diff --git "a/run-2024-10-28T15:22:08+00:00.log" "b/run-2024-10-28T15:22:08+00:00.log"
--- "a/run-2024-10-28T15:22:08+00:00.log"
+++ "b/run-2024-10-28T15:22:08+00:00.log"
@@ -4306,4 +4306,253 @@ Non-default generation parameters: {'max_length': 200, 'early_stopping': True, '
 
 94%|█████████▍| 58038/61904 [6:51:58<263:42:12, 245.56s/it]
 94%|█████████▍| 58039/61904 [6:52:00<185:05:43, 172.40s/it]
 94%|█████████▍| 58040/61904 [6:52:01<130:00:51, 121.13s/it]
                                                            
{'loss': 2.3623, 'learning_rate': 1.0626215480357839e-07, 'epoch': 15.0}
 
 94%|█████████▍| 58040/61904 [6:52:01<130:00:51, 121.13s/it]
 94%|█████████▍| 58041/61904 [6:52:03<91:25:26, 85.20s/it]  
 94%|█████████▍| 58042/61904 [6:52:04<64:27:30, 60.09s/it]
 94%|█████████▍| 58043/61904 [6:52:05<45:33:52, 42.48s/it]
 94%|█████████▍| 58044/61904 [6:52:07<32:17:39, 30.12s/it]
 94%|█████████▍| 58045/61904 [6:52:08<23:05:40, 21.54s/it]
 94%|█████████▍| 58046/61904 [6:52:10<16:35:55, 15.49s/it]
 94%|█████████▍| 58047/61904 [6:52:11<12:05:57, 11.29s/it]
 94%|█████████▍| 58048/61904 [6:52:13<8:55:45,  8.34s/it] 
 94%|█████████▍| 58049/61904 [6:52:14<6:40:02,  6.23s/it]
 94%|█████████▍| 58050/61904 [6:52:15<5:07:04,  4.78s/it]
 94%|█████████▍| 58051/61904 [6:52:17<4:00:57,  3.75s/it]
 94%|█████████▍| 58052/61904 [6:52:18<3:17:53,  3.08s/it]
 94%|█████████▍| 58053/61904 [6:52:19<2:43:33,  2.55s/it]
 94%|█████████▍| 58054/61904 [6:52:21<2:23:37,  2.24s/it]
 94%|█████████▍| 58055/61904 [6:52:22<2:05:49,  1.96s/it]
 94%|█████████▍| 58056/61904 [6:52:24<1:57:00,  1.82s/it]
 94%|█████████▍| 58057/61904 [6:52:25<1:49:34,  1.71s/it]
 94%|█████████▍| 58058/61904 [6:52:27<1:47:06,  1.67s/it]
 94%|█████████▍| 58059/61904 [6:52:28<1:41:16,  1.58s/it]
 94%|█████████▍| 58060/61904 [6:52:30<1:37:57,  1.53s/it]
                                                         
{'loss': 2.4089, 'learning_rate': 1.0622974199403602e-07, 'epoch': 15.01}
 
 94%|█████████▍| 58060/61904 [6:52:30<1:37:57,  1.53s/it]
 94%|█████████▍| 58061/61904 [6:52:31<1:36:47,  1.51s/it]
 94%|█████████▍| 58062/61904 [6:52:33<1:36:46,  1.51s/it]
 94%|█████████▍| 58063/61904 [6:52:34<1:34:30,  1.48s/it]
 94%|█████████▍| 58064/61904 [6:52:35<1:31:46,  1.43s/it]
 94%|█████████▍| 58065/61904 [6:52:37<1:32:08,  1.44s/it]
 94%|█████████▍| 58066/61904 [6:52:38<1:30:39,  1.42s/it]
 94%|█████████▍| 58067/61904 [6:52:40<1:30:13,  1.41s/it]
 94%|█████████▍| 58068/61904 [6:52:41<1:30:02,  1.41s/it]
 94%|█████████▍| 58069/61904 [6:52:42<1:29:53,  1.41s/it]
 94%|█████████▍| 58070/61904 [6:52:44<1:27:39,  1.37s/it]
 94%|█████████▍| 58071/61904 [6:52:45<1:28:05,  1.38s/it]
 94%|█████████▍| 58072/61904 [6:52:46<1:28:15,  1.38s/it]
 94%|█████████▍| 58073/61904 [6:52:48<1:32:08,  1.44s/it]
 94%|█████████▍| 58074/61904 [6:52:50<1:34:27,  1.48s/it]
 94%|█████████▍| 58075/61904 [6:52:51<1:32:20,  1.45s/it]
 94%|█████████▍| 58076/61904 [6:52:52<1:31:03,  1.43s/it]
 94%|█████████▍| 58077/61904 [6:52:54<1:30:43,  1.42s/it]
 94%|█████████▍| 58078/61904 [6:52:55<1:32:26,  1.45s/it]
 94%|█████████▍| 58079/61904 [6:52:57<1:31:47,  1.44s/it]
 94%|█████████▍| 58080/61904 [6:52:58<1:33:14,  1.46s/it]
                                                         
{'loss': 2.5134, 'learning_rate': 1.0619732918449371e-07, 'epoch': 15.01}
-
 94%|█████████▍| 58080/61904 [6:52:58<1:33:14,  1.46s/it]
 94%|█████████▍| 58081/61904 [6:52:59<1:30:58,  1.43s/it]
\ No newline at end of file
+
 94%|█████████▍| 58080/61904 [6:52:58<1:33:14,  1.46s/it]
 94%|█████████▍| 58081/61904 [6:52:59<1:30:58,  1.43s/it]
 94%|█████████▍| 58082/61904 [6:53:01<1:31:26,  1.44s/it]
 94%|█████████▍| 58083/61904 [6:53:02<1:29:29,  1.41s/it]
 94%|█████████▍| 58084/61904 [6:53:04<1:32:36,  1.45s/it]
 94%|█████████▍| 58085/61904 [6:53:05<1:31:08,  1.43s/it]
 94%|█████████▍| 58086/61904 [6:53:07<1:31:40,  1.44s/it]
 94%|█████████▍| 58087/61904 [6:53:08<1:33:56,  1.48s/it]
 94%|█████████▍| 58088/61904 [6:53:10<1:36:58,  1.52s/it]
 94%|█████████▍| 58089/61904 [6:53:11<1:35:10,  1.50s/it]
 94%|█████████▍| 58090/61904 [6:53:13<1:35:07,  1.50s/it]
 94%|█████████���| 58091/61904 [6:53:14<1:31:54,  1.45s/it]
 94%|█████████▍| 58092/61904 [6:53:16<1:31:36,  1.44s/it]
 94%|█████████▍| 58093/61904 [6:53:17<1:34:30,  1.49s/it]
 94%|█████████▍| 58094/61904 [6:53:19<1:36:05,  1.51s/it]
 94%|█████████▍| 58095/61904 [6:53:20<1:34:33,  1.49s/it]
 94%|█████████▍| 58096/61904 [6:53:22<1:31:53,  1.45s/it]
 94%|█████████▍| 58097/61904 [6:53:23<1:30:05,  1.42s/it]
 94%|█████████▍| 58098/61904 [6:53:24<1:29:31,  1.41s/it]
 94%|█████████▍| 58099/61904 [6:53:26<1:31:08,  1.44s/it]
 94%|█████████▍| 58100/61904 [6:53:27<1:28:36,  1.40s/it]
                                                         
{'loss': 2.4379, 'learning_rate': 1.0616491637495137e-07, 'epoch': 15.02}
+
 94%|█████████▍| 58100/61904 [6:53:27<1:28:36,  1.40s/it]
 94%|█████████▍| 58101/61904 [6:53:29<1:30:46,  1.43s/it]
 94%|█████████▍| 58102/61904 [6:53:30<1:33:15,  1.47s/it]
 94%|█████████▍| 58103/61904 [6:53:31<1:29:58,  1.42s/it]
 94%|█████████▍| 58104/61904 [6:53:33<1:31:09,  1.44s/it]
 94%|█████████▍| 58105/61904 [6:53:34<1:26:14,  1.36s/it]
 94%|█████████▍| 58106/61904 [6:53:36<1:28:20,  1.40s/it]
 94%|█████████▍| 58107/61904 [6:53:37<1:26:38,  1.37s/it]
 94%|█████████▍| 58108/61904 [6:53:39<1:33:07,  1.47s/it]
 94%|█████████▍| 58109/61904 [6:53:40<1:34:13,  1.49s/it]
 94%|█████████▍| 58110/61904 [6:53:42<1:32:19,  1.46s/it]
 94%|█████████▍| 58111/61904 [6:53:43<1:33:23,  1.48s/it]
 94%|█████████▍| 58112/61904 [6:53:45<1:38:26,  1.56s/it]
 94%|█████████▍| 58113/61904 [6:53:46<1:39:17,  1.57s/it]
 94%|█████████▍| 58114/61904 [6:53:48<1:37:03,  1.54s/it]
 94%|█████████▍| 58115/61904 [6:53:49<1:34:55,  1.50s/it]
 94%|█████████▍| 58116/61904 [6:53:51<1:33:54,  1.49s/it]
 94%|█████████▍| 58117/61904 [6:53:52<1:32:40,  1.47s/it]
 94%|█████████▍| 58118/61904 [6:53:54<1:31:42,  1.45s/it]
 94%|█████████▍| 58119/61904 [6:53:55<1:29:44,  1.42s/it]
 94%|█████████▍| 58120/61904 [6:53:56<1:29:01,  1.41s/it]
                                                         
{'loss': 2.4265, 'learning_rate': 1.0613250356540906e-07, 'epoch': 15.02}
+
 94%|█████████▍| 58120/61904 [6:53:56<1:29:01,  1.41s/it]
 94%|█████████▍| 58121/61904 [6:53:58<1:29:38,  1.42s/it]
 94%|█████████▍| 58122/61904 [6:53:59<1:29:53,  1.43s/it]
 94%|█████████▍| 58123/61904 [6:54:01<1:29:16,  1.42s/it]
 94%|█████████▍| 58124/61904 [6:54:02<1:29:07,  1.41s/it]
 94%|█████████▍| 58125/61904 [6:54:03<1:28:51,  1.41s/it]
 94%|█████████▍| 58126/61904 [6:54:05<1:28:48,  1.41s/it]
 94%|█████████▍| 58127/61904 [6:54:07<1:34:00,  1.49s/it]
 94%|█████████▍| 58128/61904 [6:54:08<1:34:40,  1.50s/it]
 94%|█████████▍| 58129/61904 [6:54:10<1:37:43,  1.55s/it]
 94%|█████████▍| 58130/61904 [6:54:11<1:35:00,  1.51s/it]
 94%|█████████▍| 58131/61904 [6:54:13<1:32:43,  1.47s/it]
 94%|█████████▍| 58132/61904 [6:54:14<1:30:49,  1.44s/it]
 94%|█████████▍| 58133/61904 [6:54:15<1:31:34,  1.46s/it]
 94%|█████████▍| 58134/61904 [6:54:17<1:30:37,  1.44s/it]
 94%|█████████▍| 58135/61904 [6:54:18<1:30:26,  1.44s/it]
 94%|█████████▍| 58136/61904 [6:54:20<1:31:49,  1.46s/it]
 94%|█████████▍| 58137/61904 [6:54:21<1:32:47,  1.48s/it]
 94%|█████████▍| 58138/61904 [6:54:23<1:31:51,  1.46s/it]
 94%|█████████▍| 58139/61904 [6:54:24<1:33:38,  1.49s/it]
 94%|█████████▍| 58140/61904 [6:54:26<1:30:37,  1.44s/it]
                                                         
{'loss': 2.438, 'learning_rate': 1.061000907558667e-07, 'epoch': 15.03}
+
 94%|█████████▍| 58140/61904 [6:54:26<1:30:37,  1.44s/it]
 94%|█████████▍| 58141/61904 [6:54:27<1:30:28,  1.44s/it]
 94%|█████████▍| 58142/61904 [6:54:28<1:30:51,  1.45s/it]
 94%|█████████▍| 58143/61904 [6:54:30<1:31:02,  1.45s/it]
 94%|█████████▍| 58144/61904 [6:54:31<1:31:46,  1.46s/it]
 94%|█████████▍| 58145/61904 [6:54:33<1:29:34,  1.43s/it]
 94%|█████████▍| 58146/61904 [6:54:34<1:26:23,  1.38s/it]
 94%|█████████▍| 58147/61904 [6:54:35<1:28:11,  1.41s/it]
 94%|█████████▍| 58148/61904 [6:54:37<1:28:44,  1.42s/it]
 94%|█████████▍| 58149/61904 [6:54:38<1:28:34,  1.42s/it]
 94%|█████████▍| 58150/61904 [6:54:40<1:30:00,  1.44s/it]
 94%|█████████▍| 58151/61904 [6:54:41<1:29:44,  1.43s/it]
 94%|█████████▍| 58152/61904 [6:54:43<1:30:09,  1.44s/it]
 94%|█████████▍| 58153/61904 [6:54:44<1:29:35,  1.43s/it]
 94%|█████████▍| 58154/61904 [6:54:45<1:28:12,  1.41s/it]
 94%|█████████▍| 58155/61904 [6:54:47<1:27:11,  1.40s/it]
 94%|█████████▍| 58156/61904 [6:54:48<1:28:37,  1.42s/it]
 94%|█████████▍| 58157/61904 [6:54:50<1:27:08,  1.40s/it]
 94%|█████████▍| 58158/61904 [6:54:51<1:29:58,  1.44s/it]
 94%|█████████▍| 58159/61904 [6:54:53<1:32:32,  1.48s/it]
 94%|█████████▍| 58160/61904 [6:54:54<1:29:31,  1.43s/it]
                                                         
{'loss': 2.4204, 'learning_rate': 1.0606767794632439e-07, 'epoch': 15.03}
+
 94%|█████████▍| 58160/61904 [6:54:54<1:29:31,  1.43s/it]
 94%|█████████▍| 58161/61904 [6:54:55<1:27:30,  1.40s/it]
 94%|█████████▍| 58162/61904 [6:54:57<1:27:10,  1.40s/it]
 94%|█████████▍| 58163/61904 [6:54:58<1:25:22,  1.37s/it]
 94%|█████████▍| 58164/61904 [6:54:59<1:25:08,  1.37s/it]
 94%|█████████▍| 58165/61904 [6:55:01<1:27:09,  1.40s/it]
 94%|█████████▍| 58166/61904 [6:55:02<1:27:49,  1.41s/it]
 94%|█████████▍| 58167/61904 [6:55:04<1:27:35,  1.41s/it]
 94%|█████████▍| 58168/61904 [6:55:05<1:25:59,  1.38s/it]
 94%|█████████▍| 58169/61904 [6:55:07<1:25:53,  1.38s/it]
 94%|█████████▍| 58170/61904 [6:55:08<1:26:23,  1.39s/it]
 94%|█████████▍| 58171/61904 [6:55:09<1:25:00,  1.37s/it]
 94%|█████████▍| 58172/61904 [6:55:11<1:25:28,  1.37s/it]
 94%|█████████▍| 58173/61904 [6:55:12<1:25:04,  1.37s/it]
 94%|█████████▍| 58174/61904 [6:55:13<1:22:42,  1.33s/it]
 94%|█████████▍| 58175/61904 [6:55:15<1:23:01,  1.34s/it]
 94%|█████████▍| 58176/61904 [6:55:16<1:24:17,  1.36s/it]
 94%|█████████▍| 58177/61904 [6:55:17<1:26:07,  1.39s/it]
 94%|█████████▍| 58178/61904 [6:55:19<1:26:18,  1.39s/it]
 94%|█████████▍| 58179/61904 [6:55:20<1:25:59,  1.39s/it]
 94%|█████████▍| 58180/61904 [6:55:22<1:26:37,  1.40s/it]
                                                         
{'loss': 2.4318, 'learning_rate': 1.0603526513678205e-07, 'epoch': 15.04}
+
 94%|█████████▍| 58180/61904 [6:55:22<1:26:37,  1.40s/it]
 94%|█████████▍| 58181/61904 [6:55:23<1:27:55,  1.42s/it]
 94%|█████████▍| 58182/61904 [6:55:24<1:26:04,  1.39s/it]
 94%|█████████▍| 58183/61904 [6:55:26<1:25:32,  1.38s/it]
 94%|█████████▍| 58184/61904 [6:55:27<1:25:14,  1.37s/it]
 94%|█████████▍| 58185/61904 [6:55:28<1:22:42,  1.33s/it]
 94%|█████████▍| 58186/61904 [6:55:30<1:23:58,  1.36s/it]
 94%|█████████▍| 58187/61904 [6:55:31<1:22:15,  1.33s/it]
 94%|█████████▍| 58188/61904 [6:55:32<1:23:44,  1.35s/it]
 94%|█████████▍| 58189/61904 [6:55:34<1:21:32,  1.32s/it]
 94%|█████████▍| 58190/61904 [6:55:35<1:20:23,  1.30s/it]
 94%|█████████▍| 58191/61904 [6:55:36<1:21:42,  1.32s/it]
 94%|█████████▍| 58192/61904 [6:55:38<1:24:06,  1.36s/it]
 94%|█████████▍| 58193/61904 [6:55:39<1:22:50,  1.34s/it]
 94%|█████████▍| 58194/61904 [6:55:40<1:22:00,  1.33s/it]
 94%|█████████▍| 58195/61904 [6:55:42<1:21:51,  1.32s/it]
 94%|█████████▍| 58196/61904 [6:55:43<1:24:32,  1.37s/it]
 94%|█████████▍| 58197/61904 [6:55:44<1:24:26,  1.37s/it]
 94%|█████████▍| 58198/61904 [6:55:46<1:21:51,  1.33s/it]
 94%|█████████▍| 58199/61904 [6:55:47<1:23:26,  1.35s/it]
 94%|█████████▍| 58200/61904 [6:55:49<1:27:46,  1.42s/it]
                                                         
{'loss': 2.4512, 'learning_rate': 1.0600285232723974e-07, 'epoch': 15.04}
+
 94%|█████████▍| 58200/61904 [6:55:49<1:27:46,  1.42s/it]
 94%|█████████▍| 58201/61904 [6:55:50<1:27:37,  1.42s/it]
 94%|█████████▍| 58202/61904 [6:55:51<1:26:03,  1.39s/it]
 94%|█████████▍| 58203/61904 [6:55:53<1:27:03,  1.41s/it]
 94%|█████████▍| 58204/61904 [6:55:54<1:24:58,  1.38s/it]
 94%|█████████▍| 58205/61904 [6:55:55<1:22:54,  1.34s/it]
 94%|█████████���| 58206/61904 [6:55:57<1:23:05,  1.35s/it]
 94%|█████████▍| 58207/61904 [6:55:58<1:23:15,  1.35s/it]
 94%|█████████▍| 58208/61904 [6:56:00<1:23:17,  1.35s/it]
 94%|█████████▍| 58209/61904 [6:56:01<1:25:01,  1.38s/it]
 94%|█████████▍| 58210/61904 [6:56:02<1:24:55,  1.38s/it]
 94%|█████████▍| 58211/61904 [6:56:04<1:25:25,  1.39s/it]
 94%|█████████▍| 58212/61904 [6:56:05<1:26:05,  1.40s/it]
 94%|█████████▍| 58213/61904 [6:56:07<1:24:35,  1.38s/it]
 94%|█████████▍| 58214/61904 [6:56:08<1:21:55,  1.33s/it]
 94%|█████████▍| 58215/61904 [6:56:09<1:23:03,  1.35s/it]
 94%|█████████▍| 58216/61904 [6:56:10<1:22:34,  1.34s/it]
 94%|█████████▍| 58217/61904 [6:56:12<1:24:55,  1.38s/it]
 94%|█████████▍| 58218/61904 [6:56:14<1:27:54,  1.43s/it]
 94%|█████████▍| 58219/61904 [6:56:15<1:26:05,  1.40s/it]
 94%|█████████▍| 58220/61904 [6:56:16<1:26:30,  1.41s/it]
                                                         
{'loss': 2.4247, 'learning_rate': 1.0597043951769737e-07, 'epoch': 15.05}
+
 94%|█████████▍| 58220/61904 [6:56:16<1:26:30,  1.41s/it]
 94%|█████████▍| 58221/61904 [6:56:18<1:24:59,  1.38s/it]
 94%|█████████▍| 58222/61904 [6:56:19<1:25:09,  1.39s/it]
 94%|█████████▍| 58223/61904 [6:56:20<1:22:43,  1.35s/it]
 94%|█████████▍| 58224/61904 [6:56:22<1:23:22,  1.36s/it]
 94%|█████████▍| 58225/61904 [6:56:23<1:24:50,  1.38s/it]
 94%|█████████▍| 58226/61904 [6:56:24<1:25:34,  1.40s/it]
 94%|█████████▍| 58227/61904 [6:56:26<1:27:09,  1.42s/it]
 94%|█████████▍| 58228/61904 [6:56:27<1:26:03,  1.40s/it]
 94%|█████████▍| 58229/61904 [6:56:29<1:26:34,  1.41s/it]
 94%|█████████▍| 58230/61904 [6:56:30<1:24:40,  1.38s/it]
 94%|█████████▍| 58231/61904 [6:56:32<1:25:57,  1.40s/it]
 94%|█████████▍| 58232/61904 [6:56:33<1:25:31,  1.40s/it]
 94%|█████████▍| 58233/61904 [6:56:34<1:22:50,  1.35s/it]
 94%|█████████▍| 58234/61904 [6:56:36<1:22:58,  1.36s/it]
 94%|█████████▍| 58235/61904 [6:56:37<1:23:01,  1.36s/it]
 94%|█████████▍| 58236/61904 [6:56:38<1:23:06,  1.36s/it]
 94%|█████████▍| 58237/61904 [6:56:40<1:24:28,  1.38s/it]
 94%|█████████▍| 58238/61904 [6:56:41<1:25:22,  1.40s/it]
 94%|█████████▍| 58239/61904 [6:56:43<1:28:07,  1.44s/it]
 94%|█████████▍| 58240/61904 [6:56:44<1:27:25,  1.43s/it]
                                                         
{'loss': 2.4195, 'learning_rate': 1.0593802670815506e-07, 'epoch': 15.05}
+
 94%|█████████▍| 58240/61904 [6:56:44<1:27:25,  1.43s/it]
 94%|█████████▍| 58241/61904 [6:56:46<1:27:29,  1.43s/it]
 94%|█████████▍| 58242/61904 [6:56:47<1:28:02,  1.44s/it]
 94%|█████████▍| 58243/61904 [6:56:48<1:26:59,  1.43s/it]
 94%|█████████▍| 58244/61904 [6:56:50<1:29:26,  1.47s/it]
 94%|█████████▍| 58245/61904 [6:56:51<1:25:09,  1.40s/it]
 94%|█████████▍| 58246/61904 [6:56:53<1:25:54,  1.41s/it]
 94%|█████████▍| 58247/61904 [6:56:54<1:25:33,  1.40s/it]
 94%|█████████▍| 58248/61904 [6:56:55<1:24:46,  1.39s/it]
 94%|█████████▍| 58249/61904 [6:56:57<1:20:46,  1.33s/it]
 94%|█████████▍| 58250/61904 [6:56:58<1:21:20,  1.34s/it]
 94%|█████████▍| 58251/61904 [6:56:59<1:19:53,  1.31s/it]
 94%|█████████▍| 58252/61904 [6:57:00<1:19:23,  1.30s/it]
 94%|█████████▍| 58253/61904 [6:57:02<1:19:55,  1.31s/it]
 94%|█████████▍| 58254/61904 [6:57:03<1:19:43,  1.31s/it]
 94%|█████████▍| 58255/61904 [6:57:04<1:19:09,  1.30s/it]
 94%|█████████▍| 58256/61904 [6:57:06<1:19:49,  1.31s/it]
 94%|█████████▍| 58257/61904 [6:57:07<1:23:29,  1.37s/it]
 94%|█████████▍| 58258/61904 [6:57:09<1:24:50,  1.40s/it]
 94%|█████████▍| 58259/61904 [6:57:10<1:25:16,  1.40s/it]
 94%|█████████▍| 58260/61904 [6:57:11<1:23:56,  1.38s/it]
                                                         
{'loss': 2.4264, 'learning_rate': 1.0590561389861272e-07, 'epoch': 15.06}
+
 94%|█████████▍| 58260/61904 [6:57:11<1:23:56,  1.38s/it]
 94%|█████████▍| 58261/61904 [6:57:13<1:23:02,  1.37s/it]
 94%|█████████▍| 58262/61904 [6:57:14<1:23:08,  1.37s/it]
 94%|█████████▍| 58263/61904 [6:57:15<1:21:52,  1.35s/it]
 94%|█████████▍| 58264/61904 [6:57:17<1:22:23,  1.36s/it]
 94%|█████████▍| 58265/61904 [6:57:18<1:22:50,  1.37s/it]
 94%|█████████▍| 58266/61904 [6:57:20<1:23:51,  1.38s/it]
 94%|█████████▍| 58267/61904 [6:57:21<1:21:37,  1.35s/it]
 94%|█████████▍| 58268/61904 [6:57:22<1:19:54,  1.32s/it]
 94%|█████████▍| 58269/61904 [6:57:24<1:21:12,  1.34s/it]
 94%|█████████▍| 58270/61904 [6:57:25<1:22:18,  1.36s/it]
 94%|█████████▍| 58271/61904 [6:57:26<1:22:36,  1.36s/it]
 94%|█████████▍| 58272/61904 [6:57:28<1:21:04,  1.34s/it]
 94%|█████████▍| 58273/61904 [6:57:29<1:21:17,  1.34s/it]
 94%|█████████▍| 58274/61904 [6:57:30<1:22:08,  1.36s/it]
 94%|█████████▍| 58275/61904 [6:57:32<1:25:58,  1.42s/it]
 94%|█████████▍| 58276/61904 [6:57:33<1:23:02,  1.37s/it]
 94%|█████████▍| 58277/61904 [6:57:34<1:22:19,  1.36s/it]
 94%|█████████▍| 58278/61904 [6:57:36<1:23:23,  1.38s/it]
 94%|█████████▍| 58279/61904 [6:57:37<1:26:22,  1.43s/it]
 94%|█████████▍| 58280/61904 [6:57:39<1:23:37,  1.38s/it]
                                                         
{'loss': 2.4425, 'learning_rate': 1.0587320108907041e-07, 'epoch': 15.06}
+
 94%|█████████▍| 58280/61904 [6:57:39<1:23:37,  1.38s/it]
 94%|█████████▍| 58281/61904 [6:57:40<1:24:07,  1.39s/it]
 94%|█████████▍| 58282/61904 [6:57:42<1:25:01,  1.41s/it]
 94%|█████████▍| 58283/61904 [6:57:43<1:23:00,  1.38s/it]
 94%|█████████▍| 58284/61904 [6:57:44<1:21:20,  1.35s/it]
 94%|█████████▍| 58285/61904 [6:57:46<1:21:57,  1.36s/it]
 94%|█████████▍| 58286/61904 [6:57:47<1:23:34,  1.39s/it]
 94%|█████████▍| 58287/61904 [6:57:48<1:25:09,  1.41s/it]
 94%|█████████▍| 58288/61904 [6:57:50<1:26:27,  1.43s/it]
 94%|█████████▍| 58289/61904 [6:57:51<1:24:53,  1.41s/it]
 94%|█████████▍| 58290/61904 [6:57:53<1:24:08,  1.40s/it]
 94%|█████████▍| 58291/61904 [6:57:54<1:23:53,  1.39s/it]
 94%|█████████▍| 58292/61904 [6:57:56<1:26:54,  1.44s/it]
 94%|█████████▍| 58293/61904 [6:57:57<1:25:50,  1.43s/it]
 94%|█████████▍| 58294/61904 [6:57:58<1:23:22,  1.39s/it]
 94%|█████████▍| 58295/61904 [6:58:00<1:21:17,  1.35s/it]
 94%|█████████▍| 58296/61904 [6:58:01<1:22:33,  1.37s/it]
 94%|█████████▍| 58297/61904 [6:58:02<1:23:01,  1.38s/it]
 94%|█████████▍| 58298/61904 [6:58:04<1:24:17,  1.40s/it]
 94%|█████████▍| 58299/61904 [6:58:05<1:24:50,  1.41s/it]
 94%|█████████▍| 58300/61904 [6:58:07<1:23:57,  1.40s/it]
                                                         
{'loss': 2.3938, 'learning_rate': 1.0584078827952805e-07, 'epoch': 15.07}
+
 94%|█████████▍| 58300/61904 [6:58:07<1:23:57,  1.40s/it]
 94%|█████████▍| 58301/61904 [6:58:08<1:20:28,  1.34s/it]
 94%|█████████▍| 58302/61904 [6:58:09<1:19:54,  1.33s/it]
 94%|█████████▍| 58303/61904 [6:58:11<1:21:08,  1.35s/it]
 94%|█████████▍| 58304/61904 [6:58:12<1:22:28,  1.37s/it]
 94%|█████████▍| 58305/61904 [6:58:13<1:22:53,  1.38s/it]
 94%|█████████▍| 58306/61904 [6:58:15<1:21:26,  1.36s/it]
 94%|█████████▍| 58307/61904 [6:58:16<1:20:16,  1.34s/it]
 94%|█████████▍| 58308/61904 [6:58:17<1:20:18,  1.34s/it]
 94%|█████████▍| 58309/61904 [6:58:19<1:24:50,  1.42s/it]
 94%|█████████▍| 58310/61904 [6:58:20<1:25:51,  1.43s/it]
 94%|█████████▍| 58311/61904 [6:58:22<1:28:00,  1.47s/it]
 94%|█████████▍| 58312/61904 [6:58:23<1:28:11,  1.47s/it]
 94%|█████████▍| 58313/61904 [6:58:25<1:25:42,  1.43s/it]
 94%|█████████▍| 58314/61904 [6:58:26<1:24:59,  1.42s/it]
 94%|█████████▍| 58315/61904 [6:58:28<1:28:38,  1.48s/it]
 94%|█████████▍| 58316/61904 [6:58:29<1:26:01,  1.44s/it]
 94%|█████████▍| 58317/61904 [6:58:31<1:27:21,  1.46s/it]
 94%|█████████▍| 58318/61904 [6:58:32<1:25:10,  1.43s/it]
 94%|█████████▍| 58319/61904 [6:58:33<1:23:34,  1.40s/it]
 94%|█████████▍| 58320/61904 [6:58:35<1:24:26,  1.41s/it]
                                                         
{'loss': 2.4447, 'learning_rate': 1.0580837546998573e-07, 'epoch': 15.07}
+
 94%|█████████▍| 58320/61904 [6:58:35<1:24:26,  1.41s/it]
 94%|████████��▍| 58321/61904 [6:58:36<1:23:00,  1.39s/it]
 94%|█████████▍| 58322/61904 [6:58:38<1:25:27,  1.43s/it]
 94%|█████████▍| 58323/61904 [6:58:39<1:24:28,  1.42s/it]
 94%|█████████▍| 58324/61904 [6:58:40<1:20:49,  1.35s/it]
 94%|█████████▍| 58325/61904 [6:58:42<1:22:17,  1.38s/it]
 94%|█████████▍| 58326/61904 [6:58:43<1:22:41,  1.39s/it]
 94%|█████████▍| 58327/61904 [6:58:45<1:24:09,  1.41s/it]
 94%|█████████▍| 58328/61904 [6:58:46<1:28:15,  1.48s/it]
 94%|█████████▍| 58329/61904 [6:58:47<1:24:41,  1.42s/it]
 94%|█████████▍| 58330/61904 [6:58:49<1:23:26,  1.40s/it]
 94%|█████████▍| 58331/61904 [6:58:50<1:23:21,  1.40s/it]
 94%|█████████▍| 58332/61904 [6:58:52<1:24:22,  1.42s/it]
 94%|█████████▍| 58333/61904 [6:58:53<1:24:20,  1.42s/it]
 94%|█████████▍| 58334/61904 [6:58:54<1:23:58,  1.41s/it]
 94%|█████████▍| 58335/61904 [6:58:56<1:26:12,  1.45s/it]
 94%|█████████▍| 58336/61904 [6:58:57<1:23:06,  1.40s/it]
 94%|█████████▍| 58337/61904 [6:58:59<1:23:08,  1.40s/it]
 94%|█████████▍| 58338/61904 [6:59:00<1:22:35,  1.39s/it]
 94%|█████████▍| 58339/61904 [6:59:01<1:22:01,  1.38s/it]
 94%|█████████▍| 58340/61904 [6:59:03<1:21:46,  1.38s/it]
                                                         
{'loss': 2.3923, 'learning_rate': 1.0577596266044342e-07, 'epoch': 15.08}
+
 94%|█████████▍| 58340/61904 [6:59:03<1:21:46,  1.38s/it]
 94%|█████████▍| 58341/61904 [6:59:04<1:22:38,  1.39s/it]
 94%|█████████▍| 58342/61904 [6:59:06<1:21:04,  1.37s/it]
 94%|█████████▍| 58343/61904 [6:59:07<1:20:06,  1.35s/it]
 94%|█████████▍| 58344/61904 [6:59:08<1:18:53,  1.33s/it]
 94%|█████████▍| 58345/61904 [6:59:09<1:19:25,  1.34s/it]
 94%|█████████▍| 58346/61904 [6:59:11<1:21:44,  1.38s/it]
 94%|█████████▍| 58347/61904 [6:59:12<1:19:37,  1.34s/it]
 94%|█████████▍| 58348/61904 [6:59:14<1:18:47,  1.33s/it]
 94%|█████████▍| 58349/61904 [6:59:15<1:19:33,  1.34s/it]
 94%|█████████▍| 58350/61904 [6:59:16<1:20:37,  1.36s/it]
 94%|█████████▍| 58351/61904 [6:59:18<1:19:22,  1.34s/it]
 94%|█████████▍| 58352/61904 [6:59:19<1:23:03,  1.40s/it]
 94%|█████████▍| 58353/61904 [6:59:20<1:22:00,  1.39s/it]
 94%|█████████▍| 58354/61904 [6:59:22<1:21:07,  1.37s/it]
 94%|█████████▍| 58355/61904 [6:59:23<1:23:22,  1.41s/it]
 94%|█████████▍| 58356/61904 [6:59:25<1:23:24,  1.41s/it]
 94%|█████████▍| 58357/61904 [6:59:26<1:22:07,  1.39s/it]
 94%|█████████▍| 58358/61904 [6:59:27<1:22:17,  1.39s/it]
 94%|█████████▍| 58359/61904 [6:59:29<1:20:17,  1.36s/it]
 94%|█████████▍| 58360/61904 [6:59:30<1:20:24,  1.36s/it]
                                                         
{'loss': 2.4065, 'learning_rate': 1.0574354985090108e-07, 'epoch': 15.08}
+
 94%|█████████▍| 58360/61904 [6:59:30<1:20:24,  1.36s/it]
 94%|█████████▍| 58361/61904 [6:59:31<1:20:03,  1.36s/it]
 94%|█████████▍| 58362/61904 [6:59:33<1:20:35,  1.37s/it]
 94%|█████████▍| 58363/61904 [6:59:34<1:23:55,  1.42s/it]
 94%|█████████▍| 58364/61904 [6:59:36<1:21:47,  1.39s/it]
 94%|█████████▍| 58365/61904 [6:59:37<1:21:07,  1.38s/it]
 94%|█████████▍| 58366/61904 [6:59:38<1:19:16,  1.34s/it]
 94%|█████████▍| 58367/61904 [6:59:40<1:18:50,  1.34s/it]
 94%|█████████▍| 58368/61904 [6:59:41<1:17:29,  1.31s/it]
 94%|█████████▍| 58369/61904 [6:59:42<1:18:48,  1.34s/it]
 94%|█████████▍| 58370/61904 [6:59:44<1:19:22,  1.35s/it]
 94%|█████████▍| 58371/61904 [6:59:45<1:17:13,  1.31s/it]
 94%|█████████▍| 58372/61904 [6:59:46<1:17:59,  1.32s/it]
 94%|█████████▍| 58373/61904 [6:59:48<1:17:09,  1.31s/it]
 94%|█████████▍| 58374/61904 [6:59:49<1:17:35,  1.32s/it]
 94%|█████████▍| 58375/61904 [6:59:50<1:17:38,  1.32s/it]
 94%|█████████▍| 58376/61904 [6:59:52<1:21:01,  1.38s/it]
 94%|█████████▍| 58377/61904 [6:59:53<1:20:32,  1.37s/it]
 94%|█████████▍| 58378/61904 [6:59:54<1:20:35,  1.37s/it]
 94%|█████████▍| 58379/61904 [6:59:56<1:22:11,  1.40s/it]
 94%|█████████▍| 58380/61904 [6:59:57<1:20:34,  1.37s/it]
                                                         
{'loss': 2.4171, 'learning_rate': 1.0571113704135875e-07, 'epoch': 15.09}
+
 94%|█████████▍| 58380/61904 [6:59:57<1:20:34,  1.37s/it]
 94%|█████████▍| 58381/61904 [6:59:59<1:19:55,  1.36s/it]
 94%|█████████▍| 58382/61904 [7:00:00<1:20:55,  1.38s/it]
 94%|█████████▍| 58383/61904 [7:00:01<1:20:38,  1.37s/it]
 94%|█████████▍| 58384/61904 [7:00:03<1:22:51,  1.41s/it]
 94%|█████████▍| 58385/61904 [7:00:04<1:22:03,  1.40s/it]
 94%|█████████▍| 58386/61904 [7:00:06<1:21:21,  1.39s/it]
 94%|█████████▍| 58387/61904 [7:00:07<1:21:37,  1.39s/it]
 94%|█████████▍| 58388/61904 [7:00:08<1:20:43,  1.38s/it]
 94%|█████████▍| 58389/61904 [7:00:10<1:21:40,  1.39s/it]
 94%|█████████▍| 58390/61904 [7:00:11<1:19:48,  1.36s/it]
 94%|█████████▍| 58391/61904 [7:00:12<1:20:24,  1.37s/it]
 94%|█████████▍| 58392/61904 [7:00:14<1:23:07,  1.42s/it]
 94%|█████████▍| 58393/61904 [7:00:16<1:25:55,  1.47s/it]
 94%|█████████▍| 58394/61904 [7:00:17<1:24:21,  1.44s/it]
 94%|█████████▍| 58395/61904 [7:00:18<1:22:31,  1.41s/it]
 94%|█████████▍| 58396/61904 [7:00:20<1:22:34,  1.41s/it]
 94%|█████████▍| 58397/61904 [7:00:21<1:20:48,  1.38s/it]
 94%|█████████▍| 58398/61904 [7:00:22<1:20:20,  1.37s/it]
 94%|█████████▍| 58399/61904 [7:00:24<1:24:34,  1.45s/it]
 94%|█████████▍| 58400/61904 [7:00:25<1:23:50,  1.44s/it]
                                                         
{'loss': 2.4148, 'learning_rate': 1.0567872423181641e-07, 'epoch': 15.09}
+
 94%|█████████▍| 58400/61904 [7:00:25<1:23:50,  1.44s/it]
 94%|█████████▍| 58401/61904 [7:00:27<1:26:28,  1.48s/it]
 94%|█████████▍| 58402/61904 [7:00:28<1:23:31,  1.43s/it]
 94%|█████████▍| 58403/61904 [7:00:30<1:21:22,  1.39s/it]
 94%|█████████▍| 58404/61904 [7:00:31<1:20:19,  1.38s/it]
 94%|█████████▍| 58405/61904 [7:00:32<1:18:51,  1.35s/it]
 94%|█████████▍| 58406/61904 [7:00:34<1:19:51,  1.37s/it]
 94%|█████████▍| 58407/61904 [7:00:35<1:22:28,  1.42s/it]
 94%|█████████▍| 58408/61904 [7:00:36<1:20:21,  1.38s/it]
 94%|█████████▍| 58409/61904 [7:00:38<1:18:42,  1.35s/it]
 94%|█████████▍| 58410/61904 [7:00:39<1:20:06,  1.38s/it]
 94%|█████████▍| 58411/61904 [7:00:40<1:16:40,  1.32s/it]
 94%|█████████▍| 58412/61904 [7:00:42<1:19:09,  1.36s/it]
 94%|█████████▍| 58413/61904 [7:00:43<1:20:24,  1.38s/it]
 94%|█████████▍| 58414/61904 [7:00:45<1:23:18,  1.43s/it]
 94%|█████████▍| 58415/61904 [7:00:46<1:21:25,  1.40s/it]
 94%|█████████▍| 58416/61904 [7:00:47<1:19:34,  1.37s/it]
 94%|█████████▍| 58417/61904 [7:00:49<1:18:18,  1.35s/it]
 94%|█████████▍| 58418/61904 [7:00:50<1:20:18,  1.38s/it]
 94%|█████████▍| 58419/61904 [7:00:51<1:19:08,  1.36s/it]
 94%|█████████▍| 58420/61904 [7:00:53<1:18:41,  1.36s/it]
                                                         
{'loss': 2.4317, 'learning_rate': 1.056463114222741e-07, 'epoch': 15.1}
+
 94%|█████████▍| 58420/61904 [7:00:53<1:18:41,  1.36s/it]
 94%|█████████▍| 58421/61904 [7:00:54<1:17:43,  1.34s/it]
 94%|█████████▍| 58422/61904 [7:00:55<1:16:29,  1.32s/it]
 94%|█████████▍| 58423/61904 [7:00:57<1:17:16,  1.33s/it]
 94%|█████████▍| 58424/61904 [7:00:58<1:18:25,  1.35s/it]
 94%|█████████▍| 58425/61904 [7:00:59<1:17:52,  1.34s/it]
 94%|█████████▍| 58426/61904 [7:01:01<1:20:15,  1.38s/it]
 94%|█████████▍| 58427/61904 [7:01:02<1:18:27,  1.35s/it]
 94%|█████████▍| 58428/61904 [7:01:04<1:22:56,  1.43s/it]
 94%|█████████▍| 58429/61904 [7:01:05<1:23:26,  1.44s/it]
 94%|█████████▍| 58430/61904 [7:01:07<1:22:11,  1.42s/it]
 94%|█████████▍| 58431/61904 [7:01:08<1:21:31,  1.41s/it]
 94%|█████████▍| 58432/61904 [7:01:10<1:23:09,  1.44s/it]
 94%|█████████▍| 58433/61904 [7:01:11<1:20:15,  1.39s/it]
 94%|█████████▍| 58434/61904 [7:01:12<1:19:37,  1.38s/it]
 94%|█████████▍| 58435/61904 [7:01:14<1:18:42,  1.36s/it]
 94%|█████████▍| 58436/61904 [7:01:15<1:17:12,  1.34s/it]
 94%|█████████▍| 58437/61904 [7:01:16<1:19:21,  1.37s/it]
 94%|█████████▍| 58438/61904 [7:01:18<1:19:41,  1.38s/it]
 94%|█���███████▍| 58439/61904 [7:01:19<1:18:14,  1.35s/it]
 94%|█████████▍| 58440/61904 [7:01:20<1:18:02,  1.35s/it]
                                                         
{'loss': 2.3749, 'learning_rate': 1.0561389861273176e-07, 'epoch': 15.1}
+
 94%|█████████▍| 58440/61904 [7:01:20<1:18:02,  1.35s/it]
 94%|█████████▍| 58441/61904 [7:01:22<1:16:53,  1.33s/it]
 94%|█████████▍| 58442/61904 [7:01:23<1:17:16,  1.34s/it]
 94%|█████████▍| 58443/61904 [7:01:24<1:16:04,  1.32s/it]
 94%|█████████▍| 58444/61904 [7:01:26<1:16:04,  1.32s/it]
 94%|█████████▍| 58445/61904 [7:01:27<1:15:58,  1.32s/it]
 94%|█████████▍| 58446/61904 [7:01:28<1:14:41,  1.30s/it]
 94%|█████████▍| 58447/61904 [7:01:30<1:17:48,  1.35s/it]
 94%|█████████▍| 58448/61904 [7:01:31<1:19:01,  1.37s/it]
 94%|█████████▍| 58449/61904 [7:01:32<1:18:06,  1.36s/it]
 94%|█████████▍| 58450/61904 [7:01:34<1:19:03,  1.37s/it]
 94%|█████████▍| 58451/61904 [7:01:35<1:16:33,  1.33s/it]
 94%|█████████▍| 58452/61904 [7:01:36<1:16:50,  1.34s/it]
 94%|█████████▍| 58453/61904 [7:01:38<1:18:39,  1.37s/it]
 94%|█████████▍| 58454/61904 [7:01:39<1:22:01,  1.43s/it]
 94%|█████████▍| 58455/61904 [7:01:41<1:19:16,  1.38s/it]
 94%|█████████▍| 58456/61904 [7:01:42<1:18:46,  1.37s/it]
 94%|█████████▍| 58457/61904 [7:01:43<1:18:25,  1.37s/it]
 94%|█████████▍| 58458/61904 [7:01:45<1:19:35,  1.39s/it]
 94%|█████████▍| 58459/61904 [7:01:46<1:21:37,  1.42s/it]
 94%|█████████▍| 58460/61904 [7:01:47<1:17:40,  1.35s/it]
                                                         
{'loss': 2.3947, 'learning_rate': 1.0558148580318942e-07, 'epoch': 15.11}
+
 94%|█████████▍| 58460/61904 [7:01:47<1:17:40,  1.35s/it]
 94%|█████████▍| 58461/61904 [7:01:49<1:15:57,  1.32s/it]
 94%|█████████▍| 58462/61904 [7:01:50<1:17:42,  1.35s/it]
 94%|█████████▍| 58463/61904 [7:01:52<1:19:19,  1.38s/it]
 94%|█████████▍| 58464/61904 [7:01:53<1:19:10,  1.38s/it]
 94%|█████████▍| 58465/61904 [7:01:54<1:17:03,  1.34s/it]
 94%|█████████▍| 58466/61904 [7:01:55<1:16:08,  1.33s/it]
 94%|█████████▍| 58467/61904 [7:01:57<1:16:53,  1.34s/it]
 94%|█████████▍| 58468/61904 [7:01:58<1:18:53,  1.38s/it]
 94%|█████████▍| 58469/61904 [7:02:00<1:19:34,  1.39s/it]
 94%|█████████▍| 58470/61904 [7:02:01<1:21:44,  1.43s/it]
 94%|█████████▍| 58471/61904 [7:02:03<1:20:17,  1.40s/it]
 94%|█████████▍| 58472/61904 [7:02:04<1:18:31,  1.37s/it]
 94%|█████████▍| 58473/61904 [7:02:05<1:17:16,  1.35s/it]
 94%|█████████▍| 58474/61904 [7:02:06<1:16:21,  1.34s/it]
 94%|█████████▍| 58475/61904 [7:02:08<1:14:45,  1.31s/it]
 94%|█████████▍| 58476/61904 [7:02:09<1:17:02,  1.35s/it]
 94%|█████████▍| 58477/61904 [7:02:11<1:18:50,  1.38s/it]
 94%|█████████▍| 58478/61904 [7:02:12<1:17:32,  1.36s/it]
 94%|█████████▍| 58479/61904 [7:02:13<1:19:31,  1.39s/it]
 94%|█████████▍| 58480/61904 [7:02:15<1:20:34,  1.41s/it]
                                                         
{'loss': 2.3908, 'learning_rate': 1.0554907299364708e-07, 'epoch': 15.11}
+
 94%|█████████▍| 58480/61904 [7:02:15<1:20:34,  1.41s/it]
 94%|█████████▍| 58481/61904 [7:02:16<1:21:24,  1.43s/it]
 94%|█████████▍| 58482/61904 [7:02:18<1:20:51,  1.42s/it]
 94%|█████████▍| 58483/61904 [7:02:19<1:22:05,  1.44s/it]
 94%|█████████▍| 58484/61904 [7:02:21<1:20:02,  1.40s/it]
 94%|█████████▍| 58485/61904 [7:02:22<1:21:47,  1.44s/it]
 94%|█████████▍| 58486/61904 [7:02:23<1:21:49,  1.44s/it]
 94%|█████████▍| 58487/61904 [7:02:25<1:18:49,  1.38s/it]
 94%|█████████▍| 58488/61904 [7:02:26<1:18:12,  1.37s/it]
 94%|█████████▍| 58489/61904 [7:02:27<1:17:31,  1.36s/it]
 94%|█████████▍| 58490/61904 [7:02:29<1:17:19,  1.36s/it]
 94%|█████████▍| 58491/61904 [7:02:30<1:15:57,  1.34s/it]
 94%|█████████▍| 58492/61904 [7:02:31<1:15:54,  1.33s/it]
 94%|█████████▍| 58493/61904 [7:02:33<1:17:59,  1.37s/it]
 94%|█████████▍| 58494/61904 [7:02:34<1:17:24,  1.36s/it]
 94%|█████████▍| 58495/61904 [7:02:36<1:25:07,  1.50s/it]
 94%|█████████▍| 58496/61904 [7:02:37<1:22:02,  1.44s/it]
 94%|█████████▍| 58497/61904 [7:02:39<1:24:33,  1.49s/it]
 94%|█████████▍| 58498/61904 [7:02:40<1:22:01,  1.45s/it]
 94%|█████████▍| 58499/61904 [7:02:42<1:20:01,  1.41s/it]
 95%|█████████▍| 58500/61904 [7:02:43<1:19:47,  1.41s/it]
                                                         
{'loss': 2.3965, 'learning_rate': 1.0551666018410477e-07, 'epoch': 15.12}
+
 95%|█████████▍| 58500/61904 [7:02:43<1:19:47,  1.41s/it]
 95%|█████████▍| 58501/61904 [7:02:44<1:18:57,  1.39s/it]
 95%|█████████▍| 58502/61904 [7:02:46<1:18:23,  1.38s/it]
 95%|█████████▍| 58503/61904 [7:02:47<1:17:12,  1.36s/it]
 95%|█████████▍| 58504/61904 [7:02:48<1:15:59,  1.34s/it]
 95%|█████████▍| 58505/61904 [7:02:50<1:16:50,  1.36s/it]
 95%|█████████▍| 58506/61904 [7:02:51<1:18:35,  1.39s/it]
 95%|█████████▍| 58507/61904 [7:02:52<1:17:30,  1.37s/it]
 95%|█████████▍| 58508/61904 [7:02:54<1:16:41,  1.35s/it]
 95%|█████████▍| 58509/61904 [7:02:55<1:17:47,  1.37s/it]
 95%|█████████▍| 58510/61904 [7:02:57<1:17:59,  1.38s/it]
 95%|█████████▍| 58511/61904 [7:02:58<1:17:28,  1.37s/it]
 95%|█████████▍| 58512/61904 [7:02:59<1:17:21,  1.37s/it]
 95%|█████████▍| 58513/61904 [7:03:01<1:17:27,  1.37s/it]
 95%|█████████▍| 58514/61904 [7:03:02<1:19:22,  1.40s/it]
 95%|█████████▍| 58515/61904 [7:03:04<1:18:04,  1.38s/it]
 95%|█████████▍| 58516/61904 [7:03:05<1:18:14,  1.39s/it]
 95%|█████████▍| 58517/61904 [7:03:06<1:17:19,  1.37s/it]
 95%|█████████▍| 58518/61904 [7:03:08<1:20:19,  1.42s/it]
 95%|█████████▍| 58519/61904 [7:03:09<1:21:52,  1.45s/it]
 95%|█████████▍| 58520/61904 [7:03:11<1:21:59,  1.45s/it]
                                                         
{'loss': 2.4536, 'learning_rate': 1.0548424737456243e-07, 'epoch': 15.12}
+
 95%|█████████▍| 58520/61904 [7:03:11<1:21:59,  1.45s/it]
 95%|█████████▍| 58521/61904 [7:03:12<1:20:14,  1.42s/it]
 95%|█████████▍| 58522/61904 [7:03:13<1:18:14,  1.39s/it]
 95%|█████████▍| 58523/61904 [7:03:15<1:21:22,  1.44s/it]
 95%|█████████▍| 58524/61904 [7:03:16<1:19:51,  1.42s/it]
 95%|█████████▍| 58525/61904 [7:03:18<1:17:50,  1.38s/it]
 95%|█████████▍| 58526/61904 [7:03:19<1:17:41,  1.38s/it]
 95%|█████████▍| 58527/61904 [7:03:20<1:16:44,  1.36s/it]
 95%|█████████▍| 58528/61904 [7:03:22<1:16:54,  1.37s/it]
 95%|█████████▍| 58529/61904 [7:03:23<1:17:06,  1.37s/it]
 95%|█████████▍| 58530/61904 [7:03:25<1:19:26,  1.41s/it]
 95%|█████████▍| 58531/61904 [7:03:26<1:18:38,  1.40s/it]
 95%|█████████▍| 58532/61904 [7:03:27<1:16:37,  1.36s/it]
 95%|█████████▍| 58533/61904 [7:03:28<1:14:23,  1.32s/it]
 95%|█████████▍| 58534/61904 [7:03:30<1:18:10,  1.39s/it]
 95%|█████████▍| 58535/61904 [7:03:31<1:17:01,  1.37s/it]
 95%|█████████▍| 58536/61904 [7:03:33<1:17:24,  1.38s/it]
 95%|█████████▍| 58537/61904 [7:03:34<1:15:59,  1.35s/it]
 95%|█████████▍| 58538/61904 [7:03:36<1:18:51,  1.41s/it]
 95%|█████████▍| 58539/61904 [7:03:37<1:17:58,  1.39s/it]
 95%|█████████▍| 58540/61904 [7:03:38<1:20:26,  1.43s/it]
                                                         
{'loss': 2.4602, 'learning_rate': 1.054518345650201e-07, 'epoch': 15.13}
+
 95%|█████████▍| 58540/61904 [7:03:38<1:20:26,  1.43s/it]
 95%|█████████▍| 58541/61904 [7:03:40<1:18:48,  1.41s/it]
 95%|█████████▍| 58542/61904 [7:03:41<1:20:21,  1.43s/it]
 95%|█████████▍| 58543/61904 [7:03:43<1:19:02,  1.41s/it]
 95%|█████████▍| 58544/61904 [7:03:44<1:18:45,  1.41s/it]
 95%|█████████▍| 58545/61904 [7:03:46<1:19:58,  1.43s/it]
 95%|█████████▍| 58546/61904 [7:03:47<1:18:20,  1.40s/it]
 95%|█████████▍| 58547/61904 [7:03:48<1:18:41,  1.41s/it]
 95%|█████████▍| 58548/61904 [7:03:50<1:19:36,  1.42s/it]
 95%|█████████▍| 58549/61904 [7:03:51<1:17:11,  1.38s/it]
 95%|█████████▍| 58550/61904 [7:03:52<1:15:16,  1.35s/it]
 95%|█████████▍| 58551/61904 [7:03:54<1:16:56,  1.38s/it]
 95%|█████████▍| 58552/61904 [7:03:55<1:19:46,  1.43s/it]
 95%|█████████▍| 58553/61904 [7:03:57<1:19:48,  1.43s/it]
 95%|█���███████▍| 58554/61904 [7:03:58<1:21:00,  1.45s/it]
 95%|█████████▍| 58555/61904 [7:04:00<1:20:21,  1.44s/it]
 95%|█████████▍| 58556/61904 [7:04:01<1:16:37,  1.37s/it]
 95%|█████████▍| 58557/61904 [7:04:02<1:18:00,  1.40s/it]
 95%|█████████▍| 58558/61904 [7:04:04<1:18:59,  1.42s/it]
 95%|█████████▍| 58559/61904 [7:04:05<1:19:24,  1.42s/it]
 95%|█████████▍| 58560/61904 [7:04:07<1:17:06,  1.38s/it]
                                                         
{'loss': 2.4214, 'learning_rate': 1.0541942175547776e-07, 'epoch': 15.14}
+
 95%|█████████▍| 58560/61904 [7:04:07<1:17:06,  1.38s/it]
 95%|█████████▍| 58561/61904 [7:04:08<1:20:11,  1.44s/it]
 95%|█████████▍| 58562/61904 [7:04:10<1:21:44,  1.47s/it]
 95%|█████████▍| 58563/61904 [7:04:11<1:18:14,  1.41s/it]
 95%|█████████▍| 58564/61904 [7:04:12<1:16:47,  1.38s/it]
 95%|█████████▍| 58565/61904 [7:04:14<1:16:55,  1.38s/it]
 95%|█████████▍| 58566/61904 [7:04:15<1:19:18,  1.43s/it]
 95%|█████████▍| 58567/61904 [7:04:17<1:19:13,  1.42s/it]
 95%|█████████▍| 58568/61904 [7:04:18<1:22:39,  1.49s/it]
 95%|█████████▍| 58569/61904 [7:04:20<1:21:48,  1.47s/it]
 95%|█████████▍| 58570/61904 [7:04:21<1:18:11,  1.41s/it]
 95%|█████████▍| 58571/61904 [7:04:22<1:17:17,  1.39s/it]
 95%|█████████▍| 58572/61904 [7:04:24<1:16:24,  1.38s/it]
 95%|█████████▍| 58573/61904 [7:04:25<1:15:03,  1.35s/it]
 95%|█████████▍| 58574/61904 [7:04:26<1:14:40,  1.35s/it]
 95%|█████████▍| 58575/61904 [7:04:28<1:14:11,  1.34s/it]
 95%|█████████▍| 58576/61904 [7:04:29<1:14:32,  1.34s/it]
 95%|█████████▍| 58577/61904 [7:04:30<1:15:32,  1.36s/it]
 95%|█████████▍| 58578/61904 [7:04:32<1:13:58,  1.33s/it]
 95%|█████████▍| 58579/61904 [7:04:33<1:12:14,  1.30s/it]
 95%|█████████▍| 58580/61904 [7:04:34<1:13:07,  1.32s/it]
                                                         
{'loss': 2.4254, 'learning_rate': 1.0538700894593544e-07, 'epoch': 15.14}
+
 95%|█████████▍| 58580/61904 [7:04:34<1:13:07,  1.32s/it]
 95%|█████████▍| 58581/61904 [7:04:35<1:12:42,  1.31s/it]
 95%|█████████▍| 58582/61904 [7:04:37<1:12:59,  1.32s/it]
 95%|█████████▍| 58583/61904 [7:04:38<1:12:12,  1.30s/it]
 95%|█████████▍| 58584/61904 [7:04:40<1:17:18,  1.40s/it]
 95%|█████████▍| 58585/61904 [7:04:41<1:16:29,  1.38s/it]
 95%|█████████▍| 58586/61904 [7:04:42<1:14:48,  1.35s/it]
 95%|█████████▍| 58587/61904 [7:04:43<1:12:24,  1.31s/it]
 95%|█████████▍| 58588/61904 [7:04:45<1:13:58,  1.34s/it]
 95%|█████████▍| 58589/61904 [7:04:46<1:11:53,  1.30s/it]
 95%|█████████▍| 58590/61904 [7:04:47<1:11:18,  1.29s/it]
 95%|█████████▍| 58591/61904 [7:04:49<1:14:20,  1.35s/it]
 95%|█████████▍| 58592/61904 [7:04:50<1:15:57,  1.38s/it]
 95%|█████████▍| 58593/61904 [7:04:52<1:15:47,  1.37s/it]
 95%|█████████▍| 58594/61904 [7:04:53<1:15:20,  1.37s/it]
 95%|█████████▍| 58595/61904 [7:04:54<1:13:43,  1.34s/it]
 95%|█████████▍| 58596/61904 [7:04:56<1:13:08,  1.33s/it]
 95%|█████████▍| 58597/61904 [7:04:57<1:15:49,  1.38s/it]
 95%|█████████▍| 58598/61904 [7:04:58<1:16:18,  1.38s/it]
 95%|█████████▍| 58599/61904 [7:05:00<1:16:03,  1.38s/it]
 95%|█████████▍| 58600/61904 [7:05:01<1:17:40,  1.41s/it]
                                                         
{'loss': 2.446, 'learning_rate': 1.053545961363931e-07, 'epoch': 15.15}
+
 95%|█████████▍| 58600/61904 [7:05:01<1:17:40,  1.41s/it]
 95%|█████████▍| 58601/61904 [7:05:03<1:16:39,  1.39s/it]
 95%|█████████▍| 58602/61904 [7:05:04<1:18:14,  1.42s/it]
 95%|█████████▍| 58603/61904 [7:05:05<1:15:12,  1.37s/it]
 95%|█████████▍| 58604/61904 [7:05:07<1:14:09,  1.35s/it]
 95%|█████████▍| 58605/61904 [7:05:08<1:16:47,  1.40s/it]
 95%|█████████▍| 58606/61904 [7:05:10<1:19:14,  1.44s/it]
 95%|█████████▍| 58607/61904 [7:05:11<1:17:47,  1.42s/it]
 95%|█████████▍| 58608/61904 [7:05:12<1:16:26,  1.39s/it]
 95%|█████████▍| 58609/61904 [7:05:14<1:14:54,  1.36s/it]
 95%|█████████▍| 58610/61904 [7:05:15<1:13:08,  1.33s/it]
 95%|█████████▍| 58611/61904 [7:05:16<1:13:47,  1.34s/it]
 95%|█████████▍| 58612/61904 [7:05:18<1:13:10,  1.33s/it]
 95%|█████████▍| 58613/61904 [7:05:19<1:13:31,  1.34s/it]
 95%|█████████▍| 58614/61904 [7:05:21<1:15:49,  1.38s/it]
 95%|█████████▍| 58615/61904 [7:05:22<1:17:23,  1.41s/it]
 95%|█████████▍| 58616/61904 [7:05:23<1:16:36,  1.40s/it]
 95%|█████████▍| 58617/61904 [7:05:25<1:15:30,  1.38s/it]
 95%|█████████▍| 58618/61904 [7:05:26<1:14:57,  1.37s/it]
 95%|█████████▍| 58619/61904 [7:05:27<1:14:42,  1.36s/it]
 95%|█████████▍| 58620/61904 [7:05:29<1:15:19,  1.38s/it]
                                                         
{'loss': 2.4541, 'learning_rate': 1.0532218332685077e-07, 'epoch': 15.15}
+
 95%|█████████▍| 58620/61904 [7:05:29<1:15:19,  1.38s/it]
 95%|█████████▍| 58621/61904 [7:05:30<1:12:49,  1.33s/it]
 95%|█████████▍| 58622/61904 [7:05:31<1:11:27,  1.31s/it]
 95%|█████████▍| 58623/61904 [7:05:33<1:14:17,  1.36s/it]
 95%|█████████▍| 58624/61904 [7:05:34<1:14:20,  1.36s/it]
 95%|█████████▍| 58625/61904 [7:05:36<1:14:57,  1.37s/it]
 95%|█████████▍| 58626/61904 [7:05:37<1:13:59,  1.35s/it]
 95%|█████████▍| 58627/61904 [7:05:38<1:15:41,  1.39s/it]
 95%|█████████▍| 58628/61904 [7:05:40<1:14:01,  1.36s/it]
 95%|█████████▍| 58629/61904 [7:05:41<1:15:53,  1.39s/it]
 95%|█████████▍| 58630/61904 [7:05:42<1:15:08,  1.38s/it]
 95%|█████████▍| 58631/61904 [7:05:44<1:14:51,  1.37s/it]
 95%|█████████▍| 58632/61904 [7:05:45<1:15:48,  1.39s/it]
 95%|█████████▍| 58633/61904 [7:05:47<1:16:35,  1.40s/it]
 95%|█████████▍| 58634/61904 [7:05:48<1:16:22,  1.40s/it]
 95%|█████████▍| 58635/61904 [7:05:50<1:18:25,  1.44s/it]
 95%|█████████▍| 58636/61904 [7:05:51<1:17:18,  1.42s/it]
 95%|█████████▍| 58637/61904 [7:05:52<1:16:59,  1.41s/it]
 95%|█████████▍| 58638/61904 [7:05:54<1:16:02,  1.40s/it]
 95%|█████████▍| 58639/61904 [7:05:55<1:16:01,  1.40s/it]
 95%|█████████▍| 58640/61904 [7:05:56<1:14:31,  1.37s/it]
                                                         
{'loss': 2.4487, 'learning_rate': 1.0528977051730846e-07, 'epoch': 15.16}
+
 95%|█████████▍| 58640/61904 [7:05:56<1:14:31,  1.37s/it]
 95%|█████████▍| 58641/61904 [7:05:58<1:15:52,  1.40s/it]
 95%|█████████▍| 58642/61904 [7:05:59<1:15:40,  1.39s/it]
 95%|█████████▍| 58643/61904 [7:06:01<1:15:18,  1.39s/it]
 95%|█████████▍| 58644/61904 [7:06:02<1:14:37,  1.37s/it]
 95%|█████████▍| 58645/61904 [7:06:03<1:13:30,  1.35s/it]
 95%|█████████▍| 58646/61904 [7:06:05<1:14:07,  1.36s/it]
 95%|█████████▍| 58647/61904 [7:06:06<1:12:37,  1.34s/it]
 95%|█████████▍| 58648/61904 [7:06:07<1:11:15,  1.31s/it]
 95%|█████████▍| 58649/61904 [7:06:09<1:13:46,  1.36s/it]
 95%|█████████▍| 58650/61904 [7:06:10<1:16:58,  1.42s/it]
 95%|█████████▍| 58651/61904 [7:06:11<1:14:00,  1.37s/it]
 95%|█████████▍| 58652/61904 [7:06:13<1:13:15,  1.35s/it]
 95%|█████████▍| 58653/61904 [7:06:14<1:16:45,  1.42s/it]
 95%|█████████▍| 58654/61904 [7:06:16<1:15:23,  1.39s/it]
 95%|█████████▍| 58655/61904 [7:06:17<1:15:35,  1.40s/it]
 95%|█████████▍| 58656/61904 [7:06:19<1:16:42,  1.42s/it]
 95%|█████████▍| 58657/61904 [7:06:20<1:19:13,  1.46s/it]
 95%|█████████▍| 58658/61904 [7:06:22<1:18:13,  1.45s/it]
 95%|█████████▍| 58659/61904 [7:06:23<1:17:47,  1.44s/it]
 95%|█████████▍| 58660/61904 [7:06:24<1:15:35,  1.40s/it]
                                                         
{'loss': 2.3776, 'learning_rate': 1.0525735770776612e-07, 'epoch': 15.16}
+
 95%|█████████▍| 58660/61904 [7:06:24<1:15:35,  1.40s/it]
 95%|█████████▍| 58661/61904 [7:06:26<1:14:54,  1.39s/it]
 95%|█████████▍| 58662/61904 [7:06:27<1:12:52,  1.35s/it]
 95%|█████████▍| 58663/61904 [7:06:28<1:12:41,  1.35s/it]
 95%|█████████▍| 58664/61904 [7:06:30<1:12:15,  1.34s/it]
 95%|█████████▍| 58665/61904 [7:06:31<1:11:58,  1.33s/it]
 95%|█████████▍| 58666/61904 [7:06:32<1:12:05,  1.34s/it]
 95%|█████████▍| 58667/61904 [7:06:34<1:14:00,  1.37s/it]
 95%|█████████▍| 58668/61904 [7:06:35<1:14:30,  1.38s/it]
 95%|█���███████▍| 58669/61904 [7:06:36<1:14:21,  1.38s/it]
 95%|█████████▍| 58670/61904 [7:06:38<1:13:49,  1.37s/it]
 95%|█████████▍| 58671/61904 [7:06:39<1:15:34,  1.40s/it]
 95%|█████████▍| 58672/61904 [7:06:41<1:17:00,  1.43s/it]
 95%|█████████▍| 58673/61904 [7:06:42<1:19:42,  1.48s/it]
 95%|█████████▍| 58674/61904 [7:06:44<1:18:41,  1.46s/it]
 95%|█████████▍| 58675/61904 [7:06:45<1:17:32,  1.44s/it]
 95%|█████████▍| 58676/61904 [7:06:47<1:17:03,  1.43s/it]
 95%|█████████▍| 58677/61904 [7:06:48<1:15:29,  1.40s/it]
 95%|█████████▍| 58678/61904 [7:06:49<1:15:58,  1.41s/it]
 95%|█████████▍| 58679/61904 [7:06:51<1:17:09,  1.44s/it]
 95%|█████████▍| 58680/61904 [7:06:52<1:17:21,  1.44s/it]
                                                         
{'loss': 2.3837, 'learning_rate': 1.0522494489822378e-07, 'epoch': 15.17}
+
 95%|█████████▍| 58680/61904 [7:06:52<1:17:21,  1.44s/it]
 95%|█████████▍| 58681/61904 [7:06:54<1:15:04,  1.40s/it]
 95%|█████████▍| 58682/61904 [7:06:55<1:13:42,  1.37s/it]
 95%|█████████▍| 58683/61904 [7:06:56<1:12:20,  1.35s/it]
 95%|█████████▍| 58684/61904 [7:06:58<1:12:17,  1.35s/it]
 95%|█████████▍| 58685/61904 [7:06:59<1:10:58,  1.32s/it]
 95%|█████████▍| 58686/61904 [7:07:00<1:10:30,  1.31s/it]
 95%|█████████▍| 58687/61904 [7:07:01<1:12:05,  1.34s/it]
 95%|█████████▍| 58688/61904 [7:07:03<1:11:06,  1.33s/it]
 95%|█████████▍| 58689/61904 [7:07:04<1:13:55,  1.38s/it]
 95%|█████████▍| 58690/61904 [7:07:06<1:16:23,  1.43s/it]
 95%|█████████▍| 58691/61904 [7:07:07<1:14:55,  1.40s/it]
 95%|█████████▍| 58692/61904 [7:07:09<1:15:07,  1.40s/it]
 95%|█████████▍| 58693/61904 [7:07:10<1:13:45,  1.38s/it]
 95%|█████████▍| 58694/61904 [7:07:11<1:14:09,  1.39s/it]
 95%|█████████▍| 58695/61904 [7:07:13<1:13:15,  1.37s/it]
 95%|█████████▍| 58696/61904 [7:07:14<1:12:36,  1.36s/it]
 95%|█████████▍| 58697/61904 [7:07:15<1:12:59,  1.37s/it]
 95%|█████████▍| 58698/61904 [7:07:17<1:12:41,  1.36s/it]
 95%|█████████▍| 58699/61904 [7:07:18<1:14:14,  1.39s/it]
 95%|█████████▍| 58700/61904 [7:07:19<1:12:35,  1.36s/it]
                                                         
{'loss': 2.3505, 'learning_rate': 1.0519253208868144e-07, 'epoch': 15.17}
+
 95%|█████████▍| 58700/61904 [7:07:19<1:12:35,  1.36s/it]
 95%|█████████▍| 58701/61904 [7:07:21<1:10:45,  1.33s/it]
 95%|█████████▍| 58702/61904 [7:07:22<1:09:18,  1.30s/it]
 95%|█████████▍| 58703/61904 [7:07:23<1:12:17,  1.35s/it]
 95%|█████████▍| 58704/61904 [7:07:25<1:12:52,  1.37s/it]
 95%|█████████▍| 58705/61904 [7:07:26<1:11:27,  1.34s/it]
 95%|█████████▍| 58706/61904 [7:07:27<1:11:19,  1.34s/it]
 95%|█████████▍| 58707/61904 [7:07:29<1:13:53,  1.39s/it]
 95%|█████████▍| 58708/61904 [7:07:30<1:16:30,  1.44s/it]
 95%|█████████▍| 58709/61904 [7:07:32<1:13:46,  1.39s/it]
 95%|█████████▍| 58710/61904 [7:07:33<1:15:08,  1.41s/it]
 95%|█████████▍| 58711/61904 [7:07:34<1:12:26,  1.36s/it]
 95%|█████████▍| 58712/61904 [7:07:36<1:11:45,  1.35s/it]
 95%|█████████▍| 58713/61904 [7:07:37<1:14:15,  1.40s/it]
 95%|█████████▍| 58714/61904 [7:07:39<1:12:41,  1.37s/it]
 95%|█████████▍| 58715/61904 [7:07:40<1:14:23,  1.40s/it]
 95%|█████████▍| 58716/61904 [7:07:41<1:14:28,  1.40s/it]
 95%|█████████▍| 58717/61904 [7:07:43<1:13:51,  1.39s/it]
 95%|█████████▍| 58718/61904 [7:07:44<1:11:36,  1.35s/it]
 95%|█████████▍| 58719/61904 [7:07:45<1:11:58,  1.36s/it]
 95%|█████████▍| 58720/61904 [7:07:47<1:09:31,  1.31s/it]
                                                         
{'loss': 2.4518, 'learning_rate': 1.0516011927913913e-07, 'epoch': 15.18}
+
 95%|█████████▍| 58720/61904 [7:07:47<1:09:31,  1.31s/it]
 95%|█████████▍| 58721/61904 [7:07:48<1:09:37,  1.31s/it]
 95%|█████████▍| 58722/61904 [7:07:50<1:14:51,  1.41s/it]
 95%|█████████▍| 58723/61904 [7:07:51<1:13:47,  1.39s/it]
 95%|█████████▍| 58724/61904 [7:07:52<1:12:02,  1.36s/it]
 95%|█████████▍| 58725/61904 [7:07:53<1:10:17,  1.33s/it]
 95%|█████████▍| 58726/61904 [7:07:55<1:08:51,  1.30s/it]
 95%|█████████▍| 58727/61904 [7:07:56<1:08:50,  1.30s/it]
 95%|█████████▍| 58728/61904 [7:07:57<1:08:37,  1.30s/it]
 95%|█████████▍| 58729/61904 [7:07:59<1:10:21,  1.33s/it]
 95%|█████████▍| 58730/61904 [7:08:00<1:11:25,  1.35s/it]
 95%|█████████▍| 58731/61904 [7:08:01<1:09:49,  1.32s/it]
 95%|█████████▍| 58732/61904 [7:08:03<1:10:03,  1.33s/it]
 95%|█████████▍| 58733/61904 [7:08:04<1:12:31,  1.37s/it]
 95%|█████████▍| 58734/61904 [7:08:06<1:11:38,  1.36s/it]
 95%|█████████▍| 58735/61904 [7:08:07<1:12:04,  1.36s/it]
 95%|█████████▍| 58736/61904 [7:08:08<1:14:49,  1.42s/it]
 95%|█████████▍| 58737/61904 [7:08:10<1:14:17,  1.41s/it]
 95%|█████████▍| 58738/61904 [7:08:11<1:16:39,  1.45s/it]
 95%|█████████▍| 58739/61904 [7:08:13<1:15:16,  1.43s/it]
 95%|█████████▍| 58740/61904 [7:08:14<1:14:16,  1.41s/it]
                                                         
{'loss': 2.3862, 'learning_rate': 1.0512770646959679e-07, 'epoch': 15.18}
+
 95%|█████████▍| 58740/61904 [7:08:14<1:14:16,  1.41s/it]
 95%|█████████▍| 58741/61904 [7:08:15<1:12:10,  1.37s/it]
 95%|█████████▍| 58742/61904 [7:08:17<1:11:15,  1.35s/it]
 95%|█████████▍| 58743/61904 [7:08:18<1:10:50,  1.34s/it]
 95%|█████████▍| 58744/61904 [7:08:19<1:12:55,  1.38s/it]
 95%|█████████▍| 58745/61904 [7:08:21<1:14:24,  1.41s/it]
 95%|█████████▍| 58746/61904 [7:08:22<1:12:30,  1.38s/it]
 95%|█████████▍| 58747/61904 [7:08:24<1:12:33,  1.38s/it]
 95%|█████████▍| 58748/61904 [7:08:25<1:11:40,  1.36s/it]
 95%|█████████▍| 58749/61904 [7:08:26<1:12:20,  1.38s/it]
 95%|█████████▍| 58750/61904 [7:08:28<1:08:59,  1.31s/it]
 95%|█████████▍| 58751/61904 [7:08:29<1:09:45,  1.33s/it]
 95%|█████████▍| 58752/61904 [7:08:30<1:08:57,  1.31s/it]
 95%|█████████▍| 58753/61904 [7:08:32<1:11:09,  1.35s/it]
 95%|█████████▍| 58754/61904 [7:08:33<1:10:42,  1.35s/it]
 95%|█████████▍| 58755/61904 [7:08:34<1:10:07,  1.34s/it]
 95%|█████████▍| 58756/61904 [7:08:36<1:08:43,  1.31s/it]
 95%|█████████▍| 58757/61904 [7:08:37<1:11:06,  1.36s/it]
 95%|█████████▍| 58758/61904 [7:08:39<1:13:38,  1.40s/it]
 95%|█████████▍| 58759/61904 [7:08:40<1:12:01,  1.37s/it]
 95%|█████████▍| 58760/61904 [7:08:41<1:15:15,  1.44s/it]
                                                         
{'loss': 2.3564, 'learning_rate': 1.0509529366005445e-07, 'epoch': 15.19}
+
 95%|█████████▍| 58760/61904 [7:08:41<1:15:15,  1.44s/it]
 95%|█████████▍| 58761/61904 [7:08:43<1:14:33,  1.42s/it]
 95%|█████████▍| 58762/61904 [7:08:44<1:12:28,  1.38s/it]
 95%|█████████▍| 58763/61904 [7:08:45<1:11:28,  1.37s/it]
 95%|█████████▍| 58764/61904 [7:08:47<1:12:09,  1.38s/it]
 95%|█████████▍| 58765/61904 [7:08:48<1:10:12,  1.34s/it]
 95%|█████████▍| 58766/61904 [7:08:49<1:09:01,  1.32s/it]
 95%|█████████▍| 58767/61904 [7:08:51<1:09:25,  1.33s/it]
 95%|█████████▍| 58768/61904 [7:08:52<1:11:11,  1.36s/it]
 95%|█████████▍| 58769/61904 [7:08:53<1:10:16,  1.35s/it]
 95%|█████████▍| 58770/61904 [7:08:55<1:10:58,  1.36s/it]
 95%|█████████▍| 58771/61904 [7:08:56<1:10:24,  1.35s/it]
 95%|█████████▍| 58772/61904 [7:08:58<1:11:52,  1.38s/it]
 95%|█████████▍| 58773/61904 [7:08:59<1:11:47,  1.38s/it]
 95%|█████████▍| 58774/61904 [7:09:00<1:13:01,  1.40s/it]
 95%|█████████▍| 58775/61904 [7:09:02<1:11:15,  1.37s/it]
 95%|█████████▍| 58776/61904 [7:09:03<1:12:42,  1.39s/it]
 95%|█████████▍| 58777/61904 [7:09:05<1:14:06,  1.42s/it]
 95%|█████████▍| 58778/61904 [7:09:06<1:13:13,  1.41s/it]
 95%|█████████▍| 58779/61904 [7:09:07<1:11:16,  1.37s/it]
 95%|█████████▍| 58780/61904 [7:09:09<1:12:50,  1.40s/it]
                                                         
{'loss': 2.3832, 'learning_rate': 1.0506288085051212e-07, 'epoch': 15.19}
+
 95%|█████████▍| 58780/61904 [7:09:09<1:12:50,  1.40s/it]
 95%|█████████▍| 58781/61904 [7:09:10<1:14:26,  1.43s/it]
 95%|█████████▍| 58782/61904 [7:09:12<1:12:16,  1.39s/it]
 95%|█████████▍| 58783/61904 [7:09:13<1:14:05,  1.42s/it]
 95%|��████████▍| 58784/61904 [7:09:14<1:12:58,  1.40s/it]
 95%|█████████▍| 58785/61904 [7:09:16<1:12:24,  1.39s/it]
 95%|█████████▍| 58786/61904 [7:09:17<1:11:10,  1.37s/it]
 95%|█████████▍| 58787/61904 [7:09:18<1:10:55,  1.37s/it]
 95%|█████████▍| 58788/61904 [7:09:20<1:11:19,  1.37s/it]
 95%|█████████▍| 58789/61904 [7:09:21<1:11:46,  1.38s/it]
 95%|█████████▍| 58790/61904 [7:09:23<1:11:13,  1.37s/it]
 95%|█████████▍| 58791/61904 [7:09:24<1:14:41,  1.44s/it]
 95%|█████████▍| 58792/61904 [7:09:26<1:13:56,  1.43s/it]
 95%|█████████▍| 58793/61904 [7:09:27<1:11:36,  1.38s/it]
 95%|█████████▍| 58794/61904 [7:09:28<1:12:04,  1.39s/it]
 95%|█████████▍| 58795/61904 [7:09:30<1:13:05,  1.41s/it]
 95%|█████████▍| 58796/61904 [7:09:31<1:14:02,  1.43s/it]
 95%|█████████▍| 58797/61904 [7:09:33<1:12:51,  1.41s/it]
 95%|█████████▍| 58798/61904 [7:09:34<1:12:48,  1.41s/it]
 95%|█████████▍| 58799/61904 [7:09:35<1:12:41,  1.40s/it]
 95%|█████████▍| 58800/61904 [7:09:37<1:11:11,  1.38s/it]
                                                         
{'loss': 2.4699, 'learning_rate': 1.050304680409698e-07, 'epoch': 15.2}
+
 95%|█████████▍| 58800/61904 [7:09:37<1:11:11,  1.38s/it]
 95%|█████████▍| 58801/61904 [7:09:38<1:10:30,  1.36s/it]
 95%|█████████▍| 58802/61904 [7:09:40<1:13:09,  1.41s/it]
 95%|█████████▍| 58803/61904 [7:09:41<1:11:51,  1.39s/it]
 95%|█████████▍| 58804/61904 [7:09:42<1:11:20,  1.38s/it]
 95%|█████████▍| 58805/61904 [7:09:44<1:11:58,  1.39s/it]
 95%|█████████▍| 58806/61904 [7:09:45<1:13:23,  1.42s/it]
 95%|█████████▍| 58807/61904 [7:09:46<1:11:31,  1.39s/it]
 95%|█████████▍| 58808/61904 [7:09:48<1:09:56,  1.36s/it]
 95%|█████████▌| 58809/61904 [7:09:49<1:11:46,  1.39s/it]
 95%|█████████▌| 58810/61904 [7:09:51<1:12:43,  1.41s/it]
 95%|█████████▌| 58811/61904 [7:09:52<1:11:08,  1.38s/it]
 95%|█████████▌| 58812/61904 [7:09:53<1:11:38,  1.39s/it]
 95%|█████████▌| 58813/61904 [7:09:55<1:11:04,  1.38s/it]
 95%|█████████▌| 58814/61904 [7:09:56<1:14:46,  1.45s/it]
 95%|█████████▌| 58815/61904 [7:09:58<1:12:06,  1.40s/it]
 95%|█████████▌| 58816/61904 [7:09:59<1:10:51,  1.38s/it]
 95%|█████████▌| 58817/61904 [7:10:00<1:08:36,  1.33s/it]
 95%|█████████▌| 58818/61904 [7:10:02<1:08:58,  1.34s/it]
 95%|█████████▌| 58819/61904 [7:10:03<1:08:21,  1.33s/it]
 95%|█████████▌| 58820/61904 [7:10:04<1:10:47,  1.38s/it]
                                                         
{'loss': 2.4436, 'learning_rate': 1.0499805523142747e-07, 'epoch': 15.2}
+
 95%|█████████▌| 58820/61904 [7:10:04<1:10:47,  1.38s/it]
 95%|█████████▌| 58821/61904 [7:10:06<1:10:12,  1.37s/it]
 95%|█████████▌| 58822/61904 [7:10:07<1:10:27,  1.37s/it]
 95%|█████████▌| 58823/61904 [7:10:09<1:12:30,  1.41s/it]
 95%|█████████▌| 58824/61904 [7:10:10<1:11:09,  1.39s/it]
 95%|█████████▌| 58825/61904 [7:10:11<1:10:28,  1.37s/it]
 95%|█████████▌| 58826/61904 [7:10:13<1:08:36,  1.34s/it]
 95%|█████████▌| 58827/61904 [7:10:14<1:10:35,  1.38s/it]
 95%|█████████▌| 58828/61904 [7:10:16<1:14:50,  1.46s/it]
 95%|█████████▌| 58829/61904 [7:10:17<1:13:17,  1.43s/it]
 95%|█████████▌| 58830/61904 [7:10:18<1:12:29,  1.41s/it]
 95%|█████████▌| 58831/61904 [7:10:20<1:12:28,  1.42s/it]
 95%|█████████▌| 58832/61904 [7:10:21<1:10:54,  1.38s/it]
 95%|█████████▌| 58833/61904 [7:10:22<1:10:33,  1.38s/it]
 95%|█████████▌| 58834/61904 [7:10:24<1:08:11,  1.33s/it]
 95%|█████████▌| 58835/61904 [7:10:25<1:08:42,  1.34s/it]
 95%|█████████▌| 58836/61904 [7:10:26<1:08:21,  1.34s/it]
 95%|█████████▌| 58837/61904 [7:10:28<1:11:56,  1.41s/it]
 95%|█████████▌| 58838/61904 [7:10:29<1:11:14,  1.39s/it]
 95%|█████████▌| 58839/61904 [7:10:31<1:11:09,  1.39s/it]
 95%|█████████▌| 58840/61904 [7:10:32<1:11:08,  1.39s/it]
                                                         
{'loss': 2.3911, 'learning_rate': 1.0496564242188513e-07, 'epoch': 15.21}
+
 95%|█████████▌| 58840/61904 [7:10:32<1:11:08,  1.39s/it]
 95%|█████████▌| 58841/61904 [7:10:33<1:10:51,  1.39s/it]
 95%|█████████▌| 58842/61904 [7:10:35<1:10:06,  1.37s/it]
 95%|█████████▌| 58843/61904 [7:10:36<1:08:33,  1.34s/it]
 95%|█████████▌| 58844/61904 [7:10:37<1:09:21,  1.36s/it]
 95%|█████████▌| 58845/61904 [7:10:39<1:09:58,  1.37s/it]
 95%|█████████▌| 58846/61904 [7:10:40<1:08:40,  1.35s/it]
 95%|█████████▌| 58847/61904 [7:10:42<1:10:21,  1.38s/it]
 95%|█████████▌| 58848/61904 [7:10:43<1:10:43,  1.39s/it]
 95%|█████████▌| 58849/61904 [7:10:44<1:10:03,  1.38s/it]
 95%|█████████▌| 58850/61904 [7:10:46<1:09:40,  1.37s/it]
 95%|█████████▌| 58851/61904 [7:10:47<1:09:27,  1.37s/it]
 95%|█████████▌| 58852/61904 [7:10:48<1:08:58,  1.36s/it]
 95%|█████████▌| 58853/61904 [7:10:50<1:12:02,  1.42s/it]
 95%|█████████▌| 58854/61904 [7:10:51<1:12:45,  1.43s/it]
 95%|█████████▌| 58855/61904 [7:10:53<1:14:39,  1.47s/it]
 95%|█████████▌| 58856/61904 [7:10:55<1:15:14,  1.48s/it]
 95%|█████████▌| 58857/61904 [7:10:56<1:12:47,  1.43s/it]
 95%|█████████▌| 58858/61904 [7:10:57<1:13:07,  1.44s/it]
 95%|█████████▌| 58859/61904 [7:10:59<1:13:24,  1.45s/it]
 95%|█████████▌| 58860/61904 [7:11:00<1:11:40,  1.41s/it]
                                                         
{'loss': 2.3914, 'learning_rate': 1.0493322961234279e-07, 'epoch': 15.21}
+
 95%|█████████▌| 58860/61904 [7:11:00<1:11:40,  1.41s/it]
 95%|█████████▌| 58861/61904 [7:11:01<1:10:46,  1.40s/it]
 95%|█████████▌| 58862/61904 [7:11:03<1:10:10,  1.38s/it]
 95%|█████████▌| 58863/61904 [7:11:04<1:09:31,  1.37s/it]
 95%|█████████▌| 58864/61904 [7:11:06<1:12:20,  1.43s/it]
 95%|█████████▌| 58865/61904 [7:11:07<1:12:01,  1.42s/it]
 95%|█████████▌| 58866/61904 [7:11:08<1:11:11,  1.41s/it]
 95%|█████████▌| 58867/61904 [7:11:10<1:09:54,  1.38s/it]
 95%|█████████▌| 58868/61904 [7:11:11<1:08:16,  1.35s/it]
 95%|█████████▌| 58869/61904 [7:11:13<1:10:12,  1.39s/it]
 95%|█████████▌| 58870/61904 [7:11:14<1:10:25,  1.39s/it]
 95%|█████████▌| 58871/61904 [7:11:15<1:09:06,  1.37s/it]
 95%|█████████▌| 58872/61904 [7:11:17<1:09:11,  1.37s/it]
 95%|█████████▌| 58873/61904 [7:11:18<1:09:30,  1.38s/it]
 95%|█████████▌| 58874/61904 [7:11:19<1:10:26,  1.39s/it]
 95%|█████████▌| 58875/61904 [7:11:21<1:11:04,  1.41s/it]
 95%|█████████▌| 58876/61904 [7:11:22<1:10:11,  1.39s/it]
 95%|█████████▌| 58877/61904 [7:11:24<1:11:31,  1.42s/it]
 95%|█████████▌| 58878/61904 [7:11:25<1:09:42,  1.38s/it]
 95%|█████████▌| 58879/61904 [7:11:26<1:08:23,  1.36s/it]
 95%|█████████▌| 58880/61904 [7:11:28<1:09:23,  1.38s/it]
                                                         
{'loss': 2.454, 'learning_rate': 1.0490081680280048e-07, 'epoch': 15.22}
+
 95%|█████████▌| 58880/61904 [7:11:28<1:09:23,  1.38s/it]
 95%|█████████▌| 58881/61904 [7:11:29<1:07:16,  1.34s/it]
 95%|█████████▌| 58882/61904 [7:11:30<1:07:23,  1.34s/it]
 95%|█████████▌| 58883/61904 [7:11:32<1:06:53,  1.33s/it]
 95%|█████████▌| 58884/61904 [7:11:33<1:05:34,  1.30s/it]
 95%|█████████▌| 58885/61904 [7:11:34<1:06:12,  1.32s/it]
 95%|█████████▌| 58886/61904 [7:11:36<1:06:51,  1.33s/it]
 95%|█████████▌| 58887/61904 [7:11:37<1:06:01,  1.31s/it]
 95%|█████████▌| 58888/61904 [7:11:38<1:07:27,  1.34s/it]
 95%|█████████▌| 58889/61904 [7:11:40<1:06:51,  1.33s/it]
 95%|█████████▌| 58890/61904 [7:11:41<1:05:54,  1.31s/it]
 95%|█████████▌| 58891/61904 [7:11:42<1:09:10,  1.38s/it]
 95%|█████████▌| 58892/61904 [7:11:44<1:09:34,  1.39s/it]
 95%|█████████▌| 58893/61904 [7:11:45<1:08:49,  1.37s/it]
 95%|█████████▌| 58894/61904 [7:11:46<1:07:26,  1.34s/it]
 95%|█████████▌| 58895/61904 [7:11:48<1:08:38,  1.37s/it]
 95%|█████████▌| 58896/61904 [7:11:49<1:06:49,  1.33s/it]
 95%|█████████▌| 58897/61904 [7:11:50<1:06:12,  1.32s/it]
 95%|█████████▌| 58898/61904 [7:11:52<1:08:35,  1.37s/it]
 95%|█████████▌| 58899/61904 [7:11:53<1:09:26,  1.39s/it]
 95%|█████████▌| 58900/61904 [7:11:55<1:07:48,  1.35s/it]
                                                         
{'loss': 2.424, 'learning_rate': 1.0486840399325814e-07, 'epoch': 15.22}
+
 95%|█████████▌| 58900/61904 [7:11:55<1:07:48,  1.35s/it]
 95%|█████████▌| 58901/61904 [7:11:56<1:05:47,  1.31s/it]
 95%|█████████▌| 58902/61904 [7:11:57<1:06:13,  1.32s/it]
 95%|█████████▌| 58903/61904 [7:11:59<1:06:35,  1.33s/it]
 95%|█████████▌| 58904/61904 [7:12:00<1:09:09,  1.38s/it]
 95%|█████████▌| 58905/61904 [7:12:01<1:07:02,  1.34s/it]
 95%|█████████▌| 58906/61904 [7:12:03<1:09:02,  1.38s/it]
 95%|█████████▌| 58907/61904 [7:12:04<1:07:49,  1.36s/it]
 95%|█████████▌| 58908/61904 [7:12:06<1:10:16,  1.41s/it]
 95%|█████████▌| 58909/61904 [7:12:07<1:08:41,  1.38s/it]
 95%|█████████▌| 58910/61904 [7:12:08<1:08:13,  1.37s/it]
 95%|█████████▌| 58911/61904 [7:12:10<1:07:31,  1.35s/it]
 95%|█████████▌| 58912/61904 [7:12:11<1:07:17,  1.35s/it]
 95%|█████████▌| 58913/61904 [7:12:12<1:10:43,  1.42s/it]
 95%|█████████▌| 58914/61904 [7:12:14<1:09:41,  1.40s/it]
 95%|█████████▌| 58915/61904 [7:12:15<1:12:27,  1.45s/it]
 95%|█████████▌| 58916/61904 [7:12:17<1:13:41,  1.48s/it]
 95%|█████████▌| 58917/61904 [7:12:18<1:12:50,  1.46s/it]
 95%|█████████▌| 58918/61904 [7:12:20<1:10:31,  1.42s/it]
 95%|█████████▌| 58919/61904 [7:12:21<1:09:20,  1.39s/it]
 95%|█████████▌| 58920/61904 [7:12:22<1:07:23,  1.36s/it]
                                                         
{'loss': 2.4053, 'learning_rate': 1.048359911837158e-07, 'epoch': 15.23}
+
 95%|█████████▌| 58920/61904 [7:12:22<1:07:23,  1.36s/it]
 95%|█████████▌| 58921/61904 [7:12:24<1:07:03,  1.35s/it]
 95%|█████████▌| 58922/61904 [7:12:25<1:07:01,  1.35s/it]
 95%|█████████▌| 58923/61904 [7:12:26<1:08:15,  1.37s/it]
 95%|█████████▌| 58924/61904 [7:12:28<1:08:36,  1.38s/it]
 95%|█████████▌| 58925/61904 [7:12:29<1:06:32,  1.34s/it]
 95%|█████████▌| 58926/61904 [7:12:30<1:08:27,  1.38s/it]
 95%|█████████▌| 58927/61904 [7:12:32<1:07:09,  1.35s/it]
 95%|█████████▌| 58928/61904 [7:12:33<1:06:30,  1.34s/it]
 95%|█████████▌| 58929/61904 [7:12:34<1:07:04,  1.35s/it]
 95%|█████████▌| 58930/61904 [7:12:36<1:07:41,  1.37s/it]
 95%|█████████▌| 58931/61904 [7:12:37<1:08:03,  1.37s/it]
 95%|█████████▌| 58932/61904 [7:12:39<1:09:46,  1.41s/it]
 95%|█████████▌| 58933/61904 [7:12:40<1:08:17,  1.38s/it]
 95%|█████████▌| 58934/61904 [7:12:41<1:08:59,  1.39s/it]
 95%|█████████▌| 58935/61904 [7:12:43<1:08:10,  1.38s/it]
 95%|█████████▌| 58936/61904 [7:12:44<1:08:32,  1.39s/it]
 95%|█████████▌| 58937/61904 [7:12:46<1:08:42,  1.39s/it]
 95%|█████████▌| 58938/61904 [7:12:47<1:06:19,  1.34s/it]
 95%|█████████▌| 58939/61904 [7:12:48<1:06:23,  1.34s/it]
 95%|█████████▌| 58940/61904 [7:12:50<1:07:57,  1.38s/it]
                                                         
{'loss': 2.41, 'learning_rate': 1.0480357837417349e-07, 'epoch': 15.23}
+
 95%|█████████▌| 58940/61904 [7:12:50<1:07:57,  1.38s/it]
 95%|█████████▌| 58941/61904 [7:12:51<1:07:49,  1.37s/it]
 95%|█████████▌| 58942/61904 [7:12:52<1:07:25,  1.37s/it]
 95%|█████████▌| 58943/61904 [7:12:54<1:07:57,  1.38s/it]
 95%|█████████▌| 58944/61904 [7:12:55<1:06:27,  1.35s/it]
 95%|█████████▌| 58945/61904 [7:12:56<1:06:57,  1.36s/it]
 95%|█████████▌| 58946/61904 [7:12:58<1:07:17,  1.36s/it]
 95%|█████████▌| 58947/61904 [7:12:59<1:06:53,  1.36s/it]
 95%|█████████▌| 58948/61904 [7:13:00<1:05:44,  1.33s/it]
 95%|█████████▌| 58949/61904 [7:13:02<1:07:21,  1.37s/it]
 95%|█████████▌| 58950/61904 [7:13:03<1:05:54,  1.34s/it]
 95%|█████████▌| 58951/61904 [7:13:05<1:09:21,  1.41s/it]
 95%|█████████▌| 58952/61904 [7:13:06<1:08:15,  1.39s/it]
 95%|█████████▌| 58953/61904 [7:13:07<1:07:51,  1.38s/it]
 95%|█████████▌| 58954/61904 [7:13:09<1:10:34,  1.44s/it]
 95%|█████████▌| 58955/61904 [7:13:10<1:08:36,  1.40s/it]
 95%|█████████▌| 58956/61904 [7:13:12<1:07:37,  1.38s/it]
 95%|█████████▌| 58957/61904 [7:13:13<1:07:31,  1.37s/it]
 95%|█████████▌| 58958/61904 [7:13:14<1:07:19,  1.37s/it]
 95%|█████████▌| 58959/61904 [7:13:16<1:08:02,  1.39s/it]
 95%|█████████▌| 58960/61904 [7:13:17<1:06:07,  1.35s/it]
                                                         
{'loss': 2.4504, 'learning_rate': 1.0477116556463115e-07, 'epoch': 15.24}
+
 95%|█████████▌| 58960/61904 [7:13:17<1:06:07,  1.35s/it]
 95%|█████████▌| 58961/61904 [7:13:18<1:07:03,  1.37s/it]
 95%|█████████▌| 58962/61904 [7:13:20<1:05:55,  1.34s/it]
 95%|█████████▌| 58963/61904 [7:13:21<1:05:58,  1.35s/it]
 95%|█████████▌| 58964/61904 [7:13:23<1:07:12,  1.37s/it]
 95%|█████████▌| 58965/61904 [7:13:24<1:07:38,  1.38s/it]
 95%|█████████▌| 58966/61904 [7:13:25<1:08:03,  1.39s/it]
 95%|█████████▌| 58967/61904 [7:13:27<1:07:33,  1.38s/it]
 95%|█████████▌| 58968/61904 [7:13:28<1:05:28,  1.34s/it]
 95%|█████████▌| 58969/61904 [7:13:29<1:07:06,  1.37s/it]
 95%|█████████▌| 58970/61904 [7:13:31<1:06:16,  1.36s/it]
 95%|█████████▌| 58971/61904 [7:13:32<1:06:21,  1.36s/it]
 95%|█████████▌| 58972/61904 [7:13:33<1:07:03,  1.37s/it]
 95%|█████████▌| 58973/61904 [7:13:35<1:07:53,  1.39s/it]
 95%|█████████▌| 58974/61904 [7:13:36<1:06:39,  1.37s/it]
 95%|█████████▌| 58975/61904 [7:13:38<1:09:55,  1.43s/it]
 95%|█████████▌| 58976/61904 [7:13:39<1:08:12,  1.40s/it]
 95%|█████████▌| 58977/61904 [7:13:41<1:09:53,  1.43s/it]
 95%|█████████▌| 58978/61904 [7:13:42<1:08:02,  1.40s/it]
 95%|█████████▌| 58979/61904 [7:13:43<1:07:19,  1.38s/it]
 95%|█████████▌| 58980/61904 [7:13:45<1:05:08,  1.34s/it]
                                                         
{'loss': 2.4132, 'learning_rate': 1.0473875275508881e-07, 'epoch': 15.24}
+
 95%|█████████▌| 58980/61904 [7:13:45<1:05:08,  1.34s/it]
 95%|█████████▌| 58981/61904 [7:13:46<1:05:03,  1.34s/it]
 95%|█████████▌| 58982/61904 [7:13:47<1:07:52,  1.39s/it]
 95%|█████████▌| 58983/61904 [7:13:49<1:06:55,  1.37s/it]
 95%|█████████▌| 58984/61904 [7:13:50<1:07:22,  1.38s/it]
 95%|█████████▌| 58985/61904 [7:13:51<1:06:53,  1.37s/it]
 95%|█████████▌| 58986/61904 [7:13:53<1:05:02,  1.34s/it]
 95%|█████████▌| 58987/61904 [7:13:54<1:03:14,  1.30s/it]
 95%|█████████▌| 58988/61904 [7:13:55<1:03:56,  1.32s/it]
 95%|█████████▌| 58989/61904 [7:13:57<1:04:50,  1.33s/it]
 95%|█████████▌| 58990/61904 [7:13:58<1:05:00,  1.34s/it]
 95%|█████████▌| 58991/61904 [7:13:59<1:05:38,  1.35s/it]
 95%|█████████▌| 58992/61904 [7:14:01<1:04:46,  1.33s/it]
 95%|█████████▌| 58993/61904 [7:14:02<1:04:22,  1.33s/it]
 95%|█████████▌| 58994/61904 [7:14:03<1:05:20,  1.35s/it]
 95%|█████████▌| 58995/61904 [7:14:05<1:04:15,  1.33s/it]
 95%|█████████▌| 58996/61904 [7:14:06<1:06:49,  1.38s/it]
 95%|█████████▌| 58997/61904 [7:14:07<1:05:56,  1.36s/it]
 95%|█████████▌| 58998/61904 [7:14:09<1:06:44,  1.38s/it]
 95%|█████████▌| 58999/61904 [7:14:10<1:05:18,  1.35s/it]
 95%|█████████▌| 59000/61904 [7:14:12<1:06:00,  1.36s/it]
                                                         
{'loss': 2.4664, 'learning_rate': 1.0470633994554648e-07, 'epoch': 15.25}
+
 95%|█████████▌| 59000/61904 [7:14:12<1:06:00,  1.36s/it]
 95%|█████████▌| 59001/61904 [7:14:13<1:05:50,  1.36s/it]
 95%|█████████▌| 59002/61904 [7:14:14<1:05:09,  1.35s/it]
 95%|█████████▌| 59003/61904 [7:14:16<1:07:35,  1.40s/it]
 95%|█████████▌| 59004/61904 [7:14:17<1:04:50,  1.34s/it]
 95%|█████████▌| 59005/61904 [7:14:18<1:06:07,  1.37s/it]
 95%|█████████▌| 59006/61904 [7:14:20<1:06:37,  1.38s/it]
 95%|█████████▌| 59007/61904 [7:14:21<1:04:44,  1.34s/it]
 95%|█████████▌| 59008/61904 [7:14:22<1:03:39,  1.32s/it]
 95%|█████████▌| 59009/61904 [7:14:24<1:06:12,  1.37s/it]
 95%|█████████▌| 59010/61904 [7:14:25<1:08:57,  1.43s/it]
 95%|█████████▌| 59011/61904 [7:14:27<1:07:39,  1.40s/it]
 95%|█████████▌| 59012/61904 [7:14:28<1:07:59,  1.41s/it]
 95%|█████████▌| 59013/61904 [7:14:30<1:07:10,  1.39s/it]
 95%|█████████▌| 59014/61904 [7:14:31<1:06:45,  1.39s/it]
 95%|█████████▌| 59015/61904 [7:14:32<1:06:39,  1.38s/it]
 95%|█████████▌| 59016/61904 [7:14:34<1:08:18,  1.42s/it]
 95%|█████████▌| 59017/61904 [7:14:35<1:05:50,  1.37s/it]
 95%|█████████▌| 59018/61904 [7:14:36<1:05:58,  1.37s/it]
 95%|█████████▌| 59019/61904 [7:14:38<1:04:28,  1.34s/it]
 95%|█████████▌| 59020/61904 [7:14:39<1:07:04,  1.40s/it]
                                                         
{'loss': 2.4222, 'learning_rate': 1.0467392713600416e-07, 'epoch': 15.25}
+
 95%|█████████▌| 59020/61904 [7:14:39<1:07:04,  1.40s/it]
 95%|█████████▌| 59021/61904 [7:14:40<1:05:09,  1.36s/it]
 95%|█████████▌| 59022/61904 [7:14:42<1:05:01,  1.35s/it]
 95%|█████████▌| 59023/61904 [7:14:43<1:06:41,  1.39s/it]
 95%|█████████▌| 59024/61904 [7:14:45<1:05:36,  1.37s/it]
 95%|█████████▌| 59025/61904 [7:14:46<1:06:56,  1.39s/it]
 95%|█████████▌| 59026/61904 [7:14:47<1:07:29,  1.41s/it]
 95%|█████████▌| 59027/61904 [7:14:49<1:08:31,  1.43s/it]
 95%|█████████▌| 59028/61904 [7:14:50<1:06:02,  1.38s/it]
 95%|█████████▌| 59029/61904 [7:14:52<1:05:32,  1.37s/it]
 95%|█████████▌| 59030/61904 [7:14:53<1:04:49,  1.35s/it]
 95%|█████████▌| 59031/61904 [7:14:54<1:06:07,  1.38s/it]
 95%|█████████▌| 59032/61904 [7:14:56<1:06:07,  1.38s/it]
 95%|█████████▌| 59033/61904 [7:14:57<1:04:49,  1.35s/it]
 95%|█████████▌| 59034/61904 [7:14:58<1:05:46,  1.38s/it]
 95%|█████████▌| 59035/61904 [7:15:00<1:04:35,  1.35s/it]
 95%|█████████▌| 59036/61904 [7:15:01<1:05:37,  1.37s/it]
 95%|█████████▌| 59037/61904 [7:15:03<1:07:41,  1.42s/it]
 95%|█████████▌| 59038/61904 [7:15:04<1:07:45,  1.42s/it]
 95%|█████████▌| 59039/61904 [7:15:06<1:08:44,  1.44s/it]
 95%|█████████▌| 59040/61904 [7:15:07<1:07:43,  1.42s/it]
                                                         
{'loss': 2.4471, 'learning_rate': 1.0464151432646183e-07, 'epoch': 15.26}
+
 95%|█████████▌| 59040/61904 [7:15:07<1:07:43,  1.42s/it]
 95%|█████████▌| 59041/61904 [7:15:08<1:08:07,  1.43s/it]
 95%|█████████▌| 59042/61904 [7:15:10<1:07:53,  1.42s/it]
 95%|█████████▌| 59043/61904 [7:15:11<1:08:39,  1.44s/it]
 95%|█████████▌| 59044/61904 [7:15:13<1:09:52,  1.47s/it]
 95%|█████████▌| 59045/61904 [7:15:14<1:08:06,  1.43s/it]
 95%|█████████▌| 59046/61904 [7:15:15<1:06:28,  1.40s/it]
 95%|█████████▌| 59047/61904 [7:15:17<1:05:53,  1.38s/it]
 95%|█████████▌| 59048/61904 [7:15:18<1:06:16,  1.39s/it]
 95%|█████████▌| 59049/61904 [7:15:20<1:04:56,  1.36s/it]
 95%|█████████▌| 59050/61904 [7:15:21<1:03:57,  1.34s/it]
 95%|█████████▌| 59051/61904 [7:15:22<1:04:02,  1.35s/it]
 95%|█████████▌| 59052/61904 [7:15:23<1:02:58,  1.32s/it]
 95%|█████████▌| 59053/61904 [7:15:25<1:07:08,  1.41s/it]
 95%|█████████▌| 59054/61904 [7:15:26<1:05:14,  1.37s/it]
 95%|█████████▌| 59055/61904 [7:15:28<1:03:11,  1.33s/it]
 95%|█████████▌| 59056/61904 [7:15:29<1:05:02,  1.37s/it]
 95%|█████████▌| 59057/61904 [7:15:30<1:05:10,  1.37s/it]
 95%|█████████▌| 59058/61904 [7:15:32<1:06:44,  1.41s/it]
 95%|█████████▌| 59059/61904 [7:15:33<1:04:25,  1.36s/it]
 95%|█████████▌| 59060/61904 [7:15:34<1:03:13,  1.33s/it]
                                                         
{'loss': 2.402, 'learning_rate': 1.0460910151691949e-07, 'epoch': 15.26}
+
 95%|█████████▌| 59060/61904 [7:15:34<1:03:13,  1.33s/it]
 95%|█████████▌| 59061/61904 [7:15:36<1:02:33,  1.32s/it]
 95%|█████████▌| 59062/61904 [7:15:37<1:03:41,  1.34s/it]
 95%|█████████▌| 59063/61904 [7:15:39<1:06:58,  1.41s/it]
 95%|█████████▌| 59064/61904 [7:15:40<1:05:32,  1.38s/it]
 95%|█████████▌| 59065/61904 [7:15:41<1:04:35,  1.36s/it]
 95%|█████████▌| 59066/61904 [7:15:43<1:03:26,  1.34s/it]
 95%|█████████▌| 59067/61904 [7:15:44<1:05:24,  1.38s/it]
 95%|█████████▌| 59068/61904 [7:15:45<1:04:43,  1.37s/it]
 95%|█████████▌| 59069/61904 [7:15:47<1:03:25,  1.34s/it]
 95%|█████████▌| 59070/61904 [7:15:48<1:04:12,  1.36s/it]
 95%|█████████▌| 59071/61904 [7:15:50<1:05:18,  1.38s/it]
 95%|█████████▌| 59072/61904 [7:15:51<1:02:37,  1.33s/it]
 95%|█████████▌| 59073/61904 [7:15:52<1:04:38,  1.37s/it]
 95%|███████��█▌| 59074/61904 [7:15:54<1:06:52,  1.42s/it]
 95%|█████████▌| 59075/61904 [7:15:55<1:04:27,  1.37s/it]
 95%|█████████▌| 59076/61904 [7:15:56<1:03:33,  1.35s/it]
 95%|█████████▌| 59077/61904 [7:15:58<1:06:35,  1.41s/it]
 95%|█████████▌| 59078/61904 [7:15:59<1:06:50,  1.42s/it]
 95%|█████████▌| 59079/61904 [7:16:01<1:06:13,  1.41s/it]
 95%|█████████▌| 59080/61904 [7:16:02<1:04:26,  1.37s/it]
                                                         
{'loss': 2.3928, 'learning_rate': 1.0457668870737715e-07, 'epoch': 15.27}
+
 95%|█████████▌| 59080/61904 [7:16:02<1:04:26,  1.37s/it]
 95%|█████████▌| 59081/61904 [7:16:03<1:06:18,  1.41s/it]
 95%|█████████▌| 59082/61904 [7:16:05<1:06:12,  1.41s/it]
 95%|█████████▌| 59083/61904 [7:16:06<1:05:43,  1.40s/it]
 95%|█████████▌| 59084/61904 [7:16:08<1:04:53,  1.38s/it]
 95%|█████████▌| 59085/61904 [7:16:09<1:03:26,  1.35s/it]
 95%|█████████▌| 59086/61904 [7:16:10<1:04:22,  1.37s/it]
 95%|█████████▌| 59087/61904 [7:16:12<1:06:25,  1.41s/it]
 95%|█████████▌| 59088/61904 [7:16:13<1:04:49,  1.38s/it]
 95%|█████████▌| 59089/61904 [7:16:14<1:04:16,  1.37s/it]
 95%|█████████▌| 59090/61904 [7:16:16<1:03:40,  1.36s/it]
 95%|█████████▌| 59091/61904 [7:16:17<1:04:01,  1.37s/it]
 95%|█████████▌| 59092/61904 [7:16:19<1:06:50,  1.43s/it]
 95%|█████████▌| 59093/61904 [7:16:20<1:04:53,  1.39s/it]
 95%|█████████▌| 59094/61904 [7:16:21<1:04:13,  1.37s/it]
 95%|█████████▌| 59095/61904 [7:16:23<1:04:47,  1.38s/it]
 95%|█████████▌| 59096/61904 [7:16:24<1:04:14,  1.37s/it]
 95%|█████████▌| 59097/61904 [7:16:25<1:03:22,  1.35s/it]
 95%|█████████▌| 59098/61904 [7:16:27<1:05:35,  1.40s/it]
 95%|█████████▌| 59099/61904 [7:16:28<1:03:50,  1.37s/it]
 95%|█████████▌| 59100/61904 [7:16:30<1:03:09,  1.35s/it]
                                                         
{'loss': 2.3765, 'learning_rate': 1.0454427589783484e-07, 'epoch': 15.27}
+
 95%|█████████▌| 59100/61904 [7:16:30<1:03:09,  1.35s/it]
 95%|█████████▌| 59101/61904 [7:16:31<1:05:14,  1.40s/it]
 95%|█████████▌| 59102/61904 [7:16:32<1:04:51,  1.39s/it]
 95%|█████████▌| 59103/61904 [7:16:34<1:04:46,  1.39s/it]
 95%|█████████▌| 59104/61904 [7:16:35<1:05:46,  1.41s/it]
 95%|█████████▌| 59105/61904 [7:16:37<1:04:32,  1.38s/it]
 95%|█████████▌| 59106/61904 [7:16:38<1:05:34,  1.41s/it]
 95%|█████████▌| 59107/61904 [7:16:39<1:03:13,  1.36s/it]
 95%|█████████▌| 59108/61904 [7:16:41<1:05:05,  1.40s/it]
 95%|█████████▌| 59109/61904 [7:16:42<1:06:19,  1.42s/it]
 95%|█████████▌| 59110/61904 [7:16:44<1:05:58,  1.42s/it]
 95%|█████████▌| 59111/61904 [7:16:45<1:05:01,  1.40s/it]
 95%|█████████▌| 59112/61904 [7:16:46<1:03:53,  1.37s/it]
 95%|█████████▌| 59113/61904 [7:16:48<1:05:18,  1.40s/it]
 95%|█████████▌| 59114/61904 [7:16:49<1:04:36,  1.39s/it]
 95%|█████████▌| 59115/61904 [7:16:51<1:03:39,  1.37s/it]
 95%|█████████▌| 59116/61904 [7:16:52<1:05:18,  1.41s/it]
 95%|█████████▌| 59117/61904 [7:16:53<1:04:28,  1.39s/it]
 95%|█████████▌| 59118/61904 [7:16:55<1:04:26,  1.39s/it]
 96%|█████████▌| 59119/61904 [7:16:56<1:05:43,  1.42s/it]
 96%|█████████▌| 59120/61904 [7:16:58<1:05:31,  1.41s/it]
                                                         
{'loss': 2.3731, 'learning_rate': 1.045118630882925e-07, 'epoch': 15.28}
+
 96%|█████████▌| 59120/61904 [7:16:58<1:05:31,  1.41s/it]
 96%|█████████▌| 59121/61904 [7:16:59<1:05:03,  1.40s/it]
 96%|█████████▌| 59122/61904 [7:17:00<1:05:28,  1.41s/it]
 96%|█████████▌| 59123/61904 [7:17:02<1:07:16,  1.45s/it]
 96%|█████████▌| 59124/61904 [7:17:03<1:07:53,  1.47s/it]
 96%|█████████▌| 59125/61904 [7:17:05<1:08:26,  1.48s/it]
 96%|█████████▌| 59126/61904 [7:17:06<1:06:53,  1.44s/it]
 96%|█████████▌| 59127/61904 [7:17:08<1:05:18,  1.41s/it]
 96%|█████████▌| 59128/61904 [7:17:09<1:03:46,  1.38s/it]
 96%|█████████▌| 59129/61904 [7:17:10<1:04:19,  1.39s/it]
 96%|█████████▌| 59130/61904 [7:17:12<1:04:34,  1.40s/it]
 96%|█████████▌| 59131/61904 [7:17:13<1:04:34,  1.40s/it]
 96%|█████████▌| 59132/61904 [7:17:14<1:02:18,  1.35s/it]
 96%|█████████▌| 59133/61904 [7:17:16<1:03:01,  1.36s/it]
 96%|█████████▌| 59134/61904 [7:17:17<1:03:25,  1.37s/it]
 96%|█████████▌| 59135/61904 [7:17:19<1:05:06,  1.41s/it]
 96%|█████████▌| 59136/61904 [7:17:20<1:04:07,  1.39s/it]
 96%|█████████▌| 59137/61904 [7:17:21<1:04:12,  1.39s/it]
 96%|█████████▌| 59138/61904 [7:17:23<1:03:18,  1.37s/it]
 96%|█████████▌| 59139/61904 [7:17:24<1:04:40,  1.40s/it]
 96%|█████████▌| 59140/61904 [7:17:26<1:04:34,  1.40s/it]
                                                         
{'loss': 2.4251, 'learning_rate': 1.0447945027875016e-07, 'epoch': 15.29}
+
 96%|█████████▌| 59140/61904 [7:17:26<1:04:34,  1.40s/it]
 96%|█████████▌| 59141/61904 [7:17:27<1:05:11,  1.42s/it]
 96%|█████████▌| 59142/61904 [7:17:29<1:05:35,  1.43s/it]
 96%|█████████▌| 59143/61904 [7:17:30<1:05:06,  1.41s/it]
 96%|█████████▌| 59144/61904 [7:17:31<1:03:32,  1.38s/it]
 96%|█████████▌| 59145/61904 [7:17:33<1:01:51,  1.35s/it]
 96%|█████████▌| 59146/61904 [7:17:34<1:00:02,  1.31s/it]
 96%|█████████▌| 59147/61904 [7:17:35<1:02:05,  1.35s/it]
 96%|█████████▌| 59148/61904 [7:17:37<1:01:26,  1.34s/it]
 96%|█████████▌| 59149/61904 [7:17:38<1:02:03,  1.35s/it]
 96%|█████████▌| 59150/61904 [7:17:39<1:01:48,  1.35s/it]
 96%|█████████▌| 59151/61904 [7:17:41<1:02:14,  1.36s/it]
 96%|█████████▌| 59152/61904 [7:17:42<1:03:04,  1.38s/it]
 96%|█████████▌| 59153/61904 [7:17:43<1:04:17,  1.40s/it]
 96%|█████████▌| 59154/61904 [7:17:45<1:03:53,  1.39s/it]
 96%|█████████▌| 59155/61904 [7:17:46<1:02:20,  1.36s/it]
 96%|█████████▌| 59156/61904 [7:17:48<1:05:02,  1.42s/it]
 96%|█████████▌| 59157/61904 [7:17:49<1:02:13,  1.36s/it]
 96%|█████████▌| 59158/61904 [7:17:50<1:04:40,  1.41s/it]
 96%|█████████▌| 59159/61904 [7:17:52<1:02:21,  1.36s/it]
 96%|█████████▌| 59160/61904 [7:17:53<1:04:11,  1.40s/it]
                                                         
{'loss': 2.4078, 'learning_rate': 1.0444703746920782e-07, 'epoch': 15.29}
+
 96%|█████████▌| 59160/61904 [7:17:53<1:04:11,  1.40s/it]
 96%|█████████▌| 59161/61904 [7:17:55<1:05:08,  1.42s/it]
 96%|█████████▌| 59162/61904 [7:17:56<1:07:08,  1.47s/it]
 96%|█████████▌| 59163/61904 [7:17:58<1:04:31,  1.41s/it]
 96%|█████████▌| 59164/61904 [7:17:59<1:05:17,  1.43s/it]
 96%|█████████▌| 59165/61904 [7:18:00<1:03:03,  1.38s/it]
 96%|█████████▌| 59166/61904 [7:18:02<1:02:21,  1.37s/it]
 96%|█████████▌| 59167/61904 [7:18:03<1:03:40,  1.40s/it]
 96%|█████████▌| 59168/61904 [7:18:04<1:02:40,  1.37s/it]
 96%|█████████▌| 59169/61904 [7:18:06<1:01:11,  1.34s/it]
 96%|█████████▌| 59170/61904 [7:18:07<1:03:00,  1.38s/it]
 96%|█████████▌| 59171/61904 [7:18:08<1:02:33,  1.37s/it]
 96%|█████████▌| 59172/61904 [7:18:10<1:01:14,  1.34s/it]
 96%|█████████▌| 59173/61904 [7:18:11<1:01:07,  1.34s/it]
 96%|█████████▌| 59174/61904 [7:18:12<1:00:43,  1.33s/it]
 96%|█████████▌| 59175/61904 [7:18:14<1:02:32,  1.37s/it]
 96%|█████████▌| 59176/61904 [7:18:15<1:04:10,  1.41s/it]
 96%|█████████▌| 59177/61904 [7:18:17<1:03:26,  1.40s/it]
 96%|█████████▌| 59178/61904 [7:18:18<1:03:07,  1.39s/it]
 96%|█████████▌| 59179/61904 [7:18:19<1:02:59,  1.39s/it]
 96%|█████████▌| 59180/61904 [7:18:21<1:03:05,  1.39s/it]
                                                         
{'loss': 2.3711, 'learning_rate': 1.0441462465966551e-07, 'epoch': 15.3}
+
 96%|█████████▌| 59180/61904 [7:18:21<1:03:05,  1.39s/it]
 96%|█████████▌| 59181/61904 [7:18:22<1:02:34,  1.38s/it]
 96%|█████████▌| 59182/61904 [7:18:24<1:01:44,  1.36s/it]
 96%|█████████▌| 59183/61904 [7:18:25<1:02:54,  1.39s/it]
 96%|█████████▌| 59184/61904 [7:18:26<1:01:37,  1.36s/it]
 96%|█████████▌| 59185/61904 [7:18:28<1:03:57,  1.41s/it]
 96%|█████████▌| 59186/61904 [7:18:29<1:02:59,  1.39s/it]
 96%|█████████▌| 59187/61904 [7:18:31<1:03:23,  1.40s/it]
 96%|█████████▌| 59188/61904 [7:18:32<1:02:09,  1.37s/it]
 96%|███████��█▌| 59189/61904 [7:18:33<1:02:06,  1.37s/it]
 96%|█████████▌| 59190/61904 [7:18:35<1:02:20,  1.38s/it]
 96%|█████████▌| 59191/61904 [7:18:36<1:01:23,  1.36s/it]
 96%|█████████▌| 59192/61904 [7:18:37<1:00:55,  1.35s/it]
 96%|█████████▌| 59193/61904 [7:18:39<1:02:54,  1.39s/it]
 96%|█████████▌| 59194/61904 [7:18:40<1:02:55,  1.39s/it]
 96%|█████████▌| 59195/61904 [7:18:41<1:01:18,  1.36s/it]
 96%|█████████▌| 59196/61904 [7:18:43<1:01:33,  1.36s/it]
 96%|█████████▌| 59197/61904 [7:18:44<1:01:49,  1.37s/it]
 96%|█████████▌| 59198/61904 [7:18:46<1:02:51,  1.39s/it]
 96%|█████████▌| 59199/61904 [7:18:47<1:03:12,  1.40s/it]
 96%|█████████▌| 59200/61904 [7:18:48<1:02:38,  1.39s/it]
                                                         
{'loss': 2.4432, 'learning_rate': 1.0438221185012317e-07, 'epoch': 15.3}
+
 96%|█████████▌| 59200/61904 [7:18:48<1:02:38,  1.39s/it]
 96%|█████████▌| 59201/61904 [7:18:50<1:02:48,  1.39s/it]
 96%|█████████▌| 59202/61904 [7:18:51<1:05:33,  1.46s/it]
 96%|█████████▌| 59203/61904 [7:18:53<1:05:37,  1.46s/it]
 96%|█████████▌| 59204/61904 [7:18:54<1:04:23,  1.43s/it]
 96%|█████████▌| 59205/61904 [7:18:56<1:03:14,  1.41s/it]
 96%|█████████▌| 59206/61904 [7:18:57<1:02:34,  1.39s/it]
 96%|█████████▌| 59207/61904 [7:18:58<1:00:55,  1.36s/it]
 96%|█████████▌| 59208/61904 [7:19:00<1:01:40,  1.37s/it]
 96%|█████████▌| 59209/61904 [7:19:01<1:00:56,  1.36s/it]
 96%|█████████▌| 59210/61904 [7:19:02<1:00:29,  1.35s/it]
 96%|█████████▌| 59211/61904 [7:19:04<1:00:43,  1.35s/it]
 96%|█████████▌| 59212/61904 [7:19:05<1:00:33,  1.35s/it]
 96%|█████████▌| 59213/61904 [7:19:06<59:20,  1.32s/it]  
 96%|█████████▌| 59214/61904 [7:19:08<1:00:55,  1.36s/it]
 96%|█████████▌| 59215/61904 [7:19:09<1:00:18,  1.35s/it]
 96%|█████████▌| 59216/61904 [7:19:11<1:01:43,  1.38s/it]
 96%|█████████▌| 59217/61904 [7:19:12<59:54,  1.34s/it]  
 96%|█████████▌| 59218/61904 [7:19:13<59:03,  1.32s/it]
 96%|█████████▌| 59219/61904 [7:19:14<59:05,  1.32s/it]
 96%|█████████▌| 59220/61904 [7:19:16<58:17,  1.30s/it]
                                                       
{'loss': 2.4697, 'learning_rate': 1.0434979904058084e-07, 'epoch': 15.31}
+
 96%|█████████▌| 59220/61904 [7:19:16<58:17,  1.30s/it]
 96%|█████████▌| 59221/61904 [7:19:17<1:00:20,  1.35s/it]
 96%|█████████▌| 59222/61904 [7:19:18<1:00:32,  1.35s/it]
 96%|█████████▌| 59223/61904 [7:19:20<1:00:55,  1.36s/it]
 96%|█████████▌| 59224/61904 [7:19:21<1:00:04,  1.34s/it]
 96%|█████████▌| 59225/61904 [7:19:23<1:01:41,  1.38s/it]
 96%|█████████▌| 59226/61904 [7:19:24<1:01:14,  1.37s/it]
 96%|█████████▌| 59227/61904 [7:19:25<1:02:53,  1.41s/it]
 96%|█████████▌| 59228/61904 [7:19:27<1:01:28,  1.38s/it]
 96%|█████████▌| 59229/61904 [7:19:28<1:02:45,  1.41s/it]
 96%|█████████▌| 59230/61904 [7:19:30<1:07:55,  1.52s/it]
 96%|█████████▌| 59231/61904 [7:19:31<1:04:30,  1.45s/it]
 96%|█████████▌| 59232/61904 [7:19:33<1:03:01,  1.42s/it]
 96%|█████████▌| 59233/61904 [7:19:34<1:01:57,  1.39s/it]
 96%|█████████▌| 59234/61904 [7:19:35<1:01:25,  1.38s/it]
 96%|█████████▌| 59235/61904 [7:19:37<1:02:47,  1.41s/it]
 96%|█████████▌| 59236/61904 [7:19:38<1:02:02,  1.40s/it]
 96%|█████████▌| 59237/61904 [7:19:40<1:01:33,  1.38s/it]
 96%|█████████▌| 59238/61904 [7:19:41<1:05:08,  1.47s/it]
 96%|█████████▌| 59239/61904 [7:19:42<1:02:57,  1.42s/it]
 96%|█████████▌| 59240/61904 [7:19:44<1:05:24,  1.47s/it]
                                                         
{'loss': 2.4792, 'learning_rate': 1.0431738623103852e-07, 'epoch': 15.31}
+
 96%|█████████▌| 59240/61904 [7:19:44<1:05:24,  1.47s/it]
 96%|█████████▌| 59241/61904 [7:19:46<1:05:28,  1.48s/it]
 96%|█████████▌| 59242/61904 [7:19:47<1:03:22,  1.43s/it]
 96%|█████████▌| 59243/61904 [7:19:48<1:03:16,  1.43s/it]
 96%|█████████▌| 59244/61904 [7:19:50<1:05:01,  1.47s/it]
 96%|█████████▌| 59245/61904 [7:19:51<1:04:48,  1.46s/it]
 96%|█████████▌| 59246/61904 [7:19:53<1:03:11,  1.43s/it]
 96%|█████████▌| 59247/61904 [7:19:54<1:00:27,  1.37s/it]
 96%|█████████▌| 59248/61904 [7:19:55<59:30,  1.34s/it]  
 96%|█████████▌| 59249/61904 [7:19:57<1:00:40,  1.37s/it]
 96%|█████████▌| 59250/61904 [7:19:58<59:23,  1.34s/it]  
 96%|█████████▌| 59251/61904 [7:19:59<59:55,  1.36s/it]
 96%|█████████▌| 59252/61904 [7:20:01<1:01:55,  1.40s/it]
 96%|█████████▌| 59253/61904 [7:20:02<59:47,  1.35s/it]  
 96%|█████████▌| 59254/61904 [7:20:03<59:57,  1.36s/it]
 96%|█████████▌| 59255/61904 [7:20:05<1:00:29,  1.37s/it]
 96%|█████████▌| 59256/61904 [7:20:06<1:01:18,  1.39s/it]
 96%|█████████▌| 59257/61904 [7:20:08<1:01:33,  1.40s/it]
 96%|█████████▌| 59258/61904 [7:20:09<1:01:30,  1.39s/it]
 96%|█████████▌| 59259/61904 [7:20:10<59:25,  1.35s/it]  
 96%|█████████▌| 59260/61904 [7:20:12<59:41,  1.35s/it]
                                                       
{'loss': 2.4445, 'learning_rate': 1.0428497342149619e-07, 'epoch': 15.32}
+
 96%|█████████▌| 59260/61904 [7:20:12<59:41,  1.35s/it]
 96%|█████████▌| 59261/61904 [7:20:13<1:01:47,  1.40s/it]
 96%|█████████▌| 59262/61904 [7:20:15<1:03:55,  1.45s/it]
 96%|█████████▌| 59263/61904 [7:20:16<1:02:43,  1.43s/it]
 96%|█████████▌| 59264/61904 [7:20:18<1:02:54,  1.43s/it]
 96%|█████████▌| 59265/61904 [7:20:19<1:02:09,  1.41s/it]
 96%|█████████▌| 59266/61904 [7:20:20<1:02:38,  1.42s/it]
 96%|█████████▌| 59267/61904 [7:20:22<1:02:46,  1.43s/it]
 96%|█████████▌| 59268/61904 [7:20:23<1:04:07,  1.46s/it]
 96%|█████████▌| 59269/61904 [7:20:25<1:03:09,  1.44s/it]
 96%|█████████▌| 59270/61904 [7:20:26<1:02:16,  1.42s/it]
 96%|█████████▌| 59271/61904 [7:20:27<1:01:27,  1.40s/it]
 96%|█████████▌| 59272/61904 [7:20:29<1:02:24,  1.42s/it]
 96%|█████████▌| 59273/61904 [7:20:30<1:00:52,  1.39s/it]
 96%|█████████▌| 59274/61904 [7:20:32<1:02:48,  1.43s/it]
 96%|█████████▌| 59275/61904 [7:20:33<1:02:03,  1.42s/it]
 96%|█████████▌| 59276/61904 [7:20:34<59:25,  1.36s/it]  
 96%|█████████▌| 59277/61904 [7:20:36<1:01:39,  1.41s/it]
 96%|█████████▌| 59278/61904 [7:20:37<1:01:21,  1.40s/it]
 96%|█████████▌| 59279/61904 [7:20:39<1:00:06,  1.37s/it]
 96%|█████████▌| 59280/61904 [7:20:40<59:32,  1.36s/it]  
                                                       
{'loss': 2.4796, 'learning_rate': 1.0425256061195385e-07, 'epoch': 15.32}
+
 96%|█████████▌| 59280/61904 [7:20:40<59:32,  1.36s/it]
 96%|█████████▌| 59281/61904 [7:20:41<59:52,  1.37s/it]
 96%|█████████▌| 59282/61904 [7:20:43<59:44,  1.37s/it]
 96%|█████████▌| 59283/61904 [7:20:44<58:51,  1.35s/it]
 96%|█████████▌| 59284/61904 [7:20:45<58:08,  1.33s/it]
 96%|█████████▌| 59285/61904 [7:20:47<1:02:32,  1.43s/it]
 96%|█████████▌| 59286/61904 [7:20:48<1:03:23,  1.45s/it]
 96%|█████████▌| 59287/61904 [7:20:50<1:01:34,  1.41s/it]
 96%|█████████▌| 59288/61904 [7:20:51<59:37,  1.37s/it]  
 96%|█████████▌| 59289/61904 [7:20:52<59:24,  1.36s/it]
 96%|█████████▌| 59290/61904 [7:20:54<58:10,  1.34s/it]
 96%|█████████▌| 59291/61904 [7:20:55<1:00:36,  1.39s/it]
 96%|█████████▌| 59292/61904 [7:20:56<59:29,  1.37s/it]  
 96%|█████████▌| 59293/61904 [7:20:58<58:45,  1.35s/it]
 96%|█████████▌| 59294/61904 [7:20:59<58:38,  1.35s/it]
 96%|█████████▌| 59295/61904 [7:21:00<58:31,  1.35s/it]
 96%|█████████▌| 59296/61904 [7:21:02<57:32,  1.32s/it]
 96%|█████████▌| 59297/61904 [7:21:03<56:49,  1.31s/it]
 96%|█████████▌| 59298/61904 [7:21:04<57:52,  1.33s/it]
 96%|█████████▌| 59299/61904 [7:21:06<58:36,  1.35s/it]
 96%|█████████▌| 59300/61904 [7:21:07<58:14,  1.34s/it]
                                                       
{'loss': 2.4082, 'learning_rate': 1.0422014780241151e-07, 'epoch': 15.33}
+
 96%|█████████▌| 59300/61904 [7:21:07<58:14,  1.34s/it]
 96%|█████████▌| 59301/61904 [7:21:09<58:56,  1.36s/it]
 96%|█████████▌| 59302/61904 [7:21:10<58:27,  1.35s/it]
 96%|█████████▌| 59303/61904 [7:21:11<57:40,  1.33s/it]
 96%|█████████▌| 59304/61904 [7:21:12<58:00,  1.34s/it]
 96%|██��██████▌| 59305/61904 [7:21:14<58:46,  1.36s/it]
 96%|█████████▌| 59306/61904 [7:21:15<58:09,  1.34s/it]
 96%|█████████▌| 59307/61904 [7:21:17<58:18,  1.35s/it]
 96%|█████████▌| 59308/61904 [7:21:18<1:00:54,  1.41s/it]
 96%|█████████▌| 59309/61904 [7:21:20<1:02:27,  1.44s/it]
 96%|█████████▌| 59310/61904 [7:21:21<1:01:26,  1.42s/it]
 96%|█████████▌| 59311/61904 [7:21:22<1:00:00,  1.39s/it]
 96%|█████████▌| 59312/61904 [7:21:24<1:01:13,  1.42s/it]
 96%|█████████▌| 59313/61904 [7:21:25<1:00:35,  1.40s/it]
 96%|█████████▌| 59314/61904 [7:21:27<1:00:39,  1.41s/it]
 96%|█████████▌| 59315/61904 [7:21:28<1:00:44,  1.41s/it]
 96%|█████████▌| 59316/61904 [7:21:29<1:00:59,  1.41s/it]
 96%|█████████▌| 59317/61904 [7:21:31<1:00:41,  1.41s/it]
 96%|█████████▌| 59318/61904 [7:21:32<59:49,  1.39s/it]  
 96%|█████████▌| 59319/61904 [7:21:33<58:45,  1.36s/it]
 96%|█████████▌| 59320/61904 [7:21:35<1:00:21,  1.40s/it]
                                                         
{'loss': 2.4877, 'learning_rate': 1.041877349928692e-07, 'epoch': 15.33}
+
 96%|█████████▌| 59320/61904 [7:21:35<1:00:21,  1.40s/it]
 96%|█████████▌| 59321/61904 [7:21:36<1:01:07,  1.42s/it]
 96%|█████████▌| 59322/61904 [7:21:38<1:00:05,  1.40s/it]
 96%|█████████▌| 59323/61904 [7:21:39<1:00:58,  1.42s/it]
 96%|█████████▌| 59324/61904 [7:21:41<1:00:54,  1.42s/it]
 96%|█████████▌| 59325/61904 [7:21:42<59:47,  1.39s/it]  
 96%|█████████▌| 59326/61904 [7:21:43<1:00:13,  1.40s/it]
 96%|█████████▌| 59327/61904 [7:21:45<1:03:07,  1.47s/it]
 96%|█████████▌| 59328/61904 [7:21:46<1:01:29,  1.43s/it]
 96%|█████████▌| 59329/61904 [7:21:48<59:23,  1.38s/it]  
 96%|█████████▌| 59330/61904 [7:21:49<1:00:06,  1.40s/it]
 96%|█████████▌| 59331/61904 [7:21:50<59:59,  1.40s/it]  
 96%|█████████▌| 59332/61904 [7:21:52<1:00:03,  1.40s/it]
 96%|█████████▌| 59333/61904 [7:21:53<59:30,  1.39s/it]  
 96%|█████████▌| 59334/61904 [7:21:55<1:01:20,  1.43s/it]
 96%|█████████▌| 59335/61904 [7:21:56<1:01:27,  1.44s/it]
 96%|█████████▌| 59336/61904 [7:21:58<1:01:56,  1.45s/it]
 96%|█████████▌| 59337/61904 [7:21:59<1:02:27,  1.46s/it]
 96%|█████████▌| 59338/61904 [7:22:01<1:02:27,  1.46s/it]
 96%|█████████▌| 59339/61904 [7:22:02<1:03:20,  1.48s/it]
 96%|█████████▌| 59340/61904 [7:22:03<1:01:24,  1.44s/it]
                                                         
{'loss': 2.3853, 'learning_rate': 1.0415532218332686e-07, 'epoch': 15.34}
+
 96%|█████████▌| 59340/61904 [7:22:03<1:01:24,  1.44s/it]
 96%|█████████▌| 59341/61904 [7:22:05<59:34,  1.39s/it]  
 96%|█████████▌| 59342/61904 [7:22:06<57:45,  1.35s/it]
 96%|█████████▌| 59343/61904 [7:22:07<58:23,  1.37s/it]
 96%|█████████▌| 59344/61904 [7:22:09<58:56,  1.38s/it]
 96%|█████████▌| 59345/61904 [7:22:10<1:01:02,  1.43s/it]
 96%|█████████▌| 59346/61904 [7:22:12<1:00:10,  1.41s/it]
 96%|█████████▌| 59347/61904 [7:22:13<59:25,  1.39s/it]  
 96%|█████████▌| 59348/61904 [7:22:14<57:49,  1.36s/it]
 96%|█████████▌| 59349/61904 [7:22:16<58:21,  1.37s/it]
 96%|█████████▌| 59350/61904 [7:22:17<57:54,  1.36s/it]
 96%|█████████▌| 59351/61904 [7:22:18<57:25,  1.35s/it]
 96%|█████████▌| 59352/61904 [7:22:20<56:27,  1.33s/it]
 96%|█████████▌| 59353/61904 [7:22:21<57:28,  1.35s/it]
 96%|█████████▌| 59354/61904 [7:22:22<57:14,  1.35s/it]
 96%|█████████▌| 59355/61904 [7:22:24<56:17,  1.33s/it]
 96%|█████████▌| 59356/61904 [7:22:25<56:12,  1.32s/it]
 96%|█████████▌| 59357/61904 [7:22:26<55:56,  1.32s/it]
 96%|█████████▌| 59358/61904 [7:22:28<58:30,  1.38s/it]
 96%|█████████▌| 59359/61904 [7:22:29<58:31,  1.38s/it]
 96%|█████████▌| 59360/61904 [7:22:31<59:17,  1.40s/it]
                                                       
{'loss': 2.4456, 'learning_rate': 1.0412290937378452e-07, 'epoch': 15.34}
+
 96%|█████████▌| 59360/61904 [7:22:31<59:17,  1.40s/it]
 96%|█████████▌| 59361/61904 [7:22:32<57:05,  1.35s/it]
 96%|█████████▌| 59362/61904 [7:22:33<58:43,  1.39s/it]
 96%|█████��███▌| 59363/61904 [7:22:35<59:09,  1.40s/it]
 96%|█████████▌| 59364/61904 [7:22:36<58:11,  1.37s/it]
 96%|█████████▌| 59365/61904 [7:22:38<59:49,  1.41s/it]
 96%|█████████▌| 59366/61904 [7:22:39<1:02:23,  1.48s/it]
 96%|█████████▌| 59367/61904 [7:22:41<1:00:58,  1.44s/it]
 96%|█████████▌| 59368/61904 [7:22:42<58:30,  1.38s/it]  
 96%|█████████▌| 59369/61904 [7:22:43<59:57,  1.42s/it]
 96%|█████████▌| 59370/61904 [7:22:45<59:24,  1.41s/it]
 96%|█████████▌| 59371/61904 [7:22:46<58:59,  1.40s/it]
 96%|█████████▌| 59372/61904 [7:22:48<59:37,  1.41s/it]
 96%|█████████▌| 59373/61904 [7:22:49<59:22,  1.41s/it]
 96%|█████████▌| 59374/61904 [7:22:50<59:08,  1.40s/it]
 96%|█████████▌| 59375/61904 [7:22:52<57:26,  1.36s/it]
 96%|█████████▌| 59376/61904 [7:22:53<58:49,  1.40s/it]
 96%|█████████▌| 59377/61904 [7:22:55<1:00:41,  1.44s/it]
 96%|█████████▌| 59378/61904 [7:22:56<1:00:17,  1.43s/it]
 96%|█████████▌| 59379/61904 [7:22:58<1:00:31,  1.44s/it]
 96%|█████████▌| 59380/61904 [7:22:59<59:49,  1.42s/it]  
                                                       
{'loss': 2.3743, 'learning_rate': 1.0409049656424218e-07, 'epoch': 15.35}
+
 96%|█████████▌| 59380/61904 [7:22:59<59:49,  1.42s/it]
 96%|█████████▌| 59381/61904 [7:23:00<1:00:05,  1.43s/it]
 96%|█████████▌| 59382/61904 [7:23:02<1:00:41,  1.44s/it]
 96%|█████████▌| 59383/61904 [7:23:03<1:00:58,  1.45s/it]
 96%|█████████▌| 59384/61904 [7:23:05<1:00:41,  1.45s/it]
 96%|█████████▌| 59385/61904 [7:23:06<59:50,  1.43s/it]  
 96%|█████████▌| 59386/61904 [7:23:07<57:48,  1.38s/it]
 96%|█████████▌| 59387/61904 [7:23:09<56:26,  1.35s/it]
 96%|█████████▌| 59388/61904 [7:23:10<55:16,  1.32s/it]
 96%|█████████▌| 59389/61904 [7:23:11<55:09,  1.32s/it]
 96%|█████████▌| 59390/61904 [7:23:13<55:32,  1.33s/it]
 96%|█████████▌| 59391/61904 [7:23:14<54:13,  1.29s/it]
 96%|█████████▌| 59392/61904 [7:23:15<53:14,  1.27s/it]
 96%|█████████▌| 59393/61904 [7:23:16<53:58,  1.29s/it]
 96%|█████████▌| 59394/61904 [7:23:18<57:07,  1.37s/it]
 96%|█████████▌| 59395/61904 [7:23:19<58:08,  1.39s/it]
 96%|█████████▌| 59396/61904 [7:23:21<56:49,  1.36s/it]
 96%|█████████▌| 59397/61904 [7:23:22<56:21,  1.35s/it]
 96%|█████████▌| 59398/61904 [7:23:23<55:42,  1.33s/it]
 96%|█████████▌| 59399/61904 [7:23:25<56:27,  1.35s/it]
 96%|█████████▌| 59400/61904 [7:23:26<56:48,  1.36s/it]
                                                       
{'loss': 2.4828, 'learning_rate': 1.0405808375469987e-07, 'epoch': 15.35}
+
 96%|█████████▌| 59400/61904 [7:23:26<56:48,  1.36s/it]
 96%|█████████▌| 59401/61904 [7:23:27<57:25,  1.38s/it]
 96%|█████████▌| 59402/61904 [7:23:29<57:38,  1.38s/it]
 96%|█████████▌| 59403/61904 [7:23:30<57:55,  1.39s/it]
 96%|█████████▌| 59404/61904 [7:23:32<57:19,  1.38s/it]
 96%|█████████▌| 59405/61904 [7:23:33<58:39,  1.41s/it]
 96%|█████████▌| 59406/61904 [7:23:34<57:29,  1.38s/it]
 96%|█████████▌| 59407/61904 [7:23:36<56:20,  1.35s/it]
 96%|█████████▌| 59408/61904 [7:23:37<55:38,  1.34s/it]
 96%|█████████▌| 59409/61904 [7:23:39<58:08,  1.40s/it]
 96%|█████████▌| 59410/61904 [7:23:40<57:06,  1.37s/it]
 96%|█████████▌| 59411/61904 [7:23:41<56:09,  1.35s/it]
 96%|█████████▌| 59412/61904 [7:23:43<57:31,  1.39s/it]
 96%|█████████▌| 59413/61904 [7:23:44<58:18,  1.40s/it]
 96%|█████████▌| 59414/61904 [7:23:45<56:40,  1.37s/it]
 96%|█████████▌| 59415/61904 [7:23:47<54:40,  1.32s/it]
 96%|█████████▌| 59416/61904 [7:23:48<53:29,  1.29s/it]
 96%|█████████▌| 59417/61904 [7:23:49<54:14,  1.31s/it]
 96%|█████████▌| 59418/61904 [7:23:50<54:05,  1.31s/it]
 96%|█████████▌| 59419/61904 [7:23:52<53:05,  1.28s/it]
 96%|█████████▌| 59420/61904 [7:23:53<55:51,  1.35s/it]
                                                       
{'loss': 2.4157, 'learning_rate': 1.0402567094515753e-07, 'epoch': 15.36}
+
 96%|█████████▌| 59420/61904 [7:23:53<55:51,  1.35s/it]
 96%|█████████▌| 59421/61904 [7:23:55<59:03,  1.43s/it]
 96%|█��███████▌| 59422/61904 [7:23:56<58:49,  1.42s/it]
 96%|█████████▌| 59423/61904 [7:23:58<59:07,  1.43s/it]
 96%|█████████▌| 59424/61904 [7:23:59<57:21,  1.39s/it]
 96%|█████████▌| 59425/61904 [7:24:00<56:37,  1.37s/it]
 96%|█████████▌| 59426/61904 [7:24:02<57:33,  1.39s/it]
 96%|█████████▌| 59427/61904 [7:24:03<57:34,  1.39s/it]
 96%|█████████▌| 59428/61904 [7:24:04<57:21,  1.39s/it]
 96%|█████████▌| 59429/61904 [7:24:06<58:41,  1.42s/it]
 96%|█████████▌| 59430/61904 [7:24:07<58:50,  1.43s/it]
 96%|█████████▌| 59431/61904 [7:24:09<59:06,  1.43s/it]
 96%|█████████▌| 59432/61904 [7:24:10<1:00:03,  1.46s/it]
 96%|█████████▌| 59433/61904 [7:24:12<59:53,  1.45s/it]  
 96%|█████████▌| 59434/61904 [7:24:13<58:15,  1.42s/it]
 96%|█████████▌| 59435/61904 [7:24:15<58:28,  1.42s/it]
 96%|█████████▌| 59436/61904 [7:24:16<57:23,  1.40s/it]
 96%|█████████▌| 59437/61904 [7:24:17<56:14,  1.37s/it]
 96%|█████████▌| 59438/61904 [7:24:19<57:07,  1.39s/it]
 96%|█████████▌| 59439/61904 [7:24:20<57:03,  1.39s/it]
 96%|█████████▌| 59440/61904 [7:24:21<57:39,  1.40s/it]
                                                       
{'loss': 2.4593, 'learning_rate': 1.039932581356152e-07, 'epoch': 15.36}
+
 96%|█████████▌| 59440/61904 [7:24:21<57:39,  1.40s/it]
 96%|█████████▌| 59441/61904 [7:24:23<56:00,  1.36s/it]
 96%|█████████▌| 59442/61904 [7:24:24<56:18,  1.37s/it]
 96%|█████████▌| 59443/61904 [7:24:25<54:40,  1.33s/it]
 96%|█████████▌| 59444/61904 [7:24:27<54:48,  1.34s/it]
 96%|█████████▌| 59445/61904 [7:24:28<54:23,  1.33s/it]
 96%|█████████▌| 59446/61904 [7:24:29<54:27,  1.33s/it]
 96%|█████████▌| 59447/61904 [7:24:31<52:58,  1.29s/it]
 96%|█████████▌| 59448/61904 [7:24:32<53:46,  1.31s/it]
 96%|█████████▌| 59449/61904 [7:24:33<54:52,  1.34s/it]
 96%|█████████▌| 59450/61904 [7:24:35<55:03,  1.35s/it]
 96%|█████████▌| 59451/61904 [7:24:36<56:23,  1.38s/it]
 96%|█████████▌| 59452/61904 [7:24:38<56:27,  1.38s/it]
 96%|█████████▌| 59453/61904 [7:24:39<55:56,  1.37s/it]
 96%|█████████▌| 59454/61904 [7:24:40<54:30,  1.33s/it]
 96%|█████████▌| 59455/61904 [7:24:42<55:02,  1.35s/it]
 96%|█████████▌| 59456/61904 [7:24:43<53:56,  1.32s/it]
 96%|█████████▌| 59457/61904 [7:24:44<55:24,  1.36s/it]
 96%|█████████▌| 59458/61904 [7:24:46<55:39,  1.37s/it]
 96%|█████████▌| 59459/61904 [7:24:47<55:20,  1.36s/it]
 96%|█████████▌| 59460/61904 [7:24:48<56:54,  1.40s/it]
                                                       
{'loss': 2.3706, 'learning_rate': 1.0396084532607286e-07, 'epoch': 15.37}
+
 96%|█████████▌| 59460/61904 [7:24:48<56:54,  1.40s/it]
 96%|█████████▌| 59461/61904 [7:24:50<57:14,  1.41s/it]
 96%|█████████▌| 59462/61904 [7:24:51<55:47,  1.37s/it]
 96%|█████████▌| 59463/61904 [7:24:52<54:27,  1.34s/it]
 96%|█████████▌| 59464/61904 [7:24:54<54:44,  1.35s/it]
 96%|█████████▌| 59465/61904 [7:24:55<55:10,  1.36s/it]
 96%|█████████▌| 59466/61904 [7:24:57<56:43,  1.40s/it]
 96%|█████████▌| 59467/61904 [7:24:58<57:29,  1.42s/it]
 96%|█████████▌| 59468/61904 [7:24:59<55:55,  1.38s/it]
 96%|█████████▌| 59469/61904 [7:25:01<56:30,  1.39s/it]
 96%|█████████▌| 59470/61904 [7:25:02<55:07,  1.36s/it]
 96%|█████████▌| 59471/61904 [7:25:04<57:58,  1.43s/it]
 96%|█████████▌| 59472/61904 [7:25:05<58:01,  1.43s/it]
 96%|█████████▌| 59473/61904 [7:25:06<55:54,  1.38s/it]
 96%|█████████▌| 59474/61904 [7:25:08<54:29,  1.35s/it]
 96%|█████████▌| 59475/61904 [7:25:09<54:36,  1.35s/it]
 96%|█████████▌| 59476/61904 [7:25:10<54:28,  1.35s/it]
 96%|█████████▌| 59477/61904 [7:25:12<54:15,  1.34s/it]
 96%|█████████▌| 59478/61904 [7:25:13<56:55,  1.41s/it]
 96%|█████████▌| 59479/61904 [7:25:15<57:15,  1.42s/it]
 96%|█████████▌| 59480/61904 [7:25:16<58:09,  1.44s/it]
                                                       
{'loss': 2.4284, 'learning_rate': 1.0392843251653055e-07, 'epoch': 15.37}
+
 96%|█████████▌| 59480/61904 [7:25:16<58:09,  1.44s/it]
 96%|████��████▌| 59481/61904 [7:25:18<56:56,  1.41s/it]
 96%|█████████▌| 59482/61904 [7:25:19<55:41,  1.38s/it]
 96%|█████████▌| 59483/61904 [7:25:20<56:15,  1.39s/it]
 96%|█████████▌| 59484/61904 [7:25:22<55:54,  1.39s/it]
 96%|█████████▌| 59485/61904 [7:25:23<56:32,  1.40s/it]
 96%|█████████▌| 59486/61904 [7:25:25<57:19,  1.42s/it]
 96%|█████████▌| 59487/61904 [7:25:26<56:09,  1.39s/it]
 96%|█████████▌| 59488/61904 [7:25:27<56:39,  1.41s/it]
 96%|█████████▌| 59489/61904 [7:25:29<56:32,  1.40s/it]
 96%|█████████▌| 59490/61904 [7:25:30<54:02,  1.34s/it]
 96%|█████████▌| 59491/61904 [7:25:31<53:18,  1.33s/it]
 96%|█████████▌| 59492/61904 [7:25:32<53:02,  1.32s/it]
 96%|█████████▌| 59493/61904 [7:25:34<52:08,  1.30s/it]
 96%|█████████▌| 59494/61904 [7:25:35<52:56,  1.32s/it]
 96%|█████████▌| 59495/61904 [7:25:36<53:46,  1.34s/it]
 96%|█████████▌| 59496/61904 [7:25:38<54:00,  1.35s/it]
 96%|█████████▌| 59497/61904 [7:25:39<54:54,  1.37s/it]
 96%|█████████▌| 59498/61904 [7:25:41<54:46,  1.37s/it]
 96%|█████████▌| 59499/61904 [7:25:42<54:40,  1.36s/it]
 96%|█████████▌| 59500/61904 [7:25:44<59:24,  1.48s/it]
                                                       
{'loss': 2.4174, 'learning_rate': 1.0389601970698821e-07, 'epoch': 15.38}
+
 96%|█████████▌| 59500/61904 [7:25:44<59:24,  1.48s/it]
 96%|█████████▌| 59501/61904 [7:25:45<58:59,  1.47s/it]
 96%|█████████▌| 59502/61904 [7:25:47<59:39,  1.49s/it]
 96%|█████████▌| 59503/61904 [7:25:48<57:33,  1.44s/it]
 96%|█████████▌| 59504/61904 [7:25:49<57:19,  1.43s/it]
 96%|█████████▌| 59505/61904 [7:25:51<55:23,  1.39s/it]
 96%|█████████▌| 59506/61904 [7:25:52<55:41,  1.39s/it]
 96%|█████████▌| 59507/61904 [7:25:54<55:09,  1.38s/it]
 96%|█████████▌| 59508/61904 [7:25:55<54:45,  1.37s/it]
 96%|█████████▌| 59509/61904 [7:25:56<56:34,  1.42s/it]
 96%|█████████▌| 59510/61904 [7:25:58<54:26,  1.36s/it]
 96%|█████████▌| 59511/61904 [7:25:59<54:56,  1.38s/it]
 96%|█████████▌| 59512/61904 [7:26:00<53:34,  1.34s/it]
 96%|█████████▌| 59513/61904 [7:26:02<52:34,  1.32s/it]
 96%|█████████▌| 59514/61904 [7:26:03<52:55,  1.33s/it]
 96%|█████████▌| 59515/61904 [7:26:04<54:14,  1.36s/it]
 96%|█████████▌| 59516/61904 [7:26:06<54:26,  1.37s/it]
 96%|█████████▌| 59517/61904 [7:26:07<53:52,  1.35s/it]
 96%|█████████▌| 59518/61904 [7:26:09<55:27,  1.39s/it]
 96%|█████████▌| 59519/61904 [7:26:10<57:00,  1.43s/it]
 96%|█████████▌| 59520/61904 [7:26:12<57:10,  1.44s/it]
                                                       
{'loss': 2.3777, 'learning_rate': 1.0386360689744587e-07, 'epoch': 15.38}
+
 96%|█████████▌| 59520/61904 [7:26:12<57:10,  1.44s/it]
 96%|█████████▌| 59521/61904 [7:26:13<55:33,  1.40s/it]
 96%|█████████▌| 59522/61904 [7:26:14<54:43,  1.38s/it]
 96%|█████████▌| 59523/61904 [7:26:16<56:28,  1.42s/it]
 96%|█████████▌| 59524/61904 [7:26:17<57:30,  1.45s/it]
 96%|█████████▌| 59525/61904 [7:26:19<56:33,  1.43s/it]
 96%|█████████▌| 59526/61904 [7:26:20<54:49,  1.38s/it]
 96%|█████████▌| 59527/61904 [7:26:21<54:29,  1.38s/it]
 96%|█████████▌| 59528/61904 [7:26:22<52:37,  1.33s/it]
 96%|█████████▌| 59529/61904 [7:26:24<54:35,  1.38s/it]
 96%|█████████▌| 59530/61904 [7:26:25<54:59,  1.39s/it]
 96%|█████████▌| 59531/61904 [7:26:27<53:52,  1.36s/it]
 96%|█████████▌| 59532/61904 [7:26:28<54:24,  1.38s/it]
 96%|█████████▌| 59533/61904 [7:26:30<56:35,  1.43s/it]
 96%|█████████▌| 59534/61904 [7:26:31<55:01,  1.39s/it]
 96%|█████████▌| 59535/61904 [7:26:32<54:01,  1.37s/it]
 96%|█████████▌| 59536/61904 [7:26:34<53:22,  1.35s/it]
 96%|█████████▌| 59537/61904 [7:26:35<53:35,  1.36s/it]
 96%|█████████▌| 59538/61904 [7:26:36<54:09,  1.37s/it]
 96%|█████████▌| 59539/61904 [7:26:38<54:35,  1.39s/it]
 96%|█████████▌| 59540/61904 [7:26:39<53:57,  1.37s/it]
                                                       
{'loss': 2.3894, 'learning_rate': 1.0383119408790354e-07, 'epoch': 15.39}
+
 96%|████████��▌| 59540/61904 [7:26:39<53:57,  1.37s/it]
 96%|█████████▌| 59541/61904 [7:26:40<54:17,  1.38s/it]
 96%|█████████▌| 59542/61904 [7:26:42<52:45,  1.34s/it]
 96%|█████████▌| 59543/61904 [7:26:43<53:11,  1.35s/it]
 96%|█████████▌| 59544/61904 [7:26:45<55:05,  1.40s/it]
 96%|█████████▌| 59545/61904 [7:26:46<53:31,  1.36s/it]
 96%|█████████▌| 59546/61904 [7:26:47<54:42,  1.39s/it]
 96%|█████████▌| 59547/61904 [7:26:49<54:00,  1.37s/it]
 96%|█████████▌| 59548/61904 [7:26:50<54:48,  1.40s/it]
 96%|█████████▌| 59549/61904 [7:26:52<55:59,  1.43s/it]
 96%|█████████▌| 59550/61904 [7:26:53<55:46,  1.42s/it]
 96%|█████████▌| 59551/61904 [7:26:54<55:38,  1.42s/it]
 96%|█████████▌| 59552/61904 [7:26:56<55:04,  1.41s/it]
 96%|█████████▌| 59553/61904 [7:26:57<55:15,  1.41s/it]
 96%|█████████▌| 59554/61904 [7:26:59<54:48,  1.40s/it]
 96%|█████████▌| 59555/61904 [7:27:00<56:33,  1.44s/it]
 96%|█████████▌| 59556/61904 [7:27:02<56:23,  1.44s/it]
 96%|█████████▌| 59557/61904 [7:27:03<55:06,  1.41s/it]
 96%|█████████▌| 59558/61904 [7:27:04<53:31,  1.37s/it]
 96%|█████████▌| 59559/61904 [7:27:05<52:09,  1.33s/it]
 96%|█████████▌| 59560/61904 [7:27:07<51:34,  1.32s/it]
                                                       
{'loss': 2.4183, 'learning_rate': 1.0379878127836122e-07, 'epoch': 15.39}
+
 96%|█████████▌| 59560/61904 [7:27:07<51:34,  1.32s/it]
 96%|█████████▌| 59561/61904 [7:27:08<51:32,  1.32s/it]
 96%|█████████▌| 59562/61904 [7:27:09<51:36,  1.32s/it]
 96%|█████████▌| 59563/61904 [7:27:11<52:07,  1.34s/it]
 96%|█████████▌| 59564/61904 [7:27:12<55:44,  1.43s/it]
 96%|█████████▌| 59565/61904 [7:27:14<55:15,  1.42s/it]
 96%|█████████▌| 59566/61904 [7:27:15<54:10,  1.39s/it]
 96%|█████████▌| 59567/61904 [7:27:16<53:41,  1.38s/it]
 96%|█████████▌| 59568/61904 [7:27:18<54:10,  1.39s/it]
 96%|█████████▌| 59569/61904 [7:27:20<56:46,  1.46s/it]
 96%|█████████▌| 59570/61904 [7:27:21<55:45,  1.43s/it]
 96%|█████████▌| 59571/61904 [7:27:22<54:07,  1.39s/it]
 96%|█████████▌| 59572/61904 [7:27:24<53:19,  1.37s/it]
 96%|█████████▌| 59573/61904 [7:27:25<54:21,  1.40s/it]
 96%|█████████▌| 59574/61904 [7:27:26<53:21,  1.37s/it]
 96%|█████████▌| 59575/61904 [7:27:28<52:44,  1.36s/it]
 96%|█████████▌| 59576/61904 [7:27:29<54:53,  1.41s/it]
 96%|█████████▌| 59577/61904 [7:27:31<54:31,  1.41s/it]
 96%|█████████▌| 59578/61904 [7:27:32<53:47,  1.39s/it]
 96%|█████████▌| 59579/61904 [7:27:33<53:03,  1.37s/it]
 96%|█████████▌| 59580/61904 [7:27:35<54:33,  1.41s/it]
                                                       
{'loss': 2.3614, 'learning_rate': 1.0376636846881888e-07, 'epoch': 15.4}
+
 96%|█████████▌| 59580/61904 [7:27:35<54:33,  1.41s/it]
 96%|█████████▌| 59581/61904 [7:27:36<54:55,  1.42s/it]
 96%|█████████▌| 59582/61904 [7:27:37<53:28,  1.38s/it]
 96%|█████████▋| 59583/61904 [7:27:39<53:44,  1.39s/it]
 96%|█████████▋| 59584/61904 [7:27:40<54:45,  1.42s/it]
 96%|█████████▋| 59585/61904 [7:27:42<53:49,  1.39s/it]
 96%|█████████▋| 59586/61904 [7:27:43<57:35,  1.49s/it]
 96%|█████████▋| 59587/61904 [7:27:45<54:30,  1.41s/it]
 96%|█████████▋| 59588/61904 [7:27:46<53:53,  1.40s/it]
 96%|█████████▋| 59589/61904 [7:27:47<52:10,  1.35s/it]
 96%|█████████▋| 59590/61904 [7:27:49<52:21,  1.36s/it]
 96%|█████████▋| 59591/61904 [7:27:50<52:28,  1.36s/it]
 96%|█████████▋| 59592/61904 [7:27:51<53:25,  1.39s/it]
 96%|█████████▋| 59593/61904 [7:27:53<53:08,  1.38s/it]
 96%|█████████▋| 59594/61904 [7:27:54<54:40,  1.42s/it]
 96%|█████████▋| 59595/61904 [7:27:56<54:27,  1.41s/it]
 96%|█████████▋| 59596/61904 [7:27:57<53:22,  1.39s/it]
 96%|█████████▋| 59597/61904 [7:27:58<52:35,  1.37s/it]
 96%|█████████▋| 59598/61904 [7:28:00<52:23,  1.36s/it]
 96%|█████████▋| 59599/61904 [7:28:01<54:04,  1.41s/it]
 96%|█████████▋| 59600/61904 [7:28:02<52:32,  1.37s/it]
                                                       
{'loss': 2.4399, 'learning_rate': 1.0373395565927654e-07, 'epoch': 15.4}
+
 96%|█████████▋| 59600/61904 [7:28:02<52:32,  1.37s/it]
 96%|█████████▋| 59601/61904 [7:28:04<51:13,  1.33s/it]
 96%|█████████▋| 59602/61904 [7:28:05<50:50,  1.33s/it]
 96%|█████████▋| 59603/61904 [7:28:06<52:09,  1.36s/it]
 96%|█████████▋| 59604/61904 [7:28:08<52:40,  1.37s/it]
 96%|█████████▋| 59605/61904 [7:28:09<52:11,  1.36s/it]
 96%|█████████▋| 59606/61904 [7:28:10<50:53,  1.33s/it]
 96%|█████████▋| 59607/61904 [7:28:12<50:58,  1.33s/it]
 96%|█████████▋| 59608/61904 [7:28:13<52:51,  1.38s/it]
 96%|█████████▋| 59609/61904 [7:28:15<52:07,  1.36s/it]
 96%|█████████▋| 59610/61904 [7:28:16<50:20,  1.32s/it]
 96%|█████████▋| 59611/61904 [7:28:17<50:10,  1.31s/it]
 96%|█████████▋| 59612/61904 [7:28:18<49:36,  1.30s/it]
 96%|█████████▋| 59613/61904 [7:28:20<50:33,  1.32s/it]
 96%|█████████▋| 59614/61904 [7:28:21<52:20,  1.37s/it]
 96%|█████████▋| 59615/61904 [7:28:23<54:21,  1.42s/it]
 96%|█████████▋| 59616/61904 [7:28:24<53:42,  1.41s/it]
 96%|█████████▋| 59617/61904 [7:28:26<55:32,  1.46s/it]
 96%|█████████▋| 59618/61904 [7:28:27<55:38,  1.46s/it]
 96%|█████████▋| 59619/61904 [7:28:29<55:22,  1.45s/it]
 96%|█████████▋| 59620/61904 [7:28:30<54:11,  1.42s/it]
                                                       
{'loss': 2.3998, 'learning_rate': 1.0370154284973422e-07, 'epoch': 15.41}
+
 96%|█████████▋| 59620/61904 [7:28:30<54:11,  1.42s/it]
 96%|█████████▋| 59621/61904 [7:28:31<54:08,  1.42s/it]
 96%|█████████▋| 59622/61904 [7:28:33<53:12,  1.40s/it]
 96%|█████████▋| 59623/61904 [7:28:34<54:03,  1.42s/it]
 96%|█████████▋| 59624/61904 [7:28:36<52:35,  1.38s/it]
 96%|█████████▋| 59625/61904 [7:28:37<51:45,  1.36s/it]
 96%|█████████▋| 59626/61904 [7:28:38<51:24,  1.35s/it]
 96%|█████████▋| 59627/61904 [7:28:40<51:26,  1.36s/it]
 96%|█████████▋| 59628/61904 [7:28:41<51:40,  1.36s/it]
 96%|█████████▋| 59629/61904 [7:28:42<51:17,  1.35s/it]
 96%|█████████▋| 59630/61904 [7:28:44<50:49,  1.34s/it]
 96%|█████████▋| 59631/61904 [7:28:45<50:43,  1.34s/it]
 96%|█████████▋| 59632/61904 [7:28:46<52:53,  1.40s/it]
 96%|█████████▋| 59633/61904 [7:28:48<52:05,  1.38s/it]
 96%|█████████▋| 59634/61904 [7:28:49<50:41,  1.34s/it]
 96%|█████████▋| 59635/61904 [7:28:50<50:31,  1.34s/it]
 96%|█████████▋| 59636/61904 [7:28:52<50:22,  1.33s/it]
 96%|█████████▋| 59637/61904 [7:28:53<53:35,  1.42s/it]
 96%|█████████▋| 59638/61904 [7:28:55<52:55,  1.40s/it]
 96%|█████████▋| 59639/61904 [7:28:56<51:37,  1.37s/it]
 96%|█████████▋| 59640/61904 [7:28:57<51:36,  1.37s/it]
                                                       
{'loss': 2.4962, 'learning_rate': 1.036691300401919e-07, 'epoch': 15.41}
+
 96%|█████████▋| 59640/61904 [7:28:57<51:36,  1.37s/it]
 96%|█████████▋| 59641/61904 [7:28:59<50:03,  1.33s/it]
 96%|█████████▋| 59642/61904 [7:29:00<50:24,  1.34s/it]
 96%|█████████▋| 59643/61904 [7:29:01<51:04,  1.36s/it]
 96%|█████████▋| 59644/61904 [7:29:03<51:46,  1.37s/it]
 96%|█████████▋| 59645/61904 [7:29:04<52:08,  1.38s/it]
 96%|█████████▋| 59646/61904 [7:29:05<51:25,  1.37s/it]
 96%|█████████▋| 59647/61904 [7:29:07<52:46,  1.40s/it]
 96%|█████████▋| 59648/61904 [7:29:08<52:14,  1.39s/it]
 96%|█████████▋| 59649/61904 [7:29:10<55:15,  1.47s/it]
 96%|█████████▋| 59650/61904 [7:29:11<53:56,  1.44s/it]
 96%|█████████▋| 59651/61904 [7:29:13<51:33,  1.37s/it]
 96%|█████████▋| 59652/61904 [7:29:14<51:14,  1.37s/it]
 96%|█████████▋| 59653/61904 [7:29:15<50:46,  1.35s/it]
 96%|█████████▋| 59654/61904 [7:29:17<52:26,  1.40s/it]
 96%|█████████▋| 59655/61904 [7:29:18<52:59,  1.41s/it]
 96%|█████████▋| 59656/61904 [7:29:20<52:15,  1.39s/it]
 96%|█████████▋| 59657/61904 [7:29:21<51:02,  1.36s/it]
 96%|█████████▋| 59658/61904 [7:29:22<50:39,  1.35s/it]
 96%|█████████▋| 59659/61904 [7:29:24<51:59,  1.39s/it]
 96%|█████████▋| 59660/61904 [7:29:25<51:42,  1.38s/it]
                                                       
{'loss': 2.3728, 'learning_rate': 1.0363671723064956e-07, 'epoch': 15.42}
+
 96%|█████████▋| 59660/61904 [7:29:25<51:42,  1.38s/it]
 96%|█████████▋| 59661/61904 [7:29:26<52:17,  1.40s/it]
 96%|█████████▋| 59662/61904 [7:29:28<52:15,  1.40s/it]
 96%|█████████▋| 59663/61904 [7:29:29<52:03,  1.39s/it]
 96%|█████████▋| 59664/61904 [7:29:31<51:02,  1.37s/it]
 96%|█████████▋| 59665/61904 [7:29:32<52:46,  1.41s/it]
 96%|█████████▋| 59666/61904 [7:29:33<52:30,  1.41s/it]
 96%|█████████▋| 59667/61904 [7:29:35<52:43,  1.41s/it]
 96%|█████████▋| 59668/61904 [7:29:36<53:51,  1.45s/it]
 96%|█████████▋| 59669/61904 [7:29:38<53:47,  1.44s/it]
 96%|█████████▋| 59670/61904 [7:29:39<51:37,  1.39s/it]
 96%|█████████▋| 59671/61904 [7:29:40<51:28,  1.38s/it]
 96%|█████████▋| 59672/61904 [7:29:42<50:38,  1.36s/it]
 96%|█████████▋| 59673/61904 [7:29:43<49:04,  1.32s/it]
 96%|█████████▋| 59674/61904 [7:29:44<50:14,  1.35s/it]
 96%|█████████▋| 59675/61904 [7:29:46<50:28,  1.36s/it]
 96%|█████████▋| 59676/61904 [7:29:47<49:20,  1.33s/it]
 96%|█████████▋| 59677/61904 [7:29:48<49:09,  1.32s/it]
 96%|█████████▋| 59678/61904 [7:29:50<50:04,  1.35s/it]
 96%|█████████▋| 59679/61904 [7:29:51<50:01,  1.35s/it]
 96%|█████████▋| 59680/61904 [7:29:52<49:39,  1.34s/it]
                                                       
{'loss': 2.4273, 'learning_rate': 1.0360430442110722e-07, 'epoch': 15.42}
+
 96%|█████████▋| 59680/61904 [7:29:52<49:39,  1.34s/it]
 96%|█████████▋| 59681/61904 [7:29:54<49:44,  1.34s/it]
 96%|█████████▋| 59682/61904 [7:29:55<50:56,  1.38s/it]
 96%|█████████▋| 59683/61904 [7:29:57<51:05,  1.38s/it]
 96%|█████████▋| 59684/61904 [7:29:58<50:06,  1.35s/it]
 96%|█████████▋| 59685/61904 [7:29:59<50:50,  1.37s/it]
 96%|█████████▋| 59686/61904 [7:30:01<52:14,  1.41s/it]
 96%|█████████▋| 59687/61904 [7:30:02<51:35,  1.40s/it]
 96%|█████████▋| 59688/61904 [7:30:04<53:11,  1.44s/it]
 96%|█████████▋| 59689/61904 [7:30:05<53:53,  1.46s/it]
 96%|█████████▋| 59690/61904 [7:30:07<53:23,  1.45s/it]
 96%|█████████▋| 59691/61904 [7:30:08<53:22,  1.45s/it]
 96%|█████████▋| 59692/61904 [7:30:09<51:16,  1.39s/it]
 96%|█████████▋| 59693/61904 [7:30:11<50:44,  1.38s/it]
 96%|█████████▋| 59694/61904 [7:30:12<50:02,  1.36s/it]
 96%|█████████▋| 59695/61904 [7:30:13<50:30,  1.37s/it]
 96%|█████████▋| 59696/61904 [7:30:15<51:59,  1.41s/it]
 96%|█████████▋| 59697/61904 [7:30:16<50:53,  1.38s/it]
 96%|█████████▋| 59698/61904 [7:30:18<51:32,  1.40s/it]
 96%|█████████▋| 59699/61904 [7:30:19<51:34,  1.40s/it]
 96%|█████████▋| 59700/61904 [7:30:20<50:53,  1.39s/it]
                                                       
{'loss': 2.4366, 'learning_rate': 1.0357189161156489e-07, 'epoch': 15.43}
+
 96%|█████████▋| 59700/61904 [7:30:20<50:53,  1.39s/it]
 96%|█████████▋| 59701/61904 [7:30:22<49:18,  1.34s/it]
 96%|█████████▋| 59702/61904 [7:30:23<50:26,  1.37s/it]
 96%|█████████▋| 59703/61904 [7:30:24<48:46,  1.33s/it]
 96%|█████████▋| 59704/61904 [7:30:26<49:32,  1.35s/it]
 96%|█████████▋| 59705/61904 [7:30:27<52:16,  1.43s/it]
 96%|█████████▋| 59706/61904 [7:30:29<52:41,  1.44s/it]
 96%|█████████▋| 59707/61904 [7:30:30<52:11,  1.43s/it]
 96%|█████████▋| 59708/61904 [7:30:32<52:30,  1.43s/it]
 96%|█████████▋| 59709/61904 [7:30:33<52:25,  1.43s/it]
 96%|█████████▋| 59710/61904 [7:30:34<51:25,  1.41s/it]
 96%|█████████▋| 59711/61904 [7:30:36<50:25,  1.38s/it]
 96%|█████████▋| 59712/61904 [7:30:37<49:08,  1.34s/it]
 96%|█████████▋| 59713/61904 [7:30:38<48:57,  1.34s/it]
 96%|█████████▋| 59714/61904 [7:30:40<49:14,  1.35s/it]
 96%|█████████▋| 59715/61904 [7:30:41<49:29,  1.36s/it]
 96%|█████████▋| 59716/61904 [7:30:42<49:15,  1.35s/it]
 96%|█████████▋| 59717/61904 [7:30:44<50:26,  1.38s/it]
 96%|█████████▋| 59718/61904 [7:30:45<50:43,  1.39s/it]
 96%|█████████▋| 59719/61904 [7:30:47<50:29,  1.39s/it]
 96%|█████████▋| 59720/61904 [7:30:48<51:23,  1.41s/it]
                                                       
{'loss': 2.4697, 'learning_rate': 1.0353947880202257e-07, 'epoch': 15.43}
+
 96%|█████████▋| 59720/61904 [7:30:48<51:23,  1.41s/it]
 96%|█████████▋| 59721/61904 [7:30:50<51:11,  1.41s/it]
 96%|█████████▋| 59722/61904 [7:30:51<51:16,  1.41s/it]
 96%|█████████▋| 59723/61904 [7:30:52<51:01,  1.40s/it]
 96%|█████████▋| 59724/61904 [7:30:54<50:04,  1.38s/it]
 96%|█████████▋| 59725/61904 [7:30:55<50:51,  1.40s/it]
 96%|█████████▋| 59726/61904 [7:30:56<49:49,  1.37s/it]
 96%|█████████▋| 59727/61904 [7:30:58<51:11,  1.41s/it]
 96%|█████████▋| 59728/61904 [7:30:59<52:05,  1.44s/it]
 96%|█████████▋| 59729/61904 [7:31:01<50:45,  1.40s/it]
 96%|█████████▋| 59730/61904 [7:31:02<50:38,  1.40s/it]
 96%|█████████▋| 59731/61904 [7:31:03<49:58,  1.38s/it]
 96%|█████████▋| 59732/61904 [7:31:05<48:43,  1.35s/it]
 96%|█████████▋| 59733/61904 [7:31:06<49:39,  1.37s/it]
 96%|█████████▋| 59734/61904 [7:31:08<50:39,  1.40s/it]
 96%|█████████▋| 59735/61904 [7:31:09<51:52,  1.43s/it]
 96%|█████████▋| 59736/61904 [7:31:11<54:16,  1.50s/it]
 96%|█████████▋| 59737/61904 [7:31:12<52:54,  1.46s/it]
 97%|█████████▋| 59738/61904 [7:31:13<50:32,  1.40s/it]
 97%|█████████▋| 59739/61904 [7:31:15<49:01,  1.36s/it]
 97%|█████████▋| 59740/61904 [7:31:16<50:00,  1.39s/it]
                                                       
{'loss': 2.3705, 'learning_rate': 1.0350706599248023e-07, 'epoch': 15.44}
+
 97%|█████████▋| 59740/61904 [7:31:16<50:00,  1.39s/it]
 97%|█████████▋| 59741/61904 [7:31:18<50:10,  1.39s/it]
 97%|█████████▋| 59742/61904 [7:31:19<49:04,  1.36s/it]
 97%|█████████▋| 59743/61904 [7:31:20<48:47,  1.35s/it]
 97%|█████████▋| 59744/61904 [7:31:22<49:31,  1.38s/it]
 97%|█████████▋| 59745/61904 [7:31:23<49:35,  1.38s/it]
 97%|█████████▋| 59746/61904 [7:31:25<52:18,  1.45s/it]
 97%|█████████▋| 59747/61904 [7:31:26<50:04,  1.39s/it]
 97%|█████████▋| 59748/61904 [7:31:27<49:57,  1.39s/it]
 97%|█████████▋| 59749/61904 [7:31:29<49:24,  1.38s/it]
 97%|█████████▋| 59750/61904 [7:31:30<47:53,  1.33s/it]
 97%|█████████▋| 59751/61904 [7:31:31<49:24,  1.38s/it]
 97%|█████████▋| 59752/61904 [7:31:33<49:30,  1.38s/it]
 97%|█████████▋| 59753/61904 [7:31:34<48:58,  1.37s/it]
 97%|█████████▋| 59754/61904 [7:31:35<49:22,  1.38s/it]
 97%|█████████▋| 59755/61904 [7:31:37<48:40,  1.36s/it]
 97%|█████████▋| 59756/61904 [7:31:38<47:59,  1.34s/it]
 97%|█████████▋| 59757/61904 [7:31:39<48:02,  1.34s/it]
 97%|█████████▋| 59758/61904 [7:31:41<49:54,  1.40s/it]
 97%|█████████▋| 59759/61904 [7:31:42<48:57,  1.37s/it]
 97%|█████████▋| 59760/61904 [7:31:44<49:14,  1.38s/it]
                                                       
{'loss': 2.4004, 'learning_rate': 1.0347465318293789e-07, 'epoch': 15.45}
+
 97%|█████████▋| 59760/61904 [7:31:44<49:14,  1.38s/it]
 97%|█████████▋| 59761/61904 [7:31:45<49:17,  1.38s/it]
 97%|█████████▋| 59762/61904 [7:31:46<48:10,  1.35s/it]
 97%|█████████▋| 59763/61904 [7:31:48<49:26,  1.39s/it]
 97%|█████████▋| 59764/61904 [7:31:49<50:30,  1.42s/it]
 97%|█████████▋| 59765/61904 [7:31:51<50:12,  1.41s/it]
 97%|█████████▋| 59766/61904 [7:31:52<50:01,  1.40s/it]
 97%|█████████▋| 59767/61904 [7:31:53<49:38,  1.39s/it]
 97%|█████████▋| 59768/61904 [7:31:55<49:06,  1.38s/it]
 97%|█████████▋| 59769/61904 [7:31:56<49:54,  1.40s/it]
 97%|█████████▋| 59770/61904 [7:31:58<50:33,  1.42s/it]
 97%|█████████▋| 59771/61904 [7:31:59<50:47,  1.43s/it]
 97%|█████████▋| 59772/61904 [7:32:00<50:04,  1.41s/it]
 97%|█████████▋| 59773/61904 [7:32:02<49:55,  1.41s/it]
 97%|█████████▋| 59774/61904 [7:32:03<50:41,  1.43s/it]
 97%|█████████▋| 59775/61904 [7:32:05<49:44,  1.40s/it]
 97%|█████████▋| 59776/61904 [7:32:06<49:27,  1.39s/it]
 97%|█████████▋| 59777/61904 [7:32:08<49:49,  1.41s/it]
 97%|█████████▋| 59778/61904 [7:32:09<49:02,  1.38s/it]
 97%|█████████▋| 59779/61904 [7:32:10<48:46,  1.38s/it]
 97%|█████████▋| 59780/61904 [7:32:12<48:44,  1.38s/it]
                                                       
{'loss': 2.4214, 'learning_rate': 1.0344224037339557e-07, 'epoch': 15.45}
+
 97%|█████████▋| 59780/61904 [7:32:12<48:44,  1.38s/it]
 97%|█████████▋| 59781/61904 [7:32:13<47:21,  1.34s/it]
 97%|█████████▋| 59782/61904 [7:32:14<47:17,  1.34s/it]
 97%|█████████▋| 59783/61904 [7:32:16<47:51,  1.35s/it]
 97%|█████████▋| 59784/61904 [7:32:17<48:50,  1.38s/it]
 97%|█████████▋| 59785/61904 [7:32:18<48:24,  1.37s/it]
 97%|█████████▋| 59786/61904 [7:32:20<48:36,  1.38s/it]
 97%|█████████▋| 59787/61904 [7:32:21<48:17,  1.37s/it]
 97%|█████████▋| 59788/61904 [7:32:22<48:11,  1.37s/it]
 97%|█████████▋| 59789/61904 [7:32:24<50:44,  1.44s/it]
 97%|█████████▋| 59790/61904 [7:32:26<52:03,  1.48s/it]
 97%|█████████▋| 59791/61904 [7:32:27<50:37,  1.44s/it]
 97%|█████████▋| 59792/61904 [7:32:28<48:56,  1.39s/it]
 97%|█████████▋| 59793/61904 [7:32:30<48:39,  1.38s/it]
 97%|█████████▋| 59794/61904 [7:32:31<47:40,  1.36s/it]
 97%|█████████▋| 59795/61904 [7:32:32<48:06,  1.37s/it]
 97%|█████████▋| 59796/61904 [7:32:34<47:29,  1.35s/it]
 97%|█████████▋| 59797/61904 [7:32:35<48:23,  1.38s/it]
 97%|█████████▋| 59798/61904 [7:32:37<49:23,  1.41s/it]
 97%|█████████▋| 59799/61904 [7:32:38<49:06,  1.40s/it]
 97%|█████████▋| 59800/61904 [7:32:39<48:45,  1.39s/it]
                                                       
{'loss': 2.4458, 'learning_rate': 1.0340982756385324e-07, 'epoch': 15.46}
+
 97%|█████████▋| 59800/61904 [7:32:39<48:45,  1.39s/it]
 97%|█████████▋| 59801/61904 [7:32:41<48:36,  1.39s/it]
 97%|█████████▋| 59802/61904 [7:32:42<46:32,  1.33s/it]
 97%|█████████▋| 59803/61904 [7:32:43<45:57,  1.31s/it]
 97%|█████████▋| 59804/61904 [7:32:45<46:36,  1.33s/it]
 97%|█████████▋| 59805/61904 [7:32:46<47:42,  1.36s/it]
 97%|█████████▋| 59806/61904 [7:32:47<48:09,  1.38s/it]
 97%|█████████▋| 59807/61904 [7:32:49<49:23,  1.41s/it]
 97%|█████████▋| 59808/61904 [7:32:50<51:08,  1.46s/it]
 97%|█████████▋| 59809/61904 [7:32:52<48:46,  1.40s/it]
 97%|█████████▋| 59810/61904 [7:32:53<47:29,  1.36s/it]
 97%|█████████▋| 59811/61904 [7:32:54<49:14,  1.41s/it]
 97%|█████████▋| 59812/61904 [7:32:56<49:00,  1.41s/it]
 97%|█████████▋| 59813/61904 [7:32:57<47:40,  1.37s/it]
 97%|█████████▋| 59814/61904 [7:32:59<47:26,  1.36s/it]
 97%|█████████▋| 59815/61904 [7:33:00<47:22,  1.36s/it]
 97%|█████████▋| 59816/61904 [7:33:01<47:42,  1.37s/it]
 97%|█████████▋| 59817/61904 [7:33:03<47:50,  1.38s/it]
 97%|█████████▋| 59818/61904 [7:33:04<46:58,  1.35s/it]
 97%|█████████▋| 59819/61904 [7:33:05<47:30,  1.37s/it]
 97%|█████████▋| 59820/61904 [7:33:07<49:38,  1.43s/it]
                                                       
{'loss': 2.4129, 'learning_rate': 1.033774147543109e-07, 'epoch': 15.46}
+
 97%|█████████▋| 59820/61904 [7:33:07<49:38,  1.43s/it]
 97%|█████████▋| 59821/61904 [7:33:08<48:58,  1.41s/it]
 97%|█████████▋| 59822/61904 [7:33:10<47:29,  1.37s/it]
 97%|█████████▋| 59823/61904 [7:33:11<45:57,  1.33s/it]
 97%|█████████▋| 59824/61904 [7:33:12<45:32,  1.31s/it]
 97%|█████████▋| 59825/61904 [7:33:13<46:13,  1.33s/it]
 97%|█████████▋| 59826/61904 [7:33:15<45:42,  1.32s/it]
 97%|█████████▋| 59827/61904 [7:33:16<45:14,  1.31s/it]
 97%|█████████▋| 59828/61904 [7:33:17<45:24,  1.31s/it]
 97%|█████████▋| 59829/61904 [7:33:19<46:03,  1.33s/it]
 97%|█████████▋| 59830/61904 [7:33:20<46:29,  1.35s/it]
 97%|█████████▋| 59831/61904 [7:33:21<45:56,  1.33s/it]
 97%|█████████▋| 59832/61904 [7:33:23<45:27,  1.32s/it]
 97%|█████████▋| 59833/61904 [7:33:24<43:46,  1.27s/it]
 97%|█████████▋| 59834/61904 [7:33:25<45:16,  1.31s/it]
 97%|█████████▋| 59835/61904 [7:33:26<44:24,  1.29s/it]
 97%|█████████▋| 59836/61904 [7:33:28<47:09,  1.37s/it]
 97%|█████████▋| 59837/61904 [7:33:29<48:01,  1.39s/it]
 97%|█████████▋| 59838/61904 [7:33:31<47:26,  1.38s/it]
 97%|█████████▋| 59839/61904 [7:33:32<47:32,  1.38s/it]
 97%|█████████▋| 59840/61904 [7:33:34<48:27,  1.41s/it]
                                                       
{'loss': 2.3648, 'learning_rate': 1.0334500194476858e-07, 'epoch': 15.47}
+
 97%|█████████▋| 59840/61904 [7:33:34<48:27,  1.41s/it]
 97%|█████████▋| 59841/61904 [7:33:35<48:07,  1.40s/it]
 97%|█████████▋| 59842/61904 [7:33:36<46:31,  1.35s/it]
 97%|█████████▋| 59843/61904 [7:33:38<48:56,  1.42s/it]
 97%|█████████▋| 59844/61904 [7:33:39<48:05,  1.40s/it]
 97%|█████████▋| 59845/61904 [7:33:41<46:34,  1.36s/it]
 97%|█████████▋| 59846/61904 [7:33:42<46:58,  1.37s/it]
 97%|█████████▋| 59847/61904 [7:33:43<46:53,  1.37s/it]
 97%|█████████▋| 59848/61904 [7:33:45<46:32,  1.36s/it]
 97%|█████████▋| 59849/61904 [7:33:46<46:06,  1.35s/it]
 97%|█████████▋| 59850/61904 [7:33:47<47:39,  1.39s/it]
 97%|█████████▋| 59851/61904 [7:33:49<46:58,  1.37s/it]
 97%|█████████▋| 59852/61904 [7:33:50<47:27,  1.39s/it]
 97%|█████████▋| 59853/61904 [7:33:52<47:24,  1.39s/it]
 97%|█████████▋| 59854/61904 [7:33:53<47:38,  1.39s/it]
 97%|█████████▋| 59855/61904 [7:33:54<48:01,  1.41s/it]
 97%|█████████▋| 59856/61904 [7:33:56<46:28,  1.36s/it]
 97%|█████████▋| 59857/61904 [7:33:57<45:26,  1.33s/it]
 97%|█████████▋| 59858/61904 [7:33:58<46:54,  1.38s/it]
 97%|█████████▋| 59859/61904 [7:34:00<47:27,  1.39s/it]
 97%|█████████▋| 59860/61904 [7:34:01<47:01,  1.38s/it]
                                                       
{'loss': 2.3726, 'learning_rate': 1.0331258913522624e-07, 'epoch': 15.47}
+
 97%|█████████▋| 59860/61904 [7:34:01<47:01,  1.38s/it]
 97%|█████████▋| 59861/61904 [7:34:02<46:16,  1.36s/it]
 97%|█████████▋| 59862/61904 [7:34:04<46:57,  1.38s/it]
 97%|█████████▋| 59863/61904 [7:34:05<46:57,  1.38s/it]
 97%|█████████▋| 59864/61904 [7:34:07<46:03,  1.35s/it]
 97%|█████████▋| 59865/61904 [7:34:08<46:14,  1.36s/it]
 97%|█████████▋| 59866/61904 [7:34:09<46:04,  1.36s/it]
 97%|█████████▋| 59867/61904 [7:34:11<45:26,  1.34s/it]
 97%|█████████▋| 59868/61904 [7:34:12<45:04,  1.33s/it]
 97%|█████████▋| 59869/61904 [7:34:13<45:18,  1.34s/it]
 97%|█████████▋| 59870/61904 [7:34:15<46:18,  1.37s/it]
 97%|█████████▋| 59871/61904 [7:34:16<45:39,  1.35s/it]
 97%|█████████▋| 59872/61904 [7:34:17<45:28,  1.34s/it]
 97%|█████████▋| 59873/61904 [7:34:19<46:29,  1.37s/it]
 97%|█████████▋| 59874/61904 [7:34:20<46:18,  1.37s/it]
 97%|█████████▋| 59875/61904 [7:34:22<46:39,  1.38s/it]
 97%|█████████▋| 59876/61904 [7:34:23<46:18,  1.37s/it]
 97%|█████████▋| 59877/61904 [7:34:24<46:29,  1.38s/it]
 97%|█████████▋| 59878/61904 [7:34:26<47:23,  1.40s/it]
 97%|█████████▋| 59879/61904 [7:34:27<47:02,  1.39s/it]
 97%|█████████▋| 59880/61904 [7:34:29<47:33,  1.41s/it]
                                                       
{'loss': 2.4154, 'learning_rate': 1.0328017632568392e-07, 'epoch': 15.48}
+
 97%|█████████▋| 59880/61904 [7:34:29<47:33,  1.41s/it]
 97%|█████████▋| 59881/61904 [7:34:30<46:52,  1.39s/it]
 97%|█████████▋| 59882/61904 [7:34:31<46:22,  1.38s/it]
 97%|█████████▋| 59883/61904 [7:34:33<45:43,  1.36s/it]
 97%|█████████▋| 59884/61904 [7:34:34<45:19,  1.35s/it]
 97%|█████████▋| 59885/61904 [7:34:35<47:40,  1.42s/it]
 97%|█████████▋| 59886/61904 [7:34:37<47:30,  1.41s/it]
 97%|█████████▋| 59887/61904 [7:34:38<47:31,  1.41s/it]
 97%|█████████▋| 59888/61904 [7:34:40<46:59,  1.40s/it]
 97%|█████████▋| 59889/61904 [7:34:41<47:09,  1.40s/it]
 97%|█████████▋| 59890/61904 [7:34:42<46:28,  1.38s/it]
 97%|█████████▋| 59891/61904 [7:34:44<46:32,  1.39s/it]
 97%|█████████▋| 59892/61904 [7:34:45<46:51,  1.40s/it]
 97%|█████████▋| 59893/61904 [7:34:47<47:49,  1.43s/it]
 97%|█████████▋| 59894/61904 [7:34:48<48:40,  1.45s/it]
 97%|█████████▋| 59895/61904 [7:34:50<48:47,  1.46s/it]
 97%|█████████▋| 59896/61904 [7:34:51<46:57,  1.40s/it]
 97%|█████████▋| 59897/61904 [7:34:52<46:56,  1.40s/it]
 97%|█████████▋| 59898/61904 [7:34:54<46:21,  1.39s/it]
 97%|█████████▋| 59899/61904 [7:34:55<47:01,  1.41s/it]
 97%|█████████▋| 59900/61904 [7:34:56<45:36,  1.37s/it]
                                                       
{'loss': 2.41, 'learning_rate': 1.0324776351614158e-07, 'epoch': 15.48}
+
 97%|█████████▋| 59900/61904 [7:34:56<45:36,  1.37s/it]
 97%|█████████▋| 59901/61904 [7:34:58<46:19,  1.39s/it]
 97%|█████████▋| 59902/61904 [7:34:59<46:59,  1.41s/it]
 97%|█████████▋| 59903/61904 [7:35:01<45:58,  1.38s/it]
 97%|█████████▋| 59904/61904 [7:35:02<47:11,  1.42s/it]
 97%|█████████▋| 59905/61904 [7:35:03<45:51,  1.38s/it]
 97%|█████████▋| 59906/61904 [7:35:05<45:02,  1.35s/it]
 97%|█████████▋| 59907/61904 [7:35:06<45:37,  1.37s/it]
 97%|█████████▋| 59908/61904 [7:35:07<45:11,  1.36s/it]
 97%|█████████▋| 59909/61904 [7:35:09<44:39,  1.34s/it]
 97%|█████████▋| 59910/61904 [7:35:10<44:32,  1.34s/it]
 97%|█████████▋| 59911/61904 [7:35:11<44:04,  1.33s/it]
 97%|█████████▋| 59912/61904 [7:35:13<45:23,  1.37s/it]
 97%|█████████▋| 59913/61904 [7:35:14<45:56,  1.38s/it]
 97%|█████████▋| 59914/61904 [7:35:16<46:56,  1.42s/it]
 97%|█████████▋| 59915/61904 [7:35:17<46:52,  1.41s/it]
 97%|█████████▋| 59916/61904 [7:35:19<47:22,  1.43s/it]
 97%|█████████▋| 59917/61904 [7:35:20<47:42,  1.44s/it]
 97%|█████████▋| 59918/61904 [7:35:22<47:51,  1.45s/it]
 97%|█████████▋| 59919/61904 [7:35:23<45:44,  1.38s/it]
 97%|█████████▋| 59920/61904 [7:35:24<44:52,  1.36s/it]
                                                       
{'loss': 2.4175, 'learning_rate': 1.0321535070659925e-07, 'epoch': 15.49}
+
 97%|█████████▋| 59920/61904 [7:35:24<44:52,  1.36s/it]
 97%|█████████▋| 59921/61904 [7:35:25<44:41,  1.35s/it]
 97%|█████████▋| 59922/61904 [7:35:27<44:23,  1.34s/it]
 97%|█████████▋| 59923/61904 [7:35:28<44:27,  1.35s/it]
 97%|█████████▋| 59924/61904 [7:35:30<44:54,  1.36s/it]
 97%|█████████▋| 59925/61904 [7:35:31<45:03,  1.37s/it]
 97%|█████████▋| 59926/61904 [7:35:32<44:34,  1.35s/it]
 97%|█████████▋| 59927/61904 [7:35:33<43:24,  1.32s/it]
 97%|█████████▋| 59928/61904 [7:35:35<42:25,  1.29s/it]
 97%|█████████▋| 59929/61904 [7:35:36<44:29,  1.35s/it]
 97%|█████████▋| 59930/61904 [7:35:37<43:08,  1.31s/it]
 97%|█████████▋| 59931/61904 [7:35:39<42:58,  1.31s/it]
 97%|█████████▋| 59932/61904 [7:35:40<43:39,  1.33s/it]
 97%|█████████▋| 59933/61904 [7:35:41<43:05,  1.31s/it]
 97%|█████████▋| 59934/61904 [7:35:43<44:05,  1.34s/it]
 97%|█████████▋| 59935/61904 [7:35:44<44:17,  1.35s/it]
 97%|█████████▋| 59936/61904 [7:35:45<44:02,  1.34s/it]
 97%|█████████▋| 59937/61904 [7:35:47<43:16,  1.32s/it]
 97%|█████████▋| 59938/61904 [7:35:48<43:26,  1.33s/it]
 97%|█████████▋| 59939/61904 [7:35:49<43:39,  1.33s/it]
 97%|█████████▋| 59940/61904 [7:35:51<43:30,  1.33s/it]
                                                       
{'loss': 2.4498, 'learning_rate': 1.0318293789705691e-07, 'epoch': 15.49}
+
 97%|█████████▋| 59940/61904 [7:35:51<43:30,  1.33s/it]
 97%|█████████▋| 59941/61904 [7:35:52<43:29,  1.33s/it]
 97%|█████████▋| 59942/61904 [7:35:53<43:49,  1.34s/it]
 97%|█████████▋| 59943/61904 [7:35:55<44:21,  1.36s/it]
 97%|█████████▋| 59944/61904 [7:35:56<44:41,  1.37s/it]
 97%|█████████▋| 59945/61904 [7:35:58<45:12,  1.38s/it]
 97%|█████████▋| 59946/61904 [7:35:59<44:51,  1.37s/it]
 97%|█████████▋| 59947/61904 [7:36:00<45:47,  1.40s/it]
 97%|█████████▋| 59948/61904 [7:36:02<45:24,  1.39s/it]
 97%|█████████▋| 59949/61904 [7:36:03<46:03,  1.41s/it]
 97%|█████████▋| 59950/61904 [7:36:05<46:57,  1.44s/it]
 97%|█████████▋| 59951/61904 [7:36:06<45:28,  1.40s/it]
 97%|█████████▋| 59952/61904 [7:36:07<44:24,  1.37s/it]
 97%|█████████▋| 59953/61904 [7:36:09<45:52,  1.41s/it]
 97%|█████████▋| 59954/61904 [7:36:10<47:12,  1.45s/it]
 97%|█████████▋| 59955/61904 [7:36:12<46:17,  1.42s/it]
 97%|█████████▋| 59956/61904 [7:36:13<45:16,  1.39s/it]
 97%|██████��██▋| 59957/61904 [7:36:14<43:32,  1.34s/it]
 97%|█████████▋| 59958/61904 [7:36:16<45:10,  1.39s/it]
 97%|█████████▋| 59959/61904 [7:36:17<44:06,  1.36s/it]
 97%|█████████▋| 59960/61904 [7:36:19<44:21,  1.37s/it]
                                                       
{'loss': 2.4872, 'learning_rate': 1.0315052508751459e-07, 'epoch': 15.5}
+
 97%|█████████▋| 59960/61904 [7:36:19<44:21,  1.37s/it]
 97%|█████████▋| 59961/61904 [7:36:20<44:27,  1.37s/it]
 97%|█████████▋| 59962/61904 [7:36:21<44:02,  1.36s/it]
 97%|█████████▋| 59963/61904 [7:36:23<44:31,  1.38s/it]
 97%|█████████▋| 59964/61904 [7:36:24<44:30,  1.38s/it]
 97%|█████████▋| 59965/61904 [7:36:25<44:55,  1.39s/it]
 97%|█████████▋| 59966/61904 [7:36:27<44:20,  1.37s/it]
 97%|█████████▋| 59967/61904 [7:36:28<43:38,  1.35s/it]
 97%|█████████▋| 59968/61904 [7:36:30<44:20,  1.37s/it]
 97%|█████████▋| 59969/61904 [7:36:31<44:18,  1.37s/it]
 97%|█████████▋| 59970/61904 [7:36:32<43:49,  1.36s/it]
 97%|█████████▋| 59971/61904 [7:36:33<41:57,  1.30s/it]
 97%|█████████▋| 59972/61904 [7:36:35<43:35,  1.35s/it]
 97%|█████████▋| 59973/61904 [7:36:36<45:02,  1.40s/it]
 97%|█████████▋| 59974/61904 [7:36:38<44:54,  1.40s/it]
 97%|█████████▋| 59975/61904 [7:36:39<45:20,  1.41s/it]
 97%|█████████▋| 59976/61904 [7:36:41<45:14,  1.41s/it]
 97%|█████████▋| 59977/61904 [7:36:42<45:26,  1.41s/it]
 97%|█████████▋| 59978/61904 [7:36:43<44:27,  1.38s/it]
 97%|█████████▋| 59979/61904 [7:36:45<45:49,  1.43s/it]
 97%|█████████▋| 59980/61904 [7:36:46<44:35,  1.39s/it]
                                                       
{'loss': 2.3658, 'learning_rate': 1.0311811227797225e-07, 'epoch': 15.5}
+
 97%|█████████▋| 59980/61904 [7:36:46<44:35,  1.39s/it]
 97%|█████████▋| 59981/61904 [7:36:48<44:52,  1.40s/it]
 97%|█████████▋| 59982/61904 [7:36:49<45:14,  1.41s/it]
 97%|█████████▋| 59983/61904 [7:36:51<45:51,  1.43s/it]
 97%|█████████▋| 59984/61904 [7:36:52<46:40,  1.46s/it]
 97%|█████████▋| 59985/61904 [7:36:54<46:40,  1.46s/it]
 97%|█████████▋| 59986/61904 [7:36:55<47:16,  1.48s/it]
 97%|█████████▋| 59987/61904 [7:36:56<45:25,  1.42s/it]
 97%|█████████▋| 59988/61904 [7:36:58<45:09,  1.41s/it]
 97%|█████████▋| 59989/61904 [7:36:59<44:57,  1.41s/it]
 97%|█████████▋| 59990/61904 [7:37:01<45:19,  1.42s/it]
 97%|█████████▋| 59991/61904 [7:37:02<45:51,  1.44s/it]
 97%|█████████▋| 59992/61904 [7:37:04<46:16,  1.45s/it]
 97%|█████████▋| 59993/61904 [7:37:05<45:43,  1.44s/it]
 97%|█████████▋| 59994/61904 [7:37:06<46:29,  1.46s/it]
 97%|█████████▋| 59995/61904 [7:37:08<46:35,  1.46s/it]
 97%|█████████▋| 59996/61904 [7:37:09<46:14,  1.45s/it]
 97%|█████████▋| 59997/61904 [7:37:11<44:39,  1.40s/it]
 97%|█████████▋| 59998/61904 [7:37:12<43:57,  1.38s/it]
 97%|█████████▋| 59999/61904 [7:37:13<44:03,  1.39s/it]
 97%|█████████▋| 60000/61904 [7:37:15<43:07,  1.36s/it]
                                                       
{'loss': 2.4036, 'learning_rate': 1.0308569946842993e-07, 'epoch': 15.51}
+
 97%|█████████▋| 60000/61904 [7:37:15<43:07,  1.36s/it]
 97%|█████████▋| 60001/61904 [7:37:16<43:07,  1.36s/it]
 97%|█████████▋| 60002/61904 [7:37:17<42:12,  1.33s/it]
 97%|█████████▋| 60003/61904 [7:37:19<46:01,  1.45s/it]
 97%|█████████▋| 60004/61904 [7:37:21<46:16,  1.46s/it]
 97%|█████████▋| 60005/61904 [7:37:22<45:04,  1.42s/it]
 97%|█████████▋| 60006/61904 [7:37:23<44:39,  1.41s/it]
 97%|█████████▋| 60007/61904 [7:37:25<43:25,  1.37s/it]
 97%|█████████▋| 60008/61904 [7:37:26<42:20,  1.34s/it]
 97%|█████████▋| 60009/61904 [7:37:27<44:08,  1.40s/it]
 97%|█████████▋| 60010/61904 [7:37:29<44:31,  1.41s/it]
 97%|█████████▋| 60011/61904 [7:37:30<43:50,  1.39s/it]
 97%|█████████▋| 60012/61904 [7:37:32<45:33,  1.44s/it]
 97%|█████████▋| 60013/61904 [7:37:33<45:12,  1.43s/it]
 97%|█████████▋| 60014/61904 [7:37:34<43:23,  1.38s/it]
 97%|█████████▋| 60015/61904 [7:37:36<42:14,  1.34s/it]
 97%|█████████▋| 60016/61904 [7:37:37<42:35,  1.35s/it]
 97%|█████████▋| 60017/61904 [7:37:38<41:46,  1.33s/it]
 97%|█████████▋| 60018/61904 [7:37:40<42:56,  1.37s/it]
 97%|█████████▋| 60019/61904 [7:37:41<42:53,  1.37s/it]
 97%|█████████▋| 60020/61904 [7:37:43<43:48,  1.40s/it]
                                                       
{'loss': 2.4134, 'learning_rate': 1.0305328665888759e-07, 'epoch': 15.51}
+
 97%|█████████▋| 60020/61904 [7:37:43<43:48,  1.40s/it]
 97%|█████████▋| 60021/61904 [7:37:44<43:32,  1.39s/it]
 97%|█████████▋| 60022/61904 [7:37:45<44:41,  1.43s/it]
 97%|█████████▋| 60023/61904 [7:37:47<43:06,  1.37s/it]
 97%|█████████▋| 60024/61904 [7:37:48<43:48,  1.40s/it]
 97%|█████████▋| 60025/61904 [7:37:49<42:47,  1.37s/it]
 97%|█████████▋| 60026/61904 [7:37:51<43:42,  1.40s/it]
 97%|█████████▋| 60027/61904 [7:37:52<43:21,  1.39s/it]
 97%|█████████▋| 60028/61904 [7:37:54<42:19,  1.35s/it]
 97%|█████████▋| 60029/61904 [7:37:55<42:23,  1.36s/it]
 97%|█████████▋| 60030/61904 [7:37:56<41:50,  1.34s/it]
 97%|█████████▋| 60031/61904 [7:37:58<42:50,  1.37s/it]
 97%|█████████▋| 60032/61904 [7:37:59<42:52,  1.37s/it]
 97%|█████████▋| 60033/61904 [7:38:00<41:26,  1.33s/it]
 97%|█████████▋| 60034/61904 [7:38:02<41:51,  1.34s/it]
 97%|█████████▋| 60035/61904 [7:38:03<42:36,  1.37s/it]
 97%|█████████▋| 60036/61904 [7:38:04<43:02,  1.38s/it]
 97%|█████████▋| 60037/61904 [7:38:06<44:32,  1.43s/it]
 97%|█████████▋| 60038/61904 [7:38:07<44:13,  1.42s/it]
 97%|█████████▋| 60039/61904 [7:38:09<43:45,  1.41s/it]
 97%|█████████▋| 60040/61904 [7:38:10<43:34,  1.40s/it]
                                                       
{'loss': 2.4383, 'learning_rate': 1.0302087384934526e-07, 'epoch': 15.52}
+
 97%|█████████▋| 60040/61904 [7:38:10<43:34,  1.40s/it]
 97%|█████████▋| 60041/61904 [7:38:11<42:34,  1.37s/it]
 97%|█████████▋| 60042/61904 [7:38:13<43:34,  1.40s/it]
 97%|█████████▋| 60043/61904 [7:38:14<42:27,  1.37s/it]
 97%|█████████▋| 60044/61904 [7:38:16<43:06,  1.39s/it]
 97%|█████████▋| 60045/61904 [7:38:17<43:25,  1.40s/it]
 97%|█████████▋| 60046/61904 [7:38:18<42:23,  1.37s/it]
 97%|█████████▋| 60047/61904 [7:38:20<42:55,  1.39s/it]
 97%|█████████▋| 60048/61904 [7:38:21<44:12,  1.43s/it]
 97%|█████████▋| 60049/61904 [7:38:23<44:00,  1.42s/it]
 97%|█████████▋| 60050/61904 [7:38:24<43:10,  1.40s/it]
 97%|█████████▋| 60051/61904 [7:38:25<43:01,  1.39s/it]
 97%|█████████▋| 60052/61904 [7:38:27<43:41,  1.42s/it]
 97%|█████████▋| 60053/61904 [7:38:28<43:41,  1.42s/it]
 97%|█████████▋| 60054/61904 [7:38:30<44:37,  1.45s/it]
 97%|█████████▋| 60055/61904 [7:38:31<44:05,  1.43s/it]
 97%|█████████▋| 60056/61904 [7:38:33<43:13,  1.40s/it]
 97%|█████████▋| 60057/61904 [7:38:34<42:56,  1.40s/it]
 97%|█████████▋| 60058/61904 [7:38:35<43:30,  1.41s/it]
 97%|█████████▋| 60059/61904 [7:38:37<43:18,  1.41s/it]
 97%|█████████▋| 60060/61904 [7:38:38<42:37,  1.39s/it]
                                                       
{'loss': 2.3699, 'learning_rate': 1.0298846103980293e-07, 'epoch': 15.52}
+
 97%|█████████▋| 60060/61904 [7:38:38<42:37,  1.39s/it]
 97%|█████████▋| 60061/61904 [7:38:40<43:41,  1.42s/it]
 97%|█████████▋| 60062/61904 [7:38:41<42:55,  1.40s/it]
 97%|█████████▋| 60063/61904 [7:38:43<44:18,  1.44s/it]
 97%|█████████▋| 60064/61904 [7:38:44<42:33,  1.39s/it]
 97%|█████████▋| 60065/61904 [7:38:45<44:07,  1.44s/it]
 97%|█████████▋| 60066/61904 [7:38:47<43:57,  1.43s/it]
 97%|█████████▋| 60067/61904 [7:38:48<42:22,  1.38s/it]
 97%|█████████▋| 60068/61904 [7:38:50<42:41,  1.39s/it]
 97%|█████████▋| 60069/61904 [7:38:51<43:13,  1.41s/it]
 97%|█████████▋| 60070/61904 [7:38:52<42:43,  1.40s/it]
 97%|█████████▋| 60071/61904 [7:38:54<43:05,  1.41s/it]
 97%|█████████▋| 60072/61904 [7:38:55<42:35,  1.39s/it]
 97%|█████████▋| 60073/61904 [7:38:56<41:47,  1.37s/it]
 97%|█████████▋| 60074/61904 [7:38:58<42:47,  1.40s/it]
 97%|█████████▋| 60075/61904 [7:38:59<43:40,  1.43s/it]
 97%|█████████▋| 60076/61904 [7:39:01<42:53,  1.41s/it]
 97%|█████████▋| 60077/61904 [7:39:02<42:48,  1.41s/it]
 97%|█████████▋| 60078/61904 [7:39:04<42:24,  1.39s/it]
 97%|█████████▋| 60079/61904 [7:39:05<42:21,  1.39s/it]
 97%|█████████▋| 60080/61904 [7:39:06<43:25,  1.43s/it]
                                                       
{'loss': 2.3865, 'learning_rate': 1.029560482302606e-07, 'epoch': 15.53}
+
 97%|█████████▋| 60080/61904 [7:39:06<43:25,  1.43s/it]
 97%|█████████▋| 60081/61904 [7:39:08<44:46,  1.47s/it]
 97%|█████████▋| 60082/61904 [7:39:09<43:43,  1.44s/it]
 97%|█████████▋| 60083/61904 [7:39:11<43:58,  1.45s/it]
 97%|█████████▋| 60084/61904 [7:39:12<43:42,  1.44s/it]
 97%|█████████▋| 60085/61904 [7:39:14<42:36,  1.41s/it]
 97%|█████████▋| 60086/61904 [7:39:15<42:11,  1.39s/it]
 97%|█████████▋| 60087/61904 [7:39:16<42:33,  1.41s/it]
 97%|█████████▋| 60088/61904 [7:39:18<43:54,  1.45s/it]
 97%|█████████▋| 60089/61904 [7:39:19<43:37,  1.44s/it]
 97%|█████████▋| 60090/61904 [7:39:21<44:30,  1.47s/it]
 97%|█████████▋| 60091/61904 [7:39:22<43:00,  1.42s/it]
 97%|█████████▋| 60092/61904 [7:39:24<42:56,  1.42s/it]
 97%|█████████▋| 60093/61904 [7:39:25<42:55,  1.42s/it]
 97%|█████████▋| 60094/61904 [7:39:26<42:04,  1.39s/it]
 97%|█████████▋| 60095/61904 [7:39:28<42:17,  1.40s/it]
 97%|█████████▋| 60096/61904 [7:39:29<42:27,  1.41s/it]
 97%|█████████▋| 60097/61904 [7:39:31<42:07,  1.40s/it]
 97%|█████████▋| 60098/61904 [7:39:32<41:19,  1.37s/it]
 97%|█████████▋| 60099/61904 [7:39:33<41:25,  1.38s/it]
 97%|█████████▋| 60100/61904 [7:39:35<40:48,  1.36s/it]
                                                       
{'loss': 2.3725, 'learning_rate': 1.0292363542071826e-07, 'epoch': 15.53}
+
 97%|█████████▋| 60100/61904 [7:39:35<40:48,  1.36s/it]
 97%|█████████▋| 60101/61904 [7:39:36<41:12,  1.37s/it]
 97%|█████████▋| 60102/61904 [7:39:37<40:46,  1.36s/it]
 97%|█████████▋| 60103/61904 [7:39:39<42:45,  1.42s/it]
 97%|█████████▋| 60104/61904 [7:39:40<42:21,  1.41s/it]
 97%|█████████▋| 60105/61904 [7:39:42<42:00,  1.40s/it]
 97%|█████████▋| 60106/61904 [7:39:43<40:26,  1.35s/it]
 97%|█████████▋| 60107/61904 [7:39:44<40:47,  1.36s/it]
 97%|█████████▋| 60108/61904 [7:39:46<40:12,  1.34s/it]
 97%|█████████▋| 60109/61904 [7:39:47<40:43,  1.36s/it]
 97%|█████████▋| 60110/61904 [7:39:48<41:24,  1.39s/it]
 97%|█████████▋| 60111/61904 [7:39:50<41:32,  1.39s/it]
 97%|█████████▋| 60112/61904 [7:39:51<41:05,  1.38s/it]
 97%|█████████▋| 60113/61904 [7:39:53<45:49,  1.54s/it]
 97%|█████████▋| 60114/61904 [7:39:55<44:47,  1.50s/it]
 97%|█████████▋| 60115/61904 [7:39:56<43:45,  1.47s/it]
 97%|█████████▋| 60116/61904 [7:39:57<42:21,  1.42s/it]
 97%|█████████▋| 60117/61904 [7:39:59<41:47,  1.40s/it]
 97%|█████████▋| 60118/61904 [7:40:00<41:47,  1.40s/it]
 97%|█████████▋| 60119/61904 [7:40:02<43:06,  1.45s/it]
 97%|█████████▋| 60120/61904 [7:40:03<42:52,  1.44s/it]
                                                       
{'loss': 2.3363, 'learning_rate': 1.0289122261117594e-07, 'epoch': 15.54}
+
 97%|█████████▋| 60120/61904 [7:40:03<42:52,  1.44s/it]
 97%|█████████▋| 60121/61904 [7:40:04<41:39,  1.40s/it]
 97%|█████████▋| 60122/61904 [7:40:06<41:05,  1.38s/it]
 97%|█████████▋| 60123/61904 [7:40:07<40:06,  1.35s/it]
 97%|█████████▋| 60124/61904 [7:40:09<42:49,  1.44s/it]
 97%|█████████▋| 60125/61904 [7:40:10<42:08,  1.42s/it]
 97%|█████████▋| 60126/61904 [7:40:11<41:39,  1.41s/it]
 97%|█████████▋| 60127/61904 [7:40:13<42:03,  1.42s/it]
 97%|█████████▋| 60128/61904 [7:40:14<40:45,  1.38s/it]
 97%|█████████▋| 60129/61904 [7:40:16<41:54,  1.42s/it]
 97%|█████████▋| 60130/61904 [7:40:17<40:23,  1.37s/it]
 97%|█████████▋| 60131/61904 [7:40:18<40:20,  1.37s/it]
 97%|█████████▋| 60132/61904 [7:40:20<40:26,  1.37s/it]
 97%|█████████▋| 60133/61904 [7:40:21<40:31,  1.37s/it]
 97%|█████████▋| 60134/61904 [7:40:22<42:09,  1.43s/it]
 97%|█████████▋| 60135/61904 [7:40:24<41:17,  1.40s/it]
 97%|█████████▋| 60136/61904 [7:40:25<41:03,  1.39s/it]
 97%|█████████▋| 60137/61904 [7:40:27<41:22,  1.40s/it]
 97%|█████████▋| 60138/61904 [7:40:28<41:21,  1.41s/it]
 97%|█████████▋| 60139/61904 [7:40:29<41:35,  1.41s/it]
 97%|█████████▋| 60140/61904 [7:40:31<41:37,  1.42s/it]
                                                       
{'loss': 2.3921, 'learning_rate': 1.028588098016336e-07, 'epoch': 15.54}
+
 97%|█████████▋| 60140/61904 [7:40:31<41:37,  1.42s/it]
 97%|█████████▋| 60141/61904 [7:40:32<40:57,  1.39s/it]
 97%|█████████▋| 60142/61904 [7:40:34<40:13,  1.37s/it]
 97%|█████████▋| 60143/61904 [7:40:35<42:09,  1.44s/it]
 97%|█████████▋| 60144/61904 [7:40:36<41:08,  1.40s/it]
 97%|█████████▋| 60145/61904 [7:40:38<41:31,  1.42s/it]
 97%|█████████▋| 60146/61904 [7:40:39<40:05,  1.37s/it]
 97%|█████████▋| 60147/61904 [7:40:41<40:13,  1.37s/it]
 97%|█████████▋| 60148/61904 [7:40:42<41:23,  1.41s/it]
 97%|█████████▋| 60149/61904 [7:40:43<39:49,  1.36s/it]
 97%|█████████▋| 60150/61904 [7:40:45<41:10,  1.41s/it]
 97%|█████████▋| 60151/61904 [7:40:46<40:00,  1.37s/it]
 97%|█████████▋| 60152/61904 [7:40:47<39:24,  1.35s/it]
 97%|█████████▋| 60153/61904 [7:40:49<41:03,  1.41s/it]
 97%|█████████▋| 60154/61904 [7:40:50<39:43,  1.36s/it]
 97%|█████████▋| 60155/61904 [7:40:52<40:02,  1.37s/it]
 97%|█████████▋| 60156/61904 [7:40:53<39:31,  1.36s/it]
 97%|█████████▋| 60157/61904 [7:40:54<39:17,  1.35s/it]
 97%|█████████▋| 60158/61904 [7:40:56<38:46,  1.33s/it]
 97%|█████████▋| 60159/61904 [7:40:57<38:27,  1.32s/it]
 97%|█████████▋| 60160/61904 [7:40:58<38:34,  1.33s/it]
                                                       
{'loss': 2.4028, 'learning_rate': 1.0282639699209127e-07, 'epoch': 15.55}
+
 97%|█████████▋| 60160/61904 [7:40:58<38:34,  1.33s/it]
 97%|█████████▋| 60161/61904 [7:41:00<40:10,  1.38s/it]
 97%|█████████▋| 60162/61904 [7:41:01<40:15,  1.39s/it]
 97%|█████████▋| 60163/61904 [7:41:02<38:49,  1.34s/it]
 97%|█████████▋| 60164/61904 [7:41:04<38:53,  1.34s/it]
 97%|█████████▋| 60165/61904 [7:41:05<39:14,  1.35s/it]
 97%|█████████▋| 60166/61904 [7:41:06<38:56,  1.34s/it]
 97%|█████████▋| 60167/61904 [7:41:08<40:18,  1.39s/it]
 97%|█████████▋| 60168/61904 [7:41:09<39:23,  1.36s/it]
 97%|█████████▋| 60169/61904 [7:41:11<39:46,  1.38s/it]
 97%|█████████▋| 60170/61904 [7:41:12<39:15,  1.36s/it]
 97%|█████████▋| 60171/61904 [7:41:13<39:12,  1.36s/it]
 97%|█████████▋| 60172/61904 [7:41:15<38:37,  1.34s/it]
 97%|█████████▋| 60173/61904 [7:41:16<41:30,  1.44s/it]
 97%|█████████▋| 60174/61904 [7:41:17<40:18,  1.40s/it]
 97%|█████████▋| 60175/61904 [7:41:19<40:16,  1.40s/it]
 97%|█████████▋| 60176/61904 [7:41:20<40:10,  1.39s/it]
 97%|█████████▋| 60177/61904 [7:41:22<40:26,  1.41s/it]
 97%|█████████▋| 60178/61904 [7:41:23<40:13,  1.40s/it]
 97%|█████████▋| 60179/61904 [7:41:25<41:48,  1.45s/it]
 97%|█████████▋| 60180/61904 [7:41:26<41:01,  1.43s/it]
                                                       
{'loss': 2.4546, 'learning_rate': 1.0279398418254894e-07, 'epoch': 15.55}
+
 97%|█████████▋| 60180/61904 [7:41:26<41:01,  1.43s/it]
 97%|█████████▋| 60181/61904 [7:41:27<39:45,  1.38s/it]
 97%|█████████▋| 60182/61904 [7:41:29<40:53,  1.42s/it]
 97%|█████████▋| 60183/61904 [7:41:30<40:16,  1.40s/it]
 97%|█████████▋| 60184/61904 [7:41:32<41:15,  1.44s/it]
 97%|█████████▋| 60185/61904 [7:41:33<40:13,  1.40s/it]
 97%|█████████▋| 60186/61904 [7:41:34<40:06,  1.40s/it]
 97%|█████████▋| 60187/61904 [7:41:36<39:25,  1.38s/it]
 97%|█████████▋| 60188/61904 [7:41:37<39:05,  1.37s/it]
 97%|█████████▋| 60189/61904 [7:41:39<39:59,  1.40s/it]
 97%|█████████▋| 60190/61904 [7:41:40<39:26,  1.38s/it]
 97%|█████████▋| 60191/61904 [7:41:41<39:12,  1.37s/it]
 97%|█████████▋| 60192/61904 [7:41:43<39:01,  1.37s/it]
 97%|█████████▋| 60193/61904 [7:41:44<38:36,  1.35s/it]
 97%|█████████▋| 60194/61904 [7:41:45<37:29,  1.32s/it]
 97%|█████████▋| 60195/61904 [7:41:47<37:44,  1.33s/it]
 97%|█████████▋| 60196/61904 [7:41:48<37:10,  1.31s/it]
 97%|█████████▋| 60197/61904 [7:41:49<36:58,  1.30s/it]
 97%|█████████▋| 60198/61904 [7:41:50<37:13,  1.31s/it]
 97%|█████████▋| 60199/61904 [7:41:52<38:29,  1.35s/it]
 97%|█████████▋| 60200/61904 [7:41:53<40:22,  1.42s/it]
                                                       
{'loss': 2.3757, 'learning_rate': 1.0276157137300661e-07, 'epoch': 15.56}
+
 97%|█████████▋| 60200/61904 [7:41:53<40:22,  1.42s/it]
 97%|█████████▋| 60201/61904 [7:41:55<40:07,  1.41s/it]
 97%|█████████▋| 60202/61904 [7:41:56<39:04,  1.38s/it]
 97%|█████████▋| 60203/61904 [7:41:57<38:18,  1.35s/it]
 97%|█████████▋| 60204/61904 [7:41:59<38:12,  1.35s/it]
 97%|█████████▋| 60205/61904 [7:42:00<37:55,  1.34s/it]
 97%|█████████▋| 60206/61904 [7:42:01<37:27,  1.32s/it]
 97%|█████████▋| 60207/61904 [7:42:03<37:45,  1.34s/it]
 97%|█████████▋| 60208/61904 [7:42:04<40:47,  1.44s/it]
 97%|█████████▋| 60209/61904 [7:42:06<40:12,  1.42s/it]
 97%|█████████▋| 60210/61904 [7:42:07<40:14,  1.43s/it]
 97%|█████████▋| 60211/61904 [7:42:09<40:03,  1.42s/it]
 97%|█████████▋| 60212/61904 [7:42:10<39:31,  1.40s/it]
 97%|█████████▋| 60213/61904 [7:42:11<38:59,  1.38s/it]
 97%|█████████▋| 60214/61904 [7:42:13<38:27,  1.37s/it]
 97%|█████████▋| 60215/61904 [7:42:14<39:21,  1.40s/it]
 97%|█████████▋| 60216/61904 [7:42:16<41:16,  1.47s/it]
 97%|█████████▋| 60217/61904 [7:42:17<40:33,  1.44s/it]
 97%|█████████▋| 60218/61904 [7:42:19<40:42,  1.45s/it]
 97%|█████████▋| 60219/61904 [7:42:20<39:29,  1.41s/it]
 97%|█████████▋| 60220/61904 [7:42:21<40:15,  1.43s/it]
                                                       
{'loss': 2.3857, 'learning_rate': 1.0272915856346427e-07, 'epoch': 15.56}
+
 97%|█████████▋| 60220/61904 [7:42:21<40:15,  1.43s/it]
 97%|█████████▋| 60221/61904 [7:42:23<40:08,  1.43s/it]
 97%|█████████▋| 60222/61904 [7:42:24<40:14,  1.44s/it]
 97%|█████████▋| 60223/61904 [7:42:26<40:17,  1.44s/it]
 97%|█████████▋| 60224/61904 [7:42:27<40:31,  1.45s/it]
 97%|█████████▋| 60225/61904 [7:42:29<40:46,  1.46s/it]
 97%|█████████▋| 60226/61904 [7:42:30<41:25,  1.48s/it]
 97%|█████████▋| 60227/61904 [7:42:32<41:46,  1.49s/it]
 97%|█████████▋| 60228/61904 [7:42:33<41:45,  1.50s/it]
 97%|█████████▋| 60229/61904 [7:42:35<40:08,  1.44s/it]
 97%|█████████▋| 60230/61904 [7:42:36<39:35,  1.42s/it]
 97%|█████████▋| 60231/61904 [7:42:37<38:56,  1.40s/it]
 97%|█████████▋| 60232/61904 [7:42:39<39:02,  1.40s/it]
 97%|█████████▋| 60233/61904 [7:42:40<39:33,  1.42s/it]
 97%|█████████▋| 60234/61904 [7:42:41<38:30,  1.38s/it]
 97%|█████████▋| 60235/61904 [7:42:43<37:30,  1.35s/it]
 97%|█████████▋| 60236/61904 [7:42:44<36:47,  1.32s/it]
 97%|█████████▋| 60237/61904 [7:42:45<38:03,  1.37s/it]
 97%|█████████▋| 60238/61904 [7:42:47<37:26,  1.35s/it]
 97%|█████████▋| 60239/61904 [7:42:48<37:02,  1.33s/it]
 97%|█████████▋| 60240/61904 [7:42:49<37:48,  1.36s/it]
                                                       
{'loss': 2.4224, 'learning_rate': 1.0269674575392195e-07, 'epoch': 15.57}
+
 97%|█████████▋| 60240/61904 [7:42:49<37:48,  1.36s/it]
 97%|█████████▋| 60241/61904 [7:42:51<38:08,  1.38s/it]
 97%|█████████▋| 60242/61904 [7:42:52<38:12,  1.38s/it]
 97%|█████████▋| 60243/61904 [7:42:54<40:11,  1.45s/it]
 97%|█████████▋| 60244/61904 [7:42:56<41:42,  1.51s/it]
 97%|█████████▋| 60245/61904 [7:42:57<41:01,  1.48s/it]
 97%|█████████▋| 60246/61904 [7:42:59<41:55,  1.52s/it]
 97%|█████████▋| 60247/61904 [7:43:00<41:23,  1.50s/it]
 97%|█████████▋| 60248/61904 [7:43:01<39:30,  1.43s/it]
 97%|█████████▋| 60249/61904 [7:43:03<39:01,  1.41s/it]
 97%|█████████▋| 60250/61904 [7:43:04<37:54,  1.38s/it]
 97%|█████████▋| 60251/61904 [7:43:05<37:09,  1.35s/it]
 97%|█████████▋| 60252/61904 [7:43:07<36:56,  1.34s/it]
 97%|██��██████▋| 60253/61904 [7:43:08<37:58,  1.38s/it]
 97%|█████████▋| 60254/61904 [7:43:09<38:12,  1.39s/it]
 97%|█████████▋| 60255/61904 [7:43:11<37:24,  1.36s/it]
 97%|█████████▋| 60256/61904 [7:43:12<37:27,  1.36s/it]
 97%|█████████▋| 60257/61904 [7:43:13<36:52,  1.34s/it]
 97%|█████████▋| 60258/61904 [7:43:15<37:46,  1.38s/it]
 97%|█████████▋| 60259/61904 [7:43:16<38:41,  1.41s/it]
 97%|█████████▋| 60260/61904 [7:43:18<38:48,  1.42s/it]
                                                       
{'loss': 2.4753, 'learning_rate': 1.0266433294437962e-07, 'epoch': 15.57}
+
 97%|█████████▋| 60260/61904 [7:43:18<38:48,  1.42s/it]
 97%|█████████▋| 60261/61904 [7:43:19<37:53,  1.38s/it]
 97%|█████████▋| 60262/61904 [7:43:21<38:47,  1.42s/it]
 97%|█████████▋| 60263/61904 [7:43:22<37:06,  1.36s/it]
 97%|█████████▋| 60264/61904 [7:43:23<38:06,  1.39s/it]
 97%|█████████▋| 60265/61904 [7:43:25<37:30,  1.37s/it]
 97%|█████████▋| 60266/61904 [7:43:26<36:58,  1.35s/it]
 97%|█████████▋| 60267/61904 [7:43:27<37:19,  1.37s/it]
 97%|█████████▋| 60268/61904 [7:43:29<37:39,  1.38s/it]
 97%|█████████▋| 60269/61904 [7:43:30<37:15,  1.37s/it]
 97%|█████████▋| 60270/61904 [7:43:32<38:53,  1.43s/it]
 97%|█████████▋| 60271/61904 [7:43:33<37:58,  1.40s/it]
 97%|█████████▋| 60272/61904 [7:43:34<38:18,  1.41s/it]
 97%|█████████▋| 60273/61904 [7:43:36<38:54,  1.43s/it]
 97%|█████████▋| 60274/61904 [7:43:37<38:33,  1.42s/it]
 97%|█████████▋| 60275/61904 [7:43:39<38:52,  1.43s/it]
 97%|█████████▋| 60276/61904 [7:43:40<38:23,  1.42s/it]
 97%|█████████▋| 60277/61904 [7:43:41<37:12,  1.37s/it]
 97%|█████████▋| 60278/61904 [7:43:43<37:02,  1.37s/it]
 97%|█████████▋| 60279/61904 [7:43:44<39:29,  1.46s/it]
 97%|█████████▋| 60280/61904 [7:43:46<38:38,  1.43s/it]
                                                       
{'loss': 2.3691, 'learning_rate': 1.0263192013483729e-07, 'epoch': 15.58}
+
 97%|█████████▋| 60280/61904 [7:43:46<38:38,  1.43s/it]
 97%|█████████▋| 60281/61904 [7:43:47<37:35,  1.39s/it]
 97%|█████████▋| 60282/61904 [7:43:49<39:59,  1.48s/it]
 97%|█████████▋| 60283/61904 [7:43:50<40:04,  1.48s/it]
 97%|█████████▋| 60284/61904 [7:43:52<41:06,  1.52s/it]
 97%|█████████▋| 60285/61904 [7:43:53<39:32,  1.47s/it]
 97%|█████████▋| 60286/61904 [7:43:55<39:25,  1.46s/it]
 97%|█████████▋| 60287/61904 [7:43:56<38:54,  1.44s/it]
 97%|█████████▋| 60288/61904 [7:43:58<40:12,  1.49s/it]
 97%|█████████▋| 60289/61904 [7:43:59<39:06,  1.45s/it]
 97%|█████████▋| 60290/61904 [7:44:01<39:40,  1.48s/it]
 97%|█████████▋| 60291/61904 [7:44:02<39:20,  1.46s/it]
 97%|█████████▋| 60292/61904 [7:44:03<39:05,  1.46s/it]
 97%|█████████▋| 60293/61904 [7:44:05<39:46,  1.48s/it]
 97%|█████████▋| 60294/61904 [7:44:06<39:54,  1.49s/it]
 97%|█████████▋| 60295/61904 [7:44:08<38:47,  1.45s/it]
 97%|█████████▋| 60296/61904 [7:44:09<38:43,  1.45s/it]
 97%|█████████▋| 60297/61904 [7:44:11<39:20,  1.47s/it]
 97%|█████████▋| 60298/61904 [7:44:12<38:10,  1.43s/it]
 97%|█████████▋| 60299/61904 [7:44:14<40:29,  1.51s/it]
 97%|█████████▋| 60300/61904 [7:44:15<39:56,  1.49s/it]
                                                       
{'loss': 2.363, 'learning_rate': 1.0259950732529495e-07, 'epoch': 15.58}
+
 97%|█████████▋| 60300/61904 [7:44:15<39:56,  1.49s/it]
 97%|█████████▋| 60301/61904 [7:44:17<38:18,  1.43s/it]
 97%|█████████▋| 60302/61904 [7:44:18<38:06,  1.43s/it]
 97%|█████████▋| 60303/61904 [7:44:19<38:51,  1.46s/it]
 97%|█████████▋| 60304/61904 [7:44:21<37:48,  1.42s/it]
 97%|█████████▋| 60305/61904 [7:44:22<37:00,  1.39s/it]
 97%|█████████▋| 60306/61904 [7:44:23<36:05,  1.36s/it]
 97%|█████████▋| 60307/61904 [7:44:25<37:13,  1.40s/it]
 97%|█████████▋| 60308/61904 [7:44:26<37:52,  1.42s/it]
 97%|█████████▋| 60309/61904 [7:44:28<38:15,  1.44s/it]
 97%|█████████▋| 60310/61904 [7:44:30<40:14,  1.51s/it]
 97%|█████████▋| 60311/61904 [7:44:31<38:17,  1.44s/it]
 97%|█████████▋| 60312/61904 [7:44:32<38:01,  1.43s/it]
 97%|█████████▋| 60313/61904 [7:44:34<36:55,  1.39s/it]
 97%|█████████▋| 60314/61904 [7:44:35<36:22,  1.37s/it]
 97%|█████████▋| 60315/61904 [7:44:36<37:11,  1.40s/it]
 97%|█████████▋| 60316/61904 [7:44:38<36:45,  1.39s/it]
 97%|█████████▋| 60317/61904 [7:44:39<36:34,  1.38s/it]
 97%|█████████▋| 60318/61904 [7:44:40<36:47,  1.39s/it]
 97%|█████████▋| 60319/61904 [7:44:42<39:53,  1.51s/it]
 97%|█████████▋| 60320/61904 [7:44:44<39:03,  1.48s/it]
                                                       
{'loss': 2.4099, 'learning_rate': 1.0256709451575262e-07, 'epoch': 15.59}
+
 97%|█████████▋| 60320/61904 [7:44:44<39:03,  1.48s/it]
 97%|█████████▋| 60321/61904 [7:44:45<38:27,  1.46s/it]
 97%|█████████▋| 60322/61904 [7:44:47<38:51,  1.47s/it]
 97%|█████████▋| 60323/61904 [7:44:48<40:32,  1.54s/it]
 97%|█████████▋| 60324/61904 [7:44:50<39:11,  1.49s/it]
 97%|█████████▋| 60325/61904 [7:44:51<38:39,  1.47s/it]
 97%|█████████▋| 60326/61904 [7:44:53<38:58,  1.48s/it]
 97%|█████████▋| 60327/61904 [7:44:54<37:51,  1.44s/it]
 97%|█████████▋| 60328/61904 [7:44:55<37:41,  1.43s/it]
 97%|█████████▋| 60329/61904 [7:44:57<36:13,  1.38s/it]
 97%|█████████▋| 60330/61904 [7:44:58<35:53,  1.37s/it]
 97%|█████████▋| 60331/61904 [7:44:59<36:13,  1.38s/it]
 97%|█████████▋| 60332/61904 [7:45:01<36:13,  1.38s/it]
 97%|█████████▋| 60333/61904 [7:45:02<36:12,  1.38s/it]
 97%|█████████▋| 60334/61904 [7:45:03<35:43,  1.37s/it]
 97%|█████████▋| 60335/61904 [7:45:05<34:59,  1.34s/it]
 97%|█████████▋| 60336/61904 [7:45:06<35:11,  1.35s/it]
 97%|█████████▋| 60337/61904 [7:45:07<35:25,  1.36s/it]
 97%|█████████▋| 60338/61904 [7:45:09<35:27,  1.36s/it]
 97%|█████████▋| 60339/61904 [7:45:10<35:54,  1.38s/it]
 97%|█████████▋| 60340/61904 [7:45:12<36:08,  1.39s/it]
                                                       
{'loss': 2.4276, 'learning_rate': 1.025346817062103e-07, 'epoch': 15.6}
+
 97%|█████████▋| 60340/61904 [7:45:12<36:08,  1.39s/it]
 97%|█████████▋| 60341/61904 [7:45:13<35:12,  1.35s/it]
 97%|█████████▋| 60342/61904 [7:45:14<35:34,  1.37s/it]
 97%|█████████▋| 60343/61904 [7:45:16<34:55,  1.34s/it]
 97%|█████████▋| 60344/61904 [7:45:17<35:49,  1.38s/it]
 97%|█████████▋| 60345/61904 [7:45:18<35:27,  1.36s/it]
 97%|█████████▋| 60346/61904 [7:45:20<36:42,  1.41s/it]
 97%|█████████▋| 60347/61904 [7:45:21<36:44,  1.42s/it]
 97%|█████████▋| 60348/61904 [7:45:23<36:23,  1.40s/it]
 97%|█████████▋| 60349/61904 [7:45:24<37:35,  1.45s/it]
 97%|█████████▋| 60350/61904 [7:45:26<36:58,  1.43s/it]
 97%|█████████▋| 60351/61904 [7:45:27<36:12,  1.40s/it]
 97%|█████████▋| 60352/61904 [7:45:28<36:37,  1.42s/it]
 97%|█████████▋| 60353/61904 [7:45:30<35:39,  1.38s/it]
 97%|█████████▋| 60354/61904 [7:45:31<35:16,  1.37s/it]
 97%|█████████▋| 60355/61904 [7:45:32<34:16,  1.33s/it]
 97%|█████████▋| 60356/61904 [7:45:34<34:01,  1.32s/it]
 98%|█████████▊| 60357/61904 [7:45:35<35:34,  1.38s/it]
 98%|█████████▊| 60358/61904 [7:45:37<36:15,  1.41s/it]
 98%|█████████▊| 60359/61904 [7:45:38<36:05,  1.40s/it]
 98%|█████████▊| 60360/61904 [7:45:39<35:40,  1.39s/it]
                                                       
{'loss': 2.4374, 'learning_rate': 1.0250226889666796e-07, 'epoch': 15.6}
+
 98%|█████████▊| 60360/61904 [7:45:39<35:40,  1.39s/it]
 98%|█████████▊| 60361/61904 [7:45:41<36:35,  1.42s/it]
 98%|█████████▊| 60362/61904 [7:45:42<35:40,  1.39s/it]
 98%|█████████▊| 60363/61904 [7:45:43<35:13,  1.37s/it]
 98%|█████████▊| 60364/61904 [7:45:45<35:05,  1.37s/it]
 98%|█████████▊| 60365/61904 [7:45:46<35:18,  1.38s/it]
 98%|█████████▊| 60366/61904 [7:45:48<35:17,  1.38s/it]
 98%|█████████▊| 60367/61904 [7:45:49<35:12,  1.37s/it]
 98%|█████████▊| 60368/61904 [7:45:50<34:51,  1.36s/it]
 98%|█████████▊| 60369/61904 [7:45:52<36:33,  1.43s/it]
 98%|█████████▊| 60370/61904 [7:45:53<36:04,  1.41s/it]
 98%|█████████▊| 60371/61904 [7:45:55<37:47,  1.48s/it]
 98%|█████████▊| 60372/61904 [7:45:56<36:52,  1.44s/it]
 98%|█████████▊| 60373/61904 [7:45:58<35:46,  1.40s/it]
 98%|█████████▊| 60374/61904 [7:45:59<34:50,  1.37s/it]
 98%|█████████▊| 60375/61904 [7:46:00<34:50,  1.37s/it]
 98%|█████████▊| 60376/61904 [7:46:02<35:20,  1.39s/it]
 98%|█████████▊| 60377/61904 [7:46:03<35:34,  1.40s/it]
 98%|█████████▊| 60378/61904 [7:46:04<35:31,  1.40s/it]
 98%|█████████▊| 60379/61904 [7:46:06<35:57,  1.41s/it]
 98%|█████████▊| 60380/61904 [7:46:07<34:40,  1.36s/it]
                                                       
{'loss': 2.426, 'learning_rate': 1.0246985608712562e-07, 'epoch': 15.61}
+
 98%|█████████▊| 60380/61904 [7:46:07<34:40,  1.36s/it]
 98%|█████████▊| 60381/61904 [7:46:08<33:58,  1.34s/it]
 98%|█████████▊| 60382/61904 [7:46:10<35:58,  1.42s/it]
 98%|█████████▊| 60383/61904 [7:46:11<35:16,  1.39s/it]
 98%|█████████▊| 60384/61904 [7:46:13<35:11,  1.39s/it]
 98%|█████████▊| 60385/61904 [7:46:14<35:03,  1.38s/it]
 98%|█████████▊| 60386/61904 [7:46:15<34:05,  1.35s/it]
 98%|█████████▊| 60387/61904 [7:46:17<34:19,  1.36s/it]
 98%|█████████▊| 60388/61904 [7:46:18<35:08,  1.39s/it]
 98%|█████████▊| 60389/61904 [7:46:20<35:59,  1.43s/it]
 98%|█████████▊| 60390/61904 [7:46:21<34:59,  1.39s/it]
 98%|█████████▊| 60391/61904 [7:46:23<36:23,  1.44s/it]
 98%|█████████▊| 60392/61904 [7:46:24<36:24,  1.44s/it]
 98%|█████████▊| 60393/61904 [7:46:25<35:30,  1.41s/it]
 98%|█████████▊| 60394/61904 [7:46:27<35:06,  1.39s/it]
 98%|█████████▊| 60395/61904 [7:46:28<35:35,  1.41s/it]
 98%|█████████▊| 60396/61904 [7:46:30<35:39,  1.42s/it]
 98%|█████████▊| 60397/61904 [7:46:31<35:32,  1.42s/it]
 98%|█████████▊| 60398/61904 [7:46:32<34:57,  1.39s/it]
 98%|█████████▊| 60399/61904 [7:46:34<35:10,  1.40s/it]
 98%|█████████▊| 60400/61904 [7:46:35<34:44,  1.39s/it]
                                                       
{'loss': 2.4147, 'learning_rate': 1.024374432775833e-07, 'epoch': 15.61}
+
 98%|█████████▊| 60400/61904 [7:46:35<34:44,  1.39s/it]
 98%|█████████▊| 60401/61904 [7:46:37<34:11,  1.37s/it]
 98%|█████████▊| 60402/61904 [7:46:38<34:36,  1.38s/it]
 98%|█████████▊| 60403/61904 [7:46:39<34:21,  1.37s/it]
 98%|█████████▊| 60404/61904 [7:46:41<33:52,  1.35s/it]
 98%|█████████▊| 60405/61904 [7:46:42<34:16,  1.37s/it]
 98%|█████████▊| 60406/61904 [7:46:43<34:23,  1.38s/it]
 98%|█████████▊| 60407/61904 [7:46:45<33:22,  1.34s/it]
 98%|█████████▊| 60408/61904 [7:46:46<33:43,  1.35s/it]
 98%|█████████▊| 60409/61904 [7:46:47<32:52,  1.32s/it]
 98%|█████████▊| 60410/61904 [7:46:49<33:46,  1.36s/it]
 98%|█████████▊| 60411/61904 [7:46:50<34:06,  1.37s/it]
 98%|█████████▊| 60412/61904 [7:46:51<33:11,  1.33s/it]
 98%|█████████▊| 60413/61904 [7:46:53<34:04,  1.37s/it]
 98%|█████████▊| 60414/61904 [7:46:54<33:34,  1.35s/it]
 98%|█████████▊| 60415/61904 [7:46:56<34:28,  1.39s/it]
 98%|█████████▊| 60416/61904 [7:46:57<34:31,  1.39s/it]
 98%|█████████▊| 60417/61904 [7:46:58<33:49,  1.37s/it]
 98%|█████████▊| 60418/61904 [7:47:00<33:46,  1.36s/it]
 98%|█████████▊| 60419/61904 [7:47:01<35:07,  1.42s/it]
 98%|█████████▊| 60420/61904 [7:47:03<35:02,  1.42s/it]
                                                       
{'loss': 2.4362, 'learning_rate': 1.0240503046804097e-07, 'epoch': 15.62}
+
 98%|█████████▊| 60420/61904 [7:47:03<35:02,  1.42s/it]
 98%|█████████▊| 60421/61904 [7:47:04<34:38,  1.40s/it]
 98%|█████████▊| 60422/61904 [7:47:05<34:04,  1.38s/it]
 98%|█████████▊| 60423/61904 [7:47:07<35:30,  1.44s/it]
 98%|█████████▊| 60424/61904 [7:47:08<35:49,  1.45s/it]
 98%|█████████▊| 60425/61904 [7:47:10<34:53,  1.42s/it]
 98%|█████████▊| 60426/61904 [7:47:11<34:19,  1.39s/it]
 98%|█████████▊| 60427/61904 [7:47:12<33:56,  1.38s/it]
 98%|█████████▊| 60428/61904 [7:47:14<32:54,  1.34s/it]
 98%|█████████▊| 60429/61904 [7:47:15<32:29,  1.32s/it]
 98%|█████████▊| 60430/61904 [7:47:16<32:19,  1.32s/it]
 98%|█████████▊| 60431/61904 [7:47:18<32:41,  1.33s/it]
 98%|█████████▊| 60432/61904 [7:47:19<32:59,  1.34s/it]
 98%|█████████▊| 60433/61904 [7:47:20<33:58,  1.39s/it]
 98%|█████████▊| 60434/61904 [7:47:22<33:09,  1.35s/it]
 98%|█████████▊| 60435/61904 [7:47:23<34:11,  1.40s/it]
 98%|█████████▊| 60436/61904 [7:47:25<34:16,  1.40s/it]
 98%|█████████▊| 60437/61904 [7:47:26<34:08,  1.40s/it]
 98%|█████████▊| 60438/61904 [7:47:27<33:11,  1.36s/it]
 98%|█████████▊| 60439/61904 [7:47:29<34:39,  1.42s/it]
 98%|█████████▊| 60440/61904 [7:47:30<33:47,  1.38s/it]
                                                       
{'loss': 2.4182, 'learning_rate': 1.0237261765849863e-07, 'epoch': 15.62}
+
 98%|█████████▊| 60440/61904 [7:47:30<33:47,  1.38s/it]
 98%|█████████▊| 60441/61904 [7:47:32<34:04,  1.40s/it]
 98%|█████████▊| 60442/61904 [7:47:33<34:28,  1.42s/it]
 98%|█████████▊| 60443/61904 [7:47:35<35:02,  1.44s/it]
 98%|█████████▊| 60444/61904 [7:47:36<33:53,  1.39s/it]
 98%|█████████▊| 60445/61904 [7:47:37<34:08,  1.40s/it]
 98%|█████████▊| 60446/61904 [7:47:39<33:26,  1.38s/it]
 98%|█████████▊| 60447/61904 [7:47:40<32:48,  1.35s/it]
 98%|█████████▊| 60448/61904 [7:47:41<32:49,  1.35s/it]
 98%|█████████▊| 60449/61904 [7:47:43<32:54,  1.36s/it]
 98%|█████████▊| 60450/61904 [7:47:44<32:57,  1.36s/it]
 98%|█████████▊| 60451/61904 [7:47:45<33:16,  1.37s/it]
 98%|█████████▊| 60452/61904 [7:47:47<32:57,  1.36s/it]
 98%|█████████▊| 60453/61904 [7:47:48<33:43,  1.39s/it]
 98%|█████████▊| 60454/61904 [7:47:50<33:58,  1.41s/it]
 98%|█████████▊| 60455/61904 [7:47:51<33:46,  1.40s/it]
 98%|█████████▊| 60456/61904 [7:47:52<33:34,  1.39s/it]
 98%|█████████▊| 60457/61904 [7:47:54<32:57,  1.37s/it]
 98%|█████████▊| 60458/61904 [7:47:55<32:59,  1.37s/it]
 98%|█████████▊| 60459/61904 [7:47:56<32:41,  1.36s/it]
 98%|█████████▊| 60460/61904 [7:47:58<32:27,  1.35s/it]
                                                       
{'loss': 2.389, 'learning_rate': 1.023402048489563e-07, 'epoch': 15.63}
+
 98%|█████████▊| 60460/61904 [7:47:58<32:27,  1.35s/it]
 98%|█████████▊| 60461/61904 [7:47:59<32:31,  1.35s/it]
 98%|█████████▊| 60462/61904 [7:48:01<33:10,  1.38s/it]
 98%|█████████▊| 60463/61904 [7:48:02<33:14,  1.38s/it]
 98%|█████████▊| 60464/61904 [7:48:03<33:46,  1.41s/it]
 98%|█████████▊| 60465/61904 [7:48:05<34:40,  1.45s/it]
 98%|█████████▊| 60466/61904 [7:48:07<36:28,  1.52s/it]
 98%|█████████▊| 60467/61904 [7:48:08<35:37,  1.49s/it]
 98%|█████████▊| 60468/61904 [7:48:09<34:54,  1.46s/it]
 98%|█████████▊| 60469/61904 [7:48:11<34:20,  1.44s/it]
 98%|█████████▊| 60470/61904 [7:48:12<33:57,  1.42s/it]
 98%|█████████▊| 60471/61904 [7:48:14<33:30,  1.40s/it]
 98%|█████████▊| 60472/61904 [7:48:15<33:04,  1.39s/it]
 98%|█████████▊| 60473/61904 [7:48:16<33:25,  1.40s/it]
 98%|█████████▊| 60474/61904 [7:48:18<33:09,  1.39s/it]
 98%|█████████▊| 60475/61904 [7:48:19<33:31,  1.41s/it]
 98%|█████████▊| 60476/61904 [7:48:21<34:36,  1.45s/it]
 98%|█████████▊| 60477/61904 [7:48:22<34:07,  1.44s/it]
 98%|█████████▊| 60478/61904 [7:48:24<34:30,  1.45s/it]
 98%|█████████▊| 60479/61904 [7:48:25<33:41,  1.42s/it]
 98%|█████████▊| 60480/61904 [7:48:26<32:58,  1.39s/it]
                                                       
{'loss': 2.4295, 'learning_rate': 1.0230779203941397e-07, 'epoch': 15.63}
+
 98%|█████████▊| 60480/61904 [7:48:26<32:58,  1.39s/it]
 98%|█████████▊| 60481/61904 [7:48:28<32:25,  1.37s/it]
 98%|█████████▊| 60482/61904 [7:48:29<32:46,  1.38s/it]
 98%|█████████▊| 60483/61904 [7:48:30<32:32,  1.37s/it]
 98%|█████████▊| 60484/61904 [7:48:32<32:26,  1.37s/it]
 98%|█████████▊| 60485/61904 [7:48:33<32:18,  1.37s/it]
 98%|█████████▊| 60486/61904 [7:48:34<32:12,  1.36s/it]
 98%|█████████▊| 60487/61904 [7:48:36<31:50,  1.35s/it]
 98%|█████████▊| 60488/61904 [7:48:37<31:41,  1.34s/it]
 98%|█████████▊| 60489/61904 [7:48:39<32:36,  1.38s/it]
 98%|█████████▊| 60490/61904 [7:48:40<31:44,  1.35s/it]
 98%|█████████▊| 60491/61904 [7:48:41<32:03,  1.36s/it]
 98%|█████████▊| 60492/61904 [7:48:43<32:46,  1.39s/it]
 98%|█████████▊| 60493/61904 [7:48:44<33:27,  1.42s/it]
 98%|█████████▊| 60494/61904 [7:48:46<33:12,  1.41s/it]
 98%|█████████▊| 60495/61904 [7:48:47<33:01,  1.41s/it]
 98%|█████████▊| 60496/61904 [7:48:48<32:25,  1.38s/it]
 98%|█████████▊| 60497/61904 [7:48:50<31:48,  1.36s/it]
 98%|█████████▊| 60498/61904 [7:48:51<31:49,  1.36s/it]
 98%|█████████▊| 60499/61904 [7:48:52<31:37,  1.35s/it]
 98%|█████████▊| 60500/61904 [7:48:54<32:18,  1.38s/it]
                                                       
{'loss': 2.4227, 'learning_rate': 1.0227537922987165e-07, 'epoch': 15.64}
+
 98%|█████████▊| 60500/61904 [7:48:54<32:18,  1.38s/it]
 98%|█████████▊| 60501/61904 [7:48:55<32:23,  1.39s/it]
 98%|█████████▊| 60502/61904 [7:48:56<32:23,  1.39s/it]
 98%|█████████▊| 60503/61904 [7:48:58<31:44,  1.36s/it]
 98%|█████████▊| 60504/61904 [7:48:59<32:31,  1.39s/it]
 98%|█████████▊| 60505/61904 [7:49:01<32:21,  1.39s/it]
 98%|█████████▊| 60506/61904 [7:49:02<32:16,  1.39s/it]
 98%|█████████▊| 60507/61904 [7:49:03<32:15,  1.39s/it]
 98%|█████████▊| 60508/61904 [7:49:05<32:13,  1.38s/it]
 98%|█████████▊| 60509/61904 [7:49:06<31:21,  1.35s/it]
 98%|█████████▊| 60510/61904 [7:49:07<31:55,  1.37s/it]
 98%|█████████▊| 60511/61904 [7:49:09<31:31,  1.36s/it]
 98%|█████████▊| 60512/61904 [7:49:10<31:56,  1.38s/it]
 98%|█████████▊| 60513/61904 [7:49:11<31:03,  1.34s/it]
 98%|█████████▊| 60514/61904 [7:49:13<30:51,  1.33s/it]
 98%|█████████▊| 60515/61904 [7:49:14<31:35,  1.36s/it]
 98%|█████████▊| 60516/61904 [7:49:16<31:07,  1.35s/it]
 98%|█████████▊| 60517/61904 [7:49:17<31:55,  1.38s/it]
 98%|█████████▊| 60518/61904 [7:49:18<31:29,  1.36s/it]
 98%|█████████▊| 60519/61904 [7:49:20<31:54,  1.38s/it]
 98%|█████████▊| 60520/61904 [7:49:21<31:52,  1.38s/it]
                                                       
{'loss': 2.4355, 'learning_rate': 1.0224296642032931e-07, 'epoch': 15.64}
+
 98%|█████████▊| 60520/61904 [7:49:21<31:52,  1.38s/it]
 98%|█████████▊| 60521/61904 [7:49:22<31:29,  1.37s/it]
 98%|█████████▊| 60522/61904 [7:49:24<31:24,  1.36s/it]
 98%|█████████▊| 60523/61904 [7:49:25<32:46,  1.42s/it]
 98%|█████████▊| 60524/61904 [7:49:27<32:23,  1.41s/it]
 98%|█████████▊| 60525/61904 [7:49:28<31:53,  1.39s/it]
 98%|█████████▊| 60526/61904 [7:49:29<31:49,  1.39s/it]
 98%|█████████▊| 60527/61904 [7:49:31<31:02,  1.35s/it]
 98%|█████████▊| 60528/61904 [7:49:32<31:43,  1.38s/it]
 98%|█████████▊| 60529/61904 [7:49:34<33:00,  1.44s/it]
 98%|█████████▊| 60530/61904 [7:49:35<32:52,  1.44s/it]
 98%|█████████▊| 60531/61904 [7:49:36<31:54,  1.39s/it]
 98%|█████████▊| 60532/61904 [7:49:38<33:16,  1.46s/it]
 98%|█████████▊| 60533/61904 [7:49:39<32:00,  1.40s/it]
 98%|█████████▊| 60534/61904 [7:49:41<31:33,  1.38s/it]
 98%|█████████▊| 60535/61904 [7:49:42<31:50,  1.40s/it]
 98%|█████████▊| 60536/61904 [7:49:43<31:24,  1.38s/it]
 98%|█████████▊| 60537/61904 [7:49:45<31:01,  1.36s/it]
 98%|█████████▊| 60538/61904 [7:49:46<30:50,  1.35s/it]
 98%|█████████▊| 60539/61904 [7:49:47<30:06,  1.32s/it]
 98%|█████████▊| 60540/61904 [7:49:49<30:15,  1.33s/it]
                                                       
{'loss': 2.3482, 'learning_rate': 1.0221055361078698e-07, 'epoch': 15.65}
+
 98%|█████████▊| 60540/61904 [7:49:49<30:15,  1.33s/it]
 98%|█████████▊| 60541/61904 [7:49:50<30:49,  1.36s/it]
 98%|█████████▊| 60542/61904 [7:49:51<30:44,  1.35s/it]
 98%|█████████▊| 60543/61904 [7:49:53<30:10,  1.33s/it]
 98%|█████████▊| 60544/61904 [7:49:54<30:05,  1.33s/it]
 98%|█████████▊| 60545/61904 [7:49:55<30:17,  1.34s/it]
 98%|█████████▊| 60546/61904 [7:49:57<30:01,  1.33s/it]
 98%|█████████▊| 60547/61904 [7:49:58<30:21,  1.34s/it]
 98%|█████████▊| 60548/61904 [7:50:00<30:54,  1.37s/it]
 98%|█████████▊| 60549/61904 [7:50:01<31:02,  1.37s/it]
 98%|█████████▊| 60550/61904 [7:50:02<31:32,  1.40s/it]
 98%|█████████▊| 60551/61904 [7:50:04<30:52,  1.37s/it]
 98%|█████████▊| 60552/61904 [7:50:05<31:12,  1.39s/it]
 98%|█████████▊| 60553/61904 [7:50:07<31:22,  1.39s/it]
 98%|█████████▊| 60554/61904 [7:50:08<30:30,  1.36s/it]
 98%|█████████▊| 60555/61904 [7:50:09<30:06,  1.34s/it]
 98%|█████████▊| 60556/61904 [7:50:11<31:48,  1.42s/it]
 98%|█████████▊| 60557/61904 [7:50:12<31:02,  1.38s/it]
 98%|█████████▊| 60558/61904 [7:50:13<30:41,  1.37s/it]
 98%|█████████▊| 60559/61904 [7:50:15<30:37,  1.37s/it]
 98%|█████████▊| 60560/61904 [7:50:16<29:47,  1.33s/it]
                                                       
{'loss': 2.4117, 'learning_rate': 1.0217814080124464e-07, 'epoch': 15.65}
+
 98%|█████████▊| 60560/61904 [7:50:16<29:47,  1.33s/it]
 98%|█████████▊| 60561/61904 [7:50:17<31:09,  1.39s/it]
 98%|█████████▊| 60562/61904 [7:50:19<31:16,  1.40s/it]
 98%|█████████▊| 60563/61904 [7:50:20<31:40,  1.42s/it]
 98%|█████████▊| 60564/61904 [7:50:22<30:40,  1.37s/it]
 98%|█████████▊| 60565/61904 [7:50:23<30:49,  1.38s/it]
 98%|█████████▊| 60566/61904 [7:50:24<30:40,  1.38s/it]
 98%|█████████▊| 60567/61904 [7:50:26<30:27,  1.37s/it]
 98%|█████████▊| 60568/61904 [7:50:27<30:09,  1.35s/it]
 98%|█████████▊| 60569/61904 [7:50:28<30:53,  1.39s/it]
 98%|█████████▊| 60570/61904 [7:50:30<31:24,  1.41s/it]
 98%|█████████▊| 60571/61904 [7:50:31<31:28,  1.42s/it]
 98%|█████████▊| 60572/61904 [7:50:33<30:41,  1.38s/it]
 98%|█████████▊| 60573/61904 [7:50:34<31:12,  1.41s/it]
 98%|█████████▊| 60574/61904 [7:50:36<31:13,  1.41s/it]
 98%|█████████▊| 60575/61904 [7:50:37<31:24,  1.42s/it]
 98%|█████████▊| 60576/61904 [7:50:38<31:00,  1.40s/it]
 98%|█████████▊| 60577/61904 [7:50:40<30:37,  1.38s/it]
 98%|█████████▊| 60578/61904 [7:50:41<30:17,  1.37s/it]
 98%|█████████▊| 60579/61904 [7:50:42<30:36,  1.39s/it]
 98%|█████████▊| 60580/61904 [7:50:44<30:26,  1.38s/it]
                                                       
{'loss': 2.3671, 'learning_rate': 1.0214572799170232e-07, 'epoch': 15.66}
+
 98%|█████████▊| 60580/61904 [7:50:44<30:26,  1.38s/it]
 98%|█████████▊| 60581/61904 [7:50:45<29:25,  1.33s/it]
 98%|█████████▊| 60582/61904 [7:50:47<30:18,  1.38s/it]
 98%|█████████▊| 60583/61904 [7:50:48<30:00,  1.36s/it]
 98%|█████████▊| 60584/61904 [7:50:49<29:23,  1.34s/it]
 98%|█████████▊| 60585/61904 [7:50:51<29:46,  1.35s/it]
 98%|█████████▊| 60586/61904 [7:50:52<29:45,  1.35s/it]
 98%|█████████▊| 60587/61904 [7:50:53<30:26,  1.39s/it]
 98%|█████████▊| 60588/61904 [7:50:55<29:59,  1.37s/it]
 98%|█████████▊| 60589/61904 [7:50:56<29:08,  1.33s/it]
 98%|█████████▊| 60590/61904 [7:50:57<29:02,  1.33s/it]
 98%|█████████▊| 60591/61904 [7:50:59<29:35,  1.35s/it]
 98%|█████████▊| 60592/61904 [7:51:00<29:27,  1.35s/it]
 98%|█████████▊| 60593/61904 [7:51:01<29:24,  1.35s/it]
 98%|█████████▊| 60594/61904 [7:51:03<29:03,  1.33s/it]
 98%|█████████▊| 60595/61904 [7:51:04<29:52,  1.37s/it]
 98%|█████████▊| 60596/61904 [7:51:05<29:52,  1.37s/it]
 98%|█████████▊| 60597/61904 [7:51:07<30:01,  1.38s/it]
 98%|█████████▊| 60598/61904 [7:51:08<29:29,  1.36s/it]
 98%|█████████▊| 60599/61904 [7:51:09<29:01,  1.33s/it]
 98%|█████████▊| 60600/61904 [7:51:11<28:26,  1.31s/it]
                                                       
{'loss': 2.44, 'learning_rate': 1.0211331518215998e-07, 'epoch': 15.66}
+
 98%|█████████▊| 60600/61904 [7:51:11<28:26,  1.31s/it]
 98%|█████████▊| 60601/61904 [7:51:12<28:31,  1.31s/it]
 98%|█████████▊| 60602/61904 [7:51:13<28:16,  1.30s/it]
 98%|█████████▊| 60603/61904 [7:51:15<28:37,  1.32s/it]
 98%|█████████▊| 60604/61904 [7:51:16<29:23,  1.36s/it]
 98%|█████████▊| 60605/61904 [7:51:18<30:10,  1.39s/it]
 98%|█████████▊| 60606/61904 [7:51:19<29:56,  1.38s/it]
 98%|█████████▊| 60607/61904 [7:51:20<29:00,  1.34s/it]
 98%|████��████▊| 60608/61904 [7:51:22<29:14,  1.35s/it]
 98%|█████████▊| 60609/61904 [7:51:23<29:27,  1.37s/it]
 98%|█████████▊| 60610/61904 [7:51:24<29:01,  1.35s/it]
 98%|█████████▊| 60611/61904 [7:51:26<28:49,  1.34s/it]
 98%|█████████▊| 60612/61904 [7:51:27<28:41,  1.33s/it]
 98%|█████████▊| 60613/61904 [7:51:28<28:37,  1.33s/it]
 98%|█████████▊| 60614/61904 [7:51:30<29:14,  1.36s/it]
 98%|█████████▊| 60615/61904 [7:51:31<30:16,  1.41s/it]
 98%|█████████▊| 60616/61904 [7:51:33<29:43,  1.38s/it]
 98%|█████████▊| 60617/61904 [7:51:34<29:45,  1.39s/it]
 98%|█████████▊| 60618/61904 [7:51:35<29:39,  1.38s/it]
 98%|█████████▊| 60619/61904 [7:51:37<28:56,  1.35s/it]
 98%|█████████▊| 60620/61904 [7:51:38<29:03,  1.36s/it]
                                                       
{'loss': 2.4273, 'learning_rate': 1.0208090237261766e-07, 'epoch': 15.67}
+
 98%|█████████▊| 60620/61904 [7:51:38<29:03,  1.36s/it]
 98%|█████████▊| 60621/61904 [7:51:39<28:52,  1.35s/it]
 98%|█████████▊| 60622/61904 [7:51:41<28:49,  1.35s/it]
 98%|█████████▊| 60623/61904 [7:51:42<28:45,  1.35s/it]
 98%|█████████▊| 60624/61904 [7:51:43<29:28,  1.38s/it]
 98%|█████████▊| 60625/61904 [7:51:45<29:08,  1.37s/it]
 98%|█████████▊| 60626/61904 [7:51:46<29:56,  1.41s/it]
 98%|█████████▊| 60627/61904 [7:51:48<30:23,  1.43s/it]
 98%|█████████▊| 60628/61904 [7:51:49<29:42,  1.40s/it]
 98%|█████████▊| 60629/61904 [7:51:51<30:57,  1.46s/it]
 98%|█████████▊| 60630/61904 [7:51:52<30:17,  1.43s/it]
 98%|█████████▊| 60631/61904 [7:51:53<29:03,  1.37s/it]
 98%|█████████▊| 60632/61904 [7:51:55<29:32,  1.39s/it]
 98%|█████████▊| 60633/61904 [7:51:56<30:25,  1.44s/it]
 98%|█████████▊| 60634/61904 [7:51:58<29:54,  1.41s/it]
 98%|█████████▊| 60635/61904 [7:51:59<29:35,  1.40s/it]
 98%|█████████▊| 60636/61904 [7:52:00<29:45,  1.41s/it]
 98%|█████████▊| 60637/61904 [7:52:02<29:18,  1.39s/it]
 98%|█████████▊| 60638/61904 [7:52:03<28:32,  1.35s/it]
 98%|█████████▊| 60639/61904 [7:52:04<28:46,  1.36s/it]
 98%|█████████▊| 60640/61904 [7:52:06<28:22,  1.35s/it]
                                                       
{'loss': 2.4038, 'learning_rate': 1.0204848956307532e-07, 'epoch': 15.67}
+
 98%|█████████▊| 60640/61904 [7:52:06<28:22,  1.35s/it]
 98%|█████████▊| 60641/61904 [7:52:07<28:35,  1.36s/it]
 98%|█████████▊| 60642/61904 [7:52:08<27:57,  1.33s/it]
 98%|█████████▊| 60643/61904 [7:52:10<28:24,  1.35s/it]
 98%|█████████▊| 60644/61904 [7:52:11<28:18,  1.35s/it]
 98%|█████████▊| 60645/61904 [7:52:12<27:40,  1.32s/it]
 98%|█████████▊| 60646/61904 [7:52:14<27:22,  1.31s/it]
 98%|█████████▊| 60647/61904 [7:52:15<28:54,  1.38s/it]
 98%|█████████▊| 60648/61904 [7:52:17<28:57,  1.38s/it]
 98%|█████████▊| 60649/61904 [7:52:18<30:24,  1.45s/it]
 98%|█████████▊| 60650/61904 [7:52:19<29:32,  1.41s/it]
 98%|█████████▊| 60651/61904 [7:52:21<30:00,  1.44s/it]
 98%|█████████▊| 60652/61904 [7:52:22<29:29,  1.41s/it]
 98%|█████████▊| 60653/61904 [7:52:24<28:34,  1.37s/it]
 98%|█████████▊| 60654/61904 [7:52:25<28:58,  1.39s/it]
 98%|█████████▊| 60655/61904 [7:52:26<28:35,  1.37s/it]
 98%|█████████▊| 60656/61904 [7:52:28<28:15,  1.36s/it]
 98%|█████████▊| 60657/61904 [7:52:29<29:04,  1.40s/it]
 98%|█████████▊| 60658/61904 [7:52:30<28:12,  1.36s/it]
 98%|█████████▊| 60659/61904 [7:52:32<29:45,  1.43s/it]
 98%|█████████▊| 60660/61904 [7:52:34<30:06,  1.45s/it]
                                                       
{'loss': 2.4434, 'learning_rate': 1.0201607675353299e-07, 'epoch': 15.68}
+
 98%|█████████▊| 60660/61904 [7:52:34<30:06,  1.45s/it]
 98%|█████████▊| 60661/61904 [7:52:35<29:36,  1.43s/it]
 98%|█████████▊| 60662/61904 [7:52:36<29:19,  1.42s/it]
 98%|█████████▊| 60663/61904 [7:52:38<28:05,  1.36s/it]
 98%|█████████▊| 60664/61904 [7:52:39<28:34,  1.38s/it]
 98%|█████████▊| 60665/61904 [7:52:40<28:33,  1.38s/it]
 98%|█████████▊| 60666/61904 [7:52:42<28:22,  1.38s/it]
 98%|████████��▊| 60667/61904 [7:52:43<28:36,  1.39s/it]
 98%|█████████▊| 60668/61904 [7:52:44<28:05,  1.36s/it]
 98%|█████████▊| 60669/61904 [7:52:46<28:43,  1.40s/it]
 98%|█████████▊| 60670/61904 [7:52:47<28:26,  1.38s/it]
 98%|█████████▊| 60671/61904 [7:52:49<27:58,  1.36s/it]
 98%|█████████▊| 60672/61904 [7:52:50<28:16,  1.38s/it]
 98%|█████████▊| 60673/61904 [7:52:51<28:28,  1.39s/it]
 98%|█████████▊| 60674/61904 [7:52:53<28:21,  1.38s/it]
 98%|█████████▊| 60675/61904 [7:52:54<27:35,  1.35s/it]
 98%|█████████▊| 60676/61904 [7:52:55<27:46,  1.36s/it]
 98%|█████████▊| 60677/61904 [7:52:57<28:25,  1.39s/it]
 98%|█████████▊| 60678/61904 [7:52:58<28:54,  1.41s/it]
 98%|█████████▊| 60679/61904 [7:53:00<28:09,  1.38s/it]
 98%|█████████▊| 60680/61904 [7:53:01<28:16,  1.39s/it]
                                                       
{'loss': 2.3874, 'learning_rate': 1.0198366394399066e-07, 'epoch': 15.68}
+
 98%|█████████▊| 60680/61904 [7:53:01<28:16,  1.39s/it]
 98%|█████████▊| 60681/61904 [7:53:02<28:03,  1.38s/it]
 98%|█████████▊| 60682/61904 [7:53:04<27:56,  1.37s/it]
 98%|█████████▊| 60683/61904 [7:53:05<28:13,  1.39s/it]
 98%|█████████▊| 60684/61904 [7:53:07<27:41,  1.36s/it]
 98%|█████████▊| 60685/61904 [7:53:08<27:46,  1.37s/it]
 98%|█████████▊| 60686/61904 [7:53:09<27:57,  1.38s/it]
 98%|█████████▊| 60687/61904 [7:53:11<28:47,  1.42s/it]
 98%|█████████▊| 60688/61904 [7:53:12<28:34,  1.41s/it]
 98%|█████████▊| 60689/61904 [7:53:14<28:42,  1.42s/it]
 98%|█████████▊| 60690/61904 [7:53:15<28:48,  1.42s/it]
 98%|█████████▊| 60691/61904 [7:53:17<29:25,  1.46s/it]
 98%|█████████▊| 60692/61904 [7:53:18<28:38,  1.42s/it]
 98%|█████████▊| 60693/61904 [7:53:19<28:50,  1.43s/it]
 98%|█████████▊| 60694/61904 [7:53:21<28:34,  1.42s/it]
 98%|█████████▊| 60695/61904 [7:53:22<28:25,  1.41s/it]
 98%|█████████▊| 60696/61904 [7:53:24<28:16,  1.40s/it]
 98%|█████████▊| 60697/61904 [7:53:25<27:29,  1.37s/it]
 98%|█████████▊| 60698/61904 [7:53:26<27:38,  1.38s/it]
 98%|█████████▊| 60699/61904 [7:53:27<26:52,  1.34s/it]
 98%|█████████▊| 60700/61904 [7:53:29<27:43,  1.38s/it]
                                                       
{'loss': 2.4237, 'learning_rate': 1.0195125113444833e-07, 'epoch': 15.69}
+
 98%|█████████▊| 60700/61904 [7:53:29<27:43,  1.38s/it]
 98%|█████████▊| 60701/61904 [7:53:30<27:19,  1.36s/it]
 98%|█████████▊| 60702/61904 [7:53:32<27:00,  1.35s/it]
 98%|█████████▊| 60703/61904 [7:53:33<27:44,  1.39s/it]
 98%|█████████▊| 60704/61904 [7:53:35<28:08,  1.41s/it]
 98%|█████████▊| 60705/61904 [7:53:36<28:15,  1.41s/it]
 98%|█████████▊| 60706/61904 [7:53:37<27:53,  1.40s/it]
 98%|█████████▊| 60707/61904 [7:53:39<28:00,  1.40s/it]
 98%|█████████▊| 60708/61904 [7:53:40<27:33,  1.38s/it]
 98%|█████████▊| 60709/61904 [7:53:41<27:41,  1.39s/it]
 98%|█████████▊| 60710/61904 [7:53:43<27:13,  1.37s/it]
 98%|█████████▊| 60711/61904 [7:53:44<27:41,  1.39s/it]
 98%|█████████▊| 60712/61904 [7:53:46<27:52,  1.40s/it]
 98%|█████████▊| 60713/61904 [7:53:47<27:24,  1.38s/it]
 98%|█████████▊| 60714/61904 [7:53:48<27:58,  1.41s/it]
 98%|█████████▊| 60715/61904 [7:53:50<27:14,  1.37s/it]
 98%|█████████▊| 60716/61904 [7:53:51<26:37,  1.35s/it]
 98%|█████████▊| 60717/61904 [7:53:52<26:41,  1.35s/it]
 98%|█████████▊| 60718/61904 [7:53:54<26:27,  1.34s/it]
 98%|█████████▊| 60719/61904 [7:53:55<26:16,  1.33s/it]
 98%|█████████▊| 60720/61904 [7:53:56<25:46,  1.31s/it]
                                                       
{'loss': 2.3947, 'learning_rate': 1.0191883832490599e-07, 'epoch': 15.69}
+
 98%|█████████▊| 60720/61904 [7:53:56<25:46,  1.31s/it]
 98%|█████████▊| 60721/61904 [7:53:58<25:46,  1.31s/it]
 98%|█████████▊| 60722/61904 [7:53:59<25:46,  1.31s/it]
 98%|█████████▊| 60723/61904 [7:54:00<25:22,  1.29s/it]
 98%|█████████▊| 60724/61904 [7:54:01<25:00,  1.27s/it]
 98%|█████████▊| 60725/61904 [7:54:03<25:04,  1.28s/it]
 98%|█████████▊| 60726/61904 [7:54:04<27:10,  1.38s/it]
 98%|█████████▊| 60727/61904 [7:54:06<27:16,  1.39s/it]
 98%|█████████▊| 60728/61904 [7:54:07<27:05,  1.38s/it]
 98%|█████████▊| 60729/61904 [7:54:08<26:40,  1.36s/it]
 98%|█████████▊| 60730/61904 [7:54:10<26:14,  1.34s/it]
 98%|█████████▊| 60731/61904 [7:54:11<26:42,  1.37s/it]
 98%|█████████▊| 60732/61904 [7:54:12<26:25,  1.35s/it]
 98%|█████████▊| 60733/61904 [7:54:14<25:42,  1.32s/it]
 98%|█████████▊| 60734/61904 [7:54:15<26:01,  1.33s/it]
 98%|█████████▊| 60735/61904 [7:54:16<25:52,  1.33s/it]
 98%|█████████▊| 60736/61904 [7:54:18<26:50,  1.38s/it]
 98%|█████████▊| 60737/61904 [7:54:19<26:47,  1.38s/it]
 98%|█████████▊| 60738/61904 [7:54:21<26:19,  1.35s/it]
 98%|█████████▊| 60739/61904 [7:54:22<27:13,  1.40s/it]
 98%|█████████▊| 60740/61904 [7:54:23<26:54,  1.39s/it]
                                                       
{'loss': 2.4482, 'learning_rate': 1.0188642551536367e-07, 'epoch': 15.7}
+
 98%|█████████▊| 60740/61904 [7:54:23<26:54,  1.39s/it]
 98%|█████████▊| 60741/61904 [7:54:25<26:41,  1.38s/it]
 98%|█████████▊| 60742/61904 [7:54:26<26:48,  1.38s/it]
 98%|█████████▊| 60743/61904 [7:54:27<26:36,  1.38s/it]
 98%|█████████▊| 60744/61904 [7:54:29<26:20,  1.36s/it]
 98%|█████████▊| 60745/61904 [7:54:30<26:17,  1.36s/it]
 98%|█████████▊| 60746/61904 [7:54:31<25:31,  1.32s/it]
 98%|█████████▊| 60747/61904 [7:54:33<25:48,  1.34s/it]
 98%|█████████▊| 60748/61904 [7:54:34<27:34,  1.43s/it]
 98%|█████████▊| 60749/61904 [7:54:36<26:51,  1.40s/it]
 98%|█████████▊| 60750/61904 [7:54:37<26:11,  1.36s/it]
 98%|█████████▊| 60751/61904 [7:54:38<25:28,  1.33s/it]
 98%|█████████▊| 60752/61904 [7:54:40<26:22,  1.37s/it]
 98%|█████████▊| 60753/61904 [7:54:41<27:25,  1.43s/it]
 98%|█████████▊| 60754/61904 [7:54:43<27:11,  1.42s/it]
 98%|█████████▊| 60755/61904 [7:54:44<27:47,  1.45s/it]
 98%|█████████▊| 60756/61904 [7:54:45<26:30,  1.39s/it]
 98%|█████████▊| 60757/61904 [7:54:47<25:55,  1.36s/it]
 98%|█████████▊| 60758/61904 [7:54:48<26:36,  1.39s/it]
 98%|█████████▊| 60759/61904 [7:54:50<27:01,  1.42s/it]
 98%|█████████▊| 60760/61904 [7:54:51<26:53,  1.41s/it]
                                                       
{'loss': 2.4592, 'learning_rate': 1.0185401270582133e-07, 'epoch': 15.7}
+
 98%|█████████▊| 60760/61904 [7:54:51<26:53,  1.41s/it]
 98%|█████████▊| 60761/61904 [7:54:52<26:05,  1.37s/it]
 98%|█████████▊| 60762/61904 [7:54:54<26:07,  1.37s/it]
 98%|█████████▊| 60763/61904 [7:54:55<25:43,  1.35s/it]
 98%|█████████▊| 60764/61904 [7:54:56<25:08,  1.32s/it]
 98%|█████████▊| 60765/61904 [7:54:58<24:42,  1.30s/it]
 98%|█████████▊| 60766/61904 [7:54:59<25:04,  1.32s/it]
 98%|█████████▊| 60767/61904 [7:55:00<25:03,  1.32s/it]
 98%|█████████▊| 60768/61904 [7:55:02<25:05,  1.33s/it]
 98%|█████████▊| 60769/61904 [7:55:03<25:31,  1.35s/it]
 98%|█████████▊| 60770/61904 [7:55:04<26:14,  1.39s/it]
 98%|█████████▊| 60771/61904 [7:55:06<25:23,  1.34s/it]
 98%|█████████▊| 60772/61904 [7:55:07<26:12,  1.39s/it]
 98%|█████████▊| 60773/61904 [7:55:09<25:56,  1.38s/it]
 98%|█████████▊| 60774/61904 [7:55:10<26:07,  1.39s/it]
 98%|█████████▊| 60775/61904 [7:55:11<25:36,  1.36s/it]
 98%|█████████▊| 60776/61904 [7:55:13<25:51,  1.38s/it]
 98%|█████████▊| 60777/61904 [7:55:14<26:27,  1.41s/it]
 98%|█████████▊| 60778/61904 [7:55:16<26:33,  1.42s/it]
 98%|█████████▊| 60779/61904 [7:55:17<26:06,  1.39s/it]
 98%|█████████▊| 60780/61904 [7:55:18<26:24,  1.41s/it]
                                                       
{'loss': 2.4356, 'learning_rate': 1.01821599896279e-07, 'epoch': 15.71}
+
 98%|█████████▊| 60780/61904 [7:55:18<26:24,  1.41s/it]
 98%|█████████▊| 60781/61904 [7:55:20<26:19,  1.41s/it]
 98%|█████████▊| 60782/61904 [7:55:21<27:09,  1.45s/it]
 98%|█████████▊| 60783/61904 [7:55:23<27:33,  1.48s/it]
 98%|█████████▊| 60784/61904 [7:55:24<27:57,  1.50s/it]
 98%|█████████▊| 60785/61904 [7:55:26<26:51,  1.44s/it]
 98%|█████████▊| 60786/61904 [7:55:27<26:36,  1.43s/it]
 98%|█████████▊| 60787/61904 [7:55:28<26:05,  1.40s/it]
 98%|█████████▊| 60788/61904 [7:55:30<25:20,  1.36s/it]
 98%|█████████▊| 60789/61904 [7:55:31<25:08,  1.35s/it]
 98%|█████████▊| 60790/61904 [7:55:32<24:46,  1.33s/it]
 98%|█████████▊| 60791/61904 [7:55:34<25:22,  1.37s/it]
 98%|█████████▊| 60792/61904 [7:55:35<24:09,  1.30s/it]
 98%|█████████▊| 60793/61904 [7:55:36<25:15,  1.36s/it]
 98%|█████████▊| 60794/61904 [7:55:38<24:43,  1.34s/it]
 98%|█████████▊| 60795/61904 [7:55:39<25:30,  1.38s/it]
 98%|█████████▊| 60796/61904 [7:55:40<24:43,  1.34s/it]
 98%|█████████▊| 60797/61904 [7:55:42<24:18,  1.32s/it]
 98%|█████████▊| 60798/61904 [7:55:43<24:11,  1.31s/it]
 98%|█████████▊| 60799/61904 [7:55:44<24:46,  1.35s/it]
 98%|█████████▊| 60800/61904 [7:55:46<24:53,  1.35s/it]
                                                       
{'loss': 2.3921, 'learning_rate': 1.0178918708673667e-07, 'epoch': 15.71}
+
 98%|█████████▊| 60800/61904 [7:55:46<24:53,  1.35s/it]
 98%|█████████▊| 60801/61904 [7:55:47<26:01,  1.42s/it]
 98%|█████████▊| 60802/61904 [7:55:49<25:06,  1.37s/it]
 98%|█████████▊| 60803/61904 [7:55:50<25:38,  1.40s/it]
 98%|█████████▊| 60804/61904 [7:55:52<25:40,  1.40s/it]
 98%|█████████▊| 60805/61904 [7:55:53<25:13,  1.38s/it]
 98%|█████████▊| 60806/61904 [7:55:54<25:47,  1.41s/it]
 98%|█████████▊| 60807/61904 [7:55:56<25:33,  1.40s/it]
 98%|█████████▊| 60808/61904 [7:55:57<25:09,  1.38s/it]
 98%|█████████▊| 60809/61904 [7:55:58<25:17,  1.39s/it]
 98%|█████████▊| 60810/61904 [7:56:00<25:27,  1.40s/it]
 98%|█████████▊| 60811/61904 [7:56:01<24:52,  1.37s/it]
 98%|█████████▊| 60812/61904 [7:56:03<24:57,  1.37s/it]
 98%|█████████▊| 60813/61904 [7:56:04<25:05,  1.38s/it]
 98%|█████████▊| 60814/61904 [7:56:05<25:36,  1.41s/it]
 98%|█████████▊| 60815/61904 [7:56:07<24:54,  1.37s/it]
 98%|█████████▊| 60816/61904 [7:56:08<24:55,  1.37s/it]
 98%|█████████▊| 60817/61904 [7:56:09<25:02,  1.38s/it]
 98%|█████████▊| 60818/61904 [7:56:11<25:26,  1.41s/it]
 98%|█████████▊| 60819/61904 [7:56:12<24:51,  1.37s/it]
 98%|█████████▊| 60820/61904 [7:56:14<24:28,  1.35s/it]
                                                       
{'loss': 2.4722, 'learning_rate': 1.0175677427719434e-07, 'epoch': 15.72}
+
 98%|█████████▊| 60820/61904 [7:56:14<24:28,  1.35s/it]
 98%|█████████▊| 60821/61904 [7:56:15<25:27,  1.41s/it]
 98%|█████████▊| 60822/61904 [7:56:16<24:39,  1.37s/it]
 98%|█████████▊| 60823/61904 [7:56:18<24:28,  1.36s/it]
 98%|█████████▊| 60824/61904 [7:56:19<25:01,  1.39s/it]
 98%|█████████▊| 60825/61904 [7:56:21<25:08,  1.40s/it]
 98%|█████████▊| 60826/61904 [7:56:22<25:12,  1.40s/it]
 98%|█████████▊| 60827/61904 [7:56:24<25:58,  1.45s/it]
 98%|█████████▊| 60828/61904 [7:56:25<25:32,  1.42s/it]
 98%|█████████▊| 60829/61904 [7:56:26<24:55,  1.39s/it]
 98%|█████████▊| 60830/61904 [7:56:28<24:46,  1.38s/it]
 98%|█████████▊| 60831/61904 [7:56:29<24:03,  1.35s/it]
 98%|█████████▊| 60832/61904 [7:56:30<24:28,  1.37s/it]
 98%|█████████▊| 60833/61904 [7:56:32<25:07,  1.41s/it]
 98%|█████████▊| 60834/61904 [7:56:33<25:01,  1.40s/it]
 98%|█████████▊| 60835/61904 [7:56:35<26:01,  1.46s/it]
 98%|█████████▊| 60836/61904 [7:56:36<25:40,  1.44s/it]
 98%|█████████▊| 60837/61904 [7:56:38<25:31,  1.44s/it]
 98%|█████████▊| 60838/61904 [7:56:39<25:23,  1.43s/it]
 98%|█████████▊| 60839/61904 [7:56:40<24:41,  1.39s/it]
 98%|█████████▊| 60840/61904 [7:56:42<23:52,  1.35s/it]
                                                       
{'loss': 2.3778, 'learning_rate': 1.01724361467652e-07, 'epoch': 15.72}
+
 98%|█████████▊| 60840/61904 [7:56:42<23:52,  1.35s/it]
 98%|█████████▊| 60841/61904 [7:56:43<23:59,  1.35s/it]
 98%|█████████▊| 60842/61904 [7:56:44<24:15,  1.37s/it]
 98%|█████████▊| 60843/61904 [7:56:46<24:52,  1.41s/it]
 98%|█████████▊| 60844/61904 [7:56:47<24:29,  1.39s/it]
 98%|█████████▊| 60845/61904 [7:56:49<25:27,  1.44s/it]
 98%|█████████▊| 60846/61904 [7:56:50<25:19,  1.44s/it]
 98%|█████████▊| 60847/61904 [7:56:52<25:24,  1.44s/it]
 98%|█████████▊| 60848/61904 [7:56:53<25:15,  1.44s/it]
 98%|█████████▊| 60849/61904 [7:56:54<24:26,  1.39s/it]
 98%|█████████▊| 60850/61904 [7:56:56<25:28,  1.45s/it]
 98%|█████████▊| 60851/61904 [7:56:57<24:31,  1.40s/it]
 98%|█████████▊| 60852/61904 [7:56:59<25:22,  1.45s/it]
 98%|█████████▊| 60853/61904 [7:57:00<25:14,  1.44s/it]
 98%|█████████▊| 60854/61904 [7:57:01<24:42,  1.41s/it]
 98%|█████████▊| 60855/61904 [7:57:03<25:00,  1.43s/it]
 98%|█████████▊| 60856/61904 [7:57:04<24:43,  1.42s/it]
 98%|█████████▊| 60857/61904 [7:57:06<23:57,  1.37s/it]
 98%|█████████▊| 60858/61904 [7:57:07<24:11,  1.39s/it]
 98%|█████████▊| 60859/61904 [7:57:09<24:48,  1.42s/it]
 98%|█████████▊| 60860/61904 [7:57:10<24:50,  1.43s/it]
                                                       
{'loss': 2.4242, 'learning_rate': 1.0169194865810968e-07, 'epoch': 15.73}
+
 98%|█████████▊| 60860/61904 [7:57:10<24:50,  1.43s/it]
 98%|█████████▊| 60861/61904 [7:57:11<24:26,  1.41s/it]
 98%|█████████▊| 60862/61904 [7:57:13<24:29,  1.41s/it]
 98%|█████████▊| 60863/61904 [7:57:14<23:57,  1.38s/it]
 98%|█████████▊| 60864/61904 [7:57:16<24:24,  1.41s/it]
 98%|█████████▊| 60865/61904 [7:57:17<24:18,  1.40s/it]
 98%|█████████▊| 60866/61904 [7:57:18<24:19,  1.41s/it]
 98%|█████████▊| 60867/61904 [7:57:20<24:34,  1.42s/it]
 98%|█████████▊| 60868/61904 [7:57:21<23:58,  1.39s/it]
 98%|█████████▊| 60869/61904 [7:57:22<23:31,  1.36s/it]
 98%|█████████▊| 60870/61904 [7:57:24<23:22,  1.36s/it]
 98%|█████████▊| 60871/61904 [7:57:25<23:30,  1.37s/it]
 98%|█████████▊| 60872/61904 [7:57:26<23:19,  1.36s/it]
 98%|█████████▊| 60873/61904 [7:57:28<23:11,  1.35s/it]
 98%|█████████▊| 60874/61904 [7:57:29<23:00,  1.34s/it]
 98%|█████████▊| 60875/61904 [7:57:31<23:08,  1.35s/it]
 98%|█████████▊| 60876/61904 [7:57:32<22:49,  1.33s/it]
 98%|█████████▊| 60877/61904 [7:57:33<23:03,  1.35s/it]
 98%|█████████▊| 60878/61904 [7:57:34<22:45,  1.33s/it]
 98%|█████████▊| 60879/61904 [7:57:36<23:10,  1.36s/it]
 98%|█████████▊| 60880/61904 [7:57:37<22:56,  1.34s/it]
                                                       
{'loss': 2.4437, 'learning_rate': 1.0165953584856734e-07, 'epoch': 15.73}
+
 98%|█████████▊| 60880/61904 [7:57:37<22:56,  1.34s/it]
 98%|█████████▊| 60881/61904 [7:57:39<22:59,  1.35s/it]
 98%|█████████▊| 60882/61904 [7:57:40<23:28,  1.38s/it]
 98%|█████████▊| 60883/61904 [7:57:41<23:36,  1.39s/it]
 98%|█████████▊| 60884/61904 [7:57:43<23:04,  1.36s/it]
 98%|█████████▊| 60885/61904 [7:57:44<23:22,  1.38s/it]
 98%|█████████▊| 60886/61904 [7:57:45<22:57,  1.35s/it]
 98%|█████████▊| 60887/61904 [7:57:47<23:19,  1.38s/it]
 98%|█████████▊| 60888/61904 [7:57:48<23:25,  1.38s/it]
 98%|█████████▊| 60889/61904 [7:57:50<22:58,  1.36s/it]
 98%|█████████▊| 60890/61904 [7:57:51<23:01,  1.36s/it]
 98%|█████████▊| 60891/61904 [7:57:52<22:45,  1.35s/it]
 98%|█████████▊| 60892/61904 [7:57:54<22:52,  1.36s/it]
 98%|█████████▊| 60893/61904 [7:57:55<22:49,  1.35s/it]
 98%|█████████▊| 60894/61904 [7:57:56<22:19,  1.33s/it]
 98%|█████████▊| 60895/61904 [7:57:58<23:59,  1.43s/it]
 98%|█████████▊| 60896/61904 [7:57:59<24:12,  1.44s/it]
 98%|█████████▊| 60897/61904 [7:58:01<23:21,  1.39s/it]
 98%|█████████▊| 60898/61904 [7:58:02<23:36,  1.41s/it]
 98%|█████████▊| 60899/61904 [7:58:04<23:46,  1.42s/it]
 98%|█████████▊| 60900/61904 [7:58:05<22:46,  1.36s/it]
                                                       
{'loss': 2.4182, 'learning_rate': 1.0162712303902502e-07, 'epoch': 15.74}
+
 98%|█████████▊| 60900/61904 [7:58:05<22:46,  1.36s/it]
 98%|█████████▊| 60901/61904 [7:58:06<23:21,  1.40s/it]
 98%|█████████▊| 60902/61904 [7:58:08<23:42,  1.42s/it]
 98%|█████████▊| 60903/61904 [7:58:09<23:56,  1.44s/it]
 98%|█���███████▊| 60904/61904 [7:58:11<23:29,  1.41s/it]
 98%|█████████▊| 60905/61904 [7:58:12<22:58,  1.38s/it]
 98%|█████████▊| 60906/61904 [7:58:13<22:47,  1.37s/it]
 98%|█████████▊| 60907/61904 [7:58:15<22:41,  1.37s/it]
 98%|█████████▊| 60908/61904 [7:58:16<23:06,  1.39s/it]
 98%|█████████▊| 60909/61904 [7:58:17<23:08,  1.40s/it]
 98%|█████████▊| 60910/61904 [7:58:19<23:01,  1.39s/it]
 98%|█████████▊| 60911/61904 [7:58:20<22:20,  1.35s/it]
 98%|█████████▊| 60912/61904 [7:58:21<22:15,  1.35s/it]
 98%|█████████▊| 60913/61904 [7:58:23<23:06,  1.40s/it]
 98%|█████████▊| 60914/61904 [7:58:24<22:55,  1.39s/it]
 98%|█████████▊| 60915/61904 [7:58:26<22:31,  1.37s/it]
 98%|█████████▊| 60916/61904 [7:58:27<23:20,  1.42s/it]
 98%|█████████▊| 60917/61904 [7:58:28<22:32,  1.37s/it]
 98%|█████████▊| 60918/61904 [7:58:30<22:08,  1.35s/it]
 98%|█████████▊| 60919/61904 [7:58:31<22:19,  1.36s/it]
 98%|█████████▊| 60920/61904 [7:58:33<23:06,  1.41s/it]
                                                       
{'loss': 2.3767, 'learning_rate': 1.0159471022948268e-07, 'epoch': 15.75}
+
 98%|█████████▊| 60920/61904 [7:58:33<23:06,  1.41s/it]
 98%|█████████▊| 60921/61904 [7:58:34<23:14,  1.42s/it]
 98%|█████████▊| 60922/61904 [7:58:35<23:07,  1.41s/it]
 98%|█████████▊| 60923/61904 [7:58:37<22:44,  1.39s/it]
 98%|█████████▊| 60924/61904 [7:58:38<22:47,  1.40s/it]
 98%|█████████▊| 60925/61904 [7:58:39<22:20,  1.37s/it]
 98%|█████████▊| 60926/61904 [7:58:41<22:40,  1.39s/it]
 98%|█████████▊| 60927/61904 [7:58:42<22:15,  1.37s/it]
 98%|█████████▊| 60928/61904 [7:58:44<22:01,  1.35s/it]
 98%|█████████▊| 60929/61904 [7:58:45<22:34,  1.39s/it]
 98%|█████████▊| 60930/61904 [7:58:46<22:23,  1.38s/it]
 98%|█████████▊| 60931/61904 [7:58:48<21:52,  1.35s/it]
 98%|█████████▊| 60932/61904 [7:58:49<21:50,  1.35s/it]
 98%|█████████▊| 60933/61904 [7:58:50<21:50,  1.35s/it]
 98%|█████████▊| 60934/61904 [7:58:52<21:27,  1.33s/it]
 98%|█████████▊| 60935/61904 [7:58:53<21:48,  1.35s/it]
 98%|█████████▊| 60936/61904 [7:58:54<22:16,  1.38s/it]
 98%|█████████▊| 60937/61904 [7:58:56<22:19,  1.38s/it]
 98%|█████████▊| 60938/61904 [7:58:57<22:33,  1.40s/it]
 98%|█████████▊| 60939/61904 [7:58:59<22:02,  1.37s/it]
 98%|█████████▊| 60940/61904 [7:59:00<21:56,  1.37s/it]
                                                       
{'loss': 2.4421, 'learning_rate': 1.0156229741994035e-07, 'epoch': 15.75}
+
 98%|█████████▊| 60940/61904 [7:59:00<21:56,  1.37s/it]
 98%|█████████▊| 60941/61904 [7:59:01<21:55,  1.37s/it]
 98%|█████████▊| 60942/61904 [7:59:03<22:34,  1.41s/it]
 98%|█████████▊| 60943/61904 [7:59:04<22:37,  1.41s/it]
 98%|█████████▊| 60944/61904 [7:59:06<22:05,  1.38s/it]
 98%|█████████▊| 60945/61904 [7:59:07<22:02,  1.38s/it]
 98%|█████████▊| 60946/61904 [7:59:08<22:13,  1.39s/it]
 98%|█████████▊| 60947/61904 [7:59:10<21:54,  1.37s/it]
 98%|█████████▊| 60948/61904 [7:59:11<21:49,  1.37s/it]
 98%|█████████▊| 60949/61904 [7:59:12<21:53,  1.37s/it]
 98%|█████████▊| 60950/61904 [7:59:14<21:44,  1.37s/it]
 98%|█████████▊| 60951/61904 [7:59:15<21:37,  1.36s/it]
 98%|█████████▊| 60952/61904 [7:59:16<20:58,  1.32s/it]
 98%|█████████▊| 60953/61904 [7:59:18<21:13,  1.34s/it]
 98%|█████████▊| 60954/61904 [7:59:19<21:34,  1.36s/it]
 98%|█████████▊| 60955/61904 [7:59:21<21:32,  1.36s/it]
 98%|█████████▊| 60956/61904 [7:59:22<21:24,  1.35s/it]
 98%|█████████▊| 60957/61904 [7:59:23<21:01,  1.33s/it]
 98%|█████████▊| 60958/61904 [7:59:25<21:46,  1.38s/it]
 98%|█████████▊| 60959/61904 [7:59:26<21:15,  1.35s/it]
 98%|█████████▊| 60960/61904 [7:59:27<21:32,  1.37s/it]
                                                       
{'loss': 2.4444, 'learning_rate': 1.0152988461039801e-07, 'epoch': 15.76}
+
 98%|█████████▊| 60960/61904 [7:59:27<21:32,  1.37s/it]
 98%|█████████▊| 60961/61904 [7:59:29<23:02,  1.47s/it]
 98%|█████████▊| 60962/61904 [7:59:30<22:24,  1.43s/it]
 98%|█████���███▊| 60963/61904 [7:59:32<21:48,  1.39s/it]
 98%|█████████▊| 60964/61904 [7:59:33<21:55,  1.40s/it]
 98%|█████████▊| 60965/61904 [7:59:34<21:53,  1.40s/it]
 98%|█████████▊| 60966/61904 [7:59:36<22:15,  1.42s/it]
 98%|█████████▊| 60967/61904 [7:59:37<21:43,  1.39s/it]
 98%|█████████▊| 60968/61904 [7:59:39<21:06,  1.35s/it]
 98%|█████████▊| 60969/61904 [7:59:40<21:00,  1.35s/it]
 98%|█████████▊| 60970/61904 [7:59:41<20:46,  1.33s/it]
 98%|█████████▊| 60971/61904 [7:59:43<21:25,  1.38s/it]
 98%|█████████▊| 60972/61904 [7:59:44<20:56,  1.35s/it]
 98%|█████████▊| 60973/61904 [7:59:45<21:32,  1.39s/it]
 98%|█████████▊| 60974/61904 [7:59:47<21:26,  1.38s/it]
 98%|█████████▊| 60975/61904 [7:59:48<21:06,  1.36s/it]
 99%|█████████▊| 60976/61904 [7:59:49<20:53,  1.35s/it]
 99%|█████████▊| 60977/61904 [7:59:51<20:18,  1.31s/it]
 99%|█████████▊| 60978/61904 [7:59:52<21:26,  1.39s/it]
 99%|█████████▊| 60979/61904 [7:59:54<21:17,  1.38s/it]
 99%|█████████▊| 60980/61904 [7:59:55<20:45,  1.35s/it]
                                                       
{'loss': 2.4428, 'learning_rate': 1.0149747180085569e-07, 'epoch': 15.76}
+
 99%|█████████▊| 60980/61904 [7:59:55<20:45,  1.35s/it]
 99%|█████████▊| 60981/61904 [7:59:56<20:21,  1.32s/it]
 99%|█████████▊| 60982/61904 [7:59:57<20:26,  1.33s/it]
 99%|█████████▊| 60983/61904 [7:59:59<20:54,  1.36s/it]
 99%|█████████▊| 60984/61904 [8:00:00<21:16,  1.39s/it]
 99%|█████████▊| 60985/61904 [8:00:02<21:21,  1.39s/it]
 99%|█████████▊| 60986/61904 [8:00:03<21:16,  1.39s/it]
 99%|█████████▊| 60987/61904 [8:00:04<20:59,  1.37s/it]
 99%|█████████▊| 60988/61904 [8:00:06<20:26,  1.34s/it]
 99%|█████████▊| 60989/61904 [8:00:07<21:24,  1.40s/it]
 99%|█████████▊| 60990/61904 [8:00:09<20:56,  1.38s/it]
 99%|█████████▊| 60991/61904 [8:00:10<21:29,  1.41s/it]
 99%|█████████▊| 60992/61904 [8:00:12<21:47,  1.43s/it]
 99%|█████████▊| 60993/61904 [8:00:13<21:20,  1.41s/it]
 99%|█████████▊| 60994/61904 [8:00:14<21:19,  1.41s/it]
 99%|█████████▊| 60995/61904 [8:00:16<21:28,  1.42s/it]
 99%|█████████▊| 60996/61904 [8:00:17<22:11,  1.47s/it]
 99%|█████████▊| 60997/61904 [8:00:19<21:36,  1.43s/it]
 99%|█████████▊| 60998/61904 [8:00:20<21:08,  1.40s/it]
 99%|█████████▊| 60999/61904 [8:00:21<21:21,  1.42s/it]
 99%|█████████▊| 61000/61904 [8:00:23<20:25,  1.36s/it]
                                                       
{'loss': 2.4303, 'learning_rate': 1.0146505899131335e-07, 'epoch': 15.77}
+
 99%|█████████▊| 61000/61904 [8:00:23<20:25,  1.36s/it]
 99%|█████████▊| 61001/61904 [8:00:24<20:31,  1.36s/it]
 99%|█████████▊| 61002/61904 [8:00:25<20:25,  1.36s/it]
 99%|█████████▊| 61003/61904 [8:00:27<20:46,  1.38s/it]
 99%|█████████▊| 61004/61904 [8:00:28<21:11,  1.41s/it]
 99%|█████████▊| 61005/61904 [8:00:30<21:05,  1.41s/it]
 99%|█████████▊| 61006/61904 [8:00:31<21:02,  1.41s/it]
 99%|█████████▊| 61007/61904 [8:00:33<20:47,  1.39s/it]
 99%|█████████▊| 61008/61904 [8:00:34<21:17,  1.43s/it]
 99%|█████████▊| 61009/61904 [8:00:36<21:45,  1.46s/it]
 99%|█████████▊| 61010/61904 [8:00:37<21:14,  1.43s/it]
 99%|█████████▊| 61011/61904 [8:00:38<21:34,  1.45s/it]
 99%|█████████▊| 61012/61904 [8:00:40<20:51,  1.40s/it]
 99%|█████████▊| 61013/61904 [8:00:41<20:04,  1.35s/it]
 99%|█████████▊| 61014/61904 [8:00:42<20:19,  1.37s/it]
 99%|█████████▊| 61015/61904 [8:00:44<19:51,  1.34s/it]
 99%|█████████▊| 61016/61904 [8:00:45<19:56,  1.35s/it]
 99%|█████████▊| 61017/61904 [8:00:46<19:33,  1.32s/it]
 99%|█████████▊| 61018/61904 [8:00:48<20:51,  1.41s/it]
 99%|█████████▊| 61019/61904 [8:00:49<20:23,  1.38s/it]
 99%|█████████▊| 61020/61904 [8:00:50<19:44,  1.34s/it]
                                                       
{'loss': 2.385, 'learning_rate': 1.0143264618177103e-07, 'epoch': 15.77}
+
 99%|█████████▊| 61020/61904 [8:00:50<19:44,  1.34s/it]
 99%|█████████▊| 61021/61904 [8:00:52<19:37,  1.33s/it]
 99%|█████████��| 61022/61904 [8:00:53<20:22,  1.39s/it]
 99%|█████████▊| 61023/61904 [8:00:55<19:52,  1.35s/it]
 99%|█████████▊| 61024/61904 [8:00:56<19:37,  1.34s/it]
 99%|█████████▊| 61025/61904 [8:00:57<19:15,  1.31s/it]
 99%|█████████▊| 61026/61904 [8:00:58<19:28,  1.33s/it]
 99%|█████████▊| 61027/61904 [8:01:00<19:47,  1.35s/it]
 99%|█████████▊| 61028/61904 [8:01:01<20:16,  1.39s/it]
 99%|█████████▊| 61029/61904 [8:01:03<20:31,  1.41s/it]
 99%|█████████▊| 61030/61904 [8:01:04<20:49,  1.43s/it]
 99%|█████████▊| 61031/61904 [8:01:06<20:18,  1.40s/it]
 99%|█████████▊| 61032/61904 [8:01:07<20:12,  1.39s/it]
 99%|█████████▊| 61033/61904 [8:01:08<20:25,  1.41s/it]
 99%|█████████▊| 61034/61904 [8:01:10<19:34,  1.35s/it]
 99%|█████████▊| 61035/61904 [8:01:11<19:40,  1.36s/it]
 99%|█████████▊| 61036/61904 [8:01:12<19:27,  1.34s/it]
 99%|█████████▊| 61037/61904 [8:01:14<19:55,  1.38s/it]
 99%|█████████▊| 61038/61904 [8:01:15<20:51,  1.45s/it]
 99%|█████████▊| 61039/61904 [8:01:17<20:08,  1.40s/it]
 99%|█████████▊| 61040/61904 [8:01:18<20:06,  1.40s/it]
                                                       
{'loss': 2.4281, 'learning_rate': 1.0140023337222869e-07, 'epoch': 15.78}
+
 99%|█████████▊| 61040/61904 [8:01:18<20:06,  1.40s/it]
 99%|█████████▊| 61041/61904 [8:01:19<19:44,  1.37s/it]
 99%|█████████▊| 61042/61904 [8:01:21<20:21,  1.42s/it]
 99%|█████████▊| 61043/61904 [8:01:22<20:38,  1.44s/it]
 99%|█████████▊| 61044/61904 [8:01:24<20:24,  1.42s/it]
 99%|█████████▊| 61045/61904 [8:01:25<20:11,  1.41s/it]
 99%|█████████▊| 61046/61904 [8:01:26<19:45,  1.38s/it]
 99%|█████████▊| 61047/61904 [8:01:28<19:54,  1.39s/it]
 99%|█████████▊| 61048/61904 [8:01:29<20:09,  1.41s/it]
 99%|█████████▊| 61049/61904 [8:01:31<19:43,  1.38s/it]
 99%|█████████▊| 61050/61904 [8:01:32<19:39,  1.38s/it]
 99%|█████████▊| 61051/61904 [8:01:33<19:09,  1.35s/it]
 99%|█████████▊| 61052/61904 [8:01:35<19:20,  1.36s/it]
 99%|█████████▊| 61053/61904 [8:01:36<19:12,  1.35s/it]
 99%|█████████▊| 61054/61904 [8:01:37<19:11,  1.36s/it]
 99%|█████████▊| 61055/61904 [8:01:39<19:11,  1.36s/it]
 99%|█████████▊| 61056/61904 [8:01:40<18:49,  1.33s/it]
 99%|█████████▊| 61057/61904 [8:01:41<18:50,  1.33s/it]
 99%|█████████▊| 61058/61904 [8:01:43<19:46,  1.40s/it]
 99%|█████████▊| 61059/61904 [8:01:44<19:16,  1.37s/it]
 99%|█████████▊| 61060/61904 [8:01:46<19:32,  1.39s/it]
                                                       
{'loss': 2.4551, 'learning_rate': 1.0136782056268636e-07, 'epoch': 15.78}
+
 99%|█████████▊| 61060/61904 [8:01:46<19:32,  1.39s/it]
 99%|█████████▊| 61061/61904 [8:01:47<18:53,  1.34s/it]
 99%|█████████▊| 61062/61904 [8:01:48<18:28,  1.32s/it]
 99%|█████████▊| 61063/61904 [8:01:49<18:12,  1.30s/it]
 99%|█████████▊| 61064/61904 [8:01:51<18:28,  1.32s/it]
 99%|█████████▊| 61065/61904 [8:01:52<18:53,  1.35s/it]
 99%|█████████▊| 61066/61904 [8:01:53<18:27,  1.32s/it]
 99%|█████████▊| 61067/61904 [8:01:55<18:22,  1.32s/it]
 99%|█████████▊| 61068/61904 [8:01:56<18:18,  1.31s/it]
 99%|█████████▊| 61069/61904 [8:01:57<18:20,  1.32s/it]
 99%|█████████▊| 61070/61904 [8:01:59<18:29,  1.33s/it]
 99%|█████████▊| 61071/61904 [8:02:00<18:16,  1.32s/it]
 99%|█████████▊| 61072/61904 [8:02:01<18:36,  1.34s/it]
 99%|█████████▊| 61073/61904 [8:02:03<18:22,  1.33s/it]
 99%|█████████▊| 61074/61904 [8:02:04<18:22,  1.33s/it]
 99%|█████████▊| 61075/61904 [8:02:05<18:39,  1.35s/it]
 99%|█████████▊| 61076/61904 [8:02:07<18:45,  1.36s/it]
 99%|█████████▊| 61077/61904 [8:02:08<18:27,  1.34s/it]
 99%|█████████▊| 61078/61904 [8:02:09<18:19,  1.33s/it]
 99%|█████████▊| 61079/61904 [8:02:11<18:38,  1.36s/it]
 99%|█████████▊| 61080/61904 [8:02:12<18:18,  1.33s/it]
                                                       
{'loss': 2.4592, 'learning_rate': 1.0133540775314404e-07, 'epoch': 15.79}
+
 99%|█████████▊| 61080/61904 [8:02:12<18:18,  1.33s/it]
 99%|█████████▊| 61081/61904 [8:02:14<18:32,  1.35s/it]
 99%|█████████▊| 61082/61904 [8:02:15<18:01,  1.32s/it]
 99%|█████████▊| 61083/61904 [8:02:16<17:53,  1.31s/it]
 99%|█████████▊| 61084/61904 [8:02:17<18:09,  1.33s/it]
 99%|█████████▊| 61085/61904 [8:02:19<19:02,  1.40s/it]
 99%|█████████▊| 61086/61904 [8:02:20<18:55,  1.39s/it]
 99%|█████████▊| 61087/61904 [8:02:22<19:08,  1.41s/it]
 99%|█████████▊| 61088/61904 [8:02:23<19:03,  1.40s/it]
 99%|█████████▊| 61089/61904 [8:02:25<19:18,  1.42s/it]
 99%|█████████▊| 61090/61904 [8:02:26<19:13,  1.42s/it]
 99%|█████████▊| 61091/61904 [8:02:27<18:56,  1.40s/it]
 99%|█████████▊| 61092/61904 [8:02:29<18:40,  1.38s/it]
 99%|█████████▊| 61093/61904 [8:02:30<18:27,  1.37s/it]
 99%|█████████▊| 61094/61904 [8:02:31<18:23,  1.36s/it]
 99%|█████████▊| 61095/61904 [8:02:33<18:36,  1.38s/it]
 99%|█████████▊| 61096/61904 [8:02:34<18:03,  1.34s/it]
 99%|█████████▊| 61097/61904 [8:02:35<17:51,  1.33s/it]
 99%|█████████▊| 61098/61904 [8:02:37<17:36,  1.31s/it]
 99%|█████████▊| 61099/61904 [8:02:38<17:39,  1.32s/it]
 99%|█████████▊| 61100/61904 [8:02:39<17:45,  1.32s/it]
                                                       
{'loss': 2.4028, 'learning_rate': 1.013029949436017e-07, 'epoch': 15.79}
+
 99%|█████████▊| 61100/61904 [8:02:39<17:45,  1.32s/it]
 99%|█████████▊| 61101/61904 [8:02:41<17:46,  1.33s/it]
 99%|█████████▊| 61102/61904 [8:02:42<17:50,  1.33s/it]
 99%|█████████▊| 61103/61904 [8:02:43<17:59,  1.35s/it]
 99%|█████████▊| 61104/61904 [8:02:45<17:46,  1.33s/it]
 99%|█████████▊| 61105/61904 [8:02:46<17:36,  1.32s/it]
 99%|█████████▊| 61106/61904 [8:02:47<17:44,  1.33s/it]
 99%|█████████▊| 61107/61904 [8:02:49<17:40,  1.33s/it]
 99%|█████████▊| 61108/61904 [8:02:50<17:54,  1.35s/it]
 99%|█████████▊| 61109/61904 [8:02:51<17:50,  1.35s/it]
 99%|█████████▊| 61110/61904 [8:02:53<18:16,  1.38s/it]
 99%|█████████▊| 61111/61904 [8:02:54<18:26,  1.39s/it]
 99%|█████████▊| 61112/61904 [8:02:56<18:47,  1.42s/it]
 99%|█████████▊| 61113/61904 [8:02:57<18:45,  1.42s/it]
 99%|█████████▊| 61114/61904 [8:02:59<18:10,  1.38s/it]
 99%|█████████▊| 61115/61904 [8:03:00<18:14,  1.39s/it]
 99%|█████████▊| 61116/61904 [8:03:01<18:11,  1.38s/it]
 99%|█████████▊| 61117/61904 [8:03:03<17:57,  1.37s/it]
 99%|█████████▊| 61118/61904 [8:03:04<17:42,  1.35s/it]
 99%|█████████▊| 61119/61904 [8:03:05<17:45,  1.36s/it]
 99%|█████████▊| 61120/61904 [8:03:07<17:16,  1.32s/it]
                                                       
{'loss': 2.466, 'learning_rate': 1.0127058213405936e-07, 'epoch': 15.8}
+
 99%|█████████▊| 61120/61904 [8:03:07<17:16,  1.32s/it]
 99%|█████████▊| 61121/61904 [8:03:08<17:24,  1.33s/it]
 99%|█████████▊| 61122/61904 [8:03:09<17:56,  1.38s/it]
 99%|█████████▊| 61123/61904 [8:03:11<18:05,  1.39s/it]
 99%|█████████▊| 61124/61904 [8:03:12<18:20,  1.41s/it]
 99%|█████████▊| 61125/61904 [8:03:14<18:07,  1.40s/it]
 99%|█████████▊| 61126/61904 [8:03:15<18:04,  1.39s/it]
 99%|█████████▊| 61127/61904 [8:03:16<17:43,  1.37s/it]
 99%|█████████▊| 61128/61904 [8:03:18<17:32,  1.36s/it]
 99%|█████████▊| 61129/61904 [8:03:19<18:06,  1.40s/it]
 99%|█████████▊| 61130/61904 [8:03:21<17:46,  1.38s/it]
 99%|█████████▉| 61131/61904 [8:03:22<18:30,  1.44s/it]
 99%|█████████▉| 61132/61904 [8:03:23<18:05,  1.41s/it]
 99%|█████████▉| 61133/61904 [8:03:25<18:12,  1.42s/it]
 99%|█████████▉| 61134/61904 [8:03:26<18:29,  1.44s/it]
 99%|█████████▉| 61135/61904 [8:03:28<18:05,  1.41s/it]
 99%|█████████▉| 61136/61904 [8:03:29<18:28,  1.44s/it]
 99%|█████████▉| 61137/61904 [8:03:31<18:21,  1.44s/it]
 99%|█████████▉| 61138/61904 [8:03:32<17:46,  1.39s/it]
 99%|█████████▉| 61139/61904 [8:03:33<17:38,  1.38s/it]
 99%|█████████▉| 61140/61904 [8:03:35<17:47,  1.40s/it]
                                                       
{'loss': 2.4135, 'learning_rate': 1.0123816932451704e-07, 'epoch': 15.8}
+
 99%|█████████▉| 61140/61904 [8:03:35<17:47,  1.40s/it]
 99%|█████████▉| 61141/61904 [8:03:36<17:26,  1.37s/it]
 99%|█████████▉| 61142/61904 [8:03:37<16:57,  1.33s/it]
 99%|█████████▉| 61143/61904 [8:03:39<17:17,  1.36s/it]
 99%|█████████▉| 61144/61904 [8:03:40<17:30,  1.38s/it]
 99%|█████████▉| 61145/61904 [8:03:42<17:40,  1.40s/it]
 99%|█████████▉| 61146/61904 [8:03:43<17:02,  1.35s/it]
 99%|█████████▉| 61147/61904 [8:03:44<17:00,  1.35s/it]
 99%|█████████▉| 61148/61904 [8:03:46<17:02,  1.35s/it]
 99%|█████████▉| 61149/61904 [8:03:47<17:09,  1.36s/it]
 99%|█████████▉| 61150/61904 [8:03:48<17:42,  1.41s/it]
 99%|█████████▉| 61151/61904 [8:03:50<16:59,  1.35s/it]
 99%|█████████▉| 61152/61904 [8:03:51<16:22,  1.31s/it]
 99%|█████████▉| 61153/61904 [8:03:52<16:23,  1.31s/it]
 99%|█████████▉| 61154/61904 [8:03:53<16:21,  1.31s/it]
 99%|█████████▉| 61155/61904 [8:03:55<16:22,  1.31s/it]
 99%|█████████▉| 61156/61904 [8:03:56<16:57,  1.36s/it]
 99%|█████████▉| 61157/61904 [8:03:58<16:40,  1.34s/it]
 99%|█████████▉| 61158/61904 [8:03:59<16:56,  1.36s/it]
 99%|█████████▉| 61159/61904 [8:04:00<16:32,  1.33s/it]
 99%|█████████▉| 61160/61904 [8:04:02<16:21,  1.32s/it]
                                                       
{'loss': 2.3495, 'learning_rate': 1.0120575651497471e-07, 'epoch': 15.81}
+
 99%|█████████▉| 61160/61904 [8:04:02<16:21,  1.32s/it]
 99%|█████████▉| 61161/61904 [8:04:03<16:06,  1.30s/it]
 99%|█████████▉| 61162/61904 [8:04:04<16:18,  1.32s/it]
 99%|█████████▉| 61163/61904 [8:04:05<16:10,  1.31s/it]
 99%|█████████▉| 61164/61904 [8:04:07<15:57,  1.29s/it]
 99%|█████████▉| 61165/61904 [8:04:08<15:55,  1.29s/it]
 99%|█████████▉| 61166/61904 [8:04:09<16:17,  1.32s/it]
 99%|█████████▉| 61167/61904 [8:04:11<16:44,  1.36s/it]
 99%|█████████▉| 61168/61904 [8:04:12<16:35,  1.35s/it]
 99%|█████████▉| 61169/61904 [8:04:14<16:46,  1.37s/it]
 99%|█████████▉| 61170/61904 [8:04:15<16:56,  1.39s/it]
 99%|█████████▉| 61171/61904 [8:04:16<16:42,  1.37s/it]
 99%|█████████▉| 61172/61904 [8:04:18<16:34,  1.36s/it]
 99%|█████████▉| 61173/61904 [8:04:19<16:20,  1.34s/it]
 99%|█████████▉| 61174/61904 [8:04:20<16:22,  1.35s/it]
 99%|█████████▉| 61175/61904 [8:04:22<16:14,  1.34s/it]
 99%|█████████▉| 61176/61904 [8:04:23<16:33,  1.36s/it]
 99%|█████████▉| 61177/61904 [8:04:24<16:20,  1.35s/it]
 99%|█████████▉| 61178/61904 [8:04:26<16:39,  1.38s/it]
 99%|█████████▉| 61179/61904 [8:04:27<16:23,  1.36s/it]
 99%|█████████▉| 61180/61904 [8:04:28<16:16,  1.35s/it]
                                                       
{'loss': 2.435, 'learning_rate': 1.0117334370543237e-07, 'epoch': 15.81}
+
 99%|█████████▉| 61180/61904 [8:04:28<16:16,  1.35s/it]
 99%|█████████▉| 61181/61904 [8:04:30<16:57,  1.41s/it]
 99%|█████████▉| 61182/61904 [8:04:31<16:42,  1.39s/it]
 99%|█████████▉| 61183/61904 [8:04:33<17:12,  1.43s/it]
 99%|█████████▉| 61184/61904 [8:04:34<16:42,  1.39s/it]
 99%|█████████▉| 61185/61904 [8:04:36<16:59,  1.42s/it]
 99%|█████████▉| 61186/61904 [8:04:37<16:33,  1.38s/it]
 99%|█████████▉| 61187/61904 [8:04:38<16:18,  1.36s/it]
 99%|█████████▉| 61188/61904 [8:04:40<16:10,  1.35s/it]
 99%|█████████▉| 61189/61904 [8:04:41<16:00,  1.34s/it]
 99%|█████████▉| 61190/61904 [8:04:43<17:15,  1.45s/it]
 99%|█████████▉| 61191/61904 [8:04:44<16:58,  1.43s/it]
 99%|█████████▉| 61192/61904 [8:04:45<16:35,  1.40s/it]
 99%|█████████▉| 61193/61904 [8:04:47<16:42,  1.41s/it]
 99%|█████████▉| 61194/61904 [8:04:48<17:05,  1.44s/it]
 99%|█████████▉| 61195/61904 [8:04:50<16:32,  1.40s/it]
 99%|█████████▉| 61196/61904 [8:04:51<16:10,  1.37s/it]
 99%|█████████▉| 61197/61904 [8:04:52<16:11,  1.37s/it]
 99%|█████████▉| 61198/61904 [8:04:54<16:17,  1.38s/it]
 99%|█████████▉| 61199/61904 [8:04:55<16:13,  1.38s/it]
 99%|█████████▉| 61200/61904 [8:04:56<16:01,  1.37s/it]
                                                       
{'loss': 2.4339, 'learning_rate': 1.0114093089589004e-07, 'epoch': 15.82}
+
 99%|█████████▉| 61200/61904 [8:04:56<16:01,  1.37s/it]
 99%|█████████▉| 61201/61904 [8:04:58<15:39,  1.34s/it]
 99%|█████████▉| 61202/61904 [8:04:59<15:44,  1.35s/it]
 99%|█████████▉| 61203/61904 [8:05:00<15:21,  1.31s/it]
 99%|█████████▉| 61204/61904 [8:05:01<15:08,  1.30s/it]
 99%|█████████▉| 61205/61904 [8:05:03<15:00,  1.29s/it]
 99%|█████████▉| 61206/61904 [8:05:04<15:24,  1.32s/it]
 99%|█████████▉| 61207/61904 [8:05:06<16:14,  1.40s/it]
 99%|█████████▉| 61208/61904 [8:05:07<16:00,  1.38s/it]
 99%|█████████▉| 61209/61904 [8:05:09<16:46,  1.45s/it]
 99%|█████████▉| 61210/61904 [8:05:10<16:49,  1.46s/it]
 99%|█████████▉| 61211/61904 [8:05:11<16:07,  1.40s/it]
 99%|█████████▉| 61212/61904 [8:05:13<16:03,  1.39s/it]
 99%|█████████▉| 61213/61904 [8:05:14<15:55,  1.38s/it]
 99%|█████████▉| 61214/61904 [8:05:15<15:40,  1.36s/it]
 99%|█████████▉| 61215/61904 [8:05:17<15:38,  1.36s/it]
 99%|█████████▉| 61216/61904 [8:05:18<15:25,  1.34s/it]
 99%|█████████▉| 61217/61904 [8:05:20<15:39,  1.37s/it]
 99%|█████████▉| 61218/61904 [8:05:21<15:47,  1.38s/it]
 99%|█████████▉| 61219/61904 [8:05:22<15:31,  1.36s/it]
 99%|█████████▉| 61220/61904 [8:05:24<15:50,  1.39s/it]
                                                       
{'loss': 2.4557, 'learning_rate': 1.0110851808634771e-07, 'epoch': 15.82}
+
 99%|█████████▉| 61220/61904 [8:05:24<15:50,  1.39s/it]
 99%|█████████▉| 61221/61904 [8:05:25<15:33,  1.37s/it]
 99%|█████████▉| 61222/61904 [8:05:27<16:00,  1.41s/it]
 99%|█████████▉| 61223/61904 [8:05:28<16:25,  1.45s/it]
 99%|█████████▉| 61224/61904 [8:05:29<15:58,  1.41s/it]
 99%|█████████▉| 61225/61904 [8:05:31<15:38,  1.38s/it]
 99%|█████████▉| 61226/61904 [8:05:32<15:30,  1.37s/it]
 99%|█████████▉| 61227/61904 [8:05:33<15:17,  1.35s/it]
 99%|█████████▉| 61228/61904 [8:05:35<15:49,  1.40s/it]
 99%|█████████▉| 61229/61904 [8:05:36<15:41,  1.39s/it]
 99%|█████████▉| 61230/61904 [8:05:38<15:44,  1.40s/it]
 99%|█████████▉| 61231/61904 [8:05:39<15:26,  1.38s/it]
 99%|█████████▉| 61232/61904 [8:05:40<14:59,  1.34s/it]
 99%|█████████▉| 61233/61904 [8:05:42<15:10,  1.36s/it]
 99%|█████████▉| 61234/61904 [8:05:43<15:25,  1.38s/it]
 99%|█████████▉| 61235/61904 [8:05:44<15:19,  1.37s/it]
 99%|█████████▉| 61236/61904 [8:05:46<15:19,  1.38s/it]
 99%|█████████▉| 61237/61904 [8:05:47<15:34,  1.40s/it]
 99%|█████████▉| 61238/61904 [8:05:49<15:37,  1.41s/it]
 99%|█████████▉| 61239/61904 [8:05:50<15:46,  1.42s/it]
 99%|█████████▉| 61240/61904 [8:05:52<16:13,  1.47s/it]
                                                       
{'loss': 2.4107, 'learning_rate': 1.0107610527680539e-07, 'epoch': 15.83}
+
 99%|█████████▉| 61240/61904 [8:05:52<16:13,  1.47s/it]
 99%|█████████▉| 61241/61904 [8:05:53<15:44,  1.42s/it]
 99%|█████████▉| 61242/61904 [8:05:54<15:34,  1.41s/it]
 99%|█████████▉| 61243/61904 [8:05:56<14:52,  1.35s/it]
 99%|█████████▉| 61244/61904 [8:05:57<15:01,  1.37s/it]
 99%|█████████▉| 61245/61904 [8:05:58<15:03,  1.37s/it]
 99%|█████████▉| 61246/61904 [8:06:00<14:44,  1.34s/it]
 99%|█████████▉| 61247/61904 [8:06:01<14:26,  1.32s/it]
 99%|█████████▉| 61248/61904 [8:06:02<14:33,  1.33s/it]
 99%|█████████▉| 61249/61904 [8:06:04<14:49,  1.36s/it]
 99%|█████████▉| 61250/61904 [8:06:05<14:54,  1.37s/it]
 99%|█████████▉| 61251/61904 [8:06:06<14:38,  1.35s/it]
 99%|█████████▉| 61252/61904 [8:06:08<14:52,  1.37s/it]
 99%|█████████▉| 61253/61904 [8:06:09<15:17,  1.41s/it]
 99%|█████████▉| 61254/61904 [8:06:11<15:03,  1.39s/it]
 99%|█████████▉| 61255/61904 [8:06:12<14:51,  1.37s/it]
 99%|█████████▉| 61256/61904 [8:06:14<15:20,  1.42s/it]
 99%|█████████▉| 61257/61904 [8:06:15<15:17,  1.42s/it]
 99%|█████████▉| 61258/61904 [8:06:16<15:25,  1.43s/it]
 99%|█████████▉| 61259/61904 [8:06:18<15:47,  1.47s/it]
 99%|█████████▉| 61260/61904 [8:06:19<15:22,  1.43s/it]
                                                       
{'loss': 2.424, 'learning_rate': 1.0104369246726305e-07, 'epoch': 15.83}
+
 99%|█████████▉| 61260/61904 [8:06:19<15:22,  1.43s/it]
 99%|█████████▉| 61261/61904 [8:06:21<15:15,  1.42s/it]
 99%|█████████▉| 61262/61904 [8:06:22<14:49,  1.39s/it]
 99%|█████████▉| 61263/61904 [8:06:23<14:29,  1.36s/it]
 99%|█████████▉| 61264/61904 [8:06:25<14:05,  1.32s/it]
 99%|█████████▉| 61265/61904 [8:06:26<14:10,  1.33s/it]
 99%|█████████▉| 61266/61904 [8:06:27<14:08,  1.33s/it]
 99%|█████████▉| 61267/61904 [8:06:29<14:04,  1.33s/it]
 99%|█████████▉| 61268/61904 [8:06:30<13:49,  1.30s/it]
 99%|█████████▉| 61269/61904 [8:06:31<14:08,  1.34s/it]
 99%|█████████▉| 61270/61904 [8:06:33<14:22,  1.36s/it]
 99%|█████████▉| 61271/61904 [8:06:34<14:46,  1.40s/it]
 99%|█████████▉| 61272/61904 [8:06:36<14:36,  1.39s/it]
 99%|█████████▉| 61273/61904 [8:06:37<15:14,  1.45s/it]
 99%|█████████▉| 61274/61904 [8:06:38<14:36,  1.39s/it]
 99%|█████████▉| 61275/61904 [8:06:40<14:37,  1.40s/it]
 99%|█████████▉| 61276/61904 [8:06:41<14:03,  1.34s/it]
 99%|█████████▉| 61277/61904 [8:06:43<14:26,  1.38s/it]
 99%|█████████▉| 61278/61904 [8:06:44<14:37,  1.40s/it]
 99%|█████████▉| 61279/61904 [8:06:45<14:18,  1.37s/it]
 99%|█████████▉| 61280/61904 [8:06:47<14:33,  1.40s/it]
                                                       
{'loss': 2.3895, 'learning_rate': 1.0101127965772071e-07, 'epoch': 15.84}
+
 99%|█████████▉| 61280/61904 [8:06:47<14:33,  1.40s/it]
 99%|█████████▉| 61281/61904 [8:06:48<14:20,  1.38s/it]
 99%|█████████▉| 61282/61904 [8:06:49<14:27,  1.39s/it]
 99%|█████████▉| 61283/61904 [8:06:51<14:45,  1.43s/it]
 99%|█████████▉| 61284/61904 [8:06:52<14:36,  1.41s/it]
 99%|█████████▉| 61285/61904 [8:06:54<14:22,  1.39s/it]
 99%|█████████▉| 61286/61904 [8:06:55<14:12,  1.38s/it]
 99%|█████████▉| 61287/61904 [8:06:56<13:57,  1.36s/it]
 99%|█████████▉| 61288/61904 [8:06:58<13:57,  1.36s/it]
 99%|█████████▉| 61289/61904 [8:06:59<13:55,  1.36s/it]
 99%|█████████▉| 61290/61904 [8:07:00<14:03,  1.37s/it]
 99%|█████████▉| 61291/61904 [8:07:02<14:13,  1.39s/it]
 99%|█████████▉| 61292/61904 [8:07:03<14:08,  1.39s/it]
 99%|█████████▉| 61293/61904 [8:07:05<14:18,  1.40s/it]
 99%|█████████▉| 61294/61904 [8:07:06<13:52,  1.36s/it]
 99%|█████████▉| 61295/61904 [8:07:07<13:42,  1.35s/it]
 99%|█████████▉| 61296/61904 [8:07:09<13:52,  1.37s/it]
 99%|█████████▉| 61297/61904 [8:07:10<13:44,  1.36s/it]
 99%|█████████▉| 61298/61904 [8:07:12<13:57,  1.38s/it]
 99%|█████████▉| 61299/61904 [8:07:13<13:59,  1.39s/it]
 99%|█████████▉| 61300/61904 [8:07:14<13:59,  1.39s/it]
                                                       
{'loss': 2.3533, 'learning_rate': 1.0097886684817838e-07, 'epoch': 15.84}
+
 99%|█████████▉| 61300/61904 [8:07:14<13:59,  1.39s/it]
 99%|█████████▉| 61301/61904 [8:07:16<13:46,  1.37s/it]
 99%|█████████▉| 61302/61904 [8:07:17<13:45,  1.37s/it]
 99%|█████████▉| 61303/61904 [8:07:19<14:11,  1.42s/it]
 99%|█████████▉| 61304/61904 [8:07:20<13:54,  1.39s/it]
 99%|█████████▉| 61305/61904 [8:07:21<13:55,  1.39s/it]
 99%|█████████▉| 61306/61904 [8:07:23<13:38,  1.37s/it]
 99%|█████████▉| 61307/61904 [8:07:24<13:09,  1.32s/it]
 99%|█████████▉| 61308/61904 [8:07:25<13:35,  1.37s/it]
 99%|█████████▉| 61309/61904 [8:07:27<13:17,  1.34s/it]
 99%|█████████▉| 61310/61904 [8:07:28<13:05,  1.32s/it]
 99%|█████████▉| 61311/61904 [8:07:29<13:15,  1.34s/it]
 99%|█████████▉| 61312/61904 [8:07:30<12:59,  1.32s/it]
 99%|█████████▉| 61313/61904 [8:07:32<12:54,  1.31s/it]
 99%|█████████▉| 61314/61904 [8:07:33<12:40,  1.29s/it]
 99%|█████████▉| 61315/61904 [8:07:34<12:58,  1.32s/it]
 99%|█████████▉| 61316/61904 [8:07:36<13:12,  1.35s/it]
 99%|█████████▉| 61317/61904 [8:07:37<13:44,  1.40s/it]
 99%|█████████▉| 61318/61904 [8:07:39<13:28,  1.38s/it]
 99%|█████████▉| 61319/61904 [8:07:40<13:44,  1.41s/it]
 99%|█████████▉| 61320/61904 [8:07:41<13:10,  1.35s/it]
                                                       
{'loss': 2.4579, 'learning_rate': 1.0094645403863606e-07, 'epoch': 15.85}
+
 99%|█████████▉| 61320/61904 [8:07:41<13:10,  1.35s/it]
 99%|█████████▉| 61321/61904 [8:07:43<13:21,  1.37s/it]
 99%|█████████▉| 61322/61904 [8:07:44<13:04,  1.35s/it]
 99%|█████████▉| 61323/61904 [8:07:45<13:08,  1.36s/it]
 99%|█████████▉| 61324/61904 [8:07:47<13:23,  1.38s/it]
 99%|█████████▉| 61325/61904 [8:07:48<13:35,  1.41s/it]
 99%|█████████▉| 61326/61904 [8:07:50<13:48,  1.43s/it]
 99%|█████████▉| 61327/61904 [8:07:51<13:40,  1.42s/it]
 99%|█████████▉| 61328/61904 [8:07:53<13:55,  1.45s/it]
 99%|█████████▉| 61329/61904 [8:07:54<13:38,  1.42s/it]
 99%|█████████▉| 61330/61904 [8:07:55<13:14,  1.38s/it]
 99%|█████████▉| 61331/61904 [8:07:57<13:32,  1.42s/it]
 99%|█████████▉| 61332/61904 [8:07:58<13:26,  1.41s/it]
 99%|█████████▉| 61333/61904 [8:08:00<12:59,  1.37s/it]
 99%|█████████▉| 61334/61904 [8:08:01<12:41,  1.34s/it]
 99%|█████████▉| 61335/61904 [8:08:02<12:54,  1.36s/it]
 99%|█████████▉| 61336/61904 [8:08:04<12:52,  1.36s/it]
 99%|█████████▉| 61337/61904 [8:08:05<12:53,  1.36s/it]
 99%|█████████▉| 61338/61904 [8:08:06<13:11,  1.40s/it]
 99%|█████████▉| 61339/61904 [8:08:08<13:06,  1.39s/it]
 99%|█████████▉| 61340/61904 [8:08:09<12:56,  1.38s/it]
                                                       
{'loss': 2.4648, 'learning_rate': 1.0091404122909372e-07, 'epoch': 15.85}
+
 99%|█████████▉| 61340/61904 [8:08:09<12:56,  1.38s/it]
 99%|█████████▉| 61341/61904 [8:08:10<12:34,  1.34s/it]
 99%|█████████▉| 61342/61904 [8:08:12<12:38,  1.35s/it]
 99%|█████████▉| 61343/61904 [8:08:13<12:50,  1.37s/it]
 99%|█████████▉| 61344/61904 [8:08:15<12:58,  1.39s/it]
 99%|█████████▉| 61345/61904 [8:08:16<13:16,  1.42s/it]
 99%|█████████▉| 61346/61904 [8:08:18<13:19,  1.43s/it]
 99%|█████████▉| 61347/61904 [8:08:19<13:05,  1.41s/it]
 99%|█████████▉| 61348/61904 [8:08:20<12:40,  1.37s/it]
 99%|█████████▉| 61349/61904 [8:08:22<12:36,  1.36s/it]
 99%|█████████▉| 61350/61904 [8:08:23<12:33,  1.36s/it]
 99%|█████████▉| 61351/61904 [8:08:24<12:32,  1.36s/it]
 99%|█████████▉| 61352/61904 [8:08:26<12:57,  1.41s/it]
 99%|█████████▉| 61353/61904 [8:08:27<12:38,  1.38s/it]
 99%|█████████▉| 61354/61904 [8:08:29<12:34,  1.37s/it]
 99%|█████████▉| 61355/61904 [8:08:30<12:28,  1.36s/it]
 99%|█████████▉| 61356/61904 [8:08:31<12:27,  1.36s/it]
 99%|█████████▉| 61357/61904 [8:08:33<12:25,  1.36s/it]
 99%|█████████▉| 61358/61904 [8:08:34<12:21,  1.36s/it]
 99%|█████████▉| 61359/61904 [8:08:35<12:20,  1.36s/it]
 99%|█████████▉| 61360/61904 [8:08:37<12:25,  1.37s/it]
                                                       
{'loss': 2.4004, 'learning_rate': 1.0088162841955138e-07, 'epoch': 15.86}
+
 99%|█████████▉| 61360/61904 [8:08:37<12:25,  1.37s/it]
 99%|█████████▉| 61361/61904 [8:08:38<11:56,  1.32s/it]
 99%|█████████▉| 61362/61904 [8:08:39<12:03,  1.34s/it]
 99%|█████████▉| 61363/61904 [8:08:41<12:28,  1.38s/it]
 99%|█████████▉| 61364/61904 [8:08:42<13:11,  1.47s/it]
 99%|█████████▉| 61365/61904 [8:08:44<12:43,  1.42s/it]
 99%|█████████▉| 61366/61904 [8:08:45<13:04,  1.46s/it]
 99%|█████████▉| 61367/61904 [8:08:47<12:37,  1.41s/it]
 99%|█████████▉| 61368/61904 [8:08:48<12:30,  1.40s/it]
 99%|█████████▉| 61369/61904 [8:08:49<12:17,  1.38s/it]
 99%|█████████▉| 61370/61904 [8:08:51<12:20,  1.39s/it]
 99%|█████████▉| 61371/61904 [8:08:52<12:38,  1.42s/it]
 99%|█████████▉| 61372/61904 [8:08:54<12:39,  1.43s/it]
 99%|█████████▉| 61373/61904 [8:08:55<12:29,  1.41s/it]
 99%|█████████▉| 61374/61904 [8:08:56<12:21,  1.40s/it]
 99%|█████████▉| 61375/61904 [8:08:58<12:33,  1.42s/it]
 99%|█████████▉| 61376/61904 [8:08:59<12:18,  1.40s/it]
 99%|█████████▉| 61377/61904 [8:09:01<12:15,  1.40s/it]
 99%|█████████▉| 61378/61904 [8:09:02<12:14,  1.40s/it]
 99%|█████████▉| 61379/61904 [8:09:03<11:46,  1.35s/it]
 99%|███��█████▉| 61380/61904 [8:09:04<11:27,  1.31s/it]
                                                       
{'loss': 2.4231, 'learning_rate': 1.0084921561000907e-07, 'epoch': 15.86}
+
 99%|█████████▉| 61380/61904 [8:09:04<11:27,  1.31s/it]
 99%|█████████▉| 61381/61904 [8:09:06<11:42,  1.34s/it]
 99%|█████████▉| 61382/61904 [8:09:07<11:59,  1.38s/it]
 99%|█████████▉| 61383/61904 [8:09:09<12:19,  1.42s/it]
 99%|█████████▉| 61384/61904 [8:09:10<12:26,  1.44s/it]
 99%|█████████▉| 61385/61904 [8:09:12<12:15,  1.42s/it]
 99%|█████████▉| 61386/61904 [8:09:13<12:01,  1.39s/it]
 99%|█████████▉| 61387/61904 [8:09:14<11:46,  1.37s/it]
 99%|█████████▉| 61388/61904 [8:09:16<11:55,  1.39s/it]
 99%|█████████▉| 61389/61904 [8:09:17<11:59,  1.40s/it]
 99%|█████████▉| 61390/61904 [8:09:19<11:56,  1.39s/it]
 99%|█████████▉| 61391/61904 [8:09:20<12:14,  1.43s/it]
 99%|█████████▉| 61392/61904 [8:09:22<12:26,  1.46s/it]
 99%|█████████▉| 61393/61904 [8:09:23<12:11,  1.43s/it]
 99%|█████████▉| 61394/61904 [8:09:24<11:57,  1.41s/it]
 99%|█████████▉| 61395/61904 [8:09:26<11:55,  1.41s/it]
 99%|█████████▉| 61396/61904 [8:09:27<11:40,  1.38s/it]
 99%|█████████▉| 61397/61904 [8:09:29<12:15,  1.45s/it]
 99%|█████████▉| 61398/61904 [8:09:30<11:55,  1.41s/it]
 99%|█████████▉| 61399/61904 [8:09:31<11:27,  1.36s/it]
 99%|█████████▉| 61400/61904 [8:09:33<11:32,  1.37s/it]
                                                       
{'loss': 2.4427, 'learning_rate': 1.0081680280046673e-07, 'epoch': 15.87}
+
 99%|█████████▉| 61400/61904 [8:09:33<11:32,  1.37s/it]
 99%|█████████▉| 61401/61904 [8:09:34<11:16,  1.35s/it]
 99%|█████████▉| 61402/61904 [8:09:35<11:24,  1.36s/it]
 99%|█████████▉| 61403/61904 [8:09:37<11:17,  1.35s/it]
 99%|█████████▉| 61404/61904 [8:09:38<11:37,  1.39s/it]
 99%|█████████▉| 61405/61904 [8:09:40<11:40,  1.40s/it]
 99%|█████████▉| 61406/61904 [8:09:41<11:19,  1.36s/it]
 99%|█████████▉| 61407/61904 [8:09:42<11:39,  1.41s/it]
 99%|█████████▉| 61408/61904 [8:09:44<11:37,  1.41s/it]
 99%|█████████▉| 61409/61904 [8:09:45<11:26,  1.39s/it]
 99%|█████████▉| 61410/61904 [8:09:46<11:18,  1.37s/it]
 99%|█████████▉| 61411/61904 [8:09:48<11:25,  1.39s/it]
 99%|█████████▉| 61412/61904 [8:09:49<11:13,  1.37s/it]
 99%|█████████▉| 61413/61904 [8:09:51<11:05,  1.36s/it]
 99%|█████████▉| 61414/61904 [8:09:52<10:54,  1.34s/it]
 99%|█████████▉| 61415/61904 [8:09:53<11:20,  1.39s/it]
 99%|█████████▉| 61416/61904 [8:09:55<11:14,  1.38s/it]
 99%|█████████▉| 61417/61904 [8:09:56<11:23,  1.40s/it]
 99%|█████████▉| 61418/61904 [8:09:57<11:15,  1.39s/it]
 99%|█████████▉| 61419/61904 [8:09:59<11:37,  1.44s/it]
 99%|█████████▉| 61420/61904 [8:10:01<11:58,  1.48s/it]
                                                       
{'loss': 2.4253, 'learning_rate': 1.007843899909244e-07, 'epoch': 15.87}
+
 99%|█████████▉| 61420/61904 [8:10:01<11:58,  1.48s/it]
 99%|█████████▉| 61421/61904 [8:10:02<11:50,  1.47s/it]
 99%|█████████▉| 61422/61904 [8:10:04<11:43,  1.46s/it]
 99%|█████████▉| 61423/61904 [8:10:05<11:33,  1.44s/it]
 99%|█████████▉| 61424/61904 [8:10:06<11:26,  1.43s/it]
 99%|█████████▉| 61425/61904 [8:10:08<11:17,  1.41s/it]
 99%|█████████▉| 61426/61904 [8:10:09<11:29,  1.44s/it]
 99%|█████████▉| 61427/61904 [8:10:11<11:34,  1.46s/it]
 99%|█████████▉| 61428/61904 [8:10:12<11:14,  1.42s/it]
 99%|█████████▉| 61429/61904 [8:10:13<11:17,  1.43s/it]
 99%|█████████▉| 61430/61904 [8:10:15<10:59,  1.39s/it]
 99%|█████████▉| 61431/61904 [8:10:16<11:13,  1.42s/it]
 99%|█████████▉| 61432/61904 [8:10:18<10:47,  1.37s/it]
 99%|█████████▉| 61433/61904 [8:10:19<10:50,  1.38s/it]
 99%|█████████▉| 61434/61904 [8:10:20<10:36,  1.35s/it]
 99%|█████████▉| 61435/61904 [8:10:22<10:27,  1.34s/it]
 99%|█████████▉| 61436/61904 [8:10:23<10:20,  1.33s/it]
 99%|█████████▉| 61437/61904 [8:10:24<10:09,  1.30s/it]
 99%|█████████▉| 61438/61904 [8:10:25<10:08,  1.31s/it]
 99%|█████████▉| 61439/61904 [8:10:27<10:32,  1.36s/it]
 99%|█████████▉| 61440/61904 [8:10:28<10:43,  1.39s/it]
                                                       
{'loss': 2.3745, 'learning_rate': 1.0075197718138206e-07, 'epoch': 15.88}
+
 99%|█████████▉| 61440/61904 [8:10:28<10:43,  1.39s/it]
 99%|█████████▉| 61441/61904 [8:10:30<10:41,  1.39s/it]
 99%|█████████▉| 61442/61904 [8:10:31<11:05,  1.44s/it]
 99%|█████████▉| 61443/61904 [8:10:33<11:19,  1.47s/it]
 99%|█████████▉| 61444/61904 [8:10:34<11:05,  1.45s/it]
 99%|█████████▉| 61445/61904 [8:10:36<10:54,  1.43s/it]
 99%|█████████▉| 61446/61904 [8:10:37<10:51,  1.42s/it]
 99%|█████████▉| 61447/61904 [8:10:38<10:53,  1.43s/it]
 99%|█████████▉| 61448/61904 [8:10:40<10:53,  1.43s/it]
 99%|█████████▉| 61449/61904 [8:10:41<10:50,  1.43s/it]
 99%|█████████▉| 61450/61904 [8:10:43<10:49,  1.43s/it]
 99%|█████████▉| 61451/61904 [8:10:44<10:34,  1.40s/it]
 99%|█████████▉| 61452/61904 [8:10:45<10:25,  1.38s/it]
 99%|█████████▉| 61453/61904 [8:10:47<10:04,  1.34s/it]
 99%|█████████▉| 61454/61904 [8:10:48<09:52,  1.32s/it]
 99%|█████████▉| 61455/61904 [8:10:49<10:11,  1.36s/it]
 99%|█████████▉| 61456/61904 [8:10:51<10:06,  1.35s/it]
 99%|█████████▉| 61457/61904 [8:10:52<10:01,  1.35s/it]
 99%|█████████▉| 61458/61904 [8:10:54<10:34,  1.42s/it]
 99%|█████████▉| 61459/61904 [8:10:55<10:26,  1.41s/it]
 99%|█████████▉| 61460/61904 [8:10:56<10:30,  1.42s/it]
                                                       
{'loss': 2.4168, 'learning_rate': 1.0071956437183975e-07, 'epoch': 15.88}
+
 99%|█████████▉| 61460/61904 [8:10:56<10:30,  1.42s/it]
 99%|█████████▉| 61461/61904 [8:10:58<10:48,  1.46s/it]
 99%|█████████▉| 61462/61904 [8:11:00<10:53,  1.48s/it]
 99%|█████████▉| 61463/61904 [8:11:01<10:24,  1.42s/it]
 99%|█████████▉| 61464/61904 [8:11:02<10:04,  1.37s/it]
 99%|█████████▉| 61465/61904 [8:11:03<09:54,  1.36s/it]
 99%|█████████▉| 61466/61904 [8:11:05<09:47,  1.34s/it]
 99%|█████████▉| 61467/61904 [8:11:06<09:53,  1.36s/it]
 99%|█████████▉| 61468/61904 [8:11:07<09:55,  1.37s/it]
 99%|█████████▉| 61469/61904 [8:11:09<10:05,  1.39s/it]
 99%|█████████▉| 61470/61904 [8:11:10<09:53,  1.37s/it]
 99%|█████████▉| 61471/61904 [8:11:12<09:45,  1.35s/it]
 99%|█████████▉| 61472/61904 [8:11:13<09:47,  1.36s/it]
 99%|█████████▉| 61473/61904 [8:11:14<09:45,  1.36s/it]
 99%|█████████▉| 61474/61904 [8:11:16<10:00,  1.40s/it]
 99%|█████████▉| 61475/61904 [8:11:17<10:11,  1.42s/it]
 99%|█████████▉| 61476/61904 [8:11:19<10:01,  1.40s/it]
 99%|█████████▉| 61477/61904 [8:11:20<09:53,  1.39s/it]
 99%|█████████▉| 61478/61904 [8:11:21<09:56,  1.40s/it]
 99%|█████████▉| 61479/61904 [8:11:23<09:41,  1.37s/it]
 99%|█████████▉| 61480/61904 [8:11:24<09:52,  1.40s/it]
                                                       
{'loss': 2.4033, 'learning_rate': 1.0068715156229741e-07, 'epoch': 15.89}
+
 99%|█████████▉| 61480/61904 [8:11:24<09:52,  1.40s/it]
 99%|█████████▉| 61481/61904 [8:11:25<09:35,  1.36s/it]
 99%|█████████▉| 61482/61904 [8:11:27<09:55,  1.41s/it]
 99%|█████████▉| 61483/61904 [8:11:28<09:37,  1.37s/it]
 99%|█████████▉| 61484/61904 [8:11:30<09:34,  1.37s/it]
 99%|█████████▉| 61485/61904 [8:11:31<09:12,  1.32s/it]
 99%|█████████▉| 61486/61904 [8:11:32<09:23,  1.35s/it]
 99%|█████████▉| 61487/61904 [8:11:34<09:29,  1.37s/it]
 99%|█████████▉| 61488/61904 [8:11:35<09:42,  1.40s/it]
 99%|█████████▉| 61489/61904 [8:11:37<09:42,  1.40s/it]
 99%|█████████▉| 61490/61904 [8:11:38<09:31,  1.38s/it]
 99%|█████████▉| 61491/61904 [8:11:39<09:20,  1.36s/it]
 99%|█████████▉| 61492/61904 [8:11:41<09:40,  1.41s/it]
 99%|█████████▉| 61493/61904 [8:11:42<09:46,  1.43s/it]
 99%|█████████▉| 61494/61904 [8:11:44<09:50,  1.44s/it]
 99%|█████████▉| 61495/61904 [8:11:45<09:32,  1.40s/it]
 99%|█████████▉| 61496/61904 [8:11:46<09:41,  1.43s/it]
 99%|█████████▉| 61497/61904 [8:11:48<09:43,  1.43s/it]
 99%|█████████▉| 61498/61904 [8:11:49<09:32,  1.41s/it]
 99%|█████████▉| 61499/61904 [8:11:51<09:50,  1.46s/it]
 99%|█████████▉| 61500/61904 [8:11:52<09:26,  1.40s/it]
                                                       
{'loss': 2.3622, 'learning_rate': 1.0065473875275507e-07, 'epoch': 15.89}
+
 99%|█████████▉| 61500/61904 [8:11:52<09:26,  1.40s/it]
 99%|█████████▉| 61501/61904 [8:11:53<09:16,  1.38s/it]
 99%|█████████▉| 61502/61904 [8:11:55<09:12,  1.37s/it]
 99%|█████████▉| 61503/61904 [8:11:56<09:08,  1.37s/it]
 99%|█████████▉| 61504/61904 [8:11:57<09:05,  1.36s/it]
 99%|█████████▉| 61505/61904 [8:11:59<09:11,  1.38s/it]
 99%|█████████▉| 61506/61904 [8:12:00<09:08,  1.38s/it]
 99%|█████████▉| 61507/61904 [8:12:02<09:25,  1.42s/it]
 99%|█████████▉| 61508/61904 [8:12:03<09:37,  1.46s/it]
 99%|█████████▉| 61509/61904 [8:12:05<09:21,  1.42s/it]
 99%|█████████▉| 61510/61904 [8:12:06<09:05,  1.38s/it]
 99%|█████████▉| 61511/61904 [8:12:07<08:59,  1.37s/it]
 99%|█████████▉| 61512/61904 [8:12:09<09:02,  1.38s/it]
 99%|█████████▉| 61513/61904 [8:12:10<09:05,  1.39s/it]
 99%|█████████▉| 61514/61904 [8:12:12<09:08,  1.41s/it]
 99%|█████████▉| 61515/61904 [8:12:13<09:07,  1.41s/it]
 99%|█████████▉| 61516/61904 [8:12:14<09:01,  1.39s/it]
 99%|█████████▉| 61517/61904 [8:12:16<08:58,  1.39s/it]
 99%|█████████▉| 61518/61904 [8:12:17<08:59,  1.40s/it]
 99%|█████████▉| 61519/61904 [8:12:18<08:51,  1.38s/it]
 99%|█████████▉| 61520/61904 [8:12:20<08:54,  1.39s/it]
                                                       
{'loss': 2.4244, 'learning_rate': 1.0062232594321273e-07, 'epoch': 15.9}
+
 99%|█████████▉| 61520/61904 [8:12:20<08:54,  1.39s/it]
 99%|█████████▉| 61521/61904 [8:12:22<09:17,  1.45s/it]
 99%|█████████▉| 61522/61904 [8:12:23<09:01,  1.42s/it]
 99%|█████████▉| 61523/61904 [8:12:24<08:46,  1.38s/it]
 99%|█████████▉| 61524/61904 [8:12:25<08:28,  1.34s/it]
 99%|█████████▉| 61525/61904 [8:12:27<08:50,  1.40s/it]
 99%|█████████▉| 61526/61904 [8:12:28<09:03,  1.44s/it]
 99%|█████████▉| 61527/61904 [8:12:30<08:49,  1.41s/it]
 99%|█████████▉| 61528/61904 [8:12:31<08:46,  1.40s/it]
 99%|█████████▉| 61529/61904 [8:12:32<08:35,  1.38s/it]
 99%|█████████▉| 61530/61904 [8:12:34<08:48,  1.41s/it]
 99%|█████████▉| 61531/61904 [8:12:36<09:01,  1.45s/it]
 99%|█████████▉| 61532/61904 [8:12:37<09:25,  1.52s/it]
 99%|█████████▉| 61533/61904 [8:12:39<09:13,  1.49s/it]
 99%|█████████▉| 61534/61904 [8:12:40<09:02,  1.47s/it]
 99%|█████████▉| 61535/61904 [8:12:42<09:02,  1.47s/it]
 99%|█████████▉| 61536/61904 [8:12:43<08:52,  1.45s/it]
 99%|█████████▉| 61537/61904 [8:12:44<08:36,  1.41s/it]
 99%|█████████▉| 61538/61904 [8:12:46<08:41,  1.43s/it]
 99%|█████████▉| 61539/61904 [8:12:47<08:40,  1.43s/it]
 99%|█████████▉| 61540/61904 [8:12:49<08:44,  1.44s/it]
                                                       
{'loss': 2.3934, 'learning_rate': 1.0058991313367042e-07, 'epoch': 15.91}
+
 99%|█████████▉| 61540/61904 [8:12:49<08:44,  1.44s/it]
 99%|█████████▉| 61541/61904 [8:12:50<08:49,  1.46s/it]
 99%|█████████▉| 61542/61904 [8:12:51<08:34,  1.42s/it]
 99%|█████████▉| 61543/61904 [8:12:53<08:36,  1.43s/it]
 99%|█████████▉| 61544/61904 [8:12:54<08:29,  1.41s/it]
 99%|█████████▉| 61545/61904 [8:12:56<08:14,  1.38s/it]
 99%|█████████▉| 61546/61904 [8:12:57<08:22,  1.40s/it]
 99%|█████████▉| 61547/61904 [8:12:58<08:16,  1.39s/it]
 99%|█████████▉| 61548/61904 [8:13:00<08:53,  1.50s/it]
 99%|█████████▉| 61549/61904 [8:13:02<08:43,  1.47s/it]
 99%|█████████▉| 61550/61904 [8:13:03<08:24,  1.42s/it]
 99%|█████████▉| 61551/61904 [8:13:04<08:25,  1.43s/it]
 99%|█████████▉| 61552/61904 [8:13:06<08:08,  1.39s/it]
 99%|█████████▉| 61553/61904 [8:13:07<08:15,  1.41s/it]
 99%|█████████▉| 61554/61904 [8:13:08<08:11,  1.40s/it]
 99%|█████████▉| 61555/61904 [8:13:10<08:07,  1.40s/it]
 99%|█████████▉| 61556/61904 [8:13:11<08:02,  1.39s/it]
 99%|█████████▉| 61557/61904 [8:13:13<08:07,  1.41s/it]
 99%|█████████▉| 61558/61904 [8:13:14<08:07,  1.41s/it]
 99%|█████████▉| 61559/61904 [8:13:15<07:52,  1.37s/it]
 99%|█████████▉| 61560/61904 [8:13:17<07:48,  1.36s/it]
                                                       
{'loss': 2.4082, 'learning_rate': 1.0055750032412808e-07, 'epoch': 15.91}
+
 99%|█████████▉| 61560/61904 [8:13:17<07:48,  1.36s/it]
 99%|█████████▉| 61561/61904 [8:13:18<07:52,  1.38s/it]
 99%|█████████▉| 61562/61904 [8:13:19<07:45,  1.36s/it]
 99%|█████████▉| 61563/61904 [8:13:21<07:46,  1.37s/it]
 99%|█████████▉| 61564/61904 [8:13:22<07:48,  1.38s/it]
 99%|█████████▉| 61565/61904 [8:13:24<07:55,  1.40s/it]
 99%|█████████▉| 61566/61904 [8:13:25<07:52,  1.40s/it]
 99%|█████████▉| 61567/61904 [8:13:26<07:42,  1.37s/it]
 99%|█████████▉| 61568/61904 [8:13:28<07:30,  1.34s/it]
 99%|█████████▉| 61569/61904 [8:13:29<07:41,  1.38s/it]
 99%|█████████▉| 61570/61904 [8:13:30<07:42,  1.39s/it]
 99%|█████████▉| 61571/61904 [8:13:32<07:27,  1.35s/it]
 99%|█████████▉| 61572/61904 [8:13:33<07:20,  1.33s/it]
 99%|█████████▉| 61573/61904 [8:13:35<07:38,  1.39s/it]
 99%|█████████▉| 61574/61904 [8:13:36<07:37,  1.39s/it]
 99%|█████████▉| 61575/61904 [8:13:37<07:37,  1.39s/it]
 99%|█████████▉| 61576/61904 [8:13:39<07:32,  1.38s/it]
 99%|█████████▉| 61577/61904 [8:13:40<07:36,  1.40s/it]
 99%|█████████▉| 61578/61904 [8:13:42<07:46,  1.43s/it]
 99%|█████████▉| 61579/61904 [8:13:43<07:34,  1.40s/it]
 99%|█████████▉| 61580/61904 [8:13:44<07:28,  1.38s/it]
                                                       
{'loss': 2.4445, 'learning_rate': 1.0052508751458574e-07, 'epoch': 15.92}
+
 99%|█████████▉| 61580/61904 [8:13:44<07:28,  1.38s/it]
 99%|█████████▉| 61581/61904 [8:13:46<07:19,  1.36s/it]
 99%|█████████▉| 61582/61904 [8:13:47<07:29,  1.40s/it]
 99%|█████████▉| 61583/61904 [8:13:48<07:27,  1.39s/it]
 99%|█████████▉| 61584/61904 [8:13:50<07:33,  1.42s/it]
 99%|█████████▉| 61585/61904 [8:13:51<07:33,  1.42s/it]
 99%|█████████▉| 61586/61904 [8:13:53<07:14,  1.37s/it]
 99%|█████████▉| 61587/61904 [8:13:54<07:16,  1.38s/it]
 99%|█████████▉| 61588/61904 [8:13:55<07:14,  1.37s/it]
 99%|█████████▉| 61589/61904 [8:13:57<07:11,  1.37s/it]
 99%|█████████▉| 61590/61904 [8:13:58<07:20,  1.40s/it]
 99%|█████████▉| 61591/61904 [8:14:00<07:17,  1.40s/it]
 99%|█████████▉| 61592/61904 [8:14:01<07:11,  1.38s/it]
 99%|█████████▉| 61593/61904 [8:14:02<07:05,  1.37s/it]
 99%|█████████▉| 61594/61904 [8:14:04<07:00,  1.36s/it]
100%|█████████▉| 61595/61904 [8:14:05<06:54,  1.34s/it]
100%|█████████▉| 61596/61904 [8:14:06<07:08,  1.39s/it]
100%|█████████▉| 61597/61904 [8:14:08<07:02,  1.37s/it]
100%|█████████▉| 61598/61904 [8:14:09<07:21,  1.44s/it]
100%|█████████▉| 61599/61904 [8:14:11<07:08,  1.41s/it]
100%|█████████▉| 61600/61904 [8:14:12<07:16,  1.44s/it]
                                                       
{'loss': 2.4324, 'learning_rate': 1.0049267470504342e-07, 'epoch': 15.92}
+
100%|█████████▉| 61600/61904 [8:14:12<07:16,  1.44s/it]
100%|█████████▉| 61601/61904 [8:14:14<07:08,  1.41s/it]
100%|█████████▉| 61602/61904 [8:14:15<07:01,  1.40s/it]
100%|█████████▉| 61603/61904 [8:14:16<06:54,  1.38s/it]
100%|█████████▉| 61604/61904 [8:14:18<06:45,  1.35s/it]
100%|█████████▉| 61605/61904 [8:14:19<06:41,  1.34s/it]
100%|█████████▉| 61606/61904 [8:14:20<06:54,  1.39s/it]
100%|█████████▉| 61607/61904 [8:14:22<06:49,  1.38s/it]
100%|█████████▉| 61608/61904 [8:14:23<06:39,  1.35s/it]
100%|█████████▉| 61609/61904 [8:14:24<06:50,  1.39s/it]
100%|█████████▉| 61610/61904 [8:14:26<06:46,  1.38s/it]
100%|█████████▉| 61611/61904 [8:14:27<06:44,  1.38s/it]
100%|█████████▉| 61612/61904 [8:14:29<06:44,  1.38s/it]
100%|█████████▉| 61613/61904 [8:14:30<06:37,  1.37s/it]
100%|█████████▉| 61614/61904 [8:14:31<06:38,  1.37s/it]
100%|█████████▉| 61615/61904 [8:14:33<06:36,  1.37s/it]
100%|█████████▉| 61616/61904 [8:14:34<06:27,  1.34s/it]
100%|█████████▉| 61617/61904 [8:14:35<06:25,  1.34s/it]
100%|█████████▉| 61618/61904 [8:14:37<06:47,  1.42s/it]
100%|█████████▉| 61619/61904 [8:14:38<06:39,  1.40s/it]
100%|█████████▉| 61620/61904 [8:14:40<06:36,  1.40s/it]
                                                       
{'loss': 2.3891, 'learning_rate': 1.004602618955011e-07, 'epoch': 15.93}
+
100%|█████████▉| 61620/61904 [8:14:40<06:36,  1.40s/it]
100%|█████████▉| 61621/61904 [8:14:41<06:40,  1.41s/it]
100%|█████████▉| 61622/61904 [8:14:42<06:34,  1.40s/it]
100%|█████████▉| 61623/61904 [8:14:44<06:36,  1.41s/it]
100%|█████████▉| 61624/61904 [8:14:45<06:33,  1.41s/it]
100%|█████████▉| 61625/61904 [8:14:46<06:12,  1.33s/it]
100%|█████████▉| 61626/61904 [8:14:48<06:22,  1.38s/it]
100%|█████████▉| 61627/61904 [8:14:49<06:21,  1.38s/it]
100%|█████████▉| 61628/61904 [8:14:51<06:21,  1.38s/it]
100%|█████████▉| 61629/61904 [8:14:52<06:27,  1.41s/it]
100%|█████████▉| 61630/61904 [8:14:54<06:23,  1.40s/it]
100%|█████████▉| 61631/61904 [8:14:55<06:23,  1.41s/it]
100%|█████████▉| 61632/61904 [8:14:57<06:32,  1.44s/it]
100%|█████████▉| 61633/61904 [8:14:58<06:27,  1.43s/it]
100%|█████████▉| 61634/61904 [8:14:59<06:24,  1.42s/it]
100%|█████████▉| 61635/61904 [8:15:01<06:13,  1.39s/it]
100%|█████████▉| 61636/61904 [8:15:02<06:06,  1.37s/it]
100%|█████████▉| 61637/61904 [8:15:03<06:07,  1.38s/it]
100%|█████████▉| 61638/61904 [8:15:05<06:08,  1.39s/it]
100%|█████████▉| 61639/61904 [8:15:06<06:09,  1.40s/it]
100%|█████████▉| 61640/61904 [8:15:07<06:00,  1.37s/it]
                                                       
{'loss': 2.4304, 'learning_rate': 1.0042784908595876e-07, 'epoch': 15.93}
+
100%|█████████▉| 61640/61904 [8:15:07<06:00,  1.37s/it]
100%|█████████▉| 61641/61904 [8:15:09<06:09,  1.41s/it]
100%|█████████▉| 61642/61904 [8:15:10<06:10,  1.41s/it]
100%|█████████▉| 61643/61904 [8:15:12<06:02,  1.39s/it]
100%|█████████▉| 61644/61904 [8:15:13<06:00,  1.39s/it]
100%|█████████▉| 61645/61904 [8:15:14<05:50,  1.35s/it]
100%|█████████▉| 61646/61904 [8:15:16<05:50,  1.36s/it]
100%|█████████▉| 61647/61904 [8:15:17<05:49,  1.36s/it]
100%|█████████▉| 61648/61904 [8:15:19<05:54,  1.38s/it]
100%|█████████▉| 61649/61904 [8:15:20<05:42,  1.34s/it]
100%|█████████▉| 61650/61904 [8:15:21<05:54,  1.40s/it]
100%|█████████▉| 61651/61904 [8:15:23<05:58,  1.42s/it]
100%|█████████▉| 61652/61904 [8:15:24<05:45,  1.37s/it]
100%|█████████▉| 61653/61904 [8:15:25<05:39,  1.35s/it]
100%|█████████▉| 61654/61904 [8:15:27<05:47,  1.39s/it]
100%|█████████▉| 61655/61904 [8:15:28<05:46,  1.39s/it]
100%|█████████▉| 61656/61904 [8:15:30<05:40,  1.37s/it]
100%|█████████▉| 61657/61904 [8:15:31<05:38,  1.37s/it]
100%|█████████▉| 61658/61904 [8:15:32<05:45,  1.40s/it]
100%|█████████▉| 61659/61904 [8:15:34<05:55,  1.45s/it]
100%|█████████▉| 61660/61904 [8:15:35<05:48,  1.43s/it]
                                                       
{'loss': 2.4452, 'learning_rate': 1.0039543627641642e-07, 'epoch': 15.94}
+
100%|█████████▉| 61660/61904 [8:15:35<05:48,  1.43s/it]
100%|█████████▉| 61661/61904 [8:15:37<05:41,  1.40s/it]
100%|█████████▉| 61662/61904 [8:15:38<05:40,  1.41s/it]
100%|█████████▉| 61663/61904 [8:15:39<05:33,  1.38s/it]
100%|█████████▉| 61664/61904 [8:15:41<05:25,  1.36s/it]
100%|█████████▉| 61665/61904 [8:15:42<05:35,  1.40s/it]
100%|█████████▉| 61666/61904 [8:15:44<05:23,  1.36s/it]
100%|█████████▉| 61667/61904 [8:15:45<05:26,  1.38s/it]
100%|█████████▉| 61668/61904 [8:15:46<05:23,  1.37s/it]
100%|█████████▉| 61669/61904 [8:15:48<05:40,  1.45s/it]
100%|█████████▉| 61670/61904 [8:15:49<05:37,  1.44s/it]
100%|█████████▉| 61671/61904 [8:15:51<05:28,  1.41s/it]
100%|█████████▉| 61672/61904 [8:15:52<05:18,  1.37s/it]
100%|█████████▉| 61673/61904 [8:15:53<05:14,  1.36s/it]
100%|█████████▉| 61674/61904 [8:15:55<05:15,  1.37s/it]
100%|█████████▉| 61675/61904 [8:15:56<05:14,  1.37s/it]
100%|█████████▉| 61676/61904 [8:15:58<05:25,  1.43s/it]
100%|█████████▉| 61677/61904 [8:15:59<05:21,  1.42s/it]
100%|█████████▉| 61678/61904 [8:16:00<05:15,  1.40s/it]
100%|█████████▉| 61679/61904 [8:16:02<05:10,  1.38s/it]
100%|█████████▉| 61680/61904 [8:16:03<05:08,  1.38s/it]
                                                       
{'loss': 2.4355, 'learning_rate': 1.003630234668741e-07, 'epoch': 15.94}
+
100%|█████████▉| 61680/61904 [8:16:03<05:08,  1.38s/it]
100%|█████████▉| 61681/61904 [8:16:04<05:00,  1.35s/it]
100%|█████████▉| 61682/61904 [8:16:06<05:14,  1.42s/it]
100%|█████████▉| 61683/61904 [8:16:07<05:14,  1.42s/it]
100%|█████████▉| 61684/61904 [8:16:09<05:13,  1.42s/it]
100%|█████████▉| 61685/61904 [8:16:10<05:05,  1.39s/it]
100%|█████████▉| 61686/61904 [8:16:12<05:07,  1.41s/it]
100%|█████████▉| 61687/61904 [8:16:13<05:10,  1.43s/it]
100%|█████████▉| 61688/61904 [8:16:14<05:05,  1.41s/it]
100%|█████████▉| 61689/61904 [8:16:16<04:51,  1.35s/it]
100%|█████████▉| 61690/61904 [8:16:17<04:56,  1.39s/it]
100%|█████████▉| 61691/61904 [8:16:19<05:03,  1.43s/it]
100%|█████████▉| 61692/61904 [8:16:20<04:52,  1.38s/it]
100%|█████████▉| 61693/61904 [8:16:21<04:52,  1.38s/it]
100%|█████████▉| 61694/61904 [8:16:23<04:55,  1.41s/it]
100%|█████████▉| 61695/61904 [8:16:24<04:55,  1.41s/it]
100%|█████████▉| 61696/61904 [8:16:26<04:49,  1.39s/it]
100%|█████████▉| 61697/61904 [8:16:27<04:47,  1.39s/it]
100%|█████████▉| 61698/61904 [8:16:28<04:50,  1.41s/it]
100%|█████████▉| 61699/61904 [8:16:30<04:50,  1.42s/it]
100%|█████████▉| 61700/61904 [8:16:31<04:55,  1.45s/it]
                                                       
{'loss': 2.3643, 'learning_rate': 1.0033061065733177e-07, 'epoch': 15.95}
+
100%|█████████▉| 61700/61904 [8:16:31<04:55,  1.45s/it]
100%|█████████▉| 61701/61904 [8:16:33<04:53,  1.45s/it]
100%|█████████▉| 61702/61904 [8:16:34<04:39,  1.38s/it]
100%|█████████▉| 61703/61904 [8:16:35<04:37,  1.38s/it]
100%|█████████▉| 61704/61904 [8:16:37<04:31,  1.36s/it]
100%|█████████▉| 61705/61904 [8:16:38<04:34,  1.38s/it]
100%|█████████▉| 61706/61904 [8:16:39<04:32,  1.38s/it]
100%|█████████▉| 61707/61904 [8:16:41<04:28,  1.36s/it]
100%|█████████▉| 61708/61904 [8:16:42<04:26,  1.36s/it]
100%|█████████▉| 61709/61904 [8:16:44<04:27,  1.37s/it]
100%|█████████▉| 61710/61904 [8:16:45<04:27,  1.38s/it]
100%|█████████▉| 61711/61904 [8:16:46<04:23,  1.37s/it]
100%|█████████▉| 61712/61904 [8:16:48<04:17,  1.34s/it]
100%|█████████▉| 61713/61904 [8:16:49<04:14,  1.33s/it]
100%|█████████▉| 61714/61904 [8:16:50<04:11,  1.32s/it]
100%|█████████▉| 61715/61904 [8:16:52<04:14,  1.35s/it]
100%|█████████▉| 61716/61904 [8:16:53<04:18,  1.37s/it]
100%|█████████▉| 61717/61904 [8:16:55<04:24,  1.41s/it]
100%|█████████▉| 61718/61904 [8:16:56<04:23,  1.42s/it]
100%|█████████▉| 61719/61904 [8:16:57<04:17,  1.39s/it]
100%|█████████▉| 61720/61904 [8:16:59<04:19,  1.41s/it]
                                                       
{'loss': 2.3778, 'learning_rate': 1.0029819784778943e-07, 'epoch': 15.95}
+
100%|█████████▉| 61720/61904 [8:16:59<04:19,  1.41s/it]
100%|█████████▉| 61721/61904 [8:17:00<04:21,  1.43s/it]
100%|█████████▉| 61722/61904 [8:17:02<04:15,  1.40s/it]
100%|█████████▉| 61723/61904 [8:17:03<04:08,  1.37s/it]
100%|█████████▉| 61724/61904 [8:17:04<04:13,  1.41s/it]
100%|█████████▉| 61725/61904 [8:17:06<04:06,  1.38s/it]
100%|█████████▉| 61726/61904 [8:17:07<04:03,  1.37s/it]
100%|█████████▉| 61727/61904 [8:17:08<04:07,  1.40s/it]
100%|█████████▉| 61728/61904 [8:17:10<04:06,  1.40s/it]
100%|█████████▉| 61729/61904 [8:17:11<04:03,  1.39s/it]
100%|█████████▉| 61730/61904 [8:17:13<04:08,  1.43s/it]
100%|█████████▉| 61731/61904 [8:17:14<04:05,  1.42s/it]
100%|█████████▉| 61732/61904 [8:17:16<04:08,  1.44s/it]
100%|█████████▉| 61733/61904 [8:17:17<04:04,  1.43s/it]
100%|█████████▉| 61734/61904 [8:17:18<03:56,  1.39s/it]
100%|███��█████▉| 61735/61904 [8:17:20<03:53,  1.38s/it]
100%|█████████▉| 61736/61904 [8:17:21<03:52,  1.39s/it]
100%|█████████▉| 61737/61904 [8:17:23<04:03,  1.46s/it]
100%|█████████▉| 61738/61904 [8:17:24<03:58,  1.44s/it]
100%|█████████▉| 61739/61904 [8:17:26<03:55,  1.42s/it]
100%|█████████▉| 61740/61904 [8:17:27<03:55,  1.44s/it]
                                                       
{'loss': 2.4225, 'learning_rate': 1.0026578503824709e-07, 'epoch': 15.96}
+
100%|█████████▉| 61740/61904 [8:17:27<03:55,  1.44s/it]
100%|█████████▉| 61741/61904 [8:17:28<03:48,  1.40s/it]
100%|█████████▉| 61742/61904 [8:17:30<03:50,  1.42s/it]
100%|█████████▉| 61743/61904 [8:17:31<03:46,  1.40s/it]
100%|█████████▉| 61744/61904 [8:17:33<03:48,  1.43s/it]
100%|█████████▉| 61745/61904 [8:17:34<04:02,  1.52s/it]
100%|█████████▉| 61746/61904 [8:17:36<04:01,  1.53s/it]
100%|█████████▉| 61747/61904 [8:17:37<03:55,  1.50s/it]
100%|█████████▉| 61748/61904 [8:17:39<03:44,  1.44s/it]
100%|█████████▉| 61749/61904 [8:17:40<03:35,  1.39s/it]
100%|█████████▉| 61750/61904 [8:17:41<03:33,  1.39s/it]
100%|█████████▉| 61751/61904 [8:17:43<03:32,  1.39s/it]
100%|█████████▉| 61752/61904 [8:17:44<03:31,  1.39s/it]
100%|█████████▉| 61753/61904 [8:17:45<03:26,  1.37s/it]
100%|█████████▉| 61754/61904 [8:17:47<03:24,  1.36s/it]
100%|█████████▉| 61755/61904 [8:17:48<03:26,  1.39s/it]
100%|█████████▉| 61756/61904 [8:17:50<03:22,  1.37s/it]
100%|█████████▉| 61757/61904 [8:17:51<03:21,  1.37s/it]
100%|█████████▉| 61758/61904 [8:17:52<03:27,  1.42s/it]
100%|█████████▉| 61759/61904 [8:17:54<03:21,  1.39s/it]
100%|█████████▉| 61760/61904 [8:17:55<03:19,  1.38s/it]
                                                       
{'loss': 2.374, 'learning_rate': 1.0023337222870478e-07, 'epoch': 15.96}
+
100%|█████████▉| 61760/61904 [8:17:55<03:19,  1.38s/it]
100%|█████████▉| 61761/61904 [8:17:56<03:14,  1.36s/it]
100%|█████████▉| 61762/61904 [8:17:58<03:17,  1.39s/it]
100%|█████████▉| 61763/61904 [8:17:59<03:20,  1.42s/it]
100%|█████████▉| 61764/61904 [8:18:01<03:13,  1.38s/it]
100%|█████████▉| 61765/61904 [8:18:02<03:08,  1.36s/it]
100%|█████████▉| 61766/61904 [8:18:03<03:11,  1.39s/it]
100%|█████████▉| 61767/61904 [8:18:05<03:03,  1.34s/it]
100%|█████████▉| 61768/61904 [8:18:06<03:03,  1.35s/it]
100%|█████████▉| 61769/61904 [8:18:07<03:03,  1.36s/it]
100%|█████████▉| 61770/61904 [8:18:09<03:02,  1.36s/it]
100%|█████████▉| 61771/61904 [8:18:10<02:57,  1.34s/it]
100%|█████████▉| 61772/61904 [8:18:12<03:01,  1.37s/it]
100%|█████████▉| 61773/61904 [8:18:13<02:58,  1.36s/it]
100%|█████████▉| 61774/61904 [8:18:14<02:56,  1.36s/it]
100%|█████████▉| 61775/61904 [8:18:16<02:55,  1.36s/it]
100%|█████████▉| 61776/61904 [8:18:17<02:56,  1.38s/it]
100%|█████████▉| 61777/61904 [8:18:19<03:00,  1.42s/it]
100%|█████████▉| 61778/61904 [8:18:20<02:57,  1.41s/it]
100%|█████████▉| 61779/61904 [8:18:21<02:54,  1.40s/it]
100%|█████████▉| 61780/61904 [8:18:23<02:46,  1.34s/it]
                                                       
{'loss': 2.4335, 'learning_rate': 1.0020095941916244e-07, 'epoch': 15.97}
+
100%|█████████▉| 61780/61904 [8:18:23<02:46,  1.34s/it]
100%|█████████▉| 61781/61904 [8:18:24<02:52,  1.40s/it]
100%|█████████▉| 61782/61904 [8:18:25<02:51,  1.41s/it]
100%|█████████▉| 61783/61904 [8:18:27<02:47,  1.38s/it]
100%|█████████▉| 61784/61904 [8:18:28<02:43,  1.36s/it]
100%|█████████▉| 61785/61904 [8:18:30<02:45,  1.39s/it]
100%|█████████▉| 61786/61904 [8:18:31<02:41,  1.37s/it]
100%|█████████▉| 61787/61904 [8:18:32<02:39,  1.36s/it]
100%|█████████▉| 61788/61904 [8:18:34<02:38,  1.37s/it]
100%|█████████▉| 61789/61904 [8:18:35<02:35,  1.35s/it]
100%|█████████▉| 61790/61904 [8:18:36<02:33,  1.34s/it]
100%|█████████▉| 61791/61904 [8:18:38<02:32,  1.35s/it]
100%|█████████▉| 61792/61904 [8:18:39<02:30,  1.35s/it]
100%|█████████▉| 61793/61904 [8:18:40<02:30,  1.35s/it]
100%|█████████▉| 61794/61904 [8:18:42<02:36,  1.42s/it]
100%|█████████▉| 61795/61904 [8:18:43<02:38,  1.46s/it]
100%|█████████▉| 61796/61904 [8:18:45<02:38,  1.46s/it]
100%|█████████▉| 61797/61904 [8:18:46<02:34,  1.45s/it]
100%|█████████▉| 61798/61904 [8:18:48<02:31,  1.43s/it]
100%|█████████▉| 61799/61904 [8:18:49<02:24,  1.37s/it]
100%|█████████▉| 61800/61904 [8:18:50<02:18,  1.33s/it]
                                                       
{'loss': 2.4207, 'learning_rate': 1.001685466096201e-07, 'epoch': 15.97}
+
100%|█████████▉| 61800/61904 [8:18:50<02:18,  1.33s/it]
100%|█████████▉| 61801/61904 [8:18:52<02:28,  1.45s/it]
100%|█████████▉| 61802/61904 [8:18:53<02:28,  1.45s/it]
100%|█████████▉| 61803/61904 [8:18:55<02:31,  1.50s/it]
100%|█████████▉| 61804/61904 [8:18:56<02:23,  1.44s/it]
100%|█████████▉| 61805/61904 [8:18:58<02:24,  1.46s/it]
100%|█████████▉| 61806/61904 [8:18:59<02:18,  1.42s/it]
100%|█████████▉| 61807/61904 [8:19:00<02:16,  1.41s/it]
100%|█████████▉| 61808/61904 [8:19:02<02:16,  1.42s/it]
100%|█████████▉| 61809/61904 [8:19:03<02:19,  1.47s/it]
100%|█████████▉| 61810/61904 [8:19:05<02:14,  1.43s/it]
100%|█████████▉| 61811/61904 [8:19:06<02:09,  1.39s/it]
100%|█████████▉| 61812/61904 [8:19:07<02:06,  1.37s/it]
100%|█████████▉| 61813/61904 [8:19:09<02:02,  1.35s/it]
100%|█████████▉| 61814/61904 [8:19:10<02:01,  1.35s/it]
100%|█████████▉| 61815/61904 [8:19:11<01:57,  1.32s/it]
100%|█████████▉| 61816/61904 [8:19:13<02:00,  1.36s/it]
100%|█████████▉| 61817/61904 [8:19:14<02:01,  1.40s/it]
100%|█████████▉| 61818/61904 [8:19:16<01:57,  1.37s/it]
100%|█████████▉| 61819/61904 [8:19:17<01:54,  1.34s/it]
100%|█████████▉| 61820/61904 [8:19:18<01:57,  1.39s/it]
                                                       
{'loss': 2.3516, 'learning_rate': 1.0013613380007777e-07, 'epoch': 15.98}
+
100%|█████████▉| 61820/61904 [8:19:18<01:57,  1.39s/it]
100%|█████████▉| 61821/61904 [8:19:20<01:57,  1.42s/it]
100%|█████████▉| 61822/61904 [8:19:21<01:54,  1.39s/it]
100%|█████████▉| 61823/61904 [8:19:23<01:55,  1.43s/it]
100%|█████████▉| 61824/61904 [8:19:24<01:52,  1.40s/it]
100%|█████████▉| 61825/61904 [8:19:26<01:52,  1.42s/it]
100%|█████████▉| 61826/61904 [8:19:27<01:50,  1.41s/it]
100%|█████████▉| 61827/61904 [8:19:28<01:49,  1.42s/it]
100%|█████████▉| 61828/61904 [8:19:30<01:46,  1.40s/it]
100%|█████████▉| 61829/61904 [8:19:31<01:45,  1.40s/it]
100%|█████████▉| 61830/61904 [8:19:33<01:43,  1.40s/it]
100%|█████████▉| 61831/61904 [8:19:34<01:42,  1.41s/it]
100%|█████████▉| 61832/61904 [8:19:35<01:41,  1.41s/it]
100%|█████████▉| 61833/61904 [8:19:37<01:40,  1.41s/it]
100%|█████████▉| 61834/61904 [8:19:38<01:34,  1.36s/it]
100%|█████████▉| 61835/61904 [8:19:39<01:32,  1.34s/it]
100%|█████████▉| 61836/61904 [8:19:41<01:33,  1.38s/it]
100%|█████████▉| 61837/61904 [8:19:42<01:31,  1.37s/it]
100%|█████████▉| 61838/61904 [8:19:43<01:30,  1.37s/it]
100%|█████████▉| 61839/61904 [8:19:45<01:26,  1.34s/it]
100%|█████████▉| 61840/61904 [8:19:46<01:29,  1.40s/it]
                                                       
{'loss': 2.4139, 'learning_rate': 1.0010372099053545e-07, 'epoch': 15.98}
+
100%|█████████▉| 61840/61904 [8:19:46<01:29,  1.40s/it]
100%|█████████▉| 61841/61904 [8:19:48<01:25,  1.36s/it]
100%|█████████▉| 61842/61904 [8:19:49<01:28,  1.43s/it]
100%|█████████▉| 61843/61904 [8:19:51<01:26,  1.42s/it]
100%|█████████▉| 61844/61904 [8:19:52<01:25,  1.43s/it]
100%|█████████▉| 61845/61904 [8:19:53<01:22,  1.40s/it]
100%|█████████▉| 61846/61904 [8:19:55<01:21,  1.40s/it]
100%|█████████▉| 61847/61904 [8:19:56<01:18,  1.38s/it]
100%|█████████▉| 61848/61904 [8:19:58<01:18,  1.39s/it]
100%|█████████▉| 61849/61904 [8:19:59<01:14,  1.35s/it]
100%|█████████▉| 61850/61904 [8:20:00<01:15,  1.39s/it]
100%|█████████▉| 61851/61904 [8:20:02<01:15,  1.42s/it]
100%|█████████▉| 61852/61904 [8:20:03<01:12,  1.39s/it]
100%|█████████▉| 61853/61904 [8:20:04<01:10,  1.37s/it]
100%|█████████▉| 61854/61904 [8:20:06<01:13,  1.47s/it]
100%|█████████▉| 61855/61904 [8:20:07<01:09,  1.41s/it]
100%|█████████▉| 61856/61904 [8:20:09<01:07,  1.40s/it]
100%|█████████▉| 61857/61904 [8:20:10<01:04,  1.38s/it]
100%|█████████▉| 61858/61904 [8:20:11<01:02,  1.35s/it]
100%|█████████▉| 61859/61904 [8:20:13<00:59,  1.33s/it]
100%|█████████▉| 61860/61904 [8:20:14<01:01,  1.40s/it]
                                                       
{'loss': 2.4381, 'learning_rate': 1.0007130818099312e-07, 'epoch': 15.99}
+
100%|█████████▉| 61860/61904 [8:20:14<01:01,  1.40s/it]
100%|█████████▉| 61861/61904 [8:20:15<00:58,  1.35s/it]
100%|█████████▉| 61862/61904 [8:20:17<00:56,  1.35s/it]
100%|█████████▉| 61863/61904 [8:20:18<00:56,  1.37s/it]
100%|█████████▉| 61864/61904 [8:20:20<00:54,  1.37s/it]
100%|█████████▉| 61865/61904 [8:20:21<00:54,  1.39s/it]
100%|█████████▉| 61866/61904 [8:20:22<00:53,  1.40s/it]
100%|█████████▉| 61867/61904 [8:20:24<00:52,  1.42s/it]
100%|█████████▉| 61868/61904 [8:20:25<00:50,  1.41s/it]
100%|█████████▉| 61869/61904 [8:20:27<00:48,  1.38s/it]
100%|█████████▉| 61870/61904 [8:20:28<00:46,  1.38s/it]
100%|█████████▉| 61871/61904 [8:20:29<00:44,  1.35s/it]
100%|█████████▉| 61872/61904 [8:20:31<00:44,  1.39s/it]
100%|█████████▉| 61873/61904 [8:20:32<00:43,  1.39s/it]
100%|█████████▉| 61874/61904 [8:20:33<00:41,  1.37s/it]
100%|█████████▉| 61875/61904 [8:20:35<00:40,  1.40s/it]
100%|█████████▉| 61876/61904 [8:20:36<00:38,  1.38s/it]
100%|█████████▉| 61877/61904 [8:20:38<00:37,  1.40s/it]
100%|█████████▉| 61878/61904 [8:20:39<00:36,  1.42s/it]
100%|█████████▉| 61879/61904 [8:20:41<00:35,  1.42s/it]
100%|█████████▉| 61880/61904 [8:20:42<00:33,  1.38s/it]
                                                       
{'loss': 2.4053, 'learning_rate': 1.0003889537145078e-07, 'epoch': 15.99}
+
100%|█████████▉| 61880/61904 [8:20:42<00:33,  1.38s/it]
100%|█████████▉| 61881/61904 [8:20:43<00:32,  1.41s/it]
100%|█████████▉| 61882/61904 [8:20:45<00:30,  1.40s/it]
100%|█████████▉| 61883/61904 [8:20:46<00:28,  1.37s/it]
100%|█████████▉| 61884/61904 [8:20:47<00:26,  1.35s/it]
100%|█████████▉| 61885/61904 [8:20:49<00:25,  1.33s/it]
100%|█████████▉| 61886/61904 [8:20:50<00:24,  1.35s/it]
100%|█████████▉| 61887/61904 [8:20:51<00:22,  1.32s/it]
100%|█████████▉| 61888/61904 [8:20:53<00:22,  1.40s/it]
100%|█████████▉| 61889/61904 [8:20:54<00:21,  1.41s/it]
100%|█████████▉| 61890/61904 [8:20:56<00:19,  1.42s/it]
100%|█████████▉| 61891/61904 [8:20:57<00:18,  1.43s/it]
100%|█████████▉| 61892/61904 [8:20:59<00:17,  1.44s/it]
100%|█████████▉| 61893/61904 [8:21:00<00:15,  1.44s/it]
100%|█████████▉| 61894/61904 [8:21:01<00:14,  1.42s/it]
100%|█████████▉| 61895/61904 [8:21:03<00:12,  1.44s/it]
100%|█████████▉| 61896/61904 [8:21:04<00:11,  1.43s/it]
100%|█████████▉| 61897/61904 [8:21:06<00:10,  1.49s/it]
100%|█████████▉| 61898/61904 [8:21:07<00:08,  1.44s/it]
100%|█████████▉| 61899/61904 [8:21:09<00:07,  1.44s/it]
100%|█████████▉| 61900/61904 [8:21:10<00:05,  1.40s/it]
                                                       
{'loss': 2.439, 'learning_rate': 1.0000648256190844e-07, 'epoch': 16.0}
+
100%|█████████▉| 61900/61904 [8:21:10<00:05,  1.40s/it]
100%|█████████▉| 61901/61904 [8:21:11<00:04,  1.41s/it]
100%|█████████▉| 61902/61904 [8:21:13<00:02,  1.40s/it]
100%|█████████▉| 61903/61904 [8:21:14<00:01,  1.36s/it]
100%|██████████| 61904/61904 [8:21:15<00:00,  1.35s/it][WARNING|configuration_utils.py:448] 2024-10-28 23:46:55,902 >> 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}
+Generation Kwargs:
+{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}
+/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()
+
+
  0%|          | 0/861 [00:00<?, ?it/s]
+
  0%|          | 2/861 [00:01<10:09,  1.41it/s]
+
  0%|          | 3/861 [00:03<18:10,  1.27s/it]
+
  0%|          | 4/861 [00:04<15:54,  1.11s/it]
+
  1%|          | 5/861 [00:05<15:28,  1.09s/it]
+
  1%|          | 6/861 [00:06<15:18,  1.07s/it]
+
  1%|          | 7/861 [00:06<12:27,  1.14it/s]
+
  1%|          | 8/861 [00:07<12:11,  1.17it/s]
+
  1%|          | 9/861 [00:08<11:29,  1.24it/s]
+
  1%|          | 10/861 [00:09<10:43,  1.32it/s]
+
  1%|▏         | 11/861 [00:10<14:54,  1.05s/it]
+
  1%|▏         | 12/861 [00:11<15:11,  1.07s/it]
+
  2%|▏         | 13/861 [00:12<14:21,  1.02s/it]
+
  2%|▏         | 14/861 [00:13<11:28,  1.23it/s]
+
  2%|▏         | 15/861 [00:13<11:24,  1.24it/s]
+
  2%|▏         | 16/861 [00:14<09:33,  1.47it/s]
+
  2%|▏         | 17/861 [00:15<12:25,  1.13it/s]
+
  2%|▏         | 18/861 [00:15<10:04,  1.39it/s]
+
  2%|▏         | 19/861 [00:18<16:36,  1.18s/it]
+
  2%|▏         | 20/861 [00:19<15:37,  1.11s/it]
+
  2%|▏         | 21/861 [00:20<16:28,  1.18s/it]
+
  3%|▎         | 22/861 [00:22<19:12,  1.37s/it]
+
  3%|▎         | 23/861 [00:22<14:57,  1.07s/it]
+
  3%|▎         | 24/861 [00:24<17:34,  1.26s/it]
+
  3%|▎         | 25/861 [00:25<16:59,  1.22s/it]
+
  3%|▎         | 26/861 [00:26<16:39,  1.20s/it]
+
  3%|▎         | 27/861 [00:28<17:43,  1.28s/it]
+
  3%|▎         | 28/861 [00:31<25:57,  1.87s/it]
+
  3%|▎         | 29/861 [00:31<19:28,  1.40s/it]
+
  3%|▎         | 30/861 [00:33<19:22,  1.40s/it]
+
  4%|▎         | 31/861 [00:33<16:15,  1.18s/it]
+
  4%|▎         | 32/861 [00:34<13:11,  1.05it/s]
+
  4%|▍         | 33/861 [00:35<13:45,  1.00it/s]
+
  4%|▍         | 34/861 [00:36<13:47,  1.00s/it]
+
  4%|▍         | 35/861 [00:38<17:21,  1.26s/it]
+
  4%|▍         | 36/861 [00:39<16:03,  1.17s/it]
+
  4%|▍         | 37/861 [00:40<15:22,  1.12s/it]
+
  4%|▍         | 38/861 [00:41<16:45,  1.22s/it]
+
  5%|▍         | 39/861 [00:42<14:16,  1.04s/it]
+
  5%|▍         | 40/861 [00:42<12:43,  1.08it/s]
+
  5%|▍         | 41/861 [00:43<10:47,  1.27it/s]
+
  5%|▍         | 42/861 [00:44<12:51,  1.06it/s]
+
  5%|▍         | 43/861 [00:45<13:06,  1.04it/s]
+
  5%|▌         | 44/861 [00:46<11:56,  1.14it/s]
+
  5%|▌         | 45/861 [00:47<12:04,  1.13it/s]
+
  5%|▌         | 46/861 [00:49<17:42,  1.30s/it]
+
  5%|▌         | 47/861 [00:50<17:42,  1.31s/it]
+
  6%|▌         | 48/861 [00:52<20:29,  1.51s/it]
+
  6%|▌         | 49/861 [00:54<19:24,  1.43s/it]
+
  6%|▌         | 50/861 [00:54<14:23,  1.06s/it]
+
  6%|▌         | 51/861 [00:55<14:28,  1.07s/it]
+
  6%|▌         | 52/861 [00:56<13:27,  1.00it/s]
\ No newline at end of file