     | 169760/371472 [2:34:20<16:34:10,  3.38it/s]
                                                            
{'loss': 2.895, 'learning_rate': 5.889698118899351e-07, 'epoch': 7.31}
+
 46%|████▌     | 169760/371472 [2:34:20<16:34:10,  3.38it/s]
 46%|████▌     | 169761/371472 [2:34:20<16:10:05,  3.47it/s]
 46%|████▌     | 169762/371472 [2:34:21<16:35:40,  3.38it/s]
 46%|████▌     | 169763/371472 [2:34:21<16:13:02,  3.45it/s]
 46%|████▌     | 169764/371472 [2:34:21<16:20:28,  3.43it/s]
 46%|████▌     | 169765/371472 [2:34:21<16:43:06,  3.35it/s]
 46%|████▌     | 169766/371472 [2:34:22<16:06:41,  3.48it/s]
 46%|████▌     | 169767/371472 [2:34:22<16:29:19,  3.40it/s]
 46%|████▌     | 169768/371472 [2:34:22<16:06:03,  3.48it/s]
 46%|████▌     | 169769/371472 [2:34:23<16:31:40,  3.39it/s]
 46%|████▌     | 169770/371472 [2:34:23<16:44:56,  3.35it/s]
 46%|████▌     | 169771/371472 [2:34:23<16:48:25,  3.33it/s]
 46%|████▌     | 169772/371472 [2:34:24<17:16:53,  3.24it/s]
 46%|████▌     | 169773/371472 [2:34:24<16:50:31,  3.33it/s]
 46%|████▌     | 169774/371472 [2:34:24<16:38:46,  3.37it/s]
 46%|████▌     | 169775/371472 [2:34:24<16:17:57,  3.44it/s]
 46%|████▌     | 169776/371472 [2:34:25<16:31:13,  3.39it/s]
 46%|████▌     | 169777/371472 [2:34:25<16:29:53,  3.40it/s]
 46%|████▌     | 169778/371472 [2:34:25<16:22:56,  3.42it/s]
 46%|████▌     | 169779/371472 [2:34:26<16:38:17,  3.37it/s]
 46%|████▌     | 169780/371472 [2:34:26<16:01:45,  3.50it/s]
                                                            
{'loss': 2.8632, 'learning_rate': 5.889213299144562e-07, 'epoch': 7.31}
+
 46%|████▌     | 169780/371472 [2:34:26<16:01:45,  3.50it/s]
 46%|████▌     | 169781/371472 [2:34:26<19:22:37,  2.89it/s]
 46%|████▌     | 169782/371472 [2:34:27<18:41:06,  3.00it/s]
 46%|████▌     | 169783/371472 [2:34:27<18:47:46,  2.98it/s]
 46%|████▌     | 169784/371472 [2:34:27<18:16:42,  3.07it/s]
 46%|████▌     | 169785/371472 [2:34:28<17:59:35,  3.11it/s]
 46%|████▌     | 169786/371472 [2:34:28<17:17:44,  3.24it/s]
 46%|████▌     | 169787/371472 [2:34:28<17:22:39,  3.22it/s]
 46%|████▌     | 169788/371472 [2:34:29<17:06:05,  3.28it/s]
 46%|████▌     | 169789/371472 [2:34:29<17:06:38,  3.27it/s]
 46%|████▌     | 169790/371472 [2:34:29<17:24:24,  3.22it/s]
 46%|████▌     | 169791/371472 [2:34:29<17:31:38,  3.20it/s]
 46%|████▌     | 169792/371472 [2:34:30<17:05:06,  3.28it/s]
 46%|████▌     | 169793/371472 [2:34:30<16:51:09,  3.32it/s]
 46%|████▌     | 169794/371472 [2:34:30<16:57:24,  3.30it/s]
 46%|████▌     | 169795/371472 [2:34:31<16:29:28,  3.40it/s]
 46%|████▌     | 169796/371472 [2:34:31<16:48:41,  3.33it/s]
 46%|████▌     | 169797/371472 [2:34:31<20:47:19,  2.69it/s]
 46%|████▌     | 169798/371472 [2:34:32<19:43:08,  2.84it/s]
 46%|████▌     | 169799/371472 [2:34:32<18:49:17,  2.98it/s]
 46%|████▌     | 169800/371472 [2:34:32<18:23:46,  3.05it/s]
                                                            
{'loss': 2.8107, 'learning_rate': 5.888728479389773e-07, 'epoch': 7.31}
+
 46%|████▌     | 169800/371472 [2:34:32<18:23:46,  3.05it/s]
 46%|████▌     | 169801/371472 [2:34:33<17:35:30,  3.18it/s]
 46%|████▌     | 169802/371472 [2:34:33<17:03:20,  3.28it/s]
 46%|████▌     | 169803/371472 [2:34:33<16:54:17,  3.31it/s]
 46%|████▌     | 169804/371472 [2:34:34<16:59:53,  3.30it/s]
 46%|████▌     | 169805/371472 [2:34:34<17:39:21,  3.17it/s]
 46%|████▌     | 169806/371472 [2:34:34<16:44:51,  3.34it/s]
 46%|████▌     | 169807/371472 [2:34:34<16:08:09,  3.47it/s]
 46%|████▌     | 169808/371472 [2:34:35<16:37:28,  3.37it/s]
 46%|████▌     | 169809/371472 [2:34:35<16:18:21,  3.44it/s]
 46%|████▌     | 169810/371472 [2:34:35<17:05:51,  3.28it/s]
 46%|████▌     | 169811/371472 [2:34:36<16:42:09,  3.35it/s]
 46%|████▌     | 169812/371472 [2:34:36<16:43:53,  3.35it/s]
 46%|████▌     | 169813/371472 [2:34:36<16:41:25,  3.36it/s]
 46%|████▌     | 169814/371472 [2:34:36<16:02:04,  3.49it/s]
 46%|████▌     | 169815/371472 [2:34:37<16:42:48,  3.35it/s]
 46%|████▌     | 169816/371472 [2:34:37<16:53:55,  3.31it/s]
 46%|████▌     | 169817/371472 [2:34:37<16:34:03,  3.38it/s]
 46%|████▌     | 169818/371472 [2:34:38<16:09:23,  3.47it/s]
 46%|████▌     | 169819/371472 [2:34:38<16:19:56,  3.43it/s]
 46%|████▌     | 169820/371472 [2:34:38<16:28:17,  3.40it/s]
                                                            
{'loss': 3.0592, 'learning_rate': 5.888243659634984e-07, 'epoch': 7.31}
+
 46%|████▌     | 169820/371472 [2:34:38<16:28:17,  3.40it/s]
 46%|████▌     | 169821/371472 [2:34:39<16:06:33,  3.48it/s]
 46%|████▌     | 169822/371472 [2:34:39<16:34:03,  3.38it/s]
 46%|████▌     | 169823/371472 [2:34:39<18:17:39,  3.06it/s]
 46%|████▌     | 169824/371472 [2:34:40<17:32:10,  3.19it/s]
 46%|████▌     | 169825/371472 [2:34:40<17:16:21,  3.24it/s]
 46%|████▌     | 169826/371472 [2:34:40<17:19:22,  3.23it/s]
 46%|████▌     | 169827/371472 [2:34:40<17:07:41,  3.27it/s]
 46%|████▌     | 169828/371472 [2:34:41<17:04:59,  3.28it/s]
 46%|████▌     | 169829/371472 [2:34:41<17:14:13,  3.25it/s]
 46%|████▌     | 169830/371472 [2:34:41<17:06:42,  3.27it/s]
 46%|████▌     | 169831/371472 [2:34:42<17:41:09,  3.17it/s]
 46%|████▌     | 169832/371472 [2:34:42<17:09:51,  3.26it/s]
 46%|████▌     | 169833/371472 [2:34:42<17:37:32,  3.18it/s]
 46%|████▌     | 169834/371472 [2:34:43<17:12:45,  3.25it/s]
 46%|████▌     | 169835/371472 [2:34:43<16:35:08,  3.38it/s]
 46%|████▌     | 169836/371472 [2:34:43<16:31:02,  3.39it/s]
 46%|████▌     | 169837/371472 [2:34:44<17:05:32,  3.28it/s]
 46%|████▌     | 169838/371472 [2:34:44<16:42:44,  3.35it/s]
 46%|████▌     | 169839/371472 [2:34:44<16:12:17,  3.46it/s]
 46%|████▌     | 169840/371472 [2:34:44<16:05:50,  3.48it/s]
                                                            
{'loss': 2.7838, 'learning_rate': 5.887758839880196e-07, 'epoch': 7.32}
+
 46%|████▌     | 169840/371472 [2:34:44<16:05:50,  3.48it/s]
 46%|████▌     | 169841/371472 [2:34:45<16:19:44,  3.43it/s]
 46%|████▌     | 169842/371472 [2:34:45<17:35:11,  3.18it/s]
 46%|████▌     | 169843/371472 [2:34:45<17:43:13,  3.16it/s]
 46%|████▌     | 169844/371472 [2:34:46<17:07:25,  3.27it/s]
 46%|████▌     | 169845/371472 [2:34:46<17:10:39,  3.26it/s]
 46%|████▌     | 169846/371472 [2:34:46<16:56:56,  3.30it/s]
 46%|████▌     | 169847/371472 [2:34:47<17:12:36,  3.25it/s]
 46%|████▌     | 169848/371472 [2:34:47<17:12:30,  3.25it/s]
 46%|████▌     | 169849/371472 [2:34:47<17:11:23,  3.26it/s]
 46%|████▌     | 169850/371472 [2:34:47<17:10:02,  3.26it/s]
 46%|████▌     | 169851/371472 [2:34:48<16:49:11,  3.33it/s]
 46%|████▌     | 169852/371472 [2:34:48<16:35:56,  3.37it/s]
 46%|████▌     | 169853/371472 [2:34:48<16:35:47,  3.37it/s]
 46%|████▌     | 169854/371472 [2:34:49<16:39:19,  3.36it/s]
 46%|████▌     | 169855/371472 [2:34:49<17:20:38,  3.23it/s]
 46%|████▌     | 169856/371472 [2:34:49<17:12:12,  3.26it/s]
 46%|████▌     | 169857/371472 [2:34:50<16:42:56,  3.35it/s]
 46%|████▌     | 169858/371472 [2:34:50<16:51:03,  3.32it/s]
 46%|████▌     | 169859/371472 [2:34:50<17:37:37,  3.18it/s]
 46%|████▌     | 169860/371472 [2:34:50<16:53:59,  3.31it/s]
                                                            
{'loss': 2.854, 'learning_rate': 5.887274020125406e-07, 'epoch': 7.32}
+
 46%|████▌     | 169860/371472 [2:34:50<16:53:59,  3.31it/s]
 46%|████▌     | 169861/371472 [2:34:51<16:45:40,  3.34it/s]
 46%|████▌     | 169862/371472 [2:34:51<16:04:54,  3.48it/s]
 46%|████▌     | 169863/371472 [2:34:51<16:10:32,  3.46it/s]
 46%|████▌     | 169864/371472 [2:34:52<15:45:07,  3.56it/s]
 46%|████▌     | 169865/371472 [2:34:52<16:26:24,  3.41it/s]
 46%|████▌     | 169866/371472 [2:34:52<15:59:45,  3.50it/s]
 46%|████▌     | 169867/371472 [2:34:52<16:22:52,  3.42it/s]
 46%|████▌     | 169868/371472 [2:34:53<16:27:58,  3.40it/s]
 46%|████▌     | 169869/371472 [2:34:53<17:13:57,  3.25it/s]
 46%|████▌     | 169870/371472 [2:34:53<17:10:04,  3.26it/s]
 46%|████▌     | 169871/371472 [2:34:54<17:04:16,  3.28it/s]
 46%|████▌     | 169872/371472 [2:34:54<16:17:14,  3.44it/s]
 46%|████▌     | 169873/371472 [2:34:54<15:40:22,  3.57it/s]
 46%|████▌     | 169874/371472 [2:34:55<15:49:29,  3.54it/s]
 46%|████▌     | 169875/371472 [2:34:55<15:51:03,  3.53it/s]
 46%|████▌     | 169876/371472 [2:34:55<16:11:08,  3.46it/s]
 46%|████▌     | 169877/371472 [2:34:55<16:22:05,  3.42it/s]
 46%|████▌     | 169878/371472 [2:34:56<15:50:32,  3.53it/s]
 46%|████▌     | 169879/371472 [2:34:56<16:06:21,  3.48it/s]
 46%|████▌     | 169880/371472 [2:34:56<17:13:26,  3.25it/s]
                                                            
{'loss': 3.1152, 'learning_rate': 5.886789200370617e-07, 'epoch': 7.32}
+
 46%|████▌     | 169880/371472 [2:34:56<17:13:26,  3.25it/s]
 46%|████▌     | 169881/371472 [2:34:57<17:33:42,  3.19it/s]
 46%|████▌     | 169882/371472 [2:34:57<18:50:12,  2.97it/s]
 46%|████▌     | 169883/371472 [2:34:57<18:31:25,  3.02it/s]
 46%|████▌     | 169884/371472 [2:34:58<17:55:58,  3.12it/s]
 46%|████▌     | 169885/371472 [2:34:58<17:26:09,  3.21it/s]
 46%|████▌     | 169886/371472 [2:34:58<16:49:08,  3.33it/s]
 46%|████▌     | 169887/371472 [2:34:58<16:21:59,  3.42it/s]
 46%|████▌     | 169888/371472 [2:34:59<16:27:24,  3.40it/s]
 46%|████▌     | 169889/371472 [2:34:59<16:36:13,  3.37it/s]
 46%|████▌     | 169890/371472 [2:34:59<16:04:50,  3.48it/s]
 46%|████▌     | 169891/371472 [2:35:00<15:58:32,  3.51it/s]
 46%|████▌     | 169892/371472 [2:35:00<16:25:32,  3.41it/s]
 46%|████▌     | 169893/371472 [2:35:00<16:28:21,  3.40it/s]
 46%|████▌     | 169894/371472 [2:35:01<16:29:44,  3.39it/s]
 46%|████▌     | 169895/371472 [2:35:01<16:25:13,  3.41it/s]
 46%|████▌     | 169896/371472 [2:35:01<15:44:35,  3.56it/s]
 46%|████▌     | 169897/371472 [2:35:01<16:24:59,  3.41it/s]
 46%|████▌     | 169898/371472 [2:35:02<16:09:50,  3.46it/s]
 46%|████▌     | 169899/371472 [2:35:02<15:57:17,  3.51it/s]
 46%|████▌     | 169900/371472 [2:35:02<15:34:18,  3.60it/s]
                                                            
{'loss': 2.9547, 'learning_rate': 5.886304380615828e-07, 'epoch': 7.32}
+
 46%|████▌     | 169900/371472 [2:35:02<15:34:18,  3.60it/s]
 46%|████▌     | 169901/371472 [2:35:02<15:36:41,  3.59it/s]
 46%|████▌     | 169902/371472 [2:35:03<15:56:06,  3.51it/s]
 46%|████▌     | 169903/371472 [2:35:03<15:51:42,  3.53it/s]
 46%|████▌     | 169904/371472 [2:35:03<16:19:38,  3.43it/s]
 46%|████▌     | 169905/371472 [2:35:04<16:20:58,  3.42it/s]
 46%|████▌     | 169906/371472 [2:35:04<16:02:22,  3.49it/s]
 46%|████▌     | 169907/371472 [2:35:04<16:27:25,  3.40it/s]
 46%|████▌     | 169908/371472 [2:35:05<16:39:42,  3.36it/s]
 46%|████▌     | 169909/371472 [2:35:05<16:10:11,  3.46it/s]
 46%|████▌     | 169910/371472 [2:35:05<15:54:10,  3.52it/s]
 46%|████▌     | 169911/371472 [2:35:05<15:56:35,  3.51it/s]
 46%|████▌     | 169912/371472 [2:35:06<15:59:41,  3.50it/s]
 46%|████▌     | 169913/371472 [2:35:06<15:43:56,  3.56it/s]
 46%|████▌     | 169914/371472 [2:35:06<16:26:02,  3.41it/s]
 46%|████▌     | 169915/371472 [2:35:07<16:05:34,  3.48it/s]
 46%|████▌     | 169916/371472 [2:35:07<16:24:37,  3.41it/s]
 46%|████▌     | 169917/371472 [2:35:07<16:37:27,  3.37it/s]
 46%|████▌     | 169918/371472 [2:35:07<17:03:44,  3.28it/s]
 46%|████▌     | 169919/371472 [2:35:08<17:09:43,  3.26it/s]
 46%|████▌     | 169920/371472 [2:35:08<17:05:37,  3.28it/s]
                                                            
{'loss': 3.009, 'learning_rate': 5.88581956086104e-07, 'epoch': 7.32}
+
 46%|████▌     | 169920/371472 [2:35:08<17:05:37,  3.28it/s]
 46%|████▌     | 169921/371472 [2:35:08<16:22:11,  3.42it/s]
 46%|████▌     | 169922/371472 [2:35:09<16:44:55,  3.34it/s]
 46%|████▌     | 169923/371472 [2:35:09<16:30:37,  3.39it/s]
 46%|████▌     | 169924/371472 [2:35:09<16:52:48,  3.32it/s]
 46%|████▌     | 169925/371472 [2:35:10<16:41:51,  3.35it/s]
 46%|████▌     | 169926/371472 [2:35:10<16:21:52,  3.42it/s]
 46%|████▌     | 169927/371472 [2:35:10<16:38:02,  3.37it/s]
 46%|████▌     | 169928/371472 [2:35:10<16:29:38,  3.39it/s]
 46%|████▌     | 169929/371472 [2:35:11<16:08:44,  3.47it/s]
 46%|████▌     | 169930/371472 [2:35:11<16:42:23,  3.35it/s]
 46%|████▌     | 169931/371472 [2:35:11<16:19:41,  3.43it/s]
 46%|████▌     | 169932/371472 [2:35:12<15:59:52,  3.50it/s]
 46%|████▌     | 169933/371472 [2:35:12<15:48:03,  3.54it/s]
 46%|████▌     | 169934/371472 [2:35:12<15:50:26,  3.53it/s]
 46%|████▌     | 169935/371472 [2:35:12<15:53:32,  3.52it/s]
 46%|████▌     | 169936/371472 [2:35:13<16:12:58,  3.45it/s]
 46%|████▌     | 169937/371472 [2:35:13<16:00:55,  3.50it/s]
 46%|████▌     | 169938/371472 [2:35:13<16:19:22,  3.43it/s]
 46%|████▌     | 169939/371472 [2:35:14<16:34:06,  3.38it/s]
 46%|████▌     | 169940/371472 [2:35:14<17:02:53,  3.28it/s]
                                                            
{'loss': 2.9955, 'learning_rate': 5.885334741106251e-07, 'epoch': 7.32}
+
 46%|████▌     | 169940/371472 [2:35:14<17:02:53,  3.28it/s]
 46%|████▌     | 169941/371472 [2:35:14<16:33:17,  3.38it/s]
 46%|████▌     | 169942/371472 [2:35:15<17:19:16,  3.23it/s]
 46%|████▌     | 169943/371472 [2:35:15<16:44:08,  3.34it/s]
 46%|████▌     | 169944/371472 [2:35:15<16:50:26,  3.32it/s]
 46%|████▌     | 169945/371472 [2:35:15<16:32:49,  3.38it/s]
 46%|████▌     | 169946/371472 [2:35:16<16:28:35,  3.40it/s]
 46%|████▌     | 169947/371472 [2:35:16<16:31:40,  3.39it/s]
 46%|████▌     | 169948/371472 [2:35:16<16:37:05,  3.37it/s]
 46%|████▌     | 169949/371472 [2:35:17<17:47:28,  3.15it/s]
 46%|████▌     | 169950/371472 [2:35:17<17:31:50,  3.19it/s]
 46%|████▌     | 169951/371472 [2:35:17<17:07:41,  3.27it/s]
 46%|████▌     | 169952/371472 [2:35:18<16:56:05,  3.31it/s]
 46%|████▌     | 169953/371472 [2:35:18<16:28:45,  3.40it/s]
 46%|████▌     | 169954/371472 [2:35:18<16:34:22,  3.38it/s]
 46%|████▌     | 169955/371472 [2:35:18<16:31:27,  3.39it/s]
 46%|████▌     | 169956/371472 [2:35:19<16:46:27,  3.34it/s]
 46%|████▌     | 169957/371472 [2:35:19<16:25:32,  3.41it/s]
 46%|████▌     | 169958/371472 [2:35:19<16:06:37,  3.47it/s]
 46%|████▌     | 169959/371472 [2:35:20<16:26:35,  3.40it/s]
 46%|████▌     | 169960/371472 [2:35:20<17:11:27,  3.26it/s]
                                                            
{'loss': 2.8114, 'learning_rate': 5.884849921351462e-07, 'epoch': 7.32}
+
 46%|████▌     | 169960/371472 [2:35:20<17:11:27,  3.26it/s]
 46%|████▌     | 169961/371472 [2:35:20<17:28:48,  3.20it/s]
 46%|████▌     | 169962/371472 [2:35:21<17:04:13,  3.28it/s]
 46%|████▌     | 169963/371472 [2:35:21<16:57:38,  3.30it/s]
 46%|████▌     | 169964/371472 [2:35:21<16:53:33,  3.31it/s]
 46%|████▌     | 169965/371472 [2:35:21<17:19:50,  3.23it/s]
 46%|████▌     | 169966/371472 [2:35:22<16:28:05,  3.40it/s]
 46%|████▌     | 169967/371472 [2:35:22<16:47:45,  3.33it/s]
 46%|████▌     | 169968/371472 [2:35:22<16:52:55,  3.32it/s]
 46%|████▌     | 169969/371472 [2:35:23<16:42:02,  3.35it/s]
 46%|████▌     | 169970/371472 [2:35:23<17:07:24,  3.27it/s]
 46%|████▌     | 169971/371472 [2:35:23<16:46:23,  3.34it/s]
 46%|████▌     | 169972/371472 [2:35:24<17:06:08,  3.27it/s]
 46%|████▌     | 169973/371472 [2:35:24<17:07:05,  3.27it/s]
 46%|████▌     | 169974/371472 [2:35:24<17:05:25,  3.28it/s]
 46%|████▌     | 169975/371472 [2:35:25<17:22:16,  3.22it/s]
 46%|████▌     | 169976/371472 [2:35:25<20:18:40,  2.76it/s]
 46%|████▌     | 169977/371472 [2:35:25<19:14:38,  2.91it/s]
 46%|████▌     | 169978/371472 [2:35:26<17:50:11,  3.14it/s]
 46%|████▌     | 169979/371472 [2:35:26<18:30:28,  3.02it/s]
 46%|████▌     | 169980/371472 [2:35:26<17:23:09,  3.22it/s]
                                                            
{'loss': 2.9754, 'learning_rate': 5.884365101596673e-07, 'epoch': 7.32}
+
 46%|████▌     | 169980/371472 [2:35:26<17:23:09,  3.22it/s]
 46%|████▌     | 169981/371472 [2:35:26<17:03:49,  3.28it/s]
 46%|████▌     | 169982/371472 [2:35:27<17:03:09,  3.28it/s]
 46%|████▌     | 169983/371472 [2:35:27<16:39:25,  3.36it/s]
 46%|████▌     | 169984/371472 [2:35:27<16:44:11,  3.34it/s]
 46%|████▌     | 169985/371472 [2:35:28<17:20:20,  3.23it/s]
 46%|████▌     | 169986/371472 [2:35:28<17:15:17,  3.24it/s]
 46%|████▌     | 169987/371472 [2:35:28<17:59:50,  3.11it/s]
 46%|████▌     | 169988/371472 [2:35:29<17:47:33,  3.15it/s]
 46%|████▌     | 169989/371472 [2:35:29<17:16:04,  3.24it/s]
 46%|████▌     | 169990/371472 [2:35:29<16:54:04,  3.31it/s]
 46%|████▌     | 169991/371472 [2:35:30<16:36:12,  3.37it/s]
 46%|████▌     | 169992/371472 [2:35:30<16:14:14,  3.45it/s]
 46%|████▌     | 169993/371472 [2:35:30<15:58:24,  3.50it/s]
 46%|████▌     | 169994/371472 [2:35:30<16:34:02,  3.38it/s]
 46%|████▌     | 169995/371472 [2:35:31<16:50:18,  3.32it/s]
 46%|████▌     | 169996/371472 [2:35:31<17:30:25,  3.20it/s]
 46%|████▌     | 169997/371472 [2:35:31<17:31:28,  3.19it/s]
 46%|████▌     | 169998/371472 [2:35:32<17:35:12,  3.18it/s]
 46%|████▌     | 169999/371472 [2:35:32<17:12:28,  3.25it/s]
 46%|████▌     | 170000/371472 [2:35:32<16:42:02,  3.35it/s]
                                                            
{'loss': 2.9266, 'learning_rate': 5.883880281841884e-07, 'epoch': 7.32}
+
 46%|████▌     | 170000/371472 [2:35:32<16:42:02,  3.35it/s]
 46%|████▌     | 170001/371472 [2:35:33<16:33:41,  3.38it/s]
 46%|████▌     | 170002/371472 [2:35:33<16:28:46,  3.40it/s]
 46%|████▌     | 170003/371472 [2:35:33<17:11:49,  3.25it/s]
 46%|████▌     | 170004/371472 [2:35:33<17:15:39,  3.24it/s]
 46%|████▌     | 170005/371472 [2:35:34<16:52:44,  3.32it/s]
 46%|████▌     | 170006/371472 [2:35:34<17:02:08,  3.29it/s]
 46%|████▌     | 170007/371472 [2:35:34<16:56:15,  3.30it/s]
 46%|████▌     | 170008/371472 [2:35:35<16:49:51,  3.32it/s]
 46%|████▌     | 170009/371472 [2:35:35<19:07:32,  2.93it/s]
 46%|████▌     | 170010/371472 [2:35:35<18:21:08,  3.05it/s]
 46%|████▌     | 170011/371472 [2:35:36<18:28:06,  3.03it/s]
 46%|████▌     | 170012/371472 [2:35:36<17:57:20,  3.12it/s]
 46%|████▌     | 170013/371472 [2:35:36<17:24:18,  3.22it/s]
 46%|████▌     | 170014/371472 [2:35:37<17:15:29,  3.24it/s]
 46%|████▌     | 170015/371472 [2:35:37<16:33:48,  3.38it/s]
 46%|████▌     | 170016/371472 [2:35:37<16:19:48,  3.43it/s]
 46%|████▌     | 170017/371472 [2:35:37<16:32:55,  3.38it/s]
 46%|████▌     | 170018/371472 [2:35:38<16:25:30,  3.41it/s]
 46%|████▌     | 170019/371472 [2:35:38<16:26:52,  3.40it/s]
 46%|████▌     | 170020/371472 [2:35:38<16:21:18,  3.42it/s]
                                                            
{'loss': 2.8869, 'learning_rate': 5.883395462087095e-07, 'epoch': 7.32}
+
 46%|████▌     | 170020/371472 [2:35:38<16:21:18,  3.42it/s]
 46%|████▌     | 170021/371472 [2:35:39<16:54:52,  3.31it/s]
 46%|████▌     | 170022/371472 [2:35:39<17:04:22,  3.28it/s]
 46%|████▌     | 170023/371472 [2:35:39<17:06:04,  3.27it/s]
 46%|████▌     | 170024/371472 [2:35:40<17:08:21,  3.26it/s]
 46%|████▌     | 170025/371472 [2:35:40<17:08:18,  3.27it/s]
 46%|████▌     | 170026/371472 [2:35:40<17:09:24,  3.26it/s]
 46%|████▌     | 170027/371472 [2:35:40<16:41:41,  3.35it/s]
 46%|████▌     | 170028/371472 [2:35:41<16:04:24,  3.48it/s]
 46%|████▌     | 170029/371472 [2:35:41<16:08:43,  3.47it/s]
 46%|████▌     | 170030/371472 [2:35:41<16:48:40,  3.33it/s]
 46%|████▌     | 170031/371472 [2:35:42<17:06:14,  3.27it/s]
 46%|████▌     | 170032/371472 [2:35:42<17:06:55,  3.27it/s]
 46%|████▌     | 170033/371472 [2:35:42<17:17:10,  3.24it/s]
 46%|████▌     | 170034/371472 [2:35:43<16:47:25,  3.33it/s]
 46%|████▌     | 170035/371472 [2:35:43<16:41:18,  3.35it/s]
 46%|████▌     | 170036/371472 [2:35:43<16:17:46,  3.43it/s]
 46%|████▌     | 170037/371472 [2:35:43<16:30:49,  3.39it/s]
 46%|████▌     | 170038/371472 [2:35:44<17:47:15,  3.15it/s]
 46%|████▌     | 170039/371472 [2:35:44<17:22:34,  3.22it/s]
 46%|████▌     | 170040/371472 [2:35:44<17:23:41,  3.22it/s]
                                                            
{'loss': 2.9221, 'learning_rate': 5.882910642332306e-07, 'epoch': 7.32}
+
 46%|████▌     | 170040/371472 [2:35:44<17:23:41,  3.22it/s]
 46%|████▌     | 170041/371472 [2:35:45<17:50:40,  3.14it/s]
 46%|████▌     | 170042/371472 [2:35:45<17:50:44,  3.14it/s]
 46%|████▌     | 170043/371472 [2:35:45<18:08:23,  3.08it/s]
 46%|████▌     | 170044/371472 [2:35:46<17:24:41,  3.21it/s]
 46%|████▌     | 170045/371472 [2:35:46<18:08:59,  3.08it/s]
 46%|████▌     | 170046/371472 [2:35:46<17:55:41,  3.12it/s]
 46%|████▌     | 170047/371472 [2:35:47<17:22:29,  3.22it/s]
 46%|████▌     | 170048/371472 [2:35:47<19:03:31,  2.94it/s]
 46%|████▌     | 170049/371472 [2:35:47<18:15:15,  3.07it/s]
 46%|████▌     | 170050/371472 [2:35:48<17:40:32,  3.17it/s]
 46%|████▌     | 170051/371472 [2:35:48<17:47:26,  3.14it/s]
 46%|████▌     | 170052/371472 [2:35:48<17:13:26,  3.25it/s]
 46%|████▌     | 170053/371472 [2:35:49<16:53:48,  3.31it/s]
 46%|████▌     | 170054/371472 [2:35:49<16:59:33,  3.29it/s]
 46%|████▌     | 170055/371472 [2:35:49<18:53:54,  2.96it/s]
 46%|████▌     | 170056/371472 [2:35:50<17:59:39,  3.11it/s]
 46%|████▌     | 170057/371472 [2:35:50<17:44:00,  3.15it/s]
 46%|████▌     | 170058/371472 [2:35:50<17:45:48,  3.15it/s]
 46%|████▌     | 170059/371472 [2:35:51<18:03:48,  3.10it/s]
 46%|████▌     | 170060/371472 [2:35:51<17:36:29,  3.18it/s]
                                                            
{'loss': 2.8042, 'learning_rate': 5.882425822577517e-07, 'epoch': 7.32}
+
 46%|████▌     | 170060/371472 [2:35:51<17:36:29,  3.18it/s]
 46%|████▌     | 170061/371472 [2:35:51<17:47:09,  3.15it/s]
 46%|████▌     | 170062/371472 [2:35:51<17:33:15,  3.19it/s]
 46%|████▌     | 170063/371472 [2:35:52<17:13:16,  3.25it/s]
 46%|████▌     | 170064/371472 [2:35:52<17:01:27,  3.29it/s]
 46%|████▌     | 170065/371472 [2:35:52<17:32:12,  3.19it/s]
 46%|████▌     | 170066/371472 [2:35:53<17:12:04,  3.25it/s]
 46%|████▌     | 170067/371472 [2:35:53<16:45:27,  3.34it/s]
 46%|████▌     | 170068/371472 [2:35:53<16:30:34,  3.39it/s]
 46%|████▌     | 170069/371472 [2:35:54<16:56:17,  3.30it/s]
 46%|████▌     | 170070/371472 [2:35:54<16:42:43,  3.35it/s]
 46%|████▌     | 170071/371472 [2:35:54<16:22:13,  3.42it/s]
 46%|████▌     | 170072/371472 [2:35:54<16:30:46,  3.39it/s]
 46%|████▌     | 170073/371472 [2:35:55<16:32:14,  3.38it/s]
 46%|████▌     | 170074/371472 [2:35:55<16:31:23,  3.39it/s]
 46%|████▌     | 170075/371472 [2:35:55<18:21:10,  3.05it/s]
 46%|████▌     | 170076/371472 [2:35:56<19:54:03,  2.81it/s]
 46%|████▌     | 170077/371472 [2:35:56<19:13:50,  2.91it/s]
 46%|████▌     | 170078/371472 [2:35:56<18:29:31,  3.03it/s]
 46%|████▌     | 170079/371472 [2:35:57<18:31:14,  3.02it/s]
 46%|████▌     | 170080/371472 [2:35:57<17:46:49,  3.15it/s]
                                                            
{'loss': 2.8651, 'learning_rate': 5.881941002822729e-07, 'epoch': 7.33}
+
 46%|████▌     | 170080/371472 [2:35:57<17:46:49,  3.15it/s]
 46%|████▌     | 170081/371472 [2:35:57<18:26:43,  3.03it/s]
 46%|████▌     | 170082/371472 [2:35:58<17:59:39,  3.11it/s]
 46%|████▌     | 170083/371472 [2:35:58<17:19:38,  3.23it/s]
 46%|████▌     | 170084/371472 [2:35:58<16:42:42,  3.35it/s]
 46%|████▌     | 170085/371472 [2:35:59<16:25:05,  3.41it/s]
 46%|████▌     | 170086/371472 [2:35:59<16:54:37,  3.31it/s]
 46%|████▌     | 170087/371472 [2:35:59<17:15:31,  3.24it/s]
 46%|████▌     | 170088/371472 [2:36:00<17:25:52,  3.21it/s]
 46%|████▌     | 170089/371472 [2:36:00<17:20:38,  3.23it/s]
 46%|████▌     | 170090/371472 [2:36:00<17:42:44,  3.16it/s]
 46%|████▌     | 170091/371472 [2:36:01<18:03:12,  3.10it/s]
 46%|████▌     | 170092/371472 [2:36:01<17:20:23,  3.23it/s]
 46%|████▌     | 170093/371472 [2:36:01<17:09:41,  3.26it/s]
 46%|████▌     | 170094/371472 [2:36:01<16:53:56,  3.31it/s]
 46%|████▌     | 170095/371472 [2:36:02<16:44:47,  3.34it/s]
 46%|████▌     | 170096/371472 [2:36:02<16:31:57,  3.38it/s]
 46%|████▌     | 170097/371472 [2:36:02<16:29:02,  3.39it/s]
 46%|████▌     | 170098/371472 [2:36:03<16:41:25,  3.35it/s]
 46%|████▌     | 170099/371472 [2:36:03<16:40:59,  3.35it/s]
 46%|████▌     | 170100/371472 [2:36:03<17:26:37,  3.21it/s]
                                                            
{'loss': 2.9741, 'learning_rate': 5.88145618306794e-07, 'epoch': 7.33}
+
 46%|████▌     | 170100/371472 [2:36:03<17:26:37,  3.21it/s]
 46%|████▌     | 170101/371472 [2:36:04<17:55:41,  3.12it/s]
 46%|████▌     | 170102/371472 [2:36:04<17:17:40,  3.23it/s]
 46%|████▌     | 170103/371472 [2:36:04<17:57:47,  3.11it/s]
 46%|████▌     | 170104/371472 [2:36:05<19:08:18,  2.92it/s]
 46%|████▌     | 170105/371472 [2:36:05<18:10:03,  3.08it/s]
 46%|████▌     | 170106/371472 [2:36:05<17:24:24,  3.21it/s]
 46%|████▌     | 170107/371472 [2:36:05<16:56:48,  3.30it/s]
 46%|████▌     | 170108/371472 [2:36:06<17:06:14,  3.27it/s]
 46%|████▌     | 170109/371472 [2:36:06<17:09:20,  3.26it/s]
 46%|████▌     | 170110/371472 [2:36:06<17:37:50,  3.17it/s]
 46%|████▌     | 170111/371472 [2:36:07<17:12:59,  3.25it/s]
 46%|████▌     | 170112/371472 [2:36:07<18:15:04,  3.06it/s]
 46%|████▌     | 170113/371472 [2:36:07<18:09:39,  3.08it/s]
 46%|████▌     | 170114/371472 [2:36:08<17:26:17,  3.21it/s]
 46%|████▌     | 170115/371472 [2:36:08<16:48:10,  3.33it/s]
 46%|████▌     | 170116/371472 [2:36:08<16:55:18,  3.31it/s]
 46%|████▌     | 170117/371472 [2:36:09<17:15:09,  3.24it/s]
 46%|████▌     | 170118/371472 [2:36:09<17:00:41,  3.29it/s]
 46%|████▌     | 170119/371472 [2:36:09<17:20:16,  3.23it/s]
 46%|████▌     | 170120/371472 [2:36:09<16:32:19,  3.38it/s]
                                                            
{'loss': 2.6987, 'learning_rate': 5.880971363313149e-07, 'epoch': 7.33}
+
 46%|████▌     | 170120/371472 [2:36:09<16:32:19,  3.38it/s]
 46%|████▌     | 170121/371472 [2:36:10<17:18:39,  3.23it/s]
 46%|████▌     | 170122/371472 [2:36:10<16:54:30,  3.31it/s]
 46%|████▌     | 170123/371472 [2:36:10<16:34:25,  3.37it/s]
 46%|████▌     | 170124/371472 [2:36:11<16:17:16,  3.43it/s]
 46%|████▌     | 170125/371472 [2:36:11<16:45:07,  3.34it/s]
 46%|████▌     | 170126/371472 [2:36:11<16:39:02,  3.36it/s]
 46%|████▌     | 170127/371472 [2:36:12<16:19:37,  3.43it/s]
 46%|████▌     | 170128/371472 [2:36:12<16:02:47,  3.49it/s]
 46%|████▌     | 170129/371472 [2:36:12<16:13:30,  3.45it/s]
 46%|████▌     | 170130/371472 [2:36:12<15:46:52,  3.54it/s]
 46%|████▌     | 170131/371472 [2:36:13<16:13:27,  3.45it/s]
 46%|████▌     | 170132/371472 [2:36:13<16:03:05,  3.48it/s]
 46%|████▌     | 170133/371472 [2:36:13<16:49:34,  3.32it/s]
 46%|████▌     | 170134/371472 [2:36:14<16:48:38,  3.33it/s]
 46%|████▌     | 170135/371472 [2:36:14<16:30:52,  3.39it/s]
 46%|████▌     | 170136/371472 [2:36:14<16:38:43,  3.36it/s]
 46%|████▌     | 170137/371472 [2:36:14<16:23:14,  3.41it/s]
 46%|████▌     | 170138/371472 [2:36:15<17:52:00,  3.13it/s]
 46%|████▌     | 170139/371472 [2:36:15<17:15:41,  3.24it/s]
 46%|████▌     | 170140/371472 [2:36:15<18:17:52,  3.06it/s]
                                                            
{'loss': 3.0572, 'learning_rate': 5.880486543558361e-07, 'epoch': 7.33}
+
 46%|████▌     | 170140/371472 [2:36:15<18:17:52,  3.06it/s]
 46%|████▌     | 170141/371472 [2:36:16<17:43:29,  3.16it/s]
 46%|████▌     | 170142/371472 [2:36:16<17:19:06,  3.23it/s]
 46%|████▌     | 170143/371472 [2:36:16<17:45:36,  3.15it/s]
 46%|████▌     | 170144/371472 [2:36:17<19:01:01,  2.94it/s]
 46%|████▌     | 170145/371472 [2:36:17<17:53:23,  3.13it/s]
 46%|████▌     | 170146/371472 [2:36:17<17:22:30,  3.22it/s]
 46%|████▌     | 170147/371472 [2:36:18<17:33:44,  3.18it/s]
 46%|████▌     | 170148/371472 [2:36:18<16:51:24,  3.32it/s]
 46%|████▌     | 170149/371472 [2:36:18<16:47:14,  3.33it/s]
 46%|████▌     | 170150/371472 [2:36:19<17:30:44,  3.19it/s]
 46%|████▌     | 170151/371472 [2:36:19<17:14:56,  3.24it/s]
 46%|████▌     | 170152/371472 [2:36:19<17:11:55,  3.25it/s]
 46%|████▌     | 170153/371472 [2:36:19<16:53:19,  3.31it/s]
 46%|████▌     | 170154/371472 [2:36:20<16:51:48,  3.32it/s]
 46%|████▌     | 170155/371472 [2:36:20<16:26:10,  3.40it/s]
 46%|████▌     | 170156/371472 [2:36:20<17:03:09,  3.28it/s]
 46%|████▌     | 170157/371472 [2:36:21<16:45:16,  3.34it/s]
 46%|████▌     | 170158/371472 [2:36:21<16:52:41,  3.31it/s]
 46%|████▌     | 170159/371472 [2:36:21<16:37:00,  3.37it/s]
 46%|████▌     | 170160/371472 [2:36:22<16:22:40,  3.41it/s]
                                                            
{'loss': 2.7799, 'learning_rate': 5.880001723803572e-07, 'epoch': 7.33}
+
 46%|████▌     | 170160/371472 [2:36:22<16:22:40,  3.41it/s]
 46%|████▌     | 170161/371472 [2:36:22<16:17:28,  3.43it/s]
 46%|████▌     | 170162/371472 [2:36:22<16:22:25,  3.42it/s]
 46%|████▌     | 170163/371472 [2:36:22<16:02:29,  3.49it/s]
 46%|████▌     | 170164/371472 [2:36:23<16:28:37,  3.39it/s]
 46%|████▌     | 170165/371472 [2:36:23<16:32:25,  3.38it/s]
 46%|████▌     | 170166/371472 [2:36:23<16:59:12,  3.29it/s]
 46%|████▌     | 170167/371472 [2:36:24<16:51:20,  3.32it/s]
 46%|████▌     | 170168/371472 [2:36:24<17:14:12,  3.24it/s]
 46%|████▌     | 170169/371472 [2:36:24<17:37:27,  3.17it/s]
 46%|████▌     | 170170/371472 [2:36:25<17:10:04,  3.26it/s]
 46%|████▌     | 170171/371472 [2:36:25<16:35:20,  3.37it/s]
 46%|████▌     | 170172/371472 [2:36:25<18:46:11,  2.98it/s]
 46%|████▌     | 170173/371472 [2:36:26<18:01:29,  3.10it/s]
 46%|████▌     | 170174/371472 [2:36:26<17:50:59,  3.13it/s]
 46%|████▌     | 170175/371472 [2:36:26<17:24:26,  3.21it/s]
 46%|████▌     | 170176/371472 [2:36:26<17:12:50,  3.25it/s]
 46%|████▌     | 170177/371472 [2:36:27<18:08:39,  3.08it/s]
 46%|████▌     | 170178/371472 [2:36:27<18:25:34,  3.03it/s]
 46%|████▌     | 170179/371472 [2:36:27<18:08:33,  3.08it/s]
 46%|████▌     | 170180/371472 [2:36:28<17:28:45,  3.20it/s]
                                                            
{'loss': 2.9505, 'learning_rate': 5.879516904048783e-07, 'epoch': 7.33}
+
 46%|████▌     | 170180/371472 [2:36:28<17:28:45,  3.20it/s]
 46%|████▌     | 170181/371472 [2:36:28<17:08:35,  3.26it/s]
 46%|████▌     | 170182/371472 [2:36:28<17:04:44,  3.27it/s]
 46%|████▌     | 170183/371472 [2:36:29<16:45:10,  3.34it/s]
 46%|████▌     | 170184/371472 [2:36:29<16:57:10,  3.30it/s]
 46%|████▌     | 170185/371472 [2:36:29<17:07:28,  3.27it/s]
 46%|████▌     | 170186/371472 [2:36:30<17:22:01,  3.22it/s]
 46%|████▌     | 170187/371472 [2:36:30<18:03:05,  3.10it/s]
 46%|████▌     | 170188/371472 [2:36:30<17:27:59,  3.20it/s]
 46%|████▌     | 170189/371472 [2:36:31<16:53:56,  3.31it/s]
 46%|████▌     | 170190/371472 [2:36:31<16:41:39,  3.35it/s]
 46%|████▌     | 170191/371472 [2:36:31<17:21:08,  3.22it/s]
 46%|████▌     | 170192/371472 [2:36:31<17:00:44,  3.29it/s]
 46%|████▌     | 170193/371472 [2:36:32<16:46:49,  3.33it/s]
 46%|████▌     | 170194/371472 [2:36:32<16:39:09,  3.36it/s]
 46%|████▌     | 170195/371472 [2:36:32<16:36:03,  3.37it/s]
 46%|████▌     | 170196/371472 [2:36:33<16:48:49,  3.33it/s]
 46%|████▌     | 170197/371472 [2:36:33<16:53:51,  3.31it/s]
 46%|████▌     | 170198/371472 [2:36:33<17:41:42,  3.16it/s]
 46%|████▌     | 170199/371472 [2:36:34<17:12:33,  3.25it/s]
 46%|████▌     | 170200/371472 [2:36:34<16:46:41,  3.33it/s]
                                                            
{'loss': 3.0217, 'learning_rate': 5.879032084293994e-07, 'epoch': 7.33}
+
 46%|████▌     | 170200/371472 [2:36:34<16:46:41,  3.33it/s]
 46%|████▌     | 170201/371472 [2:36:34<16:23:21,  3.41it/s]
 46%|████▌     | 170202/371472 [2:36:34<16:16:48,  3.43it/s]
 46%|████▌     | 170203/371472 [2:36:35<16:18:38,  3.43it/s]
 46%|████▌     | 170204/371472 [2:36:35<16:39:56,  3.35it/s]
 46%|████▌     | 170205/371472 [2:36:35<16:59:00,  3.29it/s]
 46%|████▌     | 170206/371472 [2:36:36<17:20:17,  3.22it/s]
 46%|████▌     | 170207/371472 [2:36:36<18:05:14,  3.09it/s]
 46%|████▌     | 170208/371472 [2:36:36<17:37:09,  3.17it/s]
 46%|████▌     | 170209/371472 [2:36:37<16:42:39,  3.35it/s]
 46%|████▌     | 170210/371472 [2:36:37<16:26:33,  3.40it/s]
 46%|████▌     | 170211/371472 [2:36:37<16:33:52,  3.38it/s]
 46%|████▌     | 170212/371472 [2:36:37<16:32:56,  3.38it/s]
 46%|████▌     | 170213/371472 [2:36:38<16:33:15,  3.38it/s]
 46%|████▌     | 170214/371472 [2:36:38<16:30:17,  3.39it/s]
 46%|████▌     | 170215/371472 [2:36:38<16:24:41,  3.41it/s]
 46%|████▌     | 170216/371472 [2:36:39<16:24:37,  3.41it/s]
 46%|████▌     | 170217/371472 [2:36:39<16:16:43,  3.43it/s]
 46%|████▌     | 170218/371472 [2:36:39<17:26:13,  3.21it/s]
 46%|████▌     | 170219/371472 [2:36:40<17:02:07,  3.28it/s]
 46%|████▌     | 170220/371472 [2:36:40<17:01:44,  3.28it/s]
                                                            
{'loss': 3.004, 'learning_rate': 5.878547264539206e-07, 'epoch': 7.33}
+
 46%|████▌     | 170220/371472 [2:36:40<17:01:44,  3.28it/s]
 46%|████▌     | 170221/371472 [2:36:40<16:54:25,  3.31it/s]
 46%|████▌     | 170222/371472 [2:36:40<17:03:03,  3.28it/s]
 46%|████▌     | 170223/371472 [2:36:41<17:05:54,  3.27it/s]
 46%|████▌     | 170224/371472 [2:36:41<16:50:30,  3.32it/s]
 46%|████▌     | 170225/371472 [2:36:41<17:02:39,  3.28it/s]
 46%|████▌     | 170226/371472 [2:36:42<16:32:19,  3.38it/s]
 46%|████▌     | 170227/371472 [2:36:42<16:31:43,  3.38it/s]
 46%|████▌     | 170228/371472 [2:36:42<16:39:00,  3.36it/s]
 46%|████▌     | 170229/371472 [2:36:43<18:06:49,  3.09it/s]
 46%|████▌     | 170230/371472 [2:36:43<18:18:45,  3.05it/s]
 46%|████▌     | 170231/371472 [2:36:43<18:24:01,  3.04it/s]
 46%|████▌     | 170232/371472 [2:36:44<18:53:30,  2.96it/s]
 46%|████▌     | 170233/371472 [2:36:44<18:03:53,  3.09it/s]
 46%|████▌     | 170234/371472 [2:36:44<18:07:19,  3.08it/s]
 46%|████▌     | 170235/371472 [2:36:45<17:48:36,  3.14it/s]
 46%|████▌     | 170236/371472 [2:36:45<17:20:52,  3.22it/s]
 46%|████▌     | 170237/371472 [2:36:45<16:59:32,  3.29it/s]
 46%|████▌     | 170238/371472 [2:36:45<16:49:28,  3.32it/s]
 46%|████▌     | 170239/371472 [2:36:46<17:16:39,  3.24it/s]
 46%|████▌     | 170240/371472 [2:36:46<16:42:12,  3.35it/s]
                                                            
{'loss': 2.9208, 'learning_rate': 5.878062444784416e-07, 'epoch': 7.33}
+
 46%|████▌     | 170240/371472 [2:36:46<16:42:12,  3.35it/s]
 46%|████▌     | 170241/371472 [2:36:46<16:33:07,  3.38it/s]
 46%|████▌     | 170242/371472 [2:36:47<17:00:49,  3.29it/s]
 46%|████▌     | 170243/371472 [2:36:47<17:45:28,  3.15it/s]
 46%|████▌     | 170244/371472 [2:36:47<17:42:27,  3.16it/s]
 46%|████▌     | 170245/371472 [2:36:48<17:25:55,  3.21it/s]
 46%|████▌     | 170246/371472 [2:36:48<17:58:10,  3.11it/s]
 46%|████▌     | 170247/371472 [2:36:48<18:18:38,  3.05it/s]
 46%|████▌     | 170248/371472 [2:36:49<17:25:07,  3.21it/s]
 46%|████▌     | 170249/371472 [2:36:49<17:28:53,  3.20it/s]
 46%|████▌     | 170250/371472 [2:36:49<16:57:51,  3.29it/s]
 46%|████▌     | 170251/371472 [2:36:49<16:25:04,  3.40it/s]
 46%|████▌     | 170252/371472 [2:36:50<16:47:20,  3.33it/s]
 46%|████▌     | 170253/371472 [2:36:50<16:50:16,  3.32it/s]
 46%|████▌     | 170254/371472 [2:36:50<16:31:48,  3.38it/s]
 46%|████▌     | 170255/371472 [2:36:51<16:04:49,  3.48it/s]
 46%|████▌     | 170256/371472 [2:36:51<16:04:59,  3.48it/s]
 46%|████▌     | 170257/371472 [2:36:51<16:47:40,  3.33it/s]
 46%|████▌     | 170258/371472 [2:36:52<17:19:28,  3.23it/s]
 46%|████▌     | 170259/371472 [2:36:52<17:11:55,  3.25it/s]
 46%|████▌     | 170260/371472 [2:36:52<17:34:13,  3.18it/s]
                                                            
{'loss': 2.8257, 'learning_rate': 5.877577625029627e-07, 'epoch': 7.33}
+
 46%|████▌     | 170260/371472 [2:36:52<17:34:13,  3.18it/s]
 46%|████▌     | 170261/371472 [2:36:53<17:04:55,  3.27it/s]
 46%|████▌     | 170262/371472 [2:36:53<16:28:17,  3.39it/s]
 46%|████▌     | 170263/371472 [2:36:53<16:25:56,  3.40it/s]
 46%|████▌     | 170264/371472 [2:36:53<16:16:00,  3.44it/s]
 46%|████▌     | 170265/371472 [2:36:54<15:52:00,  3.52it/s]
 46%|████▌     | 170266/371472 [2:36:54<17:04:10,  3.27it/s]
 46%|████▌     | 170267/371472 [2:36:54<17:16:30,  3.24it/s]
 46%|████▌     | 170268/371472 [2:36:55<16:39:12,  3.36it/s]
 46%|████▌     | 170269/371472 [2:36:55<16:27:12,  3.40it/s]
 46%|████▌     | 170270/371472 [2:36:55<16:17:18,  3.43it/s]
 46%|████▌     | 170271/371472 [2:36:55<16:27:24,  3.40it/s]
 46%|████▌     | 170272/371472 [2:36:56<16:04:09,  3.48it/s]
 46%|████▌     | 170273/371472 [2:36:56<16:18:06,  3.43it/s]
 46%|████▌     | 170274/371472 [2:36:56<17:36:33,  3.17it/s]
 46%|████▌     | 170275/371472 [2:36:57<17:23:03,  3.21it/s]
 46%|████▌     | 170276/371472 [2:36:57<16:56:11,  3.30it/s]
 46%|████▌     | 170277/371472 [2:36:57<17:57:49,  3.11it/s]
 46%|████▌     | 170278/371472 [2:36:58<17:56:35,  3.11it/s]
 46%|████▌     | 170279/371472 [2:36:58<17:27:40,  3.20it/s]
 46%|████▌     | 170280/371472 [2:36:58<17:00:30,  3.29it/s]
                                                            
{'loss': 3.045, 'learning_rate': 5.877092805274838e-07, 'epoch': 7.33}
+
 46%|████▌     | 170280/371472 [2:36:58<17:00:30,  3.29it/s]
 46%|████▌     | 170281/371472 [2:36:59<16:51:25,  3.32it/s]
 46%|████▌     | 170282/371472 [2:36:59<16:53:14,  3.31it/s]
 46%|████▌     | 170283/371472 [2:36:59<16:26:51,  3.40it/s]
 46%|████▌     | 170284/371472 [2:36:59<16:24:43,  3.41it/s]
 46%|████▌     | 170285/371472 [2:37:00<16:21:19,  3.42it/s]
 46%|████▌     | 170286/371472 [2:37:00<15:57:24,  3.50it/s]
 46%|████▌     | 170287/371472 [2:37:00<16:22:48,  3.41it/s]
 46%|████▌     | 170288/371472 [2:37:01<16:06:36,  3.47it/s]
 46%|████▌     | 170289/371472 [2:37:01<16:08:58,  3.46it/s]
 46%|████▌     | 170290/371472 [2:37:01<16:26:42,  3.40it/s]
 46%|████▌     | 170291/371472 [2:37:01<16:30:55,  3.38it/s]
 46%|████▌     | 170292/371472 [2:37:02<16:37:57,  3.36it/s]
 46%|████▌     | 170293/371472 [2:37:02<16:31:20,  3.38it/s]
 46%|████▌     | 170294/371472 [2:37:02<16:29:40,  3.39it/s]
 46%|████▌     | 170295/371472 [2:37:03<16:29:02,  3.39it/s]
 46%|████▌     | 170296/371472 [2:37:03<17:17:14,  3.23it/s]
 46%|████▌     | 170297/371472 [2:37:03<17:48:18,  3.14it/s]
 46%|████▌     | 170298/371472 [2:37:04<18:04:15,  3.09it/s]
 46%|████▌     | 170299/371472 [2:37:04<17:34:50,  3.18it/s]
 46%|████▌     | 170300/371472 [2:37:04<17:33:57,  3.18it/s]
                                                            
{'loss': 2.9598, 'learning_rate': 5.87660798552005e-07, 'epoch': 7.34}
+
 46%|████▌     | 170300/371472 [2:37:04<17:33:57,  3.18it/s]
 46%|████▌     | 170301/371472 [2:37:05<17:16:08,  3.24it/s]
 46%|████▌     | 170302/371472 [2:37:05<16:51:51,  3.31it/s]
 46%|████▌     | 170303/371472 [2:37:05<17:13:10,  3.25it/s]
 46%|████▌     | 170304/371472 [2:37:05<16:53:15,  3.31it/s]
 46%|████▌     | 170305/371472 [2:37:06<17:10:44,  3.25it/s]
 46%|████▌     | 170306/371472 [2:37:06<16:59:42,  3.29it/s]
 46%|████▌     | 170307/371472 [2:37:06<17:09:51,  3.26it/s]
 46%|████▌     | 170308/371472 [2:37:07<16:54:41,  3.30it/s]
 46%|████▌     | 170309/371472 [2:37:07<16:41:36,  3.35it/s]
 46%|████▌     | 170310/371472 [2:37:07<16:46:04,  3.33it/s]
 46%|████▌     | 170311/371472 [2:37:08<16:56:27,  3.30it/s]
 46%|████▌     | 170312/371472 [2:37:08<16:43:58,  3.34it/s]
 46%|████▌     | 170313/371472 [2:37:08<16:25:42,  3.40it/s]
 46%|████▌     | 170314/371472 [2:37:08<16:18:39,  3.43it/s]
 46%|████▌     | 170315/371472 [2:37:09<17:14:47,  3.24it/s]
 46%|████▌     | 170316/371472 [2:37:09<16:34:48,  3.37it/s]
 46%|████▌     | 170317/371472 [2:37:09<16:59:59,  3.29it/s]
 46%|████▌     | 170318/371472 [2:37:10<16:28:57,  3.39it/s]
 46%|████▌     | 170319/371472 [2:37:10<16:16:30,  3.43it/s]
 46%|████▌     | 170320/371472 [2:37:10<16:21:27,  3.42it/s]
                                                            
{'loss': 3.1423, 'learning_rate': 5.876123165765261e-07, 'epoch': 7.34}
+
 46%|████▌     | 170320/371472 [2:37:10<16:21:27,  3.42it/s]
 46%|████▌     | 170321/371472 [2:37:10<16:04:25,  3.48it/s]
 46%|████▌     | 170322/371472 [2:37:11<16:58:24,  3.29it/s]
 46%|████▌     | 170323/371472 [2:37:11<17:40:27,  3.16it/s]
 46%|████▌     | 170324/371472 [2:37:12<17:55:41,  3.12it/s]
 46%|████▌     | 170325/371472 [2:37:12<17:40:43,  3.16it/s]
 46%|████▌     | 170326/371472 [2:37:12<17:33:10,  3.18it/s]
 46%|████▌     | 170327/371472 [2:37:12<17:58:45,  3.11it/s]
 46%|████▌     | 170328/371472 [2:37:13<17:28:02,  3.20it/s]
 46%|████▌     | 170329/371472 [2:37:13<17:16:43,  3.23it/s]
 46%|████▌     | 170330/371472 [2:37:13<17:32:48,  3.18it/s]
 46%|████▌     | 170331/371472 [2:37:14<17:05:33,  3.27it/s]
 46%|████▌     | 170332/371472 [2:37:14<16:35:14,  3.37it/s]
 46%|████▌     | 170333/371472 [2:37:14<16:02:35,  3.48it/s]
 46%|████▌     | 170334/371472 [2:37:14<15:56:15,  3.51it/s]
 46%|████▌     | 170335/371472 [2:37:15<16:33:35,  3.37it/s]
 46%|████▌     | 170336/371472 [2:37:15<16:28:29,  3.39it/s]
 46%|████▌     | 170337/371472 [2:37:15<16:27:11,  3.40it/s]
 46%|████▌     | 170338/371472 [2:37:16<16:42:47,  3.34it/s]
 46%|████▌     | 170339/371472 [2:37:16<16:28:08,  3.39it/s]
 46%|████▌     | 170340/371472 [2:37:16<16:58:14,  3.29it/s]
                                                            
{'loss': 2.8198, 'learning_rate': 5.875638346010472e-07, 'epoch': 7.34}
+
 46%|████▌     | 170340/371472 [2:37:16<16:58:14,  3.29it/s]
 46%|████▌     | 170341/371472 [2:37:17<17:33:11,  3.18it/s]
 46%|████▌     | 170342/371472 [2:37:17<16:56:12,  3.30it/s]
 46%|████▌     | 170343/371472 [2:37:17<16:42:39,  3.34it/s]
 46%|████▌     | 170344/371472 [2:37:18<16:47:08,  3.33it/s]
 46%|████▌     | 170345/371472 [2:37:18<17:11:04,  3.25it/s]
 46%|████▌     | 170346/371472 [2:37:18<16:30:24,  3.38it/s]
 46%|████▌     | 170347/371472 [2:37:18<17:32:34,  3.18it/s]
 46%|████▌     | 170348/371472 [2:37:19<19:12:16,  2.91it/s]
 46%|████▌     | 170349/371472 [2:37:19<18:10:37,  3.07it/s]
 46%|████▌     | 170350/371472 [2:37:20<18:44:37,  2.98it/s]
 46%|████▌     | 170351/371472 [2:37:20<17:53:58,  3.12it/s]
 46%|████▌     | 170352/371472 [2:37:20<17:03:17,  3.28it/s]
 46%|████▌     | 170353/371472 [2:37:20<17:45:13,  3.15it/s]
 46%|████▌     | 170354/371472 [2:37:21<17:01:14,  3.28it/s]
 46%|████▌     | 170355/371472 [2:37:21<16:52:27,  3.31it/s]
 46%|████▌     | 170356/371472 [2:37:21<16:34:21,  3.37it/s]
 46%|████▌     | 170357/371472 [2:37:22<17:38:47,  3.17it/s]
 46%|████▌     | 170358/371472 [2:37:22<16:47:33,  3.33it/s]
 46%|████▌     | 170359/371472 [2:37:22<18:01:49,  3.10it/s]
 46%|████▌     | 170360/371472 [2:37:23<17:32:51,  3.18it/s]
                                                            
{'loss': 2.9087, 'learning_rate': 5.875153526255683e-07, 'epoch': 7.34}
+
 46%|████▌     | 170360/371472 [2:37:23<17:32:51,  3.18it/s]
 46%|████▌     | 170361/371472 [2:37:23<17:03:22,  3.28it/s]
 46%|████▌     | 170362/371472 [2:37:23<17:06:13,  3.27it/s]
 46%|████▌     | 170363/371472 [2:37:23<17:10:44,  3.25it/s]
 46%|████▌     | 170364/371472 [2:37:24<16:54:37,  3.30it/s]
 46%|████▌     | 170365/371472 [2:37:24<16:48:07,  3.32it/s]
 46%|████▌     | 170366/371472 [2:37:24<16:31:38,  3.38it/s]
 46%|████▌     | 170367/371472 [2:37:25<16:22:12,  3.41it/s]
 46%|████▌     | 170368/371472 [2:37:25<16:26:07,  3.40it/s]
 46%|████▌     | 170369/371472 [2:37:25<16:17:47,  3.43it/s]
 46%|████▌     | 170370/371472 [2:37:26<16:40:01,  3.35it/s]
 46%|████▌     | 170371/371472 [2:37:26<16:29:48,  3.39it/s]
 46%|████▌     | 170372/371472 [2:37:26<19:49:13,  2.82it/s]
 46%|████▌     | 170373/371472 [2:37:27<19:17:19,  2.90it/s]
 46%|████▌     | 170374/371472 [2:37:27<18:05:08,  3.09it/s]
 46%|████▌     | 170375/371472 [2:37:27<18:12:47,  3.07it/s]
 46%|████▌     | 170376/371472 [2:37:28<17:45:39,  3.15it/s]
 46%|████▌     | 170377/371472 [2:37:28<16:55:11,  3.30it/s]
 46%|████▌     | 170378/371472 [2:37:28<16:38:58,  3.36it/s]
 46%|████▌     | 170379/371472 [2:37:28<16:26:56,  3.40it/s]
 46%|████▌     | 170380/371472 [2:37:29<16:33:16,  3.37it/s]
                                                            
{'loss': 3.1305, 'learning_rate': 5.874668706500894e-07, 'epoch': 7.34}
+
 46%|████▌     | 170380/371472 [2:37:29<16:33:16,  3.37it/s]
 46%|████▌     | 170381/371472 [2:37:29<16:32:28,  3.38it/s]
 46%|████▌     | 170382/371472 [2:37:29<16:06:46,  3.47it/s]
 46%|████▌     | 170383/371472 [2:37:30<15:55:44,  3.51it/s]
 46%|████▌     | 170384/371472 [2:37:30<16:02:13,  3.48it/s]
 46%|████▌     | 170385/371472 [2:37:30<15:56:47,  3.50it/s]
 46%|████▌     | 170386/371472 [2:37:30<16:01:15,  3.49it/s]
 46%|████▌     | 170387/371472 [2:37:31<16:01:02,  3.49it/s]
 46%|████▌     | 170388/371472 [2:37:31<15:57:48,  3.50it/s]
 46%|████▌     | 170389/371472 [2:37:31<16:23:06,  3.41it/s]
 46%|████▌     | 170390/371472 [2:37:32<16:19:52,  3.42it/s]
 46%|████▌     | 170391/371472 [2:37:32<19:43:12,  2.83it/s]
 46%|████▌     | 170392/371472 [2:37:32<18:35:27,  3.00it/s]
 46%|████▌     | 170393/371472 [2:37:33<18:56:11,  2.95it/s]
 46%|████▌     | 170394/371472 [2:37:33<18:14:33,  3.06it/s]
 46%|████▌     | 170395/371472 [2:37:33<17:34:57,  3.18it/s]
 46%|████▌     | 170396/371472 [2:37:34<16:45:07,  3.33it/s]
 46%|████▌     | 170397/371472 [2:37:34<16:42:22,  3.34it/s]
 46%|████▌     | 170398/371472 [2:37:34<17:29:06,  3.19it/s]
 46%|████▌     | 170399/371472 [2:37:34<17:21:10,  3.22it/s]
 46%|████▌     | 170400/371472 [2:37:35<17:00:19,  3.28it/s]
                                                            
{'loss': 2.8604, 'learning_rate': 5.874183886746105e-07, 'epoch': 7.34}
+
 46%|████▌     | 170400/371472 [2:37:35<17:00:19,  3.28it/s]
 46%|████▌     | 170401/371472 [2:37:35<17:11:52,  3.25it/s]
 46%|████▌     | 170402/371472 [2:37:35<17:30:16,  3.19it/s]
 46%|████▌     | 170403/371472 [2:37:36<17:59:43,  3.10it/s]
 46%|████▌     | 170404/371472 [2:37:36<17:36:58,  3.17it/s]
 46%|████▌     | 170405/371472 [2:37:36<17:39:38,  3.16it/s]
 46%|████▌     | 170406/371472 [2:37:37<17:02:02,  3.28it/s]
 46%|████▌     | 170407/371472 [2:37:37<16:55:05,  3.30it/s]
 46%|████▌     | 170408/371472 [2:37:37<17:05:18,  3.27it/s]
 46%|████▌     | 170409/371472 [2:37:38<17:25:39,  3.20it/s]
 46%|████▌     | 170410/371472 [2:37:38<17:55:58,  3.11it/s]
 46%|████▌     | 170411/371472 [2:37:38<17:41:23,  3.16it/s]
 46%|████▌     | 170412/371472 [2:37:39<18:14:38,  3.06it/s]
 46%|████▌     | 170413/371472 [2:37:39<18:11:58,  3.07it/s]
 46%|████▌     | 170414/371472 [2:37:39<17:32:38,  3.18it/s]
 46%|████▌     | 170415/371472 [2:37:40<17:50:50,  3.13it/s]
 46%|████▌     | 170416/371472 [2:37:40<17:39:39,  3.16it/s]
 46%|████▌     | 170417/371472 [2:37:40<17:46:44,  3.14it/s]
 46%|████▌     | 170418/371472 [2:37:40<17:21:01,  3.22it/s]
 46%|████▌     | 170419/371472 [2:37:41<17:43:03,  3.15it/s]
 46%|████▌     | 170420/371472 [2:37:41<17:28:48,  3.19it/s]
                                                            
{'loss': 2.8556, 'learning_rate': 5.873699066991315e-07, 'epoch': 7.34}
+
 46%|████▌     | 170420/371472 [2:37:41<17:28:48,  3.19it/s]
 46%|████▌     | 170421/371472 [2:37:41<16:54:50,  3.30it/s]
 46%|████▌     | 170422/371472 [2:37:42<16:37:09,  3.36it/s]
 46%|████▌     | 170423/371472 [2:37:42<16:29:55,  3.38it/s]
 46%|████▌     | 170424/371472 [2:37:42<18:23:52,  3.04it/s]
 46%|████▌     | 170425/371472 [2:37:43<17:39:21,  3.16it/s]
 46%|████▌     | 170426/371472 [2:37:43<17:20:17,  3.22it/s]
 46%|████▌     | 170427/371472 [2:37:43<16:29:09,  3.39it/s]
 46%|████▌     | 170428/371472 [2:37:44<16:27:59,  3.39it/s]
 46%|████▌     | 170429/371472 [2:37:44<16:55:10,  3.30it/s]
 46%|████▌     | 170430/371472 [2:37:44<16:42:39,  3.34it/s]
 46%|████▌     | 170431/371472 [2:37:45<18:21:26,  3.04it/s]
 46%|████▌     | 170432/371472 [2:37:45<18:21:07,  3.04it/s]
 46%|████▌     | 170433/371472 [2:37:45<17:18:27,  3.23it/s]
 46%|████▌     | 170434/371472 [2:37:45<17:50:01,  3.13it/s]
 46%|████▌     | 170435/371472 [2:37:46<17:34:27,  3.18it/s]
 46%|████▌     | 170436/371472 [2:37:46<17:00:12,  3.28it/s]
 46%|████▌     | 170437/371472 [2:37:46<16:56:56,  3.29it/s]
 46%|████▌     | 170438/371472 [2:37:47<16:30:57,  3.38it/s]
 46%|████▌     | 170439/371472 [2:37:47<17:36:08,  3.17it/s]
 46%|████▌     | 170440/371472 [2:37:47<18:11:01,  3.07it/s]
                                                            
{'loss': 2.7255, 'learning_rate': 5.873214247236527e-07, 'epoch': 7.34}
+
 46%|████▌     | 170440/371472 [2:37:47<18:11:01,  3.07it/s]
 46%|████▌     | 170441/371472 [2:37:48<18:00:34,  3.10it/s]
 46%|████▌     | 170442/371472 [2:37:48<17:17:53,  3.23it/s]
 46%|████▌     | 170443/371472 [2:37:48<16:54:18,  3.30it/s]
 46%|████▌     | 170444/371472 [2:37:48<16:22:12,  3.41it/s]
 46%|████▌     | 170445/371472 [2:37:49<16:08:31,  3.46it/s]
 46%|████▌     | 170446/371472 [2:37:49<17:08:31,  3.26it/s]
 46%|████▌     | 170447/371472 [2:37:49<16:55:09,  3.30it/s]
 46%|████▌     | 170448/371472 [2:37:50<17:15:07,  3.24it/s]
 46%|████▌     | 170449/371472 [2:37:50<17:36:56,  3.17it/s]
 46%|████▌     | 170450/371472 [2:37:50<16:48:46,  3.32it/s]
 46%|████▌     | 170451/371472 [2:37:51<17:22:44,  3.21it/s]
 46%|████▌     | 170452/371472 [2:37:51<17:14:35,  3.24it/s]
 46%|████▌     | 170453/371472 [2:37:51<17:11:17,  3.25it/s]
 46%|████▌     | 170454/371472 [2:37:52<17:31:25,  3.19it/s]
 46%|████▌     | 170455/371472 [2:37:52<17:32:42,  3.18it/s]
 46%|████▌     | 170456/371472 [2:37:52<17:43:16,  3.15it/s]
 46%|████▌     | 170457/371472 [2:37:53<17:16:24,  3.23it/s]
 46%|████▌     | 170458/371472 [2:37:53<18:17:02,  3.05it/s]
 46%|████▌     | 170459/371472 [2:37:53<18:31:55,  3.01it/s]
 46%|████▌     | 170460/371472 [2:37:54<17:33:57,  3.18it/s]
                                                            
{'loss': 3.0197, 'learning_rate': 5.872729427481739e-07, 'epoch': 7.34}
+
 46%|████▌     | 170460/371472 [2:37:54<17:33:57,  3.18it/s]
 46%|████▌     | 170461/371472 [2:37:54<16:50:37,  3.31it/s]
 46%|████▌     | 170462/371472 [2:37:54<16:18:28,  3.42it/s]
 46%|████▌     | 170463/371472 [2:37:54<16:21:21,  3.41it/s]
 46%|████▌     | 170464/371472 [2:37:55<16:19:21,  3.42it/s]
 46%|████▌     | 170465/371472 [2:37:55<16:22:37,  3.41it/s]
 46%|████▌     | 170466/371472 [2:37:55<16:10:06,  3.45it/s]
 46%|████▌     | 170467/371472 [2:37:55<15:56:28,  3.50it/s]
 46%|████▌     | 170468/371472 [2:37:56<16:39:44,  3.35it/s]
 46%|████▌     | 170469/371472 [2:37:56<16:22:42,  3.41it/s]
 46%|████▌     | 170470/371472 [2:37:56<16:20:47,  3.42it/s]
 46%|████▌     | 170471/371472 [2:37:57<17:11:51,  3.25it/s]
 46%|████▌     | 170472/371472 [2:37:57<16:34:51,  3.37it/s]
 46%|████▌     | 170473/371472 [2:37:57<17:20:56,  3.22it/s]
 46%|████▌     | 170474/371472 [2:37:58<17:23:01,  3.21it/s]
 46%|████▌     | 170475/371472 [2:37:58<16:57:04,  3.29it/s]
 46%|████▌     | 170476/371472 [2:37:58<16:36:17,  3.36it/s]
 46%|████▌     | 170477/371472 [2:37:59<18:30:11,  3.02it/s]
 46%|████▌     | 170478/371472 [2:37:59<17:34:44,  3.18it/s]
 46%|████▌     | 170479/371472 [2:37:59<17:19:46,  3.22it/s]
 46%|████▌     | 170480/371472 [2:38:00<16:56:20,  3.30it/s]
                                                            
{'loss': 2.7561, 'learning_rate': 5.87224460772695e-07, 'epoch': 7.34}
+
 46%|████▌     | 170480/371472 [2:38:00<16:56:20,  3.30it/s]
 46%|████▌     | 170481/371472 [2:38:00<16:32:08,  3.38it/s]
 46%|████▌     | 170482/371472 [2:38:00<16:55:57,  3.30it/s]
 46%|████▌     | 170483/371472 [2:38:00<17:27:45,  3.20it/s]
 46%|████▌     | 170484/371472 [2:38:01<17:36:20,  3.17it/s]
 46%|████▌     | 170485/371472 [2:38:01<18:34:52,  3.00it/s]
 46%|████▌     | 170486/371472 [2:38:01<17:35:14,  3.17it/s]
 46%|████▌     | 170487/371472 [2:38:02<18:10:26,  3.07it/s]
 46%|████▌     | 170488/371472 [2:38:02<17:25:30,  3.20it/s]
 46%|████▌     | 170489/371472 [2:38:02<17:39:53,  3.16it/s]
 46%|████▌     | 170490/371472 [2:38:03<16:53:39,  3.30it/s]
 46%|████▌     | 170491/371472 [2:38:03<16:48:10,  3.32it/s]
 46%|████▌     | 170492/371472 [2:38:03<16:16:36,  3.43it/s]
 46%|████▌     | 170493/371472 [2:38:03<15:50:34,  3.52it/s]
 46%|████▌     | 170494/371472 [2:38:04<15:46:33,  3.54it/s]
 46%|████▌     | 170495/371472 [2:38:04<16:49:06,  3.32it/s]
 46%|████▌     | 170496/371472 [2:38:04<16:25:00,  3.40it/s]
 46%|████▌     | 170497/371472 [2:38:05<16:12:05,  3.45it/s]
 46%|████▌     | 170498/371472 [2:38:05<16:15:42,  3.43it/s]
 46%|████▌     | 170499/371472 [2:38:05<16:29:24,  3.39it/s]
 46%|████▌     | 170500/371472 [2:38:06<16:40:37,  3.35it/s]
                                                            
{'loss': 2.8936, 'learning_rate': 5.871759787972159e-07, 'epoch': 7.34}
+
 46%|████▌     | 170500/371472 [2:38:06<16:40:37,  3.35it/s]
 46%|████▌     | 170501/371472 [2:38:06<16:13:43,  3.44it/s]
 46%|████▌     | 170502/371472 [2:38:06<16:04:51,  3.47it/s]
 46%|████▌     | 170503/371472 [2:38:06<16:17:12,  3.43it/s]
 46%|████▌     | 170504/371472 [2:38:07<15:55:12,  3.51it/s]
 46%|████▌     | 170505/371472 [2:38:07<15:43:39,  3.55it/s]
 46%|████▌     | 170506/371472 [2:38:07<15:54:09,  3.51it/s]
 46%|████▌     | 170507/371472 [2:38:08<16:56:28,  3.30it/s]
 46%|████▌     | 170508/371472 [2:38:08<18:19:19,  3.05it/s]
 46%|████▌     | 170509/371472 [2:38:08<17:24:18,  3.21it/s]
 46%|████▌     | 170510/371472 [2:38:09<17:25:48,  3.20it/s]
 46%|████▌     | 170511/371472 [2:38:09<18:01:49,  3.10it/s]
 46%|████▌     | 170512/371472 [2:38:09<17:56:08,  3.11it/s]
 46%|████▌     | 170513/371472 [2:38:10<17:39:59,  3.16it/s]
 46%|████▌     | 170514/371472 [2:38:10<17:23:52,  3.21it/s]
 46%|████▌     | 170515/371472 [2:38:10<17:26:07,  3.20it/s]
 46%|████▌     | 170516/371472 [2:38:10<17:06:48,  3.26it/s]
 46%|████▌     | 170517/371472 [2:38:11<17:07:12,  3.26it/s]
 46%|████▌     | 170518/371472 [2:38:11<17:02:33,  3.28it/s]
 46%|████▌     | 170519/371472 [2:38:11<16:37:16,  3.36it/s]
 46%|████▌     | 170520/371472 [2:38:12<17:04:33,  3.27it/s]
                                                            
{'loss': 2.9464, 'learning_rate': 5.871274968217371e-07, 'epoch': 7.34}
+
 46%|████▌     | 170520/371472 [2:38:12<17:04:33,  3.27it/s]
 46%|████▌     | 170521/371472 [2:38:12<17:40:19,  3.16it/s]
 46%|████▌     | 170522/371472 [2:38:12<17:33:01,  3.18it/s]
 46%|████▌     | 170523/371472 [2:38:13<17:19:11,  3.22it/s]
 46%|████▌     | 170524/371472 [2:38:13<16:51:28,  3.31it/s]
 46%|████▌     | 170525/371472 [2:38:13<17:55:14,  3.11it/s]
 46%|████▌     | 170526/371472 [2:38:14<17:37:45,  3.17it/s]
 46%|████▌     | 170527/371472 [2:38:14<18:07:07,  3.08it/s]
 46%|████▌     | 170528/371472 [2:38:14<17:04:59,  3.27it/s]
 46%|████▌     | 170529/371472 [2:38:14<16:43:29,  3.34it/s]
 46%|████▌     | 170530/371472 [2:38:15<16:21:41,  3.41it/s]
 46%|████▌     | 170531/371472 [2:38:15<16:09:16,  3.46it/s]
 46%|█��██▌     | 170532/371472 [2:38:15<16:20:51,  3.41it/s]
 46%|████▌     | 170533/371472 [2:38:16<16:29:58,  3.38it/s]
 46%|████▌     | 170534/371472 [2:38:16<16:14:43,  3.44it/s]
 46%|████▌     | 170535/371472 [2:38:16<15:42:34,  3.55it/s]
 46%|████▌     | 170536/371472 [2:38:16<15:32:13,  3.59it/s]
 46%|████▌     | 170537/371472 [2:38:17<15:43:35,  3.55it/s]
 46%|████▌     | 170538/371472 [2:38:17<16:37:31,  3.36it/s]
 46%|████▌     | 170539/371472 [2:38:17<16:30:53,  3.38it/s]
 46%|████▌     | 170540/371472 [2:38:18<16:29:07,  3.39it/s]
                                                            
{'loss': 2.8811, 'learning_rate': 5.870790148462583e-07, 'epoch': 7.35}
+
 46%|████▌     | 170540/371472 [2:38:18<16:29:07,  3.39it/s]
 46%|████▌     | 170541/371472 [2:38:18<16:40:14,  3.35it/s]
 46%|████▌     | 170542/371472 [2:38:18<16:49:41,  3.32it/s]
 46%|████▌     | 170543/371472 [2:38:19<16:21:24,  3.41it/s]
 46%|████▌     | 170544/371472 [2:38:19<15:54:27,  3.51it/s]
 46%|████▌     | 170545/371472 [2:38:19<15:53:07,  3.51it/s]
 46%|████▌     | 170546/371472 [2:38:19<16:18:49,  3.42it/s]
 46%|████▌     | 170547/371472 [2:38:20<16:29:43,  3.38it/s]
 46%|████▌     | 170548/371472 [2:38:20<17:03:56,  3.27it/s]
 46%|████▌     | 170549/371472 [2:38:20<16:43:04,  3.34it/s]
 46%|████▌     | 170550/371472 [2:38:21<16:31:55,  3.38it/s]
 46%|████▌     | 170551/371472 [2:38:21<16:35:32,  3.36it/s]
 46%|████▌     | 170552/371472 [2:38:21<16:32:24,  3.37it/s]
 46%|████▌     | 170553/371472 [2:38:21<16:23:21,  3.41it/s]
 46%|████▌     | 170554/371472 [2:38:22<16:28:11,  3.39it/s]
 46%|████▌     | 170555/371472 [2:38:22<18:35:13,  3.00it/s]
 46%|████▌     | 170556/371472 [2:38:23<18:40:53,  2.99it/s]
 46%|████▌     | 170557/371472 [2:38:23<18:11:57,  3.07it/s]
 46%|████▌     | 170558/371472 [2:38:23<17:38:44,  3.16it/s]
 46%|████▌     | 170559/371472 [2:38:23<17:13:57,  3.24it/s]
 46%|████▌     | 170560/371472 [2:38:24<16:42:13,  3.34it/s]
                                                            
{'loss': 2.9148, 'learning_rate': 5.870305328707794e-07, 'epoch': 7.35}
+
 46%|████▌     | 170560/371472 [2:38:24<16:42:13,  3.34it/s]
 46%|████▌     | 170561/371472 [2:38:24<16:30:11,  3.38it/s]
 46%|████▌     | 170562/371472 [2:38:24<16:22:46,  3.41it/s]
 46%|████▌     | 170563/371472 [2:38:25<17:45:34,  3.14it/s]
 46%|████▌     | 170564/371472 [2:38:25<17:03:16,  3.27it/s]
 46%|████▌     | 170565/371472 [2:38:25<16:49:00,  3.32it/s]
 46%|████▌     | 170566/371472 [2:38:26<17:12:47,  3.24it/s]
 46%|████▌     | 170567/371472 [2:38:26<17:04:36,  3.27it/s]
 46%|████▌     | 170568/371472 [2:38:26<17:11:52,  3.24it/s]
 46%|████▌     | 170569/371472 [2:38:26<16:52:40,  3.31it/s]
 46%|████▌     | 170570/371472 [2:38:27<16:42:32,  3.34it/s]
 46%|████▌     | 170571/371472 [2:38:27<16:52:32,  3.31it/s]
 46%|████▌     | 170572/371472 [2:38:27<16:47:49,  3.32it/s]
 46%|████▌     | 170573/371472 [2:38:28<17:45:15,  3.14it/s]
 46%|████▌     | 170574/371472 [2:38:28<19:12:18,  2.91it/s]
 46%|████▌     | 170575/371472 [2:38:28<19:26:06,  2.87it/s]
 46%|████▌     | 170576/371472 [2:38:29<18:47:54,  2.97it/s]
 46%|████▌     | 170577/371472 [2:38:29<17:45:16,  3.14it/s]
 46%|████▌     | 170578/371472 [2:38:29<17:29:21,  3.19it/s]
 46%|████▌     | 170579/371472 [2:38:30<17:08:32,  3.26it/s]
 46%|████▌     | 170580/371472 [2:38:30<16:42:33,  3.34it/s]
                                                            
{'loss': 3.0389, 'learning_rate': 5.869820508953004e-07, 'epoch': 7.35}
+
 46%|████▌     | 170580/371472 [2:38:30<16:42:33,  3.34it/s]
 46%|████▌     | 170581/371472 [2:38:30<16:52:15,  3.31it/s]
 46%|████▌     | 170582/371472 [2:38:31<16:31:30,  3.38it/s]
 46%|████▌     | 170583/371472 [2:38:31<16:29:56,  3.38it/s]
 46%|████▌     | 170584/371472 [2:38:31<16:24:36,  3.40it/s]
 46%|████▌     | 170585/371472 [2:38:31<17:38:40,  3.16it/s]
 46%|████▌     | 170586/371472 [2:38:32<17:22:17,  3.21it/s]
 46%|████▌     | 170587/371472 [2:38:32<16:45:21,  3.33it/s]
 46%|████▌     | 170588/371472 [2:38:32<16:12:49,  3.44it/s]
 46%|████▌     | 170589/371472 [2:38:33<16:20:39,  3.41it/s]
 46%|████▌     | 170590/371472 [2:38:33<16:08:18,  3.46it/s]
 46%|████▌     | 170591/371472 [2:38:33<16:20:24,  3.41it/s]
 46%|████▌     | 170592/371472 [2:38:33<16:26:40,  3.39it/s]
 46%|████▌     | 170593/371472 [2:38:34<16:24:54,  3.40it/s]
 46%|████▌     | 170594/371472 [2:38:34<16:26:35,  3.39it/s]
 46%|████▌     | 170595/371472 [2:38:34<16:20:08,  3.42it/s]
 46%|████▌     | 170596/371472 [2:38:35<16:48:27,  3.32it/s]
 46%|████▌     | 170597/371472 [2:38:35<16:38:37,  3.35it/s]
 46%|████▌     | 170598/371472 [2:38:35<17:48:39,  3.13it/s]
 46%|████▌     | 170599/371472 [2:38:36<17:19:08,  3.22it/s]
 46%|████▌     | 170600/371472 [2:38:36<17:10:25,  3.25it/s]
                                                            
{'loss': 2.991, 'learning_rate': 5.869335689198216e-07, 'epoch': 7.35}
+
 46%|████▌     | 170600/371472 [2:38:36<17:10:25,  3.25it/s]
 46%|████▌     | 170601/371472 [2:38:36<16:59:27,  3.28it/s]
 46%|████▌     | 170602/371472 [2:38:37<16:35:08,  3.36it/s]
 46%|████▌     | 170603/371472 [2:38:37<16:43:39,  3.34it/s]
 46%|████▌     | 170604/371472 [2:38:37<16:44:38,  3.33it/s]
 46%|████▌     | 170605/371472 [2:38:37<17:13:02,  3.24it/s]
 46%|████▌     | 170606/371472 [2:38:38<16:36:20,  3.36it/s]
 46%|████▌     | 170607/371472 [2:38:38<15:53:11,  3.51it/s]
 46%|████▌     | 170608/371472 [2:38:38<15:46:46,  3.54it/s]
 46%|████▌     | 170609/371472 [2:38:39<16:25:52,  3.40it/s]
 46%|████▌     | 170610/371472 [2:38:39<16:15:50,  3.43it/s]
 46%|████▌     | 170611/371472 [2:38:39<16:40:12,  3.35it/s]
 46%|████▌     | 170612/371472 [2:38:40<17:29:18,  3.19it/s]
 46%|████▌     | 170613/371472 [2:38:40<17:10:51,  3.25it/s]
 46%|████▌     | 170614/371472 [2:38:40<16:35:00,  3.36it/s]
 46%|████▌     | 170615/371472 [2:38:40<17:00:27,  3.28it/s]
 46%|████▌     | 170616/371472 [2:38:41<16:41:08,  3.34it/s]
 46%|████▌     | 170617/371472 [2:38:41<16:47:45,  3.32it/s]
 46%|████▌     | 170618/371472 [2:38:41<16:55:02,  3.30it/s]
 46%|████▌     | 170619/371472 [2:38:42<16:54:00,  3.30it/s]
 46%|████▌     | 170620/371472 [2:38:42<16:55:47,  3.30it/s]
                                                            
{'loss': 3.1231, 'learning_rate': 5.868850869443427e-07, 'epoch': 7.35}
+
 46%|████▌     | 170620/371472 [2:38:42<16:55:47,  3.30it/s]
 46%|████▌     | 170621/371472 [2:38:42<18:02:46,  3.09it/s]
 46%|████▌     | 170622/371472 [2:38:43<17:18:19,  3.22it/s]
 46%|████▌     | 170623/371472 [2:38:43<17:16:18,  3.23it/s]
 46%|████▌     | 170624/371472 [2:38:43<17:01:04,  3.28it/s]
 46%|████▌     | 170625/371472 [2:38:43<17:19:35,  3.22it/s]
 46%|████▌     | 170626/371472 [2:38:44<16:48:25,  3.32it/s]
 46%|████▌     | 170627/371472 [2:38:44<16:45:20,  3.33it/s]
 46%|████▌     | 170628/371472 [2:38:44<16:55:23,  3.30it/s]
 46%|████▌     | 170629/371472 [2:38:45<16:52:30,  3.31it/s]
 46%|████▌     | 170630/371472 [2:38:45<16:39:48,  3.35it/s]
 46%|████▌     | 170631/371472 [2:38:45<16:46:42,  3.33it/s]
 46%|████▌     | 170632/371472 [2:38:46<16:20:04,  3.42it/s]
 46%|████▌     | 170633/371472 [2:38:46<16:18:58,  3.42it/s]
 46%|████▌     | 170634/371472 [2:38:46<16:05:16,  3.47it/s]
 46%|████▌     | 170635/371472 [2:38:46<16:01:31,  3.48it/s]
 46%|████▌     | 170636/371472 [2:38:47<16:12:02,  3.44it/s]
 46%|████▌     | 170637/371472 [2:38:47<16:08:37,  3.46it/s]
 46%|████▌     | 170638/371472 [2:38:47<16:38:30,  3.35it/s]
 46%|████▌     | 170639/371472 [2:38:48<16:35:50,  3.36it/s]
 46%|████▌     | 170640/371472 [2:38:48<16:20:07,  3.42it/s]
                                                            
{'loss': 2.7957, 'learning_rate': 5.868366049688638e-07, 'epoch': 7.35}
+
 46%|████▌     | 170640/371472 [2:38:48<16:20:07,  3.42it/s]
 46%|████▌     | 170641/371472 [2:38:48<16:42:48,  3.34it/s]
 46%|████▌     | 170642/371472 [2:38:48<16:23:51,  3.40it/s]
 46%|████▌     | 170643/371472 [2:38:49<16:46:12,  3.33it/s]
 46%|████▌     | 170644/371472 [2:38:49<16:30:13,  3.38it/s]
 46%|████▌     | 170645/371472 [2:38:49<17:38:38,  3.16it/s]
 46%|████▌     | 170646/371472 [2:38:50<16:59:03,  3.28it/s]
 46%|████▌     | 170647/371472 [2:38:50<17:35:02,  3.17it/s]
 46%|████▌     | 170648/371472 [2:38:50<17:13:10,  3.24it/s]
 46%|████▌     | 170649/371472 [2:38:51<17:08:01,  3.26it/s]
 46%|████▌     | 170650/371472 [2:38:51<17:55:59,  3.11it/s]
 46%|████▌     | 170651/371472 [2:38:51<17:18:32,  3.22it/s]
 46%|████▌     | 170652/371472 [2:38:52<16:57:14,  3.29it/s]
 46%|████▌     | 170653/371472 [2:38:52<17:08:32,  3.25it/s]
 46%|████▌     | 170654/371472 [2:38:52<16:40:48,  3.34it/s]
 46%|████▌     | 170655/371472 [2:38:52<16:20:21,  3.41it/s]
 46%|████▌     | 170656/371472 [2:38:53<15:50:59,  3.52it/s]
 46%|████▌     | 170657/371472 [2:38:53<15:41:04,  3.56it/s]
 46%|████▌     | 170658/371472 [2:38:53<15:43:33,  3.55it/s]
 46%|████▌     | 170659/371472 [2:38:54<16:20:24,  3.41it/s]
 46%|████▌     | 170660/371472 [2:38:54<16:48:56,  3.32it/s]
                                                            
{'loss': 3.1204, 'learning_rate': 5.867881229933848e-07, 'epoch': 7.35}
+
 46%|████▌     | 170660/371472 [2:38:54<16:48:56,  3.32it/s]
 46%|████▌     | 170661/371472 [2:38:54<16:31:06,  3.38it/s]
 46%|████▌     | 170662/371472 [2:38:54<16:18:48,  3.42it/s]
 46%|████▌     | 170663/371472 [2:38:55<16:12:28,  3.44it/s]
 46%|████▌     | 170664/371472 [2:38:55<16:01:01,  3.48it/s]
 46%|████▌     | 170665/371472 [2:38:55<15:59:10,  3.49it/s]
 46%|████▌     | 170666/371472 [2:38:56<16:26:27,  3.39it/s]
 46%|████▌     | 170667/371472 [2:38:56<16:27:47,  3.39it/s]
 46%|████▌     | 170668/371472 [2:38:56<16:20:33,  3.41it/s]
 46%|████▌     | 170669/371472 [2:38:57<16:25:23,  3.40it/s]
 46%|████▌     | 170670/371472 [2:38:57<16:16:59,  3.43it/s]
 46%|████▌     | 170671/371472 [2:38:57<17:47:10,  3.14it/s]
 46%|████▌     | 170672/371472 [2:38:58<17:50:21,  3.13it/s]
 46%|████▌     | 170673/371472 [2:38:58<18:10:33,  3.07it/s]
 46%|████▌     | 170674/371472 [2:38:58<18:06:09,  3.08it/s]
 46%|████▌     | 170675/371472 [2:38:58<17:39:17,  3.16it/s]
 46%|████▌     | 170676/371472 [2:38:59<18:01:39,  3.09it/s]
 46%|████▌     | 170677/371472 [2:38:59<18:27:34,  3.02it/s]
 46%|████▌     | 170678/371472 [2:38:59<17:34:46,  3.17it/s]
 46%|████▌     | 170679/371472 [2:39:00<19:25:08,  2.87it/s]
 46%|████▌     | 170680/371472 [2:39:00<18:20:40,  3.04it/s]
                                                            
{'loss': 2.8421, 'learning_rate': 5.86739641017906e-07, 'epoch': 7.35}
+
 46%|████▌     | 170680/371472 [2:39:00<18:20:40,  3.04it/s]
 46%|████▌     | 170681/371472 [2:39:00<17:45:25,  3.14it/s]
 46%|████▌     | 170682/371472 [2:39:01<17:07:03,  3.26it/s]
 46%|████▌     | 170683/371472 [2:39:01<16:39:29,  3.35it/s]
 46%|████▌     | 170684/371472 [2:39:01<16:28:56,  3.38it/s]
 46%|████▌     | 170685/371472 [2:39:02<16:33:51,  3.37it/s]
 46%|████▌     | 170686/371472 [2:39:02<16:25:55,  3.39it/s]
 46%|████▌     | 170687/371472 [2:39:02<16:41:15,  3.34it/s]
 46%|████▌     | 170688/371472 [2:39:02<16:24:28,  3.40it/s]
 46%|████▌     | 170689/371472 [2:39:03<15:58:34,  3.49it/s]
 46%|████▌     | 170690/371472 [2:39:03<15:59:55,  3.49it/s]
 46%|████▌     | 170691/371472 [2:39:03<16:24:15,  3.40it/s]
 46%|████▌     | 170692/371472 [2:39:04<16:11:31,  3.44it/s]
 46%|████▌     | 170693/371472 [2:39:04<16:36:53,  3.36it/s]
 46%|████▌     | 170694/371472 [2:39:04<16:42:10,  3.34it/s]
 46%|████▌     | 170695/371472 [2:39:05<16:21:09,  3.41it/s]
 46%|████▌     | 170696/371472 [2:39:05<16:22:47,  3.40it/s]
 46%|████▌     | 170697/371472 [2:39:05<15:59:20,  3.49it/s]
 46%|████▌     | 170698/371472 [2:39:05<16:16:54,  3.43it/s]
 46%|████▌     | 170699/371472 [2:39:06<16:21:08,  3.41it/s]
 46%|████▌     | 170700/371472 [2:39:06<16:09:10,  3.45it/s]
                                                            
{'loss': 2.7792, 'learning_rate': 5.866911590424271e-07, 'epoch': 7.35}
+
 46%|████▌     | 170700/371472 [2:39:06<16:09:10,  3.45it/s]
 46%|████▌     | 170701/371472 [2:39:06<16:11:03,  3.45it/s]
 46%|████▌     | 170702/371472 [2:39:07<16:14:56,  3.43it/s]
 46%|████▌     | 170703/371472 [2:39:07<18:07:40,  3.08it/s]
 46%|████▌     | 170704/371472 [2:39:07<17:41:24,  3.15it/s]
 46%|████▌     | 170705/371472 [2:39:08<18:12:38,  3.06it/s]
 46%|████▌     | 170706/371472 [2:39:08<17:37:48,  3.16it/s]
 46%|████▌     | 170707/371472 [2:39:08<17:09:30,  3.25it/s]
 46%|████▌     | 170708/371472 [2:39:08<16:41:18,  3.34it/s]
 46%|████▌     | 170709/371472 [2:39:09<16:29:26,  3.38it/s]
 46%|████▌     | 170710/371472 [2:39:09<16:03:39,  3.47it/s]
 46%|████▌     | 170711/371472 [2:39:09<17:16:24,  3.23it/s]
 46%|████▌     | 170712/371472 [2:39:10<17:05:53,  3.26it/s]
 46%|████▌     | 170713/371472 [2:39:10<17:09:22,  3.25it/s]
 46%|████▌     | 170714/371472 [2:39:10<17:49:20,  3.13it/s]
 46%|████▌     | 170715/371472 [2:39:11<17:23:40,  3.21it/s]
 46%|████▌     | 170716/371472 [2:39:11<16:57:27,  3.29it/s]
 46%|████▌     | 170717/371472 [2:39:11<16:29:18,  3.38it/s]
 46%|████▌     | 170718/371472 [2:39:11<16:10:45,  3.45it/s]
 46%|████▌     | 170719/371472 [2:39:12<16:54:54,  3.30it/s]
 46%|████▌     | 170720/371472 [2:39:12<18:38:09,  2.99it/s]
                                                            
{'loss': 3.1122, 'learning_rate': 5.866426770669481e-07, 'epoch': 7.35}
+
 46%|████▌     | 170720/371472 [2:39:12<18:38:09,  2.99it/s]
 46%|████▌     | 170721/371472 [2:39:13<17:58:47,  3.10it/s]
 46%|████▌     | 170722/371472 [2:39:13<19:00:46,  2.93it/s]
 46%|████▌     | 170723/371472 [2:39:13<18:15:10,  3.06it/s]
 46%|████▌     | 170724/371472 [2:39:14<17:56:42,  3.11it/s]
 46%|████▌     | 170725/371472 [2:39:14<17:39:22,  3.16it/s]
 46%|████▌     | 170726/371472 [2:39:14<16:58:45,  3.28it/s]
 46%|████▌     | 170727/371472 [2:39:14<16:22:14,  3.41it/s]
 46%|████▌     | 170728/371472 [2:39:15<16:14:47,  3.43it/s]
 46%|████▌     | 170729/371472 [2:39:15<16:12:37,  3.44it/s]
 46%|████▌     | 170730/371472 [2:39:15<16:08:08,  3.46it/s]
 46%|████▌     | 170731/371472 [2:39:16<15:56:29,  3.50it/s]
 46%|████▌     | 170732/371472 [2:39:16<16:10:53,  3.45it/s]
 46%|████▌     | 170733/371472 [2:39:16<16:27:27,  3.39it/s]
 46%|████▌     | 170734/371472 [2:39:16<16:23:49,  3.40it/s]
 46%|████▌     | 170735/371472 [2:39:17<16:13:04,  3.44it/s]
 46%|████▌     | 170736/371472 [2:39:17<16:24:54,  3.40it/s]
 46%|████▌     | 170737/371472 [2:39:17<16:18:53,  3.42it/s]
 46%|████▌     | 170738/371472 [2:39:18<16:34:05,  3.37it/s]
 46%|████▌     | 170739/371472 [2:39:18<16:45:09,  3.33it/s]
 46%|████▌     | 170740/371472 [2:39:18<16:43:01,  3.34it/s]
                                                            
{'loss': 2.8722, 'learning_rate': 5.865941950914693e-07, 'epoch': 7.35}
+
 46%|████▌     | 170740/371472 [2:39:18<16:43:01,  3.34it/s]
 46%|████▌     | 170741/371472 [2:39:18<16:26:42,  3.39it/s]
 46%|████▌     | 170742/371472 [2:39:19<16:34:36,  3.36it/s]
 46%|████▌     | 170743/371472 [2:39:19<16:30:42,  3.38it/s]
 46%|████▌     | 170744/371472 [2:39:19<16:38:07,  3.35it/s]
 46%|████▌     | 170745/371472 [2:39:20<16:28:33,  3.38it/s]
 46%|████▌     | 170746/371472 [2:39:20<17:00:55,  3.28it/s]
 46%|████▌     | 170747/371472 [2:39:20<17:08:12,  3.25it/s]
 46%|████▌     | 170748/371472 [2:39:21<16:48:39,  3.32it/s]
 46%|████▌     | 170749/371472 [2:39:21<16:44:37,  3.33it/s]
 46%|████▌     | 170750/371472 [2:39:21<18:18:00,  3.05it/s]
 46%|████▌     | 170751/371472 [2:39:22<17:23:31,  3.21it/s]
 46%|████▌     | 170752/371472 [2:39:22<17:59:53,  3.10it/s]
 46%|████▌     | 170753/371472 [2:39:22<17:49:27,  3.13it/s]
 46%|████▌     | 170754/371472 [2:39:23<18:12:33,  3.06it/s]
 46%|████▌     | 170755/371472 [2:39:23<18:22:28,  3.03it/s]
 46%|████▌     | 170756/371472 [2:39:23<17:37:33,  3.16it/s]
 46%|████▌     | 170757/371472 [2:39:23<17:09:10,  3.25it/s]
 46%|████▌     | 170758/371472 [2:39:24<16:39:59,  3.35it/s]
 46%|████▌     | 170759/371472 [2:39:24<16:36:45,  3.36it/s]
 46%|████▌     | 170760/371472 [2:39:24<16:07:14,  3.46it/s]
                                                            
{'loss': 2.8448, 'learning_rate': 5.865457131159904e-07, 'epoch': 7.35}
+
 46%|████▌     | 170760/371472 [2:39:24<16:07:14,  3.46it/s]
 46%|████▌     | 170761/371472 [2:39:25<16:19:42,  3.41it/s]
 46%|████▌     | 170762/371472 [2:39:25<17:25:11,  3.20it/s]
 46%|████▌     | 170763/371472 [2:39:25<17:29:18,  3.19it/s]
 46%|████▌     | 170764/371472 [2:39:26<18:03:46,  3.09it/s]
 46%|████▌     | 170765/371472 [2:39:26<17:46:37,  3.14it/s]
 46%|████▌     | 170766/371472 [2:39:26<18:13:45,  3.06it/s]
 46%|████▌     | 170767/371472 [2:39:27<17:38:33,  3.16it/s]
 46%|████▌     | 170768/371472 [2:39:27<18:35:11,  3.00it/s]
 46%|████▌     | 170769/371472 [2:39:27<18:17:48,  3.05it/s]
 46%|████▌     | 170770/371472 [2:39:28<17:50:57,  3.12it/s]
 46%|████▌     | 170771/371472 [2:39:28<17:57:22,  3.10it/s]
 46%|████▌     | 170772/371472 [2:39:28<17:13:14,  3.24it/s]
 46%|████▌     | 170773/371472 [2:39:29<17:49:13,  3.13it/s]
 46%|████▌     | 170774/371472 [2:39:29<17:22:01,  3.21it/s]
 46%|████▌     | 170775/371472 [2:39:29<16:57:24,  3.29it/s]
 46%|████▌     | 170776/371472 [2:39:29<16:38:26,  3.35it/s]
 46%|████▌     | 170777/371472 [2:39:30<16:19:23,  3.42it/s]
 46%|████▌     | 170778/371472 [2:39:30<16:27:47,  3.39it/s]
 46%|████▌     | 170779/371472 [2:39:30<17:24:03,  3.20it/s]
 46%|████▌     | 170780/371472 [2:39:31<16:51:02,  3.31it/s]
                                                            
{'loss': 3.027, 'learning_rate': 5.864972311405115e-07, 'epoch': 7.36}
+
 46%|████▌     | 170780/371472 [2:39:31<16:51:02,  3.31it/s]
 46%|████▌     | 170781/371472 [2:39:31<16:45:00,  3.33it/s]
 46%|████▌     | 170782/371472 [2:39:31<16:12:15,  3.44it/s]
 46%|████▌     | 170783/371472 [2:39:31<16:14:07,  3.43it/s]
 46%|████▌     | 170784/371472 [2:39:32<16:55:54,  3.29it/s]
 46%|████▌     | 170785/371472 [2:39:32<16:40:53,  3.34it/s]
 46%|████▌     | 170786/371472 [2:39:32<16:15:58,  3.43it/s]
 46%|████▌     | 170787/371472 [2:39:33<16:29:08,  3.38it/s]
 46%|████▌     | 170788/371472 [2:39:33<16:36:34,  3.36it/s]
 46%|████▌     | 170789/371472 [2:39:33<16:35:41,  3.36it/s]
 46%|████▌     | 170790/371472 [2:39:34<16:20:51,  3.41it/s]
 46%|████▌     | 170791/371472 [2:39:34<16:13:40,  3.44it/s]
 46%|████▌     | 170792/371472 [2:39:34<16:42:31,  3.34it/s]
 46%|████▌     | 170793/371472 [2:39:34<16:22:34,  3.40it/s]
 46%|████▌     | 170794/371472 [2:39:35<16:15:46,  3.43it/s]
 46%|████▌     | 170795/371472 [2:39:35<16:06:47,  3.46it/s]
 46%|████▌     | 170796/371472 [2:39:35<16:45:33,  3.33it/s]
 46%|████▌     | 170797/371472 [2:39:36<16:42:19,  3.34it/s]
 46%|████▌     | 170798/371472 [2:39:36<16:24:12,  3.40it/s]
 46%|████▌     | 170799/371472 [2:39:36<16:08:19,  3.45it/s]
 46%|████▌     | 170800/371472 [2:39:37<17:11:01,  3.24it/s]
                                                            
{'loss': 2.8187, 'learning_rate': 5.864487491650325e-07, 'epoch': 7.36}
+
 46%|████▌     | 170800/371472 [2:39:37<17:11:01,  3.24it/s]
 46%|████▌     | 170801/371472 [2:39:37<16:32:50,  3.37it/s]
 46%|████▌     | 170802/371472 [2:39:37<16:23:53,  3.40it/s]
 46%|████▌     | 170803/371472 [2:39:37<17:02:39,  3.27it/s]
 46%|████▌     | 170804/371472 [2:39:38<16:23:14,  3.40it/s]
 46%|████▌     | 170805/371472 [2:39:38<16:12:50,  3.44it/s]
 46%|████▌     | 170806/371472 [2:39:38<16:08:04,  3.45it/s]
 46%|████▌     | 170807/371472 [2:39:39<16:22:42,  3.40it/s]
 46%|████▌     | 170808/371472 [2:39:39<16:10:14,  3.45it/s]
 46%|████▌     | 170809/371472 [2:39:39<16:24:29,  3.40it/s]
 46%|████▌     | 170810/371472 [2:39:39<16:04:54,  3.47it/s]
 46%|████▌     | 170811/371472 [2:39:40<15:27:04,  3.61it/s]
 46%|████▌     | 170812/371472 [2:39:40<15:37:52,  3.57it/s]
 46%|████▌     | 170813/371472 [2:39:40<15:27:01,  3.61it/s]
 46%|████▌     | 170814/371472 [2:39:41<16:22:48,  3.40it/s]
 46%|████▌     | 170815/371472 [2:39:41<16:43:22,  3.33it/s]
 46%|████▌     | 170816/371472 [2:39:41<16:05:40,  3.46it/s]
 46%|████▌     | 170817/371472 [2:39:41<16:09:20,  3.45it/s]
 46%|████▌     | 170818/371472 [2:39:42<16:16:23,  3.43it/s]
 46%|████▌     | 170819/371472 [2:39:42<16:00:57,  3.48it/s]
 46%|████▌     | 170820/371472 [2:39:42<17:00:34,  3.28it/s]
                                                            
{'loss': 2.9756, 'learning_rate': 5.864002671895537e-07, 'epoch': 7.36}
+
 46%|████▌     | 170820/371472 [2:39:42<17:00:34,  3.28it/s]
 46%|████▌     | 170821/371472 [2:39:43<17:14:33,  3.23it/s]
 46%|████▌     | 170822/371472 [2:39:43<16:55:34,  3.29it/s]
 46%|████▌     | 170823/371472 [2:39:43<17:04:31,  3.26it/s]
 46%|████▌     | 170824/371472 [2:39:44<19:00:53,  2.93it/s]
 46%|████▌     | 170825/371472 [2:39:44<18:10:23,  3.07it/s]
 46%|████▌     | 170826/371472 [2:39:44<18:53:47,  2.95it/s]
 46%|████▌     | 170827/371472 [2:39:45<18:03:08,  3.09it/s]
 46%|████▌     | 170828/371472 [2:39:45<17:13:51,  3.23it/s]
 46%|████▌     | 170829/371472 [2:39:45<17:20:31,  3.21it/s]
 46%|████▌     | 170830/371472 [2:39:46<17:39:36,  3.16it/s]
 46%|████▌     | 170831/371472 [2:39:46<16:59:46,  3.28it/s]
 46%|████▌     | 170832/371472 [2:39:46<16:31:25,  3.37it/s]
 46%|████▌     | 170833/371472 [2:39:46<17:03:13,  3.27it/s]
 46%|████▌     | 170834/371472 [2:39:47<16:52:37,  3.30it/s]
 46%|████▌     | 170835/371472 [2:39:47<16:36:55,  3.35it/s]
 46%|████▌     | 170836/371472 [2:39:47<16:42:01,  3.34it/s]
 46%|████▌     | 170837/371472 [2:39:48<17:04:51,  3.26it/s]
 46%|████▌     | 170838/371472 [2:39:48<16:49:34,  3.31it/s]
 46%|████▌     | 170839/371472 [2:39:48<16:58:14,  3.28it/s]
 46%|████▌     | 170840/371472 [2:39:49<17:26:15,  3.20it/s]
                                                            
{'loss': 2.8773, 'learning_rate': 5.863517852140749e-07, 'epoch': 7.36}
+
 46%|████▌     | 170840/371472 [2:39:49<17:26:15,  3.20it/s]
 46%|████▌     | 170841/371472 [2:39:49<17:14:45,  3.23it/s]
 46%|████▌     | 170842/371472 [2:39:49<17:01:32,  3.27it/s]
 46%|████▌     | 170843/371472 [2:39:50<17:17:41,  3.22it/s]
 46%|████▌     | 170844/371472 [2:39:50<17:15:32,  3.23it/s]
 46%|████▌     | 170845/371472 [2:39:50<16:54:11,  3.30it/s]
 46%|████▌     | 170846/371472 [2:39:50<16:26:02,  3.39it/s]
 46%|████▌     | 170847/371472 [2:39:51<16:34:51,  3.36it/s]
 46%|████▌     | 170848/371472 [2:39:51<16:33:48,  3.36it/s]
 46%|████▌     | 170849/371472 [2:39:51<17:09:53,  3.25it/s]
 46%|████▌     | 170850/371472 [2:39:52<17:08:44,  3.25it/s]
 46%|████▌     | 170851/371472 [2:39:52<16:36:03,  3.36it/s]
 46%|████▌     | 170852/371472 [2:39:52<17:22:14,  3.21it/s]
 46%|████▌     | 170853/371472 [2:39:53<16:42:21,  3.34it/s]
 46%|████▌     | 170854/371472 [2:39:53<17:58:18,  3.10it/s]
 46%|████▌     | 170855/371472 [2:39:53<18:43:08,  2.98it/s]
 46%|████▌     | 170856/371472 [2:39:54<19:36:11,  2.84it/s]
 46%|████▌     | 170857/371472 [2:39:54<18:26:27,  3.02it/s]
 46%|████▌     | 170858/371472 [2:39:54<17:44:04,  3.14it/s]
 46%|████▌     | 170859/371472 [2:39:55<17:20:37,  3.21it/s]
 46%|████▌     | 170860/371472 [2:39:55<16:59:47,  3.28it/s]
                                                            
{'loss': 2.7869, 'learning_rate': 5.86303303238596e-07, 'epoch': 7.36}
+
 46%|████▌     | 170860/371472 [2:39:55<16:59:47,  3.28it/s]
 46%|████▌     | 170861/371472 [2:39:55<18:05:07,  3.08it/s]
 46%|████▌     | 170862/371472 [2:39:55<17:14:38,  3.23it/s]
 46%|████▌     | 170863/371472 [2:39:56<16:35:29,  3.36it/s]
 46%|████▌     | 170864/371472 [2:39:56<17:32:17,  3.18it/s]
 46%|████▌     | 170865/371472 [2:39:56<18:13:21,  3.06it/s]
 46%|████▌     | 170866/371472 [2:39:57<17:58:15,  3.10it/s]
 46%|████▌     | 170867/371472 [2:39:57<17:19:04,  3.22it/s]
 46%|████▌     | 170868/371472 [2:39:57<17:19:19,  3.22it/s]
 46%|████▌     | 170869/371472 [2:39:58<17:37:32,  3.16it/s]
 46%|████▌     | 170870/371472 [2:39:58<16:45:48,  3.32it/s]
 46%|████▌     | 170871/371472 [2:39:58<16:34:32,  3.36it/s]
 46%|████▌     | 170872/371472 [2:39:58<16:14:17,  3.43it/s]
 46%|████▌     | 170873/371472 [2:39:59<16:38:11,  3.35it/s]
 46%|████▌     | 170874/371472 [2:39:59<16:55:14,  3.29it/s]
 46%|████▌     | 170875/371472 [2:39:59<16:42:57,  3.33it/s]
 46%|████▌     | 170876/371472 [2:40:00<17:10:49,  3.24it/s]
 46%|████▌     | 170877/371472 [2:40:00<16:35:06,  3.36it/s]
 46%|████▌     | 170878/371472 [2:40:00<16:22:32,  3.40it/s]
 46%|████▌     | 170879/371472 [2:40:01<15:59:06,  3.49it/s]
 46%|████▌     | 170880/371472 [2:40:01<15:47:07,  3.53it/s]
                                                            
{'loss': 3.163, 'learning_rate': 5.862548212631169e-07, 'epoch': 7.36}
+
 46%|████▌     | 170880/371472 [2:40:01<15:47:07,  3.53it/s]
 46%|████▌     | 170881/371472 [2:40:01<17:04:01,  3.26it/s]
 46%|████▌     | 170882/371472 [2:40:01<16:35:02,  3.36it/s]
 46%|████▌     | 170883/371472 [2:40:02<16:17:43,  3.42it/s]
 46%|████▌     | 170884/371472 [2:40:02<17:30:32,  3.18it/s]
 46%|████▌     | 170885/371472 [2:40:02<17:05:46,  3.26it/s]
 46%|████▌     | 170886/371472 [2:40:03<17:10:59,  3.24it/s]
 46%|████▌     | 170887/371472 [2:40:03<17:28:36,  3.19it/s]
 46%|████▌     | 170888/371472 [2:40:03<17:54:05,  3.11it/s]
 46%|████▌     | 170889/371472 [2:40:04<17:22:12,  3.21it/s]
 46%|████▌     | 170890/371472 [2:40:04<17:07:55,  3.25it/s]
 46%|████▌     | 170891/371472 [2:40:04<16:51:29,  3.31it/s]
 46%|████▌     | 170892/371472 [2:40:05<16:58:15,  3.28it/s]
 46%|████▌     | 170893/371472 [2:40:05<16:47:41,  3.32it/s]
 46%|████▌     | 170894/371472 [2:40:05<16:48:11,  3.32it/s]
 46%|████▌     | 170895/371472 [2:40:05<16:47:43,  3.32it/s]
 46%|████▌     | 170896/371472 [2:40:06<16:43:10,  3.33it/s]
 46%|████▌     | 170897/371472 [2:40:06<16:32:55,  3.37it/s]
 46%|████▌     | 170898/371472 [2:40:06<16:16:17,  3.42it/s]
 46%|████▌     | 170899/371472 [2:40:07<16:43:24,  3.33it/s]
 46%|████▌     | 170900/371472 [2:40:07<16:25:31,  3.39it/s]
                                                            
{'loss': 2.8545, 'learning_rate': 5.862063392876381e-07, 'epoch': 7.36}
+
 46%|████▌     | 170900/371472 [2:40:07<16:25:31,  3.39it/s]
 46%|████▌     | 170901/371472 [2:40:07<17:23:10,  3.20it/s]
 46%|████▌     | 170902/371472 [2:40:08<17:18:29,  3.22it/s]
 46%|████▌     | 170903/371472 [2:40:08<17:26:42,  3.19it/s]
 46%|████▌     | 170904/371472 [2:40:08<17:14:19,  3.23it/s]
 46%|████▌     | 170905/371472 [2:40:09<16:44:28,  3.33it/s]
 46%|████▌     | 170906/371472 [2:40:09<16:11:02,  3.44it/s]
 46%|████▌     | 170907/371472 [2:40:09<15:51:39,  3.51it/s]
 46%|████▌     | 170908/371472 [2:40:09<15:39:45,  3.56it/s]
 46%|████▌     | 170909/371472 [2:40:10<15:56:03,  3.50it/s]
 46%|████▌     | 170910/371472 [2:40:10<16:20:33,  3.41it/s]
 46%|████▌     | 170911/371472 [2:40:10<16:22:10,  3.40it/s]
 46%|████▌     | 170912/371472 [2:40:11<17:28:43,  3.19it/s]
 46%|████▌     | 170913/371472 [2:40:11<18:33:16,  3.00it/s]
 46%|████▌     | 170914/371472 [2:40:11<18:01:57,  3.09it/s]
 46%|████▌     | 170915/371472 [2:40:12<17:17:42,  3.22it/s]
 46%|████▌     | 170916/371472 [2:40:12<17:40:50,  3.15it/s]
 46%|████▌     | 170917/371472 [2:40:12<17:16:55,  3.22it/s]
 46%|████▌     | 170918/371472 [2:40:12<17:09:14,  3.25it/s]
 46%|████▌     | 170919/371472 [2:40:13<16:55:46,  3.29it/s]
 46%|████▌     | 170920/371472 [2:40:13<17:32:09,  3.18it/s]
                                                            
{'loss': 2.8849, 'learning_rate': 5.861578573121593e-07, 'epoch': 7.36}
+
 46%|████▌     | 170920/371472 [2:40:13<17:32:09,  3.18it/s]
 46%|████▌     | 170921/371472 [2:40:13<17:03:51,  3.26it/s]
 46%|████▌     | 170922/371472 [2:40:14<17:05:34,  3.26it/s]
 46%|████▌     | 170923/371472 [2:40:14<16:40:49,  3.34it/s]
 46%|████▌     | 170924/371472 [2:40:14<16:32:15,  3.37it/s]
 46%|████▌     | 170925/371472 [2:40:15<16:17:48,  3.42it/s]
 46%|████▌     | 170926/371472 [2:40:15<16:13:38,  3.43it/s]
 46%|████▌     | 170927/371472 [2:40:15<16:29:53,  3.38it/s]
 46%|████▌     | 170928/371472 [2:40:15<16:27:07,  3.39it/s]
 46%|████▌     | 170929/371472 [2:40:16<16:07:42,  3.45it/s]
 46%|████▌     | 170930/371472 [2:40:16<15:58:23,  3.49it/s]
 46%|████▌     | 170931/371472 [2:40:16<16:01:28,  3.48it/s]
 46%|████▌     | 170932/371472 [2:40:17<16:41:48,  3.34it/s]
 46%|████▌     | 170933/371472 [2:40:17<16:12:32,  3.44it/s]
 46%|████▌     | 170934/371472 [2:40:17<17:46:39,  3.13it/s]
 46%|████▌     | 170935/371472 [2:40:18<19:47:37,  2.81it/s]
 46%|████▌     | 170936/371472 [2:40:18<18:31:40,  3.01it/s]
 46%|████▌     | 170937/371472 [2:40:18<18:05:04,  3.08it/s]
 46%|████▌     | 170938/371472 [2:40:19<22:31:36,  2.47it/s]
 46%|████▌     | 170939/371472 [2:40:19<22:09:36,  2.51it/s]
 46%|████▌     | 170940/371472 [2:40:20<21:25:02,  2.60it/s]
                                                            
{'loss': 2.9166, 'learning_rate': 5.861093753366804e-07, 'epoch': 7.36}
+
 46%|████▌     | 170940/371472 [2:40:20<21:25:02,  2.60it/s]
 46%|████▌     | 170941/371472 [2:40:20<19:56:25,  2.79it/s]
 46%|████▌     | 170942/371472 [2:40:20<18:29:03,  3.01it/s]
 46%|████▌     | 170943/371472 [2:40:21<18:25:19,  3.02it/s]
 46%|████▌     | 170944/371472 [2:40:21<18:22:42,  3.03it/s]
 46%|████▌     | 170945/371472 [2:40:21<17:54:37,  3.11it/s]
 46%|████▌     | 170946/371472 [2:40:21<18:12:45,  3.06it/s]
 46%|████▌     | 170947/371472 [2:40:22<19:22:44,  2.87it/s]
 46%|████▌     | 170948/371472 [2:40:22<18:18:14,  3.04it/s]
 46%|████▌     | 170949/371472 [2:40:22<18:15:13,  3.05it/s]
 46%|████▌     | 170950/371472 [2:40:23<17:43:56,  3.14it/s]
 46%|████▌     | 170951/371472 [2:40:23<17:36:18,  3.16it/s]
 46%|████▌     | 170952/371472 [2:40:23<17:28:14,  3.19it/s]
 46%|████▌     | 170953/371472 [2:40:24<17:17:55,  3.22it/s]
 46%|████▌     | 170954/371472 [2:40:24<17:16:36,  3.22it/s]
 46%|████▌     | 170955/371472 [2:40:24<17:26:58,  3.19it/s]
 46%|████▌     | 170956/371472 [2:40:25<17:13:43,  3.23it/s]
 46%|████▌     | 170957/371472 [2:40:25<17:01:27,  3.27it/s]
 46%|████▌     | 170958/371472 [2:40:25<17:03:50,  3.26it/s]
 46%|████▌     | 170959/371472 [2:40:26<16:47:23,  3.32it/s]
 46%|████▌     | 170960/371472 [2:40:26<17:22:44,  3.20it/s]
                                                            
{'loss': 2.7729, 'learning_rate': 5.860608933612014e-07, 'epoch': 7.36}
+
 46%|████▌     | 170960/371472 [2:40:26<17:22:44,  3.20it/s]
 46%|████▌     | 170961/371472 [2:40:26<16:57:18,  3.29it/s]
 46%|████▌     | 170962/371472 [2:40:26<16:39:45,  3.34it/s]
 46%|████▌     | 170963/371472 [2:40:27<19:33:10,  2.85it/s]
 46%|████▌     | 170964/371472 [2:40:27<18:46:31,  2.97it/s]
 46%|████▌     | 170965/371472 [2:40:28<19:38:24,  2.84it/s]
 46%|████▌     | 170966/371472 [2:40:28<19:43:28,  2.82it/s]
 46%|████▌     | 170967/371472 [2:40:28<18:39:30,  2.99it/s]
 46%|████▌     | 170968/371472 [2:40:29<18:16:06,  3.05it/s]
 46%|████▌     | 170969/371472 [2:40:29<17:44:53,  3.14it/s]
 46%|████▌     | 170970/371472 [2:40:29<17:01:29,  3.27it/s]
 46%|████▌     | 170971/371472 [2:40:29<16:43:27,  3.33it/s]
 46%|████▌     | 170972/371472 [2:40:30<16:33:04,  3.36it/s]
 46%|██���█▌     | 170973/371472 [2:40:30<17:12:00,  3.24it/s]
 46%|████▌     | 170974/371472 [2:40:30<18:36:45,  2.99it/s]
 46%|████▌     | 170975/371472 [2:40:31<18:19:12,  3.04it/s]
 46%|████▌     | 170976/371472 [2:40:31<18:08:34,  3.07it/s]
 46%|████▌     | 170977/371472 [2:40:31<17:38:40,  3.16it/s]
 46%|████▌     | 170978/371472 [2:40:32<16:47:56,  3.32it/s]
 46%|████▌     | 170979/371472 [2:40:32<17:03:27,  3.26it/s]
 46%|████▌     | 170980/371472 [2:40:32<18:46:51,  2.97it/s]
                                                            
{'loss': 2.8605, 'learning_rate': 5.860124113857227e-07, 'epoch': 7.36}
+
 46%|████▌     | 170980/371472 [2:40:32<18:46:51,  2.97it/s]
 46%|████▌     | 170981/371472 [2:40:33<17:52:00,  3.12it/s]
 46%|████▌     | 170982/371472 [2:40:33<17:21:15,  3.21it/s]
 46%|████▌     | 170983/371472 [2:40:33<16:46:38,  3.32it/s]
 46%|████▌     | 170984/371472 [2:40:34<16:25:33,  3.39it/s]
 46%|████▌     | 170985/371472 [2:40:34<16:13:53,  3.43it/s]
 46%|████▌     | 170986/371472 [2:40:34<16:13:33,  3.43it/s]
 46%|████▌     | 170987/371472 [2:40:34<16:11:15,  3.44it/s]
 46%|████▌     | 170988/371472 [2:40:35<18:04:36,  3.08it/s]
 46%|████▌     | 170989/371472 [2:40:35<17:29:06,  3.18it/s]
 46%|████▌     | 170990/371472 [2:40:35<17:07:06,  3.25it/s]
 46%|████▌     | 170991/371472 [2:40:36<17:13:41,  3.23it/s]
 46%|████▌     | 170992/371472 [2:40:36<16:43:51,  3.33it/s]
 46%|████▌     | 170993/371472 [2:40:36<16:35:43,  3.36it/s]
 46%|████▌     | 170994/371472 [2:40:37<16:28:20,  3.38it/s]
 46%|████▌     | 170995/371472 [2:40:37<16:04:54,  3.46it/s]
 46%|████▌     | 170996/371472 [2:40:37<16:02:20,  3.47it/s]
 46%|████▌     | 170997/371472 [2:40:37<16:27:01,  3.39it/s]
 46%|████▌     | 170998/371472 [2:40:38<16:04:37,  3.46it/s]
 46%|████▌     | 170999/371472 [2:40:38<15:57:50,  3.49it/s]
 46%|████▌     | 171000/371472 [2:40:38<16:42:20,  3.33it/s]
                                                            
{'loss': 3.039, 'learning_rate': 5.859639294102437e-07, 'epoch': 7.37}
+
 46%|████▌     | 171000/371472 [2:40:38<16:42:20,  3.33it/s]
 46%|████▌     | 171001/371472 [2:40:39<16:36:16,  3.35it/s]
 46%|████▌     | 171002/371472 [2:40:39<16:31:48,  3.37it/s]
 46%|████▌     | 171003/371472 [2:40:39<16:54:49,  3.29it/s]
 46%|████▌     | 171004/371472 [2:40:39<16:32:49,  3.37it/s]
 46%|████▌     | 171005/371472 [2:40:40<16:35:34,  3.36it/s]
 46%|████▌     | 171006/371472 [2:40:40<16:36:35,  3.35it/s]
 46%|████▌     | 171007/371472 [2:40:40<16:39:07,  3.34it/s]
 46%|████▌     | 171008/371472 [2:40:41<16:38:43,  3.35it/s]
 46%|████▌     | 171009/371472 [2:40:41<16:45:16,  3.32it/s]
 46%|████▌     | 171010/371472 [2:40:41<16:28:07,  3.38it/s]
 46%|████▌     | 171011/371472 [2:40:42<16:40:04,  3.34it/s]
 46%|████▌     | 171012/371472 [2:40:42<17:18:32,  3.22it/s]
 46%|████▌     | 171013/371472 [2:40:42<17:19:53,  3.21it/s]
 46%|████▌     | 171014/371472 [2:40:43<17:26:49,  3.19it/s]
 46%|████▌     | 171015/371472 [2:40:43<17:45:59,  3.13it/s]
 46%|████▌     | 171016/371472 [2:40:43<17:41:30,  3.15it/s]
 46%|████▌     | 171017/371472 [2:40:43<17:13:01,  3.23it/s]
 46%|████▌     | 171018/371472 [2:40:44<16:48:48,  3.31it/s]
 46%|████▌     | 171019/371472 [2:40:44<16:32:09,  3.37it/s]
 46%|████▌     | 171020/371472 [2:40:44<16:39:33,  3.34it/s]
                                                            
{'loss': 2.8706, 'learning_rate': 5.859154474347647e-07, 'epoch': 7.37}
+
 46%|████▌     | 171020/371472 [2:40:44<16:39:33,  3.34it/s]
 46%|████▌     | 171021/371472 [2:40:45<16:14:44,  3.43it/s]
 46%|████▌     | 171022/371472 [2:40:45<16:18:00,  3.42it/s]
 46%|████▌     | 171023/371472 [2:40:45<16:31:44,  3.37it/s]
 46%|████▌     | 171024/371472 [2:40:46<16:38:40,  3.35it/s]
 46%|████▌     | 171025/371472 [2:40:46<18:23:51,  3.03it/s]
 46%|████▌     | 171026/371472 [2:40:46<18:01:29,  3.09it/s]
 46%|████▌     | 171027/371472 [2:40:47<17:25:54,  3.19it/s]
 46%|████▌     | 171028/371472 [2:40:47<16:56:30,  3.29it/s]
 46%|████▌     | 171029/371472 [2:40:47<17:57:00,  3.10it/s]
 46%|████▌     | 171030/371472 [2:40:47<17:47:19,  3.13it/s]
 46%|████▌     | 171031/371472 [2:40:48<17:26:36,  3.19it/s]
 46%|████▌     | 171032/371472 [2:40:48<17:00:12,  3.27it/s]
 46%|████▌     | 171033/371472 [2:40:48<17:43:48,  3.14it/s]
 46%|████▌     | 171034/371472 [2:40:49<17:53:56,  3.11it/s]
 46%|████▌     | 171035/371472 [2:40:49<17:39:39,  3.15it/s]
 46%|████▌     | 171036/371472 [2:40:49<17:34:52,  3.17it/s]
 46%|████▌     | 171037/371472 [2:40:50<17:14:00,  3.23it/s]
 46%|████▌     | 171038/371472 [2:40:50<17:03:19,  3.26it/s]
 46%|████▌     | 171039/371472 [2:40:50<17:43:25,  3.14it/s]
 46%|████▌     | 171040/371472 [2:40:51<17:07:32,  3.25it/s]
                                                            
{'loss': 2.8606, 'learning_rate': 5.858669654592858e-07, 'epoch': 7.37}
+
 46%|████▌     | 171040/371472 [2:40:51<17:07:32,  3.25it/s]
 46%|████▌     | 171041/371472 [2:40:51<16:48:08,  3.31it/s]
 46%|████▌     | 171042/371472 [2:40:51<16:16:14,  3.42it/s]
 46%|████▌     | 171043/371472 [2:40:51<16:52:12,  3.30it/s]
 46%|████▌     | 171044/371472 [2:40:52<16:59:36,  3.28it/s]
 46%|████▌     | 171045/371472 [2:40:52<16:22:42,  3.40it/s]
 46%|████▌     | 171046/371472 [2:40:52<16:23:29,  3.40it/s]
 46%|████▌     | 171047/371472 [2:40:53<16:24:20,  3.39it/s]
 46%|████▌     | 171048/371472 [2:40:53<16:38:58,  3.34it/s]
 46%|████▌     | 171049/371472 [2:40:53<16:42:02,  3.33it/s]
 46%|████▌     | 171050/371472 [2:40:54<17:32:27,  3.17it/s]
 46%|████▌     | 171051/371472 [2:40:54<17:33:08,  3.17it/s]
 46%|████▌     | 171052/371472 [2:40:54<17:08:46,  3.25it/s]
 46%|████▌     | 171053/371472 [2:40:55<16:49:49,  3.31it/s]
 46%|████▌     | 171054/371472 [2:40:55<16:56:26,  3.29it/s]
 46%|████▌     | 171055/371472 [2:40:55<16:50:46,  3.30it/s]
 46%|████▌     | 171056/371472 [2:40:55<16:34:33,  3.36it/s]
 46%|████▌     | 171057/371472 [2:40:56<16:53:25,  3.30it/s]
 46%|████▌     | 171058/371472 [2:40:56<17:08:39,  3.25it/s]
 46%|████▌     | 171059/371472 [2:40:56<17:52:37,  3.11it/s]
 46%|████▌     | 171060/371472 [2:40:57<18:11:56,  3.06it/s]
                                                            
{'loss': 2.9551, 'learning_rate': 5.85818483483807e-07, 'epoch': 7.37}
+
 46%|████▌     | 171060/371472 [2:40:57<18:11:56,  3.06it/s]
 46%|████▌     | 171061/371472 [2:40:57<17:31:10,  3.18it/s]
 46%|████▌     | 171062/371472 [2:40:57<17:19:38,  3.21it/s]
 46%|████▌     | 171063/371472 [2:40:58<17:20:25,  3.21it/s]
 46%|████▌     | 171064/371472 [2:40:58<17:18:54,  3.22it/s]
 46%|████▌     | 171065/371472 [2:40:58<17:24:14,  3.20it/s]
 46%|████▌     | 171066/371472 [2:40:59<16:40:25,  3.34it/s]
 46%|████▌     | 171067/371472 [2:40:59<16:08:45,  3.45it/s]
 46%|████▌     | 171068/371472 [2:40:59<16:17:19,  3.42it/s]
 46%|████▌     | 171069/371472 [2:40:59<16:57:47,  3.28it/s]
 46%|████▌     | 171070/371472 [2:41:00<16:42:21,  3.33it/s]
 46%|████▌     | 171071/371472 [2:41:00<16:48:50,  3.31it/s]
 46%|████▌     | 171072/371472 [2:41:00<17:19:45,  3.21it/s]
 46%|████▌     | 171073/371472 [2:41:01<17:02:20,  3.27it/s]
 46%|████▌     | 171074/371472 [2:41:01<16:47:38,  3.31it/s]
 46%|████▌     | 171075/371472 [2:41:01<16:50:34,  3.30it/s]
 46%|████▌     | 171076/371472 [2:41:02<17:01:40,  3.27it/s]
 46%|████▌     | 171077/371472 [2:41:02<17:45:37,  3.13it/s]
 46%|████▌     | 171078/371472 [2:41:02<17:33:02,  3.17it/s]
 46%|████▌     | 171079/371472 [2:41:03<17:12:48,  3.23it/s]
 46%|████▌     | 171080/371472 [2:41:03<17:08:33,  3.25it/s]
                                                            
{'loss': 2.8875, 'learning_rate': 5.857700015083282e-07, 'epoch': 7.37}
+
 46%|████▌     | 171080/371472 [2:41:03<17:08:33,  3.25it/s]
 46%|████▌     | 171081/371472 [2:41:03<16:41:39,  3.33it/s]
 46%|████▌     | 171082/371472 [2:41:03<16:22:03,  3.40it/s]
 46%|████▌     | 171083/371472 [2:41:04<17:16:43,  3.22it/s]
 46%|████▌     | 171084/371472 [2:41:04<17:44:02,  3.14it/s]
 46%|████▌     | 171085/371472 [2:41:04<17:09:27,  3.24it/s]
 46%|████▌     | 171086/371472 [2:41:05<16:31:15,  3.37it/s]
 46%|████▌     | 171087/371472 [2:41:05<16:13:40,  3.43it/s]
 46%|████▌     | 171088/371472 [2:41:05<16:36:19,  3.35it/s]
 46%|████▌     | 171089/371472 [2:41:06<18:00:02,  3.09it/s]
 46%|████▌     | 171090/371472 [2:41:06<18:00:41,  3.09it/s]
 46%|████▌     | 171091/371472 [2:41:06<17:08:45,  3.25it/s]
 46%|████▌     | 171092/371472 [2:41:06<16:51:36,  3.30it/s]
 46%|████▌     | 171093/371472 [2:41:07<16:20:34,  3.41it/s]
 46%|████▌     | 171094/371472 [2:41:07<16:15:39,  3.42it/s]
 46%|████▌     | 171095/371472 [2:41:07<16:37:01,  3.35it/s]
 46%|████▌     | 171096/371472 [2:41:08<16:42:05,  3.33it/s]
 46%|████▌     | 171097/371472 [2:41:08<16:20:53,  3.40it/s]
 46%|████▌     | 171098/371472 [2:41:08<16:03:55,  3.46it/s]
 46%|████▌     | 171099/371472 [2:41:08<15:52:43,  3.51it/s]
 46%|████▌     | 171100/371472 [2:41:09<16:28:21,  3.38it/s]
                                                            
{'loss': 2.9301, 'learning_rate': 5.857215195328492e-07, 'epoch': 7.37}
+
 46%|████▌     | 171100/371472 [2:41:09<16:28:21,  3.38it/s]
 46%|████▌     | 171101/371472 [2:41:09<16:15:48,  3.42it/s]
 46%|████▌     | 171102/371472 [2:41:09<16:12:54,  3.43it/s]
 46%|████▌     | 171103/371472 [2:41:10<16:45:28,  3.32it/s]
 46%|████▌     | 171104/371472 [2:41:10<16:34:52,  3.36it/s]
 46%|████▌     | 171105/371472 [2:41:10<16:32:28,  3.36it/s]
 46%|████▌     | 171106/371472 [2:41:11<16:45:40,  3.32it/s]
 46%|████▌     | 171107/371472 [2:41:11<16:30:59,  3.37it/s]
 46%|████▌     | 171108/371472 [2:41:11<16:33:25,  3.36it/s]
 46%|████▌     | 171109/371472 [2:41:11<16:30:54,  3.37it/s]
 46%|████▌     | 171110/371472 [2:41:12<16:25:53,  3.39it/s]
 46%|████▌     | 171111/371472 [2:41:12<16:22:35,  3.40it/s]
 46%|████▌     | 171112/371472 [2:41:12<16:15:54,  3.42it/s]
 46%|████▌     | 171113/371472 [2:41:13<16:34:08,  3.36it/s]
 46%|████▌     | 171114/371472 [2:41:13<16:11:48,  3.44it/s]
 46%|████▌     | 171115/371472 [2:41:13<16:26:02,  3.39it/s]
 46%|████▌     | 171116/371472 [2:41:14<16:05:05,  3.46it/s]
 46%|████▌     | 171117/371472 [2:41:14<16:19:23,  3.41it/s]
 46%|████▌     | 171118/371472 [2:41:14<18:00:36,  3.09it/s]
 46%|████▌     | 171119/371472 [2:41:15<18:24:48,  3.02it/s]
 46%|████▌     | 171120/371472 [2:41:15<17:17:29,  3.22it/s]
                                                            
{'loss': 3.0549, 'learning_rate': 5.856730375573703e-07, 'epoch': 7.37}
+
 46%|████▌     | 171120/371472 [2:41:15<17:17:29,  3.22it/s]
 46%|████▌     | 171121/371472 [2:41:15<16:45:44,  3.32it/s]
 46%|████▌     | 171122/371472 [2:41:15<17:19:52,  3.21it/s]
 46%|████▌     | 171123/371472 [2:41:16<17:18:34,  3.22it/s]
 46%|████▌     | 171124/371472 [2:41:16<16:47:18,  3.31it/s]
 46%|████▌     | 171125/371472 [2:41:16<16:15:46,  3.42it/s]
 46%|████▌     | 171126/371472 [2:41:17<16:03:58,  3.46it/s]
 46%|████▌     | 171127/371472 [2:41:17<15:43:41,  3.54it/s]
 46%|████▌     | 171128/371472 [2:41:17<15:52:23,  3.51it/s]
 46%|████▌     | 171129/371472 [2:41:17<16:25:55,  3.39it/s]
 46%|████▌     | 171130/371472 [2:41:18<16:06:44,  3.45it/s]
 46%|████▌     | 171131/371472 [2:41:18<16:08:44,  3.45it/s]
 46%|████▌     | 171132/371472 [2:41:18<16:36:08,  3.35it/s]
 46%|████▌     | 171133/371472 [2:41:19<16:07:13,  3.45it/s]
 46%|████▌     | 171134/371472 [2:41:19<16:11:18,  3.44it/s]
 46%|████▌     | 171135/371472 [2:41:19<16:48:38,  3.31it/s]
 46%|████▌     | 171136/371472 [2:41:20<16:28:30,  3.38it/s]
 46%|████▌     | 171137/371472 [2:41:20<16:01:57,  3.47it/s]
 46%|████▌     | 171138/371472 [2:41:20<15:42:37,  3.54it/s]
 46%|████▌     | 171139/371472 [2:41:20<15:24:34,  3.61it/s]
 46%|████▌     | 171140/371472 [2:41:21<15:37:00,  3.56it/s]
                                                            
{'loss': 2.9536, 'learning_rate': 5.856245555818914e-07, 'epoch': 7.37}
+
 46%|████▌     | 171140/371472 [2:41:21<15:37:00,  3.56it/s]
 46%|████▌     | 171141/371472 [2:41:21<15:49:14,  3.52it/s]
 46%|████▌     | 171142/371472 [2:41:21<15:45:12,  3.53it/s]
 46%|████▌     | 171143/371472 [2:41:21<15:56:47,  3.49it/s]
 46%|████▌     | 171144/371472 [2:41:22<15:41:34,  3.55it/s]
 46%|████▌     | 171145/371472 [2:41:22<15:45:07,  3.53it/s]
 46%|████▌     | 171146/371472 [2:41:22<16:05:06,  3.46it/s]
 46%|████▌     | 171147/371472 [2:41:23<16:37:56,  3.35it/s]
 46%|████▌     | 171148/371472 [2:41:23<17:04:12,  3.26it/s]
 46%|████▌     | 171149/371472 [2:41:23<17:52:59,  3.11it/s]
 46%|████▌     | 171150/371472 [2:41:24<17:13:44,  3.23it/s]
 46%|████▌     | 171151/371472 [2:41:24<16:57:59,  3.28it/s]
 46%|████▌     | 171152/371472 [2:41:24<17:42:11,  3.14it/s]
 46%|████▌     | 171153/371472 [2:41:25<17:44:56,  3.14it/s]
 46%|████▌     | 171154/371472 [2:41:25<17:27:00,  3.19it/s]
 46%|████▌     | 171155/371472 [2:41:25<17:18:10,  3.22it/s]
 46%|████▌     | 171156/371472 [2:41:25<16:47:26,  3.31it/s]
 46%|████▌     | 171157/371472 [2:41:26<16:13:06,  3.43it/s]
 46%|████▌     | 171158/371472 [2:41:26<16:03:50,  3.46it/s]
 46%|████▌     | 171159/371472 [2:41:26<16:48:33,  3.31it/s]
 46%|████▌     | 171160/371472 [2:41:27<16:24:51,  3.39it/s]
                                                            
{'loss': 2.7503, 'learning_rate': 5.855760736064126e-07, 'epoch': 7.37}
+
 46%|████▌     | 171160/371472 [2:41:27<16:24:51,  3.39it/s]
 46%|████▌     | 171161/371472 [2:41:27<17:30:57,  3.18it/s]
 46%|████▌     | 171162/371472 [2:41:27<17:50:52,  3.12it/s]
 46%|████▌     | 171163/371472 [2:41:28<18:09:10,  3.07it/s]
 46%|████▌     | 171164/371472 [2:41:28<17:58:43,  3.09it/s]
 46%|████▌     | 171165/371472 [2:41:28<17:44:31,  3.14it/s]
 46%|████▌     | 171166/371472 [2:41:29<17:04:20,  3.26it/s]
 46%|████▌     | 171167/371472 [2:41:29<17:49:59,  3.12it/s]
 46%|████▌     | 171168/371472 [2:41:29<17:08:12,  3.25it/s]
 46%|████▌     | 171169/371472 [2:41:30<16:53:44,  3.29it/s]
 46%|████▌     | 171170/371472 [2:41:30<16:43:49,  3.33it/s]
 46%|████▌     | 171171/371472 [2:41:30<16:29:29,  3.37it/s]
 46%|████▌     | 171172/371472 [2:41:30<16:47:25,  3.31it/s]
 46%|████▌     | 171173/371472 [2:41:31<17:00:06,  3.27it/s]
 46%|████▌     | 171174/371472 [2:41:31<17:14:10,  3.23it/s]
 46%|████▌     | 171175/371472 [2:41:31<18:25:44,  3.02it/s]
 46%|████▌     | 171176/371472 [2:41:32<17:40:10,  3.15it/s]
 46%|████▌     | 171177/371472 [2:41:32<16:46:37,  3.32it/s]
 46%|████▌     | 171178/371472 [2:41:32<16:32:31,  3.36it/s]
 46%|████▌     | 171179/371472 [2:41:33<16:10:49,  3.44it/s]
 46%|████▌     | 171180/371472 [2:41:33<15:46:35,  3.53it/s]
                                                            
{'loss': 2.9457, 'learning_rate': 5.855275916309336e-07, 'epoch': 7.37}
+
 46%|████▌     | 171180/371472 [2:41:33<15:46:35,  3.53it/s]
 46%|████▌     | 171181/371472 [2:41:33<15:50:08,  3.51it/s]
 46%|████▌     | 171182/371472 [2:41:33<15:50:30,  3.51it/s]
 46%|████▌     | 171183/371472 [2:41:34<16:39:05,  3.34it/s]
 46%|████▌     | 171184/371472 [2:41:34<17:05:07,  3.26it/s]
 46%|████▌     | 171185/371472 [2:41:34<17:06:38,  3.25it/s]
 46%|████▌     | 171186/371472 [2:41:35<17:28:19,  3.18it/s]
 46%|████▌     | 171187/371472 [2:41:35<17:06:12,  3.25it/s]
 46%|████▌     | 171188/371472 [2:41:35<17:27:50,  3.19it/s]
 46%|████▌     | 171189/371472 [2:41:36<17:36:08,  3.16it/s]
 46%|████▌     | 171190/371472 [2:41:36<17:01:19,  3.27it/s]
 46%|████▌     | 171191/371472 [2:41:36<16:28:57,  3.38it/s]
 46%|████▌     | 171192/371472 [2:41:36<16:19:44,  3.41it/s]
 46%|████▌     | 171193/371472 [2:41:37<16:00:33,  3.48it/s]
 46%|████▌     | 171194/371472 [2:41:37<16:15:18,  3.42it/s]
 46%|████▌     | 171195/371472 [2:41:37<16:34:04,  3.36it/s]
 46%|████▌     | 171196/371472 [2:41:38<16:19:10,  3.41it/s]
 46%|████▌     | 171197/371472 [2:41:38<16:46:39,  3.32it/s]
 46%|████▌     | 171198/371472 [2:41:38<17:01:34,  3.27it/s]
 46%|████▌     | 171199/371472 [2:41:39<18:11:18,  3.06it/s]
 46%|████▌     | 171200/371472 [2:41:39<17:05:29,  3.25it/s]
                                                            
{'loss': 2.9001, 'learning_rate': 5.854791096554547e-07, 'epoch': 7.37}
+
 46%|████▌     | 171200/371472 [2:41:39<17:05:29,  3.25it/s]
 46%|████▌     | 171201/371472 [2:41:39<16:45:09,  3.32it/s]
 46%|████▌     | 171202/371472 [2:41:39<16:30:41,  3.37it/s]
 46%|████▌     | 171203/371472 [2:41:40<16:33:07,  3.36it/s]
 46%|████▌     | 171204/371472 [2:41:40<16:49:33,  3.31it/s]
 46%|████▌     | 171205/371472 [2:41:40<16:18:35,  3.41it/s]
 46%|████▌     | 171206/371472 [2:41:41<16:31:17,  3.37it/s]
 46%|████▌     | 171207/371472 [2:41:41<16:20:17,  3.40it/s]
 46%|████▌     | 171208/371472 [2:41:41<16:57:51,  3.28it/s]
 46%|████▌     | 171209/371472 [2:41:42<18:26:20,  3.02it/s]
 46%|████▌     | 171210/371472 [2:41:42<18:40:07,  2.98it/s]
 46%|████▌     | 171211/371472 [2:41:42<18:11:34,  3.06it/s]
 46%|████▌     | 171212/371472 [2:41:43<17:46:00,  3.13it/s]
 46%|████▌     | 171213/371472 [2:41:43<18:04:41,  3.08it/s]
 46%|████▌     | 171214/371472 [2:41:43<17:42:57,  3.14it/s]
 46%|████▌     | 171215/371472 [2:41:44<17:19:38,  3.21it/s]
 46%|████▌     | 171216/371472 [2:41:44<16:42:36,  3.33it/s]
 46%|████▌     | 171217/371472 [2:41:44<16:26:27,  3.38it/s]
 46%|████▌     | 171218/371472 [2:41:44<16:19:32,  3.41it/s]
 46%|████▌     | 171219/371472 [2:41:45<15:45:50,  3.53it/s]
 46%|████▌     | 171220/371472 [2:41:45<16:28:31,  3.38it/s]
                                                            
{'loss': 2.7928, 'learning_rate': 5.854306276799759e-07, 'epoch': 7.37}
+
 46%|████▌     | 171220/371472 [2:41:45<16:28:31,  3.38it/s]
 46%|████▌     | 171221/371472 [2:41:45<16:31:30,  3.37it/s]
 46%|████▌     | 171222/371472 [2:41:46<16:27:45,  3.38it/s]
 46%|████▌     | 171223/371472 [2:41:46<16:16:48,  3.42it/s]
 46%|████▌     | 171224/371472 [2:41:46<16:08:14,  3.45it/s]
 46%|████▌     | 171225/371472 [2:41:46<15:50:31,  3.51it/s]
 46%|████▌     | 171226/371472 [2:41:47<16:01:00,  3.47it/s]
 46%|████▌     | 171227/371472 [2:41:47<17:02:10,  3.27it/s]
 46%|████▌     | 171228/371472 [2:41:47<17:00:26,  3.27it/s]
 46%|████▌     | 171229/371472 [2:41:48<17:03:26,  3.26it/s]
 46%|████▌     | 171230/371472 [2:41:48<17:41:33,  3.14it/s]
 46%|████▌     | 171231/371472 [2:41:48<18:36:08,  2.99it/s]
 46%|████▌     | 171232/371472 [2:41:49<18:15:03,  3.05it/s]
 46%|████▌     | 171233/371472 [2:41:49<17:34:56,  3.16it/s]
 46%|████▌     | 171234/371472 [2:41:49<17:03:00,  3.26it/s]
 46%|████▌     | 171235/371472 [2:41:50<16:38:57,  3.34it/s]
 46%|████▌     | 171236/371472 [2:41:50<16:41:39,  3.33it/s]
 46%|████▌     | 171237/371472 [2:41:50<16:44:54,  3.32it/s]
 46%|████▌     | 171238/371472 [2:41:50<16:09:12,  3.44it/s]
 46%|████▌     | 171239/371472 [2:41:51<17:20:40,  3.21it/s]
 46%|████▌     | 171240/371472 [2:41:51<17:03:57,  3.26it/s]
                                                            
{'loss': 2.8237, 'learning_rate': 5.85382145704497e-07, 'epoch': 7.38}
+
 46%|████▌     | 171240/371472 [2:41:51<17:03:57,  3.26it/s]
 46%|████▌     | 171241/371472 [2:41:51<16:38:07,  3.34it/s]
 46%|████▌     | 171242/371472 [2:41:52<15:55:44,  3.49it/s]
 46%|████▌     | 171243/371472 [2:41:52<15:50:03,  3.51it/s]
 46%|████▌     | 171244/371472 [2:41:52<15:59:04,  3.48it/s]
 46%|████▌     | 171245/371472 [2:41:53<17:17:05,  3.22it/s]
 46%|████▌     | 171246/371472 [2:41:53<17:16:25,  3.22it/s]
 46%|████▌     | 171247/371472 [2:41:53<16:39:30,  3.34it/s]
 46%|████▌     | 171248/371472 [2:41:53<16:34:08,  3.36it/s]
 46%|████▌     | 171249/371472 [2:41:54<16:37:24,  3.35it/s]
 46%|████▌     | 171250/371472 [2:41:54<16:36:29,  3.35it/s]
 46%|████▌     | 171251/371472 [2:41:54<16:47:12,  3.31it/s]
 46%|████▌     | 171252/371472 [2:41:55<18:28:35,  3.01it/s]
 46%|████▌     | 171253/371472 [2:41:55<17:57:49,  3.10it/s]
 46%|████▌     | 171254/371472 [2:41:55<17:16:36,  3.22it/s]
 46%|████▌     | 171255/371472 [2:41:56<17:14:22,  3.23it/s]
 46%|████▌     | 171256/371472 [2:41:56<17:08:36,  3.24it/s]
 46%|████▌     | 171257/371472 [2:41:56<17:28:28,  3.18it/s]
 46%|████▌     | 171258/371472 [2:41:57<16:54:58,  3.29it/s]
 46%|████▌     | 171259/371472 [2:41:57<16:40:16,  3.34it/s]
 46%|████▌     | 171260/371472 [2:41:57<16:29:26,  3.37it/s]
                                                            
{'loss': 3.0204, 'learning_rate': 5.85333663729018e-07, 'epoch': 7.38}
+
 46%|████▌     | 171260/371472 [2:41:57<16:29:26,  3.37it/s]
 46%|████▌     | 171261/371472 [2:41:57<16:35:47,  3.35it/s]
 46%|████▌     | 171262/371472 [2:41:58<16:56:56,  3.28it/s]
 46%|████▌     | 171263/371472 [2:41:58<22:24:06,  2.48it/s]
 46%|████▌     | 171264/371472 [2:41:59<21:07:51,  2.63it/s]
 46%|████▌     | 171265/371472 [2:41:59<19:53:59,  2.79it/s]
 46%|████▌     | 171266/371472 [2:41:59<18:47:13,  2.96it/s]
 46%|████▌     | 171267/371472 [2:42:00<18:07:19,  3.07it/s]
 46%|████▌     | 171268/371472 [2:42:00<17:33:58,  3.17it/s]
 46%|████▌     | 171269/371472 [2:42:00<17:13:04,  3.23it/s]
 46%|████▌     | 171270/371472 [2:42:00<16:51:25,  3.30it/s]
 46%|████▌     | 171271/371472 [2:42:01<17:07:33,  3.25it/s]
 46%|████▌     | 171272/371472 [2:42:01<16:54:38,  3.29it/s]
 46%|████▌     | 171273/371472 [2:42:01<16:54:44,  3.29it/s]
 46%|████▌     | 171274/371472 [2:42:02<16:56:25,  3.28it/s]
 46%|████▌     | 171275/371472 [2:42:02<18:59:43,  2.93it/s]
 46%|████▌     | 171276/371472 [2:42:03<19:26:09,  2.86it/s]
 46%|████▌     | 171277/371472 [2:42:03<19:28:01,  2.86it/s]
 46%|████▌     | 171278/371472 [2:42:03<19:40:37,  2.83it/s]
 46%|████▌     | 171279/371472 [2:42:04<18:39:49,  2.98it/s]
 46%|████▌     | 171280/371472 [2:42:04<17:48:53,  3.12it/s]
                                                            
{'loss': 3.0339, 'learning_rate': 5.852851817535391e-07, 'epoch': 7.38}
+
 46%|████▌     | 171280/371472 [2:42:04<17:48:53,  3.12it/s]
 46%|████▌     | 171281/371472 [2:42:04<17:16:10,  3.22it/s]
 46%|████▌     | 171282/371472 [2:42:04<17:13:24,  3.23it/s]
 46%|████▌     | 171283/371472 [2:42:05<16:45:57,  3.32it/s]
 46%|████▌     | 171284/371472 [2:42:05<16:26:40,  3.38it/s]
 46%|████▌     | 171285/371472 [2:42:05<17:20:42,  3.21it/s]
 46%|████▌     | 171286/371472 [2:42:06<17:43:33,  3.14it/s]
 46%|████▌     | 171287/371472 [2:42:06<17:08:13,  3.24it/s]
 46%|████▌     | 171288/371472 [2:42:06<18:14:57,  3.05it/s]
 46%|████▌     | 171289/371472 [2:42:07<17:22:10,  3.20it/s]
 46%|████▌     | 171290/371472 [2:42:07<17:49:23,  3.12it/s]
 46%|████▌     | 171291/371472 [2:42:07<18:07:03,  3.07it/s]
 46%|████▌     | 171292/371472 [2:42:08<17:54:29,  3.11it/s]
 46%|████▌     | 171293/371472 [2:42:08<17:26:11,  3.19it/s]
 46%|████▌     | 171294/371472 [2:42:08<17:03:58,  3.26it/s]
 46%|████▌     | 171295/371472 [2:42:08<17:25:08,  3.19it/s]
 46%|████▌     | 171296/371472 [2:42:09<17:15:09,  3.22it/s]
 46%|████▌     | 171297/371472 [2:42:09<17:34:43,  3.16it/s]
 46%|████▌     | 171298/371472 [2:42:09<17:04:07,  3.26it/s]
 46%|████▌     | 171299/371472 [2:42:10<16:33:21,  3.36it/s]
 46%|████▌     | 171300/371472 [2:42:10<16:21:03,  3.40it/s]
                                                            
{'loss': 2.8556, 'learning_rate': 5.852366997780603e-07, 'epoch': 7.38}
+
 46%|████▌     | 171300/371472 [2:42:10<16:21:03,  3.40it/s]
 46%|████▌     | 171301/371472 [2:42:10<16:11:05,  3.44it/s]
 46%|████▌     | 171302/371472 [2:42:11<15:47:53,  3.52it/s]
 46%|████▌     | 171303/371472 [2:42:11<16:03:38,  3.46it/s]
 46%|████▌     | 171304/371472 [2:42:11<15:50:33,  3.51it/s]
 46%|████▌     | 171305/371472 [2:42:11<15:51:25,  3.51it/s]
 46%|████▌     | 171306/371472 [2:42:12<15:25:23,  3.61it/s]
 46%|████▌     | 171307/371472 [2:42:12<15:46:19,  3.53it/s]
 46%|████▌     | 171308/371472 [2:42:12<15:58:20,  3.48it/s]
 46%|████▌     | 171309/371472 [2:42:13<16:01:42,  3.47it/s]
 46%|████▌     | 171310/371472 [2:42:13<15:45:19,  3.53it/s]
 46%|████▌     | 171311/371472 [2:42:13<16:36:52,  3.35it/s]
 46%|████▌     | 171312/371472 [2:42:13<16:26:52,  3.38it/s]
 46%|████▌     | 171313/371472 [2:42:14<16:29:09,  3.37it/s]
 46%|████▌     | 171314/371472 [2:42:14<16:54:14,  3.29it/s]
 46%|████▌     | 171315/371472 [2:42:14<16:37:58,  3.34it/s]
 46%|████▌     | 171316/371472 [2:42:15<17:31:07,  3.17it/s]
 46%|████▌     | 171317/371472 [2:42:15<17:16:19,  3.22it/s]
 46%|████▌     | 171318/371472 [2:42:15<16:54:34,  3.29it/s]
 46%|████▌     | 171319/371472 [2:42:16<16:44:50,  3.32it/s]
 46%|████▌     | 171320/371472 [2:42:16<16:33:16,  3.36it/s]
                                                            
{'loss': 3.0505, 'learning_rate': 5.851882178025814e-07, 'epoch': 7.38}
+
 46%|████▌     | 171320/371472 [2:42:16<16:33:16,  3.36it/s]
 46%|████▌     | 171321/371472 [2:42:16<16:31:43,  3.36it/s]
 46%|████▌     | 171322/371472 [2:42:17<17:24:10,  3.19it/s]
 46%|████▌     | 171323/371472 [2:42:17<17:47:50,  3.12it/s]
 46%|████▌     | 171324/371472 [2:42:17<17:00:42,  3.27it/s]
 46%|████▌     | 171325/371472 [2:42:17<16:45:50,  3.32it/s]
 46%|████▌     | 171326/371472 [2:42:18<17:04:33,  3.26it/s]
 46%|████▌     | 171327/371472 [2:42:18<17:00:42,  3.27it/s]
 46%|████▌     | 171328/371472 [2:42:18<17:21:53,  3.20it/s]
 46%|████▌     | 171329/371472 [2:42:19<17:01:48,  3.26it/s]
 46%|████▌     | 171330/371472 [2:42:19<16:38:16,  3.34it/s]
 46%|████▌     | 171331/371472 [2:42:19<18:49:12,  2.95it/s]
 46%|████▌     | 171332/371472 [2:42:20<19:23:27,  2.87it/s]
 46%|████▌     | 171333/371472 [2:42:20<19:26:42,  2.86it/s]
 46%|████▌     | 171334/371472 [2:42:20<18:24:30,  3.02it/s]
 46%|████▌     | 171335/371472 [2:42:21<22:15:25,  2.50it/s]
 46%|████▌     | 171336/371472 [2:42:21<20:42:44,  2.68it/s]
 46%|████▌     | 171337/371472 [2:42:22<19:17:08,  2.88it/s]
 46%|████▌     | 171338/371472 [2:42:22<18:08:30,  3.06it/s]
 46%|████▌     | 171339/371472 [2:42:22<17:18:01,  3.21it/s]
 46%|████▌     | 171340/371472 [2:42:22<16:40:32,  3.33it/s]
                                                            
{'loss': 2.7923, 'learning_rate': 5.851397358271024e-07, 'epoch': 7.38}
+
 46%|████▌     | 171340/371472 [2:42:22<16:40:32,  3.33it/s]
 46%|████▌     | 171341/371472 [2:42:23<16:27:53,  3.38it/s]
 46%|████▌     | 171342/371472 [2:42:23<16:25:44,  3.38it/s]
 46%|████▌     | 171343/371472 [2:42:23<16:09:02,  3.44it/s]
 46%|████▌     | 171344/371472 [2:42:23<15:51:24,  3.51it/s]
 46%|████▌     | 171345/371472 [2:42:24<15:36:29,  3.56it/s]
 46%|████▌     | 171346/371472 [2:42:24<16:13:36,  3.43it/s]
 46%|████▌     | 171347/371472 [2:42:24<15:55:29,  3.49it/s]
 46%|████▌     | 171348/371472 [2:42:25<16:17:24,  3.41it/s]
 46%|████▌     | 171349/371472 [2:42:25<16:29:13,  3.37it/s]
 46%|████▌     | 171350/371472 [2:42:25<16:16:13,  3.42it/s]
 46%|████▌     | 171351/371472 [2:42:26<16:13:30,  3.43it/s]
 46%|████▌     | 171352/371472 [2:42:26<17:04:13,  3.26it/s]
 46%|████▌     | 171353/371472 [2:42:26<18:00:34,  3.09it/s]
 46%|████▌     | 171354/371472 [2:42:27<18:08:29,  3.06it/s]
 46%|████▌     | 171355/371472 [2:42:27<18:06:16,  3.07it/s]
 46%|████▌     | 171356/371472 [2:42:27<17:42:53,  3.14it/s]
 46%|████▌     | 171357/371472 [2:42:28<17:50:57,  3.11it/s]
 46%|████▌     | 171358/371472 [2:42:28<17:06:30,  3.25it/s]
 46%|████▌     | 171359/371472 [2:42:28<16:30:58,  3.37it/s]
 46%|████▌     | 171360/371472 [2:42:28<16:25:18,  3.38it/s]
                                                            
{'loss': 3.0507, 'learning_rate': 5.850912538516236e-07, 'epoch': 7.38}
+
 46%|████▌     | 171360/371472 [2:42:28<16:25:18,  3.38it/s]
 46%|████▌     | 171361/371472 [2:42:29<16:14:26,  3.42it/s]
 46%|████▌     | 171362/371472 [2:42:29<15:52:35,  3.50it/s]
 46%|████▌     | 171363/371472 [2:42:29<16:11:06,  3.43it/s]
 46%|████▌     | 171364/371472 [2:42:30<16:09:41,  3.44it/s]
 46%|████▌     | 171365/371472 [2:42:30<15:54:44,  3.49it/s]
 46%|████▌     | 171366/371472 [2:42:30<16:05:26,  3.45it/s]
 46%|████▌     | 171367/371472 [2:42:30<15:54:06,  3.50it/s]
 46%|████▌     | 171368/371472 [2:42:31<16:08:33,  3.44it/s]
 46%|████▌     | 171369/371472 [2:42:31<15:58:55,  3.48it/s]
 46%|████▌     | 171370/371472 [2:42:31<16:42:37,  3.33it/s]
 46%|████▌     | 171371/371472 [2:42:32<16:27:06,  3.38it/s]
 46%|████▌     | 171372/371472 [2:42:32<16:16:53,  3.41it/s]
 46%|████▌     | 171373/371472 [2:42:32<16:30:12,  3.37it/s]
 46%|████▌     | 171374/371472 [2:42:32<16:17:29,  3.41it/s]
 46%|████▌     | 171375/371472 [2:42:33<16:22:46,  3.39it/s]
 46%|████▌     | 171376/371472 [2:42:33<16:13:35,  3.43it/s]
 46%|████▌     | 171377/371472 [2:42:33<16:22:13,  3.40it/s]
 46%|████▌     | 171378/371472 [2:42:34<16:21:24,  3.40it/s]
 46%|████▌     | 171379/371472 [2:42:34<17:13:27,  3.23it/s]
 46%|████▌     | 171380/371472 [2:42:34<17:23:15,  3.20it/s]
                                                            
{'loss': 3.1366, 'learning_rate': 5.850427718761448e-07, 'epoch': 7.38}
+
 46%|████▌     | 171380/371472 [2:42:34<17:23:15,  3.20it/s]
 46%|████▌     | 171381/371472 [2:42:35<17:12:05,  3.23it/s]
 46%|████▌     | 171382/371472 [2:42:35<16:56:09,  3.28it/s]
 46%|████▌     | 171383/371472 [2:42:35<17:04:39,  3.25it/s]
 46%|████▌     | 171384/371472 [2:42:36<17:31:29,  3.17it/s]
 46%|████▌     | 171385/371472 [2:42:36<17:17:12,  3.22it/s]
 46%|████▌     | 171386/371472 [2:42:36<17:10:06,  3.24it/s]
 46%|████▌     | 171387/371472 [2:42:36<17:05:19,  3.25it/s]
 46%|████▌     | 171388/371472 [2:42:37<16:42:33,  3.33it/s]
 46%|████▌     | 171389/371472 [2:42:37<16:45:51,  3.32it/s]
 46%|████▌     | 171390/371472 [2:42:37<18:22:55,  3.02it/s]
 46%|████▌     | 171391/371472 [2:42:38<17:28:07,  3.18it/s]
 46%|████▌     | 171392/371472 [2:42:38<17:28:41,  3.18it/s]
 46%|████▌     | 171393/371472 [2:42:38<17:30:43,  3.17it/s]
 46%|████▌     | 171394/371472 [2:42:39<17:13:22,  3.23it/s]
 46%|████▌     | 171395/371472 [2:42:39<17:08:28,  3.24it/s]
 46%|████▌     | 171396/371472 [2:42:39<17:12:54,  3.23it/s]
 46%|████▌     | 171397/371472 [2:42:40<17:10:16,  3.24it/s]
 46%|████▌     | 171398/371472 [2:42:40<17:27:17,  3.18it/s]
 46%|████▌     | 171399/371472 [2:42:40<17:02:53,  3.26it/s]
 46%|████▌     | 171400/371472 [2:42:40<16:34:25,  3.35it/s]
                                                            
{'loss': 3.0351, 'learning_rate': 5.849942899006657e-07, 'epoch': 7.38}
+
 46%|████▌     | 171400/371472 [2:42:40<16:34:25,  3.35it/s]
 46%|████▌     | 171401/371472 [2:42:41<16:18:26,  3.41it/s]
 46%|████▌     | 171402/371472 [2:42:41<16:08:28,  3.44it/s]
 46%|████▌     | 171403/371472 [2:42:41<16:01:05,  3.47it/s]
 46%|████▌     | 171404/371472 [2:42:42<16:20:46,  3.40it/s]
 46%|████▌     | 171405/371472 [2:42:42<17:56:57,  3.10it/s]
 46%|████▌     | 171406/371472 [2:42:42<17:17:19,  3.21it/s]
 46%|████▌     | 171407/371472 [2:42:43<17:32:09,  3.17it/s]
 46%|████▌     | 171408/371472 [2:42:43<17:21:14,  3.20it/s]
 46%|████▌     | 171409/371472 [2:42:43<17:13:49,  3.23it/s]
 46%|████▌     | 171410/371472 [2:42:43<16:31:41,  3.36it/s]
 46%|████▌     | 171411/371472 [2:42:44<16:22:36,  3.39it/s]
 46%|████▌     | 171412/371472 [2:42:44<16:28:52,  3.37it/s]
 46%|████▌     | 171413/371472 [2:42:44<16:26:21,  3.38it/s]
 46%|██��█▌     | 171414/371472 [2:42:45<16:11:07,  3.43it/s]
 46%|████▌     | 171415/371472 [2:42:45<16:34:04,  3.35it/s]
 46%|████▌     | 171416/371472 [2:42:45<16:33:56,  3.35it/s]
 46%|████▌     | 171417/371472 [2:42:46<16:17:51,  3.41it/s]
 46%|████▌     | 171418/371472 [2:42:46<15:53:21,  3.50it/s]
 46%|████▌     | 171419/371472 [2:42:46<15:54:34,  3.49it/s]
 46%|████▌     | 171420/371472 [2:42:46<15:45:41,  3.53it/s]
                                                            
{'loss': 3.0174, 'learning_rate': 5.849458079251868e-07, 'epoch': 7.38}
+
 46%|████▌     | 171420/371472 [2:42:46<15:45:41,  3.53it/s]
 46%|████▌     | 171421/371472 [2:42:47<16:00:02,  3.47it/s]
 46%|████▌     | 171422/371472 [2:42:47<16:06:00,  3.45it/s]
 46%|████▌     | 171423/371472 [2:42:47<16:08:18,  3.44it/s]
 46%|████▌     | 171424/371472 [2:42:48<16:16:52,  3.41it/s]
 46%|████▌     | 171425/371472 [2:42:48<17:42:50,  3.14it/s]
 46%|████▌     | 171426/371472 [2:42:48<17:07:25,  3.25it/s]
 46%|████▌     | 171427/371472 [2:42:49<16:58:02,  3.27it/s]
 46%|████▌     | 171428/371472 [2:42:49<16:11:00,  3.43it/s]
 46%|████▌     | 171429/371472 [2:42:49<16:10:18,  3.44it/s]
 46%|████▌     | 171430/371472 [2:42:49<16:04:09,  3.46it/s]
 46%|████▌     | 171431/371472 [2:42:50<16:23:42,  3.39it/s]
 46%|████▌     | 171432/371472 [2:42:50<16:01:42,  3.47it/s]
 46%|████▌     | 171433/371472 [2:42:50<16:50:48,  3.30it/s]
 46%|████▌     | 171434/371472 [2:42:51<16:19:49,  3.40it/s]
 46%|████▌     | 171435/371472 [2:42:51<16:18:51,  3.41it/s]
 46%|████▌     | 171436/371472 [2:42:51<15:58:33,  3.48it/s]
 46%|████▌     | 171437/371472 [2:42:51<16:01:42,  3.47it/s]
 46%|████▌     | 171438/371472 [2:42:52<16:09:49,  3.44it/s]
 46%|████▌     | 171439/371472 [2:42:52<17:30:02,  3.18it/s]
 46%|████▌     | 171440/371472 [2:42:52<17:30:37,  3.17it/s]
                                                            
{'loss': 2.9193, 'learning_rate': 5.84897325949708e-07, 'epoch': 7.38}
+
 46%|████▌     | 171440/371472 [2:42:52<17:30:37,  3.17it/s]
 46%|████▌     | 171441/371472 [2:42:53<16:56:27,  3.28it/s]
 46%|████▌     | 171442/371472 [2:42:53<16:52:25,  3.29it/s]
 46%|████▌     | 171443/371472 [2:42:53<16:27:14,  3.38it/s]
 46%|████▌     | 171444/371472 [2:42:54<16:31:54,  3.36it/s]
 46%|████▌     | 171445/371472 [2:42:54<16:51:11,  3.30it/s]
 46%|████▌     | 171446/371472 [2:42:54<16:40:07,  3.33it/s]
 46%|████▌     | 171447/371472 [2:42:54<16:59:59,  3.27it/s]
 46%|████▌     | 171448/371472 [2:42:55<18:04:26,  3.07it/s]
 46%|████▌     | 171449/371472 [2:42:55<17:15:08,  3.22it/s]
 46%|████▌     | 171450/371472 [2:42:55<16:43:17,  3.32it/s]
 46%|████▌     | 171451/371472 [2:42:56<16:47:52,  3.31it/s]
 46%|████▌     | 171452/371472 [2:42:56<16:33:07,  3.36it/s]
 46%|████▌     | 171453/371472 [2:42:56<18:01:17,  3.08it/s]
 46%|████▌     | 171454/371472 [2:42:57<17:57:02,  3.10it/s]
 46%|████▌     | 171455/371472 [2:42:57<17:22:54,  3.20it/s]
 46%|████▌     | 171456/371472 [2:42:57<16:41:12,  3.33it/s]
 46%|████▌     | 171457/371472 [2:42:58<19:54:23,  2.79it/s]
 46%|████▌     | 171458/371472 [2:42:58<19:37:45,  2.83it/s]
 46%|████▌     | 171459/371472 [2:42:58<18:37:21,  2.98it/s]
 46%|████▌     | 171460/371472 [2:42:59<17:53:00,  3.11it/s]
                                                            
{'loss': 2.993, 'learning_rate': 5.848488439742292e-07, 'epoch': 7.39}
+
 46%|████▌     | 171460/371472 [2:42:59<17:53:00,  3.11it/s]
 46%|████▌     | 171461/371472 [2:42:59<17:57:50,  3.09it/s]
 46%|████▌     | 171462/371472 [2:42:59<17:18:36,  3.21it/s]
 46%|████▌     | 171463/371472 [2:43:00<16:55:57,  3.28it/s]
 46%|████▌     | 171464/371472 [2:43:00<17:33:10,  3.17it/s]
 46%|████▌     | 171465/371472 [2:43:00<16:51:07,  3.30it/s]
 46%|████▌     | 171466/371472 [2:43:01<17:13:49,  3.22it/s]
 46%|████▌     | 171467/371472 [2:43:01<17:19:44,  3.21it/s]
 46%|████▌     | 171468/371472 [2:43:01<16:53:01,  3.29it/s]
 46%|████▌     | 171469/371472 [2:43:01<17:40:57,  3.14it/s]
 46%|████▌     | 171470/371472 [2:43:02<17:33:16,  3.16it/s]
 46%|████▌     | 171471/371472 [2:43:02<17:12:30,  3.23it/s]
 46%|████▌     | 171472/371472 [2:43:02<16:50:14,  3.30it/s]
 46%|████▌     | 171473/371472 [2:43:03<16:44:20,  3.32it/s]
 46%|████▌     | 171474/371472 [2:43:03<16:26:33,  3.38it/s]
 46%|████▌     | 171475/371472 [2:43:03<16:36:10,  3.35it/s]
 46%|████▌     | 171476/371472 [2:43:04<16:25:13,  3.38it/s]
 46%|████▌     | 171477/371472 [2:43:04<17:06:32,  3.25it/s]
 46%|████▌     | 171478/371472 [2:43:04<16:58:07,  3.27it/s]
 46%|████▌     | 171479/371472 [2:43:04<17:00:13,  3.27it/s]
 46%|████▌     | 171480/371472 [2:43:05<17:06:38,  3.25it/s]
                                                            
{'loss': 2.8399, 'learning_rate': 5.848003619987502e-07, 'epoch': 7.39}
+
 46%|████▌     | 171480/371472 [2:43:05<17:06:38,  3.25it/s]
 46%|████▌     | 171481/371472 [2:43:05<18:57:43,  2.93it/s]
 46%|████▌     | 171482/371472 [2:43:06<18:31:30,  3.00it/s]
 46%|████▌     | 171483/371472 [2:43:06<18:07:44,  3.06it/s]
 46%|████▌     | 171484/371472 [2:43:06<17:30:23,  3.17it/s]
 46%|████▌     | 171485/371472 [2:43:06<17:01:24,  3.26it/s]
 46%|████▌     | 171486/371472 [2:43:07<17:01:23,  3.26it/s]
 46%|████▌     | 171487/371472 [2:43:07<16:38:06,  3.34it/s]
 46%|████▌     | 171488/371472 [2:43:07<16:31:14,  3.36it/s]
 46%|████▌     | 171489/371472 [2:43:08<16:43:08,  3.32it/s]
 46%|████▌     | 171490/371472 [2:43:08<16:39:30,  3.33it/s]
 46%|████▌     | 171491/371472 [2:43:08<16:30:25,  3.37it/s]
 46%|████▌     | 171492/371472 [2:43:08<16:29:42,  3.37it/s]
 46%|████▌     | 171493/371472 [2:43:09<17:04:50,  3.25it/s]
 46%|████▌     | 171494/371472 [2:43:09<16:49:11,  3.30it/s]
 46%|████▌     | 171495/371472 [2:43:09<17:09:44,  3.24it/s]
 46%|████▌     | 171496/371472 [2:43:10<16:58:42,  3.27it/s]
 46%|████▌     | 171497/371472 [2:43:10<16:48:38,  3.30it/s]
 46%|████▌     | 171498/371472 [2:43:10<16:47:22,  3.31it/s]
 46%|████▌     | 171499/371472 [2:43:11<16:43:24,  3.32it/s]
 46%|████▌     | 171500/371472 [2:43:11<16:39:02,  3.34it/s]
                                                            
{'loss': 2.8423, 'learning_rate': 5.847518800232713e-07, 'epoch': 7.39}
+
 46%|████▌     | 171500/371472 [2:43:11<16:39:02,  3.34it/s]
 46%|████▌     | 171501/371472 [2:43:11<17:08:41,  3.24it/s]
 46%|████▌     | 171502/371472 [2:43:12<16:43:01,  3.32it/s]
 46%|████▌     | 171503/371472 [2:43:12<16:32:41,  3.36it/s]
 46%|████▌     | 171504/371472 [2:43:12<16:13:28,  3.42it/s]
 46%|████▌     | 171505/371472 [2:43:12<16:32:17,  3.36it/s]
 46%|████▌     | 171506/371472 [2:43:13<17:05:53,  3.25it/s]
 46%|████▌     | 171507/371472 [2:43:13<17:08:37,  3.24it/s]
 46%|████▌     | 171508/371472 [2:43:13<16:50:38,  3.30it/s]
 46%|████▌     | 171509/371472 [2:43:14<16:24:07,  3.39it/s]
 46%|████▌     | 171510/371472 [2:43:14<16:19:00,  3.40it/s]
 46%|████▌     | 171511/371472 [2:43:14<16:15:45,  3.42it/s]
 46%|████▌     | 171512/371472 [2:43:15<16:34:56,  3.35it/s]
 46%|████▌     | 171513/371472 [2:43:15<16:21:34,  3.40it/s]
 46%|████▌     | 171514/371472 [2:43:15<16:13:10,  3.42it/s]
 46%|████▌     | 171515/371472 [2:43:15<16:27:16,  3.38it/s]
 46%|████▌     | 171516/371472 [2:43:16<16:30:51,  3.36it/s]
 46%|████▌     | 171517/371472 [2:43:16<16:26:31,  3.38it/s]
 46%|████▌     | 171518/371472 [2:43:16<16:44:04,  3.32it/s]
 46%|████▌     | 171519/371472 [2:43:17<16:36:56,  3.34it/s]
 46%|████▌     | 171520/371472 [2:43:17<16:35:17,  3.35it/s]
                                                            
{'loss': 2.953, 'learning_rate': 5.847033980477924e-07, 'epoch': 7.39}
+
 46%|████▌     | 171520/371472 [2:43:17<16:35:17,  3.35it/s]
 46%|████▌     | 171521/371472 [2:43:17<16:28:03,  3.37it/s]
 46%|████▌     | 171522/371472 [2:43:18<16:50:54,  3.30it/s]
 46%|████▌     | 171523/371472 [2:43:18<17:08:06,  3.24it/s]
 46%|████▌     | 171524/371472 [2:43:18<18:18:18,  3.03it/s]
 46%|████▌     | 171525/371472 [2:43:18<17:28:53,  3.18it/s]
 46%|████▌     | 171526/371472 [2:43:19<17:22:28,  3.20it/s]
 46%|████▌     | 171527/371472 [2:43:19<16:46:21,  3.31it/s]
 46%|████▌     | 171528/371472 [2:43:19<16:36:41,  3.34it/s]
 46%|████▌     | 171529/371472 [2:43:20<16:21:01,  3.40it/s]
 46%|████▌     | 171530/371472 [2:43:20<16:25:16,  3.38it/s]
 46%|████▌     | 171531/371472 [2:43:20<16:30:30,  3.36it/s]
 46%|████▌     | 171532/371472 [2:43:21<16:53:41,  3.29it/s]
 46%|████▌     | 171533/371472 [2:43:21<16:48:45,  3.30it/s]
 46%|████▌     | 171534/371472 [2:43:21<16:39:01,  3.34it/s]
 46%|████▌     | 171535/371472 [2:43:21<16:17:29,  3.41it/s]
 46%|████▌     | 171536/371472 [2:43:22<16:48:32,  3.30it/s]
 46%|████▌     | 171537/371472 [2:43:22<16:46:09,  3.31it/s]
 46%|████▌     | 171538/371472 [2:43:22<16:24:32,  3.38it/s]
 46%|████▌     | 171539/371472 [2:43:23<16:46:11,  3.31it/s]
 46%|████▌     | 171540/371472 [2:43:23<16:17:04,  3.41it/s]
                                                            
{'loss': 2.8429, 'learning_rate': 5.846549160723136e-07, 'epoch': 7.39}
+
 46%|████▌     | 171540/371472 [2:43:23<16:17:04,  3.41it/s]
 46%|████▌     | 171541/371472 [2:43:23<16:17:21,  3.41it/s]
 46%|████▌     | 171542/371472 [2:43:24<16:20:30,  3.40it/s]
 46%|████▌     | 171543/371472 [2:43:24<16:23:54,  3.39it/s]
 46%|████▌     | 171544/371472 [2:43:24<16:34:44,  3.35it/s]
 46%|████▌     | 171545/371472 [2:43:24<17:07:02,  3.24it/s]
 46%|████▌     | 171546/371472 [2:43:25<16:41:14,  3.33it/s]
 46%|████▌     | 171547/371472 [2:43:25<16:33:09,  3.36it/s]
 46%|████▌     | 171548/371472 [2:43:25<16:26:48,  3.38it/s]
 46%|████▌     | 171549/371472 [2:43:26<16:02:19,  3.46it/s]
 46%|████▌     | 171550/371472 [2:43:26<16:21:32,  3.39it/s]
 46%|████▌     | 171551/371472 [2:43:26<16:43:56,  3.32it/s]
 46%|████▌     | 171552/371472 [2:43:26<16:07:16,  3.44it/s]
 46%|████▌     | 171553/371472 [2:43:27<16:06:37,  3.45it/s]
 46%|████▌     | 171554/371472 [2:43:27<16:26:03,  3.38it/s]
 46%|████▌     | 171555/371472 [2:43:27<16:05:45,  3.45it/s]
 46%|████▌     | 171556/371472 [2:43:28<16:26:29,  3.38it/s]
 46%|████▌     | 171557/371472 [2:43:28<16:41:33,  3.33it/s]
 46%|████▌     | 171558/371472 [2:43:28<16:36:59,  3.34it/s]
 46%|████▌     | 171559/371472 [2:43:29<16:43:59,  3.32it/s]
 46%|████▌     | 171560/371472 [2:43:29<16:10:36,  3.43it/s]
                                                            
{'loss': 2.9913, 'learning_rate': 5.846064340968346e-07, 'epoch': 7.39}
+
 46%|████▌     | 171560/371472 [2:43:29<16:10:36,  3.43it/s]
 46%|████▌     | 171561/371472 [2:43:29<16:42:00,  3.33it/s]
 46%|████▌     | 171562/371472 [2:43:29<16:41:26,  3.33it/s]
 46%|████▌     | 171563/371472 [2:43:30<16:20:48,  3.40it/s]
 46%|████▌     | 171564/371472 [2:43:30<15:55:01,  3.49it/s]
 46%|████▌     | 171565/371472 [2:43:30<16:12:55,  3.42it/s]
 46%|████▌     | 171566/371472 [2:43:31<15:58:21,  3.48it/s]
 46%|████▌     | 171567/371472 [2:43:31<16:51:38,  3.29it/s]
 46%|████▌     | 171568/371472 [2:43:31<16:50:36,  3.30it/s]
 46%|████▌     | 171569/371472 [2:43:32<16:47:59,  3.31it/s]
 46%|████▌     | 171570/371472 [2:43:32<16:50:53,  3.30it/s]
 46%|████▌     | 171571/371472 [2:43:32<17:52:09,  3.11it/s]
 46%|████▌     | 171572/371472 [2:43:33<18:32:25,  2.99it/s]
 46%|████▌     | 171573/371472 [2:43:33<17:52:17,  3.11it/s]
 46%|████▌     | 171574/371472 [2:43:33<17:16:57,  3.21it/s]
 46%|████▌     | 171575/371472 [2:43:33<16:58:15,  3.27it/s]
 46%|████▌     | 171576/371472 [2:43:34<16:22:47,  3.39it/s]
 46%|████▌     | 171577/371472 [2:43:34<15:59:31,  3.47it/s]
 46%|████▌     | 171578/371472 [2:43:34<15:58:30,  3.48it/s]
 46%|████▌     | 171579/371472 [2:43:35<15:53:35,  3.49it/s]
 46%|████▌     | 171580/371472 [2:43:35<16:25:40,  3.38it/s]
                                                            
{'loss': 2.9053, 'learning_rate': 5.845579521213557e-07, 'epoch': 7.39}
+
 46%|████▌     | 171580/371472 [2:43:35<16:25:40,  3.38it/s]
 46%|████▌     | 171581/371472 [2:43:35<17:03:08,  3.26it/s]
 46%|████▌     | 171582/371472 [2:43:36<17:02:35,  3.26it/s]
 46%|████▌     | 171583/371472 [2:43:36<16:40:13,  3.33it/s]
 46%|████▌     | 171584/371472 [2:43:36<16:49:18,  3.30it/s]
 46%|████▌     | 171585/371472 [2:43:36<17:24:40,  3.19it/s]
 46%|████▌     | 171586/371472 [2:43:37<17:12:56,  3.23it/s]
 46%|████▌     | 171587/371472 [2:43:37<17:50:02,  3.11it/s]
 46%|████▌     | 171588/371472 [2:43:38<18:55:20,  2.93it/s]
 46%|████▌     | 171589/371472 [2:43:38<18:11:15,  3.05it/s]
 46%|████▌     | 171590/371472 [2:43:38<17:45:01,  3.13it/s]
 46%|████▌     | 171591/371472 [2:43:38<17:51:08,  3.11it/s]
 46%|████▌     | 171592/371472 [2:43:39<17:40:33,  3.14it/s]
 46%|████▌     | 171593/371472 [2:43:39<17:12:39,  3.23it/s]
 46%|████▌     | 171594/371472 [2:43:39<17:24:09,  3.19it/s]
 46%|████▌     | 171595/371472 [2:43:40<17:22:59,  3.19it/s]
 46%|████▌     | 171596/371472 [2:43:40<16:39:23,  3.33it/s]
 46%|████▌     | 171597/371472 [2:43:40<16:15:39,  3.41it/s]
 46%|████▌     | 171598/371472 [2:43:41<16:21:52,  3.39it/s]
 46%|████▌     | 171599/371472 [2:43:41<15:56:40,  3.48it/s]
 46%|████▌     | 171600/371472 [2:43:41<15:49:46,  3.51it/s]
                                                            
{'loss': 2.9369, 'learning_rate': 5.845094701458769e-07, 'epoch': 7.39}
+
 46%|████▌     | 171600/371472 [2:43:41<15:49:46,  3.51it/s]
 46%|████▌     | 171601/371472 [2:43:41<15:57:50,  3.48it/s]
 46%|████▌     | 171602/371472 [2:43:42<15:51:02,  3.50it/s]
 46%|████▌     | 171603/371472 [2:43:42<16:00:21,  3.47it/s]
 46%|████▌     | 171604/371472 [2:43:42<15:55:49,  3.49it/s]
 46%|████▌     | 171605/371472 [2:43:43<16:12:49,  3.42it/s]
 46%|████▌     | 171606/371472 [2:43:43<16:09:31,  3.44it/s]
 46%|████▌     | 171607/371472 [2:43:43<16:06:12,  3.45it/s]
 46%|████▌     | 171608/371472 [2:43:43<16:10:52,  3.43it/s]
 46%|████▌     | 171609/371472 [2:43:44<16:28:49,  3.37it/s]
 46%|████▌     | 171610/371472 [2:43:44<16:48:59,  3.30it/s]
 46%|████▌     | 171611/371472 [2:43:44<17:15:03,  3.22it/s]
 46%|████▌     | 171612/371472 [2:43:45<17:38:57,  3.15it/s]
 46%|████▌     | 171613/371472 [2:43:45<16:55:56,  3.28it/s]
 46%|████▌     | 171614/371472 [2:43:45<17:22:29,  3.20it/s]
 46%|████▌     | 171615/371472 [2:43:46<16:50:18,  3.30it/s]
 46%|████▌     | 171616/371472 [2:43:46<18:08:01,  3.06it/s]
 46%|████▌     | 171617/371472 [2:43:46<18:20:35,  3.03it/s]
 46%|████▌     | 171618/371472 [2:43:47<17:44:48,  3.13it/s]
 46%|████▌     | 171619/371472 [2:43:47<17:15:01,  3.22it/s]
 46%|████▌     | 171620/371472 [2:43:47<16:47:33,  3.31it/s]
                                                            
{'loss': 2.8386, 'learning_rate': 5.844609881703981e-07, 'epoch': 7.39}
+
 46%|████▌     | 171620/371472 [2:43:47<16:47:33,  3.31it/s]
 46%|████▌     | 171621/371472 [2:43:47<17:19:18,  3.20it/s]
 46%|████▌     | 171622/371472 [2:43:48<16:52:28,  3.29it/s]
 46%|████▌     | 171623/371472 [2:43:48<17:34:51,  3.16it/s]
 46%|████▌     | 171624/371472 [2:43:48<17:02:04,  3.26it/s]
 46%|████▌     | 171625/371472 [2:43:49<16:47:09,  3.31it/s]
 46%|████▌     | 171626/371472 [2:43:49<16:13:45,  3.42it/s]
 46%|████▌     | 171627/371472 [2:43:49<17:07:26,  3.24it/s]
 46%|████▌     | 171628/371472 [2:43:50<16:44:54,  3.31it/s]
 46%|████▌     | 171629/371472 [2:43:50<16:35:18,  3.35it/s]
 46%|████▌     | 171630/371472 [2:43:50<16:54:39,  3.28it/s]
 46%|████▌     | 171631/371472 [2:43:51<17:40:49,  3.14it/s]
 46%|████▌     | 171632/371472 [2:43:51<17:06:03,  3.25it/s]
 46%|████▌     | 171633/371472 [2:43:51<17:18:09,  3.21it/s]
 46%|████▌     | 171634/371472 [2:43:51<16:51:40,  3.29it/s]
 46%|████▌     | 171635/371472 [2:43:52<17:15:48,  3.22it/s]
 46%|████▌     | 171636/371472 [2:43:52<17:12:31,  3.23it/s]
 46%|████▌     | 171637/371472 [2:43:52<17:03:05,  3.26it/s]
 46%|████▌     | 171638/371472 [2:43:53<16:55:56,  3.28it/s]
 46%|████▌     | 171639/371472 [2:43:53<16:36:23,  3.34it/s]
 46%|████▌     | 171640/371472 [2:43:53<17:58:27,  3.09it/s]
                                                            
{'loss': 2.8679, 'learning_rate': 5.84412506194919e-07, 'epoch': 7.39}
+
 46%|████▌     | 171640/371472 [2:43:53<17:58:27,  3.09it/s]
 46%|████▌     | 171641/371472 [2:43:54<17:15:59,  3.21it/s]
 46%|████▌     | 171642/371472 [2:43:54<16:41:50,  3.32it/s]
 46%|████▌     | 171643/371472 [2:43:54<16:12:55,  3.42it/s]
 46%|████▌     | 171644/371472 [2:43:54<16:34:56,  3.35it/s]
 46%|████▌     | 171645/371472 [2:43:55<16:39:00,  3.33it/s]
 46%|████▌     | 171646/371472 [2:43:55<18:46:09,  2.96it/s]
 46%|████▌     | 171647/371472 [2:43:56<18:18:13,  3.03it/s]
 46%|████▌     | 171648/371472 [2:43:56<18:06:52,  3.06it/s]
 46%|████▌     | 171649/371472 [2:43:56<17:29:03,  3.17it/s]
 46%|████▌     | 171650/371472 [2:43:56<17:16:18,  3.21it/s]
 46%|████▌     | 171651/371472 [2:43:57<17:02:45,  3.26it/s]
 46%|████▌     | 171652/371472 [2:43:57<16:34:05,  3.35it/s]
 46%|████▌     | 171653/371472 [2:43:57<16:45:32,  3.31it/s]
 46%|████▌     | 171654/371472 [2:43:58<16:57:07,  3.27it/s]
 46%|████▌     | 171655/371472 [2:43:58<16:30:43,  3.36it/s]
 46%|████▌     | 171656/371472 [2:43:58<16:43:04,  3.32it/s]
 46%|████▌     | 171657/371472 [2:43:59<16:30:59,  3.36it/s]
 46%|████▌     | 171658/371472 [2:43:59<16:00:09,  3.47it/s]
 46%|████▌     | 171659/371472 [2:43:59<17:14:17,  3.22it/s]
 46%|████▌     | 171660/371472 [2:43:59<16:41:52,  3.32it/s]
                                                            
{'loss': 2.7829, 'learning_rate': 5.843640242194401e-07, 'epoch': 7.39}
+
 46%|████▌     | 171660/371472 [2:43:59<16:41:52,  3.32it/s]
 46%|████▌     | 171661/371472 [2:44:00<17:20:47,  3.20it/s]
 46%|████▌     | 171662/371472 [2:44:00<16:37:02,  3.34it/s]
 46%|████▌     | 171663/371472 [2:44:00<16:36:48,  3.34it/s]
 46%|████▌     | 171664/371472 [2:44:01<16:40:36,  3.33it/s]
 46%|████▌     | 171665/371472 [2:44:01<16:43:47,  3.32it/s]
 46%|████▌     | 171666/371472 [2:44:01<16:21:02,  3.39it/s]
 46%|████▌     | 171667/371472 [2:44:02<16:14:59,  3.42it/s]
 46%|████▌     | 171668/371472 [2:44:02<16:47:33,  3.31it/s]
 46%|████▌     | 171669/371472 [2:44:02<16:33:31,  3.35it/s]
 46%|████▌     | 171670/371472 [2:44:02<16:09:34,  3.43it/s]
 46%|████▌     | 171671/371472 [2:44:03<16:06:59,  3.44it/s]
 46%|████▌     | 171672/371472 [2:44:03<16:21:10,  3.39it/s]
 46%|████▌     | 171673/371472 [2:44:03<16:06:53,  3.44it/s]
 46%|████▌     | 171674/371472 [2:44:04<16:55:34,  3.28it/s]
 46%|████▌     | 171675/371472 [2:44:04<16:38:32,  3.33it/s]
 46%|████▌     | 171676/371472 [2:44:04<16:32:16,  3.36it/s]
 46%|████▌     | 171677/371472 [2:44:04<16:28:40,  3.37it/s]
 46%|████▌     | 171678/371472 [2:44:05<17:27:47,  3.18it/s]
 46%|████▌     | 171679/371472 [2:44:05<17:14:50,  3.22it/s]
 46%|████▌     | 171680/371472 [2:44:05<16:44:47,  3.31it/s]
                                                            
{'loss': 2.8549, 'learning_rate': 5.843155422439613e-07, 'epoch': 7.39}
+
 46%|████▌     | 171680/371472 [2:44:05<16:44:47,  3.31it/s]
 46%|████▌     | 171681/371472 [2:44:06<16:48:03,  3.30it/s]
 46%|████▌     | 171682/371472 [2:44:06<16:57:38,  3.27it/s]
 46%|████▌     | 171683/371472 [2:44:06<16:29:04,  3.37it/s]
 46%|████▌     | 171684/371472 [2:44:07<15:47:06,  3.52it/s]
 46%|████▌     | 171685/371472 [2:44:07<16:30:37,  3.36it/s]
 46%|████▌     | 171686/371472 [2:44:07<16:20:47,  3.39it/s]
 46%|████▌     | 171687/371472 [2:44:08<16:49:52,  3.30it/s]
 46%|████▌     | 171688/371472 [2:44:08<16:31:49,  3.36it/s]
 46%|████▌     | 171689/371472 [2:44:08<16:20:02,  3.40it/s]
 46%|████▌     | 171690/371472 [2:44:08<16:41:40,  3.32it/s]
 46%|████▌     | 171691/371472 [2:44:09<16:46:14,  3.31it/s]
 46%|████▌     | 171692/371472 [2:44:09<16:57:25,  3.27it/s]
 46%|████▌     | 171693/371472 [2:44:09<16:59:55,  3.26it/s]
 46%|████▌     | 171694/371472 [2:44:10<16:44:33,  3.31it/s]
 46%|████▌     | 171695/371472 [2:44:10<16:26:33,  3.37it/s]
 46%|████▌     | 171696/371472 [2:44:10<16:32:15,  3.36it/s]
 46%|████▌     | 171697/371472 [2:44:11<17:23:29,  3.19it/s]
 46%|████▌     | 171698/371472 [2:44:11<17:14:31,  3.22it/s]
 46%|████▌     | 171699/371472 [2:44:11<16:34:39,  3.35it/s]
 46%|████▌     | 171700/371472 [2:44:11<16:15:48,  3.41it/s]
                                                            
{'loss': 2.8714, 'learning_rate': 5.842670602684825e-07, 'epoch': 7.4}
+
 46%|████▌     | 171700/371472 [2:44:11<16:15:48,  3.41it/s]
 46%|████▌     | 171701/371472 [2:44:12<16:21:36,  3.39it/s]
 46%|████▌     | 171702/371472 [2:44:12<16:49:48,  3.30it/s]
 46%|████▌     | 171703/371472 [2:44:12<16:22:31,  3.39it/s]
 46%|████▌     | 171704/371472 [2:44:13<16:03:00,  3.46it/s]
 46%|████▌     | 171705/371472 [2:44:13<16:32:46,  3.35it/s]
 46%|████▌     | 171706/371472 [2:44:13<16:15:43,  3.41it/s]
 46%|████▌     | 171707/371472 [2:44:14<16:49:07,  3.30it/s]
 46%|████▌     | 171708/371472 [2:44:14<17:01:05,  3.26it/s]
 46%|████▌     | 171709/371472 [2:44:14<18:24:40,  3.01it/s]
 46%|████▌     | 171710/371472 [2:44:14<17:38:44,  3.14it/s]
 46%|████▌     | 171711/371472 [2:44:15<17:10:48,  3.23it/s]
 46%|████▌     | 171712/371472 [2:44:15<17:00:44,  3.26it/s]
 46%|████▌     | 171713/371472 [2:44:15<16:38:05,  3.34it/s]
 46%|████▌     | 171714/371472 [2:44:16<16:31:55,  3.36it/s]
 46%|████▌     | 171715/371472 [2:44:16<16:29:33,  3.36it/s]
 46%|████▌     | 171716/371472 [2:44:16<16:44:12,  3.32it/s]
 46%|████▌     | 171717/371472 [2:44:17<16:21:52,  3.39it/s]
 46%|████▌     | 171718/371472 [2:44:17<17:37:16,  3.15it/s]
 46%|████▌     | 171719/371472 [2:44:17<17:09:58,  3.23it/s]
 46%|████▌     | 171720/371472 [2:44:18<17:35:01,  3.16it/s]
                                                            
{'loss': 2.7525, 'learning_rate': 5.842185782930035e-07, 'epoch': 7.4}
+
 46%|████▌     | 171720/371472 [2:44:18<17:35:01,  3.16it/s]
 46%|████▌     | 171721/371472 [2:44:18<17:37:43,  3.15it/s]
 46%|████▌     | 171722/371472 [2:44:18<17:10:49,  3.23it/s]
 46%|████▌     | 171723/371472 [2:44:18<16:58:43,  3.27it/s]
 46%|████▌     | 171724/371472 [2:44:19<16:55:06,  3.28it/s]
 46%|████▌     | 171725/371472 [2:44:19<16:25:21,  3.38it/s]
 46%|████▌     | 171726/371472 [2:44:19<16:48:03,  3.30it/s]
 46%|████▌     | 171727/371472 [2:44:20<17:04:45,  3.25it/s]
 46%|████▌     | 171728/371472 [2:44:20<17:46:19,  3.12it/s]
 46%|████▌     | 171729/371472 [2:44:20<17:50:06,  3.11it/s]
 46%|████▌     | 171730/371472 [2:44:21<17:10:00,  3.23it/s]
 46%|████▌     | 171731/371472 [2:44:21<16:46:10,  3.31it/s]
 46%|████▌     | 171732/371472 [2:44:21<17:05:29,  3.25it/s]
 46%|████▌     | 171733/371472 [2:44:22<16:37:07,  3.34it/s]
 46%|████▌     | 171734/371472 [2:44:22<16:20:00,  3.40it/s]
 46%|████▌     | 171735/371472 [2:44:22<16:22:41,  3.39it/s]
 46%|████▌     | 171736/371472 [2:44:22<17:26:01,  3.18it/s]
 46%|████▌     | 171737/371472 [2:44:23<17:16:50,  3.21it/s]
 46%|████▌     | 171738/371472 [2:44:23<16:56:58,  3.27it/s]
 46%|████▌     | 171739/371472 [2:44:23<16:41:22,  3.32it/s]
 46%|████▌     | 171740/371472 [2:44:24<16:26:57,  3.37it/s]
                                                            
{'loss': 2.8591, 'learning_rate': 5.841700963175246e-07, 'epoch': 7.4}
+
 46%|████▌     | 171740/371472 [2:44:24<16:26:57,  3.37it/s]
 46%|████▌     | 171741/371472 [2:44:24<16:36:03,  3.34it/s]
 46%|████▌     | 171742/371472 [2:44:24<16:27:20,  3.37it/s]
 46%|████▌     | 171743/371472 [2:44:25<16:50:34,  3.29it/s]
 46%|████▌     | 171744/371472 [2:44:25<16:21:56,  3.39it/s]
 46%|████▌     | 171745/371472 [2:44:25<17:03:50,  3.25it/s]
 46%|████▌     | 171746/371472 [2:44:25<16:52:21,  3.29it/s]
 46%|████▌     | 171747/371472 [2:44:26<16:39:41,  3.33it/s]
 46%|████▌     | 171748/371472 [2:44:26<16:52:07,  3.29it/s]
 46%|████▌     | 171749/371472 [2:44:26<16:29:53,  3.36it/s]
 46%|████▌     | 171750/371472 [2:44:27<16:18:29,  3.40it/s]
 46%|████▌     | 171751/371472 [2:44:27<16:52:20,  3.29it/s]
 46%|████▌     | 171752/371472 [2:44:27<16:34:11,  3.35it/s]
 46%|████▌     | 171753/371472 [2:44:28<16:52:13,  3.29it/s]
 46%|████▌     | 171754/371472 [2:44:28<16:34:03,  3.35it/s]
 46%|████▌     | 171755/371472 [2:44:28<16:37:35,  3.34it/s]
 46%|████▌     | 171756/371472 [2:44:28<16:39:15,  3.33it/s]
 46%|████▌     | 171757/371472 [2:44:29<16:49:24,  3.30it/s]
 46%|████▌     | 171758/371472 [2:44:29<16:45:31,  3.31it/s]
 46%|████▌     | 171759/371472 [2:44:29<16:14:46,  3.41it/s]
 46%|████▌     | 171760/371472 [2:44:30<16:53:43,  3.28it/s]
                                                            
{'loss': 2.8466, 'learning_rate': 5.841216143420458e-07, 'epoch': 7.4}
+
 46%|████▌     | 171760/371472 [2:44:30<16:53:43,  3.28it/s]
 46%|████▌     | 171761/371472 [2:44:30<16:55:15,  3.28it/s]
 46%|████▌     | 171762/371472 [2:44:30<17:08:25,  3.24it/s]
 46%|████▌     | 171763/371472 [2:44:31<17:39:04,  3.14it/s]
 46%|████▌     | 171764/371472 [2:44:31<17:14:01,  3.22it/s]
 46%|████▌     | 171765/371472 [2:44:31<16:48:09,  3.30it/s]
 46%|████▌     | 171766/371472 [2:44:31<16:47:35,  3.30it/s]
 46%|████▌     | 171767/371472 [2:44:32<16:15:09,  3.41it/s]
 46%|████▌     | 171768/371472 [2:44:32<16:10:18,  3.43it/s]
 46%|████▌     | 171769/371472 [2:44:32<16:19:21,  3.40it/s]
 46%|████▌     | 171770/371472 [2:44:33<17:18:48,  3.20it/s]
 46%|████▌     | 171771/371472 [2:44:33<18:06:40,  3.06it/s]
 46%|████▌     | 171772/371472 [2:44:33<18:05:32,  3.07it/s]
 46%|████▌     | 171773/371472 [2:44:34<18:20:07,  3.03it/s]
 46%|████▌     | 171774/371472 [2:44:34<18:14:37,  3.04it/s]
 46%|████▌     | 171775/371472 [2:44:34<18:31:49,  2.99it/s]
 46%|████▌     | 171776/371472 [2:44:35<17:42:34,  3.13it/s]
 46%|████▌     | 171777/371472 [2:44:35<17:10:51,  3.23it/s]
 46%|████▌     | 171778/371472 [2:44:35<17:51:44,  3.11it/s]
 46%|████▌     | 171779/371472 [2:44:36<17:45:42,  3.12it/s]
 46%|████▌     | 171780/371472 [2:44:36<17:26:07,  3.18it/s]
                                                            
{'loss': 2.8126, 'learning_rate': 5.840731323665667e-07, 'epoch': 7.4}
+
 46%|████▌     | 171780/371472 [2:44:36<17:26:07,  3.18it/s]
 46%|████▌     | 171781/371472 [2:44:36<18:26:26,  3.01it/s]
 46%|████▌     | 171782/371472 [2:44:37<17:43:23,  3.13it/s]
 46%|████▌     | 171783/371472 [2:44:37<17:19:49,  3.20it/s]
 46%|████▌     | 171784/371472 [2:44:37<16:50:29,  3.29it/s]
 46%|████▌     | 171785/371472 [2:44:38<17:59:50,  3.08it/s]
 46%|████▌     | 171786/371472 [2:44:38<17:28:15,  3.17it/s]
 46%|████▌     | 171787/371472 [2:44:38<17:53:36,  3.10it/s]
 46%|████▌     | 171788/371472 [2:44:39<17:40:04,  3.14it/s]
 46%|████▌     | 171789/371472 [2:44:39<17:09:47,  3.23it/s]
 46%|████▌     | 171790/371472 [2:44:39<16:31:39,  3.36it/s]
 46%|████▌     | 171791/371472 [2:44:39<16:01:11,  3.46it/s]
 46%|████▌     | 171792/371472 [2:44:40<15:35:42,  3.56it/s]
 46%|████▌     | 171793/371472 [2:44:40<16:40:59,  3.32it/s]
 46%|████▌     | 171794/371472 [2:44:40<16:39:26,  3.33it/s]
 46%|████▌     | 171795/371472 [2:44:41<18:09:06,  3.06it/s]
 46%|████▌     | 171796/371472 [2:44:41<17:34:16,  3.16it/s]
 46%|████▌     | 171797/371472 [2:44:41<16:53:42,  3.28it/s]
 46%|████▌     | 171798/371472 [2:44:42<17:15:58,  3.21it/s]
 46%|████▌     | 171799/371472 [2:44:42<17:15:19,  3.21it/s]
 46%|████▌     | 171800/371472 [2:44:42<17:11:57,  3.22it/s]
                                                            
{'loss': 2.9123, 'learning_rate': 5.840246503910878e-07, 'epoch': 7.4}
+
 46%|████▌     | 171800/371472 [2:44:42<17:11:57,  3.22it/s]
 46%|████▌     | 171801/371472 [2:44:42<16:39:33,  3.33it/s]
 46%|████▌     | 171802/371472 [2:44:43<16:31:51,  3.36it/s]
 46%|████▌     | 171803/371472 [2:44:43<16:25:49,  3.38it/s]
 46%|████▌     | 171804/371472 [2:44:43<16:10:23,  3.43it/s]
 46%|████▌     | 171805/371472 [2:44:44<17:41:32,  3.13it/s]
 46%|████▋     | 171806/371472 [2:44:44<17:11:31,  3.23it/s]
 46%|████▋     | 171807/371472 [2:44:44<17:59:05,  3.08it/s]
 46%|████▋     | 171808/371472 [2:44:45<17:25:49,  3.18it/s]
 46%|████▋     | 171809/371472 [2:44:45<17:24:55,  3.18it/s]
 46%|████▋     | 171810/371472 [2:44:45<16:59:04,  3.27it/s]
 46%|████▋     | 171811/371472 [2:44:45<16:39:03,  3.33it/s]
 46%|████▋     | 171812/371472 [2:44:46<16:45:30,  3.31it/s]
 46%|████▋     | 171813/371472 [2:44:46<16:40:10,  3.33it/s]
 46%|████▋     | 171814/371472 [2:44:46<17:24:40,  3.19it/s]
 46%|████▋     | 171815/371472 [2:44:47<17:04:59,  3.25it/s]
 46%|████▋     | 171816/371472 [2:44:47<17:14:49,  3.22it/s]
 46%|████▋     | 171817/371472 [2:44:47<16:47:48,  3.30it/s]
 46%|████▋     | 171818/371472 [2:44:48<17:22:42,  3.19it/s]
 46%|████▋     | 171819/371472 [2:44:48<17:25:49,  3.18it/s]
 46%|████▋     | 171820/371472 [2:44:48<16:34:11,  3.35it/s]
                                                            
{'loss': 2.8722, 'learning_rate': 5.83976168415609e-07, 'epoch': 7.4}
+
 46%|████▋     | 171820/371472 [2:44:48<16:34:11,  3.35it/s]
 46%|████▋     | 171821/371472 [2:44:49<16:19:00,  3.40it/s]
 46%|████▋     | 171822/371472 [2:44:49<16:30:57,  3.36it/s]
 46%|████▋     | 171823/371472 [2:44:49<16:28:23,  3.37it/s]
 46%|████▋     | 171824/371472 [2:44:49<16:31:05,  3.36it/s]
 46%|████▋     | 171825/371472 [2:44:50<16:35:56,  3.34it/s]
 46%|████▋     | 171826/371472 [2:44:50<16:42:35,  3.32it/s]
 46%|████▋     | 171827/371472 [2:44:50<18:09:23,  3.05it/s]
 46%|████▋     | 171828/371472 [2:44:51<17:53:27,  3.10it/s]
 46%|████▋     | 171829/371472 [2:44:51<17:13:58,  3.22it/s]
 46%|████▋     | 171830/371472 [2:44:51<17:15:27,  3.21it/s]
 46%|████▋     | 171831/371472 [2:44:52<17:24:12,  3.19it/s]
 46%|████▋     | 171832/371472 [2:44:52<17:09:58,  3.23it/s]
 46%|████▋     | 171833/371472 [2:44:52<16:45:53,  3.31it/s]
 46%|████▋     | 171834/371472 [2:44:53<16:19:41,  3.40it/s]
 46%|████▋     | 171835/371472 [2:44:53<16:24:03,  3.38it/s]
 46%|████▋     | 171836/371472 [2:44:53<16:30:30,  3.36it/s]
 46%|████▋     | 171837/371472 [2:44:53<16:43:15,  3.32it/s]
 46%|████▋     | 171838/371472 [2:44:54<17:49:48,  3.11it/s]
 46%|████▋     | 171839/371472 [2:44:54<17:54:47,  3.10it/s]
 46%|████▋     | 171840/371472 [2:44:54<17:15:20,  3.21it/s]
                                                            
{'loss': 2.9351, 'learning_rate': 5.839276864401302e-07, 'epoch': 7.4}
+
 46%|████▋     | 171840/371472 [2:44:54<17:15:20,  3.21it/s]
 46%|████▋     | 171841/371472 [2:44:55<16:52:59,  3.28it/s]
 46%|████▋     | 171842/371472 [2:44:55<16:53:26,  3.28it/s]
 46%|████▋     | 171843/371472 [2:44:55<16:21:37,  3.39it/s]
 46%|████▋     | 171844/371472 [2:44:56<16:28:47,  3.36it/s]
 46%|████▋     | 171845/371472 [2:44:56<16:48:08,  3.30it/s]
 46%|████▋     | 171846/371472 [2:44:56<16:18:25,  3.40it/s]
 46%|████▋     | 171847/371472 [2:44:57<17:33:29,  3.16it/s]
 46%|████▋     | 171848/371472 [2:44:57<17:31:05,  3.17it/s]
 46%|████▋     | 171849/371472 [2:44:57<17:09:56,  3.23it/s]
 46%|████▋     | 171850/371472 [2:44:57<17:19:17,  3.20it/s]
 46%|████▋     | 171851/371472 [2:44:58<17:00:27,  3.26it/s]
 46%|████▋     | 171852/371472 [2:44:58<16:55:10,  3.28it/s]
 46%|████▋     | 171853/371472 [2:44:58<16:44:30,  3.31it/s]
 46%|████▋     | 171854/371472 [2:44:59<16:16:56,  3.41it/s]
 46%|████▋     | 171855/371472 [2:44:59<16:19:18,  3.40it/s]
 46%|████▋     | 171856/371472 [2:44:59<16:28:06,  3.37it/s]
 46%|████▋     | 171857/371472 [2:45:00<16:14:01,  3.42it/s]
 46%|████▋     | 171858/371472 [2:45:00<17:31:06,  3.17it/s]
 46%|████▋     | 171859/371472 [2:45:00<17:11:04,  3.23it/s]
 46%|████▋     | 171860/371472 [2:45:00<16:48:17,  3.30it/s]
                                                            
{'loss': 2.9546, 'learning_rate': 5.838792044646512e-07, 'epoch': 7.4}
+
 46%|████▋     | 171860/371472 [2:45:00<16:48:17,  3.30it/s]
 46%|████▋     | 171861/371472 [2:45:01<16:53:36,  3.28it/s]
 46%|████▋     | 171862/371472 [2:45:01<16:21:48,  3.39it/s]
 46%|████▋     | 171863/371472 [2:45:01<16:28:03,  3.37it/s]
 46%|████▋     | 171864/371472 [2:45:02<16:39:17,  3.33it/s]
 46%|████▋     | 171865/371472 [2:45:02<18:02:13,  3.07it/s]
 46%|████▋     | 171866/371472 [2:45:02<19:16:38,  2.88it/s]
 46%|████▋     | 171867/371472 [2:45:03<18:50:29,  2.94it/s]
 46%|████▋     | 171868/371472 [2:45:03<17:54:10,  3.10it/s]
 46%|████▋     | 171869/371472 [2:45:03<17:18:15,  3.20it/s]
 46%|████▋     | 171870/371472 [2:45:04<16:48:59,  3.30it/s]
 46%|████▋     | 171871/371472 [2:45:04<17:24:36,  3.18it/s]
 46%|████▋     | 171872/371472 [2:45:04<16:36:49,  3.34it/s]
 46%|████▋     | 171873/371472 [2:45:05<16:24:26,  3.38it/s]
 46%|████▋     | 171874/371472 [2:45:05<16:23:10,  3.38it/s]
 46%|████▋     | 171875/371472 [2:45:05<16:34:59,  3.34it/s]
 46%|████▋     | 171876/371472 [2:45:05<17:28:13,  3.17it/s]
 46%|████▋     | 171877/371472 [2:45:06<17:11:27,  3.23it/s]
 46%|████▋     | 171878/371472 [2:45:06<16:47:26,  3.30it/s]
 46%|████▋     | 171879/371472 [2:45:06<16:35:00,  3.34it/s]
 46%|████▋     | 171880/371472 [2:45:07<16:25:24,  3.38it/s]
                                                            
{'loss': 2.9289, 'learning_rate': 5.838307224891723e-07, 'epoch': 7.4}
+
 46%|████▋     | 171880/371472 [2:45:07<16:25:24,  3.38it/s]
 46%|████▋     | 171881/371472 [2:45:07<16:30:34,  3.36it/s]
 46%|████▋     | 171882/371472 [2:45:07<16:26:41,  3.37it/s]
 46%|████▋     | 171883/371472 [2:45:08<16:26:19,  3.37it/s]
 46%|████▋     | 171884/371472 [2:45:08<16:29:39,  3.36it/s]
 46%|████▋     | 171885/371472 [2:45:08<16:01:31,  3.46it/s]
 46%|████▋     | 171886/371472 [2:45:09<18:07:51,  3.06it/s]
 46%|████▋     | 171887/371472 [2:45:09<18:19:24,  3.03it/s]
 46%|████▋     | 171888/371472 [2:45:09<17:31:02,  3.16it/s]
 46%|████▋     | 171889/371472 [2:45:09<17:02:44,  3.25it/s]
 46%|████▋     | 171890/371472 [2:45:10<16:26:51,  3.37it/s]
 46%|████▋     | 171891/371472 [2:45:10<16:14:23,  3.41it/s]
 46%|████▋     | 171892/371472 [2:45:10<17:02:05,  3.25it/s]
 46%|████▋     | 171893/371472 [2:45:11<17:16:36,  3.21it/s]
 46%|████▋     | 171894/371472 [2:45:11<16:56:37,  3.27it/s]
 46%|████▋     | 171895/371472 [2:45:11<16:51:52,  3.29it/s]
 46%|████▋     | 171896/371472 [2:45:12<17:06:02,  3.24it/s]
 46%|████▋     | 171897/371472 [2:45:12<16:50:15,  3.29it/s]
 46%|████▋     | 171898/371472 [2:45:12<16:29:38,  3.36it/s]
 46%|████▋     | 171899/371472 [2:45:12<16:23:27,  3.38it/s]
 46%|████▋     | 171900/371472 [2:45:13<16:09:23,  3.43it/s]
                                                            
{'loss': 2.9627, 'learning_rate': 5.837822405136934e-07, 'epoch': 7.4}
+
 46%|████▋     | 171900/371472 [2:45:13<16:09:23,  3.43it/s]
 46%|████▋     | 171901/371472 [2:45:13<16:09:40,  3.43it/s]
 46%|████▋     | 171902/371472 [2:45:13<15:59:44,  3.47it/s]
 46%|████▋     | 171903/371472 [2:45:14<16:24:20,  3.38it/s]
 46%|████▋     | 171904/371472 [2:45:14<16:54:30,  3.28it/s]
 46%|████▋     | 171905/371472 [2:45:14<18:04:15,  3.07it/s]
 46%|████▋     | 171906/371472 [2:45:15<17:16:10,  3.21it/s]
 46%|████▋     | 171907/371472 [2:45:15<16:34:18,  3.35it/s]
 46%|████▋     | 171908/371472 [2:45:15<16:23:13,  3.38it/s]
 46%|████▋     | 171909/371472 [2:45:15<15:47:16,  3.51it/s]
 46%|████▋     | 171910/371472 [2:45:16<15:41:08,  3.53it/s]
 46%|████▋     | 171911/371472 [2:45:16<15:33:26,  3.56it/s]
 46%|████▋     | 171912/371472 [2:45:16<15:52:48,  3.49it/s]
 46%|████▋     | 171913/371472 [2:45:17<16:04:06,  3.45it/s]
 46%|████▋     | 171914/371472 [2:45:17<16:22:46,  3.38it/s]
 46%|████▋     | 171915/371472 [2:45:17<16:08:04,  3.44it/s]
 46%|████▋     | 171916/371472 [2:45:17<15:50:26,  3.50it/s]
 46%|████▋     | 171917/371472 [2:45:18<15:32:49,  3.57it/s]
 46%|████▋     | 171918/371472 [2:45:18<16:14:38,  3.41it/s]
 46%|████▋     | 171919/371472 [2:45:18<16:39:30,  3.33it/s]
 46%|████▋     | 171920/371472 [2:45:19<17:34:43,  3.15it/s]
                                                            
{'loss': 2.9691, 'learning_rate': 5.837337585382146e-07, 'epoch': 7.4}
+
 46%|████▋     | 171920/371472 [2:45:19<17:34:43,  3.15it/s]
 46%|████▋     | 171921/371472 [2:45:19<17:14:56,  3.21it/s]
 46%|████▋     | 171922/371472 [2:45:19<16:48:52,  3.30it/s]
 46%|████▋     | 171923/371472 [2:45:20<16:21:05,  3.39it/s]
 46%|████▋     | 171924/371472 [2:45:20<19:18:38,  2.87it/s]
 46%|████▋     | 171925/371472 [2:45:20<18:12:35,  3.04it/s]
 46%|████▋     | 171926/371472 [2:45:21<17:42:00,  3.13it/s]
 46%|████▋     | 171927/371472 [2:45:21<17:05:33,  3.24it/s]
 46%|████▋     | 171928/371472 [2:45:21<17:30:09,  3.17it/s]
 46%|████▋     | 171929/371472 [2:45:21<17:15:46,  3.21it/s]
 46%|████▋     | 171930/371472 [2:45:22<16:47:27,  3.30it/s]
 46%|████▋     | 171931/371472 [2:45:22<17:01:52,  3.25it/s]
 46%|████▋     | 171932/371472 [2:45:22<16:25:18,  3.38it/s]
 46%|████▋     | 171933/371472 [2:45:23<16:13:52,  3.41it/s]
 46%|████▋     | 171934/371472 [2:45:23<16:02:16,  3.46it/s]
 46%|████▋     | 171935/371472 [2:45:23<15:45:38,  3.52it/s]
 46%|████▋     | 171936/371472 [2:45:23<15:36:40,  3.55it/s]
 46%|████▋     | 171937/371472 [2:45:24<15:41:36,  3.53it/s]
 46%|████▋     | 171938/371472 [2:45:24<15:57:05,  3.47it/s]
 46%|████▋     | 171939/371472 [2:45:24<15:57:27,  3.47it/s]
 46%|████▋     | 171940/371472 [2:45:25<16:11:17,  3.42it/s]
                                                            
{'loss': 2.8775, 'learning_rate': 5.836852765627356e-07, 'epoch': 7.41}
+
 46%|████▋     | 171940/371472 [2:45:25<16:11:17,  3.42it/s]
 46%|████▋     | 171941/371472 [2:45:25<16:00:48,  3.46it/s]
 46%|████▋     | 171942/371472 [2:45:25<16:03:16,  3.45it/s]
 46%|████▋     | 171943/371472 [2:45:26<16:33:16,  3.35it/s]
 46%|████▋     | 171944/371472 [2:45:26<16:26:37,  3.37it/s]
 46%|████▋     | 171945/371472 [2:45:26<17:27:02,  3.18it/s]
 46%|████▋     | 171946/371472 [2:45:27<17:45:50,  3.12it/s]
 46%|████▋     | 171947/371472 [2:45:27<16:54:42,  3.28it/s]
 46%|████▋     | 171948/371472 [2:45:27<16:26:19,  3.37it/s]
 46%|████▋     | 171949/371472 [2:45:27<16:27:11,  3.37it/s]
 46%|████▋     | 171950/371472 [2:45:28<16:26:49,  3.37it/s]
 46%|████▋     | 171951/371472 [2:45:28<16:22:26,  3.38it/s]
 46%|████▋     | 171952/371472 [2:45:28<16:06:12,  3.44it/s]
 46%|████▋     | 171953/371472 [2:45:29<17:41:17,  3.13it/s]
 46%|████▋     | 171954/371472 [2:45:29<16:54:27,  3.28it/s]
 46%|████▋     | 171955/371472 [2:45:29<17:06:03,  3.24it/s]
 46%|████▋     | 171956/371472 [2:45:29<16:38:43,  3.33it/s]
 46%|████▋     | 171957/371472 [2:45:30<17:22:08,  3.19it/s]
 46%|████▋     | 171958/371472 [2:45:30<16:46:32,  3.30it/s]
 46%|████▋     | 171959/371472 [2:45:30<16:33:11,  3.35it/s]
 46%|████▋     | 171960/371472 [2:45:31<16:29:56,  3.36it/s]
                                                            
{'loss': 2.8242, 'learning_rate': 5.836367945872567e-07, 'epoch': 7.41}
+
 46%|████▋     | 171960/371472 [2:45:31<16:29:56,  3.36it/s]
 46%|████▋     | 171961/371472 [2:45:31<16:29:21,  3.36it/s]
 46%|████▋     | 171962/371472 [2:45:31<16:28:56,  3.36it/s]
 46%|████▋     | 171963/371472 [2:45:32<16:33:43,  3.35it/s]
 46%|████▋     | 171964/371472 [2:45:32<16:06:31,  3.44it/s]
 46%|████▋     | 171965/371472 [2:45:32<15:54:08,  3.48it/s]
 46%|████▋     | 171966/371472 [2:45:32<15:55:17,  3.48it/s]
 46%|████▋     | 171967/371472 [2:45:33<16:02:36,  3.45it/s]
 46%|████▋     | 171968/371472 [2:45:33<16:08:18,  3.43it/s]
 46%|████▋     | 171969/371472 [2:45:33<17:31:15,  3.16it/s]
 46%|████▋     | 171970/371472 [2:45:34<17:42:21,  3.13it/s]
 46%|████▋     | 171971/371472 [2:45:34<17:03:01,  3.25it/s]
 46%|████▋     | 171972/371472 [2:45:34<17:19:46,  3.20it/s]
 46%|████▋     | 171973/371472 [2:45:35<16:57:48,  3.27it/s]
 46%|████▋     | 171974/371472 [2:45:35<16:24:48,  3.38it/s]
 46%|████▋     | 171975/371472 [2:45:35<15:51:45,  3.49it/s]
 46%|████▋     | 171976/371472 [2:45:35<15:41:10,  3.53it/s]
 46%|████▋     | 171977/371472 [2:45:36<16:02:22,  3.45it/s]
 46%|████▋     | 171978/371472 [2:45:36<15:45:11,  3.52it/s]
 46%|████▋     | 171979/371472 [2:45:36<15:41:58,  3.53it/s]
 46%|████▋     | 171980/371472 [2:45:37<17:29:10,  3.17it/s]
                                                            
{'loss': 2.8642, 'learning_rate': 5.835883126117779e-07, 'epoch': 7.41}
+
 46%|████▋     | 171980/371472 [2:45:37<17:29:10,  3.17it/s]
 46%|████▋     | 171981/371472 [2:45:37<16:52:41,  3.28it/s]
 46%|████▋     | 171982/371472 [2:45:37<16:42:17,  3.32it/s]
 46%|████▋     | 171983/371472 [2:45:38<16:46:54,  3.30it/s]
 46%|████▋     | 171984/371472 [2:45:38<18:44:21,  2.96it/s]
 46%|████▋     | 171985/371472 [2:45:38<17:39:57,  3.14it/s]
 46%|████▋     | 171986/371472 [2:45:39<17:00:29,  3.26it/s]
 46%|████▋     | 171987/371472 [2:45:39<16:51:15,  3.29it/s]
 46%|████▋     | 171988/371472 [2:45:39<18:24:20,  3.01it/s]
 46%|████▋     | 171989/371472 [2:45:40<18:08:43,  3.05it/s]
 46%|████▋     | 171990/371472 [2:45:40<17:34:38,  3.15it/s]
 46%|████▋     | 171991/371472 [2:45:40<17:49:02,  3.11it/s]
 46%|████▋     | 171992/371472 [2:45:40<17:15:40,  3.21it/s]
 46%|████▋     | 171993/371472 [2:45:41<17:17:39,  3.20it/s]
 46%|████▋     | 171994/371472 [2:45:41<17:15:51,  3.21it/s]
 46%|████▋     | 171995/371472 [2:45:41<16:54:34,  3.28it/s]
 46%|████▋     | 171996/371472 [2:45:42<16:34:03,  3.34it/s]
 46%|████▋     | 171997/371472 [2:45:42<15:58:31,  3.47it/s]
 46%|████▋     | 171998/371472 [2:45:42<15:30:32,  3.57it/s]
 46%|████▋     | 171999/371472 [2:45:42<15:31:52,  3.57it/s]
 46%|████▋     | 172000/371472 [2:45:43<16:40:52,  3.32it/s]
                                                            
{'loss': 2.927, 'learning_rate': 5.83539830636299e-07, 'epoch': 7.41}
+
 46%|████▋     | 172000/371472 [2:45:43<16:40:52,  3.32it/s]
 46%|████▋     | 172001/371472 [2:45:43<17:01:53,  3.25it/s]
 46%|████▋     | 172002/371472 [2:45:43<17:22:04,  3.19it/s]
 46%|████▋     | 172003/371472 [2:45:44<16:58:28,  3.26it/s]
 46%|████▋     | 172004/371472 [2:45:44<17:15:20,  3.21it/s]
 46%|████▋     | 172005/371472 [2:45:44<18:09:31,  3.05it/s]
 46%|████▋     | 172006/371472 [2:45:45<17:51:56,  3.10it/s]
 46%|████▋     | 172007/371472 [2:45:45<17:07:59,  3.23it/s]
 46%|████▋     | 172008/371472 [2:45:45<16:48:57,  3.29it/s]
 46%|████▋     | 172009/371472 [2:45:46<16:27:33,  3.37it/s]
 46%|████▋     | 172010/371472 [2:45:46<16:21:19,  3.39it/s]
 46%|████▋     | 172011/371472 [2:45:46<16:43:39,  3.31it/s]
 46%|████▋     | 172012/371472 [2:45:46<16:15:41,  3.41it/s]
 46%|████▋     | 172013/371472 [2:45:47<16:37:36,  3.33it/s]
 46%|████▋     | 172014/371472 [2:45:47<16:24:51,  3.38it/s]
 46%|████▋     | 172015/371472 [2:45:47<16:31:48,  3.35it/s]
 46%|████▋     | 172016/371472 [2:45:48<16:14:20,  3.41it/s]
 46%|████▋     | 172017/371472 [2:45:48<16:03:50,  3.45it/s]
 46%|████▋     | 172018/371472 [2:45:48<16:22:47,  3.38it/s]
 46%|████▋     | 172019/371472 [2:45:49<15:59:59,  3.46it/s]
 46%|████▋     | 172020/371472 [2:45:49<15:47:45,  3.51it/s]
                                                            
{'loss': 2.9396, 'learning_rate': 5.8349134866082e-07, 'epoch': 7.41}
+
 46%|████▋     | 172020/371472 [2:45:49<15:47:45,  3.51it/s]
 46%|████▋     | 172021/371472 [2:45:49<15:24:02,  3.60it/s]
 46%|████▋     | 172022/371472 [2:45:49<15:22:43,  3.60it/s]
 46%|████▋     | 172023/371472 [2:45:50<15:42:47,  3.53it/s]
 46%|████▋     | 172024/371472 [2:45:50<15:28:50,  3.58it/s]
 46%|████▋     | 172025/371472 [2:45:50<16:47:42,  3.30it/s]
 46%|████▋     | 172026/371472 [2:45:51<16:38:54,  3.33it/s]
 46%|████▋     | 172027/371472 [2:45:51<16:22:18,  3.38it/s]
 46%|████▋     | 172028/371472 [2:45:51<16:11:59,  3.42it/s]
 46%|████▋     | 172029/371472 [2:45:51<16:12:51,  3.42it/s]
 46%|████▋     | 172030/371472 [2:45:52<15:55:48,  3.48it/s]
 46%|████▋     | 172031/371472 [2:45:52<17:03:41,  3.25it/s]
 46%|████▋     | 172032/371472 [2:45:52<16:51:40,  3.29it/s]
 46%|████▋     | 172033/371472 [2:45:53<16:39:29,  3.33it/s]
 46%|████▋     | 172034/371472 [2:45:53<16:52:02,  3.28it/s]
 46%|████▋     | 172035/371472 [2:45:53<16:26:27,  3.37it/s]
 46%|████▋     | 172036/371472 [2:45:54<17:15:31,  3.21it/s]
 46%|████▋     | 172037/371472 [2:45:54<17:00:04,  3.26it/s]
 46%|████▋     | 172038/371472 [2:45:54<16:24:55,  3.37it/s]
 46%|████▋     | 172039/371472 [2:45:54<16:10:08,  3.43it/s]
 46%|████▋     | 172040/371472 [2:45:55<15:48:26,  3.50it/s]
                                                            
{'loss': 2.909, 'learning_rate': 5.834428666853411e-07, 'epoch': 7.41}
+
 46%|████▋     | 172040/371472 [2:45:55<15:48:26,  3.50it/s]
 46%|████▋     | 172041/371472 [2:45:55<16:00:45,  3.46it/s]
 46%|████▋     | 172042/371472 [2:45:55<16:04:05,  3.45it/s]
 46%|████▋     | 172043/371472 [2:45:56<16:35:33,  3.34it/s]
 46%|████▋     | 172044/371472 [2:45:56<16:39:45,  3.32it/s]
 46%|████▋     | 172045/371472 [2:45:56<17:25:55,  3.18it/s]
 46%|████▋     | 172046/371472 [2:45:57<17:14:19,  3.21it/s]
 46%|████▋     | 172047/371472 [2:45:57<17:28:52,  3.17it/s]
 46%|████▋     | 172048/371472 [2:45:57<16:52:49,  3.28it/s]
 46%|████▋     | 172049/371472 [2:45:58<17:44:24,  3.12it/s]
 46%|████▋     | 172050/371472 [2:45:58<17:25:52,  3.18it/s]
 46%|████▋     | 172051/371472 [2:45:58<16:43:40,  3.31it/s]
 46%|████▋     | 172052/371472 [2:45:58<16:24:04,  3.38it/s]
 46%|████▋     | 172053/371472 [2:45:59<17:59:12,  3.08it/s]
 46%|████▋     | 172054/371472 [2:45:59<17:17:30,  3.20it/s]
 46%|████▋     | 172055/371472 [2:45:59<17:10:13,  3.23it/s]
 46%|████▋     | 172056/371472 [2:46:00<17:12:18,  3.22it/s]
 46%|████▋     | 172057/371472 [2:46:00<16:52:09,  3.28it/s]
 46%|████▋     | 172058/371472 [2:46:00<16:36:16,  3.34it/s]
 46%|████▋     | 172059/371472 [2:46:01<17:59:30,  3.08it/s]
 46%|████▋     | 172060/371472 [2:46:01<17:27:56,  3.17it/s]
                                                            
{'loss': 2.9112, 'learning_rate': 5.833943847098623e-07, 'epoch': 7.41}
+
 46%|████▋     | 172060/371472 [2:46:01<17:27:56,  3.17it/s]
 46%|████▋     | 172061/371472 [2:46:01<16:59:38,  3.26it/s]
 46%|████▋     | 172062/371472 [2:46:01<16:15:20,  3.41it/s]
 46%|████▋     | 172063/371472 [2:46:02<15:46:24,  3.51it/s]
 46%|████▋     | 172064/371472 [2:46:02<15:31:26,  3.57it/s]
 46%|████▋     | 172065/371472 [2:46:02<16:17:41,  3.40it/s]
 46%|████▋     | 172066/371472 [2:46:03<16:38:55,  3.33it/s]
 46%|████▋     | 172067/371472 [2:46:03<16:27:40,  3.36it/s]
 46%|████▋     | 172068/371472 [2:46:03<16:00:58,  3.46it/s]
 46%|████▋     | 172069/371472 [2:46:04<16:19:02,  3.39it/s]
 46%|████▋     | 172070/371472 [2:46:04<16:32:46,  3.35it/s]
 46%|████▋     | 172071/371472 [2:46:04<15:45:15,  3.52it/s]
 46%|████▋     | 172072/371472 [2:46:04<15:58:23,  3.47it/s]
 46%|████▋     | 172073/371472 [2:46:05<16:18:42,  3.40it/s]
 46%|████▋     | 172074/371472 [2:46:05<16:10:57,  3.42it/s]
 46%|████▋     | 172075/371472 [2:46:05<16:48:13,  3.30it/s]
 46%|████▋     | 172076/371472 [2:46:06<16:41:20,  3.32it/s]
 46%|████▋     | 172077/371472 [2:46:06<16:23:25,  3.38it/s]
 46%|████▋     | 172078/371472 [2:46:06<16:26:19,  3.37it/s]
 46%|████▋     | 172079/371472 [2:46:07<17:01:14,  3.25it/s]
 46%|████▋     | 172080/371472 [2:46:07<17:39:16,  3.14it/s]
                                                            
{'loss': 2.9629, 'learning_rate': 5.833459027343834e-07, 'epoch': 7.41}
+
 46%|████▋     | 172080/371472 [2:46:07<17:39:16,  3.14it/s]
 46%|████▋     | 172081/371472 [2:46:07<17:24:07,  3.18it/s]
 46%|████▋     | 172082/371472 [2:46:07<17:40:12,  3.13it/s]
 46%|████▋     | 172083/371472 [2:46:08<16:56:59,  3.27it/s]
 46%|████▋     | 172084/371472 [2:46:08<16:39:15,  3.33it/s]
 46%|████▋     | 172085/371472 [2:46:08<16:19:27,  3.39it/s]
 46%|████▋     | 172086/371472 [2:46:09<16:40:52,  3.32it/s]
 46%|████▋     | 172087/371472 [2:46:09<16:23:11,  3.38it/s]
 46%|████▋     | 172088/371472 [2:46:09<15:51:53,  3.49it/s]
 46%|████▋     | 172089/371472 [2:46:10<16:37:13,  3.33it/s]
 46%|████▋     | 172090/371472 [2:46:10<17:01:58,  3.25it/s]
 46%|████▋     | 172091/371472 [2:46:10<16:48:47,  3.29it/s]
 46%|████▋     | 172092/371472 [2:46:10<16:30:49,  3.35it/s]
 46%|████▋     | 172093/371472 [2:46:11<16:22:54,  3.38it/s]
 46%|████▋     | 172094/371472 [2:46:11<17:06:21,  3.24it/s]
 46%|████▋     | 172095/371472 [2:46:11<16:57:08,  3.27it/s]
 46%|████▋     | 172096/371472 [2:46:12<16:29:26,  3.36it/s]
 46%|████▋     | 172097/371472 [2:46:12<16:26:33,  3.37it/s]
 46%|████▋     | 172098/371472 [2:46:12<16:14:03,  3.41it/s]
 46%|████▋     | 172099/371472 [2:46:13<16:03:39,  3.45it/s]
 46%|████▋     | 172100/371472 [2:46:13<15:45:04,  3.52it/s]
                                                            
{'loss': 2.9921, 'learning_rate': 5.832974207589045e-07, 'epoch': 7.41}
+
 46%|████▋     | 172100/371472 [2:46:13<15:45:04,  3.52it/s]
 46%|████▋     | 172101/371472 [2:46:13<15:58:49,  3.47it/s]
 46%|████▋     | 172102/371472 [2:46:13<16:10:14,  3.42it/s]
 46%|████▋     | 172103/371472 [2:46:14<16:06:40,  3.44it/s]
 46%|████▋     | 172104/371472 [2:46:14<16:17:26,  3.40it/s]
 46%|████▋     | 172105/371472 [2:46:14<16:52:02,  3.28it/s]
 46%|██��█▋     | 172106/371472 [2:46:15<16:52:49,  3.28it/s]
 46%|████▋     | 172107/371472 [2:46:15<17:25:04,  3.18it/s]
 46%|████▋     | 172108/371472 [2:46:15<17:11:54,  3.22it/s]
 46%|████▋     | 172109/371472 [2:46:16<16:46:59,  3.30it/s]
 46%|████▋     | 172110/371472 [2:46:16<16:18:57,  3.39it/s]
 46%|████▋     | 172111/371472 [2:46:16<16:13:18,  3.41it/s]
 46%|████▋     | 172112/371472 [2:46:16<17:49:00,  3.11it/s]
 46%|████▋     | 172113/371472 [2:46:17<16:55:12,  3.27it/s]
 46%|████▋     | 172114/371472 [2:46:17<16:52:13,  3.28it/s]
 46%|████▋     | 172115/371472 [2:46:17<16:37:02,  3.33it/s]
 46%|████▋     | 172116/371472 [2:46:18<17:05:05,  3.24it/s]
 46%|████▋     | 172117/371472 [2:46:18<16:48:20,  3.30it/s]
 46%|████▋     | 172118/371472 [2:46:18<18:23:40,  3.01it/s]
 46%|████▋     | 172119/371472 [2:46:19<19:00:01,  2.91it/s]
 46%|████▋     | 172120/371472 [2:46:19<17:48:11,  3.11it/s]
                                                            
{'loss': 3.0032, 'learning_rate': 5.832489387834256e-07, 'epoch': 7.41}
+
 46%|████▋     | 172120/371472 [2:46:19<17:48:11,  3.11it/s]
 46%|████▋     | 172121/371472 [2:46:19<17:47:49,  3.11it/s]
 46%|████▋     | 172122/371472 [2:46:20<17:49:07,  3.11it/s]
 46%|████▋     | 172123/371472 [2:46:20<17:18:06,  3.20it/s]
 46%|████▋     | 172124/371472 [2:46:20<17:13:03,  3.22it/s]
 46%|████▋     | 172125/371472 [2:46:21<16:46:41,  3.30it/s]
 46%|████▋     | 172126/371472 [2:46:21<17:43:54,  3.12it/s]
 46%|████▋     | 172127/371472 [2:46:21<17:07:13,  3.23it/s]
 46%|████▋     | 172128/371472 [2:46:21<16:56:59,  3.27it/s]
 46%|████▋     | 172129/371472 [2:46:22<17:10:36,  3.22it/s]
 46%|████▋     | 172130/371472 [2:46:22<16:46:38,  3.30it/s]
 46%|████▋     | 172131/371472 [2:46:22<16:33:55,  3.34it/s]
 46%|████▋     | 172132/371472 [2:46:23<17:21:35,  3.19it/s]
 46%|████▋     | 172133/371472 [2:46:23<16:50:20,  3.29it/s]
 46%|████▋     | 172134/371472 [2:46:23<16:49:53,  3.29it/s]
 46%|████▋     | 172135/371472 [2:46:24<16:34:07,  3.34it/s]
 46%|████▋     | 172136/371472 [2:46:24<16:42:46,  3.31it/s]
 46%|████▋     | 172137/371472 [2:46:24<16:54:04,  3.28it/s]
 46%|████▋     | 172138/371472 [2:46:24<16:34:14,  3.34it/s]
 46%|████▋     | 172139/371472 [2:46:25<16:27:48,  3.36it/s]
 46%|████▋     | 172140/371472 [2:46:25<16:30:24,  3.35it/s]
                                                            
{'loss': 3.0308, 'learning_rate': 5.832004568079468e-07, 'epoch': 7.41}
+
 46%|████▋     | 172140/371472 [2:46:25<16:30:24,  3.35it/s]
 46%|████▋     | 172141/371472 [2:46:25<16:27:33,  3.36it/s]
 46%|████▋     | 172142/371472 [2:46:26<16:16:17,  3.40it/s]
 46%|████▋     | 172143/371472 [2:46:26<16:07:01,  3.44it/s]
 46%|████▋     | 172144/371472 [2:46:26<16:11:34,  3.42it/s]
 46%|████▋     | 172145/371472 [2:46:27<17:15:27,  3.21it/s]
 46%|████▋     | 172146/371472 [2:46:27<16:49:16,  3.29it/s]
 46%|████▋     | 172147/371472 [2:46:27<16:40:32,  3.32it/s]
 46%|████▋     | 172148/371472 [2:46:27<16:38:48,  3.33it/s]
 46%|████▋     | 172149/371472 [2:46:28<16:58:41,  3.26it/s]
 46%|████▋     | 172150/371472 [2:46:28<17:05:21,  3.24it/s]
 46%|████▋     | 172151/371472 [2:46:28<17:07:40,  3.23it/s]
 46%|████▋     | 172152/371472 [2:46:29<16:53:33,  3.28it/s]
 46%|████▋     | 172153/371472 [2:46:29<17:46:45,  3.11it/s]
 46%|████▋     | 172154/371472 [2:46:29<17:21:10,  3.19it/s]
 46%|████▋     | 172155/371472 [2:46:30<17:15:35,  3.21it/s]
 46%|████▋     | 172156/371472 [2:46:30<16:54:54,  3.27it/s]
 46%|████▋     | 172157/371472 [2:46:30<16:51:24,  3.28it/s]
 46%|████▋     | 172158/371472 [2:46:31<16:44:38,  3.31it/s]
 46%|████▋     | 172159/371472 [2:46:31<16:18:12,  3.40it/s]
 46%|████▋     | 172160/371472 [2:46:31<16:29:17,  3.36it/s]
                                                            
{'loss': 2.9708, 'learning_rate': 5.831519748324678e-07, 'epoch': 7.42}
+
 46%|████▋     | 172160/371472 [2:46:31<16:29:17,  3.36it/s]
 46%|████▋     | 172161/371472 [2:46:31<16:18:50,  3.39it/s]
 46%|████▋     | 172162/371472 [2:46:32<17:07:23,  3.23it/s]
 46%|████▋     | 172163/371472 [2:46:32<16:32:29,  3.35it/s]
 46%|████▋     | 172164/371472 [2:46:32<16:02:59,  3.45it/s]
 46%|████▋     | 172165/371472 [2:46:33<15:47:01,  3.51it/s]
 46%|████▋     | 172166/371472 [2:46:33<16:08:19,  3.43it/s]
 46%|████▋     | 172167/371472 [2:46:33<15:54:55,  3.48it/s]
 46%|████▋     | 172168/371472 [2:46:33<16:11:09,  3.42it/s]
 46%|████▋     | 172169/371472 [2:46:34<16:00:14,  3.46it/s]
 46%|████▋     | 172170/371472 [2:46:34<15:47:15,  3.51it/s]
 46%|████▋     | 172171/371472 [2:46:34<15:42:46,  3.52it/s]
 46%|████▋     | 172172/371472 [2:46:35<15:53:41,  3.48it/s]
 46%|████▋     | 172173/371472 [2:46:35<15:50:25,  3.49it/s]
 46%|████▋     | 172174/371472 [2:46:35<15:32:08,  3.56it/s]
 46%|████▋     | 172175/371472 [2:46:35<15:37:45,  3.54it/s]
 46%|████▋     | 172176/371472 [2:46:36<15:46:20,  3.51it/s]
 46%|████▋     | 172177/371472 [2:46:36<15:46:45,  3.51it/s]
 46%|████▋     | 172178/371472 [2:46:36<16:00:56,  3.46it/s]
 46%|████▋     | 172179/371472 [2:46:37<16:18:35,  3.39it/s]
 46%|████▋     | 172180/371472 [2:46:37<16:48:15,  3.29it/s]
                                                            
{'loss': 3.0427, 'learning_rate': 5.831034928569889e-07, 'epoch': 7.42}
+
 46%|████▋     | 172180/371472 [2:46:37<16:48:15,  3.29it/s]
 46%|████▋     | 172181/371472 [2:46:37<16:33:36,  3.34it/s]
 46%|████▋     | 172182/371472 [2:46:38<16:18:33,  3.39it/s]
 46%|████▋     | 172183/371472 [2:46:38<16:05:05,  3.44it/s]
 46%|████▋     | 172184/371472 [2:46:38<15:48:06,  3.50it/s]
 46%|████▋     | 172185/371472 [2:46:38<15:33:55,  3.56it/s]
 46%|████▋     | 172186/371472 [2:46:39<15:51:09,  3.49it/s]
 46%|████▋     | 172187/371472 [2:46:39<16:52:50,  3.28it/s]
 46%|████▋     | 172188/371472 [2:46:39<16:50:43,  3.29it/s]
 46%|████▋     | 172189/371472 [2:46:40<16:34:44,  3.34it/s]
 46%|████▋     | 172190/371472 [2:46:40<16:28:39,  3.36it/s]
 46%|████▋     | 172191/371472 [2:46:40<16:15:38,  3.40it/s]
 46%|████▋     | 172192/371472 [2:46:40<16:27:14,  3.36it/s]
 46%|████▋     | 172193/371472 [2:46:41<15:57:48,  3.47it/s]
 46%|████▋     | 172194/371472 [2:46:41<15:25:57,  3.59it/s]
 46%|████▋     | 172195/371472 [2:46:41<16:25:08,  3.37it/s]
 46%|████▋     | 172196/371472 [2:46:42<16:06:20,  3.44it/s]
 46%|████▋     | 172197/371472 [2:46:42<16:49:04,  3.29it/s]
 46%|████▋     | 172198/371472 [2:46:42<16:59:36,  3.26it/s]
 46%|████▋     | 172199/371472 [2:46:43<16:30:50,  3.35it/s]
 46%|████▋     | 172200/371472 [2:46:43<16:18:39,  3.39it/s]
                                                            
{'loss': 2.8585, 'learning_rate': 5.8305501088151e-07, 'epoch': 7.42}
+
 46%|████▋     | 172200/371472 [2:46:43<16:18:39,  3.39it/s]
 46%|████▋     | 172201/371472 [2:46:43<16:17:18,  3.40it/s]
 46%|████▋     | 172202/371472 [2:46:43<15:51:22,  3.49it/s]
 46%|████▋     | 172203/371472 [2:46:44<15:41:20,  3.53it/s]
 46%|████▋     | 172204/371472 [2:46:44<16:25:58,  3.37it/s]
 46%|████▋     | 172205/371472 [2:46:44<16:50:20,  3.29it/s]
 46%|████▋     | 172206/371472 [2:46:45<17:03:50,  3.24it/s]
 46%|████▋     | 172207/371472 [2:46:45<16:27:31,  3.36it/s]
 46%|████▋     | 172208/371472 [2:46:45<16:40:06,  3.32it/s]
 46%|████▋     | 172209/371472 [2:46:46<16:57:10,  3.26it/s]
 46%|████▋     | 172210/371472 [2:46:46<16:30:52,  3.35it/s]
 46%|████▋     | 172211/371472 [2:46:46<16:24:04,  3.37it/s]
 46%|████▋     | 172212/371472 [2:46:46<16:54:59,  3.27it/s]
 46%|████▋     | 172213/371472 [2:46:47<16:45:37,  3.30it/s]
 46%|████▋     | 172214/371472 [2:46:47<16:39:08,  3.32it/s]
 46%|████▋     | 172215/371472 [2:46:47<17:11:08,  3.22it/s]
 46%|████▋     | 172216/371472 [2:46:48<16:36:20,  3.33it/s]
 46%|████▋     | 172217/371472 [2:46:48<17:48:51,  3.11it/s]
 46%|████▋     | 172218/371472 [2:46:48<17:39:40,  3.13it/s]
 46%|████▋     | 172219/371472 [2:46:49<17:51:05,  3.10it/s]
 46%|████▋     | 172220/371472 [2:46:49<17:19:11,  3.20it/s]
                                                            
{'loss': 3.0821, 'learning_rate': 5.830065289060312e-07, 'epoch': 7.42}
+
 46%|████▋     | 172220/371472 [2:46:49<17:19:11,  3.20it/s]
 46%|████▋     | 172221/371472 [2:46:49<17:57:15,  3.08it/s]
 46%|████▋     | 172222/371472 [2:46:50<17:15:13,  3.21it/s]
 46%|████▋     | 172223/371472 [2:46:50<16:47:54,  3.29it/s]
 46%|████▋     | 172224/371472 [2:46:50<16:23:43,  3.38it/s]
 46%|████▋     | 172225/371472 [2:46:50<16:11:20,  3.42it/s]
 46%|████▋     | 172226/371472 [2:46:51<15:59:54,  3.46it/s]
 46%|████▋     | 172227/371472 [2:46:51<15:48:13,  3.50it/s]
 46%|████▋     | 172228/371472 [2:46:51<15:49:52,  3.50it/s]
 46%|████▋     | 172229/371472 [2:46:52<15:22:46,  3.60it/s]
 46%|████▋     | 172230/371472 [2:46:52<15:49:41,  3.50it/s]
 46%|████▋     | 172231/371472 [2:46:52<15:53:19,  3.48it/s]
 46%|████▋     | 172232/371472 [2:46:52<15:56:08,  3.47it/s]
 46%|████▋     | 172233/371472 [2:46:53<16:25:32,  3.37it/s]
 46%|████▋     | 172234/371472 [2:46:53<16:30:07,  3.35it/s]
 46%|████▋     | 172235/371472 [2:46:53<16:21:00,  3.38it/s]
 46%|████▋     | 172236/371472 [2:46:54<17:47:06,  3.11it/s]
 46%|████▋     | 172237/371472 [2:46:54<17:00:37,  3.25it/s]
 46%|████▋     | 172238/371472 [2:46:54<18:42:58,  2.96it/s]
 46%|████▋     | 172239/371472 [2:46:55<19:09:11,  2.89it/s]
 46%|████▋     | 172240/371472 [2:46:55<18:16:26,  3.03it/s]
                                                            
{'loss': 2.7136, 'learning_rate': 5.829580469305523e-07, 'epoch': 7.42}
+
 46%|████▋     | 172240/371472 [2:46:55<18:16:26,  3.03it/s]
 46%|████▋     | 172241/371472 [2:46:55<18:17:05,  3.03it/s]
 46%|████▋     | 172242/371472 [2:46:56<17:05:19,  3.24it/s]
 46%|████▋     | 172243/371472 [2:46:56<18:01:17,  3.07it/s]
 46%|████▋     | 172244/371472 [2:46:56<20:14:41,  2.73it/s]
 46%|████▋     | 172245/371472 [2:46:57<18:35:07,  2.98it/s]
 46%|████▋     | 172246/371472 [2:46:57<18:31:41,  2.99it/s]
 46%|████▋     | 172247/371472 [2:46:57<17:49:08,  3.11it/s]
 46%|████▋     | 172248/371472 [2:46:58<17:43:08,  3.12it/s]
 46%|████▋     | 172249/371472 [2:46:58<16:54:15,  3.27it/s]
 46%|████▋     | 172250/371472 [2:46:58<16:27:04,  3.36it/s]
 46%|████▋     | 172251/371472 [2:46:58<15:49:39,  3.50it/s]
 46%|████▋     | 172252/371472 [2:46:59<15:46:26,  3.51it/s]
 46%|████▋     | 172253/371472 [2:46:59<17:17:24,  3.20it/s]
 46%|████▋     | 172254/371472 [2:46:59<17:11:21,  3.22it/s]
 46%|████▋     | 172255/371472 [2:47:00<17:06:21,  3.23it/s]
 46%|████▋     | 172256/371472 [2:47:00<17:25:10,  3.18it/s]
 46%|████▋     | 172257/371472 [2:47:00<17:38:10,  3.14it/s]
 46%|████▋     | 172258/371472 [2:47:01<17:11:26,  3.22it/s]
 46%|████▋     | 172259/371472 [2:47:01<17:13:39,  3.21it/s]
 46%|████▋     | 172260/371472 [2:47:01<16:42:23,  3.31it/s]
                                                            
{'loss': 2.9593, 'learning_rate': 5.829095649550734e-07, 'epoch': 7.42}
+
 46%|████▋     | 172260/371472 [2:47:01<16:42:23,  3.31it/s]
 46%|████▋     | 172261/371472 [2:47:02<16:16:57,  3.40it/s]
 46%|████▋     | 172262/371472 [2:47:02<15:46:07,  3.51it/s]
 46%|████▋     | 172263/371472 [2:47:02<16:04:19,  3.44it/s]
 46%|████▋     | 172264/371472 [2:47:02<15:52:52,  3.48it/s]
 46%|████▋     | 172265/371472 [2:47:03<16:28:24,  3.36it/s]
 46%|████▋     | 172266/371472 [2:47:03<16:53:30,  3.28it/s]
 46%|████▋     | 172267/371472 [2:47:03<17:04:02,  3.24it/s]
 46%|████▋     | 172268/371472 [2:47:04<18:26:25,  3.00it/s]
 46%|████▋     | 172269/371472 [2:47:04<18:29:59,  2.99it/s]
 46%|████▋     | 172270/371472 [2:47:04<17:29:33,  3.16it/s]
 46%|████▋     | 172271/371472 [2:47:05<17:11:56,  3.22it/s]
 46%|████▋     | 172272/371472 [2:47:05<16:43:01,  3.31it/s]
 46%|████▋     | 172273/371472 [2:47:05<17:05:53,  3.24it/s]
 46%|████▋     | 172274/371472 [2:47:06<16:33:04,  3.34it/s]
 46%|████▋     | 172275/371472 [2:47:06<16:34:46,  3.34it/s]
 46%|████▋     | 172276/371472 [2:47:06<16:19:10,  3.39it/s]
 46%|████▋     | 172277/371472 [2:47:06<16:13:27,  3.41it/s]
 46%|████▋     | 172278/371472 [2:47:07<16:06:03,  3.44it/s]
 46%|████▋     | 172279/371472 [2:47:07<15:44:44,  3.51it/s]
 46%|████▋     | 172280/371472 [2:47:07<15:50:29,  3.49it/s]
                                                            
{'loss': 2.9629, 'learning_rate': 5.828610829795944e-07, 'epoch': 7.42}
+
 46%|████▋     | 172280/371472 [2:47:07<15:50:29,  3.49it/s]
 46%|████▋     | 172281/371472 [2:47:08<16:09:47,  3.42it/s]
 46%|████▋     | 172282/371472 [2:47:08<15:55:38,  3.47it/s]
 46%|████▋     | 172283/371472 [2:47:08<16:02:08,  3.45it/s]
 46%|████▋     | 172284/371472 [2:47:08<15:59:30,  3.46it/s]
 46%|████▋     | 172285/371472 [2:47:09<15:43:12,  3.52it/s]
 46%|████▋     | 172286/371472 [2:47:09<15:57:56,  3.47it/s]
 46%|████▋     | 172287/371472 [2:47:09<15:37:39,  3.54it/s]
 46%|████▋     | 172288/371472 [2:47:10<16:49:51,  3.29it/s]
 46%|████▋     | 172289/371472 [2:47:10<16:53:29,  3.28it/s]
 46%|████▋     | 172290/371472 [2:47:10<16:41:30,  3.31it/s]
 46%|████▋     | 172291/371472 [2:47:11<16:27:29,  3.36it/s]
 46%|████▋     | 172292/371472 [2:47:11<16:20:07,  3.39it/s]
 46%|████▋     | 172293/371472 [2:47:11<16:05:45,  3.44it/s]
 46%|████▋     | 172294/371472 [2:47:11<15:56:05,  3.47it/s]
 46%|████▋     | 172295/371472 [2:47:12<15:52:36,  3.48it/s]
 46%|████▋     | 172296/371472 [2:47:12<16:10:12,  3.42it/s]
 46%|████▋     | 172297/371472 [2:47:12<16:15:27,  3.40it/s]
 46%|████▋     | 172298/371472 [2:47:13<16:23:59,  3.37it/s]
 46%|████▋     | 172299/371472 [2:47:13<15:45:45,  3.51it/s]
 46%|████▋     | 172300/371472 [2:47:13<15:36:19,  3.55it/s]
                                                            
{'loss': 2.9325, 'learning_rate': 5.828126010041155e-07, 'epoch': 7.42}
+
 46%|████▋     | 172300/371472 [2:47:13<15:36:19,  3.55it/s]
 46%|████▋     | 172301/371472 [2:47:13<15:26:17,  3.58it/s]
 46%|████▋     | 172302/371472 [2:47:14<16:34:23,  3.34it/s]
 46%|████▋     | 172303/371472 [2:47:14<16:09:45,  3.42it/s]
 46%|████▋     | 172304/371472 [2:47:14<15:42:56,  3.52it/s]
 46%|████▋     | 172305/371472 [2:47:15<15:55:18,  3.47it/s]
 46%|████▋     | 172306/371472 [2:47:15<15:41:38,  3.53it/s]
 46%|████▋     | 172307/371472 [2:47:15<15:44:41,  3.51it/s]
 46%|████▋     | 172308/371472 [2:47:15<15:47:37,  3.50it/s]
 46%|████▋     | 172309/371472 [2:47:16<16:26:18,  3.37it/s]
 46%|████▋     | 172310/371472 [2:47:16<16:01:28,  3.45it/s]
 46%|████▋     | 172311/371472 [2:47:16<15:45:04,  3.51it/s]
 46%|████▋     | 172312/371472 [2:47:17<15:49:14,  3.50it/s]
 46%|████▋     | 172313/371472 [2:47:17<16:01:15,  3.45it/s]
 46%|████▋     | 172314/371472 [2:47:17<16:20:33,  3.39it/s]
 46%|████▋     | 172315/371472 [2:47:18<17:24:07,  3.18it/s]
 46%|████▋     | 172316/371472 [2:47:18<17:05:11,  3.24it/s]
 46%|████▋     | 172317/371472 [2:47:18<17:14:13,  3.21it/s]
 46%|████▋     | 172318/371472 [2:47:18<16:54:18,  3.27it/s]
 46%|████▋     | 172319/371472 [2:47:19<16:59:27,  3.26it/s]
 46%|████▋     | 172320/371472 [2:47:19<17:11:32,  3.22it/s]
                                                            
{'loss': 2.9699, 'learning_rate': 5.827641190286366e-07, 'epoch': 7.42}
+
 46%|████▋     | 172320/371472 [2:47:19<17:11:32,  3.22it/s]
 46%|████▋     | 172321/371472 [2:47:19<16:49:40,  3.29it/s]
 46%|████▋     | 172322/371472 [2:47:20<16:38:49,  3.32it/s]
 46%|████▋     | 172323/371472 [2:47:20<17:07:52,  3.23it/s]
 46%|████▋     | 172324/371472 [2:47:20<17:43:18,  3.12it/s]
 46%|████▋     | 172325/371472 [2:47:21<17:01:42,  3.25it/s]
 46%|████▋     | 172326/371472 [2:47:21<17:25:38,  3.17it/s]
 46%|████▋     | 172327/371472 [2:47:21<16:27:03,  3.36it/s]
 46%|████▋     | 172328/371472 [2:47:21<16:02:59,  3.45it/s]
 46%|████▋     | 172329/371472 [2:47:22<15:58:57,  3.46it/s]
 46%|████▋     | 172330/371472 [2:47:22<16:17:39,  3.39it/s]
 46%|████▋     | 172331/371472 [2:47:22<16:41:49,  3.31it/s]
 46%|████▋     | 172332/371472 [2:47:23<17:19:58,  3.19it/s]
 46%|████▋     | 172333/371472 [2:47:23<16:52:59,  3.28it/s]
 46%|████▋     | 172334/371472 [2:47:23<16:52:48,  3.28it/s]
 46%|████▋     | 172335/371472 [2:47:24<17:04:09,  3.24it/s]
 46%|████▋     | 172336/371472 [2:47:24<16:45:01,  3.30it/s]
 46%|████▋     | 172337/371472 [2:47:24<16:41:05,  3.32it/s]
 46%|████▋     | 172338/371472 [2:47:25<16:54:17,  3.27it/s]
 46%|████▋     | 172339/371472 [2:47:25<16:44:23,  3.30it/s]
 46%|████▋     | 172340/371472 [2:47:25<16:29:40,  3.35it/s]
                                                            
{'loss': 3.0142, 'learning_rate': 5.827156370531577e-07, 'epoch': 7.42}
+
 46%|████▋     | 172340/371472 [2:47:25<16:29:40,  3.35it/s]
 46%|████▋     | 172341/371472 [2:47:25<17:36:49,  3.14it/s]
 46%|████▋     | 172342/371472 [2:47:26<17:17:39,  3.20it/s]
 46%|████▋     | 172343/371472 [2:47:26<17:13:58,  3.21it/s]
 46%|████▋     | 172344/371472 [2:47:26<16:59:39,  3.25it/s]
 46%|████▋     | 172345/371472 [2:47:27<17:13:10,  3.21it/s]
 46%|████▋     | 172346/371472 [2:47:27<17:49:16,  3.10it/s]
 46%|████▋     | 172347/371472 [2:47:27<18:50:55,  2.93it/s]
 46%|████▋     | 172348/371472 [2:47:28<18:01:38,  3.07it/s]
 46%|████▋     | 172349/371472 [2:47:28<18:10:10,  3.04it/s]
 46%|████▋     | 172350/371472 [2:47:28<17:48:45,  3.11it/s]
 46%|████▋     | 172351/371472 [2:47:29<17:21:36,  3.19it/s]
 46%|████▋     | 172352/371472 [2:47:29<17:02:59,  3.24it/s]
 46%|████▋     | 172353/371472 [2:47:29<16:40:03,  3.32it/s]
 46%|████▋     | 172354/371472 [2:47:30<16:41:24,  3.31it/s]
 46%|████▋     | 172355/371472 [2:47:30<17:11:45,  3.22it/s]
 46%|████▋     | 172356/371472 [2:47:30<17:41:19,  3.13it/s]
 46%|████▋     | 172357/371472 [2:47:30<16:52:43,  3.28it/s]
 46%|████▋     | 172358/371472 [2:47:31<17:13:10,  3.21it/s]
 46%|████▋     | 172359/371472 [2:47:31<17:04:02,  3.24it/s]
 46%|████▋     | 172360/371472 [2:47:31<16:50:52,  3.28it/s]
                                                            
{'loss': 2.7816, 'learning_rate': 5.826671550776789e-07, 'epoch': 7.42}
+
 46%|████▋     | 172360/371472 [2:47:31<16:50:52,  3.28it/s]
 46%|████▋     | 172361/371472 [2:47:32<16:38:06,  3.32it/s]
 46%|████▋     | 172362/371472 [2:47:32<16:15:52,  3.40it/s]
 46%|████▋     | 172363/371472 [2:47:32<17:03:13,  3.24it/s]
 46%|████▋     | 172364/371472 [2:47:33<17:23:43,  3.18it/s]
 46%|████▋     | 172365/371472 [2:47:33<17:38:48,  3.13it/s]
 46%|████▋     | 172366/371472 [2:47:33<17:33:03,  3.15it/s]
 46%|████▋     | 172367/371472 [2:47:34<17:13:18,  3.21it/s]
 46%|████▋     | 172368/371472 [2:47:34<17:05:09,  3.24it/s]
 46%|████▋     | 172369/371472 [2:47:34<16:38:46,  3.32it/s]
 46%|████▋     | 172370/371472 [2:47:35<17:12:10,  3.21it/s]
 46%|████▋     | 172371/371472 [2:47:35<18:00:52,  3.07it/s]
 46%|████▋     | 172372/371472 [2:47:35<18:09:34,  3.05it/s]
 46%|████▋     | 172373/371472 [2:47:36<17:59:10,  3.07it/s]
 46%|████▋     | 172374/371472 [2:47:36<17:57:46,  3.08it/s]
 46%|████▋     | 172375/371472 [2:47:36<19:32:28,  2.83it/s]
 46%|████▋     | 172376/371472 [2:47:37<18:57:12,  2.92it/s]
 46%|████▋     | 172377/371472 [2:47:37<18:55:48,  2.92it/s]
 46%|████▋     | 172378/371472 [2:47:37<18:14:53,  3.03it/s]
 46%|████▋     | 172379/371472 [2:47:38<18:05:38,  3.06it/s]
 46%|████▋     | 172380/371472 [2:47:38<18:30:44,  2.99it/s]
                                                            
{'loss': 2.8549, 'learning_rate': 5.826186731022e-07, 'epoch': 7.42}
+
 46%|████▋     | 172380/371472 [2:47:38<18:30:44,  2.99it/s]
 46%|████▋     | 172381/371472 [2:47:38<18:38:17,  2.97it/s]
 46%|████▋     | 172382/371472 [2:47:39<17:49:30,  3.10it/s]
 46%|████▋     | 172383/371472 [2:47:39<17:34:20,  3.15it/s]
 46%|████▋     | 172384/371472 [2:47:39<17:19:13,  3.19it/s]
 46%|████▋     | 172385/371472 [2:47:39<17:41:55,  3.12it/s]
 46%|████▋     | 172386/371472 [2:47:40<17:32:31,  3.15it/s]
 46%|████▋     | 172387/371472 [2:47:40<16:54:37,  3.27it/s]
 46%|████▋     | 172388/371472 [2:47:40<16:28:11,  3.36it/s]
 46%|████▋     | 172389/371472 [2:47:41<16:06:24,  3.43it/s]
 46%|████▋     | 172390/371472 [2:47:41<16:41:14,  3.31it/s]
 46%|████▋     | 172391/371472 [2:47:41<16:31:49,  3.35it/s]
 46%|████▋     | 172392/371472 [2:47:42<16:15:48,  3.40it/s]
 46%|████▋     | 172393/371472 [2:47:42<19:01:38,  2.91it/s]
 46%|████▋     | 172394/371472 [2:47:42<18:13:55,  3.03it/s]
 46%|████▋     | 172395/371472 [2:47:43<17:33:29,  3.15it/s]
 46%|████▋     | 172396/371472 [2:47:43<16:53:16,  3.27it/s]
 46%|████▋     | 172397/371472 [2:47:43<16:35:49,  3.33it/s]
 46%|████▋     | 172398/371472 [2:47:43<16:32:06,  3.34it/s]
 46%|████▋     | 172399/371472 [2:47:44<16:38:04,  3.32it/s]
 46%|████▋     | 172400/371472 [2:47:44<16:12:41,  3.41it/s]
                                                            
{'loss': 2.9331, 'learning_rate': 5.825701911267211e-07, 'epoch': 7.43}
+
 46%|████▋     | 172400/371472 [2:47:44<16:12:41,  3.41it/s]
 46%|████▋     | 172401/371472 [2:47:44<16:16:46,  3.40it/s]
 46%|████▋     | 172402/371472 [2:47:45<16:05:22,  3.44it/s]
 46%|████▋     | 172403/371472 [2:47:45<16:39:14,  3.32it/s]
 46%|████▋     | 172404/371472 [2:47:45<16:44:41,  3.30it/s]
 46%|████▋     | 172405/371472 [2:47:46<16:23:57,  3.37it/s]
 46%|████▋     | 172406/371472 [2:47:46<17:34:03,  3.15it/s]
 46%|████▋     | 172407/371472 [2:47:46<16:54:20,  3.27it/s]
 46%|████▋     | 172408/371472 [2:47:46<16:39:46,  3.32it/s]
 46%|████▋     | 172409/371472 [2:47:47<16:45:11,  3.30it/s]
 46%|████▋     | 172410/371472 [2:47:47<16:13:41,  3.41it/s]
 46%|████▋     | 172411/371472 [2:47:47<16:27:15,  3.36it/s]
 46%|████▋     | 172412/371472 [2:47:48<17:10:43,  3.22it/s]
 46%|████▋     | 172413/371472 [2:47:48<16:35:49,  3.33it/s]
 46%|████▋     | 172414/371472 [2:47:48<18:15:22,  3.03it/s]
 46%|████▋     | 172415/371472 [2:47:49<18:01:38,  3.07it/s]
 46%|████▋     | 172416/371472 [2:47:49<17:23:53,  3.18it/s]
 46%|████▋     | 172417/371472 [2:47:49<19:50:11,  2.79it/s]
 46%|████▋     | 172418/371472 [2:47:50<18:42:14,  2.96it/s]
 46%|████▋     | 172419/371472 [2:47:50<18:55:25,  2.92it/s]
 46%|████▋     | 172420/371472 [2:47:50<18:08:06,  3.05it/s]
                                                            
{'loss': 2.8974, 'learning_rate': 5.825217091512421e-07, 'epoch': 7.43}
+
 46%|████▋     | 172420/371472 [2:47:50<18:08:06,  3.05it/s]
 46%|████▋     | 172421/371472 [2:47:51<18:48:38,  2.94it/s]
 46%|████▋     | 172422/371472 [2:47:51<18:09:10,  3.05it/s]
 46%|████▋     | 172423/371472 [2:47:51<17:13:10,  3.21it/s]
 46%|████▋     | 172424/371472 [2:47:52<16:41:12,  3.31it/s]
 46%|████▋     | 172425/371472 [2:47:52<16:01:08,  3.45it/s]
 46%|████▋     | 172426/371472 [2:47:52<17:09:54,  3.22it/s]
 46%|████▋     | 172427/371472 [2:47:53<17:15:10,  3.20it/s]
 46%|████▋     | 172428/371472 [2:47:53<17:07:12,  3.23it/s]
 46%|████▋     | 172429/371472 [2:47:53<16:33:32,  3.34it/s]
 46%|████▋     | 172430/371472 [2:47:53<16:11:08,  3.42it/s]
 46%|████▋     | 172431/371472 [2:47:54<16:24:52,  3.37it/s]
 46%|████▋     | 172432/371472 [2:47:54<16:36:16,  3.33it/s]
 46%|████▋     | 172433/371472 [2:47:54<16:37:56,  3.32it/s]
 46%|████▋     | 172434/371472 [2:47:55<16:16:21,  3.40it/s]
 46%|████▋     | 172435/371472 [2:47:55<16:13:15,  3.41it/s]
 46%|████▋     | 172436/371472 [2:47:55<16:05:43,  3.44it/s]
 46%|████▋     | 172437/371472 [2:47:55<15:56:40,  3.47it/s]
 46%|████▋     | 172438/371472 [2:47:56<15:38:14,  3.54it/s]
 46%|████▋     | 172439/371472 [2:47:56<15:47:56,  3.50it/s]
 46%|████▋     | 172440/371472 [2:47:56<16:42:20,  3.31it/s]
                                                            
{'loss': 3.2114, 'learning_rate': 5.824732271757633e-07, 'epoch': 7.43}
+
 46%|████▋     | 172440/371472 [2:47:56<16:42:20,  3.31it/s]
 46%|████▋     | 172441/371472 [2:47:57<18:49:55,  2.94it/s]
 46%|████▋     | 172442/371472 [2:47:57<17:58:57,  3.07it/s]
 46%|████▋     | 172443/371472 [2:47:57<17:53:04,  3.09it/s]
 46%|████▋     | 172444/371472 [2:47:58<17:15:24,  3.20it/s]
 46%|████▋     | 172445/371472 [2:47:58<16:48:19,  3.29it/s]
 46%|████▋     | 172446/371472 [2:47:58<16:16:08,  3.40it/s]
 46%|████▋     | 172447/371472 [2:47:59<16:24:45,  3.37it/s]
 46%|████▋     | 172448/371472 [2:47:59<15:57:53,  3.46it/s]
 46%|████▋     | 172449/371472 [2:47:59<16:08:50,  3.42it/s]
 46%|████▋     | 172450/371472 [2:47:59<16:52:13,  3.28it/s]
 46%|████▋     | 172451/371472 [2:48:00<17:50:49,  3.10it/s]
 46%|████▋     | 172452/371472 [2:48:00<17:28:50,  3.16it/s]
 46%|████▋     | 172453/371472 [2:48:00<16:39:58,  3.32it/s]
 46%|████▋     | 172454/371472 [2:48:01<16:35:01,  3.33it/s]
 46%|████▋     | 172455/371472 [2:48:01<16:35:08,  3.33it/s]
 46%|████▋     | 172456/371472 [2:48:01<16:03:51,  3.44it/s]
 46%|████▋     | 172457/371472 [2:48:01<16:00:26,  3.45it/s]
 46%|████▋     | 172458/371472 [2:48:02<16:21:37,  3.38it/s]
 46%|████▋     | 172459/371472 [2:48:02<16:01:53,  3.45it/s]
 46%|████▋     | 172460/371472 [2:48:02<15:52:17,  3.48it/s]
                                                            
{'loss': 2.9152, 'learning_rate': 5.824247452002844e-07, 'epoch': 7.43}
+
 46%|████▋     | 172460/371472 [2:48:02<15:52:17,  3.48it/s]
 46%|████▋     | 172461/371472 [2:48:03<15:56:44,  3.47it/s]
 46%|████▋     | 172462/371472 [2:48:03<16:14:50,  3.40it/s]
 46%|████▋     | 172463/371472 [2:48:03<16:16:01,  3.40it/s]
 46%|████▋     | 172464/371472 [2:48:04<16:12:11,  3.41it/s]
 46%|████▋     | 172465/371472 [2:48:04<17:03:53,  3.24it/s]
 46%|████▋     | 172466/371472 [2:48:04<16:49:22,  3.29it/s]
 46%|████▋     | 172467/371472 [2:48:04<16:30:16,  3.35it/s]
 46%|████▋     | 172468/371472 [2:48:05<16:22:04,  3.38it/s]
 46%|████▋     | 172469/371472 [2:48:05<16:09:24,  3.42it/s]
 46%|████▋     | 172470/371472 [2:48:05<16:03:17,  3.44it/s]
 46%|████▋     | 172471/371472 [2:48:06<15:46:29,  3.50it/s]
 46%|████▋     | 172472/371472 [2:48:06<15:40:09,  3.53it/s]
 46%|████▋     | 172473/371472 [2:48:06<15:37:31,  3.54it/s]
 46%|████▋     | 172474/371472 [2:48:06<15:55:44,  3.47it/s]
 46%|████▋     | 172475/371472 [2:48:07<16:11:41,  3.41it/s]
 46%|████▋     | 172476/371472 [2:48:07<16:13:35,  3.41it/s]
 46%|████▋     | 172477/371472 [2:48:07<16:27:45,  3.36it/s]
 46%|████▋     | 172478/371472 [2:48:08<16:15:53,  3.40it/s]
 46%|████▋     | 172479/371472 [2:48:08<15:51:53,  3.48it/s]
 46%|████▋     | 172480/371472 [2:48:08<15:54:04,  3.48it/s]
                                                            
{'loss': 2.8957, 'learning_rate': 5.823762632248055e-07, 'epoch': 7.43}
+
 46%|████▋     | 172480/371472 [2:48:08<15:54:04,  3.48it/s]
 46%|████▋     | 172481/371472 [2:48:09<16:02:11,  3.45it/s]
 46%|████▋     | 172482/371472 [2:48:09<18:13:49,  3.03it/s]
 46%|████▋     | 172483/371472 [2:48:09<17:28:25,  3.16it/s]
 46%|████▋     | 172484/371472 [2:48:10<17:24:16,  3.18it/s]
 46%|████▋     | 172485/371472 [2:48:10<17:43:45,  3.12it/s]
 46%|████▋     | 172486/371472 [2:48:10<18:02:51,  3.06it/s]
 46%|████▋     | 172487/371472 [2:48:11<17:47:06,  3.11it/s]
 46%|████▋     | 172488/371472 [2:48:11<17:28:33,  3.16it/s]
 46%|████▋     | 172489/371472 [2:48:11<16:52:46,  3.27it/s]
 46%|████▋     | 172490/371472 [2:48:11<16:50:18,  3.28it/s]
 46%|████▋     | 172491/371472 [2:48:12<16:32:22,  3.34it/s]
 46%|████▋     | 172492/371472 [2:48:12<16:34:29,  3.33it/s]
 46%|████▋     | 172493/371472 [2:48:12<16:52:21,  3.28it/s]
 46%|████▋     | 172494/371472 [2:48:13<16:30:12,  3.35it/s]
 46%|████▋     | 172495/371472 [2:48:13<16:19:39,  3.39it/s]
 46%|████▋     | 172496/371472 [2:48:13<16:47:37,  3.29it/s]
 46%|████▋     | 172497/371472 [2:48:13<16:10:20,  3.42it/s]
 46%|████▋     | 172498/371472 [2:48:14<16:07:18,  3.43it/s]
 46%|████▋     | 172499/371472 [2:48:14<16:05:39,  3.43it/s]
 46%|████▋     | 172500/371472 [2:48:14<16:05:12,  3.44it/s]
                                                            
{'loss': 2.8788, 'learning_rate': 5.823277812493266e-07, 'epoch': 7.43}
+
 46%|████▋     | 172500/371472 [2:48:14<16:05:12,  3.44it/s]
 46%|████▋     | 172501/371472 [2:48:15<15:47:46,  3.50it/s]
 46%|████▋     | 172502/371472 [2:48:15<15:24:45,  3.59it/s]
 46%|████▋     | 172503/371472 [2:48:15<15:46:38,  3.50it/s]
 46%|████▋     | 172504/371472 [2:48:16<19:54:27,  2.78it/s]
 46%|████▋     | 172505/371472 [2:48:16<19:47:08,  2.79it/s]
 46%|████▋     | 172506/371472 [2:48:16<18:41:37,  2.96it/s]
 46%|████▋     | 172507/371472 [2:48:17<18:33:15,  2.98it/s]
 46%|████▋     | 172508/371472 [2:48:17<17:26:08,  3.17it/s]
 46%|████▋     | 172509/371472 [2:48:17<16:49:12,  3.29it/s]
 46%|████▋     | 172510/371472 [2:48:18<16:43:52,  3.30it/s]
 46%|████▋     | 172511/371472 [2:48:18<17:01:47,  3.25it/s]
 46%|████▋     | 172512/371472 [2:48:18<16:33:05,  3.34it/s]
 46%|████▋     | 172513/371472 [2:48:18<16:03:58,  3.44it/s]
 46%|████▋     | 172514/371472 [2:48:19<16:06:16,  3.43it/s]
 46%|████▋     | 172515/371472 [2:48:19<15:26:48,  3.58it/s]
 46%|████▋     | 172516/371472 [2:48:19<16:01:33,  3.45it/s]
 46%|████▋     | 172517/371472 [2:48:20<15:59:27,  3.46it/s]
 46%|████▋     | 172518/371472 [2:48:20<16:51:57,  3.28it/s]
 46%|████▋     | 172519/371472 [2:48:20<17:01:28,  3.25it/s]
 46%|████▋     | 172520/371472 [2:48:21<16:49:26,  3.28it/s]
                                                            
{'loss': 2.8834, 'learning_rate': 5.822792992738478e-07, 'epoch': 7.43}
+
 46%|████▋     | 172520/371472 [2:48:21<16:49:26,  3.28it/s]
 46%|████▋     | 172521/371472 [2:48:21<16:29:11,  3.35it/s]
 46%|████▋     | 172522/371472 [2:48:21<16:42:35,  3.31it/s]
 46%|████▋     | 172523/371472 [2:48:21<16:47:43,  3.29it/s]
 46%|████▋     | 172524/371472 [2:48:22<16:28:44,  3.35it/s]
 46%|████▋     | 172525/371472 [2:48:22<16:38:53,  3.32it/s]
 46%|████▋     | 172526/371472 [2:48:22<16:53:02,  3.27it/s]
 46%|████▋     | 172527/371472 [2:48:23<16:36:38,  3.33it/s]
 46%|████▋     | 172528/371472 [2:48:23<16:23:05,  3.37it/s]
 46%|████▋     | 172529/371472 [2:48:23<16:28:48,  3.35it/s]
 46%|████▋     | 172530/371472 [2:48:24<16:39:17,  3.32it/s]
 46%|████▋     | 172531/371472 [2:48:24<16:35:49,  3.33it/s]
 46%|████▋     | 172532/371472 [2:48:24<16:48:03,  3.29it/s]
 46%|████▋     | 172533/371472 [2:48:24<16:22:25,  3.37it/s]
 46%|████▋     | 172534/371472 [2:48:25<15:56:15,  3.47it/s]
 46%|████▋     | 172535/371472 [2:48:25<15:47:56,  3.50it/s]
 46%|████▋     | 172536/371472 [2:48:25<15:38:43,  3.53it/s]
 46%|████▋     | 172537/371472 [2:48:26<17:56:23,  3.08it/s]
 46%|████▋     | 172538/371472 [2:48:26<17:30:25,  3.16it/s]
 46%|████▋     | 172539/371472 [2:48:26<17:04:34,  3.24it/s]
 46%|████▋     | 172540/371472 [2:48:27<17:12:17,  3.21it/s]
                                                            
{'loss': 3.0285, 'learning_rate': 5.822308172983688e-07, 'epoch': 7.43}
+
 46%|████▋     | 172540/371472 [2:48:27<17:12:17,  3.21it/s]
 46%|████▋     | 172541/371472 [2:48:27<18:14:50,  3.03it/s]
 46%|████▋     | 172542/371472 [2:48:27<17:49:38,  3.10it/s]
 46%|████▋     | 172543/371472 [2:48:28<18:10:26,  3.04it/s]
 46%|████▋     | 172544/371472 [2:48:28<17:47:08,  3.11it/s]
 46%|████▋     | 172545/371472 [2:48:28<17:28:23,  3.16it/s]
 46%|████▋     | 172546/371472 [2:48:28<16:50:28,  3.28it/s]
 46%|███���▋     | 172547/371472 [2:48:29<16:39:12,  3.32it/s]
 46%|████▋     | 172548/371472 [2:48:29<16:49:25,  3.28it/s]
 46%|████▋     | 172549/371472 [2:48:29<17:45:49,  3.11it/s]
 46%|████▋     | 172550/371472 [2:48:30<17:30:40,  3.16it/s]
 46%|████▋     | 172551/371472 [2:48:30<17:38:02,  3.13it/s]
 46%|████▋     | 172552/371472 [2:48:30<17:31:04,  3.15it/s]
 46%|████▋     | 172553/371472 [2:48:31<17:22:54,  3.18it/s]
 46%|████▋     | 172554/371472 [2:48:31<19:10:25,  2.88it/s]
 46%|████▋     | 172555/371472 [2:48:31<19:03:13,  2.90it/s]
 46%|████▋     | 172556/371472 [2:48:32<18:31:19,  2.98it/s]
 46%|████▋     | 172557/371472 [2:48:32<17:21:40,  3.18it/s]
 46%|████▋     | 172558/371472 [2:48:32<16:47:45,  3.29it/s]
 46%|████▋     | 172559/371472 [2:48:33<16:35:56,  3.33it/s]
 46%|████▋     | 172560/371472 [2:48:33<16:03:23,  3.44it/s]
                                                            
{'loss': 2.9356, 'learning_rate': 5.821823353228899e-07, 'epoch': 7.43}
+
 46%|████▋     | 172560/371472 [2:48:33<16:03:23,  3.44it/s]
 46%|████▋     | 172561/371472 [2:48:33<16:05:07,  3.43it/s]
 46%|████▋     | 172562/371472 [2:48:33<16:24:31,  3.37it/s]
 46%|████▋     | 172563/371472 [2:48:34<16:30:49,  3.35it/s]
 46%|████▋     | 172564/371472 [2:48:34<16:29:22,  3.35it/s]
 46%|████▋     | 172565/371472 [2:48:34<16:34:16,  3.33it/s]
 46%|████▋     | 172566/371472 [2:48:35<16:24:19,  3.37it/s]
 46%|████▋     | 172567/371472 [2:48:35<16:08:12,  3.42it/s]
 46%|████▋     | 172568/371472 [2:48:35<16:49:41,  3.28it/s]
 46%|████▋     | 172569/371472 [2:48:36<16:57:57,  3.26it/s]
 46%|████▋     | 172570/371472 [2:48:36<16:40:12,  3.31it/s]
 46%|████▋     | 172571/371472 [2:48:36<16:41:06,  3.31it/s]
 46%|████▋     | 172572/371472 [2:48:36<16:35:48,  3.33it/s]
 46%|████▋     | 172573/371472 [2:48:37<16:18:48,  3.39it/s]
 46%|████▋     | 172574/371472 [2:48:37<16:24:05,  3.37it/s]
 46%|████▋     | 172575/371472 [2:48:37<16:39:15,  3.32it/s]
 46%|████▋     | 172576/371472 [2:48:38<16:41:36,  3.31it/s]
 46%|████▋     | 172577/371472 [2:48:38<16:26:47,  3.36it/s]
 46%|████▋     | 172578/371472 [2:48:38<16:23:56,  3.37it/s]
 46%|████▋     | 172579/371472 [2:48:39<16:05:15,  3.43it/s]
 46%|████▋     | 172580/371472 [2:48:39<17:21:20,  3.18it/s]
                                                            
{'loss': 2.9336, 'learning_rate': 5.82133853347411e-07, 'epoch': 7.43}
+
 46%|████▋     | 172580/371472 [2:48:39<17:21:20,  3.18it/s]
 46%|████▋     | 172581/371472 [2:48:39<16:50:15,  3.28it/s]
 46%|████▋     | 172582/371472 [2:48:39<16:49:50,  3.28it/s]
 46%|████▋     | 172583/371472 [2:48:40<17:16:53,  3.20it/s]
 46%|████▋     | 172584/371472 [2:48:40<16:39:31,  3.32it/s]
 46%|████▋     | 172585/371472 [2:48:40<17:05:39,  3.23it/s]
 46%|████▋     | 172586/371472 [2:48:41<18:54:32,  2.92it/s]
 46%|████▋     | 172587/371472 [2:48:41<18:47:37,  2.94it/s]
 46%|████▋     | 172588/371472 [2:48:41<18:32:02,  2.98it/s]
 46%|████▋     | 172589/371472 [2:48:42<18:13:10,  3.03it/s]
 46%|████▋     | 172590/371472 [2:48:42<17:19:03,  3.19it/s]
 46%|████▋     | 172591/371472 [2:48:42<16:37:10,  3.32it/s]
 46%|████▋     | 172592/371472 [2:48:43<17:03:23,  3.24it/s]
 46%|████▋     | 172593/371472 [2:48:43<17:05:43,  3.23it/s]
 46%|████▋     | 172594/371472 [2:48:43<17:11:28,  3.21it/s]
 46%|████▋     | 172595/371472 [2:48:44<16:37:13,  3.32it/s]
 46%|████▋     | 172596/371472 [2:48:44<16:20:41,  3.38it/s]
 46%|████▋     | 172597/371472 [2:48:44<16:55:59,  3.26it/s]
 46%|████▋     | 172598/371472 [2:48:45<17:00:54,  3.25it/s]
 46%|████▋     | 172599/371472 [2:48:45<16:29:37,  3.35it/s]
 46%|████▋     | 172600/371472 [2:48:45<16:15:02,  3.40it/s]
                                                            
{'loss': 2.8127, 'learning_rate': 5.820853713719322e-07, 'epoch': 7.43}
+
 46%|████▋     | 172600/371472 [2:48:45<16:15:02,  3.40it/s]
 46%|████▋     | 172601/371472 [2:48:45<16:17:57,  3.39it/s]
 46%|████▋     | 172602/371472 [2:48:46<16:14:46,  3.40it/s]
 46%|████▋     | 172603/371472 [2:48:46<17:26:25,  3.17it/s]
 46%|████▋     | 172604/371472 [2:48:46<17:26:24,  3.17it/s]
 46%|████▋     | 172605/371472 [2:48:47<17:04:42,  3.23it/s]
 46%|████▋     | 172606/371472 [2:48:47<17:28:04,  3.16it/s]
 46%|████▋     | 172607/371472 [2:48:47<17:58:33,  3.07it/s]
 46%|████▋     | 172608/371472 [2:48:48<17:28:47,  3.16it/s]
 46%|████▋     | 172609/371472 [2:48:48<16:53:46,  3.27it/s]
 46%|████▋     | 172610/371472 [2:48:48<16:51:15,  3.28it/s]
 46%|████▋     | 172611/371472 [2:48:49<16:46:32,  3.29it/s]
 46%|████▋     | 172612/371472 [2:48:49<16:44:25,  3.30it/s]
 46%|████▋     | 172613/371472 [2:48:49<16:24:04,  3.37it/s]
 46%|████▋     | 172614/371472 [2:48:49<16:20:11,  3.38it/s]
 46%|████▋     | 172615/371472 [2:48:50<16:21:59,  3.38it/s]
 46%|████▋     | 172616/371472 [2:48:50<16:40:24,  3.31it/s]
 46%|████▋     | 172617/371472 [2:48:50<16:21:48,  3.38it/s]
 46%|████▋     | 172618/371472 [2:48:51<16:13:55,  3.40it/s]
 46%|████▋     | 172619/371472 [2:48:51<16:24:10,  3.37it/s]
 46%|████▋     | 172620/371472 [2:48:51<16:41:04,  3.31it/s]
                                                            
{'loss': 3.0354, 'learning_rate': 5.820368893964533e-07, 'epoch': 7.44}
+
 46%|████▋     | 172620/371472 [2:48:51<16:41:04,  3.31it/s]
 46%|████▋     | 172621/371472 [2:48:52<17:06:32,  3.23it/s]
 46%|████▋     | 172622/371472 [2:48:52<16:52:34,  3.27it/s]
 46%|████▋     | 172623/371472 [2:48:52<17:27:12,  3.16it/s]
 46%|████▋     | 172624/371472 [2:48:52<17:11:42,  3.21it/s]
 46%|████▋     | 172625/371472 [2:48:53<16:58:07,  3.26it/s]
 46%|████▋     | 172626/371472 [2:48:53<16:41:34,  3.31it/s]
 46%|████▋     | 172627/371472 [2:48:53<16:59:16,  3.25it/s]
 46%|████▋     | 172628/371472 [2:48:54<16:30:01,  3.35it/s]
 46%|████▋     | 172629/371472 [2:48:54<16:29:12,  3.35it/s]
 46%|████▋     | 172630/371472 [2:48:54<15:59:04,  3.46it/s]
 46%|████▋     | 172631/371472 [2:48:54<16:03:35,  3.44it/s]
 46%|████▋     | 172632/371472 [2:48:55<17:40:03,  3.13it/s]
 46%|████▋     | 172633/371472 [2:48:55<17:33:41,  3.15it/s]
 46%|████▋     | 172634/371472 [2:48:56<17:24:48,  3.17it/s]
 46%|████▋     | 172635/371472 [2:48:56<17:10:24,  3.22it/s]
 46%|████▋     | 172636/371472 [2:48:56<17:04:01,  3.24it/s]
 46%|████▋     | 172637/371472 [2:48:56<16:55:51,  3.26it/s]
 46%|████▋     | 172638/371472 [2:48:57<17:56:45,  3.08it/s]
 46%|████▋     | 172639/371472 [2:48:57<17:29:14,  3.16it/s]
 46%|████▋     | 172640/371472 [2:48:57<17:14:26,  3.20it/s]
                                                            
{'loss': 2.916, 'learning_rate': 5.819884074209744e-07, 'epoch': 7.44}
+
 46%|████▋     | 172640/371472 [2:48:57<17:14:26,  3.20it/s]
 46%|████▋     | 172641/371472 [2:48:58<17:54:50,  3.08it/s]
 46%|████▋     | 172642/371472 [2:48:58<17:57:48,  3.07it/s]
 46%|████▋     | 172643/371472 [2:48:58<17:34:38,  3.14it/s]
 46%|████▋     | 172644/371472 [2:48:59<17:12:58,  3.21it/s]
 46%|████▋     | 172645/371472 [2:48:59<18:21:19,  3.01it/s]
 46%|████▋     | 172646/371472 [2:48:59<17:49:12,  3.10it/s]
 46%|████▋     | 172647/371472 [2:49:00<17:37:04,  3.13it/s]
 46%|████▋     | 172648/371472 [2:49:00<17:16:57,  3.20it/s]
 46%|████▋     | 172649/371472 [2:49:00<16:59:43,  3.25it/s]
 46%|████▋     | 172650/371472 [2:49:01<16:45:21,  3.30it/s]
 46%|████▋     | 172651/371472 [2:49:01<16:58:46,  3.25it/s]
 46%|████▋     | 172652/371472 [2:49:01<16:46:35,  3.29it/s]
 46%|████▋     | 172653/371472 [2:49:01<16:28:18,  3.35it/s]
 46%|████▋     | 172654/371472 [2:49:02<16:33:56,  3.33it/s]
 46%|████▋     | 172655/371472 [2:49:02<16:25:25,  3.36it/s]
 46%|████▋     | 172656/371472 [2:49:02<16:07:27,  3.43it/s]
 46%|████▋     | 172657/371472 [2:49:03<16:27:05,  3.36it/s]
 46%|████▋     | 172658/371472 [2:49:03<16:15:08,  3.40it/s]
 46%|████▋     | 172659/371472 [2:49:03<16:25:08,  3.36it/s]
 46%|████▋     | 172660/371472 [2:49:04<17:25:22,  3.17it/s]
                                                            
{'loss': 2.8452, 'learning_rate': 5.819399254454954e-07, 'epoch': 7.44}
+
 46%|████▋     | 172660/371472 [2:49:04<17:25:22,  3.17it/s]
 46%|████▋     | 172661/371472 [2:49:04<17:22:55,  3.18it/s]
 46%|████▋     | 172662/371472 [2:49:04<17:05:02,  3.23it/s]
 46%|████▋     | 172663/371472 [2:49:05<17:24:21,  3.17it/s]
 46%|████▋     | 172664/371472 [2:49:05<16:59:41,  3.25it/s]
 46%|████▋     | 172665/371472 [2:49:05<16:47:38,  3.29it/s]
 46%|████▋     | 172666/371472 [2:49:05<17:06:47,  3.23it/s]
 46%|████▋     | 172667/371472 [2:49:06<16:35:32,  3.33it/s]
 46%|████▋     | 172668/371472 [2:49:06<16:07:56,  3.42it/s]
 46%|████▋     | 172669/371472 [2:49:06<16:04:10,  3.44it/s]
 46%|████▋     | 172670/371472 [2:49:07<16:07:49,  3.42it/s]
 46%|████▋     | 172671/371472 [2:49:07<15:54:15,  3.47it/s]
 46%|████▋     | 172672/371472 [2:49:07<16:27:42,  3.35it/s]
 46%|████▋     | 172673/371472 [2:49:07<16:24:14,  3.37it/s]
 46%|████▋     | 172674/371472 [2:49:08<16:38:51,  3.32it/s]
 46%|████▋     | 172675/371472 [2:49:08<16:22:33,  3.37it/s]
 46%|████▋     | 172676/371472 [2:49:08<17:05:27,  3.23it/s]
 46%|████▋     | 172677/371472 [2:49:09<17:08:38,  3.22it/s]
 46%|████▋     | 172678/371472 [2:49:09<17:02:08,  3.24it/s]
 46%|████▋     | 172679/371472 [2:49:09<16:31:31,  3.34it/s]
 46%|████▋     | 172680/371472 [2:49:10<16:33:38,  3.33it/s]
                                                            
{'loss': 2.8804, 'learning_rate': 5.818914434700165e-07, 'epoch': 7.44}
+
 46%|████▋     | 172680/371472 [2:49:10<16:33:38,  3.33it/s]
 46%|████▋     | 172681/371472 [2:49:10<17:02:21,  3.24it/s]
 46%|████▋     | 172682/371472 [2:49:10<16:47:19,  3.29it/s]
 46%|████▋     | 172683/371472 [2:49:11<16:56:17,  3.26it/s]
 46%|████▋     | 172684/371472 [2:49:11<17:39:05,  3.13it/s]
 46%|████▋     | 172685/371472 [2:49:11<17:15:15,  3.20it/s]
 46%|████▋     | 172686/371472 [2:49:11<17:05:29,  3.23it/s]
 46%|████▋     | 172687/371472 [2:49:12<16:30:07,  3.35it/s]
 46%|████▋     | 172688/371472 [2:49:12<16:41:11,  3.31it/s]
 46%|████▋     | 172689/371472 [2:49:12<16:19:05,  3.38it/s]
 46%|████▋     | 172690/371472 [2:49:13<16:10:42,  3.41it/s]
 46%|████▋     | 172691/371472 [2:49:13<16:42:31,  3.30it/s]
 46%|████▋     | 172692/371472 [2:49:13<16:30:06,  3.35it/s]
 46%|████▋     | 172693/371472 [2:49:14<16:23:07,  3.37it/s]
 46%|████▋     | 172694/371472 [2:49:14<15:59:00,  3.45it/s]
 46%|████▋     | 172695/371472 [2:49:14<16:12:07,  3.41it/s]
 46%|████▋     | 172696/371472 [2:49:14<16:18:44,  3.38it/s]
 46%|████▋     | 172697/371472 [2:49:15<16:30:26,  3.34it/s]
 46%|████▋     | 172698/371472 [2:49:15<16:19:17,  3.38it/s]
 46%|████▋     | 172699/371472 [2:49:15<16:16:20,  3.39it/s]
 46%|████▋     | 172700/371472 [2:49:16<18:33:32,  2.98it/s]
                                                            
{'loss': 2.958, 'learning_rate': 5.818429614945377e-07, 'epoch': 7.44}
+
 46%|████▋     | 172700/371472 [2:49:16<18:33:32,  2.98it/s]
 46%|████▋     | 172701/371472 [2:49:16<19:15:30,  2.87it/s]
 46%|████▋     | 172702/371472 [2:49:16<18:12:16,  3.03it/s]
 46%|████▋     | 172703/371472 [2:49:17<17:13:37,  3.21it/s]
 46%|████▋     | 172704/371472 [2:49:17<16:57:19,  3.26it/s]
 46%|████▋     | 172705/371472 [2:49:17<17:35:39,  3.14it/s]
 46%|████▋     | 172706/371472 [2:49:18<17:51:16,  3.09it/s]
 46%|████▋     | 172707/371472 [2:49:18<17:21:37,  3.18it/s]
 46%|████▋     | 172708/371472 [2:49:18<16:42:37,  3.30it/s]
 46%|████▋     | 172709/371472 [2:49:18<16:43:35,  3.30it/s]
 46%|████▋     | 172710/371472 [2:49:19<16:39:15,  3.32it/s]
 46%|████▋     | 172711/371472 [2:49:19<16:20:08,  3.38it/s]
 46%|████▋     | 172712/371472 [2:49:19<16:06:27,  3.43it/s]
 46%|████▋     | 172713/371472 [2:49:20<17:26:40,  3.16it/s]
 46%|████▋     | 172714/371472 [2:49:20<16:47:16,  3.29it/s]
 46%|████▋     | 172715/371472 [2:49:20<16:36:21,  3.32it/s]
 46%|████▋     | 172716/371472 [2:49:21<16:36:53,  3.32it/s]
 46%|████▋     | 172717/371472 [2:49:21<16:20:12,  3.38it/s]
 46%|████▋     | 172718/371472 [2:49:21<16:05:46,  3.43it/s]
 46%|████▋     | 172719/371472 [2:49:21<16:49:19,  3.28it/s]
 46%|████▋     | 172720/371472 [2:49:22<16:44:11,  3.30it/s]
                                                            
{'loss': 2.897, 'learning_rate': 5.817944795190588e-07, 'epoch': 7.44}
+
 46%|████▋     | 172720/371472 [2:49:22<16:44:11,  3.30it/s]
 46%|████▋     | 172721/371472 [2:49:22<16:39:57,  3.31it/s]
 46%|████▋     | 172722/371472 [2:49:22<16:32:46,  3.34it/s]
 46%|████▋     | 172723/371472 [2:49:23<17:17:28,  3.19it/s]
 46%|████▋     | 172724/371472 [2:49:23<17:30:14,  3.15it/s]
 46%|████▋     | 172725/371472 [2:49:23<16:58:23,  3.25it/s]
 46%|████▋     | 172726/371472 [2:49:24<16:58:02,  3.25it/s]
 46%|████▋     | 172727/371472 [2:49:24<16:32:18,  3.34it/s]
 46%|████▋     | 172728/371472 [2:49:24<16:22:03,  3.37it/s]
 46%|████▋     | 172729/371472 [2:49:25<16:14:31,  3.40it/s]
 46%|████▋     | 172730/371472 [2:49:25<16:28:37,  3.35it/s]
 46%|████▋     | 172731/371472 [2:49:25<16:12:42,  3.41it/s]
 46%|████▋     | 172732/371472 [2:49:25<16:27:23,  3.35it/s]
 46%|████▋     | 172733/371472 [2:49:26<16:28:28,  3.35it/s]
 46%|████▋     | 172734/371472 [2:49:26<17:00:00,  3.25it/s]
 47%|████▋     | 172735/371472 [2:49:26<16:50:25,  3.28it/s]
 47%|████▋     | 172736/371472 [2:49:27<16:52:12,  3.27it/s]
 47%|████▋     | 172737/371472 [2:49:27<16:37:08,  3.32it/s]
 47%|████▋     | 172738/371472 [2:49:27<16:32:29,  3.34it/s]
 47%|████▋     | 172739/371472 [2:49:28<17:26:58,  3.16it/s]
 47%|████▋     | 172740/371472 [2:49:28<16:50:37,  3.28it/s]
                                                            
{'loss': 2.895, 'learning_rate': 5.817459975435799e-07, 'epoch': 7.44}
+
 47%|████▋     | 172740/371472 [2:49:28<16:50:37,  3.28it/s]
 47%|████▋     | 172741/371472 [2:49:28<17:26:03,  3.17it/s]
 47%|████▋     | 172742/371472 [2:49:29<17:01:34,  3.24it/s]
 47%|████▋     | 172743/371472 [2:49:29<16:39:14,  3.31it/s]
 47%|████▋     | 172744/371472 [2:49:29<16:56:51,  3.26it/s]
 47%|████▋     | 172745/371472 [2:49:29<16:26:35,  3.36it/s]
 47%|████▋     | 172746/371472 [2:49:30<16:00:46,  3.45it/s]
 47%|████▋     | 172747/371472 [2:49:30<17:02:07,  3.24it/s]
 47%|████▋     | 172748/371472 [2:49:30<16:41:16,  3.31it/s]
 47%|████▋     | 172749/371472 [2:49:31<16:45:03,  3.30it/s]
 47%|████▋     | 172750/371472 [2:49:31<17:39:30,  3.13it/s]
 47%|████▋     | 172751/371472 [2:49:31<17:35:01,  3.14it/s]
 47%|████▋     | 172752/371472 [2:49:32<18:13:16,  3.03it/s]
 47%|████▋     | 172753/371472 [2:49:32<17:19:11,  3.19it/s]
 47%|████▋     | 172754/371472 [2:49:32<17:05:35,  3.23it/s]
 47%|████▋     | 172755/371472 [2:49:33<17:19:25,  3.19it/s]
 47%|████▋     | 172756/371472 [2:49:33<17:14:18,  3.20it/s]
 47%|████▋     | 172757/371472 [2:49:33<16:51:00,  3.28it/s]
 47%|████▋     | 172758/371472 [2:49:33<16:33:45,  3.33it/s]
 47%|████▋     | 172759/371472 [2:49:34<16:45:47,  3.29it/s]
 47%|████▋     | 172760/371472 [2:49:34<17:03:10,  3.24it/s]
                                                            
{'loss': 2.9375, 'learning_rate': 5.816975155681011e-07, 'epoch': 7.44}
+
 47%|████▋     | 172760/371472 [2:49:34<17:03:10,  3.24it/s]
 47%|████▋     | 172761/371472 [2:49:34<16:54:19,  3.27it/s]
 47%|████▋     | 172762/371472 [2:49:35<16:33:54,  3.33it/s]
 47%|████▋     | 172763/371472 [2:49:35<16:25:18,  3.36it/s]
 47%|████▋     | 172764/371472 [2:49:35<16:10:33,  3.41it/s]
 47%|████▋     | 172765/371472 [2:49:35<15:45:12,  3.50it/s]
 47%|████▋     | 172766/371472 [2:49:36<15:37:52,  3.53it/s]
 47%|████▋     | 172767/371472 [2:49:36<15:32:02,  3.55it/s]
 47%|████▋     | 172768/371472 [2:49:36<15:39:45,  3.52it/s]
 47%|████▋     | 172769/371472 [2:49:37<15:49:06,  3.49it/s]
 47%|████▋     | 172770/371472 [2:49:37<15:36:26,  3.54it/s]
 47%|████▋     | 172771/371472 [2:49:37<15:26:21,  3.57it/s]
 47%|████▋     | 172772/371472 [2:49:37<16:16:25,  3.39it/s]
 47%|████▋     | 172773/371472 [2:49:38<16:29:47,  3.35it/s]
 47%|████▋     | 172774/371472 [2:49:38<16:18:04,  3.39it/s]
 47%|████▋     | 172775/371472 [2:49:38<16:30:04,  3.34it/s]
 47%|████▋     | 172776/371472 [2:49:39<16:18:16,  3.39it/s]
 47%|████▋     | 172777/371472 [2:49:39<16:02:17,  3.44it/s]
 47%|████▋     | 172778/371472 [2:49:39<15:59:07,  3.45it/s]
 47%|████▋     | 172779/371472 [2:49:40<17:34:40,  3.14it/s]
 47%|████▋     | 172780/371472 [2:49:40<16:59:57,  3.25it/s]
                                                            
{'loss': 2.9213, 'learning_rate': 5.816490335926221e-07, 'epoch': 7.44}
+
 47%|████▋     | 172780/371472 [2:49:40<16:59:57,  3.25it/s]
 47%|████▋     | 172781/371472 [2:49:40<16:51:05,  3.28it/s]
 47%|████▋     | 172782/371472 [2:49:41<16:54:59,  3.26it/s]
 47%|████▋     | 172783/371472 [2:49:41<17:00:55,  3.24it/s]
 47%|████▋     | 172784/371472 [2:49:41<17:06:15,  3.23it/s]
 47%|████▋     | 172785/371472 [2:49:41<16:48:48,  3.28it/s]
 47%|████▋     | 172786/371472 [2:49:42<16:35:49,  3.33it/s]
 47%|████▋     | 172787/371472 [2:49:42<16:23:06,  3.37it/s]
 47%|████▋     | 172788/371472 [2:49:42<15:52:20,  3.48it/s]
 47%|████▋     | 172789/371472 [2:49:43<16:28:30,  3.35it/s]
 47%|████▋     | 172790/371472 [2:49:43<15:58:09,  3.46it/s]
 47%|████▋     | 172791/371472 [2:49:43<16:10:16,  3.41it/s]
 47%|████▋     | 172792/371472 [2:49:44<17:13:36,  3.20it/s]
 47%|████▋     | 172793/371472 [2:49:44<17:05:49,  3.23it/s]
 47%|████▋     | 172794/371472 [2:49:44<17:06:08,  3.23it/s]
 47%|████▋     | 172795/371472 [2:49:44<16:31:05,  3.34it/s]
 47%|████▋     | 172796/371472 [2:49:45<16:06:11,  3.43it/s]
 47%|████▋     | 172797/371472 [2:49:45<15:56:53,  3.46it/s]
 47%|████▋     | 172798/371472 [2:49:45<16:09:15,  3.42it/s]
 47%|████▋     | 172799/371472 [2:49:46<16:15:47,  3.39it/s]
 47%|████▋     | 172800/371472 [2:49:46<16:16:26,  3.39it/s]
                                                            
{'loss': 2.8961, 'learning_rate': 5.816005516171432e-07, 'epoch': 7.44}
+
 47%|████▋     | 172800/371472 [2:49:46<16:16:26,  3.39it/s]
 47%|████▋     | 172801/371472 [2:49:46<16:09:58,  3.41it/s]
 47%|████▋     | 172802/371472 [2:49:47<17:36:49,  3.13it/s]
 47%|████▋     | 172803/371472 [2:49:47<16:56:44,  3.26it/s]
 47%|████▋     | 172804/371472 [2:49:47<16:57:15,  3.25it/s]
 47%|████▋     | 172805/371472 [2:49:47<16:38:45,  3.32it/s]
 47%|████▋     | 172806/371472 [2:49:48<16:16:46,  3.39it/s]
 47%|████▋     | 172807/371472 [2:49:48<16:17:09,  3.39it/s]
 47%|████▋     | 172808/371472 [2:49:48<15:50:33,  3.48it/s]
 47%|████▋     | 172809/371472 [2:49:49<15:50:03,  3.49it/s]
 47%|████▋     | 172810/371472 [2:49:49<15:56:38,  3.46it/s]
 47%|████▋     | 172811/371472 [2:49:49<16:22:16,  3.37it/s]
 47%|████▋     | 172812/371472 [2:49:49<16:04:10,  3.43it/s]
 47%|████▋     | 172813/371472 [2:49:50<16:19:03,  3.38it/s]
 47%|████▋     | 172814/371472 [2:49:50<16:05:44,  3.43it/s]
 47%|████▋     | 172815/371472 [2:49:50<16:11:43,  3.41it/s]
 47%|████▋     | 172816/371472 [2:49:51<16:13:08,  3.40it/s]
 47%|████▋     | 172817/371472 [2:49:51<16:17:13,  3.39it/s]
 47%|████▋     | 172818/371472 [2:49:51<16:03:21,  3.44it/s]
 47%|████▋     | 172819/371472 [2:49:52<16:32:27,  3.34it/s]
 47%|████▋     | 172820/371472 [2:49:52<17:06:06,  3.23it/s]
                                                            
{'loss': 2.8334, 'learning_rate': 5.815520696416643e-07, 'epoch': 7.44}
+
 47%|████▋     | 172820/371472 [2:49:52<17:06:06,  3.23it/s]
 47%|████▋     | 172821/371472 [2:49:52<16:40:10,  3.31it/s]
 47%|████▋     | 172822/371472 [2:49:53<18:03:10,  3.06it/s]
 47%|████▋     | 172823/371472 [2:49:53<17:32:48,  3.14it/s]
 47%|████▋     | 172824/371472 [2:49:53<16:58:38,  3.25it/s]
 47%|████▋     | 172825/371472 [2:49:53<16:54:53,  3.26it/s]
 47%|████▋     | 172826/371472 [2:49:54<16:30:23,  3.34it/s]
 47%|████▋     | 172827/371472 [2:49:54<17:09:00,  3.22it/s]
 47%|████▋     | 172828/371472 [2:49:54<17:21:24,  3.18it/s]
 47%|████▋     | 172829/371472 [2:49:55<19:40:49,  2.80it/s]
 47%|████▋     | 172830/371472 [2:49:55<18:30:50,  2.98it/s]
 47%|████▋     | 172831/371472 [2:49:55<17:32:58,  3.14it/s]
 47%|████▋     | 172832/371472 [2:49:56<17:38:06,  3.13it/s]
 47%|████▋     | 172833/371472 [2:49:56<17:23:44,  3.17it/s]
 47%|████▋     | 172834/371472 [2:49:56<16:53:40,  3.27it/s]
 47%|████▋     | 172835/371472 [2:49:57<16:35:55,  3.32it/s]
 47%|████▋     | 172836/371472 [2:49:57<17:35:40,  3.14it/s]
 47%|████▋     | 172837/371472 [2:49:57<17:31:15,  3.15it/s]
 47%|████▋     | 172838/371472 [2:49:58<17:12:43,  3.21it/s]
 47%|████▋     | 172839/371472 [2:49:58<18:24:43,  3.00it/s]
 47%|████▋     | 172840/371472 [2:49:58<18:26:31,  2.99it/s]
                                                            
{'loss': 2.7548, 'learning_rate': 5.815035876661854e-07, 'epoch': 7.44}
+
 47%|████▋     | 172840/371472 [2:49:58<18:26:31,  2.99it/s]
 47%|████▋     | 172841/371472 [2:49:59<18:05:23,  3.05it/s]
 47%|████▋     | 172842/371472 [2:49:59<17:56:53,  3.07it/s]
 47%|████▋     | 172843/371472 [2:49:59<17:14:54,  3.20it/s]
 47%|████▋     | 172844/371472 [2:49:59<16:52:42,  3.27it/s]
 47%|████▋     | 172845/371472 [2:50:00<16:54:39,  3.26it/s]
 47%|████▋     | 172846/371472 [2:50:00<17:02:14,  3.24it/s]
 47%|████▋     | 172847/371472 [2:50:00<17:21:11,  3.18it/s]
 47%|████▋     | 172848/371472 [2:50:01<16:32:00,  3.34it/s]
 47%|████▋     | 172849/371472 [2:50:01<16:04:11,  3.43it/s]
 47%|████▋     | 172850/371472 [2:50:01<16:19:06,  3.38it/s]
 47%|████▋     | 172851/371472 [2:50:02<16:47:08,  3.29it/s]
 47%|████▋     | 172852/371472 [2:50:02<17:29:17,  3.15it/s]
 47%|████▋     | 172853/371472 [2:50:02<17:20:14,  3.18it/s]
 47%|████▋     | 172854/371472 [2:50:03<17:00:47,  3.24it/s]
 47%|████▋     | 172855/371472 [2:50:03<16:22:05,  3.37it/s]
 47%|████▋     | 172856/371472 [2:50:03<16:58:27,  3.25it/s]
 47%|████▋     | 172857/371472 [2:50:03<16:49:06,  3.28it/s]
 47%|████▋     | 172858/371472 [2:50:04<17:21:54,  3.18it/s]
 47%|████▋     | 172859/371472 [2:50:04<16:49:19,  3.28it/s]
 47%|████▋     | 172860/371472 [2:50:04<16:07:37,  3.42it/s]
                                                            
{'loss': 2.9896, 'learning_rate': 5.814551056907065e-07, 'epoch': 7.45}
+
 47%|████▋     | 172860/371472 [2:50:04<16:07:37,  3.42it/s]
 47%|████▋     | 172861/371472 [2:50:05<15:29:07,  3.56it/s]
 47%|████▋     | 172862/371472 [2:50:05<15:30:57,  3.56it/s]
 47%|████▋     | 172863/371472 [2:50:05<16:59:37,  3.25it/s]
 47%|████▋     | 172864/371472 [2:50:06<16:38:51,  3.31it/s]
 47%|████▋     | 172865/371472 [2:50:06<16:44:02,  3.30it/s]
 47%|████▋     | 172866/371472 [2:50:06<16:30:21,  3.34it/s]
 47%|████▋     | 172867/371472 [2:50:07<18:55:16,  2.92it/s]
 47%|████▋     | 172868/371472 [2:50:07<18:12:14,  3.03it/s]
 47%|████▋     | 172869/371472 [2:50:07<17:14:16,  3.20it/s]
 47%|████▋     | 172870/371472 [2:50:07<17:05:27,  3.23it/s]
 47%|████▋     | 172871/371472 [2:50:08<16:28:33,  3.35it/s]
 47%|████▋     | 172872/371472 [2:50:08<16:16:10,  3.39it/s]
 47%|████▋     | 172873/371472 [2:50:08<16:13:26,  3.40it/s]
 47%|████▋     | 172874/371472 [2:50:09<16:06:06,  3.43it/s]
 47%|████▋     | 172875/371472 [2:50:09<16:59:41,  3.25it/s]
 47%|████▋     | 172876/371472 [2:50:09<16:28:03,  3.35it/s]
 47%|████▋     | 172877/371472 [2:50:09<16:15:33,  3.39it/s]
 47%|████▋     | 172878/371472 [2:50:10<16:31:17,  3.34it/s]
 47%|████▋     | 172879/371472 [2:50:10<16:19:43,  3.38it/s]
 47%|████▋     | 172880/371472 [2:50:10<16:04:27,  3.43it/s]
                                                            
{'loss': 2.9465, 'learning_rate': 5.814066237152276e-07, 'epoch': 7.45}
+
 47%|████▋     | 172880/371472 [2:50:10<16:04:27,  3.43it/s]
 47%|████▋     | 172881/371472 [2:50:11<16:24:35,  3.36it/s]
 47%|████▋     | 172882/371472 [2:50:11<16:38:11,  3.32it/s]
 47%|████▋     | 172883/371472 [2:50:11<16:28:31,  3.35it/s]
 47%|████▋     | 172884/371472 [2:50:12<17:21:36,  3.18it/s]
 47%|████▋     | 172885/371472 [2:50:12<16:50:26,  3.28it/s]
 47%|████▋     | 172886/371472 [2:50:12<16:46:54,  3.29it/s]
 47%|████▋     | 172887/371472 [2:50:12<16:28:46,  3.35it/s]
 47%|████▋     | 172888/371472 [2:50:13<16:17:58,  3.38it/s]
 47%|████▋     | 172889/371472 [2:50:13<16:05:32,  3.43it/s]
 47%|████▋     | 172890/371472 [2:50:13<15:41:49,  3.51it/s]
 47%|████▋     | 172891/371472 [2:50:14<15:17:10,  3.61it/s]
 47%|████▋     | 172892/371472 [2:50:14<15:35:02,  3.54it/s]
 47%|████▋     | 172893/371472 [2:50:14<15:55:32,  3.46it/s]
 47%|████▋     | 172894/371472 [2:50:15<17:43:09,  3.11it/s]
 47%|████▋     | 172895/371472 [2:50:15<17:05:58,  3.23it/s]
 47%|████▋     | 172896/371472 [2:50:15<18:36:33,  2.96it/s]
 47%|████▋     | 172897/371472 [2:50:16<17:37:40,  3.13it/s]
 47%|████▋     | 172898/371472 [2:50:16<17:14:13,  3.20it/s]
 47%|████▋     | 172899/371472 [2:50:16<17:04:14,  3.23it/s]
 47%|████▋     | 172900/371472 [2:50:17<17:43:57,  3.11it/s]
                                                            
{'loss': 2.9069, 'learning_rate': 5.813581417397488e-07, 'epoch': 7.45}
+
 47%|████▋     | 172900/371472 [2:50:17<17:43:57,  3.11it/s]
 47%|████▋     | 172901/371472 [2:50:17<17:21:35,  3.18it/s]
 47%|████▋     | 172902/371472 [2:50:17<19:02:45,  2.90it/s]
 47%|████▋     | 172903/371472 [2:50:18<18:47:14,  2.94it/s]
 47%|████▋     | 172904/371472 [2:50:18<17:50:03,  3.09it/s]
 47%|████▋     | 172905/371472 [2:50:18<18:01:38,  3.06it/s]
 47%|████▋     | 172906/371472 [2:50:18<17:28:54,  3.16it/s]
 47%|████▋     | 172907/371472 [2:50:19<16:38:46,  3.31it/s]
 47%|████▋     | 172908/371472 [2:50:19<16:15:05,  3.39it/s]
 47%|████▋     | 172909/371472 [2:50:19<15:53:07,  3.47it/s]
 47%|████▋     | 172910/371472 [2:50:20<15:37:53,  3.53it/s]
 47%|████▋     | 172911/371472 [2:50:20<15:32:51,  3.55it/s]
 47%|████▋     | 172912/371472 [2:50:20<15:41:51,  3.51it/s]
 47%|████▋     | 172913/371472 [2:50:20<15:25:33,  3.58it/s]
 47%|████▋     | 172914/371472 [2:50:21<15:27:36,  3.57it/s]
 47%|████▋     | 172915/371472 [2:50:21<15:54:56,  3.47it/s]
 47%|████▋     | 172916/371472 [2:50:21<15:52:48,  3.47it/s]
 47%|████▋     | 172917/371472 [2:50:22<16:24:08,  3.36it/s]
 47%|████▋     | 172918/371472 [2:50:22<16:15:13,  3.39it/s]
 47%|████▋     | 172919/371472 [2:50:22<15:56:10,  3.46it/s]
 47%|████▋     | 172920/371472 [2:50:22<15:37:46,  3.53it/s]
                                                            
{'loss': 2.8928, 'learning_rate': 5.813096597642698e-07, 'epoch': 7.45}
+
 47%|████▋     | 172920/371472 [2:50:22<15:37:46,  3.53it/s]
 47%|████▋     | 172921/371472 [2:50:23<15:16:57,  3.61it/s]
 47%|████▋     | 172922/371472 [2:50:23<14:57:59,  3.69it/s]
 47%|████▋     | 172923/371472 [2:50:23<15:24:54,  3.58it/s]
 47%|████▋     | 172924/371472 [2:50:24<15:20:36,  3.59it/s]
 47%|████▋     | 172925/371472 [2:50:24<15:29:04,  3.56it/s]
 47%|████▋     | 172926/371472 [2:50:24<16:57:08,  3.25it/s]
 47%|████▋     | 172927/371472 [2:50:24<16:13:05,  3.40it/s]
 47%|████▋     | 172928/371472 [2:50:25<15:58:32,  3.45it/s]
 47%|████▋     | 172929/371472 [2:50:25<17:02:35,  3.24it/s]
 47%|████▋     | 172930/371472 [2:50:25<17:47:40,  3.10it/s]
 47%|████▋     | 172931/371472 [2:50:26<18:16:22,  3.02it/s]
 47%|████▋     | 172932/371472 [2:50:26<18:58:16,  2.91it/s]
 47%|████▋     | 172933/371472 [2:50:27<19:36:59,  2.81it/s]
 47%|████▋     | 172934/371472 [2:50:27<18:21:15,  3.00it/s]
 47%|████▋     | 172935/371472 [2:50:27<18:29:17,  2.98it/s]
 47%|████▋     | 172936/371472 [2:50:27<18:11:00,  3.03it/s]
 47%|████▋     | 172937/371472 [2:50:28<17:19:22,  3.18it/s]
 47%|████▋     | 172938/371472 [2:50:28<16:35:27,  3.32it/s]
 47%|████▋     | 172939/371472 [2:50:28<16:09:17,  3.41it/s]
 47%|████▋     | 172940/371472 [2:50:29<16:56:27,  3.26it/s]
                                                            
{'loss': 2.7724, 'learning_rate': 5.812611777887909e-07, 'epoch': 7.45}
+
 47%|████▋     | 172940/371472 [2:50:29<16:56:27,  3.26it/s]
 47%|████▋     | 172941/371472 [2:50:29<16:51:25,  3.27it/s]
 47%|████▋     | 172942/371472 [2:50:29<16:54:46,  3.26it/s]
 47%|████▋     | 172943/371472 [2:50:30<16:40:56,  3.31it/s]
 47%|████▋     | 172944/371472 [2:50:30<16:39:24,  3.31it/s]
 47%|████▋     | 172945/371472 [2:50:30<16:00:13,  3.45it/s]
 47%|████▋     | 172946/371472 [2:50:30<16:03:42,  3.43it/s]
 47%|████▋     | 172947/371472 [2:50:31<15:57:46,  3.45it/s]
 47%|████▋     | 172948/371472 [2:50:31<16:26:11,  3.36it/s]
 47%|████▋     | 172949/371472 [2:50:31<16:03:42,  3.43it/s]
 47%|████▋     | 172950/371472 [2:50:32<15:59:41,  3.45it/s]
 47%|████▋     | 172951/371472 [2:50:32<16:46:41,  3.29it/s]
 47%|████▋     | 172952/371472 [2:50:32<16:30:08,  3.34it/s]
 47%|████▋     | 172953/371472 [2:50:32<16:20:04,  3.38it/s]
 47%|████▋     | 172954/371472 [2:50:33<16:00:18,  3.45it/s]
 47%|████▋     | 172955/371472 [2:50:33<15:45:30,  3.50it/s]
 47%|████▋     | 172956/371472 [2:50:33<16:06:00,  3.43it/s]
 47%|████▋     | 172957/371472 [2:50:34<16:04:01,  3.43it/s]
 47%|████▋     | 172958/371472 [2:50:34<15:42:43,  3.51it/s]
 47%|████▋     | 172959/371472 [2:50:34<15:50:33,  3.48it/s]
 47%|████▋     | 172960/371472 [2:50:34<15:36:27,  3.53it/s]
                                                            
{'loss': 2.8192, 'learning_rate': 5.81212695813312e-07, 'epoch': 7.45}
+
 47%|████▋     | 172960/371472 [2:50:34<15:36:27,  3.53it/s]
 47%|████▋     | 172961/371472 [2:50:35<15:24:53,  3.58it/s]
 47%|████▋     | 172962/371472 [2:50:35<15:36:59,  3.53it/s]
 47%|████▋     | 172963/371472 [2:50:35<15:45:19,  3.50it/s]
 47%|████▋     | 172964/371472 [2:50:36<16:37:53,  3.32it/s]
 47%|████▋     | 172965/371472 [2:50:36<16:06:56,  3.42it/s]
 47%|████▋     | 172966/371472 [2:50:36<15:42:19,  3.51it/s]
 47%|████▋     | 172967/371472 [2:50:36<15:51:42,  3.48it/s]
 47%|████▋     | 172968/371472 [2:50:37<16:27:18,  3.35it/s]
 47%|████▋     | 172969/371472 [2:50:37<18:32:13,  2.97it/s]
 47%|████▋     | 172970/371472 [2:50:38<18:37:23,  2.96it/s]
 47%|████▋     | 172971/371472 [2:50:38<17:38:21,  3.13it/s]
 47%|████▋     | 172972/371472 [2:50:38<17:17:52,  3.19it/s]
 47%|████▋     | 172973/371472 [2:50:38<17:09:05,  3.21it/s]
 47%|████▋     | 172974/371472 [2:50:39<16:30:06,  3.34it/s]
 47%|████▋     | 172975/371472 [2:50:39<16:38:10,  3.31it/s]
 47%|████▋     | 172976/371472 [2:50:39<16:09:53,  3.41it/s]
 47%|████▋     | 172977/371472 [2:50:40<16:18:49,  3.38it/s]
 47%|████▋     | 172978/371472 [2:50:40<17:00:46,  3.24it/s]
 47%|████▋     | 172979/371472 [2:50:40<16:31:11,  3.34it/s]
 47%|████▋     | 172980/371472 [2:50:41<16:57:55,  3.25it/s]
                                                            
{'loss': 3.0283, 'learning_rate': 5.811642138378331e-07, 'epoch': 7.45}
+
 47%|████▋     | 172980/371472 [2:50:41<16:57:55,  3.25it/s]
 47%|████▋     | 172981/371472 [2:50:41<16:38:48,  3.31it/s]
 47%|████▋     | 172982/371472 [2:50:41<16:17:47,  3.38it/s]
 47%|████▋     | 172983/371472 [2:50:41<15:54:38,  3.47it/s]
 47%|████▋     | 172984/371472 [2:50:42<15:26:26,  3.57it/s]
 47%|████▋     | 172985/371472 [2:50:42<15:43:02,  3.51it/s]
 47%|████▋     | 172986/371472 [2:50:42<16:00:41,  3.44it/s]
 47%|████▋     | 172987/371472 [2:50:43<16:29:13,  3.34it/s]
 47%|████���     | 172988/371472 [2:50:43<16:05:20,  3.43it/s]
 47%|████▋     | 172989/371472 [2:50:43<16:00:00,  3.45it/s]
 47%|████▋     | 172990/371472 [2:50:43<15:49:43,  3.48it/s]
 47%|████▋     | 172991/371472 [2:50:44<16:51:04,  3.27it/s]
 47%|████▋     | 172992/371472 [2:50:44<16:40:02,  3.31it/s]
 47%|████▋     | 172993/371472 [2:50:44<16:21:51,  3.37it/s]
 47%|████▋     | 172994/371472 [2:50:45<17:12:22,  3.20it/s]
 47%|████▋     | 172995/371472 [2:50:45<16:47:05,  3.28it/s]
 47%|████▋     | 172996/371472 [2:50:45<16:22:12,  3.37it/s]
 47%|████▋     | 172997/371472 [2:50:46<16:18:05,  3.38it/s]
 47%|████▋     | 172998/371472 [2:50:46<15:56:07,  3.46it/s]
 47%|████▋     | 172999/371472 [2:50:46<16:10:35,  3.41it/s]
 47%|████▋     | 173000/371472 [2:50:46<16:11:22,  3.41it/s]
                                                            
{'loss': 3.0158, 'learning_rate': 5.811157318623543e-07, 'epoch': 7.45}
+
 47%|████▋     | 173000/371472 [2:50:46<16:11:22,  3.41it/s]
 47%|████▋     | 173001/371472 [2:50:47<16:30:43,  3.34it/s]
 47%|████▋     | 173002/371472 [2:50:47<16:22:17,  3.37it/s]
 47%|████▋     | 173003/371472 [2:50:47<16:38:24,  3.31it/s]
 47%|████▋     | 173004/371472 [2:50:48<16:49:52,  3.28it/s]
 47%|████▋     | 173005/371472 [2:50:48<17:13:42,  3.20it/s]
 47%|████▋     | 173006/371472 [2:50:48<17:31:24,  3.15it/s]
 47%|████▋     | 173007/371472 [2:50:49<17:01:32,  3.24it/s]
 47%|████▋     | 173008/371472 [2:50:49<16:47:36,  3.28it/s]
 47%|████▋     | 173009/371472 [2:50:49<16:40:00,  3.31it/s]
 47%|████▋     | 173010/371472 [2:50:50<18:04:48,  3.05it/s]
 47%|████▋     | 173011/371472 [2:50:50<17:45:42,  3.10it/s]
 47%|████▋     | 173012/371472 [2:50:50<17:28:06,  3.16it/s]
 47%|████▋     | 173013/371472 [2:50:50<16:54:27,  3.26it/s]
 47%|████▋     | 173014/371472 [2:50:51<16:32:37,  3.33it/s]
 47%|████▋     | 173015/371472 [2:50:51<16:05:10,  3.43it/s]
 47%|████▋     | 173016/371472 [2:50:51<15:54:47,  3.46it/s]
 47%|████▋     | 173017/371472 [2:50:52<15:57:19,  3.46it/s]
 47%|████▋     | 173018/371472 [2:50:52<16:34:14,  3.33it/s]
 47%|████▋     | 173019/371472 [2:50:52<16:10:41,  3.41it/s]
 47%|████▋     | 173020/371472 [2:50:52<15:59:04,  3.45it/s]
                                                            
{'loss': 2.9748, 'learning_rate': 5.810672498868754e-07, 'epoch': 7.45}
+
 47%|████▋     | 173020/371472 [2:50:52<15:59:04,  3.45it/s]
 47%|████▋     | 173021/371472 [2:50:53<16:04:22,  3.43it/s]
 47%|████▋     | 173022/371472 [2:50:53<17:02:01,  3.24it/s]
 47%|████▋     | 173023/371472 [2:50:53<17:42:27,  3.11it/s]
 47%|████▋     | 173024/371472 [2:50:54<16:53:29,  3.26it/s]
 47%|████▋     | 173025/371472 [2:50:54<16:26:57,  3.35it/s]
 47%|████▋     | 173026/371472 [2:50:54<16:33:16,  3.33it/s]
 47%|████▋     | 173027/371472 [2:50:55<16:02:29,  3.44it/s]
 47%|████▋     | 173028/371472 [2:50:55<15:39:57,  3.52it/s]
 47%|████▋     | 173029/371472 [2:50:55<15:53:03,  3.47it/s]
 47%|████▋     | 173030/371472 [2:50:55<15:51:48,  3.47it/s]
 47%|████▋     | 173031/371472 [2:50:56<17:08:53,  3.21it/s]
 47%|████▋     | 173032/371472 [2:50:56<16:39:13,  3.31it/s]
 47%|████▋     | 173033/371472 [2:50:56<17:22:31,  3.17it/s]
 47%|████▋     | 173034/371472 [2:50:57<17:21:23,  3.18it/s]
 47%|████▋     | 173035/371472 [2:50:57<18:15:11,  3.02it/s]
 47%|████▋     | 173036/371472 [2:50:58<19:24:42,  2.84it/s]
 47%|████▋     | 173037/371472 [2:50:58<18:31:27,  2.98it/s]
 47%|████▋     | 173038/371472 [2:50:58<18:32:31,  2.97it/s]
 47%|████▋     | 173039/371472 [2:50:58<17:34:30,  3.14it/s]
 47%|████▋     | 173040/371472 [2:50:59<17:47:53,  3.10it/s]
                                                            
{'loss': 2.9266, 'learning_rate': 5.810187679113965e-07, 'epoch': 7.45}
+
 47%|████▋     | 173040/371472 [2:50:59<17:47:53,  3.10it/s]
 47%|████▋     | 173041/371472 [2:50:59<16:56:36,  3.25it/s]
 47%|████▋     | 173042/371472 [2:50:59<16:56:40,  3.25it/s]
 47%|████▋     | 173043/371472 [2:51:00<16:24:34,  3.36it/s]
 47%|████▋     | 173044/371472 [2:51:00<17:23:10,  3.17it/s]
 47%|████▋     | 173045/371472 [2:51:00<17:01:28,  3.24it/s]
 47%|████▋     | 173046/371472 [2:51:01<17:04:51,  3.23it/s]
 47%|████▋     | 173047/371472 [2:51:01<16:38:39,  3.31it/s]
 47%|████▋     | 173048/371472 [2:51:01<15:55:29,  3.46it/s]
 47%|████▋     | 173049/371472 [2:51:01<15:51:57,  3.47it/s]
 47%|████▋     | 173050/371472 [2:51:02<15:55:23,  3.46it/s]
 47%|████▋     | 173051/371472 [2:51:02<15:55:16,  3.46it/s]
 47%|████▋     | 173052/371472 [2:51:02<16:18:10,  3.38it/s]
 47%|████▋     | 173053/371472 [2:51:03<16:09:04,  3.41it/s]
 47%|████▋     | 173054/371472 [2:51:03<16:23:10,  3.36it/s]
 47%|████▋     | 173055/371472 [2:51:03<16:36:24,  3.32it/s]
 47%|████▋     | 173056/371472 [2:51:04<16:30:59,  3.34it/s]
 47%|████▋     | 173057/371472 [2:51:04<16:00:26,  3.44it/s]
 47%|████▋     | 173058/371472 [2:51:04<15:55:51,  3.46it/s]
 47%|████▋     | 173059/371472 [2:51:04<16:00:34,  3.44it/s]
 47%|████▋     | 173060/371472 [2:51:05<16:51:01,  3.27it/s]
                                                            
{'loss': 2.8645, 'learning_rate': 5.809702859359175e-07, 'epoch': 7.45}
+
 47%|████▋     | 173060/371472 [2:51:05<16:51:01,  3.27it/s]
 47%|████▋     | 173061/371472 [2:51:05<17:44:41,  3.11it/s]
 47%|████▋     | 173062/371472 [2:51:05<17:17:17,  3.19it/s]
 47%|████▋     | 173063/371472 [2:51:06<16:57:12,  3.25it/s]
 47%|████▋     | 173064/371472 [2:51:06<16:31:25,  3.34it/s]
 47%|████▋     | 173065/371472 [2:51:06<16:00:25,  3.44it/s]
 47%|████▋     | 173066/371472 [2:51:06<15:50:15,  3.48it/s]
 47%|████▋     | 173067/371472 [2:51:07<15:41:39,  3.51it/s]
 47%|████▋     | 173068/371472 [2:51:07<15:47:21,  3.49it/s]
 47%|████▋     | 173069/371472 [2:51:07<15:44:33,  3.50it/s]
 47%|████▋     | 173070/371472 [2:51:08<16:14:52,  3.39it/s]
 47%|████▋     | 173071/371472 [2:51:08<16:37:23,  3.32it/s]
 47%|████▋     | 173072/371472 [2:51:08<16:48:04,  3.28it/s]
 47%|████▋     | 173073/371472 [2:51:09<16:29:10,  3.34it/s]
 47%|████▋     | 173074/371472 [2:51:09<16:36:47,  3.32it/s]
 47%|████▋     | 173075/371472 [2:51:09<17:16:40,  3.19it/s]
 47%|████▋     | 173076/371472 [2:51:10<16:58:17,  3.25it/s]
 47%|████▋     | 173077/371472 [2:51:10<17:13:55,  3.20it/s]
 47%|████▋     | 173078/371472 [2:51:10<17:09:25,  3.21it/s]
 47%|████▋     | 173079/371472 [2:51:10<16:48:46,  3.28it/s]
 47%|████▋     | 173080/371472 [2:51:11<16:31:45,  3.33it/s]
                                                            
{'loss': 2.975, 'learning_rate': 5.809218039604387e-07, 'epoch': 7.45}
+
 47%|████▋     | 173080/371472 [2:51:11<16:31:45,  3.33it/s]
 47%|████▋     | 173081/371472 [2:51:11<16:18:42,  3.38it/s]
 47%|████▋     | 173082/371472 [2:51:11<16:38:29,  3.31it/s]
 47%|████▋     | 173083/371472 [2:51:12<16:25:27,  3.36it/s]
 47%|████▋     | 173084/371472 [2:51:12<16:07:21,  3.42it/s]
 47%|████▋     | 173085/371472 [2:51:12<16:10:22,  3.41it/s]
 47%|████▋     | 173086/371472 [2:51:12<16:16:02,  3.39it/s]
 47%|████▋     | 173087/371472 [2:51:13<16:06:02,  3.42it/s]
 47%|████▋     | 173088/371472 [2:51:13<15:59:18,  3.45it/s]
 47%|████▋     | 173089/371472 [2:51:13<15:51:33,  3.47it/s]
 47%|████▋     | 173090/371472 [2:51:14<15:42:12,  3.51it/s]
 47%|████▋     | 173091/371472 [2:51:14<15:42:05,  3.51it/s]
 47%|████▋     | 173092/371472 [2:51:14<16:24:26,  3.36it/s]
 47%|████▋     | 173093/371472 [2:51:15<16:44:24,  3.29it/s]
 47%|████▋     | 173094/371472 [2:51:15<16:47:03,  3.28it/s]
 47%|████▋     | 173095/371472 [2:51:15<16:11:37,  3.40it/s]
 47%|████▋     | 173096/371472 [2:51:15<16:14:48,  3.39it/s]
 47%|████▋     | 173097/371472 [2:51:16<15:52:45,  3.47it/s]
 47%|████▋     | 173098/371472 [2:51:16<16:43:55,  3.29it/s]
 47%|████▋     | 173099/371472 [2:51:16<17:17:29,  3.19it/s]
 47%|████▋     | 173100/371472 [2:51:17<17:12:33,  3.20it/s]
                                                            
{'loss': 2.8677, 'learning_rate': 5.808733219849598e-07, 'epoch': 7.46}
+
 47%|████▋     | 173100/371472 [2:51:17<17:12:33,  3.20it/s]
 47%|████▋     | 173101/371472 [2:51:17<16:39:12,  3.31it/s]
 47%|████▋     | 173102/371472 [2:51:17<16:25:09,  3.36it/s]
 47%|████▋     | 173103/371472 [2:51:18<16:36:17,  3.32it/s]
 47%|████▋     | 173104/371472 [2:51:18<16:01:52,  3.44it/s]
 47%|████▋     | 173105/371472 [2:51:18<16:04:48,  3.43it/s]
 47%|████▋     | 173106/371472 [2:51:18<15:52:52,  3.47it/s]
 47%|████▋     | 173107/371472 [2:51:19<17:15:37,  3.19it/s]
 47%|████▋     | 173108/371472 [2:51:19<17:02:21,  3.23it/s]
 47%|████▋     | 173109/371472 [2:51:20<19:10:07,  2.87it/s]
 47%|████▋     | 173110/371472 [2:51:20<18:38:43,  2.96it/s]
 47%|████▋     | 173111/371472 [2:51:20<17:42:21,  3.11it/s]
 47%|████▋     | 173112/371472 [2:51:20<17:37:03,  3.13it/s]
 47%|████▋     | 173113/371472 [2:51:21<17:14:48,  3.19it/s]
 47%|████▋     | 173114/371472 [2:51:21<17:03:49,  3.23it/s]
 47%|���███▋     | 173115/371472 [2:51:21<17:58:18,  3.07it/s]
 47%|████▋     | 173116/371472 [2:51:22<17:08:11,  3.22it/s]
 47%|████▋     | 173117/371472 [2:51:22<16:46:14,  3.29it/s]
 47%|████▋     | 173118/371472 [2:51:22<17:28:20,  3.15it/s]
 47%|████▋     | 173119/371472 [2:51:23<16:55:09,  3.26it/s]
 47%|████▋     | 173120/371472 [2:51:23<16:10:33,  3.41it/s]
                                                            
{'loss': 3.0536, 'learning_rate': 5.808248400094809e-07, 'epoch': 7.46}
+
 47%|████▋     | 173120/371472 [2:51:23<16:10:33,  3.41it/s]
 47%|████▋     | 173121/371472 [2:51:23<16:27:12,  3.35it/s]
 47%|████▋     | 173122/371472 [2:51:23<16:39:16,  3.31it/s]
 47%|████▋     | 173123/371472 [2:51:24<16:15:10,  3.39it/s]
 47%|████▋     | 173124/371472 [2:51:24<16:37:51,  3.31it/s]
 47%|████▋     | 173125/371472 [2:51:24<16:27:15,  3.35it/s]
 47%|████▋     | 173126/371472 [2:51:25<16:25:11,  3.36it/s]
 47%|████▋     | 173127/371472 [2:51:25<16:25:14,  3.36it/s]
 47%|████▋     | 173128/371472 [2:51:25<15:59:52,  3.44it/s]
 47%|████▋     | 173129/371472 [2:51:25<15:52:47,  3.47it/s]
 47%|████▋     | 173130/371472 [2:51:26<15:55:20,  3.46it/s]
 47%|████▋     | 173131/371472 [2:51:26<15:41:27,  3.51it/s]
 47%|████▋     | 173132/371472 [2:51:26<15:43:44,  3.50it/s]
 47%|████▋     | 173133/371472 [2:51:27<16:02:15,  3.44it/s]
 47%|████▋     | 173134/371472 [2:51:27<15:39:12,  3.52it/s]
 47%|████▋     | 173135/371472 [2:51:27<15:37:51,  3.52it/s]
 47%|████▋     | 173136/371472 [2:51:28<16:09:14,  3.41it/s]
 47%|████▋     | 173137/371472 [2:51:28<16:08:37,  3.41it/s]
 47%|████▋     | 173138/371472 [2:51:28<16:03:24,  3.43it/s]
 47%|████▋     | 173139/371472 [2:51:28<15:44:20,  3.50it/s]
 47%|████▋     | 173140/371472 [2:51:29<15:46:33,  3.49it/s]
                                                            
{'loss': 2.7891, 'learning_rate': 5.80776358034002e-07, 'epoch': 7.46}
+
 47%|████▋     | 173140/371472 [2:51:29<15:46:33,  3.49it/s]
 47%|████▋     | 173141/371472 [2:51:29<16:06:26,  3.42it/s]
 47%|████▋     | 173142/371472 [2:51:29<17:59:16,  3.06it/s]
 47%|████▋     | 173143/371472 [2:51:30<17:05:33,  3.22it/s]
 47%|████▋     | 173144/371472 [2:51:30<17:00:10,  3.24it/s]
 47%|████▋     | 173145/371472 [2:51:30<16:33:29,  3.33it/s]
 47%|████▋     | 173146/371472 [2:51:31<17:17:03,  3.19it/s]
 47%|████▋     | 173147/371472 [2:51:31<16:55:42,  3.25it/s]
 47%|████▋     | 173148/371472 [2:51:31<17:18:02,  3.18it/s]
 47%|████▋     | 173149/371472 [2:51:32<17:20:06,  3.18it/s]
 47%|████▋     | 173150/371472 [2:51:32<17:36:59,  3.13it/s]
 47%|████▋     | 173151/371472 [2:51:32<17:28:13,  3.15it/s]
 47%|████▋     | 173152/371472 [2:51:32<17:15:00,  3.19it/s]
 47%|████▋     | 173153/371472 [2:51:33<18:02:50,  3.05it/s]
 47%|████▋     | 173154/371472 [2:51:33<17:40:49,  3.12it/s]
 47%|████▋     | 173155/371472 [2:51:33<17:08:53,  3.21it/s]
 47%|████▋     | 173156/371472 [2:51:34<17:24:03,  3.17it/s]
 47%|████▋     | 173157/371472 [2:51:34<17:00:54,  3.24it/s]
 47%|████▋     | 173158/371472 [2:51:34<16:46:56,  3.28it/s]
 47%|████▋     | 173159/371472 [2:51:35<17:06:20,  3.22it/s]
 47%|████▋     | 173160/371472 [2:51:35<17:40:15,  3.12it/s]
                                                            
{'loss': 2.697, 'learning_rate': 5.807278760585232e-07, 'epoch': 7.46}
+
 47%|████▋     | 173160/371472 [2:51:35<17:40:15,  3.12it/s]
 47%|████▋     | 173161/371472 [2:51:35<17:06:55,  3.22it/s]
 47%|████▋     | 173162/371472 [2:51:36<16:24:53,  3.36it/s]
 47%|████▋     | 173163/371472 [2:51:36<17:17:59,  3.18it/s]
 47%|████▋     | 173164/371472 [2:51:36<17:02:45,  3.23it/s]
 47%|████▋     | 173165/371472 [2:51:36<16:32:20,  3.33it/s]
 47%|████▋     | 173166/371472 [2:51:37<17:25:56,  3.16it/s]
 47%|████▋     | 173167/371472 [2:51:37<16:49:56,  3.27it/s]
 47%|████▋     | 173168/371472 [2:51:37<16:42:42,  3.30it/s]
 47%|████▋     | 173169/371472 [2:51:38<16:42:46,  3.30it/s]
 47%|████▋     | 173170/371472 [2:51:38<17:35:27,  3.13it/s]
 47%|████▋     | 173171/371472 [2:51:38<17:30:53,  3.14it/s]
 47%|████▋     | 173172/371472 [2:51:39<17:07:49,  3.22it/s]
 47%|████▋     | 173173/371472 [2:51:39<16:56:17,  3.25it/s]
 47%|████▋     | 173174/371472 [2:51:39<16:26:41,  3.35it/s]
 47%|████▋     | 173175/371472 [2:51:40<16:07:12,  3.42it/s]
 47%|████▋     | 173176/371472 [2:51:40<16:10:13,  3.41it/s]
 47%|████▋     | 173177/371472 [2:51:40<16:31:12,  3.33it/s]
 47%|████▋     | 173178/371472 [2:51:40<17:10:21,  3.21it/s]
 47%|████▋     | 173179/371472 [2:51:41<17:07:42,  3.22it/s]
 47%|████▋     | 173180/371472 [2:51:41<17:04:52,  3.22it/s]
                                                            
{'loss': 2.8482, 'learning_rate': 5.806793940830442e-07, 'epoch': 7.46}
+
 47%|████▋     | 173180/371472 [2:51:41<17:04:52,  3.22it/s]
 47%|████▋     | 173181/371472 [2:51:41<17:12:16,  3.20it/s]
 47%|████▋     | 173182/371472 [2:51:42<16:41:09,  3.30it/s]
 47%|████▋     | 173183/371472 [2:51:42<16:23:16,  3.36it/s]
 47%|████▋     | 173184/371472 [2:51:42<16:40:50,  3.30it/s]
 47%|████▋     | 173185/371472 [2:51:43<16:22:01,  3.37it/s]
 47%|████▋     | 173186/371472 [2:51:43<16:09:57,  3.41it/s]
 47%|████▋     | 173187/371472 [2:51:43<16:49:45,  3.27it/s]
 47%|████▋     | 173188/371472 [2:51:43<16:06:52,  3.42it/s]
 47%|████▋     | 173189/371472 [2:51:44<16:12:49,  3.40it/s]
 47%|████▋     | 173190/371472 [2:51:44<16:56:52,  3.25it/s]
 47%|████▋     | 173191/371472 [2:51:44<17:07:58,  3.21it/s]
 47%|████▋     | 173192/371472 [2:51:45<17:27:16,  3.16it/s]
 47%|████▋     | 173193/371472 [2:51:45<16:45:56,  3.29it/s]
 47%|████▋     | 173194/371472 [2:51:45<16:18:07,  3.38it/s]
 47%|████▋     | 173195/371472 [2:51:46<16:07:13,  3.42it/s]
 47%|████▋     | 173196/371472 [2:51:46<15:34:58,  3.53it/s]
 47%|████▋     | 173197/371472 [2:51:46<15:38:40,  3.52it/s]
 47%|████▋     | 173198/371472 [2:51:47<17:18:15,  3.18it/s]
 47%|████▋     | 173199/371472 [2:51:47<17:08:57,  3.21it/s]
 47%|████▋     | 173200/371472 [2:51:47<16:50:43,  3.27it/s]
                                                            
{'loss': 2.9113, 'learning_rate': 5.806309121075652e-07, 'epoch': 7.46}
+
 47%|████▋     | 173200/371472 [2:51:47<16:50:43,  3.27it/s]
 47%|████▋     | 173201/371472 [2:51:47<16:42:21,  3.30it/s]
 47%|████▋     | 173202/371472 [2:51:48<17:00:10,  3.24it/s]
 47%|████▋     | 173203/371472 [2:51:48<16:48:05,  3.28it/s]
 47%|████▋     | 173204/371472 [2:51:48<18:02:38,  3.05it/s]
 47%|████▋     | 173205/371472 [2:51:49<16:57:27,  3.25it/s]
 47%|████▋     | 173206/371472 [2:51:49<16:27:06,  3.35it/s]
 47%|████▋     | 173207/371472 [2:51:49<16:51:48,  3.27it/s]
 47%|████▋     | 173208/371472 [2:51:50<16:19:44,  3.37it/s]
 47%|████▋     | 173209/371472 [2:51:50<16:34:53,  3.32it/s]
 47%|████▋     | 173210/371472 [2:51:50<16:20:15,  3.37it/s]
 47%|████▋     | 173211/371472 [2:51:50<15:59:35,  3.44it/s]
 47%|████▋     | 173212/371472 [2:51:51<16:13:56,  3.39it/s]
 47%|████▋     | 173213/371472 [2:51:51<17:10:33,  3.21it/s]
 47%|████▋     | 173214/371472 [2:51:51<16:41:29,  3.30it/s]
 47%|████▋     | 173215/371472 [2:51:52<16:28:06,  3.34it/s]
 47%|████▋     | 173216/371472 [2:51:52<16:40:40,  3.30it/s]
 47%|████▋     | 173217/371472 [2:51:52<16:10:51,  3.40it/s]
 47%|████▋     | 173218/371472 [2:51:53<16:45:22,  3.29it/s]
 47%|████▋     | 173219/371472 [2:51:53<16:02:11,  3.43it/s]
 47%|████▋     | 173220/371472 [2:51:53<16:48:40,  3.28it/s]
                                                            
{'loss': 3.0873, 'learning_rate': 5.805824301320864e-07, 'epoch': 7.46}
+
 47%|████▋     | 173220/371472 [2:51:53<16:48:40,  3.28it/s]
 47%|████▋     | 173221/371472 [2:51:53<16:23:47,  3.36it/s]
 47%|████▋     | 173222/371472 [2:51:54<16:20:57,  3.37it/s]
 47%|████▋     | 173223/371472 [2:51:54<16:50:09,  3.27it/s]
 47%|████▋     | 173224/371472 [2:51:54<17:06:57,  3.22it/s]
 47%|████▋     | 173225/371472 [2:51:55<17:22:44,  3.17it/s]
 47%|████▋     | 173226/371472 [2:51:55<17:07:42,  3.22it/s]
 47%|████▋     | 173227/371472 [2:51:55<16:56:51,  3.25it/s]
 47%|████▋     | 173228/371472 [2:51:56<17:27:50,  3.15it/s]
 47%|████▋     | 173229/371472 [2:51:56<17:33:28,  3.14it/s]
 47%|████▋     | 173230/371472 [2:51:56<16:56:54,  3.25it/s]
 47%|████▋     | 173231/371472 [2:51:57<16:39:28,  3.31it/s]
 47%|████▋     | 173232/371472 [2:51:57<16:01:21,  3.44it/s]
 47%|████▋     | 173233/371472 [2:51:57<15:45:11,  3.50it/s]
 47%|████▋     | 173234/371472 [2:51:57<16:06:48,  3.42it/s]
 47%|████▋     | 173235/371472 [2:51:58<15:58:34,  3.45it/s]
 47%|████▋     | 173236/371472 [2:51:58<15:32:27,  3.54it/s]
 47%|████▋     | 173237/371472 [2:51:58<15:47:15,  3.49it/s]
 47%|████▋     | 173238/371472 [2:51:59<15:54:31,  3.46it/s]
 47%|████▋     | 173239/371472 [2:51:59<16:18:01,  3.38it/s]
 47%|████▋     | 173240/371472 [2:51:59<16:18:08,  3.38it/s]
                                                            
{'loss': 3.0078, 'learning_rate': 5.805339481566076e-07, 'epoch': 7.46}
+
 47%|████▋     | 173240/371472 [2:51:59<16:18:08,  3.38it/s]
 47%|████▋     | 173241/371472 [2:51:59<16:13:11,  3.39it/s]
 47%|████▋     | 173242/371472 [2:52:00<16:08:59,  3.41it/s]
 47%|████▋     | 173243/371472 [2:52:00<16:09:47,  3.41it/s]
 47%|████▋     | 173244/371472 [2:52:00<16:37:41,  3.31it/s]
 47%|████▋     | 173245/371472 [2:52:01<16:31:48,  3.33it/s]
 47%|████▋     | 173246/371472 [2:52:01<16:27:19,  3.35it/s]
 47%|████▋     | 173247/371472 [2:52:01<16:05:37,  3.42it/s]
 47%|████▋     | 173248/371472 [2:52:02<16:42:29,  3.30it/s]
 47%|████▋     | 173249/371472 [2:52:02<16:26:21,  3.35it/s]
 47%|████▋     | 173250/371472 [2:52:02<16:06:59,  3.42it/s]
 47%|████▋     | 173251/371472 [2:52:02<16:00:40,  3.44it/s]
 47%|████▋     | 173252/371472 [2:52:03<16:26:25,  3.35it/s]
 47%|████▋     | 173253/371472 [2:52:03<16:03:06,  3.43it/s]
 47%|████▋     | 173254/371472 [2:52:03<16:13:00,  3.40it/s]
 47%|████▋     | 173255/371472 [2:52:04<16:22:14,  3.36it/s]
 47%|████▋     | 173256/371472 [2:52:04<15:54:38,  3.46it/s]
 47%|████▋     | 173257/371472 [2:52:04<15:29:02,  3.56it/s]
 47%|████▋     | 173258/371472 [2:52:04<15:58:13,  3.45it/s]
 47%|████▋     | 173259/371472 [2:52:05<15:41:55,  3.51it/s]
 47%|████▋     | 173260/371472 [2:52:05<15:25:07,  3.57it/s]
                                                            
{'loss': 2.8836, 'learning_rate': 5.804854661811287e-07, 'epoch': 7.46}
+
 47%|████▋     | 173260/371472 [2:52:05<15:25:07,  3.57it/s]
 47%|████▋     | 173261/371472 [2:52:05<16:38:39,  3.31it/s]
 47%|████▋     | 173262/371472 [2:52:06<16:27:10,  3.35it/s]
 47%|████▋     | 173263/371472 [2:52:06<17:01:08,  3.24it/s]
 47%|████▋     | 173264/371472 [2:52:06<16:47:32,  3.28it/s]
 47%|████▋     | 173265/371472 [2:52:07<16:15:54,  3.38it/s]
 47%|████▋     | 173266/371472 [2:52:07<16:10:38,  3.40it/s]
 47%|████▋     | 173267/371472 [2:52:07<16:03:59,  3.43it/s]
 47%|████▋     | 173268/371472 [2:52:07<16:23:59,  3.36it/s]
 47%|████▋     | 173269/371472 [2:52:08<16:21:05,  3.37it/s]
 47%|████▋     | 173270/371472 [2:52:08<16:23:32,  3.36it/s]
 47%|████▋     | 173271/371472 [2:52:08<16:20:03,  3.37it/s]
 47%|████▋     | 173272/371472 [2:52:09<16:30:54,  3.33it/s]
 47%|████▋     | 173273/371472 [2:52:09<16:16:36,  3.38it/s]
 47%|████▋     | 173274/371472 [2:52:09<16:08:42,  3.41it/s]
 47%|████▋     | 173275/371472 [2:52:10<17:19:55,  3.18it/s]
 47%|████▋     | 173276/371472 [2:52:10<17:23:29,  3.17it/s]
 47%|████▋     | 173277/371472 [2:52:10<17:23:36,  3.17it/s]
 47%|████▋     | 173278/371472 [2:52:10<17:14:13,  3.19it/s]
 47%|████▋     | 173279/371472 [2:52:11<17:18:39,  3.18it/s]
 47%|████▋     | 173280/371472 [2:52:11<17:28:05,  3.15it/s]
                                                            
{'loss': 2.9884, 'learning_rate': 5.804369842056497e-07, 'epoch': 7.46}
+
 47%|████▋     | 173280/371472 [2:52:11<17:28:05,  3.15it/s]
 47%|████▋     | 173281/371472 [2:52:11<17:05:39,  3.22it/s]
 47%|████▋     | 173282/371472 [2:52:12<17:44:00,  3.10it/s]
 47%|████▋     | 173283/371472 [2:52:12<16:59:20,  3.24it/s]
 47%|████▋     | 173284/371472 [2:52:12<16:46:59,  3.28it/s]
 47%|████▋     | 173285/371472 [2:52:13<17:03:27,  3.23it/s]
 47%|████▋     | 173286/371472 [2:52:13<16:58:23,  3.24it/s]
 47%|████▋     | 173287/371472 [2:52:13<16:22:48,  3.36it/s]
 47%|████▋     | 173288/371472 [2:52:14<16:02:47,  3.43it/s]
 47%|████▋     | 173289/371472 [2:52:14<15:57:19,  3.45it/s]
 47%|████▋     | 173290/371472 [2:52:14<15:57:47,  3.45it/s]
 47%|████▋     | 173291/371472 [2:52:14<16:01:55,  3.43it/s]
 47%|████▋     | 173292/371472 [2:52:15<15:58:01,  3.45it/s]
 47%|████▋     | 173293/371472 [2:52:15<15:38:51,  3.52it/s]
 47%|████▋     | 173294/371472 [2:52:15<15:40:58,  3.51it/s]
 47%|████▋     | 173295/371472 [2:52:16<15:48:18,  3.48it/s]
 47%|████▋     | 173296/371472 [2:52:16<16:04:12,  3.43it/s]
 47%|████▋     | 173297/371472 [2:52:16<15:56:49,  3.45it/s]
 47%|████▋     | 173298/371472 [2:52:16<16:16:41,  3.38it/s]
 47%|████▋     | 173299/371472 [2:52:17<15:44:38,  3.50it/s]
 47%|████▋     | 173300/371472 [2:52:17<17:20:19,  3.17it/s]
                                                            
{'loss': 3.0345, 'learning_rate': 5.803885022301708e-07, 'epoch': 7.46}
+
 47%|████▋     | 173300/371472 [2:52:17<17:20:19,  3.17it/s]
 47%|████▋     | 173301/371472 [2:52:17<17:26:22,  3.16it/s]
 47%|████▋     | 173302/371472 [2:52:18<16:53:21,  3.26it/s]
 47%|████▋     | 173303/371472 [2:52:18<16:34:25,  3.32it/s]
 47%|████▋     | 173304/371472 [2:52:18<16:48:43,  3.27it/s]
 47%|████▋     | 173305/371472 [2:52:19<16:41:49,  3.30it/s]
 47%|████▋     | 173306/371472 [2:52:19<16:29:45,  3.34it/s]
 47%|████▋     | 173307/371472 [2:52:19<16:59:48,  3.24it/s]
 47%|████▋     | 173308/371472 [2:52:19<16:38:50,  3.31it/s]
 47%|████▋     | 173309/371472 [2:52:20<17:20:43,  3.17it/s]
 47%|████▋     | 173310/371472 [2:52:20<17:32:05,  3.14it/s]
 47%|████▋     | 173311/371472 [2:52:20<16:39:19,  3.30it/s]
 47%|████▋     | 173312/371472 [2:52:21<17:00:27,  3.24it/s]
 47%|████▋     | 173313/371472 [2:52:21<17:12:05,  3.20it/s]
 47%|████▋     | 173314/371472 [2:52:21<16:48:06,  3.28it/s]
 47%|████▋     | 173315/371472 [2:52:22<16:53:53,  3.26it/s]
 47%|████▋     | 173316/371472 [2:52:22<16:47:29,  3.28it/s]
 47%|████▋     | 173317/371472 [2:52:22<16:48:39,  3.27it/s]
 47%|████▋     | 173318/371472 [2:52:23<16:14:21,  3.39it/s]
 47%|████▋     | 173319/371472 [2:52:23<17:09:33,  3.21it/s]
 47%|████▋     | 173320/371472 [2:52:23<16:29:07,  3.34it/s]
                                                            
{'loss': 2.9537, 'learning_rate': 5.80340020254692e-07, 'epoch': 7.47}
+
 47%|████▋     | 173320/371472 [2:52:23<16:29:07,  3.34it/s]
 47%|████▋     | 173321/371472 [2:52:23<16:49:32,  3.27it/s]
 47%|████▋     | 173322/371472 [2:52:24<16:29:25,  3.34it/s]
 47%|████▋     | 173323/371472 [2:52:24<16:38:36,  3.31it/s]
 47%|████▋     | 173324/371472 [2:52:24<16:55:21,  3.25it/s]
 47%|████▋     | 173325/371472 [2:52:25<16:44:43,  3.29it/s]
 47%|████▋     | 173326/371472 [2:52:25<17:41:59,  3.11it/s]
 47%|████▋     | 173327/371472 [2:52:25<17:35:41,  3.13it/s]
 47%|████▋     | 173328/371472 [2:52:26<18:12:23,  3.02it/s]
 47%|████▋     | 173329/371472 [2:52:26<18:10:32,  3.03it/s]
 47%|████▋     | 173330/371472 [2:52:26<17:22:30,  3.17it/s]
 47%|████▋     | 173331/371472 [2:52:27<16:55:51,  3.25it/s]
 47%|████▋     | 173332/371472 [2:52:27<17:40:40,  3.11it/s]
 47%|████▋     | 173333/371472 [2:52:27<18:05:09,  3.04it/s]
 47%|████▋     | 173334/371472 [2:52:28<17:36:41,  3.13it/s]
 47%|████▋     | 173335/371472 [2:52:28<17:18:23,  3.18it/s]
 47%|████▋     | 173336/371472 [2:52:28<16:51:57,  3.26it/s]
 47%|████▋     | 173337/371472 [2:52:29<17:01:18,  3.23it/s]
 47%|████▋     | 173338/371472 [2:52:29<17:00:25,  3.24it/s]
 47%|████▋     | 173339/371472 [2:52:29<16:47:01,  3.28it/s]
 47%|████▋     | 173340/371472 [2:52:29<16:29:55,  3.34it/s]
                                                            
{'loss': 2.8841, 'learning_rate': 5.802915382792131e-07, 'epoch': 7.47}
+
 47%|████▋     | 173340/371472 [2:52:29<16:29:55,  3.34it/s]
 47%|████▋     | 173341/371472 [2:52:30<17:14:30,  3.19it/s]
 47%|████▋     | 173342/371472 [2:52:30<17:15:14,  3.19it/s]
 47%|████▋     | 173343/371472 [2:52:30<18:19:55,  3.00it/s]
 47%|████▋     | 173344/371472 [2:52:31<17:28:02,  3.15it/s]
 47%|████▋     | 173345/371472 [2:52:31<16:52:27,  3.26it/s]
 47%|████▋     | 173346/371472 [2:52:31<16:45:15,  3.28it/s]
 47%|████▋     | 173347/371472 [2:52:32<17:05:44,  3.22it/s]
 47%|████▋     | 173348/371472 [2:52:32<16:55:50,  3.25it/s]
 47%|████▋     | 173349/371472 [2:52:32<17:28:44,  3.15it/s]
 47%|████▋     | 173350/371472 [2:52:33<17:09:04,  3.21it/s]
 47%|████▋     | 173351/371472 [2:52:33<17:05:10,  3.22it/s]
 47%|████▋     | 173352/371472 [2:52:33<17:25:33,  3.16it/s]
 47%|████▋     | 173353/371472 [2:52:34<16:52:02,  3.26it/s]
 47%|████▋     | 173354/371472 [2:52:34<17:31:30,  3.14it/s]
 47%|████▋     | 173355/371472 [2:52:34<17:06:26,  3.22it/s]
 47%|████▋     | 173356/371472 [2:52:34<17:01:59,  3.23it/s]
 47%|████▋     | 173357/371472 [2:52:35<17:39:53,  3.12it/s]
 47%|████▋     | 173358/371472 [2:52:35<17:09:15,  3.21it/s]
 47%|████▋     | 173359/371472 [2:52:35<18:09:17,  3.03it/s]
 47%|████▋     | 173360/371472 [2:52:36<17:39:23,  3.12it/s]
                                                            
{'loss': 2.6887, 'learning_rate': 5.802430563037341e-07, 'epoch': 7.47}
+
 47%|████▋     | 173360/371472 [2:52:36<17:39:23,  3.12it/s]
 47%|████▋     | 173361/371472 [2:52:36<17:02:55,  3.23it/s]
 47%|████▋     | 173362/371472 [2:52:36<16:45:51,  3.28it/s]
 47%|████▋     | 173363/371472 [2:52:37<16:33:07,  3.32it/s]
 47%|████▋     | 173364/371472 [2:52:37<18:35:38,  2.96it/s]
 47%|████▋     | 173365/371472 [2:52:37<18:18:30,  3.01it/s]
 47%|████▋     | 173366/371472 [2:52:38<17:44:47,  3.10it/s]
 47%|████▋     | 173367/371472 [2:52:38<17:47:58,  3.09it/s]
 47%|████▋     | 173368/371472 [2:52:38<17:26:32,  3.15it/s]
 47%|████▋     | 173369/371472 [2:52:39<16:47:56,  3.28it/s]
 47%|████▋     | 173370/371472 [2:52:39<16:35:29,  3.32it/s]
 47%|████▋     | 173371/371472 [2:52:39<17:19:28,  3.18it/s]
 47%|████▋     | 173372/371472 [2:52:40<16:36:15,  3.31it/s]
 47%|████▋     | 173373/371472 [2:52:40<16:46:18,  3.28it/s]
 47%|████▋     | 173374/371472 [2:52:40<16:47:47,  3.28it/s]
 47%|████▋     | 173375/371472 [2:52:40<16:44:23,  3.29it/s]
 47%|████▋     | 173376/371472 [2:52:41<16:45:21,  3.28it/s]
 47%|████▋     | 173377/371472 [2:52:41<16:50:17,  3.27it/s]
 47%|████▋     | 173378/371472 [2:52:41<17:30:41,  3.14it/s]
 47%|████▋     | 173379/371472 [2:52:42<16:50:29,  3.27it/s]
 47%|████▋     | 173380/371472 [2:52:42<16:40:43,  3.30it/s]
                                                            
{'loss': 2.9607, 'learning_rate': 5.801945743282553e-07, 'epoch': 7.47}
+
 47%|████▋     | 173380/371472 [2:52:42<16:40:43,  3.30it/s]
 47%|████▋     | 173381/371472 [2:52:42<16:24:22,  3.35it/s]
 47%|████▋     | 173382/371472 [2:52:43<16:22:35,  3.36it/s]
 47%|████▋     | 173383/371472 [2:52:43<17:16:32,  3.19it/s]
 47%|████▋     | 173384/371472 [2:52:43<16:56:02,  3.25it/s]
 47%|████▋     | 173385/371472 [2:52:43<16:46:28,  3.28it/s]
 47%|████▋     | 173386/371472 [2:52:44<18:19:55,  3.00it/s]
 47%|████▋     | 173387/371472 [2:52:44<17:31:30,  3.14it/s]
 47%|████▋     | 173388/371472 [2:52:44<17:10:44,  3.20it/s]
 47%|████▋     | 173389/371472 [2:52:45<16:35:19,  3.32it/s]
 47%|████▋     | 173390/371472 [2:52:45<16:10:55,  3.40it/s]
 47%|████▋     | 173391/371472 [2:52:45<16:50:09,  3.27it/s]
 47%|████▋     | 173392/371472 [2:52:46<16:28:10,  3.34it/s]
 47%|████▋     | 173393/371472 [2:52:46<16:28:51,  3.34it/s]
 47%|████▋     | 173394/371472 [2:52:46<16:27:26,  3.34it/s]
 47%|████▋     | 173395/371472 [2:52:47<16:24:40,  3.35it/s]
 47%|████▋     | 173396/371472 [2:52:47<16:52:39,  3.26it/s]
 47%|████▋     | 173397/371472 [2:52:47<16:50:25,  3.27it/s]
 47%|████▋     | 173398/371472 [2:52:47<16:27:05,  3.34it/s]
 47%|████▋     | 173399/371472 [2:52:48<16:34:16,  3.32it/s]
 47%|████▋     | 173400/371472 [2:52:48<16:52:55,  3.26it/s]
                                                            
{'loss': 2.9414, 'learning_rate': 5.801460923527764e-07, 'epoch': 7.47}
+
 47%|████▋     | 173400/371472 [2:52:48<16:52:55,  3.26it/s]
 47%|████▋     | 173401/371472 [2:52:48<16:55:24,  3.25it/s]
 47%|████▋     | 173402/371472 [2:52:49<16:36:24,  3.31it/s]
 47%|████▋     | 173403/371472 [2:52:49<16:28:23,  3.34it/s]
 47%|████▋     | 173404/371472 [2:52:49<16:02:51,  3.43it/s]
 47%|████▋     | 173405/371472 [2:52:50<16:06:17,  3.42it/s]
 47%|████▋     | 173406/371472 [2:52:50<15:52:32,  3.47it/s]
 47%|████▋     | 173407/371472 [2:52:50<16:23:51,  3.36it/s]
 47%|████▋     | 173408/371472 [2:52:50<16:16:23,  3.38it/s]
 47%|████▋     | 173409/371472 [2:52:51<15:52:32,  3.47it/s]
 47%|████▋     | 173410/371472 [2:52:51<16:07:03,  3.41it/s]
 47%|████▋     | 173411/371472 [2:52:51<16:15:50,  3.38it/s]
 47%|████▋     | 173412/371472 [2:52:52<17:17:44,  3.18it/s]
 47%|████▋     | 173413/371472 [2:52:52<16:41:58,  3.29it/s]
 47%|████▋     | 173414/371472 [2:52:52<16:34:59,  3.32it/s]
 47%|████▋     | 173415/371472 [2:52:53<17:15:11,  3.19it/s]
 47%|████▋     | 173416/371472 [2:52:53<16:43:29,  3.29it/s]
 47%|████▋     | 173417/371472 [2:52:53<16:16:50,  3.38it/s]
 47%|████▋     | 173418/371472 [2:52:53<16:03:21,  3.43it/s]
 47%|████▋     | 173419/371472 [2:52:54<15:59:17,  3.44it/s]
 47%|████▋     | 173420/371472 [2:52:54<16:03:02,  3.43it/s]
                                                            
{'loss': 3.0906, 'learning_rate': 5.800976103772975e-07, 'epoch': 7.47}
+
 47%|████▋     | 173420/371472 [2:52:54<16:03:02,  3.43it/s]
 47%|████▋     | 173421/371472 [2:52:54<18:24:08,  2.99it/s]
 47%|████▋     | 173422/371472 [2:52:55<17:56:57,  3.06it/s]
 47%|████▋     | 173423/371472 [2:52:55<17:03:02,  3.23it/s]
 47%|████▋     | 173424/371472 [2:52:55<16:40:23,  3.30it/s]
 47%|████▋     | 173425/371472 [2:52:56<17:00:24,  3.23it/s]
 47%|████▋     | 173426/371472 [2:52:56<16:56:33,  3.25it/s]
 47%|████▋     | 173427/371472 [2:52:56<17:07:32,  3.21it/s]
 47%|████▋     | 173428/371472 [2:52:57<16:58:57,  3.24it/s]
 47%|████��     | 173429/371472 [2:52:57<16:39:56,  3.30it/s]
 47%|████▋     | 173430/371472 [2:52:57<16:32:54,  3.32it/s]
 47%|████▋     | 173431/371472 [2:52:57<17:22:07,  3.17it/s]
 47%|████▋     | 173432/371472 [2:52:58<17:04:30,  3.22it/s]
 47%|████▋     | 173433/371472 [2:52:58<16:29:48,  3.33it/s]
 47%|████▋     | 173434/371472 [2:52:58<16:15:18,  3.38it/s]
 47%|████▋     | 173435/371472 [2:52:59<16:16:12,  3.38it/s]
 47%|████▋     | 173436/371472 [2:52:59<17:28:35,  3.15it/s]
 47%|████▋     | 173437/371472 [2:52:59<16:55:13,  3.25it/s]
 47%|████▋     | 173438/371472 [2:53:00<18:37:12,  2.95it/s]
 47%|████▋     | 173439/371472 [2:53:00<17:56:02,  3.07it/s]
 47%|████▋     | 173440/371472 [2:53:00<17:06:11,  3.22it/s]
                                                            
{'loss': 2.8137, 'learning_rate': 5.800491284018185e-07, 'epoch': 7.47}
+
 47%|████▋     | 173440/371472 [2:53:00<17:06:11,  3.22it/s]
 47%|████▋     | 173441/371472 [2:53:01<17:02:36,  3.23it/s]
 47%|████▋     | 173442/371472 [2:53:01<16:19:04,  3.37it/s]
 47%|████▋     | 173443/371472 [2:53:01<15:58:12,  3.44it/s]
 47%|████▋     | 173444/371472 [2:53:01<15:33:20,  3.54it/s]
 47%|████▋     | 173445/371472 [2:53:02<16:51:34,  3.26it/s]
 47%|████▋     | 173446/371472 [2:53:02<16:33:58,  3.32it/s]
 47%|████▋     | 173447/371472 [2:53:02<16:45:48,  3.28it/s]
 47%|████▋     | 173448/371472 [2:53:03<16:21:39,  3.36it/s]
 47%|████▋     | 173449/371472 [2:53:03<16:25:36,  3.35it/s]
 47%|████▋     | 173450/371472 [2:53:03<16:48:17,  3.27it/s]
 47%|████▋     | 173451/371472 [2:53:04<17:04:48,  3.22it/s]
 47%|████▋     | 173452/371472 [2:53:04<16:44:57,  3.28it/s]
 47%|████▋     | 173453/371472 [2:53:04<16:31:22,  3.33it/s]
 47%|████▋     | 173454/371472 [2:53:05<17:38:09,  3.12it/s]
 47%|████▋     | 173455/371472 [2:53:05<16:46:33,  3.28it/s]
 47%|████▋     | 173456/371472 [2:53:05<16:16:54,  3.38it/s]
 47%|████▋     | 173457/371472 [2:53:05<16:04:50,  3.42it/s]
 47%|████▋     | 173458/371472 [2:53:06<16:07:55,  3.41it/s]
 47%|████▋     | 173459/371472 [2:53:06<15:51:03,  3.47it/s]
 47%|████▋     | 173460/371472 [2:53:06<16:51:53,  3.26it/s]
                                                            
{'loss': 2.9699, 'learning_rate': 5.800006464263397e-07, 'epoch': 7.47}
+
 47%|████▋     | 173460/371472 [2:53:06<16:51:53,  3.26it/s]
 47%|████▋     | 173461/371472 [2:53:07<16:11:23,  3.40it/s]
 47%|████▋     | 173462/371472 [2:53:07<16:08:01,  3.41it/s]
 47%|████▋     | 173463/371472 [2:53:07<16:11:55,  3.40it/s]
 47%|████▋     | 173464/371472 [2:53:07<15:51:51,  3.47it/s]
 47%|████▋     | 173465/371472 [2:53:08<17:29:45,  3.14it/s]
 47%|████▋     | 173466/371472 [2:53:08<17:00:22,  3.23it/s]
 47%|████▋     | 173467/371472 [2:53:08<16:25:50,  3.35it/s]
 47%|████▋     | 173468/371472 [2:53:09<16:12:23,  3.39it/s]
 47%|████▋     | 173469/371472 [2:53:09<16:02:49,  3.43it/s]
 47%|████▋     | 173470/371472 [2:53:09<15:51:42,  3.47it/s]
 47%|████▋     | 173471/371472 [2:53:10<16:40:16,  3.30it/s]
 47%|████▋     | 173472/371472 [2:53:10<16:01:58,  3.43it/s]
 47%|████▋     | 173473/371472 [2:53:10<15:48:01,  3.48it/s]
 47%|████▋     | 173474/371472 [2:53:10<16:32:28,  3.33it/s]
 47%|████▋     | 173475/371472 [2:53:11<16:24:50,  3.35it/s]
 47%|████▋     | 173476/371472 [2:53:11<16:51:38,  3.26it/s]
 47%|████▋     | 173477/371472 [2:53:11<16:27:31,  3.34it/s]
 47%|████▋     | 173478/371472 [2:53:12<16:11:36,  3.40it/s]
 47%|████▋     | 173479/371472 [2:53:12<17:35:07,  3.13it/s]
 47%|████▋     | 173480/371472 [2:53:12<17:59:53,  3.06it/s]
                                                            
{'loss': 3.0245, 'learning_rate': 5.799521644508608e-07, 'epoch': 7.47}
+
 47%|████▋     | 173480/371472 [2:53:12<17:59:53,  3.06it/s]
 47%|████▋     | 173481/371472 [2:53:13<17:27:17,  3.15it/s]
 47%|████▋     | 173482/371472 [2:53:13<17:12:13,  3.20it/s]
 47%|████▋     | 173483/371472 [2:53:13<17:52:51,  3.08it/s]
 47%|████▋     | 173484/371472 [2:53:14<17:40:22,  3.11it/s]
 47%|████▋     | 173485/371472 [2:53:14<17:18:35,  3.18it/s]
 47%|████▋     | 173486/371472 [2:53:14<16:48:13,  3.27it/s]
 47%|████▋     | 173487/371472 [2:53:15<17:26:15,  3.15it/s]
 47%|████▋     | 173488/371472 [2:53:15<17:07:25,  3.21it/s]
 47%|████▋     | 173489/371472 [2:53:15<16:45:17,  3.28it/s]
 47%|████▋     | 173490/371472 [2:53:15<16:40:51,  3.30it/s]
 47%|████▋     | 173491/371472 [2:53:16<16:23:55,  3.35it/s]
 47%|████▋     | 173492/371472 [2:53:16<16:28:11,  3.34it/s]
 47%|████▋     | 173493/371472 [2:53:16<16:32:00,  3.33it/s]
 47%|████▋     | 173494/371472 [2:53:17<16:39:58,  3.30it/s]
 47%|████▋     | 173495/371472 [2:53:17<17:34:45,  3.13it/s]
 47%|████▋     | 173496/371472 [2:53:17<17:19:13,  3.18it/s]
 47%|████▋     | 173497/371472 [2:53:18<17:21:03,  3.17it/s]
 47%|████▋     | 173498/371472 [2:53:18<17:25:12,  3.16it/s]
 47%|████▋     | 173499/371472 [2:53:18<16:47:28,  3.28it/s]
 47%|████▋     | 173500/371472 [2:53:18<16:21:23,  3.36it/s]
                                                            
{'loss': 2.9055, 'learning_rate': 5.799036824753817e-07, 'epoch': 7.47}
+
 47%|████▋     | 173500/371472 [2:53:18<16:21:23,  3.36it/s]
 47%|████▋     | 173501/371472 [2:53:19<16:06:11,  3.41it/s]
 47%|████▋     | 173502/371472 [2:53:19<15:53:51,  3.46it/s]
 47%|████▋     | 173503/371472 [2:53:19<17:00:47,  3.23it/s]
 47%|████▋     | 173504/371472 [2:53:20<16:32:59,  3.32it/s]
 47%|████▋     | 173505/371472 [2:53:20<16:38:24,  3.30it/s]
 47%|████▋     | 173506/371472 [2:53:20<16:22:33,  3.36it/s]
 47%|████▋     | 173507/371472 [2:53:21<17:13:19,  3.19it/s]
 47%|████▋     | 173508/371472 [2:53:21<17:02:17,  3.23it/s]
 47%|████▋     | 173509/371472 [2:53:21<16:50:37,  3.26it/s]
 47%|████▋     | 173510/371472 [2:53:22<17:19:18,  3.17it/s]
 47%|████▋     | 173511/371472 [2:53:22<17:51:35,  3.08it/s]
 47%|████▋     | 173512/371472 [2:53:22<17:16:48,  3.18it/s]
 47%|████▋     | 173513/371472 [2:53:22<16:48:15,  3.27it/s]
 47%|████▋     | 173514/371472 [2:53:23<16:57:56,  3.24it/s]
 47%|████▋     | 173515/371472 [2:53:23<16:57:34,  3.24it/s]
 47%|████▋     | 173516/371472 [2:53:23<17:14:51,  3.19it/s]
 47%|████▋     | 173517/371472 [2:53:24<17:01:57,  3.23it/s]
 47%|████▋     | 173518/371472 [2:53:24<16:56:31,  3.25it/s]
 47%|████▋     | 173519/371472 [2:53:24<16:23:12,  3.36it/s]
 47%|████▋     | 173520/371472 [2:53:25<16:05:41,  3.42it/s]
                                                            
{'loss': 2.8786, 'learning_rate': 5.79855200499903e-07, 'epoch': 7.47}
+
 47%|████▋     | 173520/371472 [2:53:25<16:05:41,  3.42it/s]
 47%|████▋     | 173521/371472 [2:53:25<16:04:29,  3.42it/s]
 47%|████▋     | 173522/371472 [2:53:25<16:32:11,  3.33it/s]
 47%|████▋     | 173523/371472 [2:53:25<16:09:04,  3.40it/s]
 47%|████▋     | 173524/371472 [2:53:26<17:04:24,  3.22it/s]
 47%|████▋     | 173525/371472 [2:53:26<16:56:28,  3.25it/s]
 47%|████▋     | 173526/371472 [2:53:26<16:36:06,  3.31it/s]
 47%|████▋     | 173527/371472 [2:53:27<16:24:02,  3.35it/s]
 47%|████▋     | 173528/371472 [2:53:27<16:09:53,  3.40it/s]
 47%|████▋     | 173529/371472 [2:53:27<16:26:54,  3.34it/s]
 47%|████▋     | 173530/371472 [2:53:28<16:47:23,  3.27it/s]
 47%|████▋     | 173531/371472 [2:53:28<16:08:25,  3.41it/s]
 47%|████▋     | 173532/371472 [2:53:28<16:00:19,  3.44it/s]
 47%|████▋     | 173533/371472 [2:53:28<15:58:49,  3.44it/s]
 47%|████▋     | 173534/371472 [2:53:29<16:06:04,  3.41it/s]
 47%|████▋     | 173535/371472 [2:53:29<15:55:11,  3.45it/s]
 47%|████▋     | 173536/371472 [2:53:29<15:49:59,  3.47it/s]
 47%|████▋     | 173537/371472 [2:53:30<16:08:53,  3.40it/s]
 47%|████▋     | 173538/371472 [2:53:30<17:55:54,  3.07it/s]
 47%|████▋     | 173539/371472 [2:53:30<17:11:09,  3.20it/s]
 47%|████▋     | 173540/371472 [2:53:31<17:20:56,  3.17it/s]
                                                            
{'loss': 3.0392, 'learning_rate': 5.798067185244242e-07, 'epoch': 7.47}
+
 47%|████▋     | 173540/371472 [2:53:31<17:20:56,  3.17it/s]
 47%|████▋     | 173541/371472 [2:53:31<16:49:17,  3.27it/s]
 47%|████▋     | 173542/371472 [2:53:31<16:51:26,  3.26it/s]
 47%|████▋     | 173543/371472 [2:53:31<16:22:04,  3.36it/s]
 47%|████▋     | 173544/371472 [2:53:32<16:57:00,  3.24it/s]
 47%|████▋     | 173545/371472 [2:53:32<16:39:34,  3.30it/s]
 47%|████▋     | 173546/371472 [2:53:32<16:29:43,  3.33it/s]
 47%|████▋     | 173547/371472 [2:53:33<16:12:25,  3.39it/s]
 47%|████▋     | 173548/371472 [2:53:33<16:15:28,  3.38it/s]
 47%|████▋     | 173549/371472 [2:53:33<16:09:43,  3.40it/s]
 47%|████▋     | 173550/371472 [2:53:34<16:35:30,  3.31it/s]
 47%|████▋     | 173551/371472 [2:53:34<16:38:17,  3.30it/s]
 47%|████▋     | 173552/371472 [2:53:34<16:18:24,  3.37it/s]
 47%|████▋     | 173553/371472 [2:53:34<16:28:54,  3.34it/s]
 47%|████▋     | 173554/371472 [2:53:35<17:21:54,  3.17it/s]
 47%|████▋     | 173555/371472 [2:53:35<16:54:27,  3.25it/s]
 47%|��███▋     | 173556/371472 [2:53:35<16:46:14,  3.28it/s]
 47%|████▋     | 173557/371472 [2:53:36<16:18:21,  3.37it/s]
 47%|████▋     | 173558/371472 [2:53:36<16:18:02,  3.37it/s]
 47%|████▋     | 173559/371472 [2:53:36<16:30:29,  3.33it/s]
 47%|████▋     | 173560/371472 [2:53:37<16:21:28,  3.36it/s]
                                                            
{'loss': 2.9517, 'learning_rate': 5.797582365489452e-07, 'epoch': 7.48}
+
 47%|████▋     | 173560/371472 [2:53:37<16:21:28,  3.36it/s]
 47%|████▋     | 173561/371472 [2:53:37<16:24:42,  3.35it/s]
 47%|████▋     | 173562/371472 [2:53:37<16:16:33,  3.38it/s]
 47%|████▋     | 173563/371472 [2:53:38<16:51:16,  3.26it/s]
 47%|████▋     | 173564/371472 [2:53:38<16:07:22,  3.41it/s]
 47%|████▋     | 173565/371472 [2:53:38<16:17:08,  3.38it/s]
 47%|████▋     | 173566/371472 [2:53:38<16:19:36,  3.37it/s]
 47%|████▋     | 173567/371472 [2:53:39<15:49:58,  3.47it/s]
 47%|████▋     | 173568/371472 [2:53:39<15:54:57,  3.45it/s]
 47%|████▋     | 173569/371472 [2:53:39<15:32:00,  3.54it/s]
 47%|████▋     | 173570/371472 [2:53:39<15:19:44,  3.59it/s]
 47%|████▋     | 173571/371472 [2:53:40<15:33:13,  3.53it/s]
 47%|████▋     | 173572/371472 [2:53:40<15:45:59,  3.49it/s]
 47%|████▋     | 173573/371472 [2:53:40<15:52:25,  3.46it/s]
 47%|████▋     | 173574/371472 [2:53:41<16:14:53,  3.38it/s]
 47%|████▋     | 173575/371472 [2:53:41<16:26:03,  3.34it/s]
 47%|████▋     | 173576/371472 [2:53:41<17:04:44,  3.22it/s]
 47%|████▋     | 173577/371472 [2:53:42<16:28:01,  3.34it/s]
 47%|████▋     | 173578/371472 [2:53:42<16:56:08,  3.25it/s]
 47%|████▋     | 173579/371472 [2:53:42<16:28:29,  3.34it/s]
 47%|████▋     | 173580/371472 [2:53:42<16:02:13,  3.43it/s]
                                                            
{'loss': 2.9106, 'learning_rate': 5.797097545734662e-07, 'epoch': 7.48}
+
 47%|████▋     | 173580/371472 [2:53:42<16:02:13,  3.43it/s]
 47%|████▋     | 173581/371472 [2:53:43<17:24:33,  3.16it/s]
 47%|████▋     | 173582/371472 [2:53:43<18:19:48,  3.00it/s]
 47%|████▋     | 173583/371472 [2:53:44<17:33:23,  3.13it/s]
 47%|████▋     | 173584/371472 [2:53:44<17:45:34,  3.10it/s]
 47%|████▋     | 173585/371472 [2:53:44<17:48:26,  3.09it/s]
 47%|████▋     | 173586/371472 [2:53:44<17:20:15,  3.17it/s]
 47%|████▋     | 173587/371472 [2:53:45<17:23:59,  3.16it/s]
 47%|████▋     | 173588/371472 [2:53:45<16:47:18,  3.27it/s]
 47%|████▋     | 173589/371472 [2:53:45<18:19:30,  3.00it/s]
 47%|████▋     | 173590/371472 [2:53:46<18:06:56,  3.03it/s]
 47%|████▋     | 173591/371472 [2:53:46<17:29:08,  3.14it/s]
 47%|████▋     | 173592/371472 [2:53:46<17:26:07,  3.15it/s]
 47%|████▋     | 173593/371472 [2:53:47<17:07:53,  3.21it/s]
 47%|████▋     | 173594/371472 [2:53:47<17:46:56,  3.09it/s]
 47%|████▋     | 173595/371472 [2:53:47<17:29:02,  3.14it/s]
 47%|████▋     | 173596/371472 [2:53:48<17:27:38,  3.15it/s]
 47%|████▋     | 173597/371472 [2:53:48<17:04:35,  3.22it/s]
 47%|████▋     | 173598/371472 [2:53:48<17:34:22,  3.13it/s]
 47%|████▋     | 173599/371472 [2:53:49<16:56:57,  3.24it/s]
 47%|████▋     | 173600/371472 [2:53:49<16:42:20,  3.29it/s]
                                                            
{'loss': 3.0123, 'learning_rate': 5.796612725979874e-07, 'epoch': 7.48}
+
 47%|████▋     | 173600/371472 [2:53:49<16:42:20,  3.29it/s]
 47%|████▋     | 173601/371472 [2:53:49<17:52:53,  3.07it/s]
 47%|████▋     | 173602/371472 [2:53:50<16:59:36,  3.23it/s]
 47%|████▋     | 173603/371472 [2:53:50<16:38:55,  3.30it/s]
 47%|████▋     | 173604/371472 [2:53:50<16:32:07,  3.32it/s]
 47%|████▋     | 173605/371472 [2:53:50<16:48:27,  3.27it/s]
 47%|████▋     | 173606/371472 [2:53:51<17:17:56,  3.18it/s]
 47%|████▋     | 173607/371472 [2:53:51<17:49:29,  3.08it/s]
 47%|████▋     | 173608/371472 [2:53:51<16:49:25,  3.27it/s]
 47%|████▋     | 173609/371472 [2:53:52<16:58:54,  3.24it/s]
 47%|████▋     | 173610/371472 [2:53:52<16:27:47,  3.34it/s]
 47%|████▋     | 173611/371472 [2:53:52<16:56:11,  3.25it/s]
 47%|████▋     | 173612/371472 [2:53:53<16:28:21,  3.34it/s]
 47%|████▋     | 173613/371472 [2:53:53<16:11:36,  3.39it/s]
 47%|████▋     | 173614/371472 [2:53:53<16:13:05,  3.39it/s]
 47%|████▋     | 173615/371472 [2:53:53<16:56:03,  3.25it/s]
 47%|████▋     | 173616/371472 [2:53:54<17:13:35,  3.19it/s]
 47%|████▋     | 173617/371472 [2:53:54<17:19:51,  3.17it/s]
 47%|████▋     | 173618/371472 [2:53:54<16:52:21,  3.26it/s]
 47%|████▋     | 173619/371472 [2:53:55<16:32:28,  3.32it/s]
 47%|████▋     | 173620/371472 [2:53:55<17:30:35,  3.14it/s]
                                                            
{'loss': 2.824, 'learning_rate': 5.796127906225086e-07, 'epoch': 7.48}
+
 47%|████▋     | 173620/371472 [2:53:55<17:30:35,  3.14it/s]
 47%|████▋     | 173621/371472 [2:53:55<17:00:39,  3.23it/s]
 47%|████▋     | 173622/371472 [2:53:56<17:00:20,  3.23it/s]
 47%|████▋     | 173623/371472 [2:53:56<16:28:37,  3.34it/s]
 47%|████▋     | 173624/371472 [2:53:56<16:48:02,  3.27it/s]
 47%|████▋     | 173625/371472 [2:53:57<16:35:46,  3.31it/s]
 47%|████▋     | 173626/371472 [2:53:57<17:35:12,  3.12it/s]
 47%|████▋     | 173627/371472 [2:53:57<17:52:01,  3.08it/s]
 47%|████▋     | 173628/371472 [2:53:58<17:26:02,  3.15it/s]
 47%|████▋     | 173629/371472 [2:53:58<17:06:40,  3.21it/s]
 47%|████▋     | 173630/371472 [2:53:58<17:27:03,  3.15it/s]
 47%|████▋     | 173631/371472 [2:53:58<16:53:59,  3.25it/s]
 47%|████▋     | 173632/371472 [2:53:59<16:17:54,  3.37it/s]
 47%|████▋     | 173633/371472 [2:53:59<16:05:32,  3.41it/s]
 47%|████▋     | 173634/371472 [2:53:59<16:06:31,  3.41it/s]
 47%|████▋     | 173635/371472 [2:54:00<15:45:35,  3.49it/s]
 47%|████▋     | 173636/371472 [2:54:00<15:46:13,  3.48it/s]
 47%|████▋     | 173637/371472 [2:54:00<15:55:12,  3.45it/s]
 47%|████▋     | 173638/371472 [2:54:00<15:27:52,  3.55it/s]
 47%|████▋     | 173639/371472 [2:54:01<15:10:20,  3.62it/s]
 47%|████▋     | 173640/371472 [2:54:01<15:05:36,  3.64it/s]
                                                            
{'loss': 3.0775, 'learning_rate': 5.795643086470297e-07, 'epoch': 7.48}
+
 47%|████▋     | 173640/371472 [2:54:01<15:05:36,  3.64it/s]
 47%|████▋     | 173641/371472 [2:54:01<15:19:47,  3.58it/s]
 47%|████▋     | 173642/371472 [2:54:02<15:33:36,  3.53it/s]
 47%|████▋     | 173643/371472 [2:54:02<15:34:34,  3.53it/s]
 47%|████▋     | 173644/371472 [2:54:02<15:34:35,  3.53it/s]
 47%|████▋     | 173645/371472 [2:54:02<15:34:39,  3.53it/s]
 47%|████▋     | 173646/371472 [2:54:03<16:13:57,  3.39it/s]
 47%|████▋     | 173647/371472 [2:54:03<16:03:48,  3.42it/s]
 47%|████▋     | 173648/371472 [2:54:03<16:37:57,  3.30it/s]
 47%|████▋     | 173649/371472 [2:54:04<16:20:27,  3.36it/s]
 47%|████▋     | 173650/371472 [2:54:04<16:28:47,  3.33it/s]
 47%|████▋     | 173651/371472 [2:54:04<16:15:09,  3.38it/s]
 47%|████▋     | 173652/371472 [2:54:05<16:47:31,  3.27it/s]
 47%|████▋     | 173653/371472 [2:54:05<16:41:38,  3.29it/s]
 47%|████▋     | 173654/371472 [2:54:05<16:57:33,  3.24it/s]
 47%|████▋     | 173655/371472 [2:54:05<16:29:57,  3.33it/s]
 47%|████▋     | 173656/371472 [2:54:06<16:43:01,  3.29it/s]
 47%|████▋     | 173657/371472 [2:54:06<16:52:37,  3.26it/s]
 47%|████▋     | 173658/371472 [2:54:06<17:06:29,  3.21it/s]
 47%|████▋     | 173659/371472 [2:54:07<16:40:11,  3.30it/s]
 47%|████▋     | 173660/371472 [2:54:07<16:59:37,  3.23it/s]
                                                            
{'loss': 2.8225, 'learning_rate': 5.795158266715507e-07, 'epoch': 7.48}
+
 47%|████▋     | 173660/371472 [2:54:07<16:59:37,  3.23it/s]
 47%|████▋     | 173661/371472 [2:54:07<16:52:19,  3.26it/s]
 47%|████▋     | 173662/371472 [2:54:08<18:14:32,  3.01it/s]
 47%|████▋     | 173663/371472 [2:54:08<17:26:15,  3.15it/s]
 47%|████▋     | 173664/371472 [2:54:08<17:09:17,  3.20it/s]
 47%|████▋     | 173665/371472 [2:54:09<16:56:18,  3.24it/s]
 47%|████▋     | 173666/371472 [2:54:09<16:44:51,  3.28it/s]
 47%|████▋     | 173667/371472 [2:54:09<16:25:23,  3.35it/s]
 47%|████▋     | 173668/371472 [2:54:10<18:57:26,  2.90it/s]
 47%|████▋     | 173669/371472 [2:54:10<18:36:34,  2.95it/s]
 47%|████▋     | 173670/371472 [2:54:10<19:12:36,  2.86it/s]
 47%|████▋     | 173671/371472 [2:54:11<18:24:20,  2.99it/s]
 47%|████▋     | 173672/371472 [2:54:11<17:31:49,  3.13it/s]
 47%|████▋     | 173673/371472 [2:54:11<17:11:06,  3.20it/s]
 47%|████▋     | 173674/371472 [2:54:12<18:11:27,  3.02it/s]
 47%|████▋     | 173675/371472 [2:54:12<17:26:14,  3.15it/s]
 47%|████▋     | 173676/371472 [2:54:12<16:44:34,  3.28it/s]
 47%|████▋     | 173677/371472 [2:54:12<16:22:30,  3.36it/s]
 47%|████▋     | 173678/371472 [2:54:13<16:42:04,  3.29it/s]
 47%|████▋     | 173679/371472 [2:54:13<16:23:03,  3.35it/s]
 47%|████▋     | 173680/371472 [2:54:13<16:23:10,  3.35it/s]
                                                            
{'loss': 2.9347, 'learning_rate': 5.794673446960718e-07, 'epoch': 7.48}
+
 47%|████▋     | 173680/371472 [2:54:13<16:23:10,  3.35it/s]
 47%|████▋     | 173681/371472 [2:54:14<16:22:05,  3.36it/s]
 47%|████▋     | 173682/371472 [2:54:14<16:35:00,  3.31it/s]
 47%|████▋     | 173683/371472 [2:54:14<16:18:04,  3.37it/s]
 47%|████▋     | 173684/371472 [2:54:14<16:14:34,  3.38it/s]
 47%|████▋     | 173685/371472 [2:54:15<16:05:34,  3.41it/s]
 47%|████▋     | 173686/371472 [2:54:15<16:19:09,  3.37it/s]
 47%|████▋     | 173687/371472 [2:54:15<16:11:22,  3.39it/s]
 47%|████▋     | 173688/371472 [2:54:16<15:57:29,  3.44it/s]
 47%|████▋     | 173689/371472 [2:54:16<15:43:01,  3.50it/s]
 47%|████▋     | 173690/371472 [2:54:16<15:59:53,  3.43it/s]
 47%|████▋     | 173691/371472 [2:54:17<15:43:58,  3.49it/s]
 47%|████▋     | 173692/371472 [2:54:17<16:35:04,  3.31it/s]
 47%|████▋     | 173693/371472 [2:54:17<17:03:38,  3.22it/s]
 47%|████▋     | 173694/371472 [2:54:17<17:08:10,  3.21it/s]
 47%|████▋     | 173695/371472 [2:54:18<17:02:57,  3.22it/s]
 47%|████▋     | 173696/371472 [2:54:18<18:00:34,  3.05it/s]
 47%|████▋     | 173697/371472 [2:54:18<17:27:52,  3.15it/s]
 47%|████▋     | 173698/371472 [2:54:19<17:00:33,  3.23it/s]
 47%|████▋     | 173699/371472 [2:54:19<17:03:03,  3.22it/s]
 47%|████▋     | 173700/371472 [2:54:19<16:49:21,  3.27it/s]
                                                            
{'loss': 2.7681, 'learning_rate': 5.79418862720593e-07, 'epoch': 7.48}
+
 47%|████▋     | 173700/371472 [2:54:19<16:49:21,  3.27it/s]
 47%|████▋     | 173701/371472 [2:54:20<17:02:32,  3.22it/s]
 47%|████▋     | 173702/371472 [2:54:20<16:52:34,  3.26it/s]
 47%|████▋     | 173703/371472 [2:54:20<16:41:51,  3.29it/s]
 47%|████▋     | 173704/371472 [2:54:21<16:27:29,  3.34it/s]
 47%|████▋     | 173705/371472 [2:54:21<18:01:27,  3.05it/s]
 47%|████▋     | 173706/371472 [2:54:21<17:21:34,  3.16it/s]
 47%|████▋     | 173707/371472 [2:54:22<16:31:54,  3.32it/s]
 47%|████▋     | 173708/371472 [2:54:22<16:29:11,  3.33it/s]
 47%|████▋     | 173709/371472 [2:54:22<17:40:59,  3.11it/s]
 47%|████▋     | 173710/371472 [2:54:22<17:18:14,  3.17it/s]
 47%|████▋     | 173711/371472 [2:54:23<17:05:55,  3.21it/s]
 47%|████▋     | 173712/371472 [2:54:23<16:50:01,  3.26it/s]
 47%|████▋     | 173713/371472 [2:54:23<16:27:41,  3.34it/s]
 47%|████▋     | 173714/371472 [2:54:24<16:01:20,  3.43it/s]
 47%|████▋     | 173715/371472 [2:54:24<15:50:49,  3.47it/s]
 47%|████▋     | 173716/371472 [2:54:24<15:48:58,  3.47it/s]
 47%|████▋     | 173717/371472 [2:54:25<16:05:09,  3.41it/s]
 47%|████▋     | 173718/371472 [2:54:25<15:56:01,  3.45it/s]
 47%|████▋     | 173719/371472 [2:54:25<15:59:19,  3.44it/s]
 47%|████▋     | 173720/371472 [2:54:25<16:54:33,  3.25it/s]
                                                            
{'loss': 2.8223, 'learning_rate': 5.793703807451141e-07, 'epoch': 7.48}
+
 47%|████▋     | 173720/371472 [2:54:25<16:54:33,  3.25it/s]
 47%|████▋     | 173721/371472 [2:54:26<17:07:25,  3.21it/s]
 47%|████▋     | 173722/371472 [2:54:26<16:42:49,  3.29it/s]
 47%|████▋     | 173723/371472 [2:54:26<16:39:19,  3.30it/s]
 47%|████▋     | 173724/371472 [2:54:27<16:07:59,  3.40it/s]
 47%|████▋     | 173725/371472 [2:54:27<17:05:20,  3.21it/s]
 47%|████▋     | 173726/371472 [2:54:27<16:43:56,  3.28it/s]
 47%|████▋     | 173727/371472 [2:54:28<16:28:43,  3.33it/s]
 47%|████▋     | 173728/371472 [2:54:28<16:21:57,  3.36it/s]
 47%|████▋     | 173729/371472 [2:54:28<16:04:16,  3.42it/s]
 47%|████▋     | 173730/371472 [2:54:28<15:33:00,  3.53it/s]
 47%|████▋     | 173731/371472 [2:54:29<15:33:58,  3.53it/s]
 47%|████▋     | 173732/371472 [2:54:29<16:07:01,  3.41it/s]
 47%|████▋     | 173733/371472 [2:54:29<16:37:22,  3.30it/s]
 47%|████▋     | 173734/371472 [2:54:30<16:27:17,  3.34it/s]
 47%|████▋     | 173735/371472 [2:54:30<16:43:28,  3.28it/s]
 47%|████▋     | 173736/371472 [2:54:30<17:51:30,  3.08it/s]
 47%|████▋     | 173737/371472 [2:54:31<17:02:40,  3.22it/s]
 47%|████▋     | 173738/371472 [2:54:31<16:34:32,  3.31it/s]
 47%|████▋     | 173739/371472 [2:54:31<16:37:49,  3.30it/s]
 47%|████▋     | 173740/371472 [2:54:31<16:07:39,  3.41it/s]
                                                            
{'loss': 2.8764, 'learning_rate': 5.793218987696351e-07, 'epoch': 7.48}
+
 47%|████▋     | 173740/371472 [2:54:31<16:07:39,  3.41it/s]
 47%|████▋     | 173741/371472 [2:54:32<16:23:17,  3.35it/s]
 47%|████▋     | 173742/371472 [2:54:32<16:45:16,  3.28it/s]
 47%|████▋     | 173743/371472 [2:54:32<16:28:12,  3.33it/s]
 47%|████▋     | 173744/371472 [2:54:33<17:29:15,  3.14it/s]
 47%|████▋     | 173745/371472 [2:54:33<16:48:25,  3.27it/s]
 47%|████▋     | 173746/371472 [2:54:33<16:54:52,  3.25it/s]
 47%|████▋     | 173747/371472 [2:54:34<16:30:49,  3.33it/s]
 47%|████▋     | 173748/371472 [2:54:34<16:14:33,  3.38it/s]
 47%|████▋     | 173749/371472 [2:54:34<16:11:09,  3.39it/s]
 47%|████▋     | 173750/371472 [2:54:34<16:14:07,  3.38it/s]
 47%|████▋     | 173751/371472 [2:54:35<16:30:18,  3.33it/s]
 47%|████▋     | 173752/371472 [2:54:35<16:23:39,  3.35it/s]
 47%|████▋     | 173753/371472 [2:54:35<17:18:48,  3.17it/s]
 47%|████▋     | 173754/371472 [2:54:36<16:42:20,  3.29it/s]
 47%|████▋     | 173755/371472 [2:54:36<17:14:31,  3.19it/s]
 47%|████▋     | 173756/371472 [2:54:36<16:51:03,  3.26it/s]
 47%|████▋     | 173757/371472 [2:54:37<16:23:53,  3.35it/s]
 47%|████▋     | 173758/371472 [2:54:37<17:25:50,  3.15it/s]
 47%|████▋     | 173759/371472 [2:54:37<17:39:04,  3.11it/s]
 47%|████▋     | 173760/371472 [2:54:38<17:53:44,  3.07it/s]
                                                            
{'loss': 2.8406, 'learning_rate': 5.792734167941563e-07, 'epoch': 7.48}
+
 47%|████▋     | 173760/371472 [2:54:38<17:53:44,  3.07it/s]
 47%|████▋     | 173761/371472 [2:54:38<17:27:02,  3.15it/s]
 47%|████▋     | 173762/371472 [2:54:38<17:00:35,  3.23it/s]
 47%|████▋     | 173763/371472 [2:54:38<16:41:35,  3.29it/s]
 47%|████▋     | 173764/371472 [2:54:39<16:37:33,  3.30it/s]
 47%|████▋     | 173765/371472 [2:54:39<16:17:46,  3.37it/s]
 47%|████▋     | 173766/371472 [2:54:39<16:21:30,  3.36it/s]
 47%|████▋     | 173767/371472 [2:54:40<15:59:26,  3.43it/s]
 47%|████▋     | 173768/371472 [2:54:40<17:07:22,  3.21it/s]
 47%|████▋     | 173769/371472 [2:54:40<16:56:40,  3.24it/s]
 47%|████▋     | 173770/371472 [2:54:41<16:20:36,  3.36it/s]
 47%|████▋     | 173771/371472 [2:54:41<16:59:25,  3.23it/s]
 47%|████▋     | 173772/371472 [2:54:41<17:38:56,  3.11it/s]
 47%|████▋     | 173773/371472 [2:54:42<17:15:20,  3.18it/s]
 47%|████▋     | 173774/371472 [2:54:42<16:43:10,  3.28it/s]
 47%|████▋     | 173775/371472 [2:54:42<16:13:07,  3.39it/s]
 47%|████▋     | 173776/371472 [2:54:42<15:52:06,  3.46it/s]
 47%|████▋     | 173777/371472 [2:54:43<16:24:20,  3.35it/s]
 47%|████▋     | 173778/371472 [2:54:43<16:30:45,  3.33it/s]
 47%|████▋     | 173779/371472 [2:54:43<16:09:37,  3.40it/s]
 47%|████▋     | 173780/371472 [2:54:44<16:27:27,  3.34it/s]
                                                            
{'loss': 2.7933, 'learning_rate': 5.792249348186775e-07, 'epoch': 7.49}
+
 47%|████▋     | 173780/371472 [2:54:44<16:27:27,  3.34it/s]
 47%|████▋     | 173781/371472 [2:54:44<17:07:29,  3.21it/s]
 47%|████▋     | 173782/371472 [2:54:44<17:46:56,  3.09it/s]
 47%|████▋     | 173783/371472 [2:54:45<17:24:38,  3.15it/s]
 47%|████▋     | 173784/371472 [2:54:45<17:09:25,  3.20it/s]
 47%|████▋     | 173785/371472 [2:54:45<17:26:50,  3.15it/s]
 47%|████▋     | 173786/371472 [2:54:46<17:17:45,  3.17it/s]
 47%|████▋     | 173787/371472 [2:54:46<16:53:03,  3.25it/s]
 47%|████▋     | 173788/371472 [2:54:46<17:12:07,  3.19it/s]
 47%|████▋     | 173789/371472 [2:54:46<16:48:33,  3.27it/s]
 47%|████▋     | 173790/371472 [2:54:47<16:25:53,  3.34it/s]
 47%|████▋     | 173791/371472 [2:54:47<16:14:27,  3.38it/s]
 47%|████▋     | 173792/371472 [2:54:47<16:15:11,  3.38it/s]
 47%|████▋     | 173793/371472 [2:54:48<16:10:15,  3.40it/s]
 47%|████▋     | 173794/371472 [2:54:48<17:05:03,  3.21it/s]
 47%|████▋     | 173795/371472 [2:54:48<16:28:38,  3.33it/s]
 47%|████▋     | 173796/371472 [2:54:49<16:07:13,  3.41it/s]
 47%|████▋     | 173797/371472 [2:54:49<16:43:58,  3.28it/s]
 47%|████▋     | 173798/371472 [2:54:49<16:44:36,  3.28it/s]
 47%|████▋     | 173799/371472 [2:54:49<16:32:14,  3.32it/s]
 47%|████▋     | 173800/371472 [2:54:50<15:57:59,  3.44it/s]
                                                            
{'loss': 3.0147, 'learning_rate': 5.791764528431985e-07, 'epoch': 7.49}
+
 47%|████▋     | 173800/371472 [2:54:50<15:57:59,  3.44it/s]
 47%|████▋     | 173801/371472 [2:54:50<16:58:55,  3.23it/s]
 47%|████▋     | 173802/371472 [2:54:50<16:51:22,  3.26it/s]
 47%|████▋     | 173803/371472 [2:54:51<16:33:31,  3.32it/s]
 47%|████▋     | 173804/371472 [2:54:51<16:23:24,  3.35it/s]
 47%|████▋     | 173805/371472 [2:54:51<17:02:19,  3.22it/s]
 47%|████▋     | 173806/371472 [2:54:52<16:24:04,  3.35it/s]
 47%|████▋     | 173807/371472 [2:54:52<16:08:39,  3.40it/s]
 47%|████▋     | 173808/371472 [2:54:52<15:47:49,  3.48it/s]
 47%|████▋     | 173809/371472 [2:54:52<17:00:48,  3.23it/s]
 47%|████▋     | 173810/371472 [2:54:53<16:37:21,  3.30it/s]
 47%|████▋     | 173811/371472 [2:54:53<16:27:23,  3.34it/s]
 47%|████▋     | 173812/371472 [2:54:53<16:00:51,  3.43it/s]
 47%|████▋     | 173813/371472 [2:54:54<16:13:49,  3.38it/s]
 47%|████▋     | 173814/371472 [2:54:54<16:20:20,  3.36it/s]
 47%|████▋     | 173815/371472 [2:54:54<16:06:12,  3.41it/s]
 47%|████▋     | 173816/371472 [2:54:55<16:00:48,  3.43it/s]
 47%|████▋     | 173817/371472 [2:54:55<16:30:09,  3.33it/s]
 47%|████▋     | 173818/371472 [2:54:55<16:12:15,  3.39it/s]
 47%|████▋     | 173819/371472 [2:54:55<16:25:24,  3.34it/s]
 47%|████▋     | 173820/371472 [2:54:56<15:55:15,  3.45it/s]
                                                            
{'loss': 2.806, 'learning_rate': 5.791279708677195e-07, 'epoch': 7.49}
+
 47%|████▋     | 173820/371472 [2:54:56<15:55:15,  3.45it/s]
 47%|████▋     | 173821/371472 [2:54:56<15:57:58,  3.44it/s]
 47%|████▋     | 173822/371472 [2:54:56<16:23:22,  3.35it/s]
 47%|████▋     | 173823/371472 [2:54:57<16:54:03,  3.25it/s]
 47%|████▋     | 173824/371472 [2:54:57<16:24:21,  3.35it/s]
 47%|████▋     | 173825/371472 [2:54:57<16:21:51,  3.35it/s]
 47%|████▋     | 173826/371472 [2:54:58<17:06:38,  3.21it/s]
 47%|████▋     | 173827/371472 [2:54:58<17:31:21,  3.13it/s]
 47%|████▋     | 173828/371472 [2:54:58<17:04:12,  3.22it/s]
 47%|████▋     | 173829/371472 [2:54:58<16:41:59,  3.29it/s]
 47%|████▋     | 173830/371472 [2:54:59<17:26:27,  3.15it/s]
 47%|████▋     | 173831/371472 [2:54:59<17:16:25,  3.18it/s]
 47%|████▋     | 173832/371472 [2:54:59<16:54:12,  3.25it/s]
 47%|████▋     | 173833/371472 [2:55:00<17:47:25,  3.09it/s]
 47%|████▋     | 173834/371472 [2:55:00<17:10:09,  3.20it/s]
 47%|████▋     | 173835/371472 [2:55:00<16:36:20,  3.31it/s]
 47%|████▋     | 173836/371472 [2:55:01<16:22:00,  3.35it/s]
 47%|████▋     | 173837/371472 [2:55:01<16:00:21,  3.43it/s]
 47%|████▋     | 173838/371472 [2:55:01<16:09:25,  3.40it/s]
 47%|████▋     | 173839/371472 [2:55:01<16:07:17,  3.41it/s]
 47%|████▋     | 173840/371472 [2:55:02<16:00:24,  3.43it/s]
                                                            
{'loss': 2.8958, 'learning_rate': 5.790794888922407e-07, 'epoch': 7.49}
+
 47%|████▋     | 173840/371472 [2:55:02<16:00:24,  3.43it/s]
 47%|████▋     | 173841/371472 [2:55:02<16:29:34,  3.33it/s]
 47%|████▋     | 173842/371472 [2:55:02<16:19:41,  3.36it/s]
 47%|████▋     | 173843/371472 [2:55:03<16:01:42,  3.42it/s]
 47%|████▋     | 173844/371472 [2:55:03<16:12:45,  3.39it/s]
 47%|████▋     | 173845/371472 [2:55:03<17:30:32,  3.14it/s]
 47%|████▋     | 173846/371472 [2:55:04<16:57:47,  3.24it/s]
 47%|████▋     | 173847/371472 [2:55:04<17:08:21,  3.20it/s]
 47%|████▋     | 173848/371472 [2:55:04<16:49:14,  3.26it/s]
 47%|████▋     | 173849/371472 [2:55:05<16:16:13,  3.37it/s]
 47%|████▋     | 173850/371472 [2:55:05<16:10:40,  3.39it/s]
 47%|████▋     | 173851/371472 [2:55:05<16:17:20,  3.37it/s]
 47%|████▋     | 173852/371472 [2:55:05<16:08:05,  3.40it/s]
 47%|████▋     | 173853/371472 [2:55:06<16:01:42,  3.42it/s]
 47%|████▋     | 173854/371472 [2:55:06<15:28:13,  3.55it/s]
 47%|████▋     | 173855/371472 [2:55:06<15:37:21,  3.51it/s]
 47%|████▋     | 173856/371472 [2:55:07<15:31:32,  3.54it/s]
 47%|████▋     | 173857/371472 [2:55:07<16:06:23,  3.41it/s]
 47%|████▋     | 173858/371472 [2:55:07<15:53:38,  3.45it/s]
 47%|████▋     | 173859/371472 [2:55:07<15:48:30,  3.47it/s]
 47%|████▋     | 173860/371472 [2:55:08<15:43:11,  3.49it/s]
                                                            
{'loss': 3.0115, 'learning_rate': 5.790310069167619e-07, 'epoch': 7.49}
+
 47%|████▋     | 173860/371472 [2:55:08<15:43:11,  3.49it/s]
 47%|████▋     | 173861/371472 [2:55:08<16:26:27,  3.34it/s]
 47%|████▋     | 173862/371472 [2:55:08<16:49:36,  3.26it/s]
 47%|████▋     | 173863/371472 [2:55:09<16:44:55,  3.28it/s]
 47%|████▋     | 173864/371472 [2:55:09<16:41:50,  3.29it/s]
 47%|████▋     | 173865/371472 [2:55:09<16:29:55,  3.33it/s]
 47%|████▋     | 173866/371472 [2:55:10<16:41:31,  3.29it/s]
 47%|████▋     | 173867/371472 [2:55:10<16:29:10,  3.33it/s]
 47%|████▋     | 173868/371472 [2:55:10<16:24:10,  3.35it/s]
 47%|████▋     | 173869/371472 [2:55:10<15:57:02,  3.44it/s]
 47%|████▋     | 173870/371472 [2:55:11<15:50:41,  3.46it/s]
 47%|████▋     | 173871/371472 [2:55:11<16:30:45,  3.32it/s]
 47%|████▋     | 173872/371472 [2:55:11<16:33:16,  3.32it/s]
 47%|████▋     | 173873/371472 [2:55:12<16:32:08,  3.32it/s]
 47%|████▋     | 173874/371472 [2:55:12<15:57:02,  3.44it/s]
 47%|████▋     | 173875/371472 [2:55:12<15:50:24,  3.47it/s]
 47%|████▋     | 173876/371472 [2:55:12<15:18:54,  3.58it/s]
 47%|████▋     | 173877/371472 [2:55:13<19:01:04,  2.89it/s]
 47%|████▋     | 173878/371472 [2:55:13<17:40:30,  3.11it/s]
 47%|████▋     | 173879/371472 [2:55:14<17:43:24,  3.10it/s]
 47%|████▋     | 173880/371472 [2:55:14<17:36:32,  3.12it/s]
                                                            
{'loss': 3.0222, 'learning_rate': 5.78982524941283e-07, 'epoch': 7.49}
+
 47%|████▋     | 173880/371472 [2:55:14<17:36:32,  3.12it/s]
 47%|████▋     | 173881/371472 [2:55:14<17:35:26,  3.12it/s]
 47%|████▋     | 173882/371472 [2:55:14<16:57:51,  3.24it/s]
 47%|████▋     | 173883/371472 [2:55:15<16:45:25,  3.28it/s]
 47%|████▋     | 173884/371472 [2:55:15<16:20:39,  3.36it/s]
 47%|████▋     | 173885/371472 [2:55:15<16:03:42,  3.42it/s]
 47%|████▋     | 173886/371472 [2:55:16<15:47:39,  3.47it/s]
 47%|████▋     | 173887/371472 [2:55:16<15:53:43,  3.45it/s]
 47%|████▋     | 173888/371472 [2:55:16<15:44:44,  3.49it/s]
 47%|████▋     | 173889/371472 [2:55:16<16:02:46,  3.42it/s]
 47%|████▋     | 173890/371472 [2:55:17<15:31:43,  3.53it/s]
 47%|████▋     | 173891/371472 [2:55:17<15:12:15,  3.61it/s]
 47%|████▋     | 173892/371472 [2:55:17<15:18:58,  3.58it/s]
 47%|████▋     | 173893/371472 [2:55:18<16:12:35,  3.39it/s]
 47%|████▋     | 173894/371472 [2:55:18<15:57:00,  3.44it/s]
 47%|████▋     | 173895/371472 [2:55:18<15:55:35,  3.45it/s]
 47%|████▋     | 173896/371472 [2:55:18<16:01:31,  3.42it/s]
 47%|████▋     | 173897/371472 [2:55:19<16:25:59,  3.34it/s]
 47%|████▋     | 173898/371472 [2:55:19<17:45:08,  3.09it/s]
 47%|████▋     | 173899/371472 [2:55:19<16:55:17,  3.24it/s]
 47%|████▋     | 173900/371472 [2:55:20<16:23:33,  3.35it/s]
                                                            
{'loss': 2.9076, 'learning_rate': 5.78934042965804e-07, 'epoch': 7.49}
+
 47%|████▋     | 173900/371472 [2:55:20<16:23:33,  3.35it/s]
 47%|████▋     | 173901/371472 [2:55:20<16:41:55,  3.29it/s]
 47%|████▋     | 173902/371472 [2:55:20<16:27:25,  3.33it/s]
 47%|████▋     | 173903/371472 [2:55:21<16:33:20,  3.31it/s]
 47%|████▋     | 173904/371472 [2:55:21<17:27:22,  3.14it/s]
 47%|████▋     | 173905/371472 [2:55:21<18:24:20,  2.98it/s]
 47%|████▋     | 173906/371472 [2:55:22<18:14:52,  3.01it/s]
 47%|████▋     | 173907/371472 [2:55:22<17:16:13,  3.18it/s]
 47%|████▋     | 173908/371472 [2:55:22<16:47:51,  3.27it/s]
 47%|████▋     | 173909/371472 [2:55:23<17:14:27,  3.18it/s]
 47%|████▋     | 173910/371472 [2:55:23<17:09:23,  3.20it/s]
 47%|████▋     | 173911/371472 [2:55:23<16:47:33,  3.27it/s]
 47%|████▋     | 173912/371472 [2:55:23<16:24:53,  3.34it/s]
 47%|████▋     | 173913/371472 [2:55:24<15:44:24,  3.49it/s]
 47%|████▋     | 173914/371472 [2:55:24<16:15:17,  3.38it/s]
 47%|████▋     | 173915/371472 [2:55:24<17:10:57,  3.19it/s]
 47%|████▋     | 173916/371472 [2:55:25<17:27:07,  3.14it/s]
 47%|████▋     | 173917/371472 [2:55:25<16:57:35,  3.24it/s]
 47%|████▋     | 173918/371472 [2:55:25<17:43:06,  3.10it/s]
 47%|████▋     | 173919/371472 [2:55:26<16:44:08,  3.28it/s]
 47%|████▋     | 173920/371472 [2:55:26<17:22:48,  3.16it/s]
                                                            
{'loss': 2.921, 'learning_rate': 5.788855609903252e-07, 'epoch': 7.49}
+
 47%|████▋     | 173920/371472 [2:55:26<17:22:48,  3.16it/s]
 47%|████▋     | 173921/371472 [2:55:26<18:19:27,  2.99it/s]
 47%|████▋     | 173922/371472 [2:55:27<17:51:19,  3.07it/s]
 47%|████▋     | 173923/371472 [2:55:27<17:37:01,  3.11it/s]
 47%|████▋     | 173924/371472 [2:55:27<17:14:06,  3.18it/s]
 47%|████▋     | 173925/371472 [2:55:28<17:31:26,  3.13it/s]
 47%|████▋     | 173926/371472 [2:55:28<17:10:13,  3.20it/s]
 47%|████▋     | 173927/371472 [2:55:28<16:44:50,  3.28it/s]
 47%|████▋     | 173928/371472 [2:55:28<16:37:20,  3.30it/s]
 47%|████▋     | 173929/371472 [2:55:29<18:36:52,  2.95it/s]
 47%|████▋     | 173930/371472 [2:55:29<18:31:35,  2.96it/s]
 47%|████▋     | 173931/371472 [2:55:30<18:21:42,  2.99it/s]
 47%|████▋     | 173932/371472 [2:55:30<17:23:54,  3.15it/s]
 47%|████▋     | 173933/371472 [2:55:30<17:24:23,  3.15it/s]
 47%|████▋     | 173934/371472 [2:55:30<16:51:22,  3.26it/s]
 47%|████▋     | 173935/371472 [2:55:31<16:56:17,  3.24it/s]
 47%|████▋     | 173936/371472 [2:55:31<16:51:31,  3.25it/s]
 47%|████▋     | 173937/371472 [2:55:31<16:23:30,  3.35it/s]
 47%|████▋     | 173938/371472 [2:55:32<17:26:19,  3.15it/s]
 47%|████▋     | 173939/371472 [2:55:32<17:23:31,  3.15it/s]
 47%|████▋     | 173940/371472 [2:55:32<16:46:18,  3.27it/s]
                                                            
{'loss': 2.942, 'learning_rate': 5.788370790148462e-07, 'epoch': 7.49}
+
 47%|████▋     | 173940/371472 [2:55:32<16:46:18,  3.27it/s]
 47%|████▋     | 173941/371472 [2:55:33<16:24:37,  3.34it/s]
 47%|████▋     | 173942/371472 [2:55:33<16:13:19,  3.38it/s]
 47%|████▋     | 173943/371472 [2:55:33<15:58:11,  3.44it/s]
 47%|████▋     | 173944/371472 [2:55:33<16:22:40,  3.35it/s]
 47%|████▋     | 173945/371472 [2:55:34<17:06:39,  3.21it/s]
 47%|████▋     | 173946/371472 [2:55:34<16:48:09,  3.27it/s]
 47%|████▋     | 173947/371472 [2:55:34<17:01:51,  3.22it/s]
 47%|████▋     | 173948/371472 [2:55:35<16:33:31,  3.31it/s]
 47%|████▋     | 173949/371472 [2:55:35<15:54:59,  3.45it/s]
 47%|████▋     | 173950/371472 [2:55:35<15:52:11,  3.46it/s]
 47%|████▋     | 173951/371472 [2:55:36<16:28:37,  3.33it/s]
 47%|████▋     | 173952/371472 [2:55:36<16:14:25,  3.38it/s]
 47%|████▋     | 173953/371472 [2:55:36<16:09:05,  3.40it/s]
 47%|████▋     | 173954/371472 [2:55:37<17:45:21,  3.09it/s]
 47%|████▋     | 173955/371472 [2:55:37<16:57:21,  3.24it/s]
 47%|████▋     | 173956/371472 [2:55:37<16:47:13,  3.27it/s]
 47%|████▋     | 173957/371472 [2:55:37<16:58:22,  3.23it/s]
 47%|████▋     | 173958/371472 [2:55:38<16:41:54,  3.29it/s]
 47%|████▋     | 173959/371472 [2:55:38<16:50:21,  3.26it/s]
 47%|████▋     | 173960/371472 [2:55:38<16:33:02,  3.31it/s]
                                                            
{'loss': 2.9758, 'learning_rate': 5.787885970393672e-07, 'epoch': 7.49}
+
 47%|████▋     | 173960/371472 [2:55:38<16:33:02,  3.31it/s]
 47%|████▋     | 173961/371472 [2:55:39<17:11:59,  3.19it/s]
 47%|████▋     | 173962/371472 [2:55:39<17:38:18,  3.11it/s]
 47%|████▋     | 173963/371472 [2:55:39<16:55:05,  3.24it/s]
 47%|████▋     | 173964/371472 [2:55:40<17:16:33,  3.18it/s]
 47%|████▋     | 173965/371472 [2:55:40<16:54:03,  3.25it/s]
 47%|████▋     | 173966/371472 [2:55:40<16:39:55,  3.29it/s]
 47%|████▋     | 173967/371472 [2:55:40<16:23:16,  3.35it/s]
 47%|████▋     | 173968/371472 [2:55:41<16:13:21,  3.38it/s]
 47%|████▋     | 173969/371472 [2:55:41<16:35:47,  3.31it/s]
 47%|████▋     | 173970/371472 [2:55:41<16:25:40,  3.34it/s]
 47%|████▋     | 173971/371472 [2:55:42<16:13:54,  3.38it/s]
 47%|████▋     | 173972/371472 [2:55:42<15:52:23,  3.46it/s]
 47%|████▋     | 173973/371472 [2:55:42<15:45:06,  3.48it/s]
 47%|████▋     | 173974/371472 [2:55:42<15:21:38,  3.57it/s]
 47%|████▋     | 173975/371472 [2:55:43<16:50:09,  3.26it/s]
 47%|████▋     | 173976/371472 [2:55:43<16:30:41,  3.32it/s]
 47%|████▋     | 173977/371472 [2:55:43<16:23:18,  3.35it/s]
 47%|████▋     | 173978/371472 [2:55:44<16:56:13,  3.24it/s]
 47%|████▋     | 173979/371472 [2:55:44<17:14:09,  3.18it/s]
 47%|████▋     | 173980/371472 [2:55:44<16:57:43,  3.23it/s]
                                                            
{'loss': 3.07, 'learning_rate': 5.787401150638884e-07, 'epoch': 7.49}
+
 47%|████▋     | 173980/371472 [2:55:44<16:57:43,  3.23it/s]
 47%|████▋     | 173981/371472 [2:55:45<17:21:54,  3.16it/s]
 47%|████▋     | 173982/371472 [2:55:45<16:41:49,  3.29it/s]
 47%|████▋     | 173983/371472 [2:55:45<16:26:14,  3.34it/s]
 47%|████▋     | 173984/371472 [2:55:46<16:04:35,  3.41it/s]
 47%|████▋     | 173985/371472 [2:55:46<16:07:51,  3.40it/s]
 47%|████▋     | 173986/371472 [2:55:46<15:53:35,  3.45it/s]
 47%|████▋     | 173987/371472 [2:55:46<15:48:22,  3.47it/s]
 47%|████▋     | 173988/371472 [2:55:47<15:35:37,  3.52it/s]
 47%|████▋     | 173989/371472 [2:55:47<16:12:53,  3.38it/s]
 47%|████▋     | 173990/371472 [2:55:47<16:03:01,  3.42it/s]
 47%|████▋     | 173991/371472 [2:55:48<16:00:39,  3.43it/s]
 47%|████▋     | 173992/371472 [2:55:48<16:02:48,  3.42it/s]
 47%|████▋     | 173993/371472 [2:55:48<18:46:03,  2.92it/s]
 47%|████▋     | 173994/371472 [2:55:49<17:36:06,  3.12it/s]
 47%|████▋     | 173995/371472 [2:55:49<17:21:27,  3.16it/s]
 47%|████▋     | 173996/371472 [2:55:49<16:48:42,  3.26it/s]
 47%|██��█▋     | 173997/371472 [2:55:50<16:33:28,  3.31it/s]
 47%|████▋     | 173998/371472 [2:55:50<17:29:11,  3.14it/s]
 47%|████▋     | 173999/371472 [2:55:50<16:41:39,  3.29it/s]
 47%|████▋     | 174000/371472 [2:55:50<16:58:58,  3.23it/s]
                                                            
{'loss': 2.9814, 'learning_rate': 5.786916330884096e-07, 'epoch': 7.49}
+
 47%|████▋     | 174000/371472 [2:55:50<16:58:58,  3.23it/s]
 47%|████▋     | 174001/371472 [2:55:51<16:45:31,  3.27it/s]
 47%|████▋     | 174002/371472 [2:55:51<19:34:08,  2.80it/s]
 47%|████▋     | 174003/371472 [2:55:52<19:19:05,  2.84it/s]
 47%|████▋     | 174004/371472 [2:55:52<18:47:58,  2.92it/s]
 47%|████▋     | 174005/371472 [2:55:52<17:51:09,  3.07it/s]
 47%|████▋     | 174006/371472 [2:55:52<16:54:23,  3.24it/s]
 47%|████▋     | 174007/371472 [2:55:53<16:38:59,  3.29it/s]
 47%|████▋     | 174008/371472 [2:55:53<16:10:33,  3.39it/s]
 47%|████▋     | 174009/371472 [2:55:53<15:51:19,  3.46it/s]
 47%|████▋     | 174010/371472 [2:55:54<15:57:16,  3.44it/s]
 47%|████▋     | 174011/371472 [2:55:54<16:00:15,  3.43it/s]
 47%|████▋     | 174012/371472 [2:55:54<19:27:11,  2.82it/s]
 47%|████▋     | 174013/371472 [2:55:55<18:10:59,  3.02it/s]
 47%|████▋     | 174014/371472 [2:55:55<18:17:53,  3.00it/s]
 47%|████▋     | 174015/371472 [2:55:55<17:38:43,  3.11it/s]
 47%|████▋     | 174016/371472 [2:55:56<16:49:20,  3.26it/s]
 47%|████▋     | 174017/371472 [2:55:56<16:31:14,  3.32it/s]
 47%|████▋     | 174018/371472 [2:55:56<16:04:49,  3.41it/s]
 47%|████▋     | 174019/371472 [2:55:56<16:10:24,  3.39it/s]
 47%|████▋     | 174020/371472 [2:55:57<16:28:13,  3.33it/s]
                                                            
{'loss': 2.7575, 'learning_rate': 5.786431511129308e-07, 'epoch': 7.5}
+
 47%|████▋     | 174020/371472 [2:55:57<16:28:13,  3.33it/s]
 47%|████▋     | 174021/371472 [2:55:57<16:16:14,  3.37it/s]
 47%|████▋     | 174022/371472 [2:55:57<16:30:55,  3.32it/s]
 47%|████▋     | 174023/371472 [2:55:58<16:33:16,  3.31it/s]
 47%|████▋     | 174024/371472 [2:55:58<16:54:47,  3.24it/s]
 47%|████▋     | 174025/371472 [2:55:58<16:31:43,  3.32it/s]
 47%|████▋     | 174026/371472 [2:55:59<16:03:44,  3.41it/s]
 47%|████▋     | 174027/371472 [2:55:59<15:41:21,  3.50it/s]
 47%|████▋     | 174028/371472 [2:55:59<15:44:12,  3.49it/s]
 47%|████▋     | 174029/371472 [2:55:59<16:09:54,  3.39it/s]
 47%|████▋     | 174030/371472 [2:56:00<16:21:02,  3.35it/s]
 47%|████▋     | 174031/371472 [2:56:00<17:06:35,  3.21it/s]
 47%|████▋     | 174032/371472 [2:56:00<16:40:30,  3.29it/s]
 47%|████▋     | 174033/371472 [2:56:01<17:15:37,  3.18it/s]
 47%|████▋     | 174034/371472 [2:56:01<17:05:23,  3.21it/s]
 47%|████▋     | 174035/371472 [2:56:01<17:06:38,  3.21it/s]
 47%|████▋     | 174036/371472 [2:56:02<17:09:47,  3.20it/s]
 47%|████▋     | 174037/371472 [2:56:02<17:27:15,  3.14it/s]
 47%|████▋     | 174038/371472 [2:56:02<17:20:06,  3.16it/s]
 47%|████▋     | 174039/371472 [2:56:03<17:11:36,  3.19it/s]
 47%|████▋     | 174040/371472 [2:56:03<18:05:49,  3.03it/s]
                                                            
{'loss': 3.0069, 'learning_rate': 5.785946691374517e-07, 'epoch': 7.5}
+
 47%|████▋     | 174040/371472 [2:56:03<18:05:49,  3.03it/s]
 47%|████▋     | 174041/371472 [2:56:03<17:59:38,  3.05it/s]
 47%|████▋     | 174042/371472 [2:56:04<17:16:12,  3.18it/s]
 47%|████▋     | 174043/371472 [2:56:04<17:27:21,  3.14it/s]
 47%|████▋     | 174044/371472 [2:56:04<17:33:23,  3.12it/s]
 47%|████▋     | 174045/371472 [2:56:04<16:57:36,  3.23it/s]
 47%|████▋     | 174046/371472 [2:56:05<16:38:05,  3.30it/s]
 47%|████▋     | 174047/371472 [2:56:05<16:41:46,  3.28it/s]
 47%|████▋     | 174048/371472 [2:56:05<16:32:51,  3.31it/s]
 47%|████▋     | 174049/371472 [2:56:06<16:58:05,  3.23it/s]
 47%|████▋     | 174050/371472 [2:56:06<16:49:09,  3.26it/s]
 47%|████▋     | 174051/371472 [2:56:06<16:19:09,  3.36it/s]
 47%|████▋     | 174052/371472 [2:56:07<16:26:16,  3.34it/s]
 47%|████▋     | 174053/371472 [2:56:07<16:46:33,  3.27it/s]
 47%|████▋     | 174054/371472 [2:56:07<16:30:56,  3.32it/s]
 47%|████▋     | 174055/371472 [2:56:07<16:34:00,  3.31it/s]
 47%|████▋     | 174056/371472 [2:56:08<16:32:12,  3.32it/s]
 47%|████▋     | 174057/371472 [2:56:08<16:24:03,  3.34it/s]
 47%|████▋     | 174058/371472 [2:56:08<16:05:58,  3.41it/s]
 47%|████▋     | 174059/371472 [2:56:09<15:33:59,  3.52it/s]
 47%|████▋     | 174060/371472 [2:56:09<15:40:03,  3.50it/s]
                                                            
{'loss': 2.8659, 'learning_rate': 5.785461871619728e-07, 'epoch': 7.5}
+
 47%|████▋     | 174060/371472 [2:56:09<15:40:03,  3.50it/s]
 47%|████▋     | 174061/371472 [2:56:09<15:31:44,  3.53it/s]
 47%|████▋     | 174062/371472 [2:56:10<17:30:46,  3.13it/s]
 47%|████▋     | 174063/371472 [2:56:10<17:43:46,  3.09it/s]
 47%|████▋     | 174064/371472 [2:56:10<16:58:52,  3.23it/s]
 47%|████▋     | 174065/371472 [2:56:10<16:36:04,  3.30it/s]
 47%|████▋     | 174066/371472 [2:56:11<16:20:06,  3.36it/s]
 47%|████▋     | 174067/371472 [2:56:11<16:55:23,  3.24it/s]
 47%|████▋     | 174068/371472 [2:56:11<16:33:53,  3.31it/s]
 47%|████▋     | 174069/371472 [2:56:12<16:42:51,  3.28it/s]
 47%|████▋     | 174070/371472 [2:56:12<17:04:19,  3.21it/s]
 47%|████▋     | 174071/371472 [2:56:12<16:55:10,  3.24it/s]
 47%|████▋     | 174072/371472 [2:56:13<17:39:14,  3.11it/s]
 47%|████▋     | 174073/371472 [2:56:13<17:48:49,  3.08it/s]
 47%|████▋     | 174074/371472 [2:56:13<18:08:50,  3.02it/s]
 47%|████▋     | 174075/371472 [2:56:14<18:25:18,  2.98it/s]
 47%|████▋     | 174076/371472 [2:56:14<17:56:34,  3.06it/s]
 47%|████▋     | 174077/371472 [2:56:14<17:18:26,  3.17it/s]
 47%|████▋     | 174078/371472 [2:56:15<17:17:48,  3.17it/s]
 47%|████▋     | 174079/371472 [2:56:15<16:45:57,  3.27it/s]
 47%|████▋     | 174080/371472 [2:56:15<16:26:25,  3.34it/s]
                                                            
{'loss': 3.0161, 'learning_rate': 5.78497705186494e-07, 'epoch': 7.5}
+
 47%|████▋     | 174080/371472 [2:56:15<16:26:25,  3.34it/s]
 47%|████▋     | 174081/371472 [2:56:15<15:58:57,  3.43it/s]
 47%|████▋     | 174082/371472 [2:56:16<16:01:40,  3.42it/s]
 47%|████▋     | 174083/371472 [2:56:16<15:41:05,  3.50it/s]
 47%|████▋     | 174084/371472 [2:56:16<15:38:04,  3.51it/s]
 47%|████▋     | 174085/371472 [2:56:17<15:31:11,  3.53it/s]
 47%|████▋     | 174086/371472 [2:56:17<15:31:26,  3.53it/s]
 47%|████▋     | 174087/371472 [2:56:17<15:14:54,  3.60it/s]
 47%|████▋     | 174088/371472 [2:56:17<15:43:11,  3.49it/s]
 47%|████▋     | 174089/371472 [2:56:18<15:58:34,  3.43it/s]
 47%|████▋     | 174090/371472 [2:56:18<15:44:16,  3.48it/s]
 47%|████▋     | 174091/371472 [2:56:18<16:01:17,  3.42it/s]
 47%|████▋     | 174092/371472 [2:56:19<15:53:34,  3.45it/s]
 47%|████▋     | 174093/371472 [2:56:19<15:45:50,  3.48it/s]
 47%|████▋     | 174094/371472 [2:56:19<15:50:37,  3.46it/s]
 47%|████▋     | 174095/371472 [2:56:19<15:43:56,  3.48it/s]
 47%|████▋     | 174096/371472 [2:56:20<16:58:05,  3.23it/s]
 47%|████▋     | 174097/371472 [2:56:20<16:39:40,  3.29it/s]
 47%|████▋     | 174098/371472 [2:56:20<16:17:38,  3.36it/s]
 47%|████▋     | 174099/371472 [2:56:21<15:57:59,  3.43it/s]
 47%|████▋     | 174100/371472 [2:56:21<15:40:33,  3.50it/s]
                                                            
{'loss': 2.936, 'learning_rate': 5.784492232110151e-07, 'epoch': 7.5}
+
 47%|████▋     | 174100/371472 [2:56:21<15:40:33,  3.50it/s]
 47%|████▋     | 174101/371472 [2:56:21<16:05:17,  3.41it/s]
 47%|████▋     | 174102/371472 [2:56:22<16:49:36,  3.26it/s]
 47%|████▋     | 174103/371472 [2:56:22<16:39:50,  3.29it/s]
 47%|████▋     | 174104/371472 [2:56:22<16:09:23,  3.39it/s]
 47%|████▋     | 174105/371472 [2:56:22<16:21:14,  3.35it/s]
 47%|████▋     | 174106/371472 [2:56:23<16:32:21,  3.31it/s]
 47%|████▋     | 174107/371472 [2:56:23<15:45:07,  3.48it/s]
 47%|████▋     | 174108/371472 [2:56:23<18:21:30,  2.99it/s]
 47%|████▋     | 174109/371472 [2:56:24<17:24:24,  3.15it/s]
 47%|████▋     | 174110/371472 [2:56:24<16:58:42,  3.23it/s]
 47%|████▋     | 174111/371472 [2:56:24<16:31:37,  3.32it/s]
 47%|████▋     | 174112/371472 [2:56:25<16:27:29,  3.33it/s]
 47%|████▋     | 174113/371472 [2:56:25<16:13:46,  3.38it/s]
 47%|████▋     | 174114/371472 [2:56:25<17:32:02,  3.13it/s]
 47%|████▋     | 174115/371472 [2:56:26<17:12:03,  3.19it/s]
 47%|████▋     | 174116/371472 [2:56:26<16:31:30,  3.32it/s]
 47%|████▋     | 174117/371472 [2:56:26<17:41:05,  3.10it/s]
 47%|████▋     | 174118/371472 [2:56:27<17:17:47,  3.17it/s]
 47%|████▋     | 174119/371472 [2:56:27<16:49:59,  3.26it/s]
 47%|████▋     | 174120/371472 [2:56:27<17:15:46,  3.18it/s]
                                                            
{'loss': 2.9952, 'learning_rate': 5.784007412355361e-07, 'epoch': 7.5}
+
 47%|████▋     | 174120/371472 [2:56:27<17:15:46,  3.18it/s]
 47%|███���▋     | 174121/371472 [2:56:27<17:03:25,  3.21it/s]
 47%|████▋     | 174122/371472 [2:56:28<16:41:52,  3.28it/s]
 47%|████▋     | 174123/371472 [2:56:28<16:36:26,  3.30it/s]
 47%|████▋     | 174124/371472 [2:56:28<16:14:43,  3.37it/s]
 47%|████▋     | 174125/371472 [2:56:29<16:04:07,  3.41it/s]
 47%|████▋     | 174126/371472 [2:56:29<15:44:27,  3.48it/s]
 47%|████▋     | 174127/371472 [2:56:29<17:02:49,  3.22it/s]
 47%|████▋     | 174128/371472 [2:56:30<17:24:22,  3.15it/s]
 47%|████▋     | 174129/371472 [2:56:30<16:56:45,  3.23it/s]
 47%|████▋     | 174130/371472 [2:56:30<17:15:10,  3.18it/s]
 47%|████▋     | 174131/371472 [2:56:30<17:02:17,  3.22it/s]
 47%|████▋     | 174132/371472 [2:56:31<16:30:28,  3.32it/s]
 47%|████▋     | 174133/371472 [2:56:31<16:13:31,  3.38it/s]
 47%|████▋     | 174134/371472 [2:56:31<15:54:01,  3.45it/s]
 47%|████▋     | 174135/371472 [2:56:32<15:42:46,  3.49it/s]
 47%|████▋     | 174136/371472 [2:56:32<15:46:49,  3.47it/s]
 47%|████▋     | 174137/371472 [2:56:32<15:44:53,  3.48it/s]
 47%|████▋     | 174138/371472 [2:56:32<15:25:07,  3.56it/s]
 47%|████▋     | 174139/371472 [2:56:33<15:56:58,  3.44it/s]
 47%|████▋     | 174140/371472 [2:56:33<16:48:13,  3.26it/s]
                                                            
{'loss': 2.8454, 'learning_rate': 5.783522592600573e-07, 'epoch': 7.5}
+
 47%|████▋     | 174140/371472 [2:56:33<16:48:13,  3.26it/s]
 47%|████▋     | 174141/371472 [2:56:33<16:04:50,  3.41it/s]
 47%|████▋     | 174142/371472 [2:56:34<17:01:18,  3.22it/s]
 47%|████▋     | 174143/371472 [2:56:34<17:08:28,  3.20it/s]
 47%|████▋     | 174144/371472 [2:56:34<16:52:58,  3.25it/s]
 47%|████▋     | 174145/371472 [2:56:35<16:31:12,  3.32it/s]
 47%|████▋     | 174146/371472 [2:56:35<16:27:08,  3.33it/s]
 47%|████▋     | 174147/371472 [2:56:35<17:11:48,  3.19it/s]
 47%|████▋     | 174148/371472 [2:56:36<18:01:18,  3.04it/s]
 47%|████▋     | 174149/371472 [2:56:36<17:53:14,  3.06it/s]
 47%|████▋     | 174150/371472 [2:56:36<17:13:43,  3.18it/s]
 47%|████▋     | 174151/371472 [2:56:37<18:01:30,  3.04it/s]
 47%|████▋     | 174152/371472 [2:56:37<18:17:21,  3.00it/s]
 47%|████▋     | 174153/371472 [2:56:37<17:41:50,  3.10it/s]
 47%|████▋     | 174154/371472 [2:56:38<17:30:57,  3.13it/s]
 47%|████▋     | 174155/371472 [2:56:38<17:01:01,  3.22it/s]
 47%|████▋     | 174156/371472 [2:56:38<16:37:18,  3.30it/s]
 47%|████▋     | 174157/371472 [2:56:38<17:14:32,  3.18it/s]
 47%|████▋     | 174158/371472 [2:56:39<16:56:15,  3.24it/s]
 47%|████▋     | 174159/371472 [2:56:39<16:55:52,  3.24it/s]
 47%|████▋     | 174160/371472 [2:56:39<17:59:07,  3.05it/s]
                                                            
{'loss': 2.9106, 'learning_rate': 5.783037772845785e-07, 'epoch': 7.5}
+
 47%|████▋     | 174160/371472 [2:56:39<17:59:07,  3.05it/s]
 47%|████▋     | 174161/371472 [2:56:40<17:14:35,  3.18it/s]
 47%|████▋     | 174162/371472 [2:56:40<16:36:01,  3.30it/s]
 47%|████▋     | 174163/371472 [2:56:40<17:42:05,  3.10it/s]
 47%|████▋     | 174164/371472 [2:56:41<17:20:14,  3.16it/s]
 47%|████▋     | 174165/371472 [2:56:41<17:02:34,  3.22it/s]
 47%|████▋     | 174166/371472 [2:56:41<16:41:17,  3.28it/s]
 47%|████▋     | 174167/371472 [2:56:42<16:34:06,  3.31it/s]
 47%|████▋     | 174168/371472 [2:56:42<16:44:30,  3.27it/s]
 47%|████▋     | 174169/371472 [2:56:42<17:03:41,  3.21it/s]
 47%|████▋     | 174170/371472 [2:56:43<16:56:27,  3.24it/s]
 47%|████▋     | 174171/371472 [2:56:43<16:50:52,  3.25it/s]
 47%|████▋     | 174172/371472 [2:56:43<17:05:57,  3.21it/s]
 47%|████▋     | 174173/371472 [2:56:43<17:00:16,  3.22it/s]
 47%|████▋     | 174174/371472 [2:56:44<16:34:59,  3.30it/s]
 47%|████▋     | 174175/371472 [2:56:44<16:29:18,  3.32it/s]
 47%|████▋     | 174176/371472 [2:56:44<16:24:32,  3.34it/s]
 47%|████▋     | 174177/371472 [2:56:45<16:45:02,  3.27it/s]
 47%|████▋     | 174178/371472 [2:56:45<16:48:44,  3.26it/s]
 47%|████▋     | 174179/371472 [2:56:45<16:30:04,  3.32it/s]
 47%|████▋     | 174180/371472 [2:56:46<16:07:15,  3.40it/s]
                                                            
{'loss': 2.8405, 'learning_rate': 5.782552953090996e-07, 'epoch': 7.5}
+
 47%|████▋     | 174180/371472 [2:56:46<16:07:15,  3.40it/s]
 47%|████▋     | 174181/371472 [2:56:46<16:31:14,  3.32it/s]
 47%|████▋     | 174182/371472 [2:56:46<16:33:17,  3.31it/s]
 47%|████▋     | 174183/371472 [2:56:46<16:24:23,  3.34it/s]
 47%|████▋     | 174184/371472 [2:56:47<16:16:15,  3.37it/s]
 47%|████▋     | 174185/371472 [2:56:47<16:19:42,  3.36it/s]
 47%|████▋     | 174186/371472 [2:56:47<17:24:11,  3.15it/s]
 47%|████▋     | 174187/371472 [2:56:48<17:38:36,  3.11it/s]
 47%|████▋     | 174188/371472 [2:56:48<17:14:36,  3.18it/s]
 47%|████▋     | 174189/371472 [2:56:48<16:46:00,  3.27it/s]
 47%|████▋     | 174190/371472 [2:56:49<16:36:16,  3.30it/s]
 47%|████▋     | 174191/371472 [2:56:49<16:48:22,  3.26it/s]
 47%|████▋     | 174192/371472 [2:56:49<16:41:03,  3.28it/s]
 47%|████▋     | 174193/371472 [2:56:49<16:07:28,  3.40it/s]
 47%|████▋     | 174194/371472 [2:56:50<16:07:50,  3.40it/s]
 47%|████▋     | 174195/371472 [2:56:50<16:19:26,  3.36it/s]
 47%|████▋     | 174196/371472 [2:56:50<16:27:05,  3.33it/s]
 47%|████▋     | 174197/371472 [2:56:51<16:23:56,  3.34it/s]
 47%|████▋     | 174198/371472 [2:56:51<16:32:30,  3.31it/s]
 47%|████▋     | 174199/371472 [2:56:51<16:39:54,  3.29it/s]
 47%|████▋     | 174200/371472 [2:56:52<16:33:43,  3.31it/s]
                                                            
{'loss': 2.7486, 'learning_rate': 5.782068133336205e-07, 'epoch': 7.5}
+
 47%|████▋     | 174200/371472 [2:56:52<16:33:43,  3.31it/s]
 47%|████▋     | 174201/371472 [2:56:52<16:19:39,  3.36it/s]
 47%|████▋     | 174202/371472 [2:56:52<16:33:00,  3.31it/s]
 47%|████▋     | 174203/371472 [2:56:53<16:50:15,  3.25it/s]
 47%|████▋     | 174204/371472 [2:56:53<16:34:45,  3.31it/s]
 47%|████▋     | 174205/371472 [2:56:53<16:22:31,  3.35it/s]
 47%|████▋     | 174206/371472 [2:56:53<16:19:18,  3.36it/s]
 47%|████▋     | 174207/371472 [2:56:54<15:56:18,  3.44it/s]
 47%|████▋     | 174208/371472 [2:56:54<16:41:07,  3.28it/s]
 47%|████▋     | 174209/371472 [2:56:54<16:15:40,  3.37it/s]
 47%|████▋     | 174210/371472 [2:56:55<17:33:06,  3.12it/s]
 47%|████▋     | 174211/371472 [2:56:55<17:27:45,  3.14it/s]
 47%|████▋     | 174212/371472 [2:56:55<16:33:04,  3.31it/s]
 47%|████▋     | 174213/371472 [2:56:56<16:22:44,  3.35it/s]
 47%|████▋     | 174214/371472 [2:56:56<16:07:50,  3.40it/s]
 47%|████▋     | 174215/371472 [2:56:56<16:45:54,  3.27it/s]
 47%|████▋     | 174216/371472 [2:56:57<18:00:21,  3.04it/s]
 47%|████▋     | 174217/371472 [2:56:57<17:32:09,  3.12it/s]
 47%|████▋     | 174218/371472 [2:56:57<18:03:47,  3.03it/s]
 47%|████▋     | 174219/371472 [2:56:58<18:33:53,  2.95it/s]
 47%|████▋     | 174220/371472 [2:56:58<17:37:27,  3.11it/s]
                                                            
{'loss': 2.8409, 'learning_rate': 5.781583313581417e-07, 'epoch': 7.5}
+
 47%|████▋     | 174220/371472 [2:56:58<17:37:27,  3.11it/s]
 47%|████▋     | 174221/371472 [2:56:58<17:32:05,  3.12it/s]
 47%|████▋     | 174222/371472 [2:56:58<17:02:32,  3.22it/s]
 47%|████▋     | 174223/371472 [2:56:59<16:52:39,  3.25it/s]
 47%|████▋     | 174224/371472 [2:56:59<16:40:49,  3.28it/s]
 47%|████▋     | 174225/371472 [2:56:59<16:34:44,  3.30it/s]
 47%|████▋     | 174226/371472 [2:57:00<16:26:52,  3.33it/s]
 47%|████▋     | 174227/371472 [2:57:00<16:14:45,  3.37it/s]
 47%|████▋     | 174228/371472 [2:57:00<15:56:31,  3.44it/s]
 47%|████▋     | 174229/371472 [2:57:00<15:42:29,  3.49it/s]
 47%|████▋     | 174230/371472 [2:57:01<15:34:02,  3.52it/s]
 47%|████▋     | 174231/371472 [2:57:01<15:41:02,  3.49it/s]
 47%|████▋     | 174232/371472 [2:57:01<15:39:26,  3.50it/s]
 47%|████▋     | 174233/371472 [2:57:02<15:14:13,  3.60it/s]
 47%|████▋     | 174234/371472 [2:57:02<15:22:56,  3.56it/s]
 47%|████▋     | 174235/371472 [2:57:02<16:59:23,  3.22it/s]
 47%|████▋     | 174236/371472 [2:57:03<16:35:19,  3.30it/s]
 47%|████▋     | 174237/371472 [2:57:03<16:16:39,  3.37it/s]
 47%|████▋     | 174238/371472 [2:57:03<16:05:06,  3.41it/s]
 47%|████▋     | 174239/371472 [2:57:03<15:47:51,  3.47it/s]
 47%|████▋     | 174240/371472 [2:57:04<16:17:20,  3.36it/s]
                                                            
{'loss': 2.9866, 'learning_rate': 5.781098493826629e-07, 'epoch': 7.5}
+
 47%|████▋     | 174240/371472 [2:57:04<16:17:20,  3.36it/s]
 47%|████▋     | 174241/371472 [2:57:04<16:23:37,  3.34it/s]
 47%|████▋     | 174242/371472 [2:57:04<16:03:27,  3.41it/s]
 47%|████▋     | 174243/371472 [2:57:05<16:15:21,  3.37it/s]
 47%|████▋     | 174244/371472 [2:57:05<15:56:27,  3.44it/s]
 47%|████▋     | 174245/371472 [2:57:05<16:01:14,  3.42it/s]
 47%|████▋     | 174246/371472 [2:57:05<15:35:37,  3.51it/s]
 47%|████▋     | 174247/371472 [2:57:06<15:37:50,  3.50it/s]
 47%|████▋     | 174248/371472 [2:57:06<15:42:30,  3.49it/s]
 47%|████▋     | 174249/371472 [2:57:06<17:28:54,  3.13it/s]
 47%|████▋     | 174250/371472 [2:57:07<17:15:14,  3.18it/s]
 47%|████▋     | 174251/371472 [2:57:07<16:32:44,  3.31it/s]
 47%|████▋     | 174252/371472 [2:57:07<16:21:34,  3.35it/s]
 47%|████▋     | 174253/371472 [2:57:08<16:59:42,  3.22it/s]
 47%|████▋     | 174254/371472 [2:57:08<16:58:41,  3.23it/s]
 47%|████▋     | 174255/371472 [2:57:08<16:27:14,  3.33it/s]
 47%|████▋     | 174256/371472 [2:57:08<16:40:52,  3.28it/s]
 47%|████▋     | 174257/371472 [2:57:09<17:06:56,  3.20it/s]
 47%|████▋     | 174258/371472 [2:57:09<16:39:00,  3.29it/s]
 47%|████▋     | 174259/371472 [2:57:09<16:19:10,  3.36it/s]
 47%|████▋     | 174260/371472 [2:57:10<17:09:11,  3.19it/s]
                                                            
{'loss': 2.8109, 'learning_rate': 5.780613674071839e-07, 'epoch': 7.51}
+
 47%|████▋     | 174260/371472 [2:57:10<17:09:11,  3.19it/s]
 47%|████▋     | 174261/371472 [2:57:10<17:06:28,  3.20it/s]
 47%|████▋     | 174262/371472 [2:57:10<16:41:08,  3.28it/s]
 47%|████▋     | 174263/371472 [2:57:11<17:18:37,  3.16it/s]
 47%|████▋     | 174264/371472 [2:57:11<16:52:50,  3.25it/s]
 47%|████▋     | 174265/371472 [2:57:11<16:34:41,  3.30it/s]
 47%|████▋     | 174266/371472 [2:57:12<16:06:41,  3.40it/s]
 47%|████▋     | 174267/371472 [2:57:12<15:55:21,  3.44it/s]
 47%|████▋     | 174268/371472 [2:57:12<16:06:57,  3.40it/s]
 47%|████▋     | 174269/371472 [2:57:12<16:12:46,  3.38it/s]
 47%|████▋     | 174270/371472 [2:57:13<15:57:09,  3.43it/s]
 47%|████▋     | 174271/371472 [2:57:13<16:27:30,  3.33it/s]
 47%|████▋     | 174272/371472 [2:57:13<16:21:44,  3.35it/s]
 47%|████▋     | 174273/371472 [2:57:14<16:45:43,  3.27it/s]
 47%|████▋     | 174274/371472 [2:57:14<16:25:43,  3.33it/s]
 47%|████▋     | 174275/371472 [2:57:14<17:33:05,  3.12it/s]
 47%|████▋     | 174276/371472 [2:57:15<18:14:41,  3.00it/s]
 47%|████▋     | 174277/371472 [2:57:15<17:47:29,  3.08it/s]
 47%|████▋     | 174278/371472 [2:57:15<17:11:27,  3.19it/s]
 47%|████▋     | 174279/371472 [2:57:16<16:53:43,  3.24it/s]
 47%|████▋     | 174280/371472 [2:57:16<16:55:13,  3.24it/s]
                                                            
{'loss': 2.8109, 'learning_rate': 5.78012885431705e-07, 'epoch': 7.51}
+
 47%|████▋     | 174280/371472 [2:57:16<16:55:13,  3.24it/s]
 47%|████▋     | 174281/371472 [2:57:16<17:41:10,  3.10it/s]
 47%|████▋     | 174282/371472 [2:57:17<17:20:33,  3.16it/s]
 47%|████▋     | 174283/371472 [2:57:17<16:48:05,  3.26it/s]
 47%|████▋     | 174284/371472 [2:57:17<16:59:06,  3.22it/s]
 47%|████▋     | 174285/371472 [2:57:17<16:27:54,  3.33it/s]
 47%|████▋     | 174286/371472 [2:57:18<16:24:26,  3.34it/s]
 47%|████▋     | 174287/371472 [2:57:18<16:19:38,  3.35it/s]
 47%|████▋     | 174288/371472 [2:57:18<16:09:16,  3.39it/s]
 47%|████▋     | 174289/371472 [2:57:19<16:02:12,  3.42it/s]
 47%|████▋     | 174290/371472 [2:57:19<15:56:39,  3.44it/s]
 47%|████▋     | 174291/371472 [2:57:19<16:04:42,  3.41it/s]
 47%|████▋     | 174292/371472 [2:57:19<15:47:27,  3.47it/s]
 47%|████▋     | 174293/371472 [2:57:20<16:44:48,  3.27it/s]
 47%|████▋     | 174294/371472 [2:57:20<16:49:38,  3.25it/s]
 47%|████▋     | 174295/371472 [2:57:20<16:11:27,  3.38it/s]
 47%|████▋     | 174296/371472 [2:57:21<15:58:09,  3.43it/s]
 47%|████▋     | 174297/371472 [2:57:21<16:08:30,  3.39it/s]
 47%|████▋     | 174298/371472 [2:57:21<15:53:12,  3.45it/s]
 47%|████▋     | 174299/371472 [2:57:22<16:04:00,  3.41it/s]
 47%|████▋     | 174300/371472 [2:57:22<15:56:41,  3.43it/s]
                                                            
{'loss': 2.9757, 'learning_rate': 5.779644034562262e-07, 'epoch': 7.51}
+
 47%|████▋     | 174300/371472 [2:57:22<15:56:41,  3.43it/s]
 47%|████▋     | 174301/371472 [2:57:22<15:47:09,  3.47it/s]
 47%|████▋     | 174302/371472 [2:57:22<15:49:43,  3.46it/s]
 47%|████▋     | 174303/371472 [2:57:23<16:02:10,  3.42it/s]
 47%|████▋     | 174304/371472 [2:57:23<15:40:59,  3.49it/s]
 47%|████▋     | 174305/371472 [2:57:23<15:46:00,  3.47it/s]
 47%|████▋     | 174306/371472 [2:57:24<15:28:47,  3.54it/s]
 47%|████▋     | 174307/371472 [2:57:24<15:15:41,  3.59it/s]
 47%|████▋     | 174308/371472 [2:57:24<16:24:49,  3.34it/s]
 47%|████▋     | 174309/371472 [2:57:24<16:23:13,  3.34it/s]
 47%|████▋     | 174310/371472 [2:57:25<16:15:39,  3.37it/s]
 47%|████▋     | 174311/371472 [2:57:25<15:41:03,  3.49it/s]
 47%|████▋     | 174312/371472 [2:57:25<15:36:51,  3.51it/s]
 47%|████▋     | 174313/371472 [2:57:26<15:31:26,  3.53it/s]
 47%|████▋     | 174314/371472 [2:57:26<15:20:04,  3.57it/s]
 47%|████▋     | 174315/371472 [2:57:26<15:22:45,  3.56it/s]
 47%|████▋     | 174316/371472 [2:57:26<16:14:34,  3.37it/s]
 47%|████▋     | 174317/371472 [2:57:27<16:05:58,  3.40it/s]
 47%|████▋     | 174318/371472 [2:57:27<16:37:29,  3.29it/s]
 47%|████▋     | 174319/371472 [2:57:27<16:03:08,  3.41it/s]
 47%|████▋     | 174320/371472 [2:57:28<17:17:51,  3.17it/s]
                                                            
{'loss': 2.9165, 'learning_rate': 5.779159214807473e-07, 'epoch': 7.51}
+
 47%|████▋     | 174320/371472 [2:57:28<17:17:51,  3.17it/s]
 47%|████▋     | 174321/371472 [2:57:28<16:50:16,  3.25it/s]
 47%|████▋     | 174322/371472 [2:57:28<16:36:20,  3.30it/s]
 47%|████▋     | 174323/371472 [2:57:29<16:12:30,  3.38it/s]
 47%|████▋     | 174324/371472 [2:57:29<16:02:18,  3.41it/s]
 47%|████▋     | 174325/371472 [2:57:29<15:37:39,  3.50it/s]
 47%|████▋     | 174326/371472 [2:57:29<15:15:19,  3.59it/s]
 47%|████▋     | 174327/371472 [2:57:30<15:32:46,  3.52it/s]
 47%|████▋     | 174328/371472 [2:57:30<15:27:05,  3.54it/s]
 47%|████▋     | 174329/371472 [2:57:30<16:12:34,  3.38it/s]
 47%|████▋     | 174330/371472 [2:57:31<17:11:21,  3.19it/s]
 47%|████▋     | 174331/371472 [2:57:31<17:03:24,  3.21it/s]
 47%|████▋     | 174332/371472 [2:57:31<16:33:35,  3.31it/s]
 47%|████▋     | 174333/371472 [2:57:31<16:07:59,  3.39it/s]
 47%|████▋     | 174334/371472 [2:57:32<16:14:32,  3.37it/s]
 47%|████▋     | 174335/371472 [2:57:32<15:46:30,  3.47it/s]
 47%|████▋     | 174336/371472 [2:57:32<15:52:44,  3.45it/s]
 47%|████▋     | 174337/371472 [2:57:33<15:55:04,  3.44it/s]
 47%|████▋     | 174338/371472 [2:57:33<16:19:23,  3.35it/s]
 47%|████▋     | 174339/371472 [2:57:33<16:20:22,  3.35it/s]
 47%|████▋     | 174340/371472 [2:57:34<16:25:11,  3.33it/s]
                                                            
{'loss': 3.0805, 'learning_rate': 5.778674395052683e-07, 'epoch': 7.51}
+
 47%|████▋     | 174340/371472 [2:57:34<16:25:11,  3.33it/s]
 47%|████▋     | 174341/371472 [2:57:34<16:02:41,  3.41it/s]
 47%|████▋     | 174342/371472 [2:57:34<15:54:03,  3.44it/s]
 47%|████▋     | 174343/371472 [2:57:34<15:43:14,  3.48it/s]
 47%|████▋     | 174344/371472 [2:57:35<15:27:03,  3.54it/s]
 47%|████▋     | 174345/371472 [2:57:35<15:20:00,  3.57it/s]
 47%|████▋     | 174346/371472 [2:57:35<15:29:13,  3.54it/s]
 47%|████▋     | 174347/371472 [2:57:36<15:19:16,  3.57it/s]
 47%|████▋     | 174348/371472 [2:57:36<15:21:15,  3.57it/s]
 47%|████▋     | 174349/371472 [2:57:36<17:35:51,  3.11it/s]
 47%|████▋     | 174350/371472 [2:57:36<17:08:00,  3.20it/s]
 47%|████▋     | 174351/371472 [2:57:37<17:04:18,  3.21it/s]
 47%|████▋     | 174352/371472 [2:57:37<16:49:07,  3.26it/s]
 47%|████▋     | 174353/371472 [2:57:38<18:32:51,  2.95it/s]
 47%|████▋     | 174354/371472 [2:57:38<20:57:39,  2.61it/s]
 47%|████▋     | 174355/371472 [2:57:38<19:26:13,  2.82it/s]
 47%|████▋     | 174356/371472 [2:57:39<18:49:33,  2.91it/s]
 47%|████▋     | 174357/371472 [2:57:39<18:06:29,  3.02it/s]
 47%|████▋     | 174358/371472 [2:57:39<17:36:27,  3.11it/s]
 47%|████▋     | 174359/371472 [2:57:39<17:04:48,  3.21it/s]
 47%|████▋     | 174360/371472 [2:57:40<16:47:38,  3.26it/s]
                                                            
{'loss': 3.0664, 'learning_rate': 5.778189575297894e-07, 'epoch': 7.51}
+
 47%|████▋     | 174360/371472 [2:57:40<16:47:38,  3.26it/s]
 47%|████▋     | 174361/371472 [2:57:40<16:34:52,  3.30it/s]
 47%|████▋     | 174362/371472 [2:57:40<16:25:02,  3.34it/s]
 47%|████▋     | 174363/371472 [2:57:41<16:28:51,  3.32it/s]
 47%|████▋     | 174364/371472 [2:57:41<16:33:10,  3.31it/s]
 47%|████▋     | 174365/371472 [2:57:41<16:52:33,  3.24it/s]
 47%|████▋     | 174366/371472 [2:57:42<16:26:34,  3.33it/s]
 47%|████▋     | 174367/371472 [2:57:42<17:11:41,  3.18it/s]
 47%|████▋     | 174368/371472 [2:57:42<16:53:22,  3.24it/s]
 47%|████▋     | 174369/371472 [2:57:43<16:49:39,  3.25it/s]
 47%|████▋     | 174370/371472 [2:57:43<16:29:11,  3.32it/s]
 47%|████▋     | 174371/371472 [2:57:43<16:06:28,  3.40it/s]
 47%|████▋     | 174372/371472 [2:57:43<15:51:44,  3.45it/s]
 47%|████▋     | 174373/371472 [2:57:44<15:59:37,  3.42it/s]
 47%|████▋     | 174374/371472 [2:57:44<17:05:53,  3.20it/s]
 47%|████▋     | 174375/371472 [2:57:44<17:38:21,  3.10it/s]
 47%|████▋     | 174376/371472 [2:57:45<17:01:33,  3.22it/s]
 47%|████▋     | 174377/371472 [2:57:45<16:41:53,  3.28it/s]
 47%|████▋     | 174378/371472 [2:57:45<17:41:28,  3.09it/s]
 47%|████▋     | 174379/371472 [2:57:46<16:47:27,  3.26it/s]
 47%|████▋     | 174380/371472 [2:57:46<17:34:46,  3.11it/s]
                                                            
{'loss': 2.7602, 'learning_rate': 5.777704755543106e-07, 'epoch': 7.51}
+
 47%|████▋     | 174380/371472 [2:57:46<17:34:46,  3.11it/s]
 47%|████▋     | 174381/371472 [2:57:46<17:38:47,  3.10it/s]
 47%|████▋     | 174382/371472 [2:57:47<17:32:40,  3.12it/s]
 47%|████▋     | 174383/371472 [2:57:47<16:59:28,  3.22it/s]
 47%|████▋     | 174384/371472 [2:57:47<17:01:02,  3.22it/s]
 47%|████▋     | 174385/371472 [2:57:48<17:20:29,  3.16it/s]
 47%|████▋     | 174386/371472 [2:57:48<18:05:19,  3.03it/s]
 47%|████▋     | 174387/371472 [2:57:48<17:30:40,  3.13it/s]
 47%|████▋     | 174388/371472 [2:57:48<17:06:14,  3.20it/s]
 47%|████▋     | 174389/371472 [2:57:49<16:43:04,  3.27it/s]
 47%|████▋     | 174390/371472 [2:57:49<16:42:08,  3.28it/s]
 47%|████▋     | 174391/371472 [2:57:49<16:43:41,  3.27it/s]
 47%|████▋     | 174392/371472 [2:57:50<17:01:05,  3.22it/s]
 47%|████▋     | 174393/371472 [2:57:50<17:36:56,  3.11it/s]
 47%|████▋     | 174394/371472 [2:57:50<17:17:57,  3.16it/s]
 47%|████▋     | 174395/371472 [2:57:51<16:50:42,  3.25it/s]
 47%|████▋     | 174396/371472 [2:57:51<16:46:04,  3.26it/s]
 47%|████▋     | 174397/371472 [2:57:51<16:39:42,  3.29it/s]
 47%|████▋     | 174398/371472 [2:57:52<17:42:43,  3.09it/s]
 47%|████▋     | 174399/371472 [2:57:52<17:11:46,  3.18it/s]
 47%|████▋     | 174400/371472 [2:57:52<17:03:12,  3.21it/s]
                                                            
{'loss': 2.8023, 'learning_rate': 5.777219935788318e-07, 'epoch': 7.51}
+
 47%|████▋     | 174400/371472 [2:57:52<17:03:12,  3.21it/s]
 47%|████▋     | 174401/371472 [2:57:52<16:41:35,  3.28it/s]
 47%|████▋     | 174402/371472 [2:57:53<16:09:14,  3.39it/s]
 47%|████▋     | 174403/371472 [2:57:53<16:35:09,  3.30it/s]
 47%|████▋     | 174404/371472 [2:57:53<16:12:54,  3.38it/s]
 47%|████▋     | 174405/371472 [2:57:54<16:05:12,  3.40it/s]
 47%|████▋     | 174406/371472 [2:57:54<16:42:22,  3.28it/s]
 47%|████▋     | 174407/371472 [2:57:54<16:56:07,  3.23it/s]
 47%|████▋     | 174408/371472 [2:57:55<16:35:49,  3.30it/s]
 47%|████▋     | 174409/371472 [2:57:55<16:59:08,  3.22it/s]
 47%|████▋     | 174410/371472 [2:57:55<17:33:44,  3.12it/s]
 47%|████▋     | 174411/371472 [2:57:56<16:56:00,  3.23it/s]
 47%|████▋     | 174412/371472 [2:57:56<16:57:48,  3.23it/s]
 47%|████▋     | 174413/371472 [2:57:56<17:05:35,  3.20it/s]
 47%|████▋     | 174414/371472 [2:57:56<16:16:51,  3.36it/s]
 47%|████▋     | 174415/371472 [2:57:57<16:07:28,  3.39it/s]
 47%|████▋     | 174416/371472 [2:57:57<16:01:42,  3.42it/s]
 47%|████▋     | 174417/371472 [2:57:57<16:14:01,  3.37it/s]
 47%|████▋     | 174418/371472 [2:57:58<16:33:18,  3.31it/s]
 47%|████▋     | 174419/371472 [2:57:58<16:53:32,  3.24it/s]
 47%|████▋     | 174420/371472 [2:57:58<16:45:51,  3.27it/s]
                                                            
{'loss': 2.9864, 'learning_rate': 5.776735116033528e-07, 'epoch': 7.51}
+
 47%|████▋     | 174420/371472 [2:57:58<16:45:51,  3.27it/s]
 47%|████▋     | 174421/371472 [2:57:59<16:28:12,  3.32it/s]
 47%|████▋     | 174422/371472 [2:57:59<16:05:13,  3.40it/s]
 47%|████▋     | 174423/371472 [2:57:59<16:56:53,  3.23it/s]
 47%|████▋     | 174424/371472 [2:57:59<16:50:53,  3.25it/s]
 47%|████▋     | 174425/371472 [2:58:00<17:25:56,  3.14it/s]
 47%|████▋     | 174426/371472 [2:58:00<16:43:22,  3.27it/s]
 47%|████▋     | 174427/371472 [2:58:00<17:18:28,  3.16it/s]
 47%|████▋     | 174428/371472 [2:58:01<17:28:04,  3.13it/s]
 47%|████▋     | 174429/371472 [2:58:01<17:10:04,  3.19it/s]
 47%|████▋     | 174430/371472 [2:58:01<16:14:08,  3.37it/s]
 47%|████▋     | 174431/371472 [2:58:02<17:54:33,  3.06it/s]
 47%|████▋     | 174432/371472 [2:58:02<17:30:45,  3.13it/s]
 47%|████▋     | 174433/371472 [2:58:02<16:53:44,  3.24it/s]
 47%|████▋     | 174434/371472 [2:58:03<16:34:27,  3.30it/s]
 47%|████▋     | 174435/371472 [2:58:03<16:06:10,  3.40it/s]
 47%|████▋     | 174436/371472 [2:58:03<16:00:13,  3.42it/s]
 47%|████▋     | 174437/371472 [2:58:03<15:45:05,  3.47it/s]
 47%|████▋     | 174438/371472 [2:58:04<15:53:40,  3.44it/s]
 47%|████▋     | 174439/371472 [2:58:04<15:53:17,  3.44it/s]
 47%|████▋     | 174440/371472 [2:58:04<15:52:02,  3.45it/s]
                                                            
{'loss': 2.9893, 'learning_rate': 5.776250296278738e-07, 'epoch': 7.51}
+
 47%|████▋     | 174440/371472 [2:58:04<15:52:02,  3.45it/s]
 47%|████▋     | 174441/371472 [2:58:05<18:09:24,  3.01it/s]
 47%|████▋     | 174442/371472 [2:58:05<17:31:15,  3.12it/s]
 47%|████▋     | 174443/371472 [2:58:05<16:44:17,  3.27it/s]
 47%|████▋     | 174444/371472 [2:58:06<16:29:08,  3.32it/s]
 47%|████▋     | 174445/371472 [2:58:06<16:18:06,  3.36it/s]
 47%|████▋     | 174446/371472 [2:58:06<16:41:58,  3.28it/s]
 47%|████▋     | 174447/371472 [2:58:07<16:59:22,  3.22it/s]
 47%|████▋     | 174448/371472 [2:58:07<16:16:03,  3.36it/s]
 47%|████▋     | 174449/371472 [2:58:07<15:54:37,  3.44it/s]
 47%|████▋     | 174450/371472 [2:58:07<15:54:43,  3.44it/s]
 47%|████▋     | 174451/371472 [2:58:08<16:23:15,  3.34it/s]
 47%|████▋     | 174452/371472 [2:58:08<16:02:25,  3.41it/s]
 47%|████▋     | 174453/371472 [2:58:08<15:33:36,  3.52it/s]
 47%|████▋     | 174454/371472 [2:58:09<15:36:00,  3.51it/s]
 47%|████▋     | 174455/371472 [2:58:09<15:36:41,  3.51it/s]
 47%|████▋     | 174456/371472 [2:58:09<15:04:06,  3.63it/s]
 47%|████▋     | 174457/371472 [2:58:09<15:28:05,  3.54it/s]
 47%|████▋     | 174458/371472 [2:58:10<15:32:18,  3.52it/s]
 47%|████▋     | 174459/371472 [2:58:10<15:46:16,  3.47it/s]
 47%|████▋     | 174460/371472 [2:58:10<16:13:01,  3.37it/s]
                                                            
{'loss': 2.889, 'learning_rate': 5.77576547652395e-07, 'epoch': 7.51}
+
 47%|████▋     | 174460/371472 [2:58:10<16:13:01,  3.37it/s]
 47%|████▋     | 174461/371472 [2:58:11<15:50:40,  3.45it/s]
 47%|████▋     | 174462/371472 [2:58:11<15:49:32,  3.46it/s]
 47%|████▋     | 174463/371472 [2:58:11<16:14:13,  3.37it/s]
 47%|████▋     | 174464/371472 [2:58:11<16:31:45,  3.31it/s]
 47%|████▋     | 174465/371472 [2:58:12<16:03:45,  3.41it/s]
 47%|████▋     | 174466/371472 [2:58:12<16:18:52,  3.35it/s]
 47%|████▋     | 174467/371472 [2:58:12<16:10:55,  3.38it/s]
 47%|████▋     | 174468/371472 [2:58:13<17:00:39,  3.22it/s]
 47%|████▋     | 174469/371472 [2:58:13<16:25:08,  3.33it/s]
 47%|████▋     | 174470/371472 [2:58:13<16:03:53,  3.41it/s]
 47%|████▋     | 174471/371472 [2:58:14<16:04:15,  3.41it/s]
 47%|████▋     | 174472/371472 [2:58:14<17:34:43,  3.11it/s]
 47%|████▋     | 174473/371472 [2:58:14<17:13:11,  3.18it/s]
 47%|████▋     | 174474/371472 [2:58:14<16:27:33,  3.32it/s]
 47%|████▋     | 174475/371472 [2:58:15<16:00:29,  3.42it/s]
 47%|████▋     | 174476/371472 [2:58:15<15:49:47,  3.46it/s]
 47%|████▋     | 174477/371472 [2:58:15<16:03:20,  3.41it/s]
 47%|████▋     | 174478/371472 [2:58:16<15:42:14,  3.48it/s]
 47%|████▋     | 174479/371472 [2:58:16<15:51:27,  3.45it/s]
 47%|████▋     | 174480/371472 [2:58:16<16:10:08,  3.38it/s]
                                                            
{'loss': 3.0151, 'learning_rate': 5.77528065676916e-07, 'epoch': 7.52}
+
 47%|████▋     | 174480/371472 [2:58:16<16:10:08,  3.38it/s]
 47%|████▋     | 174481/371472 [2:58:16<16:16:58,  3.36it/s]
 47%|████▋     | 174482/371472 [2:58:17<16:13:00,  3.37it/s]
 47%|████▋     | 174483/371472 [2:58:17<16:04:23,  3.40it/s]
 47%|████▋     | 174484/371472 [2:58:17<17:30:14,  3.13it/s]
 47%|████▋     | 174485/371472 [2:58:18<17:15:37,  3.17it/s]
 47%|████▋     | 174486/371472 [2:58:18<18:29:53,  2.96it/s]
 47%|████▋     | 174487/371472 [2:58:19<19:29:28,  2.81it/s]
 47%|████▋     | 174488/371472 [2:58:19<21:03:33,  2.60it/s]
 47%|████▋     | 174489/371472 [2:58:19<19:40:04,  2.78it/s]
 47%|████▋     | 174490/371472 [2:58:20<18:59:34,  2.88it/s]
 47%|████▋     | 174491/371472 [2:58:20<18:09:55,  3.01it/s]
 47%|████▋     | 174492/371472 [2:58:20<17:40:54,  3.09it/s]
 47%|████▋     | 174493/371472 [2:58:21<17:43:27,  3.09it/s]
 47%|████▋     | 174494/371472 [2:58:21<17:05:20,  3.20it/s]
 47%|████▋     | 174495/371472 [2:58:21<16:59:06,  3.22it/s]
 47%|████▋     | 174496/371472 [2:58:21<16:44:19,  3.27it/s]
 47%|████▋     | 174497/371472 [2:58:22<16:04:01,  3.41it/s]
 47%|████▋     | 174498/371472 [2:58:22<16:06:56,  3.40it/s]
 47%|████▋     | 174499/371472 [2:58:22<16:04:59,  3.40it/s]
 47%|████▋     | 174500/371472 [2:58:23<15:43:10,  3.48it/s]
                                                            
{'loss': 2.9809, 'learning_rate': 5.774795837014371e-07, 'epoch': 7.52}
+
 47%|████▋     | 174500/371472 [2:58:23<15:43:10,  3.48it/s]
 47%|████▋     | 174501/371472 [2:58:23<16:10:40,  3.38it/s]
 47%|████▋     | 174502/371472 [2:58:23<15:56:13,  3.43it/s]
 47%|████▋     | 174503/371472 [2:58:23<15:23:56,  3.55it/s]
 47%|████▋     | 174504/371472 [2:58:24<15:20:46,  3.57it/s]
 47%|████▋     | 174505/371472 [2:58:24<15:35:02,  3.51it/s]
 47%|████▋     | 174506/371472 [2:58:24<16:45:47,  3.26it/s]
 47%|████▋     | 174507/371472 [2:58:25<16:19:53,  3.35it/s]
 47%|████▋     | 174508/371472 [2:58:25<15:55:34,  3.44it/s]
 47%|████▋     | 174509/371472 [2:58:25<15:45:03,  3.47it/s]
 47%|████▋     | 174510/371472 [2:58:25<15:30:37,  3.53it/s]
 47%|████▋     | 174511/371472 [2:58:26<15:36:04,  3.51it/s]
 47%|████▋     | 174512/371472 [2:58:26<15:56:37,  3.43it/s]
 47%|████▋     | 174513/371472 [2:58:26<16:20:39,  3.35it/s]
 47%|████▋     | 174514/371472 [2:58:27<16:47:10,  3.26it/s]
 47%|████▋     | 174515/371472 [2:58:27<16:46:14,  3.26it/s]
 47%|████▋     | 174516/371472 [2:58:27<16:16:51,  3.36it/s]
 47%|████▋     | 174517/371472 [2:58:28<16:14:34,  3.37it/s]
 47%|████▋     | 174518/371472 [2:58:28<16:35:09,  3.30it/s]
 47%|████▋     | 174519/371472 [2:58:28<16:05:16,  3.40it/s]
 47%|████▋     | 174520/371472 [2:58:28<15:44:29,  3.48it/s]
                                                            
{'loss': 2.9486, 'learning_rate': 5.774311017259583e-07, 'epoch': 7.52}
+
 47%|████▋     | 174520/371472 [2:58:28<15:44:29,  3.48it/s]
 47%|████▋     | 174521/371472 [2:58:29<16:13:53,  3.37it/s]
 47%|████▋     | 174522/371472 [2:58:29<16:51:24,  3.25it/s]
 47%|████▋     | 174523/371472 [2:58:29<16:20:25,  3.35it/s]
 47%|████▋     | 174524/371472 [2:58:30<16:05:48,  3.40it/s]
 47%|████▋     | 174525/371472 [2:58:30<16:01:25,  3.41it/s]
 47%|████▋     | 174526/371472 [2:58:30<16:05:48,  3.40it/s]
 47%|████▋     | 174527/371472 [2:58:31<15:59:10,  3.42it/s]
 47%|████▋     | 174528/371472 [2:58:31<15:40:49,  3.49it/s]
 47%|████▋     | 174529/371472 [2:58:31<15:19:30,  3.57it/s]
 47%|████▋     | 174530/371472 [2:58:31<15:25:10,  3.55it/s]
 47%|████▋     | 174531/371472 [2:58:32<15:50:48,  3.45it/s]
 47%|████▋     | 174532/371472 [2:58:32<15:44:54,  3.47it/s]
 47%|████▋     | 174533/371472 [2:58:32<16:00:21,  3.42it/s]
 47%|████▋     | 174534/371472 [2:58:33<15:34:11,  3.51it/s]
 47%|████▋     | 174535/371472 [2:58:33<15:28:28,  3.54it/s]
 47%|████▋     | 174536/371472 [2:58:33<15:57:24,  3.43it/s]
 47%|████▋     | 174537/371472 [2:58:33<15:59:56,  3.42it/s]
 47%|████▋     | 174538/371472 [2:58:34<15:55:12,  3.44it/s]
 47%|████▋     | 174539/371472 [2:58:34<15:47:17,  3.46it/s]
 47%|████▋     | 174540/371472 [2:58:34<16:27:49,  3.32it/s]
                                                            
{'loss': 2.8693, 'learning_rate': 5.773826197504796e-07, 'epoch': 7.52}
+
 47%|████▋     | 174540/371472 [2:58:34<16:27:49,  3.32it/s]
 47%|████▋     | 174541/371472 [2:58:35<17:10:37,  3.18it/s]
 47%|████▋     | 174542/371472 [2:58:35<16:36:14,  3.29it/s]
 47%|████▋     | 174543/371472 [2:58:35<17:08:31,  3.19it/s]
 47%|████▋     | 174544/371472 [2:58:36<16:57:49,  3.22it/s]
 47%|████▋     | 174545/371472 [2:58:36<16:38:01,  3.29it/s]
 47%|████▋     | 174546/371472 [2:58:36<16:26:40,  3.33it/s]
 47%|████▋     | 174547/371472 [2:58:36<16:13:00,  3.37it/s]
 47%|████▋     | 174548/371472 [2:58:37<16:28:16,  3.32it/s]
 47%|████▋     | 174549/371472 [2:58:37<16:15:44,  3.36it/s]
 47%|████▋     | 174550/371472 [2:58:37<16:15:45,  3.36it/s]
 47%|████▋     | 174551/371472 [2:58:38<16:51:41,  3.24it/s]
 47%|████▋     | 174552/371472 [2:58:38<16:26:00,  3.33it/s]
 47%|████▋     | 174553/371472 [2:58:38<16:01:57,  3.41it/s]
 47%|████▋     | 174554/371472 [2:58:38<15:42:05,  3.48it/s]
 47%|████▋     | 174555/371472 [2:58:39<16:07:57,  3.39it/s]
 47%|████▋     | 174556/371472 [2:58:39<16:02:39,  3.41it/s]
 47%|████▋     | 174557/371472 [2:58:39<16:17:52,  3.36it/s]
 47%|████▋     | 174558/371472 [2:58:40<16:02:38,  3.41it/s]
 47%|████▋     | 174559/371472 [2:58:40<16:01:08,  3.41it/s]
 47%|████▋     | 174560/371472 [2:58:40<16:36:51,  3.29it/s]
                                                            
{'loss': 2.9246, 'learning_rate': 5.773341377750005e-07, 'epoch': 7.52}
+
 47%|████▋     | 174560/371472 [2:58:40<16:36:51,  3.29it/s]
 47%|████▋     | 174561/371472 [2:58:41<16:05:39,  3.40it/s]
 47%|████▋     | 174562/371472 [2:58:41<16:23:01,  3.34it/s]
 47%|████▋     | 174563/371472 [2:58:41<16:06:42,  3.39it/s]
 47%|████▋     | 174564/371472 [2:58:41<16:30:21,  3.31it/s]
 47%|████▋     | 174565/371472 [2:58:42<16:35:27,  3.30it/s]
 47%|████▋     | 174566/371472 [2:58:42<16:01:59,  3.41it/s]
 47%|████▋     | 174567/371472 [2:58:42<15:54:29,  3.44it/s]
 47%|████▋     | 174568/371472 [2:58:43<15:44:08,  3.48it/s]
 47%|████▋     | 174569/371472 [2:58:43<15:53:07,  3.44it/s]
 47%|████▋     | 174570/371472 [2:58:43<15:49:02,  3.46it/s]
 47%|████▋     | 174571/371472 [2:58:43<15:43:45,  3.48it/s]
 47%|████▋     | 174572/371472 [2:58:44<16:11:01,  3.38it/s]
 47%|████▋     | 174573/371472 [2:58:44<16:13:34,  3.37it/s]
 47%|████▋     | 174574/371472 [2:58:44<15:59:42,  3.42it/s]
 47%|████▋     | 174575/371472 [2:58:45<15:49:12,  3.46it/s]
 47%|████▋     | 174576/371472 [2:58:45<15:43:03,  3.48it/s]
 47%|████▋     | 174577/371472 [2:58:45<15:58:21,  3.42it/s]
 47%|████▋     | 174578/371472 [2:58:46<16:19:29,  3.35it/s]
 47%|████▋     | 174579/371472 [2:58:46<16:03:07,  3.41it/s]
 47%|████▋     | 174580/371472 [2:58:46<16:18:19,  3.35it/s]
                                                            
{'loss': 3.1529, 'learning_rate': 5.772856557995215e-07, 'epoch': 7.52}
+
 47%|████▋     | 174580/371472 [2:58:46<16:18:19,  3.35it/s]
 47%|████▋     | 174581/371472 [2:58:46<16:28:31,  3.32it/s]
 47%|████▋     | 174582/371472 [2:58:47<16:07:50,  3.39it/s]
 47%|████▋     | 174583/371472 [2:58:47<16:48:45,  3.25it/s]
 47%|████▋     | 174584/371472 [2:58:47<17:27:26,  3.13it/s]
 47%|████▋     | 174585/371472 [2:58:48<17:07:06,  3.19it/s]
 47%|████▋     | 174586/371472 [2:58:48<16:47:31,  3.26it/s]
 47%|████▋     | 174587/371472 [2:58:48<17:38:24,  3.10it/s]
 47%|████▋     | 174588/371472 [2:58:49<18:08:41,  3.01it/s]
 47%|████▋     | 174589/371472 [2:58:49<18:49:19,  2.91it/s]
 47%|████▋     | 174590/371472 [2:58:50<19:49:37,  2.76it/s]
 47%|████▋     | 174591/371472 [2:58:50<19:46:10,  2.77it/s]
 47%|████▋     | 174592/371472 [2:58:50<19:53:50,  2.75it/s]
 47%|████▋     | 174593/371472 [2:58:51<20:47:41,  2.63it/s]
 47%|████▋     | 174594/371472 [2:58:51<19:48:10,  2.76it/s]
 47%|████▋     | 174595/371472 [2:58:51<19:26:07,  2.81it/s]
 47%|████▋     | 174596/371472 [2:58:52<18:35:46,  2.94it/s]
 47%|████▋     | 174597/371472 [2:58:52<17:58:31,  3.04it/s]
 47%|████▋     | 174598/371472 [2:58:52<17:58:50,  3.04it/s]
 47%|████▋     | 174599/371472 [2:58:53<18:20:34,  2.98it/s]
 47%|████▋     | 174600/371472 [2:58:53<17:34:16,  3.11it/s]
                                                            
{'loss': 2.8535, 'learning_rate': 5.772371738240427e-07, 'epoch': 7.52}
+
 47%|████▋     | 174600/371472 [2:58:53<17:34:16,  3.11it/s]
 47%|████▋     | 174601/371472 [2:58:53<16:54:52,  3.23it/s]
 47%|████▋     | 174602/371472 [2:58:53<16:57:20,  3.23it/s]
 47%|████▋     | 174603/371472 [2:58:54<16:27:33,  3.32it/s]
 47%|████▋     | 174604/371472 [2:58:54<15:46:16,  3.47it/s]
 47%|████▋     | 174605/371472 [2:58:54<15:55:56,  3.43it/s]
 47%|████▋     | 174606/371472 [2:58:55<16:26:04,  3.33it/s]
 47%|████▋     | 174607/371472 [2:58:55<16:21:22,  3.34it/s]
 47%|████▋     | 174608/371472 [2:58:55<16:15:32,  3.36it/s]
 47%|████▋     | 174609/371472 [2:58:56<16:10:38,  3.38it/s]
 47%|████▋     | 174610/371472 [2:58:56<16:31:35,  3.31it/s]
 47%|████▋     | 174611/371472 [2:58:56<16:30:00,  3.31it/s]
 47%|████▋     | 174612/371472 [2:58:56<16:16:57,  3.36it/s]
 47%|████▋     | 174613/371472 [2:58:57<16:26:17,  3.33it/s]
 47%|████▋     | 174614/371472 [2:58:57<17:13:07,  3.18it/s]
 47%|████▋     | 174615/371472 [2:58:57<16:39:50,  3.28it/s]
 47%|████▋     | 174616/371472 [2:58:58<17:25:42,  3.14it/s]
 47%|████▋     | 174617/371472 [2:58:58<16:49:12,  3.25it/s]
 47%|████▋     | 174618/371472 [2:58:58<16:14:02,  3.37it/s]
 47%|████▋     | 174619/371472 [2:58:59<16:01:58,  3.41it/s]
 47%|████▋     | 174620/371472 [2:58:59<15:42:51,  3.48it/s]
                                                            
{'loss': 2.93, 'learning_rate': 5.771886918485639e-07, 'epoch': 7.52}
+
 47%|████▋     | 174620/371472 [2:58:59<15:42:51,  3.48it/s]
 47%|████▋     | 174621/371472 [2:58:59<16:01:01,  3.41it/s]
 47%|████▋     | 174622/371472 [2:58:59<15:44:24,  3.47it/s]
 47%|████▋     | 174623/371472 [2:59:00<15:50:33,  3.45it/s]
 47%|████▋     | 174624/371472 [2:59:00<15:50:53,  3.45it/s]
 47%|████▋     | 174625/371472 [2:59:00<17:03:29,  3.21it/s]
 47%|████▋     | 174626/371472 [2:59:01<16:16:33,  3.36it/s]
 47%|████▋     | 174627/371472 [2:59:01<16:01:09,  3.41it/s]
 47%|████▋     | 174628/371472 [2:59:01<16:11:15,  3.38it/s]
 47%|████▋     | 174629/371472 [2:59:01<15:42:26,  3.48it/s]
 47%|████▋     | 174630/371472 [2:59:02<15:44:55,  3.47it/s]
 47%|████▋     | 174631/371472 [2:59:02<16:06:33,  3.39it/s]
 47%|████▋     | 174632/371472 [2:59:02<16:15:54,  3.36it/s]
 47%|████▋     | 174633/371472 [2:59:03<16:25:41,  3.33it/s]
 47%|████▋     | 174634/371472 [2:59:03<16:16:51,  3.36it/s]
 47%|████▋     | 174635/371472 [2:59:03<16:26:56,  3.32it/s]
 47%|████▋     | 174636/371472 [2:59:04<16:29:24,  3.32it/s]
 47%|████▋     | 174637/371472 [2:59:04<16:18:02,  3.35it/s]
 47%|████▋     | 174638/371472 [2:59:04<16:17:29,  3.36it/s]
 47%|████▋     | 174639/371472 [2:59:05<17:12:07,  3.18it/s]
 47%|████▋     | 174640/371472 [2:59:05<17:32:37,  3.12it/s]
                                                            
{'loss': 2.8254, 'learning_rate': 5.771402098730849e-07, 'epoch': 7.52}
+
 47%|████▋     | 174640/371472 [2:59:05<17:32:37,  3.12it/s]
 47%|████▋     | 174641/371472 [2:59:05<17:23:13,  3.14it/s]
 47%|████▋     | 174642/371472 [2:59:05<17:08:00,  3.19it/s]
 47%|████▋     | 174643/371472 [2:59:06<16:40:04,  3.28it/s]
 47%|████▋     | 174644/371472 [2:59:06<16:45:03,  3.26it/s]
 47%|████▋     | 174645/371472 [2:59:06<16:20:09,  3.35it/s]
 47%|████▋     | 174646/371472 [2:59:07<15:59:37,  3.42it/s]
 47%|████▋     | 174647/371472 [2:59:07<16:28:06,  3.32it/s]
 47%|████▋     | 174648/371472 [2:59:07<17:03:45,  3.20it/s]
 47%|████▋     | 174649/371472 [2:59:08<17:22:55,  3.15it/s]
 47%|████▋     | 174650/371472 [2:59:08<16:55:47,  3.23it/s]
 47%|████▋     | 174651/371472 [2:59:08<17:48:06,  3.07it/s]
 47%|████▋     | 174652/371472 [2:59:09<17:00:59,  3.21it/s]
 47%|████▋     | 174653/371472 [2:59:09<16:53:00,  3.24it/s]
 47%|████▋     | 174654/371472 [2:59:09<16:48:26,  3.25it/s]
 47%|████▋     | 174655/371472 [2:59:09<16:37:03,  3.29it/s]
 47%|████▋     | 174656/371472 [2:59:10<16:09:12,  3.38it/s]
 47%|████▋     | 174657/371472 [2:59:10<16:04:06,  3.40it/s]
 47%|████▋     | 174658/371472 [2:59:10<16:27:28,  3.32it/s]
 47%|████▋     | 174659/371472 [2:59:11<16:36:19,  3.29it/s]
 47%|████▋     | 174660/371472 [2:59:11<16:24:20,  3.33it/s]
                                                            
{'loss': 3.1018, 'learning_rate': 5.77091727897606e-07, 'epoch': 7.52}
+
 47%|████▋     | 174660/371472 [2:59:11<16:24:20,  3.33it/s]
 47%|████▋     | 174661/371472 [2:59:11<16:15:00,  3.36it/s]
 47%|████▋     | 174662/371472 [2:59:12<16:20:32,  3.35it/s]
 47%|████▋     | 174663/371472 [2:59:12<16:54:16,  3.23it/s]
 47%|████▋     | 174664/371472 [2:59:12<16:52:05,  3.24it/s]
 47%|████▋     | 174665/371472 [2:59:12<16:34:14,  3.30it/s]
 47%|████▋     | 174666/371472 [2:59:13<17:03:27,  3.20it/s]
 47%|████▋     | 174667/371472 [2:59:13<16:51:19,  3.24it/s]
 47%|████▋     | 174668/371472 [2:59:13<16:57:18,  3.22it/s]
 47%|████▋     | 174669/371472 [2:59:14<16:40:35,  3.28it/s]
 47%|████▋     | 174670/371472 [2:59:14<16:54:50,  3.23it/s]
 47%|████▋     | 174671/371472 [2:59:14<16:37:26,  3.29it/s]
 47%|████▋     | 174672/371472 [2:59:15<15:57:27,  3.43it/s]
 47%|████▋     | 174673/371472 [2:59:15<16:17:59,  3.35it/s]
 47%|████▋     | 174674/371472 [2:59:15<15:58:09,  3.42it/s]
 47%|████▋     | 174675/371472 [2:59:15<16:00:35,  3.41it/s]
 47%|████▋     | 174676/371472 [2:59:16<17:02:27,  3.21it/s]
 47%|████▋     | 174677/371472 [2:59:16<16:22:23,  3.34it/s]
 47%|████▋     | 174678/371472 [2:59:16<16:59:52,  3.22it/s]
 47%|████▋     | 174679/371472 [2:59:17<17:08:04,  3.19it/s]
 47%|████▋     | 174680/371472 [2:59:17<16:43:58,  3.27it/s]
                                                            
{'loss': 3.12, 'learning_rate': 5.770432459221272e-07, 'epoch': 7.52}
+
 47%|████▋     | 174680/371472 [2:59:17<16:43:58,  3.27it/s]
 47%|████▋     | 174681/371472 [2:59:17<16:31:41,  3.31it/s]
 47%|████▋     | 174682/371472 [2:59:18<16:57:11,  3.22it/s]
 47%|████▋     | 174683/371472 [2:59:18<16:27:03,  3.32it/s]
 47%|████▋     | 174684/371472 [2:59:18<16:04:49,  3.40it/s]
 47%|████▋     | 174685/371472 [2:59:19<17:07:05,  3.19it/s]
 47%|████▋     | 174686/371472 [2:59:19<17:10:42,  3.18it/s]
 47%|████▋     | 174687/371472 [2:59:19<17:52:00,  3.06it/s]
 47%|████▋     | 174688/371472 [2:59:20<17:16:15,  3.16it/s]
 47%|████▋     | 174689/371472 [2:59:20<16:55:19,  3.23it/s]
 47%|████▋     | 174690/371472 [2:59:20<16:24:11,  3.33it/s]
 47%|████▋     | 174691/371472 [2:59:20<15:46:28,  3.47it/s]
 47%|████▋     | 174692/371472 [2:59:21<15:39:27,  3.49it/s]
 47%|████▋     | 174693/371472 [2:59:21<15:57:32,  3.43it/s]
 47%|████▋     | 174694/371472 [2:59:21<16:23:37,  3.33it/s]
 47%|████▋     | 174695/371472 [2:59:22<16:26:52,  3.32it/s]
 47%|████▋     | 174696/371472 [2:59:22<17:27:55,  3.13it/s]
 47%|████▋     | 174697/371472 [2:59:22<16:49:00,  3.25it/s]
 47%|████▋     | 174698/371472 [2:59:23<16:47:46,  3.25it/s]
 47%|████▋     | 174699/371472 [2:59:23<16:26:09,  3.33it/s]
 47%|████▋     | 174700/371472 [2:59:23<16:38:09,  3.29it/s]
                                                            
{'loss': 2.7816, 'learning_rate': 5.769947639466483e-07, 'epoch': 7.52}
+
 47%|████▋     | 174700/371472 [2:59:23<16:38:09,  3.29it/s]
 47%|████▋     | 174701/371472 [2:59:23<17:17:46,  3.16it/s]
 47%|████▋     | 174702/371472 [2:59:24<17:09:28,  3.19it/s]
 47%|████▋     | 174703/371472 [2:59:24<18:15:52,  2.99it/s]
 47%|████▋     | 174704/371472 [2:59:24<17:07:56,  3.19it/s]
 47%|████▋     | 174705/371472 [2:59:25<17:06:19,  3.20it/s]
 47%|████▋     | 174706/371472 [2:59:25<16:42:42,  3.27it/s]
 47%|████▋     | 174707/371472 [2:59:25<17:45:46,  3.08it/s]
 47%|████▋     | 174708/371472 [2:59:26<17:19:29,  3.15it/s]
 47%|████▋     | 174709/371472 [2:59:26<17:14:18,  3.17it/s]
 47%|████▋     | 174710/371472 [2:59:26<17:11:45,  3.18it/s]
 47%|████▋     | 174711/371472 [2:59:27<16:41:07,  3.28it/s]
 47%|████▋     | 174712/371472 [2:59:27<16:29:01,  3.32it/s]
 47%|████▋     | 174713/371472 [2:59:27<16:44:45,  3.26it/s]
 47%|████▋     | 174714/371472 [2:59:28<16:57:26,  3.22it/s]
 47%|████▋     | 174715/371472 [2:59:28<16:05:38,  3.40it/s]
 47%|████▋     | 174716/371472 [2:59:28<16:05:03,  3.40it/s]
 47%|████▋     | 174717/371472 [2:59:28<16:11:55,  3.37it/s]
 47%|████▋     | 174718/371472 [2:59:29<17:49:27,  3.07it/s]
 47%|████▋     | 174719/371472 [2:59:29<17:37:59,  3.10it/s]
 47%|████▋     | 174720/371472 [2:59:29<17:07:14,  3.19it/s]
                                                            
{'loss': 3.0391, 'learning_rate': 5.769462819711693e-07, 'epoch': 7.53}
+
 47%|████▋     | 174720/371472 [2:59:29<17:07:14,  3.19it/s]
 47%|████▋     | 174721/371472 [2:59:30<16:52:03,  3.24it/s]
 47%|████▋     | 174722/371472 [2:59:30<16:15:08,  3.36it/s]
 47%|████▋     | 174723/371472 [2:59:30<16:45:59,  3.26it/s]
 47%|████▋     | 174724/371472 [2:59:31<16:27:43,  3.32it/s]
 47%|████▋     | 174725/371472 [2:59:31<16:25:23,  3.33it/s]
 47%|████▋     | 174726/371472 [2:59:31<16:13:02,  3.37it/s]
 47%|████▋     | 174727/371472 [2:59:31<15:54:03,  3.44it/s]
 47%|████▋     | 174728/371472 [2:59:32<15:49:22,  3.45it/s]
 47%|████▋     | 174729/371472 [2:59:32<16:28:32,  3.32it/s]
 47%|████▋     | 174730/371472 [2:59:32<16:54:57,  3.23it/s]
 47%|████▋     | 174731/371472 [2:59:33<17:11:55,  3.18it/s]
 47%|████▋     | 174732/371472 [2:59:33<16:49:26,  3.25it/s]
 47%|████▋     | 174733/371472 [2:59:33<16:20:17,  3.34it/s]
 47%|████▋     | 174734/371472 [2:59:34<15:56:36,  3.43it/s]
 47%|████▋     | 174735/371472 [2:59:34<16:08:56,  3.38it/s]
 47%|████▋     | 174736/371472 [2:59:34<16:41:18,  3.27it/s]
 47%|████▋     | 174737/371472 [2:59:34<16:20:16,  3.34it/s]
 47%|████▋     | 174738/371472 [2:59:35<16:36:48,  3.29it/s]
 47%|████▋     | 174739/371472 [2:59:35<16:14:35,  3.36it/s]
 47%|████▋     | 174740/371472 [2:59:35<16:40:22,  3.28it/s]
                                                            
{'loss': 2.8462, 'learning_rate': 5.768977999956904e-07, 'epoch': 7.53}
+
 47%|████▋     | 174740/371472 [2:59:35<16:40:22,  3.28it/s]
 47%|████▋     | 174741/371472 [2:59:36<16:21:14,  3.34it/s]
 47%|████▋     | 174742/371472 [2:59:36<15:51:19,  3.45it/s]
 47%|████▋     | 174743/371472 [2:59:36<16:11:37,  3.37it/s]
 47%|████▋     | 174744/371472 [2:59:37<16:29:41,  3.31it/s]
 47%|████▋     | 174745/371472 [2:59:37<16:09:30,  3.38it/s]
 47%|████▋     | 174746/371472 [2:59:37<16:03:32,  3.40it/s]
 47%|████▋     | 174747/371472 [2:59:37<16:38:51,  3.28it/s]
 47%|████▋     | 174748/371472 [2:59:38<16:28:36,  3.32it/s]
 47%|████▋     | 174749/371472 [2:59:38<18:12:41,  3.00it/s]
 47%|████▋     | 174750/371472 [2:59:38<17:19:53,  3.15it/s]
 47%|████▋     | 174751/371472 [2:59:39<16:18:52,  3.35it/s]
 47%|████▋     | 174752/371472 [2:59:39<16:08:51,  3.38it/s]
 47%|████▋     | 174753/371472 [2:59:39<16:16:14,  3.36it/s]
 47%|████▋     | 174754/371472 [2:59:40<15:56:33,  3.43it/s]
 47%|████▋     | 174755/371472 [2:59:40<15:31:23,  3.52it/s]
 47%|████▋     | 174756/371472 [2:59:40<15:29:58,  3.53it/s]
 47%|████▋     | 174757/371472 [2:59:40<15:11:38,  3.60it/s]
 47%|████▋     | 174758/371472 [2:59:41<15:31:47,  3.52it/s]
 47%|████▋     | 174759/371472 [2:59:41<16:30:30,  3.31it/s]
 47%|████▋     | 174760/371472 [2:59:41<16:21:47,  3.34it/s]
                                                            
{'loss': 2.9654, 'learning_rate': 5.768493180202116e-07, 'epoch': 7.53}
+
 47%|████▋     | 174760/371472 [2:59:41<16:21:47,  3.34it/s]
 47%|████▋     | 174761/371472 [2:59:42<15:49:16,  3.45it/s]
 47%|████▋     | 174762/371472 [2:59:42<16:17:34,  3.35it/s]
 47%|████▋     | 174763/371472 [2:59:42<17:27:19,  3.13it/s]
 47%|████▋     | 174764/371472 [2:59:43<17:57:37,  3.04it/s]
 47%|████▋     | 174765/371472 [2:59:43<17:46:55,  3.07it/s]
 47%|████▋     | 174766/371472 [2:59:43<17:09:48,  3.18it/s]
 47%|████▋     | 174767/371472 [2:59:44<16:24:09,  3.33it/s]
 47%|████▋     | 174768/371472 [2:59:44<15:56:39,  3.43it/s]
 47%|████▋     | 174769/371472 [2:59:44<17:22:55,  3.14it/s]
 47%|████▋     | 174770/371472 [2:59:44<17:26:05,  3.13it/s]
 47%|████▋     | 174771/371472 [2:59:45<17:32:50,  3.11it/s]
 47%|████▋     | 174772/371472 [2:59:45<17:44:35,  3.08it/s]
 47%|████▋     | 174773/371472 [2:59:45<17:29:22,  3.12it/s]
 47%|████▋     | 174774/371472 [2:59:46<17:30:31,  3.12it/s]
 47%|████▋     | 174775/371472 [2:59:46<18:50:41,  2.90it/s]
 47%|████▋     | 174776/371472 [2:59:46<17:47:54,  3.07it/s]
 47%|████▋     | 174777/371472 [2:59:47<17:07:25,  3.19it/s]
 47%|████▋     | 174778/371472 [2:59:47<17:23:33,  3.14it/s]
 47%|████▋     | 174779/371472 [2:59:47<16:56:01,  3.23it/s]
 47%|████▋     | 174780/371472 [2:59:48<16:55:13,  3.23it/s]
                                                            
{'loss': 3.0049, 'learning_rate': 5.768008360447328e-07, 'epoch': 7.53}
+
 47%|████▋     | 174780/371472 [2:59:48<16:55:13,  3.23it/s]
 47%|████▋     | 174781/371472 [2:59:48<17:41:58,  3.09it/s]
 47%|████▋     | 174782/371472 [2:59:48<16:47:15,  3.25it/s]
 47%|████▋     | 174783/371472 [2:59:49<16:43:16,  3.27it/s]
 47%|████▋     | 174784/371472 [2:59:49<16:37:47,  3.29it/s]
 47%|████▋     | 174785/371472 [2:59:49<16:10:51,  3.38it/s]
 47%|████▋     | 174786/371472 [2:59:49<16:08:39,  3.38it/s]
 47%|████▋     | 174787/371472 [2:59:50<16:25:53,  3.33it/s]
 47%|████▋     | 174788/371472 [2:59:50<16:18:55,  3.35it/s]
 47%|████▋     | 174789/371472 [2:59:50<16:44:05,  3.26it/s]
 47%|████▋     | 174790/371472 [2:59:51<16:37:14,  3.29it/s]
 47%|████▋     | 174791/371472 [2:59:51<15:52:06,  3.44it/s]
 47%|████▋     | 174792/371472 [2:59:51<15:45:08,  3.47it/s]
 47%|████▋     | 174793/371472 [2:59:52<15:27:27,  3.53it/s]
 47%|████▋     | 174794/371472 [2:59:52<15:28:59,  3.53it/s]
 47%|████▋     | 174795/371472 [2:59:52<15:51:26,  3.45it/s]
 47%|████▋     | 174796/371472 [2:59:52<15:58:50,  3.42it/s]
 47%|████▋     | 174797/371472 [2:59:53<16:34:16,  3.30it/s]
 47%|████▋     | 174798/371472 [2:59:53<16:53:46,  3.23it/s]
 47%|████▋     | 174799/371472 [2:59:53<16:26:04,  3.32it/s]
 47%|████▋     | 174800/371472 [2:59:54<16:59:30,  3.22it/s]
                                                            
{'loss': 2.9603, 'learning_rate': 5.767523540692537e-07, 'epoch': 7.53}
+
 47%|████▋     | 174800/371472 [2:59:54<16:59:30,  3.22it/s]
 47%|████▋     | 174801/371472 [2:59:54<16:43:49,  3.27it/s]
 47%|████▋     | 174802/371472 [2:59:54<16:12:30,  3.37it/s]
 47%|████▋     | 174803/371472 [2:59:55<16:37:20,  3.29it/s]
 47%|████▋     | 174804/371472 [2:59:55<16:31:32,  3.31it/s]
 47%|████▋     | 174805/371472 [2:59:55<16:28:46,  3.32it/s]
 47%|████▋     | 174806/371472 [2:59:55<16:23:06,  3.33it/s]
 47%|████▋     | 174807/371472 [2:59:56<16:07:06,  3.39it/s]
 47%|████▋     | 174808/371472 [2:59:56<17:17:26,  3.16it/s]
 47%|████▋     | 174809/371472 [2:59:56<16:24:40,  3.33it/s]
 47%|████▋     | 174810/371472 [2:59:57<15:56:45,  3.43it/s]
 47%|████▋     | 174811/371472 [2:59:57<17:03:21,  3.20it/s]
 47%|████▋     | 174812/371472 [2:59:57<18:50:31,  2.90it/s]
 47%|████▋     | 174813/371472 [2:59:58<18:18:10,  2.98it/s]
 47%|████▋     | 174814/371472 [2:59:58<17:17:12,  3.16it/s]
 47%|████▋     | 174815/371472 [2:59:58<18:19:26,  2.98it/s]
 47%|████▋     | 174816/371472 [2:59:59<17:33:11,  3.11it/s]
 47%|████▋     | 174817/371472 [2:59:59<17:05:40,  3.20it/s]
 47%|████▋     | 174818/371472 [2:59:59<16:57:59,  3.22it/s]
 47%|████▋     | 174819/371472 [3:00:00<16:24:31,  3.33it/s]
 47%|████▋     | 174820/371472 [3:00:00<16:14:39,  3.36it/s]
                                                            
{'loss': 2.8927, 'learning_rate': 5.767038720937748e-07, 'epoch': 7.53}
+
 47%|████▋     | 174820/371472 [3:00:00<16:14:39,  3.36it/s]
 47%|████▋     | 174821/371472 [3:00:00<16:30:19,  3.31it/s]
 47%|████▋     | 174822/371472 [3:00:00<16:33:26,  3.30it/s]
 47%|████▋     | 174823/371472 [3:00:01<15:58:43,  3.42it/s]
 47%|████▋     | 174824/371472 [3:00:01<15:54:27,  3.43it/s]
 47%|████▋     | 174825/371472 [3:00:01<15:41:03,  3.48it/s]
 47%|████▋     | 174826/371472 [3:00:02<15:50:48,  3.45it/s]
 47%|████▋     | 174827/371472 [3:00:02<15:58:22,  3.42it/s]
 47%|████▋     | 174828/371472 [3:00:02<15:49:34,  3.45it/s]
 47%|████▋     | 174829/371472 [3:00:02<15:37:55,  3.49it/s]
 47%|████▋     | 174830/371472 [3:00:03<16:42:44,  3.27it/s]
 47%|████▋     | 174831/371472 [3:00:03<17:27:24,  3.13it/s]
 47%|████▋     | 174832/371472 [3:00:03<16:43:46,  3.26it/s]
 47%|████▋     | 174833/371472 [3:00:04<16:02:59,  3.40it/s]
 47%|████▋     | 174834/371472 [3:00:04<15:54:51,  3.43it/s]
 47%|████▋     | 174835/371472 [3:00:04<15:58:12,  3.42it/s]
 47%|████▋     | 174836/371472 [3:00:05<16:11:58,  3.37it/s]
 47%|████▋     | 174837/371472 [3:00:05<16:29:46,  3.31it/s]
 47%|████▋     | 174838/371472 [3:00:05<16:31:06,  3.31it/s]
 47%|████▋     | 174839/371472 [3:00:06<17:49:26,  3.06it/s]
 47%|████▋     | 174840/371472 [3:00:06<17:37:52,  3.10it/s]
                                                            
{'loss': 2.9327, 'learning_rate': 5.766553901182961e-07, 'epoch': 7.53}
+
 47%|████▋     | 174840/371472 [3:00:06<17:37:52,  3.10it/s]
 47%|████▋     | 174841/371472 [3:00:06<17:17:21,  3.16it/s]
 47%|████▋     | 174842/371472 [3:00:07<17:04:45,  3.20it/s]
 47%|████▋     | 174843/371472 [3:00:07<17:06:50,  3.19it/s]
 47%|████▋     | 174844/371472 [3:00:07<16:36:40,  3.29it/s]
 47%|████▋     | 174845/371472 [3:00:07<16:20:53,  3.34it/s]
 47%|████▋     | 174846/371472 [3:00:08<16:30:48,  3.31it/s]
 47%|████▋     | 174847/371472 [3:00:08<16:14:29,  3.36it/s]
 47%|████▋     | 174848/371472 [3:00:08<15:44:18,  3.47it/s]
 47%|████▋     | 174849/371472 [3:00:09<15:38:44,  3.49it/s]
 47%|████▋     | 174850/371472 [3:00:09<16:47:25,  3.25it/s]
 47%|████▋     | 174851/371472 [3:00:09<16:04:44,  3.40it/s]
 47%|████▋     | 174852/371472 [3:00:09<16:39:13,  3.28it/s]
 47%|████▋     | 174853/371472 [3:00:10<17:43:15,  3.08it/s]
 47%|████▋     | 174854/371472 [3:00:10<16:47:54,  3.25it/s]
 47%|████▋     | 174855/371472 [3:00:10<16:34:39,  3.29it/s]
 47%|████▋     | 174856/371472 [3:00:11<16:14:38,  3.36it/s]
 47%|████▋     | 174857/371472 [3:00:11<16:39:26,  3.28it/s]
 47%|████▋     | 174858/371472 [3:00:11<16:30:50,  3.31it/s]
 47%|████▋     | 174859/371472 [3:00:12<16:19:26,  3.35it/s]
 47%|████▋     | 174860/371472 [3:00:12<19:19:48,  2.83it/s]
                                                            
{'loss': 2.8319, 'learning_rate': 5.766069081428171e-07, 'epoch': 7.53}
+
 47%|████▋     | 174860/371472 [3:00:12<19:19:48,  2.83it/s]
 47%|████▋     | 174861/371472 [3:00:12<18:17:38,  2.99it/s]
 47%|████▋     | 174862/371472 [3:00:13<17:29:37,  3.12it/s]
 47%|████▋     | 174863/371472 [3:00:13<17:50:17,  3.06it/s]
 47%|████▋     | 174864/371472 [3:00:13<19:11:02,  2.85it/s]
 47%|████▋     | 174865/371472 [3:00:14<18:06:19,  3.02it/s]
 47%|████▋     | 174866/371472 [3:00:14<18:52:51,  2.89it/s]
 47%|████▋     | 174867/371472 [3:00:14<17:42:00,  3.09it/s]
 47%|████▋     | 174868/371472 [3:00:15<18:08:00,  3.01it/s]
 47%|████▋     | 174869/371472 [3:00:15<17:41:13,  3.09it/s]
 47%|████▋     | 174870/371472 [3:00:15<17:15:15,  3.17it/s]
 47%|████▋     | 174871/371472 [3:00:16<16:50:36,  3.24it/s]
 47%|████▋     | 174872/371472 [3:00:16<16:31:13,  3.31it/s]
 47%|████▋     | 174873/371472 [3:00:16<16:17:12,  3.35it/s]
 47%|████▋     | 174874/371472 [3:00:16<15:46:33,  3.46it/s]
 47%|████▋     | 174875/371472 [3:00:17<15:59:07,  3.42it/s]
 47%|████▋     | 174876/371472 [3:00:17<15:58:50,  3.42it/s]
 47%|████▋     | 174877/371472 [3:00:17<16:28:48,  3.31it/s]
 47%|████▋     | 174878/371472 [3:00:18<16:05:16,  3.39it/s]
 47%|████▋     | 174879/371472 [3:00:18<16:07:52,  3.39it/s]
 47%|████▋     | 174880/371472 [3:00:18<15:48:52,  3.45it/s]
                                                            
{'loss': 2.9311, 'learning_rate': 5.765584261673382e-07, 'epoch': 7.53}
+
 47%|████▋     | 174880/371472 [3:00:18<15:48:52,  3.45it/s]
 47%|████▋     | 174881/371472 [3:00:18<15:39:08,  3.49it/s]
 47%|████▋     | 174882/371472 [3:00:19<16:37:04,  3.29it/s]
 47%|████▋     | 174883/371472 [3:00:19<16:46:49,  3.25it/s]
 47%|████▋     | 174884/371472 [3:00:19<17:26:11,  3.13it/s]
 47%|████▋     | 174885/371472 [3:00:20<17:04:00,  3.20it/s]
 47%|████▋     | 174886/371472 [3:00:20<16:49:02,  3.25it/s]
 47%|████▋     | 174887/371472 [3:00:20<16:40:18,  3.28it/s]
 47%|████▋     | 174888/371472 [3:00:21<17:05:57,  3.19it/s]
 47%|████▋     | 174889/371472 [3:00:21<17:41:06,  3.09it/s]
 47%|████▋     | 174890/371472 [3:00:21<16:58:25,  3.22it/s]
 47%|████▋     | 174891/371472 [3:00:22<16:27:10,  3.32it/s]
 47%|████▋     | 174892/371472 [3:00:22<16:21:57,  3.34it/s]
 47%|████▋     | 174893/371472 [3:00:22<16:12:41,  3.37it/s]
 47%|████▋     | 174894/371472 [3:00:22<15:46:37,  3.46it/s]
 47%|████▋     | 174895/371472 [3:00:23<15:43:47,  3.47it/s]
 47%|████▋     | 174896/371472 [3:00:23<15:53:55,  3.43it/s]
 47%|████▋     | 174897/371472 [3:00:23<16:21:13,  3.34it/s]
 47%|████▋     | 174898/371472 [3:00:24<17:02:00,  3.21it/s]
 47%|████▋     | 174899/371472 [3:00:24<17:27:18,  3.13it/s]
 47%|████▋     | 174900/371472 [3:00:24<17:13:26,  3.17it/s]
                                                            
{'loss': 2.8435, 'learning_rate': 5.765099441918593e-07, 'epoch': 7.53}
+
 47%|████▋     | 174900/371472 [3:00:24<17:13:26,  3.17it/s]
 47%|████▋     | 174901/371472 [3:00:25<16:58:39,  3.22it/s]
 47%|████▋     | 174902/371472 [3:00:25<16:43:37,  3.26it/s]
 47%|████▋     | 174903/371472 [3:00:25<17:37:12,  3.10it/s]
 47%|████▋     | 174904/371472 [3:00:26<16:43:34,  3.26it/s]
 47%|████▋     | 174905/371472 [3:00:26<16:26:21,  3.32it/s]
 47%|████▋     | 174906/371472 [3:00:26<16:09:26,  3.38it/s]
 47%|████▋     | 174907/371472 [3:00:26<16:33:16,  3.30it/s]
 47%|████▋     | 174908/371472 [3:00:27<15:54:07,  3.43it/s]
 47%|████▋     | 174909/371472 [3:00:27<15:48:14,  3.45it/s]
 47%|████▋     | 174910/371472 [3:00:27<17:00:07,  3.21it/s]
 47%|████▋     | 174911/371472 [3:00:28<16:51:11,  3.24it/s]
 47%|████▋     | 174912/371472 [3:00:28<16:20:05,  3.34it/s]
 47%|████▋     | 174913/371472 [3:00:28<16:32:45,  3.30it/s]
 47%|████▋     | 174914/371472 [3:00:29<16:46:01,  3.26it/s]
 47%|████▋     | 174915/371472 [3:00:29<16:34:29,  3.29it/s]
 47%|████▋     | 174916/371472 [3:00:29<16:28:09,  3.32it/s]
 47%|████▋     | 174917/371472 [3:00:29<16:18:57,  3.35it/s]
 47%|████▋     | 174918/371472 [3:00:30<16:04:50,  3.40it/s]
 47%|████▋     | 174919/371472 [3:00:30<15:40:51,  3.48it/s]
 47%|████▋     | 174920/371472 [3:00:30<16:32:47,  3.30it/s]
                                                            
{'loss': 2.9389, 'learning_rate': 5.764614622163804e-07, 'epoch': 7.53}
+
 47%|████▋     | 174920/371472 [3:00:30<16:32:47,  3.30it/s]
 47%|████▋     | 174921/371472 [3:00:31<16:40:55,  3.27it/s]
 47%|████▋     | 174922/371472 [3:00:31<16:18:34,  3.35it/s]
 47%|████▋     | 174923/371472 [3:00:31<16:13:33,  3.36it/s]
 47%|████▋     | 174924/371472 [3:00:32<16:36:41,  3.29it/s]
 47%|████▋     | 174925/371472 [3:00:32<16:05:17,  3.39it/s]
 47%|████▋     | 174926/371472 [3:00:32<15:29:40,  3.52it/s]
 47%|████▋     | 174927/371472 [3:00:32<15:40:25,  3.48it/s]
 47%|████▋     | 174928/371472 [3:00:33<16:12:36,  3.37it/s]
 47%|████▋     | 174929/371472 [3:00:33<16:22:30,  3.33it/s]
 47%|████▋     | 174930/371472 [3:00:33<16:05:38,  3.39it/s]
 47%|████▋     | 174931/371472 [3:00:34<16:00:47,  3.41it/s]
 47%|████▋     | 174932/371472 [3:00:34<15:43:43,  3.47it/s]
 47%|████▋     | 174933/371472 [3:00:34<16:07:48,  3.38it/s]
 47%|████▋     | 174934/371472 [3:00:34<15:51:26,  3.44it/s]
 47%|████▋     | 174935/371472 [3:00:35<16:13:00,  3.37it/s]
 47%|████▋     | 174936/371472 [3:00:35<15:54:54,  3.43it/s]
 47%|████▋     | 174937/371472 [3:00:35<15:54:09,  3.43it/s]
 47%|████▋     | 174938/371472 [3:00:36<16:00:13,  3.41it/s]
 47%|████▋     | 174939/371472 [3:00:36<16:10:28,  3.38it/s]
 47%|████▋     | 174940/371472 [3:00:36<17:32:06,  3.11it/s]
                                                            
{'loss': 2.7082, 'learning_rate': 5.764129802409016e-07, 'epoch': 7.53}
+
 47%|████▋     | 174940/371472 [3:00:36<17:32:06,  3.11it/s]
 47%|████▋     | 174941/371472 [3:00:37<17:23:21,  3.14it/s]
 47%|████▋     | 174942/371472 [3:00:37<16:48:52,  3.25it/s]
 47%|████▋     | 174943/371472 [3:00:37<16:49:26,  3.24it/s]
 47%|████▋     | 174944/371472 [3:00:38<17:15:50,  3.16it/s]
 47%|████▋     | 174945/371472 [3:00:38<18:06:03,  3.02it/s]
 47%|████▋     | 174946/371472 [3:00:38<18:16:48,  2.99it/s]
 47%|████▋     | 174947/371472 [3:00:39<17:06:48,  3.19it/s]
 47%|████▋     | 174948/371472 [3:00:39<16:44:14,  3.26it/s]
 47%|████▋     | 174949/371472 [3:00:39<16:42:39,  3.27it/s]
 47%|████▋     | 174950/371472 [3:00:39<16:05:05,  3.39it/s]
 47%|████▋     | 174951/371472 [3:00:40<16:14:09,  3.36it/s]
 47%|████▋     | 174952/371472 [3:00:40<16:11:37,  3.37it/s]
 47%|████▋     | 174953/371472 [3:00:40<15:46:34,  3.46it/s]
 47%|████▋     | 174954/371472 [3:00:41<15:20:18,  3.56it/s]
 47%|████▋     | 174955/371472 [3:00:41<15:39:57,  3.48it/s]
 47%|████▋     | 174956/371472 [3:00:41<15:19:29,  3.56it/s]
 47%|████▋     | 174957/371472 [3:00:41<15:14:18,  3.58it/s]
 47%|████▋     | 174958/371472 [3:00:42<15:22:51,  3.55it/s]
 47%|████▋     | 174959/371472 [3:00:42<16:00:44,  3.41it/s]
 47%|████▋     | 174960/371472 [3:00:42<16:57:14,  3.22it/s]
                                                            
{'loss': 2.9937, 'learning_rate': 5.763644982654226e-07, 'epoch': 7.54}
+
 47%|████▋     | 174960/371472 [3:00:42<16:57:14,  3.22it/s]
 47%|████▋     | 174961/371472 [3:00:43<16:46:42,  3.25it/s]
 47%|████▋     | 174962/371472 [3:00:43<16:46:40,  3.25it/s]
 47%|████▋     | 174963/371472 [3:00:43<16:43:53,  3.26it/s]
 47%|████▋     | 174964/371472 [3:00:44<17:06:16,  3.19it/s]
 47%|████▋     | 174965/371472 [3:00:44<16:31:38,  3.30it/s]
 47%|████▋     | 174966/371472 [3:00:44<16:42:55,  3.27it/s]
 47%|████▋     | 174967/371472 [3:00:45<17:45:44,  3.07it/s]
 47%|████▋     | 174968/371472 [3:00:45<17:41:11,  3.09it/s]
 47%|████▋     | 174969/371472 [3:00:45<17:07:57,  3.19it/s]
 47%|████▋     | 174970/371472 [3:00:45<16:37:41,  3.28it/s]
 47%|████▋     | 174971/371472 [3:00:46<16:33:05,  3.30it/s]
 47%|████▋     | 174972/371472 [3:00:46<16:37:50,  3.28it/s]
 47%|████▋     | 174973/371472 [3:00:46<16:12:06,  3.37it/s]
 47%|████▋     | 174974/371472 [3:00:47<15:51:39,  3.44it/s]
 47%|████▋     | 174975/371472 [3:00:47<15:43:13,  3.47it/s]
 47%|████▋     | 174976/371472 [3:00:47<15:25:47,  3.54it/s]
 47%|████▋     | 174977/371472 [3:00:48<16:16:34,  3.35it/s]
 47%|████▋     | 174978/371472 [3:00:48<16:10:13,  3.38it/s]
 47%|████▋     | 174979/371472 [3:00:48<15:59:09,  3.41it/s]
 47%|████▋     | 174980/371472 [3:00:48<15:54:49,  3.43it/s]
                                                            
{'loss': 3.1888, 'learning_rate': 5.763160162899437e-07, 'epoch': 7.54}
+
 47%|████▋     | 174980/371472 [3:00:48<15:54:49,  3.43it/s]
 47%|████▋     | 174981/371472 [3:00:49<16:42:17,  3.27it/s]
 47%|████▋     | 174982/371472 [3:00:49<16:06:46,  3.39it/s]
 47%|████▋     | 174983/371472 [3:00:49<15:54:48,  3.43it/s]
 47%|████▋     | 174984/371472 [3:00:50<16:00:55,  3.41it/s]
 47%|████▋     | 174985/371472 [3:00:50<16:48:16,  3.25it/s]
 47%|████▋     | 174986/371472 [3:00:50<17:22:14,  3.14it/s]
 47%|████▋     | 174987/371472 [3:00:51<17:21:50,  3.14it/s]
 47%|████▋     | 174988/371472 [3:00:51<17:25:54,  3.13it/s]
 47%|████▋     | 174989/371472 [3:00:51<17:21:21,  3.14it/s]
 47%|████▋     | 174990/371472 [3:00:52<17:17:37,  3.16it/s]
 47%|████▋     | 174991/371472 [3:00:52<17:25:29,  3.13it/s]
 47%|████▋     | 174992/371472 [3:00:52<17:48:14,  3.07it/s]
 47%|████▋     | 174993/371472 [3:00:52<17:26:29,  3.13it/s]
 47%|████▋     | 174994/371472 [3:00:53<17:20:07,  3.15it/s]
 47%|████▋     | 174995/371472 [3:00:53<17:40:39,  3.09it/s]
 47%|████▋     | 174996/371472 [3:00:53<17:07:49,  3.19it/s]
 47%|████▋     | 174997/371472 [3:00:54<17:06:53,  3.19it/s]
 47%|████▋     | 174998/371472 [3:00:54<17:22:23,  3.14it/s]
 47%|████▋     | 174999/371472 [3:00:54<17:44:07,  3.08it/s]
 47%|████▋     | 175000/371472 [3:00:55<17:23:41,  3.14it/s]
                                                            
{'loss': 2.7724, 'learning_rate': 5.762675343144649e-07, 'epoch': 7.54}
+
 47%|████▋     | 175000/371472 [3:00:55<17:23:41,  3.14it/s]
 47%|████▋     | 175001/371472 [3:00:55<17:40:01,  3.09it/s]
 47%|████▋     | 175002/371472 [3:00:55<17:50:52,  3.06it/s]
 47%|████▋     | 175003/371472 [3:00:56<17:25:11,  3.13it/s]
 47%|████▋     | 175004/371472 [3:00:56<17:41:37,  3.08it/s]
 47%|████▋     | 175005/371472 [3:00:56<18:17:28,  2.98it/s]
 47%|████▋     | 175006/371472 [3:00:57<17:52:47,  3.05it/s]
 47%|████▋     | 175007/371472 [3:00:57<17:12:39,  3.17it/s]
 47%|████▋     | 175008/371472 [3:00:57<16:49:31,  3.24it/s]
 47%|████▋     | 175009/371472 [3:00:58<16:34:58,  3.29it/s]
 47%|████▋     | 175010/371472 [3:00:58<16:06:26,  3.39it/s]
 47%|████▋     | 175011/371472 [3:00:58<16:05:39,  3.39it/s]
 47%|████▋     | 175012/371472 [3:00:58<16:30:29,  3.31it/s]
 47%|████▋     | 175013/371472 [3:00:59<16:25:12,  3.32it/s]
 47%|████▋     | 175014/371472 [3:00:59<15:59:22,  3.41it/s]
 47%|████▋     | 175015/371472 [3:00:59<18:08:49,  3.01it/s]
 47%|████▋     | 175016/371472 [3:01:00<17:51:37,  3.06it/s]
 47%|████▋     | 175017/371472 [3:01:00<17:08:40,  3.18it/s]
 47%|████▋     | 175018/371472 [3:01:00<16:35:17,  3.29it/s]
 47%|████▋     | 175019/371472 [3:01:01<16:24:39,  3.33it/s]
 47%|████▋     | 175020/371472 [3:01:01<16:24:18,  3.33it/s]
                                                            
{'loss': 3.0143, 'learning_rate': 5.762190523389859e-07, 'epoch': 7.54}
+
 47%|████▋     | 175020/371472 [3:01:01<16:24:18,  3.33it/s]
 47%|████▋     | 175021/371472 [3:01:01<16:39:32,  3.28it/s]
 47%|████▋     | 175022/371472 [3:01:02<16:28:19,  3.31it/s]
 47%|████▋     | 175023/371472 [3:01:02<16:28:10,  3.31it/s]
 47%|████▋     | 175024/371472 [3:01:02<17:17:57,  3.15it/s]
 47%|████▋     | 175025/371472 [3:01:02<16:38:14,  3.28it/s]
 47%|████▋     | 175026/371472 [3:01:03<16:27:15,  3.32it/s]
 47%|████▋     | 175027/371472 [3:01:03<16:28:17,  3.31it/s]
 47%|████▋     | 175028/371472 [3:01:03<16:05:09,  3.39it/s]
 47%|████▋     | 175029/371472 [3:01:04<15:53:55,  3.43it/s]
 47%|████▋     | 175030/371472 [3:01:04<15:54:28,  3.43it/s]
 47%|████▋     | 175031/371472 [3:01:04<16:11:11,  3.37it/s]
 47%|████▋     | 175032/371472 [3:01:05<15:57:51,  3.42it/s]
 47%|████▋     | 175033/371472 [3:01:05<15:52:34,  3.44it/s]
 47%|████▋     | 175034/371472 [3:01:05<15:46:50,  3.46it/s]
 47%|████▋     | 175035/371472 [3:01:05<16:13:12,  3.36it/s]
 47%|████▋     | 175036/371472 [3:01:06<16:06:38,  3.39it/s]
 47%|████▋     | 175037/371472 [3:01:06<16:05:17,  3.39it/s]
 47%|████▋     | 175038/371472 [3:01:06<15:40:39,  3.48it/s]
 47%|████▋     | 175039/371472 [3:01:07<15:37:31,  3.49it/s]
 47%|████▋     | 175040/371472 [3:01:07<15:42:25,  3.47it/s]
                                                            
{'loss': 2.9051, 'learning_rate': 5.76170570363507e-07, 'epoch': 7.54}
+
 47%|████▋     | 175040/371472 [3:01:07<15:42:25,  3.47it/s]
 47%|████▋     | 175041/371472 [3:01:07<15:27:45,  3.53it/s]
 47%|████▋     | 175042/371472 [3:01:07<17:11:08,  3.17it/s]
 47%|████▋     | 175043/371472 [3:01:08<16:52:38,  3.23it/s]
 47%|████▋     | 175044/371472 [3:01:08<16:30:45,  3.30it/s]
 47%|████▋     | 175045/371472 [3:01:08<16:16:52,  3.35it/s]
 47%|████▋     | 175046/371472 [3:01:09<18:07:46,  3.01it/s]
 47%|████▋     | 175047/371472 [3:01:09<17:38:51,  3.09it/s]
 47%|████▋     | 175048/371472 [3:01:09<18:09:41,  3.00it/s]
 47%|████▋     | 175049/371472 [3:01:10<17:29:22,  3.12it/s]
 47%|████▋     | 175050/371472 [3:01:10<17:06:49,  3.19it/s]
 47%|████▋     | 175051/371472 [3:01:10<18:53:35,  2.89it/s]
 47%|████▋     | 175052/371472 [3:01:11<18:57:25,  2.88it/s]
 47%|████▋     | 175053/371472 [3:01:11<17:40:56,  3.09it/s]
 47%|████▋     | 175054/371472 [3:01:11<17:10:18,  3.18it/s]
 47%|████▋     | 175055/371472 [3:01:12<16:43:58,  3.26it/s]
 47%|████▋     | 175056/371472 [3:01:12<16:48:15,  3.25it/s]
 47%|████▋     | 175057/371472 [3:01:12<16:08:40,  3.38it/s]
 47%|████▋     | 175058/371472 [3:01:13<15:57:01,  3.42it/s]
 47%|████▋     | 175059/371472 [3:01:13<15:43:39,  3.47it/s]
 47%|████▋     | 175060/371472 [3:01:13<15:38:20,  3.49it/s]
                                                            
{'loss': 2.929, 'learning_rate': 5.761220883880281e-07, 'epoch': 7.54}
+
 47%|████▋     | 175060/371472 [3:01:13<15:38:20,  3.49it/s]
 47%|████▋     | 175061/371472 [3:01:13<15:50:35,  3.44it/s]
 47%|████▋     | 175062/371472 [3:01:14<15:55:55,  3.42it/s]
 47%|████▋     | 175063/371472 [3:01:14<16:04:33,  3.39it/s]
 47%|████▋     | 175064/371472 [3:01:14<16:28:24,  3.31it/s]
 47%|████▋     | 175065/371472 [3:01:15<16:10:59,  3.37it/s]
 47%|████▋     | 175066/371472 [3:01:15<16:39:23,  3.28it/s]
 47%|████▋     | 175067/371472 [3:01:15<16:37:09,  3.28it/s]
 47%|████▋     | 175068/371472 [3:01:15<16:25:32,  3.32it/s]
 47%|████▋     | 175069/371472 [3:01:16<16:51:20,  3.24it/s]
 47%|████▋     | 175070/371472 [3:01:16<16:41:10,  3.27it/s]
 47%|████▋     | 175071/371472 [3:01:16<15:58:44,  3.41it/s]
 47%|████▋     | 175072/371472 [3:01:17<15:36:23,  3.50it/s]
 47%|████▋     | 175073/371472 [3:01:17<15:39:40,  3.48it/s]
 47%|████▋     | 175074/371472 [3:01:17<15:37:40,  3.49it/s]
 47%|████▋     | 175075/371472 [3:01:18<16:26:28,  3.32it/s]
 47%|████▋     | 175076/371472 [3:01:18<17:18:45,  3.15it/s]
 47%|████▋     | 175077/371472 [3:01:18<17:44:54,  3.07it/s]
 47%|████▋     | 175078/371472 [3:01:19<17:02:21,  3.20it/s]
 47%|████▋     | 175079/371472 [3:01:19<16:40:31,  3.27it/s]
 47%|████▋     | 175080/371472 [3:01:19<16:45:19,  3.26it/s]
                                                            
{'loss': 2.7748, 'learning_rate': 5.760736064125494e-07, 'epoch': 7.54}
+
 47%|████▋     | 175080/371472 [3:01:19<16:45:19,  3.26it/s]
 47%|████▋     | 175081/371472 [3:01:19<16:22:30,  3.33it/s]
 47%|████▋     | 175082/371472 [3:01:20<16:21:34,  3.33it/s]
 47%|████▋     | 175083/371472 [3:01:20<16:12:34,  3.37it/s]
 47%|████▋     | 175084/371472 [3:01:20<16:32:03,  3.30it/s]
 47%|████▋     | 175085/371472 [3:01:21<16:12:30,  3.37it/s]
 47%|████▋     | 175086/371472 [3:01:21<16:34:12,  3.29it/s]
 47%|████▋     | 175087/371472 [3:01:21<15:51:08,  3.44it/s]
 47%|████▋     | 175088/371472 [3:01:21<15:29:12,  3.52it/s]
 47%|████▋     | 175089/371472 [3:01:22<15:36:19,  3.50it/s]
 47%|████▋     | 175090/371472 [3:01:22<15:40:22,  3.48it/s]
 47%|████▋     | 175091/371472 [3:01:22<15:26:00,  3.53it/s]
 47%|████▋     | 175092/371472 [3:01:23<15:59:32,  3.41it/s]
 47%|████▋     | 175093/371472 [3:01:23<17:00:53,  3.21it/s]
 47%|████▋     | 175094/371472 [3:01:23<16:51:33,  3.24it/s]
 47%|████▋     | 175095/371472 [3:01:24<16:28:29,  3.31it/s]
 47%|████▋     | 175096/371472 [3:01:24<16:38:33,  3.28it/s]
 47%|████▋     | 175097/371472 [3:01:24<16:08:26,  3.38it/s]
 47%|████▋     | 175098/371472 [3:01:24<16:19:26,  3.34it/s]
 47%|████▋     | 175099/371472 [3:01:25<16:23:44,  3.33it/s]
 47%|████▋     | 175100/371472 [3:01:25<16:10:20,  3.37it/s]
                                                            
{'loss': 2.927, 'learning_rate': 5.760251244370704e-07, 'epoch': 7.54}
+
 47%|████▋     | 175100/371472 [3:01:25<16:10:20,  3.37it/s]
 47%|████▋     | 175101/371472 [3:01:25<16:57:35,  3.22it/s]
 47%|████▋     | 175102/371472 [3:01:26<17:15:14,  3.16it/s]
 47%|████▋     | 175103/371472 [3:01:26<16:56:53,  3.22it/s]
 47%|████▋     | 175104/371472 [3:01:26<16:28:57,  3.31it/s]
 47%|████▋     | 175105/371472 [3:01:27<17:07:50,  3.18it/s]
 47%|████▋     | 175106/371472 [3:01:27<17:14:17,  3.16it/s]
 47%|████▋     | 175107/371472 [3:01:27<17:10:51,  3.17it/s]
 47%|████▋     | 175108/371472 [3:01:28<17:34:22,  3.10it/s]
 47%|████▋     | 175109/371472 [3:01:28<17:05:40,  3.19it/s]
 47%|████▋     | 175110/371472 [3:01:28<17:54:18,  3.05it/s]
 47%|████▋     | 175111/371472 [3:01:29<17:34:42,  3.10it/s]
 47%|████▋     | 175112/371472 [3:01:29<17:21:43,  3.14it/s]
 47%|████▋     | 175113/371472 [3:01:29<17:15:00,  3.16it/s]
 47%|████▋     | 175114/371472 [3:01:30<16:48:38,  3.24it/s]
 47%|████▋     | 175115/371472 [3:01:30<16:38:28,  3.28it/s]
 47%|████▋     | 175116/371472 [3:01:30<16:16:05,  3.35it/s]
 47%|████▋     | 175117/371472 [3:01:30<15:41:46,  3.47it/s]
 47%|████▋     | 175118/371472 [3:01:31<15:33:45,  3.50it/s]
 47%|████▋     | 175119/371472 [3:01:31<15:42:30,  3.47it/s]
 47%|████▋     | 175120/371472 [3:01:31<15:45:04,  3.46it/s]
                                                            
{'loss': 2.8946, 'learning_rate': 5.759766424615914e-07, 'epoch': 7.54}
+
 47%|████▋     | 175120/371472 [3:01:31<15:45:04,  3.46it/s]
 47%|████▋     | 175121/371472 [3:01:32<16:12:16,  3.37it/s]
 47%|████▋     | 175122/371472 [3:01:32<15:57:48,  3.42it/s]
 47%|████▋     | 175123/371472 [3:01:32<15:49:21,  3.45it/s]
 47%|████▋     | 175124/371472 [3:01:32<16:22:39,  3.33it/s]
 47%|████▋     | 175125/371472 [3:01:33<16:02:31,  3.40it/s]
 47%|████▋     | 175126/371472 [3:01:33<16:11:12,  3.37it/s]
 47%|████▋     | 175127/371472 [3:01:33<16:24:39,  3.32it/s]
 47%|████▋     | 175128/371472 [3:01:34<17:45:18,  3.07it/s]
 47%|████▋     | 175129/371472 [3:01:34<17:09:09,  3.18it/s]
 47%|████▋     | 175130/371472 [3:01:34<16:30:19,  3.30it/s]
 47%|████▋     | 175131/371472 [3:01:35<16:33:17,  3.29it/s]
 47%|████▋     | 175132/371472 [3:01:35<16:16:53,  3.35it/s]
 47%|████▋     | 175133/371472 [3:01:35<16:22:50,  3.33it/s]
 47%|████▋     | 175134/371472 [3:01:35<16:46:48,  3.25it/s]
 47%|████▋     | 175135/371472 [3:01:36<16:24:34,  3.32it/s]
 47%|████▋     | 175136/371472 [3:01:36<16:07:26,  3.38it/s]
 47%|████▋     | 175137/371472 [3:01:36<16:32:05,  3.30it/s]
 47%|████▋     | 175138/371472 [3:01:37<16:26:38,  3.32it/s]
 47%|████▋     | 175139/371472 [3:01:37<16:23:58,  3.33it/s]
 47%|████▋     | 175140/371472 [3:01:37<16:28:23,  3.31it/s]
                                                            
{'loss': 2.9457, 'learning_rate': 5.759281604861126e-07, 'epoch': 7.54}
+
 47%|████▋     | 175140/371472 [3:01:37<16:28:23,  3.31it/s]
 47%|████▋     | 175141/371472 [3:01:38<16:27:25,  3.31it/s]
 47%|████▋     | 175142/371472 [3:01:38<16:33:10,  3.29it/s]
 47%|████▋     | 175143/371472 [3:01:38<16:49:26,  3.24it/s]
 47%|████▋     | 175144/371472 [3:01:39<17:46:36,  3.07it/s]
 47%|████▋     | 175145/371472 [3:01:39<17:35:42,  3.10it/s]
 47%|████▋     | 175146/371472 [3:01:39<17:24:16,  3.13it/s]
 47%|████▋     | 175147/371472 [3:01:39<16:55:05,  3.22it/s]
 47%|████▋     | 175148/371472 [3:01:40<16:49:57,  3.24it/s]
 47%|████▋     | 175149/371472 [3:01:40<16:33:58,  3.29it/s]
 47%|████▋     | 175150/371472 [3:01:40<17:30:43,  3.11it/s]
 47%|████▋     | 175151/371472 [3:01:41<16:49:27,  3.24it/s]
 47%|████▋     | 175152/371472 [3:01:41<16:37:58,  3.28it/s]
 47%|████▋     | 175153/371472 [3:01:41<16:26:57,  3.32it/s]
 47%|████▋     | 175154/371472 [3:01:42<16:32:31,  3.30it/s]
 47%|████▋     | 175155/371472 [3:01:42<17:13:09,  3.17it/s]
 47%|████▋     | 175156/371472 [3:01:42<17:28:13,  3.12it/s]
 47%|████▋     | 175157/371472 [3:01:43<19:29:37,  2.80it/s]
 47%|████▋     | 175158/371472 [3:01:43<18:30:22,  2.95it/s]
 47%|████▋     | 175159/371472 [3:01:43<18:03:09,  3.02it/s]
 47%|████▋     | 175160/371472 [3:01:44<17:27:02,  3.12it/s]
                                                            
{'loss': 3.0025, 'learning_rate': 5.758796785106337e-07, 'epoch': 7.54}
+
 47%|████▋     | 175160/371472 [3:01:44<17:27:02,  3.12it/s]
 47%|████▋     | 175161/371472 [3:01:44<16:58:39,  3.21it/s]
 47%|████▋     | 175162/371472 [3:01:44<16:28:23,  3.31it/s]
 47%|████▋     | 175163/371472 [3:01:45<16:42:01,  3.27it/s]
 47%|████▋     | 175164/371472 [3:01:45<17:54:11,  3.05it/s]
 47%|████▋     | 175165/371472 [3:01:45<17:15:26,  3.16it/s]
 47%|████▋     | 175166/371472 [3:01:46<17:14:18,  3.16it/s]
 47%|████▋     | 175167/371472 [3:01:46<18:30:52,  2.95it/s]
 47%|████▋     | 175168/371472 [3:01:46<17:15:48,  3.16it/s]
 47%|████▋     | 175169/371472 [3:01:46<17:26:16,  3.13it/s]
 47%|████▋     | 175170/371472 [3:01:47<16:59:31,  3.21it/s]
 47%|████▋     | 175171/371472 [3:01:47<16:35:46,  3.29it/s]
 47%|████▋     | 175172/371472 [3:01:47<17:11:19,  3.17it/s]
 47%|████▋     | 175173/371472 [3:01:48<17:34:16,  3.10it/s]
 47%|████▋     | 175174/371472 [3:01:48<17:55:59,  3.04it/s]
 47%|████▋     | 175175/371472 [3:01:48<17:27:02,  3.12it/s]
 47%|████▋     | 175176/371472 [3:01:49<17:01:45,  3.20it/s]
 47%|████▋     | 175177/371472 [3:01:49<17:27:18,  3.12it/s]
 47%|████▋     | 175178/371472 [3:01:49<16:49:01,  3.24it/s]
 47%|████▋     | 175179/371472 [3:01:50<17:37:32,  3.09it/s]
 47%|████▋     | 175180/371472 [3:01:50<17:15:49,  3.16it/s]
                                                            
{'loss': 2.9123, 'learning_rate': 5.758311965351547e-07, 'epoch': 7.55}
+
 47%|████▋     | 175180/371472 [3:01:50<17:15:49,  3.16it/s]
 47%|████▋     | 175181/371472 [3:01:50<17:16:57,  3.15it/s]
 47%|████▋     | 175182/371472 [3:01:51<16:31:26,  3.30it/s]
 47%|████▋     | 175183/371472 [3:01:51<16:02:53,  3.40it/s]
 47%|████▋     | 175184/371472 [3:01:51<16:07:30,  3.38it/s]
 47%|████▋     | 175185/371472 [3:01:51<17:06:37,  3.19it/s]
 47%|████▋     | 175186/371472 [3:01:52<16:33:56,  3.29it/s]
 47%|████▋     | 175187/371472 [3:01:52<16:44:07,  3.26it/s]
 47%|████▋     | 175188/371472 [3:01:52<17:31:55,  3.11it/s]
 47%|████▋     | 175189/371472 [3:01:53<17:29:49,  3.12it/s]
 47%|████▋     | 175190/371472 [3:01:53<18:21:40,  2.97it/s]
 47%|████▋     | 175191/371472 [3:01:53<17:56:35,  3.04it/s]
 47%|████▋     | 175192/371472 [3:01:54<17:05:22,  3.19it/s]
 47%|████▋     | 175193/371472 [3:01:54<16:45:44,  3.25it/s]
 47%|████▋     | 175194/371472 [3:01:54<16:55:12,  3.22it/s]
 47%|████▋     | 175195/371472 [3:01:55<17:17:28,  3.15it/s]
 47%|████▋     | 175196/371472 [3:01:55<16:47:54,  3.25it/s]
 47%|████▋     | 175197/371472 [3:01:55<16:26:57,  3.31it/s]
 47%|████▋     | 175198/371472 [3:01:56<16:21:57,  3.33it/s]
 47%|████▋     | 175199/371472 [3:01:56<16:26:07,  3.32it/s]
 47%|████▋     | 175200/371472 [3:01:56<16:13:09,  3.36it/s]
                                                            
{'loss': 2.8583, 'learning_rate': 5.757827145596758e-07, 'epoch': 7.55}
+
 47%|████▋     | 175200/371472 [3:01:56<16:13:09,  3.36it/s]
 47%|████▋     | 175201/371472 [3:01:56<16:40:13,  3.27it/s]
 47%|████▋     | 175202/371472 [3:01:57<16:30:46,  3.30it/s]
 47%|████▋     | 175203/371472 [3:01:57<16:37:27,  3.28it/s]
 47%|████▋     | 175204/371472 [3:01:57<17:10:40,  3.17it/s]
 47%|████▋     | 175205/371472 [3:01:58<17:13:26,  3.17it/s]
 47%|████▋     | 175206/371472 [3:01:58<17:02:49,  3.20it/s]
 47%|████▋     | 175207/371472 [3:01:58<17:06:08,  3.19it/s]
 47%|████▋     | 175208/371472 [3:01:59<17:36:48,  3.10it/s]
 47%|████▋     | 175209/371472 [3:01:59<17:38:14,  3.09it/s]
 47%|████▋     | 175210/371472 [3:01:59<17:29:26,  3.12it/s]
 47%|████▋     | 175211/371472 [3:02:00<16:41:03,  3.27it/s]
 47%|████▋     | 175212/371472 [3:02:00<16:37:03,  3.28it/s]
 47%|████▋     | 175213/371472 [3:02:00<16:14:46,  3.36it/s]
 47%|████▋     | 175214/371472 [3:02:00<16:26:15,  3.32it/s]
 47%|████▋     | 175215/371472 [3:02:01<16:36:40,  3.28it/s]
 47%|████▋     | 175216/371472 [3:02:01<16:26:32,  3.32it/s]
 47%|████▋     | 175217/371472 [3:02:01<16:09:16,  3.37it/s]
 47%|████▋     | 175218/371472 [3:02:02<16:04:31,  3.39it/s]
 47%|████▋     | 175219/371472 [3:02:02<16:05:57,  3.39it/s]
 47%|████▋     | 175220/371472 [3:02:02<16:50:03,  3.24it/s]
                                                            
{'loss': 2.9453, 'learning_rate': 5.757342325841971e-07, 'epoch': 7.55}
+
 47%|████▋     | 175220/371472 [3:02:02<16:50:03,  3.24it/s]
 47%|████▋     | 175221/371472 [3:02:03<16:25:14,  3.32it/s]
 47%|████▋     | 175222/371472 [3:02:03<16:25:10,  3.32it/s]
 47%|████▋     | 175223/371472 [3:02:03<16:44:12,  3.26it/s]
 47%|████▋     | 175224/371472 [3:02:03<16:19:49,  3.34it/s]
 47%|████▋     | 175225/371472 [3:02:04<16:27:43,  3.31it/s]
 47%|████▋     | 175226/371472 [3:02:04<16:02:14,  3.40it/s]
 47%|████▋     | 175227/371472 [3:02:04<16:04:33,  3.39it/s]
 47%|████▋     | 175228/371472 [3:02:05<16:51:56,  3.23it/s]
 47%|████▋     | 175229/371472 [3:02:05<16:38:06,  3.28it/s]
 47%|████▋     | 175230/371472 [3:02:05<16:29:19,  3.31it/s]
 47%|████▋     | 175231/371472 [3:02:06<17:11:15,  3.17it/s]
 47%|████▋     | 175232/371472 [3:02:06<17:18:11,  3.15it/s]
 47%|████▋     | 175233/371472 [3:02:06<16:56:31,  3.22it/s]
 47%|████▋     | 175234/371472 [3:02:07<16:41:52,  3.26it/s]
 47%|████▋     | 175235/371472 [3:02:07<16:30:15,  3.30it/s]
 47%|████▋     | 175236/371472 [3:02:07<16:22:34,  3.33it/s]
 47%|████▋     | 175237/371472 [3:02:07<16:30:40,  3.30it/s]
 47%|████▋     | 175238/371472 [3:02:08<16:47:03,  3.25it/s]
 47%|████▋     | 175239/371472 [3:02:08<16:25:55,  3.32it/s]
 47%|████▋     | 175240/371472 [3:02:08<16:25:43,  3.32it/s]
                                                            
{'loss': 3.0417, 'learning_rate': 5.756857506087181e-07, 'epoch': 7.55}
+
 47%|████▋     | 175240/371472 [3:02:08<16:25:43,  3.32it/s]
 47%|████▋     | 175241/371472 [3:02:09<16:41:15,  3.27it/s]
 47%|████▋     | 175242/371472 [3:02:09<16:29:28,  3.31it/s]
 47%|████▋     | 175243/371472 [3:02:09<16:13:05,  3.36it/s]
 47%|████▋     | 175244/371472 [3:02:10<18:39:52,  2.92it/s]
 47%|████▋     | 175245/371472 [3:02:10<17:46:11,  3.07it/s]
 47%|████▋     | 175246/371472 [3:02:10<17:15:08,  3.16it/s]
 47%|████▋     | 175247/371472 [3:02:11<16:56:24,  3.22it/s]
 47%|████▋     | 175248/371472 [3:02:11<16:37:44,  3.28it/s]
 47%|████▋     | 175249/371472 [3:02:11<16:35:53,  3.28it/s]
 47%|████▋     | 175250/371472 [3:02:11<16:34:50,  3.29it/s]
 47%|████▋     | 175251/371472 [3:02:12<16:33:02,  3.29it/s]
 47%|████▋     | 175252/371472 [3:02:12<16:02:51,  3.40it/s]
 47%|████▋     | 175253/371472 [3:02:12<17:31:38,  3.11it/s]
 47%|████▋     | 175254/371472 [3:02:13<16:48:25,  3.24it/s]
 47%|████▋     | 175255/371472 [3:02:13<17:01:59,  3.20it/s]
 47%|████▋     | 175256/371472 [3:02:13<16:25:35,  3.32it/s]
 47%|████▋     | 175257/371472 [3:02:14<16:36:20,  3.28it/s]
 47%|████▋     | 175258/371472 [3:02:14<17:09:13,  3.18it/s]
 47%|████▋     | 175259/371472 [3:02:14<16:24:07,  3.32it/s]
 47%|████▋     | 175260/371472 [3:02:15<16:37:58,  3.28it/s]
                                                            
{'loss': 2.7906, 'learning_rate': 5.756372686332392e-07, 'epoch': 7.55}
+
 47%|████▋     | 175260/371472 [3:02:15<16:37:58,  3.28it/s]
 47%|████▋     | 175261/371472 [3:02:15<16:37:39,  3.28it/s]
 47%|████▋     | 175262/371472 [3:02:15<16:34:28,  3.29it/s]
 47%|████▋     | 175263/371472 [3:02:15<16:13:55,  3.36it/s]
 47%|████▋     | 175264/371472 [3:02:16<17:06:49,  3.18it/s]
 47%|████▋     | 175265/371472 [3:02:16<16:40:15,  3.27it/s]
 47%|████▋     | 175266/371472 [3:02:16<16:12:42,  3.36it/s]
 47%|████▋     | 175267/371472 [3:02:17<16:05:09,  3.39it/s]
 47%|████▋     | 175268/371472 [3:02:17<15:54:07,  3.43it/s]
 47%|████▋     | 175269/371472 [3:02:17<15:55:18,  3.42it/s]
 47%|████▋     | 175270/371472 [3:02:18<16:10:15,  3.37it/s]
 47%|████▋     | 175271/371472 [3:02:18<16:37:59,  3.28it/s]
 47%|████▋     | 175272/371472 [3:02:18<16:42:40,  3.26it/s]
 47%|████▋     | 175273/371472 [3:02:19<17:15:55,  3.16it/s]
 47%|████▋     | 175274/371472 [3:02:19<16:20:55,  3.33it/s]
 47%|████▋     | 175275/371472 [3:02:19<15:48:28,  3.45it/s]
 47%|████▋     | 175276/371472 [3:02:19<17:03:04,  3.20it/s]
 47%|████▋     | 175277/371472 [3:02:20<17:59:17,  3.03it/s]
 47%|████▋     | 175278/371472 [3:02:20<17:45:26,  3.07it/s]
 47%|████▋     | 175279/371472 [3:02:20<17:58:14,  3.03it/s]
 47%|████▋     | 175280/371472 [3:02:21<17:23:50,  3.13it/s]
                                                            
{'loss': 2.9301, 'learning_rate': 5.755887866577602e-07, 'epoch': 7.55}
+
 47%|████▋     | 175280/371472 [3:02:21<17:23:50,  3.13it/s]
 47%|████▋     | 175281/371472 [3:02:21<17:10:39,  3.17it/s]
 47%|████▋     | 175282/371472 [3:02:21<17:31:17,  3.11it/s]
 47%|████▋     | 175283/371472 [3:02:22<17:04:40,  3.19it/s]
 47%|████▋     | 175284/371472 [3:02:22<16:42:11,  3.26it/s]
 47%|████▋     | 175285/371472 [3:02:22<16:17:36,  3.34it/s]
 47%|████▋     | 175286/371472 [3:02:23<16:11:21,  3.37it/s]
 47%|████▋     | 175287/371472 [3:02:23<15:46:56,  3.45it/s]
 47%|████▋     | 175288/371472 [3:02:23<15:51:43,  3.44it/s]
 47%|████▋     | 175289/371472 [3:02:23<15:44:24,  3.46it/s]
 47%|████▋     | 175290/371472 [3:02:24<16:05:33,  3.39it/s]
 47%|████▋     | 175291/371472 [3:02:24<17:25:50,  3.13it/s]
 47%|████▋     | 175292/371472 [3:02:24<16:41:10,  3.27it/s]
 47%|████▋     | 175293/371472 [3:02:25<16:40:31,  3.27it/s]
 47%|████▋     | 175294/371472 [3:02:25<16:05:45,  3.39it/s]
 47%|████▋     | 175295/371472 [3:02:25<15:51:32,  3.44it/s]
 47%|████▋     | 175296/371472 [3:02:25<15:23:20,  3.54it/s]
 47%|████▋     | 175297/371472 [3:02:26<15:28:14,  3.52it/s]
 47%|████▋     | 175298/371472 [3:02:26<15:36:00,  3.49it/s]
 47%|████▋     | 175299/371472 [3:02:26<15:31:46,  3.51it/s]
 47%|████▋     | 175300/371472 [3:02:27<16:06:23,  3.38it/s]
                                                            
{'loss': 2.8961, 'learning_rate': 5.755403046822814e-07, 'epoch': 7.55}
+
 47%|████▋     | 175300/371472 [3:02:27<16:06:23,  3.38it/s]
 47%|████▋     | 175301/371472 [3:02:27<15:59:12,  3.41it/s]
 47%|████▋     | 175302/371472 [3:02:27<15:45:42,  3.46it/s]
 47%|████▋     | 175303/371472 [3:02:28<15:57:33,  3.41it/s]
 47%|████▋     | 175304/371472 [3:02:28<18:31:32,  2.94it/s]
 47%|████▋     | 175305/371472 [3:02:28<17:24:31,  3.13it/s]
 47%|████▋     | 175306/371472 [3:02:29<17:06:08,  3.19it/s]
 47%|████▋     | 175307/371472 [3:02:29<16:54:09,  3.22it/s]
 47%|████▋     | 175308/371472 [3:02:29<16:44:23,  3.26it/s]
 47%|████▋     | 175309/371472 [3:02:29<17:17:48,  3.15it/s]
 47%|████▋     | 175310/371472 [3:02:30<16:54:46,  3.22it/s]
 47%|████▋     | 175311/371472 [3:02:30<16:54:32,  3.22it/s]
 47%|████▋     | 175312/371472 [3:02:30<16:37:49,  3.28it/s]
 47%|████▋     | 175313/371472 [3:02:31<16:35:27,  3.28it/s]
 47%|████▋     | 175314/371472 [3:02:31<16:10:28,  3.37it/s]
 47%|████▋     | 175315/371472 [3:02:31<16:36:45,  3.28it/s]
 47%|████▋     | 175316/371472 [3:02:32<16:18:52,  3.34it/s]
 47%|████▋     | 175317/371472 [3:02:32<17:13:22,  3.16it/s]
 47%|████▋     | 175318/371472 [3:02:32<18:58:32,  2.87it/s]
 47%|████▋     | 175319/371472 [3:02:33<17:42:04,  3.08it/s]
 47%|████▋     | 175320/371472 [3:02:33<17:25:56,  3.13it/s]
                                                            
{'loss': 3.0848, 'learning_rate': 5.754918227068026e-07, 'epoch': 7.55}
+
 47%|████▋     | 175320/371472 [3:02:33<17:25:56,  3.13it/s]
 47%|████▋     | 175321/371472 [3:02:33<17:19:59,  3.14it/s]
 47%|████▋     | 175322/371472 [3:02:34<16:38:02,  3.28it/s]
 47%|████▋     | 175323/371472 [3:02:34<16:08:06,  3.38it/s]
 47%|████▋     | 175324/371472 [3:02:34<16:25:14,  3.32it/s]
 47%|████▋     | 175325/371472 [3:02:34<16:18:55,  3.34it/s]
 47%|████▋     | 175326/371472 [3:02:35<16:24:22,  3.32it/s]
 47%|████▋     | 175327/371472 [3:02:35<16:27:22,  3.31it/s]
 47%|████▋     | 175328/371472 [3:02:35<16:07:21,  3.38it/s]
 47%|████▋     | 175329/371472 [3:02:36<15:49:28,  3.44it/s]
 47%|████▋     | 175330/371472 [3:02:36<16:50:05,  3.24it/s]
 47%|████▋     | 175331/371472 [3:02:36<17:00:19,  3.20it/s]
 47%|████▋     | 175332/371472 [3:02:37<16:14:45,  3.35it/s]
 47%|████▋     | 175333/371472 [3:02:37<18:15:20,  2.98it/s]
 47%|████▋     | 175334/371472 [3:02:37<17:36:36,  3.09it/s]
 47%|████▋     | 175335/371472 [3:02:38<17:43:48,  3.07it/s]
 47%|████▋     | 175336/371472 [3:02:38<17:23:59,  3.13it/s]
 47%|████▋     | 175337/371472 [3:02:38<17:09:25,  3.18it/s]
 47%|████▋     | 175338/371472 [3:02:38<16:45:25,  3.25it/s]
 47%|████▋     | 175339/371472 [3:02:39<16:50:28,  3.23it/s]
 47%|████▋     | 175340/371472 [3:02:39<16:47:25,  3.24it/s]
                                                            
{'loss': 2.8408, 'learning_rate': 5.754433407313237e-07, 'epoch': 7.55}
+
 47%|████▋     | 175340/371472 [3:02:39<16:47:25,  3.24it/s]
 47%|████▋     | 175341/371472 [3:02:39<16:51:09,  3.23it/s]
 47%|████▋     | 175342/371472 [3:02:40<16:45:13,  3.25it/s]
 47%|████▋     | 175343/371472 [3:02:40<17:34:48,  3.10it/s]
 47%|████▋     | 175344/371472 [3:02:40<17:19:25,  3.14it/s]
 47%|████▋     | 175345/371472 [3:02:41<17:14:21,  3.16it/s]
 47%|████▋     | 175346/371472 [3:02:41<16:37:48,  3.28it/s]
 47%|████▋     | 175347/371472 [3:02:41<16:22:14,  3.33it/s]
 47%|████▋     | 175348/371472 [3:02:41<15:46:08,  3.45it/s]
 47%|████▋     | 175349/371472 [3:02:42<15:35:43,  3.49it/s]
 47%|████▋     | 175350/371472 [3:02:42<16:09:42,  3.37it/s]
 47%|████▋     | 175351/371472 [3:02:42<16:13:58,  3.36it/s]
 47%|████▋     | 175352/371472 [3:02:43<15:56:27,  3.42it/s]
 47%|████▋     | 175353/371472 [3:02:43<16:05:42,  3.38it/s]
 47%|████▋     | 175354/371472 [3:02:43<16:57:39,  3.21it/s]
 47%|████▋     | 175355/371472 [3:02:44<16:54:49,  3.22it/s]
 47%|████▋     | 175356/371472 [3:02:44<17:15:18,  3.16it/s]
 47%|████▋     | 175357/371472 [3:02:44<16:40:04,  3.27it/s]
 47%|████▋     | 175358/371472 [3:02:45<16:11:33,  3.36it/s]
 47%|████▋     | 175359/371472 [3:02:45<16:58:07,  3.21it/s]
 47%|████▋     | 175360/371472 [3:02:45<17:00:13,  3.20it/s]
                                                            
{'loss': 2.9714, 'learning_rate': 5.753948587558448e-07, 'epoch': 7.55}
+
 47%|████▋     | 175360/371472 [3:02:45<17:00:13,  3.20it/s]
 47%|████▋     | 175361/371472 [3:02:45<16:25:41,  3.32it/s]
 47%|████▋     | 175362/371472 [3:02:46<15:58:34,  3.41it/s]
 47%|████▋     | 175363/371472 [3:02:46<16:03:38,  3.39it/s]
 47%|████▋     | 175364/371472 [3:02:46<15:35:39,  3.49it/s]
 47%|████▋     | 175365/371472 [3:02:47<15:40:04,  3.48it/s]
 47%|████▋     | 175366/371472 [3:02:47<16:32:45,  3.29it/s]
 47%|████▋     | 175367/371472 [3:02:47<16:21:13,  3.33it/s]
 47%|████▋     | 175368/371472 [3:02:48<17:16:27,  3.15it/s]
 47%|████▋     | 175369/371472 [3:02:48<16:39:14,  3.27it/s]
 47%|████▋     | 175370/371472 [3:02:48<16:04:13,  3.39it/s]
 47%|████▋     | 175371/371472 [3:02:48<15:49:29,  3.44it/s]
 47%|████▋     | 175372/371472 [3:02:49<15:43:39,  3.46it/s]
 47%|████▋     | 175373/371472 [3:02:49<15:29:52,  3.51it/s]
 47%|████▋     | 175374/371472 [3:02:49<15:23:09,  3.54it/s]
 47%|████▋     | 175375/371472 [3:02:50<16:11:04,  3.37it/s]
 47%|████▋     | 175376/371472 [3:02:50<15:33:42,  3.50it/s]
 47%|████▋     | 175377/371472 [3:02:50<15:46:34,  3.45it/s]
 47%|████▋     | 175378/371472 [3:02:50<16:45:24,  3.25it/s]
 47%|████▋     | 175379/371472 [3:02:51<16:56:46,  3.21it/s]
 47%|████▋     | 175380/371472 [3:02:51<16:16:31,  3.35it/s]
                                                            
{'loss': 3.0606, 'learning_rate': 5.753463767803659e-07, 'epoch': 7.55}
+
 47%|████▋     | 175380/371472 [3:02:51<16:16:31,  3.35it/s]
 47%|████▋     | 175381/371472 [3:02:51<16:17:23,  3.34it/s]
 47%|████▋     | 175382/371472 [3:02:52<15:58:13,  3.41it/s]
 47%|████▋     | 175383/371472 [3:02:52<15:57:48,  3.41it/s]
 47%|████▋     | 175384/371472 [3:02:52<16:09:03,  3.37it/s]
 47%|████▋     | 175385/371472 [3:02:53<16:02:18,  3.40it/s]
 47%|████▋     | 175386/371472 [3:02:53<16:12:08,  3.36it/s]
 47%|████▋     | 175387/371472 [3:02:53<16:29:21,  3.30it/s]
 47%|████▋     | 175388/371472 [3:02:53<16:47:07,  3.24it/s]
 47%|████▋     | 175389/371472 [3:02:54<16:08:29,  3.37it/s]
 47%|████▋     | 175390/371472 [3:02:54<15:53:37,  3.43it/s]
 47%|████▋     | 175391/371472 [3:02:54<16:04:27,  3.39it/s]
 47%|████▋     | 175392/371472 [3:02:55<16:24:13,  3.32it/s]
 47%|████▋     | 175393/371472 [3:02:55<16:17:57,  3.34it/s]
 47%|████▋     | 175394/371472 [3:02:55<15:54:12,  3.42it/s]
 47%|████▋     | 175395/371472 [3:02:56<15:51:34,  3.43it/s]
 47%|████▋     | 175396/371472 [3:02:56<16:04:27,  3.39it/s]
 47%|████▋     | 175397/371472 [3:02:56<16:50:50,  3.23it/s]
 47%|████▋     | 175398/371472 [3:02:56<16:48:45,  3.24it/s]
 47%|████▋     | 175399/371472 [3:02:57<17:39:53,  3.08it/s]
 47%|████▋     | 175400/371472 [3:02:57<17:01:32,  3.20it/s]
                                                            
{'loss': 2.8411, 'learning_rate': 5.75297894804887e-07, 'epoch': 7.55}
+
 47%|████▋     | 175400/371472 [3:02:57<17:01:32,  3.20it/s]
 47%|████▋     | 175401/371472 [3:02:57<16:40:37,  3.27it/s]
 47%|████▋     | 175402/371472 [3:02:58<15:59:40,  3.41it/s]
 47%|████▋     | 175403/371472 [3:02:58<15:52:48,  3.43it/s]
 47%|████▋     | 175404/371472 [3:02:58<16:16:52,  3.35it/s]
 47%|████▋     | 175405/371472 [3:02:59<15:55:15,  3.42it/s]
 47%|████▋     | 175406/371472 [3:02:59<15:43:38,  3.46it/s]
 47%|████▋     | 175407/371472 [3:02:59<15:33:48,  3.50it/s]
 47%|████▋     | 175408/371472 [3:02:59<15:45:25,  3.46it/s]
 47%|████▋     | 175409/371472 [3:03:00<15:37:23,  3.49it/s]
 47%|████▋     | 175410/371472 [3:03:00<15:40:40,  3.47it/s]
 47%|████▋     | 175411/371472 [3:03:00<16:04:07,  3.39it/s]
 47%|████▋     | 175412/371472 [3:03:01<15:53:08,  3.43it/s]
 47%|████▋     | 175413/371472 [3:03:01<16:14:23,  3.35it/s]
 47%|████▋     | 175414/371472 [3:03:01<16:50:26,  3.23it/s]
 47%|████▋     | 175415/371472 [3:03:02<17:47:44,  3.06it/s]
 47%|████▋     | 175416/371472 [3:03:02<17:28:14,  3.12it/s]
 47%|████▋     | 175417/371472 [3:03:02<16:42:56,  3.26it/s]
 47%|████▋     | 175418/371472 [3:03:02<16:41:27,  3.26it/s]
 47%|████▋     | 175419/371472 [3:03:03<16:28:22,  3.31it/s]
 47%|████▋     | 175420/371472 [3:03:03<16:35:39,  3.28it/s]
                                                            
{'loss': 2.8904, 'learning_rate': 5.752494128294081e-07, 'epoch': 7.56}
+
 47%|████▋     | 175420/371472 [3:03:03<16:35:39,  3.28it/s]
 47%|████▋     | 175421/371472 [3:03:03<16:22:14,  3.33it/s]
 47%|████▋     | 175422/371472 [3:03:04<17:02:19,  3.20it/s]
 47%|████▋     | 175423/371472 [3:03:04<16:51:41,  3.23it/s]
 47%|████▋     | 175424/371472 [3:03:04<16:18:47,  3.34it/s]
 47%|████▋     | 175425/371472 [3:03:05<16:01:23,  3.40it/s]
 47%|████▋     | 175426/371472 [3:03:05<15:47:07,  3.45it/s]
 47%|████▋     | 175427/371472 [3:03:05<16:06:55,  3.38it/s]
 47%|████▋     | 175428/371472 [3:03:05<15:47:59,  3.45it/s]
 47%|████▋     | 175429/371472 [3:03:06<16:16:14,  3.35it/s]
 47%|████▋     | 175430/371472 [3:03:06<16:01:22,  3.40it/s]
 47%|████▋     | 175431/371472 [3:03:06<16:16:02,  3.35it/s]
 47%|████▋     | 175432/371472 [3:03:07<16:05:38,  3.38it/s]
 47%|████▋     | 175433/371472 [3:03:07<16:48:55,  3.24it/s]
 47%|████▋     | 175434/371472 [3:03:07<16:48:10,  3.24it/s]
 47%|████▋     | 175435/371472 [3:03:08<17:41:49,  3.08it/s]
 47%|████▋     | 175436/371472 [3:03:08<16:58:52,  3.21it/s]
 47%|████▋     | 175437/371472 [3:03:08<16:33:03,  3.29it/s]
 47%|████▋     | 175438/371472 [3:03:09<16:22:37,  3.33it/s]
 47%|████▋     | 175439/371472 [3:03:09<16:41:28,  3.26it/s]
 47%|████▋     | 175440/371472 [3:03:09<16:24:05,  3.32it/s]
                                                            
{'loss': 2.9668, 'learning_rate': 5.752009308539291e-07, 'epoch': 7.56}
+
 47%|████▋     | 175440/371472 [3:03:09<16:24:05,  3.32it/s]
 47%|████▋     | 175441/371472 [3:03:09<16:35:53,  3.28it/s]
 47%|████▋     | 175442/371472 [3:03:10<17:01:39,  3.20it/s]
 47%|████▋     | 175443/371472 [3:03:10<20:31:31,  2.65it/s]
 47%|████▋     | 175444/371472 [3:03:11<19:01:14,  2.86it/s]
 47%|████▋     | 175445/371472 [3:03:11<17:55:07,  3.04it/s]
 47%|████▋     | 175446/371472 [3:03:11<17:02:17,  3.20it/s]
 47%|████▋     | 175447/371472 [3:03:11<16:16:48,  3.34it/s]
 47%|████▋     | 175448/371472 [3:03:12<15:47:21,  3.45it/s]
 47%|████▋     | 175449/371472 [3:03:12<15:43:37,  3.46it/s]
 47%|████▋     | 175450/371472 [3:03:12<15:45:46,  3.45it/s]
 47%|████▋     | 175451/371472 [3:03:13<15:48:15,  3.45it/s]
 47%|████▋     | 175452/371472 [3:03:13<15:25:20,  3.53it/s]
 47%|████▋     | 175453/371472 [3:03:13<15:52:34,  3.43it/s]
 47%|████▋     | 175454/371472 [3:03:13<15:40:25,  3.47it/s]
 47%|████▋     | 175455/371472 [3:03:14<15:48:22,  3.44it/s]
 47%|████▋     | 175456/371472 [3:03:14<15:51:45,  3.43it/s]
 47%|████▋     | 175457/371472 [3:03:14<15:41:02,  3.47it/s]
 47%|████▋     | 175458/371472 [3:03:15<15:46:34,  3.45it/s]
 47%|████▋     | 175459/371472 [3:03:15<15:35:48,  3.49it/s]
 47%|████▋     | 175460/371472 [3:03:15<15:53:43,  3.43it/s]
                                                            
{'loss': 3.0131, 'learning_rate': 5.751524488784504e-07, 'epoch': 7.56}
+
 47%|████▋     | 175460/371472 [3:03:15<15:53:43,  3.43it/s]
 47%|████▋     | 175461/371472 [3:03:15<16:07:58,  3.37it/s]
 47%|████▋     | 175462/371472 [3:03:16<16:08:36,  3.37it/s]
 47%|████▋     | 175463/371472 [3:03:16<17:39:16,  3.08it/s]
 47%|████▋     | 175464/371472 [3:03:16<17:07:58,  3.18it/s]
 47%|████▋     | 175465/371472 [3:03:17<16:48:42,  3.24it/s]
 47%|████▋     | 175466/371472 [3:03:17<16:40:02,  3.27it/s]
 47%|████▋     | 175467/371472 [3:03:17<16:21:22,  3.33it/s]
 47%|████▋     | 175468/371472 [3:03:18<16:35:19,  3.28it/s]
 47%|████▋     | 175469/371472 [3:03:18<16:50:12,  3.23it/s]
 47%|████▋     | 175470/371472 [3:03:18<16:43:43,  3.25it/s]
 47%|████▋     | 175471/371472 [3:03:19<16:17:44,  3.34it/s]
 47%|████▋     | 175472/371472 [3:03:19<16:33:54,  3.29it/s]
 47%|████▋     | 175473/371472 [3:03:19<17:02:49,  3.19it/s]
 47%|████▋     | 175474/371472 [3:03:19<16:49:00,  3.24it/s]
 47%|████▋     | 175475/371472 [3:03:20<17:01:49,  3.20it/s]
 47%|████▋     | 175476/371472 [3:03:20<16:41:40,  3.26it/s]
 47%|████▋     | 175477/371472 [3:03:20<16:51:38,  3.23it/s]
 47%|████▋     | 175478/371472 [3:03:21<17:23:07,  3.13it/s]
 47%|████▋     | 175479/371472 [3:03:21<16:45:00,  3.25it/s]
 47%|████▋     | 175480/371472 [3:03:21<16:32:20,  3.29it/s]
                                                            
{'loss': 2.9878, 'learning_rate': 5.751039669029714e-07, 'epoch': 7.56}
+
 47%|████▋     | 175480/371472 [3:03:21<16:32:20,  3.29it/s]
 47%|████▋     | 175481/371472 [3:03:22<15:58:03,  3.41it/s]
 47%|████▋     | 175482/371472 [3:03:22<16:08:08,  3.37it/s]
 47%|████▋     | 175483/371472 [3:03:22<15:58:53,  3.41it/s]
 47%|████▋     | 175484/371472 [3:03:22<15:54:45,  3.42it/s]
 47%|████▋     | 175485/371472 [3:03:23<15:31:36,  3.51it/s]
 47%|████▋     | 175486/371472 [3:03:23<16:05:17,  3.38it/s]
 47%|████▋     | 175487/371472 [3:03:23<15:52:19,  3.43it/s]
 47%|████▋     | 175488/371472 [3:03:24<16:23:57,  3.32it/s]
 47%|████▋     | 175489/371472 [3:03:24<15:55:19,  3.42it/s]
 47%|████▋     | 175490/371472 [3:03:24<15:50:24,  3.44it/s]
 47%|████▋     | 175491/371472 [3:03:25<15:50:47,  3.44it/s]
 47%|████▋     | 175492/371472 [3:03:25<15:41:56,  3.47it/s]
 47%|████▋     | 175493/371472 [3:03:25<15:52:53,  3.43it/s]
 47%|████▋     | 175494/371472 [3:03:25<16:07:22,  3.38it/s]
 47%|████▋     | 175495/371472 [3:03:26<16:23:34,  3.32it/s]
 47%|████▋     | 175496/371472 [3:03:26<17:01:32,  3.20it/s]
 47%|████▋     | 175497/371472 [3:03:26<16:37:36,  3.27it/s]
 47%|████▋     | 175498/371472 [3:03:27<16:42:18,  3.26it/s]
 47%|████▋     | 175499/371472 [3:03:27<16:39:44,  3.27it/s]
 47%|████▋     | 175500/371472 [3:03:27<16:33:24,  3.29it/s]
                                                            
{'loss': 2.8644, 'learning_rate': 5.750554849274925e-07, 'epoch': 7.56}
+
 47%|████▋     | 175500/371472 [3:03:27<16:33:24,  3.29it/s]
 47%|████▋     | 175501/371472 [3:03:28<16:42:39,  3.26it/s]
 47%|████▋     | 175502/371472 [3:03:28<16:44:19,  3.25it/s]
 47%|████▋     | 175503/371472 [3:03:28<16:22:13,  3.33it/s]
 47%|████▋     | 175504/371472 [3:03:28<16:16:30,  3.34it/s]
 47%|████▋     | 175505/371472 [3:03:29<16:01:09,  3.40it/s]
 47%|████▋     | 175506/371472 [3:03:29<16:03:29,  3.39it/s]
 47%|████▋     | 175507/371472 [3:03:29<16:16:41,  3.34it/s]
 47%|████▋     | 175508/371472 [3:03:30<17:34:42,  3.10it/s]
 47%|████▋     | 175509/371472 [3:03:30<17:11:54,  3.17it/s]
 47%|████▋     | 175510/371472 [3:03:30<17:25:43,  3.12it/s]
 47%|████▋     | 175511/371472 [3:03:31<17:26:16,  3.12it/s]
 47%|████▋     | 175512/371472 [3:03:31<17:30:34,  3.11it/s]
 47%|████▋     | 175513/371472 [3:03:31<18:11:07,  2.99it/s]
 47%|████▋     | 175514/371472 [3:03:32<18:40:48,  2.91it/s]
 47%|████▋     | 175515/371472 [3:03:32<19:36:16,  2.78it/s]
 47%|████▋     | 175516/371472 [3:03:33<20:10:36,  2.70it/s]
 47%|████▋     | 175517/371472 [3:03:33<20:05:22,  2.71it/s]
 47%|████▋     | 175518/371472 [3:03:33<19:08:19,  2.84it/s]
 47%|████▋     | 175519/371472 [3:03:33<18:12:15,  2.99it/s]
 47%|████▋     | 175520/371472 [3:03:34<17:45:07,  3.07it/s]
                                                            
{'loss': 2.7475, 'learning_rate': 5.750070029520136e-07, 'epoch': 7.56}
+
 47%|████▋     | 175520/371472 [3:03:34<17:45:07,  3.07it/s]
 47%|████▋     | 175521/371472 [3:03:34<17:26:47,  3.12it/s]
 47%|████▋     | 175522/371472 [3:03:34<16:55:16,  3.22it/s]
 47%|████▋     | 175523/371472 [3:03:35<16:26:23,  3.31it/s]
 47%|████▋     | 175524/371472 [3:03:35<16:25:08,  3.32it/s]
 47%|████▋     | 175525/371472 [3:03:35<16:19:30,  3.33it/s]
 47%|████▋     | 175526/371472 [3:03:36<15:56:10,  3.42it/s]
 47%|████▋     | 175527/371472 [3:03:36<16:22:39,  3.32it/s]
 47%|████▋     | 175528/371472 [3:03:36<16:31:10,  3.29it/s]
 47%|████▋     | 175529/371472 [3:03:36<16:36:34,  3.28it/s]
 47%|████▋     | 175530/371472 [3:03:37<16:06:18,  3.38it/s]
 47%|████▋     | 175531/371472 [3:03:37<15:55:50,  3.42it/s]
 47%|████▋     | 175532/371472 [3:03:37<16:11:34,  3.36it/s]
 47%|████▋     | 175533/371472 [3:03:38<16:18:43,  3.34it/s]
 47%|████▋     | 175534/371472 [3:03:38<16:37:39,  3.27it/s]
 47%|████▋     | 175535/371472 [3:03:38<16:32:14,  3.29it/s]
 47%|████▋     | 175536/371472 [3:03:39<16:17:31,  3.34it/s]
 47%|████▋     | 175537/371472 [3:03:39<17:24:51,  3.13it/s]
 47%|████▋     | 175538/371472 [3:03:39<16:45:52,  3.25it/s]
 47%|████▋     | 175539/371472 [3:03:39<16:14:44,  3.35it/s]
 47%|████▋     | 175540/371472 [3:03:40<16:22:04,  3.33it/s]
                                                            
{'loss': 2.8831, 'learning_rate': 5.749585209765347e-07, 'epoch': 7.56}
+
 47%|████▋     | 175540/371472 [3:03:40<16:22:04,  3.33it/s]
 47%|████▋     | 175541/371472 [3:03:40<16:31:15,  3.29it/s]
 47%|████▋     | 175542/371472 [3:03:40<16:12:18,  3.36it/s]
 47%|████▋     | 175543/371472 [3:03:41<16:03:23,  3.39it/s]
 47%|████▋     | 175544/371472 [3:03:41<17:11:22,  3.17it/s]
 47%|████▋     | 175545/371472 [3:03:41<17:46:28,  3.06it/s]
 47%|████▋     | 175546/371472 [3:03:42<17:31:24,  3.11it/s]
 47%|████▋     | 175547/371472 [3:03:42<17:24:46,  3.13it/s]
 47%|████▋     | 175548/371472 [3:03:42<17:22:54,  3.13it/s]
 47%|████▋     | 175549/371472 [3:03:43<16:55:59,  3.21it/s]
 47%|████▋     | 175550/371472 [3:03:43<16:22:50,  3.32it/s]
 47%|████▋     | 175551/371472 [3:03:43<16:13:52,  3.35it/s]
 47%|████▋     | 175552/371472 [3:03:43<16:07:59,  3.37it/s]
 47%|████▋     | 175553/371472 [3:03:44<15:52:40,  3.43it/s]
 47%|████▋     | 175554/371472 [3:03:44<16:33:23,  3.29it/s]
 47%|████▋     | 175555/371472 [3:03:44<16:01:03,  3.40it/s]
 47%|████▋     | 175556/371472 [3:03:45<15:57:51,  3.41it/s]
 47%|████▋     | 175557/371472 [3:03:45<16:51:56,  3.23it/s]
 47%|████▋     | 175558/371472 [3:03:45<16:47:15,  3.24it/s]
 47%|████▋     | 175559/371472 [3:03:46<17:18:57,  3.14it/s]
 47%|████▋     | 175560/371472 [3:03:46<17:31:23,  3.11it/s]
                                                            
{'loss': 2.8582, 'learning_rate': 5.749100390010557e-07, 'epoch': 7.56}
+
 47%|████▋     | 175560/371472 [3:03:46<17:31:23,  3.11it/s]
 47%|████▋     | 175561/371472 [3:03:46<17:36:08,  3.09it/s]
 47%|████▋     | 175562/371472 [3:03:47<17:10:03,  3.17it/s]
 47%|████▋     | 175563/371472 [3:03:47<16:39:01,  3.27it/s]
 47%|████▋     | 175564/371472 [3:03:47<16:37:28,  3.27it/s]
 47%|████▋     | 175565/371472 [3:03:48<16:50:05,  3.23it/s]
 47%|████▋     | 175566/371472 [3:03:48<17:08:24,  3.17it/s]
 47%|████▋     | 175567/371472 [3:03:48<17:21:47,  3.13it/s]
 47%|████▋     | 175568/371472 [3:03:49<17:37:19,  3.09it/s]
 47%|████▋     | 175569/371472 [3:03:49<17:03:42,  3.19it/s]
 47%|████▋     | 175570/371472 [3:03:49<16:32:37,  3.29it/s]
 47%|██���█▋     | 175571/371472 [3:03:49<16:01:32,  3.40it/s]
 47%|████▋     | 175572/371472 [3:03:50<16:34:54,  3.28it/s]
 47%|████▋     | 175573/371472 [3:03:50<16:53:36,  3.22it/s]
 47%|████▋     | 175574/371472 [3:03:50<16:26:06,  3.31it/s]
 47%|████▋     | 175575/371472 [3:03:51<16:37:32,  3.27it/s]
 47%|████▋     | 175576/371472 [3:03:51<16:32:44,  3.29it/s]
 47%|████▋     | 175577/371472 [3:03:51<16:25:42,  3.31it/s]
 47%|████▋     | 175578/371472 [3:03:51<16:10:48,  3.36it/s]
 47%|████▋     | 175579/371472 [3:03:52<15:59:38,  3.40it/s]
 47%|████▋     | 175580/371472 [3:03:52<15:42:15,  3.46it/s]
                                                            
{'loss': 2.7638, 'learning_rate': 5.748615570255768e-07, 'epoch': 7.56}
+
 47%|████▋     | 175580/371472 [3:03:52<15:42:15,  3.46it/s]
 47%|████▋     | 175581/371472 [3:03:52<15:38:45,  3.48it/s]
 47%|████▋     | 175582/371472 [3:03:53<15:59:41,  3.40it/s]
 47%|████▋     | 175583/371472 [3:03:53<15:45:31,  3.45it/s]
 47%|████▋     | 175584/371472 [3:03:53<15:31:47,  3.50it/s]
 47%|████▋     | 175585/371472 [3:03:53<15:27:32,  3.52it/s]
 47%|████▋     | 175586/371472 [3:03:54<15:56:25,  3.41it/s]
 47%|████▋     | 175587/371472 [3:03:54<16:08:26,  3.37it/s]
 47%|████▋     | 175588/371472 [3:03:54<15:55:00,  3.42it/s]
 47%|████▋     | 175589/371472 [3:03:55<16:37:13,  3.27it/s]
 47%|████▋     | 175590/371472 [3:03:55<16:26:29,  3.31it/s]
 47%|████▋     | 175591/371472 [3:03:55<16:13:41,  3.35it/s]
 47%|████▋     | 175592/371472 [3:03:56<15:56:32,  3.41it/s]
 47%|████▋     | 175593/371472 [3:03:56<16:20:02,  3.33it/s]
 47%|████▋     | 175594/371472 [3:03:56<16:44:08,  3.25it/s]
 47%|████▋     | 175595/371472 [3:03:57<16:32:06,  3.29it/s]
 47%|████▋     | 175596/371472 [3:03:57<16:18:11,  3.34it/s]
 47%|████▋     | 175597/371472 [3:03:57<15:57:09,  3.41it/s]
 47%|████▋     | 175598/371472 [3:03:57<17:23:32,  3.13it/s]
 47%|████▋     | 175599/371472 [3:03:58<17:02:53,  3.19it/s]
 47%|████▋     | 175600/371472 [3:03:58<17:04:29,  3.19it/s]
                                                            
{'loss': 2.9603, 'learning_rate': 5.748130750500981e-07, 'epoch': 7.56}
+
 47%|████▋     | 175600/371472 [3:03:58<17:04:29,  3.19it/s]
 47%|████▋     | 175601/371472 [3:03:58<17:01:40,  3.20it/s]
 47%|████▋     | 175602/371472 [3:03:59<16:35:31,  3.28it/s]
 47%|████▋     | 175603/371472 [3:03:59<17:01:42,  3.20it/s]
 47%|████▋     | 175604/371472 [3:03:59<16:58:34,  3.20it/s]
 47%|████▋     | 175605/371472 [3:04:00<17:09:36,  3.17it/s]
 47%|████▋     | 175606/371472 [3:04:00<16:43:19,  3.25it/s]
 47%|████▋     | 175607/371472 [3:04:00<16:12:59,  3.36it/s]
 47%|████▋     | 175608/371472 [3:04:01<16:13:52,  3.35it/s]
 47%|████▋     | 175609/371472 [3:04:01<15:59:54,  3.40it/s]
 47%|████▋     | 175610/371472 [3:04:01<15:58:23,  3.41it/s]
 47%|████▋     | 175611/371472 [3:04:01<15:28:24,  3.52it/s]
 47%|████▋     | 175612/371472 [3:04:02<15:49:11,  3.44it/s]
 47%|████▋     | 175613/371472 [3:04:02<15:48:40,  3.44it/s]
 47%|████▋     | 175614/371472 [3:04:02<15:38:42,  3.48it/s]
 47%|████▋     | 175615/371472 [3:04:03<15:32:06,  3.50it/s]
 47%|████▋     | 175616/371472 [3:04:03<16:55:56,  3.21it/s]
 47%|████▋     | 175617/371472 [3:04:03<17:10:54,  3.17it/s]
 47%|████▋     | 175618/371472 [3:04:04<17:01:12,  3.20it/s]
 47%|████▋     | 175619/371472 [3:04:04<17:28:49,  3.11it/s]
 47%|████▋     | 175620/371472 [3:04:04<17:11:14,  3.17it/s]
                                                            
{'loss': 2.8423, 'learning_rate': 5.747645930746191e-07, 'epoch': 7.56}
+
 47%|████▋     | 175620/371472 [3:04:04<17:11:14,  3.17it/s]
 47%|████▋     | 175621/371472 [3:04:05<17:39:24,  3.08it/s]
 47%|████▋     | 175622/371472 [3:04:05<17:00:17,  3.20it/s]
 47%|████▋     | 175623/371472 [3:04:05<17:51:46,  3.05it/s]
 47%|████▋     | 175624/371472 [3:04:05<16:51:39,  3.23it/s]
 47%|████▋     | 175625/371472 [3:04:06<17:56:00,  3.03it/s]
 47%|████▋     | 175626/371472 [3:04:06<17:07:03,  3.18it/s]
 47%|████▋     | 175627/371472 [3:04:06<16:35:23,  3.28it/s]
 47%|████▋     | 175628/371472 [3:04:07<17:19:20,  3.14it/s]
 47%|████▋     | 175629/371472 [3:04:07<17:27:16,  3.12it/s]
 47%|████▋     | 175630/371472 [3:04:07<17:19:33,  3.14it/s]
 47%|████▋     | 175631/371472 [3:04:08<17:06:32,  3.18it/s]
 47%|████▋     | 175632/371472 [3:04:08<16:59:12,  3.20it/s]
 47%|████▋     | 175633/371472 [3:04:08<16:36:36,  3.28it/s]
 47%|████▋     | 175634/371472 [3:04:09<16:10:30,  3.36it/s]
 47%|████▋     | 175635/371472 [3:04:09<17:17:25,  3.15it/s]
 47%|████▋     | 175636/371472 [3:04:09<16:56:53,  3.21it/s]
 47%|████▋     | 175637/371472 [3:04:10<16:55:04,  3.22it/s]
 47%|████▋     | 175638/371472 [3:04:10<16:19:53,  3.33it/s]
 47%|████▋     | 175639/371472 [3:04:10<15:44:03,  3.46it/s]
 47%|████▋     | 175640/371472 [3:04:10<15:36:41,  3.48it/s]
                                                            
{'loss': 2.85, 'learning_rate': 5.747161110991402e-07, 'epoch': 7.57}
+
 47%|████▋     | 175640/371472 [3:04:10<15:36:41,  3.48it/s]
 47%|████▋     | 175641/371472 [3:04:11<16:55:35,  3.21it/s]
 47%|████▋     | 175642/371472 [3:04:11<16:35:07,  3.28it/s]
 47%|████▋     | 175643/371472 [3:04:11<16:09:47,  3.37it/s]
 47%|████▋     | 175644/371472 [3:04:12<15:52:52,  3.43it/s]
 47%|████▋     | 175645/371472 [3:04:12<15:21:37,  3.54it/s]
 47%|████▋     | 175646/371472 [3:04:12<15:24:16,  3.53it/s]
 47%|████▋     | 175647/371472 [3:04:12<15:31:14,  3.50it/s]
 47%|████▋     | 175648/371472 [3:04:13<15:16:55,  3.56it/s]
 47%|████▋     | 175649/371472 [3:04:13<15:25:03,  3.53it/s]
 47%|████▋     | 175650/371472 [3:04:13<15:36:15,  3.49it/s]
 47%|████▋     | 175651/371472 [3:04:14<16:07:26,  3.37it/s]
 47%|████▋     | 175652/371472 [3:04:14<17:09:32,  3.17it/s]
 47%|████▋     | 175653/371472 [3:04:14<16:24:33,  3.31it/s]
 47%|████▋     | 175654/371472 [3:04:14<16:00:43,  3.40it/s]
 47%|████▋     | 175655/371472 [3:04:15<15:44:55,  3.45it/s]
 47%|████▋     | 175656/371472 [3:04:15<15:31:12,  3.50it/s]
 47%|████▋     | 175657/371472 [3:04:15<16:11:40,  3.36it/s]
 47%|████▋     | 175658/371472 [3:04:16<15:58:08,  3.41it/s]
 47%|████▋     | 175659/371472 [3:04:16<16:13:15,  3.35it/s]
 47%|████▋     | 175660/371472 [3:04:16<16:12:01,  3.36it/s]
                                                            
{'loss': 2.834, 'learning_rate': 5.746676291236613e-07, 'epoch': 7.57}
+
 47%|████▋     | 175660/371472 [3:04:16<16:12:01,  3.36it/s]
 47%|████▋     | 175661/371472 [3:04:17<16:04:19,  3.38it/s]
 47%|████▋     | 175662/371472 [3:04:17<16:23:32,  3.32it/s]
 47%|████▋     | 175663/371472 [3:04:17<17:14:55,  3.15it/s]
 47%|████▋     | 175664/371472 [3:04:17<16:43:58,  3.25it/s]
 47%|████▋     | 175665/371472 [3:04:18<16:09:39,  3.37it/s]
 47%|████▋     | 175666/371472 [3:04:18<16:06:13,  3.38it/s]
 47%|████▋     | 175667/371472 [3:04:18<15:44:13,  3.46it/s]
 47%|████▋     | 175668/371472 [3:04:19<15:44:09,  3.46it/s]
 47%|████▋     | 175669/371472 [3:04:19<15:34:57,  3.49it/s]
 47%|████▋     | 175670/371472 [3:04:19<15:38:56,  3.48it/s]
 47%|████▋     | 175671/371472 [3:04:19<16:04:39,  3.38it/s]
 47%|████▋     | 175672/371472 [3:04:20<15:58:27,  3.40it/s]
 47%|████▋     | 175673/371472 [3:04:20<16:33:17,  3.29it/s]
 47%|████▋     | 175674/371472 [3:04:20<16:23:36,  3.32it/s]
 47%|████▋     | 175675/371472 [3:04:21<16:45:31,  3.25it/s]
 47%|████▋     | 175676/371472 [3:04:21<17:09:10,  3.17it/s]
 47%|████▋     | 175677/371472 [3:04:21<16:57:10,  3.21it/s]
 47%|████▋     | 175678/371472 [3:04:22<17:10:17,  3.17it/s]
 47%|████▋     | 175679/371472 [3:04:22<16:58:52,  3.20it/s]
 47%|████▋     | 175680/371472 [3:04:22<16:35:48,  3.28it/s]
                                                            
{'loss': 2.7594, 'learning_rate': 5.746191471481823e-07, 'epoch': 7.57}
+
 47%|████▋     | 175680/371472 [3:04:22<16:35:48,  3.28it/s]
 47%|████▋     | 175681/371472 [3:04:23<16:58:54,  3.20it/s]
 47%|████▋     | 175682/371472 [3:04:23<16:50:10,  3.23it/s]
 47%|████▋     | 175683/371472 [3:04:23<16:19:23,  3.33it/s]
 47%|████▋     | 175684/371472 [3:04:23<16:07:34,  3.37it/s]
 47%|████▋     | 175685/371472 [3:04:24<16:03:01,  3.39it/s]
 47%|████▋     | 175686/371472 [3:04:24<16:35:11,  3.28it/s]
 47%|████▋     | 175687/371472 [3:04:24<16:19:27,  3.33it/s]
 47%|████▋     | 175688/371472 [3:04:25<16:04:43,  3.38it/s]
 47%|████▋     | 175689/371472 [3:04:25<15:52:08,  3.43it/s]
 47%|████▋     | 175690/371472 [3:04:25<16:06:11,  3.38it/s]
 47%|████▋     | 175691/371472 [3:04:26<15:45:30,  3.45it/s]
 47%|████▋     | 175692/371472 [3:04:26<15:47:32,  3.44it/s]
 47%|████▋     | 175693/371472 [3:04:26<15:50:45,  3.43it/s]
 47%|████▋     | 175694/371472 [3:04:26<15:31:40,  3.50it/s]
 47%|████▋     | 175695/371472 [3:04:27<16:42:17,  3.26it/s]
 47%|████▋     | 175696/371472 [3:04:27<16:39:48,  3.26it/s]
 47%|████▋     | 175697/371472 [3:04:27<16:50:41,  3.23it/s]
 47%|████▋     | 175698/371472 [3:04:28<17:00:03,  3.20it/s]
 47%|████▋     | 175699/371472 [3:04:28<16:24:46,  3.31it/s]
 47%|████▋     | 175700/371472 [3:04:28<16:04:47,  3.38it/s]
                                                            
{'loss': 2.8926, 'learning_rate': 5.745706651727036e-07, 'epoch': 7.57}
+
 47%|████▋     | 175700/371472 [3:04:28<16:04:47,  3.38it/s]
 47%|████▋     | 175701/371472 [3:04:29<15:54:52,  3.42it/s]
 47%|████▋     | 175702/371472 [3:04:29<16:09:35,  3.37it/s]
 47%|████▋     | 175703/371472 [3:04:29<15:59:00,  3.40it/s]
 47%|████▋     | 175704/371472 [3:04:29<16:14:25,  3.35it/s]
 47%|████▋     | 175705/371472 [3:04:30<16:49:11,  3.23it/s]
 47%|████▋     | 175706/371472 [3:04:30<17:57:27,  3.03it/s]
 47%|████▋     | 175707/371472 [3:04:30<17:02:43,  3.19it/s]
 47%|████▋     | 175708/371472 [3:04:31<16:50:44,  3.23it/s]
 47%|████▋     | 175709/371472 [3:04:31<16:37:50,  3.27it/s]
 47%|████▋     | 175710/371472 [3:04:31<17:42:02,  3.07it/s]
 47%|████▋     | 175711/371472 [3:04:32<17:07:27,  3.18it/s]
 47%|████▋     | 175712/371472 [3:04:32<16:45:39,  3.24it/s]
 47%|████▋     | 175713/371472 [3:04:32<16:29:46,  3.30it/s]
 47%|████▋     | 175714/371472 [3:04:33<16:33:32,  3.28it/s]
 47%|████▋     | 175715/371472 [3:04:33<16:53:16,  3.22it/s]
 47%|████▋     | 175716/371472 [3:04:33<16:19:02,  3.33it/s]
 47%|████▋     | 175717/371472 [3:04:33<16:00:17,  3.40it/s]
 47%|████▋     | 175718/371472 [3:04:34<15:47:35,  3.44it/s]
 47%|████▋     | 175719/371472 [3:04:34<15:30:57,  3.50it/s]
 47%|████▋     | 175720/371472 [3:04:34<15:24:28,  3.53it/s]
                                                            
{'loss': 3.051, 'learning_rate': 5.745221831972247e-07, 'epoch': 7.57}
+
 47%|████▋     | 175720/371472 [3:04:34<15:24:28,  3.53it/s]
 47%|████▋     | 175721/371472 [3:04:35<15:23:59,  3.53it/s]
 47%|████▋     | 175722/371472 [3:04:35<16:21:44,  3.32it/s]
 47%|████▋     | 175723/371472 [3:04:35<16:33:37,  3.28it/s]
 47%|████▋     | 175724/371472 [3:04:36<17:24:03,  3.12it/s]
 47%|████▋     | 175725/371472 [3:04:36<17:08:14,  3.17it/s]
 47%|████▋     | 175726/371472 [3:04:36<17:40:24,  3.08it/s]
 47%|████▋     | 175727/371472 [3:04:37<16:47:29,  3.24it/s]
 47%|████▋     | 175728/371472 [3:04:37<16:07:45,  3.37it/s]
 47%|████▋     | 175729/371472 [3:04:37<16:51:41,  3.22it/s]
 47%|████▋     | 175730/371472 [3:04:37<17:00:48,  3.20it/s]
 47%|████▋     | 175731/371472 [3:04:38<16:32:37,  3.29it/s]
 47%|████▋     | 175732/371472 [3:04:38<17:54:56,  3.03it/s]
 47%|████▋     | 175733/371472 [3:04:38<17:11:03,  3.16it/s]
 47%|████▋     | 175734/371472 [3:04:39<16:31:46,  3.29it/s]
 47%|████▋     | 175735/371472 [3:04:39<15:54:30,  3.42it/s]
 47%|████▋     | 175736/371472 [3:04:39<15:51:36,  3.43it/s]
 47%|████▋     | 175737/371472 [3:04:40<16:05:55,  3.38it/s]
 47%|████▋     | 175738/371472 [3:04:40<15:53:15,  3.42it/s]
 47%|████▋     | 175739/371472 [3:04:40<15:40:50,  3.47it/s]
 47%|████▋     | 175740/371472 [3:04:40<15:54:00,  3.42it/s]
                                                            
{'loss': 2.8567, 'learning_rate': 5.744737012217458e-07, 'epoch': 7.57}
+
 47%|████▋     | 175740/371472 [3:04:40<15:54:00,  3.42it/s]
 47%|████▋     | 175741/371472 [3:04:41<16:06:09,  3.38it/s]
 47%|████▋     | 175742/371472 [3:04:41<18:31:32,  2.93it/s]
 47%|████▋     | 175743/371472 [3:04:41<18:12:51,  2.98it/s]
 47%|████▋     | 175744/371472 [3:04:42<17:05:55,  3.18it/s]
 47%|████▋     | 175745/371472 [3:04:42<16:47:44,  3.24it/s]
 47%|████▋     | 175746/371472 [3:04:42<16:52:13,  3.22it/s]
 47%|████▋     | 175747/371472 [3:04:43<16:24:11,  3.31it/s]
 47%|████▋     | 175748/371472 [3:04:43<16:27:48,  3.30it/s]
 47%|████▋     | 175749/371472 [3:04:43<17:26:16,  3.12it/s]
 47%|████▋     | 175750/371472 [3:04:44<16:41:01,  3.26it/s]
 47%|████▋     | 175751/371472 [3:04:44<16:16:42,  3.34it/s]
 47%|████▋     | 175752/371472 [3:04:44<16:37:17,  3.27it/s]
 47%|████▋     | 175753/371472 [3:04:44<16:20:37,  3.33it/s]
 47%|████▋     | 175754/371472 [3:04:45<17:02:00,  3.19it/s]
 47%|████▋     | 175755/371472 [3:04:45<16:39:28,  3.26it/s]
 47%|████▋     | 175756/371472 [3:04:45<16:33:45,  3.28it/s]
 47%|████▋     | 175757/371472 [3:04:46<16:24:53,  3.31it/s]
 47%|████▋     | 175758/371472 [3:04:46<17:12:09,  3.16it/s]
 47%|████▋     | 175759/371472 [3:04:46<16:44:48,  3.25it/s]
 47%|████▋     | 175760/371472 [3:04:47<16:27:24,  3.30it/s]
                                                            
{'loss': 2.794, 'learning_rate': 5.744252192462668e-07, 'epoch': 7.57}
+
 47%|████▋     | 175760/371472 [3:04:47<16:27:24,  3.30it/s]
 47%|████▋     | 175761/371472 [3:04:47<16:47:21,  3.24it/s]
 47%|████▋     | 175762/371472 [3:04:47<16:49:39,  3.23it/s]
 47%|████▋     | 175763/371472 [3:04:48<16:51:43,  3.22it/s]
 47%|████▋     | 175764/371472 [3:04:48<16:51:41,  3.22it/s]
 47%|████▋     | 175765/371472 [3:04:48<16:29:55,  3.29it/s]
 47%|████▋     | 175766/371472 [3:04:48<16:18:33,  3.33it/s]
 47%|████▋     | 175767/371472 [3:04:49<16:00:59,  3.39it/s]
 47%|████▋     | 175768/371472 [3:04:49<16:01:00,  3.39it/s]
 47%|████▋     | 175769/371472 [3:04:49<15:55:48,  3.41it/s]
 47%|████▋     | 175770/371472 [3:04:50<16:09:37,  3.36it/s]
 47%|████▋     | 175771/371472 [3:04:50<16:29:13,  3.30it/s]
 47%|████▋     | 175772/371472 [3:04:50<16:31:37,  3.29it/s]
 47%|████▋     | 175773/371472 [3:04:51<17:19:24,  3.14it/s]
 47%|████▋     | 175774/371472 [3:04:51<17:14:36,  3.15it/s]
 47%|████▋     | 175775/371472 [3:04:51<16:31:09,  3.29it/s]
 47%|████▋     | 175776/371472 [3:04:52<16:52:21,  3.22it/s]
 47%|████▋     | 175777/371472 [3:04:52<16:17:58,  3.34it/s]
 47%|████▋     | 175778/371472 [3:04:52<16:27:55,  3.30it/s]
 47%|████▋     | 175779/371472 [3:04:52<16:04:30,  3.38it/s]
 47%|████▋     | 175780/371472 [3:04:53<16:16:21,  3.34it/s]
                                                            
{'loss': 2.9003, 'learning_rate': 5.74376737270788e-07, 'epoch': 7.57}
+
 47%|████▋     | 175780/371472 [3:04:53<16:16:21,  3.34it/s]
 47%|████▋     | 175781/371472 [3:04:53<15:58:41,  3.40it/s]
 47%|████▋     | 175782/371472 [3:04:53<15:42:38,  3.46it/s]
 47%|████▋     | 175783/371472 [3:04:54<15:42:02,  3.46it/s]
 47%|████▋     | 175784/371472 [3:04:54<15:51:48,  3.43it/s]
 47%|████▋     | 175785/371472 [3:04:54<15:45:54,  3.45it/s]
 47%|████▋     | 175786/371472 [3:04:54<15:24:41,  3.53it/s]
 47%|████▋     | 175787/371472 [3:04:55<15:09:12,  3.59it/s]
 47%|████▋     | 175788/371472 [3:04:55<15:53:19,  3.42it/s]
 47%|████▋     | 175789/371472 [3:04:55<16:31:40,  3.29it/s]
 47%|████▋     | 175790/371472 [3:04:56<16:27:52,  3.30it/s]
 47%|████▋     | 175791/371472 [3:04:56<16:15:03,  3.34it/s]
 47%|████▋     | 175792/371472 [3:04:56<16:22:25,  3.32it/s]
 47%|████▋     | 175793/371472 [3:04:56<15:55:29,  3.41it/s]
 47%|████▋     | 175794/371472 [3:04:57<15:27:24,  3.52it/s]
 47%|████▋     | 175795/371472 [3:04:57<15:07:30,  3.59it/s]
 47%|████▋     | 175796/371472 [3:04:57<15:41:04,  3.47it/s]
 47%|████▋     | 175797/371472 [3:04:58<16:55:53,  3.21it/s]
 47%|████▋     | 175798/371472 [3:04:58<16:28:38,  3.30it/s]
 47%|████▋     | 175799/371472 [3:04:58<15:55:37,  3.41it/s]
 47%|████▋     | 175800/371472 [3:04:59<16:10:58,  3.36it/s]
                                                            
{'loss': 3.0987, 'learning_rate': 5.743282552953092e-07, 'epoch': 7.57}
+
 47%|████▋     | 175800/371472 [3:04:59<16:10:58,  3.36it/s]
 47%|████▋     | 175801/371472 [3:04:59<15:52:15,  3.42it/s]
 47%|████▋     | 175802/371472 [3:04:59<16:35:38,  3.28it/s]
 47%|████▋     | 175803/371472 [3:04:59<16:16:18,  3.34it/s]
 47%|████▋     | 175804/371472 [3:05:00<16:48:28,  3.23it/s]
 47%|████▋     | 175805/371472 [3:05:00<16:44:30,  3.25it/s]
 47%|████▋     | 175806/371472 [3:05:00<17:07:58,  3.17it/s]
 47%|████▋     | 175807/371472 [3:05:01<16:40:08,  3.26it/s]
 47%|████▋     | 175808/371472 [3:05:01<15:54:21,  3.42it/s]
 47%|████▋     | 175809/371472 [3:05:01<15:37:05,  3.48it/s]
 47%|████▋     | 175810/371472 [3:05:02<15:21:09,  3.54it/s]
 47%|████▋     | 175811/371472 [3:05:02<15:11:30,  3.58it/s]
 47%|████▋     | 175812/371472 [3:05:02<15:31:48,  3.50it/s]
 47%|████▋     | 175813/371472 [3:05:02<16:12:25,  3.35it/s]
 47%|████▋     | 175814/371472 [3:05:03<16:23:36,  3.32it/s]
 47%|████▋     | 175815/371472 [3:05:03<17:43:38,  3.07it/s]
 47%|████▋     | 175816/371472 [3:05:03<17:32:53,  3.10it/s]
 47%|████▋     | 175817/371472 [3:05:04<18:43:46,  2.90it/s]
 47%|████▋     | 175818/371472 [3:05:04<17:48:39,  3.05it/s]
 47%|████▋     | 175819/371472 [3:05:04<17:31:42,  3.10it/s]
 47%|████▋     | 175820/371472 [3:05:05<17:22:56,  3.13it/s]
                                                            
{'loss': 2.7817, 'learning_rate': 5.742797733198301e-07, 'epoch': 7.57}
+
 47%|████▋     | 175820/371472 [3:05:05<17:22:56,  3.13it/s]
 47%|████▋     | 175821/371472 [3:05:05<17:14:37,  3.15it/s]
 47%|████▋     | 175822/371472 [3:05:05<17:10:07,  3.17it/s]
 47%|████▋     | 175823/371472 [3:05:06<16:38:23,  3.27it/s]
 47%|████▋     | 175824/371472 [3:05:06<16:03:47,  3.38it/s]
 47%|████▋     | 175825/371472 [3:05:06<15:53:38,  3.42it/s]
 47%|████▋     | 175826/371472 [3:05:06<15:49:45,  3.43it/s]
 47%|████▋     | 175827/371472 [3:05:07<15:57:25,  3.41it/s]
 47%|████▋     | 175828/371472 [3:05:07<16:29:21,  3.30it/s]
 47%|████▋     | 175829/371472 [3:05:07<16:48:44,  3.23it/s]
 47%|████▋     | 175830/371472 [3:05:08<16:33:35,  3.28it/s]
 47%|████▋     | 175831/371472 [3:05:08<16:25:52,  3.31it/s]
 47%|████▋     | 175832/371472 [3:05:08<16:50:43,  3.23it/s]
 47%|████▋     | 175833/371472 [3:05:09<16:16:43,  3.34it/s]
 47%|████▋     | 175834/371472 [3:05:09<16:03:08,  3.39it/s]
 47%|████▋     | 175835/371472 [3:05:09<15:47:15,  3.44it/s]
 47%|████▋     | 175836/371472 [3:05:09<16:03:23,  3.38it/s]
 47%|████▋     | 175837/371472 [3:05:10<16:45:43,  3.24it/s]
 47%|████▋     | 175838/371472 [3:05:10<16:22:23,  3.32it/s]
 47%|████▋     | 175839/371472 [3:05:10<16:22:32,  3.32it/s]
 47%|████▋     | 175840/371472 [3:05:11<16:10:46,  3.36it/s]
                                                            
{'loss': 2.8617, 'learning_rate': 5.742312913443513e-07, 'epoch': 7.57}
+
 47%|████▋     | 175840/371472 [3:05:11<16:10:46,  3.36it/s]
 47%|████▋     | 175841/371472 [3:05:11<15:57:16,  3.41it/s]
 47%|████▋     | 175842/371472 [3:05:11<16:00:38,  3.39it/s]
 47%|████▋     | 175843/371472 [3:05:12<15:42:59,  3.46it/s]
 47%|████▋     | 175844/371472 [3:05:12<15:47:10,  3.44it/s]
 47%|████▋     | 175845/371472 [3:05:12<15:26:38,  3.52it/s]
 47%|████▋     | 175846/371472 [3:05:12<15:09:15,  3.59it/s]
 47%|████▋     | 175847/371472 [3:05:13<15:23:21,  3.53it/s]
 47%|████▋     | 175848/371472 [3:05:13<15:21:52,  3.54it/s]
 47%|████▋     | 175849/371472 [3:05:13<15:19:22,  3.55it/s]
 47%|████▋     | 175850/371472 [3:05:14<15:18:05,  3.55it/s]
 47%|████▋     | 175851/371472 [3:05:14<15:23:04,  3.53it/s]
 47%|████▋     | 175852/371472 [3:05:14<16:11:41,  3.36it/s]
 47%|████▋     | 175853/371472 [3:05:14<15:39:53,  3.47it/s]
 47%|████▋     | 175854/371472 [3:05:15<16:32:54,  3.28it/s]
 47%|████▋     | 175855/371472 [3:05:15<16:07:20,  3.37it/s]
 47%|████▋     | 175856/371472 [3:05:15<15:47:29,  3.44it/s]
 47%|████▋     | 175857/371472 [3:05:16<16:16:59,  3.34it/s]
 47%|████▋     | 175858/371472 [3:05:16<17:53:41,  3.04it/s]
 47%|████▋     | 175859/371472 [3:05:16<17:00:30,  3.19it/s]
 47%|████▋     | 175860/371472 [3:05:17<16:35:53,  3.27it/s]
                                                            
{'loss': 3.0271, 'learning_rate': 5.741828093688724e-07, 'epoch': 7.57}
+
 47%|████▋     | 175860/371472 [3:05:17<16:35:53,  3.27it/s]
 47%|████▋     | 175861/371472 [3:05:17<17:26:20,  3.12it/s]
 47%|████▋     | 175862/371472 [3:05:17<16:57:41,  3.20it/s]
 47%|████▋     | 175863/371472 [3:05:18<16:48:13,  3.23it/s]
 47%|████▋     | 175864/371472 [3:05:18<16:54:50,  3.21it/s]
 47%|████▋     | 175865/371472 [3:05:18<16:45:15,  3.24it/s]
 47%|████▋     | 175866/371472 [3:05:18<16:04:03,  3.38it/s]
 47%|████▋     | 175867/371472 [3:05:19<16:36:21,  3.27it/s]
 47%|████▋     | 175868/371472 [3:05:19<16:10:25,  3.36it/s]
 47%|████▋     | 175869/371472 [3:05:19<16:03:47,  3.38it/s]
 47%|████▋     | 175870/371472 [3:05:20<16:00:34,  3.39it/s]
 47%|████▋     | 175871/371472 [3:05:20<15:59:00,  3.40it/s]
 47%|████▋     | 175872/371472 [3:05:20<15:57:46,  3.40it/s]
 47%|████▋     | 175873/371472 [3:05:21<16:02:48,  3.39it/s]
 47%|████▋     | 175874/371472 [3:05:21<16:12:18,  3.35it/s]
 47%|████▋     | 175875/371472 [3:05:21<15:59:09,  3.40it/s]
 47%|████▋     | 175876/371472 [3:05:21<16:44:31,  3.25it/s]
 47%|████▋     | 175877/371472 [3:05:22<16:23:18,  3.32it/s]
 47%|████▋     | 175878/371472 [3:05:22<16:27:33,  3.30it/s]
 47%|████▋     | 175879/371472 [3:05:22<16:07:45,  3.37it/s]
 47%|████▋     | 175880/371472 [3:05:23<16:30:42,  3.29it/s]
                                                            
{'loss': 2.9359, 'learning_rate': 5.741343273933935e-07, 'epoch': 7.58}
+
 47%|████▋     | 175880/371472 [3:05:23<16:30:42,  3.29it/s]
 47%|████▋     | 175881/371472 [3:05:23<16:35:07,  3.28it/s]
 47%|████▋     | 175882/371472 [3:05:23<16:17:35,  3.33it/s]
 47%|████▋     | 175883/371472 [3:05:24<16:23:48,  3.31it/s]
 47%|████▋     | 175884/371472 [3:05:24<16:12:41,  3.35it/s]
 47%|████▋     | 175885/371472 [3:05:24<16:21:51,  3.32it/s]
 47%|████▋     | 175886/371472 [3:05:24<16:10:22,  3.36it/s]
 47%|████▋     | 175887/371472 [3:05:25<16:08:12,  3.37it/s]
 47%|████▋     | 175888/371472 [3:05:25<16:32:48,  3.28it/s]
 47%|████▋     | 175889/371472 [3:05:25<16:35:33,  3.27it/s]
 47%|████▋     | 175890/371472 [3:05:26<17:06:08,  3.18it/s]
 47%|████▋     | 175891/371472 [3:05:26<17:11:57,  3.16it/s]
 47%|████▋     | 175892/371472 [3:05:26<17:09:30,  3.17it/s]
 47%|████▋     | 175893/371472 [3:05:27<16:50:00,  3.23it/s]
 47%|████▋     | 175894/371472 [3:05:27<16:26:31,  3.30it/s]
 47%|████▋     | 175895/371472 [3:05:27<16:18:33,  3.33it/s]
 47%|████▋     | 175896/371472 [3:05:27<16:22:39,  3.32it/s]
 47%|████▋     | 175897/371472 [3:05:28<16:10:55,  3.36it/s]
 47%|████▋     | 175898/371472 [3:05:28<16:47:10,  3.24it/s]
 47%|████▋     | 175899/371472 [3:05:28<17:08:00,  3.17it/s]
 47%|████▋     | 175900/371472 [3:05:29<17:15:24,  3.15it/s]
                                                            
{'loss': 2.7748, 'learning_rate': 5.740858454179146e-07, 'epoch': 7.58}
+
 47%|████▋     | 175900/371472 [3:05:29<17:15:24,  3.15it/s]
 47%|████▋     | 175901/371472 [3:05:29<17:11:53,  3.16it/s]
 47%|████▋     | 175902/371472 [3:05:29<17:16:21,  3.15it/s]
 47%|████▋     | 175903/371472 [3:05:30<17:16:14,  3.15it/s]
 47%|████▋     | 175904/371472 [3:05:30<16:58:36,  3.20it/s]
 47%|████▋     | 175905/371472 [3:05:30<16:28:27,  3.30it/s]
 47%|████▋     | 175906/371472 [3:05:31<16:22:38,  3.32it/s]
 47%|████▋     | 175907/371472 [3:05:31<15:38:20,  3.47it/s]
 47%|████▋     | 175908/371472 [3:05:31<16:39:10,  3.26it/s]
 47%|████▋     | 175909/371472 [3:05:32<16:36:03,  3.27it/s]
 47%|████▋     | 175910/371472 [3:05:32<16:37:18,  3.27it/s]
 47%|████▋     | 175911/371472 [3:05:32<16:36:47,  3.27it/s]
 47%|████▋     | 175912/371472 [3:05:32<16:30:29,  3.29it/s]
 47%|████▋     | 175913/371472 [3:05:33<17:06:26,  3.18it/s]
 47%|████▋     | 175914/371472 [3:05:33<16:36:41,  3.27it/s]
 47%|████▋     | 175915/371472 [3:05:33<16:01:37,  3.39it/s]
 47%|████▋     | 175916/371472 [3:05:34<15:47:03,  3.44it/s]
 47%|████▋     | 175917/371472 [3:05:34<16:51:17,  3.22it/s]
 47%|████▋     | 175918/371472 [3:05:34<19:08:34,  2.84it/s]
 47%|████▋     | 175919/371472 [3:05:35<18:12:44,  2.98it/s]
 47%|████▋     | 175920/371472 [3:05:35<17:54:08,  3.03it/s]
                                                            
{'loss': 2.7792, 'learning_rate': 5.740373634424357e-07, 'epoch': 7.58}
+
 47%|████▋     | 175920/371472 [3:05:35<17:54:08,  3.03it/s]
 47%|████▋     | 175921/371472 [3:05:35<17:50:04,  3.05it/s]
 47%|████▋     | 175922/371472 [3:05:36<17:12:46,  3.16it/s]
 47%|████▋     | 175923/371472 [3:05:36<17:07:41,  3.17it/s]
 47%|████▋     | 175924/371472 [3:05:36<17:32:41,  3.10it/s]
 47%|████▋     | 175925/371472 [3:05:37<16:43:19,  3.25it/s]
 47%|████▋     | 175926/371472 [3:05:37<17:31:43,  3.10it/s]
 47%|████▋     | 175927/371472 [3:05:37<17:04:11,  3.18it/s]
 47%|████▋     | 175928/371472 [3:05:38<17:28:01,  3.11it/s]
 47%|████▋     | 175929/371472 [3:05:38<16:50:49,  3.22it/s]
 47%|████▋     | 175930/371472 [3:05:38<16:57:18,  3.20it/s]
 47%|████▋     | 175931/371472 [3:05:38<16:20:14,  3.32it/s]
 47%|████▋     | 175932/371472 [3:05:39<16:23:05,  3.32it/s]
 47%|████▋     | 175933/371472 [3:05:39<16:12:50,  3.35it/s]
 47%|████▋     | 175934/371472 [3:05:39<16:06:45,  3.37it/s]
 47%|████▋     | 175935/371472 [3:05:40<16:08:30,  3.36it/s]
 47%|████▋     | 175936/371472 [3:05:40<15:57:38,  3.40it/s]
 47%|████▋     | 175937/371472 [3:05:40<15:52:44,  3.42it/s]
 47%|████▋     | 175938/371472 [3:05:41<17:51:32,  3.04it/s]
 47%|████▋     | 175939/371472 [3:05:41<17:01:20,  3.19it/s]
 47%|████▋     | 175940/371472 [3:05:41<16:59:31,  3.20it/s]
                                                            
{'loss': 2.7557, 'learning_rate': 5.739888814669569e-07, 'epoch': 7.58}
+
 47%|████▋     | 175940/371472 [3:05:41<16:59:31,  3.20it/s]
 47%|████▋     | 175941/371472 [3:05:42<17:09:13,  3.17it/s]
 47%|████▋     | 175942/371472 [3:05:42<17:05:30,  3.18it/s]
 47%|████▋     | 175943/371472 [3:05:42<17:11:34,  3.16it/s]
 47%|████▋     | 175944/371472 [3:05:42<16:54:11,  3.21it/s]
 47%|████▋     | 175945/371472 [3:05:43<16:03:36,  3.38it/s]
 47%|████▋     | 175946/371472 [3:05:43<16:10:06,  3.36it/s]
 47%|████▋     | 175947/371472 [3:05:43<16:00:04,  3.39it/s]
 47%|████▋     | 175948/371472 [3:05:44<15:56:31,  3.41it/s]
 47%|████▋     | 175949/371472 [3:05:44<16:02:52,  3.38it/s]
 47%|████▋     | 175950/371472 [3:05:44<15:55:11,  3.41it/s]
 47%|████▋     | 175951/371472 [3:05:44<16:06:55,  3.37it/s]
 47%|████▋     | 175952/371472 [3:05:45<16:02:43,  3.38it/s]
 47%|████▋     | 175953/371472 [3:05:45<16:00:58,  3.39it/s]
 47%|████▋     | 175954/371472 [3:05:45<16:01:44,  3.39it/s]
 47%|████▋     | 175955/371472 [3:05:46<15:53:59,  3.42it/s]
 47%|████▋     | 175956/371472 [3:05:46<15:26:23,  3.52it/s]
 47%|████▋     | 175957/371472 [3:05:46<15:36:22,  3.48it/s]
 47%|████▋     | 175958/371472 [3:05:46<15:37:43,  3.47it/s]
 47%|████▋     | 175959/371472 [3:05:47<15:41:11,  3.46it/s]
 47%|████▋     | 175960/371472 [3:05:47<15:21:22,  3.54it/s]
                                                            
{'loss': 2.8995, 'learning_rate': 5.73940399491478e-07, 'epoch': 7.58}
+
 47%|████▋     | 175960/371472 [3:05:47<15:21:22,  3.54it/s]
 47%|████▋     | 175961/371472 [3:05:47<15:34:38,  3.49it/s]
 47%|████▋     | 175962/371472 [3:05:48<16:44:23,  3.24it/s]
 47%|████▋     | 175963/371472 [3:05:48<16:16:27,  3.34it/s]
 47%|████▋     | 175964/371472 [3:05:48<16:59:27,  3.20it/s]
 47%|████▋     | 175965/371472 [3:05:49<16:42:40,  3.25it/s]
 47%|████▋     | 175966/371472 [3:05:49<16:26:51,  3.30it/s]
 47%|████▋     | 175967/371472 [3:05:49<16:09:41,  3.36it/s]
 47%|████▋     | 175968/371472 [3:05:50<16:25:55,  3.30it/s]
 47%|████▋     | 175969/371472 [3:05:50<15:58:33,  3.40it/s]
 47%|████▋     | 175970/371472 [3:05:50<16:09:31,  3.36it/s]
 47%|████▋     | 175971/371472 [3:05:50<15:31:58,  3.50it/s]
 47%|████▋     | 175972/371472 [3:05:51<17:03:40,  3.18it/s]
 47%|████▋     | 175973/371472 [3:05:51<16:26:02,  3.30it/s]
 47%|████▋     | 175974/371472 [3:05:51<16:29:41,  3.29it/s]
 47%|████▋     | 175975/371472 [3:05:52<16:01:24,  3.39it/s]
 47%|████▋     | 175976/371472 [3:05:52<15:44:42,  3.45it/s]
 47%|████▋     | 175977/371472 [3:05:52<15:48:22,  3.44it/s]
 47%|████▋     | 175978/371472 [3:05:52<15:54:22,  3.41it/s]
 47%|████▋     | 175979/371472 [3:05:53<15:48:26,  3.44it/s]
 47%|████▋     | 175980/371472 [3:05:53<15:55:07,  3.41it/s]
                                                            
{'loss': 3.0177, 'learning_rate': 5.738919175159991e-07, 'epoch': 7.58}
+
 47%|████▋     | 175980/371472 [3:05:53<15:55:07,  3.41it/s]
 47%|████▋     | 175981/371472 [3:05:53<16:18:39,  3.33it/s]
 47%|████▋     | 175982/371472 [3:05:54<16:28:01,  3.30it/s]
 47%|████▋     | 175983/371472 [3:05:54<16:03:25,  3.38it/s]
 47%|████▋     | 175984/371472 [3:05:54<15:56:31,  3.41it/s]
 47%|████▋     | 175985/371472 [3:05:55<16:12:02,  3.35it/s]
 47%|████▋     | 175986/371472 [3:05:55<17:08:41,  3.17it/s]
 47%|████▋     | 175987/371472 [3:05:55<16:37:05,  3.27it/s]
 47%|████▋     | 175988/371472 [3:05:55<16:27:40,  3.30it/s]
 47%|████▋     | 175989/371472 [3:05:56<17:01:38,  3.19it/s]
 47%|████▋     | 175990/371472 [3:05:56<16:31:36,  3.29it/s]
 47%|████▋     | 175991/371472 [3:05:56<16:26:40,  3.30it/s]
 47%|████▋     | 175992/371472 [3:05:57<16:25:51,  3.30it/s]
 47%|████▋     | 175993/371472 [3:05:57<16:00:44,  3.39it/s]
 47%|████▋     | 175994/371472 [3:05:57<15:59:29,  3.40it/s]
 47%|████▋     | 175995/371472 [3:05:58<16:50:00,  3.23it/s]
 47%|████▋     | 175996/371472 [3:05:58<17:01:35,  3.19it/s]
 47%|████▋     | 175997/371472 [3:05:58<16:27:33,  3.30it/s]
 47%|████▋     | 175998/371472 [3:05:59<16:46:11,  3.24it/s]
 47%|████▋     | 175999/371472 [3:05:59<16:10:48,  3.36it/s]
 47%|████▋     | 176000/371472 [3:05:59<15:58:02,  3.40it/s]
                                                            
{'loss': 2.9495, 'learning_rate': 5.738434355405201e-07, 'epoch': 7.58}
+
 47%|████▋     | 176000/371472 [3:05:59<15:58:02,  3.40it/s]
 47%|████▋     | 176001/371472 [3:05:59<15:49:08,  3.43it/s]
 47%|████▋     | 176002/371472 [3:06:00<15:59:25,  3.40it/s]
 47%|████▋     | 176003/371472 [3:06:00<16:12:04,  3.35it/s]
 47%|████▋     | 176004/371472 [3:06:00<16:47:16,  3.23it/s]
 47%|████▋     | 176005/371472 [3:06:01<18:53:46,  2.87it/s]
 47%|████▋     | 176006/371472 [3:06:01<18:31:53,  2.93it/s]
 47%|████▋     | 176007/371472 [3:06:01<17:29:09,  3.11it/s]
 47%|████▋     | 176008/371472 [3:06:02<16:56:09,  3.21it/s]
 47%|████▋     | 176009/371472 [3:06:02<16:20:31,  3.32it/s]
 47%|████▋     | 176010/371472 [3:06:02<16:16:36,  3.34it/s]
 47%|████▋     | 176011/371472 [3:06:03<15:42:39,  3.46it/s]
 47%|███��▋     | 176012/371472 [3:06:03<15:28:54,  3.51it/s]
 47%|████▋     | 176013/371472 [3:06:03<16:36:08,  3.27it/s]
 47%|████▋     | 176014/371472 [3:06:03<16:26:16,  3.30it/s]
 47%|████▋     | 176015/371472 [3:06:04<17:29:49,  3.10it/s]
 47%|████▋     | 176016/371472 [3:06:04<17:09:28,  3.16it/s]
 47%|████▋     | 176017/371472 [3:06:04<17:27:43,  3.11it/s]
 47%|████▋     | 176018/371472 [3:06:05<16:42:51,  3.25it/s]
 47%|████▋     | 176019/371472 [3:06:05<16:18:33,  3.33it/s]
 47%|████▋     | 176020/371472 [3:06:05<16:58:03,  3.20it/s]
                                                            
{'loss': 3.1058, 'learning_rate': 5.737949535650413e-07, 'epoch': 7.58}
+
 47%|████▋     | 176020/371472 [3:06:05<16:58:03,  3.20it/s]
 47%|████▋     | 176021/371472 [3:06:06<16:31:36,  3.29it/s]
 47%|████▋     | 176022/371472 [3:06:06<17:04:18,  3.18it/s]
 47%|████▋     | 176023/371472 [3:06:06<16:51:53,  3.22it/s]
 47%|████▋     | 176024/371472 [3:06:07<16:21:47,  3.32it/s]
 47%|████▋     | 176025/371472 [3:06:07<15:46:12,  3.44it/s]
 47%|████▋     | 176026/371472 [3:06:07<15:49:50,  3.43it/s]
 47%|████▋     | 176027/371472 [3:06:07<16:17:35,  3.33it/s]
 47%|████▋     | 176028/371472 [3:06:08<15:48:10,  3.44it/s]
 47%|████▋     | 176029/371472 [3:06:08<16:53:11,  3.21it/s]
 47%|████▋     | 176030/371472 [3:06:08<16:49:00,  3.23it/s]
 47%|████▋     | 176031/371472 [3:06:09<16:54:22,  3.21it/s]
 47%|████▋     | 176032/371472 [3:06:09<16:17:22,  3.33it/s]
 47%|████▋     | 176033/371472 [3:06:09<17:49:25,  3.05it/s]
 47%|████▋     | 176034/371472 [3:06:10<18:35:17,  2.92it/s]
 47%|████▋     | 176035/371472 [3:06:10<19:35:01,  2.77it/s]
 47%|████▋     | 176036/371472 [3:06:10<19:39:39,  2.76it/s]
 47%|████▋     | 176037/371472 [3:06:11<19:38:56,  2.76it/s]
 47%|████▋     | 176038/371472 [3:06:11<18:27:37,  2.94it/s]
 47%|████▋     | 176039/371472 [3:06:12<19:01:17,  2.85it/s]
 47%|████▋     | 176040/371472 [3:06:12<18:47:36,  2.89it/s]
                                                            
{'loss': 2.9547, 'learning_rate': 5.737464715895624e-07, 'epoch': 7.58}
+
 47%|████▋     | 176040/371472 [3:06:12<18:47:36,  2.89it/s]
 47%|████▋     | 176041/371472 [3:06:12<18:00:07,  3.02it/s]
 47%|████▋     | 176042/371472 [3:06:12<18:03:19,  3.01it/s]
 47%|████▋     | 176043/371472 [3:06:13<17:37:51,  3.08it/s]
 47%|████▋     | 176044/371472 [3:06:13<17:30:59,  3.10it/s]
 47%|████▋     | 176045/371472 [3:06:13<17:01:29,  3.19it/s]
 47%|████▋     | 176046/371472 [3:06:14<16:40:26,  3.26it/s]
 47%|████▋     | 176047/371472 [3:06:14<16:07:40,  3.37it/s]
 47%|████▋     | 176048/371472 [3:06:14<16:01:47,  3.39it/s]
 47%|████▋     | 176049/371472 [3:06:15<16:54:23,  3.21it/s]
 47%|████▋     | 176050/371472 [3:06:15<16:25:02,  3.31it/s]
 47%|████▋     | 176051/371472 [3:06:15<16:26:31,  3.30it/s]
 47%|████▋     | 176052/371472 [3:06:15<15:58:43,  3.40it/s]
 47%|████▋     | 176053/371472 [3:06:16<16:10:56,  3.35it/s]
 47%|████▋     | 176054/371472 [3:06:16<16:38:30,  3.26it/s]
 47%|████▋     | 176055/371472 [3:06:16<16:19:12,  3.33it/s]
 47%|████▋     | 176056/371472 [3:06:17<17:41:44,  3.07it/s]
 47%|████▋     | 176057/371472 [3:06:17<16:54:05,  3.21it/s]
 47%|████▋     | 176058/371472 [3:06:17<16:49:32,  3.23it/s]
 47%|████▋     | 176059/371472 [3:06:18<16:16:25,  3.34it/s]
 47%|████▋     | 176060/371472 [3:06:18<15:39:11,  3.47it/s]
                                                            
{'loss': 2.9434, 'learning_rate': 5.736979896140834e-07, 'epoch': 7.58}
+
 47%|████▋     | 176060/371472 [3:06:18<15:39:11,  3.47it/s]
 47%|████▋     | 176061/371472 [3:06:18<15:53:44,  3.41it/s]
 47%|████▋     | 176062/371472 [3:06:18<15:44:39,  3.45it/s]
 47%|████▋     | 176063/371472 [3:06:19<15:36:15,  3.48it/s]
 47%|████▋     | 176064/371472 [3:06:19<15:36:07,  3.48it/s]
 47%|████▋     | 176065/371472 [3:06:19<15:51:37,  3.42it/s]
 47%|████▋     | 176066/371472 [3:06:20<15:38:23,  3.47it/s]
 47%|████▋     | 176067/371472 [3:06:20<15:58:45,  3.40it/s]
 47%|████▋     | 176068/371472 [3:06:20<16:35:43,  3.27it/s]
 47%|████▋     | 176069/371472 [3:06:21<16:45:40,  3.24it/s]
 47%|████▋     | 176070/371472 [3:06:21<16:34:49,  3.27it/s]
 47%|████▋     | 176071/371472 [3:06:21<16:46:29,  3.24it/s]
 47%|████▋     | 176072/371472 [3:06:22<17:16:23,  3.14it/s]
 47%|████▋     | 176073/371472 [3:06:22<17:08:13,  3.17it/s]
 47%|████▋     | 176074/371472 [3:06:22<17:14:10,  3.15it/s]
 47%|████▋     | 176075/371472 [3:06:22<17:33:37,  3.09it/s]
 47%|████▋     | 176076/371472 [3:06:23<16:38:06,  3.26it/s]
 47%|████▋     | 176077/371472 [3:06:23<16:15:20,  3.34it/s]
 47%|████▋     | 176078/371472 [3:06:23<16:05:27,  3.37it/s]
 47%|████▋     | 176079/371472 [3:06:24<15:55:20,  3.41it/s]
 47%|████▋     | 176080/371472 [3:06:24<15:47:46,  3.44it/s]
                                                            
{'loss': 2.9938, 'learning_rate': 5.736495076386046e-07, 'epoch': 7.58}
+
 47%|████▋     | 176080/371472 [3:06:24<15:47:46,  3.44it/s]
 47%|████▋     | 176081/371472 [3:06:24<15:49:16,  3.43it/s]
 47%|████▋     | 176082/371472 [3:06:24<15:42:48,  3.45it/s]
 47%|████▋     | 176083/371472 [3:06:25<16:08:36,  3.36it/s]
 47%|████▋     | 176084/371472 [3:06:25<16:40:32,  3.25it/s]
 47%|████▋     | 176085/371472 [3:06:25<16:23:38,  3.31it/s]
 47%|████▋     | 176086/371472 [3:06:26<16:52:40,  3.22it/s]
 47%|████▋     | 176087/371472 [3:06:26<16:40:20,  3.26it/s]
 47%|████▋     | 176088/371472 [3:06:26<16:15:56,  3.34it/s]
 47%|████▋     | 176089/371472 [3:06:27<16:18:01,  3.33it/s]
 47%|████▋     | 176090/371472 [3:06:27<16:12:00,  3.35it/s]
 47%|████▋     | 176091/371472 [3:06:27<15:58:50,  3.40it/s]
 47%|████▋     | 176092/371472 [3:06:28<16:20:08,  3.32it/s]
 47%|████▋     | 176093/371472 [3:06:28<16:09:06,  3.36it/s]
 47%|████▋     | 176094/371472 [3:06:28<16:05:05,  3.37it/s]
 47%|████▋     | 176095/371472 [3:06:28<17:02:19,  3.19it/s]
 47%|████▋     | 176096/371472 [3:06:29<16:45:15,  3.24it/s]
 47%|████▋     | 176097/371472 [3:06:29<16:30:36,  3.29it/s]
 47%|████▋     | 176098/371472 [3:06:29<16:15:21,  3.34it/s]
 47%|████▋     | 176099/371472 [3:06:30<16:02:04,  3.38it/s]
 47%|████▋     | 176100/371472 [3:06:30<15:55:40,  3.41it/s]
                                                            
{'loss': 2.8392, 'learning_rate': 5.736010256631257e-07, 'epoch': 7.58}
+
 47%|████▋     | 176100/371472 [3:06:30<15:55:40,  3.41it/s]
 47%|████▋     | 176101/371472 [3:06:30<17:36:13,  3.08it/s]
 47%|████▋     | 176102/371472 [3:06:31<17:05:23,  3.18it/s]
 47%|████▋     | 176103/371472 [3:06:31<16:35:13,  3.27it/s]
 47%|████▋     | 176104/371472 [3:06:31<16:12:22,  3.35it/s]
 47%|████▋     | 176105/371472 [3:06:31<15:43:24,  3.45it/s]
 47%|████▋     | 176106/371472 [3:06:32<15:57:42,  3.40it/s]
 47%|████▋     | 176107/371472 [3:06:32<15:58:22,  3.40it/s]
 47%|████▋     | 176108/371472 [3:06:32<15:54:51,  3.41it/s]
 47%|████▋     | 176109/371472 [3:06:33<15:46:05,  3.44it/s]
 47%|████▋     | 176110/371472 [3:06:33<16:21:55,  3.32it/s]
 47%|████▋     | 176111/371472 [3:06:33<16:58:25,  3.20it/s]
 47%|████▋     | 176112/371472 [3:06:34<16:30:33,  3.29it/s]
 47%|████▋     | 176113/371472 [3:06:34<16:06:28,  3.37it/s]
 47%|████▋     | 176114/371472 [3:06:34<15:55:01,  3.41it/s]
 47%|████▋     | 176115/371472 [3:06:35<18:08:01,  2.99it/s]
 47%|████▋     | 176116/371472 [3:06:35<17:03:50,  3.18it/s]
 47%|████▋     | 176117/371472 [3:06:35<16:46:56,  3.23it/s]
 47%|████▋     | 176118/371472 [3:06:35<17:32:39,  3.09it/s]
 47%|████▋     | 176119/371472 [3:06:36<16:43:20,  3.25it/s]
 47%|████▋     | 176120/371472 [3:06:36<17:10:22,  3.16it/s]
                                                            
{'loss': 2.8956, 'learning_rate': 5.735525436876468e-07, 'epoch': 7.59}
+
 47%|████▋     | 176120/371472 [3:06:36<17:10:22,  3.16it/s]
 47%|████▋     | 176121/371472 [3:06:36<17:02:26,  3.18it/s]
 47%|████▋     | 176122/371472 [3:06:37<16:55:03,  3.21it/s]
 47%|████▋     | 176123/371472 [3:06:37<16:42:12,  3.25it/s]
 47%|████▋     | 176124/371472 [3:06:37<17:32:13,  3.09it/s]
 47%|████▋     | 176125/371472 [3:06:38<17:09:10,  3.16it/s]
 47%|████▋     | 176126/371472 [3:06:38<16:52:37,  3.22it/s]
 47%|████▋     | 176127/371472 [3:06:38<17:07:27,  3.17it/s]
 47%|████▋     | 176128/371472 [3:06:39<16:59:19,  3.19it/s]
 47%|████▋     | 176129/371472 [3:06:39<16:33:24,  3.28it/s]
 47%|████▋     | 176130/371472 [3:06:39<16:32:58,  3.28it/s]
 47%|████▋     | 176131/371472 [3:06:39<16:22:13,  3.31it/s]
 47%|████▋     | 176132/371472 [3:06:40<16:27:10,  3.30it/s]
 47%|████▋     | 176133/371472 [3:06:40<16:11:50,  3.35it/s]
 47%|████▋     | 176134/371472 [3:06:40<16:11:08,  3.35it/s]
 47%|████▋     | 176135/371472 [3:06:41<16:57:52,  3.20it/s]
 47%|████▋     | 176136/371472 [3:06:41<17:15:31,  3.14it/s]
 47%|████▋     | 176137/371472 [3:06:41<17:10:28,  3.16it/s]
 47%|████▋     | 176138/371472 [3:06:42<16:49:27,  3.23it/s]
 47%|████▋     | 176139/371472 [3:06:42<16:32:09,  3.28it/s]
 47%|████▋     | 176140/371472 [3:06:42<16:18:00,  3.33it/s]
                                                            
{'loss': 2.7263, 'learning_rate': 5.735040617121678e-07, 'epoch': 7.59}
+
 47%|████▋     | 176140/371472 [3:06:42<16:18:00,  3.33it/s]
 47%|████▋     | 176141/371472 [3:06:43<16:33:38,  3.28it/s]
 47%|████▋     | 176142/371472 [3:06:43<16:31:23,  3.28it/s]
 47%|████▋     | 176143/371472 [3:06:43<17:38:14,  3.08it/s]
 47%|████▋     | 176144/371472 [3:06:44<17:45:08,  3.06it/s]
 47%|████▋     | 176145/371472 [3:06:44<18:03:35,  3.00it/s]
 47%|████▋     | 176146/371472 [3:06:44<18:28:56,  2.94it/s]
 47%|████▋     | 176147/371472 [3:06:45<18:01:13,  3.01it/s]
 47%|████▋     | 176148/371472 [3:06:45<17:37:55,  3.08it/s]
 47%|████▋     | 176149/371472 [3:06:45<17:08:03,  3.17it/s]
 47%|████▋     | 176150/371472 [3:06:45<16:47:51,  3.23it/s]
 47%|████▋     | 176151/371472 [3:06:46<16:32:43,  3.28it/s]
 47%|████▋     | 176152/371472 [3:06:46<16:52:55,  3.21it/s]
 47%|████▋     | 176153/371472 [3:06:46<17:12:30,  3.15it/s]
 47%|████▋     | 176154/371472 [3:06:47<16:56:50,  3.20it/s]
 47%|████▋     | 176155/371472 [3:06:47<16:43:20,  3.24it/s]
 47%|████▋     | 176156/371472 [3:06:47<17:47:49,  3.05it/s]
 47%|████▋     | 176157/371472 [3:06:48<17:05:36,  3.17it/s]
 47%|████▋     | 176158/371472 [3:06:48<17:09:22,  3.16it/s]
 47%|████▋     | 176159/371472 [3:06:48<16:46:53,  3.23it/s]
 47%|████▋     | 176160/371472 [3:06:49<16:35:28,  3.27it/s]
                                                            
{'loss': 2.8636, 'learning_rate': 5.73455579736689e-07, 'epoch': 7.59}
+
 47%|████▋     | 176160/371472 [3:06:49<16:35:28,  3.27it/s]
 47%|████▋     | 176161/371472 [3:06:49<17:26:09,  3.11it/s]
 47%|████▋     | 176162/371472 [3:06:49<16:46:21,  3.23it/s]
 47%|████▋     | 176163/371472 [3:06:50<16:25:56,  3.30it/s]
 47%|████▋     | 176164/371472 [3:06:50<16:32:13,  3.28it/s]
 47%|████▋     | 176165/371472 [3:06:50<16:10:20,  3.35it/s]
 47%|████▋     | 176166/371472 [3:06:51<18:13:05,  2.98it/s]
 47%|████▋     | 176167/371472 [3:06:51<17:46:59,  3.05it/s]
 47%|████▋     | 176168/371472 [3:06:51<16:45:26,  3.24it/s]
 47%|████▋     | 176169/371472 [3:06:51<16:22:29,  3.31it/s]
 47%|████▋     | 176170/371472 [3:06:52<15:58:20,  3.40it/s]
 47%|████▋     | 176171/371472 [3:06:52<16:42:00,  3.25it/s]
 47%|████▋     | 176172/371472 [3:06:52<17:32:55,  3.09it/s]
 47%|████▋     | 176173/371472 [3:06:53<16:44:38,  3.24it/s]
 47%|████▋     | 176174/371472 [3:06:53<16:31:11,  3.28it/s]
 47%|████▋     | 176175/371472 [3:06:53<16:49:37,  3.22it/s]
 47%|████▋     | 176176/371472 [3:06:54<16:21:08,  3.32it/s]
 47%|████▋     | 176177/371472 [3:06:54<16:33:36,  3.28it/s]
 47%|████▋     | 176178/371472 [3:06:54<16:02:57,  3.38it/s]
 47%|████▋     | 176179/371472 [3:06:54<15:54:33,  3.41it/s]
 47%|████▋     | 176180/371472 [3:06:55<16:14:15,  3.34it/s]
                                                            
{'loss': 2.9922, 'learning_rate': 5.734070977612101e-07, 'epoch': 7.59}
+
 47%|████▋     | 176180/371472 [3:06:55<16:14:15,  3.34it/s]
 47%|████▋     | 176181/371472 [3:06:55<16:02:45,  3.38it/s]
 47%|████▋     | 176182/371472 [3:06:55<15:54:56,  3.41it/s]
 47%|████▋     | 176183/371472 [3:06:56<16:40:32,  3.25it/s]
 47%|████▋     | 176184/371472 [3:06:56<16:06:40,  3.37it/s]
 47%|████▋     | 176185/371472 [3:06:56<16:05:49,  3.37it/s]
 47%|████▋     | 176186/371472 [3:06:57<16:20:20,  3.32it/s]
 47%|████▋     | 176187/371472 [3:06:57<16:10:17,  3.35it/s]
 47%|████▋     | 176188/371472 [3:06:57<15:53:27,  3.41it/s]
 47%|████▋     | 176189/371472 [3:06:57<16:14:53,  3.34it/s]
 47%|████▋     | 176190/371472 [3:06:58<17:31:11,  3.10it/s]
 47%|████▋     | 176191/371472 [3:06:58<17:10:29,  3.16it/s]
 47%|████▋     | 176192/371472 [3:06:58<17:21:37,  3.12it/s]
 47%|████▋     | 176193/371472 [3:06:59<17:46:20,  3.05it/s]
 47%|████▋     | 176194/371472 [3:06:59<17:16:15,  3.14it/s]
 47%|████▋     | 176195/371472 [3:06:59<17:03:11,  3.18it/s]
 47%|████▋     | 176196/371472 [3:07:00<16:55:11,  3.21it/s]
 47%|████▋     | 176197/371472 [3:07:00<16:48:35,  3.23it/s]
 47%|████▋     | 176198/371472 [3:07:00<16:33:44,  3.28it/s]
 47%|████▋     | 176199/371472 [3:07:01<16:29:33,  3.29it/s]
 47%|████▋     | 176200/371472 [3:07:01<17:34:25,  3.09it/s]
                                                            
{'loss': 2.8353, 'learning_rate': 5.733586157857311e-07, 'epoch': 7.59}
+
 47%|████▋     | 176200/371472 [3:07:01<17:34:25,  3.09it/s]
 47%|████▋     | 176201/371472 [3:07:01<17:26:01,  3.11it/s]
 47%|████▋     | 176202/371472 [3:07:02<16:51:42,  3.22it/s]
 47%|████▋     | 176203/371472 [3:07:02<16:15:06,  3.34it/s]
 47%|████▋     | 176204/371472 [3:07:02<16:11:24,  3.35it/s]
 47%|████▋     | 176205/371472 [3:07:02<17:03:40,  3.18it/s]
 47%|████▋     | 176206/371472 [3:07:03<16:35:51,  3.27it/s]
 47%|████▋     | 176207/371472 [3:07:03<16:20:46,  3.32it/s]
 47%|████▋     | 176208/371472 [3:07:03<16:17:09,  3.33it/s]
 47%|████▋     | 176209/371472 [3:07:04<16:03:54,  3.38it/s]
 47%|████▋     | 176210/371472 [3:07:04<16:10:44,  3.35it/s]
 47%|████▋     | 176211/371472 [3:07:04<15:40:37,  3.46it/s]
 47%|████▋     | 176212/371472 [3:07:05<15:39:35,  3.46it/s]
 47%|████▋     | 176213/371472 [3:07:05<15:46:58,  3.44it/s]
 47%|████▋     | 176214/371472 [3:07:05<15:31:37,  3.49it/s]
 47%|████▋     | 176215/371472 [3:07:05<15:48:03,  3.43it/s]
 47%|████▋     | 176216/371472 [3:07:06<15:23:28,  3.52it/s]
 47%|████▋     | 176217/371472 [3:07:06<15:20:00,  3.54it/s]
 47%|████▋     | 176218/371472 [3:07:06<15:14:55,  3.56it/s]
 47%|████▋     | 176219/371472 [3:07:07<15:34:18,  3.48it/s]
 47%|████▋     | 176220/371472 [3:07:07<15:39:08,  3.47it/s]
                                                            
{'loss': 2.9748, 'learning_rate': 5.733101338102522e-07, 'epoch': 7.59}
+
 47%|████▋     | 176220/371472 [3:07:07<15:39:08,  3.47it/s]
 47%|████▋     | 176221/371472 [3:07:07<17:19:49,  3.13it/s]
 47%|████▋     | 176222/371472 [3:07:08<18:01:09,  3.01it/s]
 47%|████▋     | 176223/371472 [3:07:08<17:26:13,  3.11it/s]
 47%|████▋     | 176224/371472 [3:07:08<17:43:31,  3.06it/s]
 47%|████▋     | 176225/371472 [3:07:08<17:19:20,  3.13it/s]
 47%|████▋     | 176226/371472 [3:07:09<16:43:50,  3.24it/s]
 47%|████▋     | 176227/371472 [3:07:09<16:20:18,  3.32it/s]
 47%|████▋     | 176228/371472 [3:07:09<17:32:43,  3.09it/s]
 47%|████▋     | 176229/371472 [3:07:10<17:09:18,  3.16it/s]
 47%|████▋     | 176230/371472 [3:07:10<16:46:17,  3.23it/s]
 47%|████▋     | 176231/371472 [3:07:10<16:36:02,  3.27it/s]
 47%|████▋     | 176232/371472 [3:07:11<16:54:27,  3.21it/s]
 47%|████▋     | 176233/371472 [3:07:11<16:46:56,  3.23it/s]
 47%|████▋     | 176234/371472 [3:07:11<16:12:32,  3.35it/s]
 47%|████▋     | 176235/371472 [3:07:11<15:46:21,  3.44it/s]
 47%|████▋     | 176236/371472 [3:07:12<15:28:44,  3.50it/s]
 47%|████▋     | 176237/371472 [3:07:12<15:25:28,  3.52it/s]
 47%|████▋     | 176238/371472 [3:07:12<15:40:21,  3.46it/s]
 47%|████▋     | 176239/371472 [3:07:13<15:49:57,  3.43it/s]
 47%|████▋     | 176240/371472 [3:07:13<16:27:53,  3.29it/s]
                                                            
{'loss': 2.8611, 'learning_rate': 5.732616518347734e-07, 'epoch': 7.59}
+
 47%|████▋     | 176240/371472 [3:07:13<16:27:53,  3.29it/s]
 47%|████▋     | 176241/371472 [3:07:13<16:36:29,  3.27it/s]
 47%|████▋     | 176242/371472 [3:07:14<16:39:22,  3.26it/s]
 47%|████▋     | 176243/371472 [3:07:14<17:38:00,  3.08it/s]
 47%|████▋     | 176244/371472 [3:07:14<17:02:31,  3.18it/s]
 47%|████▋     | 176245/371472 [3:07:15<16:34:33,  3.27it/s]
 47%|████▋     | 176246/371472 [3:07:15<16:52:49,  3.21it/s]
 47%|████▋     | 176247/371472 [3:07:15<16:18:54,  3.32it/s]
 47%|████▋     | 176248/371472 [3:07:15<15:55:19,  3.41it/s]
 47%|████▋     | 176249/371472 [3:07:16<16:05:12,  3.37it/s]
 47%|████▋     | 176250/371472 [3:07:16<15:39:15,  3.46it/s]
 47%|████▋     | 176251/371472 [3:07:16<16:57:15,  3.20it/s]
 47%|████▋     | 176252/371472 [3:07:17<17:06:42,  3.17it/s]
 47%|████▋     | 176253/371472 [3:07:17<16:48:43,  3.23it/s]
 47%|████▋     | 176254/371472 [3:07:17<16:43:35,  3.24it/s]
 47%|████▋     | 176255/371472 [3:07:18<16:59:50,  3.19it/s]
 47%|████▋     | 176256/371472 [3:07:18<17:05:59,  3.17it/s]
 47%|████▋     | 176257/371472 [3:07:18<16:47:38,  3.23it/s]
 47%|████▋     | 176258/371472 [3:07:19<16:25:18,  3.30it/s]
 47%|████▋     | 176259/371472 [3:07:19<17:46:46,  3.05it/s]
 47%|████▋     | 176260/371472 [3:07:19<17:05:17,  3.17it/s]
                                                            
{'loss': 3.0279, 'learning_rate': 5.732131698592945e-07, 'epoch': 7.59}
+
 47%|████▋     | 176260/371472 [3:07:19<17:05:17,  3.17it/s]
 47%|████▋     | 176261/371472 [3:07:19<16:55:24,  3.20it/s]
 47%|████▋     | 176262/371472 [3:07:20<18:32:50,  2.92it/s]
 47%|████▋     | 176263/371472 [3:07:20<17:49:47,  3.04it/s]
 47%|████▋     | 176264/371472 [3:07:21<18:03:30,  3.00it/s]
 47%|████▋     | 176265/371472 [3:07:21<17:17:59,  3.13it/s]
 47%|████▋     | 176266/371472 [3:07:21<16:52:51,  3.21it/s]
 47%|████▋     | 176267/371472 [3:07:21<17:05:12,  3.17it/s]
 47%|████▋     | 176268/371472 [3:07:22<17:46:26,  3.05it/s]
 47%|████▋     | 176269/371472 [3:07:22<16:49:42,  3.22it/s]
 47%|████▋     | 176270/371472 [3:07:22<17:29:09,  3.10it/s]
 47%|████▋     | 176271/371472 [3:07:23<17:11:09,  3.16it/s]
 47%|████▋     | 176272/371472 [3:07:23<16:38:07,  3.26it/s]
 47%|████▋     | 176273/371472 [3:07:23<16:08:32,  3.36it/s]
 47%|████▋     | 176274/371472 [3:07:24<16:09:16,  3.36it/s]
 47%|████▋     | 176275/371472 [3:07:24<16:46:58,  3.23it/s]
 47%|████▋     | 176276/371472 [3:07:24<16:27:40,  3.29it/s]
 47%|████▋     | 176277/371472 [3:07:25<16:36:42,  3.26it/s]
 47%|████▋     | 176278/371472 [3:07:25<16:18:45,  3.32it/s]
 47%|████▋     | 176279/371472 [3:07:25<15:41:29,  3.46it/s]
 47%|████▋     | 176280/371472 [3:07:25<15:24:27,  3.52it/s]
                                                            
{'loss': 2.7119, 'learning_rate': 5.731646878838156e-07, 'epoch': 7.59}
+
 47%|████▋     | 176280/371472 [3:07:25<15:24:27,  3.52it/s]
 47%|████▋     | 176281/371472 [3:07:26<15:14:44,  3.56it/s]
 47%|████▋     | 176282/371472 [3:07:26<15:25:39,  3.51it/s]
 47%|████▋     | 176283/371472 [3:07:26<15:42:19,  3.45it/s]
 47%|████▋     | 176284/371472 [3:07:27<16:22:38,  3.31it/s]
 47%|████▋     | 176285/371472 [3:07:27<16:49:37,  3.22it/s]
 47%|████▋     | 176286/371472 [3:07:27<16:15:20,  3.34it/s]
 47%|████▋     | 176287/371472 [3:07:28<18:57:32,  2.86it/s]
 47%|████▋     | 176288/371472 [3:07:28<22:31:01,  2.41it/s]
 47%|████▋     | 176289/371472 [3:07:29<21:27:34,  2.53it/s]
 47%|████▋     | 176290/371472 [3:07:29<19:33:57,  2.77it/s]
 47%|████▋     | 176291/371472 [3:07:29<18:20:20,  2.96it/s]
 47%|████▋     | 176292/371472 [3:07:29<17:23:40,  3.12it/s]
 47%|████▋     | 176293/371472 [3:07:30<16:31:00,  3.28it/s]
 47%|████▋     | 176294/371472 [3:07:30<16:21:39,  3.31it/s]
 47%|████▋     | 176295/371472 [3:07:30<15:55:30,  3.40it/s]
 47%|████▋     | 176296/371472 [3:07:31<15:48:35,  3.43it/s]
 47%|████▋     | 176297/371472 [3:07:31<15:42:57,  3.45it/s]
 47%|████▋     | 176298/371472 [3:07:31<15:36:27,  3.47it/s]
 47%|████▋     | 176299/371472 [3:07:31<16:10:39,  3.35it/s]
 47%|████▋     | 176300/371472 [3:07:32<16:34:41,  3.27it/s]
                                                            
{'loss': 2.784, 'learning_rate': 5.731162059083367e-07, 'epoch': 7.59}
+
 47%|████▋     | 176300/371472 [3:07:32<16:34:41,  3.27it/s]
 47%|████▋     | 176301/371472 [3:07:32<16:19:55,  3.32it/s]
 47%|████▋     | 176302/371472 [3:07:32<16:46:47,  3.23it/s]
 47%|████▋     | 176303/371472 [3:07:33<17:17:19,  3.14it/s]
 47%|████▋     | 176304/371472 [3:07:33<16:42:27,  3.24it/s]
 47%|████▋     | 176305/371472 [3:07:33<16:26:59,  3.30it/s]
 47%|████▋     | 176306/371472 [3:07:34<16:01:21,  3.38it/s]
 47%|████▋     | 176307/371472 [3:07:34<16:25:14,  3.30it/s]
 47%|████▋     | 176308/371472 [3:07:34<16:10:00,  3.35it/s]
 47%|████▋     | 176309/371472 [3:07:34<16:52:30,  3.21it/s]
 47%|████▋     | 176310/371472 [3:07:35<17:05:23,  3.17it/s]
 47%|████▋     | 176311/371472 [3:07:35<16:44:25,  3.24it/s]
 47%|████▋     | 176312/371472 [3:07:35<16:39:26,  3.25it/s]
 47%|████▋     | 176313/371472 [3:07:36<18:09:10,  2.99it/s]
 47%|████▋     | 176314/371472 [3:07:36<18:00:58,  3.01it/s]
 47%|████▋     | 176315/371472 [3:07:36<17:12:21,  3.15it/s]
 47%|████▋     | 176316/371472 [3:07:37<16:33:59,  3.27it/s]
 47%|████▋     | 176317/371472 [3:07:37<15:51:22,  3.42it/s]
 47%|████▋     | 176318/371472 [3:07:37<15:43:34,  3.45it/s]
 47%|████▋     | 176319/371472 [3:07:38<16:01:54,  3.38it/s]
 47%|████▋     | 176320/371472 [3:07:38<15:52:02,  3.42it/s]
                                                            
{'loss': 2.8745, 'learning_rate': 5.73067723932858e-07, 'epoch': 7.59}
+
 47%|████▋     | 176320/371472 [3:07:38<15:52:02,  3.42it/s]
 47%|████▋     | 176321/371472 [3:07:38<15:57:51,  3.40it/s]
 47%|████▋     | 176322/371472 [3:07:38<15:56:36,  3.40it/s]
 47%|████▋     | 176323/371472 [3:07:39<15:39:17,  3.46it/s]
 47%|████▋     | 176324/371472 [3:07:39<15:43:30,  3.45it/s]
 47%|████▋     | 176325/371472 [3:07:39<15:31:38,  3.49it/s]
 47%|████▋     | 176326/371472 [3:07:40<15:47:48,  3.43it/s]
 47%|████▋     | 176327/371472 [3:07:40<15:56:10,  3.40it/s]
 47%|████▋     | 176328/371472 [3:07:40<15:59:15,  3.39it/s]
 47%|████▋     | 176329/371472 [3:07:40<16:08:48,  3.36it/s]
 47%|████▋     | 176330/371472 [3:07:41<15:53:27,  3.41it/s]
 47%|████▋     | 176331/371472 [3:07:41<15:51:54,  3.42it/s]
 47%|████▋     | 176332/371472 [3:07:41<15:47:35,  3.43it/s]
 47%|████▋     | 176333/371472 [3:07:42<15:28:28,  3.50it/s]
 47%|████▋     | 176334/371472 [3:07:42<15:27:17,  3.51it/s]
 47%|████▋     | 176335/371472 [3:07:42<16:39:16,  3.25it/s]
 47%|████▋     | 176336/371472 [3:07:43<16:29:00,  3.29it/s]
 47%|████▋     | 176337/371472 [3:07:43<16:11:13,  3.35it/s]
 47%|████▋     | 176338/371472 [3:07:43<17:07:17,  3.17it/s]
 47%|████▋     | 176339/371472 [3:07:44<17:08:10,  3.16it/s]
 47%|████▋     | 176340/371472 [3:07:44<16:22:22,  3.31it/s]
                                                            
{'loss': 2.9571, 'learning_rate': 5.73019241957379e-07, 'epoch': 7.6}
+
 47%|████▋     | 176340/371472 [3:07:44<16:22:22,  3.31it/s]
 47%|████▋     | 176341/371472 [3:07:44<16:38:44,  3.26it/s]
 47%|████▋     | 176342/371472 [3:07:44<16:32:26,  3.28it/s]
 47%|████▋     | 176343/371472 [3:07:45<16:54:10,  3.21it/s]
 47%|████▋     | 176344/371472 [3:07:45<17:00:06,  3.19it/s]
 47%|████▋     | 176345/371472 [3:07:45<16:20:04,  3.32it/s]
 47%|████▋     | 176346/371472 [3:07:46<16:01:35,  3.38it/s]
 47%|████▋     | 176347/371472 [3:07:46<15:44:49,  3.44it/s]
 47%|████▋     | 176348/371472 [3:07:46<16:19:19,  3.32it/s]
 47%|████▋     | 176349/371472 [3:07:47<16:49:33,  3.22it/s]
 47%|████▋     | 176350/371472 [3:07:47<16:49:55,  3.22it/s]
 47%|████▋     | 176351/371472 [3:07:47<16:15:43,  3.33it/s]
 47%|████▋     | 176352/371472 [3:07:48<22:08:36,  2.45it/s]
 47%|████▋     | 176353/371472 [3:07:48<20:39:39,  2.62it/s]
 47%|████▋     | 176354/371472 [3:07:48<19:27:30,  2.79it/s]
 47%|████▋     | 176355/371472 [3:07:49<17:58:55,  3.01it/s]
 47%|████▋     | 176356/371472 [3:07:49<17:35:20,  3.08it/s]
 47%|████▋     | 176357/371472 [3:07:49<17:10:03,  3.16it/s]
 47%|████▋     | 176358/371472 [3:07:50<18:11:52,  2.98it/s]
 47%|████▋     | 176359/371472 [3:07:50<17:38:45,  3.07it/s]
 47%|████▋     | 176360/371472 [3:07:50<16:48:28,  3.22it/s]
                                                            
{'loss': 2.873, 'learning_rate': 5.729707599819e-07, 'epoch': 7.6}
+
 47%|████▋     | 176360/371472 [3:07:50<16:48:28,  3.22it/s]
 47%|████▋     | 176361/371472 [3:07:51<16:28:29,  3.29it/s]
 47%|████▋     | 176362/371472 [3:07:51<16:13:48,  3.34it/s]
 47%|████▋     | 176363/371472 [3:07:51<16:07:22,  3.36it/s]
 47%|████▋     | 176364/371472 [3:07:51<15:55:35,  3.40it/s]
 47%|████▋     | 176365/371472 [3:07:52<17:10:15,  3.16it/s]
 47%|████▋     | 176366/371472 [3:07:52<16:53:47,  3.21it/s]
 47%|████▋     | 176367/371472 [3:07:52<16:21:43,  3.31it/s]
 47%|████▋     | 176368/371472 [3:07:53<16:17:32,  3.33it/s]
 47%|████▋     | 176369/371472 [3:07:53<15:46:18,  3.44it/s]
 47%|████▋     | 176370/371472 [3:07:53<15:33:14,  3.48it/s]
 47%|████▋     | 176371/371472 [3:07:53<15:41:19,  3.45it/s]
 47%|████▋     | 176372/371472 [3:07:54<15:25:41,  3.51it/s]
 47%|████▋     | 176373/371472 [3:07:54<16:12:27,  3.34it/s]
 47%|████▋     | 176374/371472 [3:07:54<16:00:12,  3.39it/s]
 47%|████▋     | 176375/371472 [3:07:55<16:21:28,  3.31it/s]
 47%|████▋     | 176376/371472 [3:07:55<16:28:41,  3.29it/s]
 47%|████▋     | 176377/371472 [3:07:55<16:16:53,  3.33it/s]
 47%|████▋     | 176378/371472 [3:07:56<15:55:42,  3.40it/s]
 47%|████▋     | 176379/371472 [3:07:56<16:14:55,  3.34it/s]
 47%|████▋     | 176380/371472 [3:07:56<16:12:08,  3.34it/s]
                                                            
{'loss': 2.7703, 'learning_rate': 5.729222780064211e-07, 'epoch': 7.6}
+
 47%|████▋     | 176380/371472 [3:07:56<16:12:08,  3.34it/s]
 47%|████▋     | 176381/371472 [3:07:56<16:27:24,  3.29it/s]
 47%|████▋     | 176382/371472 [3:07:57<16:55:27,  3.20it/s]
 47%|████▋     | 176383/371472 [3:07:57<16:25:03,  3.30it/s]
 47%|████▋     | 176384/371472 [3:07:57<16:55:05,  3.20it/s]
 47%|████▋     | 176385/371472 [3:07:58<16:12:41,  3.34it/s]
 47%|████▋     | 176386/371472 [3:07:58<15:36:47,  3.47it/s]
 47%|████▋     | 176387/371472 [3:07:58<15:32:53,  3.49it/s]
 47%|████▋     | 176388/371472 [3:07:59<17:44:46,  3.05it/s]
 47%|████▋     | 176389/371472 [3:07:59<17:24:21,  3.11it/s]
 47%|████▋     | 176390/371472 [3:07:59<17:24:00,  3.11it/s]
 47%|████▋     | 176391/371472 [3:08:00<17:30:48,  3.09it/s]
 47%|████▋     | 176392/371472 [3:08:00<17:11:43,  3.15it/s]
 47%|████▋     | 176393/371472 [3:08:00<17:02:59,  3.18it/s]
 47%|████▋     | 176394/371472 [3:08:01<18:16:00,  2.97it/s]
 47%|████▋     | 176395/371472 [3:08:01<17:26:48,  3.11it/s]
 47%|████▋     | 176396/371472 [3:08:01<17:09:05,  3.16it/s]
 47%|████▋     | 176397/371472 [3:08:02<19:41:18,  2.75it/s]
 47%|████▋     | 176398/371472 [3:08:02<18:14:15,  2.97it/s]
 47%|████▋     | 176399/371472 [3:08:02<17:57:56,  3.02it/s]
 47%|████▋     | 176400/371472 [3:08:03<17:22:06,  3.12it/s]
                                                            
{'loss': 2.7918, 'learning_rate': 5.728737960309423e-07, 'epoch': 7.6}
+
 47%|████▋     | 176400/371472 [3:08:03<17:22:06,  3.12it/s]
 47%|████▋     | 176401/371472 [3:08:03<16:55:34,  3.20it/s]
 47%|████▋     | 176402/371472 [3:08:03<16:19:16,  3.32it/s]
 47%|████▋     | 176403/371472 [3:08:03<16:06:49,  3.36it/s]
 47%|████▋     | 176404/371472 [3:08:04<16:15:17,  3.33it/s]
 47%|████▋     | 176405/371472 [3:08:04<16:20:23,  3.32it/s]
 47%|████▋     | 176406/371472 [3:08:04<16:02:52,  3.38it/s]
 47%|████▋     | 176407/371472 [3:08:05<16:19:21,  3.32it/s]
 47%|████▋     | 176408/371472 [3:08:05<15:55:26,  3.40it/s]
 47%|████▋     | 176409/371472 [3:08:05<16:03:19,  3.37it/s]
 47%|████▋     | 176410/371472 [3:08:06<16:12:37,  3.34it/s]
 47%|████▋     | 176411/371472 [3:08:06<15:55:39,  3.40it/s]
 47%|████▋     | 176412/371472 [3:08:06<15:49:43,  3.42it/s]
 47%|████▋     | 176413/371472 [3:08:06<15:27:34,  3.50it/s]
 47%|████▋     | 176414/371472 [3:08:07<16:21:14,  3.31it/s]
 47%|████▋     | 176415/371472 [3:08:07<16:40:54,  3.25it/s]
 47%|████▋     | 176416/371472 [3:08:07<16:56:26,  3.20it/s]
 47%|████▋     | 176417/371472 [3:08:08<16:40:20,  3.25it/s]
 47%|████▋     | 176418/371472 [3:08:08<16:37:09,  3.26it/s]
 47%|████▋     | 176419/371472 [3:08:08<16:44:01,  3.24it/s]
 47%|████▋     | 176420/371472 [3:08:09<16:51:45,  3.21it/s]
                                                            
{'loss': 2.8746, 'learning_rate': 5.728253140554634e-07, 'epoch': 7.6}
+
 47%|████▋     | 176420/371472 [3:08:09<16:51:45,  3.21it/s]
 47%|████▋     | 176421/371472 [3:08:09<17:02:31,  3.18it/s]
 47%|████▋     | 176422/371472 [3:08:09<16:51:21,  3.21it/s]
 47%|████▋     | 176423/371472 [3:08:10<17:08:23,  3.16it/s]
 47%|████▋     | 176424/371472 [3:08:10<17:06:03,  3.17it/s]
 47%|████▋     | 176425/371472 [3:08:10<16:30:58,  3.28it/s]
 47%|████▋     | 176426/371472 [3:08:10<16:41:47,  3.24it/s]
 47%|████▋     | 176427/371472 [3:08:11<16:19:03,  3.32it/s]
 47%|████▋     | 176428/371472 [3:08:11<15:54:37,  3.41it/s]
 47%|████▋     | 176429/371472 [3:08:11<15:38:59,  3.46it/s]
 47%|████▋     | 176430/371472 [3:08:12<15:36:30,  3.47it/s]
 47%|████▋     | 176431/371472 [3:08:12<15:44:01,  3.44it/s]
 47%|████▋     | 176432/371472 [3:08:12<15:44:09,  3.44it/s]
 47%|████▋     | 176433/371472 [3:08:12<15:33:05,  3.48it/s]
 47%|████▋     | 176434/371472 [3:08:13<15:38:56,  3.46it/s]
 47%|████▋     | 176435/371472 [3:08:13<15:34:33,  3.48it/s]
 47%|████▋     | 176436/371472 [3:08:13<15:24:35,  3.52it/s]
 47%|████▋     | 176437/371472 [3:08:14<15:16:55,  3.55it/s]
 47%|████▋     | 176438/371472 [3:08:14<15:06:03,  3.59it/s]
 47%|████▋     | 176439/371472 [3:08:14<15:02:28,  3.60it/s]
 47%|████▋     | 176440/371472 [3:08:14<15:17:11,  3.54it/s]
                                                            
{'loss': 3.0421, 'learning_rate': 5.727768320799844e-07, 'epoch': 7.6}
+
 47%|████▋     | 176440/371472 [3:08:14<15:17:11,  3.54it/s]
 47%|████▋     | 176441/371472 [3:08:15<15:13:27,  3.56it/s]
 47%|████▋     | 176442/371472 [3:08:15<15:47:02,  3.43it/s]
 47%|████▋     | 176443/371472 [3:08:15<16:00:59,  3.38it/s]
 47%|████▋     | 176444/371472 [3:08:16<17:14:51,  3.14it/s]
 47%|████▋     | 176445/371472 [3:08:16<16:52:32,  3.21it/s]
 47%|████▋     | 176446/371472 [3:08:16<17:04:35,  3.17it/s]
 47%|████▋     | 176447/371472 [3:08:17<17:05:31,  3.17it/s]
 47%|████▋     | 176448/371472 [3:08:17<16:55:01,  3.20it/s]
 47%|████▋     | 176449/371472 [3:08:17<16:56:30,  3.20it/s]
 48%|████▊     | 176450/371472 [3:08:18<17:09:43,  3.16it/s]
 48%|████▊     | 176451/371472 [3:08:18<16:42:49,  3.24it/s]
 48%|████▊     | 176452/371472 [3:08:18<16:25:31,  3.30it/s]
 48%|████▊     | 176453/371472 [3:08:18<16:05:14,  3.37it/s]
 48%|████▊     | 176454/371472 [3:08:19<16:29:33,  3.28it/s]
 48%|████▊     | 176455/371472 [3:08:19<16:38:56,  3.25it/s]
 48%|████▊     | 176456/371472 [3:08:19<16:34:22,  3.27it/s]
 48%|████▊     | 176457/371472 [3:08:20<16:38:31,  3.26it/s]
 48%|████▊     | 176458/371472 [3:08:20<16:56:23,  3.20it/s]
 48%|████▊     | 176459/371472 [3:08:20<16:38:13,  3.26it/s]
 48%|████▊     | 176460/371472 [3:08:21<16:29:22,  3.29it/s]
                                                            
{'loss': 2.8362, 'learning_rate': 5.727283501045056e-07, 'epoch': 7.6}
+
 48%|████▊     | 176460/371472 [3:08:21<16:29:22,  3.29it/s]
 48%|████▊     | 176461/371472 [3:08:21<16:21:45,  3.31it/s]
 48%|████▊     | 176462/371472 [3:08:21<16:42:00,  3.24it/s]
 48%|████▊     | 176463/371472 [3:08:22<16:18:39,  3.32it/s]
 48%|████▊     | 176464/371472 [3:08:22<16:32:45,  3.27it/s]
 48%|████▊     | 176465/371472 [3:08:22<16:08:27,  3.36it/s]
 48%|████▊     | 176466/371472 [3:08:22<16:13:44,  3.34it/s]
 48%|████▊     | 176467/371472 [3:08:23<17:25:02,  3.11it/s]
 48%|████▊     | 176468/371472 [3:08:23<17:16:35,  3.14it/s]
 48%|████▊     | 176469/371472 [3:08:23<17:42:44,  3.06it/s]
 48%|████▊     | 176470/371472 [3:08:24<17:18:21,  3.13it/s]
 48%|████▊     | 176471/371472 [3:08:24<16:49:02,  3.22it/s]
 48%|████▊     | 176472/371472 [3:08:24<16:41:05,  3.25it/s]
 48%|████▊     | 176473/371472 [3:08:25<16:18:22,  3.32it/s]
 48%|████▊     | 176474/371472 [3:08:25<16:43:58,  3.24it/s]
 48%|████▊     | 176475/371472 [3:08:25<16:54:16,  3.20it/s]
 48%|████▊     | 176476/371472 [3:08:26<16:45:24,  3.23it/s]
 48%|████▊     | 176477/371472 [3:08:26<16:28:01,  3.29it/s]
 48%|████▊     | 176478/371472 [3:08:26<16:41:34,  3.24it/s]
 48%|████▊     | 176479/371472 [3:08:26<16:20:19,  3.32it/s]
 48%|████▊     | 176480/371472 [3:08:27<15:58:23,  3.39it/s]
                                                            
{'loss': 2.9434, 'learning_rate': 5.726798681290267e-07, 'epoch': 7.6}
+
 48%|████▊     | 176480/371472 [3:08:27<15:58:23,  3.39it/s]
 48%|████▊     | 176481/371472 [3:08:27<16:11:17,  3.35it/s]
 48%|████▊     | 176482/371472 [3:08:27<16:08:19,  3.36it/s]
 48%|████▊     | 176483/371472 [3:08:28<16:41:55,  3.24it/s]
 48%|████▊     | 176484/371472 [3:08:28<16:06:09,  3.36it/s]
 48%|████▊     | 176485/371472 [3:08:28<15:45:54,  3.44it/s]
 48%|████▊     | 176486/371472 [3:08:29<15:40:11,  3.46it/s]
 48%|████▊     | 176487/371472 [3:08:29<15:28:33,  3.50it/s]
 48%|████▊     | 176488/371472 [3:08:29<15:41:38,  3.45it/s]
 48%|████▊     | 176489/371472 [3:08:29<15:56:44,  3.40it/s]
 48%|████▊     | 176490/371472 [3:08:30<15:54:54,  3.40it/s]
 48%|████▊     | 176491/371472 [3:08:30<15:47:39,  3.43it/s]
 48%|████▊     | 176492/371472 [3:08:30<15:36:11,  3.47it/s]
 48%|████▊     | 176493/371472 [3:08:31<16:38:28,  3.25it/s]
 48%|████▊     | 176494/371472 [3:08:31<16:04:50,  3.37it/s]
 48%|████▊     | 176495/371472 [3:08:31<15:58:46,  3.39it/s]
 48%|████▊     | 176496/371472 [3:08:31<16:29:02,  3.29it/s]
 48%|████▊     | 176497/371472 [3:08:32<16:07:15,  3.36it/s]
 48%|████▊     | 176498/371472 [3:08:32<16:05:06,  3.37it/s]
 48%|████▊     | 176499/371472 [3:08:32<15:56:21,  3.40it/s]
 48%|████▊     | 176500/371472 [3:08:33<16:04:29,  3.37it/s]
                                                            
{'loss': 2.7924, 'learning_rate': 5.726313861535478e-07, 'epoch': 7.6}
+
 48%|████▊     | 176500/371472 [3:08:33<16:04:29,  3.37it/s]
 48%|████▊     | 176501/371472 [3:08:33<15:37:24,  3.47it/s]
 48%|████▊     | 176502/371472 [3:08:33<15:35:58,  3.47it/s]
 48%|████▊     | 176503/371472 [3:08:33<15:20:53,  3.53it/s]
 48%|████▊     | 176504/371472 [3:08:34<15:26:22,  3.51it/s]
 48%|████▊     | 176505/371472 [3:08:34<16:14:34,  3.33it/s]
 48%|████▊     | 176506/371472 [3:08:34<17:09:35,  3.16it/s]
 48%|████▊     | 176507/371472 [3:08:35<16:37:52,  3.26it/s]
 48%|████▊     | 176508/371472 [3:08:35<16:21:26,  3.31it/s]
 48%|████▊     | 176509/371472 [3:08:35<16:12:16,  3.34it/s]
 48%|████▊     | 176510/371472 [3:08:36<16:46:37,  3.23it/s]
 48%|████▊     | 176511/371472 [3:08:36<17:21:52,  3.12it/s]
 48%|████▊     | 176512/371472 [3:08:36<17:10:10,  3.15it/s]
 48%|████▊     | 176513/371472 [3:08:37<16:18:05,  3.32it/s]
 48%|████▊     | 176514/371472 [3:08:37<15:46:15,  3.43it/s]
 48%|████▊     | 176515/371472 [3:08:37<15:59:38,  3.39it/s]
 48%|████▊     | 176516/371472 [3:08:38<16:46:36,  3.23it/s]
 48%|████▊     | 176517/371472 [3:08:38<16:37:42,  3.26it/s]
 48%|████▊     | 176518/371472 [3:08:38<16:15:46,  3.33it/s]
 48%|████▊     | 176519/371472 [3:08:38<16:16:05,  3.33it/s]
 48%|████▊     | 176520/371472 [3:08:39<16:13:41,  3.34it/s]
                                                            
{'loss': 2.8914, 'learning_rate': 5.725829041780688e-07, 'epoch': 7.6}
+
 48%|████▊     | 176520/371472 [3:08:39<16:13:41,  3.34it/s]
 48%|████▊     | 176521/371472 [3:08:39<16:16:10,  3.33it/s]
 48%|████▊     | 176522/371472 [3:08:39<17:49:48,  3.04it/s]
 48%|████▊     | 176523/371472 [3:08:40<17:10:47,  3.15it/s]
 48%|████▊     | 176524/371472 [3:08:40<17:15:13,  3.14it/s]
 48%|████▊     | 176525/371472 [3:08:40<16:40:11,  3.25it/s]
 48%|████▊     | 176526/371472 [3:08:41<16:15:14,  3.33it/s]
 48%|████▊     | 176527/371472 [3:08:41<16:01:52,  3.38it/s]
 48%|████▊     | 176528/371472 [3:08:41<15:35:56,  3.47it/s]
 48%|████▊     | 176529/371472 [3:08:41<15:26:54,  3.51it/s]
 48%|████▊     | 176530/371472 [3:08:42<15:14:23,  3.55it/s]
 48%|████▊     | 176531/371472 [3:08:42<15:19:47,  3.53it/s]
 48%|████▊     | 176532/371472 [3:08:42<15:06:54,  3.58it/s]
 48%|████▊     | 176533/371472 [3:08:43<15:17:57,  3.54it/s]
 48%|████▊     | 176534/371472 [3:08:43<15:24:12,  3.52it/s]
 48%|████▊     | 176535/371472 [3:08:43<15:36:07,  3.47it/s]
 48%|████▊     | 176536/371472 [3:08:43<15:45:12,  3.44it/s]
 48%|████▊     | 176537/371472 [3:08:44<15:54:41,  3.40it/s]
 48%|████▊     | 176538/371472 [3:08:44<15:38:08,  3.46it/s]
 48%|████▊     | 176539/371472 [3:08:44<16:10:20,  3.35it/s]
 48%|████▊     | 176540/371472 [3:08:45<16:33:51,  3.27it/s]
                                                            
{'loss': 2.8746, 'learning_rate': 5.7253442220259e-07, 'epoch': 7.6}
+
 48%|████▊     | 176540/371472 [3:08:45<16:33:51,  3.27it/s]
 48%|████▊     | 176541/371472 [3:08:45<15:58:32,  3.39it/s]
 48%|████▊     | 176542/371472 [3:08:45<15:39:14,  3.46it/s]
 48%|████▊     | 176543/371472 [3:08:45<15:45:17,  3.44it/s]
 48%|████▊     | 176544/371472 [3:08:46<15:37:14,  3.47it/s]
 48%|████▊     | 176545/371472 [3:08:46<15:33:15,  3.48it/s]
 48%|████▊     | 176546/371472 [3:08:46<15:49:33,  3.42it/s]
 48%|████▊     | 176547/371472 [3:08:47<15:50:29,  3.42it/s]
 48%|████▊     | 176548/371472 [3:08:47<16:07:54,  3.36it/s]
 48%|████▊     | 176549/371472 [3:08:47<16:18:11,  3.32it/s]
 48%|████▊     | 176550/371472 [3:08:48<16:48:35,  3.22it/s]
 48%|████▊     | 176551/371472 [3:08:48<16:41:48,  3.24it/s]
 48%|████▊     | 176552/371472 [3:08:48<16:14:47,  3.33it/s]
 48%|████▊     | 176553/371472 [3:08:48<16:23:15,  3.30it/s]
 48%|████▊     | 176554/371472 [3:08:49<16:03:43,  3.37it/s]
 48%|████▊     | 176555/371472 [3:08:49<15:52:01,  3.41it/s]
 48%|████▊     | 176556/371472 [3:08:49<15:31:22,  3.49it/s]
 48%|████▊     | 176557/371472 [3:08:50<16:10:52,  3.35it/s]
 48%|████▊     | 176558/371472 [3:08:50<15:45:50,  3.43it/s]
 48%|████▊     | 176559/371472 [3:08:50<15:23:34,  3.52it/s]
 48%|████▊     | 176560/371472 [3:08:51<16:28:14,  3.29it/s]
                                                            
{'loss': 2.9561, 'learning_rate': 5.724859402271112e-07, 'epoch': 7.6}
+
 48%|████▊     | 176560/371472 [3:08:51<16:28:14,  3.29it/s]
 48%|████▊     | 176561/371472 [3:08:51<16:11:20,  3.34it/s]
 48%|████▊     | 176562/371472 [3:08:51<16:05:56,  3.36it/s]
 48%|████▊     | 176563/371472 [3:08:51<15:25:04,  3.51it/s]
 48%|████▊     | 176564/371472 [3:08:52<15:46:54,  3.43it/s]
 48%|████▊     | 176565/371472 [3:08:52<15:15:24,  3.55it/s]
 48%|████▊     | 176566/371472 [3:08:52<15:24:30,  3.51it/s]
 48%|████▊     | 176567/371472 [3:08:53<16:01:48,  3.38it/s]
 48%|████▊     | 176568/371472 [3:08:53<16:00:48,  3.38it/s]
 48%|████▊     | 176569/371472 [3:08:53<16:16:08,  3.33it/s]
 48%|████▊     | 176570/371472 [3:08:53<15:54:08,  3.40it/s]
 48%|████▊     | 176571/371472 [3:08:54<15:55:57,  3.40it/s]
 48%|████▊     | 176572/371472 [3:08:54<15:33:24,  3.48it/s]
 48%|████▊     | 176573/371472 [3:08:54<15:26:37,  3.51it/s]
 48%|████▊     | 176574/371472 [3:08:55<15:24:07,  3.51it/s]
 48%|████▊     | 176575/371472 [3:08:55<15:20:02,  3.53it/s]
 48%|████▊     | 176576/371472 [3:08:55<16:25:47,  3.30it/s]
 48%|████▊     | 176577/371472 [3:08:55<16:07:38,  3.36it/s]
 48%|████▊     | 176578/371472 [3:08:56<16:31:52,  3.27it/s]
 48%|████▊     | 176579/371472 [3:08:56<16:21:11,  3.31it/s]
 48%|████▊     | 176580/371472 [3:08:56<16:29:11,  3.28it/s]
                                                            
{'loss': 2.8022, 'learning_rate': 5.724374582516323e-07, 'epoch': 7.61}
+
 48%|████▊     | 176580/371472 [3:08:56<16:29:11,  3.28it/s]
 48%|████▊     | 176581/371472 [3:08:57<16:19:28,  3.32it/s]
 48%|████▊     | 176582/371472 [3:08:57<15:39:28,  3.46it/s]
 48%|████▊     | 176583/371472 [3:08:57<15:39:56,  3.46it/s]
 48%|████▊     | 176584/371472 [3:08:58<17:28:13,  3.10it/s]
 48%|████▊     | 176585/371472 [3:08:58<18:02:21,  3.00it/s]
 48%|████▊     | 176586/371472 [3:08:58<18:25:21,  2.94it/s]
 48%|████▊     | 176587/371472 [3:08:59<17:31:11,  3.09it/s]
 48%|████▊     | 176588/371472 [3:08:59<16:52:20,  3.21it/s]
 48%|████▊     | 176589/371472 [3:08:59<17:26:40,  3.10it/s]
 48%|████▊     | 176590/371472 [3:09:00<16:52:21,  3.21it/s]
 48%|████▊     | 176591/371472 [3:09:00<16:31:19,  3.28it/s]
 48%|████▊     | 176592/371472 [3:09:00<16:42:42,  3.24it/s]
 48%|████▊     | 176593/371472 [3:09:00<16:35:13,  3.26it/s]
 48%|████▊     | 176594/371472 [3:09:01<16:37:48,  3.26it/s]
 48%|████▊     | 176595/371472 [3:09:01<16:10:19,  3.35it/s]
 48%|████▊     | 176596/371472 [3:09:01<15:50:53,  3.42it/s]
 48%|████▊     | 176597/371472 [3:09:02<15:39:11,  3.46it/s]
 48%|████▊     | 176598/371472 [3:09:02<16:12:19,  3.34it/s]
 48%|████▊     | 176599/371472 [3:09:02<15:53:36,  3.41it/s]
 48%|████▊     | 176600/371472 [3:09:03<15:52:55,  3.41it/s]
                                                            
{'loss': 2.9256, 'learning_rate': 5.723889762761533e-07, 'epoch': 7.61}
+
 48%|████▊     | 176600/371472 [3:09:03<15:52:55,  3.41it/s]
 48%|████▊     | 176601/371472 [3:09:03<15:34:03,  3.48it/s]
 48%|████▊     | 176602/371472 [3:09:03<15:37:33,  3.46it/s]
 48%|████▊     | 176603/371472 [3:09:03<15:45:29,  3.44it/s]
 48%|████▊     | 176604/371472 [3:09:04<15:33:54,  3.48it/s]
 48%|████▊     | 176605/371472 [3:09:04<15:25:24,  3.51it/s]
 48%|████▊     | 176606/371472 [3:09:04<15:34:35,  3.48it/s]
 48%|████▊     | 176607/371472 [3:09:05<15:37:00,  3.47it/s]
 48%|████▊     | 176608/371472 [3:09:05<15:51:52,  3.41it/s]
 48%|████▊     | 176609/371472 [3:09:05<15:40:04,  3.45it/s]
 48%|████▊     | 176610/371472 [3:09:05<15:42:44,  3.44it/s]
 48%|████▊     | 176611/371472 [3:09:06<16:00:08,  3.38it/s]
 48%|████▊     | 176612/371472 [3:09:06<16:00:47,  3.38it/s]
 48%|████▊     | 176613/371472 [3:09:06<17:26:29,  3.10it/s]
 48%|████▊     | 176614/371472 [3:09:07<16:59:58,  3.18it/s]
 48%|████▊     | 176615/371472 [3:09:07<17:18:02,  3.13it/s]
 48%|████▊     | 176616/371472 [3:09:07<17:05:34,  3.17it/s]
 48%|████▊     | 176617/371472 [3:09:08<16:47:47,  3.22it/s]
 48%|████▊     | 176618/371472 [3:09:08<18:42:35,  2.89it/s]
 48%|████▊     | 176619/371472 [3:09:08<18:02:03,  3.00it/s]
 48%|████▊     | 176620/371472 [3:09:09<17:22:39,  3.11it/s]
                                                            
{'loss': 2.8818, 'learning_rate': 5.723404943006744e-07, 'epoch': 7.61}
+
 48%|████▊     | 176620/371472 [3:09:09<17:22:39,  3.11it/s]
 48%|████▊     | 176621/371472 [3:09:09<17:02:37,  3.18it/s]
 48%|████▊     | 176622/371472 [3:09:09<16:53:14,  3.21it/s]
 48%|████▊     | 176623/371472 [3:09:10<16:41:14,  3.24it/s]
 48%|████▊     | 176624/371472 [3:09:10<16:55:16,  3.20it/s]
 48%|████▊     | 176625/371472 [3:09:10<17:48:34,  3.04it/s]
 48%|████▊     | 176626/371472 [3:09:11<17:16:51,  3.13it/s]
 48%|████▊     | 176627/371472 [3:09:11<16:53:14,  3.20it/s]
 48%|████▊     | 176628/371472 [3:09:11<17:05:26,  3.17it/s]
 48%|████▊     | 176629/371472 [3:09:11<16:49:27,  3.22it/s]
 48%|████▊     | 176630/371472 [3:09:12<16:43:55,  3.23it/s]
 48%|████▊     | 176631/371472 [3:09:12<16:20:46,  3.31it/s]
 48%|████▊     | 176632/371472 [3:09:12<16:00:51,  3.38it/s]
 48%|████▊     | 176633/371472 [3:09:13<15:49:20,  3.42it/s]
 48%|████▊     | 176634/371472 [3:09:13<15:23:27,  3.52it/s]
 48%|████▊     | 176635/371472 [3:09:13<15:35:11,  3.47it/s]
 48%|████▊     | 176636/371472 [3:09:14<16:20:35,  3.31it/s]
 48%|████▊     | 176637/371472 [3:09:14<16:42:22,  3.24it/s]
 48%|████▊     | 176638/371472 [3:09:14<16:30:13,  3.28it/s]
 48%|████▊     | 176639/371472 [3:09:14<16:30:12,  3.28it/s]
 48%|████▊     | 176640/371472 [3:09:15<16:11:15,  3.34it/s]
                                                            
{'loss': 2.8612, 'learning_rate': 5.722920123251956e-07, 'epoch': 7.61}
+
 48%|████▊     | 176640/371472 [3:09:15<16:11:15,  3.34it/s]
 48%|████▊     | 176641/371472 [3:09:15<16:18:24,  3.32it/s]
 48%|████▊     | 176642/371472 [3:09:15<16:12:09,  3.34it/s]
 48%|████▊     | 176643/371472 [3:09:16<16:27:15,  3.29it/s]
 48%|████▊     | 176644/371472 [3:09:16<16:08:53,  3.35it/s]
 48%|████▊     | 176645/371472 [3:09:16<15:48:10,  3.42it/s]
 48%|████▊     | 176646/371472 [3:09:17<16:35:34,  3.26it/s]
 48%|████▊     | 176647/371472 [3:09:17<16:06:13,  3.36it/s]
 48%|████▊     | 176648/371472 [3:09:17<16:11:16,  3.34it/s]
 48%|████▊     | 176649/371472 [3:09:17<16:24:20,  3.30it/s]
 48%|████▊     | 176650/371472 [3:09:18<16:01:09,  3.38it/s]
 48%|████▊     | 176651/371472 [3:09:18<15:56:09,  3.40it/s]
 48%|████▊     | 176652/371472 [3:09:18<16:17:07,  3.32it/s]
 48%|████▊     | 176653/371472 [3:09:19<16:33:37,  3.27it/s]
 48%|████▊     | 176654/371472 [3:09:19<16:39:46,  3.25it/s]
 48%|████▊     | 176655/371472 [3:09:19<16:21:38,  3.31it/s]
 48%|████▊     | 176656/371472 [3:09:20<16:22:54,  3.30it/s]
 48%|████▊     | 176657/371472 [3:09:20<15:59:02,  3.39it/s]
 48%|████▊     | 176658/371472 [3:09:20<15:35:45,  3.47it/s]
 48%|████▊     | 176659/371472 [3:09:20<15:29:40,  3.49it/s]
 48%|████▊     | 176660/371472 [3:09:21<15:16:24,  3.54it/s]
                                                            
{'loss': 3.0052, 'learning_rate': 5.722435303497165e-07, 'epoch': 7.61}
+
 48%|████▊     | 176660/371472 [3:09:21<15:16:24,  3.54it/s]
 48%|████▊     | 176661/371472 [3:09:21<15:54:14,  3.40it/s]
 48%|████▊     | 176662/371472 [3:09:21<15:53:33,  3.40it/s]
 48%|████▊     | 176663/371472 [3:09:22<16:22:16,  3.31it/s]
 48%|████▊     | 176664/371472 [3:09:22<15:50:22,  3.42it/s]
 48%|████▊     | 176665/371472 [3:09:22<15:47:21,  3.43it/s]
 48%|████▊     | 176666/371472 [3:09:23<17:55:42,  3.02it/s]
 48%|████▊     | 176667/371472 [3:09:23<17:00:01,  3.18it/s]
 48%|████▊     | 176668/371472 [3:09:23<16:38:45,  3.25it/s]
 48%|████▊     | 176669/371472 [3:09:23<16:31:08,  3.28it/s]
 48%|████▊     | 176670/371472 [3:09:24<16:11:32,  3.34it/s]
 48%|████▊     | 176671/371472 [3:09:24<15:48:28,  3.42it/s]
 48%|████▊     | 176672/371472 [3:09:24<15:39:08,  3.46it/s]
 48%|████▊     | 176673/371472 [3:09:25<15:41:52,  3.45it/s]
 48%|████▊     | 176674/371472 [3:09:25<15:28:48,  3.50it/s]
 48%|████▊     | 176675/371472 [3:09:25<15:42:39,  3.44it/s]
 48%|████▊     | 176676/371472 [3:09:25<15:24:31,  3.51it/s]
 48%|████▊     | 176677/371472 [3:09:26<16:05:19,  3.36it/s]
 48%|████▊     | 176678/371472 [3:09:26<17:08:45,  3.16it/s]
 48%|████▊     | 176679/371472 [3:09:26<16:49:18,  3.22it/s]
 48%|████▊     | 176680/371472 [3:09:27<16:40:43,  3.24it/s]
                                                            
{'loss': 2.7427, 'learning_rate': 5.721950483742377e-07, 'epoch': 7.61}
+
 48%|████▊     | 176680/371472 [3:09:27<16:40:43,  3.24it/s]
 48%|████▊     | 176681/371472 [3:09:27<16:40:46,  3.24it/s]
 48%|████▊     | 176682/371472 [3:09:27<17:31:22,  3.09it/s]
 48%|████▊     | 176683/371472 [3:09:28<17:53:04,  3.03it/s]
 48%|████▊     | 176684/371472 [3:09:28<18:20:35,  2.95it/s]
 48%|████▊     | 176685/371472 [3:09:28<17:46:31,  3.04it/s]
 48%|████▊     | 176686/371472 [3:09:29<17:27:53,  3.10it/s]
 48%|████▊     | 176687/371472 [3:09:29<16:48:09,  3.22it/s]
 48%|████▊     | 176688/371472 [3:09:29<16:40:32,  3.24it/s]
 48%|████▊     | 176689/371472 [3:09:30<16:25:44,  3.29it/s]
 48%|████▊     | 176690/371472 [3:09:30<16:10:49,  3.34it/s]
 48%|████▊     | 176691/371472 [3:09:30<15:55:39,  3.40it/s]
 48%|████▊     | 176692/371472 [3:09:31<17:14:41,  3.14it/s]
 48%|████▊     | 176693/371472 [3:09:31<16:34:12,  3.27it/s]
 48%|████▊     | 176694/371472 [3:09:31<16:12:45,  3.34it/s]
 48%|████▊     | 176695/371472 [3:09:31<16:42:32,  3.24it/s]
 48%|████▊     | 176696/371472 [3:09:32<16:52:36,  3.21it/s]
 48%|████▊     | 176697/371472 [3:09:32<16:38:11,  3.25it/s]
 48%|████▊     | 176698/371472 [3:09:32<16:41:23,  3.24it/s]
 48%|████▊     | 176699/371472 [3:09:33<16:12:22,  3.34it/s]
 48%|████▊     | 176700/371472 [3:09:33<16:52:41,  3.21it/s]
                                                            
{'loss': 2.946, 'learning_rate': 5.721465663987589e-07, 'epoch': 7.61}
+
 48%|████▊     | 176700/371472 [3:09:33<16:52:41,  3.21it/s]
 48%|████▊     | 176701/371472 [3:09:33<16:21:40,  3.31it/s]
 48%|████▊     | 176702/371472 [3:09:34<16:24:08,  3.30it/s]
 48%|████▊     | 176703/371472 [3:09:34<16:45:37,  3.23it/s]
 48%|████▊     | 176704/371472 [3:09:34<16:31:13,  3.27it/s]
 48%|████▊     | 176705/371472 [3:09:34<16:23:07,  3.30it/s]
 48%|████▊     | 176706/371472 [3:09:35<16:08:15,  3.35it/s]
 48%|████▊     | 176707/371472 [3:09:35<15:52:14,  3.41it/s]
 48%|████▊     | 176708/371472 [3:09:35<16:06:45,  3.36it/s]
 48%|████▊     | 176709/371472 [3:09:36<15:58:23,  3.39it/s]
 48%|████▊     | 176710/371472 [3:09:36<15:27:10,  3.50it/s]
 48%|████▊     | 176711/371472 [3:09:36<15:52:58,  3.41it/s]
 48%|████▊     | 176712/371472 [3:09:36<15:47:52,  3.42it/s]
 48%|████▊     | 176713/371472 [3:09:37<15:32:11,  3.48it/s]
 48%|████▊     | 176714/371472 [3:09:37<15:25:02,  3.51it/s]
 48%|████▊     | 176715/371472 [3:09:37<16:23:02,  3.30it/s]
 48%|████▊     | 176716/371472 [3:09:38<16:11:47,  3.34it/s]
 48%|████▊     | 176717/371472 [3:09:38<16:28:26,  3.28it/s]
 48%|████▊     | 176718/371472 [3:09:38<17:14:15,  3.14it/s]
 48%|████▊     | 176719/371472 [3:09:39<16:56:37,  3.19it/s]
 48%|████▊     | 176720/371472 [3:09:39<16:32:27,  3.27it/s]
                                                            
{'loss': 2.9249, 'learning_rate': 5.7209808442328e-07, 'epoch': 7.61}
+
 48%|████▊     | 176720/371472 [3:09:39<16:32:27,  3.27it/s]
 48%|████▊     | 176721/371472 [3:09:39<16:24:02,  3.30it/s]
 48%|████▊     | 176722/371472 [3:09:40<15:56:19,  3.39it/s]
 48%|████▊     | 176723/371472 [3:09:40<15:28:40,  3.50it/s]
 48%|████▊     | 176724/371472 [3:09:40<16:05:29,  3.36it/s]
 48%|████▊     | 176725/371472 [3:09:40<16:07:50,  3.35it/s]
 48%|████▊     | 176726/371472 [3:09:41<15:52:27,  3.41it/s]
 48%|████▊     | 176727/371472 [3:09:41<16:22:21,  3.30it/s]
 48%|████▊     | 176728/371472 [3:09:41<15:55:01,  3.40it/s]
 48%|████▊     | 176729/371472 [3:09:42<16:31:07,  3.27it/s]
 48%|████▊     | 176730/371472 [3:09:42<16:32:14,  3.27it/s]
 48%|████▊     | 176731/371472 [3:09:42<15:59:40,  3.38it/s]
 48%|████▊     | 176732/371472 [3:09:42<15:36:52,  3.46it/s]
 48%|████▊     | 176733/371472 [3:09:43<15:46:22,  3.43it/s]
 48%|████▊     | 176734/371472 [3:09:43<18:14:11,  2.97it/s]
 48%|████▊     | 176735/371472 [3:09:43<17:20:28,  3.12it/s]
 48%|████▊     | 176736/371472 [3:09:44<17:09:36,  3.15it/s]
 48%|████▊     | 176737/371472 [3:09:44<16:35:54,  3.26it/s]
 48%|████▊     | 176738/371472 [3:09:44<16:25:00,  3.29it/s]
 48%|████▊     | 176739/371472 [3:09:45<16:10:23,  3.34it/s]
 48%|████▊     | 176740/371472 [3:09:45<15:49:16,  3.42it/s]
                                                            
{'loss': 2.7948, 'learning_rate': 5.72049602447801e-07, 'epoch': 7.61}
+
 48%|████▊     | 176740/371472 [3:09:45<15:49:16,  3.42it/s]
 48%|████▊     | 176741/371472 [3:09:45<16:36:25,  3.26it/s]
 48%|████▊     | 176742/371472 [3:09:46<17:09:04,  3.15it/s]
 48%|████▊     | 176743/371472 [3:09:46<17:09:46,  3.15it/s]
 48%|████▊     | 176744/371472 [3:09:46<16:59:00,  3.18it/s]
 48%|████▊     | 176745/371472 [3:09:47<17:12:16,  3.14it/s]
 48%|████▊     | 176746/371472 [3:09:47<17:02:50,  3.17it/s]
 48%|████▊     | 176747/371472 [3:09:47<17:09:52,  3.15it/s]
 48%|████▊     | 176748/371472 [3:09:48<17:04:25,  3.17it/s]
 48%|████▊     | 176749/371472 [3:09:48<16:43:13,  3.23it/s]
 48%|████▊     | 176750/371472 [3:09:48<16:28:56,  3.28it/s]
 48%|████▊     | 176751/371472 [3:09:48<16:16:26,  3.32it/s]
 48%|████▊     | 176752/371472 [3:09:49<15:48:02,  3.42it/s]
 48%|████▊     | 176753/371472 [3:09:49<15:22:38,  3.52it/s]
 48%|████▊     | 176754/371472 [3:09:49<15:49:02,  3.42it/s]
 48%|████▊     | 176755/371472 [3:09:50<17:08:59,  3.15it/s]
 48%|████▊     | 176756/371472 [3:09:50<18:16:10,  2.96it/s]
 48%|████▊     | 176757/371472 [3:09:50<18:35:14,  2.91it/s]
 48%|████▊     | 176758/371472 [3:09:51<18:02:27,  3.00it/s]
 48%|████▊     | 176759/371472 [3:09:51<17:33:08,  3.08it/s]
 48%|████▊     | 176760/371472 [3:09:51<17:05:17,  3.17it/s]
                                                            
{'loss': 2.917, 'learning_rate': 5.720011204723221e-07, 'epoch': 7.61}
+
 48%|████▊     | 176760/371472 [3:09:51<17:05:17,  3.17it/s]
 48%|████▊     | 176761/371472 [3:09:52<17:01:33,  3.18it/s]
 48%|████▊     | 176762/371472 [3:09:52<16:24:26,  3.30it/s]
 48%|████▊     | 176763/371472 [3:09:52<15:59:11,  3.38it/s]
 48%|████▊     | 176764/371472 [3:09:52<16:46:30,  3.22it/s]
 48%|████▊     | 176765/371472 [3:09:53<16:57:14,  3.19it/s]
 48%|████▊     | 176766/371472 [3:09:53<16:28:55,  3.28it/s]
 48%|████▊     | 176767/371472 [3:09:53<15:53:00,  3.41it/s]
 48%|████▊     | 176768/371472 [3:09:54<17:41:21,  3.06it/s]
 48%|████▊     | 176769/371472 [3:09:54<16:57:22,  3.19it/s]
 48%|████▊     | 176770/371472 [3:09:54<16:37:24,  3.25it/s]
 48%|████▊     | 176771/371472 [3:09:55<16:35:51,  3.26it/s]
 48%|████▊     | 176772/371472 [3:09:55<19:23:57,  2.79it/s]
 48%|████▊     | 176773/371472 [3:09:55<18:05:07,  2.99it/s]
 48%|████▊     | 176774/371472 [3:09:56<17:53:10,  3.02it/s]
 48%|████▊     | 176775/371472 [3:09:56<16:56:06,  3.19it/s]
 48%|████▊     | 176776/371472 [3:09:56<17:17:27,  3.13it/s]
 48%|████▊     | 176777/371472 [3:09:57<16:47:20,  3.22it/s]
 48%|████▊     | 176778/371472 [3:09:57<16:15:14,  3.33it/s]
 48%|████▊     | 176779/371472 [3:09:57<16:11:27,  3.34it/s]
 48%|████▊     | 176780/371472 [3:09:58<17:24:02,  3.11it/s]
                                                            
{'loss': 2.9814, 'learning_rate': 5.719526384968433e-07, 'epoch': 7.61}
+
 48%|████▊     | 176780/371472 [3:09:58<17:24:02,  3.11it/s]
 48%|████▊     | 176781/371472 [3:09:58<16:58:49,  3.18it/s]
 48%|████▊     | 176782/371472 [3:09:58<16:49:10,  3.22it/s]
 48%|████▊     | 176783/371472 [3:09:58<16:15:42,  3.33it/s]
 48%|████▊     | 176784/371472 [3:09:59<17:16:25,  3.13it/s]
 48%|████▊     | 176785/371472 [3:09:59<16:38:42,  3.25it/s]
 48%|████▊     | 176786/371472 [3:09:59<16:26:01,  3.29it/s]
 48%|████▊     | 176787/371472 [3:10:00<16:12:35,  3.34it/s]
 48%|████▊     | 176788/371472 [3:10:00<16:15:23,  3.33it/s]
 48%|████▊     | 176789/371472 [3:10:00<17:17:09,  3.13it/s]
 48%|████▊     | 176790/371472 [3:10:01<16:47:05,  3.22it/s]
 48%|████▊     | 176791/371472 [3:10:01<16:52:23,  3.20it/s]
 48%|████▊     | 176792/371472 [3:10:01<16:21:57,  3.30it/s]
 48%|████▊     | 176793/371472 [3:10:02<16:00:45,  3.38it/s]
 48%|████▊     | 176794/371472 [3:10:02<15:49:52,  3.42it/s]
 48%|████▊     | 176795/371472 [3:10:02<15:29:36,  3.49it/s]
 48%|████▊     | 176796/371472 [3:10:02<15:44:36,  3.43it/s]
 48%|████▊     | 176797/371472 [3:10:03<15:29:15,  3.49it/s]
 48%|████▊     | 176798/371472 [3:10:03<16:07:23,  3.35it/s]
 48%|████▊     | 176799/371472 [3:10:03<15:52:02,  3.41it/s]
 48%|████▊     | 176800/371472 [3:10:04<16:42:55,  3.24it/s]
                                                            
{'loss': 2.8168, 'learning_rate': 5.719041565213644e-07, 'epoch': 7.62}
+
 48%|████▊     | 176800/371472 [3:10:04<16:42:55,  3.24it/s]
 48%|████▊     | 176801/371472 [3:10:04<16:48:35,  3.22it/s]
 48%|████▊     | 176802/371472 [3:10:04<16:43:15,  3.23it/s]
 48%|████▊     | 176803/371472 [3:10:05<16:25:28,  3.29it/s]
 48%|████▊     | 176804/371472 [3:10:05<16:17:29,  3.32it/s]
 48%|████▊     | 176805/371472 [3:10:05<16:04:23,  3.36it/s]
 48%|████▊     | 176806/371472 [3:10:05<17:19:57,  3.12it/s]
 48%|████▊     | 176807/371472 [3:10:06<16:56:30,  3.19it/s]
 48%|████▊     | 176808/371472 [3:10:06<16:22:46,  3.30it/s]
 48%|████▊     | 176809/371472 [3:10:06<15:48:47,  3.42it/s]
 48%|████▊     | 176810/371472 [3:10:07<17:03:41,  3.17it/s]
 48%|████▊     | 176811/371472 [3:10:07<16:38:59,  3.25it/s]
 48%|████▊     | 176812/371472 [3:10:07<16:13:28,  3.33it/s]
 48%|████▊     | 176813/371472 [3:10:08<16:11:16,  3.34it/s]
 48%|████▊     | 176814/371472 [3:10:08<18:20:42,  2.95it/s]
 48%|████▊     | 176815/371472 [3:10:08<17:36:50,  3.07it/s]
 48%|████▊     | 176816/371472 [3:10:09<16:46:40,  3.22it/s]
 48%|████▊     | 176817/371472 [3:10:09<16:16:43,  3.32it/s]
 48%|████▊     | 176818/371472 [3:10:09<17:02:00,  3.17it/s]
 48%|████▊     | 176819/371472 [3:10:09<16:18:20,  3.32it/s]
 48%|████▊     | 176820/371472 [3:10:10<16:00:05,  3.38it/s]
                                                            
{'loss': 2.9025, 'learning_rate': 5.718556745458854e-07, 'epoch': 7.62}
+
 48%|████▊     | 176820/371472 [3:10:10<16:00:05,  3.38it/s]
 48%|████▊     | 176821/371472 [3:10:10<16:18:39,  3.31it/s]
 48%|████▊     | 176822/371472 [3:10:10<15:50:15,  3.41it/s]
 48%|████▊     | 176823/371472 [3:10:11<15:56:18,  3.39it/s]
 48%|████▊     | 176824/371472 [3:10:11<15:40:48,  3.45it/s]
 48%|████▊     | 176825/371472 [3:10:11<15:57:28,  3.39it/s]
 48%|████▊     | 176826/371472 [3:10:11<15:48:03,  3.42it/s]
 48%|████▊     | 176827/371472 [3:10:12<15:42:12,  3.44it/s]
 48%|████▊     | 176828/371472 [3:10:12<16:32:16,  3.27it/s]
 48%|████▊     | 176829/371472 [3:10:12<16:44:59,  3.23it/s]
 48%|████▊     | 176830/371472 [3:10:13<16:18:32,  3.32it/s]
 48%|████▊     | 176831/371472 [3:10:13<15:54:51,  3.40it/s]
 48%|████▊     | 176832/371472 [3:10:13<16:46:12,  3.22it/s]
 48%|████▊     | 176833/371472 [3:10:14<16:40:50,  3.24it/s]
 48%|████▊     | 176834/371472 [3:10:14<17:02:28,  3.17it/s]
 48%|████▊     | 176835/371472 [3:10:14<16:41:53,  3.24it/s]
 48%|████▊     | 176836/371472 [3:10:15<16:00:29,  3.38it/s]
 48%|████▊     | 176837/371472 [3:10:15<16:06:35,  3.36it/s]
 48%|████▊     | 176838/371472 [3:10:15<16:34:20,  3.26it/s]
 48%|████▊     | 176839/371472 [3:10:15<15:52:06,  3.41it/s]
 48%|████▊     | 176840/371472 [3:10:16<15:45:37,  3.43it/s]
                                                            
{'loss': 2.9491, 'learning_rate': 5.718071925704066e-07, 'epoch': 7.62}
+
 48%|████▊     | 176840/371472 [3:10:16<15:45:37,  3.43it/s]
 48%|████▊     | 176841/371472 [3:10:16<16:42:13,  3.24it/s]
 48%|████▊     | 176842/371472 [3:10:16<16:00:50,  3.38it/s]
 48%|████▊     | 176843/371472 [3:10:17<16:07:19,  3.35it/s]
 48%|████▊     | 176844/371472 [3:10:17<15:50:37,  3.41it/s]
 48%|████▊     | 176845/371472 [3:10:17<15:46:17,  3.43it/s]
 48%|████▊     | 176846/371472 [3:10:17<15:44:19,  3.43it/s]
 48%|████▊     | 176847/371472 [3:10:18<15:44:19,  3.43it/s]
 48%|████▊     | 176848/371472 [3:10:18<15:54:25,  3.40it/s]
 48%|████▊     | 176849/371472 [3:10:18<16:07:49,  3.35it/s]
 48%|████▊     | 176850/371472 [3:10:19<16:07:05,  3.35it/s]
 48%|████▊     | 176851/371472 [3:10:19<16:26:41,  3.29it/s]
 48%|████▊     | 176852/371472 [3:10:19<15:49:26,  3.42it/s]
 48%|████▊     | 176853/371472 [3:10:20<15:38:05,  3.46it/s]
 48%|████▊     | 176854/371472 [3:10:20<15:36:39,  3.46it/s]
 48%|████▊     | 176855/371472 [3:10:20<16:11:50,  3.34it/s]
 48%|████▊     | 176856/371472 [3:10:21<17:13:24,  3.14it/s]
 48%|████▊     | 176857/371472 [3:10:21<17:07:14,  3.16it/s]
 48%|████▊     | 176858/371472 [3:10:21<17:04:06,  3.17it/s]
 48%|████▊     | 176859/371472 [3:10:21<17:06:22,  3.16it/s]
 48%|████▊     | 176860/371472 [3:10:22<16:50:42,  3.21it/s]
                                                            
{'loss': 3.0033, 'learning_rate': 5.717587105949277e-07, 'epoch': 7.62}
+
 48%|████▊     | 176860/371472 [3:10:22<16:50:42,  3.21it/s]
 48%|████▊     | 176861/371472 [3:10:22<16:23:36,  3.30it/s]
 48%|████▊     | 176862/371472 [3:10:22<17:12:41,  3.14it/s]
 48%|████▊     | 176863/371472 [3:10:23<16:36:57,  3.25it/s]
 48%|████▊     | 176864/371472 [3:10:23<15:52:21,  3.41it/s]
 48%|████▊     | 176865/371472 [3:10:23<17:06:08,  3.16it/s]
 48%|████▊     | 176866/371472 [3:10:24<16:21:00,  3.31it/s]
 48%|████▊     | 176867/371472 [3:10:24<16:06:37,  3.36it/s]
 48%|████▊     | 176868/371472 [3:10:24<16:05:37,  3.36it/s]
 48%|████▊     | 176869/371472 [3:10:24<15:48:40,  3.42it/s]
 48%|████▊     | 176870/371472 [3:10:25<15:40:17,  3.45it/s]
 48%|████▊     | 176871/371472 [3:10:25<15:42:31,  3.44it/s]
 48%|████▊     | 176872/371472 [3:10:25<15:36:51,  3.46it/s]
 48%|████▊     | 176873/371472 [3:10:26<15:27:55,  3.50it/s]
 48%|████▊     | 176874/371472 [3:10:26<15:17:46,  3.53it/s]
 48%|████▊     | 176875/371472 [3:10:26<15:30:21,  3.49it/s]
 48%|████▊     | 176876/371472 [3:10:26<15:15:24,  3.54it/s]
 48%|████▊     | 176877/371472 [3:10:27<15:31:15,  3.48it/s]
 48%|████▊     | 176878/371472 [3:10:27<15:29:01,  3.49it/s]
 48%|████▊     | 176879/371472 [3:10:27<16:04:01,  3.36it/s]
 48%|████▊     | 176880/371472 [3:10:28<16:24:02,  3.30it/s]
                                                            
{'loss': 3.0039, 'learning_rate': 5.717102286194488e-07, 'epoch': 7.62}
+
 48%|████▊     | 176880/371472 [3:10:28<16:24:02,  3.30it/s]
 48%|████▊     | 176881/371472 [3:10:28<15:56:52,  3.39it/s]
 48%|████▊     | 176882/371472 [3:10:28<15:34:59,  3.47it/s]
 48%|████▊     | 176883/371472 [3:10:29<15:41:15,  3.45it/s]
 48%|████▊     | 176884/371472 [3:10:29<15:25:43,  3.50it/s]
 48%|████▊     | 176885/371472 [3:10:29<16:16:16,  3.32it/s]
 48%|████▊     | 176886/371472 [3:10:29<16:20:04,  3.31it/s]
 48%|████▊     | 176887/371472 [3:10:30<16:27:55,  3.28it/s]
 48%|████▊     | 176888/371472 [3:10:30<15:58:20,  3.38it/s]
 48%|████▊     | 176889/371472 [3:10:30<15:43:06,  3.44it/s]
 48%|████▊     | 176890/371472 [3:10:31<15:42:26,  3.44it/s]
 48%|████▊     | 176891/371472 [3:10:31<15:45:42,  3.43it/s]
 48%|████▊     | 176892/371472 [3:10:31<15:36:36,  3.46it/s]
 48%|████▊     | 176893/371472 [3:10:31<15:27:25,  3.50it/s]
 48%|████▊     | 176894/371472 [3:10:32<15:00:35,  3.60it/s]
 48%|████▊     | 176895/371472 [3:10:32<15:07:01,  3.58it/s]
 48%|████▊     | 176896/371472 [3:10:32<15:50:00,  3.41it/s]
 48%|████▊     | 176897/371472 [3:10:33<16:21:29,  3.30it/s]
 48%|████▊     | 176898/371472 [3:10:33<16:03:33,  3.37it/s]
 48%|████▊     | 176899/371472 [3:10:33<16:02:35,  3.37it/s]
 48%|████▊     | 176900/371472 [3:10:34<15:58:14,  3.38it/s]
                                                            
{'loss': 3.0975, 'learning_rate': 5.716617466439698e-07, 'epoch': 7.62}
+
 48%|████▊     | 176900/371472 [3:10:34<15:58:14,  3.38it/s]
 48%|████▊     | 176901/371472 [3:10:34<15:28:51,  3.49it/s]
 48%|████▊     | 176902/371472 [3:10:34<15:05:08,  3.58it/s]
 48%|████▊     | 176903/371472 [3:10:34<15:27:51,  3.49it/s]
 48%|████▊     | 176904/371472 [3:10:35<16:05:31,  3.36it/s]
 48%|████▊     | 176905/371472 [3:10:35<16:01:10,  3.37it/s]
 48%|████▊     | 176906/371472 [3:10:35<16:09:02,  3.35it/s]
 48%|████▊     | 176907/371472 [3:10:36<16:49:16,  3.21it/s]
 48%|████▊     | 176908/371472 [3:10:36<17:21:43,  3.11it/s]
 48%|████▊     | 176909/371472 [3:10:36<16:33:50,  3.26it/s]
 48%|████▊     | 176910/371472 [3:10:36<16:14:05,  3.33it/s]
 48%|████▊     | 176911/371472 [3:10:37<16:27:49,  3.28it/s]
 48%|████▊     | 176912/371472 [3:10:37<16:10:15,  3.34it/s]
 48%|████▊     | 176913/371472 [3:10:37<16:24:12,  3.29it/s]
 48%|████▊     | 176914/371472 [3:10:38<16:16:20,  3.32it/s]
 48%|████▊     | 176915/371472 [3:10:38<16:18:55,  3.31it/s]
 48%|████▊     | 176916/371472 [3:10:38<15:52:36,  3.40it/s]
 48%|████▊     | 176917/371472 [3:10:39<15:43:50,  3.44it/s]
 48%|████▊     | 176918/371472 [3:10:39<15:33:40,  3.47it/s]
 48%|████▊     | 176919/371472 [3:10:39<15:22:17,  3.52it/s]
 48%|████▊     | 176920/371472 [3:10:39<15:44:18,  3.43it/s]
                                                            
{'loss': 2.8998, 'learning_rate': 5.71613264668491e-07, 'epoch': 7.62}
+
 48%|████▊     | 176920/371472 [3:10:39<15:44:18,  3.43it/s]
 48%|████▊     | 176921/371472 [3:10:40<15:56:10,  3.39it/s]
 48%|████▊     | 176922/371472 [3:10:40<16:25:30,  3.29it/s]
 48%|████▊     | 176923/371472 [3:10:40<16:38:44,  3.25it/s]
 48%|████▊     | 176924/371472 [3:10:41<16:11:19,  3.34it/s]
 48%|████▊     | 176925/371472 [3:10:41<15:43:23,  3.44it/s]
 48%|████▊     | 176926/371472 [3:10:41<15:46:20,  3.43it/s]
 48%|████▊     | 176927/371472 [3:10:42<16:50:43,  3.21it/s]
 48%|████▊     | 176928/371472 [3:10:42<16:43:17,  3.23it/s]
 48%|████▊     | 176929/371472 [3:10:42<16:17:59,  3.32it/s]
 48%|████▊     | 176930/371472 [3:10:42<15:53:18,  3.40it/s]
 48%|████▊     | 176931/371472 [3:10:43<15:41:56,  3.44it/s]
 48%|████▊     | 176932/371472 [3:10:43<16:17:46,  3.32it/s]
 48%|████▊     | 176933/371472 [3:10:43<16:15:50,  3.32it/s]
 48%|████▊     | 176934/371472 [3:10:44<16:04:44,  3.36it/s]
 48%|████▊     | 176935/371472 [3:10:44<17:08:26,  3.15it/s]
 48%|████▊     | 176936/371472 [3:10:44<16:46:48,  3.22it/s]
 48%|████▊     | 176937/371472 [3:10:45<16:15:40,  3.32it/s]
 48%|████▊     | 176938/371472 [3:10:45<16:12:10,  3.34it/s]
 48%|████▊     | 176939/371472 [3:10:45<15:51:48,  3.41it/s]
 48%|████▊     | 176940/371472 [3:10:45<15:48:33,  3.42it/s]
                                                            
{'loss': 2.8901, 'learning_rate': 5.715647826930122e-07, 'epoch': 7.62}
+
 48%|████▊     | 176940/371472 [3:10:45<15:48:33,  3.42it/s]
 48%|████▊     | 176941/371472 [3:10:46<15:46:51,  3.42it/s]
 48%|████▊     | 176942/371472 [3:10:46<15:53:20,  3.40it/s]
 48%|████▊     | 176943/371472 [3:10:46<16:34:12,  3.26it/s]
 48%|████▊     | 176944/371472 [3:10:47<16:20:04,  3.31it/s]
 48%|████▊     | 176945/371472 [3:10:47<16:33:23,  3.26it/s]
 48%|████▊     | 176946/371472 [3:10:47<16:44:41,  3.23it/s]
 48%|████▊     | 176947/371472 [3:10:48<16:30:45,  3.27it/s]
 48%|████▊     | 176948/371472 [3:10:48<16:04:41,  3.36it/s]
 48%|████▊     | 176949/371472 [3:10:48<15:55:15,  3.39it/s]
 48%|████▊     | 176950/371472 [3:10:48<16:16:02,  3.32it/s]
 48%|████▊     | 176951/371472 [3:10:49<15:44:27,  3.43it/s]
 48%|████▊     | 176952/371472 [3:10:49<15:19:46,  3.52it/s]
 48%|████▊     | 176953/371472 [3:10:49<16:26:32,  3.29it/s]
 48%|████▊     | 176954/371472 [3:10:50<16:10:00,  3.34it/s]
 48%|████▊     | 176955/371472 [3:10:50<16:17:02,  3.32it/s]
 48%|████▊     | 176956/371472 [3:10:50<16:10:31,  3.34it/s]
 48%|████▊     | 176957/371472 [3:10:51<15:46:59,  3.42it/s]
 48%|████▊     | 176958/371472 [3:10:51<15:38:54,  3.45it/s]
 48%|████▊     | 176959/371472 [3:10:51<15:33:11,  3.47it/s]
 48%|████▊     | 176960/371472 [3:10:51<15:33:01,  3.47it/s]
                                                            
{'loss': 2.8183, 'learning_rate': 5.715163007175333e-07, 'epoch': 7.62}
+
 48%|████▊     | 176960/371472 [3:10:51<15:33:01,  3.47it/s]
 48%|████▊     | 176961/371472 [3:10:52<15:30:38,  3.48it/s]
 48%|████▊     | 176962/371472 [3:10:52<15:39:56,  3.45it/s]
 48%|████▊     | 176963/371472 [3:10:52<15:51:41,  3.41it/s]
 48%|████▊     | 176964/371472 [3:10:53<16:27:52,  3.28it/s]
 48%|████▊     | 176965/371472 [3:10:53<16:26:18,  3.29it/s]
 48%|████▊     | 176966/371472 [3:10:53<16:43:55,  3.23it/s]
 48%|████▊     | 176967/371472 [3:10:54<16:17:15,  3.32it/s]
 48%|████▊     | 176968/371472 [3:10:54<16:31:41,  3.27it/s]
 48%|████▊     | 176969/371472 [3:10:54<16:06:54,  3.35it/s]
 48%|████▊     | 176970/371472 [3:10:54<15:45:03,  3.43it/s]
 48%|████▊     | 176971/371472 [3:10:55<15:46:28,  3.43it/s]
 48%|████▊     | 176972/371472 [3:10:55<15:29:11,  3.49it/s]
 48%|████▊     | 176973/371472 [3:10:55<15:42:07,  3.44it/s]
 48%|████▊     | 176974/371472 [3:10:56<15:49:51,  3.41it/s]
 48%|████▊     | 176975/371472 [3:10:56<15:49:57,  3.41it/s]
 48%|████▊     | 176976/371472 [3:10:56<15:36:35,  3.46it/s]
 48%|████▊     | 176977/371472 [3:10:56<16:22:57,  3.30it/s]
 48%|████▊     | 176978/371472 [3:10:57<17:30:38,  3.09it/s]
 48%|████▊     | 176979/371472 [3:10:57<17:12:50,  3.14it/s]
 48%|████▊     | 176980/371472 [3:10:57<17:04:34,  3.16it/s]
                                                            
{'loss': 2.7321, 'learning_rate': 5.714678187420543e-07, 'epoch': 7.62}
+
 48%|████▊     | 176980/371472 [3:10:57<17:04:34,  3.16it/s]
 48%|████▊     | 176981/371472 [3:10:58<17:44:54,  3.04it/s]
 48%|████▊     | 176982/371472 [3:10:58<17:04:39,  3.16it/s]
 48%|████▊     | 176983/371472 [3:10:58<16:39:24,  3.24it/s]
 48%|████▊     | 176984/371472 [3:10:59<16:12:18,  3.33it/s]
 48%|████▊     | 176985/371472 [3:10:59<16:03:56,  3.36it/s]
 48%|████▊     | 176986/371472 [3:10:59<16:12:49,  3.33it/s]
 48%|████▊     | 176987/371472 [3:11:00<16:06:41,  3.35it/s]
 48%|████▊     | 176988/371472 [3:11:00<16:15:29,  3.32it/s]
 48%|████▊     | 176989/371472 [3:11:00<17:02:27,  3.17it/s]
 48%|████▊     | 176990/371472 [3:11:01<17:07:00,  3.16it/s]
 48%|████▊     | 176991/371472 [3:11:01<16:53:44,  3.20it/s]
 48%|████▊     | 176992/371472 [3:11:01<16:47:34,  3.22it/s]
 48%|████▊     | 176993/371472 [3:11:01<16:20:38,  3.31it/s]
 48%|████▊     | 176994/371472 [3:11:02<16:14:58,  3.32it/s]
 48%|████▊     | 176995/371472 [3:11:02<16:51:01,  3.21it/s]
 48%|████▊     | 176996/371472 [3:11:02<17:50:20,  3.03it/s]
 48%|████▊     | 176997/371472 [3:11:03<17:27:00,  3.10it/s]
 48%|████▊     | 176998/371472 [3:11:03<20:03:52,  2.69it/s]
 48%|████▊     | 176999/371472 [3:11:03<18:30:48,  2.92it/s]
 48%|████▊     | 177000/371472 [3:11:04<17:39:15,  3.06it/s]
                                                            
{'loss': 2.7715, 'learning_rate': 5.714193367665754e-07, 'epoch': 7.62}
+
 48%|████▊     | 177000/371472 [3:11:04<17:39:15,  3.06it/s]
 48%|████▊     | 177001/371472 [3:11:04<16:57:05,  3.19it/s]
 48%|████▊     | 177002/371472 [3:11:04<16:28:39,  3.28it/s]
 48%|████▊     | 177003/371472 [3:11:05<16:13:46,  3.33it/s]
 48%|████▊     | 177004/371472 [3:11:05<16:41:23,  3.24it/s]
 48%|████▊     | 177005/371472 [3:11:05<16:19:08,  3.31it/s]
 48%|████▊     | 177006/371472 [3:11:06<15:48:51,  3.42it/s]
 48%|████▊     | 177007/371472 [3:11:06<15:36:25,  3.46it/s]
 48%|████▊     | 177008/371472 [3:11:06<16:14:35,  3.33it/s]
 48%|████▊     | 177009/371472 [3:11:06<15:34:38,  3.47it/s]
 48%|████▊     | 177010/371472 [3:11:07<15:34:06,  3.47it/s]
 48%|████▊     | 177011/371472 [3:11:07<15:40:52,  3.44it/s]
 48%|████▊     | 177012/371472 [3:11:07<15:56:41,  3.39it/s]
 48%|████▊     | 177013/371472 [3:11:08<16:16:59,  3.32it/s]
 48%|████▊     | 177014/371472 [3:11:08<15:52:18,  3.40it/s]
 48%|████▊     | 177015/371472 [3:11:08<15:58:42,  3.38it/s]
 48%|████▊     | 177016/371472 [3:11:08<16:15:28,  3.32it/s]
 48%|████▊     | 177017/371472 [3:11:09<16:19:07,  3.31it/s]
 48%|████▊     | 177018/371472 [3:11:09<15:54:28,  3.40it/s]
 48%|████▊     | 177019/371472 [3:11:09<15:48:40,  3.42it/s]
 48%|████▊     | 177020/371472 [3:11:10<15:46:31,  3.42it/s]
                                                            
{'loss': 2.9246, 'learning_rate': 5.713708547910966e-07, 'epoch': 7.62}
+
 48%|████▊     | 177020/371472 [3:11:10<15:46:31,  3.42it/s]
 48%|████▊     | 177021/371472 [3:11:10<15:34:56,  3.47it/s]
 48%|████▊     | 177022/371472 [3:11:10<16:11:16,  3.34it/s]
 48%|████▊     | 177023/371472 [3:11:11<17:01:06,  3.17it/s]
 48%|████▊     | 177024/371472 [3:11:11<16:34:13,  3.26it/s]
 48%|████▊     | 177025/371472 [3:11:11<16:24:39,  3.29it/s]
 48%|████▊     | 177026/371472 [3:11:11<16:00:58,  3.37it/s]
 48%|████▊     | 177027/371472 [3:11:12<16:02:12,  3.37it/s]
 48%|████▊     | 177028/371472 [3:11:12<15:41:59,  3.44it/s]
 48%|████▊     | 177029/371472 [3:11:12<15:36:48,  3.46it/s]
 48%|████▊     | 177030/371472 [3:11:13<15:36:17,  3.46it/s]
 48%|████▊     | 177031/371472 [3:11:13<15:26:25,  3.50it/s]
 48%|████▊     | 177032/371472 [3:11:13<16:33:06,  3.26it/s]
 48%|████▊     | 177033/371472 [3:11:14<16:27:37,  3.28it/s]
 48%|████▊     | 177034/371472 [3:11:14<16:32:19,  3.27it/s]
 48%|████▊     | 177035/371472 [3:11:14<17:23:56,  3.10it/s]
 48%|████▊     | 177036/371472 [3:11:15<17:06:07,  3.16it/s]
 48%|████▊     | 177037/371472 [3:11:15<16:11:53,  3.33it/s]
 48%|████▊     | 177038/371472 [3:11:15<15:48:35,  3.42it/s]
 48%|████▊     | 177039/371472 [3:11:15<15:32:59,  3.47it/s]
 48%|████▊     | 177040/371472 [3:11:16<15:37:18,  3.46it/s]
                                                            
{'loss': 2.8889, 'learning_rate': 5.713223728156176e-07, 'epoch': 7.63}
+
 48%|████▊     | 177040/371472 [3:11:16<15:37:18,  3.46it/s]
 48%|████▊     | 177041/371472 [3:11:16<16:35:14,  3.26it/s]
 48%|████▊     | 177042/371472 [3:11:16<16:34:04,  3.26it/s]
 48%|████▊     | 177043/371472 [3:11:17<15:51:58,  3.40it/s]
 48%|████▊     | 177044/371472 [3:11:17<15:59:19,  3.38it/s]
 48%|████▊     | 177045/371472 [3:11:17<16:42:12,  3.23it/s]
 48%|████▊     | 177046/371472 [3:11:18<19:50:59,  2.72it/s]
 48%|████▊     | 177047/371472 [3:11:18<18:44:22,  2.88it/s]
 48%|████▊     | 177048/371472 [3:11:18<17:42:02,  3.05it/s]
 48%|████▊     | 177049/371472 [3:11:19<17:06:24,  3.16it/s]
 48%|████▊     | 177050/371472 [3:11:19<16:12:29,  3.33it/s]
 48%|████▊     | 177051/371472 [3:11:19<16:07:12,  3.35it/s]
 48%|████▊     | 177052/371472 [3:11:19<16:40:14,  3.24it/s]
 48%|████▊     | 177053/371472 [3:11:20<16:53:14,  3.20it/s]
 48%|████▊     | 177054/371472 [3:11:20<16:30:20,  3.27it/s]
 48%|████▊     | 177055/371472 [3:11:20<16:01:14,  3.37it/s]
 48%|████▊     | 177056/371472 [3:11:21<16:31:11,  3.27it/s]
 48%|████▊     | 177057/371472 [3:11:21<16:26:02,  3.29it/s]
 48%|████▊     | 177058/371472 [3:11:21<16:38:12,  3.25it/s]
 48%|████▊     | 177059/371472 [3:11:22<17:57:33,  3.01it/s]
 48%|████▊     | 177060/371472 [3:11:22<17:17:27,  3.12it/s]
                                                            
{'loss': 2.9614, 'learning_rate': 5.712738908401386e-07, 'epoch': 7.63}
+
 48%|████▊     | 177060/371472 [3:11:22<17:17:27,  3.12it/s]
 48%|████▊     | 177061/371472 [3:11:22<16:53:44,  3.20it/s]
 48%|████▊     | 177062/371472 [3:11:23<16:29:51,  3.27it/s]
 48%|████▊     | 177063/371472 [3:11:23<16:32:32,  3.26it/s]
 48%|████▊     | 177064/371472 [3:11:23<16:08:59,  3.34it/s]
 48%|████▊     | 177065/371472 [3:11:23<16:14:15,  3.33it/s]
 48%|████▊     | 177066/371472 [3:11:24<16:00:13,  3.37it/s]
 48%|████▊     | 177067/371472 [3:11:24<16:16:08,  3.32it/s]
 48%|████▊     | 177068/371472 [3:11:24<16:34:08,  3.26it/s]
 48%|████▊     | 177069/371472 [3:11:25<16:20:29,  3.30it/s]
 48%|████▊     | 177070/371472 [3:11:25<16:11:18,  3.34it/s]
 48%|████▊     | 177071/371472 [3:11:25<16:45:43,  3.22it/s]
 48%|████▊     | 177072/371472 [3:11:26<16:07:24,  3.35it/s]
 48%|████▊     | 177073/371472 [3:11:26<16:24:05,  3.29it/s]
 48%|████▊     | 177074/371472 [3:11:26<16:38:45,  3.24it/s]
 48%|████▊     | 177075/371472 [3:11:27<17:08:52,  3.15it/s]
 48%|████▊     | 177076/371472 [3:11:27<16:40:09,  3.24it/s]
 48%|████▊     | 177077/371472 [3:11:27<16:38:39,  3.24it/s]
 48%|████▊     | 177078/371472 [3:11:27<16:27:56,  3.28it/s]
 48%|████▊     | 177079/371472 [3:11:28<16:46:57,  3.22it/s]
 48%|████▊     | 177080/371472 [3:11:28<16:24:51,  3.29it/s]
                                                            
{'loss': 2.9824, 'learning_rate': 5.712254088646599e-07, 'epoch': 7.63}
+
 48%|████▊     | 177080/371472 [3:11:28<16:24:51,  3.29it/s]
 48%|████▊     | 177081/371472 [3:11:28<16:25:52,  3.29it/s]
 48%|████▊     | 177082/371472 [3:11:29<16:13:05,  3.33it/s]
 48%|████▊     | 177083/371472 [3:11:29<16:03:41,  3.36it/s]
 48%|████▊     | 177084/371472 [3:11:29<15:55:29,  3.39it/s]
 48%|████▊     | 177085/371472 [3:11:29<15:45:38,  3.43it/s]
 48%|████▊     | 177086/371472 [3:11:30<16:04:50,  3.36it/s]
 48%|████▊     | 177087/371472 [3:11:30<15:43:40,  3.43it/s]
 48%|████▊     | 177088/371472 [3:11:30<16:05:02,  3.36it/s]
 48%|████▊     | 177089/371472 [3:11:31<15:50:05,  3.41it/s]
 48%|████▊     | 177090/371472 [3:11:31<15:32:15,  3.48it/s]
 48%|████▊     | 177091/371472 [3:11:31<15:19:29,  3.52it/s]
 48%|████▊     | 177092/371472 [3:11:32<15:24:28,  3.50it/s]
 48%|████▊     | 177093/371472 [3:11:32<15:13:00,  3.55it/s]
 48%|████▊     | 177094/371472 [3:11:32<15:33:00,  3.47it/s]
 48%|████▊     | 177095/371472 [3:11:32<16:19:58,  3.31it/s]
 48%|████▊     | 177096/371472 [3:11:33<16:13:42,  3.33it/s]
 48%|████▊     | 177097/371472 [3:11:33<15:57:06,  3.38it/s]
 48%|████▊     | 177098/371472 [3:11:33<15:50:05,  3.41it/s]
 48%|████▊     | 177099/371472 [3:11:34<15:31:48,  3.48it/s]
 48%|████▊     | 177100/371472 [3:11:34<15:33:21,  3.47it/s]
                                                            
{'loss': 2.917, 'learning_rate': 5.71176926889181e-07, 'epoch': 7.63}
+
 48%|████▊     | 177100/371472 [3:11:34<15:33:21,  3.47it/s]
 48%|████▊     | 177101/371472 [3:11:34<15:41:42,  3.44it/s]
 48%|████▊     | 177102/371472 [3:11:34<15:48:54,  3.41it/s]
 48%|████▊     | 177103/371472 [3:11:35<15:36:35,  3.46it/s]
 48%|████▊     | 177104/371472 [3:11:35<15:32:46,  3.47it/s]
 48%|████▊     | 177105/371472 [3:11:35<15:54:38,  3.39it/s]
 48%|████▊     | 177106/371472 [3:11:36<16:00:26,  3.37it/s]
 48%|████▊     | 177107/371472 [3:11:36<15:54:48,  3.39it/s]
 48%|████▊     | 177108/371472 [3:11:36<15:43:58,  3.43it/s]
 48%|████▊     | 177109/371472 [3:11:37<15:48:39,  3.41it/s]
 48%|████▊     | 177110/371472 [3:11:37<15:47:34,  3.42it/s]
 48%|████▊     | 177111/371472 [3:11:37<15:31:30,  3.48it/s]
 48%|████▊     | 177112/371472 [3:11:37<15:57:07,  3.38it/s]
 48%|████▊     | 177113/371472 [3:11:38<15:38:15,  3.45it/s]
 48%|████▊     | 177114/371472 [3:11:38<15:30:32,  3.48it/s]
 48%|████▊     | 177115/371472 [3:11:38<15:34:49,  3.47it/s]
 48%|████▊     | 177116/371472 [3:11:39<15:15:56,  3.54it/s]
 48%|████▊     | 177117/371472 [3:11:39<15:27:08,  3.49it/s]
 48%|████▊     | 177118/371472 [3:11:39<15:44:15,  3.43it/s]
 48%|████▊     | 177119/371472 [3:11:39<15:52:03,  3.40it/s]
 48%|████▊     | 177120/371472 [3:11:40<15:41:50,  3.44it/s]
                                                            
{'loss': 3.0267, 'learning_rate': 5.71128444913702e-07, 'epoch': 7.63}
+
 48%|████▊     | 177120/371472 [3:11:40<15:41:50,  3.44it/s]
 48%|████▊     | 177121/371472 [3:11:40<16:34:42,  3.26it/s]
 48%|████▊     | 177122/371472 [3:11:40<16:37:21,  3.25it/s]
 48%|████▊     | 177123/371472 [3:11:41<16:17:41,  3.31it/s]
 48%|████▊     | 177124/371472 [3:11:41<16:15:16,  3.32it/s]
 48%|████▊     | 177125/371472 [3:11:41<17:09:13,  3.15it/s]
 48%|████▊     | 177126/371472 [3:11:42<16:48:06,  3.21it/s]
 48%|████▊     | 177127/371472 [3:11:42<17:47:54,  3.03it/s]
 48%|████▊     | 177128/371472 [3:11:42<17:23:41,  3.10it/s]
 48%|████▊     | 177129/371472 [3:11:43<16:50:36,  3.21it/s]
 48%|████▊     | 177130/371472 [3:11:43<16:32:31,  3.26it/s]
 48%|████▊     | 177131/371472 [3:11:43<16:15:50,  3.32it/s]
 48%|████▊     | 177132/371472 [3:11:43<16:10:09,  3.34it/s]
 48%|████▊     | 177133/371472 [3:11:44<15:50:40,  3.41it/s]
 48%|████▊     | 177134/371472 [3:11:44<15:28:25,  3.49it/s]
 48%|████▊     | 177135/371472 [3:11:44<15:26:44,  3.49it/s]
 48%|████▊     | 177136/371472 [3:11:45<15:42:57,  3.43it/s]
 48%|████▊     | 177137/371472 [3:11:45<15:43:41,  3.43it/s]
 48%|████▊     | 177138/371472 [3:11:45<16:52:22,  3.20it/s]
 48%|████▊     | 177139/371472 [3:11:46<16:41:28,  3.23it/s]
 48%|████▊     | 177140/371472 [3:11:46<16:18:35,  3.31it/s]
                                                            
{'loss': 2.9144, 'learning_rate': 5.710799629382231e-07, 'epoch': 7.63}
+
 48%|████▊     | 177140/371472 [3:11:46<16:18:35,  3.31it/s]
 48%|████▊     | 177141/371472 [3:11:46<17:44:59,  3.04it/s]
 48%|████▊     | 177142/371472 [3:11:46<16:50:42,  3.20it/s]
 48%|████▊     | 177143/371472 [3:11:47<16:55:43,  3.19it/s]
 48%|████▊     | 177144/371472 [3:11:47<16:21:23,  3.30it/s]
 48%|████▊     | 177145/371472 [3:11:47<16:15:53,  3.32it/s]
 48%|████▊     | 177146/371472 [3:11:48<17:39:59,  3.06it/s]
 48%|████▊     | 177147/371472 [3:11:48<17:57:17,  3.01it/s]
 48%|████▊     | 177148/371472 [3:11:48<17:25:33,  3.10it/s]
 48%|████▊     | 177149/371472 [3:11:49<16:59:32,  3.18it/s]
 48%|████▊     | 177150/371472 [3:11:49<16:59:06,  3.18it/s]
 48%|████▊     | 177151/371472 [3:11:49<16:34:32,  3.26it/s]
 48%|████▊     | 177152/371472 [3:11:50<16:30:21,  3.27it/s]
 48%|████▊     | 177153/371472 [3:11:50<16:29:12,  3.27it/s]
 48%|████▊     | 177154/371472 [3:11:50<16:14:20,  3.32it/s]
 48%|████▊     | 177155/371472 [3:11:50<16:18:04,  3.31it/s]
 48%|████▊     | 177156/371472 [3:11:51<16:20:52,  3.30it/s]
 48%|████▊     | 177157/371472 [3:11:51<16:33:12,  3.26it/s]
 48%|████▊     | 177158/371472 [3:11:51<15:49:16,  3.41it/s]
 48%|████▊     | 177159/371472 [3:11:52<16:11:41,  3.33it/s]
 48%|████▊     | 177160/371472 [3:11:52<16:06:12,  3.35it/s]
                                                            
{'loss': 2.7737, 'learning_rate': 5.710314809627443e-07, 'epoch': 7.63}
+
 48%|████▊     | 177160/371472 [3:11:52<16:06:12,  3.35it/s]
 48%|████▊     | 177161/371472 [3:11:52<16:41:47,  3.23it/s]
 48%|████▊     | 177162/371472 [3:11:53<16:03:36,  3.36it/s]
 48%|████▊     | 177163/371472 [3:11:53<16:33:28,  3.26it/s]
 48%|████▊     | 177164/371472 [3:11:53<16:11:36,  3.33it/s]
 48%|████▊     | 177165/371472 [3:11:54<16:16:34,  3.32it/s]
 48%|████▊     | 177166/371472 [3:11:54<18:03:17,  2.99it/s]
 48%|████▊     | 177167/371472 [3:11:54<18:15:41,  2.96it/s]
 48%|████▊     | 177168/371472 [3:11:55<17:23:06,  3.10it/s]
 48%|████▊     | 177169/371472 [3:11:55<16:41:13,  3.23it/s]
 48%|████▊     | 177170/371472 [3:11:55<16:33:04,  3.26it/s]
 48%|████▊     | 177171/371472 [3:11:55<17:19:05,  3.12it/s]
 48%|████▊     | 177172/371472 [3:11:56<17:56:16,  3.01it/s]
 48%|████▊     | 177173/371472 [3:11:56<17:39:28,  3.06it/s]
 48%|████▊     | 177174/371472 [3:11:56<17:26:54,  3.09it/s]
 48%|████▊     | 177175/371472 [3:11:57<16:55:22,  3.19it/s]
 48%|████▊     | 177176/371472 [3:11:57<16:51:31,  3.20it/s]
 48%|████▊     | 177177/371472 [3:11:57<16:45:41,  3.22it/s]
 48%|████▊     | 177178/371472 [3:11:58<16:36:03,  3.25it/s]
 48%|████▊     | 177179/371472 [3:11:58<16:09:55,  3.34it/s]
 48%|████▊     | 177180/371472 [3:11:58<17:05:27,  3.16it/s]
                                                            
{'loss': 2.9193, 'learning_rate': 5.709829989872654e-07, 'epoch': 7.63}
+
 48%|████▊     | 177180/371472 [3:11:58<17:05:27,  3.16it/s]
 48%|████▊     | 177181/371472 [3:11:59<16:28:44,  3.28it/s]
 48%|████▊     | 177182/371472 [3:11:59<16:29:18,  3.27it/s]
 48%|████▊     | 177183/371472 [3:11:59<16:24:08,  3.29it/s]
 48%|████▊     | 177184/371472 [3:11:59<16:09:50,  3.34it/s]
 48%|████▊     | 177185/371472 [3:12:00<16:28:44,  3.27it/s]
 48%|████▊     | 177186/371472 [3:12:00<16:06:26,  3.35it/s]
 48%|████▊     | 177187/371472 [3:12:00<15:57:41,  3.38it/s]
 48%|████▊     | 177188/371472 [3:12:01<15:49:48,  3.41it/s]
 48%|████▊     | 177189/371472 [3:12:01<15:16:37,  3.53it/s]
 48%|████▊     | 177190/371472 [3:12:01<15:30:49,  3.48it/s]
 48%|████▊     | 177191/371472 [3:12:02<15:30:04,  3.48it/s]
 48%|████▊     | 177192/371472 [3:12:02<15:15:28,  3.54it/s]
 48%|████▊     | 177193/371472 [3:12:02<16:15:48,  3.32it/s]
 48%|████▊     | 177194/371472 [3:12:02<16:10:04,  3.34it/s]
 48%|████▊     | 177195/371472 [3:12:03<16:03:51,  3.36it/s]
 48%|████▊     | 177196/371472 [3:12:03<16:05:42,  3.35it/s]
 48%|████▊     | 177197/371472 [3:12:03<16:47:05,  3.22it/s]
 48%|████▊     | 177198/371472 [3:12:04<16:56:58,  3.18it/s]
 48%|████▊     | 177199/371472 [3:12:04<18:07:48,  2.98it/s]
 48%|████▊     | 177200/371472 [3:12:04<17:16:28,  3.12it/s]
                                                            
{'loss': 2.9529, 'learning_rate': 5.709345170117864e-07, 'epoch': 7.63}
+
 48%|████▊     | 177200/371472 [3:12:04<17:16:28,  3.12it/s]
 48%|████▊     | 177201/371472 [3:12:05<17:04:40,  3.16it/s]
 48%|████▊     | 177202/371472 [3:12:05<17:12:28,  3.14it/s]
 48%|████▊     | 177203/371472 [3:12:05<17:48:55,  3.03it/s]
 48%|████▊     | 177204/371472 [3:12:06<17:22:07,  3.11it/s]
 48%|████▊     | 177205/371472 [3:12:06<17:40:01,  3.05it/s]
 48%|████▊     | 177206/371472 [3:12:06<17:03:58,  3.16it/s]
 48%|████▊     | 177207/371472 [3:12:07<18:39:44,  2.89it/s]
 48%|████▊     | 177208/371472 [3:12:07<17:19:27,  3.11it/s]
 48%|████▊     | 177209/371472 [3:12:07<16:46:57,  3.22it/s]
 48%|████▊     | 177210/371472 [3:12:08<16:47:48,  3.21it/s]
 48%|████▊     | 177211/371472 [3:12:08<16:23:27,  3.29it/s]
 48%|████▊     | 177212/371472 [3:12:08<15:49:47,  3.41it/s]
 48%|████▊     | 177213/371472 [3:12:08<15:33:53,  3.47it/s]
 48%|████▊     | 177214/371472 [3:12:09<15:49:46,  3.41it/s]
 48%|████▊     | 177215/371472 [3:12:09<15:58:16,  3.38it/s]
 48%|████▊     | 177216/371472 [3:12:09<15:26:54,  3.49it/s]
 48%|████▊     | 177217/371472 [3:12:10<15:33:18,  3.47it/s]
 48%|████▊     | 177218/371472 [3:12:10<16:13:54,  3.32it/s]
 48%|████▊     | 177219/371472 [3:12:10<16:22:56,  3.29it/s]
 48%|████▊     | 177220/371472 [3:12:10<16:02:03,  3.37it/s]
                                                            
{'loss': 2.8482, 'learning_rate': 5.708860350363076e-07, 'epoch': 7.63}
+
 48%|████▊     | 177220/371472 [3:12:10<16:02:03,  3.37it/s]
 48%|████▊     | 177221/371472 [3:12:11<15:51:25,  3.40it/s]
 48%|████▊     | 177222/371472 [3:12:11<15:38:28,  3.45it/s]
 48%|████▊     | 177223/371472 [3:12:11<16:29:38,  3.27it/s]
 48%|████▊     | 177224/371472 [3:12:12<17:38:46,  3.06it/s]
 48%|████▊     | 177225/371472 [3:12:12<16:36:44,  3.25it/s]
 48%|████▊     | 177226/371472 [3:12:12<16:04:55,  3.36it/s]
 48%|████▊     | 177227/371472 [3:12:13<15:58:31,  3.38it/s]
 48%|████▊     | 177228/371472 [3:12:13<18:47:52,  2.87it/s]
 48%|████▊     | 177229/371472 [3:12:13<17:53:29,  3.02it/s]
 48%|████▊     | 177230/371472 [3:12:14<17:18:49,  3.12it/s]
 48%|████▊     | 177231/371472 [3:12:14<17:02:20,  3.17it/s]
 48%|████▊     | 177232/371472 [3:12:14<16:31:48,  3.26it/s]
 48%|████▊     | 177233/371472 [3:12:15<16:33:16,  3.26it/s]
 48%|████▊     | 177234/371472 [3:12:15<16:12:20,  3.33it/s]
 48%|████▊     | 177235/371472 [3:12:15<16:03:45,  3.36it/s]
 48%|████▊     | 177236/371472 [3:12:15<15:56:19,  3.39it/s]
 48%|████▊     | 177237/371472 [3:12:16<15:50:19,  3.41it/s]
 48%|████▊     | 177238/371472 [3:12:16<16:25:26,  3.29it/s]
 48%|████▊     | 177239/371472 [3:12:16<17:22:44,  3.10it/s]
 48%|████▊     | 177240/371472 [3:12:17<16:56:37,  3.18it/s]
                                                            
{'loss': 2.8155, 'learning_rate': 5.708375530608287e-07, 'epoch': 7.63}
+
 48%|████▊     | 177240/371472 [3:12:17<16:56:37,  3.18it/s]
 48%|████▊     | 177241/371472 [3:12:17<17:29:11,  3.09it/s]
 48%|████▊     | 177242/371472 [3:12:17<17:08:32,  3.15it/s]
 48%|████▊     | 177243/371472 [3:12:18<16:42:31,  3.23it/s]
 48%|████▊     | 177244/371472 [3:12:18<16:17:28,  3.31it/s]
 48%|████▊     | 177245/371472 [3:12:18<15:37:58,  3.45it/s]
 48%|████▊     | 177246/371472 [3:12:18<15:11:06,  3.55it/s]
 48%|████▊     | 177247/371472 [3:12:19<16:17:14,  3.31it/s]
 48%|████▊     | 177248/371472 [3:12:19<16:02:07,  3.36it/s]
 48%|████▊     | 177249/371472 [3:12:19<15:32:51,  3.47it/s]
 48%|████▊     | 177250/371472 [3:12:20<16:06:50,  3.35it/s]
 48%|████▊     | 177251/371472 [3:12:20<15:37:59,  3.45it/s]
 48%|████▊     | 177252/371472 [3:12:20<15:06:56,  3.57it/s]
 48%|████▊     | 177253/371472 [3:12:20<15:17:28,  3.53it/s]
 48%|████▊     | 177254/371472 [3:12:21<15:17:58,  3.53it/s]
 48%|████▊     | 177255/371472 [3:12:21<15:54:36,  3.39it/s]
 48%|████▊     | 177256/371472 [3:12:21<16:13:11,  3.33it/s]
 48%|████▊     | 177257/371472 [3:12:22<15:50:21,  3.41it/s]
 48%|████▊     | 177258/371472 [3:12:22<15:41:34,  3.44it/s]
 48%|████▊     | 177259/371472 [3:12:22<15:41:58,  3.44it/s]
 48%|████▊     | 177260/371472 [3:12:23<15:54:52,  3.39it/s]
                                                            
{'loss': 2.8975, 'learning_rate': 5.707890710853497e-07, 'epoch': 7.63}
+
 48%|████▊     | 177260/371472 [3:12:23<15:54:52,  3.39it/s]
 48%|████▊     | 177261/371472 [3:12:23<15:57:26,  3.38it/s]
 48%|████▊     | 177262/371472 [3:12:23<15:32:52,  3.47it/s]
 48%|████▊     | 177263/371472 [3:12:23<15:18:04,  3.53it/s]
 48%|████▊     | 177264/371472 [3:12:24<15:34:52,  3.46it/s]
 48%|████▊     | 177265/371472 [3:12:24<17:12:02,  3.14it/s]
 48%|████▊     | 177266/371472 [3:12:24<16:58:44,  3.18it/s]
 48%|████▊     | 177267/371472 [3:12:25<16:32:18,  3.26it/s]
 48%|████▊     | 177268/371472 [3:12:25<17:06:26,  3.15it/s]
 48%|████▊     | 177269/371472 [3:12:25<16:48:37,  3.21it/s]
 48%|████▊     | 177270/371472 [3:12:26<16:23:47,  3.29it/s]
 48%|████▊     | 177271/371472 [3:12:26<17:40:42,  3.05it/s]
 48%|█���██▊     | 177272/371472 [3:12:26<16:57:40,  3.18it/s]
 48%|████▊     | 177273/371472 [3:12:27<16:32:08,  3.26it/s]
 48%|████▊     | 177274/371472 [3:12:27<16:31:06,  3.27it/s]
 48%|████▊     | 177275/371472 [3:12:27<16:23:29,  3.29it/s]
 48%|████▊     | 177276/371472 [3:12:27<16:47:54,  3.21it/s]
 48%|████▊     | 177277/371472 [3:12:28<16:32:12,  3.26it/s]
 48%|████▊     | 177278/371472 [3:12:28<16:15:38,  3.32it/s]
 48%|████▊     | 177279/371472 [3:12:28<15:58:51,  3.38it/s]
 48%|████▊     | 177280/371472 [3:12:29<16:06:46,  3.35it/s]
                                                            
{'loss': 2.7884, 'learning_rate': 5.707405891098708e-07, 'epoch': 7.64}
+
 48%|████▊     | 177280/371472 [3:12:29<16:06:46,  3.35it/s]
 48%|████▊     | 177281/371472 [3:12:29<16:03:45,  3.36it/s]
 48%|████▊     | 177282/371472 [3:12:29<15:52:15,  3.40it/s]
 48%|████▊     | 177283/371472 [3:12:30<16:42:47,  3.23it/s]
 48%|████▊     | 177284/371472 [3:12:30<15:58:04,  3.38it/s]
 48%|████▊     | 177285/371472 [3:12:30<17:27:53,  3.09it/s]
 48%|████▊     | 177286/371472 [3:12:31<16:32:39,  3.26it/s]
 48%|████▊     | 177287/371472 [3:12:31<15:56:25,  3.38it/s]
 48%|████▊     | 177288/371472 [3:12:31<15:47:00,  3.42it/s]
 48%|████▊     | 177289/371472 [3:12:31<15:48:18,  3.41it/s]
 48%|████▊     | 177290/371472 [3:12:32<15:46:40,  3.42it/s]
 48%|████▊     | 177291/371472 [3:12:32<15:56:13,  3.38it/s]
 48%|████▊     | 177292/371472 [3:12:32<15:59:28,  3.37it/s]
 48%|████▊     | 177293/371472 [3:12:33<15:35:26,  3.46it/s]
 48%|████▊     | 177294/371472 [3:12:33<15:26:32,  3.49it/s]
 48%|████▊     | 177295/371472 [3:12:33<16:32:24,  3.26it/s]
 48%|████▊     | 177296/371472 [3:12:33<16:38:31,  3.24it/s]
 48%|████▊     | 177297/371472 [3:12:34<15:58:50,  3.38it/s]
 48%|████▊     | 177298/371472 [3:12:34<15:56:36,  3.38it/s]
 48%|████▊     | 177299/371472 [3:12:34<15:37:08,  3.45it/s]
 48%|████▊     | 177300/371472 [3:12:35<15:24:32,  3.50it/s]
                                                            
{'loss': 2.857, 'learning_rate': 5.70692107134392e-07, 'epoch': 7.64}
+
 48%|████▊     | 177300/371472 [3:12:35<15:24:32,  3.50it/s]
 48%|████▊     | 177301/371472 [3:12:35<15:41:18,  3.44it/s]
 48%|████▊     | 177302/371472 [3:12:35<15:32:50,  3.47it/s]
 48%|████▊     | 177303/371472 [3:12:36<16:41:56,  3.23it/s]
 48%|████▊     | 177304/371472 [3:12:36<17:15:16,  3.13it/s]
 48%|████▊     | 177305/371472 [3:12:36<17:02:37,  3.16it/s]
 48%|████▊     | 177306/371472 [3:12:36<16:55:49,  3.19it/s]
 48%|████▊     | 177307/371472 [3:12:37<16:14:19,  3.32it/s]
 48%|████▊     | 177308/371472 [3:12:37<16:19:51,  3.30it/s]
 48%|████▊     | 177309/371472 [3:12:37<16:25:48,  3.28it/s]
 48%|████▊     | 177310/371472 [3:12:38<16:02:30,  3.36it/s]
 48%|████▊     | 177311/371472 [3:12:38<16:14:41,  3.32it/s]
 48%|████▊     | 177312/371472 [3:12:38<16:01:35,  3.37it/s]
 48%|████▊     | 177313/371472 [3:12:39<17:06:51,  3.15it/s]
 48%|████▊     | 177314/371472 [3:12:39<16:39:55,  3.24it/s]
 48%|████▊     | 177315/371472 [3:12:39<16:59:22,  3.17it/s]
 48%|████▊     | 177316/371472 [3:12:40<16:20:58,  3.30it/s]
 48%|████▊     | 177317/371472 [3:12:40<16:17:44,  3.31it/s]
 48%|████▊     | 177318/371472 [3:12:40<16:08:50,  3.34it/s]
 48%|████▊     | 177319/371472 [3:12:40<16:24:29,  3.29it/s]
 48%|████▊     | 177320/371472 [3:12:41<16:34:23,  3.25it/s]
                                                            
{'loss': 2.8511, 'learning_rate': 5.706436251589132e-07, 'epoch': 7.64}
+
 48%|████▊     | 177320/371472 [3:12:41<16:34:23,  3.25it/s]
 48%|████▊     | 177321/371472 [3:12:41<16:07:31,  3.34it/s]
 48%|████▊     | 177322/371472 [3:12:41<15:41:09,  3.44it/s]
 48%|████▊     | 177323/371472 [3:12:42<15:33:27,  3.47it/s]
 48%|████▊     | 177324/371472 [3:12:42<16:00:21,  3.37it/s]
 48%|████▊     | 177325/371472 [3:12:42<15:46:21,  3.42it/s]
 48%|████▊     | 177326/371472 [3:12:43<16:23:32,  3.29it/s]
 48%|████▊     | 177327/371472 [3:12:43<16:23:16,  3.29it/s]
 48%|████▊     | 177328/371472 [3:12:43<16:13:15,  3.32it/s]
 48%|████▊     | 177329/371472 [3:12:43<17:09:35,  3.14it/s]
 48%|████▊     | 177330/371472 [3:12:44<16:41:35,  3.23it/s]
 48%|████▊     | 177331/371472 [3:12:44<16:04:30,  3.35it/s]
 48%|████▊     | 177332/371472 [3:12:44<16:10:19,  3.33it/s]
 48%|████▊     | 177333/371472 [3:12:45<16:01:40,  3.36it/s]
 48%|████▊     | 177334/371472 [3:12:45<15:53:43,  3.39it/s]
 48%|████▊     | 177335/371472 [3:12:45<16:36:48,  3.25it/s]
 48%|████▊     | 177336/371472 [3:12:46<16:20:07,  3.30it/s]
 48%|████▊     | 177337/371472 [3:12:46<16:12:14,  3.33it/s]
 48%|████▊     | 177338/371472 [3:12:46<16:29:06,  3.27it/s]
 48%|████▊     | 177339/371472 [3:12:46<16:13:59,  3.32it/s]
 48%|████▊     | 177340/371472 [3:12:47<16:37:15,  3.24it/s]
                                                            
{'loss': 2.9179, 'learning_rate': 5.705951431834342e-07, 'epoch': 7.64}
+
 48%|████▊     | 177340/371472 [3:12:47<16:37:15,  3.24it/s]
 48%|████▊     | 177341/371472 [3:12:47<15:56:56,  3.38it/s]
 48%|████▊     | 177342/371472 [3:12:47<16:35:50,  3.25it/s]
 48%|████▊     | 177343/371472 [3:12:48<16:46:13,  3.22it/s]
 48%|████▊     | 177344/371472 [3:12:48<16:23:10,  3.29it/s]
 48%|████▊     | 177345/371472 [3:12:48<16:26:10,  3.28it/s]
 48%|████▊     | 177346/371472 [3:12:49<17:14:57,  3.13it/s]
 48%|████▊     | 177347/371472 [3:12:49<16:54:14,  3.19it/s]
 48%|████▊     | 177348/371472 [3:12:49<16:36:28,  3.25it/s]
 48%|████▊     | 177349/371472 [3:12:50<16:31:52,  3.26it/s]
 48%|████▊     | 177350/371472 [3:12:50<16:20:45,  3.30it/s]
 48%|████▊     | 177351/371472 [3:12:50<16:10:46,  3.33it/s]
 48%|████▊     | 177352/371472 [3:12:50<16:04:46,  3.35it/s]
 48%|████▊     | 177353/371472 [3:12:51<16:58:39,  3.18it/s]
 48%|████▊     | 177354/371472 [3:12:51<16:21:45,  3.30it/s]
 48%|████▊     | 177355/371472 [3:12:51<15:58:49,  3.37it/s]
 48%|████▊     | 177356/371472 [3:12:52<15:57:31,  3.38it/s]
 48%|████▊     | 177357/371472 [3:12:52<15:52:29,  3.40it/s]
 48%|████▊     | 177358/371472 [3:12:52<15:54:32,  3.39it/s]
 48%|████▊     | 177359/371472 [3:12:52<15:45:56,  3.42it/s]
 48%|████▊     | 177360/371472 [3:12:53<15:43:57,  3.43it/s]
                                                            
{'loss': 2.796, 'learning_rate': 5.705466612079553e-07, 'epoch': 7.64}
+
 48%|████▊     | 177360/371472 [3:12:53<15:43:57,  3.43it/s]
 48%|████▊     | 177361/371472 [3:12:53<15:53:12,  3.39it/s]
 48%|████▊     | 177362/371472 [3:12:53<15:52:42,  3.40it/s]
 48%|████▊     | 177363/371472 [3:12:54<15:44:04,  3.43it/s]
 48%|████▊     | 177364/371472 [3:12:54<15:36:18,  3.46it/s]
 48%|████▊     | 177365/371472 [3:12:54<15:44:59,  3.42it/s]
 48%|████▊     | 177366/371472 [3:12:55<15:46:47,  3.42it/s]
 48%|████▊     | 177367/371472 [3:12:55<15:19:05,  3.52it/s]
 48%|████▊     | 177368/371472 [3:12:55<15:34:26,  3.46it/s]
 48%|████▊     | 177369/371472 [3:12:55<15:19:51,  3.52it/s]
 48%|████▊     | 177370/371472 [3:12:56<15:30:35,  3.48it/s]
 48%|████▊     | 177371/371472 [3:12:56<15:25:58,  3.49it/s]
 48%|████▊     | 177372/371472 [3:12:56<15:36:37,  3.45it/s]
 48%|████▊     | 177373/371472 [3:12:57<15:33:13,  3.47it/s]
 48%|████▊     | 177374/371472 [3:12:57<15:50:32,  3.40it/s]
 48%|████▊     | 177375/371472 [3:12:57<15:21:45,  3.51it/s]
 48%|████▊     | 177376/371472 [3:12:57<15:41:29,  3.44it/s]
 48%|████▊     | 177377/371472 [3:12:58<15:30:17,  3.48it/s]
 48%|████▊     | 177378/371472 [3:12:58<15:47:39,  3.41it/s]
 48%|████▊     | 177379/371472 [3:12:58<16:32:24,  3.26it/s]
 48%|████▊     | 177380/371472 [3:12:59<17:15:05,  3.13it/s]
                                                            
{'loss': 3.001, 'learning_rate': 5.704981792324764e-07, 'epoch': 7.64}
+
 48%|████▊     | 177380/371472 [3:12:59<17:15:05,  3.13it/s]
 48%|████▊     | 177381/371472 [3:12:59<17:33:28,  3.07it/s]
 48%|████▊     | 177382/371472 [3:12:59<17:08:37,  3.14it/s]
 48%|████▊     | 177383/371472 [3:13:00<17:34:29,  3.07it/s]
 48%|████▊     | 177384/371472 [3:13:00<17:09:10,  3.14it/s]
 48%|████▊     | 177385/371472 [3:13:00<16:21:40,  3.30it/s]
 48%|████▊     | 177386/371472 [3:13:01<17:07:18,  3.15it/s]
 48%|████▊     | 177387/371472 [3:13:01<16:33:43,  3.26it/s]
 48%|████▊     | 177388/371472 [3:13:01<17:23:30,  3.10it/s]
 48%|████▊     | 177389/371472 [3:13:02<16:40:57,  3.23it/s]
 48%|████▊     | 177390/371472 [3:13:02<16:15:58,  3.31it/s]
 48%|████▊     | 177391/371472 [3:13:02<17:12:11,  3.13it/s]
 48%|████▊     | 177392/371472 [3:13:02<16:39:21,  3.24it/s]
 48%|████▊     | 177393/371472 [3:13:03<17:01:57,  3.17it/s]
 48%|████▊     | 177394/371472 [3:13:03<16:42:45,  3.23it/s]
 48%|████▊     | 177395/371472 [3:13:03<16:15:23,  3.32it/s]
 48%|████▊     | 177396/371472 [3:13:04<15:57:44,  3.38it/s]
 48%|████▊     | 177397/371472 [3:13:04<15:51:22,  3.40it/s]
 48%|████▊     | 177398/371472 [3:13:04<16:31:06,  3.26it/s]
 48%|████▊     | 177399/371472 [3:13:05<15:58:57,  3.37it/s]
 48%|████▊     | 177400/371472 [3:13:05<16:25:25,  3.28it/s]
                                                            
{'loss': 2.7894, 'learning_rate': 5.704496972569976e-07, 'epoch': 7.64}
+
 48%|████▊     | 177400/371472 [3:13:05<16:25:25,  3.28it/s]
 48%|████▊     | 177401/371472 [3:13:05<16:03:13,  3.36it/s]
 48%|████▊     | 177402/371472 [3:13:05<15:50:35,  3.40it/s]
 48%|████▊     | 177403/371472 [3:13:06<15:47:28,  3.41it/s]
 48%|████▊     | 177404/371472 [3:13:06<15:34:40,  3.46it/s]
 48%|████▊     | 177405/371472 [3:13:06<15:49:21,  3.41it/s]
 48%|████▊     | 177406/371472 [3:13:07<16:33:30,  3.26it/s]
 48%|████▊     | 177407/371472 [3:13:07<16:39:13,  3.24it/s]
 48%|████▊     | 177408/371472 [3:13:07<16:32:11,  3.26it/s]
 48%|████▊     | 177409/371472 [3:13:08<17:23:02,  3.10it/s]
 48%|████▊     | 177410/371472 [3:13:08<16:58:11,  3.18it/s]
 48%|████▊     | 177411/371472 [3:13:08<16:36:38,  3.25it/s]
 48%|████▊     | 177412/371472 [3:13:09<16:31:28,  3.26it/s]
 48%|████▊     | 177413/371472 [3:13:09<16:12:18,  3.33it/s]
 48%|████▊     | 177414/371472 [3:13:09<15:56:57,  3.38it/s]
 48%|████▊     | 177415/371472 [3:13:09<15:53:45,  3.39it/s]
 48%|████▊     | 177416/371472 [3:13:10<15:56:30,  3.38it/s]
 48%|████▊     | 177417/371472 [3:13:10<17:41:43,  3.05it/s]
 48%|████▊     | 177418/371472 [3:13:10<17:57:08,  3.00it/s]
 48%|████▊     | 177419/371472 [3:13:11<16:55:17,  3.19it/s]
 48%|████▊     | 177420/371472 [3:13:11<16:31:46,  3.26it/s]
                                                            
{'loss': 2.9977, 'learning_rate': 5.704012152815186e-07, 'epoch': 7.64}
+
 48%|████▊     | 177420/371472 [3:13:11<16:31:46,  3.26it/s]
 48%|████▊     | 177421/371472 [3:13:11<16:22:27,  3.29it/s]
 48%|████▊     | 177422/371472 [3:13:12<16:06:00,  3.35it/s]
 48%|████▊     | 177423/371472 [3:13:12<16:10:38,  3.33it/s]
 48%|████▊     | 177424/371472 [3:13:12<16:13:20,  3.32it/s]
 48%|████▊     | 177425/371472 [3:13:12<16:10:23,  3.33it/s]
 48%|████▊     | 177426/371472 [3:13:13<15:48:02,  3.41it/s]
 48%|████▊     | 177427/371472 [3:13:13<15:33:50,  3.46it/s]
 48%|████▊     | 177428/371472 [3:13:13<15:39:23,  3.44it/s]
 48%|████▊     | 177429/371472 [3:13:14<16:03:41,  3.36it/s]
 48%|████▊     | 177430/371472 [3:13:14<15:47:13,  3.41it/s]
 48%|████▊     | 177431/371472 [3:13:14<15:52:57,  3.39it/s]
 48%|████▊     | 177432/371472 [3:13:14<15:52:09,  3.40it/s]
 48%|████▊     | 177433/371472 [3:13:15<15:43:59,  3.43it/s]
 48%|████▊     | 177434/371472 [3:13:15<15:59:53,  3.37it/s]
 48%|████▊     | 177435/371472 [3:13:15<16:09:03,  3.34it/s]
 48%|████▊     | 177436/371472 [3:13:16<15:43:22,  3.43it/s]
 48%|████▊     | 177437/371472 [3:13:16<16:00:31,  3.37it/s]
 48%|████▊     | 177438/371472 [3:13:16<15:50:07,  3.40it/s]
 48%|████▊     | 177439/371472 [3:13:17<15:56:55,  3.38it/s]
 48%|████▊     | 177440/371472 [3:13:17<16:10:33,  3.33it/s]
                                                            
{'loss': 2.8482, 'learning_rate': 5.703527333060397e-07, 'epoch': 7.64}
+
 48%|████▊     | 177440/371472 [3:13:17<16:10:33,  3.33it/s]
 48%|████▊     | 177441/371472 [3:13:17<16:09:26,  3.34it/s]
 48%|████▊     | 177442/371472 [3:13:17<16:24:51,  3.28it/s]
 48%|████▊     | 177443/371472 [3:13:18<16:27:15,  3.28it/s]
 48%|████▊     | 177444/371472 [3:13:18<15:56:18,  3.38it/s]
 48%|████▊     | 177445/371472 [3:13:18<16:54:48,  3.19it/s]
 48%|████▊     | 177446/371472 [3:13:19<16:26:39,  3.28it/s]
 48%|████▊     | 177447/371472 [3:13:19<16:42:18,  3.23it/s]
 48%|████▊     | 177448/371472 [3:13:19<16:09:36,  3.34it/s]
 48%|████▊     | 177449/371472 [3:13:20<15:46:57,  3.41it/s]
 48%|████▊     | 177450/371472 [3:13:20<15:34:58,  3.46it/s]
 48%|████▊     | 177451/371472 [3:13:20<16:00:07,  3.37it/s]
 48%|████▊     | 177452/371472 [3:13:20<16:06:47,  3.34it/s]
 48%|████▊     | 177453/371472 [3:13:21<15:44:32,  3.42it/s]
 48%|████▊     | 177454/371472 [3:13:21<15:33:57,  3.46it/s]
 48%|████▊     | 177455/371472 [3:13:21<15:34:07,  3.46it/s]
 48%|████▊     | 177456/371472 [3:13:22<15:16:55,  3.53it/s]
 48%|████▊     | 177457/371472 [3:13:22<15:37:05,  3.45it/s]
 48%|████▊     | 177458/371472 [3:13:22<15:31:47,  3.47it/s]
 48%|████▊     | 177459/371472 [3:13:23<17:25:47,  3.09it/s]
 48%|████▊     | 177460/371472 [3:13:23<16:49:26,  3.20it/s]
                                                            
{'loss': 2.9358, 'learning_rate': 5.703042513305609e-07, 'epoch': 7.64}
+
 48%|████▊     | 177460/371472 [3:13:23<16:49:26,  3.20it/s]
 48%|████▊     | 177461/371472 [3:13:23<17:02:51,  3.16it/s]
 48%|████▊     | 177462/371472 [3:13:24<17:51:57,  3.02it/s]
 48%|████▊     | 177463/371472 [3:13:24<17:12:09,  3.13it/s]
 48%|████▊     | 177464/371472 [3:13:24<16:44:57,  3.22it/s]
 48%|████▊     | 177465/371472 [3:13:25<17:51:42,  3.02it/s]
 48%|████▊     | 177466/371472 [3:13:25<16:43:53,  3.22it/s]
 48%|████▊     | 177467/371472 [3:13:25<16:26:32,  3.28it/s]
 48%|████▊     | 177468/371472 [3:13:25<15:55:12,  3.39it/s]
 48%|████▊     | 177469/371472 [3:13:26<16:14:31,  3.32it/s]
 48%|████▊     | 177470/371472 [3:13:26<16:00:35,  3.37it/s]
 48%|████▊     | 177471/371472 [3:13:26<15:40:29,  3.44it/s]
 48%|████▊     | 177472/371472 [3:13:27<15:24:31,  3.50it/s]
 48%|████▊     | 177473/371472 [3:13:27<15:05:05,  3.57it/s]
 48%|████▊     | 177474/371472 [3:13:27<15:13:58,  3.54it/s]
 48%|████▊     | 177475/371472 [3:13:27<15:23:01,  3.50it/s]
 48%|████▊     | 177476/371472 [3:13:28<15:56:41,  3.38it/s]
 48%|████▊     | 177477/371472 [3:13:28<15:58:53,  3.37it/s]
 48%|████▊     | 177478/371472 [3:13:28<16:04:37,  3.35it/s]
 48%|████▊     | 177479/371472 [3:13:29<15:59:02,  3.37it/s]
 48%|████▊     | 177480/371472 [3:13:29<16:03:15,  3.36it/s]
                                                            
{'loss': 2.9128, 'learning_rate': 5.702557693550819e-07, 'epoch': 7.64}
+
 48%|████▊     | 177480/371472 [3:13:29<16:03:15,  3.36it/s]
 48%|████▊     | 177481/371472 [3:13:29<15:55:22,  3.38it/s]
 48%|████▊     | 177482/371472 [3:13:29<15:46:31,  3.42it/s]
 48%|████▊     | 177483/371472 [3:13:30<15:44:29,  3.42it/s]
 48%|████▊     | 177484/371472 [3:13:30<16:52:05,  3.19it/s]
 48%|████▊     | 177485/371472 [3:13:30<17:15:35,  3.12it/s]
 48%|████▊     | 177486/371472 [3:13:31<18:13:59,  2.96it/s]
 48%|████▊     | 177487/371472 [3:13:31<18:19:19,  2.94it/s]
 48%|████▊     | 177488/371472 [3:13:31<17:44:12,  3.04it/s]
 48%|████▊     | 177489/371472 [3:13:32<17:18:28,  3.11it/s]
 48%|████▊     | 177490/371472 [3:13:32<16:41:42,  3.23it/s]
 48%|████▊     | 177491/371472 [3:13:32<16:38:42,  3.24it/s]
 48%|████▊     | 177492/371472 [3:13:33<16:17:17,  3.31it/s]
 48%|████▊     | 177493/371472 [3:13:33<16:36:57,  3.24it/s]
 48%|████▊     | 177494/371472 [3:13:33<17:33:52,  3.07it/s]
 48%|████▊     | 177495/371472 [3:13:34<17:02:02,  3.16it/s]
 48%|████▊     | 177496/371472 [3:13:34<16:47:03,  3.21it/s]
 48%|████▊     | 177497/371472 [3:13:34<17:18:57,  3.11it/s]
 48%|████▊     | 177498/371472 [3:13:35<17:30:31,  3.08it/s]
 48%|████▊     | 177499/371472 [3:13:35<17:29:13,  3.08it/s]
 48%|████▊     | 177500/371472 [3:13:35<18:10:22,  2.96it/s]
                                                            
{'loss': 2.8842, 'learning_rate': 5.70207287379603e-07, 'epoch': 7.65}
+
 48%|████▊     | 177500/371472 [3:13:35<18:10:22,  2.96it/s]
 48%|████▊     | 177501/371472 [3:13:36<17:25:14,  3.09it/s]
 48%|████▊     | 177502/371472 [3:13:36<16:51:20,  3.20it/s]
 48%|████▊     | 177503/371472 [3:13:36<17:15:31,  3.12it/s]
 48%|████▊     | 177504/371472 [3:13:37<17:08:42,  3.14it/s]
 48%|████▊     | 177505/371472 [3:13:37<16:40:24,  3.23it/s]
 48%|████▊     | 177506/371472 [3:13:37<16:27:21,  3.27it/s]
 48%|████▊     | 177507/371472 [3:13:37<16:09:00,  3.34it/s]
 48%|████▊     | 177508/371472 [3:13:38<16:17:47,  3.31it/s]
 48%|████▊     | 177509/371472 [3:13:38<15:58:14,  3.37it/s]
 48%|████▊     | 177510/371472 [3:13:38<15:38:18,  3.45it/s]
 48%|████▊     | 177511/371472 [3:13:39<15:27:38,  3.48it/s]
 48%|████▊     | 177512/371472 [3:13:39<15:50:36,  3.40it/s]
 48%|████▊     | 177513/371472 [3:13:39<15:51:30,  3.40it/s]
 48%|████▊     | 177514/371472 [3:13:39<15:56:09,  3.38it/s]
 48%|████▊     | 177515/371472 [3:13:40<15:56:08,  3.38it/s]
 48%|████▊     | 177516/371472 [3:13:40<15:42:04,  3.43it/s]
 48%|████▊     | 177517/371472 [3:13:40<15:22:50,  3.50it/s]
 48%|████▊     | 177518/371472 [3:13:41<15:12:34,  3.54it/s]
 48%|████▊     | 177519/371472 [3:13:41<15:05:19,  3.57it/s]
 48%|████▊     | 177520/371472 [3:13:41<15:44:46,  3.42it/s]
                                                            
{'loss': 2.9111, 'learning_rate': 5.701588054041241e-07, 'epoch': 7.65}
+
 48%|████▊     | 177520/371472 [3:13:41<15:44:46,  3.42it/s]
 48%|████▊     | 177521/371472 [3:13:41<15:46:47,  3.41it/s]
 48%|████▊     | 177522/371472 [3:13:42<15:43:08,  3.43it/s]
 48%|████▊     | 177523/371472 [3:13:42<16:01:21,  3.36it/s]
 48%|████▊     | 177524/371472 [3:13:42<15:54:34,  3.39it/s]
 48%|████▊     | 177525/371472 [3:13:43<15:47:21,  3.41it/s]
 48%|████▊     | 177526/371472 [3:13:43<15:35:10,  3.46it/s]
 48%|████▊     | 177527/371472 [3:13:43<15:22:28,  3.50it/s]
 48%|████▊     | 177528/371472 [3:13:43<15:26:37,  3.49it/s]
 48%|████▊     | 177529/371472 [3:13:44<15:33:55,  3.46it/s]
 48%|████▊     | 177530/371472 [3:13:44<16:14:00,  3.32it/s]
 48%|████▊     | 177531/371472 [3:13:44<15:59:59,  3.37it/s]
 48%|████▊     | 177532/371472 [3:13:45<15:39:53,  3.44it/s]
 48%|████▊     | 177533/371472 [3:13:45<15:44:12,  3.42it/s]
 48%|████▊     | 177534/371472 [3:13:45<15:26:54,  3.49it/s]
 48%|████▊     | 177535/371472 [3:13:46<15:25:46,  3.49it/s]
 48%|████▊     | 177536/371472 [3:13:46<15:46:01,  3.42it/s]
 48%|████▊     | 177537/371472 [3:13:46<16:13:58,  3.32it/s]
 48%|████▊     | 177538/371472 [3:13:46<15:46:23,  3.42it/s]
 48%|████▊     | 177539/371472 [3:13:47<17:05:49,  3.15it/s]
 48%|████▊     | 177540/371472 [3:13:47<16:56:31,  3.18it/s]
                                                            
{'loss': 3.0995, 'learning_rate': 5.701103234286453e-07, 'epoch': 7.65}
+
 48%|████▊     | 177540/371472 [3:13:47<16:56:31,  3.18it/s]
 48%|████▊     | 177541/371472 [3:13:47<16:48:06,  3.21it/s]
 48%|████▊     | 177542/371472 [3:13:48<16:39:04,  3.24it/s]
 48%|████▊     | 177543/371472 [3:13:48<16:22:57,  3.29it/s]
 48%|████▊     | 177544/371472 [3:13:48<16:19:47,  3.30it/s]
 48%|████▊     | 177545/371472 [3:13:49<16:32:48,  3.26it/s]
 48%|████▊     | 177546/371472 [3:13:49<16:03:42,  3.35it/s]
 48%|████▊     | 177547/371472 [3:13:49<16:08:01,  3.34it/s]
 48%|████▊     | 177548/371472 [3:13:50<16:12:00,  3.33it/s]
 48%|████▊     | 177549/371472 [3:13:50<16:43:53,  3.22it/s]
 48%|████▊     | 177550/371472 [3:13:50<15:59:54,  3.37it/s]
 48%|████▊     | 177551/371472 [3:13:50<15:42:58,  3.43it/s]
 48%|████▊     | 177552/371472 [3:13:51<15:34:03,  3.46it/s]
 48%|████▊     | 177553/371472 [3:13:51<15:32:42,  3.47it/s]
 48%|████▊     | 177554/371472 [3:13:51<15:18:08,  3.52it/s]
 48%|████▊     | 177555/371472 [3:13:52<15:09:58,  3.55it/s]
 48%|████▊     | 177556/371472 [3:13:52<16:00:14,  3.37it/s]
 48%|████▊     | 177557/371472 [3:13:52<15:54:37,  3.39it/s]
 48%|████▊     | 177558/371472 [3:13:52<15:30:04,  3.47it/s]
 48%|████▊     | 177559/371472 [3:13:53<15:31:39,  3.47it/s]
 48%|████▊     | 177560/371472 [3:13:53<15:11:43,  3.54it/s]
                                                            
{'loss': 2.993, 'learning_rate': 5.700618414531665e-07, 'epoch': 7.65}
+
 48%|████▊     | 177560/371472 [3:13:53<15:11:43,  3.54it/s]
 48%|████▊     | 177561/371472 [3:13:53<15:16:00,  3.53it/s]
 48%|████▊     | 177562/371472 [3:13:54<15:32:05,  3.47it/s]
 48%|████▊     | 177563/371472 [3:13:54<15:58:32,  3.37it/s]
 48%|████▊     | 177564/371472 [3:13:54<15:23:52,  3.50it/s]
 48%|████▊     | 177565/371472 [3:13:54<15:43:42,  3.42it/s]
 48%|████▊     | 177566/371472 [3:13:55<15:55:38,  3.38it/s]
 48%|████▊     | 177567/371472 [3:13:55<16:15:41,  3.31it/s]
 48%|████▊     | 177568/371472 [3:13:55<16:43:08,  3.22it/s]
 48%|████▊     | 177569/371472 [3:13:56<16:26:31,  3.28it/s]
 48%|████▊     | 177570/371472 [3:13:56<15:45:57,  3.42it/s]
 48%|████▊     | 177571/371472 [3:13:56<15:51:52,  3.40it/s]
 48%|████▊     | 177572/371472 [3:13:57<15:55:30,  3.38it/s]
 48%|████▊     | 177573/371472 [3:13:57<15:36:28,  3.45it/s]
 48%|████▊     | 177574/371472 [3:13:57<15:38:05,  3.44it/s]
 48%|████▊     | 177575/371472 [3:13:57<15:48:02,  3.41it/s]
 48%|████▊     | 177576/371472 [3:13:58<15:52:55,  3.39it/s]
 48%|████▊     | 177577/371472 [3:13:58<15:48:21,  3.41it/s]
 48%|████▊     | 177578/371472 [3:13:58<15:47:24,  3.41it/s]
 48%|████▊     | 177579/371472 [3:13:59<16:04:28,  3.35it/s]
 48%|████▊     | 177580/371472 [3:13:59<16:05:14,  3.35it/s]
                                                            
{'loss': 2.9807, 'learning_rate': 5.700133594776876e-07, 'epoch': 7.65}
+
 48%|████▊     | 177580/371472 [3:13:59<16:05:14,  3.35it/s]
 48%|████▊     | 177581/371472 [3:13:59<16:17:46,  3.30it/s]
 48%|████▊     | 177582/371472 [3:14:00<15:58:49,  3.37it/s]
 48%|████▊     | 177583/371472 [3:14:00<15:36:12,  3.45it/s]
 48%|████▊     | 177584/371472 [3:14:00<15:36:50,  3.45it/s]
 48%|████▊     | 177585/371472 [3:14:00<17:26:15,  3.09it/s]
 48%|████▊     | 177586/371472 [3:14:01<16:54:11,  3.19it/s]
 48%|████▊     | 177587/371472 [3:14:01<16:31:44,  3.26it/s]
 48%|████▊     | 177588/371472 [3:14:01<16:26:07,  3.28it/s]
 48%|████▊     | 177589/371472 [3:14:02<16:50:23,  3.20it/s]
 48%|████▊     | 177590/371472 [3:14:02<17:23:00,  3.10it/s]
 48%|████▊     | 177591/371472 [3:14:02<16:56:25,  3.18it/s]
 48%|████▊     | 177592/371472 [3:14:03<16:18:16,  3.30it/s]
 48%|████▊     | 177593/371472 [3:14:03<16:23:31,  3.29it/s]
 48%|████▊     | 177594/371472 [3:14:03<16:31:15,  3.26it/s]
 48%|████▊     | 177595/371472 [3:14:04<16:36:38,  3.24it/s]
 48%|████▊     | 177596/371472 [3:14:04<16:36:28,  3.24it/s]
 48%|████▊     | 177597/371472 [3:14:04<16:31:54,  3.26it/s]
 48%|████▊     | 177598/371472 [3:14:04<16:25:25,  3.28it/s]
 48%|████▊     | 177599/371472 [3:14:05<16:53:36,  3.19it/s]
 48%|████▊     | 177600/371472 [3:14:05<17:00:11,  3.17it/s]
                                                            
{'loss': 2.8282, 'learning_rate': 5.699648775022086e-07, 'epoch': 7.65}
+
 48%|████▊     | 177600/371472 [3:14:05<17:00:11,  3.17it/s]
 48%|████▊     | 177601/371472 [3:14:05<16:38:36,  3.24it/s]
 48%|████▊     | 177602/371472 [3:14:06<16:34:21,  3.25it/s]
 48%|████▊     | 177603/371472 [3:14:06<16:34:42,  3.25it/s]
 48%|████▊     | 177604/371472 [3:14:06<15:58:33,  3.37it/s]
 48%|████▊     | 177605/371472 [3:14:07<16:59:26,  3.17it/s]
 48%|████▊     | 177606/371472 [3:14:07<16:42:33,  3.22it/s]
 48%|████▊     | 177607/371472 [3:14:07<16:14:12,  3.32it/s]
 48%|████▊     | 177608/371472 [3:14:08<16:20:42,  3.29it/s]
 48%|████▊     | 177609/371472 [3:14:08<16:10:02,  3.33it/s]
 48%|████▊     | 177610/371472 [3:14:08<15:54:08,  3.39it/s]
 48%|████▊     | 177611/371472 [3:14:08<15:34:39,  3.46it/s]
 48%|████▊     | 177612/371472 [3:14:09<15:35:09,  3.46it/s]
 48%|████▊     | 177613/371472 [3:14:09<15:28:42,  3.48it/s]
 48%|████▊     | 177614/371472 [3:14:09<15:33:36,  3.46it/s]
 48%|████▊     | 177615/371472 [3:14:10<16:35:55,  3.24it/s]
 48%|████▊     | 177616/371472 [3:14:10<16:11:16,  3.33it/s]
 48%|████▊     | 177617/371472 [3:14:10<16:08:31,  3.34it/s]
 48%|████▊     | 177618/371472 [3:14:10<15:57:56,  3.37it/s]
 48%|████▊     | 177619/371472 [3:14:11<16:30:36,  3.26it/s]
 48%|████▊     | 177620/371472 [3:14:11<16:08:38,  3.34it/s]
                                                            
{'loss': 2.8604, 'learning_rate': 5.699163955267297e-07, 'epoch': 7.65}
+
 48%|████▊     | 177620/371472 [3:14:11<16:08:38,  3.34it/s]
 48%|████▊     | 177621/371472 [3:14:11<17:00:53,  3.16it/s]
 48%|████▊     | 177622/371472 [3:14:12<16:17:30,  3.31it/s]
 48%|████▊     | 177623/371472 [3:14:12<16:10:47,  3.33it/s]
 48%|████▊     | 177624/371472 [3:14:12<16:19:56,  3.30it/s]
 48%|████▊     | 177625/371472 [3:14:13<16:02:39,  3.36it/s]
 48%|████▊     | 177626/371472 [3:14:13<16:02:35,  3.36it/s]
 48%|████▊     | 177627/371472 [3:14:13<15:56:50,  3.38it/s]
 48%|████▊     | 177628/371472 [3:14:14<16:25:31,  3.28it/s]
 48%|████▊     | 177629/371472 [3:14:14<16:02:04,  3.36it/s]
 48%|████▊     | 177630/371472 [3:14:14<15:50:31,  3.40it/s]
 48%|████▊     | 177631/371472 [3:14:14<15:39:20,  3.44it/s]
 48%|████▊     | 177632/371472 [3:14:15<16:26:17,  3.28it/s]
 48%|████▊     | 177633/371472 [3:14:15<16:48:04,  3.20it/s]
 48%|████▊     | 177634/371472 [3:14:15<16:30:33,  3.26it/s]
 48%|████▊     | 177635/371472 [3:14:16<15:57:12,  3.38it/s]
 48%|████▊     | 177636/371472 [3:14:16<15:35:01,  3.46it/s]
 48%|████▊     | 177637/371472 [3:14:16<15:37:00,  3.45it/s]
 48%|████▊     | 177638/371472 [3:14:16<15:55:08,  3.38it/s]
 48%|████▊     | 177639/371472 [3:14:17<15:41:56,  3.43it/s]
 48%|████▊     | 177640/371472 [3:14:17<16:16:36,  3.31it/s]
                                                            
{'loss': 2.8404, 'learning_rate': 5.69867913551251e-07, 'epoch': 7.65}
+
 48%|████▊     | 177640/371472 [3:14:17<16:16:36,  3.31it/s]
 48%|████▊     | 177641/371472 [3:14:17<16:14:54,  3.31it/s]
 48%|████▊     | 177642/371472 [3:14:18<16:26:45,  3.27it/s]
 48%|████▊     | 177643/371472 [3:14:18<16:44:00,  3.22it/s]
 48%|████▊     | 177644/371472 [3:14:18<16:25:31,  3.28it/s]
 48%|████▊     | 177645/371472 [3:14:19<15:55:01,  3.38it/s]
 48%|████▊     | 177646/371472 [3:14:19<16:22:35,  3.29it/s]
 48%|████▊     | 177647/371472 [3:14:19<16:32:17,  3.26it/s]
 48%|████▊     | 177648/371472 [3:14:20<17:09:53,  3.14it/s]
 48%|████▊     | 177649/371472 [3:14:20<16:55:30,  3.18it/s]
 48%|████▊     | 177650/371472 [3:14:20<16:26:21,  3.28it/s]
 48%|████▊     | 177651/371472 [3:14:20<16:16:21,  3.31it/s]
 48%|████▊     | 177652/371472 [3:14:21<15:53:25,  3.39it/s]
 48%|████▊     | 177653/371472 [3:14:21<16:05:55,  3.34it/s]
 48%|████▊     | 177654/371472 [3:14:21<16:12:51,  3.32it/s]
 48%|████▊     | 177655/371472 [3:14:22<15:59:02,  3.37it/s]
 48%|████▊     | 177656/371472 [3:14:22<15:35:58,  3.45it/s]
 48%|████▊     | 177657/371472 [3:14:22<15:50:56,  3.40it/s]
 48%|████▊     | 177658/371472 [3:14:23<15:55:14,  3.38it/s]
 48%|████▊     | 177659/371472 [3:14:23<16:41:10,  3.23it/s]
 48%|████▊     | 177660/371472 [3:14:23<16:21:45,  3.29it/s]
                                                            
{'loss': 2.8981, 'learning_rate': 5.698194315757719e-07, 'epoch': 7.65}
+
 48%|████▊     | 177660/371472 [3:14:23<16:21:45,  3.29it/s]
 48%|████▊     | 177661/371472 [3:14:23<16:20:04,  3.30it/s]
 48%|████▊     | 177662/371472 [3:14:24<15:48:22,  3.41it/s]
 48%|████▊     | 177663/371472 [3:14:24<15:48:16,  3.41it/s]
 48%|████▊     | 177664/371472 [3:14:24<15:27:04,  3.48it/s]
 48%|████▊     | 177665/371472 [3:14:25<15:15:06,  3.53it/s]
 48%|████▊     | 177666/371472 [3:14:25<15:36:21,  3.45it/s]
 48%|████▊     | 177667/371472 [3:14:25<15:27:28,  3.48it/s]
 48%|████▊     | 177668/371472 [3:14:25<15:18:19,  3.52it/s]
 48%|████▊     | 177669/371472 [3:14:26<15:10:50,  3.55it/s]
 48%|████▊     | 177670/371472 [3:14:26<15:25:07,  3.49it/s]
 48%|████▊     | 177671/371472 [3:14:26<16:00:30,  3.36it/s]
 48%|████▊     | 177672/371472 [3:14:27<17:16:46,  3.12it/s]
 48%|████▊     | 177673/371472 [3:14:27<16:39:19,  3.23it/s]
 48%|████▊     | 177674/371472 [3:14:27<16:13:12,  3.32it/s]
 48%|████▊     | 177675/371472 [3:14:28<16:01:57,  3.36it/s]
 48%|████▊     | 177676/371472 [3:14:28<15:44:12,  3.42it/s]
 48%|████▊     | 177677/371472 [3:14:28<15:51:24,  3.39it/s]
 48%|████▊     | 177678/371472 [3:14:28<16:16:04,  3.31it/s]
 48%|████▊     | 177679/371472 [3:14:29<15:46:01,  3.41it/s]
 48%|████▊     | 177680/371472 [3:14:29<15:41:21,  3.43it/s]
                                                            
{'loss': 2.8425, 'learning_rate': 5.69770949600293e-07, 'epoch': 7.65}
+
 48%|████▊     | 177680/371472 [3:14:29<15:41:21,  3.43it/s]
 48%|████▊     | 177681/371472 [3:14:29<15:53:12,  3.39it/s]
 48%|████▊     | 177682/371472 [3:14:30<15:50:02,  3.40it/s]
 48%|████▊     | 177683/371472 [3:14:30<15:38:06,  3.44it/s]
 48%|████▊     | 177684/371472 [3:14:30<15:28:22,  3.48it/s]
 48%|████▊     | 177685/371472 [3:14:30<15:43:59,  3.42it/s]
 48%|████▊     | 177686/371472 [3:14:31<15:56:14,  3.38it/s]
 48%|████▊     | 177687/371472 [3:14:31<15:49:49,  3.40it/s]
 48%|████▊     | 177688/371472 [3:14:31<15:34:16,  3.46it/s]
 48%|████▊     | 177689/371472 [3:14:32<15:38:32,  3.44it/s]
 48%|████▊     | 177690/371472 [3:14:32<17:31:23,  3.07it/s]
 48%|████▊     | 177691/371472 [3:14:32<17:04:48,  3.15it/s]
 48%|████▊     | 177692/371472 [3:14:33<17:10:36,  3.13it/s]
 48%|████▊     | 177693/371472 [3:14:33<16:52:18,  3.19it/s]
 48%|████▊     | 177694/371472 [3:14:33<17:16:18,  3.12it/s]
 48%|████▊     | 177695/371472 [3:14:34<17:09:21,  3.14it/s]
 48%|████▊     | 177696/371472 [3:14:34<16:46:22,  3.21it/s]
 48%|████▊     | 177697/371472 [3:14:34<16:32:35,  3.25it/s]
 48%|████▊     | 177698/371472 [3:14:34<16:09:38,  3.33it/s]
 48%|████▊     | 177699/371472 [3:14:35<16:29:40,  3.26it/s]
 48%|████▊     | 177700/371472 [3:14:35<15:54:32,  3.38it/s]
                                                            
{'loss': 2.9297, 'learning_rate': 5.697224676248142e-07, 'epoch': 7.65}
+
 48%|████▊     | 177700/371472 [3:14:35<15:54:32,  3.38it/s]
 48%|████▊     | 177701/371472 [3:14:35<15:56:11,  3.38it/s]
 48%|████▊     | 177702/371472 [3:14:36<15:33:18,  3.46it/s]
 48%|████▊     | 177703/371472 [3:14:36<15:14:35,  3.53it/s]
 48%|████▊     | 177704/371472 [3:14:36<15:03:05,  3.58it/s]
 48%|████▊     | 177705/371472 [3:14:36<15:32:37,  3.46it/s]
 48%|████▊     | 177706/371472 [3:14:37<16:02:34,  3.35it/s]
 48%|████▊     | 177707/371472 [3:14:37<15:40:27,  3.43it/s]
 48%|████▊     | 177708/371472 [3:14:37<16:01:05,  3.36it/s]
 48%|████▊     | 177709/371472 [3:14:38<15:56:47,  3.38it/s]
 48%|████▊     | 177710/371472 [3:14:38<16:53:28,  3.19it/s]
 48%|████▊     | 177711/371472 [3:14:38<16:29:34,  3.26it/s]
 48%|████▊     | 177712/371472 [3:14:39<16:58:36,  3.17it/s]
 48%|████▊     | 177713/371472 [3:14:39<17:19:06,  3.11it/s]
 48%|████▊     | 177714/371472 [3:14:39<17:48:34,  3.02it/s]
 48%|████▊     | 177715/371472 [3:14:40<17:05:13,  3.15it/s]
 48%|████▊     | 177716/371472 [3:14:40<16:57:46,  3.17it/s]
 48%|████▊     | 177717/371472 [3:14:40<16:43:51,  3.22it/s]
 48%|████▊     | 177718/371472 [3:14:41<17:23:13,  3.10it/s]
 48%|████▊     | 177719/371472 [3:14:41<16:42:07,  3.22it/s]
 48%|████▊     | 177720/371472 [3:14:41<17:20:29,  3.10it/s]
                                                            
{'loss': 2.9438, 'learning_rate': 5.696739856493352e-07, 'epoch': 7.65}
+
 48%|████▊     | 177720/371472 [3:14:41<17:20:29,  3.10it/s]
 48%|████▊     | 177721/371472 [3:14:42<16:40:36,  3.23it/s]
 48%|████▊     | 177722/371472 [3:14:42<17:30:10,  3.07it/s]
 48%|████▊     | 177723/371472 [3:14:42<16:59:40,  3.17it/s]
 48%|████▊     | 177724/371472 [3:14:42<16:39:56,  3.23it/s]
 48%|████▊     | 177725/371472 [3:14:43<16:50:06,  3.20it/s]
 48%|████▊     | 177726/371472 [3:14:43<16:46:37,  3.21it/s]
 48%|████▊     | 177727/371472 [3:14:43<17:45:16,  3.03it/s]
 48%|████▊     | 177728/371472 [3:14:44<18:00:37,  2.99it/s]
 48%|████▊     | 177729/371472 [3:14:44<17:32:03,  3.07it/s]
 48%|████▊     | 177730/371472 [3:14:44<17:06:30,  3.15it/s]
 48%|████▊     | 177731/371472 [3:14:45<16:19:00,  3.30it/s]
 48%|████▊     | 177732/371472 [3:14:45<16:39:19,  3.23it/s]
 48%|████▊     | 177733/371472 [3:14:45<16:24:40,  3.28it/s]
 48%|████▊     | 177734/371472 [3:14:46<16:13:43,  3.32it/s]
 48%|████▊     | 177735/371472 [3:14:46<16:36:27,  3.24it/s]
 48%|████▊     | 177736/371472 [3:14:46<16:20:08,  3.29it/s]
 48%|████▊     | 177737/371472 [3:14:47<16:19:49,  3.30it/s]
 48%|████▊     | 177738/371472 [3:14:47<15:52:11,  3.39it/s]
 48%|████▊     | 177739/371472 [3:14:47<15:49:24,  3.40it/s]
 48%|████▊     | 177740/371472 [3:14:47<15:50:19,  3.40it/s]
                                                            
{'loss': 2.8202, 'learning_rate': 5.696255036738563e-07, 'epoch': 7.66}
+
 48%|████▊     | 177740/371472 [3:14:47<15:50:19,  3.40it/s]
 48%|████▊     | 177741/371472 [3:14:48<16:11:39,  3.32it/s]
 48%|████▊     | 177742/371472 [3:14:48<15:31:57,  3.46it/s]
 48%|████▊     | 177743/371472 [3:14:48<15:33:35,  3.46it/s]
 48%|████▊     | 177744/371472 [3:14:49<15:56:25,  3.38it/s]
 48%|████▊     | 177745/371472 [3:14:49<15:44:27,  3.42it/s]
 48%|████▊     | 177746/371472 [3:14:49<15:56:41,  3.37it/s]
 48%|████▊     | 177747/371472 [3:14:49<15:48:11,  3.41it/s]
 48%|████▊     | 177748/371472 [3:14:50<15:19:59,  3.51it/s]
 48%|████▊     | 177749/371472 [3:14:50<15:28:20,  3.48it/s]
 48%|████▊     | 177750/371472 [3:14:50<15:29:12,  3.47it/s]
 48%|████▊     | 177751/371472 [3:14:51<15:14:45,  3.53it/s]
 48%|████▊     | 177752/371472 [3:14:51<15:17:08,  3.52it/s]
 48%|████▊     | 177753/371472 [3:14:51<15:41:02,  3.43it/s]
 48%|████▊     | 177754/371472 [3:14:52<16:46:08,  3.21it/s]
 48%|████▊     | 177755/371472 [3:14:52<17:01:37,  3.16it/s]
 48%|████▊     | 177756/371472 [3:14:52<16:22:56,  3.28it/s]
 48%|████▊     | 177757/371472 [3:14:52<16:34:31,  3.25it/s]
 48%|████▊     | 177758/371472 [3:14:53<15:51:38,  3.39it/s]
 48%|████▊     | 177759/371472 [3:14:53<16:01:54,  3.36it/s]
 48%|████▊     | 177760/371472 [3:14:53<16:05:43,  3.34it/s]
                                                            
{'loss': 2.9952, 'learning_rate': 5.695770216983774e-07, 'epoch': 7.66}
+
 48%|████▊     | 177760/371472 [3:14:53<16:05:43,  3.34it/s]
 48%|████▊     | 177761/371472 [3:14:54<16:16:20,  3.31it/s]
 48%|████▊     | 177762/371472 [3:14:54<16:56:32,  3.18it/s]
 48%|████▊     | 177763/371472 [3:14:54<16:50:44,  3.19it/s]
 48%|████▊     | 177764/371472 [3:14:55<16:38:50,  3.23it/s]
 48%|████▊     | 177765/371472 [3:14:55<17:29:43,  3.08it/s]
 48%|████▊     | 177766/371472 [3:14:55<17:18:48,  3.11it/s]
 48%|████▊     | 177767/371472 [3:14:56<16:29:41,  3.26it/s]
 48%|████▊     | 177768/371472 [3:14:56<16:15:12,  3.31it/s]
 48%|████▊     | 177769/371472 [3:14:56<16:13:37,  3.32it/s]
 48%|████▊     | 177770/371472 [3:14:56<16:07:21,  3.34it/s]
 48%|████▊     | 177771/371472 [3:14:57<17:19:40,  3.11it/s]
 48%|████▊     | 177772/371472 [3:14:57<16:50:06,  3.20it/s]
 48%|████▊     | 177773/371472 [3:14:57<16:33:41,  3.25it/s]
 48%|████▊     | 177774/371472 [3:14:58<18:27:37,  2.91it/s]
 48%|████▊     | 177775/371472 [3:14:58<17:25:18,  3.09it/s]
 48%|████▊     | 177776/371472 [3:14:58<18:07:20,  2.97it/s]
 48%|████▊     | 177777/371472 [3:14:59<17:06:21,  3.15it/s]
 48%|████▊     | 177778/371472 [3:14:59<16:51:18,  3.19it/s]
 48%|████▊     | 177779/371472 [3:14:59<16:22:40,  3.29it/s]
 48%|████▊     | 177780/371472 [3:15:00<16:08:41,  3.33it/s]
                                                            
{'loss': 2.8149, 'learning_rate': 5.695285397228986e-07, 'epoch': 7.66}
+
 48%|████▊     | 177780/371472 [3:15:00<16:08:41,  3.33it/s]
 48%|████▊     | 177781/371472 [3:15:00<16:06:34,  3.34it/s]
 48%|████▊     | 177782/371472 [3:15:00<16:03:35,  3.35it/s]
 48%|████▊     | 177783/371472 [3:15:01<16:33:39,  3.25it/s]
 48%|████▊     | 177784/371472 [3:15:01<16:02:16,  3.35it/s]
 48%|████▊     | 177785/371472 [3:15:01<15:57:25,  3.37it/s]
 48%|████▊     | 177786/371472 [3:15:01<15:55:35,  3.38it/s]
 48%|████▊     | 177787/371472 [3:15:02<15:34:37,  3.45it/s]
 48%|████▊     | 177788/371472 [3:15:02<15:15:44,  3.53it/s]
 48%|████▊     | 177789/371472 [3:15:02<15:14:09,  3.53it/s]
 48%|████▊     | 177790/371472 [3:15:02<15:24:23,  3.49it/s]
 48%|████▊     | 177791/371472 [3:15:03<15:22:11,  3.50it/s]
 48%|████▊     | 177792/371472 [3:15:03<15:07:19,  3.56it/s]
 48%|████▊     | 177793/371472 [3:15:03<15:09:04,  3.55it/s]
 48%|████▊     | 177794/371472 [3:15:04<15:10:43,  3.54it/s]
 48%|████▊     | 177795/371472 [3:15:04<16:05:42,  3.34it/s]
 48%|████▊     | 177796/371472 [3:15:04<16:02:10,  3.35it/s]
 48%|████▊     | 177797/371472 [3:15:05<16:05:47,  3.34it/s]
 48%|████▊     | 177798/371472 [3:15:05<15:43:35,  3.42it/s]
 48%|████▊     | 177799/371472 [3:15:05<16:07:50,  3.34it/s]
 48%|████▊     | 177800/371472 [3:15:05<16:29:46,  3.26it/s]
                                                            
{'loss': 2.9931, 'learning_rate': 5.694800577474196e-07, 'epoch': 7.66}
+
 48%|████▊     | 177800/371472 [3:15:05<16:29:46,  3.26it/s]
 48%|████▊     | 177801/371472 [3:15:06<16:39:27,  3.23it/s]
 48%|████▊     | 177802/371472 [3:15:06<16:38:27,  3.23it/s]
 48%|████▊     | 177803/371472 [3:15:06<16:22:20,  3.29it/s]
 48%|████▊     | 177804/371472 [3:15:07<16:07:12,  3.34it/s]
 48%|████▊     | 177805/371472 [3:15:07<15:55:05,  3.38it/s]
 48%|████▊     | 177806/371472 [3:15:07<16:25:14,  3.28it/s]
 48%|████▊     | 177807/371472 [3:15:08<16:53:02,  3.19it/s]
 48%|████▊     | 177808/371472 [3:15:08<16:22:05,  3.29it/s]
 48%|████▊     | 177809/371472 [3:15:08<16:43:21,  3.22it/s]
 48%|████▊     | 177810/371472 [3:15:09<16:53:08,  3.19it/s]
 48%|████▊     | 177811/371472 [3:15:09<16:52:43,  3.19it/s]
 48%|████▊     | 177812/371472 [3:15:09<16:48:42,  3.20it/s]
 48%|████▊     | 177813/371472 [3:15:10<17:01:03,  3.16it/s]
 48%|████▊     | 177814/371472 [3:15:10<16:29:13,  3.26it/s]
 48%|████▊     | 177815/371472 [3:15:10<16:08:46,  3.33it/s]
 48%|████▊     | 177816/371472 [3:15:10<15:55:48,  3.38it/s]
 48%|████▊     | 177817/371472 [3:15:11<16:00:28,  3.36it/s]
 48%|████▊     | 177818/371472 [3:15:11<16:16:17,  3.31it/s]
 48%|████▊     | 177819/371472 [3:15:11<16:12:46,  3.32it/s]
 48%|████▊     | 177820/371472 [3:15:12<16:22:15,  3.29it/s]
                                                            
{'loss': 2.8799, 'learning_rate': 5.694315757719407e-07, 'epoch': 7.66}
+
 48%|████▊     | 177820/371472 [3:15:12<16:22:15,  3.29it/s]
 48%|████▊     | 177821/371472 [3:15:12<16:31:04,  3.26it/s]
 48%|████▊     | 177822/371472 [3:15:12<19:12:19,  2.80it/s]
 48%|████▊     | 177823/371472 [3:15:13<19:12:50,  2.80it/s]
 48%|████▊     | 177824/371472 [3:15:13<18:02:02,  2.98it/s]
 48%|████▊     | 177825/371472 [3:15:13<17:27:38,  3.08it/s]
 48%|████▊     | 177826/371472 [3:15:14<16:36:55,  3.24it/s]
 48%|████▊     | 177827/371472 [3:15:14<16:03:31,  3.35it/s]
 48%|████▊     | 177828/371472 [3:15:14<15:49:48,  3.40it/s]
 48%|████▊     | 177829/371472 [3:15:14<16:03:35,  3.35it/s]
 48%|████▊     | 177830/371472 [3:15:15<18:05:39,  2.97it/s]
 48%|████▊     | 177831/371472 [3:15:15<17:29:20,  3.08it/s]
 48%|████▊     | 177832/371472 [3:15:15<16:40:14,  3.23it/s]
 48%|████▊     | 177833/371472 [3:15:16<16:28:05,  3.27it/s]
 48%|████▊     | 177834/371472 [3:15:16<15:56:52,  3.37it/s]
 48%|████▊     | 177835/371472 [3:15:16<16:34:09,  3.25it/s]
 48%|████▊     | 177836/371472 [3:15:17<16:38:25,  3.23it/s]
 48%|████▊     | 177837/371472 [3:15:17<16:39:34,  3.23it/s]
 48%|████▊     | 177838/371472 [3:15:17<16:26:38,  3.27it/s]
 48%|████▊     | 177839/371472 [3:15:18<16:25:45,  3.27it/s]
 48%|████▊     | 177840/371472 [3:15:18<16:04:33,  3.35it/s]
                                                            
{'loss': 3.0778, 'learning_rate': 5.693830937964619e-07, 'epoch': 7.66}
+
 48%|████▊     | 177840/371472 [3:15:18<16:04:33,  3.35it/s]
 48%|████▊     | 177841/371472 [3:15:18<16:43:48,  3.21it/s]
 48%|████▊     | 177842/371472 [3:15:18<16:16:16,  3.31it/s]
 48%|████▊     | 177843/371472 [3:15:19<16:23:02,  3.28it/s]
 48%|████▊     | 177844/371472 [3:15:19<16:05:18,  3.34it/s]
 48%|████▊     | 177845/371472 [3:15:19<15:54:21,  3.38it/s]
 48%|████▊     | 177846/371472 [3:15:20<16:42:52,  3.22it/s]
 48%|████▊     | 177847/371472 [3:15:20<16:37:30,  3.24it/s]
 48%|████▊     | 177848/371472 [3:15:20<15:59:29,  3.36it/s]
 48%|████▊     | 177849/371472 [3:15:21<15:49:23,  3.40it/s]
 48%|████▊     | 177850/371472 [3:15:21<15:41:16,  3.43it/s]
 48%|████▊     | 177851/371472 [3:15:21<15:57:07,  3.37it/s]
 48%|████▊     | 177852/371472 [3:15:21<15:59:07,  3.36it/s]
 48%|████▊     | 177853/371472 [3:15:22<15:51:18,  3.39it/s]
 48%|████▊     | 177854/371472 [3:15:22<16:01:44,  3.36it/s]
 48%|████▊     | 177855/371472 [3:15:22<15:57:19,  3.37it/s]
 48%|████▊     | 177856/371472 [3:15:23<16:04:22,  3.35it/s]
 48%|████▊     | 177857/371472 [3:15:23<15:45:27,  3.41it/s]
 48%|████▊     | 177858/371472 [3:15:23<15:39:44,  3.43it/s]
 48%|████▊     | 177859/371472 [3:15:24<15:50:47,  3.39it/s]
 48%|████▊     | 177860/371472 [3:15:24<16:21:00,  3.29it/s]
                                                            
{'loss': 2.8611, 'learning_rate': 5.69334611820983e-07, 'epoch': 7.66}
+
 48%|████▊     | 177860/371472 [3:15:24<16:21:00,  3.29it/s]
 48%|████▊     | 177861/371472 [3:15:24<16:20:57,  3.29it/s]
 48%|████▊     | 177862/371472 [3:15:24<15:58:59,  3.36it/s]
 48%|████▊     | 177863/371472 [3:15:25<15:49:34,  3.40it/s]
 48%|████▊     | 177864/371472 [3:15:25<15:45:01,  3.41it/s]
 48%|████▊     | 177865/371472 [3:15:25<16:23:08,  3.28it/s]
 48%|████▊     | 177866/371472 [3:15:26<16:25:45,  3.27it/s]
 48%|████▊     | 177867/371472 [3:15:26<15:52:21,  3.39it/s]
 48%|████▊     | 177868/371472 [3:15:26<15:58:47,  3.37it/s]
 48%|████▊     | 177869/371472 [3:15:27<16:26:31,  3.27it/s]
 48%|████▊     | 177870/371472 [3:15:27<16:20:18,  3.29it/s]
 48%|████▊     | 177871/371472 [3:15:27<16:11:08,  3.32it/s]
 48%|████▊     | 177872/371472 [3:15:28<17:32:09,  3.07it/s]
 48%|████▊     | 177873/371472 [3:15:28<17:23:47,  3.09it/s]
 48%|████▊     | 177874/371472 [3:15:28<16:52:01,  3.19it/s]
 48%|████▊     | 177875/371472 [3:15:29<19:04:21,  2.82it/s]
 48%|████▊     | 177876/371472 [3:15:29<18:09:19,  2.96it/s]
 48%|████▊     | 177877/371472 [3:15:29<16:58:29,  3.17it/s]
 48%|████▊     | 177878/371472 [3:15:29<16:38:09,  3.23it/s]
 48%|████▊     | 177879/371472 [3:15:30<16:46:24,  3.21it/s]
 48%|████▊     | 177880/371472 [3:15:30<17:28:39,  3.08it/s]
                                                            
{'loss': 2.8026, 'learning_rate': 5.69286129845504e-07, 'epoch': 7.66}
+
 48%|████▊     | 177880/371472 [3:15:30<17:28:39,  3.08it/s]
 48%|████▊     | 177881/371472 [3:15:30<17:02:43,  3.15it/s]
 48%|████▊     | 177882/371472 [3:15:31<16:35:55,  3.24it/s]
 48%|████▊     | 177883/371472 [3:15:31<18:07:32,  2.97it/s]
 48%|████▊     | 177884/371472 [3:15:31<17:52:56,  3.01it/s]
 48%|████▊     | 177885/371472 [3:15:32<16:57:45,  3.17it/s]
 48%|████▊     | 177886/371472 [3:15:32<16:51:30,  3.19it/s]
 48%|████▊     | 177887/371472 [3:15:32<16:24:04,  3.28it/s]
 48%|████▊     | 177888/371472 [3:15:33<17:14:56,  3.12it/s]
 48%|████▊     | 177889/371472 [3:15:33<18:02:38,  2.98it/s]
 48%|████▊     | 177890/371472 [3:15:33<17:27:35,  3.08it/s]
 48%|████▊     | 177891/371472 [3:15:34<17:04:12,  3.15it/s]
 48%|████▊     | 177892/371472 [3:15:34<16:23:06,  3.28it/s]
 48%|████▊     | 177893/371472 [3:15:34<15:57:05,  3.37it/s]
 48%|████▊     | 177894/371472 [3:15:34<15:44:24,  3.42it/s]
 48%|████▊     | 177895/371472 [3:15:35<15:26:43,  3.48it/s]
 48%|████▊     | 177896/371472 [3:15:35<17:26:32,  3.08it/s]
 48%|████▊     | 177897/371472 [3:15:35<17:04:15,  3.15it/s]
 48%|████▊     | 177898/371472 [3:15:36<17:07:12,  3.14it/s]
 48%|████▊     | 177899/371472 [3:15:36<17:10:04,  3.13it/s]
 48%|████▊     | 177900/371472 [3:15:36<16:54:27,  3.18it/s]
                                                            
{'loss': 2.9164, 'learning_rate': 5.692376478700252e-07, 'epoch': 7.66}
+
 48%|████▊     | 177900/371472 [3:15:36<16:54:27,  3.18it/s]
 48%|████▊     | 177901/371472 [3:15:37<16:39:43,  3.23it/s]
 48%|████▊     | 177902/371472 [3:15:37<16:21:07,  3.29it/s]
 48%|████▊     | 177903/371472 [3:15:37<16:22:58,  3.28it/s]
 48%|████▊     | 177904/371472 [3:15:38<17:06:23,  3.14it/s]
 48%|████▊     | 177905/371472 [3:15:38<16:58:05,  3.17it/s]
 48%|████▊     | 177906/371472 [3:15:38<16:55:35,  3.18it/s]
 48%|████▊     | 177907/371472 [3:15:39<16:14:11,  3.31it/s]
 48%|████▊     | 177908/371472 [3:15:39<16:00:55,  3.36it/s]
 48%|████▊     | 177909/371472 [3:15:39<15:52:13,  3.39it/s]
 48%|████▊     | 177910/371472 [3:15:39<15:47:40,  3.40it/s]
 48%|████▊     | 177911/371472 [3:15:40<17:04:57,  3.15it/s]
 48%|████▊     | 177912/371472 [3:15:40<17:26:27,  3.08it/s]
 48%|████▊     | 177913/371472 [3:15:40<16:39:46,  3.23it/s]
 48%|████▊     | 177914/371472 [3:15:41<16:19:19,  3.29it/s]
 48%|████▊     | 177915/371472 [3:15:41<16:46:34,  3.20it/s]
 48%|████▊     | 177916/371472 [3:15:41<16:42:18,  3.22it/s]
 48%|████▊     | 177917/371472 [3:15:42<16:20:55,  3.29it/s]
 48%|████▊     | 177918/371472 [3:15:42<15:45:27,  3.41it/s]
 48%|████▊     | 177919/371472 [3:15:42<15:39:30,  3.43it/s]
 48%|████▊     | 177920/371472 [3:15:42<15:56:05,  3.37it/s]
                                                            
{'loss': 2.9282, 'learning_rate': 5.691891658945463e-07, 'epoch': 7.66}
+
 48%|████▊     | 177920/371472 [3:15:42<15:56:05,  3.37it/s]
 48%|████▊     | 177921/371472 [3:15:43<16:10:05,  3.33it/s]
 48%|████▊     | 177922/371472 [3:15:43<15:53:48,  3.38it/s]
 48%|████▊     | 177923/371472 [3:15:43<15:33:26,  3.46it/s]
 48%|████▊     | 177924/371472 [3:15:44<15:12:09,  3.54it/s]
 48%|████▊     | 177925/371472 [3:15:44<15:12:47,  3.53it/s]
 48%|████▊     | 177926/371472 [3:15:44<15:23:17,  3.49it/s]
 48%|████▊     | 177927/371472 [3:15:45<15:48:12,  3.40it/s]
 48%|████▊     | 177928/371472 [3:15:45<15:39:38,  3.43it/s]
 48%|████▊     | 177929/371472 [3:15:45<15:55:04,  3.38it/s]
 48%|████▊     | 177930/371472 [3:15:45<15:59:06,  3.36it/s]
 48%|████▊     | 177931/371472 [3:15:46<15:45:52,  3.41it/s]
 48%|████▊     | 177932/371472 [3:15:46<15:46:57,  3.41it/s]
 48%|████▊     | 177933/371472 [3:15:46<15:26:47,  3.48it/s]
 48%|████▊     | 177934/371472 [3:15:47<16:13:39,  3.31it/s]
 48%|████▊     | 177935/371472 [3:15:47<15:51:43,  3.39it/s]
 48%|████▊     | 177936/371472 [3:15:47<16:12:24,  3.32it/s]
 48%|████▊     | 177937/371472 [3:15:48<16:46:55,  3.20it/s]
 48%|████▊     | 177938/371472 [3:15:48<16:45:20,  3.21it/s]
 48%|████▊     | 177939/371472 [3:15:48<17:46:13,  3.03it/s]
 48%|████▊     | 177940/371472 [3:15:49<17:17:17,  3.11it/s]
                                                            
{'loss': 2.8347, 'learning_rate': 5.691406839190675e-07, 'epoch': 7.66}
+
 48%|████▊     | 177940/371472 [3:15:49<17:17:17,  3.11it/s]
 48%|████▊     | 177941/371472 [3:15:49<18:00:08,  2.99it/s]
 48%|████▊     | 177942/371472 [3:15:49<17:17:19,  3.11it/s]
 48%|████▊     | 177943/371472 [3:15:49<17:05:31,  3.15it/s]
 48%|████▊     | 177944/371472 [3:15:50<16:27:03,  3.27it/s]
 48%|████▊     | 177945/371472 [3:15:50<16:25:08,  3.27it/s]
 48%|████▊     | 177946/371472 [3:15:50<16:02:19,  3.35it/s]
 48%|████▊     | 177947/371472 [3:15:51<15:58:36,  3.36it/s]
 48%|████▊     | 177948/371472 [3:15:51<15:28:27,  3.47it/s]
 48%|████▊     | 177949/371472 [3:15:51<15:15:13,  3.52it/s]
 48%|████▊     | 177950/371472 [3:15:51<15:30:30,  3.47it/s]
 48%|████▊     | 177951/371472 [3:15:52<16:05:19,  3.34it/s]
 48%|████▊     | 177952/371472 [3:15:52<15:53:32,  3.38it/s]
 48%|████▊     | 177953/371472 [3:15:52<16:28:33,  3.26it/s]
 48%|████▊     | 177954/371472 [3:15:53<17:19:32,  3.10it/s]
 48%|████▊     | 177955/371472 [3:15:53<16:55:11,  3.18it/s]
 48%|████▊     | 177956/371472 [3:15:53<16:25:35,  3.27it/s]
 48%|████▊     | 177957/371472 [3:15:54<16:14:18,  3.31it/s]
 48%|████▊     | 177958/371472 [3:15:54<17:53:42,  3.00it/s]
 48%|████▊     | 177959/371472 [3:15:54<17:04:01,  3.15it/s]
 48%|████▊     | 177960/371472 [3:15:55<17:22:27,  3.09it/s]
                                                            
{'loss': 2.8105, 'learning_rate': 5.690922019435885e-07, 'epoch': 7.67}
+
 48%|████▊     | 177960/371472 [3:15:55<17:22:27,  3.09it/s]
 48%|████▊     | 177961/371472 [3:15:55<16:52:27,  3.19it/s]
 48%|████▊     | 177962/371472 [3:15:55<16:27:12,  3.27it/s]
 48%|████▊     | 177963/371472 [3:15:56<16:10:46,  3.32it/s]
 48%|████▊     | 177964/371472 [3:15:56<15:59:14,  3.36it/s]
 48%|████▊     | 177965/371472 [3:15:56<16:00:30,  3.36it/s]
 48%|████▊     | 177966/371472 [3:15:56<16:26:23,  3.27it/s]
 48%|████▊     | 177967/371472 [3:15:57<17:11:08,  3.13it/s]
 48%|████▊     | 177968/371472 [3:15:57<16:36:59,  3.23it/s]
 48%|████▊     | 177969/371472 [3:15:57<17:19:46,  3.10it/s]
 48%|████▊     | 177970/371472 [3:15:58<16:59:19,  3.16it/s]
 48%|████▊     | 177971/371472 [3:15:58<16:39:02,  3.23it/s]
 48%|████▊     | 177972/371472 [3:15:58<16:08:41,  3.33it/s]
 48%|████▊     | 177973/371472 [3:15:59<15:52:09,  3.39it/s]
 48%|████▊     | 177974/371472 [3:15:59<16:15:37,  3.31it/s]
 48%|████▊     | 177975/371472 [3:15:59<16:40:02,  3.22it/s]
 48%|████▊     | 177976/371472 [3:16:00<17:30:46,  3.07it/s]
 48%|████▊     | 177977/371472 [3:16:00<16:48:28,  3.20it/s]
 48%|████▊     | 177978/371472 [3:16:00<16:40:08,  3.22it/s]
 48%|████▊     | 177979/371472 [3:16:00<16:36:07,  3.24it/s]
 48%|████▊     | 177980/371472 [3:16:01<16:11:22,  3.32it/s]
                                                            
{'loss': 2.7934, 'learning_rate': 5.690437199681096e-07, 'epoch': 7.67}
+
 48%|████▊     | 177980/371472 [3:16:01<16:11:22,  3.32it/s]
 48%|████▊     | 177981/371472 [3:16:01<16:03:39,  3.35it/s]
 48%|████▊     | 177982/371472 [3:16:01<15:33:06,  3.46it/s]
 48%|████▊     | 177983/371472 [3:16:02<15:15:15,  3.52it/s]
 48%|████▊     | 177984/371472 [3:16:02<15:23:55,  3.49it/s]
 48%|████▊     | 177985/371472 [3:16:02<17:31:21,  3.07it/s]
 48%|████▊     | 177986/371472 [3:16:03<16:47:38,  3.20it/s]
 48%|████▊     | 177987/371472 [3:16:03<16:24:00,  3.28it/s]
 48%|████▊     | 177988/371472 [3:16:03<16:20:26,  3.29it/s]
 48%|████▊     | 177989/371472 [3:16:03<16:01:19,  3.35it/s]
 48%|████▊     | 177990/371472 [3:16:04<15:50:35,  3.39it/s]
 48%|████▊     | 177991/371472 [3:16:04<15:31:37,  3.46it/s]
 48%|████▊     | 177992/371472 [3:16:04<15:30:37,  3.47it/s]
 48%|████▊     | 177993/371472 [3:16:05<15:46:35,  3.41it/s]
 48%|████▊     | 177994/371472 [3:16:05<15:52:33,  3.39it/s]
 48%|████▊     | 177995/371472 [3:16:05<15:47:03,  3.40it/s]
 48%|████▊     | 177996/371472 [3:16:06<15:47:13,  3.40it/s]
 48%|████▊     | 177997/371472 [3:16:06<17:43:47,  3.03it/s]
 48%|████▊     | 177998/371472 [3:16:06<17:54:20,  3.00it/s]
 48%|████▊     | 177999/371472 [3:16:07<17:55:10,  3.00it/s]
 48%|████▊     | 178000/371472 [3:16:07<18:57:41,  2.83it/s]
                                                            
{'loss': 2.8627, 'learning_rate': 5.689952379926307e-07, 'epoch': 7.67}
+
 48%|████▊     | 178000/371472 [3:16:07<18:57:41,  2.83it/s]
 48%|████▊     | 178001/371472 [3:16:07<19:02:41,  2.82it/s]
 48%|████▊     | 178002/371472 [3:16:08<18:59:25,  2.83it/s]
 48%|████▊     | 178003/371472 [3:16:08<17:33:19,  3.06it/s]
 48%|████▊     | 178004/371472 [3:16:08<17:38:46,  3.05it/s]
 48%|████▊     | 178005/371472 [3:16:09<17:26:02,  3.08it/s]
 48%|████▊     | 178006/371472 [3:16:09<16:43:27,  3.21it/s]
 48%|████▊     | 178007/371472 [3:16:09<16:26:28,  3.27it/s]
 48%|████▊     | 178008/371472 [3:16:09<16:12:53,  3.31it/s]
 48%|████▊     | 178009/371472 [3:16:10<16:17:46,  3.30it/s]
 48%|████▊     | 178010/371472 [3:16:10<15:56:00,  3.37it/s]
 48%|████▊     | 178011/371472 [3:16:10<15:45:01,  3.41it/s]
 48%|████▊     | 178012/371472 [3:16:11<15:18:49,  3.51it/s]
 48%|████▊     | 178013/371472 [3:16:11<15:10:21,  3.54it/s]
 48%|████▊     | 178014/371472 [3:16:11<15:16:34,  3.52it/s]
 48%|████▊     | 178015/371472 [3:16:11<15:32:17,  3.46it/s]
 48%|████▊     | 178016/371472 [3:16:12<15:30:22,  3.47it/s]
 48%|████▊     | 178017/371472 [3:16:12<15:14:24,  3.53it/s]
 48%|████▊     | 178018/371472 [3:16:12<15:30:11,  3.47it/s]
 48%|████▊     | 178019/371472 [3:16:13<16:13:54,  3.31it/s]
 48%|████▊     | 178020/371472 [3:16:13<16:58:19,  3.17it/s]
                                                            
{'loss': 2.8653, 'learning_rate': 5.68946756017152e-07, 'epoch': 7.67}
+
 48%|████▊     | 178020/371472 [3:16:13<16:58:19,  3.17it/s]
 48%|████▊     | 178021/371472 [3:16:13<16:54:11,  3.18it/s]
 48%|████▊     | 178022/371472 [3:16:14<16:35:29,  3.24it/s]
 48%|████▊     | 178023/371472 [3:16:14<16:42:38,  3.22it/s]
 48%|████▊     | 178024/371472 [3:16:14<16:23:53,  3.28it/s]
 48%|████▊     | 178025/371472 [3:16:15<16:04:15,  3.34it/s]
 48%|████▊     | 178026/371472 [3:16:15<16:00:16,  3.36it/s]
 48%|████▊     | 178027/371472 [3:16:15<15:50:15,  3.39it/s]
 48%|████▊     | 178028/371472 [3:16:15<15:37:19,  3.44it/s]
 48%|████▊     | 178029/371472 [3:16:16<15:15:24,  3.52it/s]
 48%|████▊     | 178030/371472 [3:16:16<15:38:21,  3.44it/s]
 48%|████▊     | 178031/371472 [3:16:16<16:13:00,  3.31it/s]
 48%|████▊     | 178032/371472 [3:16:17<15:55:11,  3.38it/s]
 48%|████▊     | 178033/371472 [3:16:17<16:08:46,  3.33it/s]
 48%|████▊     | 178034/371472 [3:16:17<15:59:57,  3.36it/s]
 48%|████▊     | 178035/371472 [3:16:18<16:34:14,  3.24it/s]
 48%|████▊     | 178036/371472 [3:16:18<16:00:21,  3.36it/s]
 48%|████▊     | 178037/371472 [3:16:18<15:34:01,  3.45it/s]
 48%|████▊     | 178038/371472 [3:16:18<15:37:55,  3.44it/s]
 48%|████▊     | 178039/371472 [3:16:19<15:38:58,  3.43it/s]
 48%|████▊     | 178040/371472 [3:16:19<15:43:47,  3.42it/s]
                                                            
{'loss': 2.7763, 'learning_rate': 5.688982740416729e-07, 'epoch': 7.67}
+
 48%|████▊     | 178040/371472 [3:16:19<15:43:47,  3.42it/s]
 48%|████▊     | 178041/371472 [3:16:19<16:05:54,  3.34it/s]
 48%|████▊     | 178042/371472 [3:16:20<16:21:57,  3.28it/s]
 48%|████▊     | 178043/371472 [3:16:20<16:46:18,  3.20it/s]
 48%|████▊     | 178044/371472 [3:16:20<16:24:48,  3.27it/s]
 48%|████▊     | 178045/371472 [3:16:20<16:15:42,  3.30it/s]
 48%|████▊     | 178046/371472 [3:16:21<16:41:24,  3.22it/s]
 48%|████▊     | 178047/371472 [3:16:21<17:18:53,  3.10it/s]
 48%|████▊     | 178048/371472 [3:16:21<16:50:55,  3.19it/s]
 48%|████▊     | 178049/371472 [3:16:22<16:54:50,  3.18it/s]
 48%|████▊     | 178050/371472 [3:16:22<16:41:00,  3.22it/s]
 48%|████▊     | 178051/371472 [3:16:22<16:28:35,  3.26it/s]
 48%|████▊     | 178052/371472 [3:16:23<16:10:26,  3.32it/s]
 48%|████▊     | 178053/371472 [3:16:23<16:30:24,  3.25it/s]
 48%|████▊     | 178054/371472 [3:16:23<16:21:57,  3.28it/s]
 48%|████▊     | 178055/371472 [3:16:24<16:37:40,  3.23it/s]
 48%|████▊     | 178056/371472 [3:16:24<16:18:37,  3.29it/s]
 48%|████▊     | 178057/371472 [3:16:24<16:28:55,  3.26it/s]
 48%|████▊     | 178058/371472 [3:16:25<17:07:06,  3.14it/s]
 48%|████▊     | 178059/371472 [3:16:25<16:57:51,  3.17it/s]
 48%|████▊     | 178060/371472 [3:16:25<17:16:39,  3.11it/s]
                                                            
{'loss': 2.967, 'learning_rate': 5.68849792066194e-07, 'epoch': 7.67}
+
 48%|████▊     | 178060/371472 [3:16:25<17:16:39,  3.11it/s]
 48%|████▊     | 178061/371472 [3:16:26<17:31:58,  3.06it/s]
 48%|████▊     | 178062/371472 [3:16:26<17:24:07,  3.09it/s]
 48%|████▊     | 178063/371472 [3:16:26<18:32:25,  2.90it/s]
 48%|████▊     | 178064/371472 [3:16:27<17:27:53,  3.08it/s]
 48%|████▊     | 178065/371472 [3:16:27<16:57:26,  3.17it/s]
 48%|████▊     | 178066/371472 [3:16:27<17:04:49,  3.15it/s]
 48%|████▊     | 178067/371472 [3:16:27<17:01:56,  3.15it/s]
 48%|████▊     | 178068/371472 [3:16:28<16:36:26,  3.23it/s]
 48%|████▊     | 178069/371472 [3:16:28<16:24:00,  3.28it/s]
 48%|████▊     | 178070/371472 [3:16:28<16:04:32,  3.34it/s]
 48%|████▊     | 178071/371472 [3:16:29<15:48:23,  3.40it/s]
 48%|████▊     | 178072/371472 [3:16:29<16:00:03,  3.36it/s]
 48%|████▊     | 178073/371472 [3:16:29<16:08:51,  3.33it/s]
 48%|████▊     | 178074/371472 [3:16:30<16:08:22,  3.33it/s]
 48%|████▊     | 178075/371472 [3:16:30<16:48:35,  3.20it/s]
 48%|████▊     | 178076/371472 [3:16:30<16:35:42,  3.24it/s]
 48%|████▊     | 178077/371472 [3:16:30<16:11:22,  3.32it/s]
 48%|████▊     | 178078/371472 [3:16:31<15:57:29,  3.37it/s]
 48%|████▊     | 178079/371472 [3:16:31<16:13:58,  3.31it/s]
 48%|████▊     | 178080/371472 [3:16:31<15:31:19,  3.46it/s]
                                                            
{'loss': 2.8955, 'learning_rate': 5.688013100907152e-07, 'epoch': 7.67}
+
 48%|████▊     | 178080/371472 [3:16:31<15:31:19,  3.46it/s]
 48%|████▊     | 178081/371472 [3:16:32<15:30:22,  3.46it/s]
 48%|████▊     | 178082/371472 [3:16:32<15:36:15,  3.44it/s]
 48%|████▊     | 178083/371472 [3:16:32<16:50:04,  3.19it/s]
 48%|████▊     | 178084/371472 [3:16:33<16:24:31,  3.27it/s]
 48%|████▊     | 178085/371472 [3:16:33<16:21:31,  3.28it/s]
 48%|████▊     | 178086/371472 [3:16:33<16:51:31,  3.19it/s]
 48%|████▊     | 178087/371472 [3:16:34<17:24:12,  3.09it/s]
 48%|████▊     | 178088/371472 [3:16:34<16:46:16,  3.20it/s]
 48%|████▊     | 178089/371472 [3:16:34<16:26:48,  3.27it/s]
 48%|████▊     | 178090/371472 [3:16:34<16:22:24,  3.28it/s]
 48%|████▊     | 178091/371472 [3:16:35<16:10:50,  3.32it/s]
 48%|████▊     | 178092/371472 [3:16:35<15:55:30,  3.37it/s]
 48%|████▊     | 178093/371472 [3:16:35<16:12:51,  3.31it/s]
 48%|████▊     | 178094/371472 [3:16:36<15:43:26,  3.42it/s]
 48%|████▊     | 178095/371472 [3:16:36<16:34:45,  3.24it/s]
 48%|████▊     | 178096/371472 [3:16:36<16:32:07,  3.25it/s]
 48%|████▊     | 178097/371472 [3:16:37<16:07:32,  3.33it/s]
 48%|████▊     | 178098/371472 [3:16:37<17:40:55,  3.04it/s]
 48%|████▊     | 178099/371472 [3:16:37<17:53:36,  3.00it/s]
 48%|████▊     | 178100/371472 [3:16:38<18:19:55,  2.93it/s]
                                                            
{'loss': 2.9241, 'learning_rate': 5.687528281152362e-07, 'epoch': 7.67}
+
 48%|████▊     | 178100/371472 [3:16:38<18:19:55,  2.93it/s]
 48%|████▊     | 178101/371472 [3:16:38<17:11:19,  3.12it/s]
 48%|████▊     | 178102/371472 [3:16:38<16:38:44,  3.23it/s]
 48%|████▊     | 178103/371472 [3:16:38<16:40:32,  3.22it/s]
 48%|████▊     | 178104/371472 [3:16:39<16:40:58,  3.22it/s]
 48%|████▊     | 178105/371472 [3:16:39<16:27:53,  3.26it/s]
 48%|████▊     | 178106/371472 [3:16:39<16:17:49,  3.30it/s]
 48%|████▊     | 178107/371472 [3:16:40<16:32:51,  3.25it/s]
 48%|████▊     | 178108/371472 [3:16:40<17:01:32,  3.15it/s]
 48%|████▊     | 178109/371472 [3:16:40<16:35:26,  3.24it/s]
 48%|████▊     | 178110/371472 [3:16:41<15:59:45,  3.36it/s]
 48%|████▊     | 178111/371472 [3:16:41<15:52:31,  3.38it/s]
 48%|████▊     | 178112/371472 [3:16:41<15:31:00,  3.46it/s]
 48%|████▊     | 178113/371472 [3:16:41<15:49:45,  3.39it/s]
 48%|████▊     | 178114/371472 [3:16:42<15:28:49,  3.47it/s]
 48%|████▊     | 178115/371472 [3:16:42<15:32:07,  3.46it/s]
 48%|████▊     | 178116/371472 [3:16:42<15:36:47,  3.44it/s]
 48%|████▊     | 178117/371472 [3:16:43<16:36:43,  3.23it/s]
 48%|████▊     | 178118/371472 [3:16:43<15:52:48,  3.38it/s]
 48%|████▊     | 178119/371472 [3:16:43<15:34:23,  3.45it/s]
 48%|████▊     | 178120/371472 [3:16:43<15:02:13,  3.57it/s]
                                                            
{'loss': 2.9947, 'learning_rate': 5.687043461397573e-07, 'epoch': 7.67}
+
 48%|████▊     | 178120/371472 [3:16:43<15:02:13,  3.57it/s]
 48%|████▊     | 178121/371472 [3:16:44<15:43:39,  3.41it/s]
 48%|████▊     | 178122/371472 [3:16:44<16:16:49,  3.30it/s]
 48%|████▊     | 178123/371472 [3:16:44<15:51:26,  3.39it/s]
 48%|████▊     | 178124/371472 [3:16:45<15:41:42,  3.42it/s]
 48%|████▊     | 178125/371472 [3:16:45<16:41:55,  3.22it/s]
 48%|████▊     | 178126/371472 [3:16:45<16:25:57,  3.27it/s]
 48%|████▊     | 178127/371472 [3:16:46<16:22:29,  3.28it/s]
 48%|████▊     | 178128/371472 [3:16:46<16:12:32,  3.31it/s]
 48%|████▊     | 178129/371472 [3:16:46<16:52:21,  3.18it/s]
 48%|████▊     | 178130/371472 [3:16:47<16:00:47,  3.35it/s]
 48%|████▊     | 178131/371472 [3:16:47<16:34:14,  3.24it/s]
 48%|████▊     | 178132/371472 [3:16:47<16:50:18,  3.19it/s]
 48%|████▊     | 178133/371472 [3:16:48<16:44:57,  3.21it/s]
 48%|████▊     | 178134/371472 [3:16:48<15:58:57,  3.36it/s]
 48%|████▊     | 178135/371472 [3:16:48<15:31:16,  3.46it/s]
 48%|████▊     | 178136/371472 [3:16:48<16:44:21,  3.21it/s]
 48%|████▊     | 178137/371472 [3:16:49<16:26:13,  3.27it/s]
 48%|████▊     | 178138/371472 [3:16:49<16:02:50,  3.35it/s]
 48%|████▊     | 178139/371472 [3:16:49<18:39:13,  2.88it/s]
 48%|████▊     | 178140/371472 [3:16:50<19:01:35,  2.82it/s]
                                                            
{'loss': 2.7975, 'learning_rate': 5.686558641642784e-07, 'epoch': 7.67}
+
 48%|████▊     | 178140/371472 [3:16:50<19:01:35,  2.82it/s]
 48%|████▊     | 178141/371472 [3:16:50<17:59:48,  2.98it/s]
 48%|████▊     | 178142/371472 [3:16:50<17:26:46,  3.08it/s]
 48%|████▊     | 178143/371472 [3:16:51<17:47:34,  3.02it/s]
 48%|████▊     | 178144/371472 [3:16:51<17:05:36,  3.14it/s]
 48%|████▊     | 178145/371472 [3:16:51<17:08:30,  3.13it/s]
 48%|████▊     | 178146/371472 [3:16:52<16:34:28,  3.24it/s]
 48%|████▊     | 178147/371472 [3:16:52<16:04:38,  3.34it/s]
 48%|████▊     | 178148/371472 [3:16:52<16:05:40,  3.34it/s]
 48%|████▊     | 178149/371472 [3:16:53<15:50:48,  3.39it/s]
 48%|████▊     | 178150/371472 [3:16:53<16:12:48,  3.31it/s]
 48%|████▊     | 178151/371472 [3:16:53<16:40:14,  3.22it/s]
 48%|████▊     | 178152/371472 [3:16:53<16:41:01,  3.22it/s]
 48%|████▊     | 178153/371472 [3:16:54<17:32:30,  3.06it/s]
 48%|███��▊     | 178154/371472 [3:16:54<17:58:53,  2.99it/s]
 48%|████▊     | 178155/371472 [3:16:55<17:39:04,  3.04it/s]
 48%|████▊     | 178156/371472 [3:16:55<17:14:37,  3.11it/s]
 48%|████▊     | 178157/371472 [3:16:55<16:33:42,  3.24it/s]
 48%|████▊     | 178158/371472 [3:16:55<16:23:23,  3.28it/s]
 48%|████▊     | 178159/371472 [3:16:56<16:13:17,  3.31it/s]
 48%|████▊     | 178160/371472 [3:16:56<15:55:18,  3.37it/s]
                                                            
{'loss': 2.9721, 'learning_rate': 5.686073821887996e-07, 'epoch': 7.67}
+
 48%|████▊     | 178160/371472 [3:16:56<15:55:18,  3.37it/s]
 48%|████▊     | 178161/371472 [3:16:56<15:34:29,  3.45it/s]
 48%|████▊     | 178162/371472 [3:16:57<16:32:28,  3.25it/s]
 48%|████▊     | 178163/371472 [3:16:57<16:27:52,  3.26it/s]
 48%|████▊     | 178164/371472 [3:16:57<16:11:09,  3.32it/s]
 48%|████▊     | 178165/371472 [3:16:58<18:25:20,  2.91it/s]
 48%|████▊     | 178166/371472 [3:16:58<17:19:42,  3.10it/s]
 48%|████▊     | 178167/371472 [3:16:58<17:20:13,  3.10it/s]
 48%|████▊     | 178168/371472 [3:16:59<16:59:37,  3.16it/s]
 48%|████▊     | 178169/371472 [3:16:59<16:31:57,  3.25it/s]
 48%|████▊     | 178170/371472 [3:16:59<15:51:01,  3.39it/s]
 48%|████▊     | 178171/371472 [3:16:59<15:59:24,  3.36it/s]
 48%|████▊     | 178172/371472 [3:17:00<15:58:25,  3.36it/s]
 48%|████▊     | 178173/371472 [3:17:00<15:23:43,  3.49it/s]
 48%|████▊     | 178174/371472 [3:17:00<15:46:57,  3.40it/s]
 48%|████▊     | 178175/371472 [3:17:01<15:51:22,  3.39it/s]
 48%|████▊     | 178176/371472 [3:17:01<15:32:44,  3.45it/s]
 48%|████▊     | 178177/371472 [3:17:01<15:26:34,  3.48it/s]
 48%|████▊     | 178178/371472 [3:17:01<15:10:54,  3.54it/s]
 48%|████▊     | 178179/371472 [3:17:02<15:31:45,  3.46it/s]
 48%|████▊     | 178180/371472 [3:17:02<15:34:01,  3.45it/s]
                                                            
{'loss': 2.8841, 'learning_rate': 5.685589002133207e-07, 'epoch': 7.67}
+
 48%|████▊     | 178180/371472 [3:17:02<15:34:01,  3.45it/s]
 48%|████▊     | 178181/371472 [3:17:02<15:39:21,  3.43it/s]
 48%|████▊     | 178182/371472 [3:17:03<15:51:06,  3.39it/s]
 48%|████▊     | 178183/371472 [3:17:03<16:45:39,  3.20it/s]
 48%|████▊     | 178184/371472 [3:17:03<16:58:37,  3.16it/s]
 48%|████▊     | 178185/371472 [3:17:04<17:54:14,  3.00it/s]
 48%|████▊     | 178186/371472 [3:17:04<16:54:02,  3.18it/s]
 48%|████▊     | 178187/371472 [3:17:04<16:28:27,  3.26it/s]
 48%|████▊     | 178188/371472 [3:17:04<16:17:08,  3.30it/s]
 48%|████▊     | 178189/371472 [3:17:05<16:27:59,  3.26it/s]
 48%|████▊     | 178190/371472 [3:17:05<16:05:41,  3.34it/s]
 48%|████▊     | 178191/371472 [3:17:05<16:12:56,  3.31it/s]
 48%|████▊     | 178192/371472 [3:17:06<15:51:23,  3.39it/s]
 48%|████▊     | 178193/371472 [3:17:06<15:17:25,  3.51it/s]
 48%|████▊     | 178194/371472 [3:17:06<16:22:16,  3.28it/s]
 48%|████▊     | 178195/371472 [3:17:07<17:13:29,  3.12it/s]
 48%|████▊     | 178196/371472 [3:17:07<16:47:13,  3.20it/s]
 48%|████▊     | 178197/371472 [3:17:07<16:33:07,  3.24it/s]
 48%|████▊     | 178198/371472 [3:17:08<16:47:18,  3.20it/s]
 48%|████▊     | 178199/371472 [3:17:08<16:01:49,  3.35it/s]
 48%|████▊     | 178200/371472 [3:17:08<15:43:36,  3.41it/s]
                                                            
{'loss': 2.7844, 'learning_rate': 5.685104182378418e-07, 'epoch': 7.68}
+
 48%|████▊     | 178200/371472 [3:17:08<15:43:36,  3.41it/s]
 48%|████▊     | 178201/371472 [3:17:08<17:14:28,  3.11it/s]
 48%|████▊     | 178202/371472 [3:17:09<16:38:39,  3.23it/s]
 48%|████▊     | 178203/371472 [3:17:09<16:30:39,  3.25it/s]
 48%|████▊     | 178204/371472 [3:17:09<16:13:40,  3.31it/s]
 48%|████▊     | 178205/371472 [3:17:10<15:37:24,  3.44it/s]
 48%|████▊     | 178206/371472 [3:17:10<15:44:26,  3.41it/s]
 48%|████▊     | 178207/371472 [3:17:10<16:12:23,  3.31it/s]
 48%|████▊     | 178208/371472 [3:17:11<16:11:40,  3.31it/s]
 48%|████▊     | 178209/371472 [3:17:11<16:08:32,  3.33it/s]
 48%|████▊     | 178210/371472 [3:17:11<17:43:28,  3.03it/s]
 48%|████▊     | 178211/371472 [3:17:12<17:02:17,  3.15it/s]
 48%|████▊     | 178212/371472 [3:17:12<16:34:02,  3.24it/s]
 48%|████▊     | 178213/371472 [3:17:12<16:01:34,  3.35it/s]
 48%|████▊     | 178214/371472 [3:17:12<16:30:08,  3.25it/s]
 48%|████▊     | 178215/371472 [3:17:13<16:53:10,  3.18it/s]
 48%|████▊     | 178216/371472 [3:17:13<17:29:07,  3.07it/s]
 48%|████▊     | 178217/371472 [3:17:13<16:44:29,  3.21it/s]
 48%|████▊     | 178218/371472 [3:17:14<17:13:44,  3.12it/s]
 48%|████▊     | 178219/371472 [3:17:14<16:45:51,  3.20it/s]
 48%|████▊     | 178220/371472 [3:17:14<16:40:13,  3.22it/s]
                                                            
{'loss': 3.0574, 'learning_rate': 5.684619362623629e-07, 'epoch': 7.68}
+
 48%|████▊     | 178220/371472 [3:17:14<16:40:13,  3.22it/s]
 48%|████▊     | 178221/371472 [3:17:15<16:33:21,  3.24it/s]
 48%|████▊     | 178222/371472 [3:17:15<17:08:00,  3.13it/s]
 48%|████▊     | 178223/371472 [3:17:15<17:19:58,  3.10it/s]
 48%|████▊     | 178224/371472 [3:17:16<18:21:16,  2.92it/s]
 48%|████▊     | 178225/371472 [3:17:16<18:29:30,  2.90it/s]
 48%|████▊     | 178226/371472 [3:17:16<19:53:42,  2.70it/s]
 48%|████▊     | 178227/371472 [3:17:17<18:29:31,  2.90it/s]
 48%|████▊     | 178228/371472 [3:17:17<18:10:16,  2.95it/s]
 48%|████▊     | 178229/371472 [3:17:17<17:29:00,  3.07it/s]
 48%|████▊     | 178230/371472 [3:17:18<17:47:58,  3.02it/s]
 48%|████▊     | 178231/371472 [3:17:18<17:20:22,  3.10it/s]
 48%|████▊     | 178232/371472 [3:17:18<17:41:22,  3.03it/s]
 48%|████▊     | 178233/371472 [3:17:19<17:02:50,  3.15it/s]
 48%|████▊     | 178234/371472 [3:17:19<16:49:10,  3.19it/s]
 48%|████▊     | 178235/371472 [3:17:19<16:10:48,  3.32it/s]
 48%|████▊     | 178236/371472 [3:17:20<15:56:22,  3.37it/s]
 48%|████▊     | 178237/371472 [3:17:20<15:54:07,  3.38it/s]
 48%|████▊     | 178238/371472 [3:17:20<15:51:28,  3.38it/s]
 48%|████▊     | 178239/371472 [3:17:20<15:40:04,  3.43it/s]
 48%|████▊     | 178240/371472 [3:17:21<16:20:57,  3.28it/s]
                                                            
{'loss': 2.8605, 'learning_rate': 5.684134542868839e-07, 'epoch': 7.68}
+
 48%|████▊     | 178240/371472 [3:17:21<16:20:57,  3.28it/s]
 48%|████▊     | 178241/371472 [3:17:21<16:47:20,  3.20it/s]
 48%|████▊     | 178242/371472 [3:17:21<17:22:20,  3.09it/s]
 48%|████▊     | 178243/371472 [3:17:22<17:18:01,  3.10it/s]
 48%|████▊     | 178244/371472 [3:17:22<17:16:06,  3.11it/s]
 48%|████▊     | 178245/371472 [3:17:22<16:44:25,  3.21it/s]
 48%|████▊     | 178246/371472 [3:17:23<16:04:02,  3.34it/s]
 48%|████▊     | 178247/371472 [3:17:23<16:01:02,  3.35it/s]
 48%|████▊     | 178248/371472 [3:17:23<15:42:34,  3.42it/s]
 48%|████▊     | 178249/371472 [3:17:23<15:14:16,  3.52it/s]
 48%|████▊     | 178250/371472 [3:17:24<16:33:23,  3.24it/s]
 48%|████▊     | 178251/371472 [3:17:24<16:05:46,  3.33it/s]
 48%|████▊     | 178252/371472 [3:17:24<16:04:02,  3.34it/s]
 48%|████▊     | 178253/371472 [3:17:25<15:48:21,  3.40it/s]
 48%|████▊     | 178254/371472 [3:17:25<15:53:55,  3.38it/s]
 48%|████▊     | 178255/371472 [3:17:25<16:19:32,  3.29it/s]
 48%|████▊     | 178256/371472 [3:17:26<16:06:43,  3.33it/s]
 48%|████▊     | 178257/371472 [3:17:26<15:59:10,  3.36it/s]
 48%|████▊     | 178258/371472 [3:17:26<15:45:41,  3.41it/s]
 48%|████▊     | 178259/371472 [3:17:26<15:52:42,  3.38it/s]
 48%|████▊     | 178260/371472 [3:17:27<15:38:50,  3.43it/s]
                                                            
{'loss': 2.938, 'learning_rate': 5.68364972311405e-07, 'epoch': 7.68}
+
 48%|████▊     | 178260/371472 [3:17:27<15:38:50,  3.43it/s]
 48%|████▊     | 178261/371472 [3:17:27<15:29:26,  3.46it/s]
 48%|████▊     | 178262/371472 [3:17:27<16:27:31,  3.26it/s]
 48%|████▊     | 178263/371472 [3:17:28<16:12:44,  3.31it/s]
 48%|████▊     | 178264/371472 [3:17:28<15:35:01,  3.44it/s]
 48%|████▊     | 178265/371472 [3:17:28<19:20:24,  2.77it/s]
 48%|████▊     | 178266/371472 [3:17:29<18:59:56,  2.82it/s]
 48%|████▊     | 178267/371472 [3:17:29<18:31:40,  2.90it/s]
 48%|████▊     | 178268/371472 [3:17:29<18:28:03,  2.91it/s]
 48%|████▊     | 178269/371472 [3:17:30<17:54:29,  3.00it/s]
 48%|████▊     | 178270/371472 [3:17:30<17:27:53,  3.07it/s]
 48%|████▊     | 178271/371472 [3:17:30<17:02:46,  3.15it/s]
 48%|████▊     | 178272/371472 [3:17:31<17:01:32,  3.15it/s]
 48%|████▊     | 178273/371472 [3:17:31<16:44:08,  3.21it/s]
 48%|████▊     | 178274/371472 [3:17:31<17:08:05,  3.13it/s]
 48%|████▊     | 178275/371472 [3:17:32<17:36:59,  3.05it/s]
 48%|████▊     | 178276/371472 [3:17:32<16:48:18,  3.19it/s]
 48%|████▊     | 178277/371472 [3:17:32<16:09:57,  3.32it/s]
 48%|████▊     | 178278/371472 [3:17:33<16:23:05,  3.28it/s]
 48%|████▊     | 178279/371472 [3:17:33<16:05:19,  3.34it/s]
 48%|████▊     | 178280/371472 [3:17:33<16:00:16,  3.35it/s]
                                                            
{'loss': 2.8949, 'learning_rate': 5.683164903359261e-07, 'epoch': 7.68}
+
 48%|████▊     | 178280/371472 [3:17:33<16:00:16,  3.35it/s]
 48%|████▊     | 178281/371472 [3:17:33<16:09:15,  3.32it/s]
 48%|████▊     | 178282/371472 [3:17:34<16:08:58,  3.32it/s]
 48%|████▊     | 178283/371472 [3:17:34<15:39:09,  3.43it/s]
 48%|████▊     | 178284/371472 [3:17:34<17:05:59,  3.14it/s]
 48%|████▊     | 178285/371472 [3:17:35<16:52:38,  3.18it/s]
 48%|████▊     | 178286/371472 [3:17:35<16:23:08,  3.27it/s]
 48%|████▊     | 178287/371472 [3:17:35<16:00:36,  3.35it/s]
 48%|████▊     | 178288/371472 [3:17:36<15:38:41,  3.43it/s]
 48%|████▊     | 178289/371472 [3:17:36<15:39:15,  3.43it/s]
 48%|████▊     | 178290/371472 [3:17:36<15:14:08,  3.52it/s]
 48%|████▊     | 178291/371472 [3:17:36<17:10:22,  3.12it/s]
 48%|████▊     | 178292/371472 [3:17:37<17:44:53,  3.02it/s]
 48%|████▊     | 178293/371472 [3:17:37<19:22:46,  2.77it/s]
 48%|████▊     | 178294/371472 [3:17:38<19:34:53,  2.74it/s]
 48%|████▊     | 178295/371472 [3:17:38<19:09:53,  2.80it/s]
 48%|████▊     | 178296/371472 [3:17:38<18:23:13,  2.92it/s]
 48%|████▊     | 178297/371472 [3:17:39<17:55:43,  2.99it/s]
 48%|████▊     | 178298/371472 [3:17:39<17:14:02,  3.11it/s]
 48%|████▊     | 178299/371472 [3:17:39<16:36:46,  3.23it/s]
 48%|████▊     | 178300/371472 [3:17:39<16:10:21,  3.32it/s]
                                                            
{'loss': 2.8205, 'learning_rate': 5.682680083604473e-07, 'epoch': 7.68}
+
 48%|████▊     | 178300/371472 [3:17:39<16:10:21,  3.32it/s]
 48%|████▊     | 178301/371472 [3:17:40<16:18:26,  3.29it/s]
 48%|████▊     | 178302/371472 [3:17:40<18:46:16,  2.86it/s]
 48%|████▊     | 178303/371472 [3:17:41<17:48:29,  3.01it/s]
 48%|████▊     | 178304/371472 [3:17:41<17:18:03,  3.10it/s]
 48%|████▊     | 178305/371472 [3:17:41<17:02:08,  3.15it/s]
 48%|████▊     | 178306/371472 [3:17:41<17:02:23,  3.15it/s]
 48%|████▊     | 178307/371472 [3:17:42<17:33:13,  3.06it/s]
 48%|████▊     | 178308/371472 [3:17:42<17:38:18,  3.04it/s]
 48%|████▊     | 178309/371472 [3:17:42<16:59:30,  3.16it/s]
 48%|████▊     | 178310/371472 [3:17:43<16:47:14,  3.20it/s]
 48%|████▊     | 178311/371472 [3:17:43<16:32:54,  3.24it/s]
 48%|████▊     | 178312/371472 [3:17:43<16:00:56,  3.35it/s]
 48%|████▊     | 178313/371472 [3:17:44<15:55:05,  3.37it/s]
 48%|████▊     | 178314/371472 [3:17:44<16:01:32,  3.35it/s]
 48%|████▊     | 178315/371472 [3:17:44<15:56:16,  3.37it/s]
 48%|████▊     | 178316/371472 [3:17:44<15:55:24,  3.37it/s]
 48%|████▊     | 178317/371472 [3:17:45<15:50:29,  3.39it/s]
 48%|████▊     | 178318/371472 [3:17:45<16:05:12,  3.34it/s]
 48%|████▊     | 178319/371472 [3:17:45<16:01:05,  3.35it/s]
 48%|████▊     | 178320/371472 [3:17:46<17:50:36,  3.01it/s]
                                                            
{'loss': 2.8276, 'learning_rate': 5.682195263849684e-07, 'epoch': 7.68}
+
 48%|████▊     | 178320/371472 [3:17:46<17:50:36,  3.01it/s]
 48%|████▊     | 178321/371472 [3:17:46<16:52:27,  3.18it/s]
 48%|████▊     | 178322/371472 [3:17:46<16:23:58,  3.27it/s]
 48%|████▊     | 178323/371472 [3:17:47<16:22:00,  3.28it/s]
 48%|████▊     | 178324/371472 [3:17:47<16:11:07,  3.31it/s]
 48%|████▊     | 178325/371472 [3:17:47<15:47:47,  3.40it/s]
 48%|████▊     | 178326/371472 [3:17:48<16:57:28,  3.16it/s]
 48%|████▊     | 178327/371472 [3:17:48<16:12:43,  3.31it/s]
 48%|████▊     | 178328/371472 [3:17:48<15:58:56,  3.36it/s]
 48%|████▊     | 178329/371472 [3:17:48<16:08:14,  3.32it/s]
 48%|████▊     | 178330/371472 [3:17:49<15:46:56,  3.40it/s]
 48%|████▊     | 178331/371472 [3:17:49<15:20:38,  3.50it/s]
 48%|████▊     | 178332/371472 [3:17:49<15:52:55,  3.38it/s]
 48%|████▊     | 178333/371472 [3:17:50<16:19:59,  3.28it/s]
 48%|████▊     | 178334/371472 [3:17:50<15:49:57,  3.39it/s]
 48%|████▊     | 178335/371472 [3:17:50<15:39:06,  3.43it/s]
 48%|████▊     | 178336/371472 [3:17:51<17:42:04,  3.03it/s]
 48%|████▊     | 178337/371472 [3:17:51<16:55:25,  3.17it/s]
 48%|████▊     | 178338/371472 [3:17:51<16:03:43,  3.34it/s]
 48%|████▊     | 178339/371472 [3:17:51<16:22:45,  3.28it/s]
 48%|████▊     | 178340/371472 [3:17:52<16:02:40,  3.34it/s]
                                                            
{'loss': 2.9013, 'learning_rate': 5.681710444094895e-07, 'epoch': 7.68}
+
 48%|████▊     | 178340/371472 [3:17:52<16:02:40,  3.34it/s]
 48%|████▊     | 178341/371472 [3:17:52<16:07:00,  3.33it/s]
 48%|████▊     | 178342/371472 [3:17:52<16:48:05,  3.19it/s]
 48%|████▊     | 178343/371472 [3:17:53<16:14:25,  3.30it/s]
 48%|████▊     | 178344/371472 [3:17:53<15:51:14,  3.38it/s]
 48%|████▊     | 178345/371472 [3:17:53<16:15:11,  3.30it/s]
 48%|████▊     | 178346/371472 [3:17:54<16:18:59,  3.29it/s]
 48%|████▊     | 178347/371472 [3:17:54<16:03:06,  3.34it/s]
 48%|████▊     | 178348/371472 [3:17:54<15:56:25,  3.37it/s]
 48%|████▊     | 178349/371472 [3:17:55<16:53:22,  3.18it/s]
 48%|████▊     | 178350/371472 [3:17:55<16:21:48,  3.28it/s]
 48%|████▊     | 178351/371472 [3:17:55<16:16:11,  3.30it/s]
 48%|████▊     | 178352/371472 [3:17:55<15:46:34,  3.40it/s]
 48%|████▊     | 178353/371472 [3:17:56<15:28:12,  3.47it/s]
 48%|████▊     | 178354/371472 [3:17:56<16:26:56,  3.26it/s]
 48%|████▊     | 178355/371472 [3:17:56<17:08:06,  3.13it/s]
 48%|████▊     | 178356/371472 [3:17:57<16:09:06,  3.32it/s]
 48%|████▊     | 178357/371472 [3:17:57<16:48:04,  3.19it/s]
 48%|████▊     | 178358/371472 [3:17:57<16:34:43,  3.24it/s]
 48%|████▊     | 178359/371472 [3:17:58<17:16:58,  3.10it/s]
 48%|████▊     | 178360/371472 [3:17:58<16:58:09,  3.16it/s]
                                                            
{'loss': 3.0176, 'learning_rate': 5.681225624340106e-07, 'epoch': 7.68}
+
 48%|████▊     | 178360/371472 [3:17:58<16:58:09,  3.16it/s]
 48%|████▊     | 178361/371472 [3:17:58<17:02:37,  3.15it/s]
 48%|████▊     | 178362/371472 [3:17:59<17:33:11,  3.06it/s]
 48%|████▊     | 178363/371472 [3:17:59<17:03:23,  3.14it/s]
 48%|████▊     | 178364/371472 [3:17:59<17:28:22,  3.07it/s]
 48%|████▊     | 178365/371472 [3:18:00<16:55:45,  3.17it/s]
 48%|████▊     | 178366/371472 [3:18:00<16:47:09,  3.20it/s]
 48%|████▊     | 178367/371472 [3:18:00<16:17:05,  3.29it/s]
 48%|████▊     | 178368/371472 [3:18:00<16:58:19,  3.16it/s]
 48%|████▊     | 178369/371472 [3:18:01<16:56:58,  3.16it/s]
 48%|████▊     | 178370/371472 [3:18:01<16:25:03,  3.27it/s]
 48%|████▊     | 178371/371472 [3:18:01<17:18:43,  3.10it/s]
 48%|████▊     | 178372/371472 [3:18:02<16:54:26,  3.17it/s]
 48%|████▊     | 178373/371472 [3:18:02<16:50:05,  3.19it/s]
 48%|████▊     | 178374/371472 [3:18:02<16:33:22,  3.24it/s]
 48%|████▊     | 178375/371472 [3:18:03<16:09:37,  3.32it/s]
 48%|████▊     | 178376/371472 [3:18:03<15:52:50,  3.38it/s]
 48%|████▊     | 178377/371472 [3:18:03<15:43:28,  3.41it/s]
 48%|████▊     | 178378/371472 [3:18:03<15:40:06,  3.42it/s]
 48%|████▊     | 178379/371472 [3:18:04<15:25:34,  3.48it/s]
 48%|████▊     | 178380/371472 [3:18:04<15:15:27,  3.52it/s]
                                                            
{'loss': 2.8536, 'learning_rate': 5.680740804585317e-07, 'epoch': 7.68}
+
 48%|████▊     | 178380/371472 [3:18:04<15:15:27,  3.52it/s]
 48%|████▊     | 178381/371472 [3:18:04<16:02:06,  3.34it/s]
 48%|████▊     | 178382/371472 [3:18:05<15:56:11,  3.37it/s]
 48%|████▊     | 178383/371472 [3:18:05<16:30:21,  3.25it/s]
 48%|████▊     | 178384/371472 [3:18:05<16:07:45,  3.33it/s]
 48%|████▊     | 178385/371472 [3:18:06<16:05:08,  3.33it/s]
 48%|████▊     | 178386/371472 [3:18:06<16:03:19,  3.34it/s]
 48%|████▊     | 178387/371472 [3:18:06<16:02:58,  3.34it/s]
 48%|████▊     | 178388/371472 [3:18:06<16:03:53,  3.34it/s]
 48%|████▊     | 178389/371472 [3:18:07<16:44:53,  3.20it/s]
 48%|████▊     | 178390/371472 [3:18:07<16:35:05,  3.23it/s]
 48%|████▊     | 178391/371472 [3:18:07<16:19:54,  3.28it/s]
 48%|████▊     | 178392/371472 [3:18:08<16:06:35,  3.33it/s]
 48%|████▊     | 178393/371472 [3:18:08<15:56:21,  3.36it/s]
 48%|████▊     | 178394/371472 [3:18:08<15:36:09,  3.44it/s]
 48%|████▊     | 178395/371472 [3:18:09<16:00:35,  3.35it/s]
 48%|████▊     | 178396/371472 [3:18:09<16:05:56,  3.33it/s]
 48%|████▊     | 178397/371472 [3:18:09<16:43:56,  3.21it/s]
 48%|████▊     | 178398/371472 [3:18:09<16:17:26,  3.29it/s]
 48%|████▊     | 178399/371472 [3:18:10<16:37:38,  3.23it/s]
 48%|████▊     | 178400/371472 [3:18:10<17:15:35,  3.11it/s]
                                                            
{'loss': 2.9184, 'learning_rate': 5.680255984830529e-07, 'epoch': 7.68}
+
 48%|████▊     | 178400/371472 [3:18:10<17:15:35,  3.11it/s]
 48%|████▊     | 178401/371472 [3:18:11<17:34:08,  3.05it/s]
 48%|████▊     | 178402/371472 [3:18:11<16:47:32,  3.19it/s]
 48%|████▊     | 178403/371472 [3:18:11<16:21:09,  3.28it/s]
 48%|████▊     | 178404/371472 [3:18:11<16:14:10,  3.30it/s]
 48%|████▊     | 178405/371472 [3:18:12<15:35:55,  3.44it/s]
 48%|████▊     | 178406/371472 [3:18:12<15:19:58,  3.50it/s]
 48%|████▊     | 178407/371472 [3:18:12<15:33:05,  3.45it/s]
 48%|████▊     | 178408/371472 [3:18:13<15:39:51,  3.42it/s]
 48%|████▊     | 178409/371472 [3:18:13<15:49:18,  3.39it/s]
 48%|████▊     | 178410/371472 [3:18:13<15:48:25,  3.39it/s]
 48%|████▊     | 178411/371472 [3:18:13<16:40:55,  3.21it/s]
 48%|████▊     | 178412/371472 [3:18:14<17:06:34,  3.13it/s]
 48%|████▊     | 178413/371472 [3:18:14<16:58:23,  3.16it/s]
 48%|████▊     | 178414/371472 [3:18:14<16:38:24,  3.22it/s]
 48%|████▊     | 178415/371472 [3:18:15<16:10:32,  3.32it/s]
 48%|████▊     | 178416/371472 [3:18:15<15:51:45,  3.38it/s]
 48%|████▊     | 178417/371472 [3:18:15<15:38:01,  3.43it/s]
 48%|████▊     | 178418/371472 [3:18:16<15:30:42,  3.46it/s]
 48%|████▊     | 178419/371472 [3:18:16<15:38:22,  3.43it/s]
 48%|████▊     | 178420/371472 [3:18:16<15:30:20,  3.46it/s]
                                                            
{'loss': 2.7591, 'learning_rate': 5.67977116507574e-07, 'epoch': 7.68}
+
 48%|████▊     | 178420/371472 [3:18:16<15:30:20,  3.46it/s]
 48%|████▊     | 178421/371472 [3:18:16<15:38:18,  3.43it/s]
 48%|████▊     | 178422/371472 [3:18:17<15:34:07,  3.44it/s]
 48%|████▊     | 178423/371472 [3:18:17<15:49:46,  3.39it/s]
 48%|████▊     | 178424/371472 [3:18:17<16:05:22,  3.33it/s]
 48%|████▊     | 178425/371472 [3:18:18<16:24:40,  3.27it/s]
 48%|████▊     | 178426/371472 [3:18:18<15:53:53,  3.37it/s]
 48%|████▊     | 178427/371472 [3:18:18<15:30:00,  3.46it/s]
 48%|████▊     | 178428/371472 [3:18:18<15:26:02,  3.47it/s]
 48%|████▊     | 178429/371472 [3:18:19<14:56:24,  3.59it/s]
 48%|████▊     | 178430/371472 [3:18:19<14:44:39,  3.64it/s]
 48%|████▊     | 178431/371472 [3:18:19<14:56:55,  3.59it/s]
 48%|████▊     | 178432/371472 [3:18:20<15:00:46,  3.57it/s]
 48%|████▊     | 178433/371472 [3:18:20<15:16:25,  3.51it/s]
 48%|████▊     | 178434/371472 [3:18:20<15:43:43,  3.41it/s]
 48%|████▊     | 178435/371472 [3:18:20<16:01:13,  3.35it/s]
 48%|████▊     | 178436/371472 [3:18:21<15:59:04,  3.35it/s]
 48%|████▊     | 178437/371472 [3:18:21<15:51:53,  3.38it/s]
 48%|████▊     | 178438/371472 [3:18:21<15:59:56,  3.35it/s]
 48%|████▊     | 178439/371472 [3:18:22<16:24:34,  3.27it/s]
 48%|████▊     | 178440/371472 [3:18:22<16:14:57,  3.30it/s]
                                                            
{'loss': 2.9337, 'learning_rate': 5.67928634532095e-07, 'epoch': 7.69}
+
 48%|████▊     | 178440/371472 [3:18:22<16:14:57,  3.30it/s]
 48%|████▊     | 178441/371472 [3:18:22<16:10:10,  3.32it/s]
 48%|████▊     | 178442/371472 [3:18:23<16:55:46,  3.17it/s]
 48%|████▊     | 178443/371472 [3:18:23<16:46:06,  3.20it/s]
 48%|████▊     | 178444/371472 [3:18:23<16:13:51,  3.30it/s]
 48%|████▊     | 178445/371472 [3:18:24<16:05:15,  3.33it/s]
 48%|████▊     | 178446/371472 [3:18:24<15:58:34,  3.36it/s]
 48%|████▊     | 178447/371472 [3:18:24<15:49:28,  3.39it/s]
 48%|████▊     | 178448/371472 [3:18:24<16:13:20,  3.31it/s]
 48%|████▊     | 178449/371472 [3:18:25<15:59:43,  3.35it/s]
 48%|████▊     | 178450/371472 [3:18:25<16:54:30,  3.17it/s]
 48%|████▊     | 178451/371472 [3:18:25<17:01:16,  3.15it/s]
 48%|████▊     | 178452/371472 [3:18:26<20:49:01,  2.58it/s]
 48%|████▊     | 178453/371472 [3:18:26<19:42:51,  2.72it/s]
 48%|████▊     | 178454/371472 [3:18:27<18:22:22,  2.92it/s]
 48%|████▊     | 178455/371472 [3:18:27<17:24:14,  3.08it/s]
 48%|████▊     | 178456/371472 [3:18:27<16:55:01,  3.17it/s]
 48%|████▊     | 178457/371472 [3:18:27<17:02:38,  3.15it/s]
 48%|████▊     | 178458/371472 [3:18:28<16:32:43,  3.24it/s]
 48%|████▊     | 178459/371472 [3:18:28<15:58:36,  3.36it/s]
 48%|████▊     | 178460/371472 [3:18:28<15:53:15,  3.37it/s]
                                                            
{'loss': 2.878, 'learning_rate': 5.678801525566162e-07, 'epoch': 7.69}
+
 48%|████▊     | 178460/371472 [3:18:28<15:53:15,  3.37it/s]
 48%|████▊     | 178461/371472 [3:18:29<15:32:59,  3.45it/s]
 48%|████▊     | 178462/371472 [3:18:29<16:21:03,  3.28it/s]
 48%|████▊     | 178463/371472 [3:18:29<16:27:39,  3.26it/s]
 48%|████▊     | 178464/371472 [3:18:30<16:23:02,  3.27it/s]
 48%|████▊     | 178465/371472 [3:18:30<15:45:17,  3.40it/s]
 48%|████▊     | 178466/371472 [3:18:30<15:53:38,  3.37it/s]
 48%|████▊     | 178467/371472 [3:18:30<15:35:59,  3.44it/s]
 48%|████▊     | 178468/371472 [3:18:31<16:25:44,  3.26it/s]
 48%|████▊     | 178469/371472 [3:18:31<16:33:34,  3.24it/s]
 48%|████▊     | 178470/371472 [3:18:31<16:13:29,  3.30it/s]
 48%|████▊     | 178471/371472 [3:18:32<16:05:01,  3.33it/s]
 48%|████▊     | 178472/371472 [3:18:32<16:03:49,  3.34it/s]
 48%|████▊     | 178473/371472 [3:18:32<15:32:53,  3.45it/s]
 48%|████▊     | 178474/371472 [3:18:32<15:35:08,  3.44it/s]
 48%|████▊     | 178475/371472 [3:18:33<16:00:21,  3.35it/s]
 48%|████▊     | 178476/371472 [3:18:33<15:31:35,  3.45it/s]
 48%|████▊     | 178477/371472 [3:18:33<16:21:27,  3.28it/s]
 48%|████▊     | 178478/371472 [3:18:34<16:31:34,  3.24it/s]
 48%|████▊     | 178479/371472 [3:18:34<16:03:37,  3.34it/s]
 48%|████▊     | 178480/371472 [3:18:34<15:50:59,  3.38it/s]
                                                            
{'loss': 2.8357, 'learning_rate': 5.678316705811372e-07, 'epoch': 7.69}
+
 48%|████▊     | 178480/371472 [3:18:34<15:50:59,  3.38it/s]
 48%|████▊     | 178481/371472 [3:18:35<16:30:27,  3.25it/s]
 48%|████▊     | 178482/371472 [3:18:35<15:58:19,  3.36it/s]
 48%|████▊     | 178483/371472 [3:18:35<15:49:57,  3.39it/s]
 48%|████▊     | 178484/371472 [3:18:35<15:35:36,  3.44it/s]
 48%|████▊     | 178485/371472 [3:18:36<15:18:01,  3.50it/s]
 48%|████▊     | 178486/371472 [3:18:36<16:34:09,  3.24it/s]
 48%|████▊     | 178487/371472 [3:18:36<16:43:41,  3.20it/s]
 48%|████▊     | 178488/371472 [3:18:37<16:11:11,  3.31it/s]
 48%|████▊     | 178489/371472 [3:18:37<15:55:32,  3.37it/s]
 48%|████▊     | 178490/371472 [3:18:37<16:48:07,  3.19it/s]
 48%|████▊     | 178491/371472 [3:18:38<17:36:33,  3.04it/s]
 48%|████▊     | 178492/371472 [3:18:38<17:09:16,  3.12it/s]
 48%|████▊     | 178493/371472 [3:18:38<16:42:29,  3.21it/s]
 48%|████▊     | 178494/371472 [3:18:39<17:11:37,  3.12it/s]
 48%|████▊     | 178495/371472 [3:18:39<16:51:16,  3.18it/s]
 48%|████▊     | 178496/371472 [3:18:39<16:17:31,  3.29it/s]
 48%|████▊     | 178497/371472 [3:18:40<16:15:41,  3.30it/s]
 48%|████▊     | 178498/371472 [3:18:40<16:31:24,  3.24it/s]
 48%|████▊     | 178499/371472 [3:18:40<17:07:14,  3.13it/s]
 48%|████▊     | 178500/371472 [3:18:40<17:12:17,  3.12it/s]
                                                            
{'loss': 2.8828, 'learning_rate': 5.677831886056583e-07, 'epoch': 7.69}
+
 48%|████▊     | 178500/371472 [3:18:40<17:12:17,  3.12it/s]
 48%|████▊     | 178501/371472 [3:18:41<16:53:11,  3.17it/s]
 48%|████▊     | 178502/371472 [3:18:41<16:30:18,  3.25it/s]
 48%|████▊     | 178503/371472 [3:18:41<17:03:55,  3.14it/s]
 48%|████▊     | 178504/371472 [3:18:42<16:20:13,  3.28it/s]
 48%|████▊     | 178505/371472 [3:18:42<16:29:00,  3.25it/s]
 48%|████▊     | 178506/371472 [3:18:42<17:05:42,  3.14it/s]
 48%|████▊     | 178507/371472 [3:18:43<16:53:02,  3.17it/s]
 48%|████▊     | 178508/371472 [3:18:43<18:00:53,  2.98it/s]
 48%|████▊     | 178509/371472 [3:18:43<17:09:33,  3.12it/s]
 48%|████▊     | 178510/371472 [3:18:44<16:50:53,  3.18it/s]
 48%|████▊     | 178511/371472 [3:18:44<16:20:30,  3.28it/s]
 48%|████▊     | 178512/371472 [3:18:44<16:06:19,  3.33it/s]
 48%|████▊     | 178513/371472 [3:18:45<16:33:38,  3.24it/s]
 48%|████▊     | 178514/371472 [3:18:45<16:41:26,  3.21it/s]
 48%|████▊     | 178515/371472 [3:18:45<16:28:46,  3.25it/s]
 48%|████▊     | 178516/371472 [3:18:45<16:33:57,  3.24it/s]
 48%|████▊     | 178517/371472 [3:18:46<15:58:20,  3.36it/s]
 48%|████▊     | 178518/371472 [3:18:46<16:10:05,  3.32it/s]
 48%|████▊     | 178519/371472 [3:18:46<16:00:32,  3.35it/s]
 48%|████▊     | 178520/371472 [3:18:47<15:43:46,  3.41it/s]
                                                            
{'loss': 2.7581, 'learning_rate': 5.677347066301794e-07, 'epoch': 7.69}
+
 48%|████▊     | 178520/371472 [3:18:47<15:43:46,  3.41it/s]
 48%|████▊     | 178521/371472 [3:18:47<15:35:13,  3.44it/s]
 48%|████▊     | 178522/371472 [3:18:47<15:36:55,  3.43it/s]
 48%|████▊     | 178523/371472 [3:18:48<16:04:41,  3.33it/s]
 48%|████▊     | 178524/371472 [3:18:48<16:19:46,  3.28it/s]
 48%|████▊     | 178525/371472 [3:18:48<16:44:02,  3.20it/s]
 48%|████▊     | 178526/371472 [3:18:48<16:35:33,  3.23it/s]
 48%|████▊     | 178527/371472 [3:18:49<17:07:54,  3.13it/s]
 48%|████▊     | 178528/371472 [3:18:49<16:18:12,  3.29it/s]
 48%|████▊     | 178529/371472 [3:18:49<16:24:43,  3.27it/s]
 48%|████▊     | 178530/371472 [3:18:50<17:31:10,  3.06it/s]
 48%|████▊     | 178531/371472 [3:18:50<17:38:14,  3.04it/s]
 48%|████▊     | 178532/371472 [3:18:50<16:46:06,  3.20it/s]
 48%|████▊     | 178533/371472 [3:18:51<16:13:55,  3.30it/s]
 48%|████▊     | 178534/371472 [3:18:51<16:19:03,  3.28it/s]
 48%|████▊     | 178535/371472 [3:18:51<16:08:16,  3.32it/s]
 48%|████▊     | 178536/371472 [3:18:52<15:52:33,  3.38it/s]
 48%|████▊     | 178537/371472 [3:18:52<15:31:13,  3.45it/s]
 48%|████▊     | 178538/371472 [3:18:52<16:17:31,  3.29it/s]
 48%|████▊     | 178539/371472 [3:18:52<15:48:47,  3.39it/s]
 48%|████▊     | 178540/371472 [3:18:53<17:10:10,  3.12it/s]
                                                            
{'loss': 2.9381, 'learning_rate': 5.676862246547005e-07, 'epoch': 7.69}
+
 48%|████▊     | 178540/371472 [3:18:53<17:10:10,  3.12it/s]
 48%|████▊     | 178541/371472 [3:18:53<16:44:07,  3.20it/s]
 48%|████▊     | 178542/371472 [3:18:53<16:14:54,  3.30it/s]
 48%|████▊     | 178543/371472 [3:18:54<15:48:48,  3.39it/s]
 48%|████▊     | 178544/371472 [3:18:54<15:28:20,  3.46it/s]
 48%|████▊     | 178545/371472 [3:18:54<15:42:34,  3.41it/s]
 48%|████▊     | 178546/371472 [3:18:55<15:55:45,  3.36it/s]
 48%|████▊     | 178547/371472 [3:18:55<15:43:00,  3.41it/s]
 48%|████▊     | 178548/371472 [3:18:55<15:33:32,  3.44it/s]
 48%|████▊     | 178549/371472 [3:18:55<15:29:16,  3.46it/s]
 48%|████▊     | 178550/371472 [3:18:56<15:21:59,  3.49it/s]
 48%|████▊     | 178551/371472 [3:18:56<15:19:23,  3.50it/s]
 48%|████▊     | 178552/371472 [3:18:56<16:05:52,  3.33it/s]
 48%|████▊     | 178553/371472 [3:18:57<16:20:03,  3.28it/s]
 48%|████▊     | 178554/371472 [3:18:57<16:04:18,  3.33it/s]
 48%|████▊     | 178555/371472 [3:18:57<16:28:49,  3.25it/s]
 48%|████▊     | 178556/371472 [3:18:58<16:22:47,  3.27it/s]
 48%|████▊     | 178557/371472 [3:18:58<16:04:00,  3.34it/s]
 48%|████▊     | 178558/371472 [3:18:58<16:33:19,  3.24it/s]
 48%|████▊     | 178559/371472 [3:18:58<16:22:06,  3.27it/s]
 48%|████▊     | 178560/371472 [3:18:59<16:58:04,  3.16it/s]
                                                            
{'loss': 2.9568, 'learning_rate': 5.676377426792217e-07, 'epoch': 7.69}
+
 48%|████▊     | 178560/371472 [3:18:59<16:58:04,  3.16it/s]
 48%|████▊     | 178561/371472 [3:18:59<17:22:54,  3.08it/s]
 48%|████▊     | 178562/371472 [3:18:59<16:57:50,  3.16it/s]
 48%|████▊     | 178563/371472 [3:19:00<16:21:41,  3.28it/s]
 48%|████▊     | 178564/371472 [3:19:00<16:03:32,  3.34it/s]
 48%|████▊     | 178565/371472 [3:19:00<15:53:54,  3.37it/s]
 48%|████▊     | 178566/371472 [3:19:01<15:29:42,  3.46it/s]
 48%|████▊     | 178567/371472 [3:19:01<16:28:00,  3.25it/s]
 48%|████▊     | 178568/371472 [3:19:01<16:56:36,  3.16it/s]
 48%|████▊     | 178569/371472 [3:19:02<17:38:24,  3.04it/s]
 48%|████▊     | 178570/371472 [3:19:02<17:02:06,  3.15it/s]
 48%|████▊     | 178571/371472 [3:19:02<16:26:41,  3.26it/s]
 48%|████▊     | 178572/371472 [3:19:02<16:29:41,  3.25it/s]
 48%|████▊     | 178573/371472 [3:19:03<16:03:14,  3.34it/s]
 48%|████▊     | 178574/371472 [3:19:03<16:39:23,  3.22it/s]
 48%|████▊     | 178575/371472 [3:19:03<16:15:42,  3.29it/s]
 48%|████▊     | 178576/371472 [3:19:04<16:23:57,  3.27it/s]
 48%|████▊     | 178577/371472 [3:19:04<15:53:11,  3.37it/s]
 48%|████▊     | 178578/371472 [3:19:04<15:26:05,  3.47it/s]
 48%|████▊     | 178579/371472 [3:19:05<15:37:00,  3.43it/s]
 48%|████▊     | 178580/371472 [3:19:05<16:35:51,  3.23it/s]
                                                            
{'loss': 2.8587, 'learning_rate': 5.675892607037428e-07, 'epoch': 7.69}
+
 48%|████▊     | 178580/371472 [3:19:05<16:35:51,  3.23it/s]
 48%|████▊     | 178581/371472 [3:19:05<17:07:48,  3.13it/s]
 48%|████▊     | 178582/371472 [3:19:06<16:41:30,  3.21it/s]
 48%|████▊     | 178583/371472 [3:19:06<16:18:51,  3.28it/s]
 48%|████▊     | 178584/371472 [3:19:06<16:23:38,  3.27it/s]
 48%|████▊     | 178585/371472 [3:19:06<16:00:37,  3.35it/s]
 48%|████▊     | 178586/371472 [3:19:07<15:55:28,  3.36it/s]
 48%|████▊     | 178587/371472 [3:19:07<15:58:33,  3.35it/s]
 48%|████▊     | 178588/371472 [3:19:07<15:53:33,  3.37it/s]
 48%|████▊     | 178589/371472 [3:19:08<16:24:38,  3.26it/s]
 48%|████▊     | 178590/371472 [3:19:08<16:26:04,  3.26it/s]
 48%|████▊     | 178591/371472 [3:19:08<16:15:44,  3.29it/s]
 48%|████▊     | 178592/371472 [3:19:09<15:54:55,  3.37it/s]
 48%|████▊     | 178593/371472 [3:19:09<15:43:09,  3.41it/s]
 48%|████▊     | 178594/371472 [3:19:09<16:56:34,  3.16it/s]
 48%|████���     | 178595/371472 [3:19:09<16:27:27,  3.26it/s]
 48%|████▊     | 178596/371472 [3:19:10<16:52:30,  3.17it/s]
 48%|████▊     | 178597/371472 [3:19:10<17:03:09,  3.14it/s]
 48%|████▊     | 178598/371472 [3:19:10<16:56:56,  3.16it/s]
 48%|████▊     | 178599/371472 [3:19:11<16:31:44,  3.24it/s]
 48%|████▊     | 178600/371472 [3:19:11<16:35:42,  3.23it/s]
                                                            
{'loss': 3.0068, 'learning_rate': 5.675407787282639e-07, 'epoch': 7.69}
+
 48%|████▊     | 178600/371472 [3:19:11<16:35:42,  3.23it/s]
 48%|████▊     | 178601/371472 [3:19:12<23:20:33,  2.30it/s]
 48%|████▊     | 178602/371472 [3:19:12<21:19:36,  2.51it/s]
 48%|████▊     | 178603/371472 [3:19:12<20:33:42,  2.61it/s]
 48%|████▊     | 178604/371472 [3:19:13<19:19:12,  2.77it/s]
 48%|████▊     | 178605/371472 [3:19:13<18:30:57,  2.89it/s]
 48%|████▊     | 178606/371472 [3:19:13<17:38:22,  3.04it/s]
 48%|████▊     | 178607/371472 [3:19:14<17:03:06,  3.14it/s]
 48%|████▊     | 178608/371472 [3:19:14<16:26:00,  3.26it/s]
 48%|████▊     | 178609/371472 [3:19:14<16:01:24,  3.34it/s]
 48%|████▊     | 178610/371472 [3:19:14<15:59:24,  3.35it/s]
 48%|████▊     | 178611/371472 [3:19:15<15:41:00,  3.42it/s]
 48%|████▊     | 178612/371472 [3:19:15<15:40:28,  3.42it/s]
 48%|████▊     | 178613/371472 [3:19:15<16:00:12,  3.35it/s]
 48%|████▊     | 178614/371472 [3:19:16<16:09:29,  3.32it/s]
 48%|████▊     | 178615/371472 [3:19:16<16:41:15,  3.21it/s]
 48%|████▊     | 178616/371472 [3:19:16<16:32:25,  3.24it/s]
 48%|████▊     | 178617/371472 [3:19:17<16:52:53,  3.17it/s]
 48%|████▊     | 178618/371472 [3:19:17<16:22:00,  3.27it/s]
 48%|████▊     | 178619/371472 [3:19:17<16:15:59,  3.29it/s]
 48%|████▊     | 178620/371472 [3:19:18<16:37:24,  3.22it/s]
                                                            
{'loss': 2.8665, 'learning_rate': 5.674922967527849e-07, 'epoch': 7.69}
+
 48%|████▊     | 178620/371472 [3:19:18<16:37:24,  3.22it/s]
 48%|████▊     | 178621/371472 [3:19:18<16:38:47,  3.22it/s]
 48%|████▊     | 178622/371472 [3:19:18<17:40:08,  3.03it/s]
 48%|████▊     | 178623/371472 [3:19:19<17:25:35,  3.07it/s]
 48%|████▊     | 178624/371472 [3:19:19<17:17:26,  3.10it/s]
 48%|████▊     | 178625/371472 [3:19:19<17:43:32,  3.02it/s]
 48%|████▊     | 178626/371472 [3:19:20<17:09:45,  3.12it/s]
 48%|████▊     | 178627/371472 [3:19:20<16:42:25,  3.21it/s]
 48%|████▊     | 178628/371472 [3:19:20<16:09:08,  3.32it/s]
 48%|████▊     | 178629/371472 [3:19:20<15:45:14,  3.40it/s]
 48%|████▊     | 178630/371472 [3:19:21<15:46:55,  3.39it/s]
 48%|████▊     | 178631/371472 [3:19:21<15:51:02,  3.38it/s]
 48%|████▊     | 178632/371472 [3:19:21<15:49:30,  3.38it/s]
 48%|████▊     | 178633/371472 [3:19:22<16:21:45,  3.27it/s]
 48%|████▊     | 178634/371472 [3:19:22<16:12:51,  3.30it/s]
 48%|████▊     | 178635/371472 [3:19:22<16:39:56,  3.21it/s]
 48%|████▊     | 178636/371472 [3:19:22<16:22:15,  3.27it/s]
 48%|████▊     | 178637/371472 [3:19:23<16:10:49,  3.31it/s]
 48%|████▊     | 178638/371472 [3:19:23<16:09:59,  3.31it/s]
 48%|████▊     | 178639/371472 [3:19:23<16:46:00,  3.19it/s]
 48%|████▊     | 178640/371472 [3:19:24<16:32:51,  3.24it/s]
                                                            
{'loss': 2.9613, 'learning_rate': 5.674438147773062e-07, 'epoch': 7.69}
+
 48%|████▊     | 178640/371472 [3:19:24<16:32:51,  3.24it/s]
 48%|████▊     | 178641/371472 [3:19:24<16:36:07,  3.23it/s]
 48%|████▊     | 178642/371472 [3:19:24<16:52:34,  3.17it/s]
 48%|████▊     | 178643/371472 [3:19:25<16:31:38,  3.24it/s]
 48%|████▊     | 178644/371472 [3:19:25<16:27:10,  3.26it/s]
 48%|████▊     | 178645/371472 [3:19:25<16:40:01,  3.21it/s]
 48%|████▊     | 178646/371472 [3:19:26<15:59:29,  3.35it/s]
 48%|████▊     | 178647/371472 [3:19:26<16:59:41,  3.15it/s]
 48%|████▊     | 178648/371472 [3:19:26<16:47:45,  3.19it/s]
 48%|████▊     | 178649/371472 [3:19:27<16:38:25,  3.22it/s]
 48%|████▊     | 178650/371472 [3:19:27<16:20:33,  3.28it/s]
 48%|████▊     | 178651/371472 [3:19:27<16:39:11,  3.22it/s]
 48%|████▊     | 178652/371472 [3:19:27<17:22:15,  3.08it/s]
 48%|████▊     | 178653/371472 [3:19:28<17:38:24,  3.04it/s]
 48%|████▊     | 178654/371472 [3:19:28<17:07:47,  3.13it/s]
 48%|████▊     | 178655/371472 [3:19:28<16:20:42,  3.28it/s]
 48%|████▊     | 178656/371472 [3:19:29<16:01:03,  3.34it/s]
 48%|████▊     | 178657/371472 [3:19:29<15:43:56,  3.40it/s]
 48%|████▊     | 178658/371472 [3:19:29<15:22:36,  3.48it/s]
 48%|████▊     | 178659/371472 [3:19:30<15:23:05,  3.48it/s]
 48%|████▊     | 178660/371472 [3:19:30<15:11:35,  3.53it/s]
                                                            
{'loss': 3.003, 'learning_rate': 5.673953328018273e-07, 'epoch': 7.7}
+
 48%|████▊     | 178660/371472 [3:19:30<15:11:35,  3.53it/s]
 48%|████▊     | 178661/371472 [3:19:30<15:07:20,  3.54it/s]
 48%|████▊     | 178662/371472 [3:19:30<15:34:40,  3.44it/s]
 48%|████▊     | 178663/371472 [3:19:31<15:12:59,  3.52it/s]
 48%|████▊     | 178664/371472 [3:19:31<15:19:34,  3.49it/s]
 48%|████▊     | 178665/371472 [3:19:31<16:11:48,  3.31it/s]
 48%|████▊     | 178666/371472 [3:19:32<15:57:10,  3.36it/s]
 48%|████▊     | 178667/371472 [3:19:32<15:50:33,  3.38it/s]
 48%|████▊     | 178668/371472 [3:19:32<16:44:23,  3.20it/s]
 48%|████▊     | 178669/371472 [3:19:33<16:29:24,  3.25it/s]
 48%|████▊     | 178670/371472 [3:19:33<17:08:27,  3.12it/s]
 48%|████▊     | 178671/371472 [3:19:33<16:59:41,  3.15it/s]
 48%|████▊     | 178672/371472 [3:19:34<17:55:21,  2.99it/s]
 48%|████▊     | 178673/371472 [3:19:34<16:59:03,  3.15it/s]
 48%|████▊     | 178674/371472 [3:19:34<16:30:01,  3.25it/s]
 48%|████▊     | 178675/371472 [3:19:34<16:13:11,  3.30it/s]
 48%|████▊     | 178676/371472 [3:19:35<16:23:59,  3.27it/s]
 48%|████▊     | 178677/371472 [3:19:35<15:48:26,  3.39it/s]
 48%|████▊     | 178678/371472 [3:19:35<16:31:31,  3.24it/s]
 48%|████▊     | 178679/371472 [3:19:36<17:14:20,  3.11it/s]
 48%|████▊     | 178680/371472 [3:19:36<16:33:18,  3.23it/s]
                                                            
{'loss': 2.9981, 'learning_rate': 5.673468508263483e-07, 'epoch': 7.7}
+
 48%|████▊     | 178680/371472 [3:19:36<16:33:18,  3.23it/s]
 48%|████▊     | 178681/371472 [3:19:36<16:21:48,  3.27it/s]
 48%|████▊     | 178682/371472 [3:19:37<16:01:22,  3.34it/s]
 48%|████▊     | 178683/371472 [3:19:37<15:50:58,  3.38it/s]
 48%|████▊     | 178684/371472 [3:19:37<16:15:52,  3.29it/s]
 48%|████▊     | 178685/371472 [3:19:37<16:23:10,  3.27it/s]
 48%|████▊     | 178686/371472 [3:19:38<16:32:26,  3.24it/s]
 48%|████▊     | 178687/371472 [3:19:38<15:59:43,  3.35it/s]
 48%|████▊     | 178688/371472 [3:19:38<15:48:45,  3.39it/s]
 48%|████▊     | 178689/371472 [3:19:39<15:32:13,  3.45it/s]
 48%|████▊     | 178690/371472 [3:19:39<15:29:43,  3.46it/s]
 48%|████▊     | 178691/371472 [3:19:39<15:46:16,  3.40it/s]
 48%|████▊     | 178692/371472 [3:19:39<15:35:27,  3.43it/s]
 48%|████▊     | 178693/371472 [3:19:40<15:32:03,  3.45it/s]
 48%|████▊     | 178694/371472 [3:19:40<15:14:23,  3.51it/s]
 48%|████▊     | 178695/371472 [3:19:40<15:24:20,  3.48it/s]
 48%|████▊     | 178696/371472 [3:19:41<16:40:59,  3.21it/s]
 48%|████▊     | 178697/371472 [3:19:41<16:53:41,  3.17it/s]
 48%|████▊     | 178698/371472 [3:19:41<16:37:11,  3.22it/s]
 48%|████▊     | 178699/371472 [3:19:42<16:17:20,  3.29it/s]
 48%|████▊     | 178700/371472 [3:19:42<15:57:22,  3.36it/s]
                                                            
{'loss': 2.911, 'learning_rate': 5.672983688508694e-07, 'epoch': 7.7}
+
 48%|████▊     | 178700/371472 [3:19:42<15:57:22,  3.36it/s]
 48%|████▊     | 178701/371472 [3:19:42<15:29:58,  3.45it/s]
 48%|████▊     | 178702/371472 [3:19:42<15:28:43,  3.46it/s]
 48%|████▊     | 178703/371472 [3:19:43<15:46:10,  3.40it/s]
 48%|████▊     | 178704/371472 [3:19:43<15:41:33,  3.41it/s]
 48%|████▊     | 178705/371472 [3:19:43<15:40:45,  3.42it/s]
 48%|████▊     | 178706/371472 [3:19:44<16:15:56,  3.29it/s]
 48%|████▊     | 178707/371472 [3:19:44<15:45:30,  3.40it/s]
 48%|████▊     | 178708/371472 [3:19:44<15:55:53,  3.36it/s]
 48%|████▊     | 178709/371472 [3:19:45<15:48:54,  3.39it/s]
 48%|████▊     | 178710/371472 [3:19:45<15:39:32,  3.42it/s]
 48%|████▊     | 178711/371472 [3:19:45<15:38:02,  3.42it/s]
 48%|████▊     | 178712/371472 [3:19:45<16:20:36,  3.28it/s]
 48%|████▊     | 178713/371472 [3:19:46<16:29:25,  3.25it/s]
 48%|████▊     | 178714/371472 [3:19:46<16:27:53,  3.25it/s]
 48%|████▊     | 178715/371472 [3:19:46<16:08:11,  3.32it/s]
 48%|████▊     | 178716/371472 [3:19:47<15:46:36,  3.39it/s]
 48%|████▊     | 178717/371472 [3:19:47<15:52:31,  3.37it/s]
 48%|████▊     | 178718/371472 [3:19:47<16:24:33,  3.26it/s]
 48%|████▊     | 178719/371472 [3:19:48<17:54:48,  2.99it/s]
 48%|████▊     | 178720/371472 [3:19:48<17:33:51,  3.05it/s]
                                                            
{'loss': 3.0579, 'learning_rate': 5.672498868753906e-07, 'epoch': 7.7}
+
 48%|████▊     | 178720/371472 [3:19:48<17:33:51,  3.05it/s]
 48%|████▊     | 178721/371472 [3:19:48<16:41:35,  3.21it/s]
 48%|████▊     | 178722/371472 [3:19:49<17:10:51,  3.12it/s]
 48%|████▊     | 178723/371472 [3:19:49<16:25:48,  3.26it/s]
 48%|████▊     | 178724/371472 [3:19:49<15:44:37,  3.40it/s]
 48%|████▊     | 178725/371472 [3:19:49<15:53:41,  3.37it/s]
 48%|████▊     | 178726/371472 [3:19:50<15:36:00,  3.43it/s]
 48%|████▊     | 178727/371472 [3:19:50<16:06:49,  3.32it/s]
 48%|████▊     | 178728/371472 [3:19:50<17:56:31,  2.98it/s]
 48%|████▊     | 178729/371472 [3:19:51<18:35:27,  2.88it/s]
 48%|████▊     | 178730/371472 [3:19:51<17:43:51,  3.02it/s]
 48%|████▊     | 178731/371472 [3:19:51<17:25:25,  3.07it/s]
 48%|████▊     | 178732/371472 [3:19:52<17:06:29,  3.13it/s]
 48%|████▊     | 178733/371472 [3:19:52<16:47:57,  3.19it/s]
 48%|████▊     | 178734/371472 [3:19:52<16:42:30,  3.20it/s]
 48%|████▊     | 178735/371472 [3:19:53<16:13:36,  3.30it/s]
 48%|████▊     | 178736/371472 [3:19:53<16:06:33,  3.32it/s]
 48%|████▊     | 178737/371472 [3:19:53<16:07:49,  3.32it/s]
 48%|████▊     | 178738/371472 [3:19:54<16:26:11,  3.26it/s]
 48%|████▊     | 178739/371472 [3:19:54<16:18:30,  3.28it/s]
 48%|████▊     | 178740/371472 [3:19:54<16:42:33,  3.20it/s]
                                                            
{'loss': 2.8371, 'learning_rate': 5.672014048999116e-07, 'epoch': 7.7}
+
 48%|████▊     | 178740/371472 [3:19:54<16:42:33,  3.20it/s]
 48%|████▊     | 178741/371472 [3:19:54<16:23:54,  3.26it/s]
 48%|████▊     | 178742/371472 [3:19:55<16:06:37,  3.32it/s]
 48%|████▊     | 178743/371472 [3:19:55<17:55:02,  2.99it/s]
 48%|████▊     | 178744/371472 [3:19:56<18:19:25,  2.92it/s]
 48%|████▊     | 178745/371472 [3:19:56<17:25:03,  3.07it/s]
 48%|████▊     | 178746/371472 [3:19:56<16:29:36,  3.25it/s]
 48%|████▊     | 178747/371472 [3:19:56<16:06:20,  3.32it/s]
 48%|████▊     | 178748/371472 [3:19:57<15:40:44,  3.41it/s]
 48%|████▊     | 178749/371472 [3:19:57<16:38:37,  3.22it/s]
 48%|████▊     | 178750/371472 [3:19:57<16:15:54,  3.29it/s]
 48%|████▊     | 178751/371472 [3:19:58<16:31:07,  3.24it/s]
 48%|████▊     | 178752/371472 [3:19:58<16:06:11,  3.32it/s]
 48%|████▊     | 178753/371472 [3:19:58<15:42:19,  3.41it/s]
 48%|████▊     | 178754/371472 [3:19:58<15:27:04,  3.46it/s]
 48%|████▊     | 178755/371472 [3:19:59<16:25:06,  3.26it/s]
 48%|████▊     | 178756/371472 [3:19:59<16:09:56,  3.31it/s]
 48%|████▊     | 178757/371472 [3:19:59<16:27:48,  3.25it/s]
 48%|████▊     | 178758/371472 [3:20:00<16:31:05,  3.24it/s]
 48%|████▊     | 178759/371472 [3:20:00<16:44:58,  3.20it/s]
 48%|████▊     | 178760/371472 [3:20:00<16:47:44,  3.19it/s]
                                                            
{'loss': 2.9275, 'learning_rate': 5.671529229244327e-07, 'epoch': 7.7}
+
 48%|████▊     | 178760/371472 [3:20:00<16:47:44,  3.19it/s]
 48%|████▊     | 178761/371472 [3:20:01<16:00:58,  3.34it/s]
 48%|████▊     | 178762/371472 [3:20:01<17:08:49,  3.12it/s]
 48%|████▊     | 178763/371472 [3:20:01<17:43:03,  3.02it/s]
 48%|████▊     | 178764/371472 [3:20:02<16:55:14,  3.16it/s]
 48%|████▊     | 178765/371472 [3:20:02<16:17:16,  3.29it/s]
 48%|████▊     | 178766/371472 [3:20:02<16:56:00,  3.16it/s]
 48%|████▊     | 178767/371472 [3:20:03<16:40:12,  3.21it/s]
 48%|████▊     | 178768/371472 [3:20:03<16:15:06,  3.29it/s]
 48%|████▊     | 178769/371472 [3:20:03<16:07:53,  3.32it/s]
 48%|████▊     | 178770/371472 [3:20:04<17:09:45,  3.12it/s]
 48%|████▊     | 178771/371472 [3:20:04<17:02:10,  3.14it/s]
 48%|████▊     | 178772/371472 [3:20:04<16:31:58,  3.24it/s]
 48%|████▊     | 178773/371472 [3:20:04<16:13:11,  3.30it/s]
 48%|████▊     | 178774/371472 [3:20:05<16:02:42,  3.34it/s]
 48%|████▊     | 178775/371472 [3:20:05<15:38:43,  3.42it/s]
 48%|████▊     | 178776/371472 [3:20:05<15:53:06,  3.37it/s]
 48%|████▊     | 178777/371472 [3:20:06<15:20:20,  3.49it/s]
 48%|████▊     | 178778/371472 [3:20:06<14:48:51,  3.61it/s]
 48%|████▊     | 178779/371472 [3:20:06<14:46:23,  3.62it/s]
 48%|████▊     | 178780/371472 [3:20:06<15:33:30,  3.44it/s]
                                                            
{'loss': 2.8365, 'learning_rate': 5.671044409489539e-07, 'epoch': 7.7}
+
 48%|████▊     | 178780/371472 [3:20:06<15:33:30,  3.44it/s]
 48%|████▊     | 178781/371472 [3:20:07<16:23:04,  3.27it/s]
 48%|████▊     | 178782/371472 [3:20:07<16:47:05,  3.19it/s]
 48%|████▊     | 178783/371472 [3:20:07<16:34:40,  3.23it/s]
 48%|████▊     | 178784/371472 [3:20:08<16:34:22,  3.23it/s]
 48%|████▊     | 178785/371472 [3:20:08<16:13:10,  3.30it/s]
 48%|████▊     | 178786/371472 [3:20:08<16:31:34,  3.24it/s]
 48%|████▊     | 178787/371472 [3:20:09<17:58:10,  2.98it/s]
 48%|████▊     | 178788/371472 [3:20:09<17:16:07,  3.10it/s]
 48%|████▊     | 178789/371472 [3:20:09<17:09:27,  3.12it/s]
 48%|████▊     | 178790/371472 [3:20:10<16:37:56,  3.22it/s]
 48%|████▊     | 178791/371472 [3:20:10<16:44:04,  3.20it/s]
 48%|████▊     | 178792/371472 [3:20:10<16:50:11,  3.18it/s]
 48%|████▊     | 178793/371472 [3:20:11<16:38:14,  3.22it/s]
 48%|████▊     | 178794/371472 [3:20:11<17:38:28,  3.03it/s]
 48%|████▊     | 178795/371472 [3:20:11<17:33:54,  3.05it/s]
 48%|████▊     | 178796/371472 [3:20:12<17:17:17,  3.10it/s]
 48%|████▊     | 178797/371472 [3:20:12<17:33:33,  3.05it/s]
 48%|████▊     | 178798/371472 [3:20:12<16:44:40,  3.20it/s]
 48%|████▊     | 178799/371472 [3:20:12<17:22:46,  3.08it/s]
 48%|████▊     | 178800/371472 [3:20:13<16:38:12,  3.22it/s]
                                                            
{'loss': 2.7299, 'learning_rate': 5.670559589734749e-07, 'epoch': 7.7}
+
 48%|████▊     | 178800/371472 [3:20:13<16:38:12,  3.22it/s]
 48%|████▊     | 178801/371472 [3:20:13<16:14:11,  3.30it/s]
 48%|████▊     | 178802/371472 [3:20:13<17:36:53,  3.04it/s]
 48%|████▊     | 178803/371472 [3:20:14<17:42:21,  3.02it/s]
 48%|████▊     | 178804/371472 [3:20:14<18:01:16,  2.97it/s]
 48%|████▊     | 178805/371472 [3:20:14<17:34:07,  3.05it/s]
 48%|████▊     | 178806/371472 [3:20:15<17:12:56,  3.11it/s]
 48%|████▊     | 178807/371472 [3:20:15<17:35:41,  3.04it/s]
 48%|████▊     | 178808/371472 [3:20:15<16:36:03,  3.22it/s]
 48%|████▊     | 178809/371472 [3:20:16<15:59:38,  3.35it/s]
 48%|████▊     | 178810/371472 [3:20:16<15:51:53,  3.37it/s]
 48%|████▊     | 178811/371472 [3:20:16<15:44:38,  3.40it/s]
 48%|████▊     | 178812/371472 [3:20:17<16:26:40,  3.25it/s]
 48%|████▊     | 178813/371472 [3:20:17<15:55:00,  3.36it/s]
 48%|████▊     | 178814/371472 [3:20:17<16:50:39,  3.18it/s]
 48%|████▊     | 178815/371472 [3:20:18<17:02:58,  3.14it/s]
 48%|████▊     | 178816/371472 [3:20:18<16:28:28,  3.25it/s]
 48%|████▊     | 178817/371472 [3:20:18<16:34:20,  3.23it/s]
 48%|████▊     | 178818/371472 [3:20:18<16:34:22,  3.23it/s]
 48%|████▊     | 178819/371472 [3:20:19<16:48:06,  3.19it/s]
 48%|████▊     | 178820/371472 [3:20:19<18:16:17,  2.93it/s]
                                                            
{'loss': 2.7999, 'learning_rate': 5.67007476997996e-07, 'epoch': 7.7}
+
 48%|████▊     | 178820/371472 [3:20:19<18:16:17,  2.93it/s]
 48%|████▊     | 178821/371472 [3:20:20<18:59:24,  2.82it/s]
 48%|████▊     | 178822/371472 [3:20:20<19:17:33,  2.77it/s]
 48%|████▊     | 178823/371472 [3:20:20<18:54:04,  2.83it/s]
 48%|████▊     | 178824/371472 [3:20:21<18:52:13,  2.84it/s]
 48%|████▊     | 178825/371472 [3:20:21<18:07:44,  2.95it/s]
 48%|████▊     | 178826/371472 [3:20:21<17:23:13,  3.08it/s]
 48%|████▊     | 178827/371472 [3:20:21<16:52:06,  3.17it/s]
 48%|████▊     | 178828/371472 [3:20:22<17:06:56,  3.13it/s]
 48%|████▊     | 178829/371472 [3:20:22<17:05:57,  3.13it/s]
 48%|████▊     | 178830/371472 [3:20:22<16:43:12,  3.20it/s]
 48%|████▊     | 178831/371472 [3:20:23<16:19:14,  3.28it/s]
 48%|████▊     | 178832/371472 [3:20:23<16:25:24,  3.26it/s]
 48%|████▊     | 178833/371472 [3:20:23<16:09:10,  3.31it/s]
 48%|████▊     | 178834/371472 [3:20:24<16:01:45,  3.34it/s]
 48%|████▊     | 178835/371472 [3:20:24<15:57:52,  3.35it/s]
 48%|████▊     | 178836/371472 [3:20:24<15:34:42,  3.43it/s]
 48%|████▊     | 178837/371472 [3:20:24<15:25:41,  3.47it/s]
 48%|████▊     | 178838/371472 [3:20:25<15:14:23,  3.51it/s]
 48%|████▊     | 178839/371472 [3:20:25<15:54:32,  3.36it/s]
 48%|████▊     | 178840/371472 [3:20:25<17:03:51,  3.14it/s]
                                                            
{'loss': 3.0619, 'learning_rate': 5.66958995022517e-07, 'epoch': 7.7}
+
 48%|████▊     | 178840/371472 [3:20:25<17:03:51,  3.14it/s]
 48%|████▊     | 178841/371472 [3:20:26<16:40:30,  3.21it/s]
 48%|████▊     | 178842/371472 [3:20:26<16:18:52,  3.28it/s]
 48%|████▊     | 178843/371472 [3:20:26<16:21:09,  3.27it/s]
 48%|████▊     | 178844/371472 [3:20:27<16:20:40,  3.27it/s]
 48%|████▊     | 178845/371472 [3:20:27<16:36:43,  3.22it/s]
 48%|██��█▊     | 178846/371472 [3:20:27<16:23:32,  3.26it/s]
 48%|████▊     | 178847/371472 [3:20:28<16:20:14,  3.28it/s]
 48%|████▊     | 178848/371472 [3:20:28<16:07:24,  3.32it/s]
 48%|████▊     | 178849/371472 [3:20:28<16:20:38,  3.27it/s]
 48%|████▊     | 178850/371472 [3:20:28<16:11:57,  3.30it/s]
 48%|████▊     | 178851/371472 [3:20:29<16:11:27,  3.30it/s]
 48%|████▊     | 178852/371472 [3:20:29<15:47:59,  3.39it/s]
 48%|████▊     | 178853/371472 [3:20:29<15:48:04,  3.39it/s]
 48%|████▊     | 178854/371472 [3:20:30<15:26:33,  3.46it/s]
 48%|████▊     | 178855/371472 [3:20:30<15:07:41,  3.54it/s]
 48%|████▊     | 178856/371472 [3:20:30<15:05:00,  3.55it/s]
 48%|████▊     | 178857/371472 [3:20:31<16:08:11,  3.32it/s]
 48%|████▊     | 178858/371472 [3:20:31<15:49:50,  3.38it/s]
 48%|████▊     | 178859/371472 [3:20:31<16:30:49,  3.24it/s]
 48%|████▊     | 178860/371472 [3:20:31<16:00:38,  3.34it/s]
                                                            
{'loss': 2.861, 'learning_rate': 5.669105130470382e-07, 'epoch': 7.7}
+
 48%|████▊     | 178860/371472 [3:20:31<16:00:38,  3.34it/s]
 48%|████▊     | 178861/371472 [3:20:32<16:17:56,  3.28it/s]
 48%|████▊     | 178862/371472 [3:20:32<16:06:05,  3.32it/s]
 48%|████▊     | 178863/371472 [3:20:32<15:37:56,  3.42it/s]
 48%|████▊     | 178864/371472 [3:20:33<15:28:29,  3.46it/s]
 48%|████▊     | 178865/371472 [3:20:33<16:09:05,  3.31it/s]
 48%|████▊     | 178866/371472 [3:20:33<16:15:05,  3.29it/s]
 48%|████▊     | 178867/371472 [3:20:34<17:28:09,  3.06it/s]
 48%|████▊     | 178868/371472 [3:20:34<16:57:33,  3.15it/s]
 48%|████▊     | 178869/371472 [3:20:34<16:10:02,  3.31it/s]
 48%|████▊     | 178870/371472 [3:20:34<15:54:58,  3.36it/s]
 48%|████▊     | 178871/371472 [3:20:35<16:31:01,  3.24it/s]
 48%|████▊     | 178872/371472 [3:20:35<16:56:26,  3.16it/s]
 48%|████▊     | 178873/371472 [3:20:35<16:37:11,  3.22it/s]
 48%|████▊     | 178874/371472 [3:20:36<17:22:06,  3.08it/s]
 48%|████▊     | 178875/371472 [3:20:36<16:46:52,  3.19it/s]
 48%|████▊     | 178876/371472 [3:20:36<16:10:58,  3.31it/s]
 48%|████▊     | 178877/371472 [3:20:37<16:12:19,  3.30it/s]
 48%|████▊     | 178878/371472 [3:20:37<15:56:30,  3.36it/s]
 48%|████▊     | 178879/371472 [3:20:37<16:14:03,  3.30it/s]
 48%|████▊     | 178880/371472 [3:20:38<16:13:08,  3.30it/s]
                                                            
{'loss': 3.0203, 'learning_rate': 5.668620310715593e-07, 'epoch': 7.7}
+
 48%|████▊     | 178880/371472 [3:20:38<16:13:08,  3.30it/s]
 48%|████▊     | 178881/371472 [3:20:38<16:00:22,  3.34it/s]
 48%|████▊     | 178882/371472 [3:20:38<15:38:38,  3.42it/s]
 48%|████▊     | 178883/371472 [3:20:38<16:34:43,  3.23it/s]
 48%|████▊     | 178884/371472 [3:20:39<15:54:43,  3.36it/s]
 48%|████▊     | 178885/371472 [3:20:39<16:56:33,  3.16it/s]
 48%|████▊     | 178886/371472 [3:20:39<16:44:25,  3.20it/s]
 48%|████▊     | 178887/371472 [3:20:40<16:12:45,  3.30it/s]
 48%|████▊     | 178888/371472 [3:20:40<16:14:31,  3.29it/s]
 48%|████▊     | 178889/371472 [3:20:40<15:54:39,  3.36it/s]
 48%|████▊     | 178890/371472 [3:20:41<15:50:03,  3.38it/s]
 48%|████▊     | 178891/371472 [3:20:41<15:43:37,  3.40it/s]
 48%|████▊     | 178892/371472 [3:20:41<16:29:41,  3.24it/s]
 48%|████▊     | 178893/371472 [3:20:41<16:34:41,  3.23it/s]
 48%|████▊     | 178894/371472 [3:20:42<16:23:15,  3.26it/s]
 48%|████▊     | 178895/371472 [3:20:42<16:23:52,  3.26it/s]
 48%|████▊     | 178896/371472 [3:20:42<15:52:34,  3.37it/s]
 48%|████▊     | 178897/371472 [3:20:43<15:41:50,  3.41it/s]
 48%|████▊     | 178898/371472 [3:20:43<15:26:34,  3.46it/s]
 48%|████▊     | 178899/371472 [3:20:43<15:39:07,  3.42it/s]
 48%|████▊     | 178900/371472 [3:20:44<16:04:11,  3.33it/s]
                                                            
{'loss': 2.8358, 'learning_rate': 5.668135490960804e-07, 'epoch': 7.71}
+
 48%|████▊     | 178900/371472 [3:20:44<16:04:11,  3.33it/s]
 48%|████▊     | 178901/371472 [3:20:44<16:20:21,  3.27it/s]
 48%|████▊     | 178902/371472 [3:20:44<16:25:04,  3.26it/s]
 48%|████▊     | 178903/371472 [3:20:44<15:56:44,  3.35it/s]
 48%|████▊     | 178904/371472 [3:20:45<16:36:08,  3.22it/s]
 48%|████▊     | 178905/371472 [3:20:45<16:48:31,  3.18it/s]
 48%|████▊     | 178906/371472 [3:20:45<16:27:03,  3.25it/s]
 48%|████▊     | 178907/371472 [3:20:46<16:07:19,  3.32it/s]
 48%|████▊     | 178908/371472 [3:20:46<15:53:35,  3.37it/s]
 48%|████▊     | 178909/371472 [3:20:46<16:04:17,  3.33it/s]
 48%|████▊     | 178910/371472 [3:20:47<16:30:45,  3.24it/s]
 48%|████▊     | 178911/371472 [3:20:47<16:03:35,  3.33it/s]
 48%|████▊     | 178912/371472 [3:20:47<16:33:32,  3.23it/s]
 48%|████▊     | 178913/371472 [3:20:48<16:13:58,  3.30it/s]
 48%|████▊     | 178914/371472 [3:20:48<16:07:40,  3.32it/s]
 48%|████▊     | 178915/371472 [3:20:48<15:57:31,  3.35it/s]
 48%|████▊     | 178916/371472 [3:20:48<16:37:05,  3.22it/s]
 48%|████▊     | 178917/371472 [3:20:49<17:23:11,  3.08it/s]
 48%|████▊     | 178918/371472 [3:20:49<16:59:43,  3.15it/s]
 48%|████▊     | 178919/371472 [3:20:49<16:52:43,  3.17it/s]
 48%|████▊     | 178920/371472 [3:20:50<17:02:33,  3.14it/s]
                                                            
{'loss': 3.0071, 'learning_rate': 5.667650671206016e-07, 'epoch': 7.71}
+
 48%|████▊     | 178920/371472 [3:20:50<17:02:33,  3.14it/s]
 48%|████▊     | 178921/371472 [3:20:50<16:37:58,  3.22it/s]
 48%|████▊     | 178922/371472 [3:20:50<16:14:57,  3.29it/s]
 48%|████▊     | 178923/371472 [3:20:51<16:33:36,  3.23it/s]
 48%|████▊     | 178924/371472 [3:20:51<16:03:54,  3.33it/s]
 48%|████▊     | 178925/371472 [3:20:51<17:31:11,  3.05it/s]
 48%|████▊     | 178926/371472 [3:20:52<17:13:01,  3.11it/s]
 48%|████▊     | 178927/371472 [3:20:52<17:09:49,  3.12it/s]
 48%|████▊     | 178928/371472 [3:20:52<16:43:59,  3.20it/s]
 48%|████▊     | 178929/371472 [3:20:53<16:42:17,  3.20it/s]
 48%|████▊     | 178930/371472 [3:20:53<16:02:58,  3.33it/s]
 48%|████▊     | 178931/371472 [3:20:53<16:12:17,  3.30it/s]
 48%|████▊     | 178932/371472 [3:20:53<16:41:26,  3.20it/s]
 48%|████▊     | 178933/371472 [3:20:54<16:15:20,  3.29it/s]
 48%|████▊     | 178934/371472 [3:20:54<16:19:01,  3.28it/s]
 48%|████▊     | 178935/371472 [3:20:54<16:50:02,  3.18it/s]
 48%|████▊     | 178936/371472 [3:20:55<16:00:30,  3.34it/s]
 48%|████▊     | 178937/371472 [3:20:55<15:47:06,  3.39it/s]
 48%|████▊     | 178938/371472 [3:20:55<17:00:41,  3.14it/s]
 48%|████▊     | 178939/371472 [3:20:56<16:39:37,  3.21it/s]
 48%|████▊     | 178940/371472 [3:20:56<17:13:23,  3.11it/s]
                                                            
{'loss': 3.071, 'learning_rate': 5.667165851451227e-07, 'epoch': 7.71}
+
 48%|████▊     | 178940/371472 [3:20:56<17:13:23,  3.11it/s]
 48%|████▊     | 178941/371472 [3:20:56<17:22:40,  3.08it/s]
 48%|████▊     | 178942/371472 [3:20:57<16:52:23,  3.17it/s]
 48%|████▊     | 178943/371472 [3:20:57<16:22:21,  3.27it/s]
 48%|████▊     | 178944/371472 [3:20:57<16:06:34,  3.32it/s]
 48%|████▊     | 178945/371472 [3:20:57<16:01:32,  3.34it/s]
 48%|████▊     | 178946/371472 [3:20:58<15:24:16,  3.47it/s]
 48%|████▊     | 178947/371472 [3:20:58<15:34:51,  3.43it/s]
 48%|████▊     | 178948/371472 [3:20:58<15:44:34,  3.40it/s]
 48%|████▊     | 178949/371472 [3:20:59<15:38:52,  3.42it/s]
 48%|████▊     | 178950/371472 [3:20:59<15:23:29,  3.47it/s]
 48%|████▊     | 178951/371472 [3:20:59<15:59:24,  3.34it/s]
 48%|████▊     | 178952/371472 [3:21:00<16:14:01,  3.29it/s]
 48%|████▊     | 178953/371472 [3:21:00<15:51:06,  3.37it/s]
 48%|████▊     | 178954/371472 [3:21:00<15:27:38,  3.46it/s]
 48%|████▊     | 178955/371472 [3:21:00<15:22:08,  3.48it/s]
 48%|████▊     | 178956/371472 [3:21:01<15:22:06,  3.48it/s]
 48%|████▊     | 178957/371472 [3:21:01<15:42:27,  3.40it/s]
 48%|████▊     | 178958/371472 [3:21:01<15:40:51,  3.41it/s]
 48%|████▊     | 178959/371472 [3:21:02<15:30:35,  3.45it/s]
 48%|████▊     | 178960/371472 [3:21:02<15:29:15,  3.45it/s]
                                                            
{'loss': 2.7632, 'learning_rate': 5.666681031696438e-07, 'epoch': 7.71}
+
 48%|████▊     | 178960/371472 [3:21:02<15:29:15,  3.45it/s]
 48%|████▊     | 178961/371472 [3:21:02<15:36:19,  3.43it/s]
 48%|████▊     | 178962/371472 [3:21:02<15:44:04,  3.40it/s]
 48%|████▊     | 178963/371472 [3:21:03<15:29:30,  3.45it/s]
 48%|████▊     | 178964/371472 [3:21:03<15:37:49,  3.42it/s]
 48%|████▊     | 178965/371472 [3:21:03<16:20:34,  3.27it/s]
 48%|████▊     | 178966/371472 [3:21:04<16:07:13,  3.32it/s]
 48%|████▊     | 178967/371472 [3:21:04<16:04:17,  3.33it/s]
 48%|████▊     | 178968/371472 [3:21:04<15:45:22,  3.39it/s]
 48%|████▊     | 178969/371472 [3:21:04<15:27:02,  3.46it/s]
 48%|████▊     | 178970/371472 [3:21:05<15:11:35,  3.52it/s]
 48%|████▊     | 178971/371472 [3:21:05<15:49:01,  3.38it/s]
 48%|████▊     | 178972/371472 [3:21:05<16:11:19,  3.30it/s]
 48%|████▊     | 178973/371472 [3:21:06<16:09:52,  3.31it/s]
 48%|████▊     | 178974/371472 [3:21:06<16:21:58,  3.27it/s]
 48%|████▊     | 178975/371472 [3:21:06<16:01:51,  3.34it/s]
 48%|████▊     | 178976/371472 [3:21:07<16:43:39,  3.20it/s]
 48%|████▊     | 178977/371472 [3:21:07<16:27:10,  3.25it/s]
 48%|████▊     | 178978/371472 [3:21:07<16:25:51,  3.25it/s]
 48%|████▊     | 178979/371472 [3:21:08<16:38:37,  3.21it/s]
 48%|████▊     | 178980/371472 [3:21:08<16:55:14,  3.16it/s]
                                                            
{'loss': 2.9656, 'learning_rate': 5.666196211941649e-07, 'epoch': 7.71}
+
 48%|████▊     | 178980/371472 [3:21:08<16:55:14,  3.16it/s]
 48%|████▊     | 178981/371472 [3:21:08<16:37:59,  3.21it/s]
 48%|████▊     | 178982/371472 [3:21:09<16:49:00,  3.18it/s]
 48%|████▊     | 178983/371472 [3:21:09<17:27:40,  3.06it/s]
 48%|████▊     | 178984/371472 [3:21:09<17:09:28,  3.12it/s]
 48%|████▊     | 178985/371472 [3:21:10<17:27:45,  3.06it/s]
 48%|████▊     | 178986/371472 [3:21:10<17:40:26,  3.03it/s]
 48%|████▊     | 178987/371472 [3:21:10<16:52:27,  3.17it/s]
 48%|████▊     | 178988/371472 [3:21:10<16:44:26,  3.19it/s]
 48%|████▊     | 178989/371472 [3:21:11<16:20:22,  3.27it/s]
 48%|████▊     | 178990/371472 [3:21:11<16:44:06,  3.19it/s]
 48%|████▊     | 178991/371472 [3:21:11<16:32:09,  3.23it/s]
 48%|████▊     | 178992/371472 [3:21:12<16:17:56,  3.28it/s]
 48%|████▊     | 178993/371472 [3:21:12<16:13:46,  3.29it/s]
 48%|████▊     | 178994/371472 [3:21:12<16:20:22,  3.27it/s]
 48%|████▊     | 178995/371472 [3:21:13<17:05:13,  3.13it/s]
 48%|████▊     | 178996/371472 [3:21:13<16:48:00,  3.18it/s]
 48%|████▊     | 178997/371472 [3:21:13<16:35:01,  3.22it/s]
 48%|████▊     | 178998/371472 [3:21:13<16:00:49,  3.34it/s]
 48%|████▊     | 178999/371472 [3:21:14<16:17:07,  3.28it/s]
 48%|████▊     | 179000/371472 [3:21:14<15:58:35,  3.35it/s]
                                                            
{'loss': 2.8735, 'learning_rate': 5.665711392186859e-07, 'epoch': 7.71}
+
 48%|████▊     | 179000/371472 [3:21:14<15:58:35,  3.35it/s]
 48%|████▊     | 179001/371472 [3:21:14<16:15:20,  3.29it/s]
 48%|████▊     | 179002/371472 [3:21:15<16:12:36,  3.30it/s]
 48%|████▊     | 179003/371472 [3:21:15<16:01:29,  3.34it/s]
 48%|████▊     | 179004/371472 [3:21:15<16:40:48,  3.21it/s]
 48%|████▊     | 179005/371472 [3:21:16<15:55:27,  3.36it/s]
 48%|████▊     | 179006/371472 [3:21:16<15:39:40,  3.41it/s]
 48%|████▊     | 179007/371472 [3:21:16<17:55:41,  2.98it/s]
 48%|████▊     | 179008/371472 [3:21:17<17:11:28,  3.11it/s]
 48%|████▊     | 179009/371472 [3:21:17<16:42:21,  3.20it/s]
 48%|████▊     | 179010/371472 [3:21:17<16:48:49,  3.18it/s]
 48%|████▊     | 179011/371472 [3:21:18<16:48:18,  3.18it/s]
 48%|████▊     | 179012/371472 [3:21:18<16:30:01,  3.24it/s]
 48%|████▊     | 179013/371472 [3:21:18<15:50:51,  3.37it/s]
 48%|████▊     | 179014/371472 [3:21:18<16:00:42,  3.34it/s]
 48%|████▊     | 179015/371472 [3:21:19<15:50:23,  3.38it/s]
 48%|████▊     | 179016/371472 [3:21:19<15:44:48,  3.39it/s]
 48%|████▊     | 179017/371472 [3:21:19<15:38:09,  3.42it/s]
 48%|████▊     | 179018/371472 [3:21:20<15:16:51,  3.50it/s]
 48%|████▊     | 179019/371472 [3:21:20<15:55:09,  3.36it/s]
 48%|████▊     | 179020/371472 [3:21:20<15:56:16,  3.35it/s]
                                                            
{'loss': 3.0153, 'learning_rate': 5.665226572432072e-07, 'epoch': 7.71}
+
 48%|████▊     | 179020/371472 [3:21:20<15:56:16,  3.35it/s]
 48%|████▊     | 179021/371472 [3:21:20<15:47:26,  3.39it/s]
 48%|████▊     | 179022/371472 [3:21:21<16:02:58,  3.33it/s]
 48%|████▊     | 179023/371472 [3:21:21<15:52:17,  3.37it/s]
 48%|████▊     | 179024/371472 [3:21:21<15:57:48,  3.35it/s]
 48%|████▊     | 179025/371472 [3:21:22<15:54:59,  3.36it/s]
 48%|████▊     | 179026/371472 [3:21:22<16:23:04,  3.26it/s]
 48%|████▊     | 179027/371472 [3:21:22<16:47:14,  3.18it/s]
 48%|████▊     | 179028/371472 [3:21:23<16:09:02,  3.31it/s]
 48%|████▊     | 179029/371472 [3:21:23<16:20:20,  3.27it/s]
 48%|████▊     | 179030/371472 [3:21:23<16:16:06,  3.29it/s]
 48%|████▊     | 179031/371472 [3:21:24<16:11:09,  3.30it/s]
 48%|████▊     | 179032/371472 [3:21:24<16:08:22,  3.31it/s]
 48%|████▊     | 179033/371472 [3:21:24<15:29:28,  3.45it/s]
 48%|████▊     | 179034/371472 [3:21:24<15:06:18,  3.54it/s]
 48%|████▊     | 179035/371472 [3:21:25<15:39:23,  3.41it/s]
 48%|████▊     | 179036/371472 [3:21:25<15:31:51,  3.44it/s]
 48%|████▊     | 179037/371472 [3:21:25<16:06:51,  3.32it/s]
 48%|████▊     | 179038/371472 [3:21:26<16:57:24,  3.15it/s]
 48%|████▊     | 179039/371472 [3:21:26<16:17:01,  3.28it/s]
 48%|████▊     | 179040/371472 [3:21:26<16:07:15,  3.32it/s]
                                                            
{'loss': 2.8502, 'learning_rate': 5.664741752677283e-07, 'epoch': 7.71}
+
 48%|████▊     | 179040/371472 [3:21:26<16:07:15,  3.32it/s]
 48%|████▊     | 179041/371472 [3:21:26<16:12:43,  3.30it/s]
 48%|████▊     | 179042/371472 [3:21:27<16:03:33,  3.33it/s]
 48%|████▊     | 179043/371472 [3:21:27<16:08:53,  3.31it/s]
 48%|████▊     | 179044/371472 [3:21:27<16:32:40,  3.23it/s]
 48%|████▊     | 179045/371472 [3:21:28<16:08:15,  3.31it/s]
 48%|████▊     | 179046/371472 [3:21:28<17:12:53,  3.10it/s]
 48%|████▊     | 179047/371472 [3:21:28<16:50:29,  3.17it/s]
 48%|████▊     | 179048/371472 [3:21:29<16:17:05,  3.28it/s]
 48%|████▊     | 179049/371472 [3:21:29<15:52:22,  3.37it/s]
 48%|████▊     | 179050/371472 [3:21:29<15:37:27,  3.42it/s]
 48%|████▊     | 179051/371472 [3:21:30<15:42:26,  3.40it/s]
 48%|████▊     | 179052/371472 [3:21:30<15:29:51,  3.45it/s]
 48%|████▊     | 179053/371472 [3:21:30<15:24:23,  3.47it/s]
 48%|████▊     | 179054/371472 [3:21:30<15:14:10,  3.51it/s]
 48%|████▊     | 179055/371472 [3:21:31<15:07:30,  3.53it/s]
 48%|████▊     | 179056/371472 [3:21:31<15:07:35,  3.53it/s]
 48%|████▊     | 179057/371472 [3:21:31<15:17:52,  3.49it/s]
 48%|████▊     | 179058/371472 [3:21:31<15:13:23,  3.51it/s]
 48%|████▊     | 179059/371472 [3:21:32<15:19:42,  3.49it/s]
 48%|████▊     | 179060/371472 [3:21:32<15:34:58,  3.43it/s]
                                                            
{'loss': 2.9253, 'learning_rate': 5.664256932922493e-07, 'epoch': 7.71}
+
 48%|████▊     | 179060/371472 [3:21:32<15:34:58,  3.43it/s]
 48%|████▊     | 179061/371472 [3:21:32<15:25:24,  3.47it/s]
 48%|████▊     | 179062/371472 [3:21:33<15:15:55,  3.50it/s]
 48%|████▊     | 179063/371472 [3:21:33<15:27:00,  3.46it/s]
 48%|████▊     | 179064/371472 [3:21:33<15:09:08,  3.53it/s]
 48%|████▊     | 179065/371472 [3:21:33<15:18:40,  3.49it/s]
 48%|████▊     | 179066/371472 [3:21:34<15:53:29,  3.36it/s]
 48%|████▊     | 179067/371472 [3:21:34<16:20:55,  3.27it/s]
 48%|████▊     | 179068/371472 [3:21:34<15:57:50,  3.35it/s]
 48%|████▊     | 179069/371472 [3:21:35<15:39:06,  3.41it/s]
 48%|████▊     | 179070/371472 [3:21:35<15:35:28,  3.43it/s]
 48%|████▊     | 179071/371472 [3:21:35<15:23:42,  3.47it/s]
 48%|████▊     | 179072/371472 [3:21:36<15:09:37,  3.53it/s]
 48%|████▊     | 179073/371472 [3:21:36<14:55:38,  3.58it/s]
 48%|████▊     | 179074/371472 [3:21:36<15:12:17,  3.51it/s]
 48%|████▊     | 179075/371472 [3:21:36<15:21:03,  3.48it/s]
 48%|████▊     | 179076/371472 [3:21:37<15:21:59,  3.48it/s]
 48%|████▊     | 179077/371472 [3:21:37<15:07:08,  3.53it/s]
 48%|████▊     | 179078/371472 [3:21:37<15:48:25,  3.38it/s]
 48%|████▊     | 179079/371472 [3:21:38<16:08:21,  3.31it/s]
 48%|████▊     | 179080/371472 [3:21:38<16:01:23,  3.34it/s]
                                                            
{'loss': 2.7938, 'learning_rate': 5.663772113167704e-07, 'epoch': 7.71}
+
 48%|████▊     | 179080/371472 [3:21:38<16:01:23,  3.34it/s]
 48%|████▊     | 179081/371472 [3:21:38<15:34:40,  3.43it/s]
 48%|████▊     | 179082/371472 [3:21:38<15:47:23,  3.38it/s]
 48%|████▊     | 179083/371472 [3:21:39<16:15:21,  3.29it/s]
 48%|████▊     | 179084/371472 [3:21:39<16:11:44,  3.30it/s]
 48%|████▊     | 179085/371472 [3:21:39<17:03:51,  3.13it/s]
 48%|████▊     | 179086/371472 [3:21:40<17:39:49,  3.03it/s]
 48%|████▊     | 179087/371472 [3:21:40<17:23:47,  3.07it/s]
 48%|████▊     | 179088/371472 [3:21:40<16:52:59,  3.17it/s]
 48%|████▊     | 179089/371472 [3:21:41<17:04:27,  3.13it/s]
 48%|████▊     | 179090/371472 [3:21:41<16:22:59,  3.26it/s]
 48%|████▊     | 179091/371472 [3:21:41<15:52:11,  3.37it/s]
 48%|████▊     | 179092/371472 [3:21:42<16:00:47,  3.34it/s]
 48%|████▊     | 179093/371472 [3:21:42<15:52:54,  3.36it/s]
 48%|████▊     | 179094/371472 [3:21:42<15:43:27,  3.40it/s]
 48%|████▊     | 179095/371472 [3:21:42<15:30:26,  3.45it/s]
 48%|████▊     | 179096/371472 [3:21:43<15:45:03,  3.39it/s]
 48%|████▊     | 179097/371472 [3:21:43<15:49:49,  3.38it/s]
 48%|████▊     | 179098/371472 [3:21:43<16:03:08,  3.33it/s]
 48%|████▊     | 179099/371472 [3:21:44<16:34:16,  3.22it/s]
 48%|████▊     | 179100/371472 [3:21:44<16:18:19,  3.28it/s]
                                                            
{'loss': 2.9461, 'learning_rate': 5.663287293412916e-07, 'epoch': 7.71}
+
 48%|████▊     | 179100/371472 [3:21:44<16:18:19,  3.28it/s]
 48%|████▊     | 179101/371472 [3:21:44<16:32:39,  3.23it/s]
 48%|████▊     | 179102/371472 [3:21:45<16:07:52,  3.31it/s]
 48%|████▊     | 179103/371472 [3:21:45<15:55:32,  3.36it/s]
 48%|████▊     | 179104/371472 [3:21:45<15:45:38,  3.39it/s]
 48%|████▊     | 179105/371472 [3:21:46<16:49:59,  3.17it/s]
 48%|████▊     | 179106/371472 [3:21:46<16:57:13,  3.15it/s]
 48%|████▊     | 179107/371472 [3:21:46<16:18:52,  3.28it/s]
 48%|████▊     | 179108/371472 [3:21:46<15:58:12,  3.35it/s]
 48%|████▊     | 179109/371472 [3:21:47<16:08:36,  3.31it/s]
 48%|████▊     | 179110/371472 [3:21:47<16:05:44,  3.32it/s]
 48%|████▊     | 179111/371472 [3:21:47<15:48:52,  3.38it/s]
 48%|████▊     | 179112/371472 [3:21:48<15:52:24,  3.37it/s]
 48%|████▊     | 179113/371472 [3:21:48<15:45:57,  3.39it/s]
 48%|████▊     | 179114/371472 [3:21:48<15:26:41,  3.46it/s]
 48%|████▊     | 179115/371472 [3:21:49<17:30:18,  3.05it/s]
 48%|████▊     | 179116/371472 [3:21:49<17:28:14,  3.06it/s]
 48%|████▊     | 179117/371472 [3:21:49<16:57:14,  3.15it/s]
 48%|████▊     | 179118/371472 [3:21:50<17:23:46,  3.07it/s]
 48%|████▊     | 179119/371472 [3:21:50<16:55:50,  3.16it/s]
 48%|████▊     | 179120/371472 [3:21:50<16:23:17,  3.26it/s]
                                                            
{'loss': 2.8583, 'learning_rate': 5.662802473658126e-07, 'epoch': 7.72}
+
 48%|████▊     | 179120/371472 [3:21:50<16:23:17,  3.26it/s]
 48%|████▊     | 179121/371472 [3:21:50<15:55:42,  3.35it/s]
 48%|████▊     | 179122/371472 [3:21:51<15:46:44,  3.39it/s]
 48%|████▊     | 179123/371472 [3:21:51<15:47:43,  3.38it/s]
 48%|████▊     | 179124/371472 [3:21:51<15:28:49,  3.45it/s]
 48%|████▊     | 179125/371472 [3:21:52<15:28:52,  3.45it/s]
 48%|████▊     | 179126/371472 [3:21:52<15:13:10,  3.51it/s]
 48%|████▊     | 179127/371472 [3:21:52<15:05:56,  3.54it/s]
 48%|████▊     | 179128/371472 [3:21:52<15:03:37,  3.55it/s]
 48%|████▊     | 179129/371472 [3:21:53<15:07:41,  3.53it/s]
 48%|████▊     | 179130/371472 [3:21:53<15:04:51,  3.54it/s]
 48%|████▊     | 179131/371472 [3:21:53<16:16:28,  3.28it/s]
 48%|████▊     | 179132/371472 [3:21:54<18:27:34,  2.89it/s]
 48%|████▊     | 179133/371472 [3:21:54<17:43:34,  3.01it/s]
 48%|████▊     | 179134/371472 [3:21:54<17:33:25,  3.04it/s]
 48%|████▊     | 179135/371472 [3:21:55<16:47:33,  3.18it/s]
 48%|████▊     | 179136/371472 [3:21:55<16:29:56,  3.24it/s]
 48%|████▊     | 179137/371472 [3:21:55<16:43:32,  3.19it/s]
 48%|████▊     | 179138/371472 [3:21:56<16:21:35,  3.27it/s]
 48%|████▊     | 179139/371472 [3:21:56<16:54:45,  3.16it/s]
 48%|████▊     | 179140/371472 [3:21:56<16:29:55,  3.24it/s]
                                                            
{'loss': 2.7534, 'learning_rate': 5.662317653903336e-07, 'epoch': 7.72}
+
 48%|████▊     | 179140/371472 [3:21:56<16:29:55,  3.24it/s]
 48%|████▊     | 179141/371472 [3:21:57<17:19:34,  3.08it/s]
 48%|████▊     | 179142/371472 [3:21:57<17:31:05,  3.05it/s]
 48%|████▊     | 179143/371472 [3:21:57<16:46:52,  3.18it/s]
 48%|████▊     | 179144/371472 [3:21:58<17:09:00,  3.12it/s]
 48%|████▊     | 179145/371472 [3:21:58<18:07:41,  2.95it/s]
 48%|████▊     | 179146/371472 [3:21:59<21:58:00,  2.43it/s]
 48%|████▊     | 179147/371472 [3:21:59<20:26:01,  2.61it/s]
 48%|████▊     | 179148/371472 [3:21:59<18:56:12,  2.82it/s]
 48%|████▊     | 179149/371472 [3:21:59<18:27:34,  2.89it/s]
 48%|████▊     | 179150/371472 [3:22:00<17:10:05,  3.11it/s]
 48%|████▊     | 179151/371472 [3:22:00<16:42:17,  3.20it/s]
 48%|████▊     | 179152/371472 [3:22:00<18:17:41,  2.92it/s]
 48%|████▊     | 179153/371472 [3:22:01<18:30:57,  2.89it/s]
 48%|████▊     | 179154/371472 [3:22:01<17:22:08,  3.08it/s]
 48%|████▊     | 179155/371472 [3:22:01<17:32:52,  3.04it/s]
 48%|████▊     | 179156/371472 [3:22:02<17:29:53,  3.05it/s]
 48%|████▊     | 179157/371472 [3:22:02<17:06:45,  3.12it/s]
 48%|████▊     | 179158/371472 [3:22:02<16:52:28,  3.17it/s]
 48%|████▊     | 179159/371472 [3:22:03<17:18:43,  3.09it/s]
 48%|████▊     | 179160/371472 [3:22:03<17:00:44,  3.14it/s]
                                                            
{'loss': 2.9148, 'learning_rate': 5.661832834148549e-07, 'epoch': 7.72}
+
 48%|████▊     | 179160/371472 [3:22:03<17:00:44,  3.14it/s]
 48%|████▊     | 179161/371472 [3:22:03<17:17:10,  3.09it/s]
 48%|████▊     | 179162/371472 [3:22:04<16:46:51,  3.18it/s]
 48%|████▊     | 179163/371472 [3:22:04<16:22:16,  3.26it/s]
 48%|████▊     | 179164/371472 [3:22:04<15:47:43,  3.38it/s]
 48%|████▊     | 179165/371472 [3:22:04<15:28:31,  3.45it/s]
 48%|████▊     | 179166/371472 [3:22:05<15:17:25,  3.49it/s]
 48%|████▊     | 179167/371472 [3:22:05<15:50:50,  3.37it/s]
 48%|████▊     | 179168/371472 [3:22:05<15:37:09,  3.42it/s]
 48%|████▊     | 179169/371472 [3:22:06<15:57:25,  3.35it/s]
 48%|████▊     | 179170/371472 [3:22:06<15:28:00,  3.45it/s]
 48%|████▊     | 179171/371472 [3:22:06<15:24:10,  3.47it/s]
 48%|████▊     | 179172/371472 [3:22:07<16:46:57,  3.18it/s]
 48%|████▊     | 179173/371472 [3:22:07<16:47:51,  3.18it/s]
 48%|████▊     | 179174/371472 [3:22:07<16:22:05,  3.26it/s]
 48%|████▊     | 179175/371472 [3:22:07<17:10:19,  3.11it/s]
 48%|████▊     | 179176/371472 [3:22:08<16:29:28,  3.24it/s]
 48%|████▊     | 179177/371472 [3:22:08<17:54:19,  2.98it/s]
 48%|████▊     | 179178/371472 [3:22:08<17:09:41,  3.11it/s]
 48%|████▊     | 179179/371472 [3:22:09<17:13:34,  3.10it/s]
 48%|████▊     | 179180/371472 [3:22:09<17:15:44,  3.09it/s]
                                                            
{'loss': 3.0079, 'learning_rate': 5.66134801439376e-07, 'epoch': 7.72}
+
 48%|████▊     | 179180/371472 [3:22:09<17:15:44,  3.09it/s]
 48%|████▊     | 179181/371472 [3:22:09<16:47:15,  3.18it/s]
 48%|████▊     | 179182/371472 [3:22:10<16:46:46,  3.18it/s]
 48%|████▊     | 179183/371472 [3:22:10<16:16:54,  3.28it/s]
 48%|████▊     | 179184/371472 [3:22:11<20:06:54,  2.66it/s]
 48%|████▊     | 179185/371472 [3:22:11<19:52:15,  2.69it/s]
 48%|████▊     | 179186/371472 [3:22:11<18:41:57,  2.86it/s]
 48%|████▊     | 179187/371472 [3:22:12<17:57:59,  2.97it/s]
 48%|████▊     | 179188/371472 [3:22:12<17:30:22,  3.05it/s]
 48%|████▊     | 179189/371472 [3:22:12<17:16:32,  3.09it/s]
 48%|████▊     | 179190/371472 [3:22:12<16:50:12,  3.17it/s]
 48%|████▊     | 179191/371472 [3:22:13<16:45:18,  3.19it/s]
 48%|████▊     | 179192/371472 [3:22:13<16:13:39,  3.29it/s]
 48%|████▊     | 179193/371472 [3:22:13<16:52:01,  3.17it/s]
 48%|████▊     | 179194/371472 [3:22:14<17:27:03,  3.06it/s]
 48%|████▊     | 179195/371472 [3:22:14<17:01:28,  3.14it/s]
 48%|████▊     | 179196/371472 [3:22:14<17:13:56,  3.10it/s]
 48%|████▊     | 179197/371472 [3:22:15<16:50:02,  3.17it/s]
 48%|████▊     | 179198/371472 [3:22:15<16:21:24,  3.27it/s]
 48%|████▊     | 179199/371472 [3:22:15<16:25:34,  3.25it/s]
 48%|████▊     | 179200/371472 [3:22:16<16:18:24,  3.28it/s]
                                                            
{'loss': 2.8535, 'learning_rate': 5.660863194638971e-07, 'epoch': 7.72}
+
 48%|████▊     | 179200/371472 [3:22:16<16:18:24,  3.28it/s]
 48%|████▊     | 179201/371472 [3:22:16<16:51:50,  3.17it/s]
 48%|████▊     | 179202/371472 [3:22:16<16:52:10,  3.17it/s]
 48%|████▊     | 179203/371472 [3:22:16<16:13:11,  3.29it/s]
 48%|████▊     | 179204/371472 [3:22:17<15:48:03,  3.38it/s]
 48%|████▊     | 179205/371472 [3:22:17<16:32:35,  3.23it/s]
 48%|████▊     | 179206/371472 [3:22:17<17:13:07,  3.10it/s]
 48%|████▊     | 179207/371472 [3:22:18<16:45:59,  3.19it/s]
 48%|████▊     | 179208/371472 [3:22:18<16:18:44,  3.27it/s]
 48%|████▊     | 179209/371472 [3:22:18<15:50:33,  3.37it/s]
 48%|████▊     | 179210/371472 [3:22:19<16:00:10,  3.34it/s]
 48%|████▊     | 179211/371472 [3:22:19<15:42:58,  3.40it/s]
 48%|████▊     | 179212/371472 [3:22:19<16:36:25,  3.22it/s]
 48%|████▊     | 179213/371472 [3:22:20<16:13:04,  3.29it/s]
 48%|████▊     | 179214/371472 [3:22:20<16:02:40,  3.33it/s]
 48%|████▊     | 179215/371472 [3:22:20<15:50:01,  3.37it/s]
 48%|████▊     | 179216/371472 [3:22:20<16:10:33,  3.30it/s]
 48%|████▊     | 179217/371472 [3:22:21<16:33:25,  3.23it/s]
 48%|████▊     | 179218/371472 [3:22:21<16:45:45,  3.19it/s]
 48%|████▊     | 179219/371472 [3:22:21<16:26:17,  3.25it/s]
 48%|████▊     | 179220/371472 [3:22:22<15:56:29,  3.35it/s]
                                                            
{'loss': 2.9551, 'learning_rate': 5.660378374884181e-07, 'epoch': 7.72}
+
 48%|████▊     | 179220/371472 [3:22:22<15:56:29,  3.35it/s]
 48%|████▊     | 179221/371472 [3:22:22<16:36:19,  3.22it/s]
 48%|████▊     | 179222/371472 [3:22:22<16:29:23,  3.24it/s]
 48%|████▊     | 179223/371472 [3:22:23<15:50:49,  3.37it/s]
 48%|████▊     | 179224/371472 [3:22:23<16:01:47,  3.33it/s]
 48%|████▊     | 179225/371472 [3:22:23<15:30:22,  3.44it/s]
 48%|████▊     | 179226/371472 [3:22:23<15:18:53,  3.49it/s]
 48%|████▊     | 179227/371472 [3:22:24<15:22:50,  3.47it/s]
 48%|████▊     | 179228/371472 [3:22:24<15:42:43,  3.40it/s]
 48%|████▊     | 179229/371472 [3:22:24<16:06:20,  3.32it/s]
 48%|████▊     | 179230/371472 [3:22:25<16:05:03,  3.32it/s]
 48%|████▊     | 179231/371472 [3:22:25<16:49:23,  3.17it/s]
 48%|████▊     | 179232/371472 [3:22:25<16:38:03,  3.21it/s]
 48%|████▊     | 179233/371472 [3:22:26<16:55:24,  3.16it/s]
 48%|████▊     | 179234/371472 [3:22:26<16:34:10,  3.22it/s]
 48%|████▊     | 179235/371472 [3:22:26<16:19:04,  3.27it/s]
 48%|████▊     | 179236/371472 [3:22:27<16:17:52,  3.28it/s]
 48%|████▊     | 179237/371472 [3:22:27<16:25:33,  3.25it/s]
 48%|████▊     | 179238/371472 [3:22:27<15:59:56,  3.34it/s]
 48%|████▊     | 179239/371472 [3:22:27<16:33:17,  3.23it/s]
 48%|████▊     | 179240/371472 [3:22:28<15:54:47,  3.36it/s]
                                                            
{'loss': 2.9464, 'learning_rate': 5.659893555129392e-07, 'epoch': 7.72}
+
 48%|████▊     | 179240/371472 [3:22:28<15:54:47,  3.36it/s]
 48%|████▊     | 179241/371472 [3:22:28<16:16:44,  3.28it/s]
 48%|████▊     | 179242/371472 [3:22:28<16:05:17,  3.32it/s]
 48%|████▊     | 179243/371472 [3:22:29<16:29:59,  3.24it/s]
 48%|████▊     | 179244/371472 [3:22:29<16:17:10,  3.28it/s]
 48%|████▊     | 179245/371472 [3:22:29<16:16:09,  3.28it/s]
 48%|████▊     | 179246/371472 [3:22:30<16:48:51,  3.18it/s]
 48%|████▊     | 179247/371472 [3:22:30<16:22:42,  3.26it/s]
 48%|████▊     | 179248/371472 [3:22:30<16:17:17,  3.28it/s]
 48%|████▊     | 179249/371472 [3:22:30<16:12:31,  3.29it/s]
 48%|████▊     | 179250/371472 [3:22:31<16:04:48,  3.32it/s]
 48%|████▊     | 179251/371472 [3:22:31<16:33:01,  3.23it/s]
 48%|████▊     | 179252/371472 [3:22:31<16:00:08,  3.34it/s]
 48%|████▊     | 179253/371472 [3:22:32<16:19:10,  3.27it/s]
 48%|████▊     | 179254/371472 [3:22:32<15:58:57,  3.34it/s]
 48%|████▊     | 179255/371472 [3:22:32<16:14:31,  3.29it/s]
 48%|████▊     | 179256/371472 [3:22:33<16:04:56,  3.32it/s]
 48%|████▊     | 179257/371472 [3:22:33<15:58:16,  3.34it/s]
 48%|████▊     | 179258/371472 [3:22:33<16:03:40,  3.32it/s]
 48%|████▊     | 179259/371472 [3:22:33<15:55:48,  3.35it/s]
 48%|████▊     | 179260/371472 [3:22:34<15:47:07,  3.38it/s]
                                                            
{'loss': 2.989, 'learning_rate': 5.659408735374605e-07, 'epoch': 7.72}
+
 48%|████▊     | 179260/371472 [3:22:34<15:47:07,  3.38it/s]
 48%|████▊     | 179261/371472 [3:22:34<15:49:19,  3.37it/s]
 48%|████▊     | 179262/371472 [3:22:34<16:11:30,  3.30it/s]
 48%|████▊     | 179263/371472 [3:22:35<16:48:27,  3.18it/s]
 48%|████▊     | 179264/371472 [3:22:35<16:23:57,  3.26it/s]
 48%|████▊     | 179265/371472 [3:22:35<18:09:11,  2.94it/s]
 48%|████▊     | 179266/371472 [3:22:36<17:57:25,  2.97it/s]
 48%|████▊     | 179267/371472 [3:22:36<17:37:52,  3.03it/s]
 48%|████▊     | 179268/371472 [3:22:36<17:08:54,  3.11it/s]
 48%|████▊     | 179269/371472 [3:22:37<16:32:55,  3.23it/s]
 48%|████▊     | 179270/371472 [3:22:37<17:08:46,  3.11it/s]
 48%|████▊     | 179271/371472 [3:22:37<17:41:34,  3.02it/s]
 48%|████▊     | 179272/371472 [3:22:38<19:37:27,  2.72it/s]
 48%|████▊     | 179273/371472 [3:22:38<19:06:11,  2.79it/s]
 48%|████▊     | 179274/371472 [3:22:38<17:45:20,  3.01it/s]
 48%|████▊     | 179275/371472 [3:22:39<17:59:18,  2.97it/s]
 48%|████▊     | 179276/371472 [3:22:39<18:07:17,  2.95it/s]
 48%|████▊     | 179277/371472 [3:22:39<17:11:13,  3.11it/s]
 48%|████▊     | 179278/371472 [3:22:40<16:42:45,  3.19it/s]
 48%|████▊     | 179279/371472 [3:22:40<16:21:22,  3.26it/s]
 48%|████▊     | 179280/371472 [3:22:40<16:27:10,  3.24it/s]
                                                            
{'loss': 3.0463, 'learning_rate': 5.658923915619816e-07, 'epoch': 7.72}
+
 48%|████▊     | 179280/371472 [3:22:40<16:27:10,  3.24it/s]
 48%|████▊     | 179281/371472 [3:22:41<16:07:14,  3.31it/s]
 48%|████▊     | 179282/371472 [3:22:41<16:01:43,  3.33it/s]
 48%|████▊     | 179283/371472 [3:22:41<15:50:45,  3.37it/s]
 48%|████▊     | 179284/371472 [3:22:41<15:59:19,  3.34it/s]
 48%|████▊     | 179285/371472 [3:22:42<15:52:08,  3.36it/s]
 48%|████▊     | 179286/371472 [3:22:42<16:40:32,  3.20it/s]
 48%|███��▊     | 179287/371472 [3:22:42<15:58:22,  3.34it/s]
 48%|████▊     | 179288/371472 [3:22:43<16:49:54,  3.17it/s]
 48%|████▊     | 179289/371472 [3:22:43<16:11:37,  3.30it/s]
 48%|████▊     | 179290/371472 [3:22:43<15:44:12,  3.39it/s]
 48%|████▊     | 179291/371472 [3:22:44<15:54:43,  3.35it/s]
 48%|████▊     | 179292/371472 [3:22:44<15:44:32,  3.39it/s]
 48%|████▊     | 179293/371472 [3:22:44<15:52:32,  3.36it/s]
 48%|████▊     | 179294/371472 [3:22:45<16:17:05,  3.28it/s]
 48%|████▊     | 179295/371472 [3:22:45<16:21:20,  3.26it/s]
 48%|████▊     | 179296/371472 [3:22:45<17:07:45,  3.12it/s]
 48%|████▊     | 179297/371472 [3:22:45<16:40:36,  3.20it/s]
 48%|████▊     | 179298/371472 [3:22:46<16:22:08,  3.26it/s]
 48%|████▊     | 179299/371472 [3:22:46<16:06:26,  3.31it/s]
 48%|████▊     | 179300/371472 [3:22:46<16:09:50,  3.30it/s]
                                                            
{'loss': 2.7292, 'learning_rate': 5.658439095865026e-07, 'epoch': 7.72}
+
 48%|████▊     | 179300/371472 [3:22:46<16:09:50,  3.30it/s]
 48%|████▊     | 179301/371472 [3:22:47<15:42:03,  3.40it/s]
 48%|████▊     | 179302/371472 [3:22:47<15:50:46,  3.37it/s]
 48%|████▊     | 179303/371472 [3:22:47<15:34:22,  3.43it/s]
 48%|████▊     | 179304/371472 [3:22:48<16:12:43,  3.29it/s]
 48%|████▊     | 179305/371472 [3:22:48<15:51:14,  3.37it/s]
 48%|████▊     | 179306/371472 [3:22:48<15:41:44,  3.40it/s]
 48%|████▊     | 179307/371472 [3:22:48<16:30:28,  3.23it/s]
 48%|████▊     | 179308/371472 [3:22:49<16:11:12,  3.30it/s]
 48%|████▊     | 179309/371472 [3:22:49<15:44:44,  3.39it/s]
 48%|████▊     | 179310/371472 [3:22:49<15:28:04,  3.45it/s]
 48%|████▊     | 179311/371472 [3:22:50<15:38:41,  3.41it/s]
 48%|████▊     | 179312/371472 [3:22:50<15:18:24,  3.49it/s]
 48%|████▊     | 179313/371472 [3:22:50<15:24:12,  3.47it/s]
 48%|████▊     | 179314/371472 [3:22:50<15:28:41,  3.45it/s]
 48%|████▊     | 179315/371472 [3:22:51<16:02:40,  3.33it/s]
 48%|████▊     | 179316/371472 [3:22:51<15:48:32,  3.38it/s]
 48%|████▊     | 179317/371472 [3:22:51<16:26:35,  3.25it/s]
 48%|████▊     | 179318/371472 [3:22:52<17:06:10,  3.12it/s]
 48%|████▊     | 179319/371472 [3:22:52<16:42:23,  3.19it/s]
 48%|████▊     | 179320/371472 [3:22:52<16:15:14,  3.28it/s]
                                                            
{'loss': 3.105, 'learning_rate': 5.657954276110237e-07, 'epoch': 7.72}
+
 48%|████▊     | 179320/371472 [3:22:52<16:15:14,  3.28it/s]
 48%|████▊     | 179321/371472 [3:22:53<17:36:58,  3.03it/s]
 48%|████▊     | 179322/371472 [3:22:53<17:55:57,  2.98it/s]
 48%|████▊     | 179323/371472 [3:22:53<17:33:15,  3.04it/s]
 48%|████▊     | 179324/371472 [3:22:54<17:01:03,  3.14it/s]
 48%|████▊     | 179325/371472 [3:22:54<16:14:43,  3.29it/s]
 48%|████▊     | 179326/371472 [3:22:54<17:38:30,  3.03it/s]
 48%|████▊     | 179327/371472 [3:22:55<16:55:10,  3.15it/s]
 48%|████▊     | 179328/371472 [3:22:55<17:15:49,  3.09it/s]
 48%|████▊     | 179329/371472 [3:22:55<16:43:07,  3.19it/s]
 48%|████▊     | 179330/371472 [3:22:56<16:24:50,  3.25it/s]
 48%|████▊     | 179331/371472 [3:22:56<16:41:05,  3.20it/s]
 48%|████▊     | 179332/371472 [3:22:56<16:40:42,  3.20it/s]
 48%|████▊     | 179333/371472 [3:22:56<16:38:36,  3.21it/s]
 48%|████▊     | 179334/371472 [3:22:57<17:08:49,  3.11it/s]
 48%|████▊     | 179335/371472 [3:22:57<16:35:58,  3.22it/s]
 48%|████▊     | 179336/371472 [3:22:57<16:33:13,  3.22it/s]
 48%|████▊     | 179337/371472 [3:22:58<16:26:20,  3.25it/s]
 48%|████▊     | 179338/371472 [3:22:58<15:53:59,  3.36it/s]
 48%|████▊     | 179339/371472 [3:22:58<16:03:22,  3.32it/s]
 48%|████▊     | 179340/371472 [3:22:59<15:54:45,  3.35it/s]
                                                            
{'loss': 3.0078, 'learning_rate': 5.657469456355448e-07, 'epoch': 7.72}
+
 48%|████▊     | 179340/371472 [3:22:59<15:54:45,  3.35it/s]
 48%|████▊     | 179341/371472 [3:22:59<16:09:29,  3.30it/s]
 48%|████▊     | 179342/371472 [3:22:59<15:51:32,  3.37it/s]
 48%|████▊     | 179343/371472 [3:22:59<15:33:24,  3.43it/s]
 48%|████▊     | 179344/371472 [3:23:00<15:43:39,  3.39it/s]
 48%|████▊     | 179345/371472 [3:23:00<16:13:22,  3.29it/s]
 48%|████▊     | 179346/371472 [3:23:00<15:54:21,  3.36it/s]
 48%|████▊     | 179347/371472 [3:23:01<15:43:26,  3.39it/s]
 48%|████▊     | 179348/371472 [3:23:01<16:15:49,  3.28it/s]
 48%|████▊     | 179349/371472 [3:23:01<16:18:08,  3.27it/s]
 48%|████▊     | 179350/371472 [3:23:02<16:16:24,  3.28it/s]
 48%|████▊     | 179351/371472 [3:23:02<16:23:48,  3.25it/s]
 48%|████▊     | 179352/371472 [3:23:02<16:33:55,  3.22it/s]
 48%|████▊     | 179353/371472 [3:23:03<16:10:57,  3.30it/s]
 48%|████▊     | 179354/371472 [3:23:03<16:09:25,  3.30it/s]
 48%|████▊     | 179355/371472 [3:23:03<16:53:08,  3.16it/s]
 48%|████▊     | 179356/371472 [3:23:03<16:28:24,  3.24it/s]
 48%|████▊     | 179357/371472 [3:23:04<16:14:07,  3.29it/s]
 48%|████▊     | 179358/371472 [3:23:04<16:40:58,  3.20it/s]
 48%|████▊     | 179359/371472 [3:23:04<16:24:00,  3.25it/s]
 48%|████▊     | 179360/371472 [3:23:05<15:59:50,  3.34it/s]
                                                            
{'loss': 3.0882, 'learning_rate': 5.656984636600659e-07, 'epoch': 7.73}
+
 48%|████▊     | 179360/371472 [3:23:05<15:59:50,  3.34it/s]
 48%|████▊     | 179361/371472 [3:23:05<16:01:23,  3.33it/s]
 48%|████▊     | 179362/371472 [3:23:05<16:18:05,  3.27it/s]
 48%|████▊     | 179363/371472 [3:23:06<16:22:27,  3.26it/s]
 48%|████▊     | 179364/371472 [3:23:06<15:55:15,  3.35it/s]
 48%|████▊     | 179365/371472 [3:23:06<17:34:18,  3.04it/s]
 48%|████▊     | 179366/371472 [3:23:07<16:56:13,  3.15it/s]
 48%|████▊     | 179367/371472 [3:23:07<17:28:50,  3.05it/s]
 48%|████▊     | 179368/371472 [3:23:07<17:03:05,  3.13it/s]
 48%|████▊     | 179369/371472 [3:23:08<17:46:56,  3.00it/s]
 48%|████▊     | 179370/371472 [3:23:08<17:02:21,  3.13it/s]
 48%|████▊     | 179371/371472 [3:23:08<16:36:20,  3.21it/s]
 48%|████▊     | 179372/371472 [3:23:08<16:33:27,  3.22it/s]
 48%|████▊     | 179373/371472 [3:23:09<16:11:10,  3.30it/s]
 48%|████▊     | 179374/371472 [3:23:09<15:49:18,  3.37it/s]
 48%|████▊     | 179375/371472 [3:23:09<16:05:01,  3.32it/s]
 48%|████▊     | 179376/371472 [3:23:10<17:32:44,  3.04it/s]
 48%|████▊     | 179377/371472 [3:23:10<16:44:46,  3.19it/s]
 48%|████▊     | 179378/371472 [3:23:10<16:21:02,  3.26it/s]
 48%|████▊     | 179379/371472 [3:23:11<16:28:19,  3.24it/s]
 48%|████▊     | 179380/371472 [3:23:11<15:55:52,  3.35it/s]
                                                            
{'loss': 2.7412, 'learning_rate': 5.656499816845869e-07, 'epoch': 7.73}
+
 48%|████▊     | 179380/371472 [3:23:11<15:55:52,  3.35it/s]
 48%|████▊     | 179381/371472 [3:23:11<16:00:42,  3.33it/s]
 48%|████▊     | 179382/371472 [3:23:12<15:56:39,  3.35it/s]
 48%|████▊     | 179383/371472 [3:23:12<15:37:41,  3.41it/s]
 48%|████▊     | 179384/371472 [3:23:12<15:44:07,  3.39it/s]
 48%|████▊     | 179385/371472 [3:23:12<15:34:42,  3.43it/s]
 48%|████▊     | 179386/371472 [3:23:13<15:50:06,  3.37it/s]
 48%|████▊     | 179387/371472 [3:23:13<15:35:25,  3.42it/s]
 48%|████▊     | 179388/371472 [3:23:13<15:49:20,  3.37it/s]
 48%|████▊     | 179389/371472 [3:23:14<15:28:02,  3.45it/s]
 48%|████▊     | 179390/371472 [3:23:14<15:20:31,  3.48it/s]
 48%|████▊     | 179391/371472 [3:23:14<15:19:21,  3.48it/s]
 48%|████▊     | 179392/371472 [3:23:14<16:25:34,  3.25it/s]
 48%|████▊     | 179393/371472 [3:23:15<16:13:41,  3.29it/s]
 48%|████▊     | 179394/371472 [3:23:15<15:52:54,  3.36it/s]
 48%|████▊     | 179395/371472 [3:23:15<15:44:23,  3.39it/s]
 48%|████▊     | 179396/371472 [3:23:16<15:37:20,  3.42it/s]
 48%|████▊     | 179397/371472 [3:23:16<15:54:05,  3.36it/s]
 48%|████▊     | 179398/371472 [3:23:16<16:11:38,  3.29it/s]
 48%|████▊     | 179399/371472 [3:23:17<16:08:45,  3.30it/s]
 48%|████▊     | 179400/371472 [3:23:17<16:01:15,  3.33it/s]
                                                            
{'loss': 2.7994, 'learning_rate': 5.656014997091082e-07, 'epoch': 7.73}
+
 48%|████▊     | 179400/371472 [3:23:17<16:01:15,  3.33it/s]
 48%|████▊     | 179401/371472 [3:23:17<16:02:56,  3.32it/s]
 48%|████▊     | 179402/371472 [3:23:17<15:39:43,  3.41it/s]
 48%|████▊     | 179403/371472 [3:23:18<16:59:57,  3.14it/s]
 48%|████▊     | 179404/371472 [3:23:18<16:43:28,  3.19it/s]
 48%|████▊     | 179405/371472 [3:23:18<16:59:37,  3.14it/s]
 48%|████▊     | 179406/371472 [3:23:19<16:28:44,  3.24it/s]
 48%|████▊     | 179407/371472 [3:23:19<15:53:00,  3.36it/s]
 48%|████▊     | 179408/371472 [3:23:19<16:38:08,  3.21it/s]
 48%|████▊     | 179409/371472 [3:23:20<16:02:58,  3.32it/s]
 48%|████▊     | 179410/371472 [3:23:20<15:45:07,  3.39it/s]
 48%|████▊     | 179411/371472 [3:23:20<15:28:41,  3.45it/s]
 48%|████▊     | 179412/371472 [3:23:21<16:23:33,  3.25it/s]
 48%|████▊     | 179413/371472 [3:23:21<16:14:58,  3.28it/s]
 48%|████▊     | 179414/371472 [3:23:21<16:43:00,  3.19it/s]
 48%|████▊     | 179415/371472 [3:23:21<16:17:01,  3.28it/s]
 48%|████▊     | 179416/371472 [3:23:22<16:05:55,  3.31it/s]
 48%|████▊     | 179417/371472 [3:23:22<17:27:46,  3.05it/s]
 48%|████▊     | 179418/371472 [3:23:22<17:00:07,  3.14it/s]
 48%|████▊     | 179419/371472 [3:23:23<16:21:38,  3.26it/s]
 48%|████▊     | 179420/371472 [3:23:23<16:16:07,  3.28it/s]
                                                            
{'loss': 2.897, 'learning_rate': 5.655530177336293e-07, 'epoch': 7.73}
+
 48%|████▊     | 179420/371472 [3:23:23<16:16:07,  3.28it/s]
 48%|████▊     | 179421/371472 [3:23:23<16:03:40,  3.32it/s]
 48%|████▊     | 179422/371472 [3:23:24<15:55:34,  3.35it/s]
 48%|████▊     | 179423/371472 [3:23:24<15:53:28,  3.36it/s]
 48%|████▊     | 179424/371472 [3:23:24<15:43:11,  3.39it/s]
 48%|████▊     | 179425/371472 [3:23:24<15:40:12,  3.40it/s]
 48%|████▊     | 179426/371472 [3:23:25<15:34:08,  3.43it/s]
 48%|████▊     | 179427/371472 [3:23:25<15:19:19,  3.48it/s]
 48%|████▊     | 179428/371472 [3:23:25<15:44:16,  3.39it/s]
 48%|████▊     | 179429/371472 [3:23:26<15:38:09,  3.41it/s]
 48%|████▊     | 179430/371472 [3:23:26<15:57:27,  3.34it/s]
 48%|████▊     | 179431/371472 [3:23:26<16:03:51,  3.32it/s]
 48%|████▊     | 179432/371472 [3:23:27<16:03:52,  3.32it/s]
 48%|████▊     | 179433/371472 [3:23:27<17:01:55,  3.13it/s]
 48%|████▊     | 179434/371472 [3:23:27<16:38:44,  3.20it/s]
 48%|████▊     | 179435/371472 [3:23:28<16:50:08,  3.17it/s]
 48%|████▊     | 179436/371472 [3:23:28<17:31:42,  3.04it/s]
 48%|████▊     | 179437/371472 [3:23:28<17:25:43,  3.06it/s]
 48%|████▊     | 179438/371472 [3:23:29<17:52:34,  2.98it/s]
 48%|████▊     | 179439/371472 [3:23:29<18:11:11,  2.93it/s]
 48%|████▊     | 179440/371472 [3:23:29<17:13:56,  3.10it/s]
                                                            
{'loss': 2.809, 'learning_rate': 5.655045357581502e-07, 'epoch': 7.73}
+
 48%|████▊     | 179440/371472 [3:23:29<17:13:56,  3.10it/s]
 48%|████▊     | 179441/371472 [3:23:29<16:42:42,  3.19it/s]
 48%|████▊     | 179442/371472 [3:23:30<17:39:04,  3.02it/s]
 48%|████▊     | 179443/371472 [3:23:30<17:22:01,  3.07it/s]
 48%|████▊     | 179444/371472 [3:23:31<17:37:20,  3.03it/s]
 48%|████▊     | 179445/371472 [3:23:31<16:58:27,  3.14it/s]
 48%|████▊     | 179446/371472 [3:23:31<16:46:15,  3.18it/s]
 48%|████▊     | 179447/371472 [3:23:31<16:10:00,  3.30it/s]
 48%|████▊     | 179448/371472 [3:23:32<15:38:33,  3.41it/s]
 48%|████▊     | 179449/371472 [3:23:32<16:00:22,  3.33it/s]
 48%|████▊     | 179450/371472 [3:23:32<16:15:32,  3.28it/s]
 48%|████▊     | 179451/371472 [3:23:33<16:44:18,  3.19it/s]
 48%|████▊     | 179452/371472 [3:23:33<16:39:29,  3.20it/s]
 48%|████▊     | 179453/371472 [3:23:33<16:32:14,  3.23it/s]
 48%|████▊     | 179454/371472 [3:23:34<16:04:53,  3.32it/s]
 48%|████▊     | 179455/371472 [3:23:34<16:12:32,  3.29it/s]
 48%|████▊     | 179456/371472 [3:23:34<15:53:34,  3.36it/s]
 48%|████▊     | 179457/371472 [3:23:34<16:13:38,  3.29it/s]
 48%|████▊     | 179458/371472 [3:23:35<16:00:14,  3.33it/s]
 48%|████▊     | 179459/371472 [3:23:35<15:49:20,  3.37it/s]
 48%|████▊     | 179460/371472 [3:23:35<15:52:49,  3.36it/s]
                                                            
{'loss': 2.8083, 'learning_rate': 5.654560537826714e-07, 'epoch': 7.73}
+
 48%|████▊     | 179460/371472 [3:23:35<15:52:49,  3.36it/s]
 48%|████▊     | 179461/371472 [3:23:36<16:28:22,  3.24it/s]
 48%|████▊     | 179462/371472 [3:23:36<16:02:14,  3.33it/s]
 48%|████▊     | 179463/371472 [3:23:36<15:43:44,  3.39it/s]
 48%|████▊     | 179464/371472 [3:23:37<15:42:05,  3.40it/s]
 48%|████▊     | 179465/371472 [3:23:37<16:14:58,  3.28it/s]
 48%|████▊     | 179466/371472 [3:23:37<16:18:02,  3.27it/s]
 48%|████▊     | 179467/371472 [3:23:37<16:34:28,  3.22it/s]
 48%|████▊     | 179468/371472 [3:23:38<17:34:47,  3.03it/s]
 48%|████▊     | 179469/371472 [3:23:38<17:51:40,  2.99it/s]
 48%|████▊     | 179470/371472 [3:23:39<17:40:37,  3.02it/s]
 48%|████▊     | 179471/371472 [3:23:39<17:41:42,  3.01it/s]
 48%|████▊     | 179472/371472 [3:23:39<16:53:37,  3.16it/s]
 48%|████▊     | 179473/371472 [3:23:39<16:18:20,  3.27it/s]
 48%|████▊     | 179474/371472 [3:23:40<16:36:52,  3.21it/s]
 48%|████▊     | 179475/371472 [3:23:40<16:03:18,  3.32it/s]
 48%|████▊     | 179476/371472 [3:23:40<16:49:50,  3.17it/s]
 48%|████▊     | 179477/371472 [3:23:41<16:18:45,  3.27it/s]
 48%|████▊     | 179478/371472 [3:23:41<15:42:56,  3.39it/s]
 48%|████▊     | 179479/371472 [3:23:41<15:29:18,  3.44it/s]
 48%|████▊     | 179480/371472 [3:23:41<15:10:17,  3.52it/s]
                                                            
{'loss': 2.9846, 'learning_rate': 5.654075718071926e-07, 'epoch': 7.73}
+
 48%|████▊     | 179480/371472 [3:23:41<15:10:17,  3.52it/s]
 48%|████▊     | 179481/371472 [3:23:42<15:17:21,  3.49it/s]
 48%|████▊     | 179482/371472 [3:23:42<15:22:37,  3.47it/s]
 48%|████▊     | 179483/371472 [3:23:42<15:53:37,  3.36it/s]
 48%|████▊     | 179484/371472 [3:23:43<15:50:50,  3.37it/s]
 48%|████▊     | 179485/371472 [3:23:43<16:15:47,  3.28it/s]
 48%|████▊     | 179486/371472 [3:23:43<16:14:51,  3.28it/s]
 48%|████▊     | 179487/371472 [3:23:44<16:54:51,  3.15it/s]
 48%|████▊     | 179488/371472 [3:23:44<17:02:18,  3.13it/s]
 48%|████▊     | 179489/371472 [3:23:44<17:29:09,  3.05it/s]
 48%|████▊     | 179490/371472 [3:23:45<17:00:09,  3.14it/s]
 48%|████▊     | 179491/371472 [3:23:45<16:30:52,  3.23it/s]
 48%|████▊     | 179492/371472 [3:23:45<16:49:13,  3.17it/s]
 48%|████▊     | 179493/371472 [3:23:46<16:56:31,  3.15it/s]
 48%|████▊     | 179494/371472 [3:23:46<16:33:34,  3.22it/s]
 48%|████▊     | 179495/371472 [3:23:46<16:15:09,  3.28it/s]
 48%|████▊     | 179496/371472 [3:23:46<16:00:22,  3.33it/s]
 48%|████▊     | 179497/371472 [3:23:47<16:10:01,  3.30it/s]
 48%|████▊     | 179498/371472 [3:23:47<16:10:01,  3.30it/s]
 48%|████▊     | 179499/371472 [3:23:47<15:49:20,  3.37it/s]
 48%|████▊     | 179500/371472 [3:23:48<17:22:42,  3.07it/s]
                                                            
{'loss': 2.8899, 'learning_rate': 5.653590898317136e-07, 'epoch': 7.73}
+
 48%|████▊     | 179500/371472 [3:23:48<17:22:42,  3.07it/s]
 48%|████▊     | 179501/371472 [3:23:48<17:03:22,  3.13it/s]
 48%|████▊     | 179502/371472 [3:23:48<16:55:53,  3.15it/s]
 48%|████▊     | 179503/371472 [3:23:49<16:31:21,  3.23it/s]
 48%|████▊     | 179504/371472 [3:23:49<16:00:53,  3.33it/s]
 48%|████▊     | 179505/371472 [3:23:49<15:47:57,  3.38it/s]
 48%|████▊     | 179506/371472 [3:23:49<15:43:10,  3.39it/s]
 48%|████▊     | 179507/371472 [3:23:50<16:20:03,  3.26it/s]
 48%|████▊     | 179508/371472 [3:23:50<15:38:03,  3.41it/s]
 48%|████▊     | 179509/371472 [3:23:50<16:24:13,  3.25it/s]
 48%|████▊     | 179510/371472 [3:23:51<15:56:47,  3.34it/s]
 48%|████▊     | 179511/371472 [3:23:51<15:56:29,  3.34it/s]
 48%|████▊     | 179512/371472 [3:23:51<15:41:07,  3.40it/s]
 48%|████▊     | 179513/371472 [3:23:52<15:37:06,  3.41it/s]
 48%|████▊     | 179514/371472 [3:23:52<15:32:01,  3.43it/s]
 48%|████▊     | 179515/371472 [3:23:52<15:31:52,  3.43it/s]
 48%|████▊     | 179516/371472 [3:23:52<15:56:03,  3.35it/s]
 48%|████▊     | 179517/371472 [3:23:53<16:02:58,  3.32it/s]
 48%|████▊     | 179518/371472 [3:23:53<15:43:34,  3.39it/s]
 48%|████▊     | 179519/371472 [3:23:53<16:11:36,  3.29it/s]
 48%|████▊     | 179520/371472 [3:23:54<16:00:15,  3.33it/s]
                                                            
{'loss': 2.9043, 'learning_rate': 5.653106078562346e-07, 'epoch': 7.73}
+
 48%|████▊     | 179520/371472 [3:23:54<16:00:15,  3.33it/s]
 48%|████▊     | 179521/371472 [3:23:54<15:50:55,  3.36it/s]
 48%|████▊     | 179522/371472 [3:23:54<16:23:37,  3.25it/s]
 48%|████▊     | 179523/371472 [3:23:55<16:13:21,  3.29it/s]
 48%|████▊     | 179524/371472 [3:23:55<16:05:48,  3.31it/s]
 48%|████▊     | 179525/371472 [3:23:55<16:42:41,  3.19it/s]
 48%|████▊     | 179526/371472 [3:23:55<16:12:57,  3.29it/s]
 48%|████▊     | 179527/371472 [3:23:56<16:42:48,  3.19it/s]
 48%|████▊     | 179528/371472 [3:23:56<16:13:51,  3.28it/s]
 48%|████▊     | 179529/371472 [3:23:56<16:21:06,  3.26it/s]
 48%|████▊     | 179530/371472 [3:23:57<16:04:19,  3.32it/s]
 48%|████▊     | 179531/371472 [3:23:57<16:01:31,  3.33it/s]
 48%|████▊     | 179532/371472 [3:23:57<15:57:04,  3.34it/s]
 48%|████▊     | 179533/371472 [3:23:58<16:49:34,  3.17it/s]
 48%|████▊     | 179534/371472 [3:23:58<16:51:27,  3.16it/s]
 48%|████▊     | 179535/371472 [3:23:58<17:02:36,  3.13it/s]
 48%|████▊     | 179536/371472 [3:23:59<16:53:31,  3.16it/s]
 48%|████▊     | 179537/371472 [3:23:59<16:33:58,  3.22it/s]
 48%|████▊     | 179538/371472 [3:23:59<16:57:24,  3.14it/s]
 48%|████▊     | 179539/371472 [3:24:00<17:10:01,  3.11it/s]
 48%|████▊     | 179540/371472 [3:24:00<17:22:25,  3.07it/s]
                                                            
{'loss': 2.7846, 'learning_rate': 5.652621258807559e-07, 'epoch': 7.73}
+
 48%|████▊     | 179540/371472 [3:24:00<17:22:25,  3.07it/s]
 48%|████▊     | 179541/371472 [3:24:00<16:41:21,  3.19it/s]
 48%|████▊     | 179542/371472 [3:24:00<16:15:12,  3.28it/s]
 48%|████▊     | 179543/371472 [3:24:01<15:51:49,  3.36it/s]
 48%|████▊     | 179544/371472 [3:24:01<17:30:24,  3.05it/s]
 48%|████▊     | 179545/371472 [3:24:01<17:03:29,  3.13it/s]
 48%|████▊     | 179546/371472 [3:24:02<16:17:55,  3.27it/s]
 48%|████▊     | 179547/371472 [3:24:02<16:23:18,  3.25it/s]
 48%|████▊     | 179548/371472 [3:24:02<16:50:42,  3.16it/s]
 48%|████▊     | 179549/371472 [3:24:03<16:40:51,  3.20it/s]
 48%|████▊     | 179550/371472 [3:24:03<16:59:16,  3.14it/s]
 48%|████▊     | 179551/371472 [3:24:03<16:34:13,  3.22it/s]
 48%|████▊     | 179552/371472 [3:24:04<17:25:06,  3.06it/s]
 48%|████▊     | 179553/371472 [3:24:04<16:50:55,  3.16it/s]
 48%|████▊     | 179554/371472 [3:24:04<16:05:26,  3.31it/s]
 48%|████▊     | 179555/371472 [3:24:05<15:41:12,  3.40it/s]
 48%|████▊     | 179556/371472 [3:24:05<15:35:26,  3.42it/s]
 48%|████▊     | 179557/371472 [3:24:05<15:30:18,  3.44it/s]
 48%|████▊     | 179558/371472 [3:24:05<15:13:18,  3.50it/s]
 48%|████▊     | 179559/371472 [3:24:06<16:10:40,  3.30it/s]
 48%|████▊     | 179560/371472 [3:24:06<16:28:06,  3.24it/s]
                                                            
{'loss': 3.137, 'learning_rate': 5.65213643905277e-07, 'epoch': 7.73}
+
 48%|████▊     | 179560/371472 [3:24:06<16:28:06,  3.24it/s]
 48%|████▊     | 179561/371472 [3:24:06<16:04:56,  3.31it/s]
 48%|████▊     | 179562/371472 [3:24:07<16:01:31,  3.33it/s]
 48%|████▊     | 179563/371472 [3:24:07<15:53:48,  3.35it/s]
 48%|████▊     | 179564/371472 [3:24:07<16:25:31,  3.25it/s]
 48%|████▊     | 179565/371472 [3:24:08<16:09:25,  3.30it/s]
 48%|████▊     | 179566/371472 [3:24:08<16:23:33,  3.25it/s]
 48%|████▊     | 179567/371472 [3:24:08<16:35:06,  3.21it/s]
 48%|████▊     | 179568/371472 [3:24:08<16:30:07,  3.23it/s]
 48%|████▊     | 179569/371472 [3:24:09<16:46:10,  3.18it/s]
 48%|████▊     | 179570/371472 [3:24:09<16:17:48,  3.27it/s]
 48%|████▊     | 179571/371472 [3:24:09<17:04:28,  3.12it/s]
 48%|████▊     | 179572/371472 [3:24:10<16:55:30,  3.15it/s]
 48%|████▊     | 179573/371472 [3:24:10<16:45:28,  3.18it/s]
 48%|████▊     | 179574/371472 [3:24:10<16:14:25,  3.28it/s]
 48%|████▊     | 179575/371472 [3:24:11<16:37:07,  3.21it/s]
 48%|████▊     | 179576/371472 [3:24:11<16:20:57,  3.26it/s]
 48%|████▊     | 179577/371472 [3:24:11<16:27:13,  3.24it/s]
 48%|████▊     | 179578/371472 [3:24:12<16:25:39,  3.24it/s]
 48%|████▊     | 179579/371472 [3:24:12<15:59:54,  3.33it/s]
 48%|████▊     | 179580/371472 [3:24:12<16:50:30,  3.16it/s]
                                                            
{'loss': 2.6918, 'learning_rate': 5.651651619297981e-07, 'epoch': 7.73}
+
 48%|████▊     | 179580/371472 [3:24:12<16:50:30,  3.16it/s]
 48%|████▊     | 179581/371472 [3:24:13<16:31:55,  3.22it/s]
 48%|████▊     | 179582/371472 [3:24:13<16:10:53,  3.29it/s]
 48%|████▊     | 179583/371472 [3:24:13<16:01:21,  3.33it/s]
 48%|████▊     | 179584/371472 [3:24:13<15:26:35,  3.45it/s]
 48%|████▊     | 179585/371472 [3:24:14<16:37:25,  3.21it/s]
 48%|████▊     | 179586/371472 [3:24:14<17:12:45,  3.10it/s]
 48%|████▊     | 179587/371472 [3:24:14<17:39:29,  3.02it/s]
 48%|████▊     | 179588/371472 [3:24:15<19:12:27,  2.77it/s]
 48%|████▊     | 179589/371472 [3:24:15<18:31:25,  2.88it/s]
 48%|████▊     | 179590/371472 [3:24:15<17:45:25,  3.00it/s]
 48%|████▊     | 179591/371472 [3:24:16<17:08:41,  3.11it/s]
 48%|████▊     | 179592/371472 [3:24:16<16:47:47,  3.17it/s]
 48%|████▊     | 179593/371472 [3:24:16<16:01:32,  3.33it/s]
 48%|████▊     | 179594/371472 [3:24:17<16:00:08,  3.33it/s]
 48%|████▊     | 179595/371472 [3:24:17<15:40:22,  3.40it/s]
 48%|████▊     | 179596/371472 [3:24:17<15:36:23,  3.42it/s]
 48%|████▊     | 179597/371472 [3:24:18<15:47:47,  3.37it/s]
 48%|████▊     | 179598/371472 [3:24:18<16:02:07,  3.32it/s]
 48%|████▊     | 179599/371472 [3:24:18<16:51:36,  3.16it/s]
 48%|████▊     | 179600/371472 [3:24:18<16:18:04,  3.27it/s]
                                                            
{'loss': 3.0329, 'learning_rate': 5.651166799543191e-07, 'epoch': 7.74}
+
 48%|████▊     | 179600/371472 [3:24:18<16:18:04,  3.27it/s]
 48%|████▊     | 179601/371472 [3:24:19<17:18:46,  3.08it/s]
 48%|████▊     | 179602/371472 [3:24:19<16:22:40,  3.25it/s]
 48%|████▊     | 179603/371472 [3:24:19<16:01:45,  3.32it/s]
 48%|████▊     | 179604/371472 [3:24:20<15:47:09,  3.38it/s]
 48%|████▊     | 179605/371472 [3:24:20<16:55:50,  3.15it/s]
 48%|████▊     | 179606/371472 [3:24:20<16:51:03,  3.16it/s]
 48%|████▊     | 179607/371472 [3:24:21<16:13:51,  3.28it/s]
 48%|████▊     | 179608/371472 [3:24:21<16:12:32,  3.29it/s]
 48%|████▊     | 179609/371472 [3:24:21<16:41:22,  3.19it/s]
 48%|████▊     | 179610/371472 [3:24:22<16:42:55,  3.19it/s]
 48%|████▊     | 179611/371472 [3:24:22<16:43:45,  3.19it/s]
 48%|████▊     | 179612/371472 [3:24:22<16:27:01,  3.24it/s]
 48%|████▊     | 179613/371472 [3:24:22<16:34:16,  3.22it/s]
 48%|████▊     | 179614/371472 [3:24:23<16:28:02,  3.24it/s]
 48%|████▊     | 179615/371472 [3:24:23<16:04:09,  3.32it/s]
 48%|████▊     | 179616/371472 [3:24:23<15:46:33,  3.38it/s]
 48%|████▊     | 179617/371472 [3:24:24<16:01:29,  3.33it/s]
 48%|████▊     | 179618/371472 [3:24:24<15:47:59,  3.37it/s]
 48%|████▊     | 179619/371472 [3:24:24<16:40:04,  3.20it/s]
 48%|████▊     | 179620/371472 [3:24:25<16:25:56,  3.24it/s]
                                                            
{'loss': 2.88, 'learning_rate': 5.650681979788403e-07, 'epoch': 7.74}
+
 48%|████▊     | 179620/371472 [3:24:25<16:25:56,  3.24it/s]
 48%|████▊     | 179621/371472 [3:24:25<17:09:08,  3.11it/s]
 48%|████▊     | 179622/371472 [3:24:25<17:51:11,  2.99it/s]
 48%|████▊     | 179623/371472 [3:24:26<17:03:15,  3.12it/s]
 48%|████▊     | 179624/371472 [3:24:26<16:25:43,  3.24it/s]
 48%|████▊     | 179625/371472 [3:24:26<16:35:02,  3.21it/s]
 48%|████▊     | 179626/371472 [3:24:27<17:19:46,  3.08it/s]
 48%|████▊     | 179627/371472 [3:24:27<17:46:10,  3.00it/s]
 48%|████▊     | 179628/371472 [3:24:27<17:08:28,  3.11it/s]
 48%|████▊     | 179629/371472 [3:24:28<18:24:05,  2.90it/s]
 48%|████▊     | 179630/371472 [3:24:28<18:43:35,  2.85it/s]
 48%|████▊     | 179631/371472 [3:24:28<18:02:16,  2.95it/s]
 48%|████▊     | 179632/371472 [3:24:29<17:49:45,  2.99it/s]
 48%|████▊     | 179633/371472 [3:24:29<18:06:46,  2.94it/s]
 48%|████▊     | 179634/371472 [3:24:29<17:16:12,  3.09it/s]
 48%|████▊     | 179635/371472 [3:24:30<16:47:48,  3.17it/s]
 48%|████▊     | 179636/371472 [3:24:30<16:26:31,  3.24it/s]
 48%|████▊     | 179637/371472 [3:24:30<17:00:37,  3.13it/s]
 48%|████▊     | 179638/371472 [3:24:31<17:07:11,  3.11it/s]
 48%|████▊     | 179639/371472 [3:24:31<17:26:42,  3.05it/s]
 48%|████▊     | 179640/371472 [3:24:31<16:44:32,  3.18it/s]
                                                            
{'loss': 2.7716, 'learning_rate': 5.650197160033615e-07, 'epoch': 7.74}
+
 48%|████▊     | 179640/371472 [3:24:31<16:44:32,  3.18it/s]
 48%|████▊     | 179641/371472 [3:24:31<16:40:16,  3.20it/s]
 48%|████▊     | 179642/371472 [3:24:32<16:06:58,  3.31it/s]
 48%|████▊     | 179643/371472 [3:24:32<15:40:23,  3.40it/s]
 48%|████▊     | 179644/371472 [3:24:32<15:38:49,  3.41it/s]
 48%|████▊     | 179645/371472 [3:24:33<16:01:44,  3.32it/s]
 48%|████▊     | 179646/371472 [3:24:33<16:13:24,  3.28it/s]
 48%|████▊     | 179647/371472 [3:24:33<15:43:12,  3.39it/s]
 48%|████▊     | 179648/371472 [3:24:33<15:47:01,  3.38it/s]
 48%|████▊     | 179649/371472 [3:24:34<15:24:42,  3.46it/s]
 48%|████▊     | 179650/371472 [3:24:34<15:24:30,  3.46it/s]
 48%|████▊     | 179651/371472 [3:24:34<15:11:58,  3.51it/s]
 48%|████▊     | 179652/371472 [3:24:35<14:51:54,  3.58it/s]
 48%|████▊     | 179653/371472 [3:24:35<15:33:15,  3.43it/s]
 48%|████▊     | 179654/371472 [3:24:35<15:53:59,  3.35it/s]
 48%|████▊     | 179655/371472 [3:24:35<15:16:44,  3.49it/s]
 48%|████▊     | 179656/371472 [3:24:36<15:03:46,  3.54it/s]
 48%|████▊     | 179657/371472 [3:24:36<15:11:56,  3.51it/s]
 48%|████▊     | 179658/371472 [3:24:36<15:11:20,  3.51it/s]
 48%|████▊     | 179659/371472 [3:24:37<15:33:57,  3.42it/s]
 48%|████▊     | 179660/371472 [3:24:37<16:47:55,  3.17it/s]
                                                            
{'loss': 2.9868, 'learning_rate': 5.649712340278826e-07, 'epoch': 7.74}
+
 48%|████▊     | 179660/371472 [3:24:37<16:47:55,  3.17it/s]
 48%|████▊     | 179661/371472 [3:24:37<16:55:20,  3.15it/s]
 48%|████▊     | 179662/371472 [3:24:38<17:39:01,  3.02it/s]
 48%|████▊     | 179663/371472 [3:24:38<17:11:09,  3.10it/s]
 48%|████▊     | 179664/371472 [3:24:38<16:41:56,  3.19it/s]
 48%|████▊     | 179665/371472 [3:24:39<16:20:02,  3.26it/s]
 48%|████▊     | 179666/371472 [3:24:39<16:53:43,  3.15it/s]
 48%|████▊     | 179667/371472 [3:24:39<16:40:02,  3.20it/s]
 48%|████▊     | 179668/371472 [3:24:40<16:22:25,  3.25it/s]
 48%|████▊     | 179669/371472 [3:24:40<15:57:41,  3.34it/s]
 48%|████▊     | 179670/371472 [3:24:40<15:45:23,  3.38it/s]
 48%|████▊     | 179671/371472 [3:24:40<15:21:45,  3.47it/s]
 48%|████▊     | 179672/371472 [3:24:41<16:57:18,  3.14it/s]
 48%|████▊     | 179673/371472 [3:24:41<16:17:01,  3.27it/s]
 48%|████▊     | 179674/371472 [3:24:41<16:19:17,  3.26it/s]
 48%|████▊     | 179675/371472 [3:24:42<16:19:34,  3.26it/s]
 48%|████▊     | 179676/371472 [3:24:42<16:46:23,  3.18it/s]
 48%|████▊     | 179677/371472 [3:24:42<16:10:33,  3.29it/s]
 48%|████▊     | 179678/371472 [3:24:43<15:50:38,  3.36it/s]
 48%|████▊     | 179679/371472 [3:24:43<15:34:39,  3.42it/s]
 48%|████▊     | 179680/371472 [3:24:43<16:09:46,  3.30it/s]
                                                            
{'loss': 2.8133, 'learning_rate': 5.649227520524036e-07, 'epoch': 7.74}
+
 48%|████▊     | 179680/371472 [3:24:43<16:09:46,  3.30it/s]
 48%|████▊     | 179681/371472 [3:24:43<15:59:40,  3.33it/s]
 48%|████▊     | 179682/371472 [3:24:44<15:37:08,  3.41it/s]
 48%|████▊     | 179683/371472 [3:24:44<15:21:32,  3.47it/s]
 48%|████▊     | 179684/371472 [3:24:44<16:34:11,  3.22it/s]
 48%|████▊     | 179685/371472 [3:24:45<16:44:11,  3.18it/s]
 48%|████▊     | 179686/371472 [3:24:45<16:10:25,  3.29it/s]
 48%|████▊     | 179687/371472 [3:24:45<15:52:28,  3.36it/s]
 48%|████▊     | 179688/371472 [3:24:46<15:35:24,  3.42it/s]
 48%|████▊     | 179689/371472 [3:24:46<15:39:52,  3.40it/s]
 48%|████▊     | 179690/371472 [3:24:46<15:49:04,  3.37it/s]
 48%|████▊     | 179691/371472 [3:24:46<16:35:29,  3.21it/s]
 48%|████▊     | 179692/371472 [3:24:47<15:56:16,  3.34it/s]
 48%|████▊     | 179693/371472 [3:24:47<16:01:17,  3.33it/s]
 48%|████▊     | 179694/371472 [3:24:47<16:30:30,  3.23it/s]
 48%|████▊     | 179695/371472 [3:24:48<16:44:07,  3.18it/s]
 48%|████▊     | 179696/371472 [3:24:48<16:25:39,  3.24it/s]
 48%|████▊     | 179697/371472 [3:24:48<17:35:08,  3.03it/s]
 48%|████▊     | 179698/371472 [3:24:49<17:23:21,  3.06it/s]
 48%|████▊     | 179699/371472 [3:24:49<17:50:04,  2.99it/s]
 48%|████▊     | 179700/371472 [3:24:49<17:10:42,  3.10it/s]
                                                            
{'loss': 3.0493, 'learning_rate': 5.648742700769247e-07, 'epoch': 7.74}
+
 48%|████▊     | 179700/371472 [3:24:49<17:10:42,  3.10it/s]
 48%|████▊     | 179701/371472 [3:24:50<16:38:59,  3.20it/s]
 48%|████▊     | 179702/371472 [3:24:50<16:34:36,  3.21it/s]
 48%|████▊     | 179703/371472 [3:24:50<16:13:12,  3.28it/s]
 48%|████▊     | 179704/371472 [3:24:51<16:10:19,  3.29it/s]
 48%|████▊     | 179705/371472 [3:24:51<16:02:33,  3.32it/s]
 48%|████▊     | 179706/371472 [3:24:51<16:22:55,  3.25it/s]
 48%|████▊     | 179707/371472 [3:24:51<16:07:56,  3.30it/s]
 48%|████▊     | 179708/371472 [3:24:52<16:06:19,  3.31it/s]
 48%|████▊     | 179709/371472 [3:24:52<16:30:04,  3.23it/s]
 48%|████▊     | 179710/371472 [3:24:52<16:33:43,  3.22it/s]
 48%|████▊     | 179711/371472 [3:24:53<16:38:32,  3.20it/s]
 48%|████▊     | 179712/371472 [3:24:53<16:21:25,  3.26it/s]
 48%|████▊     | 179713/371472 [3:24:53<16:09:58,  3.29it/s]
 48%|████▊     | 179714/371472 [3:24:54<16:05:11,  3.31it/s]
 48%|████▊     | 179715/371472 [3:24:54<15:51:20,  3.36it/s]
 48%|████▊     | 179716/371472 [3:24:54<15:34:26,  3.42it/s]
 48%|████▊     | 179717/371472 [3:24:54<16:02:03,  3.32it/s]
 48%|████▊     | 179718/371472 [3:24:55<16:28:18,  3.23it/s]
 48%|████▊     | 179719/371472 [3:24:55<16:24:41,  3.25it/s]
 48%|████▊     | 179720/371472 [3:24:55<16:23:26,  3.25it/s]
                                                            
{'loss': 2.7209, 'learning_rate': 5.648257881014459e-07, 'epoch': 7.74}
+
 48%|████▊     | 179720/371472 [3:24:55<16:23:26,  3.25it/s]
 48%|████▊     | 179721/371472 [3:24:56<17:33:27,  3.03it/s]
 48%|████▊     | 179722/371472 [3:24:56<17:09:54,  3.10it/s]
 48%|████▊     | 179723/371472 [3:24:56<17:16:39,  3.08it/s]
 48%|████▊     | 179724/371472 [3:24:57<17:50:33,  2.99it/s]
 48%|████▊     | 179725/371472 [3:24:57<17:35:31,  3.03it/s]
 48%|████▊     | 179726/371472 [3:24:57<18:18:34,  2.91it/s]
 48%|████▊     | 179727/371472 [3:24:58<18:34:10,  2.87it/s]
 48%|████▊     | 179728/371472 [3:24:58<17:22:43,  3.06it/s]
 48%|████▊     | 179729/371472 [3:24:58<16:46:50,  3.17it/s]
 48%|████▊     | 179730/371472 [3:24:59<16:25:14,  3.24it/s]
 48%|████▊     | 179731/371472 [3:24:59<16:21:29,  3.26it/s]
 48%|████▊     | 179732/371472 [3:24:59<15:55:09,  3.35it/s]
 48%|████▊     | 179733/371472 [3:25:00<15:55:05,  3.35it/s]
 48%|████▊     | 179734/371472 [3:25:00<15:47:36,  3.37it/s]
 48%|████▊     | 179735/371472 [3:25:00<15:35:00,  3.42it/s]
 48%|████▊     | 179736/371472 [3:25:00<16:13:19,  3.28it/s]
 48%|████▊     | 179737/371472 [3:25:01<16:03:57,  3.32it/s]
 48%|████▊     | 179738/371472 [3:25:01<17:30:00,  3.04it/s]
 48%|████▊     | 179739/371472 [3:25:02<17:29:45,  3.04it/s]
 48%|████▊     | 179740/371472 [3:25:02<17:25:00,  3.06it/s]
                                                            
{'loss': 2.7858, 'learning_rate': 5.64777306125967e-07, 'epoch': 7.74}
+
 48%|████▊     | 179740/371472 [3:25:02<17:25:00,  3.06it/s]
 48%|████▊     | 179741/371472 [3:25:02<20:07:10,  2.65it/s]
 48%|████▊     | 179742/371472 [3:25:03<19:01:00,  2.80it/s]
 48%|████▊     | 179743/371472 [3:25:03<18:54:59,  2.82it/s]
 48%|████▊     | 179744/371472 [3:25:03<17:36:12,  3.03it/s]
 48%|████▊     | 179745/371472 [3:25:04<17:09:22,  3.10it/s]
 48%|████▊     | 179746/371472 [3:25:04<16:28:24,  3.23it/s]
 48%|████▊     | 179747/371472 [3:25:04<16:32:24,  3.22it/s]
 48%|████▊     | 179748/371472 [3:25:04<16:18:59,  3.26it/s]
 48%|████▊     | 179749/371472 [3:25:05<16:16:59,  3.27it/s]
 48%|████▊     | 179750/371472 [3:25:05<15:55:42,  3.34it/s]
 48%|████▊     | 179751/371472 [3:25:05<16:39:36,  3.20it/s]
 48%|████▊     | 179752/371472 [3:25:06<15:50:04,  3.36it/s]
 48%|████▊     | 179753/371472 [3:25:06<17:07:18,  3.11it/s]
 48%|████▊     | 179754/371472 [3:25:06<17:28:31,  3.05it/s]
 48%|████▊     | 179755/371472 [3:25:07<17:04:15,  3.12it/s]
 48%|████▊     | 179756/371472 [3:25:07<16:33:26,  3.22it/s]
 48%|████▊     | 179757/371472 [3:25:07<15:51:43,  3.36it/s]
 48%|████▊     | 179758/371472 [3:25:08<15:52:48,  3.35it/s]
 48%|████▊     | 179759/371472 [3:25:08<15:46:13,  3.38it/s]
 48%|████▊     | 179760/371472 [3:25:08<15:43:40,  3.39it/s]
                                                            
{'loss': 2.9878, 'learning_rate': 5.647288241504879e-07, 'epoch': 7.74}
+
 48%|████▊     | 179760/371472 [3:25:08<15:43:40,  3.39it/s]
 48%|████▊     | 179761/371472 [3:25:08<16:05:55,  3.31it/s]
 48%|████▊     | 179762/371472 [3:25:09<16:05:57,  3.31it/s]
 48%|████▊     | 179763/371472 [3:25:09<16:45:33,  3.18it/s]
 48%|████▊     | 179764/371472 [3:25:09<16:49:36,  3.16it/s]
 48%|████▊     | 179765/371472 [3:25:10<15:57:16,  3.34it/s]
 48%|████▊     | 179766/371472 [3:25:10<15:56:48,  3.34it/s]
 48%|████▊     | 179767/371472 [3:25:10<15:45:33,  3.38it/s]
 48%|████▊     | 179768/371472 [3:25:11<15:22:47,  3.46it/s]
 48%|████▊     | 179769/371472 [3:25:11<15:49:23,  3.37it/s]
 48%|████▊     | 179770/371472 [3:25:11<15:23:42,  3.46it/s]
 48%|████▊     | 179771/371472 [3:25:11<15:12:13,  3.50it/s]
 48%|████▊     | 179772/371472 [3:25:12<15:23:07,  3.46it/s]
 48%|████▊     | 179773/371472 [3:25:12<15:30:00,  3.44it/s]
 48%|████▊     | 179774/371472 [3:25:12<15:35:14,  3.42it/s]
 48%|████▊     | 179775/371472 [3:25:13<16:43:16,  3.18it/s]
 48%|████▊     | 179776/371472 [3:25:13<16:55:29,  3.15it/s]
 48%|████▊     | 179777/371472 [3:25:13<16:37:18,  3.20it/s]
 48%|████▊     | 179778/371472 [3:25:14<16:17:56,  3.27it/s]
 48%|████▊     | 179779/371472 [3:25:14<16:12:31,  3.29it/s]
 48%|████▊     | 179780/371472 [3:25:14<16:23:35,  3.25it/s]
                                                            
{'loss': 2.9763, 'learning_rate': 5.646803421750091e-07, 'epoch': 7.74}
+
 48%|████▊     | 179780/371472 [3:25:14<16:23:35,  3.25it/s]
 48%|████▊     | 179781/371472 [3:25:14<16:22:47,  3.25it/s]
 48%|████▊     | 179782/371472 [3:25:15<16:07:03,  3.30it/s]
 48%|████▊     | 179783/371472 [3:25:15<18:49:09,  2.83it/s]
 48%|████▊     | 179784/371472 [3:25:16<17:36:22,  3.02it/s]
 48%|████▊     | 179785/371472 [3:25:16<17:18:04,  3.08it/s]
 48%|████▊     | 179786/371472 [3:25:16<17:04:45,  3.12it/s]
 48%|████▊     | 179787/371472 [3:25:16<16:32:48,  3.22it/s]
 48%|████▊     | 179788/371472 [3:25:17<16:16:42,  3.27it/s]
 48%|████▊     | 179789/371472 [3:25:17<16:23:47,  3.25it/s]
 48%|████▊     | 179790/371472 [3:25:17<18:12:23,  2.92it/s]
 48%|████▊     | 179791/371472 [3:25:18<17:33:04,  3.03it/s]
 48%|████▊     | 179792/371472 [3:25:18<17:16:13,  3.08it/s]
 48%|████▊     | 179793/371472 [3:25:18<16:39:23,  3.20it/s]
 48%|████▊     | 179794/371472 [3:25:19<16:00:08,  3.33it/s]
 48%|████▊     | 179795/371472 [3:25:19<15:35:14,  3.42it/s]
 48%|████▊     | 179796/371472 [3:25:19<15:36:49,  3.41it/s]
 48%|████▊     | 179797/371472 [3:25:20<16:31:47,  3.22it/s]
 48%|████▊     | 179798/371472 [3:25:20<16:08:15,  3.30it/s]
 48%|████▊     | 179799/371472 [3:25:20<15:55:50,  3.34it/s]
 48%|████▊     | 179800/371472 [3:25:20<15:59:48,  3.33it/s]
                                                            
{'loss': 2.9738, 'learning_rate': 5.646318601995303e-07, 'epoch': 7.74}
+
 48%|████▊     | 179800/371472 [3:25:20<15:59:48,  3.33it/s]
 48%|████▊     | 179801/371472 [3:25:21<16:20:31,  3.26it/s]
 48%|████▊     | 179802/371472 [3:25:21<15:38:09,  3.41it/s]
 48%|████▊     | 179803/371472 [3:25:21<16:07:23,  3.30it/s]
 48%|████▊     | 179804/371472 [3:25:22<15:50:47,  3.36it/s]
 48%|████▊     | 179805/371472 [3:25:22<15:41:19,  3.39it/s]
 48%|████▊     | 179806/371472 [3:25:22<15:55:51,  3.34it/s]
 48%|████▊     | 179807/371472 [3:25:23<16:41:18,  3.19it/s]
 48%|████▊     | 179808/371472 [3:25:23<16:12:15,  3.29it/s]
 48%|████▊     | 179809/371472 [3:25:23<16:11:16,  3.29it/s]
 48%|████▊     | 179810/371472 [3:25:23<15:58:01,  3.33it/s]
 48%|████▊     | 179811/371472 [3:25:24<15:41:31,  3.39it/s]
 48%|████▊     | 179812/371472 [3:25:24<15:26:24,  3.45it/s]
 48%|████▊     | 179813/371472 [3:25:24<15:16:30,  3.49it/s]
 48%|████▊     | 179814/371472 [3:25:25<16:27:45,  3.23it/s]
 48%|████▊     | 179815/371472 [3:25:25<16:05:56,  3.31it/s]
 48%|████▊     | 179816/371472 [3:25:25<15:54:05,  3.35it/s]
 48%|████▊     | 179817/371472 [3:25:26<15:49:43,  3.36it/s]
 48%|████▊     | 179818/371472 [3:25:26<15:29:24,  3.44it/s]
 48%|████▊     | 179819/371472 [3:25:26<15:55:53,  3.34it/s]
 48%|████▊     | 179820/371472 [3:25:26<16:06:45,  3.30it/s]
                                                            
{'loss': 2.7971, 'learning_rate': 5.645833782240513e-07, 'epoch': 7.75}
+
 48%|████▊     | 179820/371472 [3:25:26<16:06:45,  3.30it/s]
 48%|████▊     | 179821/371472 [3:25:27<15:46:08,  3.38it/s]
 48%|████▊     | 179822/371472 [3:25:27<15:52:53,  3.35it/s]
 48%|████▊     | 179823/371472 [3:25:27<15:57:03,  3.34it/s]
 48%|████▊     | 179824/371472 [3:25:28<17:08:31,  3.11it/s]
 48%|████▊     | 179825/371472 [3:25:28<16:41:20,  3.19it/s]
 48%|████▊     | 179826/371472 [3:25:28<15:55:27,  3.34it/s]
 48%|████▊     | 179827/371472 [3:25:29<15:47:51,  3.37it/s]
 48%|████▊     | 179828/371472 [3:25:29<16:07:28,  3.30it/s]
 48%|████▊     | 179829/371472 [3:25:29<15:50:11,  3.36it/s]
 48%|████▊     | 179830/371472 [3:25:29<15:27:42,  3.44it/s]
 48%|████▊     | 179831/371472 [3:25:30<15:36:02,  3.41it/s]
 48%|████▊     | 179832/371472 [3:25:30<15:28:50,  3.44it/s]
 48%|████▊     | 179833/371472 [3:25:30<15:14:11,  3.49it/s]
 48%|████▊     | 179834/371472 [3:25:31<17:06:39,  3.11it/s]
 48%|████▊     | 179835/371472 [3:25:31<18:05:57,  2.94it/s]
 48%|████▊     | 179836/371472 [3:25:31<17:40:17,  3.01it/s]
 48%|████▊     | 179837/371472 [3:25:32<17:13:20,  3.09it/s]
 48%|████▊     | 179838/371472 [3:25:32<17:22:23,  3.06it/s]
 48%|████▊     | 179839/371472 [3:25:32<16:39:36,  3.20it/s]
 48%|████▊     | 179840/371472 [3:25:33<16:49:35,  3.16it/s]
                                                            
{'loss': 2.8912, 'learning_rate': 5.645348962485724e-07, 'epoch': 7.75}
+
 48%|████▊     | 179840/371472 [3:25:33<16:49:35,  3.16it/s]
 48%|████▊     | 179841/371472 [3:25:33<17:03:06,  3.12it/s]
 48%|████▊     | 179842/371472 [3:25:33<16:37:28,  3.20it/s]
 48%|████▊     | 179843/371472 [3:25:34<16:51:25,  3.16it/s]
 48%|████▊     | 179844/371472 [3:25:34<16:34:23,  3.21it/s]
 48%|████▊     | 179845/371472 [3:25:34<16:43:02,  3.18it/s]
 48%|████▊     | 179846/371472 [3:25:34<16:45:51,  3.18it/s]
 48%|████▊     | 179847/371472 [3:25:35<16:28:42,  3.23it/s]
 48%|████▊     | 179848/371472 [3:25:35<16:40:14,  3.19it/s]
 48%|████▊     | 179849/371472 [3:25:35<16:20:18,  3.26it/s]
 48%|████▊     | 179850/371472 [3:25:36<16:15:51,  3.27it/s]
 48%|████▊     | 179851/371472 [3:25:36<16:00:42,  3.32it/s]
 48%|████▊     | 179852/371472 [3:25:36<16:01:35,  3.32it/s]
 48%|████▊     | 179853/371472 [3:25:37<15:48:19,  3.37it/s]
 48%|████▊     | 179854/371472 [3:25:37<15:41:18,  3.39it/s]
 48%|████▊     | 179855/371472 [3:25:37<15:35:00,  3.42it/s]
 48%|████▊     | 179856/371472 [3:25:37<15:32:23,  3.43it/s]
 48%|████▊     | 179857/371472 [3:25:38<16:02:26,  3.32it/s]
 48%|████▊     | 179858/371472 [3:25:38<16:39:58,  3.19it/s]
 48%|████▊     | 179859/371472 [3:25:38<17:06:14,  3.11it/s]
 48%|████▊     | 179860/371472 [3:25:39<16:44:10,  3.18it/s]
                                                            
{'loss': 2.9335, 'learning_rate': 5.644864142730936e-07, 'epoch': 7.75}
+
 48%|████▊     | 179860/371472 [3:25:39<16:44:10,  3.18it/s]
 48%|████▊     | 179861/371472 [3:25:39<16:53:13,  3.15it/s]
 48%|████▊     | 179862/371472 [3:25:39<17:13:53,  3.09it/s]
 48%|████▊     | 179863/371472 [3:25:40<17:07:34,  3.11it/s]
 48%|████▊     | 179864/371472 [3:25:40<16:21:05,  3.25it/s]
 48%|████▊     | 179865/371472 [3:25:40<16:11:40,  3.29it/s]
 48%|████▊     | 179866/371472 [3:25:41<15:42:45,  3.39it/s]
 48%|████▊     | 179867/371472 [3:25:41<15:49:08,  3.36it/s]
 48%|████▊     | 179868/371472 [3:25:41<15:45:47,  3.38it/s]
 48%|████▊     | 179869/371472 [3:25:41<15:30:34,  3.43it/s]
 48%|████▊     | 179870/371472 [3:25:42<15:40:39,  3.39it/s]
 48%|████▊     | 179871/371472 [3:25:42<16:09:26,  3.29it/s]
 48%|████▊     | 179872/371472 [3:25:42<15:37:17,  3.41it/s]
 48%|████▊     | 179873/371472 [3:25:43<15:45:12,  3.38it/s]
 48%|████▊     | 179874/371472 [3:25:43<15:22:16,  3.46it/s]
 48%|████▊     | 179875/371472 [3:25:43<15:08:03,  3.52it/s]
 48%|████▊     | 179876/371472 [3:25:44<16:04:38,  3.31it/s]
 48%|████▊     | 179877/371472 [3:25:44<15:40:13,  3.40it/s]
 48%|████▊     | 179878/371472 [3:25:44<15:32:25,  3.42it/s]
 48%|████▊     | 179879/371472 [3:25:44<15:35:22,  3.41it/s]
 48%|████▊     | 179880/371472 [3:25:45<15:28:26,  3.44it/s]
                                                            
{'loss': 3.0141, 'learning_rate': 5.644379322976146e-07, 'epoch': 7.75}
+
 48%|████▊     | 179880/371472 [3:25:45<15:28:26,  3.44it/s]
 48%|████▊     | 179881/371472 [3:25:45<15:42:46,  3.39it/s]
 48%|████▊     | 179882/371472 [3:25:45<15:38:57,  3.40it/s]
 48%|████▊     | 179883/371472 [3:25:46<15:37:12,  3.41it/s]
 48%|████▊     | 179884/371472 [3:25:46<15:21:37,  3.46it/s]
 48%|████▊     | 179885/371472 [3:25:46<15:02:21,  3.54it/s]
 48%|████▊     | 179886/371472 [3:25:46<15:21:47,  3.46it/s]
 48%|████▊     | 179887/371472 [3:25:47<15:06:06,  3.52it/s]
 48%|████▊     | 179888/371472 [3:25:47<15:09:00,  3.51it/s]
 48%|████▊     | 179889/371472 [3:25:47<16:07:05,  3.30it/s]
 48%|████▊     | 179890/371472 [3:25:48<16:18:44,  3.26it/s]
 48%|████▊     | 179891/371472 [3:25:48<16:29:14,  3.23it/s]
 48%|████▊     | 179892/371472 [3:25:48<16:16:30,  3.27it/s]
 48%|████▊     | 179893/371472 [3:25:49<16:46:39,  3.17it/s]
 48%|████▊     | 179894/371472 [3:25:49<16:12:03,  3.28it/s]
 48%|████▊     | 179895/371472 [3:25:49<16:04:10,  3.31it/s]
 48%|████▊     | 179896/371472 [3:25:49<15:42:12,  3.39it/s]
 48%|████▊     | 179897/371472 [3:25:50<16:39:49,  3.19it/s]
 48%|████▊     | 179898/371472 [3:25:50<16:09:34,  3.29it/s]
 48%|████▊     | 179899/371472 [3:25:50<16:22:22,  3.25it/s]
 48%|████▊     | 179900/371472 [3:25:51<16:12:17,  3.28it/s]
                                                            
{'loss': 2.8723, 'learning_rate': 5.643894503221356e-07, 'epoch': 7.75}
+
 48%|████▊     | 179900/371472 [3:25:51<16:12:17,  3.28it/s]
 48%|████▊     | 179901/371472 [3:25:51<16:31:43,  3.22it/s]
 48%|████▊     | 179902/371472 [3:25:51<16:03:15,  3.31it/s]
 48%|████▊     | 179903/371472 [3:25:52<16:08:50,  3.30it/s]
 48%|████▊     | 179904/371472 [3:25:52<15:53:18,  3.35it/s]
 48%|████▊     | 179905/371472 [3:25:52<15:51:16,  3.36it/s]
 48%|████▊     | 179906/371472 [3:25:52<15:34:24,  3.42it/s]
 48%|████▊     | 179907/371472 [3:25:53<15:15:57,  3.49it/s]
 48%|████▊     | 179908/371472 [3:25:53<15:32:14,  3.42it/s]
 48%|████▊     | 179909/371472 [3:25:53<15:17:03,  3.48it/s]
 48%|████▊     | 179910/371472 [3:25:54<15:59:28,  3.33it/s]
 48%|████▊     | 179911/371472 [3:25:54<15:38:44,  3.40it/s]
 48%|████▊     | 179912/371472 [3:25:54<16:07:05,  3.30it/s]
 48%|████▊     | 179913/371472 [3:25:55<16:31:35,  3.22it/s]
 48%|████▊     | 179914/371472 [3:25:55<15:45:44,  3.38it/s]
 48%|████▊     | 179915/371472 [3:25:55<15:27:02,  3.44it/s]
 48%|████▊     | 179916/371472 [3:25:55<15:27:14,  3.44it/s]
 48%|████▊     | 179917/371472 [3:25:56<15:18:50,  3.47it/s]
 48%|████▊     | 179918/371472 [3:25:56<15:14:11,  3.49it/s]
 48%|████▊     | 179919/371472 [3:25:56<15:51:44,  3.35it/s]
 48%|████▊     | 179920/371472 [3:25:57<15:54:56,  3.34it/s]
                                                            
{'loss': 2.9959, 'learning_rate': 5.643409683466569e-07, 'epoch': 7.75}
+
 48%|████▊     | 179920/371472 [3:25:57<15:54:56,  3.34it/s]
 48%|████▊     | 179921/371472 [3:25:57<16:22:44,  3.25it/s]
 48%|████▊     | 179922/371472 [3:25:57<16:24:30,  3.24it/s]
 48%|████▊     | 179923/371472 [3:25:58<17:02:25,  3.12it/s]
 48%|████▊     | 179924/371472 [3:25:58<16:24:48,  3.24it/s]
 48%|████▊     | 179925/371472 [3:25:58<16:36:33,  3.20it/s]
 48%|████▊     | 179926/371472 [3:25:58<16:01:52,  3.32it/s]
 48%|████▊     | 179927/371472 [3:25:59<16:00:57,  3.32it/s]
 48%|████▊     | 179928/371472 [3:25:59<15:34:09,  3.42it/s]
 48%|████▊     | 179929/371472 [3:25:59<15:37:52,  3.40it/s]
 48%|████▊     | 179930/371472 [3:26:00<16:24:04,  3.24it/s]
 48%|████▊     | 179931/371472 [3:26:00<16:19:57,  3.26it/s]
 48%|████▊     | 179932/371472 [3:26:00<16:07:41,  3.30it/s]
 48%|████▊     | 179933/371472 [3:26:01<15:53:57,  3.35it/s]
 48%|████▊     | 179934/371472 [3:26:01<15:28:44,  3.44it/s]
 48%|████▊     | 179935/371472 [3:26:01<16:02:08,  3.32it/s]
 48%|████▊     | 179936/371472 [3:26:02<16:49:20,  3.16it/s]
 48%|████▊     | 179937/371472 [3:26:02<16:29:12,  3.23it/s]
 48%|████▊     | 179938/371472 [3:26:02<16:19:14,  3.26it/s]
 48%|████▊     | 179939/371472 [3:26:02<16:21:41,  3.25it/s]
 48%|████▊     | 179940/371472 [3:26:03<15:44:13,  3.38it/s]
                                                            
{'loss': 2.9816, 'learning_rate': 5.64292486371178e-07, 'epoch': 7.75}
+
 48%|████▊     | 179940/371472 [3:26:03<15:44:13,  3.38it/s]
 48%|████▊     | 179941/371472 [3:26:03<15:55:14,  3.34it/s]
 48%|████▊     | 179942/371472 [3:26:03<16:04:57,  3.31it/s]
 48%|████▊     | 179943/371472 [3:26:04<15:41:25,  3.39it/s]
 48%|████▊     | 179944/371472 [3:26:04<15:20:48,  3.47it/s]
 48%|████▊     | 179945/371472 [3:26:04<15:26:39,  3.44it/s]
 48%|████▊     | 179946/371472 [3:26:04<15:15:14,  3.49it/s]
 48%|████▊     | 179947/371472 [3:26:05<15:57:38,  3.33it/s]
 48%|████▊     | 179948/371472 [3:26:05<15:34:05,  3.42it/s]
 48%|████▊     | 179949/371472 [3:26:05<15:38:16,  3.40it/s]
 48%|████▊     | 179950/371472 [3:26:06<15:55:53,  3.34it/s]
 48%|████▊     | 179951/371472 [3:26:06<15:40:12,  3.39it/s]
 48%|████▊     | 179952/371472 [3:26:06<15:26:25,  3.45it/s]
 48%|████▊     | 179953/371472 [3:26:07<16:08:33,  3.30it/s]
 48%|████▊     | 179954/371472 [3:26:07<16:47:59,  3.17it/s]
 48%|████▊     | 179955/371472 [3:26:07<16:40:52,  3.19it/s]
 48%|████▊     | 179956/371472 [3:26:08<16:28:36,  3.23it/s]
 48%|████▊     | 179957/371472 [3:26:08<16:15:12,  3.27it/s]
 48%|████▊     | 179958/371472 [3:26:08<15:43:38,  3.38it/s]
 48%|████▊     | 179959/371472 [3:26:08<15:25:23,  3.45it/s]
 48%|████▊     | 179960/371472 [3:26:09<15:18:56,  3.47it/s]
                                                            
{'loss': 3.1578, 'learning_rate': 5.642440043956991e-07, 'epoch': 7.75}
+
 48%|████▊     | 179960/371472 [3:26:09<15:18:56,  3.47it/s]
 48%|████▊     | 179961/371472 [3:26:09<15:12:32,  3.50it/s]
 48%|████▊     | 179962/371472 [3:26:09<15:54:22,  3.34it/s]
 48%|████▊     | 179963/371472 [3:26:10<17:28:56,  3.04it/s]
 48%|████▊     | 179964/371472 [3:26:10<18:11:57,  2.92it/s]
 48%|████▊     | 179965/371472 [3:26:10<17:26:43,  3.05it/s]
 48%|████▊     | 179966/371472 [3:26:11<18:32:03,  2.87it/s]
 48%|████▊     | 179967/371472 [3:26:11<17:19:42,  3.07it/s]
 48%|████▊     | 179968/371472 [3:26:11<16:13:31,  3.28it/s]
 48%|████▊     | 179969/371472 [3:26:12<15:54:23,  3.34it/s]
 48%|████▊     | 179970/371472 [3:26:12<15:34:06,  3.42it/s]
 48%|████▊     | 179971/371472 [3:26:12<15:22:02,  3.46it/s]
 48%|████▊     | 179972/371472 [3:26:12<15:10:10,  3.51it/s]
 48%|████▊     | 179973/371472 [3:26:13<15:02:40,  3.54it/s]
 48%|████▊     | 179974/371472 [3:26:13<15:02:46,  3.54it/s]
 48%|████▊     | 179975/371472 [3:26:13<15:06:06,  3.52it/s]
 48%|████▊     | 179976/371472 [3:26:13<15:06:41,  3.52it/s]
 48%|████▊     | 179977/371472 [3:26:14<15:20:36,  3.47it/s]
 48%|████▊     | 179978/371472 [3:26:14<15:27:52,  3.44it/s]
 48%|████▊     | 179979/371472 [3:26:14<15:33:22,  3.42it/s]
 48%|████▊     | 179980/371472 [3:26:15<17:42:22,  3.00it/s]
                                                            
{'loss': 2.982, 'learning_rate': 5.641955224202201e-07, 'epoch': 7.75}
+
 48%|████▊     | 179980/371472 [3:26:15<17:42:22,  3.00it/s]
 48%|████▊     | 179981/371472 [3:26:15<16:54:00,  3.15it/s]
 48%|████▊     | 179982/371472 [3:26:15<16:03:08,  3.31it/s]
 48%|████▊     | 179983/371472 [3:26:16<15:50:49,  3.36it/s]
 48%|████▊     | 179984/371472 [3:26:16<15:38:29,  3.40it/s]
 48%|████▊     | 179985/371472 [3:26:16<15:38:17,  3.40it/s]
 48%|████▊     | 179986/371472 [3:26:17<16:50:34,  3.16it/s]
 48%|████▊     | 179987/371472 [3:26:17<16:26:36,  3.23it/s]
 48%|████▊     | 179988/371472 [3:26:17<15:56:56,  3.33it/s]
 48%|████▊     | 179989/371472 [3:26:18<17:15:51,  3.08it/s]
 48%|████▊     | 179990/371472 [3:26:18<16:53:22,  3.15it/s]
 48%|████▊     | 179991/371472 [3:26:18<16:19:10,  3.26it/s]
 48%|████▊     | 179992/371472 [3:26:18<17:09:28,  3.10it/s]
 48%|████▊     | 179993/371472 [3:26:19<17:00:31,  3.13it/s]
 48%|████▊     | 179994/371472 [3:26:19<16:35:43,  3.21it/s]
 48%|████▊     | 179995/371472 [3:26:19<16:54:28,  3.15it/s]
 48%|████▊     | 179996/371472 [3:26:20<17:08:01,  3.10it/s]
 48%|████▊     | 179997/371472 [3:26:20<18:06:06,  2.94it/s]
 48%|████▊     | 179998/371472 [3:26:20<16:51:31,  3.15it/s]
 48%|████▊     | 179999/371472 [3:26:21<16:25:38,  3.24it/s]
 48%|████▊     | 180000/371472 [3:26:21<16:47:10,  3.17it/s]
                                                            
{'loss': 2.7792, 'learning_rate': 5.641470404447413e-07, 'epoch': 7.75}
+
 48%|████▊     | 180000/371472 [3:26:21<16:47:10,  3.17it/s]
 48%|████▊     | 180001/371472 [3:26:21<17:04:56,  3.11it/s]
 48%|████▊     | 180002/371472 [3:26:22<16:13:20,  3.28it/s]
 48%|████▊     | 180003/371472 [3:26:22<15:48:17,  3.37it/s]
 48%|████▊     | 180004/371472 [3:26:22<15:53:30,  3.35it/s]
 48%|████▊     | 180005/371472 [3:26:22<15:38:19,  3.40it/s]
 48%|████▊     | 180006/371472 [3:26:23<15:40:26,  3.39it/s]
 48%|████▊     | 180007/371472 [3:26:23<15:53:44,  3.35it/s]
 48%|████▊     | 180008/371472 [3:26:23<15:47:37,  3.37it/s]
 48%|████▊     | 180009/371472 [3:26:24<15:57:09,  3.33it/s]
 48%|████▊     | 180010/371472 [3:26:24<16:11:23,  3.29it/s]
 48%|████▊     | 180011/371472 [3:26:24<16:23:03,  3.25it/s]
 48%|████▊     | 180012/371472 [3:26:25<15:46:17,  3.37it/s]
 48%|████▊     | 180013/371472 [3:26:25<16:11:52,  3.28it/s]
 48%|████▊     | 180014/371472 [3:26:25<15:49:42,  3.36it/s]
 48%|████▊     | 180015/371472 [3:26:25<15:33:28,  3.42it/s]
 48%|████▊     | 180016/371472 [3:26:26<15:19:19,  3.47it/s]
 48%|████▊     | 180017/371472 [3:26:26<15:05:09,  3.53it/s]
 48%|████▊     | 180018/371472 [3:26:26<15:23:36,  3.45it/s]
 48%|████▊     | 180019/371472 [3:26:27<15:27:00,  3.44it/s]
 48%|████▊     | 180020/371472 [3:26:27<16:01:08,  3.32it/s]
                                                            
{'loss': 2.8534, 'learning_rate': 5.640985584692625e-07, 'epoch': 7.75}
+
 48%|████▊     | 180020/371472 [3:26:27<16:01:08,  3.32it/s]
 48%|████▊     | 180021/371472 [3:26:27<15:30:40,  3.43it/s]
 48%|████▊     | 180022/371472 [3:26:28<15:43:08,  3.38it/s]
 48%|████▊     | 180023/371472 [3:26:28<16:26:38,  3.23it/s]
 48%|████▊     | 180024/371472 [3:26:28<16:03:48,  3.31it/s]
 48%|████▊     | 180025/371472 [3:26:28<15:53:11,  3.35it/s]
 48%|████▊     | 180026/371472 [3:26:29<15:44:51,  3.38it/s]
 48%|████▊     | 180027/371472 [3:26:29<16:07:52,  3.30it/s]
 48%|████▊     | 180028/371472 [3:26:29<15:45:28,  3.37it/s]
 48%|████▊     | 180029/371472 [3:26:30<16:20:27,  3.25it/s]
 48%|████▊     | 180030/371472 [3:26:30<16:56:18,  3.14it/s]
 48%|████▊     | 180031/371472 [3:26:30<16:31:38,  3.22it/s]
 48%|████▊     | 180032/371472 [3:26:31<16:12:59,  3.28it/s]
 48%|████▊     | 180033/371472 [3:26:31<16:23:51,  3.24it/s]
 48%|████▊     | 180034/371472 [3:26:31<15:53:18,  3.35it/s]
 48%|████▊     | 180035/371472 [3:26:32<16:21:07,  3.25it/s]
 48%|████▊     | 180036/371472 [3:26:32<15:52:46,  3.35it/s]
 48%|████▊     | 180037/371472 [3:26:32<15:46:08,  3.37it/s]
 48%|████▊     | 180038/371472 [3:26:32<15:28:45,  3.44it/s]
 48%|████▊     | 180039/371472 [3:26:33<15:48:29,  3.36it/s]
 48%|████▊     | 180040/371472 [3:26:33<15:56:29,  3.34it/s]
                                                            
{'loss': 2.9068, 'learning_rate': 5.640500764937836e-07, 'epoch': 7.75}
+
 48%|████▊     | 180040/371472 [3:26:33<15:56:29,  3.34it/s]
 48%|████▊     | 180041/371472 [3:26:33<15:38:04,  3.40it/s]
 48%|████▊     | 180042/371472 [3:26:34<15:21:33,  3.46it/s]
 48%|████▊     | 180043/371472 [3:26:34<16:52:43,  3.15it/s]
 48%|████▊     | 180044/371472 [3:26:34<16:11:06,  3.29it/s]
 48%|████▊     | 180045/371472 [3:26:35<16:30:58,  3.22it/s]
 48%|████▊     | 180046/371472 [3:26:35<15:51:17,  3.35it/s]
 48%|████▊     | 180047/371472 [3:26:35<15:52:52,  3.35it/s]
 48%|████▊     | 180048/371472 [3:26:35<16:20:36,  3.25it/s]
 48%|████▊     | 180049/371472 [3:26:36<16:39:26,  3.19it/s]
 48%|████▊     | 180050/371472 [3:26:36<16:41:38,  3.19it/s]
 48%|████▊     | 180051/371472 [3:26:36<16:41:37,  3.19it/s]
 48%|████▊     | 180052/371472 [3:26:37<16:26:21,  3.23it/s]
 48%|████▊     | 180053/371472 [3:26:37<17:29:11,  3.04it/s]
 48%|████▊     | 180054/371472 [3:26:37<18:55:59,  2.81it/s]
 48%|████▊     | 180055/371472 [3:26:38<19:06:58,  2.78it/s]
 48%|████▊     | 180056/371472 [3:26:38<19:26:28,  2.73it/s]
 48%|████▊     | 180057/371472 [3:26:38<17:59:16,  2.96it/s]
 48%|████▊     | 180058/371472 [3:26:39<16:57:45,  3.13it/s]
 48%|████▊     | 180059/371472 [3:26:39<16:09:04,  3.29it/s]
 48%|████▊     | 180060/371472 [3:26:39<16:31:27,  3.22it/s]
                                                            
{'loss': 3.0067, 'learning_rate': 5.640015945183046e-07, 'epoch': 7.76}
+
 48%|████▊     | 180060/371472 [3:26:39<16:31:27,  3.22it/s]
 48%|████▊     | 180061/371472 [3:26:40<16:46:24,  3.17it/s]
 48%|████▊     | 180062/371472 [3:26:40<17:50:46,  2.98it/s]
 48%|████▊     | 180063/371472 [3:26:40<17:19:51,  3.07it/s]
 48%|████▊     | 180064/371472 [3:26:41<16:36:49,  3.20it/s]
 48%|████▊     | 180065/371472 [3:26:41<16:41:33,  3.19it/s]
 48%|████▊     | 180066/371472 [3:26:41<16:06:30,  3.30it/s]
 48%|████▊     | 180067/371472 [3:26:42<15:46:13,  3.37it/s]
 48%|████▊     | 180068/371472 [3:26:42<15:39:55,  3.39it/s]
 48%|████▊     | 180069/371472 [3:26:42<16:00:00,  3.32it/s]
 48%|████▊     | 180070/371472 [3:26:42<16:10:15,  3.29it/s]
 48%|████▊     | 180071/371472 [3:26:43<15:50:50,  3.35it/s]
 48%|████▊     | 180072/371472 [3:26:43<15:33:15,  3.42it/s]
 48%|████▊     | 180073/371472 [3:26:43<15:18:28,  3.47it/s]
 48%|████▊     | 180074/371472 [3:26:44<15:23:53,  3.45it/s]
 48%|████▊     | 180075/371472 [3:26:44<15:35:27,  3.41it/s]
 48%|████▊     | 180076/371472 [3:26:44<16:20:42,  3.25it/s]
 48%|████▊     | 180077/371472 [3:26:45<16:52:57,  3.15it/s]
 48%|████▊     | 180078/371472 [3:26:45<19:07:51,  2.78it/s]
 48%|████▊     | 180079/371472 [3:26:45<18:08:13,  2.93it/s]
 48%|████▊     | 180080/371472 [3:26:46<17:16:04,  3.08it/s]
                                                            
{'loss': 2.9297, 'learning_rate': 5.639531125428257e-07, 'epoch': 7.76}
+
 48%|████▊     | 180080/371472 [3:26:46<17:16:04,  3.08it/s]
 48%|████▊     | 180081/371472 [3:26:46<17:12:01,  3.09it/s]
 48%|████▊     | 180082/371472 [3:26:46<16:57:48,  3.13it/s]
 48%|████▊     | 180083/371472 [3:26:47<16:37:03,  3.20it/s]
 48%|████▊     | 180084/371472 [3:26:47<15:53:32,  3.35it/s]
 48%|████▊     | 180085/371472 [3:26:47<15:20:19,  3.47it/s]
 48%|████▊     | 180086/371472 [3:26:47<15:32:17,  3.42it/s]
 48%|████▊     | 180087/371472 [3:26:48<16:49:21,  3.16it/s]
 48%|████▊     | 180088/371472 [3:26:48<16:30:25,  3.22it/s]
 48%|████▊     | 180089/371472 [3:26:48<16:13:42,  3.28it/s]
 48%|████▊     | 180090/371472 [3:26:49<16:05:19,  3.30it/s]
 48%|████▊     | 180091/371472 [3:26:49<17:05:03,  3.11it/s]
 48%|████▊     | 180092/371472 [3:26:49<16:27:40,  3.23it/s]
 48%|████▊     | 180093/371472 [3:26:50<17:33:01,  3.03it/s]
 48%|████▊     | 180094/371472 [3:26:50<16:52:44,  3.15it/s]
 48%|████▊     | 180095/371472 [3:26:50<17:10:09,  3.10it/s]
 48%|████▊     | 180096/371472 [3:26:51<17:14:38,  3.08it/s]
 48%|████▊     | 180097/371472 [3:26:51<17:58:39,  2.96it/s]
 48%|████▊     | 180098/371472 [3:26:51<16:59:12,  3.13it/s]
 48%|████▊     | 180099/371472 [3:26:52<16:14:15,  3.27it/s]
 48%|████▊     | 180100/371472 [3:26:52<17:13:13,  3.09it/s]
                                                            
{'loss': 2.7985, 'learning_rate': 5.639046305673469e-07, 'epoch': 7.76}
+
 48%|████▊     | 180100/371472 [3:26:52<17:13:13,  3.09it/s]
 48%|████▊     | 180101/371472 [3:26:52<17:42:04,  3.00it/s]
 48%|████▊     | 180102/371472 [3:26:53<16:57:18,  3.14it/s]
 48%|████▊     | 180103/371472 [3:26:53<16:32:26,  3.21it/s]
 48%|████▊     | 180104/371472 [3:26:53<16:42:30,  3.18it/s]
 48%|████▊     | 180105/371472 [3:26:53<16:31:17,  3.22it/s]
 48%|████▊     | 180106/371472 [3:26:54<16:30:18,  3.22it/s]
 48%|████▊     | 180107/371472 [3:26:54<17:15:33,  3.08it/s]
 48%|████▊     | 180108/371472 [3:26:54<16:25:24,  3.24it/s]
 48%|████▊     | 180109/371472 [3:26:55<15:55:15,  3.34it/s]
 48%|████▊     | 180110/371472 [3:26:55<16:05:41,  3.30it/s]
 48%|████▊     | 180111/371472 [3:26:55<15:34:24,  3.41it/s]
 48%|████▊     | 180112/371472 [3:26:56<15:28:11,  3.44it/s]
 48%|████▊     | 180113/371472 [3:26:56<15:56:57,  3.33it/s]
 48%|████▊     | 180114/371472 [3:26:56<15:21:30,  3.46it/s]
 48%|████▊     | 180115/371472 [3:26:56<15:19:00,  3.47it/s]
 48%|████▊     | 180116/371472 [3:26:57<15:14:11,  3.49it/s]
 48%|████▊     | 180117/371472 [3:26:57<15:23:46,  3.45it/s]
 48%|████▊     | 180118/371472 [3:26:57<15:28:03,  3.44it/s]
 48%|████▊     | 180119/371472 [3:26:58<15:41:25,  3.39it/s]
 48%|████▊     | 180120/371472 [3:26:58<15:37:28,  3.40it/s]
                                                            
{'loss': 2.8505, 'learning_rate': 5.63856148591868e-07, 'epoch': 7.76}
+
 48%|████▊     | 180120/371472 [3:26:58<15:37:28,  3.40it/s]
 48%|████▊     | 180121/371472 [3:26:58<15:21:26,  3.46it/s]
 48%|████▊     | 180122/371472 [3:26:58<15:06:46,  3.52it/s]
 48%|████▊     | 180123/371472 [3:26:59<16:01:16,  3.32it/s]
 48%|████▊     | 180124/371472 [3:26:59<15:55:07,  3.34it/s]
 48%|████▊     | 180125/371472 [3:26:59<15:44:09,  3.38it/s]
 48%|████▊     | 180126/371472 [3:27:00<15:26:07,  3.44it/s]
 48%|████▊     | 180127/371472 [3:27:00<16:19:59,  3.25it/s]
 48%|████▊     | 180128/371472 [3:27:00<15:37:24,  3.40it/s]
 48%|████▊     | 180129/371472 [3:27:01<15:25:15,  3.45it/s]
 48%|████▊     | 180130/371472 [3:27:01<15:10:43,  3.50it/s]
 48%|████▊     | 180131/371472 [3:27:01<15:59:47,  3.32it/s]
 48%|████▊     | 180132/371472 [3:27:01<16:39:07,  3.19it/s]
 48%|████▊     | 180133/371472 [3:27:02<15:53:57,  3.34it/s]
 48%|████▊     | 180134/371472 [3:27:02<15:12:43,  3.49it/s]
 48%|████▊     | 180135/371472 [3:27:02<15:19:39,  3.47it/s]
 48%|████▊     | 180136/371472 [3:27:03<15:50:26,  3.36it/s]
 48%|████▊     | 180137/371472 [3:27:03<15:32:53,  3.42it/s]
 48%|████▊     | 180138/371472 [3:27:03<15:51:55,  3.35it/s]
 48%|████▊     | 180139/371472 [3:27:03<15:37:33,  3.40it/s]
 48%|████▊     | 180140/371472 [3:27:04<15:40:52,  3.39it/s]
                                                            
{'loss': 3.0474, 'learning_rate': 5.638076666163889e-07, 'epoch': 7.76}
+
 48%|████▊     | 180140/371472 [3:27:04<15:40:52,  3.39it/s]
 48%|████▊     | 180141/371472 [3:27:04<15:52:46,  3.35it/s]
 48%|████▊     | 180142/371472 [3:27:04<15:54:46,  3.34it/s]
 48%|████▊     | 180143/371472 [3:27:05<16:18:51,  3.26it/s]
 48%|████▊     | 180144/371472 [3:27:05<15:57:21,  3.33it/s]
 48%|████▊     | 180145/371472 [3:27:05<15:36:53,  3.40it/s]
 48%|████▊     | 180146/371472 [3:27:06<15:46:39,  3.37it/s]
 48%|████▊     | 180147/371472 [3:27:06<15:21:23,  3.46it/s]
 48%|████▊     | 180148/371472 [3:27:06<15:40:42,  3.39it/s]
 48%|████▊     | 180149/371472 [3:27:06<16:19:27,  3.26it/s]
 48%|████▊     | 180150/371472 [3:27:07<16:11:18,  3.28it/s]
 48%|████▊     | 180151/371472 [3:27:07<15:47:47,  3.36it/s]
 48%|████▊     | 180152/371472 [3:27:07<16:07:59,  3.29it/s]
 48%|████▊     | 180153/371472 [3:27:08<16:17:10,  3.26it/s]
 48%|████▊     | 180154/371472 [3:27:08<15:46:11,  3.37it/s]
 48%|████▊     | 180155/371472 [3:27:08<15:57:46,  3.33it/s]
 48%|████▊     | 180156/371472 [3:27:09<16:26:52,  3.23it/s]
 48%|████▊     | 180157/371472 [3:27:09<17:11:03,  3.09it/s]
 48%|████▊     | 180158/371472 [3:27:09<16:44:55,  3.17it/s]
 48%|████▊     | 180159/371472 [3:27:10<16:27:42,  3.23it/s]
 48%|████▊     | 180160/371472 [3:27:10<16:29:27,  3.22it/s]
                                                            
{'loss': 2.7556, 'learning_rate': 5.637591846409102e-07, 'epoch': 7.76}
+
 48%|████▊     | 180160/371472 [3:27:10<16:29:27,  3.22it/s]
 48%|████▊     | 180161/371472 [3:27:10<16:47:11,  3.17it/s]
 48%|████▊     | 180162/371472 [3:27:11<16:29:21,  3.22it/s]
 48%|████▊     | 180163/371472 [3:27:11<15:46:42,  3.37it/s]
 49%|████▊     | 180164/371472 [3:27:11<15:15:22,  3.48it/s]
 49%|████▊     | 180165/371472 [3:27:11<15:16:47,  3.48it/s]
 49%|████▊     | 180166/371472 [3:27:12<16:00:05,  3.32it/s]
 49%|████▊     | 180167/371472 [3:27:12<15:35:19,  3.41it/s]
 49%|████▊     | 180168/371472 [3:27:12<15:04:59,  3.52it/s]
 49%|████▊     | 180169/371472 [3:27:12<15:20:53,  3.46it/s]
 49%|████▊     | 180170/371472 [3:27:13<15:17:00,  3.48it/s]
 49%|████▊     | 180171/371472 [3:27:13<15:20:08,  3.47it/s]
 49%|████▊     | 180172/371472 [3:27:13<15:11:08,  3.50it/s]
 49%|████▊     | 180173/371472 [3:27:14<15:13:12,  3.49it/s]
 49%|████▊     | 180174/371472 [3:27:14<15:09:04,  3.51it/s]
 49%|████▊     | 180175/371472 [3:27:14<15:09:56,  3.50it/s]
 49%|████▊     | 180176/371472 [3:27:14<15:15:32,  3.48it/s]
 49%|████▊     | 180177/371472 [3:27:15<15:13:45,  3.49it/s]
 49%|████▊     | 180178/371472 [3:27:15<15:39:35,  3.39it/s]
 49%|████▊     | 180179/371472 [3:27:15<15:23:26,  3.45it/s]
 49%|████▊     | 180180/371472 [3:27:16<15:30:09,  3.43it/s]
                                                            
{'loss': 2.8877, 'learning_rate': 5.637107026654313e-07, 'epoch': 7.76}
+
 49%|████▊     | 180180/371472 [3:27:16<15:30:09,  3.43it/s]
 49%|████▊     | 180181/371472 [3:27:16<15:52:49,  3.35it/s]
 49%|████▊     | 180182/371472 [3:27:16<17:19:08,  3.07it/s]
 49%|████▊     | 180183/371472 [3:27:17<18:01:45,  2.95it/s]
 49%|████▊     | 180184/371472 [3:27:17<17:46:56,  2.99it/s]
 49%|████▊     | 180185/371472 [3:27:17<17:04:19,  3.11it/s]
 49%|████▊     | 180186/371472 [3:27:18<16:29:42,  3.22it/s]
 49%|████▊     | 180187/371472 [3:27:18<15:55:03,  3.34it/s]
 49%|████▊     | 180188/371472 [3:27:18<15:32:51,  3.42it/s]
 49%|████▊     | 180189/371472 [3:27:19<15:48:27,  3.36it/s]
 49%|████▊     | 180190/371472 [3:27:19<15:50:21,  3.35it/s]
 49%|████▊     | 180191/371472 [3:27:19<16:29:22,  3.22it/s]
 49%|████▊     | 180192/371472 [3:27:19<15:57:19,  3.33it/s]
 49%|████▊     | 180193/371472 [3:27:20<16:00:15,  3.32it/s]
 49%|████▊     | 180194/371472 [3:27:20<16:12:13,  3.28it/s]
 49%|████▊     | 180195/371472 [3:27:20<15:51:32,  3.35it/s]
 49%|████▊     | 180196/371472 [3:27:21<15:43:10,  3.38it/s]
 49%|████▊     | 180197/371472 [3:27:21<16:31:19,  3.22it/s]
 49%|████▊     | 180198/371472 [3:27:21<16:12:42,  3.28it/s]
 49%|████▊     | 180199/371472 [3:27:22<16:02:51,  3.31it/s]
 49%|████▊     | 180200/371472 [3:27:22<16:23:20,  3.24it/s]
                                                            
{'loss': 2.9347, 'learning_rate': 5.636622206899524e-07, 'epoch': 7.76}
+
 49%|████▊     | 180200/371472 [3:27:22<16:23:20,  3.24it/s]
 49%|████▊     | 180201/371472 [3:27:22<16:12:29,  3.28it/s]
 49%|████▊     | 180202/371472 [3:27:22<15:51:21,  3.35it/s]
 49%|████▊     | 180203/371472 [3:27:23<16:33:05,  3.21it/s]
 49%|████▊     | 180204/371472 [3:27:23<16:20:02,  3.25it/s]
 49%|████▊     | 180205/371472 [3:27:24<18:15:26,  2.91it/s]
 49%|████▊     | 180206/371472 [3:27:24<17:54:10,  2.97it/s]
 49%|████▊     | 180207/371472 [3:27:24<17:22:17,  3.06it/s]
 49%|████▊     | 180208/371472 [3:27:24<16:34:08,  3.21it/s]
 49%|████▊     | 180209/371472 [3:27:25<16:35:17,  3.20it/s]
 49%|████▊     | 180210/371472 [3:27:25<16:25:55,  3.23it/s]
 49%|████▊     | 180211/371472 [3:27:25<16:04:41,  3.30it/s]
 49%|████▊     | 180212/371472 [3:27:26<16:02:26,  3.31it/s]
 49%|████▊     | 180213/371472 [3:27:26<16:03:52,  3.31it/s]
 49%|████▊     | 180214/371472 [3:27:26<16:50:58,  3.15it/s]
 49%|████▊     | 180215/371472 [3:27:27<16:25:52,  3.23it/s]
 49%|████▊     | 180216/371472 [3:27:27<15:57:36,  3.33it/s]
 49%|████▊     | 180217/371472 [3:27:27<16:14:55,  3.27it/s]
 49%|████▊     | 180218/371472 [3:27:27<16:01:47,  3.31it/s]
 49%|████▊     | 180219/371472 [3:27:28<16:20:56,  3.25it/s]
 49%|████▊     | 180220/371472 [3:27:28<16:26:03,  3.23it/s]
                                                            
{'loss': 2.8148, 'learning_rate': 5.636137387144734e-07, 'epoch': 7.76}
+
 49%|████▊     | 180220/371472 [3:27:28<16:26:03,  3.23it/s]
 49%|████▊     | 180221/371472 [3:27:28<16:23:26,  3.24it/s]
 49%|████▊     | 180222/371472 [3:27:29<16:12:01,  3.28it/s]
 49%|████▊     | 180223/371472 [3:27:29<16:01:51,  3.31it/s]
 49%|████▊     | 180224/371472 [3:27:29<16:03:50,  3.31it/s]
 49%|████▊     | 180225/371472 [3:27:30<15:35:44,  3.41it/s]
 49%|████▊     | 180226/371472 [3:27:30<15:39:32,  3.39it/s]
 49%|████▊     | 180227/371472 [3:27:30<15:28:04,  3.43it/s]
 49%|████▊     | 180228/371472 [3:27:30<15:54:26,  3.34it/s]
 49%|████▊     | 180229/371472 [3:27:31<15:48:20,  3.36it/s]
 49%|████▊     | 180230/371472 [3:27:31<15:41:29,  3.39it/s]
 49%|████▊     | 180231/371472 [3:27:31<15:38:54,  3.39it/s]
 49%|████▊     | 180232/371472 [3:27:32<16:23:58,  3.24it/s]
 49%|████▊     | 180233/371472 [3:27:32<15:58:22,  3.33it/s]
 49%|████▊     | 180234/371472 [3:27:32<15:56:04,  3.33it/s]
 49%|████▊     | 180235/371472 [3:27:33<16:04:55,  3.30it/s]
 49%|████▊     | 180236/371472 [3:27:33<16:09:40,  3.29it/s]
 49%|████▊     | 180237/371472 [3:27:33<15:49:54,  3.36it/s]
 49%|████▊     | 180238/371472 [3:27:33<15:39:54,  3.39it/s]
 49%|████▊     | 180239/371472 [3:27:34<16:15:30,  3.27it/s]
 49%|████▊     | 180240/371472 [3:27:34<15:44:11,  3.38it/s]
                                                            
{'loss': 2.9797, 'learning_rate': 5.635652567389946e-07, 'epoch': 7.76}
+
 49%|████▊     | 180240/371472 [3:27:34<15:44:11,  3.38it/s]
 49%|████▊     | 180241/371472 [3:27:34<15:28:59,  3.43it/s]
 49%|████▊     | 180242/371472 [3:27:35<15:19:48,  3.47it/s]
 49%|████▊     | 180243/371472 [3:27:35<15:56:15,  3.33it/s]
 49%|████▊     | 180244/371472 [3:27:35<16:19:11,  3.25it/s]
 49%|████▊     | 180245/371472 [3:27:36<15:59:49,  3.32it/s]
 49%|████▊     | 180246/371472 [3:27:36<16:05:20,  3.30it/s]
 49%|████▊     | 180247/371472 [3:27:36<15:50:13,  3.35it/s]
 49%|████▊     | 180248/371472 [3:27:36<15:46:08,  3.37it/s]
 49%|████▊     | 180249/371472 [3:27:37<16:03:07,  3.31it/s]
 49%|████▊     | 180250/371472 [3:27:37<15:49:58,  3.35it/s]
 49%|████▊     | 180251/371472 [3:27:37<16:10:36,  3.28it/s]
 49%|████▊     | 180252/371472 [3:27:38<15:47:12,  3.36it/s]
 49%|████▊     | 180253/371472 [3:27:38<16:16:38,  3.26it/s]
 49%|████▊     | 180254/371472 [3:27:38<16:00:16,  3.32it/s]
 49%|████▊     | 180255/371472 [3:27:39<15:51:09,  3.35it/s]
 49%|████▊     | 180256/371472 [3:27:39<15:47:15,  3.36it/s]
 49%|████▊     | 180257/371472 [3:27:39<15:41:43,  3.38it/s]
 49%|████▊     | 180258/371472 [3:27:39<15:49:34,  3.36it/s]
 49%|████▊     | 180259/371472 [3:27:40<16:22:27,  3.24it/s]
 49%|████▊     | 180260/371472 [3:27:40<16:28:32,  3.22it/s]
                                                            
{'loss': 2.9068, 'learning_rate': 5.635167747635158e-07, 'epoch': 7.76}
+
 49%|████▊     | 180260/371472 [3:27:40<16:28:32,  3.22it/s]
 49%|████▊     | 180261/371472 [3:27:40<16:31:44,  3.21it/s]
 49%|████▊     | 180262/371472 [3:27:41<16:29:00,  3.22it/s]
 49%|████▊     | 180263/371472 [3:27:41<16:37:01,  3.20it/s]
 49%|████▊     | 180264/371472 [3:27:41<16:19:42,  3.25it/s]
 49%|████▊     | 180265/371472 [3:27:42<15:32:07,  3.42it/s]
 49%|████▊     | 180266/371472 [3:27:42<15:34:42,  3.41it/s]
 49%|████▊     | 180267/371472 [3:27:42<15:34:08,  3.41it/s]
 49%|████▊     | 180268/371472 [3:27:42<15:59:11,  3.32it/s]
 49%|████▊     | 180269/371472 [3:27:43<15:54:57,  3.34it/s]
 49%|████▊     | 180270/371472 [3:27:43<15:44:06,  3.38it/s]
 49%|████▊     | 180271/371472 [3:27:43<15:32:00,  3.42it/s]
 49%|████▊     | 180272/371472 [3:27:44<16:23:22,  3.24it/s]
 49%|████▊     | 180273/371472 [3:27:44<15:52:47,  3.34it/s]
 49%|████▊     | 180274/371472 [3:27:44<15:31:55,  3.42it/s]
 49%|████▊     | 180275/371472 [3:27:45<15:35:18,  3.41it/s]
 49%|████▊     | 180276/371472 [3:27:45<15:52:42,  3.34it/s]
 49%|████▊     | 180277/371472 [3:27:45<15:47:50,  3.36it/s]
 49%|████▊     | 180278/371472 [3:27:45<15:31:30,  3.42it/s]
 49%|████▊     | 180279/371472 [3:27:46<15:23:10,  3.45it/s]
 49%|████▊     | 180280/371472 [3:27:46<15:46:10,  3.37it/s]
                                                            
{'loss': 3.0076, 'learning_rate': 5.634682927880368e-07, 'epoch': 7.76}
+
 49%|████▊     | 180280/371472 [3:27:46<15:46:10,  3.37it/s]
 49%|████▊     | 180281/371472 [3:27:46<17:31:26,  3.03it/s]
 49%|████▊     | 180282/371472 [3:27:47<16:43:37,  3.17it/s]
 49%|████▊     | 180283/371472 [3:27:47<16:19:35,  3.25it/s]
 49%|████▊     | 180284/371472 [3:27:47<16:24:28,  3.24it/s]
 49%|████▊     | 180285/371472 [3:27:48<16:28:58,  3.22it/s]
 49%|████▊     | 180286/371472 [3:27:48<16:20:30,  3.25it/s]
 49%|████▊     | 180287/371472 [3:27:48<16:11:16,  3.28it/s]
 49%|████▊     | 180288/371472 [3:27:49<16:21:12,  3.25it/s]
 49%|████▊     | 180289/371472 [3:27:49<16:40:43,  3.18it/s]
 49%|████▊     | 180290/371472 [3:27:49<16:06:07,  3.30it/s]
 49%|████▊     | 180291/371472 [3:27:49<15:37:34,  3.40it/s]
 49%|████▊     | 180292/371472 [3:27:50<15:15:53,  3.48it/s]
 49%|████▊     | 180293/371472 [3:27:50<15:13:29,  3.49it/s]
 49%|████▊     | 180294/371472 [3:27:50<15:06:23,  3.52it/s]
 49%|████▊     | 180295/371472 [3:27:51<16:30:37,  3.22it/s]
 49%|████▊     | 180296/371472 [3:27:51<16:11:49,  3.28it/s]
 49%|████▊     | 180297/371472 [3:27:51<15:40:49,  3.39it/s]
 49%|████▊     | 180298/371472 [3:27:51<15:22:20,  3.45it/s]
 49%|████▊     | 180299/371472 [3:27:52<15:04:22,  3.52it/s]
 49%|████▊     | 180300/371472 [3:27:52<16:14:55,  3.27it/s]
                                                            
{'loss': 2.8068, 'learning_rate': 5.634198108125579e-07, 'epoch': 7.77}
+
 49%|████▊     | 180300/371472 [3:27:52<16:14:55,  3.27it/s]
 49%|████▊     | 180301/371472 [3:27:52<15:50:20,  3.35it/s]
 49%|████▊     | 180302/371472 [3:27:53<16:19:29,  3.25it/s]
 49%|████▊     | 180303/371472 [3:27:53<15:59:34,  3.32it/s]
 49%|████▊     | 180304/371472 [3:27:53<15:47:48,  3.36it/s]
 49%|████▊     | 180305/371472 [3:27:54<15:57:50,  3.33it/s]
 49%|████▊     | 180306/371472 [3:27:54<15:30:33,  3.42it/s]
 49%|████▊     | 180307/371472 [3:27:54<16:28:52,  3.22it/s]
 49%|████▊     | 180308/371472 [3:27:55<16:19:26,  3.25it/s]
 49%|████▊     | 180309/371472 [3:27:55<16:16:56,  3.26it/s]
 49%|████▊     | 180310/371472 [3:27:55<15:56:01,  3.33it/s]
 49%|████▊     | 180311/371472 [3:27:55<15:38:16,  3.40it/s]
 49%|████▊     | 180312/371472 [3:27:56<15:35:51,  3.40it/s]
 49%|████▊     | 180313/371472 [3:27:56<17:47:16,  2.99it/s]
 49%|████▊     | 180314/371472 [3:27:56<17:05:17,  3.11it/s]
 49%|████▊     | 180315/371472 [3:27:57<16:38:32,  3.19it/s]
 49%|████▊     | 180316/371472 [3:27:57<16:03:02,  3.31it/s]
 49%|████▊     | 180317/371472 [3:27:57<16:05:32,  3.30it/s]
 49%|████▊     | 180318/371472 [3:27:58<16:35:20,  3.20it/s]
 49%|████▊     | 180319/371472 [3:27:58<17:58:28,  2.95it/s]
 49%|████▊     | 180320/371472 [3:27:58<16:53:46,  3.14it/s]
                                                            
{'loss': 2.8989, 'learning_rate': 5.63371328837079e-07, 'epoch': 7.77}
+
 49%|████▊     | 180320/371472 [3:27:58<16:53:46,  3.14it/s]
 49%|████▊     | 180321/371472 [3:27:59<17:37:42,  3.01it/s]
 49%|████▊     | 180322/371472 [3:27:59<17:52:19,  2.97it/s]
 49%|████▊     | 180323/371472 [3:27:59<17:03:52,  3.11it/s]
 49%|████▊     | 180324/371472 [3:28:00<17:07:26,  3.10it/s]
 49%|████▊     | 180325/371472 [3:28:00<17:40:01,  3.01it/s]
 49%|████▊     | 180326/371472 [3:28:00<16:56:45,  3.13it/s]
 49%|████▊     | 180327/371472 [3:28:01<16:26:43,  3.23it/s]
 49%|████▊     | 180328/371472 [3:28:01<16:24:14,  3.24it/s]
 49%|████▊     | 180329/371472 [3:28:01<16:31:20,  3.21it/s]
 49%|████▊     | 180330/371472 [3:28:01<16:22:02,  3.24it/s]
 49%|████▊     | 180331/371472 [3:28:02<16:08:42,  3.29it/s]
 49%|████▊     | 180332/371472 [3:28:02<15:47:58,  3.36it/s]
 49%|████▊     | 180333/371472 [3:28:02<16:25:36,  3.23it/s]
 49%|████▊     | 180334/371472 [3:28:03<15:49:16,  3.36it/s]
 49%|████▊     | 180335/371472 [3:28:03<15:34:35,  3.41it/s]
 49%|████▊     | 180336/371472 [3:28:03<15:31:30,  3.42it/s]
 49%|████▊     | 180337/371472 [3:28:04<16:14:46,  3.27it/s]
 49%|████▊     | 180338/371472 [3:28:04<15:50:19,  3.35it/s]
 49%|████▊     | 180339/371472 [3:28:04<15:52:05,  3.35it/s]
 49%|████▊     | 180340/371472 [3:28:04<15:51:37,  3.35it/s]
                                                            
{'loss': 2.8423, 'learning_rate': 5.633228468616002e-07, 'epoch': 7.77}
+
 49%|████▊     | 180340/371472 [3:28:04<15:51:37,  3.35it/s]
 49%|████▊     | 180341/371472 [3:28:05<15:46:03,  3.37it/s]
 49%|████▊     | 180342/371472 [3:28:05<15:36:19,  3.40it/s]
 49%|████▊     | 180343/371472 [3:28:05<15:39:50,  3.39it/s]
 49%|████▊     | 180344/371472 [3:28:06<15:39:53,  3.39it/s]
 49%|████▊     | 180345/371472 [3:28:06<16:02:39,  3.31it/s]
 49%|████▊     | 180346/371472 [3:28:06<16:02:39,  3.31it/s]
 49%|████▊     | 180347/371472 [3:28:07<15:31:39,  3.42it/s]
 49%|████▊     | 180348/371472 [3:28:07<15:15:47,  3.48it/s]
 49%|████▊     | 180349/371472 [3:28:07<15:22:11,  3.45it/s]
 49%|████▊     | 180350/371472 [3:28:07<15:45:20,  3.37it/s]
 49%|████▊     | 180351/371472 [3:28:08<15:39:29,  3.39it/s]
 49%|████▊     | 180352/371472 [3:28:08<16:01:48,  3.31it/s]
 49%|████▊     | 180353/371472 [3:28:08<16:35:18,  3.20it/s]
 49%|████▊     | 180354/371472 [3:28:09<16:15:31,  3.27it/s]
 49%|████▊     | 180355/371472 [3:28:09<16:03:31,  3.31it/s]
 49%|████▊     | 180356/371472 [3:28:09<15:51:16,  3.35it/s]
 49%|████▊     | 180357/371472 [3:28:10<17:09:49,  3.09it/s]
 49%|████▊     | 180358/371472 [3:28:10<17:10:35,  3.09it/s]
 49%|████▊     | 180359/371472 [3:28:10<17:11:42,  3.09it/s]
 49%|████▊     | 180360/371472 [3:28:11<16:27:44,  3.22it/s]
                                                            
{'loss': 2.9327, 'learning_rate': 5.632743648861212e-07, 'epoch': 7.77}
+
 49%|████▊     | 180360/371472 [3:28:11<16:27:44,  3.22it/s]
 49%|████▊     | 180361/371472 [3:28:11<16:35:02,  3.20it/s]
 49%|████▊     | 180362/371472 [3:28:11<16:51:54,  3.15it/s]
 49%|████▊     | 180363/371472 [3:28:11<16:50:14,  3.15it/s]
 49%|████▊     | 180364/371472 [3:28:12<16:20:50,  3.25it/s]
 49%|████▊     | 180365/371472 [3:28:12<16:07:02,  3.29it/s]
 49%|████▊     | 180366/371472 [3:28:12<17:18:20,  3.07it/s]
 49%|████▊     | 180367/371472 [3:28:13<16:48:02,  3.16it/s]
 49%|████▊     | 180368/371472 [3:28:13<16:10:20,  3.28it/s]
 49%|████▊     | 180369/371472 [3:28:13<16:51:57,  3.15it/s]
 49%|████▊     | 180370/371472 [3:28:14<17:11:22,  3.09it/s]
 49%|████▊     | 180371/371472 [3:28:14<17:09:19,  3.09it/s]
 49%|████▊     | 180372/371472 [3:28:14<16:41:06,  3.18it/s]
 49%|████▊     | 180373/371472 [3:28:15<16:24:06,  3.24it/s]
 49%|████▊     | 180374/371472 [3:28:15<16:31:06,  3.21it/s]
 49%|████▊     | 180375/371472 [3:28:15<16:10:32,  3.28it/s]
 49%|████▊     | 180376/371472 [3:28:16<15:45:29,  3.37it/s]
 49%|████▊     | 180377/371472 [3:28:16<15:31:49,  3.42it/s]
 49%|████▊     | 180378/371472 [3:28:16<15:23:25,  3.45it/s]
 49%|████▊     | 180379/371472 [3:28:16<15:49:56,  3.35it/s]
 49%|████▊     | 180380/371472 [3:28:17<16:01:25,  3.31it/s]
                                                            
{'loss': 2.829, 'learning_rate': 5.632258829106423e-07, 'epoch': 7.77}
+
 49%|████▊     | 180380/371472 [3:28:17<16:01:25,  3.31it/s]
 49%|████▊     | 180381/371472 [3:28:17<17:07:40,  3.10it/s]
 49%|████▊     | 180382/371472 [3:28:17<17:16:05,  3.07it/s]
 49%|████▊     | 180383/371472 [3:28:18<16:49:53,  3.15it/s]
 49%|████▊     | 180384/371472 [3:28:18<17:20:20,  3.06it/s]
 49%|████▊     | 180385/371472 [3:28:18<16:26:31,  3.23it/s]
 49%|████▊     | 180386/371472 [3:28:19<16:25:55,  3.23it/s]
 49%|████▊     | 180387/371472 [3:28:19<15:59:09,  3.32it/s]
 49%|████▊     | 180388/371472 [3:28:19<15:55:07,  3.33it/s]
 49%|████▊     | 180389/371472 [3:28:19<15:36:27,  3.40it/s]
 49%|████▊     | 180390/371472 [3:28:20<15:27:22,  3.43it/s]
 49%|████▊     | 180391/371472 [3:28:20<15:31:34,  3.42it/s]
 49%|████▊     | 180392/371472 [3:28:20<15:29:36,  3.43it/s]
 49%|████▊     | 180393/371472 [3:28:21<15:33:15,  3.41it/s]
 49%|████▊     | 180394/371472 [3:28:21<15:28:13,  3.43it/s]
 49%|████▊     | 180395/371472 [3:28:21<15:10:01,  3.50it/s]
 49%|████▊     | 180396/371472 [3:28:22<15:37:09,  3.40it/s]
 49%|████▊     | 180397/371472 [3:28:22<15:25:01,  3.44it/s]
 49%|████▊     | 180398/371472 [3:28:22<15:18:48,  3.47it/s]
 49%|████▊     | 180399/371472 [3:28:22<15:07:35,  3.51it/s]
 49%|████▊     | 180400/371472 [3:28:23<15:03:15,  3.53it/s]
                                                            
{'loss': 2.7907, 'learning_rate': 5.631774009351635e-07, 'epoch': 7.77}
+
 49%|████▊     | 180400/371472 [3:28:23<15:03:15,  3.53it/s]
 49%|████▊     | 180401/371472 [3:28:23<15:30:18,  3.42it/s]
 49%|████▊     | 180402/371472 [3:28:23<15:39:16,  3.39it/s]
 49%|████▊     | 180403/371472 [3:28:24<15:26:35,  3.44it/s]
 49%|████▊     | 180404/371472 [3:28:24<15:25:04,  3.44it/s]
 49%|████▊     | 180405/371472 [3:28:24<15:25:03,  3.44it/s]
 49%|████▊     | 180406/371472 [3:28:24<16:08:15,  3.29it/s]
 49%|████▊     | 180407/371472 [3:28:25<16:06:44,  3.29it/s]
 49%|████▊     | 180408/371472 [3:28:25<15:45:34,  3.37it/s]
 49%|████▊     | 180409/371472 [3:28:25<15:41:36,  3.38it/s]
 49%|████▊     | 180410/371472 [3:28:26<15:30:29,  3.42it/s]
 49%|████▊     | 180411/371472 [3:28:26<16:44:10,  3.17it/s]
 49%|████▊     | 180412/371472 [3:28:26<17:01:12,  3.12it/s]
 49%|████▊     | 180413/371472 [3:28:27<16:08:05,  3.29it/s]
 49%|████▊     | 180414/371472 [3:28:27<16:06:44,  3.29it/s]
 49%|████▊     | 180415/371472 [3:28:27<16:11:27,  3.28it/s]
 49%|████▊     | 180416/371472 [3:28:28<16:49:53,  3.15it/s]
 49%|████▊     | 180417/371472 [3:28:28<16:10:54,  3.28it/s]
 49%|████▊     | 180418/371472 [3:28:28<16:38:21,  3.19it/s]
 49%|████▊     | 180419/371472 [3:28:28<15:48:36,  3.36it/s]
 49%|████▊     | 180420/371472 [3:28:29<15:41:21,  3.38it/s]
                                                            
{'loss': 2.9406, 'learning_rate': 5.631289189596846e-07, 'epoch': 7.77}
+
 49%|████▊     | 180420/371472 [3:28:29<15:41:21,  3.38it/s]
 49%|████▊     | 180421/371472 [3:28:29<15:33:38,  3.41it/s]
 49%|████▊     | 180422/371472 [3:28:29<15:21:16,  3.46it/s]
 49%|████▊     | 180423/371472 [3:28:30<15:04:32,  3.52it/s]
 49%|████▊     | 180424/371472 [3:28:30<15:09:55,  3.50it/s]
 49%|████▊     | 180425/371472 [3:28:30<15:19:11,  3.46it/s]
 49%|████▊     | 180426/371472 [3:28:30<15:15:54,  3.48it/s]
 49%|████▊     | 180427/371472 [3:28:31<15:21:29,  3.46it/s]
 49%|████▊     | 180428/371472 [3:28:31<15:05:03,  3.52it/s]
 49%|████▊     | 180429/371472 [3:28:31<14:46:07,  3.59it/s]
 49%|████▊     | 180430/371472 [3:28:32<15:10:04,  3.50it/s]
 49%|████▊     | 180431/371472 [3:28:32<16:01:40,  3.31it/s]
 49%|████▊     | 180432/371472 [3:28:32<16:08:10,  3.29it/s]
 49%|████▊     | 180433/371472 [3:28:33<16:08:13,  3.29it/s]
 49%|████▊     | 180434/371472 [3:28:33<15:43:06,  3.38it/s]
 49%|████▊     | 180435/371472 [3:28:33<15:44:51,  3.37it/s]
 49%|████▊     | 180436/371472 [3:28:33<15:26:06,  3.44it/s]
 49%|████▊     | 180437/371472 [3:28:34<16:38:41,  3.19it/s]
 49%|████▊     | 180438/371472 [3:28:34<16:12:03,  3.28it/s]
 49%|████▊     | 180439/371472 [3:28:34<17:31:10,  3.03it/s]
 49%|████▊     | 180440/371472 [3:28:35<16:37:42,  3.19it/s]
                                                            
{'loss': 3.106, 'learning_rate': 5.630804369842056e-07, 'epoch': 7.77}
+
 49%|████▊     | 180440/371472 [3:28:35<16:37:42,  3.19it/s]
 49%|████▊     | 180441/371472 [3:28:35<16:37:55,  3.19it/s]
 49%|████▊     | 180442/371472 [3:28:35<16:49:04,  3.16it/s]
 49%|████▊     | 180443/371472 [3:28:36<17:09:48,  3.09it/s]
 49%|████▊     | 180444/371472 [3:28:36<17:39:25,  3.01it/s]
 49%|████▊     | 180445/371472 [3:28:36<17:01:28,  3.12it/s]
 49%|████▊     | 180446/371472 [3:28:37<16:52:03,  3.15it/s]
 49%|████▊     | 180447/371472 [3:28:37<16:18:10,  3.25it/s]
 49%|████▊     | 180448/371472 [3:28:37<15:57:18,  3.33it/s]
 49%|████▊     | 180449/371472 [3:28:38<17:19:27,  3.06it/s]
 49%|████▊     | 180450/371472 [3:28:38<17:49:44,  2.98it/s]
 49%|████▊     | 180451/371472 [3:28:38<16:58:07,  3.13it/s]
 49%|████▊     | 180452/371472 [3:28:38<16:19:33,  3.25it/s]
 49%|████▊     | 180453/371472 [3:28:39<16:00:38,  3.31it/s]
 49%|████▊     | 180454/371472 [3:28:39<16:52:36,  3.14it/s]
 49%|████▊     | 180455/371472 [3:28:39<16:21:16,  3.24it/s]
 49%|████▊     | 180456/371472 [3:28:40<16:25:54,  3.23it/s]
 49%|████▊     | 180457/371472 [3:28:40<16:40:15,  3.18it/s]
 49%|████▊     | 180458/371472 [3:28:40<16:46:35,  3.16it/s]
 49%|████▊     | 180459/371472 [3:28:41<16:23:57,  3.24it/s]
 49%|████▊     | 180460/371472 [3:28:41<16:53:02,  3.14it/s]
                                                            
{'loss': 2.7992, 'learning_rate': 5.630319550087267e-07, 'epoch': 7.77}
+
 49%|████▊     | 180460/371472 [3:28:41<16:53:02,  3.14it/s]
 49%|████▊     | 180461/371472 [3:28:41<16:20:02,  3.25it/s]
 49%|████▊     | 180462/371472 [3:28:42<15:59:50,  3.32it/s]
 49%|████▊     | 180463/371472 [3:28:42<15:54:58,  3.33it/s]
 49%|████▊     | 180464/371472 [3:28:42<16:30:35,  3.21it/s]
 49%|████▊     | 180465/371472 [3:28:43<16:56:33,  3.13it/s]
 49%|████▊     | 180466/371472 [3:28:43<16:53:15,  3.14it/s]
 49%|████▊     | 180467/371472 [3:28:43<16:12:12,  3.27it/s]
 49%|████▊     | 180468/371472 [3:28:43<16:17:48,  3.26it/s]
 49%|████▊     | 180469/371472 [3:28:44<15:52:01,  3.34it/s]
 49%|████▊     | 180470/371472 [3:28:44<16:34:05,  3.20it/s]
 49%|████▊     | 180471/371472 [3:28:44<17:10:18,  3.09it/s]
 49%|████▊     | 180472/371472 [3:28:45<16:59:21,  3.12it/s]
 49%|████▊     | 180473/371472 [3:28:45<17:20:52,  3.06it/s]
 49%|████▊     | 180474/371472 [3:28:45<16:40:52,  3.18it/s]
 49%|████▊     | 180475/371472 [3:28:46<16:10:44,  3.28it/s]
 49%|████▊     | 180476/371472 [3:28:46<16:28:42,  3.22it/s]
 49%|████▊     | 180477/371472 [3:28:46<16:03:03,  3.31it/s]
 49%|████▊     | 180478/371472 [3:28:47<15:55:42,  3.33it/s]
 49%|████▊     | 180479/371472 [3:28:47<16:00:11,  3.32it/s]
 49%|████▊     | 180480/371472 [3:28:47<16:04:32,  3.30it/s]
                                                            
{'loss': 2.9508, 'learning_rate': 5.629834730332479e-07, 'epoch': 7.77}
+
 49%|████▊     | 180480/371472 [3:28:47<16:04:32,  3.30it/s]
 49%|████▊     | 180481/371472 [3:28:47<15:57:57,  3.32it/s]
 49%|████▊     | 180482/371472 [3:28:48<15:33:02,  3.41it/s]
 49%|████▊     | 180483/371472 [3:28:48<15:41:55,  3.38it/s]
 49%|████▊     | 180484/371472 [3:28:48<15:46:03,  3.36it/s]
 49%|████▊     | 180485/371472 [3:28:49<15:25:24,  3.44it/s]
 49%|████▊     | 180486/371472 [3:28:49<15:18:11,  3.47it/s]
 49%|████▊     | 180487/371472 [3:28:49<14:57:42,  3.55it/s]
 49%|████▊     | 180488/371472 [3:28:49<15:14:45,  3.48it/s]
 49%|████▊     | 180489/371472 [3:28:50<15:28:19,  3.43it/s]
 49%|████▊     | 180490/371472 [3:28:50<16:45:43,  3.16it/s]
 49%|████▊     | 180491/371472 [3:28:50<16:33:09,  3.20it/s]
 49%|████▊     | 180492/371472 [3:28:51<17:17:23,  3.07it/s]
 49%|████▊     | 180493/371472 [3:28:51<16:49:45,  3.15it/s]
 49%|████▊     | 180494/371472 [3:28:51<16:11:45,  3.28it/s]
 49%|████▊     | 180495/371472 [3:28:52<17:44:54,  2.99it/s]
 49%|████▊     | 180496/371472 [3:28:52<17:17:16,  3.07it/s]
 49%|████▊     | 180497/371472 [3:28:52<17:14:29,  3.08it/s]
 49%|████▊     | 180498/371472 [3:28:53<17:04:11,  3.11it/s]
 49%|████▊     | 180499/371472 [3:28:53<16:42:12,  3.18it/s]
 49%|████▊     | 180500/371472 [3:28:53<17:14:33,  3.08it/s]
                                                            
{'loss': 2.7001, 'learning_rate': 5.629349910577689e-07, 'epoch': 7.77}
+
 49%|████▊     | 180500/371472 [3:28:53<17:14:33,  3.08it/s]
 49%|████▊     | 180501/371472 [3:28:54<17:06:07,  3.10it/s]
 49%|████▊     | 180502/371472 [3:28:54<16:38:25,  3.19it/s]
 49%|████▊     | 180503/371472 [3:28:54<16:42:00,  3.18it/s]
 49%|████▊     | 180504/371472 [3:28:55<17:05:21,  3.10it/s]
 49%|████▊     | 180505/371472 [3:28:55<16:14:15,  3.27it/s]
 49%|████▊     | 180506/371472 [3:28:55<17:53:28,  2.96it/s]
 49%|████▊     | 180507/371472 [3:28:56<17:47:40,  2.98it/s]
 49%|████▊     | 180508/371472 [3:28:56<16:56:27,  3.13it/s]
 49%|████▊     | 180509/371472 [3:28:56<18:20:01,  2.89it/s]
 49%|████▊     | 180510/371472 [3:28:57<17:48:57,  2.98it/s]
 49%|████▊     | 180511/371472 [3:28:57<16:49:39,  3.15it/s]
 49%|████▊     | 180512/371472 [3:28:57<16:44:01,  3.17it/s]
 49%|████▊     | 180513/371472 [3:28:58<16:38:43,  3.19it/s]
 49%|████▊     | 180514/371472 [3:28:58<16:26:03,  3.23it/s]
 49%|████▊     | 180515/371472 [3:28:58<16:15:07,  3.26it/s]
 49%|████▊     | 180516/371472 [3:28:58<16:07:32,  3.29it/s]
 49%|████▊     | 180517/371472 [3:28:59<15:42:16,  3.38it/s]
 49%|████▊     | 180518/371472 [3:28:59<15:45:26,  3.37it/s]
 49%|████▊     | 180519/371472 [3:28:59<15:50:06,  3.35it/s]
 49%|████▊     | 180520/371472 [3:29:00<16:05:00,  3.30it/s]
                                                            
{'loss': 2.8058, 'learning_rate': 5.6288650908229e-07, 'epoch': 7.78}
+
 49%|████▊     | 180520/371472 [3:29:00<16:05:00,  3.30it/s]
 49%|████▊     | 180521/371472 [3:29:00<15:35:46,  3.40it/s]
 49%|████▊     | 180522/371472 [3:29:00<15:31:49,  3.42it/s]
 49%|████▊     | 180523/371472 [3:29:00<15:41:55,  3.38it/s]
 49%|████▊     | 180524/371472 [3:29:01<15:46:11,  3.36it/s]
 49%|████▊     | 180525/371472 [3:29:01<15:42:18,  3.38it/s]
 49%|████▊     | 180526/371472 [3:29:01<15:50:00,  3.35it/s]
 49%|████▊     | 180527/371472 [3:29:02<15:41:50,  3.38it/s]
 49%|████▊     | 180528/371472 [3:29:02<15:22:15,  3.45it/s]
 49%|████▊     | 180529/371472 [3:29:02<15:18:19,  3.47it/s]
 49%|████▊     | 180530/371472 [3:29:03<15:36:24,  3.40it/s]
 49%|████▊     | 180531/371472 [3:29:03<15:33:36,  3.41it/s]
 49%|████▊     | 180532/371472 [3:29:03<15:42:37,  3.38it/s]
 49%|████▊     | 180533/371472 [3:29:03<15:30:59,  3.42it/s]
 49%|████▊     | 180534/371472 [3:29:04<15:42:39,  3.38it/s]
 49%|████▊     | 180535/371472 [3:29:04<16:13:55,  3.27it/s]
 49%|████▊     | 180536/371472 [3:29:04<15:53:26,  3.34it/s]
 49%|████▊     | 180537/371472 [3:29:05<20:30:17,  2.59it/s]
 49%|████▊     | 180538/371472 [3:29:05<18:40:18,  2.84it/s]
 49%|████▊     | 180539/371472 [3:29:05<17:32:14,  3.02it/s]
 49%|████▊     | 180540/371472 [3:29:06<18:14:25,  2.91it/s]
                                                            
{'loss': 2.9045, 'learning_rate': 5.628380271068112e-07, 'epoch': 7.78}
+
 49%|████▊     | 180540/371472 [3:29:06<18:14:25,  2.91it/s]
 49%|████▊     | 180541/371472 [3:29:06<17:32:27,  3.02it/s]
 49%|████▊     | 180542/371472 [3:29:06<16:42:18,  3.17it/s]
 49%|████▊     | 180543/371472 [3:29:07<16:53:36,  3.14it/s]
 49%|████▊     | 180544/371472 [3:29:07<16:43:30,  3.17it/s]
 49%|████▊     | 180545/371472 [3:29:08<19:27:43,  2.73it/s]
 49%|████▊     | 180546/371472 [3:29:08<18:11:32,  2.92it/s]
 49%|████▊     | 180547/371472 [3:29:08<17:46:24,  2.98it/s]
 49%|████▊     | 180548/371472 [3:29:08<17:22:08,  3.05it/s]
 49%|████▊     | 180549/371472 [3:29:09<16:24:51,  3.23it/s]
 49%|████▊     | 180550/371472 [3:29:09<16:07:02,  3.29it/s]
 49%|████▊     | 180551/371472 [3:29:09<15:54:22,  3.33it/s]
 49%|████▊     | 180552/371472 [3:29:10<16:45:42,  3.16it/s]
 49%|████▊     | 180553/371472 [3:29:10<17:01:24,  3.12it/s]
 49%|████▊     | 180554/371472 [3:29:10<16:46:24,  3.16it/s]
 49%|████▊     | 180555/371472 [3:29:11<16:49:04,  3.15it/s]
 49%|████▊     | 180556/371472 [3:29:11<16:11:13,  3.28it/s]
 49%|████▊     | 180557/371472 [3:29:11<16:12:32,  3.27it/s]
 49%|████▊     | 180558/371472 [3:29:12<15:55:35,  3.33it/s]
 49%|████▊     | 180559/371472 [3:29:12<16:07:19,  3.29it/s]
 49%|████▊     | 180560/371472 [3:29:12<16:39:49,  3.18it/s]
                                                            
{'loss': 2.8204, 'learning_rate': 5.627895451313323e-07, 'epoch': 7.78}
+
 49%|████▊     | 180560/371472 [3:29:12<16:39:49,  3.18it/s]
 49%|████▊     | 180561/371472 [3:29:12<16:14:10,  3.27it/s]
 49%|████▊     | 180562/371472 [3:29:13<16:46:46,  3.16it/s]
 49%|████▊     | 180563/371472 [3:29:13<16:08:45,  3.28it/s]
 49%|████▊     | 180564/371472 [3:29:13<15:47:35,  3.36it/s]
 49%|████▊     | 180565/371472 [3:29:14<15:35:47,  3.40it/s]
 49%|████▊     | 180566/371472 [3:29:14<16:45:35,  3.16it/s]
 49%|████▊     | 180567/371472 [3:29:14<16:45:59,  3.16it/s]
 49%|████▊     | 180568/371472 [3:29:15<16:33:42,  3.20it/s]
 49%|████▊     | 180569/371472 [3:29:15<16:10:40,  3.28it/s]
 49%|████▊     | 180570/371472 [3:29:15<17:26:06,  3.04it/s]
 49%|████▊     | 180571/371472 [3:29:16<17:15:55,  3.07it/s]
 49%|████▊     | 180572/371472 [3:29:16<16:51:22,  3.15it/s]
 49%|████▊     | 180573/371472 [3:29:16<16:25:42,  3.23it/s]
 49%|████▊     | 180574/371472 [3:29:16<16:13:04,  3.27it/s]
 49%|████▊     | 180575/371472 [3:29:17<15:52:27,  3.34it/s]
 49%|████▊     | 180576/371472 [3:29:17<15:50:47,  3.35it/s]
 49%|████▊     | 180577/371472 [3:29:17<16:52:12,  3.14it/s]
 49%|████▊     | 180578/371472 [3:29:18<16:21:41,  3.24it/s]
 49%|████▊     | 180579/371472 [3:29:18<16:08:51,  3.28it/s]
 49%|████▊     | 180580/371472 [3:29:18<16:05:14,  3.30it/s]
                                                            
{'loss': 2.8089, 'learning_rate': 5.627410631558533e-07, 'epoch': 7.78}
+
 49%|████▊     | 180580/371472 [3:29:18<16:05:14,  3.30it/s]
 49%|████▊     | 180581/371472 [3:29:19<16:09:05,  3.28it/s]
 49%|████▊     | 180582/371472 [3:29:19<16:28:27,  3.22it/s]
 49%|████▊     | 180583/371472 [3:29:19<16:39:33,  3.18it/s]
 49%|████▊     | 180584/371472 [3:29:20<16:35:52,  3.19it/s]
 49%|████▊     | 180585/371472 [3:29:20<16:17:26,  3.25it/s]
 49%|████▊     | 180586/371472 [3:29:20<17:19:23,  3.06it/s]
 49%|████▊     | 180587/371472 [3:29:21<16:43:58,  3.17it/s]
 49%|████▊     | 180588/371472 [3:29:21<16:33:02,  3.20it/s]
 49%|████▊     | 180589/371472 [3:29:21<16:50:33,  3.15it/s]
 49%|████▊     | 180590/371472 [3:29:21<16:28:35,  3.22it/s]
 49%|████▊     | 180591/371472 [3:29:22<16:12:51,  3.27it/s]
 49%|████▊     | 180592/371472 [3:29:22<17:08:05,  3.09it/s]
 49%|████▊     | 180593/371472 [3:29:22<16:27:48,  3.22it/s]
 49%|████▊     | 180594/371472 [3:29:23<16:12:57,  3.27it/s]
 49%|████▊     | 180595/371472 [3:29:23<16:03:42,  3.30it/s]
 49%|████▊     | 180596/371472 [3:29:23<15:57:06,  3.32it/s]
 49%|████▊     | 180597/371472 [3:29:24<16:14:10,  3.27it/s]
 49%|████▊     | 180598/371472 [3:29:24<17:17:23,  3.07it/s]
 49%|████▊     | 180599/371472 [3:29:24<16:33:52,  3.20it/s]
 49%|████▊     | 180600/371472 [3:29:25<16:34:23,  3.20it/s]
                                                            
{'loss': 2.8198, 'learning_rate': 5.626925811803744e-07, 'epoch': 7.78}
+
 49%|████▊     | 180600/371472 [3:29:25<16:34:23,  3.20it/s]
 49%|████▊     | 180601/371472 [3:29:25<16:15:56,  3.26it/s]
 49%|████▊     | 180602/371472 [3:29:25<16:11:08,  3.28it/s]
 49%|████▊     | 180603/371472 [3:29:25<16:16:16,  3.26it/s]
 49%|████▊     | 180604/371472 [3:29:26<16:05:15,  3.30it/s]
 49%|████▊     | 180605/371472 [3:29:26<16:00:09,  3.31it/s]
 49%|████▊     | 180606/371472 [3:29:26<16:09:19,  3.28it/s]
 49%|████▊     | 180607/371472 [3:29:27<16:03:16,  3.30it/s]
 49%|████▊     | 180608/371472 [3:29:27<15:54:09,  3.33it/s]
 49%|████▊     | 180609/371472 [3:29:27<16:17:02,  3.26it/s]
 49%|████▊     | 180610/371472 [3:29:28<16:37:51,  3.19it/s]
 49%|████▊     | 180611/371472 [3:29:28<16:06:25,  3.29it/s]
 49%|████▊     | 180612/371472 [3:29:28<16:12:03,  3.27it/s]
 49%|████▊     | 180613/371472 [3:29:29<15:51:31,  3.34it/s]
 49%|████▊     | 180614/371472 [3:29:29<16:29:16,  3.22it/s]
 49%|████▊     | 180615/371472 [3:29:29<16:12:42,  3.27it/s]
 49%|████▊     | 180616/371472 [3:29:29<15:45:37,  3.36it/s]
 49%|████▊     | 180617/371472 [3:29:30<17:04:26,  3.11it/s]
 49%|████▊     | 180618/371472 [3:29:30<16:32:23,  3.21it/s]
 49%|████▊     | 180619/371472 [3:29:30<16:51:24,  3.14it/s]
 49%|████▊     | 180620/371472 [3:29:31<16:59:52,  3.12it/s]
                                                            
{'loss': 2.9812, 'learning_rate': 5.626440992048955e-07, 'epoch': 7.78}
+
 49%|████▊     | 180620/371472 [3:29:31<16:59:52,  3.12it/s]
 49%|████▊     | 180621/371472 [3:29:31<16:55:33,  3.13it/s]
 49%|████▊     | 180622/371472 [3:29:31<16:24:36,  3.23it/s]
 49%|████▊     | 180623/371472 [3:29:32<16:18:48,  3.25it/s]
 49%|████▊     | 180624/371472 [3:29:32<16:52:13,  3.14it/s]
 49%|████▊     | 180625/371472 [3:29:32<16:41:12,  3.18it/s]
 49%|████▊     | 180626/371472 [3:29:33<17:10:41,  3.09it/s]
 49%|████▊     | 180627/371472 [3:29:33<16:59:38,  3.12it/s]
 49%|████▊     | 180628/371472 [3:29:33<16:21:10,  3.24it/s]
 49%|████▊     | 180629/371472 [3:29:34<15:56:08,  3.33it/s]
 49%|████▊     | 180630/371472 [3:29:34<15:30:48,  3.42it/s]
 49%|████▊     | 180631/371472 [3:29:34<15:36:45,  3.40it/s]
 49%|████▊     | 180632/371472 [3:29:34<15:36:49,  3.40it/s]
 49%|████▊     | 180633/371472 [3:29:35<15:36:58,  3.39it/s]
 49%|████▊     | 180634/371472 [3:29:35<15:37:04,  3.39it/s]
 49%|████▊     | 180635/371472 [3:29:35<15:56:32,  3.33it/s]
 49%|████▊     | 180636/371472 [3:29:36<16:00:06,  3.31it/s]
 49%|████▊     | 180637/371472 [3:29:36<15:38:08,  3.39it/s]
 49%|████▊     | 180638/371472 [3:29:36<15:48:23,  3.35it/s]
 49%|████▊     | 180639/371472 [3:29:36<15:53:09,  3.34it/s]
 49%|████▊     | 180640/371472 [3:29:37<15:58:58,  3.32it/s]
                                                            
{'loss': 2.797, 'learning_rate': 5.625956172294168e-07, 'epoch': 7.78}
+
 49%|████▊     | 180640/371472 [3:29:37<15:58:58,  3.32it/s]
 49%|████▊     | 180641/371472 [3:29:37<16:26:33,  3.22it/s]
 49%|████▊     | 180642/371472 [3:29:37<16:38:31,  3.19it/s]
 49%|████▊     | 180643/371472 [3:29:38<16:37:48,  3.19it/s]
 49%|████▊     | 180644/371472 [3:29:38<17:35:32,  3.01it/s]
 49%|████▊     | 180645/371472 [3:29:38<17:01:35,  3.11it/s]
 49%|████▊     | 180646/371472 [3:29:39<16:32:16,  3.21it/s]
 49%|████▊     | 180647/371472 [3:29:39<16:01:51,  3.31it/s]
 49%|████▊     | 180648/371472 [3:29:39<15:46:45,  3.36it/s]
 49%|████▊     | 180649/371472 [3:29:40<15:50:59,  3.34it/s]
 49%|████▊     | 180650/371472 [3:29:40<15:30:55,  3.42it/s]
 49%|████▊     | 180651/371472 [3:29:40<15:59:32,  3.31it/s]
 49%|████▊     | 180652/371472 [3:29:40<15:49:02,  3.35it/s]
 49%|████▊     | 180653/371472 [3:29:41<15:46:13,  3.36it/s]
 49%|████▊     | 180654/371472 [3:29:41<16:12:21,  3.27it/s]
 49%|████▊     | 180655/371472 [3:29:41<15:58:40,  3.32it/s]
 49%|████▊     | 180656/371472 [3:29:42<15:45:43,  3.36it/s]
 49%|████▊     | 180657/371472 [3:29:42<17:19:38,  3.06it/s]
 49%|████▊     | 180658/371472 [3:29:42<16:24:17,  3.23it/s]
 49%|████▊     | 180659/371472 [3:29:43<15:55:14,  3.33it/s]
 49%|████▊     | 180660/371472 [3:29:43<18:28:13,  2.87it/s]
                                                            
{'loss': 2.7257, 'learning_rate': 5.625471352539378e-07, 'epoch': 7.78}
+
 49%|████▊     | 180660/371472 [3:29:43<18:28:13,  2.87it/s]
 49%|████▊     | 180661/371472 [3:29:43<17:14:35,  3.07it/s]
 49%|████▊     | 180662/371472 [3:29:44<16:26:50,  3.22it/s]
 49%|████▊     | 180663/371472 [3:29:44<16:36:17,  3.19it/s]
 49%|████▊     | 180664/371472 [3:29:44<16:05:19,  3.29it/s]
 49%|████▊     | 180665/371472 [3:29:45<16:49:31,  3.15it/s]
 49%|████▊     | 180666/371472 [3:29:45<16:35:20,  3.19it/s]
 49%|████▊     | 180667/371472 [3:29:45<15:58:47,  3.32it/s]
 49%|████▊     | 180668/371472 [3:29:45<16:34:37,  3.20it/s]
 49%|████▊     | 180669/371472 [3:29:46<16:32:10,  3.21it/s]
 49%|████▊     | 180670/371472 [3:29:46<16:13:05,  3.27it/s]
 49%|████▊     | 180671/371472 [3:29:46<15:38:22,  3.39it/s]
 49%|████▊     | 180672/371472 [3:29:47<15:50:11,  3.35it/s]
 49%|████▊     | 180673/371472 [3:29:47<15:26:17,  3.43it/s]
 49%|████▊     | 180674/371472 [3:29:47<15:39:24,  3.39it/s]
 49%|████▊     | 180675/371472 [3:29:48<15:52:45,  3.34it/s]
 49%|████▊     | 180676/371472 [3:29:48<15:45:50,  3.36it/s]
 49%|████▊     | 180677/371472 [3:29:48<15:55:20,  3.33it/s]
 49%|████▊     | 180678/371472 [3:29:48<15:41:46,  3.38it/s]
 49%|████▊     | 180679/371472 [3:29:49<15:27:10,  3.43it/s]
 49%|████▊     | 180680/371472 [3:29:49<15:55:03,  3.33it/s]
                                                            
{'loss': 3.0094, 'learning_rate': 5.624986532784589e-07, 'epoch': 7.78}
+
 49%|████▊     | 180680/371472 [3:29:49<15:55:03,  3.33it/s]
 49%|████▊     | 180681/371472 [3:29:49<16:54:40,  3.13it/s]
 49%|████▊     | 180682/371472 [3:29:50<17:05:03,  3.10it/s]
 49%|████▊     | 180683/371472 [3:29:50<16:49:38,  3.15it/s]
 49%|████▊     | 180684/371472 [3:29:50<16:12:51,  3.27it/s]
 49%|████▊     | 180685/371472 [3:29:51<15:44:56,  3.37it/s]
 49%|████▊     | 180686/371472 [3:29:51<15:38:40,  3.39it/s]
 49%|████▊     | 180687/371472 [3:29:51<16:07:08,  3.29it/s]
 49%|████▊     | 180688/371472 [3:29:52<16:19:17,  3.25it/s]
 49%|████▊     | 180689/371472 [3:29:52<16:22:18,  3.24it/s]
 49%|████▊     | 180690/371472 [3:29:52<16:11:29,  3.27it/s]
 49%|████▊     | 180691/371472 [3:29:52<15:55:17,  3.33it/s]
 49%|████▊     | 180692/371472 [3:29:53<15:37:52,  3.39it/s]
 49%|████▊     | 180693/371472 [3:29:53<15:30:48,  3.42it/s]
 49%|████▊     | 180694/371472 [3:29:53<15:55:47,  3.33it/s]
 49%|████▊     | 180695/371472 [3:29:54<16:19:39,  3.25it/s]
 49%|████▊     | 180696/371472 [3:29:54<16:12:48,  3.27it/s]
 49%|████▊     | 180697/371472 [3:29:54<16:03:50,  3.30it/s]
 49%|████▊     | 180698/371472 [3:29:55<15:48:24,  3.35it/s]
 49%|████▊     | 180699/371472 [3:29:55<15:39:05,  3.39it/s]
 49%|████▊     | 180700/371472 [3:29:55<15:48:59,  3.35it/s]
                                                            
{'loss': 2.7618, 'learning_rate': 5.6245017130298e-07, 'epoch': 7.78}
+
 49%|████▊     | 180700/371472 [3:29:55<15:48:59,  3.35it/s]
 49%|████▊     | 180701/371472 [3:29:55<15:55:38,  3.33it/s]
 49%|████▊     | 180702/371472 [3:29:56<16:17:38,  3.25it/s]
 49%|████▊     | 180703/371472 [3:29:56<15:58:14,  3.32it/s]
 49%|████▊     | 180704/371472 [3:29:56<16:05:25,  3.29it/s]
 49%|████▊     | 180705/371472 [3:29:57<17:22:55,  3.05it/s]
 49%|████▊     | 180706/371472 [3:29:57<16:47:40,  3.16it/s]
 49%|████▊     | 180707/371472 [3:29:57<17:23:16,  3.05it/s]
 49%|████▊     | 180708/371472 [3:29:58<16:51:47,  3.14it/s]
 49%|████▊     | 180709/371472 [3:29:58<16:06:25,  3.29it/s]
 49%|████▊     | 180710/371472 [3:29:58<16:03:40,  3.30it/s]
 49%|████▊     | 180711/371472 [3:29:59<16:22:37,  3.24it/s]
 49%|████▊     | 180712/371472 [3:29:59<16:19:17,  3.25it/s]
 49%|████▊     | 180713/371472 [3:29:59<16:13:12,  3.27it/s]
 49%|████▊     | 180714/371472 [3:29:59<15:45:14,  3.36it/s]
 49%|████▊     | 180715/371472 [3:30:00<16:14:56,  3.26it/s]
 49%|████▊     | 180716/371472 [3:30:00<15:42:51,  3.37it/s]
 49%|████▊     | 180717/371472 [3:30:00<15:38:24,  3.39it/s]
 49%|████▊     | 180718/371472 [3:30:01<16:19:43,  3.25it/s]
 49%|████▊     | 180719/371472 [3:30:01<16:00:21,  3.31it/s]
 49%|████▊     | 180720/371472 [3:30:01<15:27:05,  3.43it/s]
                                                            
{'loss': 2.8389, 'learning_rate': 5.624016893275013e-07, 'epoch': 7.78}
+
 49%|████▊     | 180720/371472 [3:30:01<15:27:05,  3.43it/s]
 49%|████▊     | 180721/371472 [3:30:02<15:07:13,  3.50it/s]
 49%|████▊     | 180722/371472 [3:30:02<15:08:54,  3.50it/s]
 49%|████▊     | 180723/371472 [3:30:02<16:54:51,  3.13it/s]
 49%|████▊     | 180724/371472 [3:30:02<16:34:43,  3.20it/s]
 49%|████▊     | 180725/371472 [3:30:03<16:13:23,  3.27it/s]
 49%|████▊     | 180726/371472 [3:30:03<17:31:18,  3.02it/s]
 49%|████▊     | 180727/371472 [3:30:04<17:44:04,  2.99it/s]
 49%|████▊     | 180728/371472 [3:30:04<17:16:29,  3.07it/s]
 49%|████▊     | 180729/371472 [3:30:04<17:03:00,  3.11it/s]
 49%|████▊     | 180730/371472 [3:30:04<16:17:57,  3.25it/s]
 49%|████▊     | 180731/371472 [3:30:05<16:16:59,  3.25it/s]
 49%|████▊     | 180732/371472 [3:30:05<15:59:24,  3.31it/s]
 49%|████▊     | 180733/371472 [3:30:05<15:29:18,  3.42it/s]
 49%|████▊     | 180734/371472 [3:30:06<16:15:02,  3.26it/s]
 49%|████▊     | 180735/371472 [3:30:06<15:42:14,  3.37it/s]
 49%|████▊     | 180736/371472 [3:30:06<15:28:27,  3.42it/s]
 49%|██��█▊     | 180737/371472 [3:30:06<15:27:49,  3.43it/s]
 49%|████▊     | 180738/371472 [3:30:07<16:39:54,  3.18it/s]
 49%|████▊     | 180739/371472 [3:30:07<17:17:19,  3.06it/s]
 49%|████▊     | 180740/371472 [3:30:08<17:28:07,  3.03it/s]
                                                            
{'loss': 2.7675, 'learning_rate': 5.623532073520222e-07, 'epoch': 7.78}
+
 49%|████▊     | 180740/371472 [3:30:08<17:28:07,  3.03it/s]
 49%|████▊     | 180741/371472 [3:30:08<17:16:14,  3.07it/s]
 49%|████▊     | 180742/371472 [3:30:08<16:38:00,  3.19it/s]
 49%|████▊     | 180743/371472 [3:30:08<16:19:38,  3.24it/s]
 49%|████▊     | 180744/371472 [3:30:09<16:34:49,  3.20it/s]
 49%|████▊     | 180745/371472 [3:30:09<15:48:47,  3.35it/s]
 49%|████▊     | 180746/371472 [3:30:09<15:23:04,  3.44it/s]
 49%|████▊     | 180747/371472 [3:30:10<15:36:48,  3.39it/s]
 49%|████▊     | 180748/371472 [3:30:10<16:45:54,  3.16it/s]
 49%|████▊     | 180749/371472 [3:30:10<16:30:50,  3.21it/s]
 49%|████▊     | 180750/371472 [3:30:11<16:18:36,  3.25it/s]
 49%|████▊     | 180751/371472 [3:30:11<16:02:46,  3.30it/s]
 49%|████▊     | 180752/371472 [3:30:11<15:56:01,  3.32it/s]
 49%|████▊     | 180753/371472 [3:30:11<15:35:57,  3.40it/s]
 49%|████▊     | 180754/371472 [3:30:12<15:45:38,  3.36it/s]
 49%|████▊     | 180755/371472 [3:30:12<15:39:16,  3.38it/s]
 49%|████▊     | 180756/371472 [3:30:12<16:08:43,  3.28it/s]
 49%|████▊     | 180757/371472 [3:30:13<15:33:55,  3.40it/s]
 49%|████▊     | 180758/371472 [3:30:13<15:40:26,  3.38it/s]
 49%|████▊     | 180759/371472 [3:30:13<16:06:05,  3.29it/s]
 49%|████▊     | 180760/371472 [3:30:14<15:41:37,  3.38it/s]
                                                            
{'loss': 2.8425, 'learning_rate': 5.623047253765433e-07, 'epoch': 7.79}
+
 49%|████▊     | 180760/371472 [3:30:14<15:41:37,  3.38it/s]
 49%|████▊     | 180761/371472 [3:30:14<15:34:40,  3.40it/s]
 49%|████▊     | 180762/371472 [3:30:14<15:35:48,  3.40it/s]
 49%|████▊     | 180763/371472 [3:30:14<15:40:41,  3.38it/s]
 49%|████▊     | 180764/371472 [3:30:15<15:40:59,  3.38it/s]
 49%|████▊     | 180765/371472 [3:30:15<15:50:10,  3.35it/s]
 49%|████▊     | 180766/371472 [3:30:15<16:09:41,  3.28it/s]
 49%|████▊     | 180767/371472 [3:30:16<16:12:52,  3.27it/s]
 49%|████▊     | 180768/371472 [3:30:16<15:59:40,  3.31it/s]
 49%|████▊     | 180769/371472 [3:30:16<16:21:58,  3.24it/s]
 49%|████▊     | 180770/371472 [3:30:17<16:15:23,  3.26it/s]
 49%|████▊     | 180771/371472 [3:30:17<16:10:38,  3.27it/s]
 49%|████▊     | 180772/371472 [3:30:17<16:14:57,  3.26it/s]
 49%|████▊     | 180773/371472 [3:30:17<16:32:41,  3.20it/s]
 49%|████▊     | 180774/371472 [3:30:18<18:05:01,  2.93it/s]
 49%|████▊     | 180775/371472 [3:30:18<17:12:42,  3.08it/s]
 49%|████▊     | 180776/371472 [3:30:18<16:54:04,  3.13it/s]
 49%|████▊     | 180777/371472 [3:30:19<16:41:19,  3.17it/s]
 49%|████▊     | 180778/371472 [3:30:19<16:26:39,  3.22it/s]
 49%|████▊     | 180779/371472 [3:30:19<16:38:58,  3.18it/s]
 49%|████▊     | 180780/371472 [3:30:20<16:15:00,  3.26it/s]
                                                            
{'loss': 2.9683, 'learning_rate': 5.622562434010645e-07, 'epoch': 7.79}
+
 49%|████▊     | 180780/371472 [3:30:20<16:15:00,  3.26it/s]
 49%|████▊     | 180781/371472 [3:30:20<15:36:07,  3.40it/s]
 49%|████▊     | 180782/371472 [3:30:20<15:42:27,  3.37it/s]
 49%|████▊     | 180783/371472 [3:30:21<15:47:43,  3.35it/s]
 49%|████▊     | 180784/371472 [3:30:21<16:35:37,  3.19it/s]
 49%|████▊     | 180785/371472 [3:30:21<16:34:20,  3.20it/s]
 49%|████▊     | 180786/371472 [3:30:22<15:55:07,  3.33it/s]
 49%|████▊     | 180787/371472 [3:30:22<15:54:18,  3.33it/s]
 49%|████▊     | 180788/371472 [3:30:22<15:34:25,  3.40it/s]
 49%|████▊     | 180789/371472 [3:30:22<15:50:56,  3.34it/s]
 49%|████▊     | 180790/371472 [3:30:23<16:09:53,  3.28it/s]
 49%|████▊     | 180791/371472 [3:30:23<16:32:21,  3.20it/s]
 49%|████▊     | 180792/371472 [3:30:23<15:58:47,  3.31it/s]
 49%|████▊     | 180793/371472 [3:30:24<16:04:01,  3.30it/s]
 49%|████▊     | 180794/371472 [3:30:24<16:45:59,  3.16it/s]
 49%|████▊     | 180795/371472 [3:30:24<16:49:10,  3.15it/s]
 49%|████▊     | 180796/371472 [3:30:25<16:32:31,  3.20it/s]
 49%|████▊     | 180797/371472 [3:30:25<16:00:24,  3.31it/s]
 49%|████▊     | 180798/371472 [3:30:25<15:35:22,  3.40it/s]
 49%|████▊     | 180799/371472 [3:30:25<15:26:15,  3.43it/s]
 49%|████▊     | 180800/371472 [3:30:26<16:09:13,  3.28it/s]
                                                            
{'loss': 2.9076, 'learning_rate': 5.622077614255855e-07, 'epoch': 7.79}
+
 49%|████▊     | 180800/371472 [3:30:26<16:09:13,  3.28it/s]
 49%|████▊     | 180801/371472 [3:30:26<15:40:42,  3.38it/s]
 49%|████▊     | 180802/371472 [3:30:26<15:58:49,  3.31it/s]
 49%|████▊     | 180803/371472 [3:30:27<16:51:56,  3.14it/s]
 49%|████▊     | 180804/371472 [3:30:27<16:08:40,  3.28it/s]
 49%|████▊     | 180805/371472 [3:30:27<15:48:12,  3.35it/s]
 49%|████▊     | 180806/371472 [3:30:28<15:44:21,  3.37it/s]
 49%|████▊     | 180807/371472 [3:30:28<15:39:35,  3.38it/s]
 49%|████▊     | 180808/371472 [3:30:28<15:36:00,  3.39it/s]
 49%|████▊     | 180809/371472 [3:30:28<15:35:50,  3.40it/s]
 49%|████▊     | 180810/371472 [3:30:29<15:18:21,  3.46it/s]
 49%|████▊     | 180811/371472 [3:30:29<15:32:58,  3.41it/s]
 49%|████▊     | 180812/371472 [3:30:29<15:25:16,  3.43it/s]
 49%|████▊     | 180813/371472 [3:30:30<15:30:46,  3.41it/s]
 49%|████▊     | 180814/371472 [3:30:30<16:00:55,  3.31it/s]
 49%|████▊     | 180815/371472 [3:30:30<16:22:25,  3.23it/s]
 49%|████▊     | 180816/371472 [3:30:31<16:42:12,  3.17it/s]
 49%|████▊     | 180817/371472 [3:30:31<16:06:28,  3.29it/s]
 49%|████▊     | 180818/371472 [3:30:31<19:01:39,  2.78it/s]
 49%|████▊     | 180819/371472 [3:30:32<18:05:27,  2.93it/s]
 49%|████▊     | 180820/371472 [3:30:32<17:21:43,  3.05it/s]
                                                            
{'loss': 2.9029, 'learning_rate': 5.621592794501066e-07, 'epoch': 7.79}
+
 49%|████▊     | 180820/371472 [3:30:32<17:21:43,  3.05it/s]
 49%|████▊     | 180821/371472 [3:30:32<17:31:41,  3.02it/s]
 49%|████▊     | 180822/371472 [3:30:33<17:34:06,  3.01it/s]
 49%|████▊     | 180823/371472 [3:30:33<16:49:22,  3.15it/s]
 49%|████▊     | 180824/371472 [3:30:33<16:18:11,  3.25it/s]
 49%|████▊     | 180825/371472 [3:30:33<16:11:35,  3.27it/s]
 49%|████▊     | 180826/371472 [3:30:34<15:59:22,  3.31it/s]
 49%|████▊     | 180827/371472 [3:30:34<15:27:37,  3.43it/s]
 49%|████▊     | 180828/371472 [3:30:34<15:07:15,  3.50it/s]
 49%|████▊     | 180829/371472 [3:30:35<16:04:39,  3.29it/s]
 49%|████▊     | 180830/371472 [3:30:35<16:40:44,  3.18it/s]
 49%|████▊     | 180831/371472 [3:30:35<16:05:40,  3.29it/s]
 49%|████▊     | 180832/371472 [3:30:36<16:09:15,  3.28it/s]
 49%|████▊     | 180833/371472 [3:30:36<15:50:41,  3.34it/s]
 49%|████▊     | 180834/371472 [3:30:36<15:17:21,  3.46it/s]
 49%|████▊     | 180835/371472 [3:30:36<15:18:33,  3.46it/s]
 49%|████▊     | 180836/371472 [3:30:37<15:16:54,  3.47it/s]
 49%|████▊     | 180837/371472 [3:30:37<15:24:55,  3.44it/s]
 49%|████▊     | 180838/371472 [3:30:37<15:36:38,  3.39it/s]
 49%|████▊     | 180839/371472 [3:30:38<16:07:00,  3.29it/s]
 49%|████▊     | 180840/371472 [3:30:38<16:56:40,  3.13it/s]
                                                            
{'loss': 2.9947, 'learning_rate': 5.621107974746277e-07, 'epoch': 7.79}
+
 49%|████▊     | 180840/371472 [3:30:38<16:56:40,  3.13it/s]
 49%|████▊     | 180841/371472 [3:30:38<16:36:33,  3.19it/s]
 49%|████▊     | 180842/371472 [3:30:39<16:26:17,  3.22it/s]
 49%|████▊     | 180843/371472 [3:30:39<17:32:07,  3.02it/s]
 49%|████▊     | 180844/371472 [3:30:39<17:21:58,  3.05it/s]
 49%|████▊     | 180845/371472 [3:30:40<16:46:25,  3.16it/s]
 49%|████▊     | 180846/371472 [3:30:40<16:27:11,  3.22it/s]
 49%|████▊     | 180847/371472 [3:30:40<16:10:37,  3.27it/s]
 49%|████▊     | 180848/371472 [3:30:40<16:07:20,  3.28it/s]
 49%|████▊     | 180849/371472 [3:30:41<16:22:04,  3.24it/s]
 49%|████▊     | 180850/371472 [3:30:41<16:01:44,  3.30it/s]
 49%|████▊     | 180851/371472 [3:30:41<15:42:06,  3.37it/s]
 49%|████▊     | 180852/371472 [3:30:42<15:37:12,  3.39it/s]
 49%|████▊     | 180853/371472 [3:30:42<15:11:18,  3.49it/s]
 49%|████▊     | 180854/371472 [3:30:42<15:14:44,  3.47it/s]
 49%|████▊     | 180855/371472 [3:30:43<16:10:39,  3.27it/s]
 49%|████▊     | 180856/371472 [3:30:43<15:33:39,  3.40it/s]
 49%|████▊     | 180857/371472 [3:30:43<16:24:42,  3.23it/s]
 49%|████▊     | 180858/371472 [3:30:43<16:13:06,  3.26it/s]
 49%|████▊     | 180859/371472 [3:30:44<16:03:59,  3.30it/s]
 49%|████▊     | 180860/371472 [3:30:44<15:26:56,  3.43it/s]
                                                            
{'loss': 2.9691, 'learning_rate': 5.620623154991489e-07, 'epoch': 7.79}
+
 49%|████▊     | 180860/371472 [3:30:44<15:26:56,  3.43it/s]
 49%|��███▊     | 180861/371472 [3:30:44<15:12:09,  3.48it/s]
 49%|████▊     | 180862/371472 [3:30:45<15:01:11,  3.53it/s]
 49%|████▊     | 180863/371472 [3:30:45<15:12:44,  3.48it/s]
 49%|████▊     | 180864/371472 [3:30:45<15:18:18,  3.46it/s]
 49%|████▊     | 180865/371472 [3:30:46<16:08:27,  3.28it/s]
 49%|████▊     | 180866/371472 [3:30:46<16:20:26,  3.24it/s]
 49%|████▊     | 180867/371472 [3:30:46<16:00:58,  3.31it/s]
 49%|████▊     | 180868/371472 [3:30:46<15:35:13,  3.40it/s]
 49%|████▊     | 180869/371472 [3:30:47<16:10:44,  3.27it/s]
 49%|████▊     | 180870/371472 [3:30:47<17:45:09,  2.98it/s]
 49%|████▊     | 180871/371472 [3:30:47<17:29:33,  3.03it/s]
 49%|████▊     | 180872/371472 [3:30:48<16:46:44,  3.16it/s]
 49%|████▊     | 180873/371472 [3:30:48<17:54:11,  2.96it/s]
 49%|████▊     | 180874/371472 [3:30:48<17:16:05,  3.07it/s]
 49%|████▊     | 180875/371472 [3:30:49<17:11:55,  3.08it/s]
 49%|████▊     | 180876/371472 [3:30:49<16:36:34,  3.19it/s]
 49%|████▊     | 180877/371472 [3:30:49<16:31:04,  3.21it/s]
 49%|████▊     | 180878/371472 [3:30:50<16:04:03,  3.29it/s]
 49%|████▊     | 180879/371472 [3:30:50<15:40:52,  3.38it/s]
 49%|████▊     | 180880/371472 [3:30:50<15:28:52,  3.42it/s]
                                                            
{'loss': 3.0655, 'learning_rate': 5.6201383352367e-07, 'epoch': 7.79}
+
 49%|████▊     | 180880/371472 [3:30:50<15:28:52,  3.42it/s]
 49%|████▊     | 180881/371472 [3:30:51<16:03:02,  3.30it/s]
 49%|████▊     | 180882/371472 [3:30:51<16:10:42,  3.27it/s]
 49%|████▊     | 180883/371472 [3:30:51<16:28:41,  3.21it/s]
 49%|████▊     | 180884/371472 [3:30:51<16:19:57,  3.24it/s]
 49%|████▊     | 180885/371472 [3:30:52<16:11:56,  3.27it/s]
 49%|████▊     | 180886/371472 [3:30:52<16:12:31,  3.27it/s]
 49%|████▊     | 180887/371472 [3:30:52<15:31:13,  3.41it/s]
 49%|████▊     | 180888/371472 [3:30:53<15:25:19,  3.43it/s]
 49%|████▊     | 180889/371472 [3:30:53<15:17:13,  3.46it/s]
 49%|████▊     | 180890/371472 [3:30:53<16:09:49,  3.28it/s]
 49%|████▊     | 180891/371472 [3:30:54<15:57:25,  3.32it/s]
 49%|████▊     | 180892/371472 [3:30:54<16:20:13,  3.24it/s]
 49%|████▊     | 180893/371472 [3:30:54<15:47:42,  3.35it/s]
 49%|████▊     | 180894/371472 [3:30:54<15:11:18,  3.49it/s]
 49%|████▊     | 180895/371472 [3:30:55<15:03:36,  3.52it/s]
 49%|████▊     | 180896/371472 [3:30:55<15:44:14,  3.36it/s]
 49%|████▊     | 180897/371472 [3:30:55<15:50:53,  3.34it/s]
 49%|████▊     | 180898/371472 [3:30:56<15:22:59,  3.44it/s]
 49%|████▊     | 180899/371472 [3:30:56<15:25:48,  3.43it/s]
 49%|████▊     | 180900/371472 [3:30:56<15:35:30,  3.40it/s]
                                                            
{'loss': 2.7746, 'learning_rate': 5.619653515481911e-07, 'epoch': 7.79}
+
 49%|████▊     | 180900/371472 [3:30:56<15:35:30,  3.40it/s]
 49%|████▊     | 180901/371472 [3:30:56<15:49:15,  3.35it/s]
 49%|████▊     | 180902/371472 [3:30:57<15:40:57,  3.38it/s]
 49%|████▊     | 180903/371472 [3:30:57<15:56:36,  3.32it/s]
 49%|████▊     | 180904/371472 [3:30:57<15:36:37,  3.39it/s]
 49%|████▊     | 180905/371472 [3:30:58<15:38:09,  3.39it/s]
 49%|████▊     | 180906/371472 [3:30:58<15:41:41,  3.37it/s]
 49%|████▊     | 180907/371472 [3:30:58<16:29:25,  3.21it/s]
 49%|████▊     | 180908/371472 [3:30:59<16:17:40,  3.25it/s]
 49%|████▊     | 180909/371472 [3:30:59<16:11:07,  3.27it/s]
 49%|████▊     | 180910/371472 [3:30:59<16:02:52,  3.30it/s]
 49%|████▊     | 180911/371472 [3:31:00<15:57:06,  3.32it/s]
 49%|████▊     | 180912/371472 [3:31:00<16:18:58,  3.24it/s]
 49%|████▊     | 180913/371472 [3:31:00<16:04:56,  3.29it/s]
 49%|████▊     | 180914/371472 [3:31:00<15:39:02,  3.38it/s]
 49%|████▊     | 180915/371472 [3:31:01<16:53:12,  3.13it/s]
 49%|████▊     | 180916/371472 [3:31:01<17:35:41,  3.01it/s]
 49%|████▊     | 180917/371472 [3:31:01<16:58:36,  3.12it/s]
 49%|████▊     | 180918/371472 [3:31:02<17:29:02,  3.03it/s]
 49%|████▊     | 180919/371472 [3:31:02<16:41:00,  3.17it/s]
 49%|████▊     | 180920/371472 [3:31:02<16:26:44,  3.22it/s]
                                                            
{'loss': 2.8569, 'learning_rate': 5.619168695727122e-07, 'epoch': 7.79}
+
 49%|████▊     | 180920/371472 [3:31:02<16:26:44,  3.22it/s]
 49%|████▊     | 180921/371472 [3:31:03<16:03:06,  3.30it/s]
 49%|████▊     | 180922/371472 [3:31:03<15:51:53,  3.34it/s]
 49%|████▊     | 180923/371472 [3:31:03<15:26:20,  3.43it/s]
 49%|████▊     | 180924/371472 [3:31:04<15:16:21,  3.47it/s]
 49%|████▊     | 180925/371472 [3:31:04<15:29:16,  3.42it/s]
 49%|████▊     | 180926/371472 [3:31:04<15:41:28,  3.37it/s]
 49%|████▊     | 180927/371472 [3:31:04<15:36:40,  3.39it/s]
 49%|████▊     | 180928/371472 [3:31:05<15:40:10,  3.38it/s]
 49%|████▊     | 180929/371472 [3:31:05<16:15:16,  3.26it/s]
 49%|████▊     | 180930/371472 [3:31:05<16:36:10,  3.19it/s]
 49%|████▊     | 180931/371472 [3:31:06<17:22:56,  3.04it/s]
 49%|████▊     | 180932/371472 [3:31:06<17:14:48,  3.07it/s]
 49%|████▊     | 180933/371472 [3:31:06<16:40:39,  3.17it/s]
 49%|████▊     | 180934/371472 [3:31:07<17:38:10,  3.00it/s]
 49%|████▊     | 180935/371472 [3:31:07<17:48:48,  2.97it/s]
 49%|████▊     | 180936/371472 [3:31:07<19:11:10,  2.76it/s]
 49%|████▊     | 180937/371472 [3:31:08<19:48:56,  2.67it/s]
 49%|████▊     | 180938/371472 [3:31:08<19:22:38,  2.73it/s]
 49%|████▊     | 180939/371472 [3:31:09<18:12:52,  2.91it/s]
 49%|████▊     | 180940/371472 [3:31:09<17:33:35,  3.01it/s]
                                                            
{'loss': 2.8128, 'learning_rate': 5.618683875972333e-07, 'epoch': 7.79}
+
 49%|████▊     | 180940/371472 [3:31:09<17:33:35,  3.01it/s]
 49%|████▊     | 180941/371472 [3:31:09<16:53:56,  3.13it/s]
 49%|████▊     | 180942/371472 [3:31:09<16:11:50,  3.27it/s]
 49%|████▊     | 180943/371472 [3:31:10<16:04:40,  3.29it/s]
 49%|████▊     | 180944/371472 [3:31:10<16:12:16,  3.27it/s]
 49%|████▊     | 180945/371472 [3:31:10<16:06:32,  3.29it/s]
 49%|████▊     | 180946/371472 [3:31:11<16:35:25,  3.19it/s]
 49%|████▊     | 180947/371472 [3:31:11<16:18:56,  3.24it/s]
 49%|████▊     | 180948/371472 [3:31:11<15:54:09,  3.33it/s]
 49%|████▊     | 180949/371472 [3:31:12<16:02:21,  3.30it/s]
 49%|████▊     | 180950/371472 [3:31:12<16:06:20,  3.29it/s]
 49%|████▊     | 180951/371472 [3:31:12<16:08:46,  3.28it/s]
 49%|████▊     | 180952/371472 [3:31:12<15:54:32,  3.33it/s]
 49%|████▊     | 180953/371472 [3:31:13<16:25:34,  3.22it/s]
 49%|████▊     | 180954/371472 [3:31:13<15:56:00,  3.32it/s]
 49%|████▊     | 180955/371472 [3:31:13<15:46:24,  3.36it/s]
 49%|████▊     | 180956/371472 [3:31:14<16:01:27,  3.30it/s]
 49%|████▊     | 180957/371472 [3:31:14<16:03:47,  3.29it/s]
 49%|████▊     | 180958/371472 [3:31:14<15:41:10,  3.37it/s]
 49%|████▊     | 180959/371472 [3:31:15<16:14:17,  3.26it/s]
 49%|████▊     | 180960/371472 [3:31:15<16:01:43,  3.30it/s]
                                                            
{'loss': 2.9037, 'learning_rate': 5.618199056217543e-07, 'epoch': 7.79}
+
 49%|████▊     | 180960/371472 [3:31:15<16:01:43,  3.30it/s]
 49%|████▊     | 180961/371472 [3:31:15<16:01:30,  3.30it/s]
 49%|████▊     | 180962/371472 [3:31:15<15:52:02,  3.34it/s]
 49%|████▊     | 180963/371472 [3:31:16<15:53:32,  3.33it/s]
 49%|████▊     | 180964/371472 [3:31:16<16:32:02,  3.20it/s]
 49%|████▊     | 180965/371472 [3:31:16<16:20:29,  3.24it/s]
 49%|████▊     | 180966/371472 [3:31:17<17:01:18,  3.11it/s]
 49%|████▊     | 180967/371472 [3:31:17<16:29:28,  3.21it/s]
 49%|████▊     | 180968/371472 [3:31:17<16:16:34,  3.25it/s]
 49%|████▊     | 180969/371472 [3:31:18<16:31:42,  3.20it/s]
 49%|████▊     | 180970/371472 [3:31:18<16:16:20,  3.25it/s]
 49%|████▊     | 180971/371472 [3:31:18<16:44:23,  3.16it/s]
 49%|████▊     | 180972/371472 [3:31:19<16:31:00,  3.20it/s]
 49%|████▊     | 180973/371472 [3:31:19<15:47:26,  3.35it/s]
 49%|████▊     | 180974/371472 [3:31:19<15:37:09,  3.39it/s]
 49%|████▊     | 180975/371472 [3:31:19<15:54:08,  3.33it/s]
 49%|████▊     | 180976/371472 [3:31:20<15:56:56,  3.32it/s]
 49%|████▊     | 180977/371472 [3:31:20<16:02:35,  3.30it/s]
 49%|████▊     | 180978/371472 [3:31:20<16:18:36,  3.24it/s]
 49%|████▊     | 180979/371472 [3:31:21<17:43:03,  2.99it/s]
 49%|████▊     | 180980/371472 [3:31:21<17:05:12,  3.10it/s]
                                                            
{'loss': 2.7566, 'learning_rate': 5.617714236462754e-07, 'epoch': 7.8}
+
 49%|████▊     | 180980/371472 [3:31:21<17:05:12,  3.10it/s]
 49%|████▊     | 180981/371472 [3:31:21<16:24:37,  3.22it/s]
 49%|████▊     | 180982/371472 [3:31:22<16:22:38,  3.23it/s]
 49%|████▊     | 180983/371472 [3:31:22<16:56:02,  3.12it/s]
 49%|████▊     | 180984/371472 [3:31:22<16:17:25,  3.25it/s]
 49%|████▊     | 180985/371472 [3:31:23<15:49:45,  3.34it/s]
 49%|████▊     | 180986/371472 [3:31:23<15:31:26,  3.41it/s]
 49%|████▊     | 180987/371472 [3:31:23<15:58:36,  3.31it/s]
 49%|████▊     | 180988/371472 [3:31:24<16:46:32,  3.15it/s]
 49%|████▊     | 180989/371472 [3:31:24<16:16:25,  3.25it/s]
 49%|████▊     | 180990/371472 [3:31:24<15:44:18,  3.36it/s]
 49%|████▊     | 180991/371472 [3:31:24<15:39:57,  3.38it/s]
 49%|████▊     | 180992/371472 [3:31:25<15:39:57,  3.38it/s]
 49%|████▊     | 180993/371472 [3:31:25<15:12:05,  3.48it/s]
 49%|████▊     | 180994/371472 [3:31:25<15:28:07,  3.42it/s]
 49%|████▊     | 180995/371472 [3:31:26<15:36:23,  3.39it/s]
 49%|████▊     | 180996/371472 [3:31:26<15:15:23,  3.47it/s]
 49%|████▊     | 180997/371472 [3:31:26<15:04:18,  3.51it/s]
 49%|████▊     | 180998/371472 [3:31:26<14:57:41,  3.54it/s]
 49%|████▊     | 180999/371472 [3:31:27<14:59:12,  3.53it/s]
 49%|████▊     | 181000/371472 [3:31:27<15:06:17,  3.50it/s]
                                                            
{'loss': 2.8804, 'learning_rate': 5.617229416707966e-07, 'epoch': 7.8}
+
 49%|████▊     | 181000/371472 [3:31:27<15:06:17,  3.50it/s]
 49%|████▊     | 181001/371472 [3:31:27<15:14:24,  3.47it/s]
 49%|████▊     | 181002/371472 [3:31:28<15:21:32,  3.44it/s]
 49%|████▊     | 181003/371472 [3:31:28<15:14:47,  3.47it/s]
 49%|████▊     | 181004/371472 [3:31:28<15:43:13,  3.37it/s]
 49%|████▊     | 181005/371472 [3:31:28<15:41:14,  3.37it/s]
 49%|████▊     | 181006/371472 [3:31:29<16:12:13,  3.27it/s]
 49%|████▊     | 181007/371472 [3:31:29<17:28:15,  3.03it/s]
 49%|████▊     | 181008/371472 [3:31:29<16:58:35,  3.12it/s]
 49%|████▊     | 181009/371472 [3:31:30<16:40:43,  3.17it/s]
 49%|████▊     | 181010/371472 [3:31:30<17:50:33,  2.97it/s]
 49%|████▊     | 181011/371472 [3:31:30<17:31:22,  3.02it/s]
 49%|████▊     | 181012/371472 [3:31:31<16:57:57,  3.12it/s]
 49%|████▊     | 181013/371472 [3:31:31<16:33:46,  3.19it/s]
 49%|████▊     | 181014/371472 [3:31:31<18:12:38,  2.91it/s]
 49%|████▊     | 181015/371472 [3:31:32<17:24:07,  3.04it/s]
 49%|████▊     | 181016/371472 [3:31:32<16:47:42,  3.15it/s]
 49%|████▊     | 181017/371472 [3:31:32<16:26:44,  3.22it/s]
 49%|████▊     | 181018/371472 [3:31:33<15:58:45,  3.31it/s]
 49%|████▊     | 181019/371472 [3:31:33<17:05:04,  3.10it/s]
 49%|████▊     | 181020/371472 [3:31:33<16:51:52,  3.14it/s]
                                                            
{'loss': 2.7942, 'learning_rate': 5.616744596953178e-07, 'epoch': 7.8}
+
 49%|████▊     | 181020/371472 [3:31:33<16:51:52,  3.14it/s]
 49%|████▊     | 181021/371472 [3:31:34<16:38:13,  3.18it/s]
 49%|████▊     | 181022/371472 [3:31:34<16:07:15,  3.28it/s]
 49%|████▊     | 181023/371472 [3:31:34<16:33:37,  3.19it/s]
 49%|████▊     | 181024/371472 [3:31:35<16:23:07,  3.23it/s]
 49%|████▊     | 181025/371472 [3:31:35<16:21:28,  3.23it/s]
 49%|████▊     | 181026/371472 [3:31:35<15:49:28,  3.34it/s]
 49%|████▊     | 181027/371472 [3:31:35<15:42:59,  3.37it/s]
 49%|████▊     | 181028/371472 [3:31:36<16:09:03,  3.28it/s]
 49%|████▊     | 181029/371472 [3:31:36<15:50:03,  3.34it/s]
 49%|████▊     | 181030/371472 [3:31:36<16:10:01,  3.27it/s]
 49%|████▊     | 181031/371472 [3:31:37<16:26:40,  3.22it/s]
 49%|████▊     | 181032/371472 [3:31:37<15:56:58,  3.32it/s]
 49%|████▊     | 181033/371472 [3:31:37<15:25:13,  3.43it/s]
 49%|████▊     | 181034/371472 [3:31:38<15:55:41,  3.32it/s]
 49%|████▊     | 181035/371472 [3:31:38<18:07:39,  2.92it/s]
 49%|████▊     | 181036/371472 [3:31:38<17:28:49,  3.03it/s]
 49%|████▊     | 181037/371472 [3:31:39<16:54:02,  3.13it/s]
 49%|████▊     | 181038/371472 [3:31:39<16:26:07,  3.22it/s]
 49%|████▊     | 181039/371472 [3:31:39<16:17:09,  3.25it/s]
 49%|████▊     | 181040/371472 [3:31:40<17:09:52,  3.08it/s]
                                                            
{'loss': 2.8969, 'learning_rate': 5.616259777198388e-07, 'epoch': 7.8}
+
 49%|████▊     | 181040/371472 [3:31:40<17:09:52,  3.08it/s]
 49%|████▊     | 181041/371472 [3:31:40<16:47:42,  3.15it/s]
 49%|████▊     | 181042/371472 [3:31:40<16:08:46,  3.28it/s]
 49%|████▊     | 181043/371472 [3:31:40<15:39:02,  3.38it/s]
 49%|████▊     | 181044/371472 [3:31:41<16:00:36,  3.30it/s]
 49%|████▊     | 181045/371472 [3:31:41<16:57:00,  3.12it/s]
 49%|████▊     | 181046/371472 [3:31:41<17:00:13,  3.11it/s]
 49%|████▊     | 181047/371472 [3:31:42<16:43:06,  3.16it/s]
 49%|████▊     | 181048/371472 [3:31:42<16:18:38,  3.24it/s]
 49%|████▊     | 181049/371472 [3:31:42<15:48:15,  3.35it/s]
 49%|████▊     | 181050/371472 [3:31:43<15:22:17,  3.44it/s]
 49%|████▊     | 181051/371472 [3:31:43<15:17:42,  3.46it/s]
 49%|████▊     | 181052/371472 [3:31:43<16:03:50,  3.29it/s]
 49%|████▊     | 181053/371472 [3:31:43<15:33:24,  3.40it/s]
 49%|████▊     | 181054/371472 [3:31:44<15:47:21,  3.35it/s]
 49%|████▊     | 181055/371472 [3:31:44<15:39:03,  3.38it/s]
 49%|████▊     | 181056/371472 [3:31:44<15:55:18,  3.32it/s]
 49%|████▊     | 181057/371472 [3:31:45<15:51:15,  3.34it/s]
 49%|████▊     | 181058/371472 [3:31:45<15:42:16,  3.37it/s]
 49%|████▊     | 181059/371472 [3:31:45<16:07:25,  3.28it/s]
 49%|████▊     | 181060/371472 [3:31:46<15:53:22,  3.33it/s]
                                                            
{'loss': 2.9761, 'learning_rate': 5.615774957443599e-07, 'epoch': 7.8}
+
 49%|████▊     | 181060/371472 [3:31:46<15:53:22,  3.33it/s]
 49%|████▊     | 181061/371472 [3:31:46<15:31:52,  3.41it/s]
 49%|████▊     | 181062/371472 [3:31:46<15:18:25,  3.46it/s]
 49%|████▊     | 181063/371472 [3:31:46<15:21:14,  3.44it/s]
 49%|████▊     | 181064/371472 [3:31:47<15:47:12,  3.35it/s]
 49%|████▊     | 181065/371472 [3:31:47<15:45:01,  3.36it/s]
 49%|████▊     | 181066/371472 [3:31:47<16:08:27,  3.28it/s]
 49%|████▊     | 181067/371472 [3:31:48<16:36:40,  3.18it/s]
 49%|████▊     | 181068/371472 [3:31:48<16:37:59,  3.18it/s]
 49%|████▊     | 181069/371472 [3:31:48<16:44:01,  3.16it/s]
 49%|████▊     | 181070/371472 [3:31:49<16:36:18,  3.19it/s]
 49%|████▊     | 181071/371472 [3:31:49<17:03:25,  3.10it/s]
 49%|████▊     | 181072/371472 [3:31:49<16:34:35,  3.19it/s]
 49%|████▊     | 181073/371472 [3:31:49<15:53:54,  3.33it/s]
 49%|████▊     | 181074/371472 [3:31:50<16:12:35,  3.26it/s]
 49%|████▊     | 181075/371472 [3:31:50<15:39:06,  3.38it/s]
 49%|████▊     | 181076/371472 [3:31:50<15:22:32,  3.44it/s]
 49%|████▊     | 181077/371472 [3:31:51<16:06:24,  3.28it/s]
 49%|████▊     | 181078/371472 [3:31:51<16:25:59,  3.22it/s]
 49%|████▊     | 181079/371472 [3:31:51<16:13:30,  3.26it/s]
 49%|████▊     | 181080/371472 [3:31:52<16:34:34,  3.19it/s]
                                                            
{'loss': 2.8106, 'learning_rate': 5.61529013768881e-07, 'epoch': 7.8}
+
 49%|████▊     | 181080/371472 [3:31:52<16:34:34,  3.19it/s]
 49%|████▊     | 181081/371472 [3:31:52<16:04:19,  3.29it/s]
 49%|████▊     | 181082/371472 [3:31:52<17:03:20,  3.10it/s]
 49%|████▊     | 181083/371472 [3:31:53<16:43:56,  3.16it/s]
 49%|████▊     | 181084/371472 [3:31:53<16:17:54,  3.24it/s]
 49%|████▊     | 181085/371472 [3:31:53<15:55:53,  3.32it/s]
 49%|████▊     | 181086/371472 [3:31:53<15:24:18,  3.43it/s]
 49%|████▊     | 181087/371472 [3:31:54<15:50:26,  3.34it/s]
 49%|████▊     | 181088/371472 [3:31:54<15:36:07,  3.39it/s]
 49%|████▊     | 181089/371472 [3:31:54<15:39:34,  3.38it/s]
 49%|████▊     | 181090/371472 [3:31:55<16:07:19,  3.28it/s]
 49%|████▊     | 181091/371472 [3:31:55<17:24:37,  3.04it/s]
 49%|████▊     | 181092/371472 [3:31:55<17:06:24,  3.09it/s]
 49%|████▉     | 181093/371472 [3:31:56<16:24:32,  3.22it/s]
 49%|████▉     | 181094/371472 [3:31:56<16:00:22,  3.30it/s]
 49%|████▉     | 181095/371472 [3:31:56<15:46:36,  3.35it/s]
 49%|████▉     | 181096/371472 [3:31:57<15:41:12,  3.37it/s]
 49%|████▉     | 181097/371472 [3:31:57<15:45:40,  3.36it/s]
 49%|████▉     | 181098/371472 [3:31:57<15:41:47,  3.37it/s]
 49%|████▉     | 181099/371472 [3:31:57<15:35:23,  3.39it/s]
 49%|████▉     | 181100/371472 [3:31:58<15:43:35,  3.36it/s]
                                                            
{'loss': 3.0037, 'learning_rate': 5.614805317934021e-07, 'epoch': 7.8}
+
 49%|████▉     | 181100/371472 [3:31:58<15:43:35,  3.36it/s]
 49%|████▉     | 181101/371472 [3:31:58<15:55:57,  3.32it/s]
 49%|████▉     | 181102/371472 [3:31:58<16:13:11,  3.26it/s]
 49%|████▉     | 181103/371472 [3:31:59<16:02:06,  3.30it/s]
 49%|████▉     | 181104/371472 [3:31:59<15:48:14,  3.35it/s]
 49%|████▉     | 181105/371472 [3:31:59<15:43:37,  3.36it/s]
 49%|████▉     | 181106/371472 [3:32:00<15:45:46,  3.35it/s]
 49%|████▉     | 181107/371472 [3:32:00<15:34:41,  3.39it/s]
 49%|████▉     | 181108/371472 [3:32:00<15:26:42,  3.42it/s]
 49%|████▉     | 181109/371472 [3:32:00<15:09:33,  3.49it/s]
 49%|████▉     | 181110/371472 [3:32:01<16:14:37,  3.26it/s]
 49%|████▉     | 181111/371472 [3:32:01<17:13:49,  3.07it/s]
 49%|████▉     | 181112/371472 [3:32:01<16:45:15,  3.16it/s]
 49%|████▉     | 181113/371472 [3:32:02<16:10:39,  3.27it/s]
 49%|████▉     | 181114/371472 [3:32:02<16:01:10,  3.30it/s]
 49%|████▉     | 181115/371472 [3:32:02<15:49:07,  3.34it/s]
 49%|████▉     | 181116/371472 [3:32:03<16:12:04,  3.26it/s]
 49%|████▉     | 181117/371472 [3:32:03<16:28:24,  3.21it/s]
 49%|████▉     | 181118/371472 [3:32:03<16:23:22,  3.23it/s]
 49%|████▉     | 181119/371472 [3:32:03<15:52:09,  3.33it/s]
 49%|████▉     | 181120/371472 [3:32:04<15:45:43,  3.35it/s]
                                                            
{'loss': 2.9452, 'learning_rate': 5.614320498179232e-07, 'epoch': 7.8}
+
 49%|████▉     | 181120/371472 [3:32:04<15:45:43,  3.35it/s]
 49%|████▉     | 181121/371472 [3:32:04<15:38:32,  3.38it/s]
 49%|████▉     | 181122/371472 [3:32:04<15:36:28,  3.39it/s]
 49%|████▉     | 181123/371472 [3:32:05<15:36:45,  3.39it/s]
 49%|████▉     | 181124/371472 [3:32:05<15:30:56,  3.41it/s]
 49%|████▉     | 181125/371472 [3:32:05<16:29:47,  3.21it/s]
 49%|████▉     | 181126/371472 [3:32:06<15:47:44,  3.35it/s]
 49%|████▉     | 181127/371472 [3:32:06<15:45:01,  3.36it/s]
 49%|████▉     | 181128/371472 [3:32:06<15:47:40,  3.35it/s]
 49%|████▉     | 181129/371472 [3:32:06<15:38:42,  3.38it/s]
 49%|████▉     | 181130/371472 [3:32:07<15:39:47,  3.38it/s]
 49%|████▉     | 181131/371472 [3:32:07<15:46:24,  3.35it/s]
 49%|████▉     | 181132/371472 [3:32:07<15:40:31,  3.37it/s]
 49%|████▉     | 181133/371472 [3:32:08<16:01:45,  3.30it/s]
 49%|████▉     | 181134/371472 [3:32:08<15:49:10,  3.34it/s]
 49%|████▉     | 181135/371472 [3:32:08<16:10:07,  3.27it/s]
 49%|████▉     | 181136/371472 [3:32:09<15:51:59,  3.33it/s]
 49%|████▉     | 181137/371472 [3:32:09<15:57:05,  3.31it/s]
 49%|████▉     | 181138/371472 [3:32:09<16:21:11,  3.23it/s]
 49%|████▉     | 181139/371472 [3:32:10<18:37:40,  2.84it/s]
 49%|████▉     | 181140/371472 [3:32:10<17:23:58,  3.04it/s]
                                                            
{'loss': 2.9165, 'learning_rate': 5.613835678424443e-07, 'epoch': 7.8}
+
 49%|████▉     | 181140/371472 [3:32:10<17:23:58,  3.04it/s]
 49%|████▉     | 181141/371472 [3:32:10<17:00:50,  3.11it/s]
 49%|████▉     | 181142/371472 [3:32:10<16:21:39,  3.23it/s]
 49%|████▉     | 181143/371472 [3:32:11<15:58:26,  3.31it/s]
 49%|████▉     | 181144/371472 [3:32:11<15:43:38,  3.36it/s]
 49%|████▉     | 181145/371472 [3:32:11<15:58:49,  3.31it/s]
 49%|████▉     | 181146/371472 [3:32:12<16:02:52,  3.29it/s]
 49%|████▉     | 181147/371472 [3:32:12<15:23:23,  3.44it/s]
 49%|████▉     | 181148/371472 [3:32:12<15:26:09,  3.42it/s]
 49%|████▉     | 181149/371472 [3:32:13<15:27:56,  3.42it/s]
 49%|████▉     | 181150/371472 [3:32:13<15:16:47,  3.46it/s]
 49%|████▉     | 181151/371472 [3:32:13<16:40:41,  3.17it/s]
 49%|████▉     | 181152/371472 [3:32:14<16:33:02,  3.19it/s]
 49%|████▉     | 181153/371472 [3:32:14<16:04:35,  3.29it/s]
 49%|████▉     | 181154/371472 [3:32:14<15:46:45,  3.35it/s]
 49%|████▉     | 181155/371472 [3:32:14<15:49:12,  3.34it/s]
 49%|████▉     | 181156/371472 [3:32:15<15:47:39,  3.35it/s]
 49%|████▉     | 181157/371472 [3:32:15<15:50:10,  3.34it/s]
 49%|████▉     | 181158/371472 [3:32:15<15:44:36,  3.36it/s]
 49%|████▉     | 181159/371472 [3:32:16<15:25:34,  3.43it/s]
 49%|████▉     | 181160/371472 [3:32:16<15:35:55,  3.39it/s]
                                                            
{'loss': 2.8266, 'learning_rate': 5.613350858669655e-07, 'epoch': 7.8}
+
 49%|████▉     | 181160/371472 [3:32:16<15:35:55,  3.39it/s]
 49%|████▉     | 181161/371472 [3:32:16<15:32:43,  3.40it/s]
 49%|████▉     | 181162/371472 [3:32:16<15:38:32,  3.38it/s]
 49%|████▉     | 181163/371472 [3:32:17<15:24:33,  3.43it/s]
 49%|████▉     | 181164/371472 [3:32:17<16:10:57,  3.27it/s]
 49%|████▉     | 181165/371472 [3:32:17<16:15:21,  3.25it/s]
 49%|████▉     | 181166/371472 [3:32:18<16:04:29,  3.29it/s]
 49%|████▉     | 181167/371472 [3:32:18<15:41:03,  3.37it/s]
 49%|████▉     | 181168/371472 [3:32:18<16:11:28,  3.26it/s]
 49%|████▉     | 181169/371472 [3:32:19<16:52:05,  3.13it/s]
 49%|████▉     | 181170/371472 [3:32:19<17:01:09,  3.11it/s]
 49%|████▉     | 181171/371472 [3:32:19<16:28:14,  3.21it/s]
 49%|████▉     | 181172/371472 [3:32:20<16:15:21,  3.25it/s]
 49%|████▉     | 181173/371472 [3:32:20<16:11:07,  3.27it/s]
 49%|████▉     | 181174/371472 [3:32:20<15:45:24,  3.35it/s]
 49%|████▉     | 181175/371472 [3:32:20<15:41:33,  3.37it/s]
 49%|████▉     | 181176/371472 [3:32:21<17:03:11,  3.10it/s]
 49%|████▉     | 181177/371472 [3:32:21<16:47:06,  3.15it/s]
 49%|████▉     | 181178/371472 [3:32:21<16:07:59,  3.28it/s]
 49%|████▉     | 181179/371472 [3:32:22<15:45:27,  3.35it/s]
 49%|████▉     | 181180/371472 [3:32:22<15:47:16,  3.35it/s]
                                                            
{'loss': 2.9734, 'learning_rate': 5.612866038914865e-07, 'epoch': 7.8}
+
 49%|████▉     | 181180/371472 [3:32:22<15:47:16,  3.35it/s]
 49%|████▉     | 181181/371472 [3:32:22<15:30:09,  3.41it/s]
 49%|████▉     | 181182/371472 [3:32:23<15:52:29,  3.33it/s]
 49%|████▉     | 181183/371472 [3:32:23<16:27:01,  3.21it/s]
 49%|████▉     | 181184/371472 [3:32:23<16:31:33,  3.20it/s]
 49%|████▉     | 181185/371472 [3:32:24<16:13:35,  3.26it/s]
 49%|████▉     | 181186/371472 [3:32:24<15:36:51,  3.39it/s]
 49%|████▉     | 181187/371472 [3:32:24<15:30:22,  3.41it/s]
 49%|████▉     | 181188/371472 [3:32:24<15:12:43,  3.47it/s]
 49%|████▉     | 181189/371472 [3:32:25<15:10:55,  3.48it/s]
 49%|████▉     | 181190/371472 [3:32:25<15:09:15,  3.49it/s]
 49%|████▉     | 181191/371472 [3:32:25<15:39:50,  3.37it/s]
 49%|████▉     | 181192/371472 [3:32:26<15:43:26,  3.36it/s]
 49%|████▉     | 181193/371472 [3:32:26<15:58:35,  3.31it/s]
 49%|████▉     | 181194/371472 [3:32:26<15:42:18,  3.37it/s]
 49%|████▉     | 181195/371472 [3:32:26<16:04:16,  3.29it/s]
 49%|████▉     | 181196/371472 [3:32:27<16:07:44,  3.28it/s]
 49%|████▉     | 181197/371472 [3:32:27<16:54:40,  3.13it/s]
 49%|████▉     | 181198/371472 [3:32:27<16:57:17,  3.12it/s]
 49%|████▉     | 181199/371472 [3:32:28<16:20:23,  3.23it/s]
 49%|████▉     | 181200/371472 [3:32:28<16:25:19,  3.22it/s]
                                                            
{'loss': 2.9567, 'learning_rate': 5.612381219160076e-07, 'epoch': 7.8}
+
 49%|████▉     | 181200/371472 [3:32:28<16:25:19,  3.22it/s]
 49%|████▉     | 181201/371472 [3:32:28<15:55:04,  3.32it/s]
 49%|████▉     | 181202/371472 [3:32:29<15:57:25,  3.31it/s]
 49%|████▉     | 181203/371472 [3:32:29<15:57:28,  3.31it/s]
 49%|████▉     | 181204/371472 [3:32:29<16:07:28,  3.28it/s]
 49%|████▉     | 181205/371472 [3:32:30<15:53:11,  3.33it/s]
 49%|████▉     | 181206/371472 [3:32:30<15:52:04,  3.33it/s]
 49%|████▉     | 181207/371472 [3:32:30<15:25:14,  3.43it/s]
 49%|████▉     | 181208/371472 [3:32:30<15:03:40,  3.51it/s]
 49%|████▉     | 181209/371472 [3:32:31<15:42:25,  3.36it/s]
 49%|████▉     | 181210/371472 [3:32:31<15:43:21,  3.36it/s]
 49%|████▉     | 181211/371472 [3:32:31<16:09:44,  3.27it/s]
 49%|████▉     | 181212/371472 [3:32:32<16:00:41,  3.30it/s]
 49%|████▉     | 181213/371472 [3:32:32<15:23:15,  3.43it/s]
 49%|████▉     | 181214/371472 [3:32:32<15:30:19,  3.41it/s]
 49%|████▉     | 181215/371472 [3:32:32<15:33:37,  3.40it/s]
 49%|████▉     | 181216/371472 [3:32:33<15:29:23,  3.41it/s]
 49%|████▉     | 181217/371472 [3:32:33<15:41:16,  3.37it/s]
 49%|████▉     | 181218/371472 [3:32:33<15:34:20,  3.39it/s]
 49%|████▉     | 181219/371472 [3:32:34<16:06:27,  3.28it/s]
 49%|████▉     | 181220/371472 [3:32:34<15:33:38,  3.40it/s]
                                                            
{'loss': 2.9947, 'learning_rate': 5.611896399405287e-07, 'epoch': 7.81}
+
 49%|████▉     | 181220/371472 [3:32:34<15:33:38,  3.40it/s]
 49%|████▉     | 181221/371472 [3:32:34<16:23:25,  3.22it/s]
 49%|████▉     | 181222/371472 [3:32:35<16:12:37,  3.26it/s]
 49%|████▉     | 181223/371472 [3:32:35<15:55:37,  3.32it/s]
 49%|████▉     | 181224/371472 [3:32:35<15:36:57,  3.38it/s]
 49%|████▉     | 181225/371472 [3:32:35<16:20:04,  3.24it/s]
 49%|████▉     | 181226/371472 [3:32:36<16:01:46,  3.30it/s]
 49%|████▉     | 181227/371472 [3:32:36<15:48:54,  3.34it/s]
 49%|████▉     | 181228/371472 [3:32:36<15:30:06,  3.41it/s]
 49%|████▉     | 181229/371472 [3:32:37<15:11:00,  3.48it/s]
 49%|████▉     | 181230/371472 [3:32:37<15:03:46,  3.51it/s]
 49%|████▉     | 181231/371472 [3:32:37<14:52:38,  3.55it/s]
 49%|████▉     | 181232/371472 [3:32:37<14:59:06,  3.53it/s]
 49%|████▉     | 181233/371472 [3:32:38<14:37:22,  3.61it/s]
 49%|████▉     | 181234/371472 [3:32:38<14:28:53,  3.65it/s]
 49%|████▉     | 181235/371472 [3:32:38<14:30:08,  3.64it/s]
 49%|████▉     | 181236/371472 [3:32:39<14:46:12,  3.58it/s]
 49%|████▉     | 181237/371472 [3:32:39<14:51:29,  3.56it/s]
 49%|████▉     | 181238/371472 [3:32:39<15:19:53,  3.45it/s]
 49%|████▉     | 181239/371472 [3:32:39<14:52:54,  3.55it/s]
 49%|████▉     | 181240/371472 [3:32:40<14:38:33,  3.61it/s]
                                                            
{'loss': 2.9535, 'learning_rate': 5.611411579650499e-07, 'epoch': 7.81}
+
 49%|████▉     | 181240/371472 [3:32:40<14:38:33,  3.61it/s]
 49%|████▉     | 181241/371472 [3:32:40<15:07:59,  3.49it/s]
 49%|████▉     | 181242/371472 [3:32:40<15:15:43,  3.46it/s]
 49%|████▉     | 181243/371472 [3:32:41<14:53:34,  3.55it/s]
 49%|████▉     | 181244/371472 [3:32:41<14:54:14,  3.55it/s]
 49%|████▉     | 181245/371472 [3:32:41<14:54:41,  3.54it/s]
 49%|████▉     | 181246/371472 [3:32:41<14:53:44,  3.55it/s]
 49%|████▉     | 181247/371472 [3:32:42<15:03:59,  3.51it/s]
 49%|████▉     | 181248/371472 [3:32:42<14:51:23,  3.56it/s]
 49%|████▉     | 181249/371472 [3:32:42<14:57:49,  3.53it/s]
 49%|████▉     | 181250/371472 [3:32:43<14:49:36,  3.56it/s]
 49%|████▉     | 181251/371472 [3:32:43<15:09:04,  3.49it/s]
 49%|████▉     | 181252/371472 [3:32:43<15:41:54,  3.37it/s]
 49%|████▉     | 181253/371472 [3:32:43<15:17:14,  3.46it/s]
 49%|████▉     | 181254/371472 [3:32:44<15:15:17,  3.46it/s]
 49%|████▉     | 181255/371472 [3:32:44<15:19:25,  3.45it/s]
 49%|████▉     | 181256/371472 [3:32:44<15:32:50,  3.40it/s]
 49%|████▉     | 181257/371472 [3:32:45<15:17:08,  3.46it/s]
 49%|████▉     | 181258/371472 [3:32:45<16:04:21,  3.29it/s]
 49%|████▉     | 181259/371472 [3:32:45<16:00:09,  3.30it/s]
 49%|████▉     | 181260/371472 [3:32:46<15:47:48,  3.34it/s]
                                                            
{'loss': 2.9932, 'learning_rate': 5.61092675989571e-07, 'epoch': 7.81}
+
 49%|████▉     | 181260/371472 [3:32:46<15:47:48,  3.34it/s]
 49%|████▉     | 181261/371472 [3:32:46<15:34:57,  3.39it/s]
 49%|████▉     | 181262/371472 [3:32:46<16:17:12,  3.24it/s]
 49%|████▉     | 181263/371472 [3:32:46<16:00:55,  3.30it/s]
 49%|████▉     | 181264/371472 [3:32:47<16:15:36,  3.25it/s]
 49%|████▉     | 181265/371472 [3:32:47<16:25:36,  3.22it/s]
 49%|████▉     | 181266/371472 [3:32:47<15:50:37,  3.33it/s]
 49%|████▉     | 181267/371472 [3:32:48<15:37:17,  3.38it/s]
 49%|████▉     | 181268/371472 [3:32:48<15:37:30,  3.38it/s]
 49%|████▉     | 181269/371472 [3:32:48<16:19:29,  3.24it/s]
 49%|████▉     | 181270/371472 [3:32:49<15:55:14,  3.32it/s]
 49%|████▉     | 181271/371472 [3:32:49<17:35:53,  3.00it/s]
 49%|████▉     | 181272/371472 [3:32:49<16:49:36,  3.14it/s]
 49%|████▉     | 181273/371472 [3:32:50<16:26:05,  3.21it/s]
 49%|████▉     | 181274/371472 [3:32:50<16:11:09,  3.26it/s]
 49%|████▉     | 181275/371472 [3:32:50<16:21:16,  3.23it/s]
 49%|████▉     | 181276/371472 [3:32:50<15:47:30,  3.35it/s]
 49%|████▉     | 181277/371472 [3:32:51<16:18:07,  3.24it/s]
 49%|████▉     | 181278/371472 [3:32:51<16:16:52,  3.24it/s]
 49%|████▉     | 181279/371472 [3:32:51<16:17:09,  3.24it/s]
 49%|████▉     | 181280/371472 [3:32:52<15:55:06,  3.32it/s]
                                                            
{'loss': 2.8796, 'learning_rate': 5.610441940140921e-07, 'epoch': 7.81}
+
 49%|████▉     | 181280/371472 [3:32:52<15:55:06,  3.32it/s]
 49%|████▉     | 181281/371472 [3:32:52<15:55:48,  3.32it/s]
 49%|████▉     | 181282/371472 [3:32:52<16:18:04,  3.24it/s]
 49%|████▉     | 181283/371472 [3:32:53<16:16:49,  3.25it/s]
 49%|████▉     | 181284/371472 [3:32:53<15:56:10,  3.32it/s]
 49%|████▉     | 181285/371472 [3:32:53<15:38:18,  3.38it/s]
 49%|████▉     | 181286/371472 [3:32:53<15:23:50,  3.43it/s]
 49%|████▉     | 181287/371472 [3:32:54<16:35:37,  3.18it/s]
 49%|████▉     | 181288/371472 [3:32:54<16:54:13,  3.13it/s]
 49%|████▉     | 181289/371472 [3:32:54<16:28:02,  3.21it/s]
 49%|████▉     | 181290/371472 [3:32:55<17:43:45,  2.98it/s]
 49%|████▉     | 181291/371472 [3:32:55<18:10:30,  2.91it/s]
 49%|████▉     | 181292/371472 [3:32:56<18:08:42,  2.91it/s]
 49%|████▉     | 181293/371472 [3:32:56<18:05:40,  2.92it/s]
 49%|████▉     | 181294/371472 [3:32:56<18:15:40,  2.89it/s]
 49%|████▉     | 181295/371472 [3:32:56<17:11:43,  3.07it/s]
 49%|████▉     | 181296/371472 [3:32:57<16:32:59,  3.19it/s]
 49%|████▉     | 181297/371472 [3:32:57<16:10:22,  3.27it/s]
 49%|████▉     | 181298/371472 [3:32:57<16:52:37,  3.13it/s]
 49%|████▉     | 181299/371472 [3:32:58<16:19:34,  3.24it/s]
 49%|████▉     | 181300/371472 [3:32:58<15:56:02,  3.32it/s]
                                                            
{'loss': 3.0261, 'learning_rate': 5.609957120386132e-07, 'epoch': 7.81}
+
 49%|████▉     | 181300/371472 [3:32:58<15:56:02,  3.32it/s]
 49%|████▉     | 181301/371472 [3:32:58<16:14:32,  3.25it/s]
 49%|████▉     | 181302/371472 [3:32:59<15:58:52,  3.31it/s]
 49%|████▉     | 181303/371472 [3:32:59<15:32:14,  3.40it/s]
 49%|████▉     | 181304/371472 [3:32:59<16:35:31,  3.18it/s]
 49%|████▉     | 181305/371472 [3:33:00<17:27:20,  3.03it/s]
 49%|████▉     | 181306/371472 [3:33:00<16:43:26,  3.16it/s]
 49%|████▉     | 181307/371472 [3:33:00<16:07:04,  3.28it/s]
 49%|████▉     | 181308/371472 [3:33:00<15:35:21,  3.39it/s]
 49%|████▉     | 181309/371472 [3:33:01<15:27:26,  3.42it/s]
 49%|████▉     | 181310/371472 [3:33:01<15:21:01,  3.44it/s]
 49%|████▉     | 181311/371472 [3:33:01<14:59:38,  3.52it/s]
 49%|████▉     | 181312/371472 [3:33:02<15:18:50,  3.45it/s]
 49%|████▉     | 181313/371472 [3:33:02<14:58:16,  3.53it/s]
 49%|████▉     | 181314/371472 [3:33:02<15:02:25,  3.51it/s]
 49%|████▉     | 181315/371472 [3:33:02<14:57:57,  3.53it/s]
 49%|████▉     | 181316/371472 [3:33:03<15:20:32,  3.44it/s]
 49%|████▉     | 181317/371472 [3:33:03<15:03:55,  3.51it/s]
 49%|████▉     | 181318/371472 [3:33:03<14:58:18,  3.53it/s]
 49%|████▉     | 181319/371472 [3:33:04<15:36:06,  3.39it/s]
 49%|████▉     | 181320/371472 [3:33:04<15:30:16,  3.41it/s]
                                                            
{'loss': 2.8174, 'learning_rate': 5.609472300631343e-07, 'epoch': 7.81}
+
 49%|████▉     | 181320/371472 [3:33:04<15:30:16,  3.41it/s]
 49%|████▉     | 181321/371472 [3:33:04<15:19:20,  3.45it/s]
 49%|████▉     | 181322/371472 [3:33:04<15:20:19,  3.44it/s]
 49%|████▉     | 181323/371472 [3:33:05<15:43:13,  3.36it/s]
 49%|████▉     | 181324/371472 [3:33:05<15:48:05,  3.34it/s]
 49%|████▉     | 181325/371472 [3:33:05<15:47:55,  3.34it/s]
 49%|████▉     | 181326/371472 [3:33:06<15:42:25,  3.36it/s]
 49%|████▉     | 181327/371472 [3:33:06<15:25:42,  3.42it/s]
 49%|████▉     | 181328/371472 [3:33:06<15:15:52,  3.46it/s]
 49%|████▉     | 181329/371472 [3:33:07<15:05:50,  3.50it/s]
 49%|████▉     | 181330/371472 [3:33:07<15:05:22,  3.50it/s]
 49%|████▉     | 181331/371472 [3:33:07<15:13:20,  3.47it/s]
 49%|████▉     | 181332/371472 [3:33:07<15:11:47,  3.48it/s]
 49%|████▉     | 181333/371472 [3:33:08<15:08:41,  3.49it/s]
 49%|████▉     | 181334/371472 [3:33:08<15:13:56,  3.47it/s]
 49%|████▉     | 181335/371472 [3:33:08<15:30:32,  3.41it/s]
 49%|████▉     | 181336/371472 [3:33:09<15:32:56,  3.40it/s]
 49%|████▉     | 181337/371472 [3:33:09<16:36:21,  3.18it/s]
 49%|████▉     | 181338/371472 [3:33:09<16:36:14,  3.18it/s]
 49%|████▉     | 181339/371472 [3:33:10<16:10:10,  3.27it/s]
 49%|████▉     | 181340/371472 [3:33:10<16:14:44,  3.25it/s]
                                                            
{'loss': 2.9925, 'learning_rate': 5.608987480876554e-07, 'epoch': 7.81}
+
 49%|████▉     | 181340/371472 [3:33:10<16:14:44,  3.25it/s]
 49%|████▉     | 181341/371472 [3:33:10<15:44:07,  3.36it/s]
 49%|████▉     | 181342/371472 [3:33:10<16:00:30,  3.30it/s]
 49%|████▉     | 181343/371472 [3:33:11<15:41:58,  3.36it/s]
 49%|████▉     | 181344/371472 [3:33:11<15:35:37,  3.39it/s]
 49%|████▉     | 181345/371472 [3:33:11<15:14:17,  3.47it/s]
 49%|████▉     | 181346/371472 [3:33:12<15:21:44,  3.44it/s]
 49%|████▉     | 181347/371472 [3:33:12<15:22:25,  3.44it/s]
 49%|████▉     | 181348/371472 [3:33:12<15:34:30,  3.39it/s]
 49%|████▉     | 181349/371472 [3:33:12<15:29:37,  3.41it/s]
 49%|████▉     | 181350/371472 [3:33:13<15:36:09,  3.38it/s]
 49%|████▉     | 181351/371472 [3:33:13<15:39:25,  3.37it/s]
 49%|████▉     | 181352/371472 [3:33:13<15:14:03,  3.47it/s]
 49%|████▉     | 181353/371472 [3:33:14<15:51:05,  3.33it/s]
 49%|████▉     | 181354/371472 [3:33:14<16:35:43,  3.18it/s]
 49%|████▉     | 181355/371472 [3:33:14<15:58:54,  3.30it/s]
 49%|████▉     | 181356/371472 [3:33:15<15:46:51,  3.35it/s]
 49%|████▉     | 181357/371472 [3:33:15<16:04:14,  3.29it/s]
 49%|████▉     | 181358/371472 [3:33:15<15:44:55,  3.35it/s]
 49%|████▉     | 181359/371472 [3:33:15<15:59:46,  3.30it/s]
 49%|████▉     | 181360/371472 [3:33:16<15:34:06,  3.39it/s]
                                                            
{'loss': 2.8922, 'learning_rate': 5.608502661121765e-07, 'epoch': 7.81}
+
 49%|████▉     | 181360/371472 [3:33:16<15:34:06,  3.39it/s]
 49%|████▉     | 181361/371472 [3:33:16<15:59:40,  3.30it/s]
 49%|████▉     | 181362/371472 [3:33:16<15:53:41,  3.32it/s]
 49%|████▉     | 181363/371472 [3:33:17<15:25:08,  3.42it/s]
 49%|████▉     | 181364/371472 [3:33:17<15:02:55,  3.51it/s]
 49%|████▉     | 181365/371472 [3:33:17<15:51:29,  3.33it/s]
 49%|████▉     | 181366/371472 [3:33:18<18:08:27,  2.91it/s]
 49%|████▉     | 181367/371472 [3:33:18<17:12:49,  3.07it/s]
 49%|████▉     | 181368/371472 [3:33:18<17:00:33,  3.10it/s]
 49%|████▉     | 181369/371472 [3:33:19<16:51:22,  3.13it/s]
 49%|████▉     | 181370/371472 [3:33:19<16:10:58,  3.26it/s]
 49%|████▉     | 181371/371472 [3:33:19<15:53:11,  3.32it/s]
 49%|████▉     | 181372/371472 [3:33:19<15:30:36,  3.40it/s]
 49%|████▉     | 181373/371472 [3:33:20<16:16:56,  3.24it/s]
 49%|████▉     | 181374/371472 [3:33:20<15:43:09,  3.36it/s]
 49%|████▉     | 181375/371472 [3:33:20<15:53:23,  3.32it/s]
 49%|████▉     | 181376/371472 [3:33:21<15:37:17,  3.38it/s]
 49%|████▉     | 181377/371472 [3:33:21<15:28:23,  3.41it/s]
 49%|████▉     | 181378/371472 [3:33:21<15:25:45,  3.42it/s]
 49%|████▉     | 181379/371472 [3:33:22<15:11:41,  3.48it/s]
 49%|████▉     | 181380/371472 [3:33:22<15:19:06,  3.45it/s]
                                                            
{'loss': 2.7791, 'learning_rate': 5.608017841366976e-07, 'epoch': 7.81}
+
 49%|████▉     | 181380/371472 [3:33:22<15:19:06,  3.45it/s]
 49%|████▉     | 181381/371472 [3:33:22<15:38:03,  3.38it/s]
 49%|████▉     | 181382/371472 [3:33:22<15:41:54,  3.36it/s]
 49%|████▉     | 181383/371472 [3:33:23<15:54:17,  3.32it/s]
 49%|████▉     | 181384/371472 [3:33:23<15:36:42,  3.38it/s]
 49%|████▉     | 181385/371472 [3:33:23<15:24:20,  3.43it/s]
 49%|████▉     | 181386/371472 [3:33:24<15:21:41,  3.44it/s]
 49%|████▉     | 181387/371472 [3:33:24<15:15:07,  3.46it/s]
 49%|████▉     | 181388/371472 [3:33:24<15:43:31,  3.36it/s]
 49%|████▉     | 181389/371472 [3:33:24<15:31:18,  3.40it/s]
 49%|████▉     | 181390/371472 [3:33:25<15:22:15,  3.44it/s]
 49%|████▉     | 181391/371472 [3:33:25<15:21:20,  3.44it/s]
 49%|████▉     | 181392/371472 [3:33:25<15:29:31,  3.41it/s]
 49%|████▉     | 181393/371472 [3:33:26<17:01:52,  3.10it/s]
 49%|████▉     | 181394/371472 [3:33:26<17:20:23,  3.04it/s]
 49%|████▉     | 181395/371472 [3:33:26<17:28:39,  3.02it/s]
 49%|████▉     | 181396/371472 [3:33:27<16:45:52,  3.15it/s]
 49%|████▉     | 181397/371472 [3:33:27<15:59:59,  3.30it/s]
 49%|████▉     | 181398/371472 [3:33:27<16:29:01,  3.20it/s]
 49%|████▉     | 181399/371472 [3:33:28<16:39:42,  3.17it/s]
 49%|████▉     | 181400/371472 [3:33:28<17:11:55,  3.07it/s]
                                                            
{'loss': 2.8835, 'learning_rate': 5.607533021612187e-07, 'epoch': 7.81}
+
 49%|████▉     | 181400/371472 [3:33:28<17:11:55,  3.07it/s]
 49%|████▉     | 181401/371472 [3:33:28<17:13:57,  3.06it/s]
 49%|████▉     | 181402/371472 [3:33:29<16:28:50,  3.20it/s]
 49%|████▉     | 181403/371472 [3:33:29<16:09:18,  3.27it/s]
 49%|████▉     | 181404/371472 [3:33:29<16:00:06,  3.30it/s]
 49%|████▉     | 181405/371472 [3:33:29<15:24:05,  3.43it/s]
 49%|████▉     | 181406/371472 [3:33:30<16:06:58,  3.28it/s]
 49%|████▉     | 181407/371472 [3:33:30<16:14:37,  3.25it/s]
 49%|████▉     | 181408/371472 [3:33:30<16:10:17,  3.26it/s]
 49%|████▉     | 181409/371472 [3:33:31<16:39:18,  3.17it/s]
 49%|████▉     | 181410/371472 [3:33:31<16:13:32,  3.25it/s]
 49%|████▉     | 181411/371472 [3:33:31<16:12:48,  3.26it/s]
 49%|████▉     | 181412/371472 [3:33:32<16:38:28,  3.17it/s]
 49%|████▉     | 181413/371472 [3:33:32<16:29:31,  3.20it/s]
 49%|████▉     | 181414/371472 [3:33:32<16:29:11,  3.20it/s]
 49%|████▉     | 181415/371472 [3:33:33<16:36:53,  3.18it/s]
 49%|████▉     | 181416/371472 [3:33:33<16:23:55,  3.22it/s]
 49%|████▉     | 181417/371472 [3:33:33<16:14:38,  3.25it/s]
 49%|████▉     | 181418/371472 [3:33:34<17:00:46,  3.10it/s]
 49%|████▉     | 181419/371472 [3:33:34<16:29:21,  3.20it/s]
 49%|████▉     | 181420/371472 [3:33:34<15:49:56,  3.33it/s]
                                                            
{'loss': 2.8447, 'learning_rate': 5.607048201857398e-07, 'epoch': 7.81}
+
 49%|████▉     | 181420/371472 [3:33:34<15:49:56,  3.33it/s]
 49%|████▉     | 181421/371472 [3:33:34<17:01:05,  3.10it/s]
 49%|████▉     | 181422/371472 [3:33:35<16:31:56,  3.19it/s]
 49%|████▉     | 181423/371472 [3:33:35<16:11:02,  3.26it/s]
 49%|████▉     | 181424/371472 [3:33:35<15:47:33,  3.34it/s]
 49%|████▉     | 181425/371472 [3:33:36<18:42:28,  2.82it/s]
 49%|████▉     | 181426/371472 [3:33:36<17:38:36,  2.99it/s]
 49%|████▉     | 181427/371472 [3:33:36<17:14:00,  3.06it/s]
 49%|████▉     | 181428/371472 [3:33:37<16:49:48,  3.14it/s]
 49%|��███▉     | 181429/371472 [3:33:37<16:08:45,  3.27it/s]
 49%|████▉     | 181430/371472 [3:33:37<16:33:17,  3.19it/s]
 49%|████▉     | 181431/371472 [3:33:38<16:20:44,  3.23it/s]
 49%|████▉     | 181432/371472 [3:33:38<16:03:02,  3.29it/s]
 49%|████▉     | 181433/371472 [3:33:38<15:42:27,  3.36it/s]
 49%|████▉     | 181434/371472 [3:33:38<15:29:04,  3.41it/s]
 49%|████▉     | 181435/371472 [3:33:39<15:25:57,  3.42it/s]
 49%|████▉     | 181436/371472 [3:33:39<15:08:20,  3.49it/s]
 49%|████▉     | 181437/371472 [3:33:39<14:40:48,  3.60it/s]
 49%|████▉     | 181438/371472 [3:33:40<15:14:08,  3.46it/s]
 49%|████▉     | 181439/371472 [3:33:40<15:21:56,  3.44it/s]
 49%|████▉     | 181440/371472 [3:33:40<16:13:02,  3.25it/s]
                                                            
{'loss': 2.8917, 'learning_rate': 5.606563382102609e-07, 'epoch': 7.81}
+
 49%|████▉     | 181440/371472 [3:33:40<16:13:02,  3.25it/s]
 49%|████▉     | 181441/371472 [3:33:41<16:07:20,  3.27it/s]
 49%|████▉     | 181442/371472 [3:33:41<16:02:07,  3.29it/s]
 49%|████▉     | 181443/371472 [3:33:41<15:25:28,  3.42it/s]
 49%|████▉     | 181444/371472 [3:33:41<15:12:13,  3.47it/s]
 49%|████▉     | 181445/371472 [3:33:42<15:35:24,  3.39it/s]
 49%|████▉     | 181446/371472 [3:33:42<15:29:29,  3.41it/s]
 49%|████▉     | 181447/371472 [3:33:42<15:11:38,  3.47it/s]
 49%|████▉     | 181448/371472 [3:33:43<15:06:46,  3.49it/s]
 49%|████▉     | 181449/371472 [3:33:43<15:33:25,  3.39it/s]
 49%|████▉     | 181450/371472 [3:33:43<15:29:19,  3.41it/s]
 49%|████▉     | 181451/371472 [3:33:43<15:09:00,  3.48it/s]
 49%|████▉     | 181452/371472 [3:33:44<15:19:03,  3.45it/s]
 49%|████▉     | 181453/371472 [3:33:44<15:10:32,  3.48it/s]
 49%|████▉     | 181454/371472 [3:33:44<15:13:38,  3.47it/s]
 49%|████▉     | 181455/371472 [3:33:45<15:29:36,  3.41it/s]
 49%|████▉     | 181456/371472 [3:33:45<15:25:17,  3.42it/s]
 49%|████▉     | 181457/371472 [3:33:45<15:39:44,  3.37it/s]
 49%|████▉     | 181458/371472 [3:33:46<15:34:15,  3.39it/s]
 49%|████▉     | 181459/371472 [3:33:46<15:26:19,  3.42it/s]
 49%|████▉     | 181460/371472 [3:33:46<15:15:54,  3.46it/s]
                                                            
{'loss': 2.8386, 'learning_rate': 5.606078562347821e-07, 'epoch': 7.82}
+
 49%|████▉     | 181460/371472 [3:33:46<15:15:54,  3.46it/s]
 49%|████▉     | 181461/371472 [3:33:46<15:15:37,  3.46it/s]
 49%|████▉     | 181462/371472 [3:33:47<15:03:37,  3.50it/s]
 49%|████▉     | 181463/371472 [3:33:47<15:52:48,  3.32it/s]
 49%|████▉     | 181464/371472 [3:33:47<15:39:42,  3.37it/s]
 49%|████▉     | 181465/371472 [3:33:48<16:00:18,  3.30it/s]
 49%|████▉     | 181466/371472 [3:33:48<16:17:20,  3.24it/s]
 49%|████▉     | 181467/371472 [3:33:48<16:31:29,  3.19it/s]
 49%|████▉     | 181468/371472 [3:33:49<16:29:47,  3.20it/s]
 49%|████▉     | 181469/371472 [3:33:49<16:21:03,  3.23it/s]
 49%|████▉     | 181470/371472 [3:33:49<16:32:24,  3.19it/s]
 49%|████▉     | 181471/371472 [3:33:49<16:09:16,  3.27it/s]
 49%|████▉     | 181472/371472 [3:33:50<15:56:12,  3.31it/s]
 49%|████▉     | 181473/371472 [3:33:50<15:48:20,  3.34it/s]
 49%|████▉     | 181474/371472 [3:33:50<16:27:49,  3.21it/s]
 49%|████▉     | 181475/371472 [3:33:51<15:55:32,  3.31it/s]
 49%|████▉     | 181476/371472 [3:33:51<15:48:03,  3.34it/s]
 49%|████▉     | 181477/371472 [3:33:51<15:59:24,  3.30it/s]
 49%|████▉     | 181478/371472 [3:33:52<16:20:25,  3.23it/s]
 49%|████▉     | 181479/371472 [3:33:52<16:10:30,  3.26it/s]
 49%|████▉     | 181480/371472 [3:33:52<16:06:29,  3.28it/s]
                                                            
{'loss': 2.8214, 'learning_rate': 5.605593742593031e-07, 'epoch': 7.82}
+
 49%|████▉     | 181480/371472 [3:33:52<16:06:29,  3.28it/s]
 49%|████▉     | 181481/371472 [3:33:52<16:00:49,  3.30it/s]
 49%|████▉     | 181482/371472 [3:33:53<17:06:42,  3.08it/s]
 49%|████▉     | 181483/371472 [3:33:53<17:44:29,  2.97it/s]
 49%|████▉     | 181484/371472 [3:33:54<16:56:02,  3.12it/s]
 49%|████▉     | 181485/371472 [3:33:54<16:06:24,  3.28it/s]
 49%|████▉     | 181486/371472 [3:33:54<15:31:26,  3.40it/s]
 49%|████▉     | 181487/371472 [3:33:54<15:21:14,  3.44it/s]
 49%|████▉     | 181488/371472 [3:33:55<15:02:52,  3.51it/s]
 49%|████▉     | 181489/371472 [3:33:55<14:58:22,  3.52it/s]
 49%|████▉     | 181490/371472 [3:33:55<15:25:37,  3.42it/s]
 49%|████▉     | 181491/371472 [3:33:55<15:10:08,  3.48it/s]
 49%|████▉     | 181492/371472 [3:33:56<15:08:56,  3.48it/s]
 49%|████▉     | 181493/371472 [3:33:56<16:05:18,  3.28it/s]
 49%|████▉     | 181494/371472 [3:33:56<15:49:01,  3.34it/s]
 49%|████▉     | 181495/371472 [3:33:57<15:24:49,  3.42it/s]
 49%|████▉     | 181496/371472 [3:33:57<16:12:35,  3.26it/s]
 49%|████▉     | 181497/371472 [3:33:57<16:13:04,  3.25it/s]
 49%|████▉     | 181498/371472 [3:33:58<16:37:10,  3.18it/s]
 49%|████▉     | 181499/371472 [3:33:58<15:59:25,  3.30it/s]
 49%|████▉     | 181500/371472 [3:33:58<15:31:23,  3.40it/s]
                                                            
{'loss': 2.9754, 'learning_rate': 5.605108922838242e-07, 'epoch': 7.82}
+
 49%|████▉     | 181500/371472 [3:33:58<15:31:23,  3.40it/s]
 49%|████▉     | 181501/371472 [3:33:58<15:18:07,  3.45it/s]
 49%|████▉     | 181502/371472 [3:33:59<15:15:02,  3.46it/s]
 49%|████▉     | 181503/371472 [3:33:59<15:01:00,  3.51it/s]
 49%|████▉     | 181504/371472 [3:33:59<15:44:18,  3.35it/s]
 49%|████▉     | 181505/371472 [3:34:00<15:24:45,  3.42it/s]
 49%|████▉     | 181506/371472 [3:34:00<15:43:16,  3.36it/s]
 49%|████▉     | 181507/371472 [3:34:00<15:25:32,  3.42it/s]
 49%|████▉     | 181508/371472 [3:34:01<16:23:08,  3.22it/s]
 49%|████▉     | 181509/371472 [3:34:01<15:53:06,  3.32it/s]
 49%|████▉     | 181510/371472 [3:34:01<15:57:31,  3.31it/s]
 49%|████▉     | 181511/371472 [3:34:01<15:53:16,  3.32it/s]
 49%|████▉     | 181512/371472 [3:34:02<16:52:21,  3.13it/s]
 49%|████▉     | 181513/371472 [3:34:02<16:48:21,  3.14it/s]
 49%|████▉     | 181514/371472 [3:34:02<17:05:15,  3.09it/s]
 49%|████▉     | 181515/371472 [3:34:03<17:09:17,  3.08it/s]
 49%|████▉     | 181516/371472 [3:34:03<17:40:33,  2.99it/s]
 49%|████▉     | 181517/371472 [3:34:04<18:27:26,  2.86it/s]
 49%|████▉     | 181518/371472 [3:34:04<17:39:43,  2.99it/s]
 49%|████▉     | 181519/371472 [3:34:04<17:56:31,  2.94it/s]
 49%|████▉     | 181520/371472 [3:34:05<17:08:51,  3.08it/s]
                                                            
{'loss': 3.0259, 'learning_rate': 5.604624103083453e-07, 'epoch': 7.82}
+
 49%|████▉     | 181520/371472 [3:34:05<17:08:51,  3.08it/s]
 49%|████▉     | 181521/371472 [3:34:05<16:49:47,  3.14it/s]
 49%|████▉     | 181522/371472 [3:34:05<17:13:41,  3.06it/s]
 49%|████▉     | 181523/371472 [3:34:05<16:38:34,  3.17it/s]
 49%|████▉     | 181524/371472 [3:34:06<16:25:16,  3.21it/s]
 49%|████▉     | 181525/371472 [3:34:06<16:23:03,  3.22it/s]
 49%|████▉     | 181526/371472 [3:34:06<15:53:00,  3.32it/s]
 49%|████▉     | 181527/371472 [3:34:07<15:44:21,  3.35it/s]
 49%|████▉     | 181528/371472 [3:34:07<15:47:24,  3.34it/s]
 49%|████▉     | 181529/371472 [3:34:07<15:45:23,  3.35it/s]
 49%|████▉     | 181530/371472 [3:34:08<16:17:01,  3.24it/s]
 49%|████▉     | 181531/371472 [3:34:08<16:08:14,  3.27it/s]
 49%|████▉     | 181532/371472 [3:34:08<16:05:25,  3.28it/s]
 49%|████▉     | 181533/371472 [3:34:08<16:32:10,  3.19it/s]
 49%|████▉     | 181534/371472 [3:34:09<16:06:59,  3.27it/s]
 49%|████▉     | 181535/371472 [3:34:09<15:57:44,  3.31it/s]
 49%|████▉     | 181536/371472 [3:34:09<16:00:37,  3.30it/s]
 49%|████▉     | 181537/371472 [3:34:10<15:51:11,  3.33it/s]
 49%|████▉     | 181538/371472 [3:34:10<15:20:29,  3.44it/s]
 49%|████▉     | 181539/371472 [3:34:10<15:21:29,  3.44it/s]
 49%|████▉     | 181540/371472 [3:34:11<15:40:18,  3.37it/s]
                                                            
{'loss': 3.0027, 'learning_rate': 5.604139283328665e-07, 'epoch': 7.82}
+
 49%|████▉     | 181540/371472 [3:34:11<15:40:18,  3.37it/s]
 49%|████▉     | 181541/371472 [3:34:11<15:25:29,  3.42it/s]
 49%|████▉     | 181542/371472 [3:34:11<16:10:44,  3.26it/s]
 49%|████▉     | 181543/371472 [3:34:11<15:52:01,  3.33it/s]
 49%|████▉     | 181544/371472 [3:34:12<15:53:06,  3.32it/s]
 49%|████▉     | 181545/371472 [3:34:12<15:52:43,  3.32it/s]
 49%|████▉     | 181546/371472 [3:34:12<15:54:55,  3.31it/s]
 49%|████▉     | 181547/371472 [3:34:13<15:35:41,  3.38it/s]
 49%|████▉     | 181548/371472 [3:34:13<15:15:50,  3.46it/s]
 49%|████▉     | 181549/371472 [3:34:13<17:21:29,  3.04it/s]
 49%|████▉     | 181550/371472 [3:34:14<16:31:34,  3.19it/s]
 49%|████▉     | 181551/371472 [3:34:14<16:13:44,  3.25it/s]
 49%|████▉     | 181552/371472 [3:34:14<16:12:31,  3.25it/s]
 49%|████▉     | 181553/371472 [3:34:14<15:52:04,  3.32it/s]
 49%|████▉     | 181554/371472 [3:34:15<15:25:00,  3.42it/s]
 49%|████▉     | 181555/371472 [3:34:15<15:27:05,  3.41it/s]
 49%|████▉     | 181556/371472 [3:34:15<15:52:11,  3.32it/s]
 49%|████▉     | 181557/371472 [3:34:16<15:25:09,  3.42it/s]
 49%|████▉     | 181558/371472 [3:34:16<15:09:57,  3.48it/s]
 49%|████▉     | 181559/371472 [3:34:16<15:48:26,  3.34it/s]
 49%|████▉     | 181560/371472 [3:34:17<15:47:04,  3.34it/s]
                                                            
{'loss': 2.8351, 'learning_rate': 5.603654463573875e-07, 'epoch': 7.82}
+
 49%|████▉     | 181560/371472 [3:34:17<15:47:04,  3.34it/s]
 49%|████▉     | 181561/371472 [3:34:17<15:23:25,  3.43it/s]
 49%|████▉     | 181562/371472 [3:34:17<15:15:59,  3.46it/s]
 49%|████▉     | 181563/371472 [3:34:17<15:11:01,  3.47it/s]
 49%|████▉     | 181564/371472 [3:34:18<15:44:21,  3.35it/s]
 49%|████▉     | 181565/371472 [3:34:18<15:21:35,  3.43it/s]
 49%|████▉     | 181566/371472 [3:34:18<15:34:00,  3.39it/s]
 49%|████▉     | 181567/371472 [3:34:19<15:28:37,  3.41it/s]
 49%|████▉     | 181568/371472 [3:34:19<15:11:07,  3.47it/s]
 49%|████▉     | 181569/371472 [3:34:19<14:54:06,  3.54it/s]
 49%|████▉     | 181570/371472 [3:34:19<15:21:27,  3.43it/s]
 49%|████▉     | 181571/371472 [3:34:20<15:32:32,  3.39it/s]
 49%|████▉     | 181572/371472 [3:34:20<15:03:37,  3.50it/s]
 49%|████▉     | 181573/371472 [3:34:20<15:52:25,  3.32it/s]
 49%|████▉     | 181574/371472 [3:34:21<15:31:36,  3.40it/s]
 49%|████▉     | 181575/371472 [3:34:21<15:20:54,  3.44it/s]
 49%|████▉     | 181576/371472 [3:34:21<15:35:13,  3.38it/s]
 49%|████▉     | 181577/371472 [3:34:22<15:23:28,  3.43it/s]
 49%|████▉     | 181578/371472 [3:34:22<14:51:18,  3.55it/s]
 49%|████▉     | 181579/371472 [3:34:22<14:46:00,  3.57it/s]
 49%|████▉     | 181580/371472 [3:34:22<15:31:06,  3.40it/s]
                                                            
{'loss': 2.8462, 'learning_rate': 5.603169643819086e-07, 'epoch': 7.82}
+
 49%|████▉     | 181580/371472 [3:34:22<15:31:06,  3.40it/s]
 49%|████▉     | 181581/371472 [3:34:23<15:00:48,  3.51it/s]
 49%|████▉     | 181582/371472 [3:34:23<15:27:40,  3.41it/s]
 49%|████▉     | 181583/371472 [3:34:23<15:09:08,  3.48it/s]
 49%|████▉     | 181584/371472 [3:34:24<15:09:05,  3.48it/s]
 49%|████▉     | 181585/371472 [3:34:24<14:51:03,  3.55it/s]
 49%|████▉     | 181586/371472 [3:34:24<14:59:17,  3.52it/s]
 49%|████▉     | 181587/371472 [3:34:24<15:53:58,  3.32it/s]
 49%|████▉     | 181588/371472 [3:34:25<16:04:03,  3.28it/s]
 49%|████▉     | 181589/371472 [3:34:25<15:45:38,  3.35it/s]
 49%|████▉     | 181590/371472 [3:34:25<15:49:43,  3.33it/s]
 49%|████▉     | 181591/371472 [3:34:26<15:34:13,  3.39it/s]
 49%|████▉     | 181592/371472 [3:34:26<15:40:05,  3.37it/s]
 49%|████▉     | 181593/371472 [3:34:26<15:21:32,  3.43it/s]
 49%|████▉     | 181594/371472 [3:34:26<15:20:15,  3.44it/s]
 49%|████▉     | 181595/371472 [3:34:27<15:51:47,  3.32it/s]
 49%|████▉     | 181596/371472 [3:34:27<16:12:10,  3.26it/s]
 49%|████▉     | 181597/371472 [3:34:27<15:37:02,  3.38it/s]
 49%|████▉     | 181598/371472 [3:34:28<15:56:49,  3.31it/s]
 49%|████▉     | 181599/371472 [3:34:28<16:42:04,  3.16it/s]
 49%|████▉     | 181600/371472 [3:34:28<16:56:10,  3.11it/s]
                                                            
{'loss': 2.8548, 'learning_rate': 5.602684824064297e-07, 'epoch': 7.82}
+
 49%|████▉     | 181600/371472 [3:34:28<16:56:10,  3.11it/s]
 49%|████▉     | 181601/371472 [3:34:29<16:47:06,  3.14it/s]
 49%|████▉     | 181602/371472 [3:34:29<16:36:51,  3.17it/s]
 49%|████▉     | 181603/371472 [3:34:29<16:24:12,  3.22it/s]
 49%|████▉     | 181604/371472 [3:34:30<15:50:06,  3.33it/s]
 49%|████▉     | 181605/371472 [3:34:30<15:43:52,  3.35it/s]
 49%|████▉     | 181606/371472 [3:34:30<15:22:55,  3.43it/s]
 49%|████▉     | 181607/371472 [3:34:30<15:31:59,  3.40it/s]
 49%|████▉     | 181608/371472 [3:34:31<15:26:07,  3.42it/s]
 49%|████▉     | 181609/371472 [3:34:31<15:25:05,  3.42it/s]
 49%|████▉     | 181610/371472 [3:34:31<15:23:00,  3.43it/s]
 49%|████▉     | 181611/371472 [3:34:32<15:06:48,  3.49it/s]
 49%|████▉     | 181612/371472 [3:34:32<15:21:26,  3.43it/s]
 49%|████▉     | 181613/371472 [3:34:32<15:35:57,  3.38it/s]
 49%|████▉     | 181614/371472 [3:34:32<15:27:30,  3.41it/s]
 49%|████▉     | 181615/371472 [3:34:33<17:16:28,  3.05it/s]
 49%|████▉     | 181616/371472 [3:34:33<16:40:30,  3.16it/s]
 49%|████▉     | 181617/371472 [3:34:33<16:22:38,  3.22it/s]
 49%|████▉     | 181618/371472 [3:34:34<16:17:55,  3.24it/s]
 49%|████▉     | 181619/371472 [3:34:34<15:38:11,  3.37it/s]
 49%|████▉     | 181620/371472 [3:34:34<15:24:36,  3.42it/s]
                                                            
{'loss': 3.0012, 'learning_rate': 5.602200004309509e-07, 'epoch': 7.82}
+
 49%|████▉     | 181620/371472 [3:34:34<15:24:36,  3.42it/s]
 49%|████▉     | 181621/371472 [3:34:35<15:15:54,  3.45it/s]
 49%|████▉     | 181622/371472 [3:34:35<15:26:07,  3.42it/s]
 49%|████▉     | 181623/371472 [3:34:35<15:09:45,  3.48it/s]
 49%|████▉     | 181624/371472 [3:34:35<15:05:22,  3.49it/s]
 49%|████▉     | 181625/371472 [3:34:36<15:39:06,  3.37it/s]
 49%|████▉     | 181626/371472 [3:34:36<15:35:26,  3.38it/s]
 49%|████▉     | 181627/371472 [3:34:36<15:38:21,  3.37it/s]
 49%|████▉     | 181628/371472 [3:34:37<15:29:25,  3.40it/s]
 49%|████▉     | 181629/371472 [3:34:37<15:23:27,  3.43it/s]
 49%|████▉     | 181630/371472 [3:34:37<15:28:23,  3.41it/s]
 49%|████▉     | 181631/371472 [3:34:38<16:32:54,  3.19it/s]
 49%|████▉     | 181632/371472 [3:34:38<15:59:39,  3.30it/s]
 49%|████▉     | 181633/371472 [3:34:38<15:46:59,  3.34it/s]
 49%|████▉     | 181634/371472 [3:34:39<16:44:57,  3.15it/s]
 49%|████▉     | 181635/371472 [3:34:39<17:21:25,  3.04it/s]
 49%|████▉     | 181636/371472 [3:34:39<16:41:19,  3.16it/s]
 49%|████▉     | 181637/371472 [3:34:39<16:15:28,  3.24it/s]
 49%|████▉     | 181638/371472 [3:34:40<16:04:21,  3.28it/s]
 49%|████▉     | 181639/371472 [3:34:40<16:00:12,  3.29it/s]
 49%|████▉     | 181640/371472 [3:34:40<16:03:23,  3.28it/s]
                                                            
{'loss': 2.8327, 'learning_rate': 5.60171518455472e-07, 'epoch': 7.82}
+
 49%|████▉     | 181640/371472 [3:34:40<16:03:23,  3.28it/s]
 49%|████▉     | 181641/371472 [3:34:41<16:00:21,  3.29it/s]
 49%|████▉     | 181642/371472 [3:34:41<15:49:17,  3.33it/s]
 49%|████▉     | 181643/371472 [3:34:41<16:29:35,  3.20it/s]
 49%|████▉     | 181644/371472 [3:34:42<16:30:08,  3.20it/s]
 49%|████▉     | 181645/371472 [3:34:42<16:16:16,  3.24it/s]
 49%|████▉     | 181646/371472 [3:34:42<16:27:39,  3.20it/s]
 49%|████▉     | 181647/371472 [3:34:43<16:18:36,  3.23it/s]
 49%|████▉     | 181648/371472 [3:34:43<15:58:03,  3.30it/s]
 49%|████▉     | 181649/371472 [3:34:43<15:31:52,  3.39it/s]
 49%|████▉     | 181650/371472 [3:34:43<16:02:08,  3.29it/s]
 49%|████▉     | 181651/371472 [3:34:44<15:57:45,  3.30it/s]
 49%|████▉     | 181652/371472 [3:34:44<15:39:54,  3.37it/s]
 49%|████▉     | 181653/371472 [3:34:44<15:27:54,  3.41it/s]
 49%|████▉     | 181654/371472 [3:34:45<15:38:55,  3.37it/s]
 49%|████▉     | 181655/371472 [3:34:45<15:19:20,  3.44it/s]
 49%|████▉     | 181656/371472 [3:34:45<15:09:18,  3.48it/s]
 49%|████▉     | 181657/371472 [3:34:45<15:16:02,  3.45it/s]
 49%|████▉     | 181658/371472 [3:34:46<15:24:10,  3.42it/s]
 49%|████▉     | 181659/371472 [3:34:46<15:44:27,  3.35it/s]
 49%|████▉     | 181660/371472 [3:34:46<15:38:02,  3.37it/s]
                                                            
{'loss': 2.7803, 'learning_rate': 5.601230364799931e-07, 'epoch': 7.82}
+
 49%|████▉     | 181660/371472 [3:34:46<15:38:02,  3.37it/s]
 49%|████▉     | 181661/371472 [3:34:47<16:11:54,  3.25it/s]
 49%|████▉     | 181662/371472 [3:34:47<16:40:38,  3.16it/s]
 49%|████▉     | 181663/371472 [3:34:47<16:49:15,  3.13it/s]
 49%|████▉     | 181664/371472 [3:34:48<17:03:14,  3.09it/s]
 49%|████▉     | 181665/371472 [3:34:48<16:44:45,  3.15it/s]
 49%|████▉     | 181666/371472 [3:34:48<16:34:04,  3.18it/s]
 49%|████▉     | 181667/371472 [3:34:49<16:27:40,  3.20it/s]
 49%|████▉     | 181668/371472 [3:34:49<15:57:17,  3.30it/s]
 49%|████▉     | 181669/371472 [3:34:49<15:26:43,  3.41it/s]
 49%|████▉     | 181670/371472 [3:34:49<15:04:45,  3.50it/s]
 49%|████▉     | 181671/371472 [3:34:50<15:17:09,  3.45it/s]
 49%|████▉     | 181672/371472 [3:34:50<15:29:47,  3.40it/s]
 49%|████▉     | 181673/371472 [3:34:50<16:40:00,  3.16it/s]
 49%|████▉     | 181674/371472 [3:34:51<15:57:58,  3.30it/s]
 49%|████▉     | 181675/371472 [3:34:51<16:11:08,  3.26it/s]
 49%|████▉     | 181676/371472 [3:34:51<16:16:03,  3.24it/s]
 49%|████▉     | 181677/371472 [3:34:52<15:54:43,  3.31it/s]
 49%|████▉     | 181678/371472 [3:34:52<15:37:35,  3.37it/s]
 49%|████▉     | 181679/371472 [3:34:52<15:15:46,  3.45it/s]
 49%|████▉     | 181680/371472 [3:34:52<15:08:53,  3.48it/s]
                                                            
{'loss': 2.9596, 'learning_rate': 5.600745545045142e-07, 'epoch': 7.83}
+
 49%|████▉     | 181680/371472 [3:34:52<15:08:53,  3.48it/s]
 49%|████▉     | 181681/371472 [3:34:53<15:28:28,  3.41it/s]
 49%|████▉     | 181682/371472 [3:34:53<15:33:10,  3.39it/s]
 49%|████▉     | 181683/371472 [3:34:53<17:10:12,  3.07it/s]
 49%|████▉     | 181684/371472 [3:34:54<17:15:04,  3.06it/s]
 49%|████▉     | 181685/371472 [3:34:54<16:50:33,  3.13it/s]
 49%|████▉     | 181686/371472 [3:34:54<16:49:58,  3.13it/s]
 49%|████▉     | 181687/371472 [3:34:55<17:03:52,  3.09it/s]
 49%|████▉     | 181688/371472 [3:34:55<16:44:52,  3.15it/s]
 49%|████▉     | 181689/371472 [3:34:55<16:52:33,  3.12it/s]
 49%|████▉     | 181690/371472 [3:34:56<16:10:51,  3.26it/s]
 49%|████▉     | 181691/371472 [3:34:56<15:48:47,  3.33it/s]
 49%|████▉     | 181692/371472 [3:34:56<15:44:07,  3.35it/s]
 49%|████▉     | 181693/371472 [3:34:56<15:33:45,  3.39it/s]
 49%|████▉     | 181694/371472 [3:34:57<15:26:55,  3.41it/s]
 49%|████▉     | 181695/371472 [3:34:57<15:53:22,  3.32it/s]
 49%|████▉     | 181696/371472 [3:34:57<15:54:16,  3.31it/s]
 49%|████▉     | 181697/371472 [3:34:58<16:16:21,  3.24it/s]
 49%|████▉     | 181698/371472 [3:34:58<16:35:05,  3.18it/s]
 49%|████▉     | 181699/371472 [3:34:58<16:22:43,  3.22it/s]
 49%|████▉     | 181700/371472 [3:34:59<16:07:17,  3.27it/s]
                                                            
{'loss': 2.872, 'learning_rate': 5.600260725290352e-07, 'epoch': 7.83}
+
 49%|████▉     | 181700/371472 [3:34:59<16:07:17,  3.27it/s]
 49%|████▉     | 181701/371472 [3:34:59<15:50:49,  3.33it/s]
 49%|████▉     | 181702/371472 [3:34:59<15:40:17,  3.36it/s]
 49%|████▉     | 181703/371472 [3:35:00<15:35:13,  3.38it/s]
 49%|████▉     | 181704/371472 [3:35:00<15:41:50,  3.36it/s]
 49%|████▉     | 181705/371472 [3:35:00<16:52:56,  3.12it/s]
 49%|████▉     | 181706/371472 [3:35:01<16:36:37,  3.17it/s]
 49%|████▉     | 181707/371472 [3:35:01<16:00:13,  3.29it/s]
 49%|████▉     | 181708/371472 [3:35:01<16:49:10,  3.13it/s]
 49%|████▉     | 181709/371472 [3:35:01<16:30:55,  3.19it/s]
 49%|████▉     | 181710/371472 [3:35:02<16:08:37,  3.27it/s]
 49%|████▉     | 181711/371472 [3:35:02<15:54:42,  3.31it/s]
 49%|████▉     | 181712/371472 [3:35:02<16:06:43,  3.27it/s]
 49%|████▉     | 181713/371472 [3:35:03<16:14:47,  3.24it/s]
 49%|████▉     | 181714/371472 [3:35:03<16:14:12,  3.25it/s]
 49%|████▉     | 181715/371472 [3:35:03<16:11:13,  3.26it/s]
 49%|████▉     | 181716/371472 [3:35:04<15:50:43,  3.33it/s]
 49%|████▉     | 181717/371472 [3:35:04<15:31:06,  3.40it/s]
 49%|████▉     | 181718/371472 [3:35:04<16:01:59,  3.29it/s]
 49%|████▉     | 181719/371472 [3:35:04<16:02:09,  3.29it/s]
 49%|████▉     | 181720/371472 [3:35:05<16:11:37,  3.25it/s]
                                                            
{'loss': 2.9774, 'learning_rate': 5.599775905535564e-07, 'epoch': 7.83}
+
 49%|████▉     | 181720/371472 [3:35:05<16:11:37,  3.25it/s]
 49%|████▉     | 181721/371472 [3:35:05<15:44:56,  3.35it/s]
 49%|████▉     | 181722/371472 [3:35:05<15:37:56,  3.37it/s]
 49%|████▉     | 181723/371472 [3:35:06<15:16:01,  3.45it/s]
 49%|████▉     | 181724/371472 [3:35:06<15:04:11,  3.50it/s]
 49%|████▉     | 181725/371472 [3:35:06<15:11:56,  3.47it/s]
 49%|████▉     | 181726/371472 [3:35:06<15:05:17,  3.49it/s]
 49%|████▉     | 181727/371472 [3:35:07<15:18:13,  3.44it/s]
 49%|████▉     | 181728/371472 [3:35:07<15:34:31,  3.38it/s]
 49%|████▉     | 181729/371472 [3:35:07<15:36:46,  3.38it/s]
 49%|████▉     | 181730/371472 [3:35:08<16:06:48,  3.27it/s]
 49%|████▉     | 181731/371472 [3:35:08<15:47:23,  3.34it/s]
 49%|████▉     | 181732/371472 [3:35:08<16:04:36,  3.28it/s]
 49%|████▉     | 181733/371472 [3:35:09<16:11:33,  3.25it/s]
 49%|████▉     | 181734/371472 [3:35:09<15:58:31,  3.30it/s]
 49%|████▉     | 181735/371472 [3:35:09<16:26:55,  3.20it/s]
 49%|████▉     | 181736/371472 [3:35:10<15:58:52,  3.30it/s]
 49%|████▉     | 181737/371472 [3:35:10<15:44:05,  3.35it/s]
 49%|████▉     | 181738/371472 [3:35:10<15:42:24,  3.36it/s]
 49%|████▉     | 181739/371472 [3:35:10<15:35:44,  3.38it/s]
 49%|████▉     | 181740/371472 [3:35:11<15:56:55,  3.30it/s]
                                                            
{'loss': 2.9218, 'learning_rate': 5.599291085780775e-07, 'epoch': 7.83}
+
 49%|████▉     | 181740/371472 [3:35:11<15:56:55,  3.30it/s]
 49%|████▉     | 181741/371472 [3:35:11<16:09:13,  3.26it/s]
 49%|████▉     | 181742/371472 [3:35:11<16:10:53,  3.26it/s]
 49%|████��     | 181743/371472 [3:35:12<16:24:59,  3.21it/s]
 49%|████▉     | 181744/371472 [3:35:12<16:36:51,  3.17it/s]
 49%|████▉     | 181745/371472 [3:35:12<16:26:32,  3.21it/s]
 49%|████▉     | 181746/371472 [3:35:13<16:00:10,  3.29it/s]
 49%|████▉     | 181747/371472 [3:35:13<15:38:01,  3.37it/s]
 49%|████▉     | 181748/371472 [3:35:13<15:30:51,  3.40it/s]
 49%|████▉     | 181749/371472 [3:35:13<15:20:32,  3.44it/s]
 49%|████▉     | 181750/371472 [3:35:14<15:22:11,  3.43it/s]
 49%|████▉     | 181751/371472 [3:35:14<15:08:29,  3.48it/s]
 49%|████▉     | 181752/371472 [3:35:14<16:18:18,  3.23it/s]
 49%|████▉     | 181753/371472 [3:35:15<16:06:56,  3.27it/s]
 49%|████▉     | 181754/371472 [3:35:15<15:36:45,  3.38it/s]
 49%|████▉     | 181755/371472 [3:35:15<15:20:01,  3.44it/s]
 49%|████▉     | 181756/371472 [3:35:16<15:49:14,  3.33it/s]
 49%|████▉     | 181757/371472 [3:35:16<15:25:52,  3.42it/s]
 49%|████▉     | 181758/371472 [3:35:16<15:16:06,  3.45it/s]
 49%|████▉     | 181759/371472 [3:35:16<15:11:27,  3.47it/s]
 49%|████▉     | 181760/371472 [3:35:17<15:56:28,  3.31it/s]
                                                            
{'loss': 3.0218, 'learning_rate': 5.598806266025986e-07, 'epoch': 7.83}
+
 49%|████▉     | 181760/371472 [3:35:17<15:56:28,  3.31it/s]
 49%|████▉     | 181761/371472 [3:35:17<15:47:47,  3.34it/s]
 49%|████▉     | 181762/371472 [3:35:17<15:52:01,  3.32it/s]
 49%|████▉     | 181763/371472 [3:35:18<16:23:25,  3.22it/s]
 49%|████▉     | 181764/371472 [3:35:18<16:19:34,  3.23it/s]
 49%|████▉     | 181765/371472 [3:35:18<16:06:22,  3.27it/s]
 49%|████▉     | 181766/371472 [3:35:19<15:38:12,  3.37it/s]
 49%|████▉     | 181767/371472 [3:35:19<15:37:05,  3.37it/s]
 49%|████▉     | 181768/371472 [3:35:19<15:28:01,  3.41it/s]
 49%|████▉     | 181769/371472 [3:35:19<15:30:45,  3.40it/s]
 49%|████▉     | 181770/371472 [3:35:20<15:07:50,  3.48it/s]
 49%|████▉     | 181771/371472 [3:35:20<15:06:16,  3.49it/s]
 49%|████▉     | 181772/371472 [3:35:20<15:24:21,  3.42it/s]
 49%|████▉     | 181773/371472 [3:35:21<15:32:08,  3.39it/s]
 49%|████▉     | 181774/371472 [3:35:21<15:45:10,  3.34it/s]
 49%|████▉     | 181775/371472 [3:35:21<15:49:57,  3.33it/s]
 49%|████▉     | 181776/371472 [3:35:21<15:58:56,  3.30it/s]
 49%|████▉     | 181777/371472 [3:35:22<16:03:13,  3.28it/s]
 49%|████▉     | 181778/371472 [3:35:22<15:51:24,  3.32it/s]
 49%|████▉     | 181779/371472 [3:35:22<15:42:30,  3.35it/s]
 49%|████▉     | 181780/371472 [3:35:23<15:31:01,  3.40it/s]
                                                            
{'loss': 2.9055, 'learning_rate': 5.598321446271197e-07, 'epoch': 7.83}
+
 49%|████▉     | 181780/371472 [3:35:23<15:31:01,  3.40it/s]
 49%|████▉     | 181781/371472 [3:35:23<15:19:10,  3.44it/s]
 49%|████▉     | 181782/371472 [3:35:23<15:30:01,  3.40it/s]
 49%|████▉     | 181783/371472 [3:35:24<15:10:10,  3.47it/s]
 49%|████▉     | 181784/371472 [3:35:24<15:12:53,  3.46it/s]
 49%|████▉     | 181785/371472 [3:35:24<15:32:55,  3.39it/s]
 49%|████▉     | 181786/371472 [3:35:24<15:24:19,  3.42it/s]
 49%|████▉     | 181787/371472 [3:35:25<15:15:02,  3.45it/s]
 49%|████▉     | 181788/371472 [3:35:25<15:10:09,  3.47it/s]
 49%|████▉     | 181789/371472 [3:35:25<15:07:53,  3.48it/s]
 49%|████▉     | 181790/371472 [3:35:26<15:04:11,  3.50it/s]
 49%|████▉     | 181791/371472 [3:35:26<15:19:01,  3.44it/s]
 49%|████▉     | 181792/371472 [3:35:26<16:27:14,  3.20it/s]
 49%|████▉     | 181793/371472 [3:35:26<16:07:01,  3.27it/s]
 49%|████▉     | 181794/371472 [3:35:27<16:08:15,  3.26it/s]
 49%|████▉     | 181795/371472 [3:35:27<15:55:41,  3.31it/s]
 49%|████▉     | 181796/371472 [3:35:27<16:02:23,  3.28it/s]
 49%|████▉     | 181797/371472 [3:35:28<15:40:30,  3.36it/s]
 49%|████▉     | 181798/371472 [3:35:28<15:48:24,  3.33it/s]
 49%|████▉     | 181799/371472 [3:35:28<16:22:07,  3.22it/s]
 49%|████▉     | 181800/371472 [3:35:29<17:02:31,  3.09it/s]
                                                            
{'loss': 2.7596, 'learning_rate': 5.597836626516408e-07, 'epoch': 7.83}
+
 49%|████▉     | 181800/371472 [3:35:29<17:02:31,  3.09it/s]
 49%|████▉     | 181801/371472 [3:35:29<16:23:22,  3.21it/s]
 49%|████▉     | 181802/371472 [3:35:29<16:03:07,  3.28it/s]
 49%|████▉     | 181803/371472 [3:35:30<16:14:32,  3.24it/s]
 49%|████▉     | 181804/371472 [3:35:30<15:55:02,  3.31it/s]
 49%|████▉     | 181805/371472 [3:35:30<16:09:56,  3.26it/s]
 49%|████▉     | 181806/371472 [3:35:30<16:06:45,  3.27it/s]
 49%|████▉     | 181807/371472 [3:35:31<15:51:16,  3.32it/s]
 49%|████▉     | 181808/371472 [3:35:31<15:56:25,  3.31it/s]
 49%|████▉     | 181809/371472 [3:35:31<16:07:24,  3.27it/s]
 49%|████▉     | 181810/371472 [3:35:32<16:00:34,  3.29it/s]
 49%|████▉     | 181811/371472 [3:35:32<16:22:19,  3.22it/s]
 49%|████▉     | 181812/371472 [3:35:32<17:19:41,  3.04it/s]
 49%|████▉     | 181813/371472 [3:35:33<17:17:06,  3.05it/s]
 49%|████▉     | 181814/371472 [3:35:33<16:31:57,  3.19it/s]
 49%|████▉     | 181815/371472 [3:35:33<15:57:55,  3.30it/s]
 49%|████▉     | 181816/371472 [3:35:34<15:48:18,  3.33it/s]
 49%|████▉     | 181817/371472 [3:35:34<15:24:52,  3.42it/s]
 49%|████▉     | 181818/371472 [3:35:34<15:24:39,  3.42it/s]
 49%|████▉     | 181819/371472 [3:35:34<15:35:02,  3.38it/s]
 49%|████▉     | 181820/371472 [3:35:35<15:30:25,  3.40it/s]
                                                            
{'loss': 2.8521, 'learning_rate': 5.597351806761619e-07, 'epoch': 7.83}
+
 49%|████▉     | 181820/371472 [3:35:35<15:30:25,  3.40it/s]
 49%|████▉     | 181821/371472 [3:35:35<15:10:15,  3.47it/s]
 49%|████▉     | 181822/371472 [3:35:35<16:20:31,  3.22it/s]
 49%|████▉     | 181823/371472 [3:35:36<15:55:45,  3.31it/s]
 49%|████▉     | 181824/371472 [3:35:36<16:18:20,  3.23it/s]
 49%|████▉     | 181825/371472 [3:35:36<16:18:33,  3.23it/s]
 49%|████▉     | 181826/371472 [3:35:37<15:58:21,  3.30it/s]
 49%|████▉     | 181827/371472 [3:35:37<15:46:10,  3.34it/s]
 49%|████▉     | 181828/371472 [3:35:37<15:37:31,  3.37it/s]
 49%|████▉     | 181829/371472 [3:35:38<16:41:59,  3.15it/s]
 49%|████▉     | 181830/371472 [3:35:38<17:20:31,  3.04it/s]
 49%|████▉     | 181831/371472 [3:35:38<16:34:04,  3.18it/s]
 49%|████▉     | 181832/371472 [3:35:38<16:22:39,  3.22it/s]
 49%|████▉     | 181833/371472 [3:35:39<16:08:30,  3.26it/s]
 49%|████▉     | 181834/371472 [3:35:39<15:51:39,  3.32it/s]
 49%|████▉     | 181835/371472 [3:35:39<15:31:38,  3.39it/s]
 49%|████▉     | 181836/371472 [3:35:40<15:06:55,  3.48it/s]
 49%|████▉     | 181837/371472 [3:35:40<15:22:00,  3.43it/s]
 49%|████▉     | 181838/371472 [3:35:40<20:01:25,  2.63it/s]
 49%|████▉     | 181839/371472 [3:35:41<18:47:52,  2.80it/s]
 49%|████▉     | 181840/371472 [3:35:41<19:23:03,  2.72it/s]
                                                            
{'loss': 2.8664, 'learning_rate': 5.59686698700683e-07, 'epoch': 7.83}
+
 49%|████▉     | 181840/371472 [3:35:41<19:23:03,  2.72it/s]
 49%|████▉     | 181841/371472 [3:35:41<18:04:05,  2.92it/s]
 49%|████▉     | 181842/371472 [3:35:42<16:53:05,  3.12it/s]
 49%|████▉     | 181843/371472 [3:35:42<16:43:44,  3.15it/s]
 49%|████▉     | 181844/371472 [3:35:42<16:11:46,  3.25it/s]
 49%|████▉     | 181845/371472 [3:35:43<15:44:32,  3.35it/s]
 49%|████▉     | 181846/371472 [3:35:43<15:49:26,  3.33it/s]
 49%|████▉     | 181847/371472 [3:35:43<16:03:17,  3.28it/s]
 49%|████▉     | 181848/371472 [3:35:44<15:54:59,  3.31it/s]
 49%|████▉     | 181849/371472 [3:35:44<15:41:17,  3.36it/s]
 49%|████▉     | 181850/371472 [3:35:44<15:26:36,  3.41it/s]
 49%|████▉     | 181851/371472 [3:35:44<15:09:31,  3.47it/s]
 49%|████▉     | 181852/371472 [3:35:45<14:43:29,  3.58it/s]
 49%|████▉     | 181853/371472 [3:35:45<14:47:17,  3.56it/s]
 49%|████▉     | 181854/371472 [3:35:45<14:58:45,  3.52it/s]
 49%|████▉     | 181855/371472 [3:35:46<15:20:30,  3.43it/s]
 49%|████▉     | 181856/371472 [3:35:46<15:27:12,  3.41it/s]
 49%|████▉     | 181857/371472 [3:35:46<15:15:34,  3.45it/s]
 49%|████▉     | 181858/371472 [3:35:46<15:12:55,  3.46it/s]
 49%|████▉     | 181859/371472 [3:35:47<14:57:31,  3.52it/s]
 49%|████▉     | 181860/371472 [3:35:47<16:47:18,  3.14it/s]
                                                            
{'loss': 2.763, 'learning_rate': 5.596382167252041e-07, 'epoch': 7.83}
+
 49%|████▉     | 181860/371472 [3:35:47<16:47:18,  3.14it/s]
 49%|████▉     | 181861/371472 [3:35:47<16:25:36,  3.21it/s]
 49%|████▉     | 181862/371472 [3:35:48<17:02:21,  3.09it/s]
 49%|████▉     | 181863/371472 [3:35:48<17:01:36,  3.09it/s]
 49%|████▉     | 181864/371472 [3:35:48<17:02:16,  3.09it/s]
 49%|████▉     | 181865/371472 [3:35:49<16:29:45,  3.19it/s]
 49%|████▉     | 181866/371472 [3:35:49<15:50:37,  3.32it/s]
 49%|████▉     | 181867/371472 [3:35:49<15:43:15,  3.35it/s]
 49%|████▉     | 181868/371472 [3:35:49<15:14:16,  3.46it/s]
 49%|████▉     | 181869/371472 [3:35:50<15:15:41,  3.45it/s]
 49%|████▉     | 181870/371472 [3:35:50<14:52:33,  3.54it/s]
 49%|████▉     | 181871/371472 [3:35:50<15:29:12,  3.40it/s]
 49%|████▉     | 181872/371472 [3:35:51<15:30:37,  3.40it/s]
 49%|████▉     | 181873/371472 [3:35:51<15:42:09,  3.35it/s]
 49%|████▉     | 181874/371472 [3:35:51<15:30:54,  3.39it/s]
 49%|████▉     | 181875/371472 [3:35:52<15:22:15,  3.43it/s]
 49%|████▉     | 181876/371472 [3:35:52<15:33:07,  3.39it/s]
 49%|████▉     | 181877/371472 [3:35:52<15:35:32,  3.38it/s]
 49%|████▉     | 181878/371472 [3:35:52<15:47:55,  3.33it/s]
 49%|████▉     | 181879/371472 [3:35:53<16:05:40,  3.27it/s]
 49%|████▉     | 181880/371472 [3:35:53<15:43:36,  3.35it/s]
                                                            
{'loss': 2.7258, 'learning_rate': 5.595897347497253e-07, 'epoch': 7.83}
+
 49%|████▉     | 181880/371472 [3:35:53<15:43:36,  3.35it/s]
 49%|████▉     | 181881/371472 [3:35:53<16:03:56,  3.28it/s]
 49%|████▉     | 181882/371472 [3:35:54<15:57:56,  3.30it/s]
 49%|████▉     | 181883/371472 [3:35:54<15:31:16,  3.39it/s]
 49%|████▉     | 181884/371472 [3:35:54<15:56:29,  3.30it/s]
 49%|████▉     | 181885/371472 [3:35:55<16:07:09,  3.27it/s]
 49%|████▉     | 181886/371472 [3:35:55<17:08:54,  3.07it/s]
 49%|████▉     | 181887/371472 [3:35:55<16:42:00,  3.15it/s]
 49%|████▉     | 181888/371472 [3:35:56<16:21:19,  3.22it/s]
 49%|████▉     | 181889/371472 [3:35:56<16:07:45,  3.26it/s]
 49%|████▉     | 181890/371472 [3:35:56<15:56:26,  3.30it/s]
 49%|████▉     | 181891/371472 [3:35:56<15:46:40,  3.34it/s]
 49%|████▉     | 181892/371472 [3:35:57<15:26:34,  3.41it/s]
 49%|████▉     | 181893/371472 [3:35:57<15:30:13,  3.40it/s]
 49%|████▉     | 181894/371472 [3:35:57<15:38:31,  3.37it/s]
 49%|████▉     | 181895/371472 [3:35:58<15:47:41,  3.33it/s]
 49%|████▉     | 181896/371472 [3:35:58<15:34:24,  3.38it/s]
 49%|████▉     | 181897/371472 [3:35:58<15:29:53,  3.40it/s]
 49%|████▉     | 181898/371472 [3:35:58<15:16:19,  3.45it/s]
 49%|████▉     | 181899/371472 [3:35:59<15:41:10,  3.36it/s]
 49%|████▉     | 181900/371472 [3:35:59<15:06:14,  3.49it/s]
                                                            
{'loss': 2.955, 'learning_rate': 5.595412527742464e-07, 'epoch': 7.83}
+
 49%|████▉     | 181900/371472 [3:35:59<15:06:14,  3.49it/s]
 49%|████▉     | 181901/371472 [3:35:59<15:24:43,  3.42it/s]
 49%|████▉     | 181902/371472 [3:36:00<15:17:15,  3.44it/s]
 49%|████▉     | 181903/371472 [3:36:00<15:10:34,  3.47it/s]
 49%|████▉     | 181904/371472 [3:36:00<15:11:54,  3.46it/s]
 49%|████▉     | 181905/371472 [3:36:00<14:41:31,  3.58it/s]
 49%|████▉     | 181906/371472 [3:36:01<14:39:11,  3.59it/s]
 49%|████▉     | 181907/371472 [3:36:01<15:21:54,  3.43it/s]
 49%|████▉     | 181908/371472 [3:36:01<16:15:07,  3.24it/s]
 49%|████▉     | 181909/371472 [3:36:02<15:50:53,  3.32it/s]
 49%|████▉     | 181910/371472 [3:36:02<15:39:27,  3.36it/s]
 49%|████▉     | 181911/371472 [3:36:02<15:21:20,  3.43it/s]
 49%|████▉     | 181912/371472 [3:36:03<15:14:58,  3.45it/s]
 49%|████▉     | 181913/371472 [3:36:03<15:35:44,  3.38it/s]
 49%|████▉     | 181914/371472 [3:36:03<15:43:44,  3.35it/s]
 49%|████▉     | 181915/371472 [3:36:03<15:56:45,  3.30it/s]
 49%|████▉     | 181916/371472 [3:36:04<15:24:16,  3.42it/s]
 49%|████▉     | 181917/371472 [3:36:04<15:29:18,  3.40it/s]
 49%|████▉     | 181918/371472 [3:36:04<15:23:59,  3.42it/s]
 49%|████▉     | 181919/371472 [3:36:05<15:29:40,  3.40it/s]
 49%|████▉     | 181920/371472 [3:36:05<15:27:02,  3.41it/s]
                                                            
{'loss': 2.8266, 'learning_rate': 5.594927707987675e-07, 'epoch': 7.84}
+
 49%|████▉     | 181920/371472 [3:36:05<15:27:02,  3.41it/s]
 49%|████▉     | 181921/371472 [3:36:05<15:12:55,  3.46it/s]
 49%|████▉     | 181922/371472 [3:36:05<15:34:22,  3.38it/s]
 49%|████▉     | 181923/371472 [3:36:06<15:28:14,  3.40it/s]
 49%|████▉     | 181924/371472 [3:36:06<16:06:50,  3.27it/s]
 49%|████▉     | 181925/371472 [3:36:06<17:04:42,  3.08it/s]
 49%|████▉     | 181926/371472 [3:36:07<16:29:53,  3.19it/s]
 49%|████▉     | 181927/371472 [3:36:07<17:01:27,  3.09it/s]
 49%|████▉     | 181928/371472 [3:36:07<16:20:50,  3.22it/s]
 49%|████▉     | 181929/371472 [3:36:08<15:48:11,  3.33it/s]
 49%|████▉     | 181930/371472 [3:36:08<15:47:13,  3.34it/s]
 49%|████▉     | 181931/371472 [3:36:08<15:28:23,  3.40it/s]
 49%|████▉     | 181932/371472 [3:36:09<15:30:51,  3.39it/s]
 49%|████▉     | 181933/371472 [3:36:09<15:22:00,  3.43it/s]
 49%|████▉     | 181934/371472 [3:36:09<15:19:26,  3.44it/s]
 49%|████▉     | 181935/371472 [3:36:09<14:54:54,  3.53it/s]
 49%|████▉     | 181936/371472 [3:36:10<15:19:30,  3.44it/s]
 49%|████▉     | 181937/371472 [3:36:10<15:06:52,  3.48it/s]
 49%|████▉     | 181938/371472 [3:36:10<15:00:54,  3.51it/s]
 49%|████▉     | 181939/371472 [3:36:11<15:39:28,  3.36it/s]
 49%|████▉     | 181940/371472 [3:36:11<15:54:35,  3.31it/s]
                                                            
{'loss': 3.0105, 'learning_rate': 5.594442888232885e-07, 'epoch': 7.84}
+
 49%|████▉     | 181940/371472 [3:36:11<15:54:35,  3.31it/s]
 49%|████▉     | 181941/371472 [3:36:11<15:59:06,  3.29it/s]
 49%|████▉     | 181942/371472 [3:36:11<15:42:54,  3.35it/s]
 49%|████▉     | 181943/371472 [3:36:12<15:30:20,  3.40it/s]
 49%|████▉     | 181944/371472 [3:36:12<15:19:10,  3.44it/s]
 49%|████▉     | 181945/371472 [3:36:12<15:36:51,  3.37it/s]
 49%|████▉     | 181946/371472 [3:36:13<15:28:36,  3.40it/s]
 49%|████▉     | 181947/371472 [3:36:13<16:02:06,  3.28it/s]
 49%|████▉     | 181948/371472 [3:36:13<16:07:05,  3.27it/s]
 49%|████▉     | 181949/371472 [3:36:14<15:42:23,  3.35it/s]
 49%|████▉     | 181950/371472 [3:36:14<15:46:32,  3.34it/s]
 49%|████▉     | 181951/371472 [3:36:14<15:55:36,  3.31it/s]
 49%|████▉     | 181952/371472 [3:36:14<15:36:30,  3.37it/s]
 49%|████▉     | 181953/371472 [3:36:15<15:33:12,  3.38it/s]
 49%|████▉     | 181954/371472 [3:36:15<15:18:15,  3.44it/s]
 49%|████▉     | 181955/371472 [3:36:15<15:29:50,  3.40it/s]
 49%|████▉     | 181956/371472 [3:36:16<15:02:00,  3.50it/s]
 49%|████▉     | 181957/371472 [3:36:16<15:09:54,  3.47it/s]
 49%|████▉     | 181958/371472 [3:36:16<16:19:10,  3.23it/s]
 49%|████▉     | 181959/371472 [3:36:17<16:04:14,  3.28it/s]
 49%|████▉     | 181960/371472 [3:36:17<16:23:35,  3.21it/s]
                                                            
{'loss': 2.8356, 'learning_rate': 5.593958068478098e-07, 'epoch': 7.84}
+
 49%|████▉     | 181960/371472 [3:36:17<16:23:35,  3.21it/s]
 49%|████▉     | 181961/371472 [3:36:17<16:03:41,  3.28it/s]
 49%|████▉     | 181962/371472 [3:36:17<16:28:57,  3.19it/s]
 49%|████▉     | 181963/371472 [3:36:18<16:24:26,  3.21it/s]
 49%|████▉     | 181964/371472 [3:36:18<16:39:05,  3.16it/s]
 49%|████▉     | 181965/371472 [3:36:18<16:04:10,  3.28it/s]
 49%|████▉     | 181966/371472 [3:36:19<15:42:35,  3.35it/s]
 49%|████▉     | 181967/371472 [3:36:19<15:32:58,  3.39it/s]
 49%|████▉     | 181968/371472 [3:36:19<15:30:28,  3.39it/s]
 49%|████▉     | 181969/371472 [3:36:20<15:38:27,  3.37it/s]
 49%|████▉     | 181970/371472 [3:36:20<15:30:59,  3.39it/s]
 49%|████▉     | 181971/371472 [3:36:20<16:05:54,  3.27it/s]
 49%|████▉     | 181972/371472 [3:36:21<16:44:14,  3.15it/s]
 49%|████▉     | 181973/371472 [3:36:21<16:27:32,  3.20it/s]
 49%|████▉     | 181974/371472 [3:36:21<16:52:10,  3.12it/s]
 49%|████▉     | 181975/371472 [3:36:21<16:12:07,  3.25it/s]
 49%|████▉     | 181976/371472 [3:36:22<15:44:08,  3.35it/s]
 49%|████▉     | 181977/371472 [3:36:22<16:31:51,  3.18it/s]
 49%|████▉     | 181978/371472 [3:36:22<16:11:04,  3.25it/s]
 49%|████▉     | 181979/371472 [3:36:23<16:18:22,  3.23it/s]
 49%|████▉     | 181980/371472 [3:36:23<17:51:21,  2.95it/s]
                                                            
{'loss': 3.0566, 'learning_rate': 5.593473248723309e-07, 'epoch': 7.84}
+
 49%|████▉     | 181980/371472 [3:36:23<17:51:21,  2.95it/s]
 49%|████▉     | 181981/371472 [3:36:23<17:05:42,  3.08it/s]
 49%|████▉     | 181982/371472 [3:36:24<16:30:52,  3.19it/s]
 49%|████▉     | 181983/371472 [3:36:24<16:07:30,  3.26it/s]
 49%|████▉     | 181984/371472 [3:36:24<15:46:54,  3.34it/s]
 49%|████▉     | 181985/371472 [3:36:25<15:33:34,  3.38it/s]
 49%|████▉     | 181986/371472 [3:36:25<16:23:15,  3.21it/s]
 49%|████▉     | 181987/371472 [3:36:25<15:54:56,  3.31it/s]
 49%|████▉     | 181988/371472 [3:36:25<15:29:15,  3.40it/s]
 49%|████▉     | 181989/371472 [3:36:26<15:25:21,  3.41it/s]
 49%|████▉     | 181990/371472 [3:36:26<15:00:34,  3.51it/s]
 49%|████▉     | 181991/371472 [3:36:26<15:33:14,  3.38it/s]
 49%|████▉     | 181992/371472 [3:36:27<15:46:07,  3.34it/s]
 49%|████▉     | 181993/371472 [3:36:27<15:41:38,  3.35it/s]
 49%|████▉     | 181994/371472 [3:36:27<15:41:19,  3.35it/s]
 49%|████▉     | 181995/371472 [3:36:28<15:53:10,  3.31it/s]
 49%|████▉     | 181996/371472 [3:36:28<15:20:46,  3.43it/s]
 49%|████▉     | 181997/371472 [3:36:28<15:16:33,  3.45it/s]
 49%|████▉     | 181998/371472 [3:36:28<15:07:38,  3.48it/s]
 49%|████▉     | 181999/371472 [3:36:29<15:01:17,  3.50it/s]
 49%|████▉     | 182000/371472 [3:36:29<16:01:50,  3.28it/s]
                                                            
{'loss': 2.8246, 'learning_rate': 5.592988428968518e-07, 'epoch': 7.84}
+
 49%|████▉     | 182000/371472 [3:36:29<16:01:50,  3.28it/s]
 49%|████▉     | 182001/371472 [3:36:29<15:46:02,  3.34it/s]
 49%|████▉     | 182002/371472 [3:36:30<15:42:01,  3.35it/s]
 49%|████▉     | 182003/371472 [3:36:30<17:02:08,  3.09it/s]
 49%|████▉     | 182004/371472 [3:36:30<16:27:05,  3.20it/s]
 49%|████▉     | 182005/371472 [3:36:31<17:22:06,  3.03it/s]
 49%|████▉     | 182006/371472 [3:36:31<16:56:21,  3.11it/s]
 49%|████▉     | 182007/371472 [3:36:31<16:31:04,  3.19it/s]
 49%|████▉     | 182008/371472 [3:36:32<15:58:08,  3.30it/s]
 49%|████▉     | 182009/371472 [3:36:32<15:44:00,  3.34it/s]
 49%|████▉     | 182010/371472 [3:36:32<16:05:44,  3.27it/s]
 49%|████▉     | 182011/371472 [3:36:32<16:41:35,  3.15it/s]
 49%|████▉     | 182012/371472 [3:36:33<15:59:33,  3.29it/s]
 49%|████▉     | 182013/371472 [3:36:33<15:57:56,  3.30it/s]
 49%|████▉     | 182014/371472 [3:36:33<16:03:39,  3.28it/s]
 49%|████▉     | 182015/371472 [3:36:34<16:21:41,  3.22it/s]
 49%|████▉     | 182016/371472 [3:36:34<15:42:08,  3.35it/s]
 49%|████▉     | 182017/371472 [3:36:34<16:04:45,  3.27it/s]
 49%|████▉     | 182018/371472 [3:36:35<16:16:07,  3.23it/s]
 49%|████▉     | 182019/371472 [3:36:35<16:38:43,  3.16it/s]
 49%|████▉     | 182020/371472 [3:36:35<16:17:01,  3.23it/s]
                                                            
{'loss': 2.8604, 'learning_rate': 5.59250360921373e-07, 'epoch': 7.84}
+
 49%|████▉     | 182020/371472 [3:36:35<16:17:01,  3.23it/s]
 49%|████▉     | 182021/371472 [3:36:36<16:07:21,  3.26it/s]
 49%|████▉     | 182022/371472 [3:36:36<15:38:57,  3.36it/s]
 49%|████▉     | 182023/371472 [3:36:36<15:46:06,  3.34it/s]
 49%|████▉     | 182024/371472 [3:36:36<16:02:10,  3.28it/s]
 49%|████▉     | 182025/371472 [3:36:37<15:52:58,  3.31it/s]
 49%|████▉     | 182026/371472 [3:36:37<15:38:02,  3.37it/s]
 49%|████▉     | 182027/371472 [3:36:37<16:44:37,  3.14it/s]
 49%|████▉     | 182028/371472 [3:36:38<16:33:42,  3.18it/s]
 49%|████▉     | 182029/371472 [3:36:38<15:48:52,  3.33it/s]
 49%|████▉     | 182030/371472 [3:36:38<15:36:44,  3.37it/s]
 49%|████▉     | 182031/371472 [3:36:39<15:35:08,  3.38it/s]
 49%|████▉     | 182032/371472 [3:36:39<15:37:09,  3.37it/s]
 49%|████▉     | 182033/371472 [3:36:39<15:29:50,  3.40it/s]
 49%|████▉     | 182034/371472 [3:36:39<15:27:25,  3.40it/s]
 49%|████▉     | 182035/371472 [3:36:40<15:32:37,  3.39it/s]
 49%|████▉     | 182036/371472 [3:36:40<15:36:49,  3.37it/s]
 49%|████▉     | 182037/371472 [3:36:40<16:48:15,  3.13it/s]
 49%|████▉     | 182038/371472 [3:36:41<16:42:16,  3.15it/s]
 49%|████▉     | 182039/371472 [3:36:41<17:26:42,  3.02it/s]
 49%|████▉     | 182040/371472 [3:36:41<16:46:09,  3.14it/s]
                                                            
{'loss': 2.8263, 'learning_rate': 5.592018789458941e-07, 'epoch': 7.84}
+
 49%|████▉     | 182040/371472 [3:36:41<16:46:09,  3.14it/s]
 49%|████▉     | 182041/371472 [3:36:42<16:07:09,  3.26it/s]
 49%|████▉     | 182042/371472 [3:36:42<15:47:41,  3.33it/s]
 49%|████▉     | 182043/371472 [3:36:42<15:41:33,  3.35it/s]
 49%|████▉     | 182044/371472 [3:36:42<16:00:52,  3.29it/s]
 49%|████▉     | 182045/371472 [3:36:43<15:41:43,  3.35it/s]
 49%|████▉     | 182046/371472 [3:36:43<15:28:46,  3.40it/s]
 49%|████▉     | 182047/371472 [3:36:43<15:14:48,  3.45it/s]
 49%|████▉     | 182048/371472 [3:36:44<15:12:22,  3.46it/s]
 49%|████▉     | 182049/371472 [3:36:44<15:20:27,  3.43it/s]
 49%|████▉     | 182050/371472 [3:36:44<15:32:18,  3.39it/s]
 49%|████▉     | 182051/371472 [3:36:45<16:08:51,  3.26it/s]
 49%|████▉     | 182052/371472 [3:36:45<17:00:31,  3.09it/s]
 49%|████▉     | 182053/371472 [3:36:45<16:34:25,  3.17it/s]
 49%|████▉     | 182054/371472 [3:36:45<15:51:03,  3.32it/s]
 49%|████▉     | 182055/371472 [3:36:46<16:02:14,  3.28it/s]
 49%|████▉     | 182056/371472 [3:36:46<15:36:53,  3.37it/s]
 49%|████▉     | 182057/371472 [3:36:46<15:32:36,  3.39it/s]
 49%|████▉     | 182058/371472 [3:36:47<15:35:17,  3.38it/s]
 49%|████▉     | 182059/371472 [3:36:47<15:36:58,  3.37it/s]
 49%|████▉     | 182060/371472 [3:36:47<15:47:11,  3.33it/s]
                                                            
{'loss': 2.9423, 'learning_rate': 5.591533969704152e-07, 'epoch': 7.84}
+
 49%|████▉     | 182060/371472 [3:36:47<15:47:11,  3.33it/s]
 49%|████▉     | 182061/371472 [3:36:48<16:11:33,  3.25it/s]
 49%|████▉     | 182062/371472 [3:36:48<16:44:31,  3.14it/s]
 49%|████▉     | 182063/371472 [3:36:48<16:19:47,  3.22it/s]
 49%|████▉     | 182064/371472 [3:36:49<16:18:09,  3.23it/s]
 49%|████▉     | 182065/371472 [3:36:49<15:49:46,  3.32it/s]
 49%|████▉     | 182066/371472 [3:36:49<15:24:29,  3.41it/s]
 49%|████▉     | 182067/371472 [3:36:49<15:05:02,  3.49it/s]
 49%|████▉     | 182068/371472 [3:36:50<14:54:18,  3.53it/s]
 49%|████▉     | 182069/371472 [3:36:50<14:44:23,  3.57it/s]
 49%|████▉     | 182070/371472 [3:36:50<15:56:06,  3.30it/s]
 49%|████▉     | 182071/371472 [3:36:51<15:51:35,  3.32it/s]
 49%|████▉     | 182072/371472 [3:36:51<15:43:03,  3.35it/s]
 49%|████▉     | 182073/371472 [3:36:51<15:18:08,  3.44it/s]
 49%|████▉     | 182074/371472 [3:36:51<15:09:03,  3.47it/s]
 49%|████▉     | 182075/371472 [3:36:52<15:08:02,  3.48it/s]
 49%|████▉     | 182076/371472 [3:36:52<15:35:52,  3.37it/s]
 49%|████▉     | 182077/371472 [3:36:52<15:23:45,  3.42it/s]
 49%|████▉     | 182078/371472 [3:36:53<15:35:30,  3.37it/s]
 49%|████▉     | 182079/371472 [3:36:53<15:24:10,  3.42it/s]
 49%|████▉     | 182080/371472 [3:36:53<15:56:42,  3.30it/s]
                                                            
{'loss': 3.0576, 'learning_rate': 5.591049149949362e-07, 'epoch': 7.84}
+
 49%|████▉     | 182080/371472 [3:36:53<15:56:42,  3.30it/s]
 49%|████▉     | 182081/371472 [3:36:54<15:47:55,  3.33it/s]
 49%|████▉     | 182082/371472 [3:36:54<15:26:31,  3.41it/s]
 49%|████▉     | 182083/371472 [3:36:54<15:20:05,  3.43it/s]
 49%|████▉     | 182084/371472 [3:36:54<16:19:04,  3.22it/s]
 49%|████▉     | 182085/371472 [3:36:55<16:29:34,  3.19it/s]
 49%|████▉     | 182086/371472 [3:36:55<17:22:01,  3.03it/s]
 49%|████▉     | 182087/371472 [3:36:55<17:29:59,  3.01it/s]
 49%|████▉     | 182088/371472 [3:36:56<16:40:36,  3.15it/s]
 49%|████▉     | 182089/371472 [3:36:56<15:58:28,  3.29it/s]
 49%|████▉     | 182090/371472 [3:36:56<15:48:22,  3.33it/s]
 49%|████▉     | 182091/371472 [3:36:57<15:37:00,  3.37it/s]
 49%|████▉     | 182092/371472 [3:36:57<15:09:04,  3.47it/s]
 49%|████▉     | 182093/371472 [3:36:57<15:24:01,  3.42it/s]
 49%|████▉     | 182094/371472 [3:36:58<16:04:53,  3.27it/s]
 49%|████▉     | 182095/371472 [3:36:58<17:07:53,  3.07it/s]
 49%|████▉     | 182096/371472 [3:36:58<17:33:32,  3.00it/s]
 49%|████▉     | 182097/371472 [3:36:59<16:55:05,  3.11it/s]
 49%|████▉     | 182098/371472 [3:36:59<16:53:46,  3.11it/s]
 49%|████▉     | 182099/371472 [3:36:59<17:40:09,  2.98it/s]
 49%|████▉     | 182100/371472 [3:37:00<17:38:48,  2.98it/s]
                                                            
{'loss': 2.9191, 'learning_rate': 5.590564330194574e-07, 'epoch': 7.84}
+
 49%|████▉     | 182100/371472 [3:37:00<17:38:48,  2.98it/s]
 49%|████▉     | 182101/371472 [3:37:00<17:04:22,  3.08it/s]
 49%|████▉     | 182102/371472 [3:37:00<16:25:49,  3.20it/s]
 49%|████▉     | 182103/371472 [3:37:00<16:20:43,  3.22it/s]
 49%|████▉     | 182104/371472 [3:37:01<16:01:43,  3.28it/s]
 49%|████▉     | 182105/371472 [3:37:01<16:05:46,  3.27it/s]
 49%|████▉     | 182106/371472 [3:37:01<16:46:41,  3.14it/s]
 49%|████▉     | 182107/371472 [3:37:02<16:17:59,  3.23it/s]
 49%|████▉     | 182108/371472 [3:37:02<15:43:47,  3.34it/s]
 49%|████▉     | 182109/371472 [3:37:02<15:25:02,  3.41it/s]
 49%|████▉     | 182110/371472 [3:37:03<15:34:53,  3.38it/s]
 49%|████▉     | 182111/371472 [3:37:03<15:31:56,  3.39it/s]
 49%|████▉     | 182112/371472 [3:37:03<15:44:54,  3.34it/s]
 49%|████▉     | 182113/371472 [3:37:04<16:47:06,  3.13it/s]
 49%|████▉     | 182114/371472 [3:37:04<16:48:10,  3.13it/s]
 49%|████▉     | 182115/371472 [3:37:04<17:30:19,  3.00it/s]
 49%|████▉     | 182116/371472 [3:37:05<17:13:16,  3.05it/s]
 49%|████▉     | 182117/371472 [3:37:05<16:22:16,  3.21it/s]
 49%|████▉     | 182118/371472 [3:37:05<18:08:57,  2.90it/s]
 49%|████▉     | 182119/371472 [3:37:06<17:54:12,  2.94it/s]
 49%|████▉     | 182120/371472 [3:37:06<17:32:10,  3.00it/s]
                                                            
{'loss': 2.9829, 'learning_rate': 5.590079510439785e-07, 'epoch': 7.84}
+
 49%|████▉     | 182120/371472 [3:37:06<17:32:10,  3.00it/s]
 49%|████▉     | 182121/371472 [3:37:06<17:37:05,  2.99it/s]
 49%|████▉     | 182122/371472 [3:37:07<17:13:33,  3.05it/s]
 49%|████▉     | 182123/371472 [3:37:07<19:34:30,  2.69it/s]
 49%|████▉     | 182124/371472 [3:37:07<18:27:58,  2.85it/s]
 49%|████▉     | 182125/371472 [3:37:08<18:05:52,  2.91it/s]
 49%|████▉     | 182126/371472 [3:37:08<17:40:10,  2.98it/s]
 49%|████▉     | 182127/371472 [3:37:08<16:51:29,  3.12it/s]
 49%|████▉     | 182128/371472 [3:37:09<17:31:13,  3.00it/s]
 49%|████▉     | 182129/371472 [3:37:09<18:25:30,  2.85it/s]
 49%|████▉     | 182130/371472 [3:37:09<17:36:56,  2.99it/s]
 49%|████▉     | 182131/371472 [3:37:10<17:02:17,  3.09it/s]
 49%|████▉     | 182132/371472 [3:37:10<16:32:39,  3.18it/s]
 49%|████▉     | 182133/371472 [3:37:10<16:40:56,  3.15it/s]
 49%|████▉     | 182134/371472 [3:37:10<16:09:29,  3.25it/s]
 49%|████▉     | 182135/371472 [3:37:11<16:01:20,  3.28it/s]
 49%|████▉     | 182136/371472 [3:37:11<16:14:06,  3.24it/s]
 49%|████▉     | 182137/371472 [3:37:11<16:13:41,  3.24it/s]
 49%|████▉     | 182138/371472 [3:37:12<15:45:51,  3.34it/s]
 49%|████▉     | 182139/371472 [3:37:12<15:42:17,  3.35it/s]
 49%|████▉     | 182140/371472 [3:37:12<15:35:23,  3.37it/s]
                                                            
{'loss': 2.7893, 'learning_rate': 5.589594690684996e-07, 'epoch': 7.85}
+
 49%|████▉     | 182140/371472 [3:37:12<15:35:23,  3.37it/s]
 49%|████▉     | 182141/371472 [3:37:13<15:43:37,  3.34it/s]
 49%|████▉     | 182142/371472 [3:37:13<15:23:34,  3.42it/s]
 49%|████▉     | 182143/371472 [3:37:13<15:31:13,  3.39it/s]
 49%|████▉     | 182144/371472 [3:37:13<15:13:02,  3.46it/s]
 49%|████▉     | 182145/371472 [3:37:14<15:07:13,  3.48it/s]
 49%|████▉     | 182146/371472 [3:37:14<14:57:42,  3.51it/s]
 49%|████▉     | 182147/371472 [3:37:14<14:54:35,  3.53it/s]
 49%|████▉     | 182148/371472 [3:37:15<16:19:01,  3.22it/s]
 49%|████▉     | 182149/371472 [3:37:15<17:02:21,  3.09it/s]
 49%|████▉     | 182150/371472 [3:37:15<16:33:43,  3.18it/s]
 49%|████▉     | 182151/371472 [3:37:16<16:06:18,  3.27it/s]
 49%|████▉     | 182152/371472 [3:37:16<15:49:21,  3.32it/s]
 49%|████▉     | 182153/371472 [3:37:16<15:47:42,  3.33it/s]
 49%|████▉     | 182154/371472 [3:37:16<15:37:27,  3.37it/s]
 49%|████▉     | 182155/371472 [3:37:17<15:18:55,  3.43it/s]
 49%|████▉     | 182156/371472 [3:37:17<15:10:28,  3.47it/s]
 49%|████▉     | 182157/371472 [3:37:17<14:48:49,  3.55it/s]
 49%|████▉     | 182158/371472 [3:37:18<15:37:59,  3.36it/s]
 49%|████▉     | 182159/371472 [3:37:18<15:22:29,  3.42it/s]
 49%|████▉     | 182160/371472 [3:37:18<15:05:26,  3.48it/s]
                                                            
{'loss': 3.0744, 'learning_rate': 5.589109870930207e-07, 'epoch': 7.85}
+
 49%|████▉     | 182160/371472 [3:37:18<15:05:26,  3.48it/s]
 49%|████▉     | 182161/371472 [3:37:18<15:03:54,  3.49it/s]
 49%|████▉     | 182162/371472 [3:37:19<15:13:36,  3.45it/s]
 49%|████▉     | 182163/371472 [3:37:19<15:21:09,  3.43it/s]
 49%|████▉     | 182164/371472 [3:37:19<15:35:31,  3.37it/s]
 49%|████▉     | 182165/371472 [3:37:20<15:23:10,  3.42it/s]
 49%|████▉     | 182166/371472 [3:37:20<15:18:34,  3.43it/s]
 49%|████▉     | 182167/371472 [3:37:20<15:39:01,  3.36it/s]
 49%|████▉     | 182168/371472 [3:37:21<16:02:27,  3.28it/s]
 49%|████▉     | 182169/371472 [3:37:21<15:52:39,  3.31it/s]
 49%|████▉     | 182170/371472 [3:37:21<16:17:47,  3.23it/s]
 49%|████▉     | 182171/371472 [3:37:22<16:39:59,  3.16it/s]
 49%|████▉     | 182172/371472 [3:37:22<16:14:00,  3.24it/s]
 49%|████▉     | 182173/371472 [3:37:22<16:06:58,  3.26it/s]
 49%|████▉     | 182174/371472 [3:37:22<16:42:19,  3.15it/s]
 49%|████▉     | 182175/371472 [3:37:23<16:00:48,  3.28it/s]
 49%|████▉     | 182176/371472 [3:37:23<15:53:28,  3.31it/s]
 49%|████▉     | 182177/371472 [3:37:23<15:26:41,  3.40it/s]
 49%|████▉     | 182178/371472 [3:37:24<15:33:35,  3.38it/s]
 49%|████▉     | 182179/371472 [3:37:24<15:08:52,  3.47it/s]
 49%|████▉     | 182180/371472 [3:37:24<16:59:36,  3.09it/s]
                                                            
{'loss': 2.8198, 'learning_rate': 5.588625051175418e-07, 'epoch': 7.85}
+
 49%|████▉     | 182180/371472 [3:37:24<16:59:36,  3.09it/s]
 49%|████▉     | 182181/371472 [3:37:25<16:17:57,  3.23it/s]
 49%|████▉     | 182182/371472 [3:37:25<16:24:16,  3.21it/s]
 49%|████▉     | 182183/371472 [3:37:25<16:21:21,  3.21it/s]
 49%|████▉     | 182184/371472 [3:37:25<16:17:48,  3.23it/s]
 49%|████▉     | 182185/371472 [3:37:26<16:30:14,  3.19it/s]
 49%|████▉     | 182186/371472 [3:37:26<15:58:39,  3.29it/s]
 49%|████▉     | 182187/371472 [3:37:26<15:23:06,  3.42it/s]
 49%|████▉     | 182188/371472 [3:37:27<15:03:03,  3.49it/s]
 49%|████▉     | 182189/371472 [3:37:27<15:07:58,  3.47it/s]
 49%|████▉     | 182190/371472 [3:37:27<15:18:30,  3.43it/s]
 49%|████▉     | 182191/371472 [3:37:28<15:51:49,  3.31it/s]
 49%|████▉     | 182192/371472 [3:37:28<15:28:24,  3.40it/s]
 49%|████▉     | 182193/371472 [3:37:28<15:24:27,  3.41it/s]
 49%|████▉     | 182194/371472 [3:37:28<15:36:10,  3.37it/s]
 49%|████▉     | 182195/371472 [3:37:29<15:45:11,  3.34it/s]
 49%|████▉     | 182196/371472 [3:37:29<16:14:47,  3.24it/s]
 49%|████▉     | 182197/371472 [3:37:29<16:00:08,  3.29it/s]
 49%|████▉     | 182198/371472 [3:37:30<15:45:32,  3.34it/s]
 49%|████▉     | 182199/371472 [3:37:30<15:55:05,  3.30it/s]
 49%|████▉     | 182200/371472 [3:37:30<15:27:02,  3.40it/s]
                                                            
{'loss': 2.7462, 'learning_rate': 5.588140231420629e-07, 'epoch': 7.85}
+
 49%|████▉     | 182200/371472 [3:37:30<15:27:02,  3.40it/s]
 49%|████▉     | 182201/371472 [3:37:31<16:30:21,  3.19it/s]
 49%|████▉     | 182202/371472 [3:37:31<16:10:15,  3.25it/s]
 49%|████▉     | 182203/371472 [3:37:31<16:31:08,  3.18it/s]
 49%|████▉     | 182204/371472 [3:37:31<16:15:07,  3.23it/s]
 49%|████▉     | 182205/371472 [3:37:32<15:53:03,  3.31it/s]
 49%|████▉     | 182206/371472 [3:37:32<20:29:46,  2.57it/s]
 49%|████▉     | 182207/371472 [3:37:33<18:55:04,  2.78it/s]
 49%|████▉     | 182208/371472 [3:37:33<17:40:05,  2.98it/s]
 49%|████▉     | 182209/371472 [3:37:33<16:38:37,  3.16it/s]
 49%|████▉     | 182210/371472 [3:37:34<16:28:18,  3.19it/s]
 49%|████▉     | 182211/371472 [3:37:34<16:11:52,  3.25it/s]
 49%|████▉     | 182212/371472 [3:37:34<15:52:07,  3.31it/s]
 49%|████▉     | 182213/371472 [3:37:34<16:09:01,  3.26it/s]
 49%|████▉     | 182214/371472 [3:37:35<16:09:18,  3.25it/s]
 49%|████▉     | 182215/371472 [3:37:35<16:15:22,  3.23it/s]
 49%|████▉     | 182216/371472 [3:37:35<16:33:49,  3.17it/s]
 49%|████▉     | 182217/371472 [3:37:36<16:06:06,  3.26it/s]
 49%|████▉     | 182218/371472 [3:37:36<15:49:59,  3.32it/s]
 49%|████▉     | 182219/371472 [3:37:36<15:40:23,  3.35it/s]
 49%|████▉     | 182220/371472 [3:37:36<15:14:27,  3.45it/s]
                                                            
{'loss': 2.9637, 'learning_rate': 5.58765541166584e-07, 'epoch': 7.85}
+
 49%|████▉     | 182220/371472 [3:37:37<15:14:27,  3.45it/s]
 49%|████▉     | 182221/371472 [3:37:37<14:44:43,  3.57it/s]
 49%|████▉     | 182222/371472 [3:37:37<14:58:54,  3.51it/s]
 49%|████▉     | 182223/371472 [3:37:37<16:10:28,  3.25it/s]
 49%|████▉     | 182224/371472 [3:37:38<16:17:42,  3.23it/s]
 49%|████▉     | 182225/371472 [3:37:38<15:53:36,  3.31it/s]
 49%|████▉     | 182226/371472 [3:37:38<15:56:52,  3.30it/s]
 49%|████▉     | 182227/371472 [3:37:39<15:51:27,  3.31it/s]
 49%|████▉     | 182228/371472 [3:37:39<15:39:17,  3.36it/s]
 49%|████▉     | 182229/371472 [3:37:39<15:26:32,  3.40it/s]
 49%|████▉     | 182230/371472 [3:37:39<15:06:49,  3.48it/s]
 49%|████▉     | 182231/371472 [3:37:40<14:49:28,  3.55it/s]
 49%|████▉     | 182232/371472 [3:37:40<15:20:26,  3.43it/s]
 49%|████▉     | 182233/371472 [3:37:40<15:19:33,  3.43it/s]
 49%|████▉     | 182234/371472 [3:37:41<15:12:28,  3.46it/s]
 49%|████▉     | 182235/371472 [3:37:41<15:02:11,  3.50it/s]
 49%|████▉     | 182236/371472 [3:37:41<15:30:04,  3.39it/s]
 49%|████▉     | 182237/371472 [3:37:42<15:20:57,  3.42it/s]
 49%|████▉     | 182238/371472 [3:37:42<15:41:44,  3.35it/s]
 49%|████▉     | 182239/371472 [3:37:42<15:43:08,  3.34it/s]
 49%|████▉     | 182240/371472 [3:37:42<15:31:35,  3.39it/s]
                                                            
{'loss': 3.052, 'learning_rate': 5.587170591911051e-07, 'epoch': 7.85}
+
 49%|████▉     | 182240/371472 [3:37:42<15:31:35,  3.39it/s]
 49%|████▉     | 182241/371472 [3:37:43<15:28:01,  3.40it/s]
 49%|████▉     | 182242/371472 [3:37:43<15:39:29,  3.36it/s]
 49%|████▉     | 182243/371472 [3:37:43<15:41:15,  3.35it/s]
 49%|████▉     | 182244/371472 [3:37:44<15:27:15,  3.40it/s]
 49%|████▉     | 182245/371472 [3:37:44<15:37:28,  3.36it/s]
 49%|████▉     | 182246/371472 [3:37:44<15:38:51,  3.36it/s]
 49%|████▉     | 182247/371472 [3:37:44<15:42:24,  3.35it/s]
 49%|████▉     | 182248/371472 [3:37:45<16:00:50,  3.28it/s]
 49%|████▉     | 182249/371472 [3:37:45<15:25:35,  3.41it/s]
 49%|████▉     | 182250/371472 [3:37:45<15:12:38,  3.46it/s]
 49%|████▉     | 182251/371472 [3:37:46<15:51:15,  3.32it/s]
 49%|████▉     | 182252/371472 [3:37:46<15:47:23,  3.33it/s]
 49%|████▉     | 182253/371472 [3:37:46<15:54:11,  3.31it/s]
 49%|████▉     | 182254/371472 [3:37:47<15:46:39,  3.33it/s]
 49%|████▉     | 182255/371472 [3:37:47<15:35:48,  3.37it/s]
 49%|████▉     | 182256/371472 [3:37:47<15:04:52,  3.49it/s]
 49%|████▉     | 182257/371472 [3:37:47<15:09:02,  3.47it/s]
 49%|████▉     | 182258/371472 [3:37:48<15:26:17,  3.40it/s]
 49%|████▉     | 182259/371472 [3:37:48<15:27:43,  3.40it/s]
 49%|████▉     | 182260/371472 [3:37:48<15:26:11,  3.40it/s]
                                                            
{'loss': 2.9327, 'learning_rate': 5.586685772156263e-07, 'epoch': 7.85}
+
 49%|████▉     | 182260/371472 [3:37:48<15:26:11,  3.40it/s]
 49%|████▉     | 182261/371472 [3:37:49<15:23:02,  3.42it/s]
 49%|████▉     | 182262/371472 [3:37:49<14:58:21,  3.51it/s]
 49%|████▉     | 182263/371472 [3:37:49<14:49:40,  3.54it/s]
 49%|████▉     | 182264/371472 [3:37:50<16:01:27,  3.28it/s]
 49%|████▉     | 182265/371472 [3:37:50<17:14:08,  3.05it/s]
 49%|████▉     | 182266/371472 [3:37:50<16:31:25,  3.18it/s]
 49%|████▉     | 182267/371472 [3:37:50<16:21:51,  3.21it/s]
 49%|████▉     | 182268/371472 [3:37:51<15:48:56,  3.32it/s]
 49%|████▉     | 182269/371472 [3:37:51<16:46:31,  3.13it/s]
 49%|████▉     | 182270/371472 [3:37:51<16:28:30,  3.19it/s]
 49%|████▉     | 182271/371472 [3:37:52<16:21:29,  3.21it/s]
 49%|████▉     | 182272/371472 [3:37:52<16:09:12,  3.25it/s]
 49%|████▉     | 182273/371472 [3:37:52<16:30:12,  3.18it/s]
 49%|████▉     | 182274/371472 [3:37:53<16:06:12,  3.26it/s]
 49%|████▉     | 182275/371472 [3:37:53<16:07:19,  3.26it/s]
 49%|████▉     | 182276/371472 [3:37:53<16:34:43,  3.17it/s]
 49%|████▉     | 182277/371472 [3:37:54<16:02:29,  3.28it/s]
 49%|████▉     | 182278/371472 [3:37:54<15:36:56,  3.37it/s]
 49%|████▉     | 182279/371472 [3:37:54<15:37:37,  3.36it/s]
 49%|████▉     | 182280/371472 [3:37:54<15:29:24,  3.39it/s]
                                                            
{'loss': 2.8609, 'learning_rate': 5.586200952401474e-07, 'epoch': 7.85}
+
 49%|████▉     | 182280/371472 [3:37:54<15:29:24,  3.39it/s]
 49%|████▉     | 182281/371472 [3:37:55<15:49:23,  3.32it/s]
 49%|████▉     | 182282/371472 [3:37:55<15:30:12,  3.39it/s]
 49%|████▉     | 182283/371472 [3:37:55<15:38:25,  3.36it/s]
 49%|████▉     | 182284/371472 [3:37:56<15:32:29,  3.38it/s]
 49%|████▉     | 182285/371472 [3:37:56<15:42:32,  3.35it/s]
 49%|████▉     | 182286/371472 [3:37:56<16:12:30,  3.24it/s]
 49%|████▉     | 182287/371472 [3:37:57<15:58:56,  3.29it/s]
 49%|████▉     | 182288/371472 [3:37:57<15:21:23,  3.42it/s]
 49%|████▉     | 182289/371472 [3:37:57<15:00:14,  3.50it/s]
 49%|████▉     | 182290/371472 [3:37:57<15:07:29,  3.47it/s]
 49%|████▉     | 182291/371472 [3:37:58<15:36:55,  3.37it/s]
 49%|████▉     | 182292/371472 [3:37:58<17:15:55,  3.04it/s]
 49%|████▉     | 182293/371472 [3:37:58<16:18:46,  3.22it/s]
 49%|████▉     | 182294/371472 [3:37:59<16:27:51,  3.19it/s]
 49%|████▉     | 182295/371472 [3:37:59<16:05:45,  3.26it/s]
 49%|████▉     | 182296/371472 [3:37:59<15:52:56,  3.31it/s]
 49%|████▉     | 182297/371472 [3:38:00<16:59:48,  3.09it/s]
 49%|████▉     | 182298/371472 [3:38:00<16:12:57,  3.24it/s]
 49%|████▉     | 182299/371472 [3:38:00<16:03:59,  3.27it/s]
 49%|████▉     | 182300/371472 [3:38:01<15:59:41,  3.29it/s]
                                                            
{'loss': 2.864, 'learning_rate': 5.585716132646684e-07, 'epoch': 7.85}
+
 49%|████▉     | 182300/371472 [3:38:01<15:59:41,  3.29it/s]
 49%|████▉     | 182301/371472 [3:38:01<15:58:13,  3.29it/s]
 49%|████▉     | 182302/371472 [3:38:01<15:39:35,  3.36it/s]
 49%|████▉     | 182303/371472 [3:38:01<16:16:27,  3.23it/s]
 49%|████▉     | 182304/371472 [3:38:02<15:52:34,  3.31it/s]
 49%|████▉     | 182305/371472 [3:38:02<15:25:42,  3.41it/s]
 49%|████▉     | 182306/371472 [3:38:02<16:03:33,  3.27it/s]
 49%|████▉     | 182307/371472 [3:38:03<15:47:30,  3.33it/s]
 49%|████▉     | 182308/371472 [3:38:03<15:51:44,  3.31it/s]
 49%|████▉     | 182309/371472 [3:38:03<15:58:09,  3.29it/s]
 49%|████▉     | 182310/371472 [3:38:04<15:51:07,  3.31it/s]
 49%|█��██▉     | 182311/371472 [3:38:04<15:42:02,  3.35it/s]
 49%|████▉     | 182312/371472 [3:38:04<15:33:06,  3.38it/s]
 49%|████▉     | 182313/371472 [3:38:04<16:14:10,  3.24it/s]
 49%|████▉     | 182314/371472 [3:38:05<16:25:31,  3.20it/s]
 49%|████▉     | 182315/371472 [3:38:05<17:03:45,  3.08it/s]
 49%|████▉     | 182316/371472 [3:38:05<16:19:28,  3.22it/s]
 49%|████▉     | 182317/371472 [3:38:06<15:37:30,  3.36it/s]
 49%|████▉     | 182318/371472 [3:38:06<15:33:57,  3.38it/s]
 49%|████▉     | 182319/371472 [3:38:06<15:33:14,  3.38it/s]
 49%|████▉     | 182320/371472 [3:38:07<15:14:01,  3.45it/s]
                                                            
{'loss': 2.8302, 'learning_rate': 5.585231312891895e-07, 'epoch': 7.85}
+
 49%|████▉     | 182320/371472 [3:38:07<15:14:01,  3.45it/s]
 49%|████▉     | 182321/371472 [3:38:07<15:19:53,  3.43it/s]
 49%|████▉     | 182322/371472 [3:38:07<15:23:34,  3.41it/s]
 49%|████▉     | 182323/371472 [3:38:07<15:24:51,  3.41it/s]
 49%|████▉     | 182324/371472 [3:38:08<15:14:06,  3.45it/s]
 49%|████▉     | 182325/371472 [3:38:08<14:40:44,  3.58it/s]
 49%|████▉     | 182326/371472 [3:38:08<15:01:00,  3.50it/s]
 49%|████▉     | 182327/371472 [3:38:09<16:49:29,  3.12it/s]
 49%|████▉     | 182328/371472 [3:38:09<17:11:43,  3.06it/s]
 49%|████▉     | 182329/371472 [3:38:09<16:25:54,  3.20it/s]
 49%|████▉     | 182330/371472 [3:38:10<16:17:21,  3.23it/s]
 49%|████▉     | 182331/371472 [3:38:10<15:43:24,  3.34it/s]
 49%|████▉     | 182332/371472 [3:38:10<15:27:42,  3.40it/s]
 49%|████▉     | 182333/371472 [3:38:10<15:24:26,  3.41it/s]
 49%|████▉     | 182334/371472 [3:38:11<16:33:30,  3.17it/s]
 49%|████▉     | 182335/371472 [3:38:11<16:07:41,  3.26it/s]
 49%|████▉     | 182336/371472 [3:38:11<15:36:48,  3.36it/s]
 49%|████▉     | 182337/371472 [3:38:12<15:19:55,  3.43it/s]
 49%|████▉     | 182338/371472 [3:38:12<15:05:41,  3.48it/s]
 49%|████▉     | 182339/371472 [3:38:12<15:01:29,  3.50it/s]
 49%|████▉     | 182340/371472 [3:38:13<15:10:03,  3.46it/s]
                                                            
{'loss': 2.9203, 'learning_rate': 5.584746493137108e-07, 'epoch': 7.85}
+
 49%|████▉     | 182340/371472 [3:38:13<15:10:03,  3.46it/s]
 49%|████▉     | 182341/371472 [3:38:13<15:22:49,  3.42it/s]
 49%|████▉     | 182342/371472 [3:38:13<14:47:43,  3.55it/s]
 49%|████▉     | 182343/371472 [3:38:13<14:41:45,  3.57it/s]
 49%|████▉     | 182344/371472 [3:38:14<16:27:13,  3.19it/s]
 49%|████▉     | 182345/371472 [3:38:14<15:42:20,  3.35it/s]
 49%|████▉     | 182346/371472 [3:38:14<15:19:33,  3.43it/s]
 49%|████▉     | 182347/371472 [3:38:15<16:41:42,  3.15it/s]
 49%|████▉     | 182348/371472 [3:38:15<16:24:58,  3.20it/s]
 49%|████▉     | 182349/371472 [3:38:15<15:46:21,  3.33it/s]
 49%|████▉     | 182350/371472 [3:38:15<15:26:01,  3.40it/s]
 49%|████▉     | 182351/371472 [3:38:16<15:55:49,  3.30it/s]
 49%|████▉     | 182352/371472 [3:38:16<15:35:01,  3.37it/s]
 49%|████▉     | 182353/371472 [3:38:16<15:06:21,  3.48it/s]
 49%|████▉     | 182354/371472 [3:38:17<15:00:12,  3.50it/s]
 49%|████▉     | 182355/371472 [3:38:17<14:52:51,  3.53it/s]
 49%|████▉     | 182356/371472 [3:38:17<15:26:54,  3.40it/s]
 49%|████▉     | 182357/371472 [3:38:18<16:07:00,  3.26it/s]
 49%|████▉     | 182358/371472 [3:38:18<15:50:17,  3.32it/s]
 49%|████▉     | 182359/371472 [3:38:18<15:31:19,  3.38it/s]
 49%|████▉     | 182360/371472 [3:38:18<15:20:22,  3.42it/s]
                                                            
{'loss': 2.9416, 'learning_rate': 5.584261673382318e-07, 'epoch': 7.85}
+
 49%|████▉     | 182360/371472 [3:38:18<15:20:22,  3.42it/s]
 49%|████▉     | 182361/371472 [3:38:19<15:05:46,  3.48it/s]
 49%|████▉     | 182362/371472 [3:38:19<15:16:30,  3.44it/s]
 49%|████▉     | 182363/371472 [3:38:19<15:51:34,  3.31it/s]
 49%|████▉     | 182364/371472 [3:38:20<16:23:01,  3.21it/s]
 49%|████▉     | 182365/371472 [3:38:20<15:54:06,  3.30it/s]
 49%|████▉     | 182366/371472 [3:38:20<17:17:45,  3.04it/s]
 49%|████▉     | 182367/371472 [3:38:21<16:44:25,  3.14it/s]
 49%|████▉     | 182368/371472 [3:38:21<15:55:23,  3.30it/s]
 49%|████▉     | 182369/371472 [3:38:21<16:38:14,  3.16it/s]
 49%|████▉     | 182370/371472 [3:38:22<16:25:35,  3.20it/s]
 49%|████▉     | 182371/371472 [3:38:22<15:55:24,  3.30it/s]
 49%|████▉     | 182372/371472 [3:38:22<16:07:43,  3.26it/s]
 49%|████▉     | 182373/371472 [3:38:22<15:52:30,  3.31it/s]
 49%|████▉     | 182374/371472 [3:38:23<16:07:37,  3.26it/s]
 49%|████▉     | 182375/371472 [3:38:23<15:47:25,  3.33it/s]
 49%|████▉     | 182376/371472 [3:38:23<15:42:51,  3.34it/s]
 49%|████▉     | 182377/371472 [3:38:24<15:22:30,  3.42it/s]
 49%|████▉     | 182378/371472 [3:38:24<16:10:33,  3.25it/s]
 49%|████▉     | 182379/371472 [3:38:24<16:14:06,  3.24it/s]
 49%|████▉     | 182380/371472 [3:38:25<16:18:42,  3.22it/s]
                                                            
{'loss': 2.9021, 'learning_rate': 5.583776853627528e-07, 'epoch': 7.86}
+
 49%|████▉     | 182380/371472 [3:38:25<16:18:42,  3.22it/s]
 49%|████▉     | 182381/371472 [3:38:25<15:51:24,  3.31it/s]
 49%|████▉     | 182382/371472 [3:38:25<15:53:28,  3.31it/s]
 49%|████▉     | 182383/371472 [3:38:26<17:05:53,  3.07it/s]
 49%|████▉     | 182384/371472 [3:38:26<16:46:28,  3.13it/s]
 49%|████▉     | 182385/371472 [3:38:26<17:08:44,  3.06it/s]
 49%|████▉     | 182386/371472 [3:38:27<17:54:38,  2.93it/s]
 49%|████▉     | 182387/371472 [3:38:27<17:06:46,  3.07it/s]
 49%|████▉     | 182388/371472 [3:38:27<16:23:49,  3.20it/s]
 49%|████▉     | 182389/371472 [3:38:28<17:08:25,  3.06it/s]
 49%|████▉     | 182390/371472 [3:38:28<16:29:12,  3.19it/s]
 49%|████▉     | 182391/371472 [3:38:28<16:02:26,  3.27it/s]
 49%|████▉     | 182392/371472 [3:38:28<16:35:47,  3.16it/s]
 49%|████▉     | 182393/371472 [3:38:29<15:45:33,  3.33it/s]
 49%|████▉     | 182394/371472 [3:38:29<16:09:49,  3.25it/s]
 49%|████▉     | 182395/371472 [3:38:29<17:27:11,  3.01it/s]
 49%|████▉     | 182396/371472 [3:38:30<16:52:29,  3.11it/s]
 49%|████▉     | 182397/371472 [3:38:30<16:51:51,  3.11it/s]
 49%|████▉     | 182398/371472 [3:38:30<16:30:09,  3.18it/s]
 49%|████▉     | 182399/371472 [3:38:31<17:10:20,  3.06it/s]
 49%|████▉     | 182400/371472 [3:38:31<16:36:06,  3.16it/s]
                                                            
{'loss': 2.8476, 'learning_rate': 5.583292033872739e-07, 'epoch': 7.86}
+
 49%|████▉     | 182400/371472 [3:38:31<16:36:06,  3.16it/s]
 49%|████▉     | 182401/371472 [3:38:31<15:53:41,  3.30it/s]
 49%|████▉     | 182402/371472 [3:38:32<15:38:53,  3.36it/s]
 49%|████▉     | 182403/371472 [3:38:32<15:25:01,  3.41it/s]
 49%|████▉     | 182404/371472 [3:38:32<15:15:10,  3.44it/s]
 49%|████▉     | 182405/371472 [3:38:32<15:01:43,  3.49it/s]
 49%|████▉     | 182406/371472 [3:38:33<14:37:11,  3.59it/s]
 49%|████▉     | 182407/371472 [3:38:33<14:23:57,  3.65it/s]
 49%|████▉     | 182408/371472 [3:38:33<14:26:19,  3.64it/s]
 49%|████▉     | 182409/371472 [3:38:33<14:42:28,  3.57it/s]
 49%|████▉     | 182410/371472 [3:38:34<14:40:49,  3.58it/s]
 49%|████▉     | 182411/371472 [3:38:34<15:12:01,  3.45it/s]
 49%|████▉     | 182412/371472 [3:38:34<15:23:44,  3.41it/s]
 49%|████▉     | 182413/371472 [3:38:35<15:33:44,  3.37it/s]
 49%|████▉     | 182414/371472 [3:38:35<15:10:49,  3.46it/s]
 49%|████▉     | 182415/371472 [3:38:35<15:13:52,  3.45it/s]
 49%|████▉     | 182416/371472 [3:38:36<15:33:19,  3.38it/s]
 49%|████▉     | 182417/371472 [3:38:36<15:18:03,  3.43it/s]
 49%|████▉     | 182418/371472 [3:38:36<15:05:35,  3.48it/s]
 49%|████▉     | 182419/371472 [3:38:36<14:57:25,  3.51it/s]
 49%|████▉     | 182420/371472 [3:38:37<15:05:15,  3.48it/s]
                                                            
{'loss': 2.9182, 'learning_rate': 5.582807214117951e-07, 'epoch': 7.86}
+
 49%|████▉     | 182420/371472 [3:38:37<15:05:15,  3.48it/s]
 49%|████▉     | 182421/371472 [3:38:37<15:25:07,  3.41it/s]
 49%|████▉     | 182422/371472 [3:38:37<15:55:05,  3.30it/s]
 49%|████▉     | 182423/371472 [3:38:38<16:12:43,  3.24it/s]
 49%|████▉     | 182424/371472 [3:38:38<16:35:20,  3.17it/s]
 49%|████▉     | 182425/371472 [3:38:38<16:27:37,  3.19it/s]
 49%|████▉     | 182426/371472 [3:38:39<16:50:38,  3.12it/s]
 49%|████▉     | 182427/371472 [3:38:39<16:15:15,  3.23it/s]
 49%|████▉     | 182428/371472 [3:38:39<15:38:56,  3.36it/s]
 49%|████▉     | 182429/371472 [3:38:39<16:27:11,  3.19it/s]
 49%|████▉     | 182430/371472 [3:38:40<15:46:31,  3.33it/s]
 49%|████▉     | 182431/371472 [3:38:40<16:34:26,  3.17it/s]
 49%|████▉     | 182432/371472 [3:38:41<17:52:32,  2.94it/s]
 49%|████▉     | 182433/371472 [3:38:41<17:38:29,  2.98it/s]
 49%|████▉     | 182434/371472 [3:38:41<17:08:14,  3.06it/s]
 49%|████▉     | 182435/371472 [3:38:41<17:31:52,  3.00it/s]
 49%|████▉     | 182436/371472 [3:38:42<18:14:25,  2.88it/s]
 49%|████▉     | 182437/371472 [3:38:42<17:04:14,  3.08it/s]
 49%|████▉     | 182438/371472 [3:38:42<17:23:57,  3.02it/s]
 49%|████▉     | 182439/371472 [3:38:43<16:37:11,  3.16it/s]
 49%|████▉     | 182440/371472 [3:38:43<17:06:24,  3.07it/s]
                                                            
{'loss': 2.9308, 'learning_rate': 5.582322394363162e-07, 'epoch': 7.86}
+
 49%|████▉     | 182440/371472 [3:38:43<17:06:24,  3.07it/s]
 49%|████▉     | 182441/371472 [3:38:43<16:40:05,  3.15it/s]
 49%|████▉     | 182442/371472 [3:38:44<16:32:02,  3.18it/s]
 49%|████▉     | 182443/371472 [3:38:44<17:01:33,  3.08it/s]
 49%|████▉     | 182444/371472 [3:38:44<16:13:30,  3.24it/s]
 49%|████▉     | 182445/371472 [3:38:45<16:01:15,  3.28it/s]
 49%|████▉     | 182446/371472 [3:38:45<15:41:31,  3.35it/s]
 49%|████▉     | 182447/371472 [3:38:45<16:11:30,  3.24it/s]
 49%|████▉     | 182448/371472 [3:38:46<15:41:56,  3.34it/s]
 49%|████▉     | 182449/371472 [3:38:46<16:04:06,  3.27it/s]
 49%|████▉     | 182450/371472 [3:38:46<16:48:12,  3.12it/s]
 49%|████▉     | 182451/371472 [3:38:46<16:12:16,  3.24it/s]
 49%|████▉     | 182452/371472 [3:38:47<15:53:03,  3.31it/s]
 49%|████▉     | 182453/371472 [3:38:47<16:09:11,  3.25it/s]
 49%|████▉     | 182454/371472 [3:38:47<15:39:52,  3.35it/s]
 49%|████▉     | 182455/371472 [3:38:48<15:40:47,  3.35it/s]
 49%|████▉     | 182456/371472 [3:38:48<15:50:31,  3.31it/s]
 49%|████▉     | 182457/371472 [3:38:48<15:13:04,  3.45it/s]
 49%|████▉     | 182458/371472 [3:38:49<15:33:22,  3.38it/s]
 49%|████▉     | 182459/371472 [3:38:49<15:19:05,  3.43it/s]
 49%|████▉     | 182460/371472 [3:38:49<15:07:23,  3.47it/s]
                                                            
{'loss': 2.8982, 'learning_rate': 5.581837574608372e-07, 'epoch': 7.86}
+
 49%|████▉     | 182460/371472 [3:38:49<15:07:23,  3.47it/s]
 49%|████▉     | 182461/371472 [3:38:49<15:24:37,  3.41it/s]
 49%|████▉     | 182462/371472 [3:38:50<15:28:04,  3.39it/s]
 49%|████▉     | 182463/371472 [3:38:50<15:22:46,  3.41it/s]
 49%|████▉     | 182464/371472 [3:38:50<15:54:44,  3.30it/s]
 49%|████▉     | 182465/371472 [3:38:51<16:35:03,  3.17it/s]
 49%|████▉     | 182466/371472 [3:38:51<15:49:07,  3.32it/s]
 49%|████▉     | 182467/371472 [3:38:51<15:09:00,  3.47it/s]
 49%|████▉     | 182468/371472 [3:38:51<14:59:14,  3.50it/s]
 49%|████▉     | 182469/371472 [3:38:52<14:54:41,  3.52it/s]
 49%|████▉     | 182470/371472 [3:38:52<14:40:16,  3.58it/s]
 49%|████▉     | 182471/371472 [3:38:52<15:09:25,  3.46it/s]
 49%|████▉     | 182472/371472 [3:38:53<15:17:54,  3.43it/s]
 49%|████▉     | 182473/371472 [3:38:53<15:17:19,  3.43it/s]
 49%|████▉     | 182474/371472 [3:38:53<15:20:24,  3.42it/s]
 49%|████▉     | 182475/371472 [3:38:54<15:00:20,  3.50it/s]
 49%|████▉     | 182476/371472 [3:38:54<14:52:29,  3.53it/s]
 49%|████▉     | 182477/371472 [3:38:54<14:55:06,  3.52it/s]
 49%|████▉     | 182478/371472 [3:38:54<14:59:10,  3.50it/s]
 49%|████▉     | 182479/371472 [3:38:55<15:11:18,  3.46it/s]
 49%|████▉     | 182480/371472 [3:38:55<15:33:53,  3.37it/s]
                                                            
{'loss': 3.0389, 'learning_rate': 5.581352754853585e-07, 'epoch': 7.86}
+
 49%|████▉     | 182480/371472 [3:38:55<15:33:53,  3.37it/s]
 49%|████▉     | 182481/371472 [3:38:55<16:03:24,  3.27it/s]
 49%|████▉     | 182482/371472 [3:38:56<15:31:52,  3.38it/s]
 49%|████▉     | 182483/371472 [3:38:56<15:29:55,  3.39it/s]
 49%|████▉     | 182484/371472 [3:38:56<15:37:31,  3.36it/s]
 49%|████▉     | 182485/371472 [3:38:56<16:06:11,  3.26it/s]
 49%|████▉     | 182486/371472 [3:38:57<16:09:42,  3.25it/s]
 49%|████▉     | 182487/371472 [3:38:57<15:49:57,  3.32it/s]
 49%|████▉     | 182488/371472 [3:38:57<15:24:34,  3.41it/s]
 49%|████▉     | 182489/371472 [3:38:58<16:35:34,  3.16it/s]
 49%|████▉     | 182490/371472 [3:38:58<16:56:07,  3.10it/s]
 49%|████▉     | 182491/371472 [3:38:58<16:08:54,  3.25it/s]
 49%|████▉     | 182492/371472 [3:38:59<15:40:34,  3.35it/s]
 49%|████▉     | 182493/371472 [3:38:59<15:29:01,  3.39it/s]
 49%|████▉     | 182494/371472 [3:38:59<16:17:55,  3.22it/s]
 49%|████▉     | 182495/371472 [3:39:00<16:38:02,  3.16it/s]
 49%|████▉     | 182496/371472 [3:39:00<16:08:22,  3.25it/s]
 49%|████▉     | 182497/371472 [3:39:00<16:00:06,  3.28it/s]
 49%|████▉     | 182498/371472 [3:39:00<16:14:33,  3.23it/s]
 49%|████▉     | 182499/371472 [3:39:01<16:19:41,  3.21it/s]
 49%|████▉     | 182500/371472 [3:39:01<16:12:02,  3.24it/s]
                                                            
{'loss': 2.69, 'learning_rate': 5.580867935098797e-07, 'epoch': 7.86}
+
 49%|████▉     | 182500/371472 [3:39:01<16:12:02,  3.24it/s]
 49%|████▉     | 182501/371472 [3:39:01<16:16:25,  3.23it/s]
 49%|████▉     | 182502/371472 [3:39:02<16:07:59,  3.25it/s]
 49%|████▉     | 182503/371472 [3:39:02<17:36:44,  2.98it/s]
 49%|████▉     | 182504/371472 [3:39:02<16:41:44,  3.14it/s]
 49%|████▉     | 182505/371472 [3:39:03<16:36:22,  3.16it/s]
 49%|████▉     | 182506/371472 [3:39:03<16:13:43,  3.23it/s]
 49%|████▉     | 182507/371472 [3:39:03<15:55:48,  3.30it/s]
 49%|████▉     | 182508/371472 [3:39:04<15:23:26,  3.41it/s]
 49%|████▉     | 182509/371472 [3:39:04<15:03:25,  3.49it/s]
 49%|████▉     | 182510/371472 [3:39:04<14:34:34,  3.60it/s]
 49%|████▉     | 182511/371472 [3:39:04<14:26:01,  3.64it/s]
 49%|████▉     | 182512/371472 [3:39:05<14:34:04,  3.60it/s]
 49%|████▉     | 182513/371472 [3:39:05<14:30:07,  3.62it/s]
 49%|████▉     | 182514/371472 [3:39:05<15:18:39,  3.43it/s]
 49%|████▉     | 182515/371472 [3:39:06<14:48:39,  3.54it/s]
 49%|████▉     | 182516/371472 [3:39:06<14:48:59,  3.54it/s]
 49%|████▉     | 182517/371472 [3:39:06<15:52:25,  3.31it/s]
 49%|████▉     | 182518/371472 [3:39:06<15:39:04,  3.35it/s]
 49%|████▉     | 182519/371472 [3:39:07<15:29:17,  3.39it/s]
 49%|████▉     | 182520/371472 [3:39:07<15:32:24,  3.38it/s]
                                                            
{'loss': 2.9931, 'learning_rate': 5.580383115344007e-07, 'epoch': 7.86}
+
 49%|████▉     | 182520/371472 [3:39:07<15:32:24,  3.38it/s]
 49%|████▉     | 182521/371472 [3:39:07<15:49:27,  3.32it/s]
 49%|████▉     | 182522/371472 [3:39:08<15:59:46,  3.28it/s]
 49%|████▉     | 182523/371472 [3:39:08<16:52:05,  3.11it/s]
 49%|████▉     | 182524/371472 [3:39:08<16:11:58,  3.24it/s]
 49%|████▉     | 182525/371472 [3:39:09<16:12:56,  3.24it/s]
 49%|████▉     | 182526/371472 [3:39:09<16:01:56,  3.27it/s]
 49%|████▉     | 182527/371472 [3:39:09<15:42:20,  3.34it/s]
 49%|████▉     | 182528/371472 [3:39:09<15:15:48,  3.44it/s]
 49%|████▉     | 182529/371472 [3:39:10<15:13:37,  3.45it/s]
 49%|████▉     | 182530/371472 [3:39:10<15:08:06,  3.47it/s]
 49%|████▉     | 182531/371472 [3:39:10<15:02:04,  3.49it/s]
 49%|████▉     | 182532/371472 [3:39:11<15:18:29,  3.43it/s]
 49%|████▉     | 182533/371472 [3:39:11<15:22:09,  3.41it/s]
 49%|████▉     | 182534/371472 [3:39:11<15:19:11,  3.43it/s]
 49%|████▉     | 182535/371472 [3:39:11<15:06:08,  3.48it/s]
 49%|████▉     | 182536/371472 [3:39:12<15:37:23,  3.36it/s]
 49%|████▉     | 182537/371472 [3:39:12<15:57:24,  3.29it/s]
 49%|████▉     | 182538/371472 [3:39:13<17:24:04,  3.02it/s]
 49%|████▉     | 182539/371472 [3:39:13<18:01:01,  2.91it/s]
 49%|████▉     | 182540/371472 [3:39:13<18:08:49,  2.89it/s]
                                                            
{'loss': 2.9962, 'learning_rate': 5.579898295589217e-07, 'epoch': 7.86}
+
 49%|████▉     | 182540/371472 [3:39:13<18:08:49,  2.89it/s]
 49%|████▉     | 182541/371472 [3:39:14<17:31:52,  2.99it/s]
 49%|████▉     | 182542/371472 [3:39:14<17:31:58,  2.99it/s]
 49%|████▉     | 182543/371472 [3:39:14<16:56:06,  3.10it/s]
 49%|████▉     | 182544/371472 [3:39:14<16:09:46,  3.25it/s]
 49%|████▉     | 182545/371472 [3:39:15<15:35:32,  3.37it/s]
 49%|████▉     | 182546/371472 [3:39:15<15:24:35,  3.41it/s]
 49%|████▉     | 182547/371472 [3:39:15<15:12:24,  3.45it/s]
 49%|████▉     | 182548/371472 [3:39:16<15:11:31,  3.45it/s]
 49%|████▉     | 182549/371472 [3:39:16<15:18:52,  3.43it/s]
 49%|████▉     | 182550/371472 [3:39:16<15:45:33,  3.33it/s]
 49%|████▉     | 182551/371472 [3:39:16<15:35:16,  3.37it/s]
 49%|████▉     | 182552/371472 [3:39:17<16:25:00,  3.20it/s]
 49%|████▉     | 182553/371472 [3:39:17<16:43:21,  3.14it/s]
 49%|████▉     | 182554/371472 [3:39:17<16:37:33,  3.16it/s]
 49%|████▉     | 182555/371472 [3:39:18<15:52:00,  3.31it/s]
 49%|████▉     | 182556/371472 [3:39:18<15:45:59,  3.33it/s]
 49%|████▉     | 182557/371472 [3:39:18<15:55:34,  3.29it/s]
 49%|████▉     | 182558/371472 [3:39:19<15:58:59,  3.28it/s]
 49%|████▉     | 182559/371472 [3:39:19<16:22:39,  3.20it/s]
 49%|████▉     | 182560/371472 [3:39:19<17:46:31,  2.95it/s]
                                                            
{'loss': 2.9083, 'learning_rate': 5.579413475834428e-07, 'epoch': 7.86}
+
 49%|████▉     | 182560/371472 [3:39:19<17:46:31,  2.95it/s]
 49%|████▉     | 182561/371472 [3:39:20<16:44:00,  3.14it/s]
 49%|████▉     | 182562/371472 [3:39:20<16:17:20,  3.22it/s]
 49%|████▉     | 182563/371472 [3:39:20<16:43:10,  3.14it/s]
 49%|████▉     | 182564/371472 [3:39:21<16:15:47,  3.23it/s]
 49%|████▉     | 182565/371472 [3:39:21<16:23:24,  3.20it/s]
 49%|████▉     | 182566/371472 [3:39:21<15:47:22,  3.32it/s]
 49%|████▉     | 182567/371472 [3:39:21<15:27:37,  3.39it/s]
 49%|████▉     | 182568/371472 [3:39:22<15:13:36,  3.45it/s]
 49%|████▉     | 182569/371472 [3:39:22<16:46:02,  3.13it/s]
 49%|████▉     | 182570/371472 [3:39:22<16:15:07,  3.23it/s]
 49%|████▉     | 182571/371472 [3:39:23<16:11:24,  3.24it/s]
 49%|████▉     | 182572/371472 [3:39:23<15:44:32,  3.33it/s]
 49%|████▉     | 182573/371472 [3:39:23<15:23:34,  3.41it/s]
 49%|████▉     | 182574/371472 [3:39:24<15:10:27,  3.46it/s]
 49%|████▉     | 182575/371472 [3:39:24<14:56:14,  3.51it/s]
 49%|████▉     | 182576/371472 [3:39:24<16:14:55,  3.23it/s]
 49%|████▉     | 182577/371472 [3:39:25<16:38:21,  3.15it/s]
 49%|████▉     | 182578/371472 [3:39:25<16:10:08,  3.25it/s]
 49%|████▉     | 182579/371472 [3:39:25<18:19:09,  2.86it/s]
 49%|████▉     | 182580/371472 [3:39:26<18:16:56,  2.87it/s]
                                                            
{'loss': 2.9395, 'learning_rate': 5.578928656079639e-07, 'epoch': 7.86}
+
 49%|████▉     | 182580/371472 [3:39:26<18:16:56,  2.87it/s]
 49%|████▉     | 182581/371472 [3:39:26<17:17:14,  3.04it/s]
 49%|████▉     | 182582/371472 [3:39:26<16:59:50,  3.09it/s]
 49%|████▉     | 182583/371472 [3:39:26<16:30:50,  3.18it/s]
 49%|████▉     | 182584/371472 [3:39:27<16:37:16,  3.16it/s]
 49%|████▉     | 182585/371472 [3:39:27<16:13:57,  3.23it/s]
 49%|████▉     | 182586/371472 [3:39:27<16:25:21,  3.19it/s]
 49%|████▉     | 182587/371472 [3:39:28<16:02:11,  3.27it/s]
 49%|████▉     | 182588/371472 [3:39:28<15:44:26,  3.33it/s]
 49%|████▉     | 182589/371472 [3:39:28<16:38:27,  3.15it/s]
 49%|████▉     | 182590/371472 [3:39:29<16:04:19,  3.26it/s]
 49%|████▉     | 182591/371472 [3:39:29<15:50:43,  3.31it/s]
 49%|████▉     | 182592/371472 [3:39:29<15:54:44,  3.30it/s]
 49%|████▉     | 182593/371472 [3:39:30<15:57:19,  3.29it/s]
 49%|████▉     | 182594/371472 [3:39:30<15:40:43,  3.35it/s]
 49%|████▉     | 182595/371472 [3:39:30<15:29:50,  3.39it/s]
 49%|████▉     | 182596/371472 [3:39:30<15:01:41,  3.49it/s]
 49%|████▉     | 182597/371472 [3:39:31<15:04:14,  3.48it/s]
 49%|████▉     | 182598/371472 [3:39:31<14:46:31,  3.55it/s]
 49%|████▉     | 182599/371472 [3:39:31<14:57:07,  3.51it/s]
 49%|████▉     | 182600/371472 [3:39:32<15:03:11,  3.49it/s]
                                                            
{'loss': 2.8333, 'learning_rate': 5.578443836324849e-07, 'epoch': 7.86}
+
 49%|████▉     | 182600/371472 [3:39:32<15:03:11,  3.49it/s]
 49%|████▉     | 182601/371472 [3:39:32<15:14:36,  3.44it/s]
 49%|████▉     | 182602/371472 [3:39:32<14:58:15,  3.50it/s]
 49%|████▉     | 182603/371472 [3:39:32<14:54:16,  3.52it/s]
 49%|████▉     | 182604/371472 [3:39:33<14:42:54,  3.57it/s]
 49%|████▉     | 182605/371472 [3:39:33<15:01:43,  3.49it/s]
 49%|████▉     | 182606/371472 [3:39:33<14:57:20,  3.51it/s]
 49%|████▉     | 182607/371472 [3:39:34<15:06:19,  3.47it/s]
 49%|████▉     | 182608/371472 [3:39:34<15:15:52,  3.44it/s]
 49%|████▉     | 182609/371472 [3:39:34<15:22:41,  3.41it/s]
 49%|████▉     | 182610/371472 [3:39:34<15:10:59,  3.46it/s]
 49%|████▉     | 182611/371472 [3:39:35<15:30:53,  3.38it/s]
 49%|████▉     | 182612/371472 [3:39:35<15:39:49,  3.35it/s]
 49%|████▉     | 182613/371472 [3:39:35<15:34:47,  3.37it/s]
 49%|████▉     | 182614/371472 [3:39:36<15:39:44,  3.35it/s]
 49%|████▉     | 182615/371472 [3:39:36<15:15:21,  3.44it/s]
 49%|████▉     | 182616/371472 [3:39:36<14:47:44,  3.55it/s]
 49%|████▉     | 182617/371472 [3:39:37<16:48:38,  3.12it/s]
 49%|████▉     | 182618/371472 [3:39:37<16:07:01,  3.25it/s]
 49%|████▉     | 182619/371472 [3:39:37<15:27:55,  3.39it/s]
 49%|████▉     | 182620/371472 [3:39:37<15:51:03,  3.31it/s]
                                                            
{'loss': 2.9175, 'learning_rate': 5.577959016570061e-07, 'epoch': 7.87}
+
 49%|████▉     | 182620/371472 [3:39:37<15:51:03,  3.31it/s]
 49%|████▉     | 182621/371472 [3:39:38<15:33:56,  3.37it/s]
 49%|████▉     | 182622/371472 [3:39:38<15:31:57,  3.38it/s]
 49%|████▉     | 182623/371472 [3:39:38<15:39:01,  3.35it/s]
 49%|████▉     | 182624/371472 [3:39:39<15:29:31,  3.39it/s]
 49%|████▉     | 182625/371472 [3:39:39<17:13:21,  3.05it/s]
 49%|████▉     | 182626/371472 [3:39:39<17:11:11,  3.05it/s]
 49%|████▉     | 182627/371472 [3:39:40<16:14:07,  3.23it/s]
 49%|████▉     | 182628/371472 [3:39:40<16:07:06,  3.25it/s]
 49%|████▉     | 182629/371472 [3:39:40<16:59:42,  3.09it/s]
 49%|████▉     | 182630/371472 [3:39:41<16:08:31,  3.25it/s]
 49%|████▉     | 182631/371472 [3:39:41<16:00:55,  3.28it/s]
 49%|████▉     | 182632/371472 [3:39:41<15:54:37,  3.30it/s]
 49%|████▉     | 182633/371472 [3:39:41<16:00:17,  3.28it/s]
 49%|████▉     | 182634/371472 [3:39:42<15:49:03,  3.32it/s]
 49%|████▉     | 182635/371472 [3:39:42<15:27:35,  3.39it/s]
 49%|████▉     | 182636/371472 [3:39:42<15:39:49,  3.35it/s]
 49%|████▉     | 182637/371472 [3:39:43<15:18:54,  3.42it/s]
 49%|████▉     | 182638/371472 [3:39:43<15:43:08,  3.34it/s]
 49%|████▉     | 182639/371472 [3:39:43<15:35:28,  3.36it/s]
 49%|████▉     | 182640/371472 [3:39:44<16:03:29,  3.27it/s]
                                                            
{'loss': 3.083, 'learning_rate': 5.577474196815273e-07, 'epoch': 7.87}
+
 49%|████▉     | 182640/371472 [3:39:44<16:03:29,  3.27it/s]
 49%|████▉     | 182641/371472 [3:39:44<16:21:28,  3.21it/s]
 49%|████▉     | 182642/371472 [3:39:44<16:15:51,  3.23it/s]
 49%|████▉     | 182643/371472 [3:39:44<15:47:51,  3.32it/s]
 49%|████▉     | 182644/371472 [3:39:45<15:30:29,  3.38it/s]
 49%|████▉     | 182645/371472 [3:39:45<15:38:25,  3.35it/s]
 49%|████▉     | 182646/371472 [3:39:45<15:42:18,  3.34it/s]
 49%|████▉     | 182647/371472 [3:39:46<15:20:17,  3.42it/s]
 49%|████▉     | 182648/371472 [3:39:46<15:48:46,  3.32it/s]
 49%|████▉     | 182649/371472 [3:39:46<15:25:41,  3.40it/s]
 49%|████▉     | 182650/371472 [3:39:46<15:32:53,  3.37it/s]
 49%|████▉     | 182651/371472 [3:39:47<15:43:16,  3.34it/s]
 49%|████▉     | 182652/371472 [3:39:47<16:43:58,  3.13it/s]
 49%|████▉     | 182653/371472 [3:39:48<17:16:30,  3.04it/s]
 49%|████▉     | 182654/371472 [3:39:48<16:40:27,  3.15it/s]
 49%|████▉     | 182655/371472 [3:39:48<16:07:45,  3.25it/s]
 49%|████▉     | 182656/371472 [3:39:48<16:00:57,  3.27it/s]
 49%|████▉     | 182657/371472 [3:39:49<15:37:20,  3.36it/s]
 49%|████▉     | 182658/371472 [3:39:49<16:28:54,  3.18it/s]
 49%|████▉     | 182659/371472 [3:39:49<16:04:27,  3.26it/s]
 49%|████▉     | 182660/371472 [3:39:50<15:29:00,  3.39it/s]
                                                            
{'loss': 2.9667, 'learning_rate': 5.576989377060484e-07, 'epoch': 7.87}
+
 49%|████▉     | 182660/371472 [3:39:50<15:29:00,  3.39it/s]
 49%|████▉     | 182661/371472 [3:39:50<16:01:58,  3.27it/s]
 49%|████▉     | 182662/371472 [3:39:50<16:05:10,  3.26it/s]
 49%|████▉     | 182663/371472 [3:39:51<16:13:40,  3.23it/s]
 49%|████▉     | 182664/371472 [3:39:51<16:14:18,  3.23it/s]
 49%|████▉     | 182665/371472 [3:39:51<16:09:41,  3.25it/s]
 49%|████▉     | 182666/371472 [3:39:51<15:56:42,  3.29it/s]
 49%|████▉     | 182667/371472 [3:39:52<15:45:34,  3.33it/s]
 49%|████▉     | 182668/371472 [3:39:52<15:28:29,  3.39it/s]
 49%|████▉     | 182669/371472 [3:39:52<15:23:38,  3.41it/s]
 49%|████▉     | 182670/371472 [3:39:53<15:19:54,  3.42it/s]
 49%|████▉     | 182671/371472 [3:39:53<15:14:51,  3.44it/s]
 49%|████▉     | 182672/371472 [3:39:53<15:13:36,  3.44it/s]
 49%|████▉     | 182673/371472 [3:39:53<15:33:42,  3.37it/s]
 49%|████▉     | 182674/371472 [3:39:54<15:51:27,  3.31it/s]
 49%|████▉     | 182675/371472 [3:39:54<15:38:18,  3.35it/s]
 49%|████▉     | 182676/371472 [3:39:54<15:40:30,  3.35it/s]
 49%|████▉     | 182677/371472 [3:39:55<16:41:30,  3.14it/s]
 49%|████▉     | 182678/371472 [3:39:55<17:49:51,  2.94it/s]
 49%|████▉     | 182679/371472 [3:39:55<17:23:52,  3.01it/s]
 49%|████▉     | 182680/371472 [3:39:56<17:12:25,  3.05it/s]
                                                            
{'loss': 2.9499, 'learning_rate': 5.576504557305694e-07, 'epoch': 7.87}
+
 49%|████▉     | 182680/371472 [3:39:56<17:12:25,  3.05it/s]
 49%|████▉     | 182681/371472 [3:39:56<16:33:43,  3.17it/s]
 49%|████▉     | 182682/371472 [3:39:56<16:03:12,  3.27it/s]
 49%|████▉     | 182683/371472 [3:39:57<15:32:15,  3.38it/s]
 49%|████▉     | 182684/371472 [3:39:57<15:41:57,  3.34it/s]
 49%|████▉     | 182685/371472 [3:39:57<15:30:52,  3.38it/s]
 49%|████▉     | 182686/371472 [3:39:58<15:44:03,  3.33it/s]
 49%|████▉     | 182687/371472 [3:39:58<16:15:06,  3.23it/s]
 49%|████▉     | 182688/371472 [3:39:58<16:02:59,  3.27it/s]
 49%|████▉     | 182689/371472 [3:39:58<15:44:42,  3.33it/s]
 49%|████▉     | 182690/371472 [3:39:59<15:55:26,  3.29it/s]
 49%|████▉     | 182691/371472 [3:39:59<16:10:29,  3.24it/s]
 49%|████▉     | 182692/371472 [3:39:59<15:58:58,  3.28it/s]
 49%|████▉     | 182693/371472 [3:40:00<15:40:34,  3.35it/s]
 49%|████▉     | 182694/371472 [3:40:00<16:03:58,  3.26it/s]
 49%|████▉     | 182695/371472 [3:40:00<16:00:53,  3.27it/s]
 49%|████▉     | 182696/371472 [3:40:01<15:56:22,  3.29it/s]
 49%|████▉     | 182697/371472 [3:40:01<15:38:49,  3.35it/s]
 49%|████▉     | 182698/371472 [3:40:01<15:37:24,  3.36it/s]
 49%|████▉     | 182699/371472 [3:40:01<15:08:35,  3.46it/s]
 49%|████▉     | 182700/371472 [3:40:02<14:46:13,  3.55it/s]
                                                            
{'loss': 2.7947, 'learning_rate': 5.576019737550905e-07, 'epoch': 7.87}
+
 49%|████▉     | 182700/371472 [3:40:02<14:46:13,  3.55it/s]
 49%|████▉     | 182701/371472 [3:40:02<15:25:30,  3.40it/s]
 49%|████▉     | 182702/371472 [3:40:02<15:11:52,  3.45it/s]
 49%|████▉     | 182703/371472 [3:40:03<14:44:31,  3.56it/s]
 49%|████▉     | 182704/371472 [3:40:03<14:43:47,  3.56it/s]
 49%|████▉     | 182705/371472 [3:40:03<14:55:23,  3.51it/s]
 49%|████▉     | 182706/371472 [3:40:03<15:28:15,  3.39it/s]
 49%|████▉     | 182707/371472 [3:40:04<15:10:42,  3.45it/s]
 49%|████▉     | 182708/371472 [3:40:04<15:22:04,  3.41it/s]
 49%|████▉     | 182709/371472 [3:40:04<15:50:45,  3.31it/s]
 49%|████▉     | 182710/371472 [3:40:05<15:29:45,  3.38it/s]
 49%|████▉     | 182711/371472 [3:40:05<15:23:07,  3.41it/s]
 49%|████▉     | 182712/371472 [3:40:05<15:15:55,  3.43it/s]
 49%|████▉     | 182713/371472 [3:40:05<15:02:20,  3.49it/s]
 49%|████▉     | 182714/371472 [3:40:06<14:55:33,  3.51it/s]
 49%|████▉     | 182715/371472 [3:40:06<14:57:22,  3.51it/s]
 49%|████▉     | 182716/371472 [3:40:06<14:59:58,  3.50it/s]
 49%|████▉     | 182717/371472 [3:40:07<15:49:39,  3.31it/s]
 49%|████▉     | 182718/371472 [3:40:07<16:52:02,  3.11it/s]
 49%|████▉     | 182719/371472 [3:40:07<16:13:14,  3.23it/s]
 49%|████▉     | 182720/371472 [3:40:08<16:08:28,  3.25it/s]
                                                            
{'loss': 3.0048, 'learning_rate': 5.575534917796118e-07, 'epoch': 7.87}
+
 49%|████▉     | 182720/371472 [3:40:08<16:08:28,  3.25it/s]
 49%|████▉     | 182721/371472 [3:40:08<16:55:37,  3.10it/s]
 49%|████▉     | 182722/371472 [3:40:08<16:19:28,  3.21it/s]
 49%|████▉     | 182723/371472 [3:40:09<15:43:53,  3.33it/s]
 49%|████▉     | 182724/371472 [3:40:09<15:26:59,  3.39it/s]
 49%|████▉     | 182725/371472 [3:40:09<15:22:57,  3.41it/s]
 49%|████▉     | 182726/371472 [3:40:09<15:33:05,  3.37it/s]
 49%|████▉     | 182727/371472 [3:40:10<15:20:57,  3.42it/s]
 49%|████▉     | 182728/371472 [3:40:10<15:41:47,  3.34it/s]
 49%|████▉     | 182729/371472 [3:40:10<15:18:42,  3.42it/s]
 49%|████▉     | 182730/371472 [3:40:11<15:38:10,  3.35it/s]
 49%|████▉     | 182731/371472 [3:40:11<15:37:43,  3.35it/s]
 49%|████▉     | 182732/371472 [3:40:11<15:36:22,  3.36it/s]
 49%|████▉     | 182733/371472 [3:40:12<15:44:47,  3.33it/s]
 49%|████▉     | 182734/371472 [3:40:12<16:40:12,  3.14it/s]
 49%|████▉     | 182735/371472 [3:40:12<16:02:29,  3.27it/s]
 49%|████▉     | 182736/371472 [3:40:12<16:33:12,  3.17it/s]
 49%|████▉     | 182737/371472 [3:40:13<16:11:29,  3.24it/s]
 49%|████▉     | 182738/371472 [3:40:13<15:54:13,  3.30it/s]
 49%|████▉     | 182739/371472 [3:40:13<15:47:47,  3.32it/s]
 49%|████▉     | 182740/371472 [3:40:14<15:45:30,  3.33it/s]
                                                            
{'loss': 2.8448, 'learning_rate': 5.575050098041328e-07, 'epoch': 7.87}
+
 49%|████▉     | 182740/371472 [3:40:14<15:45:30,  3.33it/s]
 49%|████▉     | 182741/371472 [3:40:14<15:48:37,  3.32it/s]
 49%|████▉     | 182742/371472 [3:40:14<15:59:44,  3.28it/s]
 49%|████▉     | 182743/371472 [3:40:15<15:52:41,  3.30it/s]
 49%|████▉     | 182744/371472 [3:40:15<16:14:33,  3.23it/s]
 49%|████▉     | 182745/371472 [3:40:15<16:32:16,  3.17it/s]
 49%|████▉     | 182746/371472 [3:40:16<16:11:18,  3.24it/s]
 49%|████▉     | 182747/371472 [3:40:16<16:22:31,  3.20it/s]
 49%|████▉     | 182748/371472 [3:40:16<16:08:41,  3.25it/s]
 49%|████▉     | 182749/371472 [3:40:16<16:16:07,  3.22it/s]
 49%|████▉     | 182750/371472 [3:40:17<15:42:31,  3.34it/s]
 49%|████▉     | 182751/371472 [3:40:17<15:40:41,  3.34it/s]
 49%|█��██▉     | 182752/371472 [3:40:17<15:16:18,  3.43it/s]
 49%|████▉     | 182753/371472 [3:40:18<15:37:46,  3.35it/s]
 49%|████▉     | 182754/371472 [3:40:18<15:31:52,  3.38it/s]
 49%|████▉     | 182755/371472 [3:40:18<15:07:48,  3.46it/s]
 49%|████▉     | 182756/371472 [3:40:19<15:55:14,  3.29it/s]
 49%|████▉     | 182757/371472 [3:40:19<16:02:00,  3.27it/s]
 49%|████▉     | 182758/371472 [3:40:19<15:49:38,  3.31it/s]
 49%|████▉     | 182759/371472 [3:40:19<15:32:29,  3.37it/s]
 49%|████▉     | 182760/371472 [3:40:20<15:49:03,  3.31it/s]
                                                            
{'loss': 2.9344, 'learning_rate': 5.574565278286538e-07, 'epoch': 7.87}
+
 49%|████▉     | 182760/371472 [3:40:20<15:49:03,  3.31it/s]
 49%|████▉     | 182761/371472 [3:40:20<17:19:01,  3.03it/s]
 49%|████▉     | 182762/371472 [3:40:20<16:42:13,  3.14it/s]
 49%|████▉     | 182763/371472 [3:40:21<16:20:08,  3.21it/s]
 49%|████▉     | 182764/371472 [3:40:21<15:42:17,  3.34it/s]
 49%|████▉     | 182765/371472 [3:40:21<16:52:19,  3.11it/s]
 49%|████▉     | 182766/371472 [3:40:22<17:11:37,  3.05it/s]
 49%|████▉     | 182767/371472 [3:40:22<16:49:27,  3.12it/s]
 49%|████▉     | 182768/371472 [3:40:22<16:44:54,  3.13it/s]
 49%|████▉     | 182769/371472 [3:40:23<16:30:04,  3.18it/s]
 49%|████▉     | 182770/371472 [3:40:23<16:24:40,  3.19it/s]
 49%|████▉     | 182771/371472 [3:40:23<16:22:30,  3.20it/s]
 49%|████▉     | 182772/371472 [3:40:24<15:49:43,  3.31it/s]
 49%|████▉     | 182773/371472 [3:40:24<15:36:28,  3.36it/s]
 49%|████▉     | 182774/371472 [3:40:24<15:13:27,  3.44it/s]
 49%|████▉     | 182775/371472 [3:40:24<15:44:55,  3.33it/s]
 49%|████▉     | 182776/371472 [3:40:25<15:51:21,  3.31it/s]
 49%|████▉     | 182777/371472 [3:40:25<15:52:27,  3.30it/s]
 49%|████▉     | 182778/371472 [3:40:25<15:34:56,  3.36it/s]
 49%|████▉     | 182779/371472 [3:40:26<15:24:13,  3.40it/s]
 49%|████▉     | 182780/371472 [3:40:26<15:41:10,  3.34it/s]
                                                            
{'loss': 2.8774, 'learning_rate': 5.57408045853175e-07, 'epoch': 7.87}
+
 49%|████▉     | 182780/371472 [3:40:26<15:41:10,  3.34it/s]
 49%|████▉     | 182781/371472 [3:40:26<15:39:30,  3.35it/s]
 49%|████▉     | 182782/371472 [3:40:26<15:30:34,  3.38it/s]
 49%|████▉     | 182783/371472 [3:40:27<16:00:51,  3.27it/s]
 49%|████▉     | 182784/371472 [3:40:27<15:56:12,  3.29it/s]
 49%|████▉     | 182785/371472 [3:40:27<15:50:34,  3.31it/s]
 49%|████▉     | 182786/371472 [3:40:28<15:38:55,  3.35it/s]
 49%|████▉     | 182787/371472 [3:40:28<16:28:58,  3.18it/s]
 49%|████▉     | 182788/371472 [3:40:28<16:12:33,  3.23it/s]
 49%|████▉     | 182789/371472 [3:40:29<15:53:42,  3.30it/s]
 49%|████▉     | 182790/371472 [3:40:29<16:08:49,  3.25it/s]
 49%|████▉     | 182791/371472 [3:40:29<16:10:42,  3.24it/s]
 49%|████▉     | 182792/371472 [3:40:30<15:46:41,  3.32it/s]
 49%|████▉     | 182793/371472 [3:40:30<15:38:05,  3.35it/s]
 49%|████▉     | 182794/371472 [3:40:30<15:22:36,  3.41it/s]
 49%|████▉     | 182795/371472 [3:40:30<15:14:50,  3.44it/s]
 49%|████▉     | 182796/371472 [3:40:31<14:57:40,  3.50it/s]
 49%|████▉     | 182797/371472 [3:40:31<14:59:24,  3.50it/s]
 49%|████▉     | 182798/371472 [3:40:31<15:34:29,  3.37it/s]
 49%|████▉     | 182799/371472 [3:40:32<15:39:53,  3.35it/s]
 49%|████▉     | 182800/371472 [3:40:32<15:21:30,  3.41it/s]
                                                            
{'loss': 2.7459, 'learning_rate': 5.573595638776961e-07, 'epoch': 7.87}
+
 49%|████▉     | 182800/371472 [3:40:32<15:21:30,  3.41it/s]
 49%|████▉     | 182801/371472 [3:40:32<16:09:06,  3.24it/s]
 49%|████▉     | 182802/371472 [3:40:33<15:58:05,  3.28it/s]
 49%|████▉     | 182803/371472 [3:40:33<15:53:55,  3.30it/s]
 49%|████▉     | 182804/371472 [3:40:33<15:24:52,  3.40it/s]
 49%|████▉     | 182805/371472 [3:40:33<15:05:24,  3.47it/s]
 49%|████▉     | 182806/371472 [3:40:34<14:45:45,  3.55it/s]
 49%|████▉     | 182807/371472 [3:40:34<14:47:49,  3.54it/s]
 49%|████▉     | 182808/371472 [3:40:34<14:55:38,  3.51it/s]
 49%|████▉     | 182809/371472 [3:40:35<15:04:45,  3.48it/s]
 49%|████▉     | 182810/371472 [3:40:35<15:06:14,  3.47it/s]
 49%|████▉     | 182811/371472 [3:40:35<15:13:33,  3.44it/s]
 49%|████▉     | 182812/371472 [3:40:35<15:46:24,  3.32it/s]
 49%|████▉     | 182813/371472 [3:40:36<15:53:05,  3.30it/s]
 49%|████▉     | 182814/371472 [3:40:36<15:37:05,  3.36it/s]
 49%|████▉     | 182815/371472 [3:40:36<15:52:32,  3.30it/s]
 49%|████▉     | 182816/371472 [3:40:37<16:00:08,  3.27it/s]
 49%|████▉     | 182817/371472 [3:40:37<15:58:57,  3.28it/s]
 49%|████▉     | 182818/371472 [3:40:37<15:50:23,  3.31it/s]
 49%|████▉     | 182819/371472 [3:40:38<15:56:26,  3.29it/s]
 49%|████▉     | 182820/371472 [3:40:38<15:58:54,  3.28it/s]
                                                            
{'loss': 2.8585, 'learning_rate': 5.573110819022173e-07, 'epoch': 7.87}
+
 49%|████▉     | 182820/371472 [3:40:38<15:58:54,  3.28it/s]
 49%|████▉     | 182821/371472 [3:40:38<15:58:29,  3.28it/s]
 49%|████▉     | 182822/371472 [3:40:38<16:08:58,  3.24it/s]
 49%|████▉     | 182823/371472 [3:40:39<15:54:48,  3.29it/s]
 49%|████▉     | 182824/371472 [3:40:39<15:36:47,  3.36it/s]
 49%|████▉     | 182825/371472 [3:40:39<15:08:45,  3.46it/s]
 49%|████▉     | 182826/371472 [3:40:40<15:28:32,  3.39it/s]
 49%|████▉     | 182827/371472 [3:40:40<15:19:08,  3.42it/s]
 49%|████▉     | 182828/371472 [3:40:40<15:58:10,  3.28it/s]
 49%|████▉     | 182829/371472 [3:40:41<17:02:29,  3.07it/s]
 49%|████▉     | 182830/371472 [3:40:41<16:28:00,  3.18it/s]
 49%|████▉     | 182831/371472 [3:40:41<16:14:49,  3.23it/s]
 49%|████▉     | 182832/371472 [3:40:42<16:32:54,  3.17it/s]
 49%|████▉     | 182833/371472 [3:40:42<17:57:31,  2.92it/s]
 49%|████▉     | 182834/371472 [3:40:42<17:19:04,  3.03it/s]
 49%|████▉     | 182835/371472 [3:40:43<16:33:35,  3.16it/s]
 49%|████▉     | 182836/371472 [3:40:43<17:06:02,  3.06it/s]
 49%|████▉     | 182837/371472 [3:40:43<16:01:58,  3.27it/s]
 49%|████▉     | 182838/371472 [3:40:43<15:43:26,  3.33it/s]
 49%|████▉     | 182839/371472 [3:40:44<15:14:55,  3.44it/s]
 49%|████▉     | 182840/371472 [3:40:44<15:24:10,  3.40it/s]
                                                            
{'loss': 2.975, 'learning_rate': 5.572625999267382e-07, 'epoch': 7.88}
+
 49%|████▉     | 182840/371472 [3:40:44<15:24:10,  3.40it/s]
 49%|████▉     | 182841/371472 [3:40:44<15:14:03,  3.44it/s]
 49%|████▉     | 182842/371472 [3:40:45<15:18:34,  3.42it/s]
 49%|████▉     | 182843/371472 [3:40:45<14:49:57,  3.53it/s]
 49%|████▉     | 182844/371472 [3:40:45<15:10:16,  3.45it/s]
 49%|████▉     | 182845/371472 [3:40:45<14:54:09,  3.52it/s]
 49%|████▉     | 182846/371472 [3:40:46<14:41:14,  3.57it/s]
 49%|████▉     | 182847/371472 [3:40:46<14:24:13,  3.64it/s]
 49%|████▉     | 182848/371472 [3:40:46<15:05:57,  3.47it/s]
 49%|████▉     | 182849/371472 [3:40:47<14:59:20,  3.50it/s]
 49%|████▉     | 182850/371472 [3:40:47<15:08:39,  3.46it/s]
 49%|████▉     | 182851/371472 [3:40:47<15:10:09,  3.45it/s]
 49%|████▉     | 182852/371472 [3:40:47<15:04:34,  3.48it/s]
 49%|████▉     | 182853/371472 [3:40:48<15:24:33,  3.40it/s]
 49%|████▉     | 182854/371472 [3:40:48<16:26:55,  3.19it/s]
 49%|████▉     | 182855/371472 [3:40:48<16:48:49,  3.12it/s]
 49%|████▉     | 182856/371472 [3:40:49<16:08:23,  3.25it/s]
 49%|████▉     | 182857/371472 [3:40:49<15:44:46,  3.33it/s]
 49%|████▉     | 182858/371472 [3:40:49<15:42:02,  3.34it/s]
 49%|████▉     | 182859/371472 [3:40:50<15:27:10,  3.39it/s]
 49%|████▉     | 182860/371472 [3:40:50<15:19:06,  3.42it/s]
                                                            
{'loss': 3.0125, 'learning_rate': 5.572141179512595e-07, 'epoch': 7.88}
+
 49%|████▉     | 182860/371472 [3:40:50<15:19:06,  3.42it/s]
 49%|████▉     | 182861/371472 [3:40:50<15:21:53,  3.41it/s]
 49%|████▉     | 182862/371472 [3:40:51<16:44:15,  3.13it/s]
 49%|████▉     | 182863/371472 [3:40:51<16:01:42,  3.27it/s]
 49%|████▉     | 182864/371472 [3:40:51<15:46:33,  3.32it/s]
 49%|████▉     | 182865/371472 [3:40:51<15:31:37,  3.37it/s]
 49%|████▉     | 182866/371472 [3:40:52<15:25:35,  3.40it/s]
 49%|████▉     | 182867/371472 [3:40:52<16:52:01,  3.11it/s]
 49%|████▉     | 182868/371472 [3:40:52<16:29:49,  3.18it/s]
 49%|████▉     | 182869/371472 [3:40:53<16:15:48,  3.22it/s]
 49%|████▉     | 182870/371472 [3:40:53<15:49:04,  3.31it/s]
 49%|████▉     | 182871/371472 [3:40:53<15:32:31,  3.37it/s]
 49%|████▉     | 182872/371472 [3:40:54<15:29:40,  3.38it/s]
 49%|████▉     | 182873/371472 [3:40:54<15:49:12,  3.31it/s]
 49%|████▉     | 182874/371472 [3:40:54<15:39:48,  3.34it/s]
 49%|████▉     | 182875/371472 [3:40:54<16:05:51,  3.25it/s]
 49%|████▉     | 182876/371472 [3:40:55<15:44:49,  3.33it/s]
 49%|████▉     | 182877/371472 [3:40:55<17:16:34,  3.03it/s]
 49%|████▉     | 182878/371472 [3:40:55<16:37:59,  3.15it/s]
 49%|████▉     | 182879/371472 [3:40:56<16:12:42,  3.23it/s]
 49%|████▉     | 182880/371472 [3:40:56<16:14:57,  3.22it/s]
                                                            
{'loss': 2.9091, 'learning_rate': 5.571656359757806e-07, 'epoch': 7.88}
+
 49%|████▉     | 182880/371472 [3:40:56<16:14:57,  3.22it/s]
 49%|████▉     | 182881/371472 [3:40:56<16:22:41,  3.20it/s]
 49%|████▉     | 182882/371472 [3:40:57<16:37:12,  3.15it/s]
 49%|████▉     | 182883/371472 [3:40:57<16:54:12,  3.10it/s]
 49%|████▉     | 182884/371472 [3:40:57<16:24:01,  3.19it/s]
 49%|████▉     | 182885/371472 [3:40:58<16:41:35,  3.14it/s]
 49%|████▉     | 182886/371472 [3:40:58<16:11:28,  3.24it/s]
 49%|████▉     | 182887/371472 [3:40:58<16:08:35,  3.24it/s]
 49%|████▉     | 182888/371472 [3:40:58<15:43:31,  3.33it/s]
 49%|████▉     | 182889/371472 [3:40:59<15:38:41,  3.35it/s]
 49%|████▉     | 182890/371472 [3:40:59<16:27:20,  3.18it/s]
 49%|████▉     | 182891/371472 [3:40:59<16:48:36,  3.12it/s]
 49%|████▉     | 182892/371472 [3:41:00<16:37:17,  3.15it/s]
 49%|████▉     | 182893/371472 [3:41:00<16:13:08,  3.23it/s]
 49%|████▉     | 182894/371472 [3:41:00<15:58:19,  3.28it/s]
 49%|████▉     | 182895/371472 [3:41:01<15:50:25,  3.31it/s]
 49%|████▉     | 182896/371472 [3:41:01<15:49:27,  3.31it/s]
 49%|████▉     | 182897/371472 [3:41:01<16:01:07,  3.27it/s]
 49%|████▉     | 182898/371472 [3:41:02<16:07:58,  3.25it/s]
 49%|████▉     | 182899/371472 [3:41:02<15:50:06,  3.31it/s]
 49%|████▉     | 182900/371472 [3:41:02<16:18:26,  3.21it/s]
                                                            
{'loss': 2.894, 'learning_rate': 5.571171540003017e-07, 'epoch': 7.88}
+
 49%|████▉     | 182900/371472 [3:41:02<16:18:26,  3.21it/s]
 49%|████▉     | 182901/371472 [3:41:03<16:58:27,  3.09it/s]
 49%|████▉     | 182902/371472 [3:41:03<17:19:18,  3.02it/s]
 49%|████▉     | 182903/371472 [3:41:03<16:47:41,  3.12it/s]
 49%|████▉     | 182904/371472 [3:41:04<16:31:13,  3.17it/s]
 49%|████▉     | 182905/371472 [3:41:04<17:11:43,  3.05it/s]
 49%|████▉     | 182906/371472 [3:41:04<17:20:22,  3.02it/s]
 49%|████▉     | 182907/371472 [3:41:05<16:41:01,  3.14it/s]
 49%|████▉     | 182908/371472 [3:41:05<16:05:59,  3.25it/s]
 49%|████▉     | 182909/371472 [3:41:05<15:37:09,  3.35it/s]
 49%|████▉     | 182910/371472 [3:41:05<16:31:20,  3.17it/s]
 49%|████▉     | 182911/371472 [3:41:06<16:10:35,  3.24it/s]
 49%|████▉     | 182912/371472 [3:41:06<16:09:15,  3.24it/s]
 49%|████▉     | 182913/371472 [3:41:06<16:02:20,  3.27it/s]
 49%|████▉     | 182914/371472 [3:41:07<15:42:44,  3.33it/s]
 49%|████▉     | 182915/371472 [3:41:07<16:15:55,  3.22it/s]
 49%|████▉     | 182916/371472 [3:41:07<16:52:01,  3.11it/s]
 49%|████▉     | 182917/371472 [3:41:08<17:37:29,  2.97it/s]
 49%|████▉     | 182918/371472 [3:41:08<17:07:14,  3.06it/s]
 49%|████▉     | 182919/371472 [3:41:08<16:37:41,  3.15it/s]
 49%|████▉     | 182920/371472 [3:41:09<15:51:02,  3.30it/s]
                                                            
{'loss': 2.9009, 'learning_rate': 5.570686720248227e-07, 'epoch': 7.88}
+
 49%|████▉     | 182920/371472 [3:41:09<15:51:02,  3.30it/s]
 49%|████▉     | 182921/371472 [3:41:09<15:45:57,  3.32it/s]
 49%|████▉     | 182922/371472 [3:41:09<15:28:39,  3.38it/s]
 49%|████▉     | 182923/371472 [3:41:09<15:46:29,  3.32it/s]
 49%|████▉     | 182924/371472 [3:41:10<15:48:57,  3.31it/s]
 49%|████▉     | 182925/371472 [3:41:10<15:53:57,  3.29it/s]
 49%|████▉     | 182926/371472 [3:41:10<15:45:17,  3.32it/s]
 49%|████▉     | 182927/371472 [3:41:11<16:25:51,  3.19it/s]
 49%|████▉     | 182928/371472 [3:41:11<15:48:00,  3.31it/s]
 49%|████▉     | 182929/371472 [3:41:11<15:32:40,  3.37it/s]
 49%|████▉     | 182930/371472 [3:41:12<16:52:27,  3.10it/s]
 49%|████▉     | 182931/371472 [3:41:12<17:02:22,  3.07it/s]
 49%|████▉     | 182932/371472 [3:41:12<16:28:12,  3.18it/s]
 49%|████▉     | 182933/371472 [3:41:13<16:36:21,  3.15it/s]
 49%|████▉     | 182934/371472 [3:41:13<16:11:17,  3.24it/s]
 49%|████▉     | 182935/371472 [3:41:13<16:13:54,  3.23it/s]
 49%|████▉     | 182936/371472 [3:41:13<16:01:29,  3.27it/s]
 49%|████▉     | 182937/371472 [3:41:14<16:02:05,  3.27it/s]
 49%|████▉     | 182938/371472 [3:41:14<16:44:10,  3.13it/s]
 49%|████▉     | 182939/371472 [3:41:14<17:24:04,  3.01it/s]
 49%|████▉     | 182940/371472 [3:41:15<17:15:20,  3.03it/s]
                                                            
{'loss': 2.6669, 'learning_rate': 5.570201900493438e-07, 'epoch': 7.88}
+
 49%|████▉     | 182940/371472 [3:41:15<17:15:20,  3.03it/s]
 49%|████▉     | 182941/371472 [3:41:15<16:59:14,  3.08it/s]
 49%|████▉     | 182942/371472 [3:41:15<16:11:29,  3.23it/s]
 49%|████▉     | 182943/371472 [3:41:16<15:52:25,  3.30it/s]
 49%|████▉     | 182944/371472 [3:41:16<15:53:53,  3.29it/s]
 49%|████▉     | 182945/371472 [3:41:16<15:22:44,  3.41it/s]
 49%|████▉     | 182946/371472 [3:41:17<15:27:24,  3.39it/s]
 49%|████▉     | 182947/371472 [3:41:17<15:51:18,  3.30it/s]
 49%|████▉     | 182948/371472 [3:41:17<15:59:12,  3.28it/s]
 49%|████▉     | 182949/371472 [3:41:17<16:01:27,  3.27it/s]
 49%|████▉     | 182950/371472 [3:41:18<16:33:01,  3.16it/s]
 49%|████▉     | 182951/371472 [3:41:18<16:58:11,  3.09it/s]
 49%|████▉     | 182952/371472 [3:41:18<16:24:36,  3.19it/s]
 49%|████▉     | 182953/371472 [3:41:19<16:02:59,  3.26it/s]
 49%|████▉     | 182954/371472 [3:41:19<15:50:35,  3.31it/s]
 49%|████▉     | 182955/371472 [3:41:19<15:40:16,  3.34it/s]
 49%|████▉     | 182956/371472 [3:41:20<15:29:57,  3.38it/s]
 49%|████▉     | 182957/371472 [3:41:20<15:16:58,  3.43it/s]
 49%|████▉     | 182958/371472 [3:41:20<15:20:06,  3.41it/s]
 49%|████▉     | 182959/371472 [3:41:20<15:04:58,  3.47it/s]
 49%|████▉     | 182960/371472 [3:41:21<15:12:39,  3.44it/s]
                                                            
{'loss': 2.8498, 'learning_rate': 5.569717080738651e-07, 'epoch': 7.88}
+
 49%|████▉     | 182960/371472 [3:41:21<15:12:39,  3.44it/s]
 49%|████▉     | 182961/371472 [3:41:21<15:06:31,  3.47it/s]
 49%|████▉     | 182962/371472 [3:41:21<15:07:15,  3.46it/s]
 49%|████▉     | 182963/371472 [3:41:22<14:52:57,  3.52it/s]
 49%|████▉     | 182964/371472 [3:41:22<14:40:24,  3.57it/s]
 49%|████▉     | 182965/371472 [3:41:22<17:32:58,  2.98it/s]
 49%|████▉     | 182966/371472 [3:41:23<17:14:43,  3.04it/s]
 49%|████▉     | 182967/371472 [3:41:23<16:09:18,  3.24it/s]
 49%|████▉     | 182968/371472 [3:41:23<16:11:41,  3.23it/s]
 49%|████▉     | 182969/371472 [3:41:24<16:22:38,  3.20it/s]
 49%|████▉     | 182970/371472 [3:41:24<15:39:27,  3.34it/s]
 49%|████▉     | 182971/371472 [3:41:24<15:29:16,  3.38it/s]
 49%|████▉     | 182972/371472 [3:41:24<15:41:54,  3.34it/s]
 49%|████▉     | 182973/371472 [3:41:25<15:30:21,  3.38it/s]
 49%|████▉     | 182974/371472 [3:41:25<16:04:21,  3.26it/s]
 49%|████▉     | 182975/371472 [3:41:25<15:33:52,  3.36it/s]
 49%|████▉     | 182976/371472 [3:41:26<15:06:18,  3.47it/s]
 49%|████▉     | 182977/371472 [3:41:26<15:31:38,  3.37it/s]
 49%|████▉     | 182978/371472 [3:41:26<15:32:32,  3.37it/s]
 49%|████▉     | 182979/371472 [3:41:26<15:32:01,  3.37it/s]
 49%|████▉     | 182980/371472 [3:41:27<15:28:19,  3.38it/s]
                                                            
{'loss': 2.9496, 'learning_rate': 5.569232260983861e-07, 'epoch': 7.88}
+
 49%|████▉     | 182980/371472 [3:41:27<15:28:19,  3.38it/s]
 49%|████▉     | 182981/371472 [3:41:27<15:36:38,  3.35it/s]
 49%|████▉     | 182982/371472 [3:41:27<15:26:07,  3.39it/s]
 49%|████▉     | 182983/371472 [3:41:28<16:02:31,  3.26it/s]
 49%|████▉     | 182984/371472 [3:41:28<16:06:55,  3.25it/s]
 49%|████▉     | 182985/371472 [3:41:28<16:18:01,  3.21it/s]
 49%|████▉     | 182986/371472 [3:41:29<15:43:20,  3.33it/s]
 49%|████▉     | 182987/371472 [3:41:29<15:44:28,  3.33it/s]
 49%|████▉     | 182988/371472 [3:41:29<15:32:00,  3.37it/s]
 49%|████▉     | 182989/371472 [3:41:30<15:31:35,  3.37it/s]
 49%|████▉     | 182990/371472 [3:41:30<15:05:50,  3.47it/s]
 49%|████▉     | 182991/371472 [3:41:30<15:06:24,  3.47it/s]
 49%|████▉     | 182992/371472 [3:41:30<14:43:09,  3.56it/s]
 49%|████▉     | 182993/371472 [3:41:31<14:49:18,  3.53it/s]
 49%|████▉     | 182994/371472 [3:41:31<14:31:38,  3.60it/s]
 49%|████▉     | 182995/371472 [3:41:31<14:43:11,  3.56it/s]
 49%|████▉     | 182996/371472 [3:41:31<14:34:49,  3.59it/s]
 49%|████▉     | 182997/371472 [3:41:32<14:36:21,  3.58it/s]
 49%|████▉     | 182998/371472 [3:41:32<14:50:07,  3.53it/s]
 49%|████▉     | 182999/371472 [3:41:32<14:56:59,  3.50it/s]
 49%|████▉     | 183000/371472 [3:41:33<14:56:10,  3.51it/s]
                                                            
{'loss': 3.0787, 'learning_rate': 5.568747441229071e-07, 'epoch': 7.88}
+
 49%|████▉     | 183000/371472 [3:41:33<14:56:10,  3.51it/s]
 49%|████▉     | 183001/371472 [3:41:33<15:01:25,  3.48it/s]
 49%|████▉     | 183002/371472 [3:41:33<15:00:03,  3.49it/s]
 49%|████▉     | 183003/371472 [3:41:33<14:59:50,  3.49it/s]
 49%|████▉     | 183004/371472 [3:41:34<15:34:59,  3.36it/s]
 49%|████▉     | 183005/371472 [3:41:34<16:12:57,  3.23it/s]
 49%|████▉     | 183006/371472 [3:41:34<16:00:34,  3.27it/s]
 49%|████▉     | 183007/371472 [3:41:35<15:37:41,  3.35it/s]
 49%|████▉     | 183008/371472 [3:41:35<15:26:23,  3.39it/s]
 49%|████▉     | 183009/371472 [3:41:35<15:04:18,  3.47it/s]
 49%|████▉     | 183010/371472 [3:41:36<14:58:43,  3.50it/s]
 49%|████▉     | 183011/371472 [3:41:36<15:09:36,  3.45it/s]
 49%|████▉     | 183012/371472 [3:41:36<16:49:40,  3.11it/s]
 49%|████▉     | 183013/371472 [3:41:37<17:02:28,  3.07it/s]
 49%|████▉     | 183014/371472 [3:41:37<16:01:39,  3.27it/s]
 49%|████▉     | 183015/371472 [3:41:37<15:55:22,  3.29it/s]
 49%|████▉     | 183016/371472 [3:41:37<16:14:23,  3.22it/s]
 49%|████▉     | 183017/371472 [3:41:38<15:50:32,  3.30it/s]
 49%|████▉     | 183018/371472 [3:41:38<16:13:58,  3.22it/s]
 49%|████▉     | 183019/371472 [3:41:38<15:52:58,  3.30it/s]
 49%|████▉     | 183020/371472 [3:41:39<15:49:54,  3.31it/s]
                                                            
{'loss': 2.8212, 'learning_rate': 5.568262621474283e-07, 'epoch': 7.88}
+
 49%|████▉     | 183020/371472 [3:41:39<15:49:54,  3.31it/s]
 49%|████▉     | 183021/371472 [3:41:39<15:34:52,  3.36it/s]
 49%|████▉     | 183022/371472 [3:41:39<16:19:58,  3.21it/s]
 49%|████▉     | 183023/371472 [3:41:40<15:50:53,  3.30it/s]
 49%|████▉     | 183024/371472 [3:41:40<15:50:19,  3.30it/s]
 49%|████▉     | 183025/371472 [3:41:40<15:43:26,  3.33it/s]
 49%|████▉     | 183026/371472 [3:41:41<16:41:35,  3.14it/s]
 49%|████▉     | 183027/371472 [3:41:41<16:11:12,  3.23it/s]
 49%|████▉     | 183028/371472 [3:41:41<15:43:46,  3.33it/s]
 49%|████▉     | 183029/371472 [3:41:41<15:33:02,  3.37it/s]
 49%|████▉     | 183030/371472 [3:41:42<15:34:04,  3.36it/s]
 49%|████▉     | 183031/371472 [3:41:42<15:27:25,  3.39it/s]
 49%|████▉     | 183032/371472 [3:41:42<15:40:07,  3.34it/s]
 49%|████▉     | 183033/371472 [3:41:43<15:51:26,  3.30it/s]
 49%|████▉     | 183034/371472 [3:41:43<15:28:30,  3.38it/s]
 49%|████▉     | 183035/371472 [3:41:43<18:18:24,  2.86it/s]
 49%|████▉     | 183036/371472 [3:41:44<17:03:33,  3.07it/s]
 49%|████▉     | 183037/371472 [3:41:44<16:28:00,  3.18it/s]
 49%|████▉     | 183038/371472 [3:41:44<16:06:09,  3.25it/s]
 49%|████▉     | 183039/371472 [3:41:44<15:49:29,  3.31it/s]
 49%|████▉     | 183040/371472 [3:41:45<16:45:58,  3.12it/s]
                                                            
{'loss': 2.8339, 'learning_rate': 5.567777801719495e-07, 'epoch': 7.88}
+
 49%|████▉     | 183040/371472 [3:41:45<16:45:58,  3.12it/s]
 49%|████▉     | 183041/371472 [3:41:45<16:06:22,  3.25it/s]
 49%|████▉     | 183042/371472 [3:41:45<15:32:09,  3.37it/s]
 49%|████▉     | 183043/371472 [3:41:46<16:08:28,  3.24it/s]
 49%|████▉     | 183044/371472 [3:41:46<16:51:56,  3.10it/s]
 49%|████▉     | 183045/371472 [3:41:46<16:39:53,  3.14it/s]
 49%|████▉     | 183046/371472 [3:41:47<16:23:06,  3.19it/s]
 49%|████▉     | 183047/371472 [3:41:47<15:37:40,  3.35it/s]
 49%|████▉     | 183048/371472 [3:41:47<15:25:16,  3.39it/s]
 49%|████▉     | 183049/371472 [3:41:48<17:29:07,  2.99it/s]
 49%|████▉     | 183050/371472 [3:41:48<16:56:10,  3.09it/s]
 49%|████▉     | 183051/371472 [3:41:48<16:20:38,  3.20it/s]
 49%|████▉     | 183052/371472 [3:41:49<15:53:40,  3.29it/s]
 49%|████▉     | 183053/371472 [3:41:49<15:31:47,  3.37it/s]
 49%|████▉     | 183054/371472 [3:41:49<15:39:21,  3.34it/s]
 49%|████▉     | 183055/371472 [3:41:49<15:44:09,  3.33it/s]
 49%|████▉     | 183056/371472 [3:41:50<15:26:00,  3.39it/s]
 49%|████▉     | 183057/371472 [3:41:50<15:20:10,  3.41it/s]
 49%|████▉     | 183058/371472 [3:41:50<15:23:26,  3.40it/s]
 49%|████▉     | 183059/371472 [3:41:51<15:05:11,  3.47it/s]
 49%|████▉     | 183060/371472 [3:41:51<15:21:10,  3.41it/s]
                                                            
{'loss': 3.0194, 'learning_rate': 5.567292981964704e-07, 'epoch': 7.88}
+
 49%|████▉     | 183060/371472 [3:41:51<15:21:10,  3.41it/s]
 49%|████▉     | 183061/371472 [3:41:51<15:13:32,  3.44it/s]
 49%|████▉     | 183062/371472 [3:41:51<15:21:30,  3.41it/s]
 49%|████▉     | 183063/371472 [3:41:52<15:03:53,  3.47it/s]
 49%|████▉     | 183064/371472 [3:41:52<14:58:26,  3.50it/s]
 49%|████▉     | 183065/371472 [3:41:52<15:37:09,  3.35it/s]
 49%|████▉     | 183066/371472 [3:41:53<15:26:25,  3.39it/s]
 49%|████▉     | 183067/371472 [3:41:53<15:36:53,  3.35it/s]
 49%|████▉     | 183068/371472 [3:41:53<15:21:16,  3.41it/s]
 49%|████▉     | 183069/371472 [3:41:54<15:37:08,  3.35it/s]
 49%|████▉     | 183070/371472 [3:41:54<15:28:08,  3.38it/s]
 49%|████▉     | 183071/371472 [3:41:54<15:35:29,  3.36it/s]
 49%|████▉     | 183072/371472 [3:41:54<15:17:02,  3.42it/s]
 49%|████▉     | 183073/371472 [3:41:55<15:58:50,  3.27it/s]
 49%|████▉     | 183074/371472 [3:41:55<15:38:25,  3.35it/s]
 49%|████▉     | 183075/371472 [3:41:55<15:06:44,  3.46it/s]
 49%|████▉     | 183076/371472 [3:41:56<16:19:01,  3.21it/s]
 49%|████▉     | 183077/371472 [3:41:56<15:40:27,  3.34it/s]
 49%|████▉     | 183078/371472 [3:41:56<15:16:55,  3.42it/s]
 49%|████▉     | 183079/371472 [3:41:57<16:01:36,  3.27it/s]
 49%|████▉     | 183080/371472 [3:41:57<16:27:50,  3.18it/s]
                                                            
{'loss': 2.828, 'learning_rate': 5.566808162209915e-07, 'epoch': 7.89}
+
 49%|████▉     | 183080/371472 [3:41:57<16:27:50,  3.18it/s]
 49%|████▉     | 183081/371472 [3:41:57<16:05:36,  3.25it/s]
 49%|████▉     | 183082/371472 [3:41:57<16:13:30,  3.23it/s]
 49%|████▉     | 183083/371472 [3:41:58<16:54:24,  3.10it/s]
 49%|████▉     | 183084/371472 [3:41:58<16:26:27,  3.18it/s]
 49%|████▉     | 183085/371472 [3:41:58<16:03:09,  3.26it/s]
 49%|████▉     | 183086/371472 [3:41:59<15:42:31,  3.33it/s]
 49%|████▉     | 183087/371472 [3:41:59<18:38:33,  2.81it/s]
 49%|████▉     | 183088/371472 [3:41:59<17:17:22,  3.03it/s]
 49%|████▉     | 183089/371472 [3:42:00<16:33:43,  3.16it/s]
 49%|████▉     | 183090/371472 [3:42:00<16:33:43,  3.16it/s]
 49%|████▉     | 183091/371472 [3:42:00<16:00:49,  3.27it/s]
 49%|████▉     | 183092/371472 [3:42:01<16:13:20,  3.23it/s]
 49%|████▉     | 183093/371472 [3:42:01<15:45:54,  3.32it/s]
 49%|████▉     | 183094/371472 [3:42:01<15:12:33,  3.44it/s]
 49%|████▉     | 183095/371472 [3:42:01<15:09:00,  3.45it/s]
 49%|████▉     | 183096/371472 [3:42:02<15:00:39,  3.49it/s]
 49%|████▉     | 183097/371472 [3:42:02<14:51:24,  3.52it/s]
 49%|████▉     | 183098/371472 [3:42:02<14:40:51,  3.56it/s]
 49%|████▉     | 183099/371472 [3:42:03<14:26:53,  3.62it/s]
 49%|████▉     | 183100/371472 [3:42:03<14:58:42,  3.49it/s]
                                                            
{'loss': 2.9469, 'learning_rate': 5.566323342455128e-07, 'epoch': 7.89}
+
 49%|████▉     | 183100/371472 [3:42:03<14:58:42,  3.49it/s]
 49%|████▉     | 183101/371472 [3:42:03<15:10:03,  3.45it/s]
 49%|████▉     | 183102/371472 [3:42:03<15:17:27,  3.42it/s]
 49%|████▉     | 183103/371472 [3:42:04<15:01:03,  3.48it/s]
 49%|████▉     | 183104/371472 [3:42:04<15:33:19,  3.36it/s]
 49%|████▉     | 183105/371472 [3:42:04<15:42:15,  3.33it/s]
 49%|████▉     | 183106/371472 [3:42:05<15:54:03,  3.29it/s]
 49%|████▉     | 183107/371472 [3:42:05<16:04:04,  3.26it/s]
 49%|████▉     | 183108/371472 [3:42:05<16:19:34,  3.20it/s]
 49%|████▉     | 183109/371472 [3:42:06<16:10:39,  3.23it/s]
 49%|████▉     | 183110/371472 [3:42:06<16:02:15,  3.26it/s]
 49%|████▉     | 183111/371472 [3:42:06<15:45:18,  3.32it/s]
 49%|████▉     | 183112/371472 [3:42:07<15:24:12,  3.40it/s]
 49%|████▉     | 183113/371472 [3:42:07<16:19:22,  3.21it/s]
 49%|████▉     | 183114/371472 [3:42:07<16:07:53,  3.24it/s]
 49%|████▉     | 183115/371472 [3:42:07<16:25:27,  3.19it/s]
 49%|████▉     | 183116/371472 [3:42:08<16:08:38,  3.24it/s]
 49%|████▉     | 183117/371472 [3:42:08<15:38:17,  3.35it/s]
 49%|████▉     | 183118/371472 [3:42:08<15:57:55,  3.28it/s]
 49%|████▉     | 183119/371472 [3:42:09<15:58:10,  3.28it/s]
 49%|████▉     | 183120/371472 [3:42:09<16:48:54,  3.11it/s]
                                                            
{'loss': 2.9783, 'learning_rate': 5.565838522700339e-07, 'epoch': 7.89}
+
 49%|████▉     | 183120/371472 [3:42:09<16:48:54,  3.11it/s]
 49%|████▉     | 183121/371472 [3:42:09<17:19:01,  3.02it/s]
 49%|████▉     | 183122/371472 [3:42:10<16:41:28,  3.13it/s]
 49%|████▉     | 183123/371472 [3:42:10<15:45:23,  3.32it/s]
 49%|████▉     | 183124/371472 [3:42:10<15:24:06,  3.40it/s]
 49%|████▉     | 183125/371472 [3:42:11<15:41:44,  3.33it/s]
 49%|████▉     | 183126/371472 [3:42:11<15:30:39,  3.37it/s]
 49%|████▉     | 183127/371472 [3:42:11<16:05:02,  3.25it/s]
 49%|████▉     | 183128/371472 [3:42:11<15:35:57,  3.35it/s]
 49%|████▉     | 183129/371472 [3:42:12<15:40:04,  3.34it/s]
 49%|████▉     | 183130/371472 [3:42:12<15:20:43,  3.41it/s]
 49%|████▉     | 183131/371472 [3:42:12<15:01:41,  3.48it/s]
 49%|████▉     | 183132/371472 [3:42:13<14:49:33,  3.53it/s]
 49%|████▉     | 183133/371472 [3:42:13<14:59:55,  3.49it/s]
 49%|████▉     | 183134/371472 [3:42:13<15:04:27,  3.47it/s]
 49%|████▉     | 183135/371472 [3:42:13<15:07:24,  3.46it/s]
 49%|████▉     | 183136/371472 [3:42:14<15:50:55,  3.30it/s]
 49%|████▉     | 183137/371472 [3:42:14<15:29:49,  3.38it/s]
 49%|████▉     | 183138/371472 [3:42:14<15:13:04,  3.44it/s]
 49%|████▉     | 183139/371472 [3:42:15<14:58:51,  3.49it/s]
 49%|████▉     | 183140/371472 [3:42:15<14:54:27,  3.51it/s]
                                                            
{'loss': 3.1139, 'learning_rate': 5.565353702945548e-07, 'epoch': 7.89}
+
 49%|████▉     | 183140/371472 [3:42:15<14:54:27,  3.51it/s]
 49%|████▉     | 183141/371472 [3:42:15<15:51:26,  3.30it/s]
 49%|████▉     | 183142/371472 [3:42:16<16:46:15,  3.12it/s]
 49%|████▉     | 183143/371472 [3:42:16<16:21:02,  3.20it/s]
 49%|████▉     | 183144/371472 [3:42:16<16:47:45,  3.11it/s]
 49%|████▉     | 183145/371472 [3:42:17<17:05:34,  3.06it/s]
 49%|████▉     | 183146/371472 [3:42:17<17:04:01,  3.07it/s]
 49%|████▉     | 183147/371472 [3:42:17<16:18:38,  3.21it/s]
 49%|████▉     | 183148/371472 [3:42:18<16:24:36,  3.19it/s]
 49%|████▉     | 183149/371472 [3:42:18<16:46:56,  3.12it/s]
 49%|████▉     | 183150/371472 [3:42:18<17:48:37,  2.94it/s]
 49%|████▉     | 183151/371472 [3:42:19<17:05:56,  3.06it/s]
 49%|████▉     | 183152/371472 [3:42:19<16:31:43,  3.16it/s]
 49%|████▉     | 183153/371472 [3:42:19<16:07:56,  3.24it/s]
 49%|████▉     | 183154/371472 [3:42:19<15:53:15,  3.29it/s]
 49%|████▉     | 183155/371472 [3:42:20<15:34:05,  3.36it/s]
 49%|████▉     | 183156/371472 [3:42:20<16:03:06,  3.26it/s]
 49%|████▉     | 183157/371472 [3:42:20<15:57:14,  3.28it/s]
 49%|████▉     | 183158/371472 [3:42:21<16:31:18,  3.17it/s]
 49%|████▉     | 183159/371472 [3:42:21<16:32:25,  3.16it/s]
 49%|████▉     | 183160/371472 [3:42:21<15:49:53,  3.30it/s]
                                                            
{'loss': 2.9093, 'learning_rate': 5.56486888319076e-07, 'epoch': 7.89}
+
 49%|████▉     | 183160/371472 [3:42:21<15:49:53,  3.30it/s]
 49%|████▉     | 183161/371472 [3:42:22<15:55:43,  3.28it/s]
 49%|████▉     | 183162/371472 [3:42:22<15:33:48,  3.36it/s]
 49%|████▉     | 183163/371472 [3:42:22<15:27:16,  3.38it/s]
 49%|████▉     | 183164/371472 [3:42:22<15:24:59,  3.39it/s]
 49%|████▉     | 183165/371472 [3:42:23<15:33:26,  3.36it/s]
 49%|████▉     | 183166/371472 [3:42:23<15:15:51,  3.43it/s]
 49%|████▉     | 183167/371472 [3:42:23<15:06:50,  3.46it/s]
 49%|████▉     | 183168/371472 [3:42:24<14:46:46,  3.54it/s]
 49%|████▉     | 183169/371472 [3:42:24<15:26:50,  3.39it/s]
 49%|████▉     | 183170/371472 [3:42:24<15:04:48,  3.47it/s]
 49%|████▉     | 183171/371472 [3:42:24<14:55:01,  3.51it/s]
 49%|████▉     | 183172/371472 [3:42:25<14:34:42,  3.59it/s]
 49%|████▉     | 183173/371472 [3:42:25<14:46:23,  3.54it/s]
 49%|████▉     | 183174/371472 [3:42:25<14:33:34,  3.59it/s]
 49%|████▉     | 183175/371472 [3:42:26<14:30:51,  3.60it/s]
 49%|████▉     | 183176/371472 [3:42:26<14:38:28,  3.57it/s]
 49%|████▉     | 183177/371472 [3:42:26<14:34:16,  3.59it/s]
 49%|████▉     | 183178/371472 [3:42:26<14:28:49,  3.61it/s]
 49%|████▉     | 183179/371472 [3:42:27<14:53:40,  3.51it/s]
 49%|████▉     | 183180/371472 [3:42:27<14:52:18,  3.52it/s]
                                                            
{'loss': 2.8876, 'learning_rate': 5.564384063435972e-07, 'epoch': 7.89}
+
 49%|████▉     | 183180/371472 [3:42:27<14:52:18,  3.52it/s]
 49%|████▉     | 183181/371472 [3:42:27<14:56:48,  3.50it/s]
 49%|████▉     | 183182/371472 [3:42:28<15:10:22,  3.45it/s]
 49%|████▉     | 183183/371472 [3:42:28<14:44:25,  3.55it/s]
 49%|████▉     | 183184/371472 [3:42:28<14:52:57,  3.51it/s]
 49%|████▉     | 183185/371472 [3:42:28<14:44:06,  3.55it/s]
 49%|████▉     | 183186/371472 [3:42:29<15:11:30,  3.44it/s]
 49%|████▉     | 183187/371472 [3:42:29<15:25:20,  3.39it/s]
 49%|████▉     | 183188/371472 [3:42:29<15:13:14,  3.44it/s]
 49%|████▉     | 183189/371472 [3:42:30<17:04:35,  3.06it/s]
 49%|████▉     | 183190/371472 [3:42:30<16:38:54,  3.14it/s]
 49%|████▉     | 183191/371472 [3:42:30<16:08:26,  3.24it/s]
 49%|████▉     | 183192/371472 [3:42:31<15:52:14,  3.30it/s]
 49%|██���█▉     | 183193/371472 [3:42:31<15:39:18,  3.34it/s]
 49%|████▉     | 183194/371472 [3:42:31<15:19:27,  3.41it/s]
 49%|████▉     | 183195/371472 [3:42:31<15:02:25,  3.48it/s]
 49%|████▉     | 183196/371472 [3:42:32<16:19:03,  3.21it/s]
 49%|████▉     | 183197/371472 [3:42:32<15:57:24,  3.28it/s]
 49%|████▉     | 183198/371472 [3:42:32<15:34:56,  3.36it/s]
 49%|████▉     | 183199/371472 [3:42:33<16:59:36,  3.08it/s]
 49%|████▉     | 183200/371472 [3:42:33<16:44:12,  3.12it/s]
                                                            
{'loss': 2.813, 'learning_rate': 5.563899243681181e-07, 'epoch': 7.89}
+
 49%|████▉     | 183200/371472 [3:42:33<16:44:12,  3.12it/s]
 49%|████▉     | 183201/371472 [3:42:33<16:15:08,  3.22it/s]
 49%|████▉     | 183202/371472 [3:42:34<15:40:59,  3.33it/s]
 49%|████▉     | 183203/371472 [3:42:34<15:17:11,  3.42it/s]
 49%|████▉     | 183204/371472 [3:42:34<14:39:00,  3.57it/s]
 49%|████▉     | 183205/371472 [3:42:34<14:34:57,  3.59it/s]
 49%|████▉     | 183206/371472 [3:42:35<14:45:21,  3.54it/s]
 49%|████▉     | 183207/371472 [3:42:35<15:30:20,  3.37it/s]
 49%|████▉     | 183208/371472 [3:42:35<15:30:39,  3.37it/s]
 49%|████▉     | 183209/371472 [3:42:36<15:14:07,  3.43it/s]
 49%|████▉     | 183210/371472 [3:42:36<14:59:20,  3.49it/s]
 49%|████▉     | 183211/371472 [3:42:36<15:05:01,  3.47it/s]
 49%|████▉     | 183212/371472 [3:42:36<14:49:59,  3.53it/s]
 49%|████▉     | 183213/371472 [3:42:37<15:10:40,  3.45it/s]
 49%|████▉     | 183214/371472 [3:42:37<14:46:05,  3.54it/s]
 49%|████▉     | 183215/371472 [3:42:37<15:10:22,  3.45it/s]
 49%|████▉     | 183216/371472 [3:42:38<15:46:58,  3.31it/s]
 49%|████▉     | 183217/371472 [3:42:38<15:29:03,  3.38it/s]
 49%|████▉     | 183218/371472 [3:42:38<15:50:20,  3.30it/s]
 49%|████▉     | 183219/371472 [3:42:39<16:17:25,  3.21it/s]
 49%|████▉     | 183220/371472 [3:42:39<16:11:21,  3.23it/s]
                                                            
{'loss': 2.8334, 'learning_rate': 5.563414423926392e-07, 'epoch': 7.89}
+
 49%|████▉     | 183220/371472 [3:42:39<16:11:21,  3.23it/s]
 49%|████▉     | 183221/371472 [3:42:39<15:58:25,  3.27it/s]
 49%|████▉     | 183222/371472 [3:42:39<16:15:57,  3.21it/s]
 49%|████▉     | 183223/371472 [3:42:40<16:15:39,  3.22it/s]
 49%|████▉     | 183224/371472 [3:42:40<15:44:29,  3.32it/s]
 49%|████▉     | 183225/371472 [3:42:40<16:34:24,  3.16it/s]
 49%|████▉     | 183226/371472 [3:42:41<16:22:09,  3.19it/s]
 49%|████▉     | 183227/371472 [3:42:41<15:54:18,  3.29it/s]
 49%|████▉     | 183228/371472 [3:42:41<15:39:31,  3.34it/s]
 49%|████▉     | 183229/371472 [3:42:42<15:28:06,  3.38it/s]
 49%|████▉     | 183230/371472 [3:42:42<15:54:03,  3.29it/s]
 49%|████▉     | 183231/371472 [3:42:42<15:30:11,  3.37it/s]
 49%|████▉     | 183232/371472 [3:42:43<15:41:04,  3.33it/s]
 49%|████▉     | 183233/371472 [3:42:43<17:08:38,  3.05it/s]
 49%|████▉     | 183234/371472 [3:42:43<18:08:25,  2.88it/s]
 49%|████▉     | 183235/371472 [3:42:44<17:08:00,  3.05it/s]
 49%|████▉     | 183236/371472 [3:42:44<16:40:55,  3.13it/s]
 49%|████▉     | 183237/371472 [3:42:44<16:25:37,  3.18it/s]
 49%|████▉     | 183238/371472 [3:42:44<16:15:24,  3.22it/s]
 49%|████▉     | 183239/371472 [3:42:45<15:47:51,  3.31it/s]
 49%|████▉     | 183240/371472 [3:42:45<15:44:05,  3.32it/s]
                                                            
{'loss': 2.9396, 'learning_rate': 5.562929604171605e-07, 'epoch': 7.89}
+
 49%|████▉     | 183240/371472 [3:42:45<15:44:05,  3.32it/s]
 49%|████▉     | 183241/371472 [3:42:45<16:00:26,  3.27it/s]
 49%|████▉     | 183242/371472 [3:42:46<15:14:52,  3.43it/s]
 49%|████▉     | 183243/371472 [3:42:46<14:54:50,  3.51it/s]
 49%|████▉     | 183244/371472 [3:42:46<15:23:32,  3.40it/s]
 49%|████▉     | 183245/371472 [3:42:47<16:27:19,  3.18it/s]
 49%|████▉     | 183246/371472 [3:42:47<15:43:47,  3.32it/s]
 49%|████▉     | 183247/371472 [3:42:47<15:30:29,  3.37it/s]
 49%|████▉     | 183248/371472 [3:42:47<15:50:47,  3.30it/s]
 49%|████▉     | 183249/371472 [3:42:48<15:43:42,  3.32it/s]
 49%|████▉     | 183250/371472 [3:42:48<15:29:22,  3.38it/s]
 49%|████▉     | 183251/371472 [3:42:48<15:12:54,  3.44it/s]
 49%|████▉     | 183252/371472 [3:42:49<15:08:34,  3.45it/s]
 49%|████▉     | 183253/371472 [3:42:49<14:49:46,  3.53it/s]
 49%|████▉     | 183254/371472 [3:42:49<15:07:02,  3.46it/s]
 49%|████▉     | 183255/371472 [3:42:49<15:13:06,  3.44it/s]
 49%|████▉     | 183256/371472 [3:42:50<15:09:48,  3.45it/s]
 49%|████▉     | 183257/371472 [3:42:50<15:05:04,  3.47it/s]
 49%|████▉     | 183258/371472 [3:42:50<15:02:08,  3.48it/s]
 49%|████▉     | 183259/371472 [3:42:51<14:51:45,  3.52it/s]
 49%|████▉     | 183260/371472 [3:42:51<14:53:22,  3.51it/s]
                                                            
{'loss': 3.0149, 'learning_rate': 5.562444784416816e-07, 'epoch': 7.89}
+
 49%|████▉     | 183260/371472 [3:42:51<14:53:22,  3.51it/s]
 49%|████▉     | 183261/371472 [3:42:51<14:33:50,  3.59it/s]
 49%|████▉     | 183262/371472 [3:42:51<14:57:49,  3.49it/s]
 49%|████▉     | 183263/371472 [3:42:52<17:07:26,  3.05it/s]
 49%|████▉     | 183264/371472 [3:42:52<16:47:07,  3.11it/s]
 49%|████▉     | 183265/371472 [3:42:53<17:37:16,  2.97it/s]
 49%|████▉     | 183266/371472 [3:42:53<17:28:23,  2.99it/s]
 49%|████▉     | 183267/371472 [3:42:53<17:05:19,  3.06it/s]
 49%|████▉     | 183268/371472 [3:42:53<16:12:46,  3.22it/s]
 49%|████▉     | 183269/371472 [3:42:54<16:26:07,  3.18it/s]
 49%|████▉     | 183270/371472 [3:42:54<15:52:02,  3.29it/s]
 49%|████▉     | 183271/371472 [3:42:54<15:30:19,  3.37it/s]
 49%|████▉     | 183272/371472 [3:42:55<15:28:28,  3.38it/s]
 49%|████▉     | 183273/371472 [3:42:55<15:28:20,  3.38it/s]
 49%|████▉     | 183274/371472 [3:42:55<15:32:35,  3.36it/s]
 49%|████▉     | 183275/371472 [3:42:56<15:21:46,  3.40it/s]
 49%|████▉     | 183276/371472 [3:42:56<15:36:09,  3.35it/s]
 49%|████▉     | 183277/371472 [3:42:56<15:03:44,  3.47it/s]
 49%|████▉     | 183278/371472 [3:42:56<15:34:37,  3.36it/s]
 49%|████▉     | 183279/371472 [3:42:57<16:14:17,  3.22it/s]
 49%|████▉     | 183280/371472 [3:42:57<15:39:22,  3.34it/s]
                                                            
{'loss': 2.848, 'learning_rate': 5.561959964662026e-07, 'epoch': 7.89}
+
 49%|████▉     | 183280/371472 [3:42:57<15:39:22,  3.34it/s]
 49%|████▉     | 183281/371472 [3:42:57<16:49:58,  3.11it/s]
 49%|████▉     | 183282/371472 [3:42:58<16:58:32,  3.08it/s]
 49%|████▉     | 183283/371472 [3:42:58<16:04:35,  3.25it/s]
 49%|████▉     | 183284/371472 [3:42:58<15:52:27,  3.29it/s]
 49%|████▉     | 183285/371472 [3:42:59<16:31:21,  3.16it/s]
 49%|████▉     | 183286/371472 [3:42:59<16:00:26,  3.27it/s]
 49%|████▉     | 183287/371472 [3:42:59<16:47:48,  3.11it/s]
 49%|████▉     | 183288/371472 [3:43:00<16:17:06,  3.21it/s]
 49%|████▉     | 183289/371472 [3:43:00<16:01:35,  3.26it/s]
 49%|████▉     | 183290/371472 [3:43:00<15:48:58,  3.30it/s]
 49%|████▉     | 183291/371472 [3:43:00<15:34:10,  3.36it/s]
 49%|████▉     | 183292/371472 [3:43:01<15:52:16,  3.29it/s]
 49%|████▉     | 183293/371472 [3:43:01<16:59:35,  3.08it/s]
 49%|████▉     | 183294/371472 [3:43:01<16:30:48,  3.17it/s]
 49%|████▉     | 183295/371472 [3:43:02<16:12:21,  3.23it/s]
 49%|████▉     | 183296/371472 [3:43:02<15:32:45,  3.36it/s]
 49%|████▉     | 183297/371472 [3:43:02<15:23:42,  3.40it/s]
 49%|████▉     | 183298/371472 [3:43:03<15:20:47,  3.41it/s]
 49%|████▉     | 183299/371472 [3:43:03<15:15:16,  3.43it/s]
 49%|████▉     | 183300/371472 [3:43:03<14:56:11,  3.50it/s]
                                                            
{'loss': 2.8675, 'learning_rate': 5.561475144907237e-07, 'epoch': 7.9}
+
 49%|████▉     | 183300/371472 [3:43:03<14:56:11,  3.50it/s]
 49%|████▉     | 183301/371472 [3:43:03<14:58:42,  3.49it/s]
 49%|████▉     | 183302/371472 [3:43:04<16:20:07,  3.20it/s]
 49%|████▉     | 183303/371472 [3:43:04<15:50:30,  3.30it/s]
 49%|████▉     | 183304/371472 [3:43:04<15:40:06,  3.34it/s]
 49%|████▉     | 183305/371472 [3:43:05<15:56:54,  3.28it/s]
 49%|████▉     | 183306/371472 [3:43:05<15:33:02,  3.36it/s]
 49%|████▉     | 183307/371472 [3:43:05<16:21:30,  3.20it/s]
 49%|████▉     | 183308/371472 [3:43:06<15:58:15,  3.27it/s]
 49%|████▉     | 183309/371472 [3:43:06<15:30:22,  3.37it/s]
 49%|████▉     | 183310/371472 [3:43:06<15:19:03,  3.41it/s]
 49%|████▉     | 183311/371472 [3:43:06<15:34:20,  3.36it/s]
 49%|████▉     | 183312/371472 [3:43:07<15:19:31,  3.41it/s]
 49%|████▉     | 183313/371472 [3:43:07<15:22:57,  3.40it/s]
 49%|████▉     | 183314/371472 [3:43:07<15:53:54,  3.29it/s]
 49%|████▉     | 183315/371472 [3:43:08<15:49:11,  3.30it/s]
 49%|████▉     | 183316/371472 [3:43:08<16:24:37,  3.18it/s]
 49%|████▉     | 183317/371472 [3:43:08<15:50:11,  3.30it/s]
 49%|████▉     | 183318/371472 [3:43:09<15:53:38,  3.29it/s]
 49%|████▉     | 183319/371472 [3:43:09<15:32:02,  3.36it/s]
 49%|████▉     | 183320/371472 [3:43:09<15:29:14,  3.37it/s]
                                                            
{'loss': 2.8603, 'learning_rate': 5.560990325152448e-07, 'epoch': 7.9}
+
 49%|████▉     | 183320/371472 [3:43:09<15:29:14,  3.37it/s]
 49%|████▉     | 183321/371472 [3:43:09<15:21:59,  3.40it/s]
 49%|████▉     | 183322/371472 [3:43:10<15:51:10,  3.30it/s]
 49%|████▉     | 183323/371472 [3:43:10<15:42:55,  3.33it/s]
 49%|████▉     | 183324/371472 [3:43:10<15:38:23,  3.34it/s]
 49%|████▉     | 183325/371472 [3:43:11<15:46:01,  3.31it/s]
 49%|████▉     | 183326/371472 [3:43:11<16:48:45,  3.11it/s]
 49%|████▉     | 183327/371472 [3:43:11<16:34:21,  3.15it/s]
 49%|████▉     | 183328/371472 [3:43:12<16:23:02,  3.19it/s]
 49%|████▉     | 183329/371472 [3:43:12<15:56:04,  3.28it/s]
 49%|████▉     | 183330/371472 [3:43:12<15:35:34,  3.35it/s]
 49%|████▉     | 183331/371472 [3:43:13<15:23:36,  3.40it/s]
 49%|████▉     | 183332/371472 [3:43:13<15:04:12,  3.47it/s]
 49%|████▉     | 183333/371472 [3:43:13<15:04:19,  3.47it/s]
 49%|████▉     | 183334/371472 [3:43:13<15:12:09,  3.44it/s]
 49%|████▉     | 183335/371472 [3:43:14<15:37:24,  3.34it/s]
 49%|████▉     | 183336/371472 [3:43:14<16:27:25,  3.18it/s]
 49%|████▉     | 183337/371472 [3:43:14<16:40:16,  3.13it/s]
 49%|████▉     | 183338/371472 [3:43:15<16:33:48,  3.16it/s]
 49%|████▉     | 183339/371472 [3:43:15<16:07:00,  3.24it/s]
 49%|████▉     | 183340/371472 [3:43:15<15:33:00,  3.36it/s]
                                                            
{'loss': 2.8728, 'learning_rate': 5.56050550539766e-07, 'epoch': 7.9}
+
 49%|████▉     | 183340/371472 [3:43:15<15:33:00,  3.36it/s]
 49%|████▉     | 183341/371472 [3:43:16<15:59:39,  3.27it/s]
 49%|████▉     | 183342/371472 [3:43:16<15:37:28,  3.34it/s]
 49%|████▉     | 183343/371472 [3:43:16<15:20:48,  3.41it/s]
 49%|████▉     | 183344/371472 [3:43:16<15:29:46,  3.37it/s]
 49%|████▉     | 183345/371472 [3:43:17<15:32:44,  3.36it/s]
 49%|████▉     | 183346/371472 [3:43:17<15:47:17,  3.31it/s]
 49%|████▉     | 183347/371472 [3:43:17<17:22:40,  3.01it/s]
 49%|████▉     | 183348/371472 [3:43:18<16:58:15,  3.08it/s]
 49%|████▉     | 183349/371472 [3:43:18<16:36:56,  3.15it/s]
 49%|████▉     | 183350/371472 [3:43:18<16:19:20,  3.20it/s]
 49%|████▉     | 183351/371472 [3:43:19<16:06:00,  3.25it/s]
 49%|████▉     | 183352/371472 [3:43:19<16:03:56,  3.25it/s]
 49%|████▉     | 183353/371472 [3:43:19<16:04:36,  3.25it/s]
 49%|████▉     | 183354/371472 [3:43:20<15:26:49,  3.38it/s]
 49%|████▉     | 183355/371472 [3:43:20<15:56:30,  3.28it/s]
 49%|████▉     | 183356/371472 [3:43:20<15:44:37,  3.32it/s]
 49%|████▉     | 183357/371472 [3:43:20<15:27:56,  3.38it/s]
 49%|████▉     | 183358/371472 [3:43:21<16:10:15,  3.23it/s]
 49%|████▉     | 183359/371472 [3:43:21<16:04:03,  3.25it/s]
 49%|████▉     | 183360/371472 [3:43:21<16:20:59,  3.20it/s]
                                                            
{'loss': 2.7816, 'learning_rate': 5.560020685642871e-07, 'epoch': 7.9}
+
 49%|████▉     | 183360/371472 [3:43:21<16:20:59,  3.20it/s]
 49%|████▉     | 183361/371472 [3:43:22<17:13:59,  3.03it/s]
 49%|████▉     | 183362/371472 [3:43:22<17:25:30,  3.00it/s]
 49%|████▉     | 183363/371472 [3:43:22<16:41:28,  3.13it/s]
 49%|████▉     | 183364/371472 [3:43:23<16:18:36,  3.20it/s]
 49%|████▉     | 183365/371472 [3:43:23<15:57:49,  3.27it/s]
 49%|████▉     | 183366/371472 [3:43:23<16:37:47,  3.14it/s]
 49%|████▉     | 183367/371472 [3:43:24<17:31:32,  2.98it/s]
 49%|████▉     | 183368/371472 [3:43:24<17:20:23,  3.01it/s]
 49%|████▉     | 183369/371472 [3:43:24<17:39:18,  2.96it/s]
 49%|████▉     | 183370/371472 [3:43:25<16:56:56,  3.08it/s]
 49%|████▉     | 183371/371472 [3:43:25<16:30:51,  3.16it/s]
 49%|████▉     | 183372/371472 [3:43:25<15:44:20,  3.32it/s]
 49%|████▉     | 183373/371472 [3:43:26<16:17:39,  3.21it/s]
 49%|████▉     | 183374/371472 [3:43:26<16:26:06,  3.18it/s]
 49%|████▉     | 183375/371472 [3:43:26<16:31:28,  3.16it/s]
 49%|████▉     | 183376/371472 [3:43:27<15:55:35,  3.28it/s]
 49%|████▉     | 183377/371472 [3:43:27<15:53:34,  3.29it/s]
 49%|████▉     | 183378/371472 [3:43:27<16:36:51,  3.14it/s]
 49%|████▉     | 183379/371472 [3:43:28<16:51:59,  3.10it/s]
 49%|████▉     | 183380/371472 [3:43:28<16:55:59,  3.09it/s]
                                                            
{'loss': 2.8735, 'learning_rate': 5.559535865888081e-07, 'epoch': 7.9}
+
 49%|████▉     | 183380/371472 [3:43:28<16:55:59,  3.09it/s]
 49%|████▉     | 183381/371472 [3:43:28<17:10:16,  3.04it/s]
 49%|████▉     | 183382/371472 [3:43:29<17:46:10,  2.94it/s]
 49%|████▉     | 183383/371472 [3:43:29<17:33:39,  2.98it/s]
 49%|████▉     | 183384/371472 [3:43:29<17:05:03,  3.06it/s]
 49%|████▉     | 183385/371472 [3:43:29<16:23:23,  3.19it/s]
 49%|████▉     | 183386/371472 [3:43:30<16:00:25,  3.26it/s]
 49%|████▉     | 183387/371472 [3:43:30<16:31:13,  3.16it/s]
 49%|████▉     | 183388/371472 [3:43:30<16:31:36,  3.16it/s]
 49%|████▉     | 183389/371472 [3:43:31<16:09:14,  3.23it/s]
 49%|████▉     | 183390/371472 [3:43:31<16:28:23,  3.17it/s]
 49%|████▉     | 183391/371472 [3:43:31<16:13:52,  3.22it/s]
 49%|████▉     | 183392/371472 [3:43:32<16:03:52,  3.25it/s]
 49%|████▉     | 183393/371472 [3:43:32<16:10:20,  3.23it/s]
 49%|████▉     | 183394/371472 [3:43:32<16:24:07,  3.19it/s]
 49%|████▉     | 183395/371472 [3:43:33<16:07:55,  3.24it/s]
 49%|████▉     | 183396/371472 [3:43:33<15:51:51,  3.29it/s]
 49%|████▉     | 183397/371472 [3:43:33<15:42:58,  3.32it/s]
 49%|████▉     | 183398/371472 [3:43:33<15:52:13,  3.29it/s]
 49%|████▉     | 183399/371472 [3:43:34<15:40:33,  3.33it/s]
 49%|████▉     | 183400/371472 [3:43:34<15:28:52,  3.37it/s]
                                                            
{'loss': 2.8137, 'learning_rate': 5.559051046133293e-07, 'epoch': 7.9}
+
 49%|████▉     | 183400/371472 [3:43:34<15:28:52,  3.37it/s]
 49%|████▉     | 183401/371472 [3:43:34<15:39:09,  3.34it/s]
 49%|████▉     | 183402/371472 [3:43:35<17:07:02,  3.05it/s]
 49%|████▉     | 183403/371472 [3:43:35<16:31:28,  3.16it/s]
 49%|████▉     | 183404/371472 [3:43:35<15:57:28,  3.27it/s]
 49%|████▉     | 183405/371472 [3:43:36<16:05:06,  3.25it/s]
 49%|████▉     | 183406/371472 [3:43:36<16:06:20,  3.24it/s]
 49%|████▉     | 183407/371472 [3:43:36<18:00:54,  2.90it/s]
 49%|████▉     | 183408/371472 [3:43:37<17:05:27,  3.06it/s]
 49%|████▉     | 183409/371472 [3:43:37<16:30:25,  3.16it/s]
 49%|████▉     | 183410/371472 [3:43:37<16:13:20,  3.22it/s]
 49%|████▉     | 183411/371472 [3:43:38<16:05:57,  3.24it/s]
 49%|████▉     | 183412/371472 [3:43:38<15:57:26,  3.27it/s]
 49%|████▉     | 183413/371472 [3:43:38<17:26:03,  3.00it/s]
 49%|████▉     | 183414/371472 [3:43:39<17:33:11,  2.98it/s]
 49%|████▉     | 183415/371472 [3:43:39<18:39:37,  2.80it/s]
 49%|████▉     | 183416/371472 [3:43:39<17:40:30,  2.96it/s]
 49%|████▉     | 183417/371472 [3:43:40<17:13:47,  3.03it/s]
 49%|████▉     | 183418/371472 [3:43:40<16:31:23,  3.16it/s]
 49%|████▉     | 183419/371472 [3:43:40<16:19:24,  3.20it/s]
 49%|████▉     | 183420/371472 [3:43:40<16:11:52,  3.22it/s]
                                                            
{'loss': 2.9221, 'learning_rate': 5.558566226378505e-07, 'epoch': 7.9}
+
 49%|████▉     | 183420/371472 [3:43:40<16:11:52,  3.22it/s]
 49%|████▉     | 183421/371472 [3:43:41<16:25:34,  3.18it/s]
 49%|████▉     | 183422/371472 [3:43:41<16:53:09,  3.09it/s]
 49%|████▉     | 183423/371472 [3:43:41<16:38:39,  3.14it/s]
 49%|████▉     | 183424/371472 [3:43:42<16:32:23,  3.16it/s]
 49%|████▉     | 183425/371472 [3:43:42<16:30:05,  3.17it/s]
 49%|████▉     | 183426/371472 [3:43:42<17:24:24,  3.00it/s]
 49%|████▉     | 183427/371472 [3:43:43<17:42:11,  2.95it/s]
 49%|████▉     | 183428/371472 [3:43:43<16:51:57,  3.10it/s]
 49%|████▉     | 183429/371472 [3:43:43<16:29:40,  3.17it/s]
 49%|████▉     | 183430/371472 [3:43:44<16:17:28,  3.21it/s]
 49%|████▉     | 183431/371472 [3:43:44<15:53:13,  3.29it/s]
 49%|████▉     | 183432/371472 [3:43:44<16:39:08,  3.14it/s]
 49%|████▉     | 183433/371472 [3:43:45<16:15:01,  3.21it/s]
 49%|████▉     | 183434/371472 [3:43:45<15:43:42,  3.32it/s]
 49%|████▉     | 183435/371472 [3:43:45<15:27:24,  3.38it/s]
 49%|████▉     | 183436/371472 [3:43:46<16:00:46,  3.26it/s]
 49%|████▉     | 183437/371472 [3:43:46<15:42:37,  3.32it/s]
 49%|████▉     | 183438/371472 [3:43:46<15:40:30,  3.33it/s]
 49%|████▉     | 183439/371472 [3:43:46<16:32:17,  3.16it/s]
 49%|████▉     | 183440/371472 [3:43:47<17:20:00,  3.01it/s]
                                                            
{'loss': 2.7331, 'learning_rate': 5.558081406623714e-07, 'epoch': 7.9}
+
 49%|████▉     | 183440/371472 [3:43:47<17:20:00,  3.01it/s]
 49%|████▉     | 183441/371472 [3:43:47<17:05:09,  3.06it/s]
 49%|████▉     | 183442/371472 [3:43:47<16:57:02,  3.08it/s]
 49%|████▉     | 183443/371472 [3:43:48<16:41:19,  3.13it/s]
 49%|████▉     | 183444/371472 [3:43:48<16:29:07,  3.17it/s]
 49%|████▉     | 183445/371472 [3:43:48<16:12:00,  3.22it/s]
 49%|████▉     | 183446/371472 [3:43:49<16:19:47,  3.20it/s]
 49%|████▉     | 183447/371472 [3:43:49<16:39:56,  3.13it/s]
 49%|████▉     | 183448/371472 [3:43:49<15:55:26,  3.28it/s]
 49%|████▉     | 183449/371472 [3:43:50<15:32:09,  3.36it/s]
 49%|████▉     | 183450/371472 [3:43:50<15:10:44,  3.44it/s]
 49%|████▉     | 183451/371472 [3:43:50<15:04:19,  3.47it/s]
 49%|████▉     | 183452/371472 [3:43:50<15:00:58,  3.48it/s]
 49%|████▉     | 183453/371472 [3:43:51<14:58:05,  3.49it/s]
 49%|████▉     | 183454/371472 [3:43:51<15:19:00,  3.41it/s]
 49%|████▉     | 183455/371472 [3:43:51<15:48:05,  3.31it/s]
 49%|████▉     | 183456/371472 [3:43:52<16:25:52,  3.18it/s]
 49%|████▉     | 183457/371472 [3:43:52<16:42:20,  3.13it/s]
 49%|████▉     | 183458/371472 [3:43:52<17:49:11,  2.93it/s]
 49%|████▉     | 183459/371472 [3:43:53<17:13:44,  3.03it/s]
 49%|████▉     | 183460/371472 [3:43:53<16:49:21,  3.10it/s]
                                                            
{'loss': 2.9545, 'learning_rate': 5.557596586868925e-07, 'epoch': 7.9}
+
 49%|████▉     | 183460/371472 [3:43:53<16:49:21,  3.10it/s]
 49%|████▉     | 183461/371472 [3:43:53<16:11:56,  3.22it/s]
 49%|████▉     | 183462/371472 [3:43:54<15:55:54,  3.28it/s]
 49%|████▉     | 183463/371472 [3:43:54<15:52:44,  3.29it/s]
 49%|████▉     | 183464/371472 [3:43:54<15:40:35,  3.33it/s]
 49%|████▉     | 183465/371472 [3:43:54<15:18:15,  3.41it/s]
 49%|████▉     | 183466/371472 [3:43:55<15:42:22,  3.33it/s]
 49%|████▉     | 183467/371472 [3:43:55<15:36:35,  3.35it/s]
 49%|████▉     | 183468/371472 [3:43:55<15:32:55,  3.36it/s]
 49%|████▉     | 183469/371472 [3:43:56<15:13:11,  3.43it/s]
 49%|████▉     | 183470/371472 [3:43:56<15:59:45,  3.26it/s]
 49%|████▉     | 183471/371472 [3:43:56<15:37:42,  3.34it/s]
 49%|████▉     | 183472/371472 [3:43:57<17:16:00,  3.02it/s]
 49%|████▉     | 183473/371472 [3:43:57<16:52:53,  3.09it/s]
 49%|████▉     | 183474/371472 [3:43:57<16:55:52,  3.08it/s]
 49%|████▉     | 183475/371472 [3:43:58<16:33:01,  3.16it/s]
 49%|████▉     | 183476/371472 [3:43:58<16:36:37,  3.14it/s]
 49%|████▉     | 183477/371472 [3:43:58<16:18:50,  3.20it/s]
 49%|████▉     | 183478/371472 [3:43:59<16:16:14,  3.21it/s]
 49%|████▉     | 183479/371472 [3:43:59<15:59:41,  3.26it/s]
 49%|████▉     | 183480/371472 [3:43:59<15:32:27,  3.36it/s]
                                                            
{'loss': 3.0222, 'learning_rate': 5.557111767114138e-07, 'epoch': 7.9}
+
 49%|████▉     | 183480/371472 [3:43:59<15:32:27,  3.36it/s]
 49%|████▉     | 183481/371472 [3:43:59<15:18:55,  3.41it/s]
 49%|████▉     | 183482/371472 [3:44:00<15:25:05,  3.39it/s]
 49%|████▉     | 183483/371472 [3:44:00<15:27:36,  3.38it/s]
 49%|████▉     | 183484/371472 [3:44:00<16:31:20,  3.16it/s]
 49%|████▉     | 183485/371472 [3:44:01<16:36:46,  3.14it/s]
 49%|████▉     | 183486/371472 [3:44:01<16:11:49,  3.22it/s]
 49%|████▉     | 183487/371472 [3:44:01<15:39:17,  3.34it/s]
 49%|████▉     | 183488/371472 [3:44:02<15:21:28,  3.40it/s]
 49%|████▉     | 183489/371472 [3:44:02<15:23:41,  3.39it/s]
 49%|████▉     | 183490/371472 [3:44:02<15:40:22,  3.33it/s]
 49%|████▉     | 183491/371472 [3:44:02<15:45:12,  3.31it/s]
 49%|████▉     | 183492/371472 [3:44:03<15:21:02,  3.40it/s]
 49%|████▉     | 183493/371472 [3:44:03<15:05:40,  3.46it/s]
 49%|████▉     | 183494/371472 [3:44:03<15:06:13,  3.46it/s]
 49%|████▉     | 183495/371472 [3:44:04<15:33:51,  3.35it/s]
 49%|████▉     | 183496/371472 [3:44:04<15:39:23,  3.34it/s]
 49%|████▉     | 183497/371472 [3:44:04<15:28:51,  3.37it/s]
 49%|████▉     | 183498/371472 [3:44:04<15:24:14,  3.39it/s]
 49%|████▉     | 183499/371472 [3:44:05<15:14:21,  3.43it/s]
 49%|████▉     | 183500/371472 [3:44:05<15:12:24,  3.43it/s]
                                                            
{'loss': 2.8649, 'learning_rate': 5.556626947359349e-07, 'epoch': 7.9}
+
 49%|████▉     | 183500/371472 [3:44:05<15:12:24,  3.43it/s]
 49%|████▉     | 183501/371472 [3:44:05<15:11:25,  3.44it/s]
 49%|████▉     | 183502/371472 [3:44:06<15:21:05,  3.40it/s]
 49%|████▉     | 183503/371472 [3:44:06<14:49:19,  3.52it/s]
 49%|████▉     | 183504/371472 [3:44:06<15:55:49,  3.28it/s]
 49%|████▉     | 183505/371472 [3:44:07<15:42:19,  3.32it/s]
 49%|████▉     | 183506/371472 [3:44:07<16:39:17,  3.13it/s]
 49%|████▉     | 183507/371472 [3:44:07<16:15:49,  3.21it/s]
 49%|████▉     | 183508/371472 [3:44:08<16:41:54,  3.13it/s]
 49%|████▉     | 183509/371472 [3:44:08<16:22:26,  3.19it/s]
 49%|████▉     | 183510/371472 [3:44:08<15:51:50,  3.29it/s]
 49%|████▉     | 183511/371472 [3:44:08<15:34:24,  3.35it/s]
 49%|████▉     | 183512/371472 [3:44:09<15:41:23,  3.33it/s]
 49%|████▉     | 183513/371472 [3:44:09<15:50:02,  3.30it/s]
 49%|████▉     | 183514/371472 [3:44:09<15:25:11,  3.39it/s]
 49%|████▉     | 183515/371472 [3:44:10<16:17:45,  3.20it/s]
 49%|████▉     | 183516/371472 [3:44:10<15:48:43,  3.30it/s]
 49%|████▉     | 183517/371472 [3:44:10<15:33:12,  3.36it/s]
 49%|████▉     | 183518/371472 [3:44:11<15:12:57,  3.43it/s]
 49%|████▉     | 183519/371472 [3:44:11<14:56:21,  3.49it/s]
 49%|████▉     | 183520/371472 [3:44:11<15:04:20,  3.46it/s]
                                                            
{'loss': 2.9137, 'learning_rate': 5.556142127604559e-07, 'epoch': 7.9}
+
 49%|████▉     | 183520/371472 [3:44:11<15:04:20,  3.46it/s]
 49%|████▉     | 183521/371472 [3:44:11<14:54:51,  3.50it/s]
 49%|████▉     | 183522/371472 [3:44:12<14:42:18,  3.55it/s]
 49%|████▉     | 183523/371472 [3:44:12<14:26:54,  3.61it/s]
 49%|████▉     | 183524/371472 [3:44:12<14:26:13,  3.62it/s]
 49%|████▉     | 183525/371472 [3:44:12<14:46:31,  3.53it/s]
 49%|████▉     | 183526/371472 [3:44:13<15:01:36,  3.47it/s]
 49%|████▉     | 183527/371472 [3:44:13<14:56:50,  3.49it/s]
 49%|████▉     | 183528/371472 [3:44:13<14:48:25,  3.53it/s]
 49%|████▉     | 183529/371472 [3:44:14<14:53:33,  3.51it/s]
 49%|████▉     | 183530/371472 [3:44:14<14:39:58,  3.56it/s]
 49%|████▉     | 183531/371472 [3:44:14<15:24:32,  3.39it/s]
 49%|████▉     | 183532/371472 [3:44:15<15:32:09,  3.36it/s]
 49%|████▉     | 183533/371472 [3:44:15<15:22:44,  3.39it/s]
 49%|████▉     | 183534/371472 [3:44:15<16:43:00,  3.12it/s]
 49%|████▉     | 183535/371472 [3:44:15<15:59:32,  3.26it/s]
 49%|████▉     | 183536/371472 [3:44:16<15:40:30,  3.33it/s]
 49%|████▉     | 183537/371472 [3:44:16<15:27:11,  3.38it/s]
 49%|████▉     | 183538/371472 [3:44:16<15:23:39,  3.39it/s]
 49%|████▉     | 183539/371472 [3:44:17<15:57:40,  3.27it/s]
 49%|████▉     | 183540/371472 [3:44:17<16:03:30,  3.25it/s]
                                                            
{'loss': 2.9703, 'learning_rate': 5.55565730784977e-07, 'epoch': 7.91}
+
 49%|████▉     | 183540/371472 [3:44:17<16:03:30,  3.25it/s]
 49%|████▉     | 183541/371472 [3:44:17<15:31:27,  3.36it/s]
 49%|████▉     | 183542/371472 [3:44:18<15:42:22,  3.32it/s]
 49%|████▉     | 183543/371472 [3:44:18<15:57:45,  3.27it/s]
 49%|████▉     | 183544/371472 [3:44:18<15:40:26,  3.33it/s]
 49%|████▉     | 183545/371472 [3:44:18<15:24:55,  3.39it/s]
 49%|████▉     | 183546/371472 [3:44:19<15:11:47,  3.44it/s]
 49%|████▉     | 183547/371472 [3:44:19<15:13:39,  3.43it/s]
 49%|████▉     | 183548/371472 [3:44:19<15:14:58,  3.42it/s]
 49%|████▉     | 183549/371472 [3:44:20<15:10:21,  3.44it/s]
 49%|████▉     | 183550/371472 [3:44:20<14:41:36,  3.55it/s]
 49%|████▉     | 183551/371472 [3:44:20<15:35:19,  3.35it/s]
 49%|████▉     | 183552/371472 [3:44:20<15:16:05,  3.42it/s]
 49%|████▉     | 183553/371472 [3:44:21<15:20:00,  3.40it/s]
 49%|████▉     | 183554/371472 [3:44:21<15:20:17,  3.40it/s]
 49%|████▉     | 183555/371472 [3:44:21<15:25:08,  3.39it/s]
 49%|████▉     | 183556/371472 [3:44:22<15:46:40,  3.31it/s]
 49%|████▉     | 183557/371472 [3:44:22<16:28:08,  3.17it/s]
 49%|████▉     | 183558/371472 [3:44:22<16:13:17,  3.22it/s]
 49%|████▉     | 183559/371472 [3:44:23<15:28:22,  3.37it/s]
 49%|████▉     | 183560/371472 [3:44:23<15:48:21,  3.30it/s]
                                                            
{'loss': 2.9942, 'learning_rate': 5.555172488094982e-07, 'epoch': 7.91}
+
 49%|████▉     | 183560/371472 [3:44:23<15:48:21,  3.30it/s]
 49%|████▉     | 183561/371472 [3:44:23<16:08:03,  3.24it/s]
 49%|████▉     | 183562/371472 [3:44:24<15:56:15,  3.28it/s]
 49%|████▉     | 183563/371472 [3:44:24<15:49:30,  3.30it/s]
 49%|████▉     | 183564/371472 [3:44:24<15:29:02,  3.37it/s]
 49%|████▉     | 183565/371472 [3:44:24<14:58:55,  3.48it/s]
 49%|████▉     | 183566/371472 [3:44:25<14:46:11,  3.53it/s]
 49%|████▉     | 183567/371472 [3:44:25<15:00:37,  3.48it/s]
 49%|████▉     | 183568/371472 [3:44:25<15:43:59,  3.32it/s]
 49%|████▉     | 183569/371472 [3:44:26<15:21:25,  3.40it/s]
 49%|████▉     | 183570/371472 [3:44:26<15:32:36,  3.36it/s]
 49%|████▉     | 183571/371472 [3:44:26<16:42:33,  3.12it/s]
 49%|████▉     | 183572/371472 [3:44:27<17:26:11,  2.99it/s]
 49%|████▉     | 183573/371472 [3:44:27<18:17:06,  2.85it/s]
 49%|████▉     | 183574/371472 [3:44:27<18:38:54,  2.80it/s]
 49%|████▉     | 183575/371472 [3:44:28<18:06:26,  2.88it/s]
 49%|████▉     | 183576/371472 [3:44:28<17:06:57,  3.05it/s]
 49%|████▉     | 183577/371472 [3:44:28<16:35:21,  3.15it/s]
 49%|████▉     | 183578/371472 [3:44:29<16:13:34,  3.22it/s]
 49%|████▉     | 183579/371472 [3:44:29<15:32:29,  3.36it/s]
 49%|████▉     | 183580/371472 [3:44:29<15:37:48,  3.34it/s]
                                                            
{'loss': 2.9615, 'learning_rate': 5.554687668340194e-07, 'epoch': 7.91}
+
 49%|████▉     | 183580/371472 [3:44:29<15:37:48,  3.34it/s]
 49%|████▉     | 183581/371472 [3:44:29<15:44:38,  3.32it/s]
 49%|████▉     | 183582/371472 [3:44:30<16:07:02,  3.24it/s]
 49%|████▉     | 183583/371472 [3:44:30<15:50:20,  3.30it/s]
 49%|████▉     | 183584/371472 [3:44:30<15:48:39,  3.30it/s]
 49%|████▉     | 183585/371472 [3:44:31<15:28:20,  3.37it/s]
 49%|████▉     | 183586/371472 [3:44:31<15:20:50,  3.40it/s]
 49%|████▉     | 183587/371472 [3:44:31<16:28:35,  3.17it/s]
 49%|████▉     | 183588/371472 [3:44:32<15:42:06,  3.32it/s]
 49%|████▉     | 183589/371472 [3:44:32<15:54:00,  3.28it/s]
 49%|████▉     | 183590/371472 [3:44:32<15:14:42,  3.42it/s]
 49%|████▉     | 183591/371472 [3:44:32<16:12:36,  3.22it/s]
 49%|████▉     | 183592/371472 [3:44:33<15:50:39,  3.29it/s]
 49%|████▉     | 183593/371472 [3:44:33<15:34:50,  3.35it/s]
 49%|████▉     | 183594/371472 [3:44:33<15:29:25,  3.37it/s]
 49%|████▉     | 183595/371472 [3:44:34<15:36:15,  3.34it/s]
 49%|████▉     | 183596/371472 [3:44:34<15:20:59,  3.40it/s]
 49%|████▉     | 183597/371472 [3:44:34<15:39:00,  3.33it/s]
 49%|████▉     | 183598/371472 [3:44:35<15:35:27,  3.35it/s]
 49%|████▉     | 183599/371472 [3:44:35<15:15:21,  3.42it/s]
 49%|████▉     | 183600/371472 [3:44:35<15:21:27,  3.40it/s]
                                                            
{'loss': 2.9507, 'learning_rate': 5.554202848585404e-07, 'epoch': 7.91}
+
 49%|████▉     | 183600/371472 [3:44:35<15:21:27,  3.40it/s]
 49%|████▉     | 183601/371472 [3:44:35<16:08:57,  3.23it/s]
 49%|████▉     | 183602/371472 [3:44:36<15:36:56,  3.34it/s]
 49%|████▉     | 183603/371472 [3:44:36<15:33:53,  3.35it/s]
 49%|████▉     | 183604/371472 [3:44:36<15:35:48,  3.35it/s]
 49%|████▉     | 183605/371472 [3:44:37<15:23:33,  3.39it/s]
 49%|████▉     | 183606/371472 [3:44:37<15:40:34,  3.33it/s]
 49%|████▉     | 183607/371472 [3:44:37<15:24:05,  3.39it/s]
 49%|████▉     | 183608/371472 [3:44:38<16:01:05,  3.26it/s]
 49%|████▉     | 183609/371472 [3:44:38<15:40:19,  3.33it/s]
 49%|████▉     | 183610/371472 [3:44:38<15:23:36,  3.39it/s]
 49%|████▉     | 183611/371472 [3:44:38<15:42:25,  3.32it/s]
 49%|████▉     | 183612/371472 [3:44:39<15:05:59,  3.46it/s]
 49%|████▉     | 183613/371472 [3:44:39<15:09:59,  3.44it/s]
 49%|████▉     | 183614/371472 [3:44:39<15:37:04,  3.34it/s]
 49%|████▉     | 183615/371472 [3:44:40<15:42:27,  3.32it/s]
 49%|████▉     | 183616/371472 [3:44:40<16:13:56,  3.21it/s]
 49%|████▉     | 183617/371472 [3:44:40<15:58:51,  3.27it/s]
 49%|████▉     | 183618/371472 [3:44:41<16:37:43,  3.14it/s]
 49%|████▉     | 183619/371472 [3:44:41<16:06:36,  3.24it/s]
 49%|████▉     | 183620/371472 [3:44:41<16:05:38,  3.24it/s]
                                                            
{'loss': 2.7534, 'learning_rate': 5.553718028830615e-07, 'epoch': 7.91}
+
 49%|████▉     | 183620/371472 [3:44:41<16:05:38,  3.24it/s]
 49%|████▉     | 183621/371472 [3:44:41<16:04:37,  3.25it/s]
 49%|████▉     | 183622/371472 [3:44:42<15:51:16,  3.29it/s]
 49%|████▉     | 183623/371472 [3:44:42<15:44:49,  3.31it/s]
 49%|████▉     | 183624/371472 [3:44:42<15:43:30,  3.32it/s]
 49%|████▉     | 183625/371472 [3:44:43<15:16:03,  3.42it/s]
 49%|████▉     | 183626/371472 [3:44:43<14:46:28,  3.53it/s]
 49%|████▉     | 183627/371472 [3:44:43<15:07:48,  3.45it/s]
 49%|████▉     | 183628/371472 [3:44:43<14:52:34,  3.51it/s]
 49%|████▉     | 183629/371472 [3:44:44<14:45:13,  3.54it/s]
 49%|████▉     | 183630/371472 [3:44:44<16:52:10,  3.09it/s]
 49%|████▉     | 183631/371472 [3:44:44<16:15:37,  3.21it/s]
 49%|████▉     | 183632/371472 [3:44:45<16:05:25,  3.24it/s]
 49%|████▉     | 183633/371472 [3:44:45<15:42:00,  3.32it/s]
 49%|████▉     | 183634/371472 [3:44:45<15:24:47,  3.39it/s]
 49%|████▉     | 183635/371472 [3:44:46<15:10:20,  3.44it/s]
 49%|████▉     | 183636/371472 [3:44:46<18:14:34,  2.86it/s]
 49%|████▉     | 183637/371472 [3:44:46<17:18:28,  3.01it/s]
 49%|████▉     | 183638/371472 [3:44:47<17:53:06,  2.92it/s]
 49%|████▉     | 183639/371472 [3:44:47<16:54:05,  3.09it/s]
 49%|████▉     | 183640/371472 [3:44:47<16:38:47,  3.13it/s]
                                                            
{'loss': 2.9526, 'learning_rate': 5.553233209075826e-07, 'epoch': 7.91}
+
 49%|████▉     | 183640/371472 [3:44:47<16:38:47,  3.13it/s]
 49%|████▉     | 183641/371472 [3:44:48<16:23:53,  3.18it/s]
 49%|████▉     | 183642/371472 [3:44:48<16:08:34,  3.23it/s]
 49%|████▉     | 183643/371472 [3:44:48<15:40:32,  3.33it/s]
 49%|████▉     | 183644/371472 [3:44:49<15:45:28,  3.31it/s]
 49%|████▉     | 183645/371472 [3:44:49<15:28:18,  3.37it/s]
 49%|████▉     | 183646/371472 [3:44:49<15:15:34,  3.42it/s]
 49%|████▉     | 183647/371472 [3:44:49<15:08:16,  3.45it/s]
 49%|████▉     | 183648/371472 [3:44:50<15:20:04,  3.40it/s]
 49%|████▉     | 183649/371472 [3:44:50<15:29:35,  3.37it/s]
 49%|████▉     | 183650/371472 [3:44:50<16:12:09,  3.22it/s]
 49%|████▉     | 183651/371472 [3:44:51<15:21:36,  3.40it/s]
 49%|████▉     | 183652/371472 [3:44:51<15:42:12,  3.32it/s]
 49%|████▉     | 183653/371472 [3:44:51<15:27:04,  3.38it/s]
 49%|████▉     | 183654/371472 [3:44:52<16:15:26,  3.21it/s]
 49%|████▉     | 183655/371472 [3:44:52<16:05:33,  3.24it/s]
 49%|████▉     | 183656/371472 [3:44:52<15:41:13,  3.33it/s]
 49%|████▉     | 183657/371472 [3:44:52<15:18:25,  3.41it/s]
 49%|████▉     | 183658/371472 [3:44:53<15:47:07,  3.30it/s]
 49%|████▉     | 183659/371472 [3:44:53<15:45:07,  3.31it/s]
 49%|████▉     | 183660/371472 [3:44:53<15:40:51,  3.33it/s]
                                                            
{'loss': 2.932, 'learning_rate': 5.552748389321035e-07, 'epoch': 7.91}
+
 49%|████▉     | 183660/371472 [3:44:53<15:40:51,  3.33it/s]
 49%|████▉     | 183661/371472 [3:44:54<15:51:53,  3.29it/s]
 49%|████▉     | 183662/371472 [3:44:54<16:01:16,  3.26it/s]
 49%|████▉     | 183663/371472 [3:44:54<16:07:04,  3.24it/s]
 49%|████▉     | 183664/371472 [3:44:55<15:32:50,  3.36it/s]
 49%|████▉     | 183665/371472 [3:44:55<15:20:43,  3.40it/s]
 49%|████▉     | 183666/371472 [3:44:55<15:08:14,  3.45it/s]
 49%|████▉     | 183667/371472 [3:44:55<15:22:19,  3.39it/s]
 49%|████▉     | 183668/371472 [3:44:56<15:20:26,  3.40it/s]
 49%|████▉     | 183669/371472 [3:44:56<15:19:29,  3.40it/s]
 49%|████▉     | 183670/371472 [3:44:56<16:06:32,  3.24it/s]
 49%|████▉     | 183671/371472 [3:44:57<16:32:40,  3.15it/s]
 49%|████▉     | 183672/371472 [3:44:57<16:01:47,  3.25it/s]
 49%|████▉     | 183673/371472 [3:44:57<16:14:08,  3.21it/s]
 49%|████▉     | 183674/371472 [3:44:58<16:53:04,  3.09it/s]
 49%|████▉     | 183675/371472 [3:44:58<18:15:08,  2.86it/s]
 49%|████▉     | 183676/371472 [3:44:58<18:55:03,  2.76it/s]
 49%|████▉     | 183677/371472 [3:44:59<19:09:57,  2.72it/s]
 49%|████▉     | 183678/371472 [3:44:59<18:50:24,  2.77it/s]
 49%|████▉     | 183679/371472 [3:44:59<17:35:38,  2.96it/s]
 49%|████▉     | 183680/371472 [3:45:00<16:43:56,  3.12it/s]
                                                            
{'loss': 2.7313, 'learning_rate': 5.552263569566247e-07, 'epoch': 7.91}
+
 49%|████▉     | 183680/371472 [3:45:00<16:43:56,  3.12it/s]
 49%|████▉     | 183681/371472 [3:45:00<16:38:21,  3.13it/s]
 49%|████▉     | 183682/371472 [3:45:00<16:09:02,  3.23it/s]
 49%|████▉     | 183683/371472 [3:45:01<16:00:52,  3.26it/s]
 49%|████▉     | 183684/371472 [3:45:01<15:44:03,  3.32it/s]
 49%|████▉     | 183685/371472 [3:45:01<15:17:55,  3.41it/s]
 49%|████▉     | 183686/371472 [3:45:01<15:18:56,  3.41it/s]
 49%|████▉     | 183687/371472 [3:45:02<15:49:05,  3.30it/s]
 49%|████▉     | 183688/371472 [3:45:02<15:49:49,  3.30it/s]
 49%|████▉     | 183689/371472 [3:45:02<15:57:30,  3.27it/s]
 49%|████▉     | 183690/371472 [3:45:03<15:41:25,  3.32it/s]
 49%|████▉     | 183691/371472 [3:45:03<22:17:36,  2.34it/s]
 49%|████▉     | 183692/371472 [3:45:04<20:21:09,  2.56it/s]
 49%|████▉     | 183693/371472 [3:45:04<19:01:32,  2.74it/s]
 49%|████▉     | 183694/371472 [3:45:04<18:01:37,  2.89it/s]
 49%|████▉     | 183695/371472 [3:45:05<17:02:01,  3.06it/s]
 49%|████▉     | 183696/371472 [3:45:05<18:40:02,  2.79it/s]
 49%|████▉     | 183697/371472 [3:45:05<18:22:19,  2.84it/s]
 49%|████▉     | 183698/371472 [3:45:06<17:31:35,  2.98it/s]
 49%|████▉     | 183699/371472 [3:45:06<16:53:08,  3.09it/s]
 49%|████▉     | 183700/371472 [3:45:06<16:21:08,  3.19it/s]
                                                            
{'loss': 2.9417, 'learning_rate': 5.551778749811458e-07, 'epoch': 7.91}
+
 49%|████▉     | 183700/371472 [3:45:06<16:21:08,  3.19it/s]
 49%|████▉     | 183701/371472 [3:45:07<15:36:41,  3.34it/s]
 49%|████▉     | 183702/371472 [3:45:07<15:19:15,  3.40it/s]
 49%|████▉     | 183703/371472 [3:45:07<15:33:49,  3.35it/s]
 49%|████▉     | 183704/371472 [3:45:07<15:12:54,  3.43it/s]
 49%|████▉     | 183705/371472 [3:45:08<15:27:30,  3.37it/s]
 49%|████▉     | 183706/371472 [3:45:08<15:25:36,  3.38it/s]
 49%|████▉     | 183707/371472 [3:45:08<15:39:59,  3.33it/s]
 49%|████▉     | 183708/371472 [3:45:09<15:27:24,  3.37it/s]
 49%|████▉     | 183709/371472 [3:45:09<15:51:15,  3.29it/s]
 49%|████▉     | 183710/371472 [3:45:09<15:30:46,  3.36it/s]
 49%|████▉     | 183711/371472 [3:45:10<15:43:31,  3.32it/s]
 49%|████▉     | 183712/371472 [3:45:10<15:20:12,  3.40it/s]
 49%|████▉     | 183713/371472 [3:45:10<15:18:26,  3.41it/s]
 49%|████▉     | 183714/371472 [3:45:10<15:31:23,  3.36it/s]
 49%|████▉     | 183715/371472 [3:45:11<15:17:14,  3.41it/s]
 49%|████▉     | 183716/371472 [3:45:11<15:16:59,  3.41it/s]
 49%|████▉     | 183717/371472 [3:45:11<14:58:48,  3.48it/s]
 49%|████▉     | 183718/371472 [3:45:12<15:07:51,  3.45it/s]
 49%|████▉     | 183719/371472 [3:45:12<16:27:27,  3.17it/s]
 49%|████▉     | 183720/371472 [3:45:12<15:54:21,  3.28it/s]
                                                            
{'loss': 2.6892, 'learning_rate': 5.551293930056671e-07, 'epoch': 7.91}
+
 49%|████▉     | 183720/371472 [3:45:12<15:54:21,  3.28it/s]
 49%|████▉     | 183721/371472 [3:45:13<16:22:14,  3.19it/s]
 49%|████▉     | 183722/371472 [3:45:13<16:30:02,  3.16it/s]
 49%|████▉     | 183723/371472 [3:45:13<15:56:34,  3.27it/s]
 49%|████▉     | 183724/371472 [3:45:13<15:13:51,  3.42it/s]
 49%|████▉     | 183725/371472 [3:45:14<15:07:47,  3.45it/s]
 49%|████▉     | 183726/371472 [3:45:14<15:54:15,  3.28it/s]
 49%|████▉     | 183727/371472 [3:45:14<15:42:23,  3.32it/s]
 49%|████▉     | 183728/371472 [3:45:15<15:21:25,  3.40it/s]
 49%|████▉     | 183729/371472 [3:45:15<15:18:32,  3.41it/s]
 49%|████▉     | 183730/371472 [3:45:15<15:19:01,  3.40it/s]
 49%|████▉     | 183731/371472 [3:45:15<15:16:43,  3.41it/s]
 49%|████▉     | 183732/371472 [3:45:16<18:06:27,  2.88it/s]
 49%|████▉     | 183733/371472 [3:45:16<17:38:00,  2.96it/s]
 49%|████▉     | 183734/371472 [3:45:17<16:47:21,  3.11it/s]
 49%|████▉     | 183735/371472 [3:45:17<17:11:22,  3.03it/s]
 49%|████▉     | 183736/371472 [3:45:17<17:10:36,  3.04it/s]
 49%|████▉     | 183737/371472 [3:45:18<16:53:37,  3.09it/s]
 49%|████▉     | 183738/371472 [3:45:18<16:14:03,  3.21it/s]
 49%|████▉     | 183739/371472 [3:45:18<17:21:43,  3.00it/s]
 49%|████▉     | 183740/371472 [3:45:18<16:40:02,  3.13it/s]
                                                            
{'loss': 2.9362, 'learning_rate': 5.550809110301881e-07, 'epoch': 7.91}
+
 49%|████▉     | 183740/371472 [3:45:18<16:40:02,  3.13it/s]
 49%|████▉     | 183741/371472 [3:45:19<16:01:30,  3.25it/s]
 49%|████▉     | 183742/371472 [3:45:19<15:54:13,  3.28it/s]
 49%|████▉     | 183743/371472 [3:45:19<16:03:20,  3.25it/s]
 49%|████▉     | 183744/371472 [3:45:20<15:36:30,  3.34it/s]
 49%|████▉     | 183745/371472 [3:45:20<15:23:43,  3.39it/s]
 49%|████▉     | 183746/371472 [3:45:20<14:51:47,  3.51it/s]
 49%|████▉     | 183747/371472 [3:45:21<15:28:06,  3.37it/s]
 49%|████▉     | 183748/371472 [3:45:21<15:04:00,  3.46it/s]
 49%|████▉     | 183749/371472 [3:45:21<15:36:11,  3.34it/s]
 49%|████▉     | 183750/371472 [3:45:21<16:14:50,  3.21it/s]
 49%|████▉     | 183751/371472 [3:45:22<16:01:27,  3.25it/s]
 49%|████▉     | 183752/371472 [3:45:22<16:20:34,  3.19it/s]
 49%|████▉     | 183753/371472 [3:45:22<15:28:13,  3.37it/s]
 49%|████▉     | 183754/371472 [3:45:23<15:20:28,  3.40it/s]
 49%|████▉     | 183755/371472 [3:45:23<15:43:59,  3.31it/s]
 49%|████▉     | 183756/371472 [3:45:23<15:58:50,  3.26it/s]
 49%|████▉     | 183757/371472 [3:45:24<15:36:19,  3.34it/s]
 49%|████▉     | 183758/371472 [3:45:24<16:18:50,  3.20it/s]
 49%|████▉     | 183759/371472 [3:45:24<15:40:27,  3.33it/s]
 49%|████▉     | 183760/371472 [3:45:24<15:28:55,  3.37it/s]
                                                            
{'loss': 2.8431, 'learning_rate': 5.550324290547093e-07, 'epoch': 7.91}
+
 49%|████▉     | 183760/371472 [3:45:24<15:28:55,  3.37it/s]
 49%|████▉     | 183761/371472 [3:45:25<15:22:33,  3.39it/s]
 49%|████▉     | 183762/371472 [3:45:25<15:28:41,  3.37it/s]
 49%|████▉     | 183763/371472 [3:45:25<15:04:01,  3.46it/s]
 49%|████▉     | 183764/371472 [3:45:26<15:06:10,  3.45it/s]
 49%|████▉     | 183765/371472 [3:45:26<15:07:46,  3.45it/s]
 49%|████▉     | 183766/371472 [3:45:26<14:48:26,  3.52it/s]
 49%|████▉     | 183767/371472 [3:45:26<14:33:52,  3.58it/s]
 49%|████▉     | 183768/371472 [3:45:27<14:55:41,  3.49it/s]
 49%|████▉     | 183769/371472 [3:45:27<14:52:58,  3.50it/s]
 49%|████▉     | 183770/371472 [3:45:27<15:28:49,  3.37it/s]
 49%|████▉     | 183771/371472 [3:45:28<15:14:08,  3.42it/s]
 49%|████▉     | 183772/371472 [3:45:28<15:17:25,  3.41it/s]
 49%|████▉     | 183773/371472 [3:45:28<15:47:10,  3.30it/s]
 49%|████▉     | 183774/371472 [3:45:29<15:49:14,  3.30it/s]
 49%|████▉     | 183775/371472 [3:45:29<15:14:59,  3.42it/s]
 49%|████▉     | 183776/371472 [3:45:29<15:59:55,  3.26it/s]
 49%|████▉     | 183777/371472 [3:45:30<16:47:04,  3.11it/s]
 49%|████▉     | 183778/371472 [3:45:30<16:48:08,  3.10it/s]
 49%|████▉     | 183779/371472 [3:45:30<16:38:16,  3.13it/s]
 49%|████▉     | 183780/371472 [3:45:30<16:11:36,  3.22it/s]
                                                            
{'loss': 2.9966, 'learning_rate': 5.549839470792303e-07, 'epoch': 7.92}
+
 49%|████▉     | 183780/371472 [3:45:30<16:11:36,  3.22it/s]
 49%|████▉     | 183781/371472 [3:45:31<16:34:07,  3.15it/s]
 49%|████▉     | 183782/371472 [3:45:31<16:04:04,  3.24it/s]
 49%|████▉     | 183783/371472 [3:45:31<15:42:50,  3.32it/s]
 49%|████▉     | 183784/371472 [3:45:32<15:34:52,  3.35it/s]
 49%|████▉     | 183785/371472 [3:45:32<15:20:40,  3.40it/s]
 49%|████▉     | 183786/371472 [3:45:32<16:09:32,  3.23it/s]
 49%|████▉     | 183787/371472 [3:45:33<16:58:21,  3.07it/s]
 49%|████▉     | 183788/371472 [3:45:33<16:51:12,  3.09it/s]
 49%|████▉     | 183789/371472 [3:45:33<16:32:27,  3.15it/s]
 49%|████▉     | 183790/371472 [3:45:34<16:19:07,  3.19it/s]
 49%|████▉     | 183791/371472 [3:45:34<16:30:40,  3.16it/s]
 49%|████▉     | 183792/371472 [3:45:34<16:53:13,  3.09it/s]
 49%|████▉     | 183793/371472 [3:45:35<16:15:04,  3.21it/s]
 49%|████▉     | 183794/371472 [3:45:35<16:58:21,  3.07it/s]
 49%|████▉     | 183795/371472 [3:45:35<17:02:57,  3.06it/s]
 49%|████▉     | 183796/371472 [3:45:36<16:44:07,  3.12it/s]
 49%|████▉     | 183797/371472 [3:45:36<16:08:37,  3.23it/s]
 49%|████▉     | 183798/371472 [3:45:36<15:53:53,  3.28it/s]
 49%|████▉     | 183799/371472 [3:45:36<17:00:59,  3.06it/s]
 49%|████▉     | 183800/371472 [3:45:37<16:29:41,  3.16it/s]
                                                            
{'loss': 2.7752, 'learning_rate': 5.549354651037515e-07, 'epoch': 7.92}
+
 49%|████▉     | 183800/371472 [3:45:37<16:29:41,  3.16it/s]
 49%|████▉     | 183801/371472 [3:45:37<16:23:12,  3.18it/s]
 49%|████▉     | 183802/371472 [3:45:37<16:17:04,  3.20it/s]
 49%|████▉     | 183803/371472 [3:45:38<16:12:02,  3.22it/s]
 49%|████▉     | 183804/371472 [3:45:38<15:54:51,  3.28it/s]
 49%|████▉     | 183805/371472 [3:45:38<15:34:03,  3.35it/s]
 49%|████▉     | 183806/371472 [3:45:39<15:13:02,  3.43it/s]
 49%|████▉     | 183807/371472 [3:45:39<15:02:46,  3.46it/s]
 49%|████▉     | 183808/371472 [3:45:39<15:21:29,  3.39it/s]
 49%|████▉     | 183809/371472 [3:45:39<15:13:27,  3.42it/s]
 49%|████▉     | 183810/371472 [3:45:40<15:34:29,  3.35it/s]
 49%|████▉     | 183811/371472 [3:45:40<15:39:00,  3.33it/s]
 49%|████▉     | 183812/371472 [3:45:40<15:34:24,  3.35it/s]
 49%|████▉     | 183813/371472 [3:45:41<15:32:04,  3.36it/s]
 49%|████▉     | 183814/371472 [3:45:41<16:02:52,  3.25it/s]
 49%|████▉     | 183815/371472 [3:45:41<15:57:56,  3.26it/s]
 49%|████▉     | 183816/371472 [3:45:42<16:05:05,  3.24it/s]
 49%|████▉     | 183817/371472 [3:45:42<18:17:13,  2.85it/s]
 49%|████▉     | 183818/371472 [3:45:42<17:17:04,  3.02it/s]
 49%|████▉     | 183819/371472 [3:45:43<17:03:27,  3.06it/s]
 49%|████▉     | 183820/371472 [3:45:43<16:34:01,  3.15it/s]
                                                            
{'loss': 3.0113, 'learning_rate': 5.548869831282724e-07, 'epoch': 7.92}
+
 49%|████▉     | 183820/371472 [3:45:43<16:34:01,  3.15it/s]
 49%|████▉     | 183821/371472 [3:45:43<16:36:00,  3.14it/s]
 49%|████▉     | 183822/371472 [3:45:44<16:44:18,  3.11it/s]
 49%|████▉     | 183823/371472 [3:45:44<16:17:47,  3.20it/s]
 49%|████▉     | 183824/371472 [3:45:44<16:28:59,  3.16it/s]
 49%|████▉     | 183825/371472 [3:45:44<15:50:54,  3.29it/s]
 49%|████▉     | 183826/371472 [3:45:45<15:13:38,  3.42it/s]
 49%|████▉     | 183827/371472 [3:45:45<14:50:26,  3.51it/s]
 49%|████▉     | 183828/371472 [3:45:45<15:00:52,  3.47it/s]
 49%|████▉     | 183829/371472 [3:45:46<15:05:10,  3.46it/s]
 49%|████▉     | 183830/371472 [3:45:46<15:01:24,  3.47it/s]
 49%|████▉     | 183831/371472 [3:45:46<14:40:11,  3.55it/s]
 49%|████▉     | 183832/371472 [3:45:46<14:41:47,  3.55it/s]
 49%|████▉     | 183833/371472 [3:45:47<14:45:58,  3.53it/s]
 49%|████▉     | 183834/371472 [3:45:47<16:00:56,  3.25it/s]
 49%|████▉     | 183835/371472 [3:45:47<16:53:27,  3.09it/s]
 49%|████▉     | 183836/371472 [3:45:48<16:30:23,  3.16it/s]
 49%|████▉     | 183837/371472 [3:45:48<16:59:43,  3.07it/s]
 49%|████▉     | 183838/371472 [3:45:48<16:29:05,  3.16it/s]
 49%|████▉     | 183839/371472 [3:45:49<16:04:48,  3.24it/s]
 49%|████▉     | 183840/371472 [3:45:49<15:52:39,  3.28it/s]
                                                            
{'loss': 2.8056, 'learning_rate': 5.548385011527935e-07, 'epoch': 7.92}
+
 49%|████▉     | 183840/371472 [3:45:49<15:52:39,  3.28it/s]
 49%|████▉     | 183841/371472 [3:45:49<16:13:34,  3.21it/s]
 49%|████▉     | 183842/371472 [3:45:50<15:52:40,  3.28it/s]
 49%|████▉     | 183843/371472 [3:45:50<15:58:21,  3.26it/s]
 49%|████▉     | 183844/371472 [3:45:50<15:34:41,  3.35it/s]
 49%|████▉     | 183845/371472 [3:45:50<15:34:42,  3.35it/s]
 49%|████▉     | 183846/371472 [3:45:51<15:14:59,  3.42it/s]
 49%|████▉     | 183847/371472 [3:45:51<15:21:49,  3.39it/s]
 49%|████▉     | 183848/371472 [3:45:51<16:11:37,  3.22it/s]
 49%|████▉     | 183849/371472 [3:45:52<16:19:12,  3.19it/s]
 49%|████▉     | 183850/371472 [3:45:52<16:30:44,  3.16it/s]
 49%|████▉     | 183851/371472 [3:45:52<15:52:42,  3.28it/s]
 49%|████▉     | 183852/371472 [3:45:53<15:53:31,  3.28it/s]
 49%|████▉     | 183853/371472 [3:45:53<15:42:56,  3.32it/s]
 49%|████▉     | 183854/371472 [3:45:53<16:13:41,  3.21it/s]
 49%|████▉     | 183855/371472 [3:45:54<15:47:44,  3.30it/s]
 49%|████▉     | 183856/371472 [3:45:54<16:15:21,  3.21it/s]
 49%|████▉     | 183857/371472 [3:45:54<15:35:21,  3.34it/s]
 49%|████▉     | 183858/371472 [3:45:54<15:14:10,  3.42it/s]
 49%|████▉     | 183859/371472 [3:45:55<15:33:06,  3.35it/s]
 49%|████▉     | 183860/371472 [3:45:55<15:09:05,  3.44it/s]
                                                            
{'loss': 2.8115, 'learning_rate': 5.547900191773148e-07, 'epoch': 7.92}
+
 49%|████▉     | 183860/371472 [3:45:55<15:09:05,  3.44it/s]
 49%|████▉     | 183861/371472 [3:45:55<15:35:24,  3.34it/s]
 49%|████▉     | 183862/371472 [3:45:56<15:25:19,  3.38it/s]
 49%|████▉     | 183863/371472 [3:45:56<17:38:15,  2.95it/s]
 49%|████▉     | 183864/371472 [3:45:56<16:45:18,  3.11it/s]
 49%|████▉     | 183865/371472 [3:45:57<16:24:38,  3.18it/s]
 49%|████▉     | 183866/371472 [3:45:57<16:07:05,  3.23it/s]
 49%|████▉     | 183867/371472 [3:45:57<15:37:24,  3.34it/s]
 49%|████▉     | 183868/371472 [3:45:58<15:54:56,  3.27it/s]
 49%|████▉     | 183869/371472 [3:45:58<15:46:53,  3.30it/s]
 49%|████▉     | 183870/371472 [3:45:58<15:23:26,  3.39it/s]
 49%|████▉     | 183871/371472 [3:45:58<15:36:36,  3.34it/s]
 49%|████▉     | 183872/371472 [3:45:59<15:50:44,  3.29it/s]
 49%|████▉     | 183873/371472 [3:45:59<15:33:37,  3.35it/s]
 49%|████▉     | 183874/371472 [3:45:59<15:16:21,  3.41it/s]
 49%|████▉     | 183875/371472 [3:46:00<15:05:12,  3.45it/s]
 49%|████▉     | 183876/371472 [3:46:00<15:04:51,  3.46it/s]
 49%|████▉     | 183877/371472 [3:46:00<15:12:54,  3.42it/s]
 49%|████▉     | 183878/371472 [3:46:00<15:24:38,  3.38it/s]
 50%|████▉     | 183879/371472 [3:46:01<15:03:21,  3.46it/s]
 50%|████▉     | 183880/371472 [3:46:01<15:29:11,  3.36it/s]
                                                            
{'loss': 2.9027, 'learning_rate': 5.547415372018358e-07, 'epoch': 7.92}
+
 50%|████▉     | 183880/371472 [3:46:01<15:29:11,  3.36it/s]
 50%|████▉     | 183881/371472 [3:46:01<16:02:31,  3.25it/s]
 50%|████▉     | 183882/371472 [3:46:02<15:40:29,  3.32it/s]
 50%|████▉     | 183883/371472 [3:46:02<16:04:44,  3.24it/s]
 50%|████▉     | 183884/371472 [3:46:02<16:02:04,  3.25it/s]
 50%|��███▉     | 183885/371472 [3:46:03<15:26:59,  3.37it/s]
 50%|████▉     | 183886/371472 [3:46:03<15:33:56,  3.35it/s]
 50%|████▉     | 183887/371472 [3:46:03<16:05:14,  3.24it/s]
 50%|████▉     | 183888/371472 [3:46:03<15:52:51,  3.28it/s]
 50%|████▉     | 183889/371472 [3:46:04<15:45:47,  3.31it/s]
 50%|████▉     | 183890/371472 [3:46:04<15:44:06,  3.31it/s]
 50%|████▉     | 183891/371472 [3:46:05<17:27:23,  2.98it/s]
 50%|████▉     | 183892/371472 [3:46:05<17:32:40,  2.97it/s]
 50%|████▉     | 183893/371472 [3:46:05<16:27:41,  3.17it/s]
 50%|████▉     | 183894/371472 [3:46:05<16:16:19,  3.20it/s]
 50%|████▉     | 183895/371472 [3:46:06<15:58:02,  3.26it/s]
 50%|████▉     | 183896/371472 [3:46:06<16:46:41,  3.11it/s]
 50%|████▉     | 183897/371472 [3:46:06<16:12:12,  3.22it/s]
 50%|████▉     | 183898/371472 [3:46:07<16:37:18,  3.13it/s]
 50%|████▉     | 183899/371472 [3:46:07<16:09:43,  3.22it/s]
 50%|████▉     | 183900/371472 [3:46:07<16:07:39,  3.23it/s]
                                                            
{'loss': 2.8213, 'learning_rate': 5.546930552263569e-07, 'epoch': 7.92}
+
 50%|████▉     | 183900/371472 [3:46:07<16:07:39,  3.23it/s]
 50%|████▉     | 183901/371472 [3:46:08<16:34:03,  3.14it/s]
 50%|████▉     | 183902/371472 [3:46:08<16:14:17,  3.21it/s]
 50%|████▉     | 183903/371472 [3:46:08<15:41:52,  3.32it/s]
 50%|████▉     | 183904/371472 [3:46:08<15:31:22,  3.36it/s]
 50%|████▉     | 183905/371472 [3:46:09<15:16:16,  3.41it/s]
 50%|████▉     | 183906/371472 [3:46:09<15:42:29,  3.32it/s]
 50%|████▉     | 183907/371472 [3:46:09<15:27:21,  3.37it/s]
 50%|████▉     | 183908/371472 [3:46:10<15:11:03,  3.43it/s]
 50%|████▉     | 183909/371472 [3:46:10<14:47:44,  3.52it/s]
 50%|████▉     | 183910/371472 [3:46:10<15:01:45,  3.47it/s]
 50%|████▉     | 183911/371472 [3:46:11<15:38:46,  3.33it/s]
 50%|████▉     | 183912/371472 [3:46:11<15:36:45,  3.34it/s]
 50%|████▉     | 183913/371472 [3:46:11<16:29:58,  3.16it/s]
 50%|████▉     | 183914/371472 [3:46:12<16:14:55,  3.21it/s]
 50%|████▉     | 183915/371472 [3:46:12<16:10:53,  3.22it/s]
 50%|████▉     | 183916/371472 [3:46:12<15:40:27,  3.32it/s]
 50%|████▉     | 183917/371472 [3:46:12<15:46:29,  3.30it/s]
 50%|████▉     | 183918/371472 [3:46:13<15:51:13,  3.29it/s]
 50%|████▉     | 183919/371472 [3:46:13<15:31:47,  3.35it/s]
 50%|████▉     | 183920/371472 [3:46:13<17:14:50,  3.02it/s]
                                                            
{'loss': 2.9637, 'learning_rate': 5.54644573250878e-07, 'epoch': 7.92}
+
 50%|████▉     | 183920/371472 [3:46:13<17:14:50,  3.02it/s]
 50%|████▉     | 183921/371472 [3:46:14<16:28:18,  3.16it/s]
 50%|████▉     | 183922/371472 [3:46:14<16:18:10,  3.20it/s]
 50%|████▉     | 183923/371472 [3:46:14<16:54:38,  3.08it/s]
 50%|████▉     | 183924/371472 [3:46:15<16:21:51,  3.18it/s]
 50%|████▉     | 183925/371472 [3:46:15<16:43:01,  3.12it/s]
 50%|████▉     | 183926/371472 [3:46:15<16:07:26,  3.23it/s]
 50%|████▉     | 183927/371472 [3:46:16<16:25:17,  3.17it/s]
 50%|████▉     | 183928/371472 [3:46:16<15:53:58,  3.28it/s]
 50%|████▉     | 183929/371472 [3:46:16<16:30:04,  3.16it/s]
 50%|████▉     | 183930/371472 [3:46:16<16:02:13,  3.25it/s]
 50%|████▉     | 183931/371472 [3:46:17<15:48:23,  3.30it/s]
 50%|████▉     | 183932/371472 [3:46:17<15:59:43,  3.26it/s]
 50%|████▉     | 183933/371472 [3:46:17<16:17:59,  3.20it/s]
 50%|████▉     | 183934/371472 [3:46:18<15:35:08,  3.34it/s]
 50%|████▉     | 183935/371472 [3:46:18<15:29:09,  3.36it/s]
 50%|████▉     | 183936/371472 [3:46:18<15:28:46,  3.37it/s]
 50%|████▉     | 183937/371472 [3:46:19<15:59:47,  3.26it/s]
 50%|████▉     | 183938/371472 [3:46:19<15:51:53,  3.28it/s]
 50%|████▉     | 183939/371472 [3:46:19<16:57:27,  3.07it/s]
 50%|████▉     | 183940/371472 [3:46:20<16:07:03,  3.23it/s]
                                                            
{'loss': 2.922, 'learning_rate': 5.545960912753992e-07, 'epoch': 7.92}
+
 50%|████▉     | 183940/371472 [3:46:20<16:07:03,  3.23it/s]
 50%|████▉     | 183941/371472 [3:46:20<15:51:56,  3.28it/s]
 50%|████▉     | 183942/371472 [3:46:20<15:22:28,  3.39it/s]
 50%|████▉     | 183943/371472 [3:46:20<16:16:11,  3.20it/s]
 50%|████▉     | 183944/371472 [3:46:21<16:25:35,  3.17it/s]
 50%|████▉     | 183945/371472 [3:46:21<15:56:26,  3.27it/s]
 50%|████▉     | 183946/371472 [3:46:21<15:48:20,  3.30it/s]
 50%|████▉     | 183947/371472 [3:46:22<16:04:25,  3.24it/s]
 50%|████▉     | 183948/371472 [3:46:22<15:49:41,  3.29it/s]
 50%|████▉     | 183949/371472 [3:46:22<16:36:07,  3.14it/s]
 50%|████▉     | 183950/371472 [3:46:23<15:49:58,  3.29it/s]
 50%|████▉     | 183951/371472 [3:46:23<15:27:36,  3.37it/s]
 50%|████▉     | 183952/371472 [3:46:23<15:22:12,  3.39it/s]
 50%|████▉     | 183953/371472 [3:46:23<15:11:59,  3.43it/s]
 50%|████▉     | 183954/371472 [3:46:24<15:19:30,  3.40it/s]
 50%|████▉     | 183955/371472 [3:46:24<15:02:08,  3.46it/s]
 50%|████▉     | 183956/371472 [3:46:24<14:57:27,  3.48it/s]
 50%|████▉     | 183957/371472 [3:46:25<14:52:55,  3.50it/s]
 50%|████▉     | 183958/371472 [3:46:25<15:34:36,  3.34it/s]
 50%|████▉     | 183959/371472 [3:46:25<15:24:43,  3.38it/s]
 50%|████▉     | 183960/371472 [3:46:26<16:16:15,  3.20it/s]
                                                            
{'loss': 2.9792, 'learning_rate': 5.545476092999203e-07, 'epoch': 7.92}
+
 50%|████▉     | 183960/371472 [3:46:26<16:16:15,  3.20it/s]
 50%|████▉     | 183961/371472 [3:46:26<16:02:23,  3.25it/s]
 50%|████▉     | 183962/371472 [3:46:26<15:31:11,  3.36it/s]
 50%|████▉     | 183963/371472 [3:46:27<16:38:37,  3.13it/s]
 50%|████▉     | 183964/371472 [3:46:27<15:53:09,  3.28it/s]
 50%|████▉     | 183965/371472 [3:46:27<15:40:58,  3.32it/s]
 50%|████▉     | 183966/371472 [3:46:27<15:31:43,  3.35it/s]
 50%|████▉     | 183967/371472 [3:46:28<15:56:45,  3.27it/s]
 50%|████▉     | 183968/371472 [3:46:28<16:10:29,  3.22it/s]
 50%|████▉     | 183969/371472 [3:46:28<15:42:32,  3.32it/s]
 50%|████▉     | 183970/371472 [3:46:29<16:03:32,  3.24it/s]
 50%|████▉     | 183971/371472 [3:46:29<15:46:26,  3.30it/s]
 50%|████▉     | 183972/371472 [3:46:29<15:49:24,  3.29it/s]
 50%|████▉     | 183973/371472 [3:46:30<15:38:46,  3.33it/s]
 50%|████▉     | 183974/371472 [3:46:30<15:16:57,  3.41it/s]
 50%|████▉     | 183975/371472 [3:46:30<14:58:51,  3.48it/s]
 50%|████▉     | 183976/371472 [3:46:30<15:20:15,  3.40it/s]
 50%|████▉     | 183977/371472 [3:46:31<15:04:26,  3.46it/s]
 50%|████▉     | 183978/371472 [3:46:31<14:55:27,  3.49it/s]
 50%|████▉     | 183979/371472 [3:46:31<15:13:23,  3.42it/s]
 50%|████▉     | 183980/371472 [3:46:32<15:34:24,  3.34it/s]
                                                            
{'loss': 3.0949, 'learning_rate': 5.544991273244414e-07, 'epoch': 7.92}
+
 50%|████▉     | 183980/371472 [3:46:32<15:34:24,  3.34it/s]
 50%|████▉     | 183981/371472 [3:46:32<15:15:45,  3.41it/s]
 50%|████▉     | 183982/371472 [3:46:32<15:08:55,  3.44it/s]
 50%|████▉     | 183983/371472 [3:46:32<15:40:40,  3.32it/s]
 50%|████▉     | 183984/371472 [3:46:33<16:06:29,  3.23it/s]
 50%|████▉     | 183985/371472 [3:46:33<16:16:09,  3.20it/s]
 50%|████▉     | 183986/371472 [3:46:33<16:02:45,  3.25it/s]
 50%|████▉     | 183987/371472 [3:46:34<15:54:03,  3.28it/s]
 50%|████▉     | 183988/371472 [3:46:34<18:56:46,  2.75it/s]
 50%|████▉     | 183989/371472 [3:46:34<17:40:48,  2.95it/s]
 50%|████▉     | 183990/371472 [3:46:35<16:52:31,  3.09it/s]
 50%|████▉     | 183991/371472 [3:46:35<16:03:23,  3.24it/s]
 50%|████▉     | 183992/371472 [3:46:35<16:11:10,  3.22it/s]
 50%|████▉     | 183993/371472 [3:46:36<16:21:52,  3.18it/s]
 50%|████▉     | 183994/371472 [3:46:36<16:33:43,  3.14it/s]
 50%|████▉     | 183995/371472 [3:46:36<15:58:23,  3.26it/s]
 50%|████▉     | 183996/371472 [3:46:37<16:30:05,  3.16it/s]
 50%|████▉     | 183997/371472 [3:46:37<15:49:14,  3.29it/s]
 50%|████▉     | 183998/371472 [3:46:37<15:50:24,  3.29it/s]
 50%|████▉     | 183999/371472 [3:46:38<16:17:23,  3.20it/s]
 50%|████▉     | 184000/371472 [3:46:38<16:06:06,  3.23it/s]
                                                            
{'loss': 2.807, 'learning_rate': 5.544506453489625e-07, 'epoch': 7.93}
+
 50%|████▉     | 184000/371472 [3:46:38<16:06:06,  3.23it/s]
 50%|████▉     | 184001/371472 [3:46:38<16:31:17,  3.15it/s]
 50%|████▉     | 184002/371472 [3:46:38<16:08:14,  3.23it/s]
 50%|████▉     | 184003/371472 [3:46:39<16:22:46,  3.18it/s]
 50%|████▉     | 184004/371472 [3:46:39<15:53:52,  3.28it/s]
 50%|████▉     | 184005/371472 [3:46:39<15:42:20,  3.32it/s]
 50%|████▉     | 184006/371472 [3:46:40<15:37:45,  3.33it/s]
 50%|████▉     | 184007/371472 [3:46:40<15:24:32,  3.38it/s]
 50%|████▉     | 184008/371472 [3:46:40<16:00:00,  3.25it/s]
 50%|████▉     | 184009/371472 [3:46:41<15:56:51,  3.27it/s]
 50%|████▉     | 184010/371472 [3:46:41<16:01:06,  3.25it/s]
 50%|████▉     | 184011/371472 [3:46:41<16:31:24,  3.15it/s]
 50%|████▉     | 184012/371472 [3:46:42<15:48:32,  3.29it/s]
 50%|████▉     | 184013/371472 [3:46:42<15:24:28,  3.38it/s]
 50%|████▉     | 184014/371472 [3:46:42<15:22:36,  3.39it/s]
 50%|████▉     | 184015/371472 [3:46:42<15:36:17,  3.34it/s]
 50%|████▉     | 184016/371472 [3:46:43<16:04:53,  3.24it/s]
 50%|████▉     | 184017/371472 [3:46:43<15:48:04,  3.30it/s]
 50%|████▉     | 184018/371472 [3:46:43<15:43:25,  3.31it/s]
 50%|████▉     | 184019/371472 [3:46:44<16:08:56,  3.22it/s]
 50%|████▉     | 184020/371472 [3:46:44<16:38:35,  3.13it/s]
                                                            
{'loss': 2.9191, 'learning_rate': 5.544021633734836e-07, 'epoch': 7.93}
+
 50%|████▉     | 184020/371472 [3:46:44<16:38:35,  3.13it/s]
 50%|████▉     | 184021/371472 [3:46:44<18:27:45,  2.82it/s]
 50%|████▉     | 184022/371472 [3:46:45<17:35:00,  2.96it/s]
 50%|████▉     | 184023/371472 [3:46:45<16:50:10,  3.09it/s]
 50%|████▉     | 184024/371472 [3:46:45<16:55:33,  3.08it/s]
 50%|████▉     | 184025/371472 [3:46:46<17:27:31,  2.98it/s]
 50%|████▉     | 184026/371472 [3:46:46<16:49:08,  3.10it/s]
 50%|████▉     | 184027/371472 [3:46:46<16:15:33,  3.20it/s]
 50%|████▉     | 184028/371472 [3:46:47<15:40:28,  3.32it/s]
 50%|████▉     | 184029/371472 [3:46:47<15:51:57,  3.28it/s]
 50%|████▉     | 184030/371472 [3:46:47<15:32:47,  3.35it/s]
 50%|████▉     | 184031/371472 [3:46:47<15:53:44,  3.28it/s]
 50%|████▉     | 184032/371472 [3:46:48<15:49:52,  3.29it/s]
 50%|████▉     | 184033/371472 [3:46:48<15:25:34,  3.38it/s]
 50%|████▉     | 184034/371472 [3:46:48<14:53:51,  3.49it/s]
 50%|████▉     | 184035/371472 [3:46:49<15:09:58,  3.43it/s]
 50%|████▉     | 184036/371472 [3:46:49<16:55:06,  3.08it/s]
 50%|████▉     | 184037/371472 [3:46:49<16:08:30,  3.23it/s]
 50%|████▉     | 184038/371472 [3:46:50<15:35:44,  3.34it/s]
 50%|████▉     | 184039/371472 [3:46:50<16:14:28,  3.21it/s]
 50%|████▉     | 184040/371472 [3:46:50<16:06:44,  3.23it/s]
                                                            
{'loss': 2.865, 'learning_rate': 5.543536813980047e-07, 'epoch': 7.93}
+
 50%|████▉     | 184040/371472 [3:46:50<16:06:44,  3.23it/s]
 50%|████▉     | 184041/371472 [3:46:51<17:17:39,  3.01it/s]
 50%|████▉     | 184042/371472 [3:46:51<16:23:39,  3.18it/s]
 50%|████▉     | 184043/371472 [3:46:51<16:14:52,  3.20it/s]
 50%|████▉     | 184044/371472 [3:46:52<16:55:16,  3.08it/s]
 50%|████▉     | 184045/371472 [3:46:52<16:41:35,  3.12it/s]
 50%|████▉     | 184046/371472 [3:46:52<16:07:36,  3.23it/s]
 50%|████▉     | 184047/371472 [3:46:52<16:03:55,  3.24it/s]
 50%|████▉     | 184048/371472 [3:46:53<16:03:14,  3.24it/s]
 50%|████▉     | 184049/371472 [3:46:53<15:56:03,  3.27it/s]
 50%|████▉     | 184050/371472 [3:46:53<15:34:15,  3.34it/s]
 50%|████▉     | 184051/371472 [3:46:54<15:26:41,  3.37it/s]
 50%|████▉     | 184052/371472 [3:46:54<15:08:18,  3.44it/s]
 50%|████▉     | 184053/371472 [3:46:54<14:46:15,  3.52it/s]
 50%|████▉     | 184054/371472 [3:46:54<15:03:17,  3.46it/s]
 50%|████▉     | 184055/371472 [3:46:55<16:30:35,  3.15it/s]
 50%|████▉     | 184056/371472 [3:46:55<16:04:43,  3.24it/s]
 50%|████▉     | 184057/371472 [3:46:55<15:51:12,  3.28it/s]
 50%|████▉     | 184058/371472 [3:46:56<15:58:57,  3.26it/s]
 50%|████▉     | 184059/371472 [3:46:56<15:41:17,  3.32it/s]
 50%|████▉     | 184060/371472 [3:46:56<15:52:25,  3.28it/s]
                                                            
{'loss': 2.9347, 'learning_rate': 5.543051994225258e-07, 'epoch': 7.93}
+
 50%|████▉     | 184060/371472 [3:46:56<15:52:25,  3.28it/s]
 50%|████▉     | 184061/371472 [3:46:57<15:28:13,  3.37it/s]
 50%|████▉     | 184062/371472 [3:46:57<15:25:38,  3.37it/s]
 50%|████▉     | 184063/371472 [3:46:57<16:42:41,  3.12it/s]
 50%|████▉     | 184064/371472 [3:46:58<16:45:06,  3.11it/s]
 50%|████▉     | 184065/371472 [3:46:58<15:51:09,  3.28it/s]
 50%|████▉     | 184066/371472 [3:46:58<15:41:35,  3.32it/s]
 50%|████▉     | 184067/371472 [3:46:58<15:16:49,  3.41it/s]
 50%|████▉     | 184068/371472 [3:46:59<15:26:13,  3.37it/s]
 50%|████▉     | 184069/371472 [3:46:59<15:17:00,  3.41it/s]
 50%|████▉     | 184070/371472 [3:46:59<15:23:05,  3.38it/s]
 50%|████▉     | 184071/371472 [3:47:00<15:24:23,  3.38it/s]
 50%|████▉     | 184072/371472 [3:47:00<15:31:26,  3.35it/s]
 50%|████▉     | 184073/371472 [3:47:00<15:13:22,  3.42it/s]
 50%|████▉     | 184074/371472 [3:47:00<15:06:51,  3.44it/s]
 50%|████▉     | 184075/371472 [3:47:01<15:09:10,  3.44it/s]
 50%|████▉     | 184076/371472 [3:47:01<16:26:17,  3.17it/s]
 50%|████▉     | 184077/371472 [3:47:01<15:50:18,  3.29it/s]
 50%|████▉     | 184078/371472 [3:47:02<16:02:50,  3.24it/s]
 50%|████▉     | 184079/371472 [3:47:02<15:50:50,  3.28it/s]
 50%|████▉     | 184080/371472 [3:47:02<16:19:23,  3.19it/s]
                                                            
{'loss': 2.9221, 'learning_rate': 5.542567174470469e-07, 'epoch': 7.93}
+
 50%|████▉     | 184080/371472 [3:47:02<16:19:23,  3.19it/s]
 50%|████▉     | 184081/371472 [3:47:03<15:38:08,  3.33it/s]
 50%|████▉     | 184082/371472 [3:47:03<15:56:02,  3.27it/s]
 50%|████▉     | 184083/371472 [3:47:03<15:50:40,  3.29it/s]
 50%|████▉     | 184084/371472 [3:47:04<15:46:56,  3.30it/s]
 50%|████▉     | 184085/371472 [3:47:04<16:18:25,  3.19it/s]
 50%|████▉     | 184086/371472 [3:47:04<15:58:22,  3.26it/s]
 50%|████▉     | 184087/371472 [3:47:05<16:04:43,  3.24it/s]
 50%|████▉     | 184088/371472 [3:47:05<16:06:53,  3.23it/s]
 50%|████▉     | 184089/371472 [3:47:05<15:40:42,  3.32it/s]
 50%|████▉     | 184090/371472 [3:47:05<15:24:05,  3.38it/s]
 50%|████▉     | 184091/371472 [3:47:06<15:58:11,  3.26it/s]
 50%|████▉     | 184092/371472 [3:47:06<15:24:59,  3.38it/s]
 50%|████▉     | 184093/371472 [3:47:06<15:56:37,  3.26it/s]
 50%|████▉     | 184094/371472 [3:47:07<16:42:38,  3.11it/s]
 50%|████▉     | 184095/371472 [3:47:07<16:42:32,  3.12it/s]
 50%|████▉     | 184096/371472 [3:47:07<17:19:32,  3.00it/s]
 50%|████▉     | 184097/371472 [3:47:08<16:56:39,  3.07it/s]
 50%|████▉     | 184098/371472 [3:47:08<16:56:00,  3.07it/s]
 50%|████▉     | 184099/371472 [3:47:08<16:37:28,  3.13it/s]
 50%|████▉     | 184100/371472 [3:47:09<16:39:40,  3.12it/s]
                                                            
{'loss': 2.8588, 'learning_rate': 5.542082354715681e-07, 'epoch': 7.93}
+
 50%|████▉     | 184100/371472 [3:47:09<16:39:40,  3.12it/s]
 50%|████▉     | 184101/371472 [3:47:09<16:28:02,  3.16it/s]
 50%|████▉     | 184102/371472 [3:47:09<16:32:58,  3.14it/s]
 50%|████▉     | 184103/371472 [3:47:10<16:15:21,  3.20it/s]
 50%|████▉     | 184104/371472 [3:47:10<15:43:49,  3.31it/s]
 50%|████▉     | 184105/371472 [3:47:10<15:34:28,  3.34it/s]
 50%|████▉     | 184106/371472 [3:47:10<15:33:05,  3.35it/s]
 50%|████▉     | 184107/371472 [3:47:11<16:22:58,  3.18it/s]
 50%|████▉     | 184108/371472 [3:47:11<15:59:49,  3.25it/s]
 50%|████▉     | 184109/371472 [3:47:11<15:46:02,  3.30it/s]
 50%|████▉     | 184110/371472 [3:47:12<15:44:46,  3.31it/s]
 50%|████▉     | 184111/371472 [3:47:12<15:21:03,  3.39it/s]
 50%|████▉     | 184112/371472 [3:47:12<15:08:20,  3.44it/s]
 50%|████▉     | 184113/371472 [3:47:13<14:59:36,  3.47it/s]
 50%|████▉     | 184114/371472 [3:47:13<15:02:07,  3.46it/s]
 50%|████▉     | 184115/371472 [3:47:13<15:03:16,  3.46it/s]
 50%|████▉     | 184116/371472 [3:47:13<14:55:17,  3.49it/s]
 50%|████▉     | 184117/371472 [3:47:14<14:36:47,  3.56it/s]
 50%|████▉     | 184118/371472 [3:47:14<14:50:05,  3.51it/s]
 50%|████▉     | 184119/371472 [3:47:14<15:06:36,  3.44it/s]
 50%|████▉     | 184120/371472 [3:47:15<14:55:34,  3.49it/s]
                                                            
{'loss': 3.0246, 'learning_rate': 5.541597534960891e-07, 'epoch': 7.93}
+
 50%|████▉     | 184120/371472 [3:47:15<14:55:34,  3.49it/s]
 50%|████▉     | 184121/371472 [3:47:15<15:09:19,  3.43it/s]
 50%|████▉     | 184122/371472 [3:47:15<16:25:25,  3.17it/s]
 50%|████▉     | 184123/371472 [3:47:15<15:53:35,  3.27it/s]
 50%|████▉     | 184124/371472 [3:47:16<15:41:40,  3.32it/s]
 50%|████▉     | 184125/371472 [3:47:16<15:23:09,  3.38it/s]
 50%|████▉     | 184126/371472 [3:47:16<15:24:41,  3.38it/s]
 50%|████▉     | 184127/371472 [3:47:17<15:23:09,  3.38it/s]
 50%|████▉     | 184128/371472 [3:47:17<15:19:47,  3.39it/s]
 50%|████▉     | 184129/371472 [3:47:17<16:20:46,  3.18it/s]
 50%|████▉     | 184130/371472 [3:47:18<16:58:26,  3.07it/s]
 50%|████▉     | 184131/371472 [3:47:18<18:06:34,  2.87it/s]
 50%|████▉     | 184132/371472 [3:47:18<17:32:05,  2.97it/s]
 50%|████▉     | 184133/371472 [3:47:19<16:48:45,  3.10it/s]
 50%|████▉     | 184134/371472 [3:47:19<16:18:46,  3.19it/s]
 50%|████▉     | 184135/371472 [3:47:19<16:00:28,  3.25it/s]
 50%|████▉     | 184136/371472 [3:47:20<15:33:40,  3.34it/s]
 50%|████▉     | 184137/371472 [3:47:20<15:40:05,  3.32it/s]
 50%|████▉     | 184138/371472 [3:47:20<15:43:24,  3.31it/s]
 50%|████▉     | 184139/371472 [3:47:20<15:55:15,  3.27it/s]
 50%|████▉     | 184140/371472 [3:47:21<15:28:19,  3.36it/s]
                                                            
{'loss': 2.8957, 'learning_rate': 5.541112715206102e-07, 'epoch': 7.93}
+
 50%|████▉     | 184140/371472 [3:47:21<15:28:19,  3.36it/s]
 50%|████▉     | 184141/371472 [3:47:21<15:31:38,  3.35it/s]
 50%|████▉     | 184142/371472 [3:47:21<15:11:28,  3.43it/s]
 50%|████▉     | 184143/371472 [3:47:22<15:03:33,  3.46it/s]
 50%|████▉     | 184144/371472 [3:47:22<15:35:17,  3.34it/s]
 50%|████▉     | 184145/371472 [3:47:22<16:33:43,  3.14it/s]
 50%|████▉     | 184146/371472 [3:47:23<16:08:24,  3.22it/s]
 50%|████▉     | 184147/371472 [3:47:23<16:12:35,  3.21it/s]
 50%|████▉     | 184148/371472 [3:47:23<16:45:11,  3.11it/s]
 50%|████▉     | 184149/371472 [3:47:23<16:15:36,  3.20it/s]
 50%|████▉     | 184150/371472 [3:47:24<15:58:15,  3.26it/s]
 50%|████▉     | 184151/371472 [3:47:24<15:53:16,  3.28it/s]
 50%|████▉     | 184152/371472 [3:47:24<15:43:08,  3.31it/s]
 50%|████▉     | 184153/371472 [3:47:25<15:47:42,  3.29it/s]
 50%|████▉     | 184154/371472 [3:47:25<15:32:50,  3.35it/s]
 50%|████▉     | 184155/371472 [3:47:25<15:43:24,  3.31it/s]
 50%|████▉     | 184156/371472 [3:47:26<15:20:47,  3.39it/s]
 50%|████▉     | 184157/371472 [3:47:26<16:39:44,  3.12it/s]
 50%|████▉     | 184158/371472 [3:47:26<16:11:07,  3.21it/s]
 50%|████▉     | 184159/371472 [3:47:27<15:50:43,  3.28it/s]
 50%|████▉     | 184160/371472 [3:47:27<15:35:28,  3.34it/s]
                                                            
{'loss': 2.9124, 'learning_rate': 5.540627895451313e-07, 'epoch': 7.93}
+
 50%|████▉     | 184160/371472 [3:47:27<15:35:28,  3.34it/s]
 50%|████▉     | 184161/371472 [3:47:27<16:10:53,  3.22it/s]
 50%|████▉     | 184162/371472 [3:47:27<15:56:43,  3.26it/s]
 50%|████▉     | 184163/371472 [3:47:28<15:58:45,  3.26it/s]
 50%|████▉     | 184164/371472 [3:47:28<16:16:23,  3.20it/s]
 50%|████▉     | 184165/371472 [3:47:28<15:42:51,  3.31it/s]
 50%|████▉     | 184166/371472 [3:47:29<15:38:16,  3.33it/s]
 50%|████▉     | 184167/371472 [3:47:29<15:17:23,  3.40it/s]
 50%|████▉     | 184168/371472 [3:47:29<15:19:19,  3.40it/s]
 50%|████▉     | 184169/371472 [3:47:30<15:42:33,  3.31it/s]
 50%|████▉     | 184170/371472 [3:47:30<15:49:55,  3.29it/s]
 50%|████▉     | 184171/371472 [3:47:30<15:36:16,  3.33it/s]
 50%|████▉     | 184172/371472 [3:47:30<15:21:38,  3.39it/s]
 50%|████▉     | 184173/371472 [3:47:31<15:15:50,  3.41it/s]
 50%|████▉     | 184174/371472 [3:47:31<15:49:58,  3.29it/s]
 50%|████▉     | 184175/371472 [3:47:31<16:05:43,  3.23it/s]
 50%|████▉     | 184176/371472 [3:47:32<15:34:10,  3.34it/s]
 50%|████▉     | 184177/371472 [3:47:32<15:46:15,  3.30it/s]
 50%|████▉     | 184178/371472 [3:47:32<15:39:56,  3.32it/s]
 50%|████▉     | 184179/371472 [3:47:33<15:39:20,  3.32it/s]
 50%|████▉     | 184180/371472 [3:47:33<15:46:06,  3.30it/s]
                                                            
{'loss': 2.7781, 'learning_rate': 5.540143075696523e-07, 'epoch': 7.93}
+
 50%|████▉     | 184180/371472 [3:47:33<15:46:06,  3.30it/s]
 50%|████▉     | 184181/371472 [3:47:33<15:38:50,  3.32it/s]
 50%|████▉     | 184182/371472 [3:47:33<15:27:42,  3.36it/s]
 50%|████▉     | 184183/371472 [3:47:34<15:53:10,  3.27it/s]
 50%|████▉     | 184184/371472 [3:47:34<15:40:52,  3.32it/s]
 50%|████▉     | 184185/371472 [3:47:34<15:53:44,  3.27it/s]
 50%|████▉     | 184186/371472 [3:47:35<15:26:05,  3.37it/s]
 50%|████▉     | 184187/371472 [3:47:35<15:41:07,  3.32it/s]
 50%|████▉     | 184188/371472 [3:47:35<15:43:46,  3.31it/s]
 50%|████▉     | 184189/371472 [3:47:36<15:36:12,  3.33it/s]
 50%|████▉     | 184190/371472 [3:47:36<15:29:15,  3.36it/s]
 50%|████▉     | 184191/371472 [3:47:36<15:13:27,  3.42it/s]
 50%|████▉     | 184192/371472 [3:47:36<15:08:46,  3.43it/s]
 50%|████▉     | 184193/371472 [3:47:37<14:45:22,  3.53it/s]
 50%|████▉     | 184194/371472 [3:47:37<15:15:04,  3.41it/s]
 50%|████▉     | 184195/371472 [3:47:37<15:22:20,  3.38it/s]
 50%|████▉     | 184196/371472 [3:47:38<16:21:33,  3.18it/s]
 50%|████▉     | 184197/371472 [3:47:38<16:11:20,  3.21it/s]
 50%|████▉     | 184198/371472 [3:47:38<15:39:32,  3.32it/s]
 50%|████▉     | 184199/371472 [3:47:39<15:52:08,  3.28it/s]
 50%|████▉     | 184200/371472 [3:47:39<16:12:33,  3.21it/s]
                                                            
{'loss': 3.0612, 'learning_rate': 5.539658255941735e-07, 'epoch': 7.93}
+
 50%|████▉     | 184200/371472 [3:47:39<16:12:33,  3.21it/s]
 50%|████▉     | 184201/371472 [3:47:39<15:46:54,  3.30it/s]
 50%|████▉     | 184202/371472 [3:47:39<15:54:07,  3.27it/s]
 50%|████▉     | 184203/371472 [3:47:40<16:10:27,  3.22it/s]
 50%|████▉     | 184204/371472 [3:47:40<15:52:00,  3.28it/s]
 50%|████▉     | 184205/371472 [3:47:40<16:02:14,  3.24it/s]
 50%|████▉     | 184206/371472 [3:47:41<15:45:05,  3.30it/s]
 50%|████▉     | 184207/371472 [3:47:41<15:39:33,  3.32it/s]
 50%|████▉     | 184208/371472 [3:47:41<15:25:39,  3.37it/s]
 50%|████▉     | 184209/371472 [3:47:42<16:32:38,  3.14it/s]
 50%|████▉     | 184210/371472 [3:47:42<15:51:56,  3.28it/s]
 50%|████▉     | 184211/371472 [3:47:42<15:51:10,  3.28it/s]
 50%|████▉     | 184212/371472 [3:47:43<15:23:29,  3.38it/s]
 50%|████▉     | 184213/371472 [3:47:43<15:34:05,  3.34it/s]
 50%|████▉     | 184214/371472 [3:47:43<16:19:46,  3.19it/s]
 50%|████▉     | 184215/371472 [3:47:43<15:48:59,  3.29it/s]
 50%|████▉     | 184216/371472 [3:47:44<15:45:06,  3.30it/s]
 50%|████▉     | 184217/371472 [3:47:44<15:33:01,  3.34it/s]
 50%|████▉     | 184218/371472 [3:47:44<15:12:18,  3.42it/s]
 50%|████▉     | 184219/371472 [3:47:45<15:20:39,  3.39it/s]
 50%|████▉     | 184220/371472 [3:47:45<15:18:44,  3.40it/s]
                                                            
{'loss': 3.0434, 'learning_rate': 5.539173436186945e-07, 'epoch': 7.93}
+
 50%|████▉     | 184220/371472 [3:47:45<15:18:44,  3.40it/s]
 50%|████▉     | 184221/371472 [3:47:45<15:14:03,  3.41it/s]
 50%|████▉     | 184222/371472 [3:47:46<15:31:46,  3.35it/s]
 50%|████▉     | 184223/371472 [3:47:46<15:29:39,  3.36it/s]
 50%|████▉     | 184224/371472 [3:47:46<15:53:21,  3.27it/s]
 50%|████▉     | 184225/371472 [3:47:46<15:58:10,  3.26it/s]
 50%|████▉     | 184226/371472 [3:47:47<16:22:13,  3.18it/s]
 50%|████▉     | 184227/371472 [3:47:47<15:52:05,  3.28it/s]
 50%|████▉     | 184228/371472 [3:47:47<15:59:11,  3.25it/s]
 50%|████▉     | 184229/371472 [3:47:48<15:47:01,  3.30it/s]
 50%|████▉     | 184230/371472 [3:47:48<15:25:10,  3.37it/s]
 50%|████▉     | 184231/371472 [3:47:48<15:08:04,  3.44it/s]
 50%|████▉     | 184232/371472 [3:47:49<17:29:49,  2.97it/s]
 50%|████▉     | 184233/371472 [3:47:49<16:48:27,  3.09it/s]
 50%|████▉     | 184234/371472 [3:47:49<16:20:27,  3.18it/s]
 50%|████▉     | 184235/371472 [3:47:50<15:50:58,  3.28it/s]
 50%|████▉     | 184236/371472 [3:47:50<16:32:54,  3.14it/s]
 50%|████▉     | 184237/371472 [3:47:50<15:51:32,  3.28it/s]
 50%|████▉     | 184238/371472 [3:47:50<15:22:09,  3.38it/s]
 50%|████▉     | 184239/371472 [3:47:51<15:13:29,  3.42it/s]
 50%|████▉     | 184240/371472 [3:47:51<15:29:07,  3.36it/s]
                                                            
{'loss': 2.9978, 'learning_rate': 5.538688616432158e-07, 'epoch': 7.94}
+
 50%|████▉     | 184240/371472 [3:47:51<15:29:07,  3.36it/s]
 50%|████▉     | 184241/371472 [3:47:51<15:26:14,  3.37it/s]
 50%|████▉     | 184242/371472 [3:47:52<15:21:27,  3.39it/s]
 50%|████▉     | 184243/371472 [3:47:52<14:55:24,  3.48it/s]
 50%|████▉     | 184244/371472 [3:47:52<15:05:50,  3.44it/s]
 50%|████▉     | 184245/371472 [3:47:52<15:00:00,  3.47it/s]
 50%|████▉     | 184246/371472 [3:47:53<15:07:07,  3.44it/s]
 50%|████▉     | 184247/371472 [3:47:53<15:24:08,  3.38it/s]
 50%|████▉     | 184248/371472 [3:47:53<15:17:58,  3.40it/s]
 50%|████▉     | 184249/371472 [3:47:54<15:00:24,  3.47it/s]
 50%|████▉     | 184250/371472 [3:47:54<16:17:50,  3.19it/s]
 50%|████▉     | 184251/371472 [3:47:54<15:51:17,  3.28it/s]
 50%|████▉     | 184252/371472 [3:47:55<15:36:11,  3.33it/s]
 50%|████▉     | 184253/371472 [3:47:55<15:42:25,  3.31it/s]
 50%|████▉     | 184254/371472 [3:47:55<15:33:03,  3.34it/s]
 50%|████▉     | 184255/371472 [3:47:56<16:21:41,  3.18it/s]
 50%|████▉     | 184256/371472 [3:47:56<15:47:14,  3.29it/s]
 50%|████▉     | 184257/371472 [3:47:56<15:28:43,  3.36it/s]
 50%|████▉     | 184258/371472 [3:47:56<16:08:40,  3.22it/s]
 50%|████▉     | 184259/371472 [3:47:57<16:10:25,  3.22it/s]
 50%|████▉     | 184260/371472 [3:47:57<16:26:50,  3.16it/s]
                                                            
{'loss': 3.0963, 'learning_rate': 5.538203796677368e-07, 'epoch': 7.94}
+
 50%|████▉     | 184260/371472 [3:47:57<16:26:50,  3.16it/s]
 50%|████▉     | 184261/371472 [3:47:57<16:05:21,  3.23it/s]
 50%|████▉     | 184262/371472 [3:47:58<15:49:42,  3.29it/s]
 50%|████▉     | 184263/371472 [3:47:58<16:08:47,  3.22it/s]
 50%|████▉     | 184264/371472 [3:47:58<15:53:12,  3.27it/s]
 50%|████▉     | 184265/371472 [3:47:59<16:01:13,  3.25it/s]
 50%|████▉     | 184266/371472 [3:47:59<15:54:42,  3.27it/s]
 50%|████▉     | 184267/371472 [3:47:59<15:30:39,  3.35it/s]
 50%|████▉     | 184268/371472 [3:47:59<15:26:16,  3.37it/s]
 50%|████▉     | 184269/371472 [3:48:00<15:35:28,  3.34it/s]
 50%|████▉     | 184270/371472 [3:48:00<15:26:05,  3.37it/s]
 50%|████▉     | 184271/371472 [3:48:00<14:57:27,  3.48it/s]
 50%|████▉     | 184272/371472 [3:48:01<15:11:45,  3.42it/s]
 50%|████▉     | 184273/371472 [3:48:01<15:55:16,  3.27it/s]
 50%|████▉     | 184274/371472 [3:48:01<15:12:17,  3.42it/s]
 50%|████▉     | 184275/371472 [3:48:02<14:54:43,  3.49it/s]
 50%|████▉     | 184276/371472 [3:48:02<14:39:05,  3.55it/s]
 50%|████▉     | 184277/371472 [3:48:02<15:34:04,  3.34it/s]
 50%|████▉     | 184278/371472 [3:48:02<15:18:52,  3.40it/s]
 50%|████▉     | 184279/371472 [3:48:03<14:52:07,  3.50it/s]
 50%|████▉     | 184280/371472 [3:48:03<14:55:23,  3.48it/s]
                                                            
{'loss': 2.8242, 'learning_rate': 5.537718976922579e-07, 'epoch': 7.94}
+
 50%|████▉     | 184280/371472 [3:48:03<14:55:23,  3.48it/s]
 50%|████▉     | 184281/371472 [3:48:03<15:22:58,  3.38it/s]
 50%|████▉     | 184282/371472 [3:48:04<15:00:14,  3.47it/s]
 50%|████▉     | 184283/371472 [3:48:04<15:54:01,  3.27it/s]
 50%|████▉     | 184284/371472 [3:48:04<15:43:03,  3.31it/s]
 50%|████▉     | 184285/371472 [3:48:04<15:21:43,  3.38it/s]
 50%|████▉     | 184286/371472 [3:48:05<15:29:12,  3.36it/s]
 50%|████▉     | 184287/371472 [3:48:05<15:21:16,  3.39it/s]
 50%|████▉     | 184288/371472 [3:48:05<15:02:38,  3.46it/s]
 50%|████▉     | 184289/371472 [3:48:06<16:32:00,  3.14it/s]
 50%|████▉     | 184290/371472 [3:48:06<16:31:58,  3.14it/s]
 50%|████▉     | 184291/371472 [3:48:06<16:54:55,  3.07it/s]
 50%|████▉     | 184292/371472 [3:48:07<17:00:07,  3.06it/s]
 50%|████▉     | 184293/371472 [3:48:07<17:46:40,  2.92it/s]
 50%|████▉     | 184294/371472 [3:48:07<17:12:30,  3.02it/s]
 50%|████▉     | 184295/371472 [3:48:08<16:43:11,  3.11it/s]
 50%|████▉     | 184296/371472 [3:48:08<16:26:05,  3.16it/s]
 50%|████▉     | 184297/371472 [3:48:08<16:00:07,  3.25it/s]
 50%|████▉     | 184298/371472 [3:48:09<15:37:17,  3.33it/s]
 50%|████▉     | 184299/371472 [3:48:09<16:27:21,  3.16it/s]
 50%|████▉     | 184300/371472 [3:48:09<16:04:55,  3.23it/s]
                                                            
{'loss': 2.6657, 'learning_rate': 5.53723415716779e-07, 'epoch': 7.94}
+
 50%|████▉     | 184300/371472 [3:48:09<16:04:55,  3.23it/s]
 50%|████▉     | 184301/371472 [3:48:09<15:22:44,  3.38it/s]
 50%|████▉     | 184302/371472 [3:48:10<15:22:08,  3.38it/s]
 50%|████▉     | 184303/371472 [3:48:10<17:02:25,  3.05it/s]
 50%|████▉     | 184304/371472 [3:48:10<16:56:04,  3.07it/s]
 50%|████▉     | 184305/371472 [3:48:11<16:59:46,  3.06it/s]
 50%|████▉     | 184306/371472 [3:48:11<16:25:06,  3.17it/s]
 50%|████▉     | 184307/371472 [3:48:11<15:42:43,  3.31it/s]
 50%|████▉     | 184308/371472 [3:48:12<15:35:31,  3.33it/s]
 50%|████▉     | 184309/371472 [3:48:12<15:24:58,  3.37it/s]
 50%|████▉     | 184310/371472 [3:48:12<15:01:38,  3.46it/s]
 50%|████▉     | 184311/371472 [3:48:13<16:35:21,  3.13it/s]
 50%|████▉     | 184312/371472 [3:48:13<16:17:31,  3.19it/s]
 50%|████▉     | 184313/371472 [3:48:13<16:30:22,  3.15it/s]
 50%|████▉     | 184314/371472 [3:48:14<15:55:38,  3.26it/s]
 50%|████▉     | 184315/371472 [3:48:14<15:30:54,  3.35it/s]
 50%|████▉     | 184316/371472 [3:48:14<15:10:46,  3.42it/s]
 50%|████▉     | 184317/371472 [3:48:14<15:36:32,  3.33it/s]
 50%|████▉     | 184318/371472 [3:48:15<15:16:06,  3.40it/s]
 50%|████▉     | 184319/371472 [3:48:15<15:14:30,  3.41it/s]
 50%|████▉     | 184320/371472 [3:48:15<15:20:17,  3.39it/s]
                                                            
{'loss': 2.8766, 'learning_rate': 5.536749337413002e-07, 'epoch': 7.94}
+
 50%|████▉     | 184320/371472 [3:48:15<15:20:17,  3.39it/s]
 50%|████▉     | 184321/371472 [3:48:16<15:42:36,  3.31it/s]
 50%|████▉     | 184322/371472 [3:48:16<16:08:10,  3.22it/s]
 50%|████▉     | 184323/371472 [3:48:16<15:49:07,  3.29it/s]
 50%|████▉     | 184324/371472 [3:48:17<15:46:37,  3.29it/s]
 50%|████▉     | 184325/371472 [3:48:17<17:19:23,  3.00it/s]
 50%|█���██▉     | 184326/371472 [3:48:17<16:33:42,  3.14it/s]
 50%|████▉     | 184327/371472 [3:48:18<16:19:33,  3.18it/s]
 50%|████▉     | 184328/371472 [3:48:18<16:41:29,  3.11it/s]
 50%|████▉     | 184329/371472 [3:48:18<18:27:37,  2.82it/s]
 50%|████▉     | 184330/371472 [3:48:19<17:49:11,  2.92it/s]
 50%|████▉     | 184331/371472 [3:48:19<18:22:21,  2.83it/s]
 50%|████▉     | 184332/371472 [3:48:19<17:46:52,  2.92it/s]
 50%|████▉     | 184333/371472 [3:48:20<17:23:43,  2.99it/s]
 50%|████▉     | 184334/371472 [3:48:20<18:11:36,  2.86it/s]
 50%|████▉     | 184335/371472 [3:48:20<16:58:32,  3.06it/s]
 50%|████▉     | 184336/371472 [3:48:21<16:15:55,  3.20it/s]
 50%|████▉     | 184337/371472 [3:48:21<16:20:29,  3.18it/s]
 50%|████▉     | 184338/371472 [3:48:21<16:26:18,  3.16it/s]
 50%|████▉     | 184339/371472 [3:48:21<15:56:44,  3.26it/s]
 50%|████▉     | 184340/371472 [3:48:22<15:53:41,  3.27it/s]
                                                            
{'loss': 2.9144, 'learning_rate': 5.536264517658213e-07, 'epoch': 7.94}
+
 50%|████▉     | 184340/371472 [3:48:22<15:53:41,  3.27it/s]
 50%|████▉     | 184341/371472 [3:48:22<16:12:14,  3.21it/s]
 50%|████▉     | 184342/371472 [3:48:22<15:53:34,  3.27it/s]
 50%|████▉     | 184343/371472 [3:48:23<16:36:45,  3.13it/s]
 50%|████▉     | 184344/371472 [3:48:23<16:42:15,  3.11it/s]
 50%|████▉     | 184345/371472 [3:48:23<16:22:28,  3.17it/s]
 50%|████▉     | 184346/371472 [3:48:24<16:10:28,  3.21it/s]
 50%|████▉     | 184347/371472 [3:48:24<15:58:39,  3.25it/s]
 50%|████▉     | 184348/371472 [3:48:24<15:28:24,  3.36it/s]
 50%|████▉     | 184349/371472 [3:48:25<15:34:34,  3.34it/s]
 50%|████▉     | 184350/371472 [3:48:25<15:58:09,  3.25it/s]
 50%|████▉     | 184351/371472 [3:48:25<15:57:41,  3.26it/s]
 50%|████▉     | 184352/371472 [3:48:25<16:01:39,  3.24it/s]
 50%|████▉     | 184353/371472 [3:48:26<15:44:07,  3.30it/s]
 50%|████▉     | 184354/371472 [3:48:26<15:50:26,  3.28it/s]
 50%|████▉     | 184355/371472 [3:48:26<16:06:03,  3.23it/s]
 50%|████▉     | 184356/371472 [3:48:27<15:51:44,  3.28it/s]
 50%|████▉     | 184357/371472 [3:48:27<16:07:35,  3.22it/s]
 50%|████▉     | 184358/371472 [3:48:27<16:37:44,  3.13it/s]
 50%|████▉     | 184359/371472 [3:48:28<16:29:57,  3.15it/s]
 50%|████▉     | 184360/371472 [3:48:28<15:59:11,  3.25it/s]
                                                            
{'loss': 2.8125, 'learning_rate': 5.535779697903424e-07, 'epoch': 7.94}
+
 50%|████▉     | 184360/371472 [3:48:28<15:59:11,  3.25it/s]
 50%|████▉     | 184361/371472 [3:48:28<15:59:39,  3.25it/s]
 50%|████▉     | 184362/371472 [3:48:29<16:01:48,  3.24it/s]
 50%|████▉     | 184363/371472 [3:48:29<16:57:59,  3.06it/s]
 50%|████▉     | 184364/371472 [3:48:29<16:28:41,  3.15it/s]
 50%|████▉     | 184365/371472 [3:48:30<15:56:40,  3.26it/s]
 50%|████▉     | 184366/371472 [3:48:30<16:12:15,  3.21it/s]
 50%|████▉     | 184367/371472 [3:48:30<15:56:16,  3.26it/s]
 50%|████▉     | 184368/371472 [3:48:30<15:18:56,  3.39it/s]
 50%|████▉     | 184369/371472 [3:48:31<15:34:58,  3.34it/s]
 50%|████▉     | 184370/371472 [3:48:31<15:05:59,  3.44it/s]
 50%|████▉     | 184371/371472 [3:48:31<16:06:45,  3.23it/s]
 50%|████▉     | 184372/371472 [3:48:32<15:44:29,  3.30it/s]
 50%|████▉     | 184373/371472 [3:48:32<16:16:01,  3.19it/s]
 50%|████▉     | 184374/371472 [3:48:32<15:33:22,  3.34it/s]
 50%|████▉     | 184375/371472 [3:48:33<15:34:28,  3.34it/s]
 50%|████▉     | 184376/371472 [3:48:33<15:15:03,  3.41it/s]
 50%|████▉     | 184377/371472 [3:48:33<15:17:03,  3.40it/s]
 50%|████▉     | 184378/371472 [3:48:33<15:13:17,  3.41it/s]
 50%|████▉     | 184379/371472 [3:48:34<15:21:37,  3.38it/s]
 50%|████▉     | 184380/371472 [3:48:34<16:12:22,  3.21it/s]
                                                            
{'loss': 2.7815, 'learning_rate': 5.535294878148635e-07, 'epoch': 7.94}
+
 50%|████▉     | 184380/371472 [3:48:34<16:12:22,  3.21it/s]
 50%|████▉     | 184381/371472 [3:48:34<15:51:29,  3.28it/s]
 50%|████▉     | 184382/371472 [3:48:35<15:58:02,  3.25it/s]
 50%|████▉     | 184383/371472 [3:48:35<15:44:17,  3.30it/s]
 50%|████▉     | 184384/371472 [3:48:35<15:53:28,  3.27it/s]
 50%|████▉     | 184385/371472 [3:48:36<15:44:55,  3.30it/s]
 50%|████▉     | 184386/371472 [3:48:36<15:40:55,  3.31it/s]
 50%|████▉     | 184387/371472 [3:48:36<15:25:02,  3.37it/s]
 50%|████▉     | 184388/371472 [3:48:36<15:47:33,  3.29it/s]
 50%|████▉     | 184389/371472 [3:48:37<15:39:41,  3.32it/s]
 50%|████▉     | 184390/371472 [3:48:37<16:05:26,  3.23it/s]
 50%|████▉     | 184391/371472 [3:48:37<16:03:08,  3.24it/s]
 50%|████▉     | 184392/371472 [3:48:38<15:40:09,  3.32it/s]
 50%|████▉     | 184393/371472 [3:48:38<15:53:07,  3.27it/s]
 50%|████▉     | 184394/371472 [3:48:38<15:59:36,  3.25it/s]
 50%|████▉     | 184395/371472 [3:48:39<15:39:07,  3.32it/s]
 50%|████▉     | 184396/371472 [3:48:39<17:00:02,  3.06it/s]
 50%|████▉     | 184397/371472 [3:48:39<16:30:47,  3.15it/s]
 50%|████▉     | 184398/371472 [3:48:40<15:55:09,  3.26it/s]
 50%|████▉     | 184399/371472 [3:48:40<15:45:16,  3.30it/s]
 50%|████▉     | 184400/371472 [3:48:40<15:41:21,  3.31it/s]
                                                            
{'loss': 2.8472, 'learning_rate': 5.534810058393846e-07, 'epoch': 7.94}
+
 50%|████▉     | 184400/371472 [3:48:40<15:41:21,  3.31it/s]
 50%|████▉     | 184401/371472 [3:48:40<15:40:13,  3.32it/s]
 50%|████▉     | 184402/371472 [3:48:41<15:20:42,  3.39it/s]
 50%|████▉     | 184403/371472 [3:48:41<15:10:42,  3.42it/s]
 50%|████▉     | 184404/371472 [3:48:41<14:47:39,  3.51it/s]
 50%|████▉     | 184405/371472 [3:48:42<14:56:15,  3.48it/s]
 50%|████▉     | 184406/371472 [3:48:42<15:01:30,  3.46it/s]
 50%|████▉     | 184407/371472 [3:48:42<15:07:41,  3.43it/s]
 50%|████▉     | 184408/371472 [3:48:42<15:30:22,  3.35it/s]
 50%|████▉     | 184409/371472 [3:48:43<15:27:12,  3.36it/s]
 50%|████▉     | 184410/371472 [3:48:43<15:30:02,  3.35it/s]
 50%|████▉     | 184411/371472 [3:48:43<16:18:22,  3.19it/s]
 50%|████▉     | 184412/371472 [3:48:44<15:40:54,  3.31it/s]
 50%|████▉     | 184413/371472 [3:48:44<15:32:44,  3.34it/s]
 50%|████▉     | 184414/371472 [3:48:44<15:33:13,  3.34it/s]
 50%|████▉     | 184415/371472 [3:48:45<15:29:56,  3.35it/s]
 50%|████▉     | 184416/371472 [3:48:45<15:31:37,  3.35it/s]
 50%|████▉     | 184417/371472 [3:48:45<15:12:51,  3.42it/s]
 50%|████▉     | 184418/371472 [3:48:46<16:12:50,  3.20it/s]
 50%|████▉     | 184419/371472 [3:48:46<15:46:33,  3.29it/s]
 50%|████▉     | 184420/371472 [3:48:46<16:20:52,  3.18it/s]
                                                            
{'loss': 2.8719, 'learning_rate': 5.534325238639057e-07, 'epoch': 7.94}
+
 50%|████▉     | 184420/371472 [3:48:46<16:20:52,  3.18it/s]
 50%|████▉     | 184421/371472 [3:48:46<16:06:13,  3.23it/s]
 50%|████▉     | 184422/371472 [3:48:47<15:34:53,  3.33it/s]
 50%|████▉     | 184423/371472 [3:48:47<15:13:52,  3.41it/s]
 50%|████▉     | 184424/371472 [3:48:47<16:30:27,  3.15it/s]
 50%|████▉     | 184425/371472 [3:48:48<16:15:53,  3.19it/s]
 50%|████▉     | 184426/371472 [3:48:48<16:15:02,  3.20it/s]
 50%|████▉     | 184427/371472 [3:48:48<16:35:24,  3.13it/s]
 50%|████▉     | 184428/371472 [3:48:49<16:25:59,  3.16it/s]
 50%|████▉     | 184429/371472 [3:48:49<16:20:12,  3.18it/s]
 50%|████▉     | 184430/371472 [3:48:49<16:46:44,  3.10it/s]
 50%|████▉     | 184431/371472 [3:48:50<16:36:58,  3.13it/s]
 50%|████▉     | 184432/371472 [3:48:50<16:39:16,  3.12it/s]
 50%|████▉     | 184433/371472 [3:48:50<16:25:42,  3.16it/s]
 50%|████▉     | 184434/371472 [3:48:51<15:54:23,  3.27it/s]
 50%|████▉     | 184435/371472 [3:48:51<15:59:04,  3.25it/s]
 50%|████▉     | 184436/371472 [3:48:51<15:50:45,  3.28it/s]
 50%|████▉     | 184437/371472 [3:48:51<15:45:54,  3.30it/s]
 50%|████▉     | 184438/371472 [3:48:52<16:36:57,  3.13it/s]
 50%|████▉     | 184439/371472 [3:48:52<16:01:16,  3.24it/s]
 50%|████▉     | 184440/371472 [3:48:52<15:32:34,  3.34it/s]
                                                            
{'loss': 2.909, 'learning_rate': 5.533840418884268e-07, 'epoch': 7.94}
+
 50%|████▉     | 184440/371472 [3:48:52<15:32:34,  3.34it/s]
 50%|████▉     | 184441/371472 [3:48:53<15:35:14,  3.33it/s]
 50%|████▉     | 184442/371472 [3:48:53<15:25:53,  3.37it/s]
 50%|████▉     | 184443/371472 [3:48:53<15:22:27,  3.38it/s]
 50%|████▉     | 184444/371472 [3:48:54<15:09:36,  3.43it/s]
 50%|████▉     | 184445/371472 [3:48:54<15:12:28,  3.42it/s]
 50%|████▉     | 184446/371472 [3:48:54<15:35:12,  3.33it/s]
 50%|████▉     | 184447/371472 [3:48:54<15:06:31,  3.44it/s]
 50%|████▉     | 184448/371472 [3:48:55<14:44:50,  3.52it/s]
 50%|████▉     | 184449/371472 [3:48:55<15:04:14,  3.45it/s]
 50%|████▉     | 184450/371472 [3:48:55<15:22:08,  3.38it/s]
 50%|████▉     | 184451/371472 [3:48:56<15:14:57,  3.41it/s]
 50%|████▉     | 184452/371472 [3:48:56<15:00:37,  3.46it/s]
 50%|████▉     | 184453/371472 [3:48:56<16:18:45,  3.18it/s]
 50%|████▉     | 184454/371472 [3:48:57<18:46:08,  2.77it/s]
 50%|████▉     | 184455/371472 [3:48:57<17:30:52,  2.97it/s]
 50%|████▉     | 184456/371472 [3:48:57<16:49:33,  3.09it/s]
 50%|████▉     | 184457/371472 [3:48:58<17:06:25,  3.04it/s]
 50%|████▉     | 184458/371472 [3:48:58<16:32:47,  3.14it/s]
 50%|████▉     | 184459/371472 [3:48:58<16:24:39,  3.17it/s]
 50%|████▉     | 184460/371472 [3:48:58<16:03:35,  3.23it/s]
                                                            
{'loss': 2.9544, 'learning_rate': 5.533355599129478e-07, 'epoch': 7.95}
+
 50%|████▉     | 184460/371472 [3:48:58<16:03:35,  3.23it/s]
 50%|████▉     | 184461/371472 [3:48:59<16:01:55,  3.24it/s]
 50%|████▉     | 184462/371472 [3:48:59<15:47:49,  3.29it/s]
 50%|████▉     | 184463/371472 [3:48:59<15:41:18,  3.31it/s]
 50%|████▉     | 184464/371472 [3:49:00<15:28:09,  3.36it/s]
 50%|████▉     | 184465/371472 [3:49:00<15:17:30,  3.40it/s]
 50%|████▉     | 184466/371472 [3:49:00<15:13:25,  3.41it/s]
 50%|████▉     | 184467/371472 [3:49:01<15:31:02,  3.35it/s]
 50%|████▉     | 184468/371472 [3:49:01<15:50:47,  3.28it/s]
 50%|████▉     | 184469/371472 [3:49:01<16:41:07,  3.11it/s]
 50%|████▉     | 184470/371472 [3:49:02<16:51:45,  3.08it/s]
 50%|████▉     | 184471/371472 [3:49:02<16:29:38,  3.15it/s]
 50%|████▉     | 184472/371472 [3:49:02<16:05:32,  3.23it/s]
 50%|████▉     | 184473/371472 [3:49:02<15:57:31,  3.25it/s]
 50%|████▉     | 184474/371472 [3:49:03<16:22:23,  3.17it/s]
 50%|████▉     | 184475/371472 [3:49:03<16:02:51,  3.24it/s]
 50%|████▉     | 184476/371472 [3:49:03<16:00:15,  3.25it/s]
 50%|████▉     | 184477/371472 [3:49:04<15:48:05,  3.29it/s]
 50%|████▉     | 184478/371472 [3:49:04<15:31:19,  3.35it/s]
 50%|████▉     | 184479/371472 [3:49:04<15:29:12,  3.35it/s]
 50%|████▉     | 184480/371472 [3:49:05<15:12:06,  3.42it/s]
                                                            
{'loss': 2.8958, 'learning_rate': 5.53287077937469e-07, 'epoch': 7.95}
+
 50%|████▉     | 184480/371472 [3:49:05<15:12:06,  3.42it/s]
 50%|████▉     | 184481/371472 [3:49:05<15:22:31,  3.38it/s]
 50%|████▉     | 184482/371472 [3:49:05<15:15:07,  3.41it/s]
 50%|████▉     | 184483/371472 [3:49:05<15:45:23,  3.30it/s]
 50%|████▉     | 184484/371472 [3:49:06<15:34:21,  3.34it/s]
 50%|████▉     | 184485/371472 [3:49:06<15:32:42,  3.34it/s]
 50%|████▉     | 184486/371472 [3:49:06<16:13:29,  3.20it/s]
 50%|████▉     | 184487/371472 [3:49:07<16:06:22,  3.22it/s]
 50%|████▉     | 184488/371472 [3:49:07<16:19:41,  3.18it/s]
 50%|████▉     | 184489/371472 [3:49:07<15:59:27,  3.25it/s]
 50%|████▉     | 184490/371472 [3:49:08<17:00:03,  3.06it/s]
 50%|████▉     | 184491/371472 [3:49:08<17:35:12,  2.95it/s]
 50%|████▉     | 184492/371472 [3:49:08<16:47:30,  3.09it/s]
 50%|████▉     | 184493/371472 [3:49:09<16:19:14,  3.18it/s]
 50%|████▉     | 184494/371472 [3:49:09<15:55:05,  3.26it/s]
 50%|████▉     | 184495/371472 [3:49:09<16:00:10,  3.25it/s]
 50%|████▉     | 184496/371472 [3:49:10<16:05:05,  3.23it/s]
 50%|████▉     | 184497/371472 [3:49:10<16:17:20,  3.19it/s]
 50%|████▉     | 184498/371472 [3:49:10<15:57:41,  3.25it/s]
 50%|████▉     | 184499/371472 [3:49:11<16:02:35,  3.24it/s]
 50%|████▉     | 184500/371472 [3:49:11<15:29:17,  3.35it/s]
                                                            
{'loss': 2.9271, 'learning_rate': 5.532385959619901e-07, 'epoch': 7.95}
+
 50%|████▉     | 184500/371472 [3:49:11<15:29:17,  3.35it/s]
 50%|████▉     | 184501/371472 [3:49:11<15:26:36,  3.36it/s]
 50%|████▉     | 184502/371472 [3:49:11<15:05:54,  3.44it/s]
 50%|████▉     | 184503/371472 [3:49:12<15:02:00,  3.45it/s]
 50%|████▉     | 184504/371472 [3:49:12<15:02:25,  3.45it/s]
 50%|████▉     | 184505/371472 [3:49:12<15:09:14,  3.43it/s]
 50%|████▉     | 184506/371472 [3:49:13<15:30:43,  3.35it/s]
 50%|████▉     | 184507/371472 [3:49:13<15:05:24,  3.44it/s]
 50%|████▉     | 184508/371472 [3:49:13<14:50:00,  3.50it/s]
 50%|████▉     | 184509/371472 [3:49:13<14:47:44,  3.51it/s]
 50%|████▉     | 184510/371472 [3:49:14<14:45:19,  3.52it/s]
 50%|████▉     | 184511/371472 [3:49:14<15:07:37,  3.43it/s]
 50%|████▉     | 184512/371472 [3:49:14<15:35:33,  3.33it/s]
 50%|████▉     | 184513/371472 [3:49:15<15:44:54,  3.30it/s]
 50%|████▉     | 184514/371472 [3:49:15<15:22:31,  3.38it/s]
 50%|████▉     | 184515/371472 [3:49:15<15:04:47,  3.44it/s]
 50%|████▉     | 184516/371472 [3:49:15<15:25:27,  3.37it/s]
 50%|████▉     | 184517/371472 [3:49:16<15:34:28,  3.33it/s]
 50%|████▉     | 184518/371472 [3:49:16<15:22:12,  3.38it/s]
 50%|████▉     | 184519/371472 [3:49:16<15:14:26,  3.41it/s]
 50%|████▉     | 184520/371472 [3:49:17<15:05:58,  3.44it/s]
                                                            
{'loss': 2.8972, 'learning_rate': 5.531901139865112e-07, 'epoch': 7.95}
+
 50%|████▉     | 184520/371472 [3:49:17<15:05:58,  3.44it/s]
 50%|████▉     | 184521/371472 [3:49:17<14:56:13,  3.48it/s]
 50%|████▉     | 184522/371472 [3:49:17<14:57:15,  3.47it/s]
 50%|████▉     | 184523/371472 [3:49:17<15:17:19,  3.40it/s]
 50%|████▉     | 184524/371472 [3:49:18<14:53:33,  3.49it/s]
 50%|████▉     | 184525/371472 [3:49:18<15:19:56,  3.39it/s]
 50%|████▉     | 184526/371472 [3:49:18<14:56:36,  3.48it/s]
 50%|████▉     | 184527/371472 [3:49:19<14:54:17,  3.48it/s]
 50%|████▉     | 184528/371472 [3:49:19<14:41:17,  3.54it/s]
 50%|████▉     | 184529/371472 [3:49:19<14:34:06,  3.56it/s]
 50%|████▉     | 184530/371472 [3:49:20<15:09:47,  3.42it/s]
 50%|████▉     | 184531/371472 [3:49:20<15:18:39,  3.39it/s]
 50%|████▉     | 184532/371472 [3:49:20<15:13:46,  3.41it/s]
 50%|████▉     | 184533/371472 [3:49:20<16:33:45,  3.14it/s]
 50%|████▉     | 184534/371472 [3:49:21<17:19:22,  3.00it/s]
 50%|████▉     | 184535/371472 [3:49:21<16:29:04,  3.15it/s]
 50%|████▉     | 184536/371472 [3:49:21<16:07:03,  3.22it/s]
 50%|████▉     | 184537/371472 [3:49:22<16:50:14,  3.08it/s]
 50%|████▉     | 184538/371472 [3:49:22<15:59:49,  3.25it/s]
 50%|████▉     | 184539/371472 [3:49:22<16:25:27,  3.16it/s]
 50%|████▉     | 184540/371472 [3:49:23<15:59:23,  3.25it/s]
                                                            
{'loss': 3.0782, 'learning_rate': 5.531416320110323e-07, 'epoch': 7.95}
+
 50%|████▉     | 184540/371472 [3:49:23<15:59:23,  3.25it/s]
 50%|████▉     | 184541/371472 [3:49:23<16:01:35,  3.24it/s]
 50%|████▉     | 184542/371472 [3:49:23<15:49:48,  3.28it/s]
 50%|████▉     | 184543/371472 [3:49:24<15:41:48,  3.31it/s]
 50%|████▉     | 184544/371472 [3:49:24<15:06:40,  3.44it/s]
 50%|████▉     | 184545/371472 [3:49:24<15:03:19,  3.45it/s]
 50%|████▉     | 184546/371472 [3:49:24<14:56:47,  3.47it/s]
 50%|████▉     | 184547/371472 [3:49:25<15:05:03,  3.44it/s]
 50%|████▉     | 184548/371472 [3:49:25<14:53:24,  3.49it/s]
 50%|████▉     | 184549/371472 [3:49:25<15:00:56,  3.46it/s]
 50%|████▉     | 184550/371472 [3:49:26<15:11:09,  3.42it/s]
 50%|████▉     | 184551/371472 [3:49:26<16:28:01,  3.15it/s]
 50%|████▉     | 184552/371472 [3:49:26<17:17:18,  3.00it/s]
 50%|████▉     | 184553/371472 [3:49:27<16:43:32,  3.10it/s]
 50%|████▉     | 184554/371472 [3:49:27<16:09:54,  3.21it/s]
 50%|████▉     | 184555/371472 [3:49:27<15:50:24,  3.28it/s]
 50%|████▉     | 184556/371472 [3:49:28<16:23:45,  3.17it/s]
 50%|████▉     | 184557/371472 [3:49:28<15:43:16,  3.30it/s]
 50%|████▉     | 184558/371472 [3:49:28<15:10:49,  3.42it/s]
 50%|████▉     | 184559/371472 [3:49:28<15:08:46,  3.43it/s]
 50%|████▉     | 184560/371472 [3:49:29<15:01:48,  3.45it/s]
                                                            
{'loss': 2.8258, 'learning_rate': 5.530931500355534e-07, 'epoch': 7.95}
+
 50%|████▉     | 184560/371472 [3:49:29<15:01:48,  3.45it/s]
 50%|████▉     | 184561/371472 [3:49:29<15:00:34,  3.46it/s]
 50%|████▉     | 184562/371472 [3:49:29<14:45:57,  3.52it/s]
 50%|████▉     | 184563/371472 [3:49:29<14:46:50,  3.51it/s]
 50%|████▉     | 184564/371472 [3:49:30<14:56:56,  3.47it/s]
 50%|████▉     | 184565/371472 [3:49:30<15:57:45,  3.25it/s]
 50%|████▉     | 184566/371472 [3:49:30<15:37:13,  3.32it/s]
 50%|████▉     | 184567/371472 [3:49:31<15:27:22,  3.36it/s]
 50%|████▉     | 184568/371472 [3:49:31<15:03:38,  3.45it/s]
 50%|████▉     | 184569/371472 [3:49:31<14:59:32,  3.46it/s]
 50%|████▉     | 184570/371472 [3:49:32<14:55:32,  3.48it/s]
 50%|████▉     | 184571/371472 [3:49:32<14:52:59,  3.49it/s]
 50%|████▉     | 184572/371472 [3:49:32<15:32:53,  3.34it/s]
 50%|████▉     | 184573/371472 [3:49:32<15:04:46,  3.44it/s]
 50%|████▉     | 184574/371472 [3:49:33<14:59:23,  3.46it/s]
 50%|████▉     | 184575/371472 [3:49:33<14:58:55,  3.47it/s]
 50%|████▉     | 184576/371472 [3:49:33<16:03:29,  3.23it/s]
 50%|████▉     | 184577/371472 [3:49:34<15:37:24,  3.32it/s]
 50%|████▉     | 184578/371472 [3:49:34<16:26:38,  3.16it/s]
 50%|████▉     | 184579/371472 [3:49:34<15:54:19,  3.26it/s]
 50%|████▉     | 184580/371472 [3:49:35<15:36:25,  3.33it/s]
                                                            
{'loss': 2.815, 'learning_rate': 5.530446680600746e-07, 'epoch': 7.95}
+
 50%|████▉     | 184580/371472 [3:49:35<15:36:25,  3.33it/s]
 50%|████▉     | 184581/371472 [3:49:35<15:08:04,  3.43it/s]
 50%|████▉     | 184582/371472 [3:49:35<14:52:58,  3.49it/s]
 50%|████▉     | 184583/371472 [3:49:35<15:09:09,  3.43it/s]
 50%|████▉     | 184584/371472 [3:49:36<15:14:28,  3.41it/s]
 50%|████▉     | 184585/371472 [3:49:36<15:29:51,  3.35it/s]
 50%|████▉     | 184586/371472 [3:49:36<15:19:35,  3.39it/s]
 50%|████▉     | 184587/371472 [3:49:37<15:09:13,  3.43it/s]
 50%|████▉     | 184588/371472 [3:49:37<15:31:29,  3.34it/s]
 50%|████▉     | 184589/371472 [3:49:37<15:25:15,  3.37it/s]
 50%|████▉     | 184590/371472 [3:49:38<15:38:14,  3.32it/s]
 50%|████▉     | 184591/371472 [3:49:38<15:39:22,  3.32it/s]
 50%|████▉     | 184592/371472 [3:49:38<16:17:52,  3.19it/s]
 50%|████▉     | 184593/371472 [3:49:38<15:49:33,  3.28it/s]
 50%|████▉     | 184594/371472 [3:49:39<15:29:06,  3.35it/s]
 50%|████▉     | 184595/371472 [3:49:39<15:10:19,  3.42it/s]
 50%|████▉     | 184596/371472 [3:49:39<15:23:55,  3.37it/s]
 50%|████▉     | 184597/371472 [3:49:40<15:17:12,  3.40it/s]
 50%|████▉     | 184598/371472 [3:49:40<15:20:39,  3.38it/s]
 50%|████▉     | 184599/371472 [3:49:40<15:30:15,  3.35it/s]
 50%|████▉     | 184600/371472 [3:49:41<15:25:38,  3.36it/s]
                                                            
{'loss': 2.9328, 'learning_rate': 5.529961860845957e-07, 'epoch': 7.95}
+
 50%|████▉     | 184600/371472 [3:49:41<15:25:38,  3.36it/s]
 50%|████▉     | 184601/371472 [3:49:41<15:56:20,  3.26it/s]
 50%|████▉     | 184602/371472 [3:49:41<15:52:21,  3.27it/s]
 50%|████▉     | 184603/371472 [3:49:41<15:26:19,  3.36it/s]
 50%|████▉     | 184604/371472 [3:49:42<15:25:02,  3.37it/s]
 50%|████▉     | 184605/371472 [3:49:42<15:15:05,  3.40it/s]
 50%|████▉     | 184606/371472 [3:49:42<15:30:50,  3.35it/s]
 50%|████▉     | 184607/371472 [3:49:43<16:20:08,  3.18it/s]
 50%|████▉     | 184608/371472 [3:49:43<16:14:35,  3.20it/s]
 50%|████▉     | 184609/371472 [3:49:43<16:01:56,  3.24it/s]
 50%|████▉     | 184610/371472 [3:49:44<15:53:27,  3.27it/s]
 50%|████▉     | 184611/371472 [3:49:44<15:18:01,  3.39it/s]
 50%|████▉     | 184612/371472 [3:49:44<15:19:54,  3.39it/s]
 50%|████▉     | 184613/371472 [3:49:44<15:28:18,  3.35it/s]
 50%|████▉     | 184614/371472 [3:49:45<15:42:01,  3.31it/s]
 50%|████▉     | 184615/371472 [3:49:45<15:29:09,  3.35it/s]
 50%|████▉     | 184616/371472 [3:49:45<15:04:54,  3.44it/s]
 50%|████▉     | 184617/371472 [3:49:46<14:52:27,  3.49it/s]
 50%|████▉     | 184618/371472 [3:49:46<14:56:18,  3.47it/s]
 50%|████▉     | 184619/371472 [3:49:46<15:16:54,  3.40it/s]
 50%|████▉     | 184620/371472 [3:49:47<15:44:19,  3.30it/s]
                                                            
{'loss': 2.7971, 'learning_rate': 5.529477041091168e-07, 'epoch': 7.95}
+
 50%|████▉     | 184620/371472 [3:49:47<15:44:19,  3.30it/s]
 50%|████▉     | 184621/371472 [3:49:47<15:53:08,  3.27it/s]
 50%|████▉     | 184622/371472 [3:49:47<15:49:31,  3.28it/s]
 50%|████▉     | 184623/371472 [3:49:47<15:55:05,  3.26it/s]
 50%|████▉     | 184624/371472 [3:49:48<15:34:25,  3.33it/s]
 50%|████▉     | 184625/371472 [3:49:48<15:16:40,  3.40it/s]
 50%|████▉     | 184626/371472 [3:49:48<15:08:11,  3.43it/s]
 50%|████▉     | 184627/371472 [3:49:49<15:44:39,  3.30it/s]
 50%|████▉     | 184628/371472 [3:49:49<15:16:47,  3.40it/s]
 50%|████▉     | 184629/371472 [3:49:49<15:18:46,  3.39it/s]
 50%|████▉     | 184630/371472 [3:49:49<15:24:05,  3.37it/s]
 50%|████▉     | 184631/371472 [3:49:50<15:44:37,  3.30it/s]
 50%|████▉     | 184632/371472 [3:49:50<15:29:44,  3.35it/s]
 50%|████▉     | 184633/371472 [3:49:50<16:07:36,  3.22it/s]
 50%|████▉     | 184634/371472 [3:49:51<16:19:23,  3.18it/s]
 50%|████▉     | 184635/371472 [3:49:51<16:00:57,  3.24it/s]
 50%|████▉     | 184636/371472 [3:49:51<15:24:06,  3.37it/s]
 50%|████▉     | 184637/371472 [3:49:52<15:08:13,  3.43it/s]
 50%|████▉     | 184638/371472 [3:49:52<15:11:53,  3.41it/s]
 50%|████▉     | 184639/371472 [3:49:52<15:37:45,  3.32it/s]
 50%|████▉     | 184640/371472 [3:49:53<15:23:35,  3.37it/s]
                                                            
{'loss': 2.8274, 'learning_rate': 5.528992221336378e-07, 'epoch': 7.95}
+
 50%|████▉     | 184640/371472 [3:49:53<15:23:35,  3.37it/s]
 50%|████▉     | 184641/371472 [3:49:53<15:18:25,  3.39it/s]
 50%|████▉     | 184642/371472 [3:49:53<15:57:14,  3.25it/s]
 50%|████▉     | 184643/371472 [3:49:53<15:40:10,  3.31it/s]
 50%|████▉     | 184644/371472 [3:49:54<15:59:29,  3.25it/s]
 50%|████▉     | 184645/371472 [3:49:54<15:48:12,  3.28it/s]
 50%|████▉     | 184646/371472 [3:49:54<15:37:08,  3.32it/s]
 50%|████▉     | 184647/371472 [3:49:55<15:24:03,  3.37it/s]
 50%|████▉     | 184648/371472 [3:49:55<15:59:17,  3.25it/s]
 50%|████▉     | 184649/371472 [3:49:55<15:46:31,  3.29it/s]
 50%|████▉     | 184650/371472 [3:49:56<15:28:20,  3.35it/s]
 50%|████▉     | 184651/371472 [3:49:56<16:51:05,  3.08it/s]
 50%|████▉     | 184652/371472 [3:49:56<16:27:44,  3.15it/s]
 50%|████▉     | 184653/371472 [3:49:57<16:10:10,  3.21it/s]
 50%|████▉     | 184654/371472 [3:49:57<16:24:35,  3.16it/s]
 50%|████▉     | 184655/371472 [3:49:57<16:11:25,  3.21it/s]
 50%|████▉     | 184656/371472 [3:49:57<16:15:35,  3.19it/s]
 50%|████▉     | 184657/371472 [3:49:58<15:51:21,  3.27it/s]
 50%|████▉     | 184658/371472 [3:49:58<15:28:30,  3.35it/s]
 50%|████▉     | 184659/371472 [3:49:58<15:24:23,  3.37it/s]
 50%|████▉     | 184660/371472 [3:49:59<15:28:47,  3.35it/s]
                                                            
{'loss': 2.8176, 'learning_rate': 5.52850740158159e-07, 'epoch': 7.95}
+
 50%|████▉     | 184660/371472 [3:49:59<15:28:47,  3.35it/s]
 50%|████▉     | 184661/371472 [3:49:59<16:12:17,  3.20it/s]
 50%|████▉     | 184662/371472 [3:49:59<15:50:11,  3.28it/s]
 50%|████▉     | 184663/371472 [3:50:00<15:27:28,  3.36it/s]
 50%|████▉     | 184664/371472 [3:50:00<15:37:23,  3.32it/s]
 50%|████▉     | 184665/371472 [3:50:00<16:17:08,  3.19it/s]
 50%|████▉     | 184666/371472 [3:50:00<15:45:40,  3.29it/s]
 50%|████▉     | 184667/371472 [3:50:01<15:56:02,  3.26it/s]
 50%|████▉     | 184668/371472 [3:50:01<15:34:29,  3.33it/s]
 50%|████▉     | 184669/371472 [3:50:01<15:41:32,  3.31it/s]
 50%|████▉     | 184670/371472 [3:50:02<16:24:40,  3.16it/s]
 50%|████▉     | 184671/371472 [3:50:02<15:37:04,  3.32it/s]
 50%|████▉     | 184672/371472 [3:50:02<15:13:45,  3.41it/s]
 50%|████▉     | 184673/371472 [3:50:03<15:00:03,  3.46it/s]
 50%|████▉     | 184674/371472 [3:50:03<15:46:18,  3.29it/s]
 50%|████▉     | 184675/371472 [3:50:03<15:36:17,  3.33it/s]
 50%|████▉     | 184676/371472 [3:50:04<15:55:35,  3.26it/s]
 50%|████▉     | 184677/371472 [3:50:04<15:22:38,  3.37it/s]
 50%|████▉     | 184678/371472 [3:50:04<14:58:53,  3.46it/s]
 50%|████▉     | 184679/371472 [3:50:04<14:53:56,  3.48it/s]
 50%|████▉     | 184680/371472 [3:50:05<15:06:29,  3.43it/s]
                                                            
{'loss': 3.1136, 'learning_rate': 5.528022581826801e-07, 'epoch': 7.95}
+
 50%|████▉     | 184680/371472 [3:50:05<15:06:29,  3.43it/s]
 50%|████▉     | 184681/371472 [3:50:05<15:08:33,  3.43it/s]
 50%|████▉     | 184682/371472 [3:50:05<15:09:06,  3.42it/s]
 50%|████▉     | 184683/371472 [3:50:05<14:51:13,  3.49it/s]
 50%|████▉     | 184684/371472 [3:50:06<14:50:01,  3.50it/s]
 50%|████▉     | 184685/371472 [3:50:06<15:04:32,  3.44it/s]
 50%|████▉     | 184686/371472 [3:50:06<14:55:23,  3.48it/s]
 50%|████▉     | 184687/371472 [3:50:07<14:37:15,  3.55it/s]
 50%|████▉     | 184688/371472 [3:50:07<15:08:20,  3.43it/s]
 50%|████▉     | 184689/371472 [3:50:07<14:52:44,  3.49it/s]
 50%|████▉     | 184690/371472 [3:50:08<15:02:27,  3.45it/s]
 50%|████▉     | 184691/371472 [3:50:08<15:04:34,  3.44it/s]
 50%|████▉     | 184692/371472 [3:50:08<14:35:33,  3.56it/s]
 50%|████▉     | 184693/371472 [3:50:08<14:21:58,  3.61it/s]
 50%|████▉     | 184694/371472 [3:50:09<14:45:05,  3.52it/s]
 50%|████▉     | 184695/371472 [3:50:09<15:33:28,  3.33it/s]
 50%|████▉     | 184696/371472 [3:50:09<15:19:25,  3.39it/s]
 50%|████▉     | 184697/371472 [3:50:10<15:14:05,  3.41it/s]
 50%|████▉     | 184698/371472 [3:50:10<15:09:24,  3.42it/s]
 50%|████▉     | 184699/371472 [3:50:10<15:08:12,  3.43it/s]
 50%|████▉     | 184700/371472 [3:50:10<15:49:48,  3.28it/s]
                                                            
{'loss': 2.9203, 'learning_rate': 5.527537762072012e-07, 'epoch': 7.96}
+
 50%|████▉     | 184700/371472 [3:50:10<15:49:48,  3.28it/s]
 50%|████▉     | 184701/371472 [3:50:11<15:38:17,  3.32it/s]
 50%|████▉     | 184702/371472 [3:50:11<15:26:56,  3.36it/s]
 50%|████▉     | 184703/371472 [3:50:11<15:35:25,  3.33it/s]
 50%|████▉     | 184704/371472 [3:50:12<15:51:54,  3.27it/s]
 50%|████▉     | 184705/371472 [3:50:12<15:36:05,  3.33it/s]
 50%|████▉     | 184706/371472 [3:50:12<17:07:07,  3.03it/s]
 50%|████▉     | 184707/371472 [3:50:13<17:40:28,  2.94it/s]
 50%|████▉     | 184708/371472 [3:50:13<17:42:34,  2.93it/s]
 50%|████▉     | 184709/371472 [3:50:13<18:04:40,  2.87it/s]
 50%|████▉     | 184710/371472 [3:50:14<17:24:38,  2.98it/s]
 50%|████▉     | 184711/371472 [3:50:14<16:42:49,  3.10it/s]
 50%|████▉     | 184712/371472 [3:50:14<16:08:17,  3.21it/s]
 50%|████▉     | 184713/371472 [3:50:15<15:39:21,  3.31it/s]
 50%|████▉     | 184714/371472 [3:50:15<15:29:07,  3.35it/s]
 50%|████▉     | 184715/371472 [3:50:15<15:24:25,  3.37it/s]
 50%|████▉     | 184716/371472 [3:50:15<15:14:17,  3.40it/s]
 50%|████▉     | 184717/371472 [3:50:16<14:51:09,  3.49it/s]
 50%|████▉     | 184718/371472 [3:50:16<14:52:59,  3.49it/s]
 50%|████▉     | 184719/371472 [3:50:16<15:00:48,  3.46it/s]
 50%|████▉     | 184720/371472 [3:50:17<15:08:33,  3.43it/s]
                                                            
{'loss': 2.7676, 'learning_rate': 5.527052942317223e-07, 'epoch': 7.96}
+
 50%|████▉     | 184720/371472 [3:50:17<15:08:33,  3.43it/s]
 50%|████▉     | 184721/371472 [3:50:17<15:05:22,  3.44it/s]
 50%|████▉     | 184722/371472 [3:50:17<15:21:00,  3.38it/s]
 50%|████▉     | 184723/371472 [3:50:18<15:22:14,  3.37it/s]
 50%|████▉     | 184724/371472 [3:50:18<15:59:13,  3.24it/s]
 50%|████▉     | 184725/371472 [3:50:18<15:44:26,  3.30it/s]
 50%|████▉     | 184726/371472 [3:50:18<15:30:55,  3.34it/s]
 50%|████▉     | 184727/371472 [3:50:19<15:46:06,  3.29it/s]
 50%|████▉     | 184728/371472 [3:50:19<15:34:16,  3.33it/s]
 50%|████▉     | 184729/371472 [3:50:19<15:25:41,  3.36it/s]
 50%|████▉     | 184730/371472 [3:50:20<15:27:21,  3.36it/s]
 50%|████▉     | 184731/371472 [3:50:20<15:19:56,  3.38it/s]
 50%|████▉     | 184732/371472 [3:50:20<15:31:03,  3.34it/s]
 50%|████▉     | 184733/371472 [3:50:20<15:06:51,  3.43it/s]
 50%|████▉     | 184734/371472 [3:50:21<14:58:17,  3.46it/s]
 50%|████▉     | 184735/371472 [3:50:21<15:23:18,  3.37it/s]
 50%|████▉     | 184736/371472 [3:50:21<15:17:41,  3.39it/s]
 50%|████▉     | 184737/371472 [3:50:22<14:54:43,  3.48it/s]
 50%|████▉     | 184738/371472 [3:50:22<15:12:00,  3.41it/s]
 50%|████▉     | 184739/371472 [3:50:22<15:39:39,  3.31it/s]
 50%|████▉     | 184740/371472 [3:50:23<15:13:06,  3.41it/s]
                                                            
{'loss': 2.9574, 'learning_rate': 5.526568122562434e-07, 'epoch': 7.96}
+
 50%|████▉     | 184740/371472 [3:50:23<15:13:06,  3.41it/s]
 50%|████▉     | 184741/371472 [3:50:23<15:26:12,  3.36it/s]
 50%|████▉     | 184742/371472 [3:50:23<15:30:11,  3.35it/s]
 50%|████▉     | 184743/371472 [3:50:23<15:49:26,  3.28it/s]
 50%|████▉     | 184744/371472 [3:50:24<15:31:02,  3.34it/s]
 50%|████▉     | 184745/371472 [3:50:24<16:07:49,  3.22it/s]
 50%|████▉     | 184746/371472 [3:50:24<15:56:57,  3.25it/s]
 50%|████▉     | 184747/371472 [3:50:25<15:40:23,  3.31it/s]
 50%|████▉     | 184748/371472 [3:50:25<15:19:27,  3.38it/s]
 50%|████▉     | 184749/371472 [3:50:25<15:13:56,  3.41it/s]
 50%|████▉     | 184750/371472 [3:50:26<15:30:08,  3.35it/s]
 50%|████▉     | 184751/371472 [3:50:26<15:28:46,  3.35it/s]
 50%|████▉     | 184752/371472 [3:50:26<15:05:07,  3.44it/s]
 50%|████▉     | 184753/371472 [3:50:27<17:06:41,  3.03it/s]
 50%|████▉     | 184754/371472 [3:50:27<16:08:35,  3.21it/s]
 50%|████▉     | 184755/371472 [3:50:27<15:45:39,  3.29it/s]
 50%|████▉     | 184756/371472 [3:50:27<15:26:34,  3.36it/s]
 50%|████▉     | 184757/371472 [3:50:28<15:06:31,  3.43it/s]
 50%|████▉     | 184758/371472 [3:50:28<15:30:57,  3.34it/s]
 50%|████▉     | 184759/371472 [3:50:28<15:11:02,  3.42it/s]
 50%|████▉     | 184760/371472 [3:50:29<15:24:30,  3.37it/s]
                                                            
{'loss': 2.8543, 'learning_rate': 5.526083302807645e-07, 'epoch': 7.96}
+
 50%|████▉     | 184760/371472 [3:50:29<15:24:30,  3.37it/s]
 50%|████▉     | 184761/371472 [3:50:29<15:20:53,  3.38it/s]
 50%|████▉     | 184762/371472 [3:50:29<15:44:56,  3.29it/s]
 50%|████▉     | 184763/371472 [3:50:30<16:08:33,  3.21it/s]
 50%|████▉     | 184764/371472 [3:50:30<16:00:06,  3.24it/s]
 50%|████▉     | 184765/371472 [3:50:30<16:00:09,  3.24it/s]
 50%|████▉     | 184766/371472 [3:50:30<15:44:54,  3.29it/s]
 50%|█��██▉     | 184767/371472 [3:50:31<15:34:30,  3.33it/s]
 50%|████▉     | 184768/371472 [3:50:31<15:00:42,  3.45it/s]
 50%|████▉     | 184769/371472 [3:50:31<15:11:30,  3.41it/s]
 50%|████▉     | 184770/371472 [3:50:32<15:09:57,  3.42it/s]
 50%|████▉     | 184771/371472 [3:50:32<14:49:07,  3.50it/s]
 50%|████▉     | 184772/371472 [3:50:32<15:13:39,  3.41it/s]
 50%|████▉     | 184773/371472 [3:50:33<17:18:34,  3.00it/s]
 50%|████▉     | 184774/371472 [3:50:33<16:50:42,  3.08it/s]
 50%|████▉     | 184775/371472 [3:50:33<16:19:59,  3.18it/s]
 50%|████▉     | 184776/371472 [3:50:33<16:01:15,  3.24it/s]
 50%|████▉     | 184777/371472 [3:50:34<15:28:36,  3.35it/s]
 50%|████▉     | 184778/371472 [3:50:34<16:47:39,  3.09it/s]
 50%|████▉     | 184779/371472 [3:50:34<15:58:34,  3.25it/s]
 50%|████▉     | 184780/371472 [3:50:35<16:37:31,  3.12it/s]
                                                            
{'loss': 2.7526, 'learning_rate': 5.525598483052855e-07, 'epoch': 7.96}
+
 50%|████▉     | 184780/371472 [3:50:35<16:37:31,  3.12it/s]
 50%|████▉     | 184781/371472 [3:50:35<16:22:42,  3.17it/s]
 50%|████▉     | 184782/371472 [3:50:35<15:53:14,  3.26it/s]
 50%|████▉     | 184783/371472 [3:50:36<15:33:53,  3.33it/s]
 50%|████▉     | 184784/371472 [3:50:36<15:29:41,  3.35it/s]
 50%|████▉     | 184785/371472 [3:50:36<15:36:25,  3.32it/s]
 50%|████▉     | 184786/371472 [3:50:37<15:22:21,  3.37it/s]
 50%|████▉     | 184787/371472 [3:50:37<15:44:59,  3.29it/s]
 50%|████▉     | 184788/371472 [3:50:37<15:10:28,  3.42it/s]
 50%|████▉     | 184789/371472 [3:50:37<15:23:07,  3.37it/s]
 50%|████▉     | 184790/371472 [3:50:38<15:43:29,  3.30it/s]
 50%|████▉     | 184791/371472 [3:50:38<15:56:21,  3.25it/s]
 50%|████▉     | 184792/371472 [3:50:38<17:00:40,  3.05it/s]
 50%|████▉     | 184793/371472 [3:50:39<16:11:19,  3.20it/s]
 50%|████▉     | 184794/371472 [3:50:39<15:53:57,  3.26it/s]
 50%|████▉     | 184795/371472 [3:50:39<17:18:00,  3.00it/s]
 50%|████▉     | 184796/371472 [3:50:40<16:42:21,  3.10it/s]
 50%|████▉     | 184797/371472 [3:50:40<16:21:57,  3.17it/s]
 50%|████▉     | 184798/371472 [3:50:40<16:09:25,  3.21it/s]
 50%|████▉     | 184799/371472 [3:50:41<16:18:40,  3.18it/s]
 50%|████▉     | 184800/371472 [3:50:41<16:03:43,  3.23it/s]
                                                            
{'loss': 2.7772, 'learning_rate': 5.525113663298067e-07, 'epoch': 7.96}
+
 50%|████▉     | 184800/371472 [3:50:41<16:03:43,  3.23it/s]
 50%|████▉     | 184801/371472 [3:50:41<16:18:20,  3.18it/s]
 50%|████▉     | 184802/371472 [3:50:42<15:47:44,  3.28it/s]
 50%|████▉     | 184803/371472 [3:50:42<15:25:46,  3.36it/s]
 50%|████▉     | 184804/371472 [3:50:42<14:52:10,  3.49it/s]
 50%|████▉     | 184805/371472 [3:50:42<15:23:37,  3.37it/s]
 50%|████▉     | 184806/371472 [3:50:43<15:29:04,  3.35it/s]
 50%|████▉     | 184807/371472 [3:50:43<15:03:34,  3.44it/s]
 50%|████▉     | 184808/371472 [3:50:43<15:02:25,  3.45it/s]
 50%|████▉     | 184809/371472 [3:50:44<17:02:20,  3.04it/s]
 50%|████▉     | 184810/371472 [3:50:44<16:43:52,  3.10it/s]
 50%|████▉     | 184811/371472 [3:50:44<16:15:02,  3.19it/s]
 50%|████▉     | 184812/371472 [3:50:45<15:59:56,  3.24it/s]
 50%|████▉     | 184813/371472 [3:50:45<16:02:30,  3.23it/s]
 50%|████▉     | 184814/371472 [3:50:45<15:40:34,  3.31it/s]
 50%|████▉     | 184815/371472 [3:50:45<15:25:14,  3.36it/s]
 50%|████▉     | 184816/371472 [3:50:46<15:12:20,  3.41it/s]
 50%|████▉     | 184817/371472 [3:50:46<15:27:53,  3.35it/s]
 50%|████▉     | 184818/371472 [3:50:46<15:13:55,  3.40it/s]
 50%|████▉     | 184819/371472 [3:50:47<15:09:53,  3.42it/s]
 50%|████▉     | 184820/371472 [3:50:47<15:10:03,  3.42it/s]
                                                            
{'loss': 2.8461, 'learning_rate': 5.524628843543278e-07, 'epoch': 7.96}
+
 50%|████▉     | 184820/371472 [3:50:47<15:10:03,  3.42it/s]
 50%|████▉     | 184821/371472 [3:50:47<15:10:57,  3.41it/s]
 50%|████▉     | 184822/371472 [3:50:48<15:43:58,  3.30it/s]
 50%|████▉     | 184823/371472 [3:50:48<15:40:45,  3.31it/s]
 50%|████▉     | 184824/371472 [3:50:48<15:17:46,  3.39it/s]
 50%|████▉     | 184825/371472 [3:50:48<15:09:42,  3.42it/s]
 50%|████▉     | 184826/371472 [3:50:49<14:56:41,  3.47it/s]
 50%|████▉     | 184827/371472 [3:50:49<14:59:17,  3.46it/s]
 50%|████▉     | 184828/371472 [3:50:49<15:27:34,  3.35it/s]
 50%|████▉     | 184829/371472 [3:50:50<16:12:23,  3.20it/s]
 50%|████▉     | 184830/371472 [3:50:50<15:46:24,  3.29it/s]
 50%|████▉     | 184831/371472 [3:50:50<16:13:53,  3.19it/s]
 50%|████▉     | 184832/371472 [3:50:51<17:00:32,  3.05it/s]
 50%|████▉     | 184833/371472 [3:50:51<16:15:12,  3.19it/s]
 50%|████▉     | 184834/371472 [3:50:51<15:55:29,  3.26it/s]
 50%|████▉     | 184835/371472 [3:50:51<15:34:47,  3.33it/s]
 50%|████▉     | 184836/371472 [3:50:52<15:26:59,  3.36it/s]
 50%|████▉     | 184837/371472 [3:50:52<15:30:58,  3.34it/s]
 50%|████▉     | 184838/371472 [3:50:52<15:49:12,  3.28it/s]
 50%|████▉     | 184839/371472 [3:50:53<15:27:28,  3.35it/s]
 50%|████▉     | 184840/371472 [3:50:53<15:12:15,  3.41it/s]
                                                            
{'loss': 2.8869, 'learning_rate': 5.524144023788489e-07, 'epoch': 7.96}
+
 50%|████▉     | 184840/371472 [3:50:53<15:12:15,  3.41it/s]
 50%|████▉     | 184841/371472 [3:50:53<15:29:17,  3.35it/s]
 50%|████▉     | 184842/371472 [3:50:54<15:14:19,  3.40it/s]
 50%|████▉     | 184843/371472 [3:50:54<15:06:25,  3.43it/s]
 50%|████▉     | 184844/371472 [3:50:54<15:18:26,  3.39it/s]
 50%|████▉     | 184845/371472 [3:50:54<16:17:36,  3.18it/s]
 50%|████▉     | 184846/371472 [3:50:55<15:50:13,  3.27it/s]
 50%|████▉     | 184847/371472 [3:50:55<16:25:05,  3.16it/s]
 50%|████▉     | 184848/371472 [3:50:55<16:01:31,  3.23it/s]
 50%|████▉     | 184849/371472 [3:50:56<15:44:26,  3.29it/s]
 50%|████▉     | 184850/371472 [3:50:56<15:36:50,  3.32it/s]
 50%|████▉     | 184851/371472 [3:50:56<15:45:00,  3.29it/s]
 50%|████▉     | 184852/371472 [3:50:57<15:32:58,  3.33it/s]
 50%|████▉     | 184853/371472 [3:50:57<15:09:28,  3.42it/s]
 50%|████▉     | 184854/371472 [3:50:57<14:51:10,  3.49it/s]
 50%|████▉     | 184855/371472 [3:50:57<15:12:29,  3.41it/s]
 50%|████▉     | 184856/371472 [3:50:58<15:12:17,  3.41it/s]
 50%|████▉     | 184857/371472 [3:50:58<15:33:54,  3.33it/s]
 50%|████▉     | 184858/371472 [3:50:58<15:17:15,  3.39it/s]
 50%|████▉     | 184859/371472 [3:50:59<15:56:16,  3.25it/s]
 50%|████▉     | 184860/371472 [3:50:59<15:31:24,  3.34it/s]
                                                            
{'loss': 2.9518, 'learning_rate': 5.5236592040337e-07, 'epoch': 7.96}
+
 50%|████▉     | 184860/371472 [3:50:59<15:31:24,  3.34it/s]
 50%|████▉     | 184861/371472 [3:50:59<16:16:11,  3.19it/s]
 50%|████▉     | 184862/371472 [3:51:00<16:07:09,  3.22it/s]
 50%|████▉     | 184863/371472 [3:51:00<15:48:00,  3.28it/s]
 50%|████▉     | 184864/371472 [3:51:00<16:46:57,  3.09it/s]
 50%|████▉     | 184865/371472 [3:51:01<16:38:56,  3.11it/s]
 50%|████▉     | 184866/371472 [3:51:01<16:49:52,  3.08it/s]
 50%|████▉     | 184867/371472 [3:51:01<16:09:27,  3.21it/s]
 50%|████▉     | 184868/371472 [3:51:01<15:43:42,  3.30it/s]
 50%|████▉     | 184869/371472 [3:51:02<15:37:33,  3.32it/s]
 50%|████▉     | 184870/371472 [3:51:02<15:41:13,  3.30it/s]
 50%|████▉     | 184871/371472 [3:51:02<15:23:56,  3.37it/s]
 50%|████▉     | 184872/371472 [3:51:03<15:36:49,  3.32it/s]
 50%|████▉     | 184873/371472 [3:51:03<15:28:59,  3.35it/s]
 50%|████▉     | 184874/371472 [3:51:03<15:09:18,  3.42it/s]
 50%|████▉     | 184875/371472 [3:51:04<15:02:28,  3.45it/s]
 50%|████▉     | 184876/371472 [3:51:04<14:52:30,  3.48it/s]
 50%|████▉     | 184877/371472 [3:51:04<14:49:17,  3.50it/s]
 50%|████▉     | 184878/371472 [3:51:04<15:32:30,  3.34it/s]
 50%|████▉     | 184879/371472 [3:51:05<15:14:18,  3.40it/s]
 50%|████▉     | 184880/371472 [3:51:05<15:14:47,  3.40it/s]
                                                            
{'loss': 2.9137, 'learning_rate': 5.523174384278911e-07, 'epoch': 7.96}
+
 50%|████▉     | 184880/371472 [3:51:05<15:14:47,  3.40it/s]
 50%|████▉     | 184881/371472 [3:51:05<15:08:08,  3.42it/s]
 50%|████▉     | 184882/371472 [3:51:06<15:18:03,  3.39it/s]
 50%|████▉     | 184883/371472 [3:51:06<14:54:49,  3.48it/s]
 50%|████▉     | 184884/371472 [3:51:06<14:54:12,  3.48it/s]
 50%|████▉     | 184885/371472 [3:51:06<15:03:58,  3.44it/s]
 50%|████▉     | 184886/371472 [3:51:07<14:55:53,  3.47it/s]
 50%|████▉     | 184887/371472 [3:51:07<15:28:40,  3.35it/s]
 50%|████▉     | 184888/371472 [3:51:07<15:17:18,  3.39it/s]
 50%|████▉     | 184889/371472 [3:51:08<15:23:08,  3.37it/s]
 50%|████▉     | 184890/371472 [3:51:08<15:08:22,  3.42it/s]
 50%|████▉     | 184891/371472 [3:51:08<15:10:12,  3.42it/s]
 50%|████▉     | 184892/371472 [3:51:09<15:08:07,  3.42it/s]
 50%|████▉     | 184893/371472 [3:51:09<15:04:12,  3.44it/s]
 50%|████▉     | 184894/371472 [3:51:09<15:10:19,  3.42it/s]
 50%|████▉     | 184895/371472 [3:51:09<15:08:16,  3.42it/s]
 50%|████▉     | 184896/371472 [3:51:10<15:00:01,  3.46it/s]
 50%|████▉     | 184897/371472 [3:51:10<14:56:10,  3.47it/s]
 50%|████▉     | 184898/371472 [3:51:10<15:08:57,  3.42it/s]
 50%|████▉     | 184899/371472 [3:51:11<15:06:08,  3.43it/s]
 50%|████▉     | 184900/371472 [3:51:11<14:58:14,  3.46it/s]
                                                            
{'loss': 2.8664, 'learning_rate': 5.522689564524122e-07, 'epoch': 7.96}
+
 50%|████▉     | 184900/371472 [3:51:11<14:58:14,  3.46it/s]
 50%|████▉     | 184901/371472 [3:51:11<14:49:54,  3.49it/s]
 50%|████▉     | 184902/371472 [3:51:11<14:37:42,  3.54it/s]
 50%|████▉     | 184903/371472 [3:51:12<14:47:18,  3.50it/s]
 50%|████▉     | 184904/371472 [3:51:12<14:31:46,  3.57it/s]
 50%|████▉     | 184905/371472 [3:51:12<14:45:52,  3.51it/s]
 50%|████▉     | 184906/371472 [3:51:13<14:42:32,  3.52it/s]
 50%|████▉     | 184907/371472 [3:51:13<15:11:14,  3.41it/s]
 50%|████▉     | 184908/371472 [3:51:13<15:03:14,  3.44it/s]
 50%|████▉     | 184909/371472 [3:51:13<14:37:05,  3.55it/s]
 50%|████▉     | 184910/371472 [3:51:14<14:19:16,  3.62it/s]
 50%|████▉     | 184911/371472 [3:51:14<14:13:50,  3.64it/s]
 50%|████▉     | 184912/371472 [3:51:14<14:12:16,  3.65it/s]
 50%|████▉     | 184913/371472 [3:51:14<14:28:21,  3.58it/s]
 50%|████▉     | 184914/371472 [3:51:15<14:56:18,  3.47it/s]
 50%|████▉     | 184915/371472 [3:51:15<16:04:09,  3.22it/s]
 50%|████▉     | 184916/371472 [3:51:15<15:44:50,  3.29it/s]
 50%|████▉     | 184917/371472 [3:51:16<16:11:05,  3.20it/s]
 50%|████▉     | 184918/371472 [3:51:16<15:59:01,  3.24it/s]
 50%|████▉     | 184919/371472 [3:51:16<15:58:28,  3.24it/s]
 50%|████▉     | 184920/371472 [3:51:17<16:21:02,  3.17it/s]
                                                            
{'loss': 3.0343, 'learning_rate': 5.522204744769333e-07, 'epoch': 7.96}
+
 50%|████▉     | 184920/371472 [3:51:17<16:21:02,  3.17it/s]
 50%|████▉     | 184921/371472 [3:51:17<16:01:44,  3.23it/s]
 50%|████▉     | 184922/371472 [3:51:17<15:49:40,  3.27it/s]
 50%|████▉     | 184923/371472 [3:51:18<16:08:20,  3.21it/s]
 50%|████▉     | 184924/371472 [3:51:18<15:35:13,  3.32it/s]
 50%|████▉     | 184925/371472 [3:51:18<15:12:39,  3.41it/s]
 50%|████▉     | 184926/371472 [3:51:18<15:06:26,  3.43it/s]
 50%|████▉     | 184927/371472 [3:51:19<14:59:03,  3.46it/s]
 50%|████▉     | 184928/371472 [3:51:19<14:43:41,  3.52it/s]
 50%|████▉     | 184929/371472 [3:51:19<15:21:41,  3.37it/s]
 50%|████▉     | 184930/371472 [3:51:20<15:31:29,  3.34it/s]
 50%|████▉     | 184931/371472 [3:51:20<15:04:50,  3.44it/s]
 50%|████▉     | 184932/371472 [3:51:20<15:10:57,  3.41it/s]
 50%|████▉     | 184933/371472 [3:51:21<16:52:06,  3.07it/s]
 50%|████▉     | 184934/371472 [3:51:21<17:06:44,  3.03it/s]
 50%|████▉     | 184935/371472 [3:51:21<17:22:58,  2.98it/s]
 50%|████▉     | 184936/371472 [3:51:22<16:52:35,  3.07it/s]
 50%|████▉     | 184937/371472 [3:51:22<16:09:03,  3.21it/s]
 50%|████▉     | 184938/371472 [3:51:22<15:46:01,  3.29it/s]
 50%|████▉     | 184939/371472 [3:51:22<15:55:45,  3.25it/s]
 50%|████▉     | 184940/371472 [3:51:23<16:52:38,  3.07it/s]
                                                            
{'loss': 2.8583, 'learning_rate': 5.521719925014544e-07, 'epoch': 7.97}
+
 50%|████▉     | 184940/371472 [3:51:23<16:52:38,  3.07it/s]
 50%|████▉     | 184941/371472 [3:51:23<16:03:49,  3.23it/s]
 50%|████▉     | 184942/371472 [3:51:23<15:54:06,  3.26it/s]
 50%|████▉     | 184943/371472 [3:51:24<15:20:29,  3.38it/s]
 50%|████▉     | 184944/371472 [3:51:24<15:13:49,  3.40it/s]
 50%|████▉     | 184945/371472 [3:51:24<15:41:59,  3.30it/s]
 50%|████▉     | 184946/371472 [3:51:25<15:57:58,  3.25it/s]
 50%|████▉     | 184947/371472 [3:51:25<17:16:37,  3.00it/s]
 50%|████▉     | 184948/371472 [3:51:25<16:42:54,  3.10it/s]
 50%|████▉     | 184949/371472 [3:51:26<17:09:14,  3.02it/s]
 50%|████▉     | 184950/371472 [3:51:26<16:35:06,  3.12it/s]
 50%|████▉     | 184951/371472 [3:51:26<16:04:04,  3.22it/s]
 50%|████▉     | 184952/371472 [3:51:27<16:06:23,  3.22it/s]
 50%|████▉     | 184953/371472 [3:51:27<15:26:34,  3.36it/s]
 50%|████▉     | 184954/371472 [3:51:27<16:08:35,  3.21it/s]
 50%|████▉     | 184955/371472 [3:51:28<16:39:59,  3.11it/s]
 50%|████▉     | 184956/371472 [3:51:28<16:15:40,  3.19it/s]
 50%|████▉     | 184957/371472 [3:51:28<16:04:00,  3.22it/s]
 50%|████▉     | 184958/371472 [3:51:28<15:28:31,  3.35it/s]
 50%|████▉     | 184959/371472 [3:51:29<15:51:00,  3.27it/s]
 50%|████▉     | 184960/371472 [3:51:29<15:34:05,  3.33it/s]
                                                            
{'loss': 2.7853, 'learning_rate': 5.521235105259756e-07, 'epoch': 7.97}
+
 50%|████▉     | 184960/371472 [3:51:29<15:34:05,  3.33it/s]
 50%|████▉     | 184961/371472 [3:51:29<15:37:23,  3.32it/s]
 50%|████▉     | 184962/371472 [3:51:30<15:17:34,  3.39it/s]
 50%|████▉     | 184963/371472 [3:51:30<15:01:06,  3.45it/s]
 50%|████▉     | 184964/371472 [3:51:30<15:13:21,  3.40it/s]
 50%|████▉     | 184965/371472 [3:51:30<15:05:55,  3.43it/s]
 50%|████▉     | 184966/371472 [3:51:31<15:13:57,  3.40it/s]
 50%|████▉     | 184967/371472 [3:51:31<15:00:04,  3.45it/s]
 50%|████▉     | 184968/371472 [3:51:31<14:53:50,  3.48it/s]
 50%|████▉     | 184969/371472 [3:51:32<14:59:10,  3.46it/s]
 50%|████▉     | 184970/371472 [3:51:32<15:02:01,  3.45it/s]
 50%|████▉     | 184971/371472 [3:51:32<15:18:11,  3.39it/s]
 50%|████▉     | 184972/371472 [3:51:32<14:57:44,  3.46it/s]
 50%|████▉     | 184973/371472 [3:51:33<14:56:29,  3.47it/s]
 50%|████▉     | 184974/371472 [3:51:33<15:25:02,  3.36it/s]
 50%|████▉     | 184975/371472 [3:51:33<15:43:22,  3.29it/s]
 50%|████▉     | 184976/371472 [3:51:34<15:29:28,  3.34it/s]
 50%|████▉     | 184977/371472 [3:51:34<15:47:40,  3.28it/s]
 50%|████▉     | 184978/371472 [3:51:34<17:01:03,  3.04it/s]
 50%|████▉     | 184979/371472 [3:51:35<16:09:36,  3.21it/s]
 50%|████▉     | 184980/371472 [3:51:35<15:41:19,  3.30it/s]
                                                            
{'loss': 2.9354, 'learning_rate': 5.520750285504967e-07, 'epoch': 7.97}
+
 50%|████▉     | 184980/371472 [3:51:35<15:41:19,  3.30it/s]
 50%|████▉     | 184981/371472 [3:51:35<15:28:41,  3.35it/s]
 50%|████▉     | 184982/371472 [3:51:36<15:20:37,  3.38it/s]
 50%|████▉     | 184983/371472 [3:51:36<14:52:53,  3.48it/s]
 50%|████▉     | 184984/371472 [3:51:36<14:43:24,  3.52it/s]
 50%|████▉     | 184985/371472 [3:51:36<14:45:15,  3.51it/s]
 50%|████▉     | 184986/371472 [3:51:37<15:00:24,  3.45it/s]
 50%|████▉     | 184987/371472 [3:51:37<16:12:44,  3.20it/s]
 50%|████▉     | 184988/371472 [3:51:37<16:34:13,  3.13it/s]
 50%|████▉     | 184989/371472 [3:51:38<16:21:13,  3.17it/s]
 50%|████▉     | 184990/371472 [3:51:38<16:07:36,  3.21it/s]
 50%|████▉     | 184991/371472 [3:51:38<15:41:22,  3.30it/s]
 50%|████▉     | 184992/371472 [3:51:39<15:25:00,  3.36it/s]
 50%|████▉     | 184993/371472 [3:51:39<15:27:33,  3.35it/s]
 50%|████▉     | 184994/371472 [3:51:39<15:23:45,  3.36it/s]
 50%|████▉     | 184995/371472 [3:51:39<15:16:37,  3.39it/s]
 50%|████▉     | 184996/371472 [3:51:40<14:46:02,  3.51it/s]
 50%|████▉     | 184997/371472 [3:51:40<14:49:35,  3.49it/s]
 50%|████▉     | 184998/371472 [3:51:40<15:20:45,  3.38it/s]
 50%|████▉     | 184999/371472 [3:51:41<14:56:01,  3.47it/s]
 50%|████▉     | 185000/371472 [3:51:41<15:46:05,  3.28it/s]
                                                            
{'loss': 2.8865, 'learning_rate': 5.520265465750178e-07, 'epoch': 7.97}
+
 50%|████▉     | 185000/371472 [3:51:41<15:46:05,  3.28it/s]
 50%|████▉     | 185001/371472 [3:51:41<15:20:06,  3.38it/s]
 50%|████▉     | 185002/371472 [3:51:41<14:59:25,  3.46it/s]
 50%|████▉     | 185003/371472 [3:51:42<15:11:42,  3.41it/s]
 50%|████▉     | 185004/371472 [3:51:42<15:09:42,  3.42it/s]
 50%|████▉     | 185005/371472 [3:51:42<15:09:53,  3.42it/s]
 50%|████▉     | 185006/371472 [3:51:43<15:00:32,  3.45it/s]
 50%|████▉     | 185007/371472 [3:51:43<15:19:53,  3.38it/s]
 50%|████▉     | 185008/371472 [3:51:43<15:05:18,  3.43it/s]
 50%|████▉     | 185009/371472 [3:51:44<15:52:32,  3.26it/s]
 50%|████▉     | 185010/371472 [3:51:44<16:01:35,  3.23it/s]
 50%|████▉     | 185011/371472 [3:51:44<16:25:16,  3.15it/s]
 50%|████▉     | 185012/371472 [3:51:45<16:41:50,  3.10it/s]
 50%|████▉     | 185013/371472 [3:51:45<16:24:03,  3.16it/s]
 50%|████▉     | 185014/371472 [3:51:45<15:50:42,  3.27it/s]
 50%|████▉     | 185015/371472 [3:51:45<16:21:55,  3.16it/s]
 50%|████▉     | 185016/371472 [3:51:46<16:06:55,  3.21it/s]
 50%|████▉     | 185017/371472 [3:51:46<15:42:30,  3.30it/s]
 50%|████▉     | 185018/371472 [3:51:46<15:36:11,  3.32it/s]
 50%|████▉     | 185019/371472 [3:51:47<16:05:59,  3.22it/s]
 50%|████▉     | 185020/371472 [3:51:47<16:03:13,  3.23it/s]
                                                            
{'loss': 2.6633, 'learning_rate': 5.519780645995389e-07, 'epoch': 7.97}
+
 50%|████▉     | 185020/371472 [3:51:47<16:03:13,  3.23it/s]
 50%|████▉     | 185021/371472 [3:51:47<16:10:36,  3.20it/s]
 50%|████▉     | 185022/371472 [3:51:48<16:18:05,  3.18it/s]
 50%|████▉     | 185023/371472 [3:51:48<16:23:35,  3.16it/s]
 50%|████▉     | 185024/371472 [3:51:48<15:55:15,  3.25it/s]
 50%|████▉     | 185025/371472 [3:51:49<15:51:21,  3.27it/s]
 50%|████▉     | 185026/371472 [3:51:49<15:54:59,  3.25it/s]
 50%|████▉     | 185027/371472 [3:51:49<15:56:11,  3.25it/s]
 50%|████▉     | 185028/371472 [3:51:49<15:46:49,  3.28it/s]
 50%|████▉     | 185029/371472 [3:51:50<15:47:20,  3.28it/s]
 50%|████▉     | 185030/371472 [3:51:50<15:44:19,  3.29it/s]
 50%|████▉     | 185031/371472 [3:51:50<15:19:41,  3.38it/s]
 50%|████▉     | 185032/371472 [3:51:51<15:16:06,  3.39it/s]
 50%|████▉     | 185033/371472 [3:51:51<15:30:24,  3.34it/s]
 50%|████▉     | 185034/371472 [3:51:51<15:04:03,  3.44it/s]
 50%|████▉     | 185035/371472 [3:51:52<14:58:28,  3.46it/s]
 50%|████▉     | 185036/371472 [3:51:52<15:44:26,  3.29it/s]
 50%|████▉     | 185037/371472 [3:51:52<15:29:07,  3.34it/s]
 50%|████▉     | 185038/371472 [3:51:52<14:58:22,  3.46it/s]
 50%|████▉     | 185039/371472 [3:51:53<15:23:51,  3.36it/s]
 50%|████▉     | 185040/371472 [3:51:53<15:36:36,  3.32it/s]
                                                            
{'loss': 2.8873, 'learning_rate': 5.5192958262406e-07, 'epoch': 7.97}
+
 50%|████▉     | 185040/371472 [3:51:53<15:36:36,  3.32it/s]
 50%|████▉     | 185041/371472 [3:51:53<15:28:22,  3.35it/s]
 50%|████▉     | 185042/371472 [3:51:54<15:06:42,  3.43it/s]
 50%|████▉     | 185043/371472 [3:51:54<15:03:59,  3.44it/s]
 50%|████▉     | 185044/371472 [3:51:54<14:40:28,  3.53it/s]
 50%|████▉     | 185045/371472 [3:51:54<15:33:23,  3.33it/s]
 50%|████▉     | 185046/371472 [3:51:55<15:37:05,  3.32it/s]
 50%|████▉     | 185047/371472 [3:51:55<15:34:36,  3.32it/s]
 50%|████▉     | 185048/371472 [3:51:55<15:54:48,  3.25it/s]
 50%|████▉     | 185049/371472 [3:51:56<16:15:32,  3.18it/s]
 50%|████▉     | 185050/371472 [3:51:56<16:05:17,  3.22it/s]
 50%|████▉     | 185051/371472 [3:51:56<16:05:06,  3.22it/s]
 50%|████▉     | 185052/371472 [3:51:57<15:45:23,  3.29it/s]
 50%|████▉     | 185053/371472 [3:51:57<15:53:05,  3.26it/s]
 50%|████▉     | 185054/371472 [3:51:57<16:06:23,  3.22it/s]
 50%|████▉     | 185055/371472 [3:51:58<17:03:46,  3.03it/s]
 50%|████▉     | 185056/371472 [3:51:58<16:37:55,  3.11it/s]
 50%|████▉     | 185057/371472 [3:51:58<17:16:10,  3.00it/s]
 50%|████▉     | 185058/371472 [3:51:59<17:14:19,  3.00it/s]
 50%|████▉     | 185059/371472 [3:51:59<17:25:40,  2.97it/s]
 50%|████▉     | 185060/371472 [3:51:59<16:41:17,  3.10it/s]
                                                            
{'loss': 2.9029, 'learning_rate': 5.518811006485811e-07, 'epoch': 7.97}
+
 50%|████▉     | 185060/371472 [3:51:59<16:41:17,  3.10it/s]
 50%|████▉     | 185061/371472 [3:52:00<16:13:53,  3.19it/s]
 50%|████▉     | 185062/371472 [3:52:00<16:50:21,  3.07it/s]
 50%|████▉     | 185063/371472 [3:52:00<16:12:51,  3.19it/s]
 50%|████▉     | 185064/371472 [3:52:00<15:47:59,  3.28it/s]
 50%|████▉     | 185065/371472 [3:52:01<16:38:22,  3.11it/s]
 50%|████▉     | 185066/371472 [3:52:01<16:44:32,  3.09it/s]
 50%|████▉     | 185067/371472 [3:52:02<17:08:07,  3.02it/s]
 50%|████▉     | 185068/371472 [3:52:02<16:24:38,  3.16it/s]
 50%|████▉     | 185069/371472 [3:52:02<15:50:58,  3.27it/s]
 50%|████▉     | 185070/371472 [3:52:02<15:42:12,  3.30it/s]
 50%|████▉     | 185071/371472 [3:52:03<15:47:28,  3.28it/s]
 50%|████▉     | 185072/371472 [3:52:03<15:13:46,  3.40it/s]
 50%|████▉     | 185073/371472 [3:52:03<15:16:05,  3.39it/s]
 50%|████▉     | 185074/371472 [3:52:04<15:39:54,  3.31it/s]
 50%|████▉     | 185075/371472 [3:52:04<15:43:08,  3.29it/s]
 50%|████▉     | 185076/371472 [3:52:04<15:36:20,  3.32it/s]
 50%|████▉     | 185077/371472 [3:52:04<15:35:16,  3.32it/s]
 50%|████▉     | 185078/371472 [3:52:05<16:35:26,  3.12it/s]
 50%|████▉     | 185079/371472 [3:52:05<16:17:36,  3.18it/s]
 50%|████▉     | 185080/371472 [3:52:06<16:51:27,  3.07it/s]
                                                            
{'loss': 2.666, 'learning_rate': 5.518326186731021e-07, 'epoch': 7.97}
+
 50%|████▉     | 185080/371472 [3:52:06<16:51:27,  3.07it/s]
 50%|████▉     | 185081/371472 [3:52:06<16:59:09,  3.05it/s]
 50%|████▉     | 185082/371472 [3:52:06<16:21:34,  3.16it/s]
 50%|████▉     | 185083/371472 [3:52:06<16:06:55,  3.21it/s]
 50%|████▉     | 185084/371472 [3:52:07<16:05:08,  3.22it/s]
 50%|████▉     | 185085/371472 [3:52:07<16:39:08,  3.11it/s]
 50%|████▉     | 185086/371472 [3:52:07<16:09:13,  3.21it/s]
 50%|████▉     | 185087/371472 [3:52:08<16:44:47,  3.09it/s]
 50%|████▉     | 185088/371472 [3:52:08<16:22:36,  3.16it/s]
 50%|████▉     | 185089/371472 [3:52:08<15:55:03,  3.25it/s]
 50%|████▉     | 185090/371472 [3:52:09<15:33:10,  3.33it/s]
 50%|████▉     | 185091/371472 [3:52:09<15:31:29,  3.33it/s]
 50%|████▉     | 185092/371472 [3:52:09<15:40:22,  3.30it/s]
 50%|████▉     | 185093/371472 [3:52:10<15:45:09,  3.29it/s]
 50%|████▉     | 185094/371472 [3:52:10<15:24:30,  3.36it/s]
 50%|████▉     | 185095/371472 [3:52:10<14:50:55,  3.49it/s]
 50%|████▉     | 185096/371472 [3:52:10<14:57:33,  3.46it/s]
 50%|████▉     | 185097/371472 [3:52:11<14:44:53,  3.51it/s]
 50%|████▉     | 185098/371472 [3:52:11<15:13:55,  3.40it/s]
 50%|████▉     | 185099/371472 [3:52:11<15:24:06,  3.36it/s]
 50%|████▉     | 185100/371472 [3:52:12<15:40:00,  3.30it/s]
                                                            
{'loss': 2.9847, 'learning_rate': 5.517841366976233e-07, 'epoch': 7.97}
+
 50%|████▉     | 185100/371472 [3:52:12<15:40:00,  3.30it/s]
 50%|████▉     | 185101/371472 [3:52:12<15:55:59,  3.25it/s]
 50%|████▉     | 185102/371472 [3:52:12<15:21:08,  3.37it/s]
 50%|████▉     | 185103/371472 [3:52:12<15:17:41,  3.38it/s]
 50%|████▉     | 185104/371472 [3:52:13<15:36:59,  3.32it/s]
 50%|████▉     | 185105/371472 [3:52:13<16:55:32,  3.06it/s]
 50%|████▉     | 185106/371472 [3:52:13<16:26:54,  3.15it/s]
 50%|████▉     | 185107/371472 [3:52:14<16:33:40,  3.13it/s]
 50%|████▉     | 185108/371472 [3:52:14<15:55:41,  3.25it/s]
 50%|████▉     | 185109/371472 [3:52:14<16:13:26,  3.19it/s]
 50%|████▉     | 185110/371472 [3:52:15<16:10:35,  3.20it/s]
 50%|████▉     | 185111/371472 [3:52:15<17:56:14,  2.89it/s]
 50%|████▉     | 185112/371472 [3:52:15<17:14:23,  3.00it/s]
 50%|████▉     | 185113/371472 [3:52:16<17:04:01,  3.03it/s]
 50%|████▉     | 185114/371472 [3:52:16<16:02:15,  3.23it/s]
 50%|████▉     | 185115/371472 [3:52:16<16:25:27,  3.15it/s]
 50%|████▉     | 185116/371472 [3:52:17<15:43:27,  3.29it/s]
 50%|████▉     | 185117/371472 [3:52:17<16:13:48,  3.19it/s]
 50%|████▉     | 185118/371472 [3:52:17<16:37:14,  3.11it/s]
 50%|████▉     | 185119/371472 [3:52:18<16:42:55,  3.10it/s]
 50%|████▉     | 185120/371472 [3:52:18<16:28:11,  3.14it/s]
                                                            
{'loss': 2.8482, 'learning_rate': 5.517356547221444e-07, 'epoch': 7.97}
+
 50%|████▉     | 185120/371472 [3:52:18<16:28:11,  3.14it/s]
 50%|████▉     | 185121/371472 [3:52:18<16:53:13,  3.07it/s]
 50%|████▉     | 185122/371472 [3:52:19<16:47:06,  3.08it/s]
 50%|████▉     | 185123/371472 [3:52:19<16:25:57,  3.15it/s]
 50%|████▉     | 185124/371472 [3:52:19<16:13:06,  3.19it/s]
 50%|████▉     | 185125/371472 [3:52:20<16:14:55,  3.19it/s]
 50%|████▉     | 185126/371472 [3:52:20<15:54:37,  3.25it/s]
 50%|████▉     | 185127/371472 [3:52:20<16:14:29,  3.19it/s]
 50%|████▉     | 185128/371472 [3:52:20<15:55:58,  3.25it/s]
 50%|████▉     | 185129/371472 [3:52:21<15:44:34,  3.29it/s]
 50%|████▉     | 185130/371472 [3:52:21<15:59:07,  3.24it/s]
 50%|████▉     | 185131/371472 [3:52:21<15:55:40,  3.25it/s]
 50%|████▉     | 185132/371472 [3:52:22<15:26:29,  3.35it/s]
 50%|████▉     | 185133/371472 [3:52:22<15:54:31,  3.25it/s]
 50%|████▉     | 185134/371472 [3:52:22<16:17:41,  3.18it/s]
 50%|████▉     | 185135/371472 [3:52:23<17:10:32,  3.01it/s]
 50%|████▉     | 185136/371472 [3:52:23<16:58:53,  3.05it/s]
 50%|████▉     | 185137/371472 [3:52:23<16:25:41,  3.15it/s]
 50%|████▉     | 185138/371472 [3:52:24<16:12:09,  3.19it/s]
 50%|████▉     | 185139/371472 [3:52:24<16:00:26,  3.23it/s]
 50%|████▉     | 185140/371472 [3:52:24<15:47:21,  3.28it/s]
                                                            
{'loss': 2.8324, 'learning_rate': 5.516871727466655e-07, 'epoch': 7.97}
+
 50%|████▉     | 185140/371472 [3:52:24<15:47:21,  3.28it/s]
 50%|████▉     | 185141/371472 [3:52:24<15:35:48,  3.32it/s]
 50%|████▉     | 185142/371472 [3:52:25<15:16:46,  3.39it/s]
 50%|████▉     | 185143/371472 [3:52:25<14:46:27,  3.50it/s]
 50%|████▉     | 185144/371472 [3:52:25<15:10:21,  3.41it/s]
 50%|████▉     | 185145/371472 [3:52:26<14:50:19,  3.49it/s]
 50%|████▉     | 185146/371472 [3:52:26<15:11:38,  3.41it/s]
 50%|████▉     | 185147/371472 [3:52:26<15:16:23,  3.39it/s]
 50%|████▉     | 185148/371472 [3:52:26<15:02:43,  3.44it/s]
 50%|████▉     | 185149/371472 [3:52:27<15:44:52,  3.29it/s]
 50%|████▉     | 185150/371472 [3:52:27<15:24:44,  3.36it/s]
 50%|████▉     | 185151/371472 [3:52:27<15:01:45,  3.44it/s]
 50%|████▉     | 185152/371472 [3:52:28<15:35:40,  3.32it/s]
 50%|████▉     | 185153/371472 [3:52:28<16:24:25,  3.15it/s]
 50%|████▉     | 185154/371472 [3:52:28<16:03:14,  3.22it/s]
 50%|████▉     | 185155/371472 [3:52:29<16:01:39,  3.23it/s]
 50%|████▉     | 185156/371472 [3:52:29<15:43:25,  3.29it/s]
 50%|████▉     | 185157/371472 [3:52:29<15:25:54,  3.35it/s]
 50%|████▉     | 185158/371472 [3:52:30<15:50:21,  3.27it/s]
 50%|████▉     | 185159/371472 [3:52:30<16:00:35,  3.23it/s]
 50%|████▉     | 185160/371472 [3:52:30<15:42:45,  3.29it/s]
                                                            
{'loss': 3.0191, 'learning_rate': 5.516386907711865e-07, 'epoch': 7.98}
+
 50%|████▉     | 185160/371472 [3:52:30<15:42:45,  3.29it/s]
 50%|████▉     | 185161/371472 [3:52:30<15:39:13,  3.31it/s]
 50%|████▉     | 185162/371472 [3:52:31<15:35:37,  3.32it/s]
 50%|████▉     | 185163/371472 [3:52:31<16:02:57,  3.22it/s]
 50%|████▉     | 185164/371472 [3:52:31<16:00:54,  3.23it/s]
 50%|████▉     | 185165/371472 [3:52:32<17:14:55,  3.00it/s]
 50%|████▉     | 185166/371472 [3:52:32<16:39:11,  3.11it/s]
 50%|████▉     | 185167/371472 [3:52:32<16:34:30,  3.12it/s]
 50%|████▉     | 185168/371472 [3:52:33<16:16:52,  3.18it/s]
 50%|████▉     | 185169/371472 [3:52:33<16:08:50,  3.20it/s]
 50%|████▉     | 185170/371472 [3:52:33<15:53:57,  3.25it/s]
 50%|████▉     | 185171/371472 [3:52:34<15:53:36,  3.26it/s]
 50%|████▉     | 185172/371472 [3:52:34<15:44:15,  3.29it/s]
 50%|████▉     | 185173/371472 [3:52:34<16:26:12,  3.15it/s]
 50%|████▉     | 185174/371472 [3:52:35<15:58:35,  3.24it/s]
 50%|████▉     | 185175/371472 [3:52:35<16:27:34,  3.14it/s]
 50%|████▉     | 185176/371472 [3:52:35<16:49:30,  3.08it/s]
 50%|████▉     | 185177/371472 [3:52:36<16:24:58,  3.15it/s]
 50%|████▉     | 185178/371472 [3:52:36<16:10:36,  3.20it/s]
 50%|████▉     | 185179/371472 [3:52:36<16:09:36,  3.20it/s]
 50%|████▉     | 185180/371472 [3:52:36<15:56:40,  3.25it/s]
                                                            
{'loss': 2.8666, 'learning_rate': 5.515902087957077e-07, 'epoch': 7.98}
+
 50%|████▉     | 185180/371472 [3:52:36<15:56:40,  3.25it/s]
 50%|████▉     | 185181/371472 [3:52:37<16:01:38,  3.23it/s]
 50%|████▉     | 185182/371472 [3:52:37<18:33:20,  2.79it/s]
 50%|████▉     | 185183/371472 [3:52:37<17:27:21,  2.96it/s]
 50%|████▉     | 185184/371472 [3:52:38<16:45:12,  3.09it/s]
 50%|████▉     | 185185/371472 [3:52:38<16:15:13,  3.18it/s]
 50%|████▉     | 185186/371472 [3:52:38<15:40:52,  3.30it/s]
 50%|████▉     | 185187/371472 [3:52:39<15:17:29,  3.38it/s]
 50%|████▉     | 185188/371472 [3:52:39<15:37:34,  3.31it/s]
 50%|████▉     | 185189/371472 [3:52:39<15:38:56,  3.31it/s]
 50%|████▉     | 185190/371472 [3:52:40<15:14:10,  3.40it/s]
 50%|████▉     | 185191/371472 [3:52:40<14:59:25,  3.45it/s]
 50%|████▉     | 185192/371472 [3:52:40<15:03:35,  3.44it/s]
 50%|████▉     | 185193/371472 [3:52:40<15:13:26,  3.40it/s]
 50%|████▉     | 185194/371472 [3:52:41<14:57:37,  3.46it/s]
 50%|████▉     | 185195/371472 [3:52:41<15:44:56,  3.29it/s]
 50%|████▉     | 185196/371472 [3:52:41<15:20:34,  3.37it/s]
 50%|████▉     | 185197/371472 [3:52:42<15:29:37,  3.34it/s]
 50%|████▉     | 185198/371472 [3:52:42<15:09:06,  3.41it/s]
 50%|████▉     | 185199/371472 [3:52:42<15:29:49,  3.34it/s]
 50%|████▉     | 185200/371472 [3:52:42<15:24:49,  3.36it/s]
                                                            
{'loss': 3.0354, 'learning_rate': 5.515417268202289e-07, 'epoch': 7.98}
+
 50%|████▉     | 185200/371472 [3:52:42<15:24:49,  3.36it/s]
 50%|████▉     | 185201/371472 [3:52:43<15:32:09,  3.33it/s]
 50%|████▉     | 185202/371472 [3:52:43<17:04:14,  3.03it/s]
 50%|████▉     | 185203/371472 [3:52:44<16:58:22,  3.05it/s]
 50%|████▉     | 185204/371472 [3:52:44<16:32:46,  3.13it/s]
 50%|████▉     | 185205/371472 [3:52:44<16:23:46,  3.16it/s]
 50%|████▉     | 185206/371472 [3:52:44<16:08:26,  3.21it/s]
 50%|████▉     | 185207/371472 [3:52:45<15:54:43,  3.25it/s]
 50%|██���█▉     | 185208/371472 [3:52:45<16:19:13,  3.17it/s]
 50%|████▉     | 185209/371472 [3:52:45<16:23:03,  3.16it/s]
 50%|████▉     | 185210/371472 [3:52:46<16:08:10,  3.21it/s]
 50%|████▉     | 185211/371472 [3:52:46<15:32:34,  3.33it/s]
 50%|████▉     | 185212/371472 [3:52:46<15:21:23,  3.37it/s]
 50%|████▉     | 185213/371472 [3:52:47<16:25:23,  3.15it/s]
 50%|████▉     | 185214/371472 [3:52:47<16:05:48,  3.21it/s]
 50%|████▉     | 185215/371472 [3:52:47<15:54:59,  3.25it/s]
 50%|████▉     | 185216/371472 [3:52:48<15:56:13,  3.25it/s]
 50%|████▉     | 185217/371472 [3:52:48<15:37:08,  3.31it/s]
 50%|████▉     | 185218/371472 [3:52:48<15:38:58,  3.31it/s]
 50%|████▉     | 185219/371472 [3:52:48<15:37:40,  3.31it/s]
 50%|████▉     | 185220/371472 [3:52:49<15:06:06,  3.43it/s]
                                                            
{'loss': 2.9946, 'learning_rate': 5.5149324484475e-07, 'epoch': 7.98}
+
 50%|████▉     | 185220/371472 [3:52:49<15:06:06,  3.43it/s]
 50%|████▉     | 185221/371472 [3:52:49<15:13:50,  3.40it/s]
 50%|████▉     | 185222/371472 [3:52:49<15:34:12,  3.32it/s]
 50%|████▉     | 185223/371472 [3:52:50<15:54:13,  3.25it/s]
 50%|████▉     | 185224/371472 [3:52:50<16:01:47,  3.23it/s]
 50%|████▉     | 185225/371472 [3:52:50<15:58:58,  3.24it/s]
 50%|████▉     | 185226/371472 [3:52:51<15:34:39,  3.32it/s]
 50%|████▉     | 185227/371472 [3:52:51<15:28:46,  3.34it/s]
 50%|████▉     | 185228/371472 [3:52:51<15:00:46,  3.45it/s]
 50%|████▉     | 185229/371472 [3:52:51<15:12:35,  3.40it/s]
 50%|████▉     | 185230/371472 [3:52:52<15:12:20,  3.40it/s]
 50%|████▉     | 185231/371472 [3:52:52<15:13:15,  3.40it/s]
 50%|████▉     | 185232/371472 [3:52:52<15:16:01,  3.39it/s]
 50%|████▉     | 185233/371472 [3:52:53<15:08:50,  3.42it/s]
 50%|████▉     | 185234/371472 [3:52:53<15:16:35,  3.39it/s]
 50%|████▉     | 185235/371472 [3:52:53<17:01:25,  3.04it/s]
 50%|████▉     | 185236/371472 [3:52:54<16:46:47,  3.08it/s]
 50%|████▉     | 185237/371472 [3:52:54<15:53:52,  3.25it/s]
 50%|████▉     | 185238/371472 [3:52:54<16:54:17,  3.06it/s]
 50%|████▉     | 185239/371472 [3:52:55<17:29:42,  2.96it/s]
 50%|████▉     | 185240/371472 [3:52:55<16:33:33,  3.12it/s]
                                                            
{'loss': 2.8819, 'learning_rate': 5.51444762869271e-07, 'epoch': 7.98}
+
 50%|████▉     | 185240/371472 [3:52:55<16:33:33,  3.12it/s]
 50%|████▉     | 185241/371472 [3:52:55<16:47:34,  3.08it/s]
 50%|████▉     | 185242/371472 [3:52:56<16:45:31,  3.09it/s]
 50%|████▉     | 185243/371472 [3:52:56<16:24:35,  3.15it/s]
 50%|████▉     | 185244/371472 [3:52:56<18:31:57,  2.79it/s]
 50%|████▉     | 185245/371472 [3:52:57<18:29:44,  2.80it/s]
 50%|████▉     | 185246/371472 [3:52:57<17:20:26,  2.98it/s]
 50%|████▉     | 185247/371472 [3:52:57<16:45:26,  3.09it/s]
 50%|████▉     | 185248/371472 [3:52:58<17:05:33,  3.03it/s]
 50%|████▉     | 185249/371472 [3:52:58<17:28:45,  2.96it/s]
 50%|████▉     | 185250/371472 [3:52:58<17:03:30,  3.03it/s]
 50%|████▉     | 185251/371472 [3:52:59<16:29:06,  3.14it/s]
 50%|████▉     | 185252/371472 [3:52:59<16:16:47,  3.18it/s]
 50%|████▉     | 185253/371472 [3:52:59<15:47:06,  3.28it/s]
 50%|████▉     | 185254/371472 [3:52:59<15:24:31,  3.36it/s]
 50%|████▉     | 185255/371472 [3:53:00<15:15:11,  3.39it/s]
 50%|████▉     | 185256/371472 [3:53:00<15:12:05,  3.40it/s]
 50%|████▉     | 185257/371472 [3:53:00<15:04:04,  3.43it/s]
 50%|████▉     | 185258/371472 [3:53:01<14:43:14,  3.51it/s]
 50%|████▉     | 185259/371472 [3:53:01<14:47:38,  3.50it/s]
 50%|████▉     | 185260/371472 [3:53:01<14:38:42,  3.53it/s]
                                                            
{'loss': 2.9656, 'learning_rate': 5.513962808937921e-07, 'epoch': 7.98}
+
 50%|████▉     | 185260/371472 [3:53:01<14:38:42,  3.53it/s]
 50%|████▉     | 185261/371472 [3:53:01<15:34:22,  3.32it/s]
 50%|████▉     | 185262/371472 [3:53:02<15:15:19,  3.39it/s]
 50%|████▉     | 185263/371472 [3:53:02<15:02:30,  3.44it/s]
 50%|████▉     | 185264/371472 [3:53:02<15:12:50,  3.40it/s]
 50%|████▉     | 185265/371472 [3:53:03<15:19:39,  3.37it/s]
 50%|████▉     | 185266/371472 [3:53:03<15:27:01,  3.35it/s]
 50%|████▉     | 185267/371472 [3:53:03<15:31:17,  3.33it/s]
 50%|████▉     | 185268/371472 [3:53:03<15:09:37,  3.41it/s]
 50%|████▉     | 185269/371472 [3:53:04<17:00:29,  3.04it/s]
 50%|████▉     | 185270/371472 [3:53:04<16:31:25,  3.13it/s]
 50%|████▉     | 185271/371472 [3:53:05<16:25:36,  3.15it/s]
 50%|████▉     | 185272/371472 [3:53:05<16:08:38,  3.20it/s]
 50%|████▉     | 185273/371472 [3:53:05<15:50:43,  3.26it/s]
 50%|████▉     | 185274/371472 [3:53:05<15:38:58,  3.30it/s]
 50%|████▉     | 185275/371472 [3:53:06<15:41:16,  3.30it/s]
 50%|████▉     | 185276/371472 [3:53:06<15:48:39,  3.27it/s]
 50%|████▉     | 185277/371472 [3:53:06<15:29:35,  3.34it/s]
 50%|████▉     | 185278/371472 [3:53:07<15:52:00,  3.26it/s]
 50%|████▉     | 185279/371472 [3:53:07<15:44:23,  3.29it/s]
 50%|████▉     | 185280/371472 [3:53:07<15:39:36,  3.30it/s]
                                                            
{'loss': 2.8122, 'learning_rate': 5.513477989183132e-07, 'epoch': 7.98}
+
 50%|████▉     | 185280/371472 [3:53:07<15:39:36,  3.30it/s]
 50%|████▉     | 185281/371472 [3:53:08<16:12:29,  3.19it/s]
 50%|████▉     | 185282/371472 [3:53:08<16:07:24,  3.21it/s]
 50%|████▉     | 185283/371472 [3:53:08<15:43:33,  3.29it/s]
 50%|████▉     | 185284/371472 [3:53:08<15:32:07,  3.33it/s]
 50%|████▉     | 185285/371472 [3:53:09<15:01:41,  3.44it/s]
 50%|████▉     | 185286/371472 [3:53:09<15:09:16,  3.41it/s]
 50%|████▉     | 185287/371472 [3:53:09<15:49:43,  3.27it/s]
 50%|████▉     | 185288/371472 [3:53:10<15:20:29,  3.37it/s]
 50%|████▉     | 185289/371472 [3:53:10<16:04:53,  3.22it/s]
 50%|████▉     | 185290/371472 [3:53:10<15:42:19,  3.29it/s]
 50%|████▉     | 185291/371472 [3:53:11<16:03:45,  3.22it/s]
 50%|████▉     | 185292/371472 [3:53:11<16:19:03,  3.17it/s]
 50%|████▉     | 185293/371472 [3:53:11<16:02:59,  3.22it/s]
 50%|████▉     | 185294/371472 [3:53:12<15:56:13,  3.25it/s]
 50%|████▉     | 185295/371472 [3:53:12<15:53:05,  3.26it/s]
 50%|████▉     | 185296/371472 [3:53:12<15:24:52,  3.36it/s]
 50%|████▉     | 185297/371472 [3:53:12<15:41:14,  3.30it/s]
 50%|████▉     | 185298/371472 [3:53:13<15:17:26,  3.38it/s]
 50%|████▉     | 185299/371472 [3:53:13<14:58:30,  3.45it/s]
 50%|████▉     | 185300/371472 [3:53:13<15:26:00,  3.35it/s]
                                                            
{'loss': 2.786, 'learning_rate': 5.512993169428343e-07, 'epoch': 7.98}
+
 50%|████▉     | 185300/371472 [3:53:13<15:26:00,  3.35it/s]
 50%|████▉     | 185301/371472 [3:53:14<16:17:43,  3.17it/s]
 50%|████▉     | 185302/371472 [3:53:14<15:59:20,  3.23it/s]
 50%|████▉     | 185303/371472 [3:53:14<15:41:30,  3.30it/s]
 50%|████▉     | 185304/371472 [3:53:14<15:25:04,  3.35it/s]
 50%|████▉     | 185305/371472 [3:53:15<14:54:16,  3.47it/s]
 50%|████▉     | 185306/371472 [3:53:15<14:57:51,  3.46it/s]
 50%|████▉     | 185307/371472 [3:53:15<15:26:20,  3.35it/s]
 50%|████▉     | 185308/371472 [3:53:16<15:33:35,  3.32it/s]
 50%|████▉     | 185309/371472 [3:53:16<16:08:40,  3.20it/s]
 50%|████▉     | 185310/371472 [3:53:16<15:39:59,  3.30it/s]
 50%|████▉     | 185311/371472 [3:53:17<15:15:28,  3.39it/s]
 50%|████▉     | 185312/371472 [3:53:17<16:08:18,  3.20it/s]
 50%|████▉     | 185313/371472 [3:53:17<15:40:02,  3.30it/s]
 50%|████▉     | 185314/371472 [3:53:18<16:35:31,  3.12it/s]
 50%|████▉     | 185315/371472 [3:53:18<15:52:22,  3.26it/s]
 50%|████▉     | 185316/371472 [3:53:18<15:23:14,  3.36it/s]
 50%|████▉     | 185317/371472 [3:53:18<15:40:55,  3.30it/s]
 50%|████▉     | 185318/371472 [3:53:19<15:31:19,  3.33it/s]
 50%|████▉     | 185319/371472 [3:53:19<15:13:59,  3.39it/s]
 50%|████▉     | 185320/371472 [3:53:19<14:52:30,  3.48it/s]
                                                            
{'loss': 2.9515, 'learning_rate': 5.512508349673554e-07, 'epoch': 7.98}
+
 50%|████▉     | 185320/371472 [3:53:19<14:52:30,  3.48it/s]
 50%|████▉     | 185321/371472 [3:53:20<14:56:35,  3.46it/s]
 50%|████▉     | 185322/371472 [3:53:20<14:53:20,  3.47it/s]
 50%|████▉     | 185323/371472 [3:53:20<14:51:56,  3.48it/s]
 50%|████▉     | 185324/371472 [3:53:20<14:47:25,  3.50it/s]
 50%|████▉     | 185325/371472 [3:53:21<14:51:18,  3.48it/s]
 50%|████▉     | 185326/371472 [3:53:21<15:04:00,  3.43it/s]
 50%|████▉     | 185327/371472 [3:53:21<15:36:33,  3.31it/s]
 50%|████▉     | 185328/371472 [3:53:22<15:26:56,  3.35it/s]
 50%|████▉     | 185329/371472 [3:53:22<15:02:10,  3.44it/s]
 50%|████▉     | 185330/371472 [3:53:22<15:00:51,  3.44it/s]
 50%|████▉     | 185331/371472 [3:53:22<15:03:03,  3.44it/s]
 50%|████▉     | 185332/371472 [3:53:23<14:30:51,  3.56it/s]
 50%|████▉     | 185333/371472 [3:53:23<14:21:05,  3.60it/s]
 50%|████▉     | 185334/371472 [3:53:23<14:57:43,  3.46it/s]
 50%|████▉     | 185335/371472 [3:53:24<14:39:36,  3.53it/s]
 50%|████▉     | 185336/371472 [3:53:24<15:20:40,  3.37it/s]
 50%|████▉     | 185337/371472 [3:53:24<14:51:46,  3.48it/s]
 50%|████▉     | 185338/371472 [3:53:24<14:38:31,  3.53it/s]
 50%|████▉     | 185339/371472 [3:53:25<14:54:44,  3.47it/s]
 50%|████▉     | 185340/371472 [3:53:25<14:40:21,  3.52it/s]
                                                            
{'loss': 2.987, 'learning_rate': 5.512023529918766e-07, 'epoch': 7.98}
+
 50%|████▉     | 185340/371472 [3:53:25<14:40:21,  3.52it/s]
 50%|████▉     | 185341/371472 [3:53:25<14:41:28,  3.52it/s]
 50%|████▉     | 185342/371472 [3:53:26<15:36:16,  3.31it/s]
 50%|████▉     | 185343/371472 [3:53:26<15:38:05,  3.31it/s]
 50%|████▉     | 185344/371472 [3:53:26<16:00:25,  3.23it/s]
 50%|████▉     | 185345/371472 [3:53:27<15:28:34,  3.34it/s]
 50%|████▉     | 185346/371472 [3:53:27<15:14:00,  3.39it/s]
 50%|████▉     | 185347/371472 [3:53:27<15:06:57,  3.42it/s]
 50%|████▉     | 185348/371472 [3:53:27<15:55:34,  3.25it/s]
 50%|████▉     | 185349/371472 [3:53:28<15:50:53,  3.26it/s]
 50%|████▉     | 185350/371472 [3:53:28<15:35:52,  3.31it/s]
 50%|████▉     | 185351/371472 [3:53:28<16:21:35,  3.16it/s]
 50%|████▉     | 185352/371472 [3:53:29<16:15:19,  3.18it/s]
 50%|████▉     | 185353/371472 [3:53:29<16:17:01,  3.17it/s]
 50%|████▉     | 185354/371472 [3:53:29<15:58:05,  3.24it/s]
 50%|████▉     | 185355/371472 [3:53:30<15:46:17,  3.28it/s]
 50%|████▉     | 185356/371472 [3:53:30<15:23:20,  3.36it/s]
 50%|████▉     | 185357/371472 [3:53:30<15:21:24,  3.37it/s]
 50%|████▉     | 185358/371472 [3:53:31<15:16:07,  3.39it/s]
 50%|████▉     | 185359/371472 [3:53:31<15:08:41,  3.41it/s]
 50%|████▉     | 185360/371472 [3:53:31<14:43:33,  3.51it/s]
                                                            
{'loss': 2.78, 'learning_rate': 5.511538710163977e-07, 'epoch': 7.98}
+
 50%|████▉     | 185360/371472 [3:53:31<14:43:33,  3.51it/s]
 50%|████▉     | 185361/371472 [3:53:31<14:44:55,  3.51it/s]
 50%|████▉     | 185362/371472 [3:53:32<14:31:17,  3.56it/s]
 50%|████▉     | 185363/371472 [3:53:32<16:12:02,  3.19it/s]
 50%|████▉     | 185364/371472 [3:53:32<16:19:25,  3.17it/s]
 50%|████▉     | 185365/371472 [3:53:33<15:39:33,  3.30it/s]
 50%|████▉     | 185366/371472 [3:53:33<15:24:39,  3.35it/s]
 50%|████▉     | 185367/371472 [3:53:33<15:01:17,  3.44it/s]
 50%|████▉     | 185368/371472 [3:53:33<14:54:29,  3.47it/s]
 50%|████▉     | 185369/371472 [3:53:34<15:01:28,  3.44it/s]
 50%|████▉     | 185370/371472 [3:53:34<15:02:38,  3.44it/s]
 50%|████▉     | 185371/371472 [3:53:34<15:06:09,  3.42it/s]
 50%|████▉     | 185372/371472 [3:53:35<15:55:32,  3.25it/s]
 50%|████▉     | 185373/371472 [3:53:35<15:40:36,  3.30it/s]
 50%|████▉     | 185374/371472 [3:53:35<15:24:58,  3.35it/s]
 50%|████▉     | 185375/371472 [3:53:36<15:04:39,  3.43it/s]
 50%|████▉     | 185376/371472 [3:53:36<14:57:46,  3.45it/s]
 50%|████▉     | 185377/371472 [3:53:36<15:05:09,  3.43it/s]
 50%|████▉     | 185378/371472 [3:53:36<14:57:49,  3.45it/s]
 50%|████▉     | 185379/371472 [3:53:37<15:04:42,  3.43it/s]
 50%|████▉     | 185380/371472 [3:53:37<14:48:11,  3.49it/s]
                                                            
{'loss': 2.7717, 'learning_rate': 5.511053890409188e-07, 'epoch': 7.98}
+
 50%|████▉     | 185380/371472 [3:53:37<14:48:11,  3.49it/s]
 50%|████▉     | 185381/371472 [3:53:37<15:21:26,  3.37it/s]
 50%|████▉     | 185382/371472 [3:53:38<15:20:38,  3.37it/s]
 50%|████▉     | 185383/371472 [3:53:38<15:12:02,  3.40it/s]
 50%|████▉     | 185384/371472 [3:53:38<14:59:30,  3.45it/s]
 50%|████▉     | 185385/371472 [3:53:38<14:35:43,  3.54it/s]
 50%|████▉     | 185386/371472 [3:53:39<15:14:23,  3.39it/s]
 50%|████▉     | 185387/371472 [3:53:39<14:44:55,  3.50it/s]
 50%|████▉     | 185388/371472 [3:53:39<16:27:26,  3.14it/s]
 50%|████▉     | 185389/371472 [3:53:40<15:59:11,  3.23it/s]
 50%|████▉     | 185390/371472 [3:53:40<16:01:19,  3.23it/s]
 50%|████▉     | 185391/371472 [3:53:40<15:43:47,  3.29it/s]
 50%|████▉     | 185392/371472 [3:53:41<15:54:41,  3.25it/s]
 50%|████▉     | 185393/371472 [3:53:41<16:15:36,  3.18it/s]
 50%|████▉     | 185394/371472 [3:53:41<15:56:26,  3.24it/s]
 50%|████▉     | 185395/371472 [3:53:42<16:21:27,  3.16it/s]
 50%|████▉     | 185396/371472 [3:53:42<15:52:09,  3.26it/s]
 50%|████▉     | 185397/371472 [3:53:42<15:40:31,  3.30it/s]
 50%|████▉     | 185398/371472 [3:53:42<15:35:32,  3.31it/s]
 50%|████▉     | 185399/371472 [3:53:43<15:29:55,  3.33it/s]
 50%|████▉     | 185400/371472 [3:53:43<15:30:06,  3.33it/s]
                                                            
{'loss': 2.9943, 'learning_rate': 5.510569070654398e-07, 'epoch': 7.99}
+
 50%|████▉     | 185400/371472 [3:53:43<15:30:06,  3.33it/s]
 50%|████▉     | 185401/371472 [3:53:43<15:48:06,  3.27it/s]
 50%|████▉     | 185402/371472 [3:53:44<15:52:14,  3.26it/s]
 50%|████▉     | 185403/371472 [3:53:44<15:55:31,  3.25it/s]
 50%|████▉     | 185404/371472 [3:53:44<16:42:45,  3.09it/s]
 50%|████▉     | 185405/371472 [3:53:45<16:39:48,  3.10it/s]
 50%|████▉     | 185406/371472 [3:53:45<16:36:51,  3.11it/s]
 50%|████▉     | 185407/371472 [3:53:45<16:21:22,  3.16it/s]
 50%|████▉     | 185408/371472 [3:53:46<15:51:19,  3.26it/s]
 50%|████▉     | 185409/371472 [3:53:46<15:41:04,  3.30it/s]
 50%|████▉     | 185410/371472 [3:53:46<15:10:44,  3.40it/s]
 50%|████▉     | 185411/371472 [3:53:46<15:29:28,  3.34it/s]
 50%|████▉     | 185412/371472 [3:53:47<16:51:47,  3.06it/s]
 50%|████▉     | 185413/371472 [3:53:47<16:10:40,  3.19it/s]
 50%|████▉     | 185414/371472 [3:53:47<15:41:23,  3.29it/s]
 50%|████▉     | 185415/371472 [3:53:48<15:30:54,  3.33it/s]
 50%|████▉     | 185416/371472 [3:53:48<15:17:47,  3.38it/s]
 50%|████▉     | 185417/371472 [3:53:48<15:04:32,  3.43it/s]
 50%|████▉     | 185418/371472 [3:53:49<15:57:14,  3.24it/s]
 50%|████▉     | 185419/371472 [3:53:49<15:58:25,  3.24it/s]
 50%|████▉     | 185420/371472 [3:53:49<16:09:10,  3.20it/s]
                                                            
{'loss': 2.9615, 'learning_rate': 5.51008425089961e-07, 'epoch': 7.99}
+
 50%|████▉     | 185420/371472 [3:53:49<16:09:10,  3.20it/s]
 50%|████▉     | 185421/371472 [3:53:50<15:48:39,  3.27it/s]
 50%|████▉     | 185422/371472 [3:53:50<15:55:13,  3.25it/s]
 50%|████▉     | 185423/371472 [3:53:50<15:34:47,  3.32it/s]
 50%|████▉     | 185424/371472 [3:53:50<15:11:48,  3.40it/s]
 50%|████▉     | 185425/371472 [3:53:51<15:39:55,  3.30it/s]
 50%|████▉     | 185426/371472 [3:53:51<15:17:49,  3.38it/s]
 50%|████▉     | 185427/371472 [3:53:51<15:08:16,  3.41it/s]
 50%|████▉     | 185428/371472 [3:53:52<15:14:34,  3.39it/s]
 50%|████▉     | 185429/371472 [3:53:52<15:17:43,  3.38it/s]
 50%|████▉     | 185430/371472 [3:53:52<15:12:06,  3.40it/s]
 50%|████▉     | 185431/371472 [3:53:53<15:56:41,  3.24it/s]
 50%|████▉     | 185432/371472 [3:53:53<16:15:10,  3.18it/s]
 50%|████▉     | 185433/371472 [3:53:53<15:39:27,  3.30it/s]
 50%|████▉     | 185434/371472 [3:53:53<15:32:31,  3.32it/s]
 50%|████▉     | 185435/371472 [3:53:54<16:03:01,  3.22it/s]
 50%|████▉     | 185436/371472 [3:53:54<15:44:30,  3.28it/s]
 50%|████▉     | 185437/371472 [3:53:54<15:27:49,  3.34it/s]
 50%|████▉     | 185438/371472 [3:53:55<14:59:29,  3.45it/s]
 50%|████▉     | 185439/371472 [3:53:55<16:24:13,  3.15it/s]
 50%|████▉     | 185440/371472 [3:53:55<17:27:29,  2.96it/s]
                                                            
{'loss': 2.8716, 'learning_rate': 5.50959943114482e-07, 'epoch': 7.99}
+
 50%|████▉     | 185440/371472 [3:53:55<17:27:29,  2.96it/s]
 50%|████▉     | 185441/371472 [3:53:56<16:37:48,  3.11it/s]
 50%|████▉     | 185442/371472 [3:53:56<16:15:00,  3.18it/s]
 50%|████▉     | 185443/371472 [3:53:56<16:33:06,  3.12it/s]
 50%|████▉     | 185444/371472 [3:53:57<15:38:51,  3.30it/s]
 50%|████▉     | 185445/371472 [3:53:57<15:51:22,  3.26it/s]
 50%|████▉     | 185446/371472 [3:53:57<15:35:07,  3.32it/s]
 50%|████▉     | 185447/371472 [3:53:58<16:13:59,  3.18it/s]
 50%|████▉     | 185448/371472 [3:53:58<15:52:26,  3.26it/s]
 50%|████▉     | 185449/371472 [3:53:58<16:55:20,  3.05it/s]
 50%|████▉     | 185450/371472 [3:53:59<17:46:27,  2.91it/s]
 50%|████▉     | 185451/371472 [3:53:59<16:54:00,  3.06it/s]
 50%|████▉     | 185452/371472 [3:53:59<16:15:14,  3.18it/s]
 50%|████▉     | 185453/371472 [3:53:59<16:15:27,  3.18it/s]
 50%|████▉     | 185454/371472 [3:54:00<15:52:07,  3.26it/s]
 50%|████▉     | 185455/371472 [3:54:00<16:54:17,  3.06it/s]
 50%|████▉     | 185456/371472 [3:54:00<15:58:56,  3.23it/s]
 50%|████▉     | 185457/371472 [3:54:01<16:16:01,  3.18it/s]
 50%|████▉     | 185458/371472 [3:54:01<15:38:31,  3.30it/s]
 50%|████▉     | 185459/371472 [3:54:01<15:26:00,  3.35it/s]
 50%|████▉     | 185460/371472 [3:54:02<15:13:24,  3.39it/s]
                                                            
{'loss': 2.7545, 'learning_rate': 5.509114611390031e-07, 'epoch': 7.99}
+
 50%|████▉     | 185460/371472 [3:54:02<15:13:24,  3.39it/s]
 50%|████▉     | 185461/371472 [3:54:02<14:40:55,  3.52it/s]
 50%|████▉     | 185462/371472 [3:54:02<14:39:28,  3.53it/s]
 50%|████▉     | 185463/371472 [3:54:02<14:37:59,  3.53it/s]
 50%|████▉     | 185464/371472 [3:54:03<14:37:49,  3.53it/s]
 50%|████▉     | 185465/371472 [3:54:03<14:36:43,  3.54it/s]
 50%|████▉     | 185466/371472 [3:54:03<14:20:55,  3.60it/s]
 50%|████▉     | 185467/371472 [3:54:03<14:10:32,  3.64it/s]
 50%|████▉     | 185468/371472 [3:54:04<14:38:14,  3.53it/s]
 50%|████▉     | 185469/371472 [3:54:04<14:53:29,  3.47it/s]
 50%|████▉     | 185470/371472 [3:54:04<15:32:57,  3.32it/s]
 50%|████▉     | 185471/371472 [3:54:05<15:25:47,  3.35it/s]
 50%|████▉     | 185472/371472 [3:54:05<15:58:53,  3.23it/s]
 50%|████▉     | 185473/371472 [3:54:05<15:34:15,  3.32it/s]
 50%|████▉     | 185474/371472 [3:54:06<15:23:54,  3.36it/s]
 50%|████▉     | 185475/371472 [3:54:06<15:44:25,  3.28it/s]
 50%|████▉     | 185476/371472 [3:54:06<16:00:19,  3.23it/s]
 50%|████▉     | 185477/371472 [3:54:07<15:59:30,  3.23it/s]
 50%|████▉     | 185478/371472 [3:54:07<15:35:32,  3.31it/s]
 50%|████▉     | 185479/371472 [3:54:07<15:41:16,  3.29it/s]
 50%|████▉     | 185480/371472 [3:54:07<15:37:46,  3.31it/s]
                                                            
{'loss': 2.8347, 'learning_rate': 5.508629791635243e-07, 'epoch': 7.99}
+
 50%|████▉     | 185480/371472 [3:54:07<15:37:46,  3.31it/s]
 50%|████▉     | 185481/371472 [3:54:08<16:07:19,  3.20it/s]
 50%|████▉     | 185482/371472 [3:54:08<16:20:24,  3.16it/s]
 50%|████▉     | 185483/371472 [3:54:08<15:38:33,  3.30it/s]
 50%|████▉     | 185484/371472 [3:54:09<16:17:34,  3.17it/s]
 50%|████▉     | 185485/371472 [3:54:09<16:17:03,  3.17it/s]
 50%|████▉     | 185486/371472 [3:54:09<15:49:51,  3.26it/s]
 50%|████▉     | 185487/371472 [3:54:10<15:49:33,  3.26it/s]
 50%|████▉     | 185488/371472 [3:54:10<15:38:38,  3.30it/s]
 50%|████▉     | 185489/371472 [3:54:10<15:21:52,  3.36it/s]
 50%|████▉     | 185490/371472 [3:54:11<15:55:56,  3.24it/s]
 50%|████▉     | 185491/371472 [3:54:11<15:32:32,  3.32it/s]
 50%|████▉     | 185492/371472 [3:54:11<15:28:07,  3.34it/s]
 50%|████▉     | 185493/371472 [3:54:11<15:24:39,  3.35it/s]
 50%|████▉     | 185494/371472 [3:54:12<15:12:52,  3.40it/s]
 50%|████▉     | 185495/371472 [3:54:12<15:04:59,  3.42it/s]
 50%|████▉     | 185496/371472 [3:54:12<15:04:23,  3.43it/s]
 50%|████▉     | 185497/371472 [3:54:13<15:50:17,  3.26it/s]
 50%|████▉     | 185498/371472 [3:54:13<16:50:53,  3.07it/s]
 50%|████▉     | 185499/371472 [3:54:13<16:21:22,  3.16it/s]
 50%|████▉     | 185500/371472 [3:54:14<16:17:38,  3.17it/s]
                                                            
{'loss': 2.9001, 'learning_rate': 5.508144971880454e-07, 'epoch': 7.99}
+
 50%|████▉     | 185500/371472 [3:54:14<16:17:38,  3.17it/s]
 50%|████▉     | 185501/371472 [3:54:14<15:50:10,  3.26it/s]
 50%|████▉     | 185502/371472 [3:54:14<15:59:30,  3.23it/s]
 50%|████▉     | 185503/371472 [3:54:15<15:58:05,  3.24it/s]
 50%|████▉     | 185504/371472 [3:54:15<15:56:08,  3.24it/s]
 50%|████▉     | 185505/371472 [3:54:15<16:07:55,  3.20it/s]
 50%|████▉     | 185506/371472 [3:54:15<16:10:19,  3.19it/s]
 50%|████▉     | 185507/371472 [3:54:16<15:59:33,  3.23it/s]
 50%|████▉     | 185508/371472 [3:54:16<15:22:16,  3.36it/s]
 50%|████▉     | 185509/371472 [3:54:16<15:21:41,  3.36it/s]
 50%|████▉     | 185510/371472 [3:54:17<15:18:31,  3.37it/s]
 50%|████▉     | 185511/371472 [3:54:17<15:07:34,  3.41it/s]
 50%|████▉     | 185512/371472 [3:54:17<15:06:24,  3.42it/s]
 50%|████▉     | 185513/371472 [3:54:18<15:37:52,  3.30it/s]
 50%|████▉     | 185514/371472 [3:54:18<15:27:47,  3.34it/s]
 50%|████▉     | 185515/371472 [3:54:18<15:12:27,  3.40it/s]
 50%|████▉     | 185516/371472 [3:54:18<16:25:14,  3.15it/s]
 50%|████▉     | 185517/371472 [3:54:19<16:21:22,  3.16it/s]
 50%|████▉     | 185518/371472 [3:54:19<15:57:31,  3.24it/s]
 50%|████▉     | 185519/371472 [3:54:19<15:50:52,  3.26it/s]
 50%|████▉     | 185520/371472 [3:54:20<15:59:20,  3.23it/s]
                                                            
{'loss': 2.9832, 'learning_rate': 5.507660152125665e-07, 'epoch': 7.99}
+
 50%|████▉     | 185520/371472 [3:54:20<15:59:20,  3.23it/s]
 50%|████▉     | 185521/371472 [3:54:20<15:32:14,  3.32it/s]
 50%|████▉     | 185522/371472 [3:54:20<15:42:10,  3.29it/s]
 50%|████▉     | 185523/371472 [3:54:21<15:49:08,  3.27it/s]
 50%|████▉     | 185524/371472 [3:54:21<15:24:41,  3.35it/s]
 50%|████▉     | 185525/371472 [3:54:21<15:45:51,  3.28it/s]
 50%|████▉     | 185526/371472 [3:54:22<15:42:47,  3.29it/s]
 50%|████▉     | 185527/371472 [3:54:22<15:17:51,  3.38it/s]
 50%|████▉     | 185528/371472 [3:54:22<15:39:36,  3.30it/s]
 50%|████▉     | 185529/371472 [3:54:22<15:08:03,  3.41it/s]
 50%|████▉     | 185530/371472 [3:54:23<15:06:09,  3.42it/s]
 50%|████▉     | 185531/371472 [3:54:23<14:49:40,  3.48it/s]
 50%|████▉     | 185532/371472 [3:54:23<15:02:33,  3.43it/s]
 50%|████▉     | 185533/371472 [3:54:24<16:37:23,  3.11it/s]
 50%|████▉     | 185534/371472 [3:54:24<16:17:43,  3.17it/s]
 50%|████▉     | 185535/371472 [3:54:24<16:10:56,  3.19it/s]
 50%|████▉     | 185536/371472 [3:54:25<15:51:32,  3.26it/s]
 50%|████▉     | 185537/371472 [3:54:25<16:00:50,  3.23it/s]
 50%|████▉     | 185538/371472 [3:54:25<16:18:29,  3.17it/s]
 50%|████▉     | 185539/371472 [3:54:25<15:50:04,  3.26it/s]
 50%|████▉     | 185540/371472 [3:54:26<15:20:10,  3.37it/s]
                                                            
{'loss': 2.7182, 'learning_rate': 5.507175332370875e-07, 'epoch': 7.99}
+
 50%|████▉     | 185540/371472 [3:54:26<15:20:10,  3.37it/s]
 50%|████▉     | 185541/371472 [3:54:26<15:23:47,  3.35it/s]
 50%|████▉     | 185542/371472 [3:54:26<16:07:21,  3.20it/s]
 50%|████▉     | 185543/371472 [3:54:27<16:41:58,  3.09it/s]
 50%|████▉     | 185544/371472 [3:54:27<16:06:17,  3.21it/s]
 50%|████▉     | 185545/371472 [3:54:27<15:33:55,  3.32it/s]
 50%|████▉     | 185546/371472 [3:54:28<15:28:41,  3.34it/s]
 50%|████▉     | 185547/371472 [3:54:28<15:44:05,  3.28it/s]
 50%|████▉     | 185548/371472 [3:54:28<15:29:01,  3.34it/s]
 50%|████▉     | 185549/371472 [3:54:28<15:27:28,  3.34it/s]
 50%|████▉     | 185550/371472 [3:54:29<15:11:47,  3.40it/s]
 50%|████▉     | 185551/371472 [3:54:29<16:19:58,  3.16it/s]
 50%|████▉     | 185552/371472 [3:54:29<15:43:28,  3.28it/s]
 50%|████▉     | 185553/371472 [3:54:30<15:30:33,  3.33it/s]
 50%|████▉     | 185554/371472 [3:54:30<15:27:12,  3.34it/s]
 50%|████▉     | 185555/371472 [3:54:30<16:20:06,  3.16it/s]
 50%|████▉     | 185556/371472 [3:54:31<15:55:30,  3.24it/s]
 50%|████▉     | 185557/371472 [3:54:31<15:22:20,  3.36it/s]
 50%|████▉     | 185558/371472 [3:54:31<15:27:34,  3.34it/s]
 50%|████▉     | 185559/371472 [3:54:31<14:56:36,  3.46it/s]
 50%|████▉     | 185560/371472 [3:54:32<15:37:36,  3.30it/s]
                                                            
{'loss': 2.7733, 'learning_rate': 5.506690512616087e-07, 'epoch': 7.99}
+
 50%|████▉     | 185560/371472 [3:54:32<15:37:36,  3.30it/s]
 50%|████▉     | 185561/371472 [3:54:32<15:12:05,  3.40it/s]
 50%|████▉     | 185562/371472 [3:54:32<14:43:53,  3.51it/s]
 50%|████▉     | 185563/371472 [3:54:33<14:47:24,  3.49it/s]
 50%|████▉     | 185564/371472 [3:54:33<14:47:20,  3.49it/s]
 50%|████▉     | 185565/371472 [3:54:33<14:48:52,  3.49it/s]
 50%|████▉     | 185566/371472 [3:54:34<15:15:30,  3.38it/s]
 50%|████▉     | 185567/371472 [3:54:34<15:05:45,  3.42it/s]
 50%|████▉     | 185568/371472 [3:54:34<15:21:29,  3.36it/s]
 50%|████▉     | 185569/371472 [3:54:34<15:28:56,  3.34it/s]
 50%|████▉     | 185570/371472 [3:54:35<14:55:13,  3.46it/s]
 50%|████▉     | 185571/371472 [3:54:35<14:41:34,  3.51it/s]
 50%|████▉     | 185572/371472 [3:54:35<15:34:42,  3.31it/s]
 50%|████▉     | 185573/371472 [3:54:36<15:45:53,  3.28it/s]
 50%|████▉     | 185574/371472 [3:54:36<16:09:31,  3.20it/s]
 50%|████▉     | 185575/371472 [3:54:36<16:02:40,  3.22it/s]
 50%|████▉     | 185576/371472 [3:54:37<16:55:32,  3.05it/s]
 50%|████▉     | 185577/371472 [3:54:37<16:28:04,  3.14it/s]
 50%|████▉     | 185578/371472 [3:54:37<15:51:07,  3.26it/s]
 50%|████▉     | 185579/371472 [3:54:38<15:43:36,  3.28it/s]
 50%|████▉     | 185580/371472 [3:54:38<15:46:02,  3.27it/s]
                                                            
{'loss': 2.8181, 'learning_rate': 5.506205692861299e-07, 'epoch': 7.99}
+
 50%|████▉     | 185580/371472 [3:54:38<15:46:02,  3.27it/s]
 50%|████▉     | 185581/371472 [3:54:38<15:31:20,  3.33it/s]
 50%|████▉     | 185582/371472 [3:54:39<16:59:51,  3.04it/s]
 50%|████▉     | 185583/371472 [3:54:39<16:18:06,  3.17it/s]
 50%|████▉     | 185584/371472 [3:54:39<16:42:18,  3.09it/s]
 50%|████▉     | 185585/371472 [3:54:39<16:05:43,  3.21it/s]
 50%|████▉     | 185586/371472 [3:54:40<15:27:02,  3.34it/s]
 50%|████▉     | 185587/371472 [3:54:40<15:05:11,  3.42it/s]
 50%|████▉     | 185588/371472 [3:54:40<14:45:56,  3.50it/s]
 50%|████▉     | 185589/371472 [3:54:41<14:50:09,  3.48it/s]
 50%|████▉     | 185590/371472 [3:54:41<14:51:22,  3.48it/s]
 50%|████▉     | 185591/371472 [3:54:41<14:48:08,  3.49it/s]
 50%|████▉     | 185592/371472 [3:54:41<14:43:23,  3.51it/s]
 50%|████▉     | 185593/371472 [3:54:42<14:48:26,  3.49it/s]
 50%|████▉     | 185594/371472 [3:54:42<14:47:35,  3.49it/s]
 50%|████▉     | 185595/371472 [3:54:42<14:59:23,  3.44it/s]
 50%|████▉     | 185596/371472 [3:54:43<15:27:46,  3.34it/s]
 50%|████▉     | 185597/371472 [3:54:43<15:14:43,  3.39it/s]
 50%|████▉     | 185598/371472 [3:54:43<15:03:47,  3.43it/s]
 50%|████▉     | 185599/371472 [3:54:43<15:16:24,  3.38it/s]
 50%|████▉     | 185600/371472 [3:54:44<15:00:02,  3.44it/s]
                                                            
{'loss': 3.0215, 'learning_rate': 5.50572087310651e-07, 'epoch': 7.99}
+
 50%|████▉     | 185600/371472 [3:54:44<15:00:02,  3.44it/s]
 50%|████▉     | 185601/371472 [3:54:44<15:44:58,  3.28it/s]
 50%|████▉     | 185602/371472 [3:54:44<15:44:34,  3.28it/s]
 50%|████▉     | 185603/371472 [3:54:45<15:28:04,  3.34it/s]
 50%|████▉     | 185604/371472 [3:54:45<17:26:15,  2.96it/s]
 50%|████▉     | 185605/371472 [3:54:45<16:31:30,  3.12it/s]
 50%|████▉     | 185606/371472 [3:54:46<15:59:35,  3.23it/s]
 50%|████▉     | 185607/371472 [3:54:46<15:43:07,  3.28it/s]
 50%|████▉     | 185608/371472 [3:54:46<15:10:28,  3.40it/s]
 50%|████▉     | 185609/371472 [3:54:47<15:05:16,  3.42it/s]
 50%|████▉     | 185610/371472 [3:54:47<14:50:07,  3.48it/s]
 50%|████▉     | 185611/371472 [3:54:47<15:02:12,  3.43it/s]
 50%|████▉     | 185612/371472 [3:54:47<15:17:02,  3.38it/s]
 50%|████▉     | 185613/371472 [3:54:48<15:07:32,  3.41it/s]
 50%|████▉     | 185614/371472 [3:54:48<15:11:16,  3.40it/s]
 50%|████▉     | 185615/371472 [3:54:48<15:12:07,  3.40it/s]
 50%|████▉     | 185616/371472 [3:54:49<15:16:04,  3.38it/s]
 50%|████▉     | 185617/371472 [3:54:49<15:23:58,  3.35it/s]
 50%|████▉     | 185618/371472 [3:54:49<15:18:05,  3.37it/s]
 50%|████▉     | 185619/371472 [3:54:49<15:15:11,  3.38it/s]
 50%|████▉     | 185620/371472 [3:54:50<15:13:24,  3.39it/s]
                                                            
{'loss': 2.9515, 'learning_rate': 5.50523605335172e-07, 'epoch': 8.0}
+
 50%|████▉     | 185620/371472 [3:54:50<15:13:24,  3.39it/s]
 50%|████▉     | 185621/371472 [3:54:50<15:18:16,  3.37it/s]
 50%|████▉     | 185622/371472 [3:54:50<14:50:02,  3.48it/s]
 50%|████▉     | 185623/371472 [3:54:51<15:07:52,  3.41it/s]
 50%|████▉     | 185624/371472 [3:54:51<16:16:25,  3.17it/s]
 50%|████▉     | 185625/371472 [3:54:51<16:36:46,  3.11it/s]
 50%|████▉     | 185626/371472 [3:54:52<16:29:36,  3.13it/s]
 50%|████▉     | 185627/371472 [3:54:52<16:25:01,  3.14it/s]
 50%|████▉     | 185628/371472 [3:54:52<15:50:12,  3.26it/s]
 50%|████▉     | 185629/371472 [3:54:53<15:55:06,  3.24it/s]
 50%|████▉     | 185630/371472 [3:54:53<16:18:08,  3.17it/s]
 50%|████▉     | 185631/371472 [3:54:53<17:10:01,  3.01it/s]
 50%|████▉     | 185632/371472 [3:54:54<16:14:51,  3.18it/s]
 50%|████▉     | 185633/371472 [3:54:54<15:36:12,  3.31it/s]
 50%|████▉     | 185634/371472 [3:54:54<15:49:18,  3.26it/s]
 50%|████▉     | 185635/371472 [3:54:54<15:33:09,  3.32it/s]
 50%|████▉     | 185636/371472 [3:54:55<15:08:57,  3.41it/s]
 50%|████▉     | 185637/371472 [3:54:55<15:29:23,  3.33it/s]
 50%|████▉     | 185638/371472 [3:54:55<15:31:39,  3.32it/s]
 50%|████▉     | 185639/371472 [3:54:56<16:06:40,  3.20it/s]
 50%|████▉     | 185640/371472 [3:54:56<15:39:51,  3.30it/s]
                                                            
{'loss': 2.9126, 'learning_rate': 5.504751233596931e-07, 'epoch': 8.0}
+
 50%|████▉     | 185640/371472 [3:54:56<15:39:51,  3.30it/s]
 50%|████▉     | 185641/371472 [3:54:56<15:31:44,  3.32it/s]
 50%|████▉     | 185642/371472 [3:54:56<15:06:20,  3.42it/s]
 50%|████▉     | 185643/371472 [3:54:57<15:04:11,  3.43it/s]
 50%|████▉     | 185644/371472 [3:54:57<15:11:03,  3.40it/s]
 50%|████▉     | 185645/371472 [3:54:57<15:08:26,  3.41it/s]
 50%|████▉     | 185646/371472 [3:54:58<15:07:48,  3.41it/s]
 50%|████▉     | 185647/371472 [3:54:58<16:24:37,  3.15it/s]
 50%|████▉     | 185648/371472 [3:54:58<16:04:44,  3.21it/s]
 50%|████▉     | 185649/371472 [3:54:59<15:36:10,  3.31it/s]
 50%|████▉     | 185650/371472 [3:54:59<15:25:28,  3.35it/s]
 50%|████▉     | 185651/371472 [3:54:59<15:04:27,  3.42it/s]
 50%|████▉     | 185652/371472 [3:55:00<15:38:20,  3.30it/s]
 50%|████▉     | 185653/371472 [3:55:00<15:34:42,  3.31it/s]
 50%|████▉     | 185654/371472 [3:55:00<15:10:37,  3.40it/s]
 50%|████▉     | 185655/371472 [3:55:00<14:48:20,  3.49it/s]
 50%|████▉     | 185656/371472 [3:55:01<14:52:29,  3.47it/s]
 50%|████▉     | 185657/371472 [3:55:01<15:08:25,  3.41it/s]
 50%|████▉     | 185658/371472 [3:55:01<14:42:42,  3.51it/s]
 50%|████▉     | 185659/371472 [3:55:02<14:45:12,  3.50it/s]
 50%|████▉     | 185660/371472 [3:55:02<15:47:30,  3.27it/s]
                                                            
{'loss': 3.0746, 'learning_rate': 5.504266413842143e-07, 'epoch': 8.0}
+
 50%|████▉     | 185660/371472 [3:55:02<15:47:30,  3.27it/s]
 50%|████▉     | 185661/371472 [3:55:02<15:39:31,  3.30it/s]
 50%|████▉     | 185662/371472 [3:55:02<15:16:51,  3.38it/s]
 50%|████▉     | 185663/371472 [3:55:03<15:03:05,  3.43it/s]
 50%|████▉     | 185664/371472 [3:55:03<14:38:22,  3.53it/s]
 50%|████▉     | 185665/371472 [3:55:03<14:39:41,  3.52it/s]
 50%|████▉     | 185666/371472 [3:55:04<18:35:53,  2.78it/s]
 50%|████▉     | 185667/371472 [3:55:04<17:27:35,  2.96it/s]
 50%|████▉     | 185668/371472 [3:55:04<16:37:08,  3.11it/s]
 50%|████▉     | 185669/371472 [3:55:05<16:08:08,  3.20it/s]
 50%|████▉     | 185670/371472 [3:55:05<15:51:27,  3.25it/s]
 50%|████▉     | 185671/371472 [3:55:05<16:42:51,  3.09it/s]
 50%|████▉     | 185672/371472 [3:55:06<17:07:04,  3.02it/s]
 50%|████▉     | 185673/371472 [3:55:06<17:01:08,  3.03it/s]
 50%|████▉     | 185674/371472 [3:55:06<15:59:33,  3.23it/s]
 50%|████▉     | 185675/371472 [3:55:07<15:31:11,  3.33it/s]
 50%|████▉     | 185676/371472 [3:55:07<15:07:51,  3.41it/s]
 50%|████▉     | 185677/371472 [3:55:07<15:00:35,  3.44it/s]
 50%|████▉     | 185678/371472 [3:55:07<14:51:05,  3.48it/s]
 50%|████▉     | 185679/371472 [3:55:08<14:51:46,  3.47it/s]
 50%|████▉     | 185680/371472 [3:55:08<15:07:44,  3.41it/s]
                                                            
{'loss': 2.9059, 'learning_rate': 5.503781594087354e-07, 'epoch': 8.0}
+
 50%|████▉     | 185680/371472 [3:55:08<15:07:44,  3.41it/s]
 50%|████▉     | 185681/371472 [3:55:08<15:04:04,  3.43it/s]
 50%|████▉     | 185682/371472 [3:55:09<14:48:24,  3.49it/s]
 50%|████▉     | 185683/371472 [3:55:09<14:59:21,  3.44it/s]
 50%|████▉     | 185684/371472 [3:55:09<15:49:31,  3.26it/s]
 50%|████▉     | 185685/371472 [3:55:09<15:25:45,  3.34it/s]
 50%|████▉     | 185686/371472 [3:55:10<15:18:25,  3.37it/s]
 50%|████▉     | 185687/371472 [3:55:10<15:28:08,  3.34it/s]
 50%|████▉     | 185688/371472 [3:55:10<14:49:26,  3.48it/s]
 50%|████▉     | 185689/371472 [3:55:11<15:09:15,  3.41it/s]
 50%|████▉     | 185690/371472 [3:55:11<15:09:32,  3.40it/s]
 50%|████▉     | 185691/371472 [3:55:11<16:18:01,  3.17it/s]
 50%|████▉     | 185692/371472 [3:55:12<15:54:50,  3.24it/s]
 50%|████▉     | 185693/371472 [3:55:12<15:30:08,  3.33it/s]
 50%|████▉     | 185694/371472 [3:55:12<15:26:53,  3.34it/s]
 50%|████▉     | 185695/371472 [3:55:13<16:10:08,  3.19it/s]
 50%|████▉     | 185696/371472 [3:55:13<15:57:24,  3.23it/s]
 50%|████▉     | 185697/371472 [3:55:13<15:37:58,  3.30it/s]
 50%|████▉     | 185698/371472 [3:55:13<15:42:19,  3.29it/s]
 50%|████▉     | 185699/371472 [3:55:14<15:28:58,  3.33it/s]
 50%|████▉     | 185700/371472 [3:55:14<16:15:08,  3.18it/s]
                                                            
{'loss': 2.8672, 'learning_rate': 5.503296774332564e-07, 'epoch': 8.0}
+
 50%|████▉     | 185700/371472 [3:55:14<16:15:08,  3.18it/s]
 50%|████▉     | 185701/371472 [3:55:14<16:00:50,  3.22it/s]
 50%|████▉     | 185702/371472 [3:55:15<15:11:51,  3.40it/s]
 50%|████▉     | 185703/371472 [3:55:15<15:08:59,  3.41it/s]
 50%|████▉     | 185704/371472 [3:55:15<14:55:56,  3.46it/s]
 50%|████▉     | 185705/371472 [3:55:15<15:05:46,  3.42it/s]
 50%|████▉     | 185706/371472 [3:55:16<15:34:38,  3.31it/s]
 50%|████▉     | 185707/371472 [3:55:16<15:36:56,  3.30it/s]
 50%|████▉     | 185708/371472 [3:55:16<15:16:11,  3.38it/s]
 50%|████▉     | 185709/371472 [3:55:17<16:19:22,  3.16it/s]
 50%|████▉     | 185710/371472 [3:55:17<17:20:02,  2.98it/s]
 50%|████▉     | 185711/371472 [3:55:17<16:52:50,  3.06it/s]
 50%|████▉     | 185712/371472 [3:55:18<17:01:39,  3.03it/s]
 50%|████▉     | 185713/371472 [3:55:18<16:20:30,  3.16it/s]
 50%|████▉     | 185714/371472 [3:55:18<16:15:25,  3.17it/s]
 50%|████▉     | 185715/371472 [3:55:19<15:47:38,  3.27it/s]
 50%|████▉     | 185716/371472 [3:55:19<16:29:49,  3.13it/s]
 50%|████▉     | 185717/371472 [3:55:19<16:08:23,  3.20it/s]
 50%|████▉     | 185718/371472 [3:55:20<15:29:57,  3.33it/s]
 50%|████▉     | 185719/371472 [3:55:20<15:37:18,  3.30it/s]
 50%|████▉     | 185720/371472 [3:55:20<15:35:14,  3.31it/s]
                                                            
{'loss': 2.9432, 'learning_rate': 5.502811954577776e-07, 'epoch': 8.0}
+
 50%|████▉     | 185720/371472 [3:55:20<15:35:14,  3.31it/s]
 50%|████▉     | 185721/371472 [3:55:20<15:22:19,  3.36it/s]
 50%|████▉     | 185722/371472 [3:55:21<15:30:44,  3.33it/s]
 50%|████▉     | 185723/371472 [3:55:21<15:57:35,  3.23it/s]
 50%|████▉     | 185724/371472 [3:55:21<15:50:30,  3.26it/s]
 50%|████▉     | 185725/371472 [3:55:22<16:13:28,  3.18it/s]
 50%|████▉     | 185726/371472 [3:55:22<15:31:33,  3.32it/s]
 50%|████▉     | 185727/371472 [3:55:22<15:23:45,  3.35it/s]
 50%|████▉     | 185728/371472 [3:55:23<15:13:07,  3.39it/s]
 50%|████▉     | 185729/371472 [3:55:23<15:03:43,  3.43it/s]
 50%|████▉     | 185730/371472 [3:55:23<14:56:14,  3.45it/s]
 50%|████▉     | 185731/371472 [3:55:24<16:52:43,  3.06it/s]
 50%|████▉     | 185732/371472 [3:55:24<16:43:23,  3.09it/s]
 50%|████▉     | 185733/371472 [3:55:24<16:20:40,  3.16it/s]
 50%|████▉     | 185734/371472 [3:55:24<16:01:19,  3.22it/s]
 50%|████▉     | 185735/371472 [3:55:25<16:06:43,  3.20it/s]
 50%|█████     | 185736/371472 [3:55:25<16:37:14,  3.10it/s]Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
+Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}
+/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
+  self.pid = os.fork()
+
 50%|█████     | 185737/371472 [3:55:56<489:59:11,  9.50s/it]
 50%|█████     | 185738/371472 [3:55:56<347:39:19,  6.74s/it]
 50%|█████     | 185739/371472 [3:55:57<247:41:17,  4.80s/it]
 50%|█████     | 185740/371472 [3:55:57<180:18:05,  3.49s/it]
                                                             
{'loss': 2.8989, 'learning_rate': 5.502327134822987e-07, 'epoch': 8.0}
+
 50%|█████     | 185740/371472 [3:55:57<180:18:05,  3.49s/it]
 50%|█████     | 185741/371472 [3:55:57<131:21:48,  2.55s/it]
 50%|█████     | 185742/371472 [3:55:58<96:31:43,  1.87s/it] 
 50%|█████     | 185743/371472 [3:55:58<72:14:00,  1.40s/it]
 50%|█████     | 185744/371472 [3:55:58<55:17:01,  1.07s/it]
 50%|█████     | 185745/371472 [3:55:59<43:22:45,  1.19it/s]
 50%|█████     | 185746/371472 [3:55:59<36:43:34,  1.40it/s]
 50%|█████     | 185747/371472 [3:55:59<31:45:35,  1.62it/s]
 50%|█████     | 185748/371472 [3:56:00<28:11:07,  1.83it/s]
 50%|█████     | 185749/371472 [3:56:00<25:32:42,  2.02it/s]
 50%|█████     | 185750/371472 [3:56:01<24:12:55,  2.13it/s]
 50%|█████     | 185751/371472 [3:56:01<22:49:49,  2.26it/s]
 50%|█████     | 185752/371472 [3:56:01<20:35:32,  2.51it/s]
 50%|█████     | 185753/371472 [3:56:02<19:22:04,  2.66it/s]
 50%|█████     | 185754/371472 [3:56:02<18:34:40,  2.78it/s]
 50%|█████     | 185755/371472 [3:56:02<17:55:00,  2.88it/s]
 50%|█████     | 185756/371472 [3:56:03<18:51:43,  2.74it/s]
 50%|█████     | 185757/371472 [3:56:03<17:46:02,  2.90it/s]
 50%|█████     | 185758/371472 [3:56:03<18:07:20,  2.85it/s]
 50%|█████     | 185759/371472 [3:56:04<17:59:32,  2.87it/s]
 50%|█████     | 185760/371472 [3:56:04<17:54:29,  2.88it/s]
                                                            
{'loss': 2.7647, 'learning_rate': 5.501842315068197e-07, 'epoch': 8.0}
+
 50%|█████     | 185760/371472 [3:56:04<17:54:29,  2.88it/s]
 50%|█████     | 185761/371472 [3:56:04<17:12:09,  3.00it/s]
 50%|█████     | 185762/371472 [3:56:05<16:09:46,  3.19it/s]
 50%|█████     | 185763/371472 [3:56:05<16:19:34,  3.16it/s]
 50%|█████     | 185764/371472 [3:56:05<16:29:31,  3.13it/s]
 50%|█████     | 185765/371472 [3:56:05<15:56:37,  3.24it/s]
 50%|█████     | 185766/371472 [3:56:06<16:09:07,  3.19it/s]
 50%|█████     | 185767/371472 [3:56:06<16:13:56,  3.18it/s]
 50%|█████     | 185768/371472 [3:56:06<15:56:20,  3.24it/s]
 50%|█████     | 185769/371472 [3:56:07<16:16:34,  3.17it/s]
 50%|█████     | 185770/371472 [3:56:07<15:58:22,  3.23it/s]
 50%|█████     | 185771/371472 [3:56:07<16:11:36,  3.19it/s]
 50%|█████     | 185772/371472 [3:56:08<15:55:54,  3.24it/s]
 50%|█████     | 185773/371472 [3:56:08<16:16:14,  3.17it/s]
 50%|█████     | 185774/371472 [3:56:08<15:55:41,  3.24it/s]
 50%|█████     | 185775/371472 [3:56:09<16:00:06,  3.22it/s]
 50%|█████     | 185776/371472 [3:56:09<15:50:55,  3.25it/s]
 50%|█████     | 185777/371472 [3:56:09<15:59:15,  3.23it/s]
 50%|█████     | 185778/371472 [3:56:10<15:53:02,  3.25it/s]
 50%|█████     | 185779/371472 [3:56:10<16:13:32,  3.18it/s]
 50%|█████     | 185780/371472 [3:56:10<16:09:17,  3.19it/s]
                                                            
{'loss': 2.8602, 'learning_rate': 5.501357495313408e-07, 'epoch': 8.0}
+
 50%|█████     | 185780/371472 [3:56:10<16:09:17,  3.19it/s]
 50%|█████     | 185781/371472 [3:56:11<16:38:30,  3.10it/s]
 50%|█████     | 185782/371472 [3:56:11<16:49:43,  3.07it/s]
 50%|█████     | 185783/371472 [3:56:11<17:55:47,  2.88it/s]
 50%|█████     | 185784/371472 [3:56:12<17:57:31,  2.87it/s]
 50%|█████     | 185785/371472 [3:56:12<17:24:05,  2.96it/s]
 50%|█████     | 185786/371472 [3:56:12<16:49:57,  3.06it/s]
 50%|█████     | 185787/371472 [3:56:13<16:53:22,  3.05it/s]
 50%|█████     | 185788/371472 [3:56:13<16:15:45,  3.17it/s]
 50%|█████     | 185789/371472 [3:56:13<16:11:08,  3.19it/s]
 50%|█████     | 185790/371472 [3:56:13<16:09:42,  3.19it/s]
 50%|█████     | 185791/371472 [3:56:14<16:11:10,  3.19it/s]
 50%|█████     | 185792/371472 [3:56:14<17:06:44,  3.01it/s]
 50%|█████     | 185793/371472 [3:56:14<17:31:53,  2.94it/s]
 50%|█████     | 185794/371472 [3:56:15<17:39:25,  2.92it/s]
 50%|█████     | 185795/371472 [3:56:15<16:45:28,  3.08it/s]
 50%|█████     | 185796/371472 [3:56:16<17:42:37,  2.91it/s]
 50%|█████     | 185797/371472 [3:56:16<18:18:26,  2.82it/s]
 50%|█████     | 185798/371472 [3:56:16<18:22:41,  2.81it/s]
 50%|█████     | 185799/371472 [3:56:17<17:30:40,  2.95it/s]
 50%|█████     | 185800/371472 [3:56:17<18:16:20,  2.82it/s]
                                                            
{'loss': 2.8374, 'learning_rate': 5.50087267555862e-07, 'epoch': 8.0}
+
 50%|█████     | 185800/371472 [3:56:17<18:16:20,  2.82it/s]
 50%|█████     | 185801/371472 [3:56:17<18:24:35,  2.80it/s]
 50%|█████     | 185802/371472 [3:56:18<18:26:49,  2.80it/s]
 50%|█████     | 185803/371472 [3:56:18<18:01:45,  2.86it/s]
 50%|█████     | 185804/371472 [3:56:18<17:35:57,  2.93it/s]
 50%|█████     | 185805/371472 [3:56:19<17:09:26,  3.01it/s]
 50%|█████     | 185806/371472 [3:56:19<16:40:32,  3.09it/s]
 50%|█████     | 185807/371472 [3:56:19<16:55:57,  3.05it/s]
 50%|█████     | 185808/371472 [3:56:20<16:34:42,  3.11it/s]
 50%|█████     | 185809/371472 [3:56:20<16:31:22,  3.12it/s]
 50%|█████     | 185810/371472 [3:56:20<16:11:52,  3.18it/s]
 50%|█████     | 185811/371472 [3:56:21<16:51:03,  3.06it/s]
 50%|█████     | 185812/371472 [3:56:21<16:35:36,  3.11it/s]
 50%|█████     | 185813/371472 [3:56:21<16:11:18,  3.19it/s]
 50%|█████     | 185814/371472 [3:56:21<16:21:06,  3.15it/s]
 50%|█████     | 185815/371472 [3:56:22<16:53:28,  3.05it/s]
 50%|█████     | 185816/371472 [3:56:22<16:34:10,  3.11it/s]
 50%|█████     | 185817/371472 [3:56:22<16:22:39,  3.15it/s]
 50%|█████     | 185818/371472 [3:56:23<16:28:20,  3.13it/s]
 50%|█████     | 185819/371472 [3:56:23<17:21:37,  2.97it/s]
 50%|█████     | 185820/371472 [3:56:24<18:08:27,  2.84it/s]
                                                            
{'loss': 2.6321, 'learning_rate': 5.500387855803831e-07, 'epoch': 8.0}
+
 50%|█████     | 185820/371472 [3:56:24<18:08:27,  2.84it/s]
 50%|█████     | 185821/371472 [3:56:24<17:22:11,  2.97it/s]
 50%|█████     | 185822/371472 [3:56:24<16:47:04,  3.07it/s]
 50%|█████     | 185823/371472 [3:56:24<16:45:02,  3.08it/s]
 50%|█████     | 185824/371472 [3:56:25<16:07:29,  3.20it/s]
 50%|█████     | 185825/371472 [3:56:25<15:59:33,  3.22it/s]
 50%|█████     | 185826/371472 [3:56:25<16:08:51,  3.19it/s]
 50%|█████     | 185827/371472 [3:56:26<16:33:49,  3.11it/s]
 50%|█████     | 185828/371472 [3:56:26<16:53:58,  3.05it/s]
 50%|█████     | 185829/371472 [3:56:26<16:40:48,  3.09it/s]
 50%|█████     | 185830/371472 [3:56:27<16:13:07,  3.18it/s]
 50%|█████     | 185831/371472 [3:56:27<16:28:33,  3.13it/s]
 50%|█████     | 185832/371472 [3:56:27<16:18:13,  3.16it/s]
 50%|█████     | 185833/371472 [3:56:28<17:11:52,  3.00it/s]
 50%|█████     | 185834/371472 [3:56:28<16:54:49,  3.05it/s]
 50%|█████     | 185835/371472 [3:56:28<16:56:51,  3.04it/s]
 50%|█████     | 185836/371472 [3:56:29<17:00:54,  3.03it/s]
 50%|█████     | 185837/371472 [3:56:29<18:06:13,  2.85it/s]
 50%|█████     | 185838/371472 [3:56:29<17:22:26,  2.97it/s]
 50%|█████     | 185839/371472 [3:56:30<16:45:48,  3.08it/s]
 50%|█████     | 185840/371472 [3:56:30<16:13:46,  3.18it/s]
                                                            
{'loss': 2.6652, 'learning_rate': 5.499903036049042e-07, 'epoch': 8.0}
+
 50%|█████     | 185840/371472 [3:56:30<16:13:46,  3.18it/s]
 50%|█████     | 185841/371472 [3:56:30<16:24:57,  3.14it/s]
 50%|█████     | 185842/371472 [3:56:31<15:51:31,  3.25it/s]
 50%|█████     | 185843/371472 [3:56:31<16:17:18,  3.17it/s]
 50%|█████     | 185844/371472 [3:56:31<16:23:03,  3.15it/s]
 50%|█████     | 185845/371472 [3:56:32<16:38:19,  3.10it/s]
 50%|█████     | 185846/371472 [3:56:32<16:26:32,  3.14it/s]
 50%|█████     | 185847/371472 [3:56:32<16:15:58,  3.17it/s]
 50%|█████     | 185848/371472 [3:56:32<15:25:54,  3.34it/s]
 50%|█████     | 185849/371472 [3:56:33<16:07:07,  3.20it/s]
 50%|█████     | 185850/371472 [3:56:33<16:15:11,  3.17it/s]
 50%|█████     | 185851/371472 [3:56:33<16:02:01,  3.22it/s]
 50%|█████     | 185852/371472 [3:56:34<15:47:59,  3.26it/s]
 50%|█████     | 185853/371472 [3:56:34<15:39:56,  3.29it/s]
 50%|█████     | 185854/371472 [3:56:34<17:01:28,  3.03it/s]
 50%|█████     | 185855/371472 [3:56:35<17:38:37,  2.92it/s]
 50%|█████     | 185856/371472 [3:56:35<17:09:52,  3.00it/s]
 50%|█████     | 185857/371472 [3:56:35<16:21:17,  3.15it/s]
 50%|█████     | 185858/371472 [3:56:36<16:20:47,  3.15it/s]
 50%|█████     | 185859/371472 [3:56:36<16:13:28,  3.18it/s]
 50%|█████     | 185860/371472 [3:56:36<16:51:34,  3.06it/s]
                                                            
{'loss': 2.8973, 'learning_rate': 5.499418216294253e-07, 'epoch': 8.01}
+
 50%|█████     | 185860/371472 [3:56:36<16:51:34,  3.06it/s]
 50%|█████     | 185861/371472 [3:56:37<17:37:03,  2.93it/s]
 50%|█████     | 185862/371472 [3:56:37<17:16:18,  2.99it/s]
 50%|█████     | 185863/371472 [3:56:37<17:44:39,  2.91it/s]
 50%|█████     | 185864/371472 [3:56:38<18:58:06,  2.72it/s]
 50%|█████     | 185865/371472 [3:56:38<18:28:29,  2.79it/s]
 50%|█████     | 185866/371472 [3:56:38<18:07:49,  2.84it/s]
 50%|█████     | 185867/371472 [3:56:39<17:35:30,  2.93it/s]
 50%|█████     | 185868/371472 [3:56:39<16:55:44,  3.05it/s]
\ No newline at end of file