diff --git "a/run-2024-10-28T03:01:14+00:00.log" "b/run-2024-10-28T03:01:14+00:00.log"
--- "a/run-2024-10-28T03:01:14+00:00.log"
+++ "b/run-2024-10-28T03:01:14+00:00.log"
@@ -3242,4 +3242,1068 @@ Non-default generation parameters: {'max_length': 200, 'early_stopping': True, '
 
 50%|█████     | 30960/61904 [5:22:32<281:09:52, 32.71s/it]
 50%|█████     | 30961/61904 [5:22:33<200:43:11, 23.35s/it]
 50%|█████     | 30962/61904 [5:22:35<144:24:49, 16.80s/it]
 50%|█████     | 30963/61904 [5:22:36<104:50:31, 12.20s/it]
 50%|█████     | 30964/61904 [5:22:38<77:22:38,  9.00s/it] 
 50%|█████     | 30965/61904 [5:22:39<58:19:59,  6.79s/it]
 50%|█████     | 30966/61904 [5:22:41<44:23:15,  5.17s/it]
 50%|█████     | 30967/61904 [5:22:42<34:30:23,  4.02s/it]
 50%|█████     | 30968/61904 [5:22:43<27:47:31,  3.23s/it]
 50%|█████     | 30969/61904 [5:22:45<23:01:29,  2.68s/it]
 50%|█████     | 30970/61904 [5:22:46<19:54:01,  2.32s/it]
 50%|█████     | 30971/61904 [5:22:48<17:29:59,  2.04s/it]
 50%|█████     | 30972/61904 [5:22:49<15:31:05,  1.81s/it]
 50%|█████     | 30973/61904 [5:22:50<14:20:00,  1.67s/it]
 50%|█████     | 30974/61904 [5:22:52<13:39:47,  1.59s/it]
 50%|█████     | 30975/61904 [5:22:53<13:22:46,  1.56s/it]
 50%|█████     | 30976/61904 [5:22:55<13:04:29,  1.52s/it]
 50%|█████     | 30977/61904 [5:22:56<12:47:49,  1.49s/it]
 50%|█████     | 30978/61904 [5:22:58<13:09:08,  1.53s/it]
 50%|█████     | 30979/61904 [5:22:59<12:22:39,  1.44s/it]
 50%|█████     | 30980/61904 [5:23:00<12:23:44,  1.44s/it]
                                                          
{'loss': 2.4841, 'learning_rate': 1.5011668611435238e-07, 'epoch': 8.01}
 
 50%|█████     | 30980/61904 [5:23:00<12:23:44,  1.44s/it]
 50%|█████     | 30981/61904 [5:23:02<12:00:53,  1.40s/it]
 50%|█████     | 30982/61904 [5:23:03<12:22:37,  1.44s/it]
 50%|█████     | 30983/61904 [5:23:05<12:14:19,  1.42s/it]
 50%|█████     | 30984/61904 [5:23:06<12:22:05,  1.44s/it]
 50%|█████     | 30985/61904 [5:23:07<12:07:21,  1.41s/it]
 50%|█████     | 30986/61904 [5:23:09<11:50:09,  1.38s/it]
 50%|█████     | 30987/61904 [5:23:10<12:30:36,  1.46s/it]
 50%|█████     | 30988/61904 [5:23:12<12:11:29,  1.42s/it]
 50%|█████     | 30989/61904 [5:23:13<12:04:46,  1.41s/it]
 50%|█████     | 30990/61904 [5:23:14<11:54:39,  1.39s/it]
 50%|█████     | 30991/61904 [5:23:16<11:44:11,  1.37s/it]
 50%|█████     | 30992/61904 [5:23:17<11:45:10,  1.37s/it]
 50%|█████     | 30993/61904 [5:23:18<11:28:33,  1.34s/it]
 50%|█████     | 30994/61904 [5:23:20<11:43:57,  1.37s/it]
 50%|█████     | 30995/61904 [5:23:21<11:48:06,  1.37s/it]
 50%|█████     | 30996/61904 [5:23:22<11:25:44,  1.33s/it]
 50%|█████     | 30997/61904 [5:23:24<11:51:11,  1.38s/it]
 50%|█████     | 30998/61904 [5:23:25<11:42:41,  1.36s/it]
 50%|█████     | 30999/61904 [5:23:27<11:50:04,  1.38s/it]
 50%|█████     | 31000/61904 [5:23:28<11:39:06,  1.36s/it]
                                                          
{'loss': 2.5913, 'learning_rate': 1.5008427330481007e-07, 'epoch': 8.01}
 
 50%|█████     | 31000/61904 [5:23:28<11:39:06,  1.36s/it]
 50%|█████     | 31001/61904 [5:23:29<11:53:47,  1.39s/it]
 50%|█████     | 31002/61904 [5:23:31<11:59:15,  1.40s/it]
 50%|█████     | 31003/61904 [5:23:32<12:37:40,  1.47s/it]
 50%|█████     | 31004/61904 [5:23:34<12:27:20,  1.45s/it]
 50%|█████     | 31005/61904 [5:23:35<12:09:40,  1.42s/it]
 50%|█████     | 31006/61904 [5:23:37<12:08:15,  1.41s/it]
 50%|█████     | 31007/61904 [5:23:38<11:45:47,  1.37s/it]
 50%|█████     | 31008/61904 [5:23:39<11:36:34,  1.35s/it]
 50%|█████     | 31009/61904 [5:23:41<11:46:56,  1.37s/it]
 50%|█████     | 31010/61904 [5:23:42<12:13:55,  1.43s/it]
 50%|█████     | 31011/61904 [5:23:44<13:07:53,  1.53s/it]
 50%|█████     | 31012/61904 [5:23:45<13:09:13,  1.53s/it]
 50%|█████     | 31013/61904 [5:23:47<12:43:07,  1.48s/it]
 50%|█████     | 31014/61904 [5:23:48<12:46:29,  1.49s/it]
 50%|█████     | 31015/61904 [5:23:50<12:34:13,  1.47s/it]
 50%|█████     | 31016/61904 [5:23:51<12:14:17,  1.43s/it]
 50%|█████     | 31017/61904 [5:23:53<12:28:17,  1.45s/it]
 50%|█████     | 31018/61904 [5:23:54<12:03:32,  1.41s/it]
 50%|█████     | 31019/61904 [5:23:55<12:07:21,  1.41s/it]
 50%|█████     | 31020/61904 [5:23:57<12:09:32,  1.42s/it]
                                                          
{'loss': 2.5053, 'learning_rate': 1.5005186049526773e-07, 'epoch': 8.02}
-
 50%|█████     | 31020/61904 [5:23:57<12:09:32,  1.42s/it]
 50%|█████     | 31021/61904 [5:23:58<11:49:39,  1.38s/it]
 50%|█████     | 31022/61904 [5:23:59<11:55:03,  1.39s/it]
 50%|█████     | 31023/61904 [5:24:01<11:50:06,  1.38s/it]
 50%|█████     | 31024/61904 [5:24:02<11:59:39,  1.40s/it]
\ No newline at end of file
+
 50%|█████     | 31020/61904 [5:23:57<12:09:32,  1.42s/it]
 50%|█████     | 31021/61904 [5:23:58<11:49:39,  1.38s/it]
 50%|█████     | 31022/61904 [5:23:59<11:55:03,  1.39s/it]
 50%|█████     | 31023/61904 [5:24:01<11:50:06,  1.38s/it]
 50%|█████     | 31024/61904 [5:24:02<11:59:39,  1.40s/it]
 50%|█████     | 31025/61904 [5:24:04<12:16:48,  1.43s/it]
 50%|█████     | 31026/61904 [5:24:05<11:58:10,  1.40s/it]
 50%|█████     | 31027/61904 [5:24:06<11:58:00,  1.40s/it]
 50%|█████     | 31028/61904 [5:24:08<11:53:54,  1.39s/it]
 50%|█████     | 31029/61904 [5:24:09<12:04:31,  1.41s/it]
 50%|█████     | 31030/61904 [5:24:11<12:01:06,  1.40s/it]
 50%|█████     | 31031/61904 [5:24:12<12:22:31,  1.44s/it]
 50%|█████     | 31032/61904 [5:24:14<12:03:56,  1.41s/it]
 50%|█████     | 31033/61904 [5:24:15<12:12:19,  1.42s/it]
 50%|█████     | 31034/61904 [5:24:16<12:08:19,  1.42s/it]
 50%|█████     | 31035/61904 [5:24:18<11:56:29,  1.39s/it]
 50%|█████     | 31036/61904 [5:24:19<11:46:37,  1.37s/it]
 50%|█████     | 31037/61904 [5:24:21<12:05:09,  1.41s/it]
 50%|█████     | 31038/61904 [5:24:22<11:36:36,  1.35s/it]
 50%|█████     | 31039/61904 [5:24:23<11:39:07,  1.36s/it]
 50%|█████     | 31040/61904 [5:24:25<11:56:21,  1.39s/it]
                                                          
{'loss': 2.5612, 'learning_rate': 1.500194476857254e-07, 'epoch': 8.02}
+
 50%|█████     | 31040/61904 [5:24:25<11:56:21,  1.39s/it]
 50%|█████     | 31041/61904 [5:24:26<12:03:18,  1.41s/it]
 50%|█████     | 31042/61904 [5:24:27<11:56:00,  1.39s/it]
 50%|█████     | 31043/61904 [5:24:29<11:45:37,  1.37s/it]
 50%|█████     | 31044/61904 [5:24:30<11:46:39,  1.37s/it]
 50%|█████     | 31045/61904 [5:24:32<11:55:26,  1.39s/it]
 50%|█████     | 31046/61904 [5:24:33<12:06:58,  1.41s/it]
 50%|█████     | 31047/61904 [5:24:34<12:11:08,  1.42s/it]
 50%|█████     | 31048/61904 [5:24:36<12:13:18,  1.43s/it]
 50%|█████     | 31049/61904 [5:24:37<12:22:13,  1.44s/it]
 50%|█████     | 31050/61904 [5:24:39<12:22:23,  1.44s/it]
 50%|█████     | 31051/61904 [5:24:40<12:05:11,  1.41s/it]
 50%|█████     | 31052/61904 [5:24:42<12:24:22,  1.45s/it]
 50%|█████     | 31053/61904 [5:24:43<12:13:07,  1.43s/it]
 50%|█████     | 31054/61904 [5:24:44<12:10:11,  1.42s/it]
 50%|█████     | 31055/61904 [5:24:46<12:21:47,  1.44s/it]
 50%|█████     | 31056/61904 [5:24:47<12:23:15,  1.45s/it]
 50%|█████     | 31057/61904 [5:24:49<12:14:07,  1.43s/it]
 50%|█████     | 31058/61904 [5:24:50<12:52:15,  1.50s/it]
 50%|█████     | 31059/61904 [5:24:52<12:47:16,  1.49s/it]
 50%|█████     | 31060/61904 [5:24:53<12:20:39,  1.44s/it]
                                                          
{'loss': 2.5478, 'learning_rate': 1.4998703487618305e-07, 'epoch': 8.03}
+
 50%|█████     | 31060/61904 [5:24:53<12:20:39,  1.44s/it]
 50%|█████     | 31061/61904 [5:24:55<12:17:18,  1.43s/it]
 50%|█████     | 31062/61904 [5:24:56<12:00:54,  1.40s/it]
 50%|█████     | 31063/61904 [5:24:57<12:12:55,  1.43s/it]
 50%|█████     | 31064/61904 [5:24:59<12:13:56,  1.43s/it]
 50%|█████     | 31065/61904 [5:25:00<12:05:36,  1.41s/it]
 50%|█████     | 31066/61904 [5:25:02<11:41:41,  1.37s/it]
 50%|█████     | 31067/61904 [5:25:03<11:33:06,  1.35s/it]
 50%|█████     | 31068/61904 [5:25:04<11:44:26,  1.37s/it]
 50%|█████     | 31069/61904 [5:25:06<12:20:04,  1.44s/it]
 50%|█████     | 31070/61904 [5:25:07<12:07:13,  1.42s/it]
 50%|█████     | 31071/61904 [5:25:09<12:04:54,  1.41s/it]
 50%|█████     | 31072/61904 [5:25:10<11:59:11,  1.40s/it]
 50%|█████     | 31073/61904 [5:25:11<12:11:20,  1.42s/it]
 50%|█████     | 31074/61904 [5:25:13<12:12:22,  1.43s/it]
 50%|█████     | 31075/61904 [5:25:14<12:18:07,  1.44s/it]
 50%|█████     | 31076/61904 [5:25:16<12:23:16,  1.45s/it]
 50%|█████     | 31077/61904 [5:25:17<12:38:09,  1.48s/it]
 50%|█████     | 31078/61904 [5:25:19<12:33:54,  1.47s/it]
 50%|█████     | 31079/61904 [5:25:20<12:29:49,  1.46s/it]
 50%|█████     | 31080/61904 [5:25:22<12:25:28,  1.45s/it]
                                                          
{'loss': 2.5783, 'learning_rate': 1.4995462206664074e-07, 'epoch': 8.03}
+
 50%|█████     | 31080/61904 [5:25:22<12:25:28,  1.45s/it]
 50%|█████     | 31081/61904 [5:25:23<12:11:37,  1.42s/it]
 50%|█████     | 31082/61904 [5:25:24<12:11:53,  1.42s/it]
 50%|█████     | 31083/61904 [5:25:26<12:12:33,  1.43s/it]
 50%|█████     | 31084/61904 [5:25:27<12:06:21,  1.41s/it]
 50%|█████     | 31085/61904 [5:25:29<11:51:26,  1.39s/it]
 50%|█████     | 31086/61904 [5:25:30<11:47:53,  1.38s/it]
 50%|█████     | 31087/61904 [5:25:31<11:59:45,  1.40s/it]
 50%|█████     | 31088/61904 [5:25:33<11:47:59,  1.38s/it]
 50%|█████     | 31089/61904 [5:25:34<11:34:10,  1.35s/it]
 50%|█████     | 31090/61904 [5:25:35<11:27:37,  1.34s/it]
 50%|█████     | 31091/61904 [5:25:37<11:30:52,  1.35s/it]
 50%|█████     | 31092/61904 [5:25:38<11:58:30,  1.40s/it]
 50%|█████     | 31093/61904 [5:25:40<11:50:54,  1.38s/it]
 50%|█████     | 31094/61904 [5:25:41<11:34:07,  1.35s/it]
 50%|█████     | 31095/61904 [5:25:42<11:34:56,  1.35s/it]
 50%|█████     | 31096/61904 [5:25:44<11:30:14,  1.34s/it]
 50%|█████     | 31097/61904 [5:25:45<11:26:19,  1.34s/it]
 50%|█████     | 31098/61904 [5:25:46<11:25:06,  1.33s/it]
 50%|█████     | 31099/61904 [5:25:48<11:21:39,  1.33s/it]
 50%|█████     | 31100/61904 [5:25:49<11:33:41,  1.35s/it]
                                                          
{'loss': 2.5484, 'learning_rate': 1.499222092570984e-07, 'epoch': 8.04}
+
 50%|█████     | 31100/61904 [5:25:49<11:33:41,  1.35s/it]
 50%|█████     | 31101/61904 [5:25:50<11:16:45,  1.32s/it]
 50%|█████     | 31102/61904 [5:25:51<11:12:39,  1.31s/it]
 50%|█████     | 31103/61904 [5:25:53<11:10:30,  1.31s/it]
 50%|█████     | 31104/61904 [5:25:54<11:25:20,  1.34s/it]
 50%|█████     | 31105/61904 [5:25:55<11:12:07,  1.31s/it]
 50%|█████     | 31106/61904 [5:25:57<11:34:50,  1.35s/it]
 50%|█████     | 31107/61904 [5:25:58<11:19:43,  1.32s/it]
 50%|█████     | 31108/61904 [5:25:59<11:14:25,  1.31s/it]
 50%|█████     | 31109/61904 [5:26:01<11:29:12,  1.34s/it]
 50%|█████     | 31110/61904 [5:26:02<11:37:59,  1.36s/it]
 50%|█████     | 31111/61904 [5:26:03<11:14:15,  1.31s/it]
 50%|█████     | 31112/61904 [5:26:05<11:38:37,  1.36s/it]
 50%|█████     | 31113/61904 [5:26:06<11:35:39,  1.36s/it]
 50%|█████     | 31114/61904 [5:26:08<11:27:59,  1.34s/it]
 50%|█████     | 31115/61904 [5:26:09<11:44:47,  1.37s/it]
 50%|█████     | 31116/61904 [5:26:10<11:55:19,  1.39s/it]
 50%|█████     | 31117/61904 [5:26:12<11:46:41,  1.38s/it]
 50%|█████     | 31118/61904 [5:26:13<11:31:17,  1.35s/it]
 50%|█████     | 31119/61904 [5:26:14<11:14:29,  1.31s/it]
 50%|█████     | 31120/61904 [5:26:16<11:35:17,  1.36s/it]
                                                          
{'loss': 2.6095, 'learning_rate': 1.4988979644755606e-07, 'epoch': 8.04}
+
 50%|█████     | 31120/61904 [5:26:16<11:35:17,  1.36s/it]
 50%|█████     | 31121/61904 [5:26:17<11:24:15,  1.33s/it]
 50%|█████     | 31122/61904 [5:26:18<11:45:03,  1.37s/it]
 50%|█████     | 31123/61904 [5:26:20<11:45:33,  1.38s/it]
 50%|█████     | 31124/61904 [5:26:21<11:46:04,  1.38s/it]
 50%|█████     | 31125/61904 [5:26:23<11:47:29,  1.38s/it]
 50%|█████     | 31126/61904 [5:26:24<11:38:45,  1.36s/it]
 50%|█████     | 31127/61904 [5:26:25<11:26:34,  1.34s/it]
 50%|█████     | 31128/61904 [5:26:27<11:31:40,  1.35s/it]
 50%|█████     | 31129/61904 [5:26:28<11:29:31,  1.34s/it]
 50%|█████     | 31130/61904 [5:26:29<11:25:49,  1.34s/it]
 50%|█████     | 31131/61904 [5:26:31<11:42:37,  1.37s/it]
 50%|█████     | 31132/61904 [5:26:32<11:31:53,  1.35s/it]
 50%|█████     | 31133/61904 [5:26:33<11:23:50,  1.33s/it]
 50%|█████     | 31134/61904 [5:26:35<11:28:31,  1.34s/it]
 50%|█████     | 31135/61904 [5:26:36<11:20:04,  1.33s/it]
 50%|█████     | 31136/61904 [5:26:37<11:37:03,  1.36s/it]
 50%|█████     | 31137/61904 [5:26:39<11:28:38,  1.34s/it]
 50%|█████     | 31138/61904 [5:26:40<11:40:29,  1.37s/it]
 50%|█████     | 31139/61904 [5:26:41<11:41:53,  1.37s/it]
 50%|█████     | 31140/61904 [5:26:43<11:37:16,  1.36s/it]
                                                          
{'loss': 2.5052, 'learning_rate': 1.4985738363801373e-07, 'epoch': 8.05}
+
 50%|█████     | 31140/61904 [5:26:43<11:37:16,  1.36s/it]
 50%|█████     | 31141/61904 [5:26:45<12:55:16,  1.51s/it]
 50%|█████     | 31142/61904 [5:26:46<12:17:50,  1.44s/it]
 50%|█████     | 31143/61904 [5:26:47<12:13:18,  1.43s/it]
 50%|█████     | 31144/61904 [5:26:49<11:49:29,  1.38s/it]
 50%|█████     | 31145/61904 [5:26:50<12:08:10,  1.42s/it]
 50%|█████     | 31146/61904 [5:26:51<11:53:31,  1.39s/it]
 50%|█████     | 31147/61904 [5:26:53<11:47:14,  1.38s/it]
 50%|█████     | 31148/61904 [5:26:54<11:47:14,  1.38s/it]
 50%|���████     | 31149/61904 [5:26:56<11:50:27,  1.39s/it]
 50%|█████     | 31150/61904 [5:26:57<11:17:24,  1.32s/it]
 50%|█████     | 31151/61904 [5:26:58<11:34:32,  1.36s/it]
 50%|█████     | 31152/61904 [5:27:00<12:10:08,  1.42s/it]
 50%|█████     | 31153/61904 [5:27:01<11:50:34,  1.39s/it]
 50%|█████     | 31154/61904 [5:27:03<12:30:48,  1.46s/it]
 50%|█████     | 31155/61904 [5:27:04<12:30:11,  1.46s/it]
 50%|█████     | 31156/61904 [5:27:06<12:25:10,  1.45s/it]
 50%|█████     | 31157/61904 [5:27:07<12:16:38,  1.44s/it]
 50%|█████     | 31158/61904 [5:27:09<12:24:05,  1.45s/it]
 50%|█████     | 31159/61904 [5:27:10<12:03:51,  1.41s/it]
 50%|█████     | 31160/61904 [5:27:11<12:13:13,  1.43s/it]
                                                          
{'loss': 2.4753, 'learning_rate': 1.4982497082847141e-07, 'epoch': 8.05}
+
 50%|█████     | 31160/61904 [5:27:11<12:13:13,  1.43s/it]
 50%|█████     | 31161/61904 [5:27:13<12:21:58,  1.45s/it]
 50%|█████     | 31162/61904 [5:27:14<12:00:40,  1.41s/it]
 50%|█████     | 31163/61904 [5:27:16<11:58:58,  1.40s/it]
 50%|█████     | 31164/61904 [5:27:17<11:58:16,  1.40s/it]
 50%|█████     | 31165/61904 [5:27:18<12:24:19,  1.45s/it]
 50%|█████     | 31166/61904 [5:27:20<12:08:25,  1.42s/it]
 50%|█████     | 31167/61904 [5:27:21<12:02:46,  1.41s/it]
 50%|█████     | 31168/61904 [5:27:23<12:00:41,  1.41s/it]
 50%|█████     | 31169/61904 [5:27:24<11:59:03,  1.40s/it]
 50%|█████     | 31170/61904 [5:27:25<11:56:02,  1.40s/it]
 50%|█████     | 31171/61904 [5:27:27<11:38:13,  1.36s/it]
 50%|█████     | 31172/61904 [5:27:28<12:13:34,  1.43s/it]
 50%|█████     | 31173/61904 [5:27:30<12:02:55,  1.41s/it]
 50%|█████     | 31174/61904 [5:27:31<11:51:04,  1.39s/it]
 50%|█████     | 31175/61904 [5:27:32<11:59:14,  1.40s/it]
 50%|█████     | 31176/61904 [5:27:34<11:41:23,  1.37s/it]
 50%|█████     | 31177/61904 [5:27:35<11:55:43,  1.40s/it]
 50%|█████     | 31178/61904 [5:27:36<11:42:29,  1.37s/it]
 50%|█████     | 31179/61904 [5:27:38<11:55:17,  1.40s/it]
 50%|█████     | 31180/61904 [5:27:40<12:22:04,  1.45s/it]
                                                          
{'loss': 2.5393, 'learning_rate': 1.4979255801892908e-07, 'epoch': 8.06}
+
 50%|█████     | 31180/61904 [5:27:40<12:22:04,  1.45s/it]
 50%|█████     | 31181/61904 [5:27:41<11:51:44,  1.39s/it]
 50%|█████     | 31182/61904 [5:27:42<11:41:21,  1.37s/it]
 50%|█████     | 31183/61904 [5:27:43<11:41:34,  1.37s/it]
 50%|█████     | 31184/61904 [5:27:45<11:38:42,  1.36s/it]
 50%|█████     | 31185/61904 [5:27:46<11:23:02,  1.33s/it]
 50%|█████     | 31186/61904 [5:27:47<11:37:23,  1.36s/it]
 50%|█████     | 31187/61904 [5:27:49<11:30:20,  1.35s/it]
 50%|█████     | 31188/61904 [5:27:50<11:30:14,  1.35s/it]
 50%|█████     | 31189/61904 [5:27:51<11:25:32,  1.34s/it]
 50%|█████     | 31190/61904 [5:27:53<11:51:46,  1.39s/it]
 50%|█████     | 31191/61904 [5:27:54<11:45:23,  1.38s/it]
 50%|█████     | 31192/61904 [5:27:56<12:01:49,  1.41s/it]
 50%|█████     | 31193/61904 [5:27:57<11:38:00,  1.36s/it]
 50%|█████     | 31194/61904 [5:27:58<11:34:19,  1.36s/it]
 50%|█████     | 31195/61904 [5:28:00<11:41:09,  1.37s/it]
 50%|█████     | 31196/61904 [5:28:01<11:57:37,  1.40s/it]
 50%|█████     | 31197/61904 [5:28:03<11:47:25,  1.38s/it]
 50%|█████     | 31198/61904 [5:28:04<11:38:29,  1.36s/it]
 50%|█████     | 31199/61904 [5:28:05<11:50:10,  1.39s/it]
 50%|█████     | 31200/61904 [5:28:07<11:44:30,  1.38s/it]
                                                          
{'loss': 2.5935, 'learning_rate': 1.4976014520938674e-07, 'epoch': 8.06}
+
 50%|█████     | 31200/61904 [5:28:07<11:44:30,  1.38s/it]
 50%|█████     | 31201/61904 [5:28:08<11:47:55,  1.38s/it]
 50%|█████     | 31202/61904 [5:28:10<11:46:05,  1.38s/it]
 50%|█████     | 31203/61904 [5:28:11<11:45:43,  1.38s/it]
 50%|█████     | 31204/61904 [5:28:12<11:45:18,  1.38s/it]
 50%|█████     | 31205/61904 [5:28:14<11:44:31,  1.38s/it]
 50%|█████     | 31206/61904 [5:28:15<11:36:04,  1.36s/it]
 50%|█████     | 31207/61904 [5:28:16<11:35:15,  1.36s/it]
 50%|█████     | 31208/61904 [5:28:18<11:39:39,  1.37s/it]
 50%|█████     | 31209/61904 [5:28:19<11:26:58,  1.34s/it]
 50%|█████     | 31210/61904 [5:28:20<11:29:12,  1.35s/it]
 50%|█████     | 31211/61904 [5:28:22<11:19:45,  1.33s/it]
 50%|█████     | 31212/61904 [5:28:23<11:11:39,  1.31s/it]
 50%|█████     | 31213/61904 [5:28:24<11:08:19,  1.31s/it]
 50%|█████     | 31214/61904 [5:28:26<11:22:41,  1.33s/it]
 50%|█████     | 31215/61904 [5:28:27<12:02:20,  1.41s/it]
 50%|█████     | 31216/61904 [5:28:29<11:53:58,  1.40s/it]
 50%|█████     | 31217/61904 [5:28:30<11:37:32,  1.36s/it]
 50%|█████     | 31218/61904 [5:28:31<11:45:53,  1.38s/it]
 50%|█████     | 31219/61904 [5:28:33<11:34:09,  1.36s/it]
 50%|█████     | 31220/61904 [5:28:34<11:36:16,  1.36s/it]
                                                          
{'loss': 2.5911, 'learning_rate': 1.497277323998444e-07, 'epoch': 8.07}
+
 50%|█████     | 31220/61904 [5:28:34<11:36:16,  1.36s/it]
 50%|█████     | 31221/61904 [5:28:35<11:45:41,  1.38s/it]
 50%|█████     | 31222/61904 [5:28:37<11:39:34,  1.37s/it]
 50%|█████     | 31223/61904 [5:28:38<11:26:08,  1.34s/it]
 50%|█████     | 31224/61904 [5:28:39<11:28:05,  1.35s/it]
 50%|█████     | 31225/61904 [5:28:41<11:48:53,  1.39s/it]
 50%|█████     | 31226/61904 [5:28:42<11:36:02,  1.36s/it]
 50%|█████     | 31227/61904 [5:28:43<11:30:59,  1.35s/it]
 50%|█████     | 31228/61904 [5:28:45<11:12:19,  1.32s/it]
 50%|█████     | 31229/61904 [5:28:46<11:41:08,  1.37s/it]
 50%|█████     | 31230/61904 [5:28:47<11:29:33,  1.35s/it]
 50%|█████     | 31231/61904 [5:28:49<11:35:23,  1.36s/it]
 50%|█████     | 31232/61904 [5:28:50<11:47:05,  1.38s/it]
 50%|█████     | 31233/61904 [5:28:52<11:59:14,  1.41s/it]
 50%|█████     | 31234/61904 [5:28:53<11:40:05,  1.37s/it]
 50%|█████     | 31235/61904 [5:28:54<11:27:22,  1.34s/it]
 50%|█████     | 31236/61904 [5:28:56<11:30:46,  1.35s/it]
 50%|█████     | 31237/61904 [5:28:57<12:04:24,  1.42s/it]
 50%|█████     | 31238/61904 [5:28:59<12:38:55,  1.48s/it]
 50%|█████     | 31239/61904 [5:29:00<12:19:22,  1.45s/it]
 50%|█████     | 31240/61904 [5:29:02<12:13:42,  1.44s/it]
                                                          
{'loss': 2.572, 'learning_rate': 1.496953195903021e-07, 'epoch': 8.07}
+
 50%|█████     | 31240/61904 [5:29:02<12:13:42,  1.44s/it]
 50%|█████     | 31241/61904 [5:29:03<12:16:09,  1.44s/it]
 50%|█████     | 31242/61904 [5:29:04<11:57:36,  1.40s/it]
 50%|█████     | 31243/61904 [5:29:06<11:28:31,  1.35s/it]
 50%|█████     | 31244/61904 [5:29:07<11:32:37,  1.36s/it]
 50%|█████     | 31245/61904 [5:29:08<11:27:43,  1.35s/it]
 50%|█████     | 31246/61904 [5:29:10<11:40:53,  1.37s/it]
 50%|█████     | 31247/61904 [5:29:11<11:44:23,  1.38s/it]
 50%|█████     | 31248/61904 [5:29:12<11:30:17,  1.35s/it]
 50%|█████     | 31249/61904 [5:29:14<12:08:08,  1.43s/it]
 50%|█████     | 31250/61904 [5:29:15<11:42:45,  1.38s/it]
 50%|█████     | 31251/61904 [5:29:17<11:24:18,  1.34s/it]
 50%|█████     | 31252/61904 [5:29:18<11:14:38,  1.32s/it]
 50%|█████     | 31253/61904 [5:29:19<11:50:22,  1.39s/it]
 50%|█████     | 31254/61904 [5:29:21<11:58:23,  1.41s/it]
 50%|█████     | 31255/61904 [5:29:22<11:39:42,  1.37s/it]
 50%|█████     | 31256/61904 [5:29:24<11:57:27,  1.40s/it]
 50%|█████     | 31257/61904 [5:29:25<11:54:50,  1.40s/it]
 50%|█████     | 31258/61904 [5:29:26<11:54:38,  1.40s/it]
 50%|█████     | 31259/61904 [5:29:28<11:48:32,  1.39s/it]
 50%|█████     | 31260/61904 [5:29:29<11:26:09,  1.34s/it]
                                                          
{'loss': 2.5707, 'learning_rate': 1.4966290678075975e-07, 'epoch': 8.08}
+
 50%|█████     | 31260/61904 [5:29:29<11:26:09,  1.34s/it]
 50%|█████     | 31261/61904 [5:29:31<12:00:15,  1.41s/it]
 51%|█████     | 31262/61904 [5:29:32<11:53:02,  1.40s/it]
 51%|█████     | 31263/61904 [5:29:33<11:53:59,  1.40s/it]
 51%|█████     | 31264/61904 [5:29:35<11:50:39,  1.39s/it]
 51%|█████     | 31265/61904 [5:29:36<11:29:16,  1.35s/it]
 51%|█████     | 31266/61904 [5:29:38<12:00:59,  1.41s/it]
 51%|█████     | 31267/61904 [5:29:39<11:56:33,  1.40s/it]
 51%|█████     | 31268/61904 [5:29:40<11:39:48,  1.37s/it]
 51%|█████     | 31269/61904 [5:29:42<11:27:34,  1.35s/it]
 51%|█████     | 31270/61904 [5:29:43<11:32:28,  1.36s/it]
 51%|█████     | 31271/61904 [5:29:44<12:04:47,  1.42s/it]
 51%|█████     | 31272/61904 [5:29:46<11:50:33,  1.39s/it]
 51%|█████     | 31273/61904 [5:29:47<11:42:26,  1.38s/it]
 51%|█████     | 31274/61904 [5:29:49<11:49:19,  1.39s/it]
 51%|█████     | 31275/61904 [5:29:50<11:45:07,  1.38s/it]
 51%|█████     | 31276/61904 [5:29:51<11:45:02,  1.38s/it]
 51%|█████     | 31277/61904 [5:29:53<11:54:28,  1.40s/it]
 51%|█████     | 31278/61904 [5:29:54<11:42:53,  1.38s/it]
 51%|█████     | 31279/61904 [5:29:55<11:49:14,  1.39s/it]
 51%|█████     | 31280/61904 [5:29:57<11:38:07,  1.37s/it]
                                                          
{'loss': 2.5847, 'learning_rate': 1.496304939712174e-07, 'epoch': 8.08}
+
 51%|█████     | 31280/61904 [5:29:57<11:38:07,  1.37s/it]
 51%|█████     | 31281/61904 [5:29:58<11:38:40,  1.37s/it]
 51%|█████     | 31282/61904 [5:30:00<11:58:57,  1.41s/it]
 51%|█████     | 31283/61904 [5:30:01<11:41:29,  1.37s/it]
 51%|█████     | 31284/61904 [5:30:03<12:16:46,  1.44s/it]
 51%|█████     | 31285/61904 [5:30:04<12:12:19,  1.44s/it]
 51%|█████     | 31286/61904 [5:30:05<11:52:01,  1.40s/it]
 51%|█████     | 31287/61904 [5:30:07<11:35:17,  1.36s/it]
 51%|█████     | 31288/61904 [5:30:08<11:25:33,  1.34s/it]
 51%|█████     | 31289/61904 [5:30:09<11:17:12,  1.33s/it]
 51%|█████     | 31290/61904 [5:30:10<11:17:10,  1.33s/it]
 51%|█████     | 31291/61904 [5:30:12<11:30:31,  1.35s/it]
 51%|█████     | 31292/61904 [5:30:13<11:42:31,  1.38s/it]
 51%|█████     | 31293/61904 [5:30:15<11:39:56,  1.37s/it]
 51%|█████     | 31294/61904 [5:30:16<11:41:48,  1.38s/it]
 51%|█████     | 31295/61904 [5:30:17<11:31:00,  1.35s/it]
 51%|█████     | 31296/61904 [5:30:19<11:33:49,  1.36s/it]
 51%|█████     | 31297/61904 [5:30:20<11:26:00,  1.34s/it]
 51%|█████     | 31298/61904 [5:30:22<11:52:05,  1.40s/it]
 51%|█████     | 31299/61904 [5:30:23<11:46:14,  1.38s/it]
 51%|█████     | 31300/61904 [5:30:24<11:45:08,  1.38s/it]
                                                          
{'loss': 2.5486, 'learning_rate': 1.4959808116167507e-07, 'epoch': 8.09}
+
 51%|█████     | 31300/61904 [5:30:24<11:45:08,  1.38s/it]
 51%|█████     | 31301/61904 [5:30:26<11:38:10,  1.37s/it]
 51%|█████     | 31302/61904 [5:30:27<11:35:43,  1.36s/it]
 51%|█████     | 31303/61904 [5:30:29<12:09:28,  1.43s/it]
 51%|█████     | 31304/61904 [5:30:30<12:30:50,  1.47s/it]
 51%|█████     | 31305/61904 [5:30:32<12:14:38,  1.44s/it]
 51%|█████     | 31306/61904 [5:30:33<12:45:01,  1.50s/it]
 51%|█████     | 31307/61904 [5:30:35<12:59:07,  1.53s/it]
 51%|█████     | 31308/61904 [5:30:36<12:32:01,  1.47s/it]
 51%|█████     | 31309/61904 [5:30:37<12:07:03,  1.43s/it]
 51%|█████     | 31310/61904 [5:30:39<12:00:15,  1.41s/it]
 51%|█████     | 31311/61904 [5:30:40<11:51:43,  1.40s/it]
 51%|█████     | 31312/61904 [5:30:42<11:56:34,  1.41s/it]
 51%|█████     | 31313/61904 [5:30:43<12:01:59,  1.42s/it]
 51%|█████     | 31314/61904 [5:30:44<11:57:02,  1.41s/it]
 51%|█████     | 31315/61904 [5:30:46<11:59:57,  1.41s/it]
 51%|█████     | 31316/61904 [5:30:47<11:53:02,  1.40s/it]
 51%|█████     | 31317/61904 [5:30:49<12:13:24,  1.44s/it]
 51%|█████     | 31318/61904 [5:30:50<11:47:31,  1.39s/it]
 51%|█████     | 31319/61904 [5:30:51<12:01:49,  1.42s/it]
 51%|█████     | 31320/61904 [5:30:53<11:56:41,  1.41s/it]
                                                          
{'loss': 2.5432, 'learning_rate': 1.4956566835213276e-07, 'epoch': 8.09}
+
 51%|█████     | 31320/61904 [5:30:53<11:56:41,  1.41s/it]
 51%|█████     | 31321/61904 [5:30:54<11:56:18,  1.41s/it]
 51%|█████     | 31322/61904 [5:30:56<11:42:18,  1.38s/it]
 51%|█████     | 31323/61904 [5:30:57<12:09:44,  1.43s/it]
 51%|█████     | 31324/61904 [5:30:58<11:42:04,  1.38s/it]
 51%|█████     | 31325/61904 [5:31:00<11:41:28,  1.38s/it]
 51%|█████     | 31326/61904 [5:31:01<11:45:02,  1.38s/it]
 51%|█████     | 31327/61904 [5:31:03<11:51:15,  1.40s/it]
 51%|█████     | 31328/61904 [5:31:04<11:35:30,  1.36s/it]
 51%|█████     | 31329/61904 [5:31:05<11:29:53,  1.35s/it]
 51%|█████     | 31330/61904 [5:31:07<11:26:31,  1.35s/it]
 51%|█████     | 31331/61904 [5:31:08<11:33:40,  1.36s/it]
 51%|█████     | 31332/61904 [5:31:10<12:07:04,  1.43s/it]
 51%|█████     | 31333/61904 [5:31:11<11:58:22,  1.41s/it]
 51%|█████     | 31334/61904 [5:31:12<12:06:16,  1.43s/it]
 51%|█████     | 31335/61904 [5:31:14<12:01:45,  1.42s/it]
 51%|█████     | 31336/61904 [5:31:15<11:41:13,  1.38s/it]
 51%|█████     | 31337/61904 [5:31:16<11:30:49,  1.36s/it]
 51%|█████     | 31338/61904 [5:31:18<11:26:32,  1.35s/it]
 51%|█████     | 31339/61904 [5:31:19<11:28:51,  1.35s/it]
 51%|█████     | 31340/61904 [5:31:20<11:41:28,  1.38s/it]
                                                          
{'loss': 2.5547, 'learning_rate': 1.4953325554259042e-07, 'epoch': 8.1}
+
 51%|█████     | 31340/61904 [5:31:20<11:41:28,  1.38s/it]
 51%|█████     | 31341/61904 [5:31:22<11:31:45,  1.36s/it]
 51%|█████     | 31342/61904 [5:31:23<11:24:08,  1.34s/it]
 51%|█████     | 31343/61904 [5:31:24<11:24:55,  1.34s/it]
 51%|█████     | 31344/61904 [5:31:26<11:30:24,  1.36s/it]
 51%|█████     | 31345/61904 [5:31:27<11:37:17,  1.37s/it]
 51%|█████     | 31346/61904 [5:31:29<11:40:37,  1.38s/it]
 51%|█████     | 31347/61904 [5:31:30<11:30:36,  1.36s/it]
 51%|█████     | 31348/61904 [5:31:31<11:51:33,  1.40s/it]
 51%|█████     | 31349/61904 [5:31:33<11:36:52,  1.37s/it]
 51%|█████     | 31350/61904 [5:31:34<11:51:09,  1.40s/it]
 51%|█████     | 31351/61904 [5:31:36<11:50:59,  1.40s/it]
 51%|█████     | 31352/61904 [5:31:37<11:55:33,  1.41s/it]
 51%|█████     | 31353/61904 [5:31:39<12:16:01,  1.45s/it]
 51%|█████     | 31354/61904 [5:31:40<11:56:41,  1.41s/it]
 51%|█████     | 31355/61904 [5:31:41<11:50:29,  1.40s/it]
 51%|█████     | 31356/61904 [5:31:43<12:03:43,  1.42s/it]
 51%|█████     | 31357/61904 [5:31:44<12:15:53,  1.45s/it]
 51%|█████     | 31358/61904 [5:31:46<12:08:40,  1.43s/it]
 51%|█████     | 31359/61904 [5:31:47<12:11:06,  1.44s/it]
 51%|█████     | 31360/61904 [5:31:48<12:00:26,  1.42s/it]
                                                          
{'loss': 2.5349, 'learning_rate': 1.4950084273304809e-07, 'epoch': 8.11}
+
 51%|█████     | 31360/61904 [5:31:48<12:00:26,  1.42s/it]
 51%|█████     | 31361/61904 [5:31:50<11:46:30,  1.39s/it]
 51%|█████     | 31362/61904 [5:31:51<11:35:51,  1.37s/it]
 51%|█████     | 31363/61904 [5:31:52<11:30:11,  1.36s/it]
 51%|█████     | 31364/61904 [5:31:54<11:38:07,  1.37s/it]
 51%|█████     | 31365/61904 [5:31:55<11:40:58,  1.38s/it]
 51%|█████     | 31366/61904 [5:31:57<11:58:48,  1.41s/it]
 51%|█████     | 31367/61904 [5:31:58<12:14:14,  1.44s/it]
 51%|█████     | 31368/61904 [5:32:00<12:17:48,  1.45s/it]
 51%|█████     | 31369/61904 [5:32:01<12:02:19,  1.42s/it]
 51%|█████     | 31370/61904 [5:32:02<12:04:49,  1.42s/it]
 51%|█████     | 31371/61904 [5:32:04<11:45:19,  1.39s/it]
 51%|█████     | 31372/61904 [5:32:05<11:41:42,  1.38s/it]
 51%|█████     | 31373/61904 [5:32:07<11:46:08,  1.39s/it]
 51%|█████     | 31374/61904 [5:32:08<11:37:14,  1.37s/it]
 51%|█████     | 31375/61904 [5:32:09<11:39:53,  1.38s/it]
 51%|█████     | 31376/61904 [5:32:11<12:21:54,  1.46s/it]
 51%|█████     | 31377/61904 [5:32:12<12:25:33,  1.47s/it]
 51%|█████     | 31378/61904 [5:32:14<12:04:25,  1.42s/it]
 51%|█████     | 31379/61904 [5:32:15<12:01:17,  1.42s/it]
 51%|█████     | 31380/61904 [5:32:16<11:41:55,  1.38s/it]
                                                          
{'loss': 2.5603, 'learning_rate': 1.4946842992350577e-07, 'epoch': 8.11}
+
 51%|█████     | 31380/61904 [5:32:16<11:41:55,  1.38s/it]
 51%|█████     | 31381/61904 [5:32:18<11:34:45,  1.37s/it]
 51%|█████     | 31382/61904 [5:32:19<11:51:45,  1.40s/it]
 51%|█████     | 31383/61904 [5:32:21<11:55:51,  1.41s/it]
 51%|█████     | 31384/61904 [5:32:22<11:45:13,  1.39s/it]
 51%|█████     | 31385/61904 [5:32:23<11:16:02,  1.33s/it]
 51%|█████     | 31386/61904 [5:32:24<11:12:32,  1.32s/it]
 51%|█████     | 31387/61904 [5:32:26<11:11:38,  1.32s/it]
 51%|█████     | 31388/61904 [5:32:27<11:10:01,  1.32s/it]
 51%|█████     | 31389/61904 [5:32:28<10:56:59,  1.29s/it]
 51%|█████     | 31390/61904 [5:32:30<11:02:00,  1.30s/it]
 51%|█████     | 31391/61904 [5:32:31<11:10:11,  1.32s/it]
 51%|█████     | 31392/61904 [5:32:32<11:22:47,  1.34s/it]
 51%|█████     | 31393/61904 [5:32:34<11:33:13,  1.36s/it]
 51%|█████     | 31394/61904 [5:32:35<11:44:16,  1.38s/it]
 51%|█████     | 31395/61904 [5:32:37<11:42:18,  1.38s/it]
 51%|█████     | 31396/61904 [5:32:38<11:41:21,  1.38s/it]
 51%|█████     | 31397/61904 [5:32:39<11:24:12,  1.35s/it]
 51%|█████     | 31398/61904 [5:32:41<11:31:32,  1.36s/it]
 51%|█████     | 31399/61904 [5:32:42<11:32:42,  1.36s/it]
 51%|█████     | 31400/61904 [5:32:43<11:45:22,  1.39s/it]
                                                          
{'loss': 2.5763, 'learning_rate': 1.4943601711396344e-07, 'epoch': 8.12}
+
 51%|█████     | 31400/61904 [5:32:43<11:45:22,  1.39s/it]
 51%|█████     | 31401/61904 [5:32:45<11:35:00,  1.37s/it]
 51%|█████     | 31402/61904 [5:32:46<11:25:25,  1.35s/it]
 51%|█████     | 31403/61904 [5:32:48<11:37:54,  1.37s/it]
 51%|█████     | 31404/61904 [5:32:49<11:44:24,  1.39s/it]
 51%|█████     | 31405/61904 [5:32:50<11:55:17,  1.41s/it]
 51%|█████     | 31406/61904 [5:32:52<11:57:16,  1.41s/it]
 51%|█████     | 31407/61904 [5:32:53<11:52:32,  1.40s/it]
 51%|█████     | 31408/61904 [5:32:55<11:38:08,  1.37s/it]
 51%|█████     | 31409/61904 [5:32:56<11:20:46,  1.34s/it]
 51%|█████     | 31410/61904 [5:32:57<11:30:11,  1.36s/it]
 51%|█████     | 31411/61904 [5:32:59<12:01:33,  1.42s/it]
 51%|█████     | 31412/61904 [5:33:00<11:33:58,  1.37s/it]
 51%|█████     | 31413/61904 [5:33:01<11:23:21,  1.34s/it]
 51%|█████     | 31414/61904 [5:33:03<11:19:09,  1.34s/it]
 51%|█████     | 31415/61904 [5:33:04<11:11:07,  1.32s/it]
 51%|█████     | 31416/61904 [5:33:05<11:29:25,  1.36s/it]
 51%|█████     | 31417/61904 [5:33:07<11:21:11,  1.34s/it]
 51%|█████     | 31418/61904 [5:33:08<11:03:00,  1.30s/it]
 51%|█████     | 31419/61904 [5:33:09<11:00:51,  1.30s/it]
 51%|█████     | 31420/61904 [5:33:11<11:21:27,  1.34s/it]
                                                          
{'loss': 2.5194, 'learning_rate': 1.494036043044211e-07, 'epoch': 8.12}
+
 51%|█████     | 31420/61904 [5:33:11<11:21:27,  1.34s/it]
 51%|█████     | 31421/61904 [5:33:12<11:16:58,  1.33s/it]
 51%|█████     | 31422/61904 [5:33:13<11:18:43,  1.34s/it]
 51%|█████     | 31423/61904 [5:33:15<11:18:37,  1.34s/it]
 51%|█████     | 31424/61904 [5:33:16<11:28:26,  1.36s/it]
 51%|█████     | 31425/61904 [5:33:17<11:21:24,  1.34s/it]
 51%|█████     | 31426/61904 [5:33:19<11:33:49,  1.37s/it]
 51%|█████     | 31427/61904 [5:33:20<11:27:48,  1.35s/it]
 51%|█████     | 31428/61904 [5:33:21<11:25:12,  1.35s/it]
 51%|█████     | 31429/61904 [5:33:23<11:22:47,  1.34s/it]
 51%|█████     | 31430/61904 [5:33:24<11:07:48,  1.31s/it]
 51%|█████     | 31431/61904 [5:33:25<11:20:33,  1.34s/it]
 51%|█████     | 31432/61904 [5:33:27<11:25:42,  1.35s/it]
 51%|█████     | 31433/61904 [5:33:28<12:05:55,  1.43s/it]
 51%|█████     | 31434/61904 [5:33:30<11:57:26,  1.41s/it]
 51%|█████     | 31435/61904 [5:33:31<11:45:30,  1.39s/it]
 51%|█████     | 31436/61904 [5:33:32<11:36:58,  1.37s/it]
 51%|█████     | 31437/61904 [5:33:34<11:33:40,  1.37s/it]
 51%|█████     | 31438/61904 [5:33:35<11:24:32,  1.35s/it]
 51%|█████     | 31439/61904 [5:33:37<11:46:14,  1.39s/it]
 51%|█████     | 31440/61904 [5:33:38<11:28:27,  1.36s/it]
                                                          
{'loss': 2.5414, 'learning_rate': 1.4937119149487876e-07, 'epoch': 8.13}
+
 51%|█████     | 31440/61904 [5:33:38<11:28:27,  1.36s/it]
 51%|█████     | 31441/61904 [5:33:39<11:35:37,  1.37s/it]
 51%|█████     | 31442/61904 [5:33:41<11:42:09,  1.38s/it]
 51%|█████     | 31443/61904 [5:33:42<11:31:24,  1.36s/it]
 51%|█████     | 31444/61904 [5:33:43<11:17:49,  1.34s/it]
 51%|█████     | 31445/61904 [5:33:45<11:31:38,  1.36s/it]
 51%|█████     | 31446/61904 [5:33:46<11:23:40,  1.35s/it]
 51%|█████     | 31447/61904 [5:33:47<11:24:12,  1.35s/it]
 51%|█████     | 31448/61904 [5:33:49<11:08:40,  1.32s/it]
 51%|█████     | 31449/61904 [5:33:50<11:31:13,  1.36s/it]
 51%|█████     | 31450/61904 [5:33:51<11:36:05,  1.37s/it]
 51%|█████     | 31451/61904 [5:33:53<11:55:59,  1.41s/it]
 51%|█████     | 31452/61904 [5:33:54<11:28:45,  1.36s/it]
 51%|█████     | 31453/61904 [5:33:55<11:19:00,  1.34s/it]
 51%|█████     | 31454/61904 [5:33:57<11:31:51,  1.36s/it]
 51%|█████     | 31455/61904 [5:33:58<11:21:23,  1.34s/it]
 51%|█████     | 31456/61904 [5:34:00<11:28:27,  1.36s/it]
 51%|█████     | 31457/61904 [5:34:01<11:30:13,  1.36s/it]
 51%|█████     | 31458/61904 [5:34:02<11:52:24,  1.40s/it]
 51%|█████     | 31459/61904 [5:34:04<12:06:07,  1.43s/it]
 51%|█████     | 31460/61904 [5:34:05<11:49:52,  1.40s/it]
                                                          
{'loss': 2.5459, 'learning_rate': 1.4933877868533645e-07, 'epoch': 8.13}
+
 51%|█████     | 31460/61904 [5:34:05<11:49:52,  1.40s/it]
 51%|█████     | 31461/61904 [5:34:07<11:43:36,  1.39s/it]
 51%|█████     | 31462/61904 [5:34:08<11:29:59,  1.36s/it]
 51%|█████     | 31463/61904 [5:34:09<11:28:42,  1.36s/it]
 51%|█████     | 31464/61904 [5:34:11<11:29:34,  1.36s/it]
 51%|█████     | 31465/61904 [5:34:12<11:55:04,  1.41s/it]
 51%|█████     | 31466/61904 [5:34:13<11:52:36,  1.40s/it]
 51%|█████     | 31467/61904 [5:34:15<11:41:40,  1.38s/it]
 51%|█████     | 31468/61904 [5:34:16<11:41:23,  1.38s/it]
 51%|█████     | 31469/61904 [5:34:18<11:43:39,  1.39s/it]
 51%|█████     | 31470/61904 [5:34:19<11:53:19,  1.41s/it]
 51%|█████     | 31471/61904 [5:34:21<12:15:08,  1.45s/it]
 51%|█████     | 31472/61904 [5:34:22<12:05:18,  1.43s/it]
 51%|█████     | 31473/61904 [5:34:24<12:24:31,  1.47s/it]
 51%|█████     | 31474/61904 [5:34:25<12:09:35,  1.44s/it]
 51%|█████     | 31475/61904 [5:34:26<12:17:15,  1.45s/it]
 51%|█████     | 31476/61904 [5:34:28<12:07:43,  1.43s/it]
 51%|█████     | 31477/61904 [5:34:29<12:35:14,  1.49s/it]
 51%|█████     | 31478/61904 [5:34:31<12:34:47,  1.49s/it]
 51%|█████     | 31479/61904 [5:34:32<12:43:19,  1.51s/it]
 51%|█████     | 31480/61904 [5:34:34<12:11:27,  1.44s/it]
                                                          
{'loss': 2.5307, 'learning_rate': 1.493063658757941e-07, 'epoch': 8.14}
+
 51%|█████     | 31480/61904 [5:34:34<12:11:27,  1.44s/it]
 51%|█████     | 31481/61904 [5:34:35<12:17:07,  1.45s/it]
 51%|█████     | 31482/61904 [5:34:37<12:00:44,  1.42s/it]
 51%|█████     | 31483/61904 [5:34:38<11:29:51,  1.36s/it]
 51%|█████     | 31484/61904 [5:34:39<11:28:05,  1.36s/it]
 51%|█████     | 31485/61904 [5:34:40<11:17:12,  1.34s/it]
 51%|█████     | 31486/61904 [5:34:42<10:56:58,  1.30s/it]
 51%|█████     | 31487/61904 [5:34:43<11:10:15,  1.32s/it]
 51%|█████     | 31488/61904 [5:34:44<11:30:33,  1.36s/it]
 51%|█████     | 31489/61904 [5:34:46<11:33:56,  1.37s/it]
 51%|█████     | 31490/61904 [5:34:47<11:41:09,  1.38s/it]
 51%|█████     | 31491/61904 [5:34:49<11:44:01,  1.39s/it]
 51%|█████     | 31492/61904 [5:34:50<11:36:53,  1.37s/it]
 51%|█████     | 31493/61904 [5:34:51<11:39:53,  1.38s/it]
 51%|█████     | 31494/61904 [5:34:53<11:27:56,  1.36s/it]
 51%|█████     | 31495/61904 [5:34:54<11:38:33,  1.38s/it]
 51%|█████     | 31496/61904 [5:34:56<11:48:27,  1.40s/it]
 51%|█████     | 31497/61904 [5:34:57<11:51:52,  1.40s/it]
 51%|█████     | 31498/61904 [5:34:58<12:00:04,  1.42s/it]
 51%|█████     | 31499/61904 [5:35:00<11:42:37,  1.39s/it]
 51%|█████     | 31500/61904 [5:35:01<11:42:43,  1.39s/it]
                                                          
{'loss': 2.4837, 'learning_rate': 1.4927395306625177e-07, 'epoch': 8.14}
+
 51%|█████     | 31500/61904 [5:35:01<11:42:43,  1.39s/it]
 51%|█████     | 31501/61904 [5:35:03<11:46:30,  1.39s/it]
 51%|█████     | 31502/61904 [5:35:04<12:25:32,  1.47s/it]
 51%|█████     | 31503/61904 [5:35:06<12:14:35,  1.45s/it]
 51%|█████     | 31504/61904 [5:35:07<11:53:31,  1.41s/it]
 51%|█████     | 31505/61904 [5:35:08<11:40:53,  1.38s/it]
 51%|█████     | 31506/61904 [5:35:10<11:26:30,  1.36s/it]
 51%|█████     | 31507/61904 [5:35:11<11:21:28,  1.35s/it]
 51%|█████     | 31508/61904 [5:35:12<11:35:01,  1.37s/it]
 51%|█████     | 31509/61904 [5:35:14<11:41:58,  1.39s/it]
 51%|█████     | 31510/61904 [5:35:15<12:05:08,  1.43s/it]
 51%|█████     | 31511/61904 [5:35:17<12:05:57,  1.43s/it]
 51%|█████     | 31512/61904 [5:35:18<12:09:00,  1.44s/it]
 51%|█████     | 31513/61904 [5:35:20<12:09:51,  1.44s/it]
 51%|█████     | 31514/61904 [5:35:21<12:12:30,  1.45s/it]
 51%|█████     | 31515/61904 [5:35:23<12:31:41,  1.48s/it]
 51%|█████     | 31516/61904 [5:35:24<12:11:17,  1.44s/it]
 51%|█████     | 31517/61904 [5:35:25<11:57:12,  1.42s/it]
 51%|█████     | 31518/61904 [5:35:27<12:04:17,  1.43s/it]
 51%|█████     | 31519/61904 [5:35:28<11:43:03,  1.39s/it]
 51%|█████     | 31520/61904 [5:35:29<11:40:58,  1.38s/it]
                                                          
{'loss': 2.5149, 'learning_rate': 1.4924154025670943e-07, 'epoch': 8.15}
+
 51%|█████     | 31520/61904 [5:35:29<11:40:58,  1.38s/it]
 51%|█████     | 31521/61904 [5:35:31<11:54:37,  1.41s/it]
 51%|█████     | 31522/61904 [5:35:32<12:01:51,  1.43s/it]
 51%|█████     | 31523/61904 [5:35:34<11:44:45,  1.39s/it]
 51%|█████     | 31524/61904 [5:35:35<11:34:58,  1.37s/it]
 51%|█████     | 31525/61904 [5:35:36<11:27:10,  1.36s/it]
 51%|█████     | 31526/61904 [5:35:38<11:41:02,  1.38s/it]
 51%|█████     | 31527/61904 [5:35:39<11:32:02,  1.37s/it]
 51%|█████     | 31528/61904 [5:35:40<11:27:48,  1.36s/it]
 51%|█████     | 31529/61904 [5:35:42<11:19:14,  1.34s/it]
 51%|█████     | 31530/61904 [5:35:43<11:06:27,  1.32s/it]
 51%|█████     | 31531/61904 [5:35:44<11:25:26,  1.35s/it]
 51%|█████     | 31532/61904 [5:35:46<11:30:20,  1.36s/it]
 51%|█████     | 31533/61904 [5:35:47<12:08:02,  1.44s/it]
 51%|█████     | 31534/61904 [5:35:49<11:38:13,  1.38s/it]
 51%|█████     | 31535/61904 [5:35:50<11:25:37,  1.35s/it]
 51%|█████     | 31536/61904 [5:35:51<11:20:42,  1.34s/it]
 51%|█████     | 31537/61904 [5:35:53<11:30:46,  1.36s/it]
 51%|█████     | 31538/61904 [5:35:54<11:15:31,  1.33s/it]
 51%|█████     | 31539/61904 [5:35:55<11:05:37,  1.32s/it]
 51%|█████     | 31540/61904 [5:35:57<11:27:39,  1.36s/it]
                                                          
{'loss': 2.4708, 'learning_rate': 1.4920912744716712e-07, 'epoch': 8.15}
+
 51%|█████     | 31540/61904 [5:35:57<11:27:39,  1.36s/it]
 51%|█████     | 31541/61904 [5:35:58<11:38:31,  1.38s/it]
 51%|█████     | 31542/61904 [5:36:00<11:34:36,  1.37s/it]
 51%|█████     | 31543/61904 [5:36:01<12:01:31,  1.43s/it]
 51%|█████     | 31544/61904 [5:36:02<11:47:28,  1.40s/it]
 51%|█████     | 31545/61904 [5:36:04<11:41:27,  1.39s/it]
 51%|█████     | 31546/61904 [5:36:05<11:22:59,  1.35s/it]
 51%|█████     | 31547/61904 [5:36:06<11:15:46,  1.34s/it]
 51%|█████     | 31548/61904 [5:36:08<11:26:36,  1.36s/it]
 51%|█████     | 31549/61904 [5:36:09<11:23:34,  1.35s/it]
 51%|█████     | 31550/61904 [5:36:11<11:43:47,  1.39s/it]
 51%|█████     | 31551/61904 [5:36:12<11:33:45,  1.37s/it]
 51%|█████     | 31552/61904 [5:36:13<11:24:25,  1.35s/it]
 51%|█████     | 31553/61904 [5:36:15<11:20:25,  1.35s/it]
 51%|█████     | 31554/61904 [5:36:16<11:16:47,  1.34s/it]
 51%|█████     | 31555/61904 [5:36:17<11:07:58,  1.32s/it]
 51%|█████     | 31556/61904 [5:36:19<11:28:00,  1.36s/it]
 51%|█████     | 31557/61904 [5:36:20<11:18:10,  1.34s/it]
 51%|█████     | 31558/61904 [5:36:21<11:23:39,  1.35s/it]
 51%|█████     | 31559/61904 [5:36:23<11:24:02,  1.35s/it]
 51%|█████     | 31560/61904 [5:36:24<11:17:48,  1.34s/it]
                                                          
{'loss': 2.5476, 'learning_rate': 1.4917671463762478e-07, 'epoch': 8.16}
+
 51%|█████     | 31560/61904 [5:36:24<11:17:48,  1.34s/it]
 51%|█████     | 31561/61904 [5:36:25<11:37:34,  1.38s/it]
 51%|█████     | 31562/61904 [5:36:27<11:52:37,  1.41s/it]
 51%|█████     | 31563/61904 [5:36:28<11:57:30,  1.42s/it]
 51%|█████     | 31564/61904 [5:36:30<11:43:20,  1.39s/it]
 51%|█████     | 31565/61904 [5:36:31<11:51:05,  1.41s/it]
 51%|█████     | 31566/61904 [5:36:32<11:40:30,  1.39s/it]
 51%|█████     | 31567/61904 [5:36:34<11:36:47,  1.38s/it]
 51%|█████     | 31568/61904 [5:36:35<11:07:10,  1.32s/it]
 51%|█████     | 31569/61904 [5:36:36<11:17:51,  1.34s/it]
 51%|█████     | 31570/61904 [5:36:38<11:01:39,  1.31s/it]
 51%|█████     | 31571/61904 [5:36:39<11:02:55,  1.31s/it]
 51%|█████     | 31572/61904 [5:36:40<11:05:02,  1.32s/it]
 51%|█████     | 31573/61904 [5:36:41<10:52:44,  1.29s/it]
 51%|█████     | 31574/61904 [5:36:43<11:17:35,  1.34s/it]
 51%|█████     | 31575/61904 [5:36:44<11:18:26,  1.34s/it]
 51%|█████     | 31576/61904 [5:36:46<11:40:35,  1.39s/it]
 51%|█████     | 31577/61904 [5:36:47<12:22:14,  1.47s/it]
 51%|█████     | 31578/61904 [5:36:49<12:03:35,  1.43s/it]
 51%|█████     | 31579/61904 [5:36:50<11:44:06,  1.39s/it]
 51%|█████     | 31580/61904 [5:36:52<12:10:04,  1.44s/it]
                                                          
{'loss': 2.5492, 'learning_rate': 1.4914430182808245e-07, 'epoch': 8.16}
+
 51%|█████     | 31580/61904 [5:36:52<12:10:04,  1.44s/it]
 51%|█████     | 31581/61904 [5:36:53<11:57:11,  1.42s/it]
 51%|█████     | 31582/61904 [5:36:54<11:49:23,  1.40s/it]
 51%|█████     | 31583/61904 [5:36:56<11:49:22,  1.40s/it]
 51%|█████     | 31584/61904 [5:36:57<11:41:49,  1.39s/it]
 51%|█████     | 31585/61904 [5:36:58<11:43:45,  1.39s/it]
 51%|█████     | 31586/61904 [5:37:00<11:48:26,  1.40s/it]
 51%|█████     | 31587/61904 [5:37:01<11:44:33,  1.39s/it]
 51%|█████     | 31588/61904 [5:37:03<11:37:04,  1.38s/it]
 51%|█████     | 31589/61904 [5:37:04<11:11:17,  1.33s/it]
 51%|█████     | 31590/61904 [5:37:05<11:19:14,  1.34s/it]
 51%|█████     | 31591/61904 [5:37:07<11:14:05,  1.33s/it]
 51%|█████     | 31592/61904 [5:37:08<11:18:30,  1.34s/it]
 51%|█████     | 31593/61904 [5:37:09<11:23:44,  1.35s/it]
 51%|█████     | 31594/61904 [5:37:11<11:21:41,  1.35s/it]
 51%|█████     | 31595/61904 [5:37:12<11:31:07,  1.37s/it]
 51%|█████     | 31596/61904 [5:37:13<11:31:16,  1.37s/it]
 51%|█████     | 31597/61904 [5:37:15<11:31:36,  1.37s/it]
 51%|█████     | 31598/61904 [5:37:16<11:28:07,  1.36s/it]
 51%|█████     | 31599/61904 [5:37:18<11:34:06,  1.37s/it]
 51%|█████     | 31600/61904 [5:37:19<11:36:35,  1.38s/it]
                                                          
{'loss': 2.5697, 'learning_rate': 1.491118890185401e-07, 'epoch': 8.17}
+
 51%|█████     | 31600/61904 [5:37:19<11:36:35,  1.38s/it]
 51%|█████     | 31601/61904 [5:37:20<11:38:17,  1.38s/it]
 51%|█████     | 31602/61904 [5:37:22<11:46:20,  1.40s/it]
 51%|█████     | 31603/61904 [5:37:23<11:23:40,  1.35s/it]
 51%|█████     | 31604/61904 [5:37:24<11:22:07,  1.35s/it]
 51%|█████     | 31605/61904 [5:37:26<11:12:45,  1.33s/it]
 51%|█████     | 31606/61904 [5:37:27<11:14:49,  1.34s/it]
 51%|█████     | 31607/61904 [5:37:28<11:21:36,  1.35s/it]
 51%|█████     | 31608/61904 [5:37:30<11:26:01,  1.36s/it]
 51%|█████     | 31609/61904 [5:37:31<11:14:44,  1.34s/it]
 51%|█████     | 31610/61904 [5:37:33<11:47:54,  1.40s/it]
 51%|█████     | 31611/61904 [5:37:34<11:31:23,  1.37s/it]
 51%|█████     | 31612/61904 [5:37:35<11:41:40,  1.39s/it]
 51%|█████     | 31613/61904 [5:37:37<11:36:45,  1.38s/it]
 51%|█████     | 31614/61904 [5:37:38<11:38:01,  1.38s/it]
 51%|█████     | 31615/61904 [5:37:39<11:40:55,  1.39s/it]
 51%|█████     | 31616/61904 [5:37:41<11:46:36,  1.40s/it]
 51%|█████     | 31617/61904 [5:37:42<11:30:50,  1.37s/it]
 51%|█████     | 31618/61904 [5:37:44<11:55:14,  1.42s/it]
 51%|█████     | 31619/61904 [5:37:45<11:48:38,  1.40s/it]
 51%|█████     | 31620/61904 [5:37:46<11:38:59,  1.38s/it]
                                                          
{'loss': 2.5333, 'learning_rate': 1.490794762089978e-07, 'epoch': 8.17}
+
 51%|█████     | 31620/61904 [5:37:46<11:38:59,  1.38s/it]
 51%|█████     | 31621/61904 [5:37:48<11:39:02,  1.39s/it]
 51%|█████     | 31622/61904 [5:37:49<11:36:37,  1.38s/it]
 51%|█████     | 31623/61904 [5:37:50<11:13:40,  1.33s/it]
 51%|█████     | 31624/61904 [5:37:52<11:06:56,  1.32s/it]
 51%|█████     | 31625/61904 [5:37:53<11:06:28,  1.32s/it]
 51%|█████     | 31626/61904 [5:37:54<11:17:28,  1.34s/it]
 51%|█████     | 31627/61904 [5:37:56<11:56:08,  1.42s/it]
 51%|█████     | 31628/61904 [5:37:57<11:32:16,  1.37s/it]
 51%|█████     | 31629/61904 [5:37:59<11:54:18,  1.42s/it]
 51%|█████     | 31630/61904 [5:38:00<11:34:41,  1.38s/it]
 51%|█████     | 31631/61904 [5:38:01<11:43:08,  1.39s/it]
 51%|█████     | 31632/61904 [5:38:03<11:47:13,  1.40s/it]
 51%|█████     | 31633/61904 [5:38:04<11:37:59,  1.38s/it]
 51%|█████     | 31634/61904 [5:38:06<11:36:59,  1.38s/it]
 51%|█████     | 31635/61904 [5:38:07<11:28:19,  1.36s/it]
 51%|█████     | 31636/61904 [5:38:08<11:51:45,  1.41s/it]
 51%|█████     | 31637/61904 [5:38:10<11:45:06,  1.40s/it]
 51%|█████     | 31638/61904 [5:38:11<11:54:00,  1.42s/it]
 51%|█████     | 31639/61904 [5:38:13<12:28:58,  1.48s/it]
 51%|█████     | 31640/61904 [5:38:14<12:16:25,  1.46s/it]
                                                          
{'loss': 2.5197, 'learning_rate': 1.4904706339945546e-07, 'epoch': 8.18}
+
 51%|█████     | 31640/61904 [5:38:14<12:16:25,  1.46s/it]
 51%|█████     | 31641/61904 [5:38:16<12:03:13,  1.43s/it]
 51%|█████     | 31642/61904 [5:38:17<11:56:25,  1.42s/it]
 51%|█████     | 31643/61904 [5:38:19<12:00:40,  1.43s/it]
 51%|█████     | 31644/61904 [5:38:20<11:44:10,  1.40s/it]
 51%|█████     | 31645/61904 [5:38:21<11:41:08,  1.39s/it]
 51%|█████     | 31646/61904 [5:38:23<11:49:02,  1.41s/it]
 51%|█████     | 31647/61904 [5:38:24<11:34:55,  1.38s/it]
 51%|█████     | 31648/61904 [5:38:25<11:37:03,  1.38s/it]
 51%|█████     | 31649/61904 [5:38:27<12:15:16,  1.46s/it]
 51%|█████     | 31650/61904 [5:38:28<11:52:26,  1.41s/it]
 51%|█████     | 31651/61904 [5:38:30<11:42:29,  1.39s/it]
 51%|█████     | 31652/61904 [5:38:31<11:38:12,  1.38s/it]
 51%|█████     | 31653/61904 [5:38:32<11:26:03,  1.36s/it]
 51%|█████     | 31654/61904 [5:38:34<11:27:44,  1.36s/it]
 51%|█████     | 31655/61904 [5:38:35<11:48:44,  1.41s/it]
 51%|█████     | 31656/61904 [5:38:37<11:38:59,  1.39s/it]
 51%|█████     | 31657/61904 [5:38:38<11:59:07,  1.43s/it]
 51%|█████     | 31658/61904 [5:38:39<11:30:01,  1.37s/it]
 51%|█████     | 31659/61904 [5:38:41<11:38:19,  1.39s/it]
 51%|█████     | 31660/61904 [5:38:42<11:26:45,  1.36s/it]
                                                          
{'loss': 2.4984, 'learning_rate': 1.4901465058991312e-07, 'epoch': 8.18}
+
 51%|█████     | 31660/61904 [5:38:42<11:26:45,  1.36s/it]
 51%|█████     | 31661/61904 [5:38:44<11:42:21,  1.39s/it]
 51%|█████     | 31662/61904 [5:38:45<11:15:11,  1.34s/it]
 51%|█████     | 31663/61904 [5:38:46<11:33:25,  1.38s/it]
 51%|█████     | 31664/61904 [5:38:48<11:32:29,  1.37s/it]
 51%|█████     | 31665/61904 [5:38:49<11:36:20,  1.38s/it]
 51%|█████     | 31666/61904 [5:38:50<11:32:44,  1.37s/it]
 51%|█████     | 31667/61904 [5:38:52<11:20:41,  1.35s/it]
 51%|█████     | 31668/61904 [5:38:53<11:24:17,  1.36s/it]
 51%|█████     | 31669/61904 [5:38:55<11:48:08,  1.41s/it]
 51%|█████     | 31670/61904 [5:38:56<11:43:03,  1.40s/it]
 51%|█████     | 31671/61904 [5:38:57<11:56:56,  1.42s/it]
 51%|█████     | 31672/61904 [5:38:59<12:09:07,  1.45s/it]
 51%|█████     | 31673/61904 [5:39:00<12:03:41,  1.44s/it]
 51%|█████     | 31674/61904 [5:39:02<11:53:45,  1.42s/it]
 51%|█████     | 31675/61904 [5:39:03<11:42:50,  1.40s/it]
 51%|█████     | 31676/61904 [5:39:04<11:40:15,  1.39s/it]
 51%|█████     | 31677/61904 [5:39:06<11:45:49,  1.40s/it]
 51%|█████     | 31678/61904 [5:39:07<11:44:44,  1.40s/it]
 51%|█████     | 31679/61904 [5:39:09<11:54:41,  1.42s/it]
 51%|█████     | 31680/61904 [5:39:10<11:49:36,  1.41s/it]
                                                          
{'loss': 2.5087, 'learning_rate': 1.489822377803708e-07, 'epoch': 8.19}
+
 51%|█████     | 31680/61904 [5:39:10<11:49:36,  1.41s/it]
 51%|█████     | 31681/61904 [5:39:12<11:57:16,  1.42s/it]
 51%|█████     | 31682/61904 [5:39:13<11:43:34,  1.40s/it]
 51%|█████     | 31683/61904 [5:39:14<11:33:22,  1.38s/it]
 51%|█████     | 31684/61904 [5:39:16<11:33:05,  1.38s/it]
 51%|█████     | 31685/61904 [5:39:17<11:23:04,  1.36s/it]
 51%|█████     | 31686/61904 [5:39:18<11:20:16,  1.35s/it]
 51%|█████     | 31687/61904 [5:39:20<11:32:42,  1.38s/it]
 51%|█████     | 31688/61904 [5:39:21<11:43:54,  1.40s/it]
 51%|█████     | 31689/61904 [5:39:22<11:33:18,  1.38s/it]
 51%|█████     | 31690/61904 [5:39:24<11:40:20,  1.39s/it]
 51%|█████     | 31691/61904 [5:39:25<12:15:53,  1.46s/it]
 51%|█████     | 31692/61904 [5:39:27<11:54:02,  1.42s/it]
 51%|█████     | 31693/61904 [5:39:28<11:38:28,  1.39s/it]
 51%|█████     | 31694/61904 [5:39:29<11:25:35,  1.36s/it]
 51%|█████     | 31695/61904 [5:39:31<11:17:13,  1.35s/it]
 51%|█████     | 31696/61904 [5:39:32<11:20:38,  1.35s/it]
 51%|█████     | 31697/61904 [5:39:33<11:21:09,  1.35s/it]
 51%|█████     | 31698/61904 [5:39:35<11:03:13,  1.32s/it]
 51%|█████     | 31699/61904 [5:39:36<11:00:30,  1.31s/it]
 51%|█████     | 31700/61904 [5:39:37<11:30:48,  1.37s/it]
                                                          
{'loss': 2.5842, 'learning_rate': 1.4894982497082847e-07, 'epoch': 8.19}
+
 51%|█████     | 31700/61904 [5:39:37<11:30:48,  1.37s/it]
 51%|█████     | 31701/61904 [5:39:39<11:16:02,  1.34s/it]
 51%|█████     | 31702/61904 [5:39:40<11:26:34,  1.36s/it]
 51%|█████     | 31703/61904 [5:39:42<11:46:36,  1.40s/it]
 51%|█████     | 31704/61904 [5:39:43<11:40:34,  1.39s/it]
 51%|█████     | 31705/61904 [5:39:44<11:26:55,  1.36s/it]
 51%|█████     | 31706/61904 [5:39:46<11:21:04,  1.35s/it]
 51%|█████     | 31707/61904 [5:39:47<11:32:25,  1.38s/it]
 51%|█████     | 31708/61904 [5:39:48<11:09:55,  1.33s/it]
 51%|█████     | 31709/61904 [5:39:50<11:02:27,  1.32s/it]
 51%|█████     | 31710/61904 [5:39:51<11:14:20,  1.34s/it]
 51%|█████     | 31711/61904 [5:39:52<11:12:51,  1.34s/it]
 51%|█████     | 31712/61904 [5:39:54<11:20:53,  1.35s/it]
 51%|█████     | 31713/61904 [5:39:55<11:14:07,  1.34s/it]
 51%|█████     | 31714/61904 [5:39:56<11:29:45,  1.37s/it]
 51%|█████     | 31715/61904 [5:39:58<11:19:29,  1.35s/it]
 51%|█████     | 31716/61904 [5:39:59<11:19:21,  1.35s/it]
 51%|█████     | 31717/61904 [5:40:00<11:07:28,  1.33s/it]
 51%|█████     | 31718/61904 [5:40:02<11:19:34,  1.35s/it]
 51%|█████     | 31719/61904 [5:40:03<11:34:54,  1.38s/it]
 51%|█████     | 31720/61904 [5:40:05<11:29:33,  1.37s/it]
                                                          
{'loss': 2.5249, 'learning_rate': 1.4891741216128613e-07, 'epoch': 8.2}
+
 51%|█████     | 31720/61904 [5:40:05<11:29:33,  1.37s/it]
 51%|█████     | 31721/61904 [5:40:06<11:43:58,  1.40s/it]
 51%|█████     | 31722/61904 [5:40:07<11:40:16,  1.39s/it]
 51%|█████     | 31723/61904 [5:40:09<11:17:55,  1.35s/it]
 51%|█████     | 31724/61904 [5:40:10<11:16:00,  1.34s/it]
 51%|█████     | 31725/61904 [5:40:11<11:19:44,  1.35s/it]
 51%|█████▏    | 31726/61904 [5:40:13<11:02:28,  1.32s/it]
 51%|█████▏    | 31727/61904 [5:40:14<11:30:13,  1.37s/it]
 51%|█████▏    | 31728/61904 [5:40:16<11:52:25,  1.42s/it]
 51%|█████▏    | 31729/61904 [5:40:17<11:49:23,  1.41s/it]
 51%|█████▏    | 31730/61904 [5:40:18<11:23:07,  1.36s/it]
 51%|█████▏    | 31731/61904 [5:40:20<11:29:36,  1.37s/it]
 51%|█████▏    | 31732/61904 [5:40:21<11:20:09,  1.35s/it]
 51%|█████▏    | 31733/61904 [5:40:22<11:39:37,  1.39s/it]
 51%|█████▏    | 31734/61904 [5:40:24<12:26:32,  1.48s/it]
 51%|█████▏    | 31735/61904 [5:40:26<12:27:46,  1.49s/it]
 51%|█████▏    | 31736/61904 [5:40:27<12:22:10,  1.48s/it]
 51%|█████▏    | 31737/61904 [5:40:29<12:16:28,  1.46s/it]
 51%|█████▏    | 31738/61904 [5:40:30<11:53:41,  1.42s/it]
 51%|█████▏    | 31739/61904 [5:40:31<12:10:16,  1.45s/it]
 51%|█████▏    | 31740/61904 [5:40:33<11:34:01,  1.38s/it]
                                                          
{'loss': 2.5729, 'learning_rate': 1.488849993517438e-07, 'epoch': 8.2}
+
 51%|█████▏    | 31740/61904 [5:40:33<11:34:01,  1.38s/it]
 51%|█████▏    | 31741/61904 [5:40:34<11:12:13,  1.34s/it]
 51%|█████▏    | 31742/61904 [5:40:35<11:20:10,  1.35s/it]
 51%|█████▏    | 31743/61904 [5:40:37<11:12:57,  1.34s/it]
 51%|█████▏    | 31744/61904 [5:40:38<11:38:20,  1.39s/it]
 51%|█████▏    | 31745/61904 [5:40:40<11:50:17,  1.41s/it]
 51%|█████▏    | 31746/61904 [5:40:41<11:35:07,  1.38s/it]
 51%|█████▏    | 31747/61904 [5:40:42<11:13:36,  1.34s/it]
 51%|█████▏    | 31748/61904 [5:40:44<11:38:02,  1.39s/it]
 51%|█████▏    | 31749/61904 [5:40:45<11:52:52,  1.42s/it]
 51%|█████▏    | 31750/61904 [5:40:46<11:43:44,  1.40s/it]
 51%|█████▏    | 31751/61904 [5:40:48<11:25:22,  1.36s/it]
 51%|█████▏    | 31752/61904 [5:40:49<11:36:40,  1.39s/it]
 51%|█████▏    | 31753/61904 [5:40:50<11:33:24,  1.38s/it]
 51%|█████▏    | 31754/61904 [5:40:52<11:33:19,  1.38s/it]
 51%|█████▏    | 31755/61904 [5:40:53<11:29:37,  1.37s/it]
 51%|█████▏    | 31756/61904 [5:40:55<11:26:01,  1.37s/it]
 51%|█████▏    | 31757/61904 [5:40:56<11:15:03,  1.34s/it]
 51%|█████▏    | 31758/61904 [5:40:57<11:12:39,  1.34s/it]
 51%|█████▏    | 31759/61904 [5:40:59<11:12:18,  1.34s/it]
 51%|█████▏    | 31760/61904 [5:41:00<11:06:36,  1.33s/it]
                                                          
{'loss': 2.5038, 'learning_rate': 1.4885258654220148e-07, 'epoch': 8.21}
+
 51%|█████▏    | 31760/61904 [5:41:00<11:06:36,  1.33s/it]
 51%|█████▏    | 31761/61904 [5:41:01<11:41:10,  1.40s/it]
 51%|█████▏    | 31762/61904 [5:41:03<11:30:58,  1.38s/it]
 51%|█████▏    | 31763/61904 [5:41:04<11:38:37,  1.39s/it]
 51%|█████▏    | 31764/61904 [5:41:05<11:33:34,  1.38s/it]
 51%|█████▏    | 31765/61904 [5:41:07<11:40:58,  1.40s/it]
 51%|█████▏    | 31766/61904 [5:41:08<11:44:41,  1.40s/it]
 51%|█████▏    | 31767/61904 [5:41:10<11:41:48,  1.40s/it]
 51%|█████▏    | 31768/61904 [5:41:11<11:41:19,  1.40s/it]
 51%|█████▏    | 31769/61904 [5:41:12<11:36:31,  1.39s/it]
 51%|█████▏    | 31770/61904 [5:41:14<11:26:42,  1.37s/it]
 51%|█████▏    | 31771/61904 [5:41:15<11:28:37,  1.37s/it]
 51%|█████▏    | 31772/61904 [5:41:17<11:50:52,  1.42s/it]
 51%|█████▏    | 31773/61904 [5:41:18<12:07:48,  1.45s/it]
 51%|█████▏    | 31774/61904 [5:41:20<11:41:04,  1.40s/it]
 51%|█████▏    | 31775/61904 [5:41:21<11:28:47,  1.37s/it]
 51%|█████▏    | 31776/61904 [5:41:22<11:49:23,  1.41s/it]
 51%|█████▏    | 31777/61904 [5:41:24<11:35:32,  1.39s/it]
 51%|█████▏    | 31778/61904 [5:41:25<11:21:37,  1.36s/it]
 51%|█████▏    | 31779/61904 [5:41:26<11:34:06,  1.38s/it]
 51%|█████▏    | 31780/61904 [5:41:28<11:27:00,  1.37s/it]
                                                          
{'loss': 2.512, 'learning_rate': 1.4882017373265914e-07, 'epoch': 8.21}
+
 51%|█████▏    | 31780/61904 [5:41:28<11:27:00,  1.37s/it]
 51%|█████▏    | 31781/61904 [5:41:29<11:10:07,  1.33s/it]
 51%|█████▏    | 31782/61904 [5:41:30<11:33:48,  1.38s/it]
 51%|█████▏    | 31783/61904 [5:41:32<11:25:08,  1.36s/it]
 51%|█████▏    | 31784/61904 [5:41:34<12:18:23,  1.47s/it]
 51%|█████▏    | 31785/61904 [5:41:35<11:53:10,  1.42s/it]
 51%|█████▏    | 31786/61904 [5:41:36<11:43:44,  1.40s/it]
 51%|█████▏    | 31787/61904 [5:41:38<11:35:07,  1.38s/it]
 51%|█████▏    | 31788/61904 [5:41:39<11:52:45,  1.42s/it]
 51%|█████▏    | 31789/61904 [5:41:40<11:30:24,  1.38s/it]
 51%|█████▏    | 31790/61904 [5:41:42<11:23:28,  1.36s/it]
 51%|█████▏    | 31791/61904 [5:41:43<11:18:05,  1.35s/it]
 51%|█████▏    | 31792/61904 [5:41:44<11:18:08,  1.35s/it]
 51%|█████▏    | 31793/61904 [5:41:46<11:21:04,  1.36s/it]
 51%|█████▏    | 31794/61904 [5:41:47<11:03:34,  1.32s/it]
 51%|���████▏    | 31795/61904 [5:41:48<11:00:00,  1.32s/it]
 51%|█████▏    | 31796/61904 [5:41:50<11:08:53,  1.33s/it]
 51%|█████▏    | 31797/61904 [5:41:51<11:06:14,  1.33s/it]
 51%|█████▏    | 31798/61904 [5:41:52<11:11:57,  1.34s/it]
 51%|█████▏    | 31799/61904 [5:41:54<11:03:25,  1.32s/it]
 51%|█████▏    | 31800/61904 [5:41:55<10:52:03,  1.30s/it]
                                                          
{'loss': 2.6194, 'learning_rate': 1.487877609231168e-07, 'epoch': 8.22}
+
 51%|█████▏    | 31800/61904 [5:41:55<10:52:03,  1.30s/it]
 51%|█████▏    | 31801/61904 [5:41:56<10:51:30,  1.30s/it]
 51%|█████▏    | 31802/61904 [5:41:57<10:48:53,  1.29s/it]
 51%|█████▏    | 31803/61904 [5:41:59<10:51:49,  1.30s/it]
 51%|█████▏    | 31804/61904 [5:42:00<11:10:58,  1.34s/it]
 51%|█████▏    | 31805/61904 [5:42:01<11:12:38,  1.34s/it]
 51%|█████▏    | 31806/61904 [5:42:03<11:31:49,  1.38s/it]
 51%|█████▏    | 31807/61904 [5:42:04<11:30:28,  1.38s/it]
 51%|█████▏    | 31808/61904 [5:42:06<11:28:44,  1.37s/it]
 51%|█████▏    | 31809/61904 [5:42:07<11:04:49,  1.33s/it]
 51%|█████▏    | 31810/61904 [5:42:09<11:49:11,  1.41s/it]
 51%|█████▏    | 31811/61904 [5:42:10<12:12:55,  1.46s/it]
 51%|█████▏    | 31812/61904 [5:42:12<12:40:49,  1.52s/it]
 51%|█████▏    | 31813/61904 [5:42:13<12:30:42,  1.50s/it]
 51%|█████▏    | 31814/61904 [5:42:15<12:21:49,  1.48s/it]
 51%|█████▏    | 31815/61904 [5:42:16<12:24:46,  1.49s/it]
 51%|█████▏    | 31816/61904 [5:42:18<12:23:07,  1.48s/it]
 51%|█████▏    | 31817/61904 [5:42:19<12:00:17,  1.44s/it]
 51%|█████▏    | 31818/61904 [5:42:20<12:14:42,  1.47s/it]
 51%|█████▏    | 31819/61904 [5:42:22<12:08:27,  1.45s/it]
 51%|█████▏    | 31820/61904 [5:42:23<11:41:01,  1.40s/it]
                                                          
{'loss': 2.5354, 'learning_rate': 1.4875534811357447e-07, 'epoch': 8.22}
+
 51%|█████▏    | 31820/61904 [5:42:23<11:41:01,  1.40s/it]
 51%|█████▏    | 31821/61904 [5:42:25<11:43:50,  1.40s/it]
 51%|█████▏    | 31822/61904 [5:42:26<11:49:09,  1.41s/it]
 51%|█████▏    | 31823/61904 [5:42:27<11:16:44,  1.35s/it]
 51%|█████▏    | 31824/61904 [5:42:29<11:09:37,  1.34s/it]
 51%|█████▏    | 31825/61904 [5:42:30<11:07:43,  1.33s/it]
 51%|█████▏    | 31826/61904 [5:42:31<11:06:37,  1.33s/it]
 51%|█████▏    | 31827/61904 [5:42:33<11:20:24,  1.36s/it]
 51%|█████▏    | 31828/61904 [5:42:34<11:25:17,  1.37s/it]
 51%|█████▏    | 31829/61904 [5:42:35<11:19:26,  1.36s/it]
 51%|█████▏    | 31830/61904 [5:42:37<11:15:06,  1.35s/it]
 51%|█████▏    | 31831/61904 [5:42:38<11:35:07,  1.39s/it]
 51%|█████▏    | 31832/61904 [5:42:39<11:33:23,  1.38s/it]
 51%|█████▏    | 31833/61904 [5:42:41<11:27:03,  1.37s/it]
 51%|█████▏    | 31834/61904 [5:42:42<11:29:13,  1.38s/it]
 51%|█████▏    | 31835/61904 [5:42:44<11:40:43,  1.40s/it]
 51%|█████▏    | 31836/61904 [5:42:45<11:20:35,  1.36s/it]
 51%|█████▏    | 31837/61904 [5:42:46<11:10:18,  1.34s/it]
 51%|█████▏    | 31838/61904 [5:42:48<11:21:46,  1.36s/it]
 51%|█████▏    | 31839/61904 [5:42:49<11:09:51,  1.34s/it]
 51%|█████▏    | 31840/61904 [5:42:50<10:56:41,  1.31s/it]
                                                          
{'loss': 2.577, 'learning_rate': 1.4872293530403216e-07, 'epoch': 8.23}
+
 51%|█████▏    | 31840/61904 [5:42:50<10:56:41,  1.31s/it]
 51%|█████▏    | 31841/61904 [5:42:51<10:55:44,  1.31s/it]
 51%|█████▏    | 31842/61904 [5:42:53<11:26:15,  1.37s/it]
 51%|█████▏    | 31843/61904 [5:42:54<11:09:12,  1.34s/it]
 51%|█████▏    | 31844/61904 [5:42:56<11:15:08,  1.35s/it]
 51%|█████▏    | 31845/61904 [5:42:57<12:03:05,  1.44s/it]
 51%|█████▏    | 31846/61904 [5:42:59<12:13:59,  1.47s/it]
 51%|█████▏    | 31847/61904 [5:43:00<12:00:43,  1.44s/it]
 51%|█████▏    | 31848/61904 [5:43:02<11:48:41,  1.41s/it]
 51%|█████▏    | 31849/61904 [5:43:03<11:57:52,  1.43s/it]
 51%|█████▏    | 31850/61904 [5:43:04<11:39:45,  1.40s/it]
 51%|█████▏    | 31851/61904 [5:43:06<11:50:51,  1.42s/it]
 51%|█████▏    | 31852/61904 [5:43:07<11:27:46,  1.37s/it]
 51%|█████▏    | 31853/61904 [5:43:08<11:11:21,  1.34s/it]
 51%|█████▏    | 31854/61904 [5:43:10<11:12:22,  1.34s/it]
 51%|█████▏    | 31855/61904 [5:43:11<11:13:12,  1.34s/it]
 51%|█████▏    | 31856/61904 [5:43:12<11:13:49,  1.35s/it]
 51%|█████▏    | 31857/61904 [5:43:14<11:45:02,  1.41s/it]
 51%|█████▏    | 31858/61904 [5:43:15<12:00:11,  1.44s/it]
 51%|█████▏    | 31859/61904 [5:43:17<11:42:50,  1.40s/it]
 51%|█████▏    | 31860/61904 [5:43:18<11:31:16,  1.38s/it]
                                                          
{'loss': 2.5439, 'learning_rate': 1.4869052249448982e-07, 'epoch': 8.23}
+
 51%|█████▏    | 31860/61904 [5:43:18<11:31:16,  1.38s/it]
 51%|█████▏    | 31861/61904 [5:43:19<11:27:03,  1.37s/it]
 51%|█████▏    | 31862/61904 [5:43:21<11:20:30,  1.36s/it]
 51%|█████▏    | 31863/61904 [5:43:22<11:23:50,  1.37s/it]
 51%|█████▏    | 31864/61904 [5:43:24<11:51:41,  1.42s/it]
 51%|█████▏    | 31865/61904 [5:43:25<12:06:16,  1.45s/it]
 51%|█████▏    | 31866/61904 [5:43:27<12:01:24,  1.44s/it]
 51%|█████▏    | 31867/61904 [5:43:28<11:56:46,  1.43s/it]
 51%|█████▏    | 31868/61904 [5:43:30<12:04:37,  1.45s/it]
 51%|█████▏    | 31869/61904 [5:43:31<11:53:00,  1.42s/it]
 51%|█████▏    | 31870/61904 [5:43:32<12:14:42,  1.47s/it]
 51%|█████▏    | 31871/61904 [5:43:34<12:09:09,  1.46s/it]
 51%|█████▏    | 31872/61904 [5:43:35<12:11:55,  1.46s/it]
 51%|█████▏    | 31873/61904 [5:43:37<11:42:04,  1.40s/it]
 51%|█████▏    | 31874/61904 [5:43:38<11:23:21,  1.37s/it]
 51%|█████▏    | 31875/61904 [5:43:39<11:18:44,  1.36s/it]
 51%|█████▏    | 31876/61904 [5:43:40<11:03:50,  1.33s/it]
 51%|█████▏    | 31877/61904 [5:43:42<11:09:24,  1.34s/it]
 51%|█████▏    | 31878/61904 [5:43:43<11:09:41,  1.34s/it]
 51%|█████▏    | 31879/61904 [5:43:45<11:19:50,  1.36s/it]
 51%|█████▏    | 31880/61904 [5:43:46<11:31:52,  1.38s/it]
                                                          
{'loss': 2.4729, 'learning_rate': 1.4865810968494748e-07, 'epoch': 8.24}
+
 51%|█████▏    | 31880/61904 [5:43:46<11:31:52,  1.38s/it]
 52%|█████▏    | 31881/61904 [5:43:47<11:17:59,  1.35s/it]
 52%|█████▏    | 31882/61904 [5:43:49<11:12:20,  1.34s/it]
 52%|█████▏    | 31883/61904 [5:43:50<11:13:14,  1.35s/it]
 52%|█████▏    | 31884/61904 [5:43:51<11:16:43,  1.35s/it]
 52%|█████▏    | 31885/61904 [5:43:53<11:29:39,  1.38s/it]
 52%|█████▏    | 31886/61904 [5:43:54<11:36:25,  1.39s/it]
 52%|█████▏    | 31887/61904 [5:43:56<11:23:30,  1.37s/it]
 52%|█████▏    | 31888/61904 [5:43:57<11:40:47,  1.40s/it]
 52%|█████▏    | 31889/61904 [5:43:58<11:26:02,  1.37s/it]
 52%|█████▏    | 31890/61904 [5:44:00<11:11:24,  1.34s/it]
 52%|█████▏    | 31891/61904 [5:44:01<11:26:16,  1.37s/it]
 52%|█████▏    | 31892/61904 [5:44:02<11:10:56,  1.34s/it]
 52%|█████▏    | 31893/61904 [5:44:04<11:07:48,  1.34s/it]
 52%|█████▏    | 31894/61904 [5:44:05<11:27:32,  1.37s/it]
 52%|█████▏    | 31895/61904 [5:44:06<11:29:05,  1.38s/it]
 52%|█████▏    | 31896/61904 [5:44:08<11:29:44,  1.38s/it]
 52%|█████▏    | 31897/61904 [5:44:09<11:25:23,  1.37s/it]
 52%|█████▏    | 31898/61904 [5:44:11<11:15:34,  1.35s/it]
 52%|█████▏    | 31899/61904 [5:44:12<11:15:04,  1.35s/it]
 52%|█████▏    | 31900/61904 [5:44:13<11:02:52,  1.33s/it]
                                                          
{'loss': 2.5979, 'learning_rate': 1.4862569687540514e-07, 'epoch': 8.24}
+
 52%|█████▏    | 31900/61904 [5:44:13<11:02:52,  1.33s/it]
 52%|█████▏    | 31901/61904 [5:44:15<11:33:51,  1.39s/it]
 52%|█████▏    | 31902/61904 [5:44:16<11:29:45,  1.38s/it]
 52%|█████▏    | 31903/61904 [5:44:17<11:26:22,  1.37s/it]
 52%|█████▏    | 31904/61904 [5:44:19<11:18:41,  1.36s/it]
 52%|█████▏    | 31905/61904 [5:44:20<11:19:17,  1.36s/it]
 52%|█████▏    | 31906/61904 [5:44:22<12:00:10,  1.44s/it]
 52%|█████▏    | 31907/61904 [5:44:23<11:47:18,  1.41s/it]
 52%|█████▏    | 31908/61904 [5:44:24<11:22:55,  1.37s/it]
 52%|█████▏    | 31909/61904 [5:44:26<11:21:37,  1.36s/it]
 52%|█████▏    | 31910/61904 [5:44:27<11:25:48,  1.37s/it]
 52%|█████▏    | 31911/61904 [5:44:28<11:21:51,  1.36s/it]
 52%|█████▏    | 31912/61904 [5:44:30<11:15:54,  1.35s/it]
 52%|█████▏    | 31913/61904 [5:44:31<11:08:14,  1.34s/it]
 52%|█████▏    | 31914/61904 [5:44:32<11:25:13,  1.37s/it]
 52%|█████▏    | 31915/61904 [5:44:34<11:32:27,  1.39s/it]
 52%|█████▏    | 31916/61904 [5:44:35<11:55:55,  1.43s/it]
 52%|█████▏    | 31917/61904 [5:44:37<11:38:07,  1.40s/it]
 52%|█████▏    | 31918/61904 [5:44:38<11:33:07,  1.39s/it]
 52%|█████▏    | 31919/61904 [5:44:39<11:25:49,  1.37s/it]
 52%|█████▏    | 31920/61904 [5:44:41<11:18:45,  1.36s/it]
                                                          
{'loss': 2.5676, 'learning_rate': 1.4859328406586283e-07, 'epoch': 8.25}
+
 52%|█████▏    | 31920/61904 [5:44:41<11:18:45,  1.36s/it]
 52%|█████▏    | 31921/61904 [5:44:42<11:25:27,  1.37s/it]
 52%|█████▏    | 31922/61904 [5:44:44<11:34:52,  1.39s/it]
 52%|█████▏    | 31923/61904 [5:44:45<11:11:43,  1.34s/it]
 52%|█████▏    | 31924/61904 [5:44:46<11:02:45,  1.33s/it]
 52%|█████▏    | 31925/61904 [5:44:48<11:24:12,  1.37s/it]
 52%|█████▏    | 31926/61904 [5:44:49<11:27:15,  1.38s/it]
 52%|█████▏    | 31927/61904 [5:44:50<11:44:07,  1.41s/it]
 52%|█████▏    | 31928/61904 [5:44:52<11:38:14,  1.40s/it]
 52%|█████▏    | 31929/61904 [5:44:53<11:18:48,  1.36s/it]
 52%|█████▏    | 31930/61904 [5:44:54<11:15:19,  1.35s/it]
 52%|█████▏    | 31931/61904 [5:44:56<11:18:02,  1.36s/it]
 52%|█████▏    | 31932/61904 [5:44:57<11:22:01,  1.37s/it]
 52%|█████▏    | 31933/61904 [5:44:58<11:04:30,  1.33s/it]
 52%|█████▏    | 31934/61904 [5:45:00<11:06:52,  1.34s/it]
 52%|█████▏    | 31935/61904 [5:45:01<11:18:28,  1.36s/it]
 52%|█████▏    | 31936/61904 [5:45:03<11:16:26,  1.35s/it]
 52%|█████▏    | 31937/61904 [5:45:04<11:31:52,  1.39s/it]
 52%|█████▏    | 31938/61904 [5:45:06<11:57:16,  1.44s/it]
 52%|█████▏    | 31939/61904 [5:45:07<11:30:06,  1.38s/it]
 52%|█████▏    | 31940/61904 [5:45:08<11:02:17,  1.33s/it]
                                                          
{'loss': 2.5859, 'learning_rate': 1.485608712563205e-07, 'epoch': 8.25}
+
 52%|█████▏    | 31940/61904 [5:45:08<11:02:17,  1.33s/it]
 52%|█████▏    | 31941/61904 [5:45:09<11:04:51,  1.33s/it]
 52%|█████▏    | 31942/61904 [5:45:11<11:38:09,  1.40s/it]
 52%|█████▏    | 31943/61904 [5:45:12<11:37:16,  1.40s/it]
 52%|█████▏    | 31944/61904 [5:45:14<11:48:08,  1.42s/it]
 52%|█████▏    | 31945/61904 [5:45:15<11:37:44,  1.40s/it]
 52%|█████▏    | 31946/61904 [5:45:16<11:17:53,  1.36s/it]
 52%|█████▏    | 31947/61904 [5:45:18<11:39:26,  1.40s/it]
 52%|█████▏    | 31948/61904 [5:45:19<11:30:36,  1.38s/it]
 52%|█████▏    | 31949/61904 [5:45:21<11:18:37,  1.36s/it]
 52%|█████▏    | 31950/61904 [5:45:22<11:08:03,  1.34s/it]
 52%|█████▏    | 31951/61904 [5:45:23<11:14:59,  1.35s/it]
 52%|█████▏    | 31952/61904 [5:45:25<11:14:11,  1.35s/it]
 52%|█████▏    | 31953/61904 [5:45:26<11:23:17,  1.37s/it]
 52%|█████▏    | 31954/61904 [5:45:27<11:08:48,  1.34s/it]
 52%|█████▏    | 31955/61904 [5:45:29<11:18:26,  1.36s/it]
 52%|█████▏    | 31956/61904 [5:45:30<11:03:41,  1.33s/it]
 52%|█████▏    | 31957/61904 [5:45:32<11:45:54,  1.41s/it]
 52%|█████▏    | 31958/61904 [5:45:33<11:41:51,  1.41s/it]
 52%|█████▏    | 31959/61904 [5:45:34<11:23:53,  1.37s/it]
 52%|█████▏    | 31960/61904 [5:45:36<11:14:00,  1.35s/it]
                                                          
{'loss': 2.558, 'learning_rate': 1.4852845844677815e-07, 'epoch': 8.26}
+
 52%|█████▏    | 31960/61904 [5:45:36<11:14:00,  1.35s/it]
 52%|█████▏    | 31961/61904 [5:45:37<11:42:00,  1.41s/it]
 52%|█████▏    | 31962/61904 [5:45:38<11:19:28,  1.36s/it]
 52%|█████▏    | 31963/61904 [5:45:40<11:31:19,  1.39s/it]
 52%|█████▏    | 31964/61904 [5:45:41<11:19:54,  1.36s/it]
 52%|█████▏    | 31965/61904 [5:45:42<11:12:31,  1.35s/it]
 52%|█████▏    | 31966/61904 [5:45:44<11:17:00,  1.36s/it]
 52%|█████▏    | 31967/61904 [5:45:45<11:17:20,  1.36s/it]
 52%|█████▏    | 31968/61904 [5:45:47<11:24:44,  1.37s/it]
 52%|█████▏    | 31969/61904 [5:45:48<11:34:41,  1.39s/it]
 52%|█████▏    | 31970/61904 [5:45:49<11:23:41,  1.37s/it]
 52%|█████▏    | 31971/61904 [5:45:51<11:56:08,  1.44s/it]
 52%|█████▏    | 31972/61904 [5:45:52<11:51:04,  1.43s/it]
 52%|█████▏    | 31973/61904 [5:45:54<11:52:33,  1.43s/it]
 52%|█████▏    | 31974/61904 [5:45:55<11:41:24,  1.41s/it]
 52%|█████▏    | 31975/61904 [5:45:56<11:38:11,  1.40s/it]
 52%|█████▏    | 31976/61904 [5:45:58<11:17:04,  1.36s/it]
 52%|█████▏    | 31977/61904 [5:45:59<11:23:00,  1.37s/it]
 52%|█████▏    | 31978/61904 [5:46:00<11:17:10,  1.36s/it]
 52%|█████▏    | 31979/61904 [5:46:02<11:31:58,  1.39s/it]
 52%|█████▏    | 31980/61904 [5:46:03<11:35:49,  1.40s/it]
                                                          
{'loss': 2.5678, 'learning_rate': 1.4849604563723584e-07, 'epoch': 8.27}
+
 52%|█████▏    | 31980/61904 [5:46:03<11:35:49,  1.40s/it]
 52%|█████▏    | 31981/61904 [5:46:05<11:35:44,  1.40s/it]
 52%|█████▏    | 31982/61904 [5:46:06<11:53:45,  1.43s/it]
 52%|█████▏    | 31983/61904 [5:46:07<11:31:08,  1.39s/it]
 52%|█████▏    | 31984/61904 [5:46:09<11:37:32,  1.40s/it]
 52%|█████▏    | 31985/61904 [5:46:10<11:34:14,  1.39s/it]
 52%|█████▏    | 31986/61904 [5:46:12<11:21:07,  1.37s/it]
 52%|█████▏    | 31987/61904 [5:46:13<11:08:30,  1.34s/it]
 52%|█████▏    | 31988/61904 [5:46:14<10:55:55,  1.32s/it]
 52%|█████▏    | 31989/61904 [5:46:15<10:51:18,  1.31s/it]
 52%|█████▏    | 31990/61904 [5:46:17<11:32:07,  1.39s/it]
 52%|█████▏    | 31991/61904 [5:46:19<11:55:43,  1.44s/it]
 52%|█████▏    | 31992/61904 [5:46:20<12:08:38,  1.46s/it]
 52%|█████▏    | 31993/61904 [5:46:22<12:33:32,  1.51s/it]
 52%|█████▏    | 31994/61904 [5:46:23<11:58:38,  1.44s/it]
 52%|█████▏    | 31995/61904 [5:46:24<11:39:15,  1.40s/it]
 52%|█████▏    | 31996/61904 [5:46:26<11:26:53,  1.38s/it]
 52%|█████▏    | 31997/61904 [5:46:27<11:19:49,  1.36s/it]
 52%|█████▏    | 31998/61904 [5:46:28<11:36:35,  1.40s/it]
 52%|█████▏    | 31999/61904 [5:46:30<11:48:41,  1.42s/it]
 52%|█████▏    | 32000/61904 [5:46:31<12:13:58,  1.47s/it]
                                                          
{'loss': 2.5299, 'learning_rate': 1.484636328276935e-07, 'epoch': 8.27}
+
 52%|█████▏    | 32000/61904 [5:46:31<12:13:58,  1.47s/it]
 52%|█████▏    | 32001/61904 [5:46:33<12:33:30,  1.51s/it]
 52%|█████▏    | 32002/61904 [5:46:34<12:03:11,  1.45s/it]
 52%|█████▏    | 32003/61904 [5:46:36<12:00:54,  1.45s/it]
 52%|█████▏    | 32004/61904 [5:46:37<12:07:47,  1.46s/it]
 52%|█████▏    | 32005/61904 [5:46:39<11:54:23,  1.43s/it]
 52%|█████▏    | 32006/61904 [5:46:40<11:37:19,  1.40s/it]
 52%|█████▏    | 32007/61904 [5:46:42<11:55:10,  1.44s/it]
 52%|█████▏    | 32008/61904 [5:46:43<11:28:43,  1.38s/it]
 52%|█████▏    | 32009/61904 [5:46:44<12:04:52,  1.45s/it]
 52%|█████▏    | 32010/61904 [5:46:46<11:48:57,  1.42s/it]
 52%|█████▏    | 32011/61904 [5:46:47<11:35:13,  1.40s/it]
 52%|█████▏    | 32012/61904 [5:46:49<12:21:25,  1.49s/it]
 52%|█████▏    | 32013/61904 [5:46:50<12:01:43,  1.45s/it]
 52%|█████▏    | 32014/61904 [5:46:51<11:39:32,  1.40s/it]
 52%|█████▏    | 32015/61904 [5:46:53<11:30:10,  1.39s/it]
 52%|█████▏    | 32016/61904 [5:46:54<11:54:47,  1.43s/it]
 52%|█████▏    | 32017/61904 [5:46:56<12:05:46,  1.46s/it]
 52%|█████▏    | 32018/61904 [5:46:57<11:45:25,  1.42s/it]
 52%|█████▏    | 32019/61904 [5:46:59<11:47:40,  1.42s/it]
 52%|█████▏    | 32020/61904 [5:47:00<11:34:49,  1.40s/it]
                                                          
{'loss': 2.5439, 'learning_rate': 1.4843122001815117e-07, 'epoch': 8.28}
+
 52%|█████▏    | 32020/61904 [5:47:00<11:34:49,  1.40s/it]
 52%|█████▏    | 32021/61904 [5:47:01<11:35:33,  1.40s/it]
 52%|█████▏    | 32022/61904 [5:47:03<11:23:40,  1.37s/it]
 52%|█████▏    | 32023/61904 [5:47:04<11:28:04,  1.38s/it]
 52%|█████▏    | 32024/61904 [5:47:06<11:40:12,  1.41s/it]
 52%|█████▏    | 32025/61904 [5:47:07<11:45:15,  1.42s/it]
 52%|█████▏    | 32026/61904 [5:47:08<11:50:01,  1.43s/it]
 52%|█████▏    | 32027/61904 [5:47:10<11:40:18,  1.41s/it]
 52%|█████▏    | 32028/61904 [5:47:11<11:48:30,  1.42s/it]
 52%|█████▏    | 32029/61904 [5:47:12<11:22:36,  1.37s/it]
 52%|█████▏    | 32030/61904 [5:47:14<11:44:53,  1.42s/it]
 52%|█████▏    | 32031/61904 [5:47:15<11:54:50,  1.44s/it]
 52%|█████▏    | 32032/61904 [5:47:17<11:56:58,  1.44s/it]
 52%|█████▏    | 32033/61904 [5:47:18<11:39:59,  1.41s/it]
 52%|█████▏    | 32034/61904 [5:47:20<11:53:34,  1.43s/it]
 52%|█████▏    | 32035/61904 [5:47:21<11:31:45,  1.39s/it]
 52%|█████▏    | 32036/61904 [5:47:22<11:23:55,  1.37s/it]
 52%|█████▏    | 32037/61904 [5:47:24<11:48:47,  1.42s/it]
 52%|█████▏    | 32038/61904 [5:47:25<12:00:12,  1.45s/it]
 52%|█████▏    | 32039/61904 [5:47:27<12:06:27,  1.46s/it]
 52%|█████▏    | 32040/61904 [5:47:28<12:06:04,  1.46s/it]
                                                          
{'loss': 2.4766, 'learning_rate': 1.4839880720860883e-07, 'epoch': 8.28}
+
 52%|█████▏    | 32040/61904 [5:47:28<12:06:04,  1.46s/it]
 52%|█████▏    | 32041/61904 [5:47:30<11:51:00,  1.43s/it]
 52%|█████▏    | 32042/61904 [5:47:31<11:43:10,  1.41s/it]
 52%|█████▏    | 32043/61904 [5:47:32<11:40:42,  1.41s/it]
 52%|█████▏    | 32044/61904 [5:47:34<11:39:36,  1.41s/it]
 52%|█████▏    | 32045/61904 [5:47:35<11:24:50,  1.38s/it]
 52%|█████▏    | 32046/61904 [5:47:36<11:07:51,  1.34s/it]
 52%|█████▏    | 32047/61904 [5:47:38<11:11:55,  1.35s/it]
 52%|█████▏    | 32048/61904 [5:47:39<11:06:34,  1.34s/it]
 52%|█████▏    | 32049/61904 [5:47:41<11:15:12,  1.36s/it]
 52%|█████▏    | 32050/61904 [5:47:42<11:11:44,  1.35s/it]
 52%|█████▏    | 32051/61904 [5:47:43<11:11:15,  1.35s/it]
 52%|█████▏    | 32052/61904 [5:47:45<11:29:32,  1.39s/it]
 52%|█████▏    | 32053/61904 [5:47:46<11:33:43,  1.39s/it]
 52%|█████▏    | 32054/61904 [5:47:48<11:59:32,  1.45s/it]
 52%|█████▏    | 32055/61904 [5:47:49<11:43:49,  1.41s/it]
 52%|█████▏    | 32056/61904 [5:47:50<11:49:34,  1.43s/it]
 52%|█████▏    | 32057/61904 [5:47:52<12:04:58,  1.46s/it]
 52%|█████▏    | 32058/61904 [5:47:53<11:39:07,  1.41s/it]
 52%|█████▏    | 32059/61904 [5:47:55<11:24:09,  1.38s/it]
 52%|█████▏    | 32060/61904 [5:47:56<11:09:50,  1.35s/it]
                                                          
{'loss': 2.5289, 'learning_rate': 1.4836639439906652e-07, 'epoch': 8.29}
+
 52%|█████▏    | 32060/61904 [5:47:56<11:09:50,  1.35s/it]
 52%|█████▏    | 32061/61904 [5:47:57<11:00:26,  1.33s/it]
 52%|█████▏    | 32062/61904 [5:47:59<11:07:23,  1.34s/it]
 52%|█████▏    | 32063/61904 [5:48:00<11:42:44,  1.41s/it]
 52%|█████▏    | 32064/61904 [5:48:01<11:28:41,  1.38s/it]
 52%|█████▏    | 32065/61904 [5:48:03<12:08:20,  1.46s/it]
 52%|█████▏    | 32066/61904 [5:48:04<11:41:34,  1.41s/it]
 52%|█████▏    | 32067/61904 [5:48:06<11:23:31,  1.37s/it]
 52%|█████▏    | 32068/61904 [5:48:07<11:07:40,  1.34s/it]
 52%|█████▏    | 32069/61904 [5:48:08<11:16:58,  1.36s/it]
 52%|█████▏    | 32070/61904 [5:48:10<11:25:38,  1.38s/it]
 52%|█████▏    | 32071/61904 [5:48:11<11:20:10,  1.37s/it]
 52%|█████▏    | 32072/61904 [5:48:12<11:06:32,  1.34s/it]
 52%|█████▏    | 32073/61904 [5:48:14<11:18:04,  1.36s/it]
 52%|█████▏    | 32074/61904 [5:48:15<11:09:01,  1.35s/it]
 52%|█████▏    | 32075/61904 [5:48:16<11:03:24,  1.33s/it]
 52%|█████▏    | 32076/61904 [5:48:18<11:02:14,  1.33s/it]
 52%|█████▏    | 32077/61904 [5:48:19<11:05:59,  1.34s/it]
 52%|█████▏    | 32078/61904 [5:48:21<11:23:40,  1.38s/it]
 52%|█████▏    | 32079/61904 [5:48:22<11:29:15,  1.39s/it]
 52%|█████▏    | 32080/61904 [5:48:23<11:14:07,  1.36s/it]
                                                          
{'loss': 2.5708, 'learning_rate': 1.4833398158952418e-07, 'epoch': 8.29}
+
 52%|█████▏    | 32080/61904 [5:48:23<11:14:07,  1.36s/it]
 52%|█████▏    | 32081/61904 [5:48:25<11:32:58,  1.39s/it]
 52%|█████▏    | 32082/61904 [5:48:26<11:16:33,  1.36s/it]
 52%|█████▏    | 32083/61904 [5:48:27<11:29:14,  1.39s/it]
 52%|█████▏    | 32084/61904 [5:48:29<11:38:01,  1.40s/it]
 52%|█████▏    | 32085/61904 [5:48:30<11:44:21,  1.42s/it]
 52%|█████▏    | 32086/61904 [5:48:32<11:31:30,  1.39s/it]
 52%|█████▏    | 32087/61904 [5:48:33<11:19:42,  1.37s/it]
 52%|█████▏    | 32088/61904 [5:48:34<11:23:58,  1.38s/it]
 52%|█████▏    | 32089/61904 [5:48:36<11:07:40,  1.34s/it]
 52%|█████▏    | 32090/61904 [5:48:37<11:32:00,  1.39s/it]
 52%|█████▏    | 32091/61904 [5:48:39<11:38:23,  1.41s/it]
 52%|█████▏    | 32092/61904 [5:48:40<11:37:55,  1.40s/it]
 52%|█████▏    | 32093/61904 [5:48:41<11:29:13,  1.39s/it]
 52%|█████▏    | 32094/61904 [5:48:43<11:21:35,  1.37s/it]
 52%|█████▏    | 32095/61904 [5:48:44<11:14:54,  1.36s/it]
 52%|█████▏    | 32096/61904 [5:48:45<11:21:28,  1.37s/it]
 52%|█████▏    | 32097/61904 [5:48:47<11:05:19,  1.34s/it]
 52%|█████▏    | 32098/61904 [5:48:48<10:49:02,  1.31s/it]
 52%|█████▏    | 32099/61904 [5:48:49<10:50:56,  1.31s/it]
 52%|█████▏    | 32100/61904 [5:48:51<10:57:58,  1.32s/it]
                                                          
{'loss': 2.4981, 'learning_rate': 1.4830156877998184e-07, 'epoch': 8.3}
+
 52%|█████▏    | 32100/61904 [5:48:51<10:57:58,  1.32s/it]
 52%|█████▏    | 32101/61904 [5:48:52<10:52:33,  1.31s/it]
 52%|█████▏    | 32102/61904 [5:48:53<10:52:17,  1.31s/it]
 52%|█████▏    | 32103/61904 [5:48:55<10:54:58,  1.32s/it]
 52%|█████▏    | 32104/61904 [5:48:56<11:00:15,  1.33s/it]
 52%|█████▏    | 32105/61904 [5:48:57<11:09:15,  1.35s/it]
 52%|█████▏    | 32106/61904 [5:48:59<11:21:00,  1.37s/it]
 52%|█████▏    | 32107/61904 [5:49:00<11:23:20,  1.38s/it]
 52%|█████▏    | 32108/61904 [5:49:01<11:21:53,  1.37s/it]
 52%|█████▏    | 32109/61904 [5:49:03<11:15:05,  1.36s/it]
 52%|█████▏    | 32110/61904 [5:49:04<11:18:28,  1.37s/it]
 52%|█████▏    | 32111/61904 [5:49:06<11:18:45,  1.37s/it]
 52%|█████▏    | 32112/61904 [5:49:07<11:28:49,  1.39s/it]
 52%|█████▏    | 32113/61904 [5:49:08<11:20:23,  1.37s/it]
 52%|█████▏    | 32114/61904 [5:49:10<11:12:48,  1.36s/it]
 52%|█████▏    | 32115/61904 [5:49:11<11:10:52,  1.35s/it]
 52%|█████▏    | 32116/61904 [5:49:12<11:31:10,  1.39s/it]
 52%|█████▏    | 32117/61904 [5:49:14<11:44:33,  1.42s/it]
 52%|█████▏    | 32118/61904 [5:49:15<11:48:56,  1.43s/it]
 52%|█████▏    | 32119/61904 [5:49:17<11:50:54,  1.43s/it]
 52%|█████▏    | 32120/61904 [5:49:18<11:42:54,  1.42s/it]
                                                          
{'loss': 2.5352, 'learning_rate': 1.482691559704395e-07, 'epoch': 8.3}
+
 52%|█████▏    | 32120/61904 [5:49:18<11:42:54,  1.42s/it]
 52%|█████▏    | 32121/61904 [5:49:20<11:36:12,  1.40s/it]
 52%|█████▏    | 32122/61904 [5:49:21<11:34:36,  1.40s/it]
 52%|█████▏    | 32123/61904 [5:49:22<11:31:56,  1.39s/it]
 52%|█████▏    | 32124/61904 [5:49:24<11:17:02,  1.36s/it]
 52%|█████▏    | 32125/61904 [5:49:25<11:41:23,  1.41s/it]
 52%|█████▏    | 32126/61904 [5:49:26<11:31:10,  1.39s/it]
 52%|█████▏    | 32127/61904 [5:49:28<11:06:55,  1.34s/it]
 52%|█████▏    | 32128/61904 [5:49:29<11:17:43,  1.37s/it]
 52%|█████▏    | 32129/61904 [5:49:31<11:34:17,  1.40s/it]
 52%|█████▏    | 32130/61904 [5:49:32<11:52:45,  1.44s/it]
 52%|█████▏    | 32131/61904 [5:49:33<11:39:57,  1.41s/it]
 52%|█████▏    | 32132/61904 [5:49:35<11:26:47,  1.38s/it]
 52%|█████▏    | 32133/61904 [5:49:36<11:14:50,  1.36s/it]
 52%|█████▏    | 32134/61904 [5:49:37<11:11:09,  1.35s/it]
 52%|█████▏    | 32135/61904 [5:49:39<11:43:23,  1.42s/it]
 52%|█████▏    | 32136/61904 [5:49:40<11:47:02,  1.43s/it]
 52%|█████▏    | 32137/61904 [5:49:42<11:23:01,  1.38s/it]
 52%|█████▏    | 32138/61904 [5:49:43<11:19:51,  1.37s/it]
 52%|█████▏    | 32139/61904 [5:49:44<11:16:11,  1.36s/it]
 52%|█████▏    | 32140/61904 [5:49:46<11:14:52,  1.36s/it]
                                                          
{'loss': 2.558, 'learning_rate': 1.482367431608972e-07, 'epoch': 8.31}
+
 52%|█████▏    | 32140/61904 [5:49:46<11:14:52,  1.36s/it]
 52%|█████▏    | 32141/61904 [5:49:47<11:22:30,  1.38s/it]
 52%|█████▏    | 32142/61904 [5:49:48<11:10:19,  1.35s/it]
 52%|█████▏    | 32143/61904 [5:49:50<11:23:50,  1.38s/it]
 52%|█████▏    | 32144/61904 [5:49:51<11:38:44,  1.41s/it]
 52%|█████▏    | 32145/61904 [5:49:53<11:26:45,  1.38s/it]
 52%|█████▏    | 32146/61904 [5:49:54<11:42:03,  1.42s/it]
 52%|█████▏    | 32147/61904 [5:49:56<11:33:20,  1.40s/it]
 52%|█████▏    | 32148/61904 [5:49:57<11:24:10,  1.38s/it]
 52%|█████▏    | 32149/61904 [5:49:58<11:19:40,  1.37s/it]
 52%|█████▏    | 32150/61904 [5:49:59<10:53:18,  1.32s/it]
 52%|█████▏    | 32151/61904 [5:50:01<10:51:18,  1.31s/it]
 52%|█████▏    | 32152/61904 [5:50:02<10:58:21,  1.33s/it]
 52%|█████▏    | 32153/61904 [5:50:04<11:05:27,  1.34s/it]
 52%|█████▏    | 32154/61904 [5:50:05<10:49:34,  1.31s/it]
 52%|█████▏    | 32155/61904 [5:50:06<10:44:07,  1.30s/it]
 52%|█████▏    | 32156/61904 [5:50:08<11:18:43,  1.37s/it]
 52%|█████▏    | 32157/61904 [5:50:09<11:11:17,  1.35s/it]
 52%|█████▏    | 32158/61904 [5:50:10<11:00:41,  1.33s/it]
 52%|█████▏    | 32159/61904 [5:50:11<11:02:09,  1.34s/it]
 52%|█████▏    | 32160/61904 [5:50:13<11:22:24,  1.38s/it]
                                                          
{'loss': 2.503, 'learning_rate': 1.4820433035135485e-07, 'epoch': 8.31}
+
 52%|█████▏    | 32160/61904 [5:50:13<11:22:24,  1.38s/it]
 52%|█████▏    | 32161/61904 [5:50:14<11:28:18,  1.39s/it]
 52%|█████▏    | 32162/61904 [5:50:16<12:09:27,  1.47s/it]
 52%|█████▏    | 32163/61904 [5:50:17<11:50:56,  1.43s/it]
 52%|█████▏    | 32164/61904 [5:50:19<11:56:14,  1.45s/it]
 52%|█████▏    | 32165/61904 [5:50:20<11:38:37,  1.41s/it]
 52%|█████▏    | 32166/61904 [5:50:22<11:32:31,  1.40s/it]
 52%|█████▏    | 32167/61904 [5:50:23<11:30:57,  1.39s/it]
 52%|█████▏    | 32168/61904 [5:50:24<11:32:56,  1.40s/it]
 52%|█████▏    | 32169/61904 [5:50:26<11:34:02,  1.40s/it]
 52%|█████▏    | 32170/61904 [5:50:27<11:21:45,  1.38s/it]
 52%|█████▏    | 32171/61904 [5:50:28<11:07:49,  1.35s/it]
 52%|█████▏    | 32172/61904 [5:50:30<11:02:33,  1.34s/it]
 52%|█████▏    | 32173/61904 [5:50:31<11:12:02,  1.36s/it]
 52%|█████▏    | 32174/61904 [5:50:32<11:11:22,  1.35s/it]
 52%|█████▏    | 32175/61904 [5:50:34<11:48:32,  1.43s/it]
 52%|█████▏    | 32176/61904 [5:50:35<11:33:26,  1.40s/it]
 52%|█████▏    | 32177/61904 [5:50:37<12:21:48,  1.50s/it]
 52%|█████▏    | 32178/61904 [5:50:38<11:53:52,  1.44s/it]
 52%|█████▏    | 32179/61904 [5:50:40<11:37:32,  1.41s/it]
 52%|█████▏    | 32180/61904 [5:50:41<11:32:42,  1.40s/it]
                                                          
{'loss': 2.5792, 'learning_rate': 1.4817191754181251e-07, 'epoch': 8.32}
+
 52%|█████▏    | 32180/61904 [5:50:41<11:32:42,  1.40s/it]
 52%|█████▏    | 32181/61904 [5:50:42<11:13:41,  1.36s/it]
 52%|█████▏    | 32182/61904 [5:50:44<11:42:14,  1.42s/it]
 52%|█████▏    | 32183/61904 [5:50:45<11:23:20,  1.38s/it]
 52%|█████▏    | 32184/61904 [5:50:47<11:32:25,  1.40s/it]
 52%|█████▏    | 32185/61904 [5:50:48<11:44:37,  1.42s/it]
 52%|█████▏    | 32186/61904 [5:50:50<11:48:04,  1.43s/it]
 52%|█████▏    | 32187/61904 [5:50:51<12:07:36,  1.47s/it]
 52%|█████▏    | 32188/61904 [5:50:53<12:02:15,  1.46s/it]
 52%|█████▏    | 32189/61904 [5:50:54<12:21:22,  1.50s/it]
 52%|█████▏    | 32190/61904 [5:50:56<12:32:18,  1.52s/it]
 52%|█████▏    | 32191/61904 [5:50:57<11:58:22,  1.45s/it]
 52%|█████▏    | 32192/61904 [5:50:58<11:46:17,  1.43s/it]
 52%|█████▏    | 32193/61904 [5:51:00<11:42:42,  1.42s/it]
 52%|█████▏    | 32194/61904 [5:51:01<11:24:07,  1.38s/it]
 52%|█████▏    | 32195/61904 [5:51:02<11:09:43,  1.35s/it]
 52%|█████▏    | 32196/61904 [5:51:04<10:54:50,  1.32s/it]
 52%|█████▏    | 32197/61904 [5:51:05<10:54:18,  1.32s/it]
 52%|█████▏    | 32198/61904 [5:51:06<11:03:38,  1.34s/it]
 52%|█████▏    | 32199/61904 [5:51:08<11:14:04,  1.36s/it]
 52%|█████▏    | 32200/61904 [5:51:09<10:58:48,  1.33s/it]
                                                          
{'loss': 2.5312, 'learning_rate': 1.4813950473227018e-07, 'epoch': 8.32}
+
 52%|█████▏    | 32200/61904 [5:51:09<10:58:48,  1.33s/it]
 52%|█████▏    | 32201/61904 [5:51:10<10:55:37,  1.32s/it]
 52%|█████▏    | 32202/61904 [5:51:12<11:01:01,  1.34s/it]
 52%|█████▏    | 32203/61904 [5:51:13<11:00:28,  1.33s/it]
 52%|█████▏    | 32204/61904 [5:51:14<11:15:52,  1.37s/it]
 52%|█████▏    | 32205/61904 [5:51:16<11:32:02,  1.40s/it]
 52%|█████▏    | 32206/61904 [5:51:17<11:17:36,  1.37s/it]
 52%|█████▏    | 32207/61904 [5:51:19<11:55:37,  1.45s/it]
 52%|█████▏    | 32208/61904 [5:51:20<12:17:12,  1.49s/it]
 52%|█████▏    | 32209/61904 [5:51:22<12:02:15,  1.46s/it]
 52%|█████▏    | 32210/61904 [5:51:23<12:04:37,  1.46s/it]
 52%|█████▏    | 32211/61904 [5:51:25<11:50:23,  1.44s/it]
 52%|█████▏    | 32212/61904 [5:51:26<11:42:01,  1.42s/it]
 52%|█████▏    | 32213/61904 [5:51:27<11:20:39,  1.38s/it]
 52%|█████▏    | 32214/61904 [5:51:29<11:21:44,  1.38s/it]
 52%|█████▏    | 32215/61904 [5:51:30<11:20:25,  1.38s/it]
 52%|█████▏    | 32216/61904 [5:51:32<11:34:03,  1.40s/it]
 52%|█████▏    | 32217/61904 [5:51:33<11:22:55,  1.38s/it]
 52%|█████▏    | 32218/61904 [5:51:34<11:20:29,  1.38s/it]
 52%|█████▏    | 32219/61904 [5:51:36<11:34:26,  1.40s/it]
 52%|█████▏    | 32220/61904 [5:51:37<12:08:36,  1.47s/it]
                                                          
{'loss': 2.5503, 'learning_rate': 1.4810709192272786e-07, 'epoch': 8.33}
+
 52%|█████▏    | 32220/61904 [5:51:37<12:08:36,  1.47s/it]
 52%|█████▏    | 32221/61904 [5:51:39<12:08:36,  1.47s/it]
 52%|█████▏    | 32222/61904 [5:51:40<11:51:02,  1.44s/it]
 52%|█████▏    | 32223/61904 [5:51:42<11:46:34,  1.43s/it]
 52%|█████▏    | 32224/61904 [5:51:43<11:48:38,  1.43s/it]
 52%|█████▏    | 32225/61904 [5:51:44<11:32:26,  1.40s/it]
 52%|█████▏    | 32226/61904 [5:51:46<11:25:58,  1.39s/it]
 52%|█████▏    | 32227/61904 [5:51:47<11:03:21,  1.34s/it]
 52%|█████▏    | 32228/61904 [5:51:48<11:03:49,  1.34s/it]
 52%|█████▏    | 32229/61904 [5:51:50<11:20:06,  1.38s/it]
 52%|█████▏    | 32230/61904 [5:51:51<11:12:55,  1.36s/it]
 52%|█████▏    | 32231/61904 [5:51:53<11:29:11,  1.39s/it]
 52%|█████▏    | 32232/61904 [5:51:54<11:14:20,  1.36s/it]
 52%|█████▏    | 32233/61904 [5:51:55<11:38:14,  1.41s/it]
 52%|█████▏    | 32234/61904 [5:51:57<11:41:49,  1.42s/it]
 52%|█████▏    | 32235/61904 [5:51:58<11:53:23,  1.44s/it]
 52%|█████▏    | 32236/61904 [5:52:00<11:46:10,  1.43s/it]
 52%|█████▏    | 32237/61904 [5:52:01<11:54:49,  1.45s/it]
 52%|█████▏    | 32238/61904 [5:52:03<11:46:17,  1.43s/it]
 52%|█████▏    | 32239/61904 [5:52:04<11:45:13,  1.43s/it]
 52%|█████▏    | 32240/61904 [5:52:05<11:37:37,  1.41s/it]
                                                          
{'loss': 2.5442, 'learning_rate': 1.4807467911318553e-07, 'epoch': 8.33}
+
 52%|█████▏    | 32240/61904 [5:52:05<11:37:37,  1.41s/it]
 52%|█████▏    | 32241/61904 [5:52:07<11:29:17,  1.39s/it]
 52%|█████▏    | 32242/61904 [5:52:08<11:19:10,  1.37s/it]
 52%|█████▏    | 32243/61904 [5:52:09<11:18:55,  1.37s/it]
 52%|█████▏    | 32244/61904 [5:52:11<11:23:36,  1.38s/it]
 52%|█████▏    | 32245/61904 [5:52:12<11:16:32,  1.37s/it]
 52%|█████▏    | 32246/61904 [5:52:14<11:19:26,  1.37s/it]
 52%|█████▏    | 32247/61904 [5:52:15<11:47:01,  1.43s/it]
 52%|█████▏    | 32248/61904 [5:52:16<11:27:04,  1.39s/it]
 52%|█████▏    | 32249/61904 [5:52:18<11:23:43,  1.38s/it]
 52%|█████▏    | 32250/61904 [5:52:19<11:34:50,  1.41s/it]
 52%|█████▏    | 32251/61904 [5:52:21<11:40:38,  1.42s/it]
 52%|█████▏    | 32252/61904 [5:52:22<12:02:17,  1.46s/it]
 52%|█████▏    | 32253/61904 [5:52:24<11:37:16,  1.41s/it]
 52%|█████▏    | 32254/61904 [5:52:25<11:47:46,  1.43s/it]
 52%|█████▏    | 32255/61904 [5:52:26<11:24:10,  1.38s/it]
 52%|█████▏    | 32256/61904 [5:52:28<11:27:22,  1.39s/it]
 52%|█████▏    | 32257/61904 [5:52:29<11:25:45,  1.39s/it]
 52%|█████▏    | 32258/61904 [5:52:30<11:15:03,  1.37s/it]
 52%|█████▏    | 32259/61904 [5:52:32<11:00:36,  1.34s/it]
 52%|█████▏    | 32260/61904 [5:52:33<11:12:37,  1.36s/it]
                                                          
{'loss': 2.5578, 'learning_rate': 1.480422663036432e-07, 'epoch': 8.34}
+
 52%|█████▏    | 32260/61904 [5:52:33<11:12:37,  1.36s/it]
 52%|█████▏    | 32261/61904 [5:52:34<11:05:26,  1.35s/it]
 52%|█████▏    | 32262/61904 [5:52:36<10:54:18,  1.32s/it]
 52%|█████▏    | 32263/61904 [5:52:37<10:51:17,  1.32s/it]
 52%|█████▏    | 32264/61904 [5:52:38<10:43:03,  1.30s/it]
 52%|█████▏    | 32265/61904 [5:52:39<10:41:27,  1.30s/it]
 52%|█████▏    | 32266/61904 [5:52:41<10:45:29,  1.31s/it]
 52%|█████▏    | 32267/61904 [5:52:42<10:56:03,  1.33s/it]
 52%|█████▏    | 32268/61904 [5:52:43<10:47:59,  1.31s/it]
 52%|█████▏    | 32269/61904 [5:52:45<10:55:19,  1.33s/it]
 52%|█████▏    | 32270/61904 [5:52:46<11:13:57,  1.36s/it]
 52%|█████▏    | 32271/61904 [5:52:48<11:08:46,  1.35s/it]
 52%|█████▏    | 32272/61904 [5:52:49<11:15:25,  1.37s/it]
 52%|█████▏    | 32273/61904 [5:52:50<11:23:12,  1.38s/it]
 52%|█████▏    | 32274/61904 [5:52:52<11:19:51,  1.38s/it]
 52%|█████▏    | 32275/61904 [5:52:53<11:54:16,  1.45s/it]
 52%|█████▏    | 32276/61904 [5:52:55<11:37:40,  1.41s/it]
 52%|█████▏    | 32277/61904 [5:52:56<11:27:34,  1.39s/it]
 52%|█████▏    | 32278/61904 [5:52:57<11:20:29,  1.38s/it]
 52%|█████▏    | 32279/61904 [5:52:59<11:04:10,  1.35s/it]
 52%|█████▏    | 32280/61904 [5:53:00<11:00:52,  1.34s/it]
                                                          
{'loss': 2.5253, 'learning_rate': 1.4800985349410088e-07, 'epoch': 8.34}
+
 52%|█████▏    | 32280/61904 [5:53:00<11:00:52,  1.34s/it]
 52%|█████▏    | 32281/61904 [5:53:01<11:00:44,  1.34s/it]
 52%|█████▏    | 32282/61904 [5:53:03<11:06:25,  1.35s/it]
 52%|█████▏    | 32283/61904 [5:53:04<11:07:58,  1.35s/it]
 52%|█████▏    | 32284/61904 [5:53:06<11:35:31,  1.41s/it]
 52%|█████▏    | 32285/61904 [5:53:07<11:46:32,  1.43s/it]
 52%|█████▏    | 32286/61904 [5:53:09<12:02:03,  1.46s/it]
 52%|█████▏    | 32287/61904 [5:53:10<11:56:22,  1.45s/it]
 52%|█████▏    | 32288/61904 [5:53:11<11:45:45,  1.43s/it]
 52%|█████▏    | 32289/61904 [5:53:13<11:19:35,  1.38s/it]
 52%|█████▏    | 32290/61904 [5:53:14<11:22:06,  1.38s/it]
 52%|█████▏    | 32291/61904 [5:53:15<11:17:58,  1.37s/it]
 52%|█████▏    | 32292/61904 [5:53:17<11:43:09,  1.42s/it]
 52%|█████▏    | 32293/61904 [5:53:19<12:14:47,  1.49s/it]
 52%|█████▏    | 32294/61904 [5:53:20<11:46:31,  1.43s/it]
 52%|█████▏    | 32295/61904 [5:53:21<11:28:56,  1.40s/it]
 52%|█████▏    | 32296/61904 [5:53:23<11:20:47,  1.38s/it]
 52%|█████▏    | 32297/61904 [5:53:24<11:35:04,  1.41s/it]
 52%|█████▏    | 32298/61904 [5:53:26<11:55:21,  1.45s/it]
 52%|█████▏    | 32299/61904 [5:53:27<11:47:21,  1.43s/it]
 52%|█████▏    | 32300/61904 [5:53:28<11:28:32,  1.40s/it]
                                                          
{'loss': 2.4777, 'learning_rate': 1.4797744068455854e-07, 'epoch': 8.35}
+
 52%|█████▏    | 32300/61904 [5:53:28<11:28:32,  1.40s/it]
 52%|█████▏    | 32301/61904 [5:53:30<11:32:06,  1.40s/it]
 52%|█████▏    | 32302/61904 [5:53:31<11:15:55,  1.37s/it]
 52%|█████▏    | 32303/61904 [5:53:32<11:28:07,  1.39s/it]
 52%|█████▏    | 32304/61904 [5:53:34<11:42:56,  1.42s/it]
 52%|█████▏    | 32305/61904 [5:53:35<11:26:28,  1.39s/it]
 52%|█████▏    | 32306/61904 [5:53:37<11:21:31,  1.38s/it]
 52%|█████▏    | 32307/61904 [5:53:38<11:22:29,  1.38s/it]
 52%|█████▏    | 32308/61904 [5:53:39<11:29:16,  1.40s/it]
 52%|█████▏    | 32309/61904 [5:53:41<11:30:37,  1.40s/it]
 52%|█████▏    | 32310/61904 [5:53:42<11:44:42,  1.43s/it]
 52%|█████▏    | 32311/61904 [5:53:44<11:23:43,  1.39s/it]
 52%|█████▏    | 32312/61904 [5:53:45<11:42:36,  1.42s/it]
 52%|█████▏    | 32313/61904 [5:53:47<11:40:28,  1.42s/it]
 52%|█████▏    | 32314/61904 [5:53:48<11:23:25,  1.39s/it]
 52%|█████▏    | 32315/61904 [5:53:49<11:28:07,  1.40s/it]
 52%|█████▏    | 32316/61904 [5:53:51<11:44:53,  1.43s/it]
 52%|█████▏    | 32317/61904 [5:53:52<11:40:06,  1.42s/it]
 52%|█████▏    | 32318/61904 [5:53:54<11:29:47,  1.40s/it]
 52%|█████▏    | 32319/61904 [5:53:55<11:38:59,  1.42s/it]
 52%|█████▏    | 32320/61904 [5:53:57<11:50:11,  1.44s/it]
                                                          
{'loss': 2.525, 'learning_rate': 1.479450278750162e-07, 'epoch': 8.35}
+
 52%|█████▏    | 32320/61904 [5:53:57<11:50:11,  1.44s/it]
 52%|█████▏    | 32321/61904 [5:53:58<11:50:42,  1.44s/it]
 52%|█████▏    | 32322/61904 [5:53:59<11:44:54,  1.43s/it]
 52%|█████▏    | 32323/61904 [5:54:01<11:29:58,  1.40s/it]
 52%|█████▏    | 32324/61904 [5:54:02<11:05:45,  1.35s/it]
 52%|█████▏    | 32325/61904 [5:54:03<11:15:32,  1.37s/it]
 52%|█████▏    | 32326/61904 [5:54:05<11:09:29,  1.36s/it]
 52%|█████▏    | 32327/61904 [5:54:06<11:01:38,  1.34s/it]
 52%|█████▏    | 32328/61904 [5:54:07<10:53:13,  1.33s/it]
 52%|█████▏    | 32329/61904 [5:54:09<10:57:21,  1.33s/it]
 52%|█████▏    | 32330/61904 [5:54:10<10:48:38,  1.32s/it]
 52%|█████▏    | 32331/61904 [5:54:11<10:42:27,  1.30s/it]
 52%|█████▏    | 32332/61904 [5:54:12<10:41:03,  1.30s/it]
 52%|█████▏    | 32333/61904 [5:54:14<10:36:06,  1.29s/it]
 52%|█████▏    | 32334/61904 [5:54:15<11:05:54,  1.35s/it]
 52%|█████▏    | 32335/61904 [5:54:17<11:11:23,  1.36s/it]
 52%|█████▏    | 32336/61904 [5:54:18<11:06:32,  1.35s/it]
 52%|█████▏    | 32337/61904 [5:54:19<10:54:04,  1.33s/it]
 52%|█████▏    | 32338/61904 [5:54:20<10:44:42,  1.31s/it]
 52%|█████▏    | 32339/61904 [5:54:22<11:00:29,  1.34s/it]
 52%|█████▏    | 32340/61904 [5:54:23<11:04:20,  1.35s/it]
                                                          
{'loss': 2.5804, 'learning_rate': 1.4791261506547386e-07, 'epoch': 8.36}
+
 52%|█████▏    | 32340/61904 [5:54:23<11:04:20,  1.35s/it]
 52%|█████▏    | 32341/61904 [5:54:25<11:16:54,  1.37s/it]
 52%|█████▏    | 32342/61904 [5:54:26<11:13:51,  1.37s/it]
 52%|█████▏    | 32343/61904 [5:54:27<11:22:34,  1.39s/it]
 52%|█████▏    | 32344/61904 [5:54:29<11:26:04,  1.39s/it]
 52%|█████▏    | 32345/61904 [5:54:30<11:14:41,  1.37s/it]
 52%|█████▏    | 32346/61904 [5:54:31<11:02:23,  1.34s/it]
 52%|█████▏    | 32347/61904 [5:54:33<11:08:29,  1.36s/it]
 52%|█████▏    | 32348/61904 [5:54:34<11:33:41,  1.41s/it]
 52%|█████▏    | 32349/61904 [5:54:36<11:48:44,  1.44s/it]
 52%|█████▏    | 32350/61904 [5:54:37<11:42:22,  1.43s/it]
 52%|█████▏    | 32351/61904 [5:54:39<11:56:43,  1.46s/it]
 52%|█████▏    | 32352/61904 [5:54:40<11:49:25,  1.44s/it]
 52%|█████▏    | 32353/61904 [5:54:42<11:29:42,  1.40s/it]
 52%|█████▏    | 32354/61904 [5:54:43<11:10:45,  1.36s/it]
 52%|█████▏    | 32355/61904 [5:54:44<11:26:46,  1.39s/it]
 52%|█████▏    | 32356/61904 [5:54:46<11:11:28,  1.36s/it]
 52%|█████▏    | 32357/61904 [5:54:47<11:11:19,  1.36s/it]
 52%|█████▏    | 32358/61904 [5:54:48<11:23:17,  1.39s/it]
 52%|█████▏    | 32359/61904 [5:54:50<11:21:55,  1.38s/it]
 52%|█████▏    | 32360/61904 [5:54:51<11:19:12,  1.38s/it]
                                                          
{'loss': 2.5387, 'learning_rate': 1.4788020225593155e-07, 'epoch': 8.36}
+
 52%|█████▏    | 32360/61904 [5:54:51<11:19:12,  1.38s/it]
 52%|█████▏    | 32361/61904 [5:54:53<11:24:26,  1.39s/it]
 52%|█████▏    | 32362/61904 [5:54:54<11:17:23,  1.38s/it]
 52%|█████▏    | 32363/61904 [5:54:55<11:17:43,  1.38s/it]
 52%|█████▏    | 32364/61904 [5:54:57<11:27:16,  1.40s/it]
 52%|█████▏    | 32365/61904 [5:54:58<11:20:21,  1.38s/it]
 52%|█████▏    | 32366/61904 [5:54:59<11:15:58,  1.37s/it]
 52%|█████▏    | 32367/61904 [5:55:01<11:04:10,  1.35s/it]
 52%|█████▏    | 32368/61904 [5:55:02<11:41:50,  1.43s/it]
 52%|█████▏    | 32369/61904 [5:55:04<11:21:21,  1.38s/it]
 52%|█████▏    | 32370/61904 [5:55:05<11:16:58,  1.38s/it]
 52%|█████▏    | 32371/61904 [5:55:06<10:57:05,  1.33s/it]
 52%|█████▏    | 32372/61904 [5:55:08<11:03:45,  1.35s/it]
 52%|█████▏    | 32373/61904 [5:55:09<11:04:54,  1.35s/it]
 52%|█████▏    | 32374/61904 [5:55:10<11:07:27,  1.36s/it]
 52%|█████▏    | 32375/61904 [5:55:12<11:26:04,  1.39s/it]
 52%|█████▏    | 32376/61904 [5:55:13<11:31:46,  1.41s/it]
 52%|█████▏    | 32377/61904 [5:55:15<11:58:34,  1.46s/it]
 52%|█████▏    | 32378/61904 [5:55:16<11:41:44,  1.43s/it]
 52%|█████▏    | 32379/61904 [5:55:18<11:52:27,  1.45s/it]
 52%|█████▏    | 32380/61904 [5:55:19<11:48:11,  1.44s/it]
                                                          
{'loss': 2.5867, 'learning_rate': 1.478477894463892e-07, 'epoch': 8.37}
+
 52%|█████▏    | 32380/61904 [5:55:19<11:48:11,  1.44s/it]
 52%|█████▏    | 32381/61904 [5:55:21<12:05:44,  1.47s/it]
 52%|█████▏    | 32382/61904 [5:55:22<11:52:12,  1.45s/it]
 52%|█████▏    | 32383/61904 [5:55:23<11:38:02,  1.42s/it]
 52%|█████▏    | 32384/61904 [5:55:25<11:29:23,  1.40s/it]
 52%|█████▏    | 32385/61904 [5:55:26<11:45:40,  1.43s/it]
 52%|█████▏    | 32386/61904 [5:55:27<11:17:35,  1.38s/it]
 52%|█████▏    | 32387/61904 [5:55:29<11:17:44,  1.38s/it]
 52%|█████▏    | 32388/61904 [5:55:30<11:31:38,  1.41s/it]
 52%|█████▏    | 32389/61904 [5:55:32<11:21:14,  1.38s/it]
 52%|█████▏    | 32390/61904 [5:55:33<11:28:23,  1.40s/it]
 52%|█████▏    | 32391/61904 [5:55:34<11:17:10,  1.38s/it]
 52%|█████▏    | 32392/61904 [5:55:36<11:14:55,  1.37s/it]
 52%|█████▏    | 32393/61904 [5:55:37<11:31:00,  1.40s/it]
 52%|█████▏    | 32394/61904 [5:55:39<11:23:54,  1.39s/it]
 52%|█████▏    | 32395/61904 [5:55:40<11:15:15,  1.37s/it]
 52%|█████▏    | 32396/61904 [5:55:41<11:31:07,  1.41s/it]
 52%|█████▏    | 32397/61904 [5:55:43<11:18:58,  1.38s/it]
 52%|█████▏    | 32398/61904 [5:55:44<12:03:00,  1.47s/it]
 52%|█████▏    | 32399/61904 [5:55:46<11:53:40,  1.45s/it]
 52%|█████▏    | 32400/61904 [5:55:47<11:28:17,  1.40s/it]
                                                          
{'loss': 2.5073, 'learning_rate': 1.4781537663684687e-07, 'epoch': 8.37}
+
 52%|█████▏    | 32400/61904 [5:55:47<11:28:17,  1.40s/it]
 52%|█████▏    | 32401/61904 [5:55:48<11:03:06,  1.35s/it]
 52%|█████▏    | 32402/61904 [5:55:50<11:31:39,  1.41s/it]
 52%|█████▏    | 32403/61904 [5:55:51<11:44:36,  1.43s/it]
 52%|█████▏    | 32404/61904 [5:55:53<11:39:55,  1.42s/it]
 52%|█████▏    | 32405/61904 [5:55:54<11:12:05,  1.37s/it]
 52%|█████▏    | 32406/61904 [5:55:56<11:37:00,  1.42s/it]
 52%|█████▏    | 32407/61904 [5:55:57<11:13:00,  1.37s/it]
 52%|█████▏    | 32408/61904 [5:55:58<11:37:29,  1.42s/it]
 52%|█████▏    | 32409/61904 [5:56:00<11:04:47,  1.35s/it]
 52%|█████▏    | 32410/61904 [5:56:01<10:58:10,  1.34s/it]
 52%|█████▏    | 32411/61904 [5:56:02<11:03:39,  1.35s/it]
 52%|█████▏    | 32412/61904 [5:56:04<11:23:18,  1.39s/it]
 52%|█████▏    | 32413/61904 [5:56:05<11:07:20,  1.36s/it]
 52%|█████▏    | 32414/61904 [5:56:07<11:41:22,  1.43s/it]
 52%|█████▏    | 32415/61904 [5:56:08<11:34:10,  1.41s/it]
 52%|█████▏    | 32416/61904 [5:56:09<11:14:15,  1.37s/it]
 52%|█████▏    | 32417/61904 [5:56:11<11:32:20,  1.41s/it]
 52%|█████▏    | 32418/61904 [5:56:12<11:42:34,  1.43s/it]
 52%|█████▏    | 32419/61904 [5:56:14<11:46:26,  1.44s/it]
 52%|█████▏    | 32420/61904 [5:56:15<11:24:14,  1.39s/it]
                                                          
{'loss': 2.5671, 'learning_rate': 1.4778296382730454e-07, 'epoch': 8.38}
+
 52%|█████▏    | 32420/61904 [5:56:15<11:24:14,  1.39s/it]
 52%|█████▏    | 32421/61904 [5:56:16<11:19:33,  1.38s/it]
 52%|█████▏    | 32422/61904 [5:56:18<11:14:37,  1.37s/it]
 52%|█████▏    | 32423/61904 [5:56:19<11:12:27,  1.37s/it]
 52%|█████▏    | 32424/61904 [5:56:21<11:37:08,  1.42s/it]
 52%|█████▏    | 32425/61904 [5:56:22<11:26:29,  1.40s/it]
 52%|█████▏    | 32426/61904 [5:56:23<11:13:59,  1.37s/it]
 52%|█████▏    | 32427/61904 [5:56:24<10:52:19,  1.33s/it]
 52%|█████▏    | 32428/61904 [5:56:26<11:15:25,  1.37s/it]
 52%|█████▏    | 32429/61904 [5:56:27<11:24:42,  1.39s/it]
 52%|█████▏    | 32430/61904 [5:56:29<11:25:05,  1.39s/it]
 52%|█████▏    | 32431/61904 [5:56:30<11:01:21,  1.35s/it]
 52%|█████▏    | 32432/61904 [5:56:31<10:58:51,  1.34s/it]
 52%|█████▏    | 32433/61904 [5:56:33<11:01:39,  1.35s/it]
 52%|█████▏    | 32434/61904 [5:56:34<11:13:43,  1.37s/it]
 52%|█████▏    | 32435/61904 [5:56:36<11:33:13,  1.41s/it]
 52%|█████▏    | 32436/61904 [5:56:37<11:30:12,  1.41s/it]
 52%|█████▏    | 32437/61904 [5:56:38<11:28:26,  1.40s/it]
 52%|█████▏    | 32438/61904 [5:56:40<11:30:37,  1.41s/it]
 52%|█████▏    | 32439/61904 [5:56:41<11:32:41,  1.41s/it]
 52%|█████▏    | 32440/61904 [5:56:43<11:31:04,  1.41s/it]
                                                          
{'loss': 2.5598, 'learning_rate': 1.4775055101776222e-07, 'epoch': 8.38}
+
 52%|█████▏    | 32440/61904 [5:56:43<11:31:04,  1.41s/it]
 52%|█████▏    | 32441/61904 [5:56:44<11:59:40,  1.47s/it]
 52%|█████▏    | 32442/61904 [5:56:46<11:40:03,  1.43s/it]
 52%|█████▏    | 32443/61904 [5:56:47<11:23:24,  1.39s/it]
 52%|█████▏    | 32444/61904 [5:56:48<10:55:18,  1.33s/it]
 52%|█████▏    | 32445/61904 [5:56:49<10:52:21,  1.33s/it]
 52%|█████▏    | 32446/61904 [5:56:51<11:33:40,  1.41s/it]
 52%|█████▏    | 32447/61904 [5:56:52<11:28:46,  1.40s/it]
 52%|█████▏    | 32448/61904 [5:56:54<11:44:27,  1.43s/it]
 52%|█████▏    | 32449/61904 [5:56:55<11:37:25,  1.42s/it]
 52%|█████▏    | 32450/61904 [5:56:57<11:28:40,  1.40s/it]
 52%|█████▏    | 32451/61904 [5:56:58<11:25:57,  1.40s/it]
 52%|█████▏    | 32452/61904 [5:56:59<11:11:20,  1.37s/it]
 52%|█████▏    | 32453/61904 [5:57:01<11:17:49,  1.38s/it]
 52%|█████▏    | 32454/61904 [5:57:02<11:20:28,  1.39s/it]
 52%|█████▏    | 32455/61904 [5:57:04<11:29:15,  1.40s/it]
 52%|█████▏    | 32456/61904 [5:57:05<11:29:56,  1.41s/it]
 52%|█████▏    | 32457/61904 [5:57:06<11:36:26,  1.42s/it]
 52%|█████▏    | 32458/61904 [5:57:08<11:20:29,  1.39s/it]
 52%|█████▏    | 32459/61904 [5:57:09<11:12:39,  1.37s/it]
 52%|█████▏    | 32460/61904 [5:57:10<11:04:41,  1.35s/it]
                                                          
{'loss': 2.552, 'learning_rate': 1.4771813820821989e-07, 'epoch': 8.39}
+
 52%|█████▏    | 32460/61904 [5:57:10<11:04:41,  1.35s/it]
 52%|█████▏    | 32461/61904 [5:57:12<11:20:44,  1.39s/it]
 52%|█████▏    | 32462/61904 [5:57:13<11:16:16,  1.38s/it]
 52%|█████▏    | 32463/61904 [5:57:15<11:02:58,  1.35s/it]
 52%|█████▏    | 32464/61904 [5:57:16<11:15:33,  1.38s/it]
 52%|█████▏    | 32465/61904 [5:57:17<11:22:39,  1.39s/it]
 52%|█████▏    | 32466/61904 [5:57:19<12:22:12,  1.51s/it]
 52%|█████▏    | 32467/61904 [5:57:21<12:26:43,  1.52s/it]
 52%|█████▏    | 32468/61904 [5:57:22<12:07:24,  1.48s/it]
 52%|█████▏    | 32469/61904 [5:57:24<12:00:42,  1.47s/it]
 52%|█████▏    | 32470/61904 [5:57:25<12:04:29,  1.48s/it]
 52%|█████▏    | 32471/61904 [5:57:26<11:47:07,  1.44s/it]
 52%|█████▏    | 32472/61904 [5:57:28<11:37:16,  1.42s/it]
 52%|█████▏    | 32473/61904 [5:57:29<11:39:37,  1.43s/it]
 52%|█████▏    | 32474/61904 [5:57:31<11:22:51,  1.39s/it]
 52%|█████▏    | 32475/61904 [5:57:32<11:33:30,  1.41s/it]
 52%|█████▏    | 32476/61904 [5:57:33<11:29:13,  1.41s/it]
 52%|█████▏    | 32477/61904 [5:57:35<11:30:29,  1.41s/it]
 52%|█████▏    | 32478/61904 [5:57:36<11:29:07,  1.41s/it]
 52%|█████▏    | 32479/61904 [5:57:37<11:04:33,  1.36s/it]
 52%|█████▏    | 32480/61904 [5:57:39<10:52:50,  1.33s/it]
                                                          
{'loss': 2.5682, 'learning_rate': 1.4768572539867755e-07, 'epoch': 8.39}
+
 52%|█████▏    | 32480/61904 [5:57:39<10:52:50,  1.33s/it]
 52%|█████▏    | 32481/61904 [5:57:40<11:08:53,  1.36s/it]
 52%|█████▏    | 32482/61904 [5:57:42<11:10:30,  1.37s/it]
 52%|█████▏    | 32483/61904 [5:57:43<11:13:20,  1.37s/it]
 52%|█████▏    | 32484/61904 [5:57:44<11:33:00,  1.41s/it]
 52%|█████▏    | 32485/61904 [5:57:46<11:05:16,  1.36s/it]
 52%|█████▏    | 32486/61904 [5:57:47<11:10:37,  1.37s/it]
 52%|█████▏    | 32487/61904 [5:57:49<11:32:55,  1.41s/it]
 52%|█████▏    | 32488/61904 [5:57:50<11:20:14,  1.39s/it]
 52%|█████▏    | 32489/61904 [5:57:51<11:12:28,  1.37s/it]
 52%|█████▏    | 32490/61904 [5:57:53<11:11:56,  1.37s/it]
 52%|█████▏    | 32491/61904 [5:57:54<11:06:29,  1.36s/it]
 52%|█████▏    | 32492/61904 [5:57:55<11:18:19,  1.38s/it]
 52%|█████▏    | 32493/61904 [5:57:57<11:25:48,  1.40s/it]
 52%|█████▏    | 32494/61904 [5:57:58<11:07:13,  1.36s/it]
 52%|█████▏    | 32495/61904 [5:57:59<11:07:32,  1.36s/it]
 52%|█████▏    | 32496/61904 [5:58:01<10:54:13,  1.33s/it]
 52%|█████▏    | 32497/61904 [5:58:02<10:57:52,  1.34s/it]
 52%|█████▏    | 32498/61904 [5:58:03<11:13:43,  1.37s/it]
 52%|█████▏    | 32499/61904 [5:58:05<11:11:11,  1.37s/it]
 53%|█████▎    | 32500/61904 [5:58:06<11:08:58,  1.37s/it]
                                                          
{'loss': 2.5659, 'learning_rate': 1.476533125891352e-07, 'epoch': 8.4}
+
 53%|█████▎    | 32500/61904 [5:58:06<11:08:58,  1.37s/it]
 53%|█████▎    | 32501/61904 [5:58:08<11:04:07,  1.36s/it]
 53%|█████▎    | 32502/61904 [5:58:09<10:47:34,  1.32s/it]
 53%|█████▎    | 32503/61904 [5:58:10<11:03:03,  1.35s/it]
 53%|█████▎    | 32504/61904 [5:58:12<11:03:26,  1.35s/it]
 53%|█████▎    | 32505/61904 [5:58:13<10:51:25,  1.33s/it]
 53%|█████▎    | 32506/61904 [5:58:14<10:58:00,  1.34s/it]
 53%|█████▎    | 32507/61904 [5:58:15<10:46:53,  1.32s/it]
 53%|█████▎    | 32508/61904 [5:58:17<10:44:58,  1.32s/it]
 53%|█████▎    | 32509/61904 [5:58:18<10:42:44,  1.31s/it]
 53%|█████▎    | 32510/61904 [5:58:19<10:42:39,  1.31s/it]
 53%|█████▎    | 32511/61904 [5:58:21<10:44:41,  1.32s/it]
 53%|█████▎    | 32512/61904 [5:58:22<10:59:34,  1.35s/it]
 53%|█████▎    | 32513/61904 [5:58:24<11:01:04,  1.35s/it]
 53%|█████▎    | 32514/61904 [5:58:25<10:56:23,  1.34s/it]
 53%|█████▎    | 32515/61904 [5:58:26<11:01:54,  1.35s/it]
 53%|█████▎    | 32516/61904 [5:58:28<11:11:20,  1.37s/it]
 53%|█████▎    | 32517/61904 [5:58:29<11:11:44,  1.37s/it]
 53%|█████▎    | 32518/61904 [5:58:30<10:57:56,  1.34s/it]
 53%|█████▎    | 32519/61904 [5:58:32<10:54:29,  1.34s/it]
 53%|█████▎    | 32520/61904 [5:58:33<11:00:41,  1.35s/it]
                                                          
{'loss': 2.5365, 'learning_rate': 1.476208997795929e-07, 'epoch': 8.4}
+
 53%|█████▎    | 32520/61904 [5:58:33<11:00:41,  1.35s/it]
 53%|█████▎    | 32521/61904 [5:58:34<10:51:49,  1.33s/it]
 53%|█████▎    | 32522/61904 [5:58:36<10:56:03,  1.34s/it]
 53%|█████▎    | 32523/61904 [5:58:37<11:10:27,  1.37s/it]
 53%|█████▎    | 32524/61904 [5:58:39<11:23:02,  1.39s/it]
 53%|█████▎    | 32525/61904 [5:58:40<11:19:29,  1.39s/it]
 53%|█████▎    | 32526/61904 [5:58:41<11:13:07,  1.37s/it]
 53%|█████▎    | 32527/61904 [5:58:42<10:56:38,  1.34s/it]
 53%|█████▎    | 32528/61904 [5:58:44<10:54:59,  1.34s/it]
 53%|█████▎    | 32529/61904 [5:58:45<10:56:50,  1.34s/it]
 53%|█████▎    | 32530/61904 [5:58:47<11:01:40,  1.35s/it]
 53%|█████▎    | 32531/61904 [5:58:48<11:19:13,  1.39s/it]
 53%|█████▎    | 32532/61904 [5:58:49<11:27:20,  1.40s/it]
 53%|█████▎    | 32533/61904 [5:58:51<11:41:22,  1.43s/it]
 53%|█████▎    | 32534/61904 [5:58:52<11:37:01,  1.42s/it]
 53%|█████▎    | 32535/61904 [5:58:54<11:33:24,  1.42s/it]
 53%|█████▎    | 32536/61904 [5:58:55<11:25:02,  1.40s/it]
 53%|█████▎    | 32537/61904 [5:58:57<11:38:49,  1.43s/it]
 53%|█████▎    | 32538/61904 [5:58:58<11:29:54,  1.41s/it]
 53%|█████▎    | 32539/61904 [5:58:59<11:40:50,  1.43s/it]
 53%|█████▎    | 32540/61904 [5:59:01<11:27:39,  1.41s/it]
                                                          
{'loss': 2.5348, 'learning_rate': 1.4758848697005056e-07, 'epoch': 8.41}
+
 53%|█████▎    | 32540/61904 [5:59:01<11:27:39,  1.41s/it]
 53%|█████▎    | 32541/61904 [5:59:02<11:27:12,  1.40s/it]
 53%|█████▎    | 32542/61904 [5:59:04<11:54:11,  1.46s/it]
 53%|█████▎    | 32543/61904 [5:59:05<11:34:07,  1.42s/it]
 53%|█████▎    | 32544/61904 [5:59:07<11:35:22,  1.42s/it]
 53%|█████▎    | 32545/61904 [5:59:08<11:35:09,  1.42s/it]
 53%|█████▎    | 32546/61904 [5:59:09<11:32:07,  1.41s/it]
 53%|█████▎    | 32547/61904 [5:59:11<11:23:12,  1.40s/it]
 53%|█████▎    | 32548/61904 [5:59:12<11:05:35,  1.36s/it]
 53%|█████▎    | 32549/61904 [5:59:13<11:12:35,  1.37s/it]
 53%|█████▎    | 32550/61904 [5:59:15<11:02:57,  1.36s/it]
 53%|█████▎    | 32551/61904 [5:59:16<11:05:30,  1.36s/it]
 53%|█████▎    | 32552/61904 [5:59:17<11:04:56,  1.36s/it]
 53%|█████▎    | 32553/61904 [5:59:19<11:06:10,  1.36s/it]
 53%|█████▎    | 32554/61904 [5:59:20<11:23:55,  1.40s/it]
 53%|█████▎    | 32555/61904 [5:59:22<11:14:30,  1.38s/it]
 53%|█████▎    | 32556/61904 [5:59:23<10:59:46,  1.35s/it]
 53%|█████▎    | 32557/61904 [5:59:24<11:19:43,  1.39s/it]
 53%|█████▎    | 32558/61904 [5:59:26<11:20:27,  1.39s/it]
 53%|█████▎    | 32559/61904 [5:59:27<11:31:23,  1.41s/it]
 53%|█████▎    | 32560/61904 [5:59:29<11:30:26,  1.41s/it]
                                                          
{'loss': 2.5808, 'learning_rate': 1.4755607416050822e-07, 'epoch': 8.42}
+
 53%|█████▎    | 32560/61904 [5:59:29<11:30:26,  1.41s/it]
 53%|█████▎    | 32561/61904 [5:59:30<11:35:25,  1.42s/it]
 53%|█████▎    | 32562/61904 [5:59:32<11:35:28,  1.42s/it]
 53%|█████▎    | 32563/61904 [5:59:33<11:19:43,  1.39s/it]
 53%|█████▎    | 32564/61904 [5:59:34<11:42:16,  1.44s/it]
 53%|█████▎    | 32565/61904 [5:59:36<11:50:43,  1.45s/it]
 53%|█████▎    | 32566/61904 [5:59:37<11:52:05,  1.46s/it]
 53%|█████▎    | 32567/61904 [5:59:39<11:37:01,  1.43s/it]
 53%|█████▎    | 32568/61904 [5:59:40<11:03:16,  1.36s/it]
 53%|█████▎    | 32569/61904 [5:59:41<10:59:08,  1.35s/it]
 53%|█████▎    | 32570/61904 [5:59:43<11:03:35,  1.36s/it]
 53%|█████▎    | 32571/61904 [5:59:44<10:58:23,  1.35s/it]
 53%|█████▎    | 32572/61904 [5:59:45<10:59:54,  1.35s/it]
 53%|█████▎    | 32573/61904 [5:59:47<11:28:01,  1.41s/it]
 53%|█████▎    | 32574/61904 [5:59:48<11:38:49,  1.43s/it]
 53%|█████▎    | 32575/61904 [5:59:50<11:29:28,  1.41s/it]
 53%|█████▎    | 32576/61904 [5:59:51<11:21:23,  1.39s/it]
 53%|█████▎    | 32577/61904 [5:59:52<11:06:06,  1.36s/it]
 53%|█████▎    | 32578/61904 [5:59:54<10:53:43,  1.34s/it]
 53%|█████▎    | 32579/61904 [5:59:55<11:20:10,  1.39s/it]
 53%|█████▎    | 32580/61904 [5:59:57<11:26:17,  1.40s/it]
                                                          
{'loss': 2.5285, 'learning_rate': 1.475236613509659e-07, 'epoch': 8.42}
+
 53%|█████▎    | 32580/61904 [5:59:57<11:26:17,  1.40s/it]
 53%|█████▎    | 32581/61904 [5:59:58<11:22:59,  1.40s/it]
 53%|█████▎    | 32582/61904 [5:59:59<11:12:56,  1.38s/it]
 53%|█████▎    | 32583/61904 [6:00:01<11:17:44,  1.39s/it]
 53%|█████▎    | 32584/61904 [6:00:02<11:23:40,  1.40s/it]
 53%|█████▎    | 32585/61904 [6:00:03<11:19:34,  1.39s/it]
 53%|█████▎    | 32586/61904 [6:00:05<11:24:58,  1.40s/it]
 53%|█████▎    | 32587/61904 [6:00:06<11:41:00,  1.43s/it]
 53%|█████▎    | 32588/61904 [6:00:08<11:06:54,  1.36s/it]
 53%|█████▎    | 32589/61904 [6:00:09<10:49:23,  1.33s/it]
 53%|█████▎    | 32590/61904 [6:00:10<11:01:30,  1.35s/it]
 53%|█████▎    | 32591/61904 [6:00:12<11:01:11,  1.35s/it]
 53%|█████▎    | 32592/61904 [6:00:13<11:04:21,  1.36s/it]
 53%|█████▎    | 32593/61904 [6:00:14<11:09:11,  1.37s/it]
 53%|█████▎    | 32594/61904 [6:00:16<11:31:12,  1.41s/it]
 53%|█████▎    | 32595/61904 [6:00:17<11:31:36,  1.42s/it]
 53%|█████▎    | 32596/61904 [6:00:19<11:10:26,  1.37s/it]
 53%|█████▎    | 32597/61904 [6:00:20<11:15:57,  1.38s/it]
 53%|█████▎    | 32598/61904 [6:00:21<11:10:47,  1.37s/it]
 53%|█████▎    | 32599/61904 [6:00:23<11:04:20,  1.36s/it]
 53%|█████▎    | 32600/61904 [6:00:24<11:24:43,  1.40s/it]
                                                          
{'loss': 2.5493, 'learning_rate': 1.4749124854142357e-07, 'epoch': 8.43}
+
 53%|█████▎    | 32600/61904 [6:00:24<11:24:43,  1.40s/it]
 53%|█████▎    | 32601/61904 [6:00:26<11:31:55,  1.42s/it]
 53%|█████▎    | 32602/61904 [6:00:27<11:15:58,  1.38s/it]
 53%|█████▎    | 32603/61904 [6:00:28<11:10:55,  1.37s/it]
 53%|█████▎    | 32604/61904 [6:00:30<11:26:53,  1.41s/it]
 53%|█████▎    | 32605/61904 [6:00:31<11:10:47,  1.37s/it]
 53%|█████▎    | 32606/61904 [6:00:32<10:57:45,  1.35s/it]
 53%|█████▎    | 32607/61904 [6:00:34<10:52:46,  1.34s/it]
 53%|█████▎    | 32608/61904 [6:00:35<11:28:38,  1.41s/it]
 53%|█████▎    | 32609/61904 [6:00:37<11:07:20,  1.37s/it]
 53%|█████▎    | 32610/61904 [6:00:38<10:58:53,  1.35s/it]
 53%|█████▎    | 32611/61904 [6:00:39<10:59:34,  1.35s/it]
 53%|█████▎    | 32612/61904 [6:00:41<11:14:30,  1.38s/it]
 53%|█████▎    | 32613/61904 [6:00:42<11:08:46,  1.37s/it]
 53%|█████▎    | 32614/61904 [6:00:43<11:23:32,  1.40s/it]
 53%|█████▎    | 32615/61904 [6:00:45<11:26:18,  1.41s/it]
 53%|█████▎    | 32616/61904 [6:00:46<11:07:22,  1.37s/it]
 53%|█████▎    | 32617/61904 [6:00:48<11:08:23,  1.37s/it]
 53%|█████▎    | 32618/61904 [6:00:49<11:37:01,  1.43s/it]
 53%|█████▎    | 32619/61904 [6:00:51<11:38:13,  1.43s/it]
 53%|█████▎    | 32620/61904 [6:00:52<11:46:37,  1.45s/it]
                                                          
{'loss': 2.5594, 'learning_rate': 1.4745883573188123e-07, 'epoch': 8.43}
+
 53%|█████▎    | 32620/61904 [6:00:52<11:46:37,  1.45s/it]
 53%|█████▎    | 32621/61904 [6:00:53<11:34:08,  1.42s/it]
 53%|█████▎    | 32622/61904 [6:00:55<11:29:22,  1.41s/it]
 53%|█████▎    | 32623/61904 [6:00:56<11:00:10,  1.35s/it]
 53%|█████▎    | 32624/61904 [6:00:57<10:58:46,  1.35s/it]
 53%|█████▎    | 32625/61904 [6:00:59<11:04:42,  1.36s/it]
 53%|█████▎    | 32626/61904 [6:01:00<10:50:00,  1.33s/it]
 53%|█████▎    | 32627/61904 [6:01:01<10:44:48,  1.32s/it]
 53%|█████▎    | 32628/61904 [6:01:03<10:52:01,  1.34s/it]
 53%|█████▎    | 32629/61904 [6:01:04<11:10:32,  1.37s/it]
 53%|█████▎    | 32630/61904 [6:01:05<11:13:53,  1.38s/it]
 53%|█████▎    | 32631/61904 [6:01:07<12:02:48,  1.48s/it]
 53%|█████▎    | 32632/61904 [6:01:08<11:35:01,  1.42s/it]
 53%|█████▎    | 32633/61904 [6:01:10<11:32:01,  1.42s/it]
 53%|█████▎    | 32634/61904 [6:01:11<11:15:58,  1.39s/it]
 53%|█████▎    | 32635/61904 [6:01:13<11:42:07,  1.44s/it]
 53%|█████▎    | 32636/61904 [6:01:14<11:10:08,  1.37s/it]
 53%|█████▎    | 32637/61904 [6:01:15<11:14:54,  1.38s/it]
 53%|█████▎    | 32638/61904 [6:01:17<11:14:04,  1.38s/it]
 53%|█████▎    | 32639/61904 [6:01:18<11:04:19,  1.36s/it]
 53%|█████▎    | 32640/61904 [6:01:20<11:22:44,  1.40s/it]
                                                          
{'loss': 2.5149, 'learning_rate': 1.474264229223389e-07, 'epoch': 8.44}
+
 53%|█████▎    | 32640/61904 [6:01:20<11:22:44,  1.40s/it]
 53%|█████▎    | 32641/61904 [6:01:21<11:39:57,  1.44s/it]
 53%|█████▎    | 32642/61904 [6:01:22<11:24:51,  1.40s/it]
 53%|█████▎    | 32643/61904 [6:01:24<11:13:33,  1.38s/it]
 53%|█████▎    | 32644/61904 [6:01:25<11:11:46,  1.38s/it]
 53%|█████▎    | 32645/61904 [6:01:26<10:57:22,  1.35s/it]
 53%|█████▎    | 32646/61904 [6:01:28<11:10:23,  1.37s/it]
 53%|█████▎    | 32647/61904 [6:01:29<11:22:10,  1.40s/it]
 53%|█████▎    | 32648/61904 [6:01:31<11:32:09,  1.42s/it]
 53%|█████▎    | 32649/61904 [6:01:32<11:15:05,  1.38s/it]
 53%|█████▎    | 32650/61904 [6:01:34<11:26:43,  1.41s/it]
 53%|█████▎    | 32651/61904 [6:01:35<11:00:59,  1.36s/it]
 53%|█████▎    | 32652/61904 [6:01:36<11:05:03,  1.36s/it]
 53%|█████▎    | 32653/61904 [6:01:38<11:23:23,  1.40s/it]
 53%|█████▎    | 32654/61904 [6:01:39<11:27:35,  1.41s/it]
 53%|█████▎    | 32655/61904 [6:01:40<11:07:54,  1.37s/it]
 53%|█████▎    | 32656/61904 [6:01:42<11:09:55,  1.37s/it]
 53%|█████▎    | 32657/61904 [6:01:43<10:48:06,  1.33s/it]
 53%|█████▎    | 32658/61904 [6:01:44<10:57:01,  1.35s/it]
 53%|█████▎    | 32659/61904 [6:01:46<11:01:14,  1.36s/it]
 53%|█████▎    | 32660/61904 [6:01:47<10:56:21,  1.35s/it]
                                                          
{'loss': 2.5238, 'learning_rate': 1.4739401011279656e-07, 'epoch': 8.44}
+
 53%|█████▎    | 32660/61904 [6:01:47<10:56:21,  1.35s/it]
 53%|█████▎    | 32661/61904 [6:01:48<10:58:24,  1.35s/it]
 53%|█████▎    | 32662/61904 [6:01:50<11:14:46,  1.38s/it]
 53%|█████▎    | 32663/61904 [6:01:51<11:32:56,  1.42s/it]
 53%|█████▎    | 32664/61904 [6:01:53<11:10:47,  1.38s/it]
 53%|█████▎    | 32665/61904 [6:01:54<11:03:06,  1.36s/it]
 53%|█████▎    | 32666/61904 [6:01:55<11:04:41,  1.36s/it]
 53%|█████▎    | 32667/61904 [6:01:57<10:58:43,  1.35s/it]
 53%|█████▎    | 32668/61904 [6:01:58<11:01:02,  1.36s/it]
 53%|█████▎    | 32669/61904 [6:01:59<10:55:54,  1.35s/it]
 53%|█████▎    | 32670/61904 [6:02:01<11:11:37,  1.38s/it]
 53%|█████▎    | 32671/61904 [6:02:02<11:15:42,  1.39s/it]
 53%|█████▎    | 32672/61904 [6:02:04<11:14:24,  1.38s/it]
 53%|█████▎    | 32673/61904 [6:02:05<11:06:48,  1.37s/it]
 53%|█████▎    | 32674/61904 [6:02:06<11:22:54,  1.40s/it]
 53%|█████▎    | 32675/61904 [6:02:08<11:10:29,  1.38s/it]
 53%|█████▎    | 32676/61904 [6:02:09<11:09:38,  1.37s/it]
 53%|█████▎    | 32677/61904 [6:02:11<11:50:02,  1.46s/it]
 53%|█████▎    | 32678/61904 [6:02:12<11:33:01,  1.42s/it]
 53%|█████▎    | 32679/61904 [6:02:13<11:21:47,  1.40s/it]
 53%|█████▎    | 32680/61904 [6:02:15<11:06:46,  1.37s/it]
                                                          
{'loss': 2.5444, 'learning_rate': 1.4736159730325425e-07, 'epoch': 8.45}
+
 53%|█████▎    | 32680/61904 [6:02:15<11:06:46,  1.37s/it]
 53%|█████▎    | 32681/61904 [6:02:16<11:37:36,  1.43s/it]
 53%|█████▎    | 32682/61904 [6:02:18<11:23:02,  1.40s/it]
 53%|█████▎    | 32683/61904 [6:02:19<11:06:45,  1.37s/it]
 53%|█████▎    | 32684/61904 [6:02:20<11:33:58,  1.42s/it]
 53%|█████▎    | 32685/61904 [6:02:22<11:23:38,  1.40s/it]
 53%|█████▎    | 32686/61904 [6:02:23<11:22:33,  1.40s/it]
 53%|█████▎    | 32687/61904 [6:02:25<11:31:57,  1.42s/it]
 53%|█████▎    | 32688/61904 [6:02:26<11:17:19,  1.39s/it]
 53%|█████▎    | 32689/61904 [6:02:27<11:18:25,  1.39s/it]
 53%|█████▎    | 32690/61904 [6:02:29<10:54:44,  1.34s/it]
 53%|█████▎    | 32691/61904 [6:02:30<10:54:39,  1.34s/it]
 53%|█████▎    | 32692/61904 [6:02:31<11:07:38,  1.37s/it]
 53%|█████▎    | 32693/61904 [6:02:33<11:09:44,  1.38s/it]
 53%|█████▎    | 32694/61904 [6:02:34<11:04:12,  1.36s/it]
 53%|█████▎    | 32695/61904 [6:02:35<10:53:26,  1.34s/it]
 53%|█████▎    | 32696/61904 [6:02:37<10:50:19,  1.34s/it]
 53%|█████▎    | 32697/61904 [6:02:38<10:43:53,  1.32s/it]
 53%|█████▎    | 32698/61904 [6:02:39<10:33:18,  1.30s/it]
 53%|█████▎    | 32699/61904 [6:02:41<10:31:03,  1.30s/it]
 53%|█████▎    | 32700/61904 [6:02:42<10:52:15,  1.34s/it]
                                                          
{'loss': 2.5498, 'learning_rate': 1.473291844937119e-07, 'epoch': 8.45}
+
 53%|█████▎    | 32700/61904 [6:02:42<10:52:15,  1.34s/it]
 53%|█████▎    | 32701/61904 [6:02:43<11:03:43,  1.36s/it]
 53%|█████▎    | 32702/61904 [6:02:45<10:49:49,  1.34s/it]
 53%|█████▎    | 32703/61904 [6:02:46<10:32:03,  1.30s/it]
 53%|█████▎    | 32704/61904 [6:02:47<10:36:05,  1.31s/it]
 53%|█████▎    | 32705/61904 [6:02:49<10:36:08,  1.31s/it]
 53%|█████▎    | 32706/61904 [6:02:50<10:43:50,  1.32s/it]
 53%|█████▎    | 32707/61904 [6:02:52<11:22:37,  1.40s/it]
 53%|█████▎    | 32708/61904 [6:02:53<11:30:50,  1.42s/it]
 53%|█████▎    | 32709/61904 [6:02:54<11:18:00,  1.39s/it]
 53%|█████▎    | 32710/61904 [6:02:56<11:05:51,  1.37s/it]
 53%|█████▎    | 32711/61904 [6:02:57<11:00:01,  1.36s/it]
 53%|█████▎    | 32712/61904 [6:02:58<11:17:00,  1.39s/it]
 53%|█████▎    | 32713/61904 [6:03:00<11:33:09,  1.42s/it]
 53%|█████▎    | 32714/61904 [6:03:01<11:38:37,  1.44s/it]
 53%|█████▎    | 32715/61904 [6:03:03<11:42:27,  1.44s/it]
 53%|█████▎    | 32716/61904 [6:03:04<11:39:09,  1.44s/it]
 53%|█████▎    | 32717/61904 [6:03:06<11:41:18,  1.44s/it]
 53%|█████▎    | 32718/61904 [6:03:07<11:23:23,  1.40s/it]
 53%|█████▎    | 32719/61904 [6:03:08<10:52:09,  1.34s/it]
 53%|█████▎    | 32720/61904 [6:03:10<10:55:26,  1.35s/it]
                                                          
{'loss': 2.5182, 'learning_rate': 1.4729677168416957e-07, 'epoch': 8.46}
+
 53%|█████▎    | 32720/61904 [6:03:10<10:55:26,  1.35s/it]
 53%|█████▎    | 32721/61904 [6:03:11<11:02:19,  1.36s/it]
 53%|█████▎    | 32722/61904 [6:03:12<11:05:53,  1.37s/it]
 53%|█████▎    | 32723/61904 [6:03:14<11:15:04,  1.39s/it]
 53%|█████▎    | 32724/61904 [6:03:15<11:25:35,  1.41s/it]
 53%|█████▎    | 32725/61904 [6:03:17<11:05:10,  1.37s/it]
 53%|█████▎    | 32726/61904 [6:03:18<11:33:02,  1.43s/it]
 53%|█████▎    | 32727/61904 [6:03:19<11:26:22,  1.41s/it]
 53%|█████▎    | 32728/61904 [6:03:21<11:11:29,  1.38s/it]
 53%|█████▎    | 32729/61904 [6:03:22<11:04:01,  1.37s/it]
 53%|█████▎    | 32730/61904 [6:03:23<10:50:02,  1.34s/it]
 53%|█████▎    | 32731/61904 [6:03:25<11:09:03,  1.38s/it]
 53%|█████▎    | 32732/61904 [6:03:26<11:03:34,  1.36s/it]
 53%|█████▎    | 32733/61904 [6:03:28<10:55:09,  1.35s/it]
 53%|█████▎    | 32734/61904 [6:03:29<11:23:42,  1.41s/it]
 53%|█████▎    | 32735/61904 [6:03:30<11:15:52,  1.39s/it]
 53%|█████▎    | 32736/61904 [6:03:32<11:13:35,  1.39s/it]
 53%|█████▎    | 32737/61904 [6:03:33<11:12:11,  1.38s/it]
 53%|█████▎    | 32738/61904 [6:03:34<10:52:21,  1.34s/it]
 53%|█████▎    | 32739/61904 [6:03:36<11:01:08,  1.36s/it]
 53%|█████▎    | 32740/61904 [6:03:37<10:51:05,  1.34s/it]
                                                          
{'loss': 2.5588, 'learning_rate': 1.4726435887462726e-07, 'epoch': 8.46}
+
 53%|█████▎    | 32740/61904 [6:03:37<10:51:05,  1.34s/it]
 53%|█████▎    | 32741/61904 [6:03:39<11:05:34,  1.37s/it]
 53%|█████▎    | 32742/61904 [6:03:40<10:54:48,  1.35s/it]
 53%|█████▎    | 32743/61904 [6:03:41<11:17:30,  1.39s/it]
 53%|█████▎    | 32744/61904 [6:03:43<11:22:10,  1.40s/it]
 53%|█████▎    | 32745/61904 [6:03:44<11:19:59,  1.40s/it]
 53%|█████▎    | 32746/61904 [6:03:46<11:15:13,  1.39s/it]
 53%|█████▎    | 32747/61904 [6:03:47<11:26:22,  1.41s/it]
 53%|█████▎    | 32748/61904 [6:03:48<11:20:44,  1.40s/it]
 53%|█████▎    | 32749/61904 [6:03:50<11:28:22,  1.42s/it]
 53%|█████▎    | 32750/61904 [6:03:51<11:15:49,  1.39s/it]
 53%|█████▎    | 32751/61904 [6:03:52<11:08:28,  1.38s/it]
 53%|█████▎    | 32752/61904 [6:03:54<11:01:50,  1.36s/it]
 53%|█████▎    | 32753/61904 [6:03:55<10:54:03,  1.35s/it]
 53%|█████▎    | 32754/61904 [6:03:57<11:15:13,  1.39s/it]
 53%|█████▎    | 32755/61904 [6:03:58<11:11:14,  1.38s/it]
 53%|█████▎    | 32756/61904 [6:03:59<10:51:28,  1.34s/it]
 53%|█████▎    | 32757/61904 [6:04:01<10:49:09,  1.34s/it]
 53%|█████▎    | 32758/61904 [6:04:02<10:48:19,  1.33s/it]
 53%|█████▎    | 32759/61904 [6:04:03<10:49:24,  1.34s/it]
 53%|█████▎    | 32760/61904 [6:04:05<11:16:30,  1.39s/it]
                                                          
{'loss': 2.5302, 'learning_rate': 1.4723194606508492e-07, 'epoch': 8.47}
+
 53%|█████▎    | 32760/61904 [6:04:05<11:16:30,  1.39s/it]
 53%|█████▎    | 32761/61904 [6:04:06<11:06:09,  1.37s/it]
 53%|█████▎    | 32762/61904 [6:04:07<10:54:08,  1.35s/it]
 53%|█████▎    | 32763/61904 [6:04:09<11:14:05,  1.39s/it]
 53%|█████▎    | 32764/61904 [6:04:10<11:32:06,  1.43s/it]
 53%|█████▎    | 32765/61904 [6:04:12<11:48:34,  1.46s/it]
 53%|█████▎    | 32766/61904 [6:04:13<11:56:45,  1.48s/it]
 53%|█████▎    | 32767/61904 [6:04:15<11:42:04,  1.45s/it]
 53%|█████▎    | 32768/61904 [6:04:16<11:50:43,  1.46s/it]
 53%|█████▎    | 32769/61904 [6:04:18<11:54:09,  1.47s/it]
 53%|█████▎    | 32770/61904 [6:04:19<11:41:18,  1.44s/it]
 53%|█████▎    | 32771/61904 [6:04:20<11:24:27,  1.41s/it]
 53%|█████▎    | 32772/61904 [6:04:22<11:25:31,  1.41s/it]
 53%|█████▎    | 32773/61904 [6:04:23<11:17:27,  1.40s/it]
 53%|█████▎    | 32774/61904 [6:04:25<11:15:05,  1.39s/it]
 53%|█████▎    | 32775/61904 [6:04:26<11:38:49,  1.44s/it]
 53%|█████▎    | 32776/61904 [6:04:28<11:39:52,  1.44s/it]
 53%|█████▎    | 32777/61904 [6:04:29<11:20:13,  1.40s/it]
 53%|█████▎    | 32778/61904 [6:04:30<11:26:10,  1.41s/it]
 53%|█████▎    | 32779/61904 [6:04:32<11:39:24,  1.44s/it]
 53%|█████▎    | 32780/61904 [6:04:33<11:20:17,  1.40s/it]
                                                          
{'loss': 2.5296, 'learning_rate': 1.4719953325554258e-07, 'epoch': 8.47}
+
 53%|█████▎    | 32780/61904 [6:04:33<11:20:17,  1.40s/it]
 53%|█████▎    | 32781/61904 [6:04:34<11:02:33,  1.37s/it]
 53%|█████▎    | 32782/61904 [6:04:36<11:01:02,  1.36s/it]
 53%|█████▎    | 32783/61904 [6:04:37<10:57:35,  1.35s/it]
 53%|█████▎    | 32784/61904 [6:04:39<10:55:38,  1.35s/it]
 53%|█████▎    | 32785/61904 [6:04:40<11:02:40,  1.37s/it]
 53%|█████▎    | 32786/61904 [6:04:41<11:14:21,  1.39s/it]
 53%|█████▎    | 32787/61904 [6:04:43<10:59:22,  1.36s/it]
 53%|█████▎    | 32788/61904 [6:04:44<11:07:48,  1.38s/it]
 53%|█████▎    | 32789/61904 [6:04:45<11:02:28,  1.37s/it]
 53%|█████▎    | 32790/61904 [6:04:47<11:09:14,  1.38s/it]
 53%|█████▎    | 32791/61904 [6:04:48<11:01:30,  1.36s/it]
 53%|█████▎    | 32792/61904 [6:04:50<11:10:45,  1.38s/it]
 53%|█████▎    | 32793/61904 [6:04:51<11:05:14,  1.37s/it]
 53%|█████▎    | 32794/61904 [6:04:52<10:52:04,  1.34s/it]
 53%|█████▎    | 32795/61904 [6:04:54<10:48:09,  1.34s/it]
 53%|█████▎    | 32796/61904 [6:04:55<10:59:10,  1.36s/it]
 53%|█████▎    | 32797/61904 [6:04:56<10:58:40,  1.36s/it]
 53%|█████▎    | 32798/61904 [6:04:58<10:44:51,  1.33s/it]
 53%|█████▎    | 32799/61904 [6:04:59<11:09:46,  1.38s/it]
 53%|█████▎    | 32800/61904 [6:05:00<10:52:41,  1.35s/it]
                                                          
{'loss': 2.5676, 'learning_rate': 1.4716712044600024e-07, 'epoch': 8.48}
+
 53%|█████▎    | 32800/61904 [6:05:00<10:52:41,  1.35s/it]
 53%|█████▎    | 32801/61904 [6:05:02<11:10:51,  1.38s/it]
 53%|█████▎    | 32802/61904 [6:05:03<11:13:57,  1.39s/it]
 53%|█████▎    | 32803/61904 [6:05:05<11:09:52,  1.38s/it]
 53%|█████▎    | 32804/61904 [6:05:06<11:15:08,  1.39s/it]
 53%|█████▎    | 32805/61904 [6:05:08<11:49:12,  1.46s/it]
 53%|█████▎    | 32806/61904 [6:05:09<11:56:23,  1.48s/it]
 53%|█████▎    | 32807/61904 [6:05:11<11:51:13,  1.47s/it]
 53%|█████▎    | 32808/61904 [6:05:12<11:41:28,  1.45s/it]
 53%|█████▎    | 32809/61904 [6:05:13<11:18:00,  1.40s/it]
 53%|█████▎    | 32810/61904 [6:05:15<11:04:04,  1.37s/it]
 53%|█████▎    | 32811/61904 [6:05:16<11:01:55,  1.37s/it]
 53%|█████▎    | 32812/61904 [6:05:17<10:37:52,  1.32s/it]
 53%|█████▎    | 32813/61904 [6:05:19<10:59:59,  1.36s/it]
 53%|█████▎    | 32814/61904 [6:05:20<11:04:56,  1.37s/it]
 53%|█████▎    | 32815/61904 [6:05:21<11:11:12,  1.38s/it]
 53%|█████▎    | 32816/61904 [6:05:23<11:04:59,  1.37s/it]
 53%|█████▎    | 32817/61904 [6:05:24<10:52:40,  1.35s/it]
 53%|█████▎    | 32818/61904 [6:05:26<11:24:07,  1.41s/it]
 53%|█████▎    | 32819/61904 [6:05:27<11:10:20,  1.38s/it]
 53%|█████▎    | 32820/61904 [6:05:28<11:06:45,  1.38s/it]
                                                          
{'loss': 2.567, 'learning_rate': 1.471347076364579e-07, 'epoch': 8.48}
+
 53%|█████▎    | 32820/61904 [6:05:28<11:06:45,  1.38s/it]
 53%|█████▎    | 32821/61904 [6:05:30<11:27:01,  1.42s/it]
 53%|█████▎    | 32822/61904 [6:05:31<11:16:10,  1.40s/it]
 53%|█████▎    | 32823/61904 [6:05:32<11:02:28,  1.37s/it]
 53%|█████▎    | 32824/61904 [6:05:34<11:00:06,  1.36s/it]
 53%|█████▎    | 32825/61904 [6:05:35<11:09:13,  1.38s/it]
 53%|█████▎    | 32826/61904 [6:05:37<11:08:18,  1.38s/it]
 53%|█████▎    | 32827/61904 [6:05:38<10:55:53,  1.35s/it]
 53%|█████▎    | 32828/61904 [6:05:39<11:01:07,  1.36s/it]
 53%|█████▎    | 32829/61904 [6:05:41<11:15:15,  1.39s/it]
 53%|█████▎    | 32830/61904 [6:05:42<11:10:40,  1.38s/it]
 53%|█████▎    | 32831/61904 [6:05:43<11:15:33,  1.39s/it]
 53%|█████▎    | 32832/61904 [6:05:45<11:08:57,  1.38s/it]
 53%|█████▎    | 32833/61904 [6:05:46<11:19:59,  1.40s/it]
 53%|█████▎    | 32834/61904 [6:05:48<11:13:50,  1.39s/it]
 53%|█████▎    | 32835/61904 [6:05:49<11:11:41,  1.39s/it]
 53%|█████▎    | 32836/61904 [6:05:50<11:16:15,  1.40s/it]
 53%|█████▎    | 32837/61904 [6:05:52<11:28:24,  1.42s/it]
 53%|█████▎    | 32838/61904 [6:05:53<11:38:04,  1.44s/it]
 53%|█████▎    | 32839/61904 [6:05:55<11:36:14,  1.44s/it]
 53%|█████▎    | 32840/61904 [6:05:56<11:24:29,  1.41s/it]
                                                          
{'loss': 2.5531, 'learning_rate': 1.471022948269156e-07, 'epoch': 8.49}
+
 53%|█████▎    | 32840/61904 [6:05:56<11:24:29,  1.41s/it]
 53%|█████▎    | 32841/61904 [6:05:58<11:25:40,  1.42s/it]
 53%|█████▎    | 32842/61904 [6:05:59<11:12:24,  1.39s/it]
 53%|█████▎    | 32843/61904 [6:06:00<11:14:43,  1.39s/it]
 53%|█████▎    | 32844/61904 [6:06:02<11:10:25,  1.38s/it]
 53%|█████▎    | 32845/61904 [6:06:03<11:19:22,  1.40s/it]
 53%|█████▎    | 32846/61904 [6:06:04<11:08:10,  1.38s/it]
 53%|█████▎    | 32847/61904 [6:06:06<11:11:59,  1.39s/it]
 53%|█████▎    | 32848/61904 [6:06:07<11:10:03,  1.38s/it]
 53%|█████▎    | 32849/61904 [6:06:09<11:28:45,  1.42s/it]
 53%|█████▎    | 32850/61904 [6:06:10<11:17:09,  1.40s/it]
 53%|█████▎    | 32851/61904 [6:06:11<10:58:00,  1.36s/it]
 53%|█████▎    | 32852/61904 [6:06:13<10:55:13,  1.35s/it]
 53%|█████▎    | 32853/61904 [6:06:14<10:39:42,  1.32s/it]
 53%|█████▎    | 32854/61904 [6:06:15<11:07:54,  1.38s/it]
 53%|█████▎    | 32855/61904 [6:06:17<10:58:43,  1.36s/it]
 53%|█████▎    | 32856/61904 [6:06:18<11:06:51,  1.38s/it]
 53%|█████▎    | 32857/61904 [6:06:20<11:12:40,  1.39s/it]
 53%|█████▎    | 32858/61904 [6:06:21<11:00:01,  1.36s/it]
 53%|█████▎    | 32859/61904 [6:06:22<11:01:19,  1.37s/it]
 53%|█████▎    | 32860/61904 [6:06:24<10:55:43,  1.35s/it]
                                                          
{'loss': 2.6131, 'learning_rate': 1.4706988201737326e-07, 'epoch': 8.49}
+
 53%|█████▎    | 32860/61904 [6:06:24<10:55:43,  1.35s/it]
 53%|█████▎    | 32861/61904 [6:06:25<11:06:24,  1.38s/it]
 53%|█████▎    | 32862/61904 [6:06:27<11:29:47,  1.43s/it]
 53%|█████▎    | 32863/61904 [6:06:28<11:21:00,  1.41s/it]
 53%|█████▎    | 32864/61904 [6:06:29<11:09:56,  1.38s/it]
 53%|█████▎    | 32865/61904 [6:06:31<11:30:08,  1.43s/it]
 53%|█████▎    | 32866/61904 [6:06:32<11:11:31,  1.39s/it]
 53%|█████▎    | 32867/61904 [6:06:34<11:25:14,  1.42s/it]
 53%|█████▎    | 32868/61904 [6:06:35<11:12:54,  1.39s/it]
 53%|█████▎    | 32869/61904 [6:06:36<11:09:22,  1.38s/it]
 53%|█████▎    | 32870/61904 [6:06:38<11:15:39,  1.40s/it]
 53%|█████▎    | 32871/61904 [6:06:39<11:36:06,  1.44s/it]
 53%|█████▎    | 32872/61904 [6:06:41<11:16:23,  1.40s/it]
 53%|█████▎    | 32873/61904 [6:06:42<11:02:44,  1.37s/it]
 53%|█████▎    | 32874/61904 [6:06:43<11:05:30,  1.38s/it]
 53%|█████▎    | 32875/61904 [6:06:45<11:07:47,  1.38s/it]
 53%|█████▎    | 32876/61904 [6:06:46<11:18:13,  1.40s/it]
 53%|█████▎    | 32877/61904 [6:06:48<11:35:37,  1.44s/it]
 53%|█████▎    | 32878/61904 [6:06:49<11:21:46,  1.41s/it]
 53%|█████▎    | 32879/61904 [6:06:50<11:22:06,  1.41s/it]
 53%|█████▎    | 32880/61904 [6:06:52<11:15:53,  1.40s/it]
                                                          
{'loss': 2.5818, 'learning_rate': 1.4703746920783092e-07, 'epoch': 8.5}
+
 53%|█████▎    | 32880/61904 [6:06:52<11:15:53,  1.40s/it]
 53%|█████▎    | 32881/61904 [6:06:53<11:10:12,  1.39s/it]
 53%|█████▎    | 32882/61904 [6:06:54<11:08:31,  1.38s/it]
 53%|█████▎    | 32883/61904 [6:06:56<11:06:32,  1.38s/it]
 53%|█████▎    | 32884/61904 [6:06:57<11:01:35,  1.37s/it]
 53%|█████▎    | 32885/61904 [6:06:59<11:27:31,  1.42s/it]
 53%|█████▎    | 32886/61904 [6:07:00<11:23:15,  1.41s/it]
 53%|█████▎    | 32887/61904 [6:07:02<11:21:01,  1.41s/it]
 53%|█████▎    | 32888/61904 [6:07:03<11:27:01,  1.42s/it]
 53%|█████▎    | 32889/61904 [6:07:04<11:26:43,  1.42s/it]
 53%|█████▎    | 32890/61904 [6:07:06<11:12:35,  1.39s/it]
 53%|█████▎    | 32891/61904 [6:07:07<11:22:32,  1.41s/it]
 53%|█████▎    | 32892/61904 [6:07:09<11:19:41,  1.41s/it]
 53%|█████▎    | 32893/61904 [6:07:10<11:18:25,  1.40s/it]
 53%|█████▎    | 32894/61904 [6:07:12<11:42:18,  1.45s/it]
 53%|█████▎    | 32895/61904 [6:07:13<11:09:27,  1.38s/it]
 53%|█████▎    | 32896/61904 [6:07:14<11:04:53,  1.38s/it]
 53%|█████▎    | 32897/61904 [6:07:15<10:53:53,  1.35s/it]
 53%|█████▎    | 32898/61904 [6:07:17<11:23:23,  1.41s/it]
 53%|█████▎    | 32899/61904 [6:07:18<11:14:56,  1.40s/it]
 53%|█████▎    | 32900/61904 [6:07:20<11:10:12,  1.39s/it]
                                                          
{'loss': 2.542, 'learning_rate': 1.470050563982886e-07, 'epoch': 8.5}
+
 53%|█████▎    | 32900/61904 [6:07:20<11:10:12,  1.39s/it]
 53%|█████▎    | 32901/61904 [6:07:21<11:01:47,  1.37s/it]
 53%|█████▎    | 32902/61904 [6:07:22<10:50:45,  1.35s/it]
 53%|█████▎    | 32903/61904 [6:07:24<10:51:33,  1.35s/it]
 53%|█████▎    | 32904/61904 [6:07:25<10:55:26,  1.36s/it]
 53%|█████▎    | 32905/61904 [6:07:26<10:53:39,  1.35s/it]
 53%|█████▎    | 32906/61904 [6:07:28<10:45:24,  1.34s/it]
 53%|█████▎    | 32907/61904 [6:07:29<10:43:10,  1.33s/it]
 53%|█████▎    | 32908/61904 [6:07:30<11:04:41,  1.38s/it]
 53%|█████▎    | 32909/61904 [6:07:32<11:16:59,  1.40s/it]
 53%|█████▎    | 32910/61904 [6:07:33<11:09:40,  1.39s/it]
 53%|█████▎    | 32911/61904 [6:07:35<10:57:45,  1.36s/it]
 53%|█████▎    | 32912/61904 [6:07:36<10:57:23,  1.36s/it]
 53%|█████▎    | 32913/61904 [6:07:37<10:53:33,  1.35s/it]
 53%|█████▎    | 32914/61904 [6:07:39<10:53:59,  1.35s/it]
 53%|█████▎    | 32915/61904 [6:07:40<11:00:43,  1.37s/it]
 53%|█████▎    | 32916/61904 [6:07:41<10:55:12,  1.36s/it]
 53%|█████▎    | 32917/61904 [6:07:43<11:23:37,  1.42s/it]
 53%|█████▎    | 32918/61904 [6:07:44<11:27:22,  1.42s/it]
 53%|█████▎    | 32919/61904 [6:07:46<11:45:37,  1.46s/it]
 53%|█████▎    | 32920/61904 [6:07:47<11:30:20,  1.43s/it]
                                                          
{'loss': 2.5656, 'learning_rate': 1.4697264358874627e-07, 'epoch': 8.51}
+
 53%|█████▎    | 32920/61904 [6:07:47<11:30:20,  1.43s/it]
 53%|█████▎    | 32921/61904 [6:07:48<10:59:15,  1.36s/it]
 53%|█████▎    | 32922/61904 [6:07:50<10:43:03,  1.33s/it]
 53%|█████▎    | 32923/61904 [6:07:51<10:49:29,  1.34s/it]
 53%|█████▎    | 32924/61904 [6:07:52<10:39:44,  1.32s/it]
 53%|█████▎    | 32925/61904 [6:07:54<10:46:11,  1.34s/it]
 53%|█████▎    | 32926/61904 [6:07:55<10:34:35,  1.31s/it]
 53%|█████▎    | 32927/61904 [6:07:56<10:40:59,  1.33s/it]
 53%|█████▎    | 32928/61904 [6:07:58<10:52:06,  1.35s/it]
 53%|█████▎    | 32929/61904 [6:07:59<10:36:06,  1.32s/it]
 53%|█████▎    | 32930/61904 [6:08:00<10:46:27,  1.34s/it]
 53%|█████▎    | 32931/61904 [6:08:02<10:47:12,  1.34s/it]
 53%|█████▎    | 32932/61904 [6:08:03<10:40:52,  1.33s/it]
 53%|█████▎    | 32933/61904 [6:08:05<11:10:56,  1.39s/it]
 53%|█████▎    | 32934/61904 [6:08:06<11:09:56,  1.39s/it]
 53%|█████▎    | 32935/61904 [6:08:07<10:54:39,  1.36s/it]
 53%|█████▎    | 32936/61904 [6:08:09<11:12:33,  1.39s/it]
 53%|█████▎    | 32937/61904 [6:08:10<11:03:21,  1.37s/it]
 53%|█████▎    | 32938/61904 [6:08:11<11:04:42,  1.38s/it]
 53%|█████▎    | 32939/61904 [6:08:13<11:09:02,  1.39s/it]
 53%|█████▎    | 32940/61904 [6:08:14<11:15:22,  1.40s/it]
                                                          
{'loss': 2.5548, 'learning_rate': 1.4694023077920393e-07, 'epoch': 8.51}
+
 53%|█████▎    | 32940/61904 [6:08:14<11:15:22,  1.40s/it]
 53%|█████▎    | 32941/61904 [6:08:16<11:14:22,  1.40s/it]
 53%|█████▎    | 32942/61904 [6:08:17<11:20:51,  1.41s/it]
 53%|█████▎    | 32943/61904 [6:08:18<11:02:14,  1.37s/it]
 53%|█████▎    | 32944/61904 [6:08:20<11:06:17,  1.38s/it]
 53%|█████▎    | 32945/61904 [6:08:21<11:32:30,  1.43s/it]
 53%|█████▎    | 32946/61904 [6:08:23<11:34:23,  1.44s/it]
 53%|█████▎    | 32947/61904 [6:08:24<11:21:08,  1.41s/it]
 53%|█████▎    | 32948/61904 [6:08:26<11:16:22,  1.40s/it]
 53%|█████▎    | 32949/61904 [6:08:27<10:52:00,  1.35s/it]
 53%|█████▎    | 32950/61904 [6:08:28<10:55:59,  1.36s/it]
 53%|█████▎    | 32951/61904 [6:08:30<11:05:15,  1.38s/it]
 53%|█████▎    | 32952/61904 [6:08:31<11:10:47,  1.39s/it]
 53%|█████▎    | 32953/61904 [6:08:33<11:37:03,  1.44s/it]
 53%|█████▎    | 32954/61904 [6:08:34<11:18:32,  1.41s/it]
 53%|█████▎    | 32955/61904 [6:08:35<11:19:18,  1.41s/it]
 53%|█████▎    | 32956/61904 [6:08:37<11:25:43,  1.42s/it]
 53%|█████▎    | 32957/61904 [6:08:38<11:36:24,  1.44s/it]
 53%|█████▎    | 32958/61904 [6:08:40<11:23:41,  1.42s/it]
 53%|█████▎    | 32959/61904 [6:08:41<11:48:38,  1.47s/it]
 53%|█████▎    | 32960/61904 [6:08:43<11:36:55,  1.44s/it]
                                                          
{'loss': 2.5295, 'learning_rate': 1.4690781796966162e-07, 'epoch': 8.52}
+
 53%|█████▎    | 32960/61904 [6:08:43<11:36:55,  1.44s/it]
 53%|█████▎    | 32961/61904 [6:08:44<11:31:56,  1.43s/it]
 53%|█████▎    | 32962/61904 [6:08:45<11:13:21,  1.40s/it]
 53%|█████▎    | 32963/61904 [6:08:47<11:04:56,  1.38s/it]
 53%|█████▎    | 32964/61904 [6:08:48<11:05:03,  1.38s/it]
 53%|█████▎    | 32965/61904 [6:08:49<10:59:37,  1.37s/it]
 53%|█████▎    | 32966/61904 [6:08:51<10:59:39,  1.37s/it]
 53%|█████▎    | 32967/61904 [6:08:52<10:39:15,  1.33s/it]
 53%|█████▎    | 32968/61904 [6:08:53<11:01:25,  1.37s/it]
 53%|█████▎    | 32969/61904 [6:08:55<10:57:26,  1.36s/it]
 53%|█████▎    | 32970/61904 [6:08:56<11:02:12,  1.37s/it]
 53%|█████▎    | 32971/61904 [6:08:58<11:10:42,  1.39s/it]
 53%|█████▎    | 32972/61904 [6:08:59<11:10:50,  1.39s/it]
 53%|█████▎    | 32973/61904 [6:09:00<11:11:13,  1.39s/it]
 53%|█████▎    | 32974/61904 [6:09:02<11:34:03,  1.44s/it]
 53%|█████▎    | 32975/61904 [6:09:03<11:15:30,  1.40s/it]
 53%|█████▎    | 32976/61904 [6:09:05<11:27:05,  1.43s/it]
 53%|█████▎    | 32977/61904 [6:09:06<11:23:47,  1.42s/it]
 53%|█████▎    | 32978/61904 [6:09:07<11:17:57,  1.41s/it]
 53%|█████▎    | 32979/61904 [6:09:09<11:29:16,  1.43s/it]
 53%|█████▎    | 32980/61904 [6:09:10<11:14:55,  1.40s/it]
                                                          
{'loss': 2.4961, 'learning_rate': 1.4687540516011925e-07, 'epoch': 8.52}
+
 53%|█████▎    | 32980/61904 [6:09:10<11:14:55,  1.40s/it]
 53%|█████▎    | 32981/61904 [6:09:12<11:05:37,  1.38s/it]
 53%|█████▎    | 32982/61904 [6:09:13<11:10:21,  1.39s/it]
 53%|█████▎    | 32983/61904 [6:09:14<11:05:29,  1.38s/it]
 53%|█████▎    | 32984/61904 [6:09:16<11:04:09,  1.38s/it]
 53%|█████▎    | 32985/61904 [6:09:17<10:44:44,  1.34s/it]
 53%|█████▎    | 32986/61904 [6:09:18<10:59:40,  1.37s/it]
 53%|█████▎    | 32987/61904 [6:09:20<10:57:59,  1.37s/it]
 53%|█████▎    | 32988/61904 [6:09:21<10:56:28,  1.36s/it]
 53%|█████▎    | 32989/61904 [6:09:23<11:01:12,  1.37s/it]
 53%|█████▎    | 32990/61904 [6:09:24<11:19:27,  1.41s/it]
 53%|█████▎    | 32991/61904 [6:09:25<11:06:24,  1.38s/it]
 53%|█████▎    | 32992/61904 [6:09:27<11:09:05,  1.39s/it]
 53%|█████▎    | 32993/61904 [6:09:28<11:09:03,  1.39s/it]
 53%|█████▎    | 32994/61904 [6:09:30<11:11:33,  1.39s/it]
 53%|█████▎    | 32995/61904 [6:09:31<11:11:06,  1.39s/it]
 53%|█████▎    | 32996/61904 [6:09:32<11:06:16,  1.38s/it]
 53%|█████▎    | 32997/61904 [6:09:34<11:10:07,  1.39s/it]
 53%|█████▎    | 32998/61904 [6:09:35<11:12:26,  1.40s/it]
 53%|█████▎    | 32999/61904 [6:09:36<10:59:09,  1.37s/it]
 53%|█████▎    | 33000/61904 [6:09:38<11:23:20,  1.42s/it]
                                                          
{'loss': 2.5361, 'learning_rate': 1.4684299235057694e-07, 'epoch': 8.53}
+
 53%|█████▎    | 33000/61904 [6:09:38<11:23:20,  1.42s/it]
 53%|█████▎    | 33001/61904 [6:09:39<11:11:51,  1.39s/it]
 53%|█████▎    | 33002/61904 [6:09:41<10:54:04,  1.36s/it]
 53%|█████▎    | 33003/61904 [6:09:42<10:42:17,  1.33s/it]
 53%|█████▎    | 33004/61904 [6:09:43<11:18:38,  1.41s/it]
 53%|█████▎    | 33005/61904 [6:09:45<11:29:26,  1.43s/it]
 53%|█████▎    | 33006/61904 [6:09:46<11:29:13,  1.43s/it]
 53%|█████▎    | 33007/61904 [6:09:48<11:26:40,  1.43s/it]
 53%|█████▎    | 33008/61904 [6:09:49<11:19:43,  1.41s/it]
 53%|█████▎    | 33009/61904 [6:09:50<10:57:53,  1.37s/it]
 53%|█████▎    | 33010/61904 [6:09:52<11:15:09,  1.40s/it]
 53%|█████▎    | 33011/61904 [6:09:53<11:30:38,  1.43s/it]
 53%|█████▎    | 33012/61904 [6:09:55<11:10:05,  1.39s/it]
 53%|█████▎    | 33013/61904 [6:09:56<11:01:41,  1.37s/it]
 53%|█████▎    | 33014/61904 [6:09:58<11:27:12,  1.43s/it]
 53%|█████▎    | 33015/61904 [6:09:59<11:22:42,  1.42s/it]
 53%|█████▎    | 33016/61904 [6:10:01<11:56:30,  1.49s/it]
 53%|█████▎    | 33017/61904 [6:10:02<11:40:32,  1.46s/it]
 53%|█████▎    | 33018/61904 [6:10:03<11:29:54,  1.43s/it]
 53%|█████▎    | 33019/61904 [6:10:05<11:18:31,  1.41s/it]
 53%|█████▎    | 33020/61904 [6:10:06<11:24:38,  1.42s/it]
                                                          
{'loss': 2.5244, 'learning_rate': 1.468105795410346e-07, 'epoch': 8.53}
+
 53%|█████▎    | 33020/61904 [6:10:06<11:24:38,  1.42s/it]
 53%|█████▎    | 33021/61904 [6:10:08<11:22:27,  1.42s/it]
 53%|█████▎    | 33022/61904 [6:10:09<11:30:13,  1.43s/it]
 53%|█████▎    | 33023/61904 [6:10:11<11:33:28,  1.44s/it]
 53%|█████▎    | 33024/61904 [6:10:12<11:16:00,  1.40s/it]
 53%|█████▎    | 33025/61904 [6:10:13<11:07:38,  1.39s/it]
 53%|█████▎    | 33026/61904 [6:10:15<11:50:19,  1.48s/it]
 53%|█████▎    | 33027/61904 [6:10:16<11:39:29,  1.45s/it]
 53%|█████▎    | 33028/61904 [6:10:18<11:42:08,  1.46s/it]
 53%|█████▎    | 33029/61904 [6:10:19<11:23:36,  1.42s/it]
 53%|█████▎    | 33030/61904 [6:10:20<11:08:13,  1.39s/it]
 53%|█████▎    | 33031/61904 [6:10:22<11:11:42,  1.40s/it]
 53%|█████▎    | 33032/61904 [6:10:23<11:12:46,  1.40s/it]
 53%|█████▎    | 33033/61904 [6:10:25<11:06:55,  1.39s/it]
 53%|█████▎    | 33034/61904 [6:10:26<11:11:56,  1.40s/it]
 53%|█████▎    | 33035/61904 [6:10:27<10:53:43,  1.36s/it]
 53%|█████▎    | 33036/61904 [6:10:29<11:10:22,  1.39s/it]
 53%|█████▎    | 33037/61904 [6:10:30<10:58:54,  1.37s/it]
 53%|█████▎    | 33038/61904 [6:10:32<11:09:50,  1.39s/it]
 53%|█████▎    | 33039/61904 [6:10:33<10:54:35,  1.36s/it]
 53%|█████▎    | 33040/61904 [6:10:34<10:35:39,  1.32s/it]
                                                          
{'loss': 2.4984, 'learning_rate': 1.4677816673149227e-07, 'epoch': 8.54}
+
 53%|█████▎    | 33040/61904 [6:10:34<10:35:39,  1.32s/it]
 53%|█████▎    | 33041/61904 [6:10:35<10:41:31,  1.33s/it]
 53%|█████▎    | 33042/61904 [6:10:37<10:41:33,  1.33s/it]
 53%|█████▎    | 33043/61904 [6:10:38<10:43:26,  1.34s/it]
 53%|█████▎    | 33044/61904 [6:10:40<11:11:17,  1.40s/it]
 53%|█████▎    | 33045/61904 [6:10:41<11:07:03,  1.39s/it]
 53%|█████▎    | 33046/61904 [6:10:42<10:59:16,  1.37s/it]
 53%|█████▎    | 33047/61904 [6:10:44<11:04:36,  1.38s/it]
 53%|█████▎    | 33048/61904 [6:10:45<11:07:27,  1.39s/it]
 53%|█████▎    | 33049/61904 [6:10:47<11:20:08,  1.41s/it]
 53%|█████▎    | 33050/61904 [6:10:48<11:36:40,  1.45s/it]
 53%|█████▎    | 33051/61904 [6:10:49<11:18:41,  1.41s/it]
 53%|█████▎    | 33052/61904 [6:10:51<11:26:51,  1.43s/it]
 53%|█████▎    | 33053/61904 [6:10:52<11:23:47,  1.42s/it]
 53%|█████▎    | 33054/61904 [6:10:54<11:48:40,  1.47s/it]
 53%|█████▎    | 33055/61904 [6:10:55<11:42:47,  1.46s/it]
 53%|█████▎    | 33056/61904 [6:10:57<11:14:33,  1.40s/it]
 53%|█████▎    | 33057/61904 [6:10:58<11:03:52,  1.38s/it]
 53%|█████▎    | 33058/61904 [6:10:59<11:17:02,  1.41s/it]
 53%|█████▎    | 33059/61904 [6:11:01<10:59:48,  1.37s/it]
 53%|█████▎    | 33060/61904 [6:11:02<11:46:26,  1.47s/it]
                                                          
{'loss': 2.5107, 'learning_rate': 1.4674575392194995e-07, 'epoch': 8.54}
+
 53%|█████▎    | 33060/61904 [6:11:02<11:46:26,  1.47s/it]
 53%|█████▎    | 33061/61904 [6:11:04<11:33:10,  1.44s/it]
 53%|█████▎    | 33062/61904 [6:11:05<11:22:14,  1.42s/it]
 53%|█████▎    | 33063/61904 [6:11:06<11:08:04,  1.39s/it]
 53%|█████▎    | 33064/61904 [6:11:08<11:02:38,  1.38s/it]
 53%|█████▎    | 33065/61904 [6:11:09<10:34:58,  1.32s/it]
 53%|█████▎    | 33066/61904 [6:11:10<10:46:26,  1.34s/it]
 53%|█████▎    | 33067/61904 [6:11:12<10:37:33,  1.33s/it]
 53%|█████▎    | 33068/61904 [6:11:13<10:38:30,  1.33s/it]
 53%|█████▎    | 33069/61904 [6:11:14<10:57:58,  1.37s/it]
 53%|█████▎    | 33070/61904 [6:11:16<10:58:53,  1.37s/it]
 53%|█████▎    | 33071/61904 [6:11:17<10:56:01,  1.37s/it]
 53%|█████▎    | 33072/61904 [6:11:19<11:02:38,  1.38s/it]
 53%|█████▎    | 33073/61904 [6:11:20<10:47:11,  1.35s/it]
 53%|█████▎    | 33074/61904 [6:11:21<11:00:23,  1.37s/it]
 53%|█████▎    | 33075/61904 [6:11:23<10:59:45,  1.37s/it]
 53%|█████▎    | 33076/61904 [6:11:24<10:41:58,  1.34s/it]
 53%|█████▎    | 33077/61904 [6:11:25<10:23:24,  1.30s/it]
 53%|█████▎    | 33078/61904 [6:11:27<10:38:18,  1.33s/it]
 53%|█████▎    | 33079/61904 [6:11:28<10:45:42,  1.34s/it]
 53%|█████▎    | 33080/61904 [6:11:29<10:39:30,  1.33s/it]
                                                          
{'loss': 2.6018, 'learning_rate': 1.4671334111240762e-07, 'epoch': 8.55}
+
 53%|█████▎    | 33080/61904 [6:11:29<10:39:30,  1.33s/it]
 53%|█████▎    | 33081/61904 [6:11:31<10:58:06,  1.37s/it]
 53%|█████▎    | 33082/61904 [6:11:32<10:58:30,  1.37s/it]
 53%|█████▎    | 33083/61904 [6:11:33<11:01:49,  1.38s/it]
 53%|█████▎    | 33084/61904 [6:11:35<11:14:55,  1.41s/it]
 53%|█████▎    | 33085/61904 [6:11:36<11:18:35,  1.41s/it]
 53%|█████▎    | 33086/61904 [6:11:38<11:38:26,  1.45s/it]
 53%|█████▎    | 33087/61904 [6:11:39<11:26:15,  1.43s/it]
 53%|█████▎    | 33088/61904 [6:11:41<11:22:08,  1.42s/it]
 53%|█████▎    | 33089/61904 [6:11:42<11:43:42,  1.47s/it]
 53%|█████▎    | 33090/61904 [6:11:44<11:22:10,  1.42s/it]
 53%|█████▎    | 33091/61904 [6:11:45<11:03:22,  1.38s/it]
 53%|█████▎    | 33092/61904 [6:11:46<10:58:23,  1.37s/it]
 53%|█████▎    | 33093/61904 [6:11:48<11:17:06,  1.41s/it]
 53%|█████▎    | 33094/61904 [6:11:49<10:52:18,  1.36s/it]
 53%|█████▎    | 33095/61904 [6:11:50<10:31:33,  1.32s/it]
 53%|█████▎    | 33096/61904 [6:11:52<11:09:41,  1.39s/it]
 53%|█████▎    | 33097/61904 [6:11:53<11:03:54,  1.38s/it]
 53%|█████▎    | 33098/61904 [6:11:55<11:11:33,  1.40s/it]
 53%|█████▎    | 33099/61904 [6:11:56<10:52:53,  1.36s/it]
 53%|█████▎    | 33100/61904 [6:11:57<11:13:13,  1.40s/it]
                                                          
{'loss': 2.5481, 'learning_rate': 1.4668092830286528e-07, 'epoch': 8.55}
+
 53%|█████▎    | 33100/61904 [6:11:57<11:13:13,  1.40s/it]
 53%|█████▎    | 33101/61904 [6:11:59<11:09:57,  1.40s/it]
 53%|█████▎    | 33102/61904 [6:12:00<11:03:40,  1.38s/it]
 53%|█████▎    | 33103/61904 [6:12:01<10:42:59,  1.34s/it]
 53%|█████▎    | 33104/61904 [6:12:03<10:35:29,  1.32s/it]
 53%|█████▎    | 33105/61904 [6:12:04<10:43:20,  1.34s/it]
 53%|█████▎    | 33106/61904 [6:12:06<11:14:10,  1.40s/it]
 53%|█████▎    | 33107/61904 [6:12:07<11:19:47,  1.42s/it]
 53%|█████▎    | 33108/61904 [6:12:08<11:01:29,  1.38s/it]
 53%|█████▎    | 33109/61904 [6:12:10<11:18:31,  1.41s/it]
 53%|█████▎    | 33110/61904 [6:12:11<11:29:04,  1.44s/it]
 53%|█████▎    | 33111/61904 [6:12:13<11:11:42,  1.40s/it]
 53%|█████▎    | 33112/61904 [6:12:14<11:22:06,  1.42s/it]
 53%|█████▎    | 33113/61904 [6:12:15<11:20:35,  1.42s/it]
 53%|█████▎    | 33114/61904 [6:12:17<11:18:11,  1.41s/it]
 53%|█████▎    | 33115/61904 [6:12:18<11:27:45,  1.43s/it]
 53%|█████▎    | 33116/61904 [6:12:20<11:43:04,  1.47s/it]
 53%|█████▎    | 33117/61904 [6:12:21<11:27:15,  1.43s/it]
 53%|█████▎    | 33118/61904 [6:12:23<11:27:28,  1.43s/it]
 54%|█████▎    | 33119/61904 [6:12:24<11:26:00,  1.43s/it]
 54%|█████▎    | 33120/61904 [6:12:25<11:03:02,  1.38s/it]
                                                          
{'loss': 2.5671, 'learning_rate': 1.4664851549332297e-07, 'epoch': 8.56}
+
 54%|█████▎    | 33120/61904 [6:12:25<11:03:02,  1.38s/it]
 54%|█████▎    | 33121/61904 [6:12:27<10:56:19,  1.37s/it]
 54%|█████▎    | 33122/61904 [6:12:28<11:18:52,  1.42s/it]
 54%|█████▎    | 33123/61904 [6:12:30<11:16:38,  1.41s/it]
 54%|█████▎    | 33124/61904 [6:12:31<11:11:57,  1.40s/it]
 54%|█████▎    | 33125/61904 [6:12:33<11:47:21,  1.47s/it]
 54%|█████▎    | 33126/61904 [6:12:34<11:23:06,  1.42s/it]
 54%|█████▎    | 33127/61904 [6:12:35<10:54:02,  1.36s/it]
 54%|█████▎    | 33128/61904 [6:12:36<10:41:21,  1.34s/it]
 54%|█████▎    | 33129/61904 [6:12:38<10:42:56,  1.34s/it]
 54%|█████▎    | 33130/61904 [6:12:39<10:43:24,  1.34s/it]
 54%|█████▎    | 33131/61904 [6:12:41<11:20:27,  1.42s/it]
 54%|█████▎    | 33132/61904 [6:12:42<11:23:49,  1.43s/it]
 54%|█████▎    | 33133/61904 [6:12:44<11:29:13,  1.44s/it]
 54%|█████▎    | 33134/61904 [6:12:45<11:15:15,  1.41s/it]
 54%|█████▎    | 33135/61904 [6:12:46<11:05:07,  1.39s/it]
 54%|█████▎    | 33136/61904 [6:12:48<11:14:34,  1.41s/it]
 54%|█████▎    | 33137/61904 [6:12:49<10:50:49,  1.36s/it]
 54%|█████▎    | 33138/61904 [6:12:50<10:42:16,  1.34s/it]
 54%|█████▎    | 33139/61904 [6:12:52<10:48:17,  1.35s/it]
 54%|█████▎    | 33140/61904 [6:12:53<10:38:42,  1.33s/it]
                                                          
{'loss': 2.5587, 'learning_rate': 1.466161026837806e-07, 'epoch': 8.57}
+
 54%|█████▎    | 33140/61904 [6:12:53<10:38:42,  1.33s/it]
 54%|█████▎    | 33141/61904 [6:12:54<10:24:16,  1.30s/it]
 54%|█████▎    | 33142/61904 [6:12:56<10:26:41,  1.31s/it]
 54%|█████▎    | 33143/61904 [6:12:57<10:39:31,  1.33s/it]
 54%|█████▎    | 33144/61904 [6:12:58<10:31:48,  1.32s/it]
 54%|█████▎    | 33145/61904 [6:12:59<10:22:00,  1.30s/it]
 54%|█████▎    | 33146/61904 [6:13:01<10:42:17,  1.34s/it]
 54%|█████▎    | 33147/61904 [6:13:02<11:14:50,  1.41s/it]
 54%|█████▎    | 33148/61904 [6:13:04<11:05:51,  1.39s/it]
 54%|█████▎    | 33149/61904 [6:13:05<10:53:46,  1.36s/it]
 54%|█████▎    | 33150/61904 [6:13:06<10:56:09,  1.37s/it]
 54%|█████▎    | 33151/61904 [6:13:08<10:40:15,  1.34s/it]
 54%|█████▎    | 33152/61904 [6:13:09<10:57:24,  1.37s/it]
 54%|█████▎    | 33153/61904 [6:13:11<11:07:48,  1.39s/it]
 54%|█████▎    | 33154/61904 [6:13:12<11:14:31,  1.41s/it]
 54%|█████▎    | 33155/61904 [6:13:13<10:54:20,  1.37s/it]
 54%|█████▎    | 33156/61904 [6:13:15<11:13:10,  1.40s/it]
 54%|█████▎    | 33157/61904 [6:13:16<11:01:32,  1.38s/it]
 54%|█████▎    | 33158/61904 [6:13:17<10:53:48,  1.36s/it]
 54%|█████▎    | 33159/61904 [6:13:19<10:47:46,  1.35s/it]
 54%|█████▎    | 33160/61904 [6:13:20<10:27:33,  1.31s/it]
                                                          
{'loss': 2.4905, 'learning_rate': 1.465836898742383e-07, 'epoch': 8.57}
+
 54%|█████▎    | 33160/61904 [6:13:20<10:27:33,  1.31s/it]
 54%|█████▎    | 33161/61904 [6:13:21<10:18:23,  1.29s/it]
 54%|█████▎    | 33162/61904 [6:13:23<10:31:07,  1.32s/it]
 54%|█████▎    | 33163/61904 [6:13:24<10:58:15,  1.37s/it]
 54%|█████▎    | 33164/61904 [6:13:25<10:52:20,  1.36s/it]
 54%|█████▎    | 33165/61904 [6:13:27<10:41:00,  1.34s/it]
 54%|█████▎    | 33166/61904 [6:13:28<11:04:14,  1.39s/it]
 54%|█████▎    | 33167/61904 [6:13:30<10:52:41,  1.36s/it]
 54%|█████▎    | 33168/61904 [6:13:31<10:42:22,  1.34s/it]
 54%|█████▎    | 33169/61904 [6:13:32<10:53:53,  1.37s/it]
 54%|█████▎    | 33170/61904 [6:13:34<11:10:32,  1.40s/it]
 54%|█████▎    | 33171/61904 [6:13:35<10:50:31,  1.36s/it]
 54%|█████▎    | 33172/61904 [6:13:36<10:50:15,  1.36s/it]
 54%|█████▎    | 33173/61904 [6:13:38<10:48:58,  1.36s/it]
 54%|█████▎    | 33174/61904 [6:13:39<10:55:54,  1.37s/it]
 54%|█████▎    | 33175/61904 [6:13:41<11:16:05,  1.41s/it]
 54%|█████▎    | 33176/61904 [6:13:42<11:01:56,  1.38s/it]
 54%|█████▎    | 33177/61904 [6:13:43<11:16:37,  1.41s/it]
 54%|█████▎    | 33178/61904 [6:13:45<11:52:27,  1.49s/it]
 54%|█████▎    | 33179/61904 [6:13:47<11:39:53,  1.46s/it]
 54%|█████▎    | 33180/61904 [6:13:48<11:16:38,  1.41s/it]
                                                          
{'loss': 2.5159, 'learning_rate': 1.4655127706469598e-07, 'epoch': 8.58}
+
 54%|█████▎    | 33180/61904 [6:13:48<11:16:38,  1.41s/it]
 54%|█████▎    | 33181/61904 [6:13:49<11:01:46,  1.38s/it]
 54%|█████▎    | 33182/61904 [6:13:51<11:46:02,  1.47s/it]
 54%|█████▎    | 33183/61904 [6:13:52<11:41:31,  1.47s/it]
 54%|█████▎    | 33184/61904 [6:13:54<11:47:37,  1.48s/it]
 54%|█████▎    | 33185/61904 [6:13:55<12:18:28,  1.54s/it]
 54%|█████▎    | 33186/61904 [6:13:57<12:09:17,  1.52s/it]
 54%|█████▎    | 33187/61904 [6:13:58<11:45:05,  1.47s/it]
 54%|█████▎    | 33188/61904 [6:14:00<11:24:11,  1.43s/it]
 54%|█████▎    | 33189/61904 [6:14:01<11:13:13,  1.41s/it]
 54%|█████▎    | 33190/61904 [6:14:02<11:24:16,  1.43s/it]
 54%|█████▎    | 33191/61904 [6:14:04<11:34:45,  1.45s/it]
 54%|█████▎    | 33192/61904 [6:14:05<11:23:19,  1.43s/it]
 54%|█████▎    | 33193/61904 [6:14:07<11:29:22,  1.44s/it]
 54%|█████▎    | 33194/61904 [6:14:08<11:03:34,  1.39s/it]
 54%|█████▎    | 33195/61904 [6:14:09<10:57:31,  1.37s/it]
 54%|█████▎    | 33196/61904 [6:14:11<11:11:38,  1.40s/it]
 54%|█████▎    | 33197/61904 [6:14:12<11:02:47,  1.39s/it]
 54%|█████▎    | 33198/61904 [6:14:14<10:48:01,  1.35s/it]
 54%|█████▎    | 33199/61904 [6:14:15<10:53:41,  1.37s/it]
 54%|█████▎    | 33200/61904 [6:14:17<11:30:12,  1.44s/it]
                                                          
{'loss': 2.5419, 'learning_rate': 1.4651886425515361e-07, 'epoch': 8.58}
+
 54%|█████▎    | 33200/61904 [6:14:17<11:30:12,  1.44s/it]
 54%|█████▎    | 33201/61904 [6:14:18<11:25:06,  1.43s/it]
 54%|█████▎    | 33202/61904 [6:14:19<11:08:55,  1.40s/it]
 54%|█████▎    | 33203/61904 [6:14:21<11:25:04,  1.43s/it]
 54%|█████▎    | 33204/61904 [6:14:22<11:41:31,  1.47s/it]
 54%|█████▎    | 33205/61904 [6:14:24<11:26:32,  1.44s/it]
 54%|█████▎    | 33206/61904 [6:14:25<11:12:19,  1.41s/it]
 54%|█████▎    | 33207/61904 [6:14:26<11:02:22,  1.38s/it]
 54%|█████▎    | 33208/61904 [6:14:28<10:48:18,  1.36s/it]
 54%|█████▎    | 33209/61904 [6:14:29<10:38:45,  1.34s/it]
 54%|█████▎    | 33210/61904 [6:14:30<10:30:21,  1.32s/it]
 54%|█████▎    | 33211/61904 [6:14:32<10:37:59,  1.33s/it]
 54%|█████▎    | 33212/61904 [6:14:33<10:40:09,  1.34s/it]
 54%|█████▎    | 33213/61904 [6:14:34<10:53:19,  1.37s/it]
 54%|█████▎    | 33214/61904 [6:14:36<11:02:37,  1.39s/it]
 54%|█████▎    | 33215/61904 [6:14:37<10:59:11,  1.38s/it]
 54%|█████▎    | 33216/61904 [6:14:38<10:46:04,  1.35s/it]
 54%|█████▎    | 33217/61904 [6:14:40<10:52:26,  1.36s/it]
 54%|█████▎    | 33218/61904 [6:14:41<10:45:01,  1.35s/it]
 54%|█████▎    | 33219/61904 [6:14:42<10:37:56,  1.33s/it]
 54%|█████▎    | 33220/61904 [6:14:44<10:53:12,  1.37s/it]
                                                          
{'loss': 2.5811, 'learning_rate': 1.464864514456113e-07, 'epoch': 8.59}
+
 54%|█████▎    | 33220/61904 [6:14:44<10:53:12,  1.37s/it]
 54%|█████▎    | 33221/61904 [6:14:45<11:05:56,  1.39s/it]
 54%|█████▎    | 33222/61904 [6:14:47<10:59:51,  1.38s/it]
 54%|█████▎    | 33223/61904 [6:14:48<11:12:55,  1.41s/it]
 54%|█████▎    | 33224/61904 [6:14:50<11:15:43,  1.41s/it]
 54%|█████▎    | 33225/61904 [6:14:51<11:20:59,  1.42s/it]
 54%|█████▎    | 33226/61904 [6:14:52<11:16:37,  1.42s/it]
 54%|█████▎    | 33227/61904 [6:14:54<11:00:28,  1.38s/it]
 54%|█████▎    | 33228/61904 [6:14:55<11:02:31,  1.39s/it]
 54%|█████▎    | 33229/61904 [6:14:56<10:55:35,  1.37s/it]
 54%|█████▎    | 33230/61904 [6:14:58<10:40:09,  1.34s/it]
 54%|█████▎    | 33231/61904 [6:14:59<10:57:24,  1.38s/it]
 54%|█████▎    | 33232/61904 [6:15:01<11:19:10,  1.42s/it]
 54%|█████▎    | 33233/61904 [6:15:02<11:24:20,  1.43s/it]
 54%|█████▎    | 33234/61904 [6:15:04<11:37:37,  1.46s/it]
 54%|█████▎    | 33235/61904 [6:15:05<11:11:10,  1.40s/it]
 54%|█████▎    | 33236/61904 [6:15:07<11:34:26,  1.45s/it]
 54%|█████▎    | 33237/61904 [6:15:08<11:17:27,  1.42s/it]
 54%|█████▎    | 33238/61904 [6:15:09<11:26:00,  1.44s/it]
 54%|█████▎    | 33239/61904 [6:15:11<11:27:19,  1.44s/it]
 54%|█████▎    | 33240/61904 [6:15:12<11:13:56,  1.41s/it]
                                                          
{'loss': 2.5175, 'learning_rate': 1.4645403863606896e-07, 'epoch': 8.59}
+
 54%|█████▎    | 33240/61904 [6:15:12<11:13:56,  1.41s/it]
 54%|█████▎    | 33241/61904 [6:15:13<11:03:58,  1.39s/it]
 54%|█████▎    | 33242/61904 [6:15:15<10:44:04,  1.35s/it]
 54%|█████▎    | 33243/61904 [6:15:16<11:01:56,  1.39s/it]
 54%|█████▎    | 33244/61904 [6:15:17<10:38:19,  1.34s/it]
 54%|█████▎    | 33245/61904 [6:15:19<11:01:32,  1.38s/it]
 54%|█████▎    | 33246/61904 [6:15:20<11:15:53,  1.42s/it]
 54%|█████▎    | 33247/61904 [6:15:22<10:57:55,  1.38s/it]
 54%|█████▎    | 33248/61904 [6:15:23<10:52:15,  1.37s/it]
 54%|█████▎    | 33249/61904 [6:15:24<10:51:26,  1.36s/it]
 54%|█████▎    | 33250/61904 [6:15:26<10:48:12,  1.36s/it]
 54%|█████▎    | 33251/61904 [6:15:27<10:49:38,  1.36s/it]
 54%|█████▎    | 33252/61904 [6:15:29<11:10:31,  1.40s/it]
 54%|█████▎    | 33253/61904 [6:15:30<10:53:36,  1.37s/it]
 54%|█████▎    | 33254/61904 [6:15:31<10:55:30,  1.37s/it]
 54%|█████▎    | 33255/61904 [6:15:33<10:51:38,  1.36s/it]
 54%|█████▎    | 33256/61904 [6:15:34<10:43:35,  1.35s/it]
 54%|█████▎    | 33257/61904 [6:15:35<10:24:43,  1.31s/it]
 54%|█████▎    | 33258/61904 [6:15:37<10:44:43,  1.35s/it]
 54%|█████▎    | 33259/61904 [6:15:38<10:46:26,  1.35s/it]
 54%|█████▎    | 33260/61904 [6:15:39<10:51:47,  1.37s/it]
                                                          
{'loss': 2.553, 'learning_rate': 1.4642162582652663e-07, 'epoch': 8.6}
+
 54%|█████▎    | 33260/61904 [6:15:39<10:51:47,  1.37s/it]
 54%|█████▎    | 33261/61904 [6:15:41<11:01:49,  1.39s/it]
 54%|█████▎    | 33262/61904 [6:15:42<10:42:40,  1.35s/it]
 54%|█████▎    | 33263/61904 [6:15:43<10:33:39,  1.33s/it]
 54%|█████▎    | 33264/61904 [6:15:45<10:51:27,  1.36s/it]
 54%|█████▎    | 33265/61904 [6:15:46<10:45:50,  1.35s/it]
 54%|█████▎    | 33266/61904 [6:15:47<10:32:26,  1.33s/it]
 54%|█████▎    | 33267/61904 [6:15:49<10:31:38,  1.32s/it]
 54%|█████▎    | 33268/61904 [6:15:50<10:34:44,  1.33s/it]
 54%|█████▎    | 33269/61904 [6:15:51<10:36:49,  1.33s/it]
 54%|█████▎    | 33270/61904 [6:15:53<10:56:18,  1.38s/it]
 54%|█████▎    | 33271/61904 [6:15:54<10:46:26,  1.35s/it]
 54%|█████▎    | 33272/61904 [6:15:56<11:06:03,  1.40s/it]
 54%|█████▎    | 33273/61904 [6:15:57<11:14:45,  1.41s/it]
 54%|█████▍    | 33274/61904 [6:15:58<11:01:04,  1.39s/it]
 54%|█████▍    | 33275/61904 [6:16:00<11:08:26,  1.40s/it]
 54%|█████▍    | 33276/61904 [6:16:01<11:18:57,  1.42s/it]
 54%|█████▍    | 33277/61904 [6:16:03<11:19:52,  1.42s/it]
 54%|█████▍    | 33278/61904 [6:16:04<11:15:19,  1.42s/it]
 54%|█████▍    | 33279/61904 [6:16:06<11:43:03,  1.47s/it]
 54%|█████▍    | 33280/61904 [6:16:07<11:34:33,  1.46s/it]
                                                          
{'loss': 2.5869, 'learning_rate': 1.4638921301698431e-07, 'epoch': 8.6}
+
 54%|█████▍    | 33280/61904 [6:16:07<11:34:33,  1.46s/it]
 54%|█████▍    | 33281/61904 [6:16:08<11:06:51,  1.40s/it]
 54%|█████▍    | 33282/61904 [6:16:10<10:44:57,  1.35s/it]
 54%|█████▍    | 33283/61904 [6:16:11<10:29:04,  1.32s/it]
 54%|█████▍    | 33284/61904 [6:16:12<10:23:52,  1.31s/it]
 54%|█████▍    | 33285/61904 [6:16:13<10:16:45,  1.29s/it]
 54%|█████▍    | 33286/61904 [6:16:15<10:23:07,  1.31s/it]
 54%|█████▍    | 33287/61904 [6:16:16<10:51:53,  1.37s/it]
 54%|█████▍    | 33288/61904 [6:16:18<10:39:45,  1.34s/it]
 54%|█████▍    | 33289/61904 [6:16:19<11:08:41,  1.40s/it]
 54%|█████▍    | 33290/61904 [6:16:20<10:59:54,  1.38s/it]
 54%|█████▍    | 33291/61904 [6:16:22<11:09:01,  1.40s/it]
 54%|█████▍    | 33292/61904 [6:16:23<10:51:36,  1.37s/it]
 54%|█████▍    | 33293/61904 [6:16:25<10:50:40,  1.36s/it]
 54%|█████▍    | 33294/61904 [6:16:26<10:47:59,  1.36s/it]
 54%|█████▍    | 33295/61904 [6:16:27<10:56:09,  1.38s/it]
 54%|█████▍    | 33296/61904 [6:16:29<10:44:19,  1.35s/it]
 54%|█████▍    | 33297/61904 [6:16:30<10:50:47,  1.36s/it]
 54%|█████▍    | 33298/61904 [6:16:31<10:53:10,  1.37s/it]
 54%|█████▍    | 33299/61904 [6:16:33<10:59:25,  1.38s/it]
 54%|█████▍    | 33300/61904 [6:16:34<11:09:13,  1.40s/it]
                                                          
{'loss': 2.5046, 'learning_rate': 1.4635680020744198e-07, 'epoch': 8.61}
+
 54%|█████▍    | 33300/61904 [6:16:34<11:09:13,  1.40s/it]
 54%|█████▍    | 33301/61904 [6:16:36<11:07:25,  1.40s/it]
 54%|█████▍    | 33302/61904 [6:16:37<11:15:14,  1.42s/it]
 54%|█████▍    | 33303/61904 [6:16:38<11:00:56,  1.39s/it]
 54%|█████▍    | 33304/61904 [6:16:40<10:43:56,  1.35s/it]
 54%|█████▍    | 33305/61904 [6:16:41<10:50:38,  1.37s/it]
 54%|█████▍    | 33306/61904 [6:16:42<10:47:53,  1.36s/it]
 54%|█████▍    | 33307/61904 [6:16:44<10:32:15,  1.33s/it]
 54%|█████▍    | 33308/61904 [6:16:45<10:35:14,  1.33s/it]
 54%|█████▍    | 33309/61904 [6:16:46<10:40:08,  1.34s/it]
 54%|█████▍    | 33310/61904 [6:16:48<11:00:52,  1.39s/it]
 54%|█████▍    | 33311/61904 [6:16:49<11:11:31,  1.41s/it]
 54%|█████▍    | 33312/61904 [6:16:51<11:04:04,  1.39s/it]
 54%|█████▍    | 33313/61904 [6:16:52<10:58:26,  1.38s/it]
 54%|█████▍    | 33314/61904 [6:16:54<11:18:46,  1.42s/it]
 54%|█████▍    | 33315/61904 [6:16:55<11:02:43,  1.39s/it]
 54%|█████▍    | 33316/61904 [6:16:56<10:50:31,  1.37s/it]
 54%|█████▍    | 33317/61904 [6:16:58<10:55:34,  1.38s/it]
 54%|█████▍    | 33318/61904 [6:16:59<10:50:12,  1.36s/it]
 54%|█████▍    | 33319/61904 [6:17:00<11:13:09,  1.41s/it]
 54%|█████▍    | 33320/61904 [6:17:02<11:03:11,  1.39s/it]
                                                          
{'loss': 2.5389, 'learning_rate': 1.4632438739789964e-07, 'epoch': 8.61}
+
 54%|█████▍    | 33320/61904 [6:17:02<11:03:11,  1.39s/it]
 54%|█████▍    | 33321/61904 [6:17:03<11:09:57,  1.41s/it]
 54%|█████▍    | 33322/61904 [6:17:05<10:56:35,  1.38s/it]
 54%|█████▍    | 33323/61904 [6:17:06<10:52:38,  1.37s/it]
 54%|█████▍    | 33324/61904 [6:17:07<10:51:41,  1.37s/it]
 54%|█████▍    | 33325/61904 [6:17:09<11:02:19,  1.39s/it]
 54%|█████▍    | 33326/61904 [6:17:10<11:08:15,  1.40s/it]
 54%|█████▍    | 33327/61904 [6:17:11<10:46:53,  1.36s/it]
 54%|█████▍    | 33328/61904 [6:17:13<10:38:24,  1.34s/it]
 54%|█████▍    | 33329/61904 [6:17:14<10:29:39,  1.32s/it]
 54%|█████▍    | 33330/61904 [6:17:15<10:53:10,  1.37s/it]
 54%|█████▍    | 33331/61904 [6:17:17<11:00:14,  1.39s/it]
 54%|█████▍    | 33332/61904 [6:17:18<11:24:35,  1.44s/it]
 54%|█████▍    | 33333/61904 [6:17:20<10:58:07,  1.38s/it]
 54%|█████▍    | 33334/61904 [6:17:21<11:03:16,  1.39s/it]
 54%|█████▍    | 33335/61904 [6:17:22<10:46:21,  1.36s/it]
 54%|█████▍    | 33336/61904 [6:17:24<10:51:03,  1.37s/it]
 54%|█████▍    | 33337/61904 [6:17:25<11:04:11,  1.40s/it]
 54%|█████▍    | 33338/61904 [6:17:27<11:00:21,  1.39s/it]
 54%|█████▍    | 33339/61904 [6:17:28<11:11:11,  1.41s/it]
 54%|█████▍    | 33340/61904 [6:17:29<11:04:00,  1.39s/it]
                                                          
{'loss': 2.5497, 'learning_rate': 1.4629197458835733e-07, 'epoch': 8.62}
+
 54%|█████▍    | 33340/61904 [6:17:29<11:04:00,  1.39s/it]
 54%|█████▍    | 33341/61904 [6:17:31<11:24:28,  1.44s/it]
 54%|█████▍    | 33342/61904 [6:17:32<10:57:54,  1.38s/it]
 54%|█████▍    | 33343/61904 [6:17:34<11:22:44,  1.43s/it]
 54%|█████▍    | 33344/61904 [6:17:35<11:17:18,  1.42s/it]
 54%|█████▍    | 33345/61904 [6:17:36<10:49:26,  1.36s/it]
 54%|█████▍    | 33346/61904 [6:17:38<10:38:11,  1.34s/it]
 54%|█████▍    | 33347/61904 [6:17:39<10:32:13,  1.33s/it]
 54%|█████▍    | 33348/61904 [6:17:40<10:52:03,  1.37s/it]
 54%|█████▍    | 33349/61904 [6:17:42<11:14:47,  1.42s/it]
 54%|█████▍    | 33350/61904 [6:17:43<11:04:34,  1.40s/it]
 54%|█████▍    | 33351/61904 [6:17:45<11:11:25,  1.41s/it]
 54%|█████▍    | 33352/61904 [6:17:46<10:57:45,  1.38s/it]
 54%|█████▍    | 33353/61904 [6:17:48<11:16:14,  1.42s/it]
 54%|█████▍    | 33354/61904 [6:17:49<11:38:23,  1.47s/it]
 54%|█████▍    | 33355/61904 [6:17:51<11:16:23,  1.42s/it]
 54%|█████▍    | 33356/61904 [6:17:52<11:11:05,  1.41s/it]
 54%|█████▍    | 33357/61904 [6:17:53<11:21:52,  1.43s/it]
 54%|█████▍    | 33358/61904 [6:17:55<11:06:35,  1.40s/it]
 54%|█████▍    | 33359/61904 [6:17:56<11:05:56,  1.40s/it]
 54%|█████▍    | 33360/61904 [6:17:58<11:13:17,  1.42s/it]
                                                          
{'loss': 2.5344, 'learning_rate': 1.4625956177881496e-07, 'epoch': 8.62}
+
 54%|█████▍    | 33360/61904 [6:17:58<11:13:17,  1.42s/it]
 54%|█████▍    | 33361/61904 [6:17:59<11:16:01,  1.42s/it]
 54%|█████▍    | 33362/61904 [6:18:00<11:09:33,  1.41s/it]
 54%|█████▍    | 33363/61904 [6:18:02<11:10:11,  1.41s/it]
 54%|█████▍    | 33364/61904 [6:18:03<11:09:56,  1.41s/it]
 54%|█████▍    | 33365/61904 [6:18:05<11:09:34,  1.41s/it]
 54%|█████▍    | 33366/61904 [6:18:06<11:12:06,  1.41s/it]
 54%|█████▍    | 33367/61904 [6:18:07<10:59:43,  1.39s/it]
 54%|█████▍    | 33368/61904 [6:18:09<11:01:47,  1.39s/it]
 54%|█████▍    | 33369/61904 [6:18:10<11:06:21,  1.40s/it]
 54%|█████▍    | 33370/61904 [6:18:11<10:50:03,  1.37s/it]
 54%|█████▍    | 33371/61904 [6:18:13<10:53:41,  1.37s/it]
 54%|█████▍    | 33372/61904 [6:18:14<11:23:38,  1.44s/it]
 54%|█████▍    | 33373/61904 [6:18:16<11:21:46,  1.43s/it]
 54%|█████▍    | 33374/61904 [6:18:17<10:59:08,  1.39s/it]
 54%|█████▍    | 33375/61904 [6:18:19<11:10:48,  1.41s/it]
 54%|█████▍    | 33376/61904 [6:18:20<11:19:54,  1.43s/it]
 54%|█████▍    | 33377/61904 [6:18:22<11:21:23,  1.43s/it]
 54%|█████▍    | 33378/61904 [6:18:23<11:18:20,  1.43s/it]
 54%|█████▍    | 33379/61904 [6:18:24<11:07:54,  1.40s/it]
 54%|█████▍    | 33380/61904 [6:18:26<10:49:10,  1.37s/it]
                                                          
{'loss': 2.6, 'learning_rate': 1.4622714896927265e-07, 'epoch': 8.63}
+
 54%|█████▍    | 33380/61904 [6:18:26<10:49:10,  1.37s/it]
 54%|█████▍    | 33381/61904 [6:18:27<10:42:38,  1.35s/it]
 54%|█████▍    | 33382/61904 [6:18:28<11:09:58,  1.41s/it]
 54%|█████▍    | 33383/61904 [6:18:30<11:12:06,  1.41s/it]
 54%|█████▍    | 33384/61904 [6:18:31<11:17:43,  1.43s/it]
 54%|█████▍    | 33385/61904 [6:18:33<11:12:06,  1.41s/it]
 54%|█████▍    | 33386/61904 [6:18:34<10:54:29,  1.38s/it]
 54%|█████▍    | 33387/61904 [6:18:35<10:49:10,  1.37s/it]
 54%|█████▍    | 33388/61904 [6:18:37<10:52:48,  1.37s/it]
 54%|█████▍    | 33389/61904 [6:18:38<10:55:06,  1.38s/it]
 54%|█████▍    | 33390/61904 [6:18:39<10:47:03,  1.36s/it]
 54%|█████▍    | 33391/61904 [6:18:41<10:50:53,  1.37s/it]
 54%|█████▍    | 33392/61904 [6:18:42<10:44:08,  1.36s/it]
 54%|█████▍    | 33393/61904 [6:18:44<10:58:47,  1.39s/it]
 54%|█████▍    | 33394/61904 [6:18:45<10:39:38,  1.35s/it]
 54%|█████▍    | 33395/61904 [6:18:46<10:53:54,  1.38s/it]
 54%|█████▍    | 33396/61904 [6:18:48<10:41:11,  1.35s/it]
 54%|█████▍    | 33397/61904 [6:18:49<10:34:54,  1.34s/it]
 54%|█████▍    | 33398/61904 [6:18:50<10:41:39,  1.35s/it]
 54%|█████▍    | 33399/61904 [6:18:52<10:53:07,  1.37s/it]
 54%|█████▍    | 33400/61904 [6:18:53<11:31:20,  1.46s/it]
                                                          
{'loss': 2.5658, 'learning_rate': 1.461947361597303e-07, 'epoch': 8.63}
+
 54%|█████▍    | 33400/61904 [6:18:53<11:31:20,  1.46s/it]
 54%|█████▍    | 33401/61904 [6:18:55<11:10:58,  1.41s/it]
 54%|█████▍    | 33402/61904 [6:18:56<10:48:18,  1.36s/it]
 54%|█████▍    | 33403/61904 [6:18:57<10:33:27,  1.33s/it]
 54%|█████▍    | 33404/61904 [6:18:58<10:22:42,  1.31s/it]
 54%|█████▍    | 33405/61904 [6:19:00<10:20:18,  1.31s/it]
 54%|█████▍    | 33406/61904 [6:19:01<10:30:09,  1.33s/it]
 54%|█████▍    | 33407/61904 [6:19:02<10:35:57,  1.34s/it]
 54%|█████▍    | 33408/61904 [6:19:04<10:41:54,  1.35s/it]
 54%|█████▍    | 33409/61904 [6:19:05<10:37:15,  1.34s/it]
 54%|█████▍    | 33410/61904 [6:19:07<10:55:55,  1.38s/it]
 54%|█████▍    | 33411/61904 [6:19:08<11:02:07,  1.39s/it]
 54%|█████▍    | 33412/61904 [6:19:09<11:00:38,  1.39s/it]
 54%|█████▍    | 33413/61904 [6:19:11<10:56:28,  1.38s/it]
 54%|█████▍    | 33414/61904 [6:19:12<11:20:22,  1.43s/it]
 54%|█████▍    | 33415/61904 [6:19:14<11:31:58,  1.46s/it]
 54%|█████▍    | 33416/61904 [6:19:15<11:13:33,  1.42s/it]
 54%|█████▍    | 33417/61904 [6:19:17<11:02:56,  1.40s/it]
 54%|█████▍    | 33418/61904 [6:19:18<10:59:34,  1.39s/it]
 54%|█████▍    | 33419/61904 [6:19:19<10:53:28,  1.38s/it]
 54%|█████▍    | 33420/61904 [6:19:21<11:16:46,  1.43s/it]
                                                          
{'loss': 2.539, 'learning_rate': 1.4616232335018797e-07, 'epoch': 8.64}
+
 54%|█████▍    | 33420/61904 [6:19:21<11:16:46,  1.43s/it]
 54%|█████▍    | 33421/61904 [6:19:22<11:04:10,  1.40s/it]
 54%|█████▍    | 33422/61904 [6:19:24<11:01:30,  1.39s/it]
 54%|█████▍    | 33423/61904 [6:19:25<10:48:18,  1.37s/it]
 54%|█████▍    | 33424/61904 [6:19:26<10:51:24,  1.37s/it]
 54%|█████▍    | 33425/61904 [6:19:28<10:43:44,  1.36s/it]
 54%|█████▍    | 33426/61904 [6:19:29<10:55:33,  1.38s/it]
 54%|█████▍    | 33427/61904 [6:19:30<10:42:17,  1.35s/it]
 54%|█████▍    | 33428/61904 [6:19:32<10:42:13,  1.35s/it]
 54%|█████▍    | 33429/61904 [6:19:33<10:38:02,  1.34s/it]
 54%|█████▍    | 33430/61904 [6:19:34<10:28:08,  1.32s/it]
 54%|█████▍    | 33431/61904 [6:19:36<10:42:39,  1.35s/it]
 54%|█████▍    | 33432/61904 [6:19:37<10:39:46,  1.35s/it]
 54%|█████▍    | 33433/61904 [6:19:38<10:56:35,  1.38s/it]
 54%|█████▍    | 33434/61904 [6:19:40<10:51:53,  1.37s/it]
 54%|█████▍    | 33435/61904 [6:19:41<10:47:14,  1.36s/it]
 54%|█████▍    | 33436/61904 [6:19:42<10:41:02,  1.35s/it]
 54%|█████▍    | 33437/61904 [6:19:44<11:02:55,  1.40s/it]
 54%|█████▍    | 33438/61904 [6:19:45<10:43:36,  1.36s/it]
 54%|█████▍    | 33439/61904 [6:19:47<10:46:48,  1.36s/it]
 54%|█████▍    | 33440/61904 [6:19:48<10:53:29,  1.38s/it]
                                                          
{'loss': 2.5898, 'learning_rate': 1.4612991054064566e-07, 'epoch': 8.64}
+
 54%|█████▍    | 33440/61904 [6:19:48<10:53:29,  1.38s/it]
 54%|█████▍    | 33441/61904 [6:19:49<10:59:17,  1.39s/it]
 54%|█████▍    | 33442/61904 [6:19:51<10:46:46,  1.36s/it]
 54%|█████▍    | 33443/61904 [6:19:52<10:47:55,  1.37s/it]
 54%|█████▍    | 33444/61904 [6:19:54<10:59:27,  1.39s/it]
 54%|█████▍    | 33445/61904 [6:19:55<10:57:57,  1.39s/it]
 54%|█████▍    | 33446/61904 [6:19:57<11:25:24,  1.45s/it]
 54%|█████▍    | 33447/61904 [6:19:58<11:13:47,  1.42s/it]
 54%|█████▍    | 33448/61904 [6:19:59<11:13:38,  1.42s/it]
 54%|█████▍    | 33449/61904 [6:20:01<11:00:06,  1.39s/it]
 54%|█████▍    | 33450/61904 [6:20:02<11:01:01,  1.39s/it]
 54%|█████▍    | 33451/61904 [6:20:03<11:06:20,  1.41s/it]
 54%|█████▍    | 33452/61904 [6:20:05<10:51:45,  1.37s/it]
 54%|█████▍    | 33453/61904 [6:20:06<11:14:49,  1.42s/it]
 54%|█████▍    | 33454/61904 [6:20:08<11:03:01,  1.40s/it]
 54%|█████▍    | 33455/61904 [6:20:09<10:48:50,  1.37s/it]
 54%|█████▍    | 33456/61904 [6:20:10<10:58:09,  1.39s/it]
 54%|█████▍    | 33457/61904 [6:20:12<10:54:19,  1.38s/it]
 54%|█████▍    | 33458/61904 [6:20:13<10:56:49,  1.39s/it]
 54%|█████▍    | 33459/61904 [6:20:15<11:03:03,  1.40s/it]
 54%|█████▍    | 33460/61904 [6:20:16<10:49:49,  1.37s/it]
                                                          
{'loss': 2.4808, 'learning_rate': 1.4609749773110332e-07, 'epoch': 8.65}
+
 54%|█████▍    | 33460/61904 [6:20:16<10:49:49,  1.37s/it]
 54%|█████▍    | 33461/61904 [6:20:17<10:49:03,  1.37s/it]
 54%|█████▍    | 33462/61904 [6:20:19<10:47:53,  1.37s/it]
 54%|█████▍    | 33463/61904 [6:20:20<10:51:33,  1.37s/it]
 54%|█████▍    | 33464/61904 [6:20:21<11:09:19,  1.41s/it]
 54%|█████▍    | 33465/61904 [6:20:23<11:24:17,  1.44s/it]
 54%|█████▍    | 33466/61904 [6:20:24<10:59:38,  1.39s/it]
 54%|█████▍    | 33467/61904 [6:20:25<10:36:25,  1.34s/it]
 54%|█████▍    | 33468/61904 [6:20:27<10:45:21,  1.36s/it]
 54%|█████▍    | 33469/61904 [6:20:28<10:41:37,  1.35s/it]
 54%|█████▍    | 33470/61904 [6:20:30<11:04:11,  1.40s/it]
 54%|█████▍    | 33471/61904 [6:20:31<10:46:47,  1.36s/it]
 54%|█████▍    | 33472/61904 [6:20:32<10:35:24,  1.34s/it]
 54%|█████▍    | 33473/61904 [6:20:34<11:07:12,  1.41s/it]
 54%|█████▍    | 33474/61904 [6:20:35<11:07:29,  1.41s/it]
 54%|█████▍    | 33475/61904 [6:20:37<11:08:45,  1.41s/it]
 54%|█████▍    | 33476/61904 [6:20:38<10:46:54,  1.37s/it]
 54%|█████▍    | 33477/61904 [6:20:39<11:05:02,  1.40s/it]
 54%|█████▍    | 33478/61904 [6:20:41<10:46:18,  1.36s/it]
 54%|█████▍    | 33479/61904 [6:20:42<10:45:11,  1.36s/it]
 54%|█████▍    | 33480/61904 [6:20:44<11:25:57,  1.45s/it]
                                                          
{'loss': 2.4885, 'learning_rate': 1.4606508492156099e-07, 'epoch': 8.65}
+
 54%|█████▍    | 33480/61904 [6:20:44<11:25:57,  1.45s/it]
 54%|█████▍    | 33481/61904 [6:20:45<10:49:39,  1.37s/it]
 54%|█████▍    | 33482/61904 [6:20:46<10:54:27,  1.38s/it]
 54%|█████▍    | 33483/61904 [6:20:48<11:09:15,  1.41s/it]
 54%|█████▍    | 33484/61904 [6:20:49<10:57:29,  1.39s/it]
 54%|█████▍    | 33485/61904 [6:20:50<10:45:36,  1.36s/it]
 54%|█████▍    | 33486/61904 [6:20:52<10:29:23,  1.33s/it]
 54%|█████▍    | 33487/61904 [6:20:53<10:28:07,  1.33s/it]
 54%|█████▍    | 33488/61904 [6:20:55<11:01:18,  1.40s/it]
 54%|█████▍    | 33489/61904 [6:20:56<11:03:33,  1.40s/it]
 54%|█████▍    | 33490/61904 [6:20:57<11:01:38,  1.40s/it]
 54%|█████▍    | 33491/61904 [6:20:59<10:54:30,  1.38s/it]
 54%|█████▍    | 33492/61904 [6:21:00<10:54:06,  1.38s/it]
 54%|█████▍    | 33493/61904 [6:21:01<10:42:24,  1.36s/it]
 54%|█████▍    | 33494/61904 [6:21:03<10:36:54,  1.35s/it]
 54%|█████▍    | 33495/61904 [6:21:04<10:45:42,  1.36s/it]
 54%|█████▍    | 33496/61904 [6:21:06<11:56:01,  1.51s/it]
 54%|█████���    | 33497/61904 [6:21:07<11:43:08,  1.49s/it]
 54%|█████▍    | 33498/61904 [6:21:09<11:25:20,  1.45s/it]
 54%|█████▍    | 33499/61904 [6:21:10<11:39:27,  1.48s/it]
 54%|█████▍    | 33500/61904 [6:21:12<11:03:45,  1.40s/it]
                                                          
{'loss': 2.5437, 'learning_rate': 1.4603267211201867e-07, 'epoch': 8.66}
+
 54%|█████▍    | 33500/61904 [6:21:12<11:03:45,  1.40s/it]
 54%|█████▍    | 33501/61904 [6:21:13<11:17:44,  1.43s/it]
 54%|█████▍    | 33502/61904 [6:21:15<11:31:42,  1.46s/it]
 54%|█████▍    | 33503/61904 [6:21:16<11:15:46,  1.43s/it]
 54%|█████▍    | 33504/61904 [6:21:17<11:08:27,  1.41s/it]
 54%|█████▍    | 33505/61904 [6:21:19<11:12:20,  1.42s/it]
 54%|█████▍    | 33506/61904 [6:21:20<11:02:33,  1.40s/it]
 54%|█████▍    | 33507/61904 [6:21:22<11:12:19,  1.42s/it]
 54%|█████▍    | 33508/61904 [6:21:23<11:19:07,  1.43s/it]
 54%|█████▍    | 33509/61904 [6:21:24<10:51:36,  1.38s/it]
 54%|█████▍    | 33510/61904 [6:21:26<10:59:53,  1.39s/it]
 54%|█████▍    | 33511/61904 [6:21:27<10:44:59,  1.36s/it]
 54%|█████▍    | 33512/61904 [6:21:28<11:04:16,  1.40s/it]
 54%|█████▍    | 33513/61904 [6:21:30<10:58:11,  1.39s/it]
 54%|█████▍    | 33514/61904 [6:21:31<10:59:31,  1.39s/it]
 54%|█████▍    | 33515/61904 [6:21:33<10:57:59,  1.39s/it]
 54%|█████▍    | 33516/61904 [6:21:34<10:52:27,  1.38s/it]
 54%|█████▍    | 33517/61904 [6:21:35<10:38:41,  1.35s/it]
 54%|█████▍    | 33518/61904 [6:21:37<10:43:21,  1.36s/it]
 54%|█████▍    | 33519/61904 [6:21:38<10:56:22,  1.39s/it]
 54%|█████▍    | 33520/61904 [6:21:40<11:14:26,  1.43s/it]
                                                          
{'loss': 2.5715, 'learning_rate': 1.4600025930247634e-07, 'epoch': 8.66}
+
 54%|█████▍    | 33520/61904 [6:21:40<11:14:26,  1.43s/it]
 54%|█████▍    | 33521/61904 [6:21:41<10:59:31,  1.39s/it]
 54%|█████▍    | 33522/61904 [6:21:42<10:57:41,  1.39s/it]
 54%|█████▍    | 33523/61904 [6:21:44<10:46:02,  1.37s/it]
 54%|█████▍    | 33524/61904 [6:21:45<10:30:33,  1.33s/it]
 54%|█████▍    | 33525/61904 [6:21:46<10:42:33,  1.36s/it]
 54%|█████▍    | 33526/61904 [6:21:48<10:46:34,  1.37s/it]
 54%|█████▍    | 33527/61904 [6:21:49<10:36:30,  1.35s/it]
 54%|█████▍    | 33528/61904 [6:21:50<10:34:37,  1.34s/it]
 54%|█████▍    | 33529/61904 [6:21:52<10:46:51,  1.37s/it]
 54%|█████▍    | 33530/61904 [6:21:53<10:48:01,  1.37s/it]
 54%|█████▍    | 33531/61904 [6:21:55<10:59:44,  1.40s/it]
 54%|█████▍    | 33532/61904 [6:21:56<10:41:32,  1.36s/it]
 54%|█████▍    | 33533/61904 [6:21:57<10:51:44,  1.38s/it]
 54%|█████▍    | 33534/61904 [6:21:59<10:42:39,  1.36s/it]
 54%|█████▍    | 33535/61904 [6:22:00<10:41:22,  1.36s/it]
 54%|█████▍    | 33536/61904 [6:22:01<10:40:10,  1.35s/it]
 54%|█████▍    | 33537/61904 [6:22:03<10:36:30,  1.35s/it]
 54%|█████▍    | 33538/61904 [6:22:04<10:30:21,  1.33s/it]
 54%|█████▍    | 33539/61904 [6:22:05<10:33:28,  1.34s/it]
 54%|█████▍    | 33540/61904 [6:22:07<10:25:30,  1.32s/it]
                                                          
{'loss': 2.5828, 'learning_rate': 1.45967846492934e-07, 'epoch': 8.67}
+
 54%|█████▍    | 33540/61904 [6:22:07<10:25:30,  1.32s/it]
 54%|█████▍    | 33541/61904 [6:22:08<10:35:44,  1.34s/it]
 54%|█████▍    | 33542/61904 [6:22:09<10:43:20,  1.36s/it]
 54%|█████▍    | 33543/61904 [6:22:11<10:42:11,  1.36s/it]
 54%|█████▍    | 33544/61904 [6:22:12<10:50:53,  1.38s/it]
 54%|█████▍    | 33545/61904 [6:22:14<11:02:46,  1.40s/it]
 54%|█████▍    | 33546/61904 [6:22:15<10:49:22,  1.37s/it]
 54%|█████▍    | 33547/61904 [6:22:16<10:30:42,  1.33s/it]
 54%|█████▍    | 33548/61904 [6:22:18<11:01:58,  1.40s/it]
 54%|█████▍    | 33549/61904 [6:22:19<10:46:13,  1.37s/it]
 54%|█████▍    | 33550/61904 [6:22:20<10:45:57,  1.37s/it]
 54%|█████▍    | 33551/61904 [6:22:22<11:13:31,  1.43s/it]
 54%|█████▍    | 33552/61904 [6:22:23<10:52:54,  1.38s/it]
 54%|█████▍    | 33553/61904 [6:22:25<10:56:05,  1.39s/it]
 54%|█████▍    | 33554/61904 [6:22:26<11:09:41,  1.42s/it]
 54%|█████▍    | 33555/61904 [6:22:28<11:14:11,  1.43s/it]
 54%|█████▍    | 33556/61904 [6:22:29<11:17:21,  1.43s/it]
 54%|█████▍    | 33557/61904 [6:22:30<11:20:07,  1.44s/it]
 54%|█████▍    | 33558/61904 [6:22:32<11:28:21,  1.46s/it]
 54%|█████▍    | 33559/61904 [6:22:33<11:32:31,  1.47s/it]
 54%|█████▍    | 33560/61904 [6:22:35<10:59:35,  1.40s/it]
                                                          
{'loss': 2.4961, 'learning_rate': 1.4593543368339169e-07, 'epoch': 8.67}
+
 54%|█████▍    | 33560/61904 [6:22:35<10:59:35,  1.40s/it]
 54%|█████▍    | 33561/61904 [6:22:36<10:54:18,  1.39s/it]
 54%|█████▍    | 33562/61904 [6:22:37<11:05:17,  1.41s/it]
 54%|█████▍    | 33563/61904 [6:22:39<10:57:26,  1.39s/it]
 54%|█████▍    | 33564/61904 [6:22:40<10:43:46,  1.36s/it]
 54%|█████▍    | 33565/61904 [6:22:42<10:57:39,  1.39s/it]
 54%|█████▍    | 33566/61904 [6:22:43<10:57:05,  1.39s/it]
 54%|█████▍    | 33567/61904 [6:22:44<10:51:39,  1.38s/it]
 54%|█████▍    | 33568/61904 [6:22:46<10:30:56,  1.34s/it]
 54%|█████▍    | 33569/61904 [6:22:47<10:32:01,  1.34s/it]
 54%|█████▍    | 33570/61904 [6:22:48<10:25:38,  1.32s/it]
 54%|█████▍    | 33571/61904 [6:22:49<10:20:39,  1.31s/it]
 54%|█████▍    | 33572/61904 [6:22:51<10:09:55,  1.29s/it]
 54%|█████▍    | 33573/61904 [6:22:52<10:06:26,  1.28s/it]
 54%|█████▍    | 33574/61904 [6:22:53<10:18:41,  1.31s/it]
 54%|█████▍    | 33575/61904 [6:22:55<10:32:34,  1.34s/it]
 54%|█████▍    | 33576/61904 [6:22:56<10:47:24,  1.37s/it]
 54%|█████▍    | 33577/61904 [6:22:58<11:01:07,  1.40s/it]
 54%|█████▍    | 33578/61904 [6:22:59<10:56:12,  1.39s/it]
 54%|█████▍    | 33579/61904 [6:23:01<11:11:08,  1.42s/it]
 54%|█████▍    | 33580/61904 [6:23:02<10:52:12,  1.38s/it]
                                                          
{'loss': 2.5212, 'learning_rate': 1.4590302087384932e-07, 'epoch': 8.68}
+
 54%|█████▍    | 33580/61904 [6:23:02<10:52:12,  1.38s/it]
 54%|█████▍    | 33581/61904 [6:23:03<11:01:07,  1.40s/it]
 54%|█████▍    | 33582/61904 [6:23:05<10:40:05,  1.36s/it]
 54%|█████▍    | 33583/61904 [6:23:06<10:44:20,  1.37s/it]
 54%|█████▍    | 33584/61904 [6:23:07<10:54:14,  1.39s/it]
 54%|█████▍    | 33585/61904 [6:23:09<10:44:05,  1.36s/it]
 54%|█████▍    | 33586/61904 [6:23:10<11:14:22,  1.43s/it]
 54%|█████▍    | 33587/61904 [6:23:12<11:03:01,  1.40s/it]
 54%|█████▍    | 33588/61904 [6:23:13<11:04:29,  1.41s/it]
 54%|█████▍    | 33589/61904 [6:23:14<10:47:10,  1.37s/it]
 54%|█████▍    | 33590/61904 [6:23:16<10:51:00,  1.38s/it]
 54%|█████▍    | 33591/61904 [6:23:17<10:48:30,  1.37s/it]
 54%|█████▍    | 33592/61904 [6:23:18<10:58:20,  1.40s/it]
 54%|█████▍    | 33593/61904 [6:23:20<10:49:45,  1.38s/it]
 54%|█████▍    | 33594/61904 [6:23:21<10:51:32,  1.38s/it]
 54%|█████▍    | 33595/61904 [6:23:23<10:43:28,  1.36s/it]
 54%|█████▍    | 33596/61904 [6:23:24<10:51:45,  1.38s/it]
 54%|█████▍    | 33597/61904 [6:23:25<11:04:48,  1.41s/it]
 54%|█████▍    | 33598/61904 [6:23:27<11:00:39,  1.40s/it]
 54%|█████▍    | 33599/61904 [6:23:28<10:40:37,  1.36s/it]
 54%|█████▍    | 33600/61904 [6:23:30<11:08:00,  1.42s/it]
                                                          
{'loss': 2.5321, 'learning_rate': 1.45870608064307e-07, 'epoch': 8.68}
+
 54%|█████▍    | 33600/61904 [6:23:30<11:08:00,  1.42s/it]
 54%|█████▍    | 33601/61904 [6:23:31<11:04:41,  1.41s/it]
 54%|█████▍    | 33602/61904 [6:23:33<11:17:34,  1.44s/it]
 54%|█████▍    | 33603/61904 [6:23:34<11:06:57,  1.41s/it]
 54%|█████▍    | 33604/61904 [6:23:35<10:59:44,  1.40s/it]
 54%|█████▍    | 33605/61904 [6:23:37<10:50:57,  1.38s/it]
 54%|█████▍    | 33606/61904 [6:23:38<10:59:44,  1.40s/it]
 54%|█████▍    | 33607/61904 [6:23:39<10:51:41,  1.38s/it]
 54%|█████▍    | 33608/61904 [6:23:41<10:42:38,  1.36s/it]
 54%|█████▍    | 33609/61904 [6:23:42<10:28:47,  1.33s/it]
 54%|█████▍    | 33610/61904 [6:23:43<10:35:31,  1.35s/it]
 54%|█████▍    | 33611/61904 [6:23:45<10:18:55,  1.31s/it]
 54%|█████▍    | 33612/61904 [6:23:46<10:37:45,  1.35s/it]
 54%|█████▍    | 33613/61904 [6:23:47<10:23:05,  1.32s/it]
 54%|█████▍    | 33614/61904 [6:23:49<10:19:49,  1.31s/it]
 54%|█████▍    | 33615/61904 [6:23:50<10:21:44,  1.32s/it]
 54%|█████▍    | 33616/61904 [6:23:52<11:13:02,  1.43s/it]
 54%|█████▍    | 33617/61904 [6:23:53<11:07:21,  1.42s/it]
 54%|█████▍    | 33618/61904 [6:23:54<11:06:58,  1.41s/it]
 54%|█████▍    | 33619/61904 [6:23:56<11:07:32,  1.42s/it]
 54%|█████▍    | 33620/61904 [6:23:57<11:08:53,  1.42s/it]
                                                          
{'loss': 2.5146, 'learning_rate': 1.4583819525476467e-07, 'epoch': 8.69}
+
 54%|█████▍    | 33620/61904 [6:23:57<11:08:53,  1.42s/it]
 54%|█████▍    | 33621/61904 [6:23:59<11:10:11,  1.42s/it]
 54%|█████▍    | 33622/61904 [6:24:00<10:58:50,  1.40s/it]
 54%|█████▍    | 33623/61904 [6:24:01<10:56:11,  1.39s/it]
 54%|█████▍    | 33624/61904 [6:24:03<10:51:55,  1.38s/it]
 54%|█████▍    | 33625/61904 [6:24:04<11:12:29,  1.43s/it]
 54%|█████▍    | 33626/61904 [6:24:06<11:11:25,  1.42s/it]
 54%|█████▍    | 33627/61904 [6:24:07<11:05:56,  1.41s/it]
 54%|█████▍    | 33628/61904 [6:24:08<10:45:09,  1.37s/it]
 54%|█████▍    | 33629/61904 [6:24:10<10:34:33,  1.35s/it]
 54%|█████▍    | 33630/61904 [6:24:11<10:29:06,  1.34s/it]
 54%|█████▍    | 33631/61904 [6:24:12<10:50:18,  1.38s/it]
 54%|█████▍    | 33632/61904 [6:24:14<10:45:52,  1.37s/it]
 54%|█████▍    | 33633/61904 [6:24:15<11:05:53,  1.41s/it]
 54%|█████▍    | 33634/61904 [6:24:17<10:50:54,  1.38s/it]
 54%|█████▍    | 33635/61904 [6:24:18<10:56:59,  1.39s/it]
 54%|█████▍    | 33636/61904 [6:24:19<10:46:51,  1.37s/it]
 54%|█████▍    | 33637/61904 [6:24:21<10:47:40,  1.37s/it]
 54%|█████▍    | 33638/61904 [6:24:22<10:39:24,  1.36s/it]
 54%|█████▍    | 33639/61904 [6:24:23<10:39:49,  1.36s/it]
 54%|█████▍    | 33640/61904 [6:24:25<10:51:30,  1.38s/it]
                                                          
{'loss': 2.5531, 'learning_rate': 1.4580578244522233e-07, 'epoch': 8.69}
+
 54%|█████▍    | 33640/61904 [6:24:25<10:51:30,  1.38s/it]
 54%|█████▍    | 33641/61904 [6:24:26<10:58:03,  1.40s/it]
 54%|█████▍    | 33642/61904 [6:24:28<10:41:06,  1.36s/it]
 54%|█████▍    | 33643/61904 [6:24:29<10:32:15,  1.34s/it]
 54%|█████▍    | 33644/61904 [6:24:30<10:36:28,  1.35s/it]
 54%|█████▍    | 33645/61904 [6:24:32<10:53:29,  1.39s/it]
 54%|█████▍    | 33646/61904 [6:24:33<10:49:56,  1.38s/it]
 54%|█████▍    | 33647/61904 [6:24:34<10:34:47,  1.35s/it]
 54%|█████▍    | 33648/61904 [6:24:36<10:56:19,  1.39s/it]
 54%|█████▍    | 33649/61904 [6:24:37<10:50:26,  1.38s/it]
 54%|█████▍    | 33650/61904 [6:24:39<10:57:46,  1.40s/it]
 54%|█████▍    | 33651/61904 [6:24:40<10:59:40,  1.40s/it]
 54%|█████▍    | 33652/61904 [6:24:42<11:32:19,  1.47s/it]
 54%|█████▍    | 33653/61904 [6:24:43<11:20:11,  1.44s/it]
 54%|█████▍    | 33654/61904 [6:24:44<11:09:43,  1.42s/it]
 54%|█████▍    | 33655/61904 [6:24:46<10:46:30,  1.37s/it]
 54%|█████▍    | 33656/61904 [6:24:47<11:03:44,  1.41s/it]
 54%|█████▍    | 33657/61904 [6:24:49<10:58:12,  1.40s/it]
 54%|█████▍    | 33658/61904 [6:24:50<10:52:53,  1.39s/it]
 54%|█████▍    | 33659/61904 [6:24:51<10:44:04,  1.37s/it]
 54%|█████▍    | 33660/61904 [6:24:53<11:01:33,  1.41s/it]
                                                          
{'loss': 2.4989, 'learning_rate': 1.4577336963568002e-07, 'epoch': 8.7}
+
 54%|█████▍    | 33660/61904 [6:24:53<11:01:33,  1.41s/it]
 54%|█████▍    | 33661/61904 [6:24:54<11:06:04,  1.42s/it]
 54%|█████▍    | 33662/61904 [6:24:56<11:35:40,  1.48s/it]
 54%|█████▍    | 33663/61904 [6:24:57<11:03:39,  1.41s/it]
 54%|█████▍    | 33664/61904 [6:24:58<10:45:28,  1.37s/it]
 54%|█████▍    | 33665/61904 [6:25:00<11:01:15,  1.40s/it]
 54%|█████▍    | 33666/61904 [6:25:01<10:52:55,  1.39s/it]
 54%|█████▍    | 33667/61904 [6:25:03<11:12:38,  1.43s/it]
 54%|█████▍    | 33668/61904 [6:25:04<11:09:08,  1.42s/it]
 54%|█████▍    | 33669/61904 [6:25:05<11:00:04,  1.40s/it]
 54%|█████▍    | 33670/61904 [6:25:07<11:39:08,  1.49s/it]
 54%|█████▍    | 33671/61904 [6:25:09<11:40:21,  1.49s/it]
 54%|█████▍    | 33672/61904 [6:25:10<11:08:00,  1.42s/it]
 54%|█████▍    | 33673/61904 [6:25:11<10:59:39,  1.40s/it]
 54%|█████▍    | 33674/61904 [6:25:13<11:02:44,  1.41s/it]
 54%|█████▍    | 33675/61904 [6:25:14<10:40:35,  1.36s/it]
 54%|█████▍    | 33676/61904 [6:25:15<10:37:37,  1.36s/it]
 54%|█████▍    | 33677/61904 [6:25:17<10:27:52,  1.33s/it]
 54%|█████▍    | 33678/61904 [6:25:18<10:22:49,  1.32s/it]
 54%|█████▍    | 33679/61904 [6:25:19<10:41:37,  1.36s/it]
 54%|█████▍    | 33680/61904 [6:25:21<10:32:26,  1.34s/it]
                                                          
{'loss': 2.5502, 'learning_rate': 1.4574095682613768e-07, 'epoch': 8.7}
+
 54%|█████▍    | 33680/61904 [6:25:21<10:32:26,  1.34s/it]
 54%|█████▍    | 33681/61904 [6:25:22<10:26:50,  1.33s/it]
 54%|█████▍    | 33682/61904 [6:25:23<10:28:09,  1.34s/it]
 54%|█████▍    | 33683/61904 [6:25:24<10:19:53,  1.32s/it]
 54%|█████▍    | 33684/61904 [6:25:26<10:46:43,  1.38s/it]
 54%|█████▍    | 33685/61904 [6:25:27<11:00:18,  1.40s/it]
 54%|█████▍    | 33686/61904 [6:25:29<10:52:15,  1.39s/it]
 54%|█████▍    | 33687/61904 [6:25:30<11:00:51,  1.41s/it]
 54%|█████▍    | 33688/61904 [6:25:32<10:54:08,  1.39s/it]
 54%|█████▍    | 33689/61904 [6:25:33<10:58:46,  1.40s/it]
 54%|█████▍    | 33690/61904 [6:25:34<11:01:22,  1.41s/it]
 54%|█████▍    | 33691/61904 [6:25:36<10:41:55,  1.37s/it]
 54%|█████▍    | 33692/61904 [6:25:37<10:44:11,  1.37s/it]
 54%|█████▍    | 33693/61904 [6:25:38<10:41:16,  1.36s/it]
 54%|█████▍    | 33694/61904 [6:25:40<10:36:37,  1.35s/it]
 54%|█████▍    | 33695/61904 [6:25:41<10:54:49,  1.39s/it]
 54%|█████▍    | 33696/61904 [6:25:43<11:10:23,  1.43s/it]
 54%|█████▍    | 33697/61904 [6:25:44<10:49:36,  1.38s/it]
 54%|█████▍    | 33698/61904 [6:25:45<10:45:10,  1.37s/it]
 54%|█████▍    | 33699/61904 [6:25:47<10:40:06,  1.36s/it]
 54%|█████▍    | 33700/61904 [6:25:48<11:11:01,  1.43s/it]
                                                          
{'loss': 2.4926, 'learning_rate': 1.4570854401659535e-07, 'epoch': 8.71}
+
 54%|█████▍    | 33700/61904 [6:25:48<11:11:01,  1.43s/it]
 54%|█████▍    | 33701/61904 [6:25:50<11:09:55,  1.43s/it]
 54%|█████▍    | 33702/61904 [6:25:51<11:00:46,  1.41s/it]
 54%|█████▍    | 33703/61904 [6:25:53<11:06:35,  1.42s/it]
 54%|█████▍    | 33704/61904 [6:25:54<11:04:47,  1.41s/it]
 54%|█████▍    | 33705/61904 [6:25:55<10:32:27,  1.35s/it]
 54%|█████▍    | 33706/61904 [6:25:57<10:42:33,  1.37s/it]
 54%|█████▍    | 33707/61904 [6:25:58<10:42:37,  1.37s/it]
 54%|█████▍    | 33708/61904 [6:25:59<10:45:10,  1.37s/it]
 54%|█████▍    | 33709/61904 [6:26:01<11:04:06,  1.41s/it]
 54%|█████▍    | 33710/61904 [6:26:02<11:00:05,  1.40s/it]
 54%|█████▍    | 33711/61904 [6:26:04<11:03:32,  1.41s/it]
 54%|█████▍    | 33712/61904 [6:26:05<10:50:48,  1.39s/it]
 54%|█████▍    | 33713/61904 [6:26:06<10:36:34,  1.35s/it]
 54%|█████▍    | 33714/61904 [6:26:08<11:10:09,  1.43s/it]
 54%|█████▍    | 33715/61904 [6:26:09<11:04:28,  1.41s/it]
 54%|█████▍    | 33716/61904 [6:26:11<10:52:44,  1.39s/it]
 54%|█████▍    | 33717/61904 [6:26:12<10:37:38,  1.36s/it]
 54%|█████▍    | 33718/61904 [6:26:13<10:48:18,  1.38s/it]
 54%|█████▍    | 33719/61904 [6:26:15<10:56:55,  1.40s/it]
 54%|█████▍    | 33720/61904 [6:26:16<11:05:46,  1.42s/it]
                                                          
{'loss': 2.5462, 'learning_rate': 1.4567613120705303e-07, 'epoch': 8.71}
+
 54%|█████▍    | 33720/61904 [6:26:16<11:05:46,  1.42s/it]
 54%|█████▍    | 33721/61904 [6:26:18<11:13:03,  1.43s/it]
 54%|█████▍    | 33722/61904 [6:26:19<10:46:18,  1.38s/it]
 54%|█████▍    | 33723/61904 [6:26:21<11:31:26,  1.47s/it]
 54%|█████▍    | 33724/61904 [6:26:22<11:10:07,  1.43s/it]
 54%|█████▍    | 33725/61904 [6:26:23<11:02:49,  1.41s/it]
 54%|█████▍    | 33726/61904 [6:26:25<10:42:04,  1.37s/it]
 54%|█████▍    | 33727/61904 [6:26:26<10:37:31,  1.36s/it]
 54%|█████▍    | 33728/61904 [6:26:27<10:39:55,  1.36s/it]
 54%|█████▍    | 33729/61904 [6:26:29<10:39:24,  1.36s/it]
 54%|█████▍    | 33730/61904 [6:26:30<10:48:40,  1.38s/it]
 54%|█████▍    | 33731/61904 [6:26:31<10:34:33,  1.35s/it]
 54%|█████▍    | 33732/61904 [6:26:33<11:08:27,  1.42s/it]
 54%|█████▍    | 33733/61904 [6:26:34<10:59:16,  1.40s/it]
 54%|█████▍    | 33734/61904 [6:26:36<10:50:21,  1.39s/it]
 54%|█████▍    | 33735/61904 [6:26:37<10:22:20,  1.33s/it]
 54%|█████▍    | 33736/61904 [6:26:38<10:20:02,  1.32s/it]
 54%|█████▍    | 33737/61904 [6:26:40<10:32:48,  1.35s/it]
 55%|█████▍    | 33738/61904 [6:26:41<10:27:30,  1.34s/it]
 55%|█████▍    | 33739/61904 [6:26:42<10:37:26,  1.36s/it]
 55%|█████▍    | 33740/61904 [6:26:44<10:38:02,  1.36s/it]
                                                          
{'loss': 2.5373, 'learning_rate': 1.4564371839751067e-07, 'epoch': 8.72}
+
 55%|█████▍    | 33740/61904 [6:26:44<10:38:02,  1.36s/it]
 55%|█████▍    | 33741/61904 [6:26:45<10:30:18,  1.34s/it]
 55%|█████▍    | 33742/61904 [6:26:46<10:28:10,  1.34s/it]
 55%|█████▍    | 33743/61904 [6:26:48<10:33:21,  1.35s/it]
 55%|█████▍    | 33744/61904 [6:26:49<10:25:46,  1.33s/it]
 55%|█████▍    | 33745/61904 [6:26:50<10:27:08,  1.34s/it]
 55%|█████▍    | 33746/61904 [6:26:52<10:37:13,  1.36s/it]
 55%|█████▍    | 33747/61904 [6:26:53<10:45:13,  1.37s/it]
 55%|█████���    | 33748/61904 [6:26:54<10:41:39,  1.37s/it]
 55%|█████▍    | 33749/61904 [6:26:56<10:57:10,  1.40s/it]
 55%|█████▍    | 33750/61904 [6:26:57<11:12:19,  1.43s/it]
 55%|█████▍    | 33751/61904 [6:26:59<10:55:01,  1.40s/it]
 55%|█████▍    | 33752/61904 [6:27:00<11:04:32,  1.42s/it]
 55%|█████▍    | 33753/61904 [6:27:02<11:24:08,  1.46s/it]
 55%|█████▍    | 33754/61904 [6:27:03<10:49:40,  1.38s/it]
 55%|█████▍    | 33755/61904 [6:27:04<10:42:56,  1.37s/it]
 55%|█████▍    | 33756/61904 [6:27:06<10:45:07,  1.38s/it]
 55%|█████▍    | 33757/61904 [6:27:07<10:34:34,  1.35s/it]
 55%|█████▍    | 33758/61904 [6:27:08<10:32:07,  1.35s/it]
 55%|█████▍    | 33759/61904 [6:27:10<10:15:47,  1.31s/it]
 55%|█████▍    | 33760/61904 [6:27:11<10:05:39,  1.29s/it]
                                                          
{'loss': 2.5745, 'learning_rate': 1.4561130558796836e-07, 'epoch': 8.73}
+
 55%|█████▍    | 33760/61904 [6:27:11<10:05:39,  1.29s/it]
 55%|█████▍    | 33761/61904 [6:27:12<10:16:59,  1.32s/it]
 55%|█████▍    | 33762/61904 [6:27:14<10:47:05,  1.38s/it]
 55%|█████▍    | 33763/61904 [6:27:15<10:49:07,  1.38s/it]
 55%|█████▍    | 33764/61904 [6:27:17<10:57:16,  1.40s/it]
 55%|█████▍    | 33765/61904 [6:27:18<10:55:06,  1.40s/it]
 55%|█████▍    | 33766/61904 [6:27:19<10:58:10,  1.40s/it]
 55%|█████▍    | 33767/61904 [6:27:21<10:56:59,  1.40s/it]
 55%|█████▍    | 33768/61904 [6:27:22<11:11:15,  1.43s/it]
 55%|█████▍    | 33769/61904 [6:27:24<11:20:20,  1.45s/it]
 55%|█████▍    | 33770/61904 [6:27:25<11:10:36,  1.43s/it]
 55%|█████▍    | 33771/61904 [6:27:27<11:08:20,  1.43s/it]
 55%|█████▍    | 33772/61904 [6:27:28<11:05:08,  1.42s/it]
 55%|█████▍    | 33773/61904 [6:27:29<10:40:33,  1.37s/it]
 55%|█████▍    | 33774/61904 [6:27:31<10:47:50,  1.38s/it]
 55%|█████▍    | 33775/61904 [6:27:32<10:34:36,  1.35s/it]
 55%|█████▍    | 33776/61904 [6:27:33<10:45:34,  1.38s/it]
 55%|█████▍    | 33777/61904 [6:27:35<10:38:57,  1.36s/it]
 55%|█████▍    | 33778/61904 [6:27:36<10:33:20,  1.35s/it]
 55%|█████▍    | 33779/61904 [6:27:37<10:23:52,  1.33s/it]
 55%|█████▍    | 33780/61904 [6:27:39<10:32:28,  1.35s/it]
                                                          
{'loss': 2.5468, 'learning_rate': 1.4557889277842605e-07, 'epoch': 8.73}
+
 55%|█████▍    | 33780/61904 [6:27:39<10:32:28,  1.35s/it]
 55%|█████▍    | 33781/61904 [6:27:40<10:38:40,  1.36s/it]
 55%|█████▍    | 33782/61904 [6:27:41<10:43:09,  1.37s/it]
 55%|█████▍    | 33783/61904 [6:27:43<10:45:55,  1.38s/it]
 55%|█████▍    | 33784/61904 [6:27:44<10:51:01,  1.39s/it]
 55%|█████▍    | 33785/61904 [6:27:46<10:43:56,  1.37s/it]
 55%|█████▍    | 33786/61904 [6:27:47<10:42:05,  1.37s/it]
 55%|█████▍    | 33787/61904 [6:27:48<11:00:08,  1.41s/it]
 55%|█████▍    | 33788/61904 [6:27:50<11:14:05,  1.44s/it]
 55%|█████▍    | 33789/61904 [6:27:51<11:04:42,  1.42s/it]
 55%|█████▍    | 33790/61904 [6:27:53<11:05:39,  1.42s/it]
 55%|█████▍    | 33791/61904 [6:27:54<10:53:17,  1.39s/it]
 55%|█████▍    | 33792/61904 [6:27:55<10:48:45,  1.38s/it]
 55%|█████▍    | 33793/61904 [6:27:57<10:46:41,  1.38s/it]
 55%|█████▍    | 33794/61904 [6:27:58<10:33:25,  1.35s/it]
 55%|█████▍    | 33795/61904 [6:27:59<10:37:26,  1.36s/it]
 55%|█████▍    | 33796/61904 [6:28:01<10:18:31,  1.32s/it]
 55%|█████▍    | 33797/61904 [6:28:02<10:10:54,  1.30s/it]
 55%|█████▍    | 33798/61904 [6:28:03<10:35:13,  1.36s/it]
 55%|█████▍    | 33799/61904 [6:28:05<10:36:55,  1.36s/it]
 55%|█████▍    | 33800/61904 [6:28:06<10:31:21,  1.35s/it]
                                                          
{'loss': 2.5654, 'learning_rate': 1.4554647996888368e-07, 'epoch': 8.74}
+
 55%|█████▍    | 33800/61904 [6:28:06<10:31:21,  1.35s/it]
 55%|█████▍    | 33801/61904 [6:28:08<10:47:20,  1.38s/it]
 55%|█████▍    | 33802/61904 [6:28:09<10:36:11,  1.36s/it]
 55%|█████▍    | 33803/61904 [6:28:10<10:42:00,  1.37s/it]
 55%|█████▍    | 33804/61904 [6:28:12<11:00:29,  1.41s/it]
 55%|█████▍    | 33805/61904 [6:28:13<10:49:24,  1.39s/it]
 55%|█████▍    | 33806/61904 [6:28:15<10:56:01,  1.40s/it]
 55%|█████▍    | 33807/61904 [6:28:16<10:52:02,  1.39s/it]
 55%|█████▍    | 33808/61904 [6:28:17<11:11:51,  1.43s/it]
 55%|█████▍    | 33809/61904 [6:28:19<10:59:53,  1.41s/it]
 55%|█████▍    | 33810/61904 [6:28:20<10:54:58,  1.40s/it]
 55%|█████▍    | 33811/61904 [6:28:22<11:07:40,  1.43s/it]
 55%|█████▍    | 33812/61904 [6:28:23<10:43:45,  1.37s/it]
 55%|█████▍    | 33813/61904 [6:28:24<10:33:28,  1.35s/it]
 55%|█████▍    | 33814/61904 [6:28:26<10:22:35,  1.33s/it]
 55%|█████▍    | 33815/61904 [6:28:27<11:01:09,  1.41s/it]
 55%|█████▍    | 33816/61904 [6:28:29<11:01:45,  1.41s/it]
 55%|█████▍    | 33817/61904 [6:28:30<10:49:34,  1.39s/it]
 55%|█████▍    | 33818/61904 [6:28:31<10:48:48,  1.39s/it]
 55%|█████▍    | 33819/61904 [6:28:33<10:34:41,  1.36s/it]
 55%|█████▍    | 33820/61904 [6:28:34<10:20:32,  1.33s/it]
                                                          
{'loss': 2.5433, 'learning_rate': 1.4551406715934137e-07, 'epoch': 8.74}
+
 55%|█████▍    | 33820/61904 [6:28:34<10:20:32,  1.33s/it]
 55%|█████▍    | 33821/61904 [6:28:35<10:23:38,  1.33s/it]
 55%|█████▍    | 33822/61904 [6:28:37<10:34:03,  1.35s/it]
 55%|█████▍    | 33823/61904 [6:28:38<10:24:08,  1.33s/it]
 55%|█████▍    | 33824/61904 [6:28:39<10:59:03,  1.41s/it]
 55%|█████▍    | 33825/61904 [6:28:41<10:56:40,  1.40s/it]
 55%|█████▍    | 33826/61904 [6:28:42<10:47:08,  1.38s/it]
 55%|█████▍    | 33827/61904 [6:28:44<10:49:05,  1.39s/it]
 55%|█████▍    | 33828/61904 [6:28:45<11:07:37,  1.43s/it]
 55%|█████▍    | 33829/61904 [6:28:46<10:43:48,  1.38s/it]
 55%|█████▍    | 33830/61904 [6:28:48<10:34:44,  1.36s/it]
 55%|█████▍    | 33831/61904 [6:28:49<10:37:28,  1.36s/it]
 55%|█████▍    | 33832/61904 [6:28:50<10:32:34,  1.35s/it]
 55%|█████▍    | 33833/61904 [6:28:52<10:54:15,  1.40s/it]
 55%|█████▍    | 33834/61904 [6:28:53<10:51:36,  1.39s/it]
 55%|█████▍    | 33835/61904 [6:28:54<10:28:17,  1.34s/it]
 55%|█████▍    | 33836/61904 [6:28:56<10:42:32,  1.37s/it]
 55%|█████▍    | 33837/61904 [6:28:57<10:41:17,  1.37s/it]
 55%|█████▍    | 33838/61904 [6:28:59<10:40:20,  1.37s/it]
 55%|█████▍    | 33839/61904 [6:29:00<10:40:30,  1.37s/it]
 55%|█████▍    | 33840/61904 [6:29:01<10:48:19,  1.39s/it]
                                                          
{'loss': 2.5865, 'learning_rate': 1.4548165434979903e-07, 'epoch': 8.75}
+
 55%|█████▍    | 33840/61904 [6:29:01<10:48:19,  1.39s/it]
 55%|█████▍    | 33841/61904 [6:29:03<10:45:23,  1.38s/it]
 55%|█████▍    | 33842/61904 [6:29:04<10:38:01,  1.36s/it]
 55%|█████▍    | 33843/61904 [6:29:05<10:39:09,  1.37s/it]
 55%|█████▍    | 33844/61904 [6:29:07<10:30:03,  1.35s/it]
 55%|█████▍    | 33845/61904 [6:29:08<10:24:20,  1.34s/it]
 55%|█████▍    | 33846/61904 [6:29:09<10:30:02,  1.35s/it]
 55%|█████▍    | 33847/61904 [6:29:11<11:21:49,  1.46s/it]
 55%|█████▍    | 33848/61904 [6:29:13<11:34:21,  1.48s/it]
 55%|█████▍    | 33849/61904 [6:29:14<11:11:11,  1.44s/it]
 55%|█████▍    | 33850/61904 [6:29:15<11:09:47,  1.43s/it]
 55%|█████▍    | 33851/61904 [6:29:17<10:41:11,  1.37s/it]
 55%|█████▍    | 33852/61904 [6:29:18<10:44:25,  1.38s/it]
 55%|█████▍    | 33853/61904 [6:29:19<10:48:28,  1.39s/it]
 55%|█████▍    | 33854/61904 [6:29:21<10:52:45,  1.40s/it]
 55%|█████▍    | 33855/61904 [6:29:22<10:53:57,  1.40s/it]
 55%|█████▍    | 33856/61904 [6:29:24<10:53:56,  1.40s/it]
 55%|█████▍    | 33857/61904 [6:29:25<10:31:45,  1.35s/it]
 55%|█████▍    | 33858/61904 [6:29:26<10:30:07,  1.35s/it]
 55%|█████▍    | 33859/61904 [6:29:28<10:16:50,  1.32s/it]
 55%|█████▍    | 33860/61904 [6:29:29<10:22:20,  1.33s/it]
                                                          
{'loss': 2.5631, 'learning_rate': 1.454492415402567e-07, 'epoch': 8.75}
+
 55%|█████▍    | 33860/61904 [6:29:29<10:22:20,  1.33s/it]
 55%|█████▍    | 33861/61904 [6:29:30<10:31:44,  1.35s/it]
 55%|█████▍    | 33862/61904 [6:29:32<10:31:45,  1.35s/it]
 55%|█████▍    | 33863/61904 [6:29:33<10:37:27,  1.36s/it]
 55%|█████▍    | 33864/61904 [6:29:34<10:26:45,  1.34s/it]
 55%|█████▍    | 33865/61904 [6:29:36<10:49:32,  1.39s/it]
 55%|█████▍    | 33866/61904 [6:29:37<10:29:40,  1.35s/it]
 55%|█████▍    | 33867/61904 [6:29:38<10:34:23,  1.36s/it]
 55%|█████▍    | 33868/61904 [6:29:40<10:38:56,  1.37s/it]
 55%|█████▍    | 33869/61904 [6:29:41<10:42:54,  1.38s/it]
 55%|█████▍    | 33870/61904 [6:29:43<10:47:05,  1.38s/it]
 55%|█████▍    | 33871/61904 [6:29:44<11:06:36,  1.43s/it]
 55%|█████▍    | 33872/61904 [6:29:46<10:59:42,  1.41s/it]
 55%|█████▍    | 33873/61904 [6:29:47<11:05:50,  1.43s/it]
 55%|█████▍    | 33874/61904 [6:29:48<10:57:47,  1.41s/it]
 55%|███���█▍    | 33875/61904 [6:29:50<11:10:48,  1.44s/it]
 55%|█████▍    | 33876/61904 [6:29:51<11:17:05,  1.45s/it]
 55%|█████▍    | 33877/61904 [6:29:53<11:16:27,  1.45s/it]
 55%|█████▍    | 33878/61904 [6:29:54<10:57:54,  1.41s/it]
 55%|█████▍    | 33879/61904 [6:29:56<10:57:54,  1.41s/it]
 55%|█████▍    | 33880/61904 [6:29:57<10:43:13,  1.38s/it]
                                                          
{'loss': 2.5857, 'learning_rate': 1.4541682873071438e-07, 'epoch': 8.76}
+
 55%|█████▍    | 33880/61904 [6:29:57<10:43:13,  1.38s/it]
 55%|█████▍    | 33881/61904 [6:29:58<10:41:38,  1.37s/it]
 55%|█████▍    | 33882/61904 [6:30:00<10:34:09,  1.36s/it]
 55%|█████▍    | 33883/61904 [6:30:01<11:09:28,  1.43s/it]
 55%|█████▍    | 33884/61904 [6:30:03<11:29:52,  1.48s/it]
 55%|█████▍    | 33885/61904 [6:30:04<11:38:56,  1.50s/it]
 55%|█████▍    | 33886/61904 [6:30:06<11:39:06,  1.50s/it]
 55%|█████▍    | 33887/61904 [6:30:07<11:21:22,  1.46s/it]
 55%|█████▍    | 33888/61904 [6:30:09<11:30:32,  1.48s/it]
 55%|█████▍    | 33889/61904 [6:30:10<11:26:11,  1.47s/it]
 55%|█████▍    | 33890/61904 [6:30:11<11:16:57,  1.45s/it]
 55%|█████▍    | 33891/61904 [6:30:13<11:31:16,  1.48s/it]
 55%|█████▍    | 33892/61904 [6:30:14<11:05:58,  1.43s/it]
 55%|█████▍    | 33893/61904 [6:30:16<10:48:38,  1.39s/it]
 55%|█████▍    | 33894/61904 [6:30:17<10:49:31,  1.39s/it]
 55%|█████▍    | 33895/61904 [6:30:18<10:56:16,  1.41s/it]
 55%|█████▍    | 33896/61904 [6:30:20<10:48:41,  1.39s/it]
 55%|█████▍    | 33897/61904 [6:30:21<10:48:12,  1.39s/it]
 55%|█████▍    | 33898/61904 [6:30:23<10:44:02,  1.38s/it]
 55%|█████▍    | 33899/61904 [6:30:24<10:39:53,  1.37s/it]
 55%|█████▍    | 33900/61904 [6:30:25<10:48:32,  1.39s/it]
                                                          
{'loss': 2.5168, 'learning_rate': 1.4538441592117204e-07, 'epoch': 8.76}
+
 55%|█████▍    | 33900/61904 [6:30:25<10:48:32,  1.39s/it]
 55%|█████▍    | 33901/61904 [6:30:27<10:40:27,  1.37s/it]
 55%|█████▍    | 33902/61904 [6:30:28<11:00:01,  1.41s/it]
 55%|█████▍    | 33903/61904 [6:30:30<10:42:49,  1.38s/it]
 55%|█████▍    | 33904/61904 [6:30:31<10:56:44,  1.41s/it]
 55%|█████▍    | 33905/61904 [6:30:32<10:57:23,  1.41s/it]
 55%|█████▍    | 33906/61904 [6:30:34<10:41:25,  1.37s/it]
 55%|█████▍    | 33907/61904 [6:30:35<10:42:43,  1.38s/it]
 55%|█████▍    | 33908/61904 [6:30:37<11:00:20,  1.42s/it]
 55%|█████▍    | 33909/61904 [6:30:38<10:49:34,  1.39s/it]
 55%|█████▍    | 33910/61904 [6:30:39<10:56:30,  1.41s/it]
 55%|█████▍    | 33911/61904 [6:30:41<10:48:09,  1.39s/it]
 55%|█████▍    | 33912/61904 [6:30:42<10:40:34,  1.37s/it]
 55%|█████▍    | 33913/61904 [6:30:44<10:54:11,  1.40s/it]
 55%|█████▍    | 33914/61904 [6:30:45<10:57:39,  1.41s/it]
 55%|█████▍    | 33915/61904 [6:30:46<10:49:39,  1.39s/it]
 55%|█████▍    | 33916/61904 [6:30:48<10:41:02,  1.37s/it]
 55%|█████▍    | 33917/61904 [6:30:49<11:16:39,  1.45s/it]
 55%|█████▍    | 33918/61904 [6:30:51<11:44:01,  1.51s/it]
 55%|█████▍    | 33919/61904 [6:30:52<11:15:47,  1.45s/it]
 55%|█████▍    | 33920/61904 [6:30:54<11:16:42,  1.45s/it]
                                                          
{'loss': 2.5316, 'learning_rate': 1.453520031116297e-07, 'epoch': 8.77}
+
 55%|█████▍    | 33920/61904 [6:30:54<11:16:42,  1.45s/it]
 55%|█████▍    | 33921/61904 [6:30:55<11:24:05,  1.47s/it]
 55%|█████▍    | 33922/61904 [6:30:57<11:13:53,  1.44s/it]
 55%|█████▍    | 33923/61904 [6:30:58<11:53:18,  1.53s/it]
 55%|█████▍    | 33924/61904 [6:31:00<11:39:54,  1.50s/it]
 55%|█████▍    | 33925/61904 [6:31:01<11:18:09,  1.45s/it]
 55%|█████▍    | 33926/61904 [6:31:03<11:27:17,  1.47s/it]
 55%|█████▍    | 33927/61904 [6:31:04<11:15:44,  1.45s/it]
 55%|█████▍    | 33928/61904 [6:31:05<11:07:45,  1.43s/it]
 55%|█████▍    | 33929/61904 [6:31:07<11:37:28,  1.50s/it]
 55%|█████▍    | 33930/61904 [6:31:09<11:37:37,  1.50s/it]
 55%|█████▍    | 33931/61904 [6:31:10<11:22:36,  1.46s/it]
 55%|█████▍    | 33932/61904 [6:31:11<11:00:43,  1.42s/it]
 55%|█████▍    | 33933/61904 [6:31:13<11:08:11,  1.43s/it]
 55%|█████▍    | 33934/61904 [6:31:14<10:55:24,  1.41s/it]
 55%|█████▍    | 33935/61904 [6:31:16<11:23:00,  1.47s/it]
 55%|█████▍    | 33936/61904 [6:31:17<10:57:54,  1.41s/it]
 55%|█████▍    | 33937/61904 [6:31:18<11:02:21,  1.42s/it]
 55%|█████▍    | 33938/61904 [6:31:20<11:08:15,  1.43s/it]
 55%|█████▍    | 33939/61904 [6:31:21<11:09:13,  1.44s/it]
 55%|█████▍    | 33940/61904 [6:31:23<10:49:01,  1.39s/it]
                                                          
{'loss': 2.5464, 'learning_rate': 1.453195903020874e-07, 'epoch': 8.77}
+
 55%|█████▍    | 33940/61904 [6:31:23<10:49:01,  1.39s/it]
 55%|█████▍    | 33941/61904 [6:31:24<10:39:08,  1.37s/it]
 55%|█████▍    | 33942/61904 [6:31:25<10:45:42,  1.39s/it]
 55%|█████▍    | 33943/61904 [6:31:27<10:34:26,  1.36s/it]
 55%|█████▍    | 33944/61904 [6:31:28<10:59:52,  1.42s/it]
 55%|█████▍    | 33945/61904 [6:31:30<11:02:23,  1.42s/it]
 55%|█████▍    | 33946/61904 [6:31:31<11:19:30,  1.46s/it]
 55%|█████▍    | 33947/61904 [6:31:32<10:55:20,  1.41s/it]
 55%|█████▍    | 33948/61904 [6:31:34<11:17:31,  1.45s/it]
 55%|█████▍    | 33949/61904 [6:31:35<11:10:02,  1.44s/it]
 55%|█████▍    | 33950/61904 [6:31:37<11:00:44,  1.42s/it]
 55%|█████▍    | 33951/61904 [6:31:38<11:26:52,  1.47s/it]
 55%|█████▍    | 33952/61904 [6:31:40<11:10:44,  1.44s/it]
 55%|█████▍    | 33953/61904 [6:31:41<10:51:03,  1.40s/it]
 55%|█████▍    | 33954/61904 [6:31:42<10:31:56,  1.36s/it]
 55%|█████▍    | 33955/61904 [6:31:44<10:42:54,  1.38s/it]
 55%|█████▍    | 33956/61904 [6:31:45<10:38:51,  1.37s/it]
 55%|█████▍    | 33957/61904 [6:31:46<10:41:13,  1.38s/it]
 55%|█████▍    | 33958/61904 [6:31:48<11:05:06,  1.43s/it]
 55%|█████▍    | 33959/61904 [6:31:49<10:43:46,  1.38s/it]
 55%|█████▍    | 33960/61904 [6:31:50<10:22:30,  1.34s/it]
                                                          
{'loss': 2.5508, 'learning_rate': 1.4528717749254503e-07, 'epoch': 8.78}
+
 55%|█████▍    | 33960/61904 [6:31:50<10:22:30,  1.34s/it]
 55%|█████▍    | 33961/61904 [6:31:52<10:19:57,  1.33s/it]
 55%|█████▍    | 33962/61904 [6:31:53<10:12:28,  1.32s/it]
 55%|█████▍    | 33963/61904 [6:31:55<10:36:05,  1.37s/it]
 55%|█████▍    | 33964/61904 [6:31:56<10:35:07,  1.36s/it]
 55%|█████▍    | 33965/61904 [6:31:57<10:08:03,  1.31s/it]
 55%|█████▍    | 33966/61904 [6:31:59<10:42:08,  1.38s/it]
 55%|█████▍    | 33967/61904 [6:32:00<10:51:22,  1.40s/it]
 55%|█████▍    | 33968/61904 [6:32:02<11:06:28,  1.43s/it]
 55%|█████▍    | 33969/61904 [6:32:03<11:32:05,  1.49s/it]
 55%|█████▍    | 33970/61904 [6:32:05<11:16:48,  1.45s/it]
 55%|█████▍    | 33971/61904 [6:32:06<11:22:57,  1.47s/it]
 55%|█████▍    | 33972/61904 [6:32:08<11:22:31,  1.47s/it]
 55%|█████▍    | 33973/61904 [6:32:09<10:58:54,  1.42s/it]
 55%|█████▍    | 33974/61904 [6:32:10<11:12:48,  1.45s/it]
 55%|█████▍    | 33975/61904 [6:32:12<11:32:31,  1.49s/it]
 55%|█████▍    | 33976/61904 [6:32:13<11:06:18,  1.43s/it]
 55%|█████▍    | 33977/61904 [6:32:15<11:09:42,  1.44s/it]
 55%|█████▍    | 33978/61904 [6:32:16<10:48:11,  1.39s/it]
 55%|█████▍    | 33979/61904 [6:32:17<10:46:36,  1.39s/it]
 55%|█████▍    | 33980/61904 [6:32:19<10:41:38,  1.38s/it]
                                                          
{'loss': 2.5082, 'learning_rate': 1.4525476468300272e-07, 'epoch': 8.78}
+
 55%|█████▍    | 33980/61904 [6:32:19<10:41:38,  1.38s/it]
 55%|█████▍    | 33981/61904 [6:32:20<10:36:46,  1.37s/it]
 55%|█████▍    | 33982/61904 [6:32:22<10:48:34,  1.39s/it]
 55%|█████▍    | 33983/61904 [6:32:23<10:36:42,  1.37s/it]
 55%|█████▍    | 33984/61904 [6:32:24<10:44:36,  1.39s/it]
 55%|█████▍    | 33985/61904 [6:32:26<10:33:44,  1.36s/it]
 55%|█████▍    | 33986/61904 [6:32:27<10:32:43,  1.36s/it]
 55%|█████▍    | 33987/61904 [6:32:28<10:28:48,  1.35s/it]
 55%|█████▍    | 33988/61904 [6:32:30<10:22:16,  1.34s/it]
 55%|█████▍    | 33989/61904 [6:32:31<10:24:12,  1.34s/it]
 55%|█████▍    | 33990/61904 [6:32:32<10:31:39,  1.36s/it]
 55%|█████▍    | 33991/61904 [6:32:34<10:36:59,  1.37s/it]
 55%|█████▍    | 33992/61904 [6:32:35<10:37:38,  1.37s/it]
 55%|█████▍    | 33993/61904 [6:32:36<10:41:31,  1.38s/it]
 55%|█████▍    | 33994/61904 [6:32:38<10:28:57,  1.35s/it]
 55%|█████▍    | 33995/61904 [6:32:39<10:42:15,  1.38s/it]
 55%|█████▍    | 33996/61904 [6:32:41<11:11:41,  1.44s/it]
 55%|█████▍    | 33997/61904 [6:32:42<11:26:25,  1.48s/it]
 55%|█████▍    | 33998/61904 [6:32:44<11:19:01,  1.46s/it]
 55%|█████▍    | 33999/61904 [6:32:45<11:03:09,  1.43s/it]
 55%|█████▍    | 34000/61904 [6:32:47<11:17:46,  1.46s/it]
                                                          
{'loss': 2.502, 'learning_rate': 1.4522235187346038e-07, 'epoch': 8.79}
+
 55%|█████▍    | 34000/61904 [6:32:47<11:17:46,  1.46s/it]
 55%|█████▍    | 34001/61904 [6:32:48<10:57:24,  1.41s/it]
 55%|█████▍    | 34002/61904 [6:32:49<10:51:54,  1.40s/it]
 55%|█████▍    | 34003/61904 [6:32:51<10:56:35,  1.41s/it]
 55%|█████▍    | 34004/61904 [6:32:52<11:05:21,  1.43s/it]
 55%|█████▍    | 34005/61904 [6:32:54<10:39:20,  1.37s/it]
 55%|█████▍    | 34006/61904 [6:32:55<10:40:50,  1.38s/it]
 55%|█████▍    | 34007/61904 [6:32:56<10:34:11,  1.36s/it]
 55%|█████▍    | 34008/61904 [6:32:58<10:31:25,  1.36s/it]
 55%|█████▍    | 34009/61904 [6:32:59<10:26:14,  1.35s/it]
 55%|█████▍    | 34010/61904 [6:33:00<10:24:22,  1.34s/it]
 55%|█████▍    | 34011/61904 [6:33:02<10:36:09,  1.37s/it]
 55%|█████▍    | 34012/61904 [6:33:03<10:48:36,  1.40s/it]
 55%|█████▍    | 34013/61904 [6:33:04<10:43:53,  1.39s/it]
 55%|█████▍    | 34014/61904 [6:33:06<10:36:19,  1.37s/it]
 55%|█████▍    | 34015/61904 [6:33:07<10:21:16,  1.34s/it]
 55%|█████▍    | 34016/61904 [6:33:08<10:27:58,  1.35s/it]
 55%|█████▍    | 34017/61904 [6:33:10<10:26:07,  1.35s/it]
 55%|█████▍    | 34018/61904 [6:33:11<10:48:21,  1.40s/it]
 55%|█████▍    | 34019/61904 [6:33:13<10:49:34,  1.40s/it]
 55%|█████▍    | 34020/61904 [6:33:14<10:40:41,  1.38s/it]
                                                          
{'loss': 2.5586, 'learning_rate': 1.4518993906391804e-07, 'epoch': 8.79}
+
 55%|█████▍    | 34020/61904 [6:33:14<10:40:41,  1.38s/it]
 55%|█████▍    | 34021/61904 [6:33:15<10:35:34,  1.37s/it]
 55%|█████▍    | 34022/61904 [6:33:17<10:23:44,  1.34s/it]
 55%|█████▍    | 34023/61904 [6:33:18<10:43:04,  1.38s/it]
 55%|█████▍    | 34024/61904 [6:33:20<10:42:26,  1.38s/it]
 55%|█████▍    | 34025/61904 [6:33:21<10:52:56,  1.41s/it]
 55%|█████▍    | 34026/61904 [6:33:22<10:44:39,  1.39s/it]
 55%|█████▍    | 34027/61904 [6:33:24<10:37:01,  1.37s/it]
 55%|█████▍    | 34028/61904 [6:33:25<10:34:46,  1.37s/it]
 55%|█████▍    | 34029/61904 [6:33:26<10:39:37,  1.38s/it]
 55%|█████▍    | 34030/61904 [6:33:28<10:29:40,  1.36s/it]
 55%|█████▍    | 34031/61904 [6:33:29<10:16:43,  1.33s/it]
 55%|█████▍    | 34032/61904 [6:33:30<10:21:24,  1.34s/it]
 55%|█████▍    | 34033/61904 [6:33:32<10:43:33,  1.39s/it]
 55%|█████▍    | 34034/61904 [6:33:33<10:37:01,  1.37s/it]
 55%|█████▍    | 34035/61904 [6:33:35<10:44:02,  1.39s/it]
 55%|█████▍    | 34036/61904 [6:33:36<10:48:50,  1.40s/it]
 55%|█████▍    | 34037/61904 [6:33:37<10:30:10,  1.36s/it]
 55%|█████▍    | 34038/61904 [6:33:39<10:34:05,  1.37s/it]
 55%|█████▍    | 34039/61904 [6:33:40<10:40:56,  1.38s/it]
 55%|█████▍    | 34040/61904 [6:33:42<11:01:00,  1.42s/it]
                                                          
{'loss': 2.5555, 'learning_rate': 1.4515752625437573e-07, 'epoch': 8.8}
+
 55%|█████▍    | 34040/61904 [6:33:42<11:01:00,  1.42s/it]
 55%|█████▍    | 34041/61904 [6:33:43<10:39:14,  1.38s/it]
 55%|█████▍    | 34042/61904 [6:33:44<10:35:01,  1.37s/it]
 55%|█████▍    | 34043/61904 [6:33:46<10:52:15,  1.40s/it]
 55%|█████▍    | 34044/61904 [6:33:47<10:36:51,  1.37s/it]
 55%|█████▍    | 34045/61904 [6:33:48<10:27:53,  1.35s/it]
 55%|█████▍    | 34046/61904 [6:33:50<10:22:53,  1.34s/it]
 55%|█████▍    | 34047/61904 [6:33:51<10:14:51,  1.32s/it]
 55%|█████▌    | 34048/61904 [6:33:52<10:49:58,  1.40s/it]
 55%|█████▌    | 34049/61904 [6:33:54<10:30:22,  1.36s/it]
 55%|█████▌    | 34050/61904 [6:33:55<10:22:38,  1.34s/it]
 55%|█████▌    | 34051/61904 [6:33:56<10:13:35,  1.32s/it]
 55%|█████▌    | 34052/61904 [6:33:58<10:17:54,  1.33s/it]
 55%|█████▌    | 34053/61904 [6:33:59<10:08:37,  1.31s/it]
 55%|█████▌    | 34054/61904 [6:34:00<10:29:36,  1.36s/it]
 55%|█████▌    | 34055/61904 [6:34:02<10:07:55,  1.31s/it]
 55%|█████▌    | 34056/61904 [6:34:03<10:15:02,  1.33s/it]
 55%|█████▌    | 34057/61904 [6:34:05<10:59:30,  1.42s/it]
 55%|█████▌    | 34058/61904 [6:34:06<10:38:03,  1.37s/it]
 55%|█████▌    | 34059/61904 [6:34:07<10:48:07,  1.40s/it]
 55%|█████▌    | 34060/61904 [6:34:09<10:51:30,  1.40s/it]
                                                          
{'loss': 2.5683, 'learning_rate': 1.451251134448334e-07, 'epoch': 8.8}
+
 55%|█████▌    | 34060/61904 [6:34:09<10:51:30,  1.40s/it]
 55%|█████▌    | 34061/61904 [6:34:10<10:48:37,  1.40s/it]
 55%|█████▌    | 34062/61904 [6:34:11<10:43:43,  1.39s/it]
 55%|█████▌    | 34063/61904 [6:34:13<10:44:21,  1.39s/it]
 55%|█████▌    | 34064/61904 [6:34:14<11:05:48,  1.43s/it]
 55%|█████▌    | 34065/61904 [6:34:16<10:41:17,  1.38s/it]
 55%|█████▌    | 34066/61904 [6:34:17<10:54:18,  1.41s/it]
 55%|█████▌    | 34067/61904 [6:34:19<10:45:58,  1.39s/it]
 55%|█████▌    | 34068/61904 [6:34:20<11:00:48,  1.42s/it]
 55%|█████▌    | 34069/61904 [6:34:21<10:59:24,  1.42s/it]
 55%|█████▌    | 34070/61904 [6:34:23<10:50:50,  1.40s/it]
 55%|█████▌    | 34071/61904 [6:34:24<10:45:58,  1.39s/it]
 55%|█████▌    | 34072/61904 [6:34:26<10:42:21,  1.38s/it]
 55%|█████▌    | 34073/61904 [6:34:27<10:37:25,  1.37s/it]
 55%|█████▌    | 34074/61904 [6:34:28<10:46:55,  1.39s/it]
 55%|█████▌    | 34075/61904 [6:34:30<10:38:10,  1.38s/it]
 55%|█████▌    | 34076/61904 [6:34:31<10:49:00,  1.40s/it]
 55%|█████▌    | 34077/61904 [6:34:33<10:58:09,  1.42s/it]
 55%|█████▌    | 34078/61904 [6:34:34<10:49:31,  1.40s/it]
 55%|█████▌    | 34079/61904 [6:34:35<10:53:27,  1.41s/it]
 55%|█████▌    | 34080/61904 [6:34:37<10:56:39,  1.42s/it]
                                                          
{'loss': 2.5462, 'learning_rate': 1.4509270063529105e-07, 'epoch': 8.81}
+
 55%|█████▌    | 34080/61904 [6:34:37<10:56:39,  1.42s/it]
 55%|█████▌    | 34081/61904 [6:34:38<11:34:06,  1.50s/it]
 55%|█████▌    | 34082/61904 [6:34:40<11:03:46,  1.43s/it]
 55%|█████▌    | 34083/61904 [6:34:41<10:44:50,  1.39s/it]
 55%|█████▌    | 34084/61904 [6:34:42<10:41:46,  1.38s/it]
 55%|█████▌    | 34085/61904 [6:34:44<10:41:26,  1.38s/it]
 55%|█████▌    | 34086/61904 [6:34:45<10:23:54,  1.35s/it]
 55%|█████▌    | 34087/61904 [6:34:46<10:11:13,  1.32s/it]
 55%|█████▌    | 34088/61904 [6:34:48<10:16:56,  1.33s/it]
 55%|█████▌    | 34089/61904 [6:34:49<10:46:09,  1.39s/it]
 55%|█████▌    | 34090/61904 [6:34:51<10:53:37,  1.41s/it]
 55%|█████▌    | 34091/61904 [6:34:52<10:52:41,  1.41s/it]
 55%|█████▌    | 34092/61904 [6:34:53<10:35:41,  1.37s/it]
 55%|█████▌    | 34093/61904 [6:34:55<10:51:18,  1.41s/it]
 55%|█████▌    | 34094/61904 [6:34:56<10:35:01,  1.37s/it]
 55%|█████▌    | 34095/61904 [6:34:57<10:28:45,  1.36s/it]
 55%|█████▌    | 34096/61904 [6:34:59<10:40:56,  1.38s/it]
 55%|█████▌    | 34097/61904 [6:35:00<10:53:53,  1.41s/it]
 55%|█████▌    | 34098/61904 [6:35:02<10:37:32,  1.38s/it]
 55%|█████▌    | 34099/61904 [6:35:03<10:41:57,  1.39s/it]
 55%|█████▌    | 34100/61904 [6:35:04<10:31:55,  1.36s/it]
                                                          
{'loss': 2.4885, 'learning_rate': 1.4506028782574874e-07, 'epoch': 8.81}
+
 55%|█████▌    | 34100/61904 [6:35:04<10:31:55,  1.36s/it]
 55%|█████▌    | 34101/61904 [6:35:06<10:18:14,  1.33s/it]
 55%|█████▌    | 34102/61904 [6:35:07<10:28:59,  1.36s/it]
 55%|█████▌    | 34103/61904 [6:35:08<10:25:34,  1.35s/it]
 55%|█████▌    | 34104/61904 [6:35:10<10:37:07,  1.38s/it]
 55%|█████▌    | 34105/61904 [6:35:11<10:29:50,  1.36s/it]
 55%|█████▌    | 34106/61904 [6:35:13<10:38:05,  1.38s/it]
 55%|█████▌    | 34107/61904 [6:35:14<10:29:36,  1.36s/it]
 55%|█████▌    | 34108/61904 [6:35:15<10:45:03,  1.39s/it]
 55%|█████▌    | 34109/61904 [6:35:17<10:33:22,  1.37s/it]
 55%|█████▌    | 34110/61904 [6:35:18<10:19:26,  1.34s/it]
 55%|█████▌    | 34111/61904 [6:35:20<11:01:19,  1.43s/it]
 55%|█████▌    | 34112/61904 [6:35:21<11:19:25,  1.47s/it]
 55%|█████▌    | 34113/61904 [6:35:23<11:15:33,  1.46s/it]
 55%|█████▌    | 34114/61904 [6:35:24<10:54:45,  1.41s/it]
 55%|█████▌    | 34115/61904 [6:35:25<10:35:53,  1.37s/it]
 55%|█████▌    | 34116/61904 [6:35:26<10:32:57,  1.37s/it]
 55%|█████▌    | 34117/61904 [6:35:28<10:26:26,  1.35s/it]
 55%|█████▌    | 34118/61904 [6:35:29<10:32:16,  1.37s/it]
 55%|█████▌    | 34119/61904 [6:35:31<10:32:53,  1.37s/it]
 55%|█████▌    | 34120/61904 [6:35:32<10:28:51,  1.36s/it]
                                                          
{'loss': 2.4856, 'learning_rate': 1.450278750162064e-07, 'epoch': 8.82}
+
 55%|█████▌    | 34120/61904 [6:35:32<10:28:51,  1.36s/it]
 55%|█████▌    | 34121/61904 [6:35:33<10:37:35,  1.38s/it]
 55%|█████▌    | 34122/61904 [6:35:35<10:22:19,  1.34s/it]
 55%|█████▌    | 34123/61904 [6:35:36<10:24:06,  1.35s/it]
 55%|█████▌    | 34124/61904 [6:35:37<10:42:14,  1.39s/it]
 55%|█████▌    | 34125/61904 [6:35:39<10:28:41,  1.36s/it]
 55%|███��█▌    | 34126/61904 [6:35:40<10:40:16,  1.38s/it]
 55%|█████▌    | 34127/61904 [6:35:42<10:32:57,  1.37s/it]
 55%|█████▌    | 34128/61904 [6:35:43<10:33:01,  1.37s/it]
 55%|█████▌    | 34129/61904 [6:35:44<10:20:09,  1.34s/it]
 55%|█████▌    | 34130/61904 [6:35:45<10:09:34,  1.32s/it]
 55%|█████▌    | 34131/61904 [6:35:47<10:09:34,  1.32s/it]
 55%|█████▌    | 34132/61904 [6:35:48<10:18:34,  1.34s/it]
 55%|█████▌    | 34133/61904 [6:35:49<10:05:57,  1.31s/it]
 55%|█████▌    | 34134/61904 [6:35:51<10:23:29,  1.35s/it]
 55%|█████▌    | 34135/61904 [6:35:52<10:15:32,  1.33s/it]
 55%|█████▌    | 34136/61904 [6:35:54<10:30:41,  1.36s/it]
 55%|█████▌    | 34137/61904 [6:35:55<11:02:45,  1.43s/it]
 55%|█████▌    | 34138/61904 [6:35:56<10:53:13,  1.41s/it]
 55%|█████▌    | 34139/61904 [6:35:58<10:57:58,  1.42s/it]
 55%|█████▌    | 34140/61904 [6:35:59<10:51:41,  1.41s/it]
                                                          
{'loss': 2.538, 'learning_rate': 1.4499546220666407e-07, 'epoch': 8.82}
+
 55%|█████▌    | 34140/61904 [6:35:59<10:51:41,  1.41s/it]
 55%|█████▌    | 34141/61904 [6:36:01<11:12:33,  1.45s/it]
 55%|█████▌    | 34142/61904 [6:36:02<11:00:49,  1.43s/it]
 55%|█████▌    | 34143/61904 [6:36:04<10:48:18,  1.40s/it]
 55%|█████▌    | 34144/61904 [6:36:05<10:50:34,  1.41s/it]
 55%|█████▌    | 34145/61904 [6:36:06<10:54:36,  1.41s/it]
 55%|█████▌    | 34146/61904 [6:36:08<10:43:38,  1.39s/it]
 55%|█████▌    | 34147/61904 [6:36:09<10:34:54,  1.37s/it]
 55%|█████▌    | 34148/61904 [6:36:10<10:19:40,  1.34s/it]
 55%|█████▌    | 34149/61904 [6:36:12<10:33:04,  1.37s/it]
 55%|█████▌    | 34150/61904 [6:36:13<10:18:02,  1.34s/it]
 55%|█████▌    | 34151/61904 [6:36:14<10:14:34,  1.33s/it]
 55%|█████▌    | 34152/61904 [6:36:16<10:10:13,  1.32s/it]
 55%|█████▌    | 34153/61904 [6:36:17<10:41:01,  1.39s/it]
 55%|█████▌    | 34154/61904 [6:36:19<10:33:29,  1.37s/it]
 55%|█████▌    | 34155/61904 [6:36:20<10:16:01,  1.33s/it]
 55%|█████▌    | 34156/61904 [6:36:21<10:19:58,  1.34s/it]
 55%|█████▌    | 34157/61904 [6:36:22<10:21:51,  1.34s/it]
 55%|█████▌    | 34158/61904 [6:36:24<10:28:41,  1.36s/it]
 55%|█████▌    | 34159/61904 [6:36:25<10:31:43,  1.37s/it]
 55%|█████▌    | 34160/61904 [6:36:27<10:26:09,  1.35s/it]
                                                          
{'loss': 2.5263, 'learning_rate': 1.4496304939712175e-07, 'epoch': 8.83}
+
 55%|█████▌    | 34160/61904 [6:36:27<10:26:09,  1.35s/it]
 55%|█████▌    | 34161/61904 [6:36:28<10:11:18,  1.32s/it]
 55%|█████▌    | 34162/61904 [6:36:29<10:27:17,  1.36s/it]
 55%|█████▌    | 34163/61904 [6:36:31<10:28:39,  1.36s/it]
 55%|█████▌    | 34164/61904 [6:36:32<10:34:52,  1.37s/it]
 55%|█████▌    | 34165/61904 [6:36:33<10:25:26,  1.35s/it]
 55%|█████▌    | 34166/61904 [6:36:35<10:08:13,  1.32s/it]
 55%|█████▌    | 34167/61904 [6:36:36<10:37:00,  1.38s/it]
 55%|█████▌    | 34168/61904 [6:36:38<10:43:13,  1.39s/it]
 55%|█████▌    | 34169/61904 [6:36:39<10:27:19,  1.36s/it]
 55%|█████▌    | 34170/61904 [6:36:40<10:20:07,  1.34s/it]
 55%|█████▌    | 34171/61904 [6:36:42<10:34:47,  1.37s/it]
 55%|█████▌    | 34172/61904 [6:36:43<10:34:16,  1.37s/it]
 55%|█████▌    | 34173/61904 [6:36:44<10:31:23,  1.37s/it]
 55%|█████▌    | 34174/61904 [6:36:46<10:16:03,  1.33s/it]
 55%|█████▌    | 34175/61904 [6:36:47<10:48:52,  1.40s/it]
 55%|█████▌    | 34176/61904 [6:36:49<11:01:09,  1.43s/it]
 55%|█████▌    | 34177/61904 [6:36:50<10:48:53,  1.40s/it]
 55%|█████▌    | 34178/61904 [6:36:51<10:38:26,  1.38s/it]
 55%|█████▌    | 34179/61904 [6:36:53<10:31:40,  1.37s/it]
 55%|█████▌    | 34180/61904 [6:36:54<10:47:16,  1.40s/it]
                                                          
{'loss': 2.5397, 'learning_rate': 1.449306365875794e-07, 'epoch': 8.83}
+
 55%|█████▌    | 34180/61904 [6:36:54<10:47:16,  1.40s/it]
 55%|█████▌    | 34181/61904 [6:36:55<10:29:34,  1.36s/it]
 55%|█████▌    | 34182/61904 [6:36:57<10:41:23,  1.39s/it]
 55%|█████▌    | 34183/61904 [6:36:58<10:32:40,  1.37s/it]
 55%|█████▌    | 34184/61904 [6:37:00<10:40:06,  1.39s/it]
 55%|█████▌    | 34185/61904 [6:37:01<10:28:10,  1.36s/it]
 55%|█████▌    | 34186/61904 [6:37:02<10:36:45,  1.38s/it]
 55%|█████▌    | 34187/61904 [6:37:04<10:23:10,  1.35s/it]
 55%|█████▌    | 34188/61904 [6:37:05<10:33:04,  1.37s/it]
 55%|█████▌    | 34189/61904 [6:37:06<10:28:10,  1.36s/it]
 55%|█████▌    | 34190/61904 [6:37:08<10:21:14,  1.34s/it]
 55%|█████▌    | 34191/61904 [6:37:09<10:26:47,  1.36s/it]
 55%|█████▌    | 34192/61904 [6:37:10<10:29:48,  1.36s/it]
 55%|█████▌    | 34193/61904 [6:37:12<10:18:20,  1.34s/it]
 55%|█████▌    | 34194/61904 [6:37:13<10:52:35,  1.41s/it]
 55%|█████▌    | 34195/61904 [6:37:15<10:39:38,  1.39s/it]
 55%|█████▌    | 34196/61904 [6:37:16<10:43:49,  1.39s/it]
 55%|█████▌    | 34197/61904 [6:37:17<10:37:19,  1.38s/it]
 55%|█████▌    | 34198/61904 [6:37:19<10:35:13,  1.38s/it]
 55%|█████▌    | 34199/61904 [6:37:20<10:33:07,  1.37s/it]
 55%|█████▌    | 34200/61904 [6:37:21<10:40:18,  1.39s/it]
                                                          
{'loss': 2.5295, 'learning_rate': 1.4489822377803708e-07, 'epoch': 8.84}
+
 55%|█████▌    | 34200/61904 [6:37:21<10:40:18,  1.39s/it]
 55%|█████▌    | 34201/61904 [6:37:23<10:36:30,  1.38s/it]
 55%|█████▌    | 34202/61904 [6:37:24<10:38:43,  1.38s/it]
 55%|█████▌    | 34203/61904 [6:37:25<10:21:54,  1.35s/it]
 55%|█████▌    | 34204/61904 [6:37:27<10:09:09,  1.32s/it]
 55%|█████▌    | 34205/61904 [6:37:28<10:05:22,  1.31s/it]
 55%|█████▌    | 34206/61904 [6:37:29<10:06:50,  1.31s/it]
 55%|█████▌    | 34207/61904 [6:37:31<10:15:25,  1.33s/it]
 55%|█████▌    | 34208/61904 [6:37:32<10:50:41,  1.41s/it]
 55%|█████▌    | 34209/61904 [6:37:34<10:51:38,  1.41s/it]
 55%|█████▌    | 34210/61904 [6:37:35<10:36:21,  1.38s/it]
 55%|█████▌    | 34211/61904 [6:37:36<10:32:24,  1.37s/it]
 55%|█████▌    | 34212/61904 [6:37:38<10:35:44,  1.38s/it]
 55%|█████▌    | 34213/61904 [6:37:39<10:26:06,  1.36s/it]
 55%|█████▌    | 34214/61904 [6:37:41<11:02:56,  1.44s/it]
 55%|█████▌    | 34215/61904 [6:37:42<10:49:16,  1.41s/it]
 55%|█████▌    | 34216/61904 [6:37:43<10:22:26,  1.35s/it]
 55%|█████▌    | 34217/61904 [6:37:45<10:18:12,  1.34s/it]
 55%|█████▌    | 34218/61904 [6:37:46<10:43:38,  1.39s/it]
 55%|█████▌    | 34219/61904 [6:37:48<10:47:48,  1.40s/it]
 55%|█████▌    | 34220/61904 [6:37:49<10:31:48,  1.37s/it]
                                                          
{'loss': 2.5853, 'learning_rate': 1.4486581096849474e-07, 'epoch': 8.84}
+
 55%|█████▌    | 34220/61904 [6:37:49<10:31:48,  1.37s/it]
 55%|█████▌    | 34221/61904 [6:37:50<10:19:38,  1.34s/it]
 55%|█████▌    | 34222/61904 [6:37:51<10:14:26,  1.33s/it]
 55%|█████▌    | 34223/61904 [6:37:53<10:19:57,  1.34s/it]
 55%|█████▌    | 34224/61904 [6:37:54<10:14:51,  1.33s/it]
 55%|█████▌    | 34225/61904 [6:37:55<10:14:38,  1.33s/it]
 55%|█████▌    | 34226/61904 [6:37:57<10:10:04,  1.32s/it]
 55%|█████▌    | 34227/61904 [6:37:58<10:19:40,  1.34s/it]
 55%|█████▌    | 34228/61904 [6:37:59<10:23:03,  1.35s/it]
 55%|█████▌    | 34229/61904 [6:38:01<10:25:07,  1.36s/it]
 55%|█████▌    | 34230/61904 [6:38:02<10:21:38,  1.35s/it]
 55%|█████▌    | 34231/61904 [6:38:04<11:06:56,  1.45s/it]
 55%|█████▌    | 34232/61904 [6:38:05<11:30:37,  1.50s/it]
 55%|█████▌    | 34233/61904 [6:38:07<11:05:23,  1.44s/it]
 55%|█████▌    | 34234/61904 [6:38:08<11:18:33,  1.47s/it]
 55%|█████▌    | 34235/61904 [6:38:10<11:07:22,  1.45s/it]
 55%|█████▌    | 34236/61904 [6:38:11<11:07:41,  1.45s/it]
 55%|█████▌    | 34237/61904 [6:38:13<11:12:35,  1.46s/it]
 55%|█████▌    | 34238/61904 [6:38:14<10:56:39,  1.42s/it]
 55%|█████▌    | 34239/61904 [6:38:15<10:40:41,  1.39s/it]
 55%|█████▌    | 34240/61904 [6:38:17<10:33:46,  1.37s/it]
                                                          
{'loss': 2.5566, 'learning_rate': 1.448333981589524e-07, 'epoch': 8.85}
+
 55%|█████▌    | 34240/61904 [6:38:17<10:33:46,  1.37s/it]
 55%|█████▌    | 34241/61904 [6:38:18<10:28:03,  1.36s/it]
 55%|█████▌    | 34242/61904 [6:38:19<10:07:27,  1.32s/it]
 55%|█████▌    | 34243/61904 [6:38:21<10:14:03,  1.33s/it]
 55%|█████▌    | 34244/61904 [6:38:22<10:40:39,  1.39s/it]
 55%|█████▌    | 34245/61904 [6:38:23<10:43:32,  1.40s/it]
 55%|█████▌    | 34246/61904 [6:38:25<10:24:41,  1.36s/it]
 55%|█████▌    | 34247/61904 [6:38:26<10:22:39,  1.35s/it]
 55%|█████▌    | 34248/61904 [6:38:27<10:06:55,  1.32s/it]
 55%|█████▌    | 34249/61904 [6:38:29<10:19:43,  1.34s/it]
 55%|█████▌    | 34250/61904 [6:38:30<10:56:03,  1.42s/it]
 55%|█████▌    | 34251/61904 [6:38:32<10:57:42,  1.43s/it]
 55%|█████▌    | 34252/61904 [6:38:33<10:43:31,  1.40s/it]
 55%|██���██▌    | 34253/61904 [6:38:35<10:47:54,  1.41s/it]
 55%|█████▌    | 34254/61904 [6:38:36<10:37:07,  1.38s/it]
 55%|█████▌    | 34255/61904 [6:38:37<10:27:42,  1.36s/it]
 55%|█████▌    | 34256/61904 [6:38:39<10:49:52,  1.41s/it]
 55%|█████▌    | 34257/61904 [6:38:40<10:55:38,  1.42s/it]
 55%|█████▌    | 34258/61904 [6:38:42<12:09:39,  1.58s/it]
 55%|█████▌    | 34259/61904 [6:38:44<11:43:43,  1.53s/it]
 55%|█████▌    | 34260/61904 [6:38:45<11:24:16,  1.49s/it]
                                                          
{'loss': 2.5319, 'learning_rate': 1.448009853494101e-07, 'epoch': 8.85}
+
 55%|█████▌    | 34260/61904 [6:38:45<11:24:16,  1.49s/it]
 55%|█████▌    | 34261/61904 [6:38:46<10:59:51,  1.43s/it]
 55%|█████▌    | 34262/61904 [6:38:48<11:07:26,  1.45s/it]
 55%|█████▌    | 34263/61904 [6:38:49<10:36:39,  1.38s/it]
 55%|█████▌    | 34264/61904 [6:38:50<10:49:49,  1.41s/it]
 55%|█████▌    | 34265/61904 [6:38:52<10:39:04,  1.39s/it]
 55%|█████▌    | 34266/61904 [6:38:53<10:33:08,  1.37s/it]
 55%|█████▌    | 34267/61904 [6:38:55<10:45:59,  1.40s/it]
 55%|█████▌    | 34268/61904 [6:38:56<10:54:47,  1.42s/it]
 55%|█████▌    | 34269/61904 [6:38:57<10:46:54,  1.40s/it]
 55%|█████▌    | 34270/61904 [6:38:59<10:27:20,  1.36s/it]
 55%|█████▌    | 34271/61904 [6:39:00<10:29:23,  1.37s/it]
 55%|█████▌    | 34272/61904 [6:39:01<10:40:17,  1.39s/it]
 55%|█████▌    | 34273/61904 [6:39:03<10:51:16,  1.41s/it]
 55%|█████▌    | 34274/61904 [6:39:04<10:35:52,  1.38s/it]
 55%|█████▌    | 34275/61904 [6:39:06<10:56:20,  1.43s/it]
 55%|█████▌    | 34276/61904 [6:39:07<10:44:45,  1.40s/it]
 55%|█████▌    | 34277/61904 [6:39:08<10:32:19,  1.37s/it]
 55%|█████▌    | 34278/61904 [6:39:10<10:28:30,  1.37s/it]
 55%|█████▌    | 34279/61904 [6:39:11<10:54:18,  1.42s/it]
 55%|█████▌    | 34280/61904 [6:39:13<10:40:34,  1.39s/it]
                                                          
{'loss': 2.4863, 'learning_rate': 1.4476857253986775e-07, 'epoch': 8.86}
+
 55%|█████▌    | 34280/61904 [6:39:13<10:40:34,  1.39s/it]
 55%|█████▌    | 34281/61904 [6:39:14<10:47:33,  1.41s/it]
 55%|█████▌    | 34282/61904 [6:39:15<10:35:21,  1.38s/it]
 55%|█████▌    | 34283/61904 [6:39:17<10:23:13,  1.35s/it]
 55%|█████▌    | 34284/61904 [6:39:18<10:30:29,  1.37s/it]
 55%|█████▌    | 34285/61904 [6:39:19<10:20:17,  1.35s/it]
 55%|█████▌    | 34286/61904 [6:39:21<10:25:29,  1.36s/it]
 55%|█████▌    | 34287/61904 [6:39:22<10:26:44,  1.36s/it]
 55%|█████▌    | 34288/61904 [6:39:24<10:36:08,  1.38s/it]
 55%|█████▌    | 34289/61904 [6:39:25<10:13:48,  1.33s/it]
 55%|█████▌    | 34290/61904 [6:39:26<10:26:19,  1.36s/it]
 55%|█████▌    | 34291/61904 [6:39:28<10:33:45,  1.38s/it]
 55%|█████▌    | 34292/61904 [6:39:29<10:30:28,  1.37s/it]
 55%|█████▌    | 34293/61904 [6:39:30<10:33:40,  1.38s/it]
 55%|█████▌    | 34294/61904 [6:39:32<10:42:18,  1.40s/it]
 55%|█████▌    | 34295/61904 [6:39:33<10:37:25,  1.39s/it]
 55%|█████▌    | 34296/61904 [6:39:34<10:25:36,  1.36s/it]
 55%|█████▌    | 34297/61904 [6:39:36<10:20:23,  1.35s/it]
 55%|█████▌    | 34298/61904 [6:39:37<10:32:28,  1.37s/it]
 55%|█████▌    | 34299/61904 [6:39:39<10:35:59,  1.38s/it]
 55%|█████▌    | 34300/61904 [6:39:40<10:42:27,  1.40s/it]
                                                          
{'loss': 2.5584, 'learning_rate': 1.4473615973032541e-07, 'epoch': 8.86}
+
 55%|█████▌    | 34300/61904 [6:39:40<10:42:27,  1.40s/it]
 55%|█████▌    | 34301/61904 [6:39:41<10:47:49,  1.41s/it]
 55%|█████▌    | 34302/61904 [6:39:43<10:39:21,  1.39s/it]
 55%|█████▌    | 34303/61904 [6:39:44<10:29:21,  1.37s/it]
 55%|█████▌    | 34304/61904 [6:39:46<10:31:39,  1.37s/it]
 55%|█████▌    | 34305/61904 [6:39:47<10:35:58,  1.38s/it]
 55%|█████▌    | 34306/61904 [6:39:48<10:40:44,  1.39s/it]
 55%|█████▌    | 34307/61904 [6:39:50<10:27:46,  1.36s/it]
 55%|█████▌    | 34308/61904 [6:39:51<10:33:19,  1.38s/it]
 55%|█████▌    | 34309/61904 [6:39:52<10:20:41,  1.35s/it]
 55%|█████▌    | 34310/61904 [6:39:54<10:20:54,  1.35s/it]
 55%|█████▌    | 34311/61904 [6:39:55<10:19:21,  1.35s/it]
 55%|█████▌    | 34312/61904 [6:39:56<10:25:21,  1.36s/it]
 55%|█████▌    | 34313/61904 [6:39:58<10:26:32,  1.36s/it]
 55%|█████▌    | 34314/61904 [6:39:59<10:29:52,  1.37s/it]
 55%|█████▌    | 34315/61904 [6:40:01<10:39:11,  1.39s/it]
 55%|█████▌    | 34316/61904 [6:40:02<10:41:40,  1.40s/it]
 55%|█████▌    | 34317/61904 [6:40:03<10:44:45,  1.40s/it]
 55%|█████▌    | 34318/61904 [6:40:05<10:36:27,  1.38s/it]
 55%|█████▌    | 34319/61904 [6:40:06<10:41:09,  1.39s/it]
 55%|█████▌    | 34320/61904 [6:40:08<10:30:22,  1.37s/it]
                                                          
{'loss': 2.5321, 'learning_rate': 1.447037469207831e-07, 'epoch': 8.87}
+
 55%|█████▌    | 34320/61904 [6:40:08<10:30:22,  1.37s/it]
 55%|█████▌    | 34321/61904 [6:40:09<10:27:16,  1.36s/it]
 55%|█████▌    | 34322/61904 [6:40:10<10:31:10,  1.37s/it]
 55%|█████▌    | 34323/61904 [6:40:12<10:16:42,  1.34s/it]
 55%|█████▌    | 34324/61904 [6:40:13<10:57:27,  1.43s/it]
 55%|█████▌    | 34325/61904 [6:40:15<11:03:05,  1.44s/it]
 55%|█████▌    | 34326/61904 [6:40:16<10:50:01,  1.41s/it]
 55%|█████▌    | 34327/61904 [6:40:17<10:32:19,  1.38s/it]
 55%|█████▌    | 34328/61904 [6:40:19<10:15:29,  1.34s/it]
 55%|█████▌    | 34329/61904 [6:40:20<10:14:27,  1.34s/it]
 55%|█████▌    | 34330/61904 [6:40:21<10:08:30,  1.32s/it]
 55%|█████▌    | 34331/61904 [6:40:22<9:55:55,  1.30s/it] 
 55%|█████▌    | 34332/61904 [6:40:24<10:10:44,  1.33s/it]
 55%|█████▌    | 34333/61904 [6:40:25<10:12:18,  1.33s/it]
 55%|█████▌    | 34334/61904 [6:40:26<10:11:23,  1.33s/it]
 55%|█████▌    | 34335/61904 [6:40:28<10:15:49,  1.34s/it]
 55%|█████▌    | 34336/61904 [6:40:29<10:03:31,  1.31s/it]
 55%|█████▌    | 34337/61904 [6:40:30<10:02:00,  1.31s/it]
 55%|█████▌    | 34338/61904 [6:40:32<9:59:35,  1.31s/it] 
 55%|█████▌    | 34339/61904 [6:40:33<10:27:08,  1.37s/it]
 55%|█████▌    | 34340/61904 [6:40:35<10:36:32,  1.39s/it]
                                                          
{'loss': 2.5304, 'learning_rate': 1.4467133411124074e-07, 'epoch': 8.88}
+
 55%|█████▌    | 34340/61904 [6:40:35<10:36:32,  1.39s/it]
 55%|█████▌    | 34341/61904 [6:40:36<10:55:52,  1.43s/it]
 55%|█████▌    | 34342/61904 [6:40:38<10:59:29,  1.44s/it]
 55%|█████▌    | 34343/61904 [6:40:39<10:32:35,  1.38s/it]
 55%|█████▌    | 34344/61904 [6:40:40<10:29:44,  1.37s/it]
 55%|█████▌    | 34345/61904 [6:40:41<10:16:37,  1.34s/it]
 55%|█████▌    | 34346/61904 [6:40:43<10:18:58,  1.35s/it]
 55%|█████▌    | 34347/61904 [6:40:44<10:48:34,  1.41s/it]
 55%|█████▌    | 34348/61904 [6:40:46<10:42:05,  1.40s/it]
 55%|█████▌    | 34349/61904 [6:40:47<10:31:47,  1.38s/it]
 55%|█████▌    | 34350/61904 [6:40:48<10:29:59,  1.37s/it]
 55%|█████▌    | 34351/61904 [6:40:50<10:32:14,  1.38s/it]
 55%|█████▌    | 34352/61904 [6:40:51<10:43:33,  1.40s/it]
 55%|█████▌    | 34353/61904 [6:40:53<10:23:06,  1.36s/it]
 55%|█████▌    | 34354/61904 [6:40:54<10:46:18,  1.41s/it]
 55%|█████▌    | 34355/61904 [6:40:55<10:48:17,  1.41s/it]
 55%|█████▌    | 34356/61904 [6:40:57<10:42:32,  1.40s/it]
 56%|█████▌    | 34357/61904 [6:40:58<10:26:24,  1.36s/it]
 56%|█████▌    | 34358/61904 [6:41:00<10:25:16,  1.36s/it]
 56%|█████▌    | 34359/61904 [6:41:01<10:21:42,  1.35s/it]
 56%|█████▌    | 34360/61904 [6:41:02<10:15:25,  1.34s/it]
                                                          
{'loss': 2.5564, 'learning_rate': 1.4463892130169843e-07, 'epoch': 8.88}
+
 56%|█████▌    | 34360/61904 [6:41:02<10:15:25,  1.34s/it]
 56%|█████▌    | 34361/61904 [6:41:04<10:32:49,  1.38s/it]
 56%|█████▌    | 34362/61904 [6:41:05<10:38:24,  1.39s/it]
 56%|█████▌    | 34363/61904 [6:41:06<10:32:04,  1.38s/it]
 56%|█████▌    | 34364/61904 [6:41:08<10:37:47,  1.39s/it]
 56%|█████▌    | 34365/61904 [6:41:09<10:19:45,  1.35s/it]
 56%|█████▌    | 34366/61904 [6:41:10<10:13:17,  1.34s/it]
 56%|█████▌    | 34367/61904 [6:41:12<10:08:36,  1.33s/it]
 56%|█████▌    | 34368/61904 [6:41:13<9:57:11,  1.30s/it] 
 56%|█████▌    | 34369/61904 [6:41:14<10:16:16,  1.34s/it]
 56%|█████▌    | 34370/61904 [6:41:16<10:09:10,  1.33s/it]
 56%|█████▌    | 34371/61904 [6:41:17<10:04:26,  1.32s/it]
 56%|█████▌    | 34372/61904 [6:41:18<10:10:14,  1.33s/it]
 56%|█████▌    | 34373/61904 [6:41:20<10:17:56,  1.35s/it]
 56%|█████▌    | 34374/61904 [6:41:21<10:57:49,  1.43s/it]
 56%|█████▌    | 34375/61904 [6:41:23<11:00:35,  1.44s/it]
 56%|█████▌    | 34376/61904 [6:41:24<11:29:50,  1.50s/it]
 56%|█████▌    | 34377/61904 [6:41:26<11:06:54,  1.45s/it]
 56%|█████▌    | 34378/61904 [6:41:27<10:38:36,  1.39s/it]
 56%|█████▌    | 34379/61904 [6:41:28<10:47:58,  1.41s/it]
 56%|��████▌    | 34380/61904 [6:41:30<10:36:49,  1.39s/it]
                                                          
{'loss': 2.5027, 'learning_rate': 1.4460650849215611e-07, 'epoch': 8.89}
+
 56%|█████▌    | 34380/61904 [6:41:30<10:36:49,  1.39s/it]
 56%|█████▌    | 34381/61904 [6:41:31<10:55:46,  1.43s/it]
 56%|█████▌    | 34382/61904 [6:41:33<11:08:16,  1.46s/it]
 56%|█████▌    | 34383/61904 [6:41:34<11:09:18,  1.46s/it]
 56%|█████▌    | 34384/61904 [6:41:36<10:50:59,  1.42s/it]
 56%|█████▌    | 34385/61904 [6:41:37<10:54:51,  1.43s/it]
 56%|█████▌    | 34386/61904 [6:41:38<10:36:39,  1.39s/it]
 56%|█████▌    | 34387/61904 [6:41:40<10:56:28,  1.43s/it]
 56%|█████▌    | 34388/61904 [6:41:41<10:40:42,  1.40s/it]
 56%|█████▌    | 34389/61904 [6:41:42<10:21:54,  1.36s/it]
 56%|█████▌    | 34390/61904 [6:41:44<10:23:38,  1.36s/it]
 56%|█████▌    | 34391/61904 [6:41:45<10:24:48,  1.36s/it]
 56%|█████▌    | 34392/61904 [6:41:47<10:12:43,  1.34s/it]
 56%|█████▌    | 34393/61904 [6:41:48<10:24:07,  1.36s/it]
 56%|█████▌    | 34394/61904 [6:41:49<10:25:41,  1.36s/it]
 56%|█████▌    | 34395/61904 [6:41:51<10:38:20,  1.39s/it]
 56%|█████▌    | 34396/61904 [6:41:52<10:24:46,  1.36s/it]
 56%|█████▌    | 34397/61904 [6:41:53<10:35:40,  1.39s/it]
 56%|█████▌    | 34398/61904 [6:41:55<10:36:57,  1.39s/it]
 56%|█████▌    | 34399/61904 [6:41:56<10:29:06,  1.37s/it]
 56%|█████▌    | 34400/61904 [6:41:57<10:05:09,  1.32s/it]
                                                          
{'loss': 2.4922, 'learning_rate': 1.4457409568261375e-07, 'epoch': 8.89}
+
 56%|█████▌    | 34400/61904 [6:41:57<10:05:09,  1.32s/it]
 56%|█████▌    | 34401/61904 [6:41:59<10:18:39,  1.35s/it]
 56%|█████▌    | 34402/61904 [6:42:00<10:10:58,  1.33s/it]
 56%|█████▌    | 34403/61904 [6:42:01<10:14:51,  1.34s/it]
 56%|█████▌    | 34404/61904 [6:42:03<10:30:47,  1.38s/it]
 56%|█████▌    | 34405/61904 [6:42:04<10:32:03,  1.38s/it]
 56%|█████▌    | 34406/61904 [6:42:06<10:24:09,  1.36s/it]
 56%|█████▌    | 34407/61904 [6:42:07<10:31:53,  1.38s/it]
 56%|█████▌    | 34408/61904 [6:42:08<10:19:49,  1.35s/it]
 56%|█████▌    | 34409/61904 [6:42:10<10:17:39,  1.35s/it]
 56%|█████▌    | 34410/61904 [6:42:11<10:33:16,  1.38s/it]
 56%|█████▌    | 34411/61904 [6:42:13<10:41:45,  1.40s/it]
 56%|█████▌    | 34412/61904 [6:42:14<10:21:38,  1.36s/it]
 56%|█████▌    | 34413/61904 [6:42:15<10:26:29,  1.37s/it]
 56%|█████▌    | 34414/61904 [6:42:17<10:59:27,  1.44s/it]
 56%|█████▌    | 34415/61904 [6:42:18<10:37:19,  1.39s/it]
 56%|█████▌    | 34416/61904 [6:42:19<10:28:27,  1.37s/it]
 56%|█████▌    | 34417/61904 [6:42:21<10:24:06,  1.36s/it]
 56%|█████▌    | 34418/61904 [6:42:22<10:11:08,  1.33s/it]
 56%|█████▌    | 34419/61904 [6:42:23<10:22:54,  1.36s/it]
 56%|█████▌    | 34420/61904 [6:42:25<10:36:50,  1.39s/it]
                                                          
{'loss': 2.5166, 'learning_rate': 1.4454168287307144e-07, 'epoch': 8.9}
+
 56%|█████▌    | 34420/61904 [6:42:25<10:36:50,  1.39s/it]
 56%|█████▌    | 34421/61904 [6:42:26<10:30:28,  1.38s/it]
 56%|█████▌    | 34422/61904 [6:42:28<10:12:13,  1.34s/it]
 56%|█████▌    | 34423/61904 [6:42:29<10:14:15,  1.34s/it]
 56%|█████▌    | 34424/61904 [6:42:30<10:23:29,  1.36s/it]
 56%|█████▌    | 34425/61904 [6:42:32<10:20:18,  1.35s/it]
 56%|█████▌    | 34426/61904 [6:42:33<10:24:52,  1.36s/it]
 56%|█████▌    | 34427/61904 [6:42:34<10:20:46,  1.36s/it]
 56%|█████▌    | 34428/61904 [6:42:36<10:30:33,  1.38s/it]
 56%|█████▌    | 34429/61904 [6:42:37<10:38:22,  1.39s/it]
 56%|█████▌    | 34430/61904 [6:42:39<10:33:00,  1.38s/it]
 56%|█████▌    | 34431/61904 [6:42:40<10:05:49,  1.32s/it]
 56%|█████▌    | 34432/61904 [6:42:41<10:04:35,  1.32s/it]
 56%|█████▌    | 34433/61904 [6:42:42<10:17:47,  1.35s/it]
 56%|█████▌    | 34434/61904 [6:42:44<10:25:38,  1.37s/it]
 56%|█████▌    | 34435/61904 [6:42:45<10:42:05,  1.40s/it]
 56%|█████▌    | 34436/61904 [6:42:47<10:32:04,  1.38s/it]
 56%|█████▌    | 34437/61904 [6:42:48<10:28:47,  1.37s/it]
 56%|█████▌    | 34438/61904 [6:42:49<10:22:22,  1.36s/it]
 56%|█████▌    | 34439/61904 [6:42:51<10:26:30,  1.37s/it]
 56%|█████▌    | 34440/61904 [6:42:52<10:09:09,  1.33s/it]
                                                          
{'loss': 2.527, 'learning_rate': 1.445092700635291e-07, 'epoch': 8.9}
+
 56%|█████▌    | 34440/61904 [6:42:52<10:09:09,  1.33s/it]
 56%|█████▌    | 34441/61904 [6:42:53<10:11:30,  1.34s/it]
 56%|█████▌    | 34442/61904 [6:42:55<10:43:05,  1.41s/it]
 56%|█████▌    | 34443/61904 [6:42:56<10:39:12,  1.40s/it]
 56%|█████▌    | 34444/61904 [6:42:58<10:43:11,  1.41s/it]
 56%|█████▌    | 34445/61904 [6:42:59<10:24:28,  1.36s/it]
 56%|█████▌    | 34446/61904 [6:43:00<10:37:31,  1.39s/it]
 56%|█████▌    | 34447/61904 [6:43:02<10:29:19,  1.38s/it]
 56%|█████▌    | 34448/61904 [6:43:03<10:35:53,  1.39s/it]
 56%|█████▌    | 34449/61904 [6:43:05<10:24:57,  1.37s/it]
 56%|█████▌    | 34450/61904 [6:43:06<10:48:01,  1.42s/it]
 56%|█████▌    | 34451/61904 [6:43:07<10:29:00,  1.37s/it]
 56%|█████▌    | 34452/61904 [6:43:09<10:39:36,  1.40s/it]
 56%|█████▌    | 34453/61904 [6:43:10<10:17:13,  1.35s/it]
 56%|█████▌    | 34454/61904 [6:43:11<10:12:56,  1.34s/it]
 56%|█████▌    | 34455/61904 [6:43:13<10:20:32,  1.36s/it]
 56%|█████▌    | 34456/61904 [6:43:14<10:34:54,  1.39s/it]
 56%|█████▌    | 34457/61904 [6:43:16<10:23:10,  1.36s/it]
 56%|█████▌    | 34458/61904 [6:43:17<10:19:22,  1.35s/it]
 56%|█████▌    | 34459/61904 [6:43:18<10:12:51,  1.34s/it]
 56%|█████▌    | 34460/61904 [6:43:19<10:02:53,  1.32s/it]
                                                          
{'loss': 2.5665, 'learning_rate': 1.4447685725398676e-07, 'epoch': 8.91}
+
 56%|█████▌    | 34460/61904 [6:43:19<10:02:53,  1.32s/it]
 56%|█████▌    | 34461/61904 [6:43:21<10:38:42,  1.40s/it]
 56%|█████▌    | 34462/61904 [6:43:22<10:29:07,  1.38s/it]
 56%|█████▌    | 34463/61904 [6:43:24<11:09:09,  1.46s/it]
 56%|█████▌    | 34464/61904 [6:43:25<10:54:38,  1.43s/it]
 56%|█████▌    | 34465/61904 [6:43:27<10:50:52,  1.42s/it]
 56%|█████▌    | 34466/61904 [6:43:28<10:43:20,  1.41s/it]
 56%|█████▌    | 34467/61904 [6:43:30<10:57:09,  1.44s/it]
 56%|█████▌    | 34468/61904 [6:43:31<10:51:59,  1.43s/it]
 56%|█████▌    | 34469/61904 [6:43:32<10:37:20,  1.39s/it]
 56%|█████▌    | 34470/61904 [6:43:34<10:17:23,  1.35s/it]
 56%|█████▌    | 34471/61904 [6:43:35<10:12:26,  1.34s/it]
 56%|█████▌    | 34472/61904 [6:43:36<9:57:31,  1.31s/it] 
 56%|█████▌    | 34473/61904 [6:43:38<10:21:07,  1.36s/it]
 56%|█████▌    | 34474/61904 [6:43:39<10:23:58,  1.36s/it]
 56%|█████▌    | 34475/61904 [6:43:41<11:30:40,  1.51s/it]
 56%|█████▌    | 34476/61904 [6:43:42<11:08:19,  1.46s/it]
 56%|█████▌    | 34477/61904 [6:43:44<10:51:09,  1.42s/it]
 56%|█████▌    | 34478/61904 [6:43:45<10:51:59,  1.43s/it]
 56%|█████▌    | 34479/61904 [6:43:46<10:45:06,  1.41s/it]
 56%|█████▌    | 34480/61904 [6:43:48<10:28:41,  1.38s/it]
                                                          
{'loss': 2.5615, 'learning_rate': 1.4444444444444445e-07, 'epoch': 8.91}
+
 56%|█████▌    | 34480/61904 [6:43:48<10:28:41,  1.38s/it]
 56%|█████▌    | 34481/61904 [6:43:49<10:21:57,  1.36s/it]
 56%|█████▌    | 34482/61904 [6:43:50<10:39:47,  1.40s/it]
 56%|█████▌    | 34483/61904 [6:43:52<10:42:46,  1.41s/it]
 56%|█████▌    | 34484/61904 [6:43:53<10:51:58,  1.43s/it]
 56%|█████▌    | 34485/61904 [6:43:55<10:38:25,  1.40s/it]
 56%|█████▌    | 34486/61904 [6:43:56<10:22:28,  1.36s/it]
 56%|█████▌    | 34487/61904 [6:43:57<10:27:11,  1.37s/it]
 56%|█████▌    | 34488/61904 [6:43:59<10:13:00,  1.34s/it]
 56%|█████▌    | 34489/61904 [6:44:00<10:24:50,  1.37s/it]
 56%|█████▌    | 34490/61904 [6:44:01<10:29:19,  1.38s/it]
 56%|█████▌    | 34491/61904 [6:44:03<10:26:03,  1.37s/it]
 56%|█████▌    | 34492/61904 [6:44:04<10:37:01,  1.39s/it]
 56%|█████▌    | 34493/61904 [6:44:06<10:28:25,  1.38s/it]
 56%|█████▌    | 34494/61904 [6:44:07<10:07:34,  1.33s/it]
 56%|█████▌    | 34495/61904 [6:44:08<10:09:07,  1.33s/it]
 56%|█████▌    | 34496/61904 [6:44:10<10:13:49,  1.34s/it]
 56%|█████▌    | 34497/61904 [6:44:11<10:11:23,  1.34s/it]
 56%|█████▌    | 34498/61904 [6:44:12<10:11:57,  1.34s/it]
 56%|█████▌    | 34499/61904 [6:44:14<10:29:07,  1.38s/it]
 56%|█████▌    | 34500/61904 [6:44:15<10:56:15,  1.44s/it]
                                                          
{'loss': 2.4899, 'learning_rate': 1.444120316349021e-07, 'epoch': 8.92}
+
 56%|█████▌    | 34500/61904 [6:44:15<10:56:15,  1.44s/it]
 56%|█████▌    | 34501/61904 [6:44:17<11:04:28,  1.45s/it]
 56%|█████▌    | 34502/61904 [6:44:18<10:49:47,  1.42s/it]
 56%|█████▌    | 34503/61904 [6:44:19<10:26:14,  1.37s/it]
 56%|██��██▌    | 34504/61904 [6:44:21<10:23:54,  1.37s/it]
 56%|█████▌    | 34505/61904 [6:44:22<10:52:04,  1.43s/it]
 56%|█████▌    | 34506/61904 [6:44:24<11:02:37,  1.45s/it]
 56%|█████▌    | 34507/61904 [6:44:25<10:55:52,  1.44s/it]
 56%|█████▌    | 34508/61904 [6:44:27<10:45:58,  1.41s/it]
 56%|█████▌    | 34509/61904 [6:44:28<10:27:36,  1.37s/it]
 56%|█████▌    | 34510/61904 [6:44:29<10:31:03,  1.38s/it]
 56%|█████▌    | 34511/61904 [6:44:31<10:52:08,  1.43s/it]
 56%|█████▌    | 34512/61904 [6:44:32<10:51:53,  1.43s/it]
 56%|█████▌    | 34513/61904 [6:44:34<11:14:12,  1.48s/it]
 56%|█████▌    | 34514/61904 [6:44:35<10:59:00,  1.44s/it]
 56%|█████▌    | 34515/61904 [6:44:36<10:30:38,  1.38s/it]
 56%|█████▌    | 34516/61904 [6:44:38<10:39:28,  1.40s/it]
 56%|█████▌    | 34517/61904 [6:44:39<10:32:03,  1.38s/it]
 56%|█████▌    | 34518/61904 [6:44:41<10:30:52,  1.38s/it]
 56%|█████▌    | 34519/61904 [6:44:42<10:09:09,  1.33s/it]
 56%|█████▌    | 34520/61904 [6:44:43<10:18:15,  1.35s/it]
                                                          
{'loss': 2.5012, 'learning_rate': 1.4437961882535977e-07, 'epoch': 8.92}
+
 56%|█████▌    | 34520/61904 [6:44:43<10:18:15,  1.35s/it]
 56%|█████▌    | 34521/61904 [6:44:45<10:26:22,  1.37s/it]
 56%|█████▌    | 34522/61904 [6:44:46<11:09:11,  1.47s/it]
 56%|█████▌    | 34523/61904 [6:44:48<10:45:35,  1.41s/it]
 56%|█████▌    | 34524/61904 [6:44:49<10:16:44,  1.35s/it]
 56%|█████▌    | 34525/61904 [6:44:50<10:26:45,  1.37s/it]
 56%|█████▌    | 34526/61904 [6:44:52<10:22:22,  1.36s/it]
 56%|█████▌    | 34527/61904 [6:44:53<10:29:06,  1.38s/it]
 56%|█████▌    | 34528/61904 [6:44:54<10:01:46,  1.32s/it]
 56%|█████▌    | 34529/61904 [6:44:56<10:16:25,  1.35s/it]
 56%|█████▌    | 34530/61904 [6:44:57<10:11:31,  1.34s/it]
 56%|█████▌    | 34531/61904 [6:44:58<10:22:18,  1.36s/it]
 56%|█████▌    | 34532/61904 [6:45:00<10:18:15,  1.36s/it]
 56%|█████▌    | 34533/61904 [6:45:01<10:30:34,  1.38s/it]
 56%|█████▌    | 34534/61904 [6:45:02<10:33:17,  1.39s/it]
 56%|█████▌    | 34535/61904 [6:45:04<10:29:57,  1.38s/it]
 56%|█████▌    | 34536/61904 [6:45:05<10:15:00,  1.35s/it]
 56%|█████▌    | 34537/61904 [6:45:06<10:20:06,  1.36s/it]
 56%|█████▌    | 34538/61904 [6:45:08<10:14:15,  1.35s/it]
 56%|█████▌    | 34539/61904 [6:45:09<10:29:24,  1.38s/it]
 56%|█████▌    | 34540/61904 [6:45:11<10:32:42,  1.39s/it]
                                                          
{'loss': 2.5526, 'learning_rate': 1.4434720601581746e-07, 'epoch': 8.93}
+
 56%|█████▌    | 34540/61904 [6:45:11<10:32:42,  1.39s/it]
 56%|█████▌    | 34541/61904 [6:45:12<10:25:42,  1.37s/it]
 56%|█████▌    | 34542/61904 [6:45:13<10:27:29,  1.38s/it]
 56%|█████▌    | 34543/61904 [6:45:15<10:18:49,  1.36s/it]
 56%|█████▌    | 34544/61904 [6:45:16<10:49:57,  1.43s/it]
 56%|█████▌    | 34545/61904 [6:45:18<10:33:48,  1.39s/it]
 56%|█████▌    | 34546/61904 [6:45:19<10:14:35,  1.35s/it]
 56%|█████▌    | 34547/61904 [6:45:20<10:04:57,  1.33s/it]
 56%|█████▌    | 34548/61904 [6:45:22<10:21:27,  1.36s/it]
 56%|█████▌    | 34549/61904 [6:45:23<10:22:11,  1.36s/it]
 56%|█████▌    | 34550/61904 [6:45:24<10:33:30,  1.39s/it]
 56%|█████▌    | 34551/61904 [6:45:26<10:34:17,  1.39s/it]
 56%|█████▌    | 34552/61904 [6:45:27<10:38:24,  1.40s/it]
 56%|█████▌    | 34553/61904 [6:45:29<10:36:26,  1.40s/it]
 56%|█████▌    | 34554/61904 [6:45:30<10:25:28,  1.37s/it]
 56%|█████▌    | 34555/61904 [6:45:31<10:09:43,  1.34s/it]
 56%|█████▌    | 34556/61904 [6:45:32<10:03:51,  1.32s/it]
 56%|█████▌    | 34557/61904 [6:45:34<10:08:47,  1.34s/it]
 56%|█████▌    | 34558/61904 [6:45:35<10:14:57,  1.35s/it]
 56%|█████▌    | 34559/61904 [6:45:37<10:33:47,  1.39s/it]
 56%|█████▌    | 34560/61904 [6:45:38<10:32:08,  1.39s/it]
                                                          
{'loss': 2.5167, 'learning_rate': 1.443147932062751e-07, 'epoch': 8.93}
+
 56%|█████▌    | 34560/61904 [6:45:38<10:32:08,  1.39s/it]
 56%|█████▌    | 34561/61904 [6:45:39<10:35:01,  1.39s/it]
 56%|█████▌    | 34562/61904 [6:45:41<10:46:18,  1.42s/it]
 56%|█████▌    | 34563/61904 [6:45:42<11:01:46,  1.45s/it]
 56%|█████▌    | 34564/61904 [6:45:44<10:43:42,  1.41s/it]
 56%|█████▌    | 34565/61904 [6:45:45<10:38:59,  1.40s/it]
 56%|█████▌    | 34566/61904 [6:45:46<10:23:56,  1.37s/it]
 56%|█████▌    | 34567/61904 [6:45:48<10:13:56,  1.35s/it]
 56%|█████▌    | 34568/61904 [6:45:49<10:03:53,  1.33s/it]
 56%|█████▌    | 34569/61904 [6:45:51<10:23:53,  1.37s/it]
 56%|█████▌    | 34570/61904 [6:45:52<10:28:02,  1.38s/it]
 56%|█████▌    | 34571/61904 [6:45:53<10:47:07,  1.42s/it]
 56%|█████▌    | 34572/61904 [6:45:55<10:28:32,  1.38s/it]
 56%|█████▌    | 34573/61904 [6:45:56<10:30:02,  1.38s/it]
 56%|█████▌    | 34574/61904 [6:45:57<10:26:35,  1.38s/it]
 56%|█████▌    | 34575/61904 [6:45:59<10:42:56,  1.41s/it]
 56%|█████▌    | 34576/61904 [6:46:00<10:35:13,  1.39s/it]
 56%|█████▌    | 34577/61904 [6:46:02<10:31:59,  1.39s/it]
 56%|█████▌    | 34578/61904 [6:46:03<10:33:46,  1.39s/it]
 56%|█████▌    | 34579/61904 [6:46:04<10:30:13,  1.38s/it]
 56%|█████▌    | 34580/61904 [6:46:06<10:16:11,  1.35s/it]
                                                          
{'loss': 2.5177, 'learning_rate': 1.4428238039673279e-07, 'epoch': 8.94}
+
 56%|█████▌    | 34580/61904 [6:46:06<10:16:11,  1.35s/it]
 56%|█████▌    | 34581/61904 [6:46:07<10:10:26,  1.34s/it]
 56%|█████▌    | 34582/61904 [6:46:08<10:24:47,  1.37s/it]
 56%|█████▌    | 34583/61904 [6:46:10<10:39:49,  1.41s/it]
 56%|█████▌    | 34584/61904 [6:46:12<10:58:10,  1.45s/it]
 56%|█████▌    | 34585/61904 [6:46:13<10:40:31,  1.41s/it]
 56%|█████▌    | 34586/61904 [6:46:14<10:36:57,  1.40s/it]
 56%|█████▌    | 34587/61904 [6:46:16<10:42:14,  1.41s/it]
 56%|█████▌    | 34588/61904 [6:46:17<11:06:37,  1.46s/it]
 56%|█████▌    | 34589/61904 [6:46:19<11:06:00,  1.46s/it]
 56%|█████▌    | 34590/61904 [6:46:20<10:54:12,  1.44s/it]
 56%|█████▌    | 34591/61904 [6:46:21<10:31:31,  1.39s/it]
 56%|█████▌    | 34592/61904 [6:46:23<10:38:44,  1.40s/it]
 56%|█████▌    | 34593/61904 [6:46:24<10:37:45,  1.40s/it]
 56%|█████▌    | 34594/61904 [6:46:25<10:17:26,  1.36s/it]
 56%|█████▌    | 34595/61904 [6:46:27<10:14:36,  1.35s/it]
 56%|█████▌    | 34596/61904 [6:46:28<10:08:17,  1.34s/it]
 56%|█████▌    | 34597/61904 [6:46:29<10:15:54,  1.35s/it]
 56%|█████▌    | 34598/61904 [6:46:31<10:50:44,  1.43s/it]
 56%|█████▌    | 34599/61904 [6:46:32<10:33:32,  1.39s/it]
 56%|█████▌    | 34600/61904 [6:46:34<10:21:42,  1.37s/it]
                                                          
{'loss': 2.5548, 'learning_rate': 1.4424996758719045e-07, 'epoch': 8.94}
+
 56%|█████▌    | 34600/61904 [6:46:34<10:21:42,  1.37s/it]
 56%|█████▌    | 34601/61904 [6:46:35<10:18:24,  1.36s/it]
 56%|█████▌    | 34602/61904 [6:46:36<10:06:02,  1.33s/it]
 56%|█████▌    | 34603/61904 [6:46:38<10:48:27,  1.43s/it]
 56%|█████▌    | 34604/61904 [6:46:39<10:45:33,  1.42s/it]
 56%|█████▌    | 34605/61904 [6:46:41<10:44:44,  1.42s/it]
 56%|█████▌    | 34606/61904 [6:46:42<10:33:06,  1.39s/it]
 56%|█████▌    | 34607/61904 [6:46:44<10:49:54,  1.43s/it]
 56%|█████▌    | 34608/61904 [6:46:45<10:42:13,  1.41s/it]
 56%|█████▌    | 34609/61904 [6:46:46<10:38:58,  1.40s/it]
 56%|█████▌    | 34610/61904 [6:46:48<10:43:15,  1.41s/it]
 56%|█████▌    | 34611/61904 [6:46:49<10:48:22,  1.43s/it]
 56%|█████▌    | 34612/61904 [6:46:51<10:42:59,  1.41s/it]
 56%|█████▌    | 34613/61904 [6:46:52<10:49:14,  1.43s/it]
 56%|█████▌    | 34614/61904 [6:46:54<10:47:03,  1.42s/it]
 56%|█████▌    | 34615/61904 [6:46:55<10:31:23,  1.39s/it]
 56%|█████▌    | 34616/61904 [6:46:56<10:16:29,  1.36s/it]
 56%|█████▌    | 34617/61904 [6:46:58<10:24:49,  1.37s/it]
 56%|█████▌    | 34618/61904 [6:46:59<10:36:37,  1.40s/it]
 56%|█████▌    | 34619/61904 [6:47:00<10:06:37,  1.33s/it]
 56%|█████▌    | 34620/61904 [6:47:02<10:15:04,  1.35s/it]
                                                          
{'loss': 2.5742, 'learning_rate': 1.442175547776481e-07, 'epoch': 8.95}
+
 56%|█████▌    | 34620/61904 [6:47:02<10:15:04,  1.35s/it]
 56%|█████▌    | 34621/61904 [6:47:03<10:21:20,  1.37s/it]
 56%|█████▌    | 34622/61904 [6:47:04<10:10:57,  1.34s/it]
 56%|█████▌    | 34623/61904 [6:47:06<10:21:54,  1.37s/it]
 56%|█████▌    | 34624/61904 [6:47:07<10:19:47,  1.36s/it]
 56%|█████▌    | 34625/61904 [6:47:08<10:17:18,  1.36s/it]
 56%|█████▌    | 34626/61904 [6:47:10<10:18:46,  1.36s/it]
 56%|█████▌    | 34627/61904 [6:47:11<10:15:12,  1.35s/it]
 56%|█████▌    | 34628/61904 [6:47:12<10:07:05,  1.34s/it]
 56%|█████▌    | 34629/61904 [6:47:14<10:04:11,  1.33s/it]
 56%|█████▌    | 34630/61904 [6:47:15<10:05:07,  1.33s/it]
 56%|█████▌    | 34631/61904 [6:47:16<10:20:41,  1.37s/it]
 56%|█████▌    | 34632/61904 [6:47:18<10:37:47,  1.40s/it]
 56%|█████▌    | 34633/61904 [6:47:19<10:42:00,  1.41s/it]
 56%|█████▌    | 34634/61904 [6:47:21<10:32:17,  1.39s/it]
 56%|█████▌    | 34635/61904 [6:47:22<10:33:36,  1.39s/it]
 56%|█████▌    | 34636/61904 [6:47:24<10:42:07,  1.41s/it]
 56%|█████▌    | 34637/61904 [6:47:25<10:30:53,  1.39s/it]
 56%|█████▌    | 34638/61904 [6:47:26<10:25:14,  1.38s/it]
 56%|█████▌    | 34639/61904 [6:47:28<10:12:55,  1.35s/it]
 56%|█████▌    | 34640/61904 [6:47:29<10:10:54,  1.34s/it]
                                                          
{'loss': 2.5149, 'learning_rate': 1.441851419681058e-07, 'epoch': 8.95}
+
 56%|█████▌    | 34640/61904 [6:47:29<10:10:54,  1.34s/it]
 56%|█████▌    | 34641/61904 [6:47:30<10:10:16,  1.34s/it]
 56%|█████▌    | 34642/61904 [6:47:31<9:52:30,  1.30s/it] 
 56%|█████▌    | 34643/61904 [6:47:33<10:15:08,  1.35s/it]
 56%|█████▌    | 34644/61904 [6:47:34<10:26:37,  1.38s/it]
 56%|█████▌    | 34645/61904 [6:47:36<10:13:42,  1.35s/it]
 56%|█████▌    | 34646/61904 [6:47:37<10:12:49,  1.35s/it]
 56%|█████▌    | 34647/61904 [6:47:38<10:05:27,  1.33s/it]
 56%|█████▌    | 34648/61904 [6:47:40<10:03:49,  1.33s/it]
 56%|█████▌    | 34649/61904 [6:47:41<9:58:10,  1.32s/it] 
 56%|█████▌    | 34650/61904 [6:47:42<9:50:08,  1.30s/it]
 56%|█████▌    | 34651/61904 [6:47:43<9:51:50,  1.30s/it]
 56%|█████▌    | 34652/61904 [6:47:45<10:03:42,  1.33s/it]
 56%|█████▌    | 34653/61904 [6:47:46<10:13:39,  1.35s/it]
 56%|█████▌    | 34654/61904 [6:47:48<10:11:08,  1.35s/it]
 56%|█████▌    | 34655/61904 [6:47:49<10:37:39,  1.40s/it]
 56%|█████▌    | 34656/61904 [6:47:51<10:40:35,  1.41s/it]
 56%|█████▌    | 34657/61904 [6:47:52<10:12:49,  1.35s/it]
 56%|█████▌    | 34658/61904 [6:47:53<10:23:31,  1.37s/it]
 56%|█████▌    | 34659/61904 [6:47:55<10:40:23,  1.41s/it]
 56%|█████▌    | 34660/61904 [6:47:56<10:22:12,  1.37s/it]
                                                          
{'loss': 2.5042, 'learning_rate': 1.4415272915856346e-07, 'epoch': 8.96}
+
 56%|█████▌    | 34660/61904 [6:47:56<10:22:12,  1.37s/it]
 56%|█████▌    | 34661/61904 [6:47:57<10:15:09,  1.35s/it]
 56%|█████▌    | 34662/61904 [6:47:59<10:07:34,  1.34s/it]
 56%|█████▌    | 34663/61904 [6:48:00<10:44:27,  1.42s/it]
 56%|█████▌    | 34664/61904 [6:48:02<10:53:59,  1.44s/it]
 56%|█████▌    | 34665/61904 [6:48:03<10:29:24,  1.39s/it]
 56%|█████▌    | 34666/61904 [6:48:04<10:21:15,  1.37s/it]
 56%|█████▌    | 34667/61904 [6:48:05<10:03:03,  1.33s/it]
 56%|█████▌    | 34668/61904 [6:48:07<10:06:23,  1.34s/it]
 56%|█████▌    | 34669/61904 [6:48:08<10:12:55,  1.35s/it]
 56%|█████▌    | 34670/61904 [6:48:10<10:14:48,  1.35s/it]
 56%|█████▌    | 34671/61904 [6:48:11<10:11:14,  1.35s/it]
 56%|█████▌    | 34672/61904 [6:48:12<10:13:41,  1.35s/it]
 56%|█████▌    | 34673/61904 [6:48:14<10:05:37,  1.33s/it]
 56%|█████▌    | 34674/61904 [6:48:15<10:37:44,  1.41s/it]
 56%|█████▌    | 34675/61904 [6:48:16<10:24:29,  1.38s/it]
 56%|█████▌    | 34676/61904 [6:48:18<10:03:58,  1.33s/it]
 56%|█████▌    | 34677/61904 [6:48:19<10:25:46,  1.38s/it]
 56%|█████▌    | 34678/61904 [6:48:21<10:23:50,  1.37s/it]
 56%|█████▌    | 34679/61904 [6:48:22<10:42:21,  1.42s/it]
 56%|█████▌    | 34680/61904 [6:48:23<10:23:53,  1.38s/it]
                                                          
{'loss': 2.5076, 'learning_rate': 1.4412031634902112e-07, 'epoch': 8.96}
+
 56%|█████▌    | 34680/61904 [6:48:23<10:23:53,  1.38s/it]
 56%|█████▌    | 34681/61904 [6:48:25<10:08:39,  1.34s/it]
 56%|█████▌    | 34682/61904 [6:48:26<10:10:03,  1.34s/it]
 56%|█████▌    | 34683/61904 [6:48:27<10:09:32,  1.34s/it]
 56%|█████▌    | 34684/61904 [6:48:29<10:28:07,  1.38s/it]
 56%|█████▌    | 34685/61904 [6:48:30<10:44:28,  1.42s/it]
 56%|█████▌    | 34686/61904 [6:48:32<10:47:31,  1.43s/it]
 56%|█████▌    | 34687/61904 [6:48:33<10:32:03,  1.39s/it]
 56%|█████▌    | 34688/61904 [6:48:34<10:20:15,  1.37s/it]
 56%|█████▌    | 34689/61904 [6:48:36<10:21:46,  1.37s/it]
 56%|█████▌    | 34690/61904 [6:48:37<10:28:12,  1.39s/it]
 56%|█████▌    | 34691/61904 [6:48:38<10:18:58,  1.36s/it]
 56%|█████▌    | 34692/61904 [6:48:40<10:04:29,  1.33s/it]
 56%|█████▌    | 34693/61904 [6:48:41<10:14:23,  1.35s/it]
 56%|█████▌    | 34694/61904 [6:48:42<10:08:27,  1.34s/it]
 56%|█████▌    | 34695/61904 [6:48:44<10:19:02,  1.37s/it]
 56%|█████▌    | 34696/61904 [6:48:45<10:26:54,  1.38s/it]
 56%|█████▌    | 34697/61904 [6:48:47<10:20:08,  1.37s/it]
 56%|█████▌    | 34698/61904 [6:48:48<10:03:52,  1.33s/it]
 56%|█████▌    | 34699/61904 [6:48:49<10:00:37,  1.32s/it]
 56%|█████▌    | 34700/61904 [6:48:50<10:02:08,  1.33s/it]
                                                          
{'loss': 2.5282, 'learning_rate': 1.440879035394788e-07, 'epoch': 8.97}
+
 56%|█████▌    | 34700/61904 [6:48:50<10:02:08,  1.33s/it]
 56%|█████▌    | 34701/61904 [6:48:52<10:19:19,  1.37s/it]
 56%|█████▌    | 34702/61904 [6:48:53<10:02:55,  1.33s/it]
 56%|█████▌    | 34703/61904 [6:48:55<10:07:20,  1.34s/it]
 56%|█████▌    | 34704/61904 [6:48:56<10:04:08,  1.33s/it]
 56%|█████▌    | 34705/61904 [6:48:57<10:04:26,  1.33s/it]
 56%|█████▌    | 34706/61904 [6:48:59<10:18:24,  1.36s/it]
 56%|█████▌    | 34707/61904 [6:49:00<10:19:02,  1.37s/it]
 56%|█████▌    | 34708/61904 [6:49:01<10:31:41,  1.39s/it]
 56%|█████▌    | 34709/61904 [6:49:03<10:51:50,  1.44s/it]
 56%|█████▌    | 34710/61904 [6:49:04<10:46:23,  1.43s/it]
 56%|█████▌    | 34711/61904 [6:49:06<10:34:36,  1.40s/it]
 56%|█████▌    | 34712/61904 [6:49:07<10:43:47,  1.42s/it]
 56%|█████▌    | 34713/61904 [6:49:09<10:34:46,  1.40s/it]
 56%|█████▌    | 34714/61904 [6:49:10<10:30:57,  1.39s/it]
 56%|█████▌    | 34715/61904 [6:49:11<10:48:42,  1.43s/it]
 56%|█████▌    | 34716/61904 [6:49:13<10:43:33,  1.42s/it]
 56%|█████▌    | 34717/61904 [6:49:14<10:40:47,  1.41s/it]
 56%|█████▌    | 34718/61904 [6:49:16<10:33:57,  1.40s/it]
 56%|█████▌    | 34719/61904 [6:49:17<10:10:00,  1.35s/it]
 56%|█████▌    | 34720/61904 [6:49:18<10:44:38,  1.42s/it]
                                                          
{'loss': 2.5373, 'learning_rate': 1.4405549072993647e-07, 'epoch': 8.97}
+
 56%|█████▌    | 34720/61904 [6:49:18<10:44:38,  1.42s/it]
 56%|█████▌    | 34721/61904 [6:49:20<10:41:32,  1.42s/it]
 56%|█████▌    | 34722/61904 [6:49:21<10:27:40,  1.39s/it]
 56%|█████▌    | 34723/61904 [6:49:22<10:10:56,  1.35s/it]
 56%|█████▌    | 34724/61904 [6:49:24<10:07:57,  1.34s/it]
 56%|█████▌    | 34725/61904 [6:49:25<10:09:56,  1.35s/it]
 56%|█████▌    | 34726/61904 [6:49:27<10:17:17,  1.36s/it]
 56%|█████▌    | 34727/61904 [6:49:28<10:29:19,  1.39s/it]
 56%|█████▌    | 34728/61904 [6:49:29<10:16:31,  1.36s/it]
 56%|█████▌    | 34729/61904 [6:49:31<10:35:35,  1.40s/it]
 56%|█████▌    | 34730/61904 [6:49:32<10:25:37,  1.38s/it]
 56%|█████▌    | 34731/61904 [6:49:34<10:30:27,  1.39s/it]
 56%|█████▌    | 34732/61904 [6:49:35<10:44:03,  1.42s/it]
 56%|█████▌    | 34733/61904 [6:49:36<10:39:07,  1.41s/it]
 56%|█████▌    | 34734/61904 [6:49:38<10:34:23,  1.40s/it]
 56%|█████▌    | 34735/61904 [6:49:39<10:56:27,  1.45s/it]
 56%|█████▌    | 34736/61904 [6:49:41<10:45:01,  1.42s/it]
 56%|█████▌    | 34737/61904 [6:49:42<10:36:46,  1.41s/it]
 56%|█████▌    | 34738/61904 [6:49:43<10:38:08,  1.41s/it]
 56%|█████▌    | 34739/61904 [6:49:45<10:44:47,  1.42s/it]
 56%|█████▌    | 34740/61904 [6:49:46<10:37:04,  1.41s/it]
                                                          
{'loss': 2.5556, 'learning_rate': 1.4402307792039413e-07, 'epoch': 8.98}
+
 56%|█████▌    | 34740/61904 [6:49:46<10:37:04,  1.41s/it]
 56%|█████▌    | 34741/61904 [6:49:48<10:25:33,  1.38s/it]
 56%|█████▌    | 34742/61904 [6:49:49<10:37:52,  1.41s/it]
 56%|█████▌    | 34743/61904 [6:49:50<10:14:00,  1.36s/it]
 56%|█████▌    | 34744/61904 [6:49:52<10:15:34,  1.36s/it]
 56%|█████▌    | 34745/61904 [6:49:53<10:21:02,  1.37s/it]
 56%|█████▌    | 34746/61904 [6:49:55<10:37:22,  1.41s/it]
 56%|█████▌    | 34747/61904 [6:49:56<10:55:25,  1.45s/it]
 56%|█████▌    | 34748/61904 [6:49:58<10:46:31,  1.43s/it]
 56%|█████▌    | 34749/61904 [6:49:59<11:09:58,  1.48s/it]
 56%|█████▌    | 34750/61904 [6:50:01<11:08:02,  1.48s/it]
 56%|█████▌    | 34751/61904 [6:50:02<10:49:04,  1.43s/it]
 56%|█████▌    | 34752/61904 [6:50:03<10:31:55,  1.40s/it]
 56%|█████▌    | 34753/61904 [6:50:04<10:12:53,  1.35s/it]
 56%|█████▌    | 34754/61904 [6:50:06<10:28:10,  1.39s/it]
 56%|█████▌    | 34755/61904 [6:50:07<10:14:15,  1.36s/it]
 56%|█████▌    | 34756/61904 [6:50:09<10:28:14,  1.39s/it]
 56%|█████▌    | 34757/61904 [6:50:10<10:32:35,  1.40s/it]
 56%|█████▌    | 34758/61904 [6:50:11<10:24:55,  1.38s/it]
 56%|█████▌    | 34759/61904 [6:50:13<10:17:20,  1.36s/it]
 56%|█████▌    | 34760/61904 [6:50:14<10:18:37,  1.37s/it]
                                                          
{'loss': 2.5413, 'learning_rate': 1.4399066511085182e-07, 'epoch': 8.98}
+
 56%|█████▌    | 34760/61904 [6:50:14<10:18:37,  1.37s/it]
 56%|█████▌    | 34761/61904 [6:50:16<10:16:41,  1.36s/it]
 56%|█████▌    | 34762/61904 [6:50:17<10:19:56,  1.37s/it]
 56%|█████▌    | 34763/61904 [6:50:18<10:13:30,  1.36s/it]
 56%|█████▌    | 34764/61904 [6:50:20<10:28:07,  1.39s/it]
 56%|█████▌    | 34765/61904 [6:50:21<10:49:58,  1.44s/it]
 56%|█████▌    | 34766/61904 [6:50:23<10:39:17,  1.41s/it]
 56%|█████▌    | 34767/61904 [6:50:24<10:34:39,  1.40s/it]
 56%|█████▌    | 34768/61904 [6:50:25<10:20:51,  1.37s/it]
 56%|█████▌    | 34769/61904 [6:50:27<10:39:40,  1.41s/it]
 56%|█████▌    | 34770/61904 [6:50:28<10:43:24,  1.42s/it]
 56%|█████▌    | 34771/61904 [6:50:30<10:41:49,  1.42s/it]
 56%|█████▌    | 34772/61904 [6:50:31<10:51:59,  1.44s/it]
 56%|█████▌    | 34773/61904 [6:50:32<10:27:16,  1.39s/it]
 56%|█████▌    | 34774/61904 [6:50:34<10:23:42,  1.38s/it]
 56%|█████▌    | 34775/61904 [6:50:35<10:32:55,  1.40s/it]
 56%|█████▌    | 34776/61904 [6:50:37<10:45:12,  1.43s/it]
 56%|█████▌    | 34777/61904 [6:50:38<10:33:22,  1.40s/it]
 56%|█████▌    | 34778/61904 [6:50:39<10:30:00,  1.39s/it]
 56%|█████▌    | 34779/61904 [6:50:41<10:48:55,  1.44s/it]
 56%|█████▌    | 34780/61904 [6:50:42<10:36:15,  1.41s/it]
                                                          
{'loss': 2.5563, 'learning_rate': 1.4395825230130946e-07, 'epoch': 8.99}
+
 56%|█████▌    | 34780/61904 [6:50:42<10:36:15,  1.41s/it]
 56%|█████▌    | 34781/61904 [6:50:44<10:40:50,  1.42s/it]
 56%|█████▌    | 34782/61904 [6:50:45<10:32:59,  1.40s/it]
 56%|█████▌    | 34783/61904 [6:50:46<10:32:39,  1.40s/it]
 56%|█████▌    | 34784/61904 [6:50:48<10:11:42,  1.35s/it]
 56%|█████▌    | 34785/61904 [6:50:49<10:13:33,  1.36s/it]
 56%|█████▌    | 34786/61904 [6:50:51<10:27:54,  1.39s/it]
 56%|█████▌    | 34787/61904 [6:50:52<10:13:01,  1.36s/it]
 56%|█████▌    | 34788/61904 [6:50:53<10:16:28,  1.36s/it]
 56%|█████▌    | 34789/61904 [6:50:55<10:39:21,  1.41s/it]
 56%|█████▌    | 34790/61904 [6:50:56<10:43:28,  1.42s/it]
 56%|█████▌    | 34791/61904 [6:50:57<10:18:55,  1.37s/it]
 56%|█████▌    | 34792/61904 [6:50:59<10:23:56,  1.38s/it]
 56%|█████▌    | 34793/61904 [6:51:00<10:19:23,  1.37s/it]
 56%|█████▌    | 34794/61904 [6:51:02<10:14:25,  1.36s/it]
 56%|█████▌    | 34795/61904 [6:51:03<10:23:37,  1.38s/it]
 56%|█████▌    | 34796/61904 [6:51:04<10:38:35,  1.41s/it]
 56%|█████▌    | 34797/61904 [6:51:06<10:36:14,  1.41s/it]
 56%|█████▌    | 34798/61904 [6:51:07<10:50:34,  1.44s/it]
 56%|█████▌    | 34799/61904 [6:51:09<10:42:06,  1.42s/it]
 56%|█████▌    | 34800/61904 [6:51:10<10:27:09,  1.39s/it]
                                                          
{'loss': 2.5267, 'learning_rate': 1.4392583949176715e-07, 'epoch': 8.99}
+
 56%|█████▌    | 34800/61904 [6:51:10<10:27:09,  1.39s/it]
 56%|█████▌    | 34801/61904 [6:51:11<10:22:38,  1.38s/it]
 56%|█████▌    | 34802/61904 [6:51:13<10:21:32,  1.38s/it]
 56%|█████▌    | 34803/61904 [6:51:14<10:46:38,  1.43s/it]
 56%|█████▌    | 34804/61904 [6:51:16<10:36:58,  1.41s/it]
 56%|█████▌    | 34805/61904 [6:51:17<10:25:28,  1.38s/it]
 56%|█████▌    | 34806/61904 [6:51:18<10:12:44,  1.36s/it]
 56%|█████▌    | 34807/61904 [6:51:20<10:18:49,  1.37s/it]
 56%|█████▌    | 34808/61904 [6:51:21<10:24:25,  1.38s/it]
 56%|█████▌    | 34809/61904 [6:51:23<10:25:56,  1.39s/it]
 56%|█████▌    | 34810/61904 [6:51:24<10:34:20,  1.40s/it]
 56%|█████▌    | 34811/61904 [6:51:25<10:22:06,  1.38s/it]
 56%|█████▌    | 34812/61904 [6:51:27<10:42:44,  1.42s/it]
 56%|█████▌    | 34813/61904 [6:51:28<10:41:02,  1.42s/it]
 56%|█████▌    | 34814/61904 [6:51:30<10:57:28,  1.46s/it]
 56%|█████▌    | 34815/61904 [6:51:31<10:53:51,  1.45s/it]
 56%|█████▌    | 34816/61904 [6:51:33<10:34:54,  1.41s/it]
 56%|█████▌    | 34817/61904 [6:51:34<10:48:22,  1.44s/it]
 56%|█████▌    | 34818/61904 [6:51:35<10:38:55,  1.42s/it]
 56%|█████▌    | 34819/61904 [6:51:37<10:32:35,  1.40s/it]
 56%|█████▌    | 34820/61904 [6:51:38<10:28:39,  1.39s/it]
                                                          
{'loss': 2.5622, 'learning_rate': 1.438934266822248e-07, 'epoch': 9.0}
+
 56%|█████▌    | 34820/61904 [6:51:38<10:28:39,  1.39s/it]
 56%|█████▋    | 34821/61904 [6:51:39<10:17:03,  1.37s/it]
 56%|█████▋    | 34822/61904 [6:51:41<10:29:33,  1.39s/it]
 56%|█████▋    | 34823/61904 [6:51:42<10:36:15,  1.41s/it]Generation Kwargs:
+{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}
+
+
  0%|          | 0/861 [00:00<?, ?it/s]
+
  0%|          | 2/861 [00:00<06:24,  2.23it/s]
+
  0%|          | 3/861 [00:02<12:15,  1.17it/s]
+
  0%|          | 4/861 [00:03<14:21,  1.01s/it]
+
  1%|          | 5/861 [00:04<14:52,  1.04s/it]
+
  1%|          | 6/861 [00:06<16:31,  1.16s/it]
+
  1%|          | 7/861 [00:06<14:52,  1.04s/it]
+
  1%|          | 8/861 [00:08<16:00,  1.13s/it]
+
  1%|          | 9/861 [00:08<14:15,  1.00s/it]
+
  1%|          | 10/861 [00:09<13:53,  1.02it/s]
+
  1%|▏         | 11/861 [00:11<15:19,  1.08s/it]
+
  1%|▏         | 12/861 [00:12<15:43,  1.11s/it]
+
  2%|▏         | 13/861 [00:13<14:26,  1.02s/it]
+
  2%|▏         | 14/861 [00:13<11:20,  1.24it/s]
+
  2%|▏         | 15/861 [00:14<11:15,  1.25it/s]
+
  2%|▏         | 16/861 [00:14<09:21,  1.51it/s]
+
  2%|▏         | 17/861 [00:15<12:26,  1.13it/s]
+
  2%|▏         | 18/861 [00:16<09:33,  1.47it/s]
+
  2%|▏         | 19/861 [00:16<08:49,  1.59it/s]
+
  2%|▏         | 20/861 [00:17<10:18,  1.36it/s]
+
  2%|▏         | 21/861 [00:19<13:59,  1.00it/s]
+
  3%|▎         | 22/861 [00:20<14:55,  1.07s/it]
+
  3%|▎         | 23/861 [00:20<11:37,  1.20it/s]
+
  3%|▎         | 24/861 [00:21<11:23,  1.23it/s]
+
  3%|▎         | 25/861 [00:22<12:01,  1.16it/s]
+
  3%|▎         | 26/861 [00:23<13:00,  1.07it/s]
+
  3%|▎         | 27/861 [00:24<14:22,  1.03s/it]
+
  3%|▎         | 28/861 [00:27<20:22,  1.47s/it]
+
  3%|▎         | 29/861 [00:27<15:32,  1.12s/it]
+
  3%|▎         | 30/861 [00:29<17:08,  1.24s/it]
+
  4%|▎         | 31/861 [00:29<13:53,  1.00s/it]
+
  4%|▎         | 32/861 [00:30<11:09,  1.24it/s]
+
  4%|▍         | 33/861 [00:30<11:30,  1.20it/s]
+
  4%|▍         | 34/861 [00:31<11:53,  1.16it/s]
+
  4%|▍         | 35/861 [00:33<14:52,  1.08s/it]
+
  4%|▍         | 36/861 [00:34<14:03,  1.02s/it]
+
  4%|▍         | 37/861 [00:35<13:35,  1.01it/s]
+
  4%|▍         | 38/861 [00:36<14:32,  1.06s/it]
+
  5%|▍         | 39/861 [00:37<13:14,  1.03it/s]
+
  5%|▍         | 40/861 [00:38<12:28,  1.10it/s]
+
  5%|▍         | 41/861 [00:38<10:16,  1.33it/s]
+
  5%|▍         | 42/861 [00:39<11:19,  1.21it/s]
+
  5%|▍         | 43/861 [00:40<12:06,  1.13it/s]
+
  5%|▌         | 44/861 [00:41<11:54,  1.14it/s]
+
  5%|▌         | 45/861 [00:42<12:02,  1.13it/s]
+
  5%|▌         | 46/861 [00:44<17:18,  1.27s/it]
+
  5%|▌         | 47/861 [00:45<16:44,  1.23s/it]
+
  6%|▌         | 48/861 [00:47<19:15,  1.42s/it]
+
  6%|▌         | 49/861 [00:48<18:37,  1.38s/it]
+
  6%|▌         | 50/861 [00:48<13:55,  1.03s/it]
+
  6%|▌         | 51/861 [00:49<13:42,  1.02s/it]
+
  6%|▌         | 52/861 [00:50<12:05,  1.12it/s]
+
  6%|▌         | 53/861 [00:50<09:51,  1.37it/s]
+
  6%|▋         | 54/861 [00:51<08:03,  1.67it/s]
+
  6%|▋         | 55/861 [00:51<07:58,  1.69it/s]
+
  7%|▋         | 56/861 [00:53<11:37,  1.15it/s]
+
  7%|▋         | 57/861 [00:53<09:54,  1.35it/s]
+
  7%|▋         | 58/861 [00:53<08:07,  1.65it/s]
+
  7%|▋         | 59/861 [00:54<08:50,  1.51it/s]
+
  7%|▋         | 60/861 [00:55<08:43,  1.53it/s]
+
  7%|▋         | 61/861 [00:55<07:48,  1.71it/s]
+
  7%|▋         | 62/861 [00:56<06:57,  1.91it/s]
+
  7%|▋         | 63/861 [00:56<06:34,  2.02it/s]
+
  7%|▋         | 64/861 [00:57<06:44,  1.97it/s]
+
  8%|▊         | 65/861 [00:57<06:29,  2.04it/s]
+
  8%|▊         | 66/861 [00:58<06:23,  2.07it/s]
+
  8%|▊         | 67/861 [00:58<07:36,  1.74it/s]
+
  8%|▊         | 68/861 [00:59<09:15,  1.43it/s]
+
  8%|▊         | 69/861 [01:00<10:52,  1.21it/s]
+
  8%|▊         | 70/861 [01:02<13:30,  1.02s/it]
+
  8%|▊         | 71/861 [01:03<14:37,  1.11s/it]
+
  8%|▊         | 72/861 [01:04<13:50,  1.05s/it]
+
  8%|▊         | 73/861 [01:04<10:43,  1.22it/s]
+
  9%|▊         | 74/861 [01:05<10:10,  1.29it/s]
+
  9%|▊         | 75/861 [01:06<11:21,  1.15it/s]
+
  9%|▉         | 76/861 [01:07<12:22,  1.06it/s]
+
  9%|▉         | 77/861 [01:08<12:33,  1.04it/s]
+
  9%|▉         | 78/861 [01:09<11:29,  1.14it/s]
+
  9%|▉         | 79/861 [01:10<12:07,  1.07it/s]
+
  9%|▉         | 80/861 [01:11<10:28,  1.24it/s]
+
  9%|▉         | 81/861 [01:11<10:53,  1.19it/s]
+
 10%|▉         | 82/861 [01:12<09:42,  1.34it/s]
+
 10%|▉         | 83/861 [01:13<09:41,  1.34it/s]
+
 10%|▉         | 84/861 [01:14<11:56,  1.09it/s]
+
 10%|▉         | 85/861 [01:15<11:02,  1.17it/s]
+
 10%|▉         | 86/861 [01:15<09:32,  1.35it/s]
+
 10%|█         | 87/861 [01:16<11:08,  1.16it/s]
+
 10%|█         | 88/861 [01:17<08:47,  1.47it/s]
+
 10%|█         | 89/861 [01:17<08:43,  1.47it/s]
+
 10%|█         | 90/861 [01:19<13:25,  1.05s/it]
+
 11%|█         | 91/861 [01:21<14:53,  1.16s/it]
+
 11%|█         | 92/861 [01:21<13:28,  1.05s/it]
+
 11%|█         | 93/861 [01:22<13:18,  1.04s/it]
+
 11%|█         | 94/861 [01:23<10:12,  1.25it/s]
+
 11%|█         | 95/861 [01:23<09:21,  1.36it/s]
+
 11%|█         | 96/861 [01:24<10:00,  1.27it/s]
+
 11%|█▏        | 97/861 [01:25<11:46,  1.08it/s]
+
 11%|█▏        | 98/861 [01:26<11:34,  1.10it/s]
+
 11%|█▏        | 99/861 [01:28<15:01,  1.18s/it]
+
 12%|█▏        | 100/861 [01:29<12:34,  1.01it/s]
+
 12%|█▏        | 101/861 [01:29<11:00,  1.15it/s]
+
 12%|█▏        | 102/861 [01:30<10:07,  1.25it/s]
+
 12%|█▏        | 103/861 [01:30<08:31,  1.48it/s]
+
 12%|█▏        | 104/861 [01:31<10:29,  1.20it/s]
+
 12%|█▏        | 105/861 [01:33<11:42,  1.08it/s]
+
 12%|█▏        | 106/861 [01:33<10:17,  1.22it/s]
+
 12%|█▏        | 107/861 [01:34<09:12,  1.36it/s]
+
 13%|█▎        | 108/861 [01:34<07:21,  1.71it/s]
+
 13%|█▎        | 109/861 [01:34<06:08,  2.04it/s]
+
 13%|█▎        | 110/861 [01:35<06:48,  1.84it/s]
+
 13%|█▎        | 111/861 [01:36<09:28,  1.32it/s]
+
 13%|█▎        | 112/861 [01:37<07:54,  1.58it/s]
+
 13%|█▎        | 113/861 [01:37<08:34,  1.45it/s]
+
 13%|█▎        | 114/861 [01:38<09:38,  1.29it/s]
+
 13%|█▎        | 115/861 [01:39<08:17,  1.50it/s]
+
 13%|█▎        | 116/861 [01:39<07:05,  1.75it/s]
+
 14%|█▎        | 117/861 [01:40<09:44,  1.27it/s]
+
 14%|█▎        | 118/861 [01:41<09:35,  1.29it/s]
+
 14%|█▍        | 119/861 [01:42<08:53,  1.39it/s]
+
 14%|█▍        | 120/861 [01:42<06:58,  1.77it/s]
+
 14%|█▍        | 121/861 [01:43<08:26,  1.46it/s]
+
 14%|█▍        | 122/861 [01:44<10:19,  1.19it/s]
+
 14%|█▍        | 123/861 [01:45<09:28,  1.30it/s]
+
 14%|█▍        | 124/861 [01:46<12:12,  1.01it/s]
+
 15%|█▍        | 125/861 [01:47<11:18,  1.08it/s]
+
 15%|█▍        | 126/861 [01:48<12:22,  1.01s/it]
+
 15%|█▍        | 127/861 [01:49<12:27,  1.02s/it]
+
 15%|█▍        | 128/861 [01:50<10:24,  1.17it/s]
+
 15%|█▍        | 129/861 [01:51<11:00,  1.11it/s]
+
 15%|█▌        | 130/861 [01:51<10:40,  1.14it/s]
+
 15%|█▌        | 131/861 [01:52<10:37,  1.14it/s]
+
 15%|█▌        | 132/861 [01:53<10:32,  1.15it/s]
+
 15%|█▌        | 133/861 [01:54<10:54,  1.11it/s]
+
 16%|█▌        | 134/861 [01:54<08:16,  1.47it/s]
+
 16%|█▌        | 135/861 [01:55<07:19,  1.65it/s]
+
 16%|█▌        | 136/861 [01:55<06:39,  1.82it/s]
+
 16%|█▌        | 137/861 [01:56<05:44,  2.10it/s]
+
 16%|█▌        | 138/861 [01:56<05:33,  2.17it/s]
+
 16%|█▌        | 139/861 [01:56<05:31,  2.18it/s]
+
 16%|█▋        | 140/861 [01:57<05:20,  2.25it/s]
+
 16%|█▋        | 141/861 [01:57<05:12,  2.30it/s]
+
 16%|█▋        | 142/861 [01:58<05:03,  2.37it/s]
+
 17%|█▋        | 143/861 [01:59<07:59,  1.50it/s]
+
 17%|█▋        | 144/861 [02:00<11:27,  1.04it/s]
+
 17%|█▋        | 145/861 [02:01<09:45,  1.22it/s]
+
 17%|█▋        | 146/861 [02:02<09:12,  1.29it/s]
+
 17%|█▋        | 147/861 [02:02<09:15,  1.28it/s]
+
 17%|█▋        | 148/861 [02:03<08:10,  1.45it/s]
+
 17%|█▋        | 149/861 [02:03<07:04,  1.68it/s]
+
 17%|█▋        | 150/861 [02:05<11:30,  1.03it/s]
+
 18%|█▊        | 151/861 [02:07<13:22,  1.13s/it]
+
 18%|█▊        | 152/861 [02:08<13:00,  1.10s/it]
+
 18%|█▊        | 153/861 [02:09<12:41,  1.08s/it]
+
 18%|█▊        | 154/861 [02:09<11:11,  1.05it/s]
+
 18%|█▊        | 155/861 [02:11<13:29,  1.15s/it]
+
 18%|█▊        | 156/861 [02:12<13:41,  1.17s/it]
+
 18%|█▊        | 157/861 [02:13<11:27,  1.02it/s]
+
 18%|█▊        | 158/861 [02:14<12:03,  1.03s/it]
+
 18%|█▊        | 159/861 [02:15<10:54,  1.07it/s]
+
 19%|█▊        | 160/861 [02:15<10:24,  1.12it/s]
+
 19%|█▊        | 161/861 [02:17<14:27,  1.24s/it]
+
 19%|█▉        | 162/861 [02:18<11:03,  1.05it/s]
+
 19%|█▉        | 163/861 [02:18<08:30,  1.37it/s]
+
 19%|█▉        | 164/861 [02:19<10:43,  1.08it/s]
+
 19%|█▉        | 165/861 [02:20<10:22,  1.12it/s]
+
 19%|█▉        | 166/861 [02:21<10:14,  1.13it/s]
+
 19%|█▉        | 167/861 [02:21<07:58,  1.45it/s]
+
 20%|█▉        | 168/861 [02:22<06:47,  1.70it/s]
+
 20%|█▉        | 169/861 [02:22<07:38,  1.51it/s]
+
 20%|█▉        | 170/861 [02:23<08:08,  1.42it/s]
+
 20%|█▉        | 171/861 [02:24<08:25,  1.36it/s]
+
 20%|█▉        | 172/861 [02:24<07:30,  1.53it/s]
+
 20%|██        | 173/861 [02:25<07:35,  1.51it/s]
+
 20%|██        | 174/861 [02:27<11:52,  1.04s/it]
+
 20%|██        | 175/861 [02:28<10:47,  1.06it/s]
+
 20%|██        | 176/861 [02:28<08:15,  1.38it/s]
+
 21%|██        | 177/861 [02:29<08:31,  1.34it/s]
+
 21%|██        | 178/861 [02:30<09:22,  1.22it/s]
+
 21%|██        | 179/861 [02:31<09:01,  1.26it/s]
+
 21%|██        | 180/861 [02:31<08:16,  1.37it/s]
+
 21%|██        | 181/861 [02:31<07:05,  1.60it/s]
+
 21%|██        | 182/861 [02:32<05:47,  1.95it/s]
+
 21%|██▏       | 183/861 [02:33<07:45,  1.46it/s]
+
 21%|██▏       | 184/861 [02:34<10:06,  1.12it/s]
+
 21%|██▏       | 185/861 [02:35<08:45,  1.29it/s]
+
 22%|██▏       | 186/861 [02:35<07:39,  1.47it/s]
+
 22%|██▏       | 187/861 [02:36<08:36,  1.31it/s]
+
 22%|██▏       | 188/861 [02:37<09:31,  1.18it/s]
+
 22%|██▏       | 189/861 [02:38<11:09,  1.00it/s]
+
 22%|██▏       | 190/861 [02:39<10:46,  1.04it/s]
+
 22%|██▏       | 191/861 [02:40<09:07,  1.22it/s]
+
 22%|██▏       | 192/861 [02:41<08:35,  1.30it/s]
+
 22%|██▏       | 193/861 [02:42<10:27,  1.06it/s]
+
 23%|██▎       | 194/861 [02:42<09:06,  1.22it/s]
+
 23%|██▎       | 195/861 [02:43<07:51,  1.41it/s]
+
 23%|██▎       | 196/861 [02:43<07:19,  1.51it/s]
+
 23%|██▎       | 197/861 [02:44<07:24,  1.49it/s]
+
 23%|██▎       | 198/861 [02:45<06:35,  1.68it/s]
+
 23%|██▎       | 199/861 [02:46<08:55,  1.24it/s]
+
 23%|██▎       | 200/861 [02:47<09:03,  1.22it/s]
+
 23%|██▎       | 201/861 [02:48<09:45,  1.13it/s]
+
 23%|██▎       | 202/861 [02:49<09:36,  1.14it/s]
+
 24%|██▎       | 203/861 [02:49<07:39,  1.43it/s]
+
 24%|██▎       | 204/861 [02:49<06:04,  1.80it/s]
+
 24%|██▍       | 205/861 [02:49<05:34,  1.96it/s]
+
 24%|██▍       | 206/861 [02:50<06:34,  1.66it/s]
+
 24%|██▍       | 207/861 [02:51<06:51,  1.59it/s]
+
 24%|██▍       | 208/861 [02:51<06:29,  1.68it/s]
+
 24%|██▍       | 209/861 [02:52<07:15,  1.50it/s]
+
 24%|██▍       | 210/861 [02:53<07:48,  1.39it/s]
+
 25%|██▍       | 211/861 [02:55<10:18,  1.05it/s]
+
 25%|██▍       | 212/861 [02:56<10:19,  1.05it/s]
+
 25%|██▍       | 213/861 [02:56<08:45,  1.23it/s]
+
 25%|██▍       | 214/861 [02:57<07:54,  1.36it/s]
+
 25%|██▍       | 215/861 [02:58<08:40,  1.24it/s]
+
 25%|██▌       | 216/861 [02:58<07:26,  1.45it/s]
+
 25%|██▌       | 217/861 [02:58<06:05,  1.76it/s]
+
 25%|██▌       | 218/861 [02:59<05:32,  1.94it/s]
+
 25%|██▌       | 219/861 [03:00<06:53,  1.55it/s]
+
 26%|██▌       | 220/861 [03:00<07:14,  1.47it/s]
+
 26%|██▌       | 221/861 [03:01<06:28,  1.65it/s]
+
 26%|██▌       | 222/861 [03:02<08:42,  1.22it/s]
+
 26%|██▌       | 223/861 [03:03<07:35,  1.40it/s]
+
 26%|██▌       | 224/861 [03:03<07:01,  1.51it/s]
+
 26%|██▌       | 225/861 [03:05<09:32,  1.11it/s]
+
 26%|██▌       | 226/861 [03:06<12:17,  1.16s/it]
+
 26%|██▋       | 227/861 [03:07<11:16,  1.07s/it]
+
 26%|██▋       | 228/861 [03:08<10:01,  1.05it/s]
+
 27%|██▋       | 229/861 [03:08<08:37,  1.22it/s]
+
 27%|██▋       | 230/861 [03:09<09:06,  1.15it/s]
+
 27%|██▋       | 231/861 [03:12<13:39,  1.30s/it]
+
 27%|██▋       | 232/861 [03:12<10:09,  1.03it/s]
+
 27%|██▋       | 233/861 [03:13<09:20,  1.12it/s]
+
 27%|██▋       | 234/861 [03:13<08:18,  1.26it/s]
+
 27%|██▋       | 235/861 [03:14<08:25,  1.24it/s]
+
 27%|██▋       | 236/861 [03:15<08:08,  1.28it/s]
+
 28%|██▊       | 237/861 [03:16<08:11,  1.27it/s]
+
 28%|██▊       | 238/861 [03:16<06:38,  1.56it/s]
+
 28%|██▊       | 239/861 [03:17<09:22,  1.11it/s]
+
 28%|██▊       | 240/861 [03:18<09:09,  1.13it/s]
+
 28%|██▊       | 241/861 [03:20<10:41,  1.03s/it]
+
 28%|██▊       | 242/861 [03:20<09:07,  1.13it/s]
+
 28%|██▊       | 243/861 [03:21<08:41,  1.19it/s]
+
 28%|██▊       | 244/861 [03:22<08:29,  1.21it/s]
+
 28%|██▊       | 245/861 [03:23<09:18,  1.10it/s]
+
 29%|██▊       | 246/861 [03:24<09:07,  1.12it/s]
+
 29%|██▊       | 247/861 [03:24<07:07,  1.44it/s]
+
 29%|██▉       | 248/861 [03:24<05:30,  1.85it/s]
+
 29%|██▉       | 249/861 [03:25<06:35,  1.55it/s]
+
 29%|██▉       | 250/861 [03:26<07:14,  1.41it/s]
+
 29%|██▉       | 251/861 [03:27<07:34,  1.34it/s]
+
 29%|██▉       | 252/861 [03:27<07:13,  1.40it/s]
+
 29%|██▉       | 253/861 [03:28<06:32,  1.55it/s]
+
 30%|██▉       | 254/861 [03:28<05:22,  1.88it/s]
+
 30%|██▉       | 255/861 [03:29<05:55,  1.70it/s]
+
 30%|██▉       | 256/861 [03:30<08:00,  1.26it/s]
+
 30%|██▉       | 257/861 [03:31<08:18,  1.21it/s]
+
 30%|██▉       | 258/861 [03:32<09:19,  1.08it/s]
+
 30%|███       | 259/861 [03:33<10:18,  1.03s/it]
+
 30%|███       | 260/861 [03:34<10:27,  1.04s/it]
+
 30%|███       | 261/861 [03:37<15:47,  1.58s/it]
+
 30%|███       | 262/861 [03:38<12:52,  1.29s/it]
+
 31%|███       | 263/861 [03:38<09:31,  1.05it/s]
+
 31%|███       | 264/861 [03:39<08:30,  1.17it/s]
+
 31%|███       | 265/861 [03:39<07:21,  1.35it/s]
+
 31%|███       | 266/861 [03:40<06:31,  1.52it/s]
+
 31%|███       | 267/861 [03:40<06:01,  1.64it/s]
+
 31%|███       | 268/861 [03:41<06:02,  1.64it/s]
+
 31%|███       | 269/861 [03:41<05:59,  1.65it/s]
+
 31%|███▏      | 270/861 [03:42<06:32,  1.51it/s]
+
 31%|███▏      | 271/861 [03:43<06:48,  1.45it/s]
+
 32%|███▏      | 272/861 [03:44<08:33,  1.15it/s]
+
 32%|███▏      | 273/861 [03:45<08:52,  1.11it/s]
+
 32%|███▏      | 274/861 [03:51<23:21,  2.39s/it]
+
 32%|███▏      | 275/861 [03:51<17:01,  1.74s/it]
+
 32%|███▏      | 276/861 [03:52<14:37,  1.50s/it]
+
 32%|███▏      | 277/861 [03:55<17:49,  1.83s/it]
+
 32%|███▏      | 278/861 [03:56<16:18,  1.68s/it]
+
 32%|███▏      | 279/861 [03:57<14:00,  1.44s/it]
+
 33%|███▎      | 280/861 [03:58<12:37,  1.30s/it]
+
 33%|███▎      | 281/861 [03:59<11:47,  1.22s/it]
+
 33%|███▎      | 282/861 [04:00<10:32,  1.09s/it]
+
 33%|███▎      | 283/861 [04:00<09:14,  1.04it/s]
+
 33%|███▎      | 284/861 [04:01<07:29,  1.28it/s]
+
 33%|███▎      | 285/861 [04:01<07:02,  1.36it/s]
+
 33%|███▎      | 286/861 [04:03<10:47,  1.13s/it]
+
 33%|███▎      | 287/861 [04:05<12:22,  1.29s/it]
+
 33%|███▎      | 288/861 [04:06<11:40,  1.22s/it]
+
 34%|███▎      | 289/861 [04:07<10:06,  1.06s/it]
+
 34%|███▎      | 290/861 [04:08<09:09,  1.04it/s]
+
 34%|███▍      | 291/861 [04:08<08:30,  1.12it/s]
+
 34%|███▍      | 292/861 [04:10<10:08,  1.07s/it]
+
 34%|███▍      | 293/861 [04:11<09:05,  1.04it/s]
+
 34%|███▍      | 294/861 [04:12<09:27,  1.00s/it]
+
 34%|███▍      | 295/861 [04:12<07:20,  1.28it/s]
+
 34%|███▍      | 296/861 [04:13<06:55,  1.36it/s]
+
 34%|███▍      | 297/861 [04:14<08:55,  1.05it/s]
+
 35%|███▍      | 298/861 [04:16<12:04,  1.29s/it]
+
 35%|███▍      | 299/861 [04:18<14:10,  1.51s/it]
+
 35%|███▍      | 300/861 [04:19<12:03,  1.29s/it]
+
 35%|███▍      | 301/861 [04:21<14:50,  1.59s/it]
+
 35%|███▌      | 302/861 [04:21<11:04,  1.19s/it]
+
 35%|███▌      | 303/861 [04:23<11:40,  1.26s/it]
+
 35%|███▌      | 304/861 [04:24<11:07,  1.20s/it]
+
 35%|███▌      | 305/861 [04:25<11:33,  1.25s/it]
+
 36%|███▌      | 306/861 [04:27<12:22,  1.34s/it]
+
 36%|███▌      | 307/861 [04:29<13:37,  1.47s/it]
+
 36%|███▌      | 308/861 [04:29<10:08,  1.10s/it]
+
 36%|███▌      | 309/861 [04:30<10:13,  1.11s/it]
+
 36%|███▌      | 310/861 [04:31<10:22,  1.13s/it]
+
 36%|███▌      | 311/861 [04:32<10:29,  1.14s/it]
+
 36%|███▌      | 312/861 [04:33<10:26,  1.14s/it]
+
 36%|███▋      | 313/861 [04:35<11:04,  1.21s/it]
+
 36%|███▋      | 314/861 [04:36<10:19,  1.13s/it]
+
 37%|███▋      | 315/861 [04:36<08:49,  1.03it/s]
+
 37%|███▋      | 316/861 [04:38<10:24,  1.15s/it]
+
 37%|███▋      | 317/861 [04:38<07:52,  1.15it/s]
+
 37%|███▋      | 318/861 [04:40<11:30,  1.27s/it]
+
 37%|███▋      | 319/861 [04:42<12:33,  1.39s/it]
+
 37%|███▋      | 320/861 [04:43<10:59,  1.22s/it]
+
 37%|███▋      | 321/861 [04:44<11:23,  1.27s/it]
+
 37%|███▋      | 322/861 [04:46<13:32,  1.51s/it]
+
 38%|███▊      | 323/861 [04:47<11:43,  1.31s/it]
+
 38%|███▊      | 324/861 [04:48<11:49,  1.32s/it]
+
 38%|███▊      | 325/861 [04:50<11:26,  1.28s/it]
+
 38%|███▊      | 326/861 [04:50<08:36,  1.04it/s]
+
 38%|███▊      | 327/861 [04:51<08:12,  1.08it/s]
+
 38%|███▊      | 328/861 [04:52<08:12,  1.08it/s]
+
 38%|███▊      | 329/861 [04:53<09:15,  1.04s/it]
+
 38%|███▊      | 330/861 [04:54<08:41,  1.02it/s]
+
 38%|███▊      | 331/861 [04:57<15:48,  1.79s/it]
+
 39%|███▊      | 332/861 [04:58<13:15,  1.50s/it]
+
 39%|███▊      | 333/861 [05:00<13:50,  1.57s/it]
+
 39%|███▉      | 334/861 [05:02<14:07,  1.61s/it]
+
 39%|███▉      | 335/861 [05:03<12:55,  1.47s/it]
+
 39%|███▉      | 336/861 [05:04<12:14,  1.40s/it]
+
 39%|███▉      | 337/861 [05:05<10:05,  1.16s/it]
+
 39%|███▉      | 338/861 [05:07<12:46,  1.47s/it]
+
 39%|███▉      | 339/861 [05:08<11:44,  1.35s/it]
+
 39%|███▉      | 340/861 [05:09<10:08,  1.17s/it]
+
 40%|███▉      | 341/861 [05:09<07:51,  1.10it/s]
+
 40%|███▉      | 342/861 [05:10<07:15,  1.19it/s]
+
 40%|███▉      | 343/861 [05:11<07:25,  1.16it/s]
+
 40%|███▉      | 344/861 [05:11<06:13,  1.38it/s]
+
 40%|████      | 345/861 [05:12<06:51,  1.25it/s]
+
 40%|████      | 346/861 [05:13<07:22,  1.16it/s]
+
 40%|████      | 347/861 [05:13<06:10,  1.39it/s]
+
 40%|████      | 348/861 [05:14<05:45,  1.49it/s]
+
 41%|████      | 349/861 [05:15<06:18,  1.35it/s]
+
 41%|████      | 350/861 [05:16<06:48,  1.25it/s]
+
 41%|████      | 351/861 [05:16<06:19,  1.34it/s]
+
 41%|████      | 352/861 [05:17<06:26,  1.32it/s]
+
 41%|████      | 353/861 [05:18<06:13,  1.36it/s]
+
 41%|████      | 354/861 [05:19<06:05,  1.39it/s]
+
 41%|████      | 355/861 [05:19<05:21,  1.57it/s]
+
 41%|████▏     | 356/861 [05:19<04:48,  1.75it/s]
+
 41%|████▏     | 357/861 [05:20<04:03,  2.07it/s]
+
 42%|████▏     | 358/861 [05:20<04:15,  1.97it/s]
+
 42%|████▏     | 359/861 [05:22<06:31,  1.28it/s]
+
 42%|████▏     | 360/861 [05:23<06:42,  1.24it/s]
+
 42%|████▏     | 361/861 [05:23<06:46,  1.23it/s]
+
 42%|████▏     | 362/861 [05:24<07:21,  1.13it/s]
+
 42%|████▏     | 363/861 [05:25<06:53,  1.20it/s]
+
 42%|████▏     | 364/861 [05:26<06:24,  1.29it/s]
+
 42%|████▏     | 365/861 [05:28<10:49,  1.31s/it]
+
 43%|████▎     | 366/861 [05:29<09:44,  1.18s/it]
+
 43%|████▎     | 367/861 [05:31<11:02,  1.34s/it]
+
 43%|████▎     | 368/861 [05:32<09:54,  1.21s/it]
+
 43%|████▎     | 369/861 [05:33<09:22,  1.14s/it]
+
 43%|████▎     | 370/861 [05:34<08:18,  1.02s/it]
+
 43%|████▎     | 371/861 [05:34<07:34,  1.08it/s]
+
 43%|████▎     | 372/861 [05:35<07:36,  1.07it/s]
+
 43%|████▎     | 373/861 [05:36<06:47,  1.20it/s]
+
 43%|████▎     | 374/861 [05:38<10:07,  1.25s/it]
+
 44%|████▎     | 375/861 [05:40<11:57,  1.48s/it]
+
 44%|████▎     | 376/861 [05:41<09:49,  1.22s/it]
+
 44%|████▍     | 377/861 [05:42<11:08,  1.38s/it]
+
 44%|████▍     | 378/861 [05:44<12:32,  1.56s/it]
+
 44%|████▍     | 379/861 [05:45<09:15,  1.15s/it]
+
 44%|████▍     | 380/861 [05:45<08:27,  1.06s/it]
+
 44%|████▍     | 381/861 [05:46<07:52,  1.01it/s]
+
 44%|████▍     | 382/861 [05:47<07:45,  1.03it/s]
+
 44%|████▍     | 383/861 [05:48<07:28,  1.07it/s]
+
 45%|████▍     | 384/861 [05:49<07:09,  1.11it/s]
+
 45%|████▍     | 385/861 [05:49<05:43,  1.38it/s]
+
 45%|████▍     | 386/861 [05:50<05:49,  1.36it/s]
+
 45%|████▍     | 387/861 [05:51<07:52,  1.00it/s]
+
 45%|████▌     | 388/861 [05:52<07:19,  1.08it/s]
+
 45%|████▌     | 389/861 [05:53<06:05,  1.29it/s]
+
 45%|████▌     | 390/861 [05:53<05:40,  1.38it/s]
+
 45%|████▌     | 391/861 [05:54<06:25,  1.22it/s]
+
 46%|████▌     | 392/861 [05:55<05:53,  1.33it/s]
+
 46%|████▌     | 393/861 [05:56<07:01,  1.11it/s]
+
 46%|████▌     | 394/861 [05:58<08:29,  1.09s/it]
+
 46%|████▌     | 395/861 [05:58<07:12,  1.08it/s]
+
 46%|████▌     | 396/861 [05:59<07:52,  1.02s/it]
+
 46%|████▌     | 397/861 [06:00<05:59,  1.29it/s]
+
 46%|████▌     | 398/861 [06:00<05:43,  1.35it/s]
+
 46%|████▋     | 399/861 [06:02<06:54,  1.12it/s]
+
 46%|████▋     | 400/861 [06:03<07:43,  1.01s/it]
+
 47%|████▋     | 401/861 [06:03<06:22,  1.20it/s]
+
 47%|████▋     | 402/861 [06:04<06:15,  1.22it/s]
+
 47%|████▋     | 403/861 [06:05<06:09,  1.24it/s]
+
 47%|████▋     | 404/861 [06:06<06:23,  1.19it/s]
+
 47%|████▋     | 405/861 [06:06<05:22,  1.41it/s]
+
 47%|████▋     | 406/861 [06:07<06:18,  1.20it/s]
+
 47%|████▋     | 407/861 [06:08<06:34,  1.15it/s]
+
 47%|████▋     | 408/861 [06:09<06:07,  1.23it/s]
+
 48%|████▊     | 409/861 [06:10<05:38,  1.34it/s]
+
 48%|████▊     | 410/861 [06:10<05:42,  1.32it/s]
+
 48%|████▊     | 411/861 [06:11<04:50,  1.55it/s]
+
 48%|████▊     | 412/861 [06:12<05:24,  1.39it/s]
+
 48%|████▊     | 413/861 [06:12<05:19,  1.40it/s]
+
 48%|████▊     | 414/861 [06:13<04:48,  1.55it/s]
+
 48%|████▊     | 415/861 [06:13<04:14,  1.76it/s]
+
 48%|████▊     | 416/861 [06:14<04:27,  1.67it/s]
+
 48%|████▊     | 417/861 [06:15<04:45,  1.55it/s]
+
 49%|████▊     | 418/861 [06:15<04:51,  1.52it/s]
+
 49%|████▊     | 419/861 [06:16<05:14,  1.41it/s]
+
 49%|████▉     | 420/861 [06:17<05:28,  1.34it/s]
+
 49%|████▉     | 421/861 [06:17<04:56,  1.48it/s]
+
 49%|████▉     | 422/861 [06:18<04:13,  1.73it/s]
+
 49%|████▉     | 423/861 [06:19<05:02,  1.45it/s]
+
 49%|████▉     | 424/861 [06:19<04:30,  1.62it/s]
+
 49%|████▉     | 425/861 [06:20<04:56,  1.47it/s]
+
 49%|████▉     | 426/861 [06:21<05:44,  1.26it/s]
+
 50%|████▉     | 427/861 [06:22<05:54,  1.23it/s]
+
 50%|████▉     | 428/861 [06:23<05:34,  1.29it/s]
+
 50%|████▉     | 429/861 [06:23<05:37,  1.28it/s]
+
 50%|████▉     | 430/861 [06:25<06:38,  1.08it/s]
+
 50%|█████     | 431/861 [06:26<07:45,  1.08s/it]
+
 50%|█████     | 432/861 [06:27<07:42,  1.08s/it]
+
 50%|█████     | 433/861 [06:28<08:02,  1.13s/it]
+
 50%|█████     | 434/861 [06:29<06:32,  1.09it/s]
+
 51%|█████     | 435/861 [06:29<05:02,  1.41it/s]
+
 51%|█████     | 436/861 [06:29<04:06,  1.73it/s]
+
 51%|█████     | 437/861 [06:30<03:57,  1.79it/s]
+
 51%|█████     | 438/861 [06:31<04:21,  1.62it/s]
+
 51%|█████     | 439/861 [06:31<04:15,  1.65it/s]
+
 51%|█████     | 440/861 [06:32<03:34,  1.97it/s]
+
 51%|█████     | 441/861 [06:32<03:08,  2.23it/s]
+
 51%|█████▏    | 442/861 [06:32<03:15,  2.14it/s]
+
 51%|█████▏    | 443/861 [06:33<03:39,  1.90it/s]
+
 52%|█████▏    | 444/861 [06:33<03:29,  1.99it/s]
+
 52%|█████▏    | 445/861 [06:34<03:06,  2.23it/s]
+
 52%|█████▏    | 446/861 [06:34<02:58,  2.33it/s]
+
 52%|█████▏    | 447/861 [06:35<04:05,  1.68it/s]
+
 52%|█████▏    | 448/861 [06:36<04:56,  1.39it/s]
+
 52%|█████▏    | 449/861 [06:37<05:40,  1.21it/s]
+
 52%|█████▏    | 450/861 [06:38<06:02,  1.13it/s]
+
 52%|█████▏    | 451/861 [06:39<05:14,  1.30it/s]
+
 52%|█████▏    | 452/861 [06:39<04:59,  1.37it/s]
+
 53%|█████▎    | 453/861 [06:40<04:25,  1.53it/s]
+
 53%|█████▎    | 454/861 [06:41<04:39,  1.46it/s]
+
 53%|█████▎    | 455/861 [06:41<04:02,  1.68it/s]
+
 53%|█████▎    | 456/861 [06:42<03:52,  1.74it/s]
+
 53%|█████▎    | 457/861 [06:42<03:45,  1.79it/s]
+
 53%|█████▎    | 458/861 [06:43<04:38,  1.45it/s]
+
 53%|█████▎    | 459/861 [06:43<03:57,  1.69it/s]
+
 53%|█████▎    | 460/861 [06:44<04:18,  1.55it/s]
+
 54%|█████▎    | 461/861 [06:45<05:02,  1.32it/s]
+
 54%|█████▎    | 462/861 [06:46<04:34,  1.45it/s]
+
 54%|█████▍    | 463/861 [06:47<05:00,  1.32it/s]
+
 54%|█████▍    | 464/861 [06:47<04:23,  1.51it/s]
+
 54%|█████▍    | 465/861 [06:47<03:26,  1.91it/s]
+
 54%|█████▍    | 466/861 [06:48<03:26,  1.92it/s]
+
 54%|█████▍    | 467/861 [06:49<05:10,  1.27it/s]
+
 54%|█████▍    | 468/861 [06:50<04:13,  1.55it/s]
+
 54%|█████▍    | 469/861 [06:50<04:26,  1.47it/s]
+
 55%|█████▍    | 470/861 [06:51<04:27,  1.46it/s]
+
 55%|█████▍    | 471/861 [06:52<04:22,  1.49it/s]
+
 55%|█████▍    | 472/861 [06:52<04:05,  1.58it/s]
+
 55%|█████▍    | 473/861 [06:53<03:59,  1.62it/s]
+
 55%|█████▌    | 474/861 [06:53<03:34,  1.81it/s]
+
 55%|█████▌    | 475/861 [06:54<03:50,  1.67it/s]
+
 55%|█████▌    | 476/861 [06:54<03:24,  1.88it/s]
+
 55%|█████▌    | 477/861 [06:55<04:04,  1.57it/s]
+
 56%|█████▌    | 478/861 [06:56<03:46,  1.69it/s]
+
 56%|█████▌    | 479/861 [06:56<03:04,  2.07it/s]
+
 56%|█████▌    | 480/861 [06:57<03:51,  1.65it/s]
+
 56%|█████▌    | 481/861 [06:57<03:22,  1.88it/s]
+
 56%|█████▌    | 482/861 [06:57<02:53,  2.18it/s]
+
 56%|█████▌    | 483/861 [06:58<02:29,  2.52it/s]
+
 56%|█████▌    | 484/861 [06:58<02:32,  2.47it/s]
+
 56%|█████▋    | 485/861 [06:58<02:13,  2.83it/s]
+
 56%|█████▋    | 486/861 [06:58<01:58,  3.15it/s]
+
 57%|█████▋    | 487/861 [06:59<02:42,  2.30it/s]
+
 57%|█████▋    | 488/861 [06:59<02:22,  2.62it/s]
+
 57%|█████▋    | 489/861 [07:00<02:16,  2.73it/s]
+
 57%|█████▋    | 490/861 [07:00<02:04,  2.98it/s]
+
 57%|█████▋    | 491/861 [07:00<02:05,  2.95it/s]
+
 57%|█████▋    | 492/861 [07:01<02:16,  2.70it/s]
+
 57%|█████▋    | 493/861 [07:01<02:35,  2.37it/s]
+
 57%|█████▋    | 494/861 [07:02<02:20,  2.62it/s]
+
 57%|█████▋    | 495/861 [07:04<05:05,  1.20it/s]
+
 58%|█████▊    | 496/861 [07:04<04:55,  1.24it/s]
+
 58%|█████▊    | 497/861 [07:05<03:52,  1.56it/s]
+
 58%|█████▊    | 498/861 [07:05<03:32,  1.71it/s]
+
 58%|█████▊    | 499/861 [07:05<02:57,  2.04it/s]
+
 58%|█████▊    | 500/861 [07:06<03:03,  1.97it/s]
+
 58%|█████▊    | 501/861 [07:06<02:38,  2.28it/s]
+
 58%|█████▊    | 502/861 [07:07<03:04,  1.94it/s]
+
 58%|█████▊    | 503/861 [07:07<02:55,  2.04it/s]
+
 59%|█████▊    | 504/861 [07:08<02:52,  2.07it/s]
+
 59%|█████▊    | 505/861 [07:08<02:31,  2.35it/s]
+
 59%|█████▉    | 506/861 [07:08<02:16,  2.60it/s]
+
 59%|█████▉    | 507/861 [07:09<02:04,  2.84it/s]
+
 59%|█████▉    | 508/861 [07:09<02:55,  2.01it/s]
+
 59%|█████▉    | 509/861 [07:10<03:40,  1.59it/s]
+
 59%|█████▉    | 510/861 [07:11<03:24,  1.72it/s]
+
 59%|█████▉    | 511/861 [07:12<03:43,  1.57it/s]
+
 59%|█████▉    | 512/861 [07:12<03:47,  1.53it/s]
+
 60%|█████▉    | 513/861 [07:13<03:53,  1.49it/s]
+
 60%|█████▉    | 514/861 [07:13<03:28,  1.67it/s]
+
 60%|█████▉    | 515/861 [07:14<02:43,  2.11it/s]
+
 60%|█████▉    | 516/861 [07:14<02:14,  2.57it/s]
+
 60%|██████    | 517/861 [07:14<02:00,  2.86it/s]
+
 60%|██████    | 518/861 [07:15<02:14,  2.55it/s]
+
 60%|██████    | 519/861 [07:15<02:51,  2.00it/s]
+
 60%|██████    | 520/861 [07:16<03:03,  1.86it/s]
+
 61%|██████    | 521/861 [07:16<02:39,  2.14it/s]
+
 61%|██████    | 522/861 [07:17<03:01,  1.86it/s]
+
 61%|██████    | 523/861 [07:18<03:41,  1.53it/s]
+
 61%|██████    | 524/861 [07:19<04:21,  1.29it/s]
+
 61%|██████    | 525/861 [07:19<03:36,  1.56it/s]
+
 61%|██████    | 526/861 [07:20<03:36,  1.54it/s]
+
 61%|██████    | 527/861 [07:21<03:36,  1.54it/s]
+
 61%|██████▏   | 528/861 [07:21<03:34,  1.55it/s]
+
 61%|██████▏   | 529/861 [07:22<03:04,  1.80it/s]
+
 62%|██████▏   | 530/861 [07:22<02:45,  2.00it/s]
+
 62%|██████▏   | 531/861 [07:22<02:36,  2.10it/s]
+
 62%|██████▏   | 532/861 [07:23<02:59,  1.83it/s]
+
 62%|██████▏   | 533/861 [07:23<02:43,  2.01it/s]
+
 62%|██████▏   | 534/861 [07:24<02:54,  1.88it/s]
+
 62%|██████▏   | 535/861 [07:25<02:53,  1.88it/s]
+
 62%|██████▏   | 536/861 [07:25<03:04,  1.76it/s]
+
 62%|██████▏   | 537/861 [07:27<04:44,  1.14it/s]
+
 62%|██████▏   | 538/861 [07:27<03:51,  1.40it/s]
+
 63%|██████▎   | 539/861 [07:29<05:35,  1.04s/it]
+
 63%|██████▎   | 540/861 [07:30<05:19,  1.00it/s]
+
 63%|██████▎   | 541/861 [07:30<04:26,  1.20it/s]
+
 63%|██████▎   | 542/861 [07:31<03:29,  1.52it/s]
+
 63%|██████▎   | 543/861 [07:31<03:21,  1.57it/s]
+
 63%|██████▎   | 544/861 [07:32<03:08,  1.68it/s]
+
 63%|██████▎   | 545/861 [07:33<04:34,  1.15it/s]
+
 63%|██████▎   | 546/861 [07:34<05:05,  1.03it/s]
+
 64%|██████▎   | 547/861 [07:35<04:42,  1.11it/s]
+
 64%|██████▎   | 548/861 [07:37<05:42,  1.09s/it]
+
 64%|██████▍   | 549/861 [07:38<05:27,  1.05s/it]
+
 64%|██████▍   | 550/861 [07:38<05:06,  1.01it/s]
+
 64%|██████▍   | 551/861 [07:39<04:34,  1.13it/s]
+
 64%|██████▍   | 552/861 [07:40<04:30,  1.14it/s]
+
 64%|██████▍   | 553/861 [07:41<05:06,  1.01it/s]
+
 64%|██████▍   | 554/861 [07:42<05:28,  1.07s/it]
+
 64%|██████▍   | 555/861 [07:43<05:16,  1.03s/it]
+
 65%|██████▍   | 556/861 [07:45<05:42,  1.12s/it]
+
 65%|██████▍   | 557/861 [07:46<05:45,  1.14s/it]
+
 65%|██████▍   | 558/861 [07:47<05:12,  1.03s/it]
+
 65%|██████▍   | 559/861 [07:48<05:28,  1.09s/it]
+
 65%|██████▌   | 560/861 [07:49<05:10,  1.03s/it]
+
 65%|██████▌   | 561/861 [07:50<04:58,  1.00it/s]
+
 65%|██████▌   | 562/861 [07:53<09:06,  1.83s/it]
+
 65%|██████▌   | 563/861 [07:54<07:38,  1.54s/it]
+
 66%|██████▌   | 564/861 [07:55<06:45,  1.36s/it]
+
 66%|██████▌   | 565/861 [07:56<05:52,  1.19s/it]
+
 66%|██████▌   | 566/861 [07:57<05:45,  1.17s/it]
+
 66%|██████▌   | 567/861 [07:58<05:53,  1.20s/it]
+
 66%|██████▌   | 568/861 [08:00<05:38,  1.15s/it]
+
 66%|██████▌   | 569/861 [08:01<06:03,  1.24s/it]
+
 66%|██████▌   | 570/861 [08:02<05:31,  1.14s/it]
+
 66%|██████▋   | 571/861 [08:03<05:38,  1.17s/it]
+
 66%|██████▋   | 572/861 [08:04<05:50,  1.21s/it]
+
 67%|██████▋   | 573/861 [08:05<04:55,  1.03s/it]
+
 67%|██████▋   | 574/861 [08:06<05:18,  1.11s/it]
+
 67%|██████▋   | 575/861 [08:07<05:00,  1.05s/it]
+
 67%|██████▋   | 576/861 [08:09<05:56,  1.25s/it]
+
 67%|██████▋   | 577/861 [08:11<06:45,  1.43s/it]
+
 67%|██████▋   | 578/861 [08:12<06:21,  1.35s/it]
+
 67%|██████▋   | 579/861 [08:13<05:19,  1.13s/it]
+
 67%|██████▋   | 580/861 [08:14<05:22,  1.15s/it]
+
 67%|██████▋   | 581/861 [08:15<05:11,  1.11s/it]
+
 68%|██████▊   | 582/861 [08:17<06:54,  1.49s/it]
+
 68%|██████▊   | 583/861 [08:18<06:13,  1.34s/it]
+
 68%|██████▊   | 584/861 [08:19<05:33,  1.20s/it]
+
 68%|██████▊   | 585/861 [08:20<05:08,  1.12s/it]
+
 68%|██████▊   | 586/861 [08:21<04:23,  1.04it/s]
+
 68%|██████▊   | 587/861 [08:22<04:46,  1.04s/it]
+
 68%|██████▊   | 588/861 [08:23<04:40,  1.03s/it]
+
 68%|██████▊   | 589/861 [08:24<04:15,  1.06it/s]
+
 69%|██████▊   | 590/861 [08:25<05:01,  1.11s/it]
+
 69%|██████▊   | 591/861 [08:26<04:15,  1.06it/s]
+
 69%|██████▉   | 592/861 [08:27<04:29,  1.00s/it]
+
 69%|██████▉   | 593/861 [08:29<05:41,  1.28s/it]
+
 69%|██████▉   | 594/861 [08:30<05:52,  1.32s/it]
+
 69%|██████▉   | 595/861 [08:31<04:52,  1.10s/it]
+
 69%|██████▉   | 596/861 [08:31<03:57,  1.12it/s]
+
 69%|██████▉   | 597/861 [08:33<04:48,  1.09s/it]
+
 69%|██████▉   | 598/861 [08:34<04:36,  1.05s/it]
+
 70%|██████▉   | 599/861 [08:35<04:35,  1.05s/it]
+
 70%|██████▉   | 600/861 [08:35<04:06,  1.06it/s]
+
 70%|██████▉   | 601/861 [08:36<03:41,  1.17it/s]
+
 70%|██████▉   | 602/861 [08:38<04:51,  1.13s/it]
+
 70%|███████   | 603/861 [08:39<04:58,  1.16s/it]
+
 70%|███████   | 604/861 [08:40<04:42,  1.10s/it]
+
 70%|███████   | 605/861 [08:41<04:04,  1.05it/s]
+
 70%|███████   | 606/861 [08:41<04:01,  1.05it/s]
+
 70%|███████   | 607/861 [08:42<03:40,  1.15it/s]
+
 71%|███████   | 608/861 [08:43<03:11,  1.32it/s]
+
 71%|███████   | 609/861 [08:43<03:09,  1.33it/s]
+
 71%|███████   | 610/861 [08:45<04:07,  1.01it/s]
+
 71%|███████   | 611/861 [08:46<04:23,  1.05s/it]
+
 71%|███████   | 612/861 [08:47<04:33,  1.10s/it]
+
 71%|███████   | 613/861 [08:48<03:38,  1.14it/s]
+
 71%|███████▏  | 614/861 [08:49<03:54,  1.05it/s]
+
 71%|███████▏  | 615/861 [08:49<03:30,  1.17it/s]
+
 72%|███████▏  | 616/861 [08:52<05:06,  1.25s/it]
+
 72%|███████▏  | 617/861 [08:53<05:07,  1.26s/it]
+
 72%|███████▏  | 618/861 [08:54<05:01,  1.24s/it]
+
 72%|███████▏  | 619/861 [08:55<04:49,  1.20s/it]
+
 72%|███████▏  | 620/861 [08:57<05:15,  1.31s/it]
+
 72%|███████▏  | 621/861 [08:58<04:59,  1.25s/it]
+
 72%|███████▏  | 622/861 [08:58<04:03,  1.02s/it]
+
 72%|███████▏  | 623/861 [08:59<03:32,  1.12it/s]
+
 72%|███████▏  | 624/861 [09:00<03:26,  1.15it/s]
+
 73%|███████▎  | 625/861 [09:00<03:04,  1.28it/s]
+
 73%|███████▎  | 626/861 [09:01<03:02,  1.29it/s]
+
 73%|███████▎  | 627/861 [09:02<03:07,  1.25it/s]
+
 73%|███████▎  | 628/861 [09:03<03:28,  1.12it/s]
+
 73%|███████▎  | 629/861 [09:04<03:41,  1.05it/s]
+
 73%|███████▎  | 630/861 [09:05<03:10,  1.21it/s]
+
 73%|███████▎  | 631/861 [09:05<02:34,  1.49it/s]
+
 73%|███████▎  | 632/861 [09:07<03:42,  1.03it/s]
+
 74%|███████▎  | 633/861 [09:08<03:37,  1.05it/s]
+
 74%|███████▎  | 634/861 [09:09<04:32,  1.20s/it]
+
 74%|███████▍  | 635/861 [09:11<04:42,  1.25s/it]
+
 74%|███████▍  | 636/861 [09:11<04:07,  1.10s/it]
+
 74%|███████▍  | 637/861 [09:12<03:46,  1.01s/it]
+
 74%|███████▍  | 638/861 [09:13<03:40,  1.01it/s]
+
 74%|███████▍  | 639/861 [09:15<04:04,  1.10s/it]
+
 74%|███████▍  | 640/861 [09:15<03:42,  1.01s/it]
+
 74%|███████▍  | 641/861 [09:16<03:38,  1.00it/s]
+
 75%|███████▍  | 642/861 [09:18<03:53,  1.07s/it]
+
 75%|████��██▍  | 643/861 [09:18<03:35,  1.01it/s]
+
 75%|███████▍  | 644/861 [09:19<03:15,  1.11it/s]
+
 75%|███████▍  | 645/861 [09:19<02:41,  1.33it/s]
+
 75%|███████▌  | 646/861 [09:20<02:47,  1.28it/s]
+
 75%|███████▌  | 647/861 [09:21<02:29,  1.44it/s]
+
 75%|███████▌  | 648/861 [09:22<02:42,  1.31it/s]
+
 75%|███████▌  | 649/861 [09:22<02:36,  1.35it/s]
+
 75%|███████▌  | 650/861 [09:23<02:22,  1.49it/s]
+
 76%|███████▌  | 651/861 [09:23<02:09,  1.62it/s]
+
 76%|███████▌  | 652/861 [09:24<02:24,  1.45it/s]
+
 76%|███████▌  | 653/861 [09:25<02:28,  1.40it/s]
+
 76%|███████▌  | 654/861 [09:26<02:26,  1.42it/s]
+
 76%|███████▌  | 655/861 [09:26<02:00,  1.71it/s]
+
 76%|███████▌  | 656/861 [09:26<01:46,  1.92it/s]
+
 76%|███████▋  | 657/861 [09:27<01:44,  1.94it/s]
+
 76%|███████▋  | 658/861 [09:28<02:09,  1.57it/s]
+
 77%|███████▋  | 659/861 [09:29<02:15,  1.49it/s]
+
 77%|███████▋  | 660/861 [09:29<02:22,  1.41it/s]
+
 77%|███████▋  | 661/861 [09:30<02:11,  1.53it/s]
+
 77%|███████▋  | 662/861 [09:31<02:27,  1.35it/s]
+
 77%|███████▋  | 663/861 [09:32<02:34,  1.28it/s]
+
 77%|███████▋  | 664/861 [09:32<02:20,  1.40it/s]
+
 77%|███████▋  | 665/861 [09:33<01:59,  1.64it/s]
+
 77%|███████▋  | 666/861 [09:33<01:42,  1.90it/s]
+
 77%|███████▋  | 667/861 [09:34<01:59,  1.62it/s]
+
 78%|███████▊  | 668/861 [09:34<01:44,  1.84it/s]
+
 78%|███████▊  | 669/861 [09:35<01:33,  2.06it/s]
+
 78%|███████▊  | 670/861 [09:35<01:36,  1.98it/s]
+
 78%|███████▊  | 671/861 [09:35<01:20,  2.36it/s]
+
 78%|███████▊  | 672/861 [09:37<02:11,  1.44it/s]
+
 78%|███████▊  | 673/861 [09:37<02:03,  1.53it/s]
+
 78%|███████▊  | 674/861 [09:37<01:39,  1.88it/s]
+
 78%|███████▊  | 675/861 [09:38<02:02,  1.52it/s]
+
 79%|███████▊  | 676/861 [09:39<01:52,  1.64it/s]
+
 79%|███████▊  | 677/861 [09:40<02:07,  1.44it/s]
+
 79%|███████▊  | 678/861 [09:40<01:54,  1.60it/s]
+
 79%|███████▉  | 679/861 [09:41<01:36,  1.88it/s]
+
 79%|███████▉  | 680/861 [09:41<01:20,  2.24it/s]
+
 79%|███████▉  | 681/861 [09:41<01:25,  2.11it/s]
+
 79%|███████▉  | 682/861 [09:42<01:44,  1.71it/s]
+
 79%|███████▉  | 683/861 [09:43<01:36,  1.85it/s]
+
 79%|███████▉  | 684/861 [09:43<01:47,  1.64it/s]
+
 80%|███████▉  | 685/861 [09:44<01:48,  1.63it/s]
+
 80%|███████▉  | 686/861 [09:44<01:39,  1.76it/s]
+
 80%|███████▉  | 687/861 [09:46<02:18,  1.26it/s]
+
 80%|███████▉  | 688/861 [09:46<01:54,  1.51it/s]
+
 80%|████████  | 689/861 [09:47<01:58,  1.45it/s]
+
 80%|████████  | 690/861 [09:48<02:06,  1.35it/s]
+
 80%|████████  | 691/861 [09:49<02:11,  1.30it/s]
+
 80%|████████  | 692/861 [09:49<01:52,  1.50it/s]
+
 80%|████████  | 693/861 [09:50<02:00,  1.40it/s]
+
 81%|████████  | 694/861 [09:50<01:42,  1.63it/s]
+
 81%|████████  | 695/861 [09:51<01:45,  1.58it/s]
+
 81%|████████  | 696/861 [09:51<01:24,  1.94it/s]
+
 81%|████████  | 697/861 [09:52<01:28,  1.86it/s]
+
 81%|████████  | 698/861 [09:53<01:42,  1.59it/s]
+
 81%|████████  | 699/861 [09:53<01:46,  1.53it/s]
+
 81%|████████▏ | 700/861 [09:54<01:57,  1.37it/s]
+
 81%|████████▏ | 701/861 [09:55<02:08,  1.25it/s]
+
 82%|████████▏ | 702/861 [09:56<02:07,  1.25it/s]
+
 82%|████████▏ | 703/861 [09:56<01:47,  1.47it/s]
+
 82%|████████▏ | 704/861 [09:57<01:43,  1.52it/s]
+
 82%|████████▏ | 705/861 [09:58<01:38,  1.58it/s]
+
 82%|████████▏ | 706/861 [09:58<01:29,  1.74it/s]
+
 82%|████████▏ | 707/861 [09:58<01:19,  1.94it/s]
+
 82%|████████▏ | 708/861 [09:59<01:20,  1.89it/s]
+
 82%|████████▏ | 709/861 [09:59<01:14,  2.04it/s]
+
 82%|████████▏ | 710/861 [10:01<01:47,  1.40it/s]
+
 83%|████████▎ | 711/861 [10:01<01:44,  1.43it/s]
+
 83%|████████▎ | 712/861 [10:02<01:31,  1.63it/s]
+
 83%|████████▎ | 713/861 [10:02<01:16,  1.92it/s]
+
 83%|████████▎ | 714/861 [10:03<01:25,  1.72it/s]
+
 83%|████████▎ | 715/861 [10:04<01:43,  1.42it/s]
+
 83%|████████▎ | 716/861 [10:05<01:55,  1.25it/s]
+
 83%|████████▎ | 717/861 [10:05<01:45,  1.36it/s]
+
 83%|████████▎ | 718/861 [10:07<02:07,  1.12it/s]
+
 84%|████████▎ | 719/861 [10:07<01:54,  1.24it/s]
+
 84%|████████▎ | 720/861 [10:08<01:38,  1.43it/s]
+
 84%|████████▎ | 721/861 [10:08<01:27,  1.60it/s]
+
 84%|████████▍ | 722/861 [10:09<01:27,  1.58it/s]
+
 84%|████████▍ | 723/861 [10:09<01:18,  1.75it/s]
+
 84%|████████▍ | 724/861 [10:10<01:16,  1.79it/s]
+
 84%|████████▍ | 725/861 [10:10<01:15,  1.81it/s]
+
 84%|████████▍ | 726/861 [10:11<01:26,  1.57it/s]
+
 84%|████████▍ | 727/861 [10:13<02:07,  1.05it/s]
+
 85%|████████▍ | 728/861 [10:14<02:06,  1.05it/s]
+
 85%|████████▍ | 729/861 [10:14<02:00,  1.09it/s]
+
 85%|████████▍ | 730/861 [10:15<01:35,  1.37it/s]
+
 85%|████████▍ | 731/861 [10:15<01:32,  1.40it/s]
+
 85%|████████▌ | 732/861 [10:16<01:21,  1.58it/s]
+
 85%|████████▌ | 733/861 [10:17<01:24,  1.52it/s]
+
 85%|████████▌ | 734/861 [10:17<01:07,  1.88it/s]
+
 85%|████████▌ | 735/861 [10:17<01:05,  1.93it/s]
+
 85%|████████▌ | 736/861 [10:18<01:05,  1.90it/s]
+
 86%|████████▌ | 737/861 [10:18<01:07,  1.83it/s]
+
 86%|████████▌ | 738/861 [10:19<01:07,  1.82it/s]
+
 86%|████████▌ | 739/861 [10:19<01:01,  2.00it/s]
+
 86%|████████▌ | 740/861 [10:20<01:01,  1.98it/s]
+
 86%|████████▌ | 741/861 [10:20<00:59,  2.00it/s]
+
 86%|████████▌ | 742/861 [10:22<01:19,  1.50it/s]
+
 86%|████████▋ | 743/861 [10:22<01:09,  1.69it/s]
+
 86%|████████▋ | 744/861 [10:22<01:03,  1.84it/s]
+
 87%|████████▋ | 745/861 [10:24<01:25,  1.35it/s]
+
 87%|████████▋ | 746/861 [10:24<01:11,  1.60it/s]
+
 87%|████████▋ | 747/861 [10:25<01:24,  1.35it/s]
+
 87%|████████▋ | 748/861 [10:26<01:21,  1.39it/s]
+
 87%|████████▋ | 749/861 [10:27<01:28,  1.26it/s]
+
 87%|████████▋ | 750/861 [10:27<01:30,  1.22it/s]
+
 87%|████████▋ | 751/861 [10:28<01:09,  1.58it/s]
+
 87%|████████▋ | 752/861 [10:29<01:28,  1.23it/s]
+
 87%|████████▋ | 753/861 [10:30<01:22,  1.30it/s]
+
 88%|████████▊ | 754/861 [10:30<01:06,  1.61it/s]
+
 88%|████████▊ | 755/861 [10:31<01:13,  1.45it/s]
+
 88%|████████▊ | 756/861 [10:31<01:11,  1.48it/s]
+
 88%|████████▊ | 757/861 [10:33<01:36,  1.08it/s]
+
 88%|████████▊ | 758/861 [10:34<01:31,  1.12it/s]
+
 88%|████████▊ | 759/861 [10:34<01:18,  1.30it/s]
+
 88%|████████▊ | 760/861 [10:35<01:29,  1.13it/s]
+
 88%|████████▊ | 761/861 [10:37<01:55,  1.16s/it]
+
 89%|████████▊ | 762/861 [10:37<01:32,  1.07it/s]
+
 89%|████████▊ | 763/861 [10:38<01:20,  1.21it/s]
+
 89%|████████▊ | 764/861 [10:39<01:21,  1.19it/s]
+
 89%|████████▉ | 765/861 [10:40<01:14,  1.29it/s]
+
 89%|████████▉ | 766/861 [10:40<01:10,  1.34it/s]
+
 89%|████████▉ | 767/861 [10:45<02:50,  1.81s/it]
+
 89%|████████▉ | 768/861 [10:45<02:16,  1.47s/it]
+
 89%|████████▉ | 769/861 [10:46<02:07,  1.39s/it]
+
 89%|████████▉ | 770/861 [10:47<01:41,  1.12s/it]
+
 90%|████████▉ | 771/861 [10:47<01:21,  1.11it/s]
+
 90%|████████▉ | 772/861 [10:48<01:24,  1.06it/s]
+
 90%|████████▉ | 773/861 [10:50<01:56,  1.32s/it]
+
 90%|████████▉ | 774/861 [10:51<01:38,  1.13s/it]
+
 90%|█████████ | 775/861 [10:52<01:29,  1.04s/it]
+
 90%|█████████ | 776/861 [10:53<01:28,  1.04s/it]
+
 90%|█████████ | 777/861 [10:54<01:36,  1.15s/it]
+
 90%|█████████ | 778/861 [10:56<01:34,  1.13s/it]
+
 90%|█████████ | 779/861 [10:57<01:29,  1.09s/it]
+
 91%|█████████ | 780/861 [10:58<01:49,  1.35s/it]
+
 91%|█████████ | 781/861 [11:00<01:53,  1.42s/it]
+
 91%|█████████ | 782/861 [11:01<01:38,  1.25s/it]
+
 91%|█████████ | 783/861 [11:02<01:26,  1.11s/it]
+
 91%|█████████ | 784/861 [11:02<01:17,  1.01s/it]
+
 91%|��████████ | 785/861 [11:03<01:11,  1.06it/s]
+
 91%|█████████▏| 786/861 [11:04<01:09,  1.08it/s]
+
 91%|█████████▏| 787/861 [11:05<00:58,  1.27it/s]
+
 92%|█████████▏| 788/861 [11:05<00:55,  1.32it/s]
+
 92%|█████████▏| 789/861 [11:06<00:57,  1.26it/s]
+
 92%|█████████▏| 790/861 [11:07<01:01,  1.16it/s]
+
 92%|█████████▏| 791/861 [11:08<00:54,  1.28it/s]
+
 92%|█████████▏| 792/861 [11:08<00:49,  1.38it/s]
+
 92%|█████████▏| 793/861 [11:09<00:49,  1.36it/s]
+
 92%|█████████▏| 794/861 [11:10<00:45,  1.49it/s]
+
 92%|█████████▏| 795/861 [11:10<00:45,  1.45it/s]
+
 92%|█████████▏| 796/861 [11:11<00:37,  1.73it/s]
+
 93%|█████████▎| 797/861 [11:12<00:43,  1.48it/s]
+
 93%|█████████▎| 798/861 [11:13<00:57,  1.10it/s]
+
 93%|█████████▎| 799/861 [11:14<00:52,  1.19it/s]
+
 93%|█████████▎| 800/861 [11:14<00:48,  1.25it/s]
+
 93%|█████████▎| 801/861 [11:17<01:23,  1.39s/it]
+
 93%|█████████▎| 802/861 [11:18<01:05,  1.11s/it]
+
 93%|█████████▎| 803/861 [11:19<01:07,  1.17s/it]
+
 93%|█████████▎| 804/861 [11:20<00:59,  1.05s/it]
+
 93%|█████████▎| 805/861 [11:21<01:01,  1.10s/it]
+
 94%|█████████▎| 806/861 [11:21<00:48,  1.14it/s]
+
 94%|█████████▎| 807/861 [11:23<00:54,  1.00s/it]
+
 94%|█████████▍| 808/861 [11:24<00:59,  1.13s/it]
+
 94%|█████████▍| 809/861 [11:24<00:45,  1.14it/s]
+
 94%|█████████▍| 810/861 [11:25<00:38,  1.32it/s]
+
 94%|█████████▍| 811/861 [11:25<00:36,  1.39it/s]
+
 94%|█████████▍| 812/861 [11:26<00:31,  1.55it/s]
+
 94%|█████████▍| 813/861 [11:27<00:39,  1.21it/s]
+
 95%|█████████▍| 814/861 [11:28<00:41,  1.13it/s]
+
 95%|█████████▍| 815/861 [11:29<00:42,  1.08it/s]
+
 95%|█████████▍| 816/861 [11:30<00:37,  1.21it/s]
+
 95%|█████████▍| 817/861 [11:31<00:35,  1.22it/s]
+
 95%|█████████▌| 818/861 [11:32<00:39,  1.09it/s]
+
 95%|█████████▌| 819/861 [11:32<00:35,  1.17it/s]
+
 95%|█████████▌| 820/861 [11:33<00:35,  1.16it/s]
+
 95%|█████████▌| 821/861 [11:34<00:36,  1.09it/s]
+
 95%|█████████▌| 822/861 [11:36<00:44,  1.14s/it]
+
 96%|█████████▌| 823/861 [11:38<00:52,  1.37s/it]
+
 96%|█████████▌| 824/861 [11:39<00:41,  1.12s/it]
+
 96%|█████████▌| 825/861 [11:39<00:33,  1.06it/s]
+
 96%|█████████▌| 826/861 [11:41<00:43,  1.24s/it]
+
 96%|█████████▌| 827/861 [11:42<00:39,  1.16s/it]
+
 96%|█████████▌| 828/861 [11:42<00:31,  1.04it/s]
+
 96%|█████████▋| 829/861 [11:44<00:36,  1.15s/it]
+
 96%|█████████▋| 830/861 [11:45<00:35,  1.14s/it]
+
 97%|█████████▋| 831/861 [11:47<00:36,  1.23s/it]
+
 97%|█████████▋| 832/861 [11:47<00:30,  1.05s/it]
+
 97%|█████████▋| 833/861 [11:48<00:24,  1.13it/s]
+
 97%|█████████▋| 834/861 [11:49<00:24,  1.10it/s]
+
 97%|█████████▋| 835/861 [11:49<00:22,  1.18it/s]
+
 97%|█████████▋| 836/861 [11:50<00:21,  1.14it/s]
+
 97%|█████████▋| 837/861 [11:52<00:23,  1.02it/s]
+
 97%|█████████▋| 838/861 [11:53<00:22,  1.01it/s]
+
 97%|█████████▋| 839/861 [11:53<00:19,  1.14it/s]
+
 98%|█████████▊| 840/861 [11:54<00:16,  1.26it/s]
+
 98%|█████████▊| 841/861 [11:55<00:16,  1.22it/s]
+
 98%|█████████▊| 842/861 [11:55<00:15,  1.25it/s]
+
 98%|█████████▊| 843/861 [11:56<00:13,  1.35it/s]
+
 98%|█████████▊| 844/861 [11:57<00:11,  1.44it/s]
+
 98%|█████████▊| 845/861 [11:58<00:14,  1.12it/s]
+
 98%|█████████▊| 846/861 [11:58<00:10,  1.36it/s]
+
 98%|█████████▊| 847/861 [11:59<00:10,  1.28it/s]
+
 98%|█████████▊| 848/861 [12:00<00:09,  1.35it/s]
+
 99%|█████████▊| 849/861 [12:01<00:10,  1.12it/s]
+
 99%|█████████▊| 850/861 [12:02<00:08,  1.25it/s]
+
 99%|█████████▉| 851/861 [12:02<00:07,  1.26it/s]
+
 99%|█████████▉| 852/861 [12:03<00:06,  1.39it/s]
+
 99%|█████████▉| 853/861 [12:06<00:11,  1.38s/it]
+
 99%|█████████▉| 854/861 [12:07<00:08,  1.23s/it]
+
 99%|█████████▉| 855/861 [12:08<00:06,  1.11s/it]
+
 99%|█████████▉| 856/861 [12:09<00:05,  1.19s/it]
+
100%|█████████▉| 857/861 [12:10<00:04,  1.09s/it]
+
100%|█████████▉| 858/861 [12:11<00:03,  1.00s/it]
+
100%|█████████▉| 859/861 [12:11<00:01,  1.10it/s]
+
100%|█████████▉| 860/861 [12:12<00:00,  1.08it/s]
+
100%|██████████| 861/861 [12:13<00:00,  1.13it/s]{'score': 10.235285636672579, 'counts': [17175, 7590, 3753, 1863], 'totals': [56300, 54578, 52856, 51134], 'precisions': [30.50621669626998, 13.906702334273882, 7.1004237929468745, 3.643368404584034], 'bp': 1.0, 'sys_len': 56300, 'ref_len': 32555}
+
                                                          
+
                                                 
{'eval_loss': 2.504971742630005, 'eval_bleu': 10.2353, 'eval_gen_len': 38.2607, 'eval_runtime': 830.1656, 'eval_samples_per_second': 2.074, 'eval_steps_per_second': 1.037, 'epoch': 9.0}
+
 56%|█████▋    | 34823/61904 [7:05:32<10:36:15,  1.41s/it]
+
100%|██████████| 861/861 [13:49<00:00,  1.13it/s]
+
                                                 [WARNING|configuration_utils.py:448] 2024-10-28 10:10:15,440 >> 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()
+
 56%|█████▋    | 34824/61904 [7:06:05<1955:04:32, 259.91s/it]
 56%|█████▋    | 34825/61904 [7:06:07<1372:18:20, 182.44s/it]
 56%|█████▋    | 34826/61904 [7:06:09<963:52:02, 128.15s/it] 
 56%|█████▋    | 34827/61904 [7:06:10<678:03:42, 90.15s/it] 
 56%|█████▋    | 34828/61904 [7:06:12<477:59:34, 63.55s/it]
 56%|█████▋    | 34829/61904 [7:06:13<337:58:13, 44.94s/it]
 56%|█████▋    | 34830/61904 [7:06:14<239:40:03, 31.87s/it]
 56%|█████▋    | 34831/61904 [7:06:16<170:51:04, 22.72s/it]
 56%|█████▋    | 34832/61904 [7:06:17<122:44:10, 16.32s/it]
 56%|█████▋    | 34833/61904 [7:06:19<88:57:33, 11.83s/it] 
 56%|█████▋    | 34834/61904 [7:06:20<65:30:44,  8.71s/it]
 56%|█████▋    | 34835/61904 [7:06:21<48:55:44,  6.51s/it]
 56%|█████▋    | 34836/61904 [7:06:23<37:32:30,  4.99s/it]
 56%|█████▋    | 34837/61904 [7:06:24<29:37:02,  3.94s/it]
 56%|█████▋    | 34838/61904 [7:06:26<23:57:03,  3.19s/it]
 56%|█████▋    | 34839/61904 [7:06:27<19:52:58,  2.64s/it]
 56%|█████▋    | 34840/61904 [7:06:29<17:20:16,  2.31s/it]
                                                          
{'loss': 2.5627, 'learning_rate': 1.4386101387268247e-07, 'epoch': 9.0}
+
 56%|█████▋    | 34840/61904 [7:06:29<17:20:16,  2.31s/it]
 56%|█████▋    | 34841/61904 [7:06:30<15:15:48,  2.03s/it]
 56%|█████▋    | 34842/61904 [7:06:31<14:01:25,  1.87s/it]
 56%|█████▋    | 34843/61904 [7:06:33<12:49:25,  1.71s/it]
 56%|█████▋    | 34844/61904 [7:06:34<12:03:49,  1.60s/it]
 56%|█████▋    | 34845/61904 [7:06:36<11:38:37,  1.55s/it]
 56%|█████▋    | 34846/61904 [7:06:37<11:16:13,  1.50s/it]
 56%|█████▋    | 34847/61904 [7:06:38<11:05:54,  1.48s/it]
 56%|█████▋    | 34848/61904 [7:06:40<11:13:57,  1.49s/it]
 56%|█████▋    | 34849/61904 [7:06:41<11:13:18,  1.49s/it]
 56%|█████▋    | 34850/61904 [7:06:43<10:59:10,  1.46s/it]
 56%|█████▋    | 34851/61904 [7:06:44<10:49:56,  1.44s/it]
 56%|█████▋    | 34852/61904 [7:06:46<10:53:15,  1.45s/it]
 56%|█████▋    | 34853/61904 [7:06:47<10:39:48,  1.42s/it]
 56%|█████▋    | 34854/61904 [7:06:48<10:37:52,  1.41s/it]
 56%|█████▋    | 34855/61904 [7:06:50<10:39:17,  1.42s/it]
 56%|█████▋    | 34856/61904 [7:06:51<10:36:52,  1.41s/it]
 56%|█████▋    | 34857/61904 [7:06:53<10:35:10,  1.41s/it]
 56%|█████▋    | 34858/61904 [7:06:54<10:56:29,  1.46s/it]
 56%|█████▋    | 34859/61904 [7:06:56<10:51:27,  1.45s/it]
 56%|█████▋    | 34860/61904 [7:06:57<10:48:23,  1.44s/it]
                                                          
{'loss': 2.538, 'learning_rate': 1.4382860106314016e-07, 'epoch': 9.01}
+
 56%|█████▋    | 34860/61904 [7:06:57<10:48:23,  1.44s/it]
 56%|█████▋    | 34861/61904 [7:06:58<10:37:21,  1.41s/it]
 56%|█████▋    | 34862/61904 [7:07:00<10:26:36,  1.39s/it]
 56%|█████▋    | 34863/61904 [7:07:01<11:01:39,  1.47s/it]
 56%|█████▋    | 34864/61904 [7:07:03<10:48:31,  1.44s/it]
\ No newline at end of file