diff --git "a/run-2024-10-02T06:53:25+00:00.log" "b/run-2024-10-02T06:53:25+00:00.log"
--- "a/run-2024-10-02T06:53:25+00:00.log"
+++ "b/run-2024-10-02T06:53:25+00:00.log"
@@ -2388,4 +2388,200 @@ Non-default generation parameters: {'max_length': 200, 'early_stopping': True, '
 
 75%|███████▌  | 43217/57600 [7:35:51<2:49:51,  1.41it/s]
 75%|███████▌  | 43218/57600 [7:35:52<2:45:34,  1.45it/s]
 75%|███████▌  | 43219/57600 [7:35:53<2:48:04,  1.43it/s]
 75%|███████▌  | 43220/57600 [7:35:53<2:48:39,  1.42it/s]
                                                         
{'loss': 1.1215, 'learning_rate': 3.254703832752613e-07, 'epoch': 477.04}
 
 75%|███████▌  | 43220/57600 [7:35:53<2:48:39,  1.42it/s]
 75%|███████▌  | 43221/57600 [7:35:54<2:45:27,  1.45it/s]
 75%|███████▌  | 43222/57600 [7:35:55<2:39:45,  1.50it/s]
 75%|███████▌  | 43223/57600 [7:35:55<2:32:34,  1.57it/s]
 75%|███████▌  | 43224/57600 [7:35:56<2:36:07,  1.53it/s]
 75%|███████▌  | 43225/57600 [7:35:57<2:41:47,  1.48it/s]
 75%|███████▌  | 43226/57600 [7:35:57<2:44:36,  1.46it/s]
 75%|███████▌  | 43227/57600 [7:35:58<2:41:58,  1.48it/s]
 75%|███████▌  | 43228/57600 [7:35:59<2:44:09,  1.46it/s]
 75%|███████▌  | 43229/57600 [7:35:59<2:39:40,  1.50it/s]
 75%|███████▌  | 43230/57600 [7:36:00<2:37:34,  1.52it/s]
 75%|███████▌  | 43231/57600 [7:36:01<2:37:12,  1.52it/s]
 75%|███████▌  | 43232/57600 [7:36:01<2:41:15,  1.48it/s]
 75%|███████▌  | 43233/57600 [7:36:02<2:40:46,  1.49it/s]
 75%|███████▌  | 43234/57600 [7:36:03<2:39:41,  1.50it/s]
 75%|███████▌  | 43235/57600 [7:36:03<2:38:37,  1.51it/s]
 75%|███████▌  | 43236/57600 [7:36:04<2:38:16,  1.51it/s]
 75%|███████▌  | 43237/57600 [7:36:05<2:38:17,  1.51it/s]
 75%|███████▌  | 43238/57600 [7:36:05<2:35:04,  1.54it/s]
 75%|███████▌  | 43239/57600 [7:36:06<2:41:43,  1.48it/s]
 75%|███████▌  | 43240/57600 [7:36:07<2:38:15,  1.51it/s]
                                                         
{'loss': 1.0938, 'learning_rate': 3.2515679442508714e-07, 'epoch': 477.26}
 
 75%|███████▌  | 43240/57600 [7:36:07<2:38:15,  1.51it/s]
 75%|███████▌  | 43241/57600 [7:36:07<2:41:03,  1.49it/s]
 75%|███████▌  | 43242/57600 [7:36:08<2:41:24,  1.48it/s]
 75%|███████▌  | 43243/57600 [7:36:09<2:35:48,  1.54it/s]
 75%|███████▌  | 43244/57600 [7:36:09<2:36:10,  1.53it/s]
 75%|███████▌  | 43245/57600 [7:36:10<2:32:04,  1.57it/s]
 75%|███████▌  | 43246/57600 [7:36:11<2:28:57,  1.61it/s]
 75%|███████▌  | 43247/57600 [7:36:11<2:26:05,  1.64it/s]
 75%|███████▌  | 43248/57600 [7:36:12<2:26:45,  1.63it/s]
 75%|███████▌  | 43249/57600 [7:36:12<2:28:06,  1.61it/s]
 75%|███████▌  | 43250/57600 [7:36:13<2:27:23,  1.62it/s]
 75%|███████▌  | 43251/57600 [7:36:14<2:36:50,  1.52it/s]
 75%|███████▌  | 43252/57600 [7:36:14<2:36:00,  1.53it/s]
 75%|███████▌  | 43253/57600 [7:36:15<2:39:20,  1.50it/s]
 75%|███████▌  | 43254/57600 [7:36:16<2:36:16,  1.53it/s]
 75%|███████▌  | 43255/57600 [7:36:16<2:43:25,  1.46it/s]
 75%|███████▌  | 43256/57600 [7:36:17<2:44:07,  1.46it/s]
 75%|███████▌  | 43257/57600 [7:36:18<2:45:12,  1.45it/s]
 75%|███████▌  | 43258/57600 [7:36:19<2:51:52,  1.39it/s]
 75%|███████▌  | 43259/57600 [7:36:19<2:48:01,  1.42it/s]
 75%|███████▌  | 43260/57600 [7:36:20<2:44:07,  1.46it/s]
                                                         
{'loss': 1.1255, 'learning_rate': 3.248432055749129e-07, 'epoch': 477.48}
-
 75%|███████▌  | 43260/57600 [7:36:20<2:44:07,  1.46it/s]
 75%|███████▌  | 43261/57600 [7:36:21<2:42:17,  1.47it/s]
 75%|███████▌  | 43262/57600 [7:36:21<2:39:36,  1.50it/s]
 75%|███████▌  | 43263/57600 [7:36:22<2:37:12,  1.52it/s]
\ No newline at end of file
+
 75%|███████▌  | 43260/57600 [7:36:20<2:44:07,  1.46it/s]
 75%|███████▌  | 43261/57600 [7:36:21<2:42:17,  1.47it/s]
 75%|███████▌  | 43262/57600 [7:36:21<2:39:36,  1.50it/s]
 75%|███████▌  | 43263/57600 [7:36:22<2:37:12,  1.52it/s]
 75%|███████▌  | 43264/57600 [7:36:23<2:37:41,  1.52it/s]
 75%|███████▌  | 43265/57600 [7:36:23<2:36:19,  1.53it/s]
 75%|███████▌  | 43266/57600 [7:36:24<2:38:21,  1.51it/s]
 75%|███████▌  | 43267/57600 [7:36:24<2:36:34,  1.53it/s]
 75%|███████▌  | 43268/57600 [7:36:25<2:34:37,  1.54it/s]
 75%|███████▌  | 43269/57600 [7:36:26<2:35:15,  1.54it/s]
 75%|███████▌  | 43270/57600 [7:36:26<2:32:50,  1.56it/s]
 75%|███████▌  | 43271/57600 [7:36:27<2:34:19,  1.55it/s]
 75%|███████▌  | 43272/57600 [7:36:28<2:33:53,  1.55it/s]
 75%|███████▌  | 43273/57600 [7:36:28<2:37:13,  1.52it/s]
 75%|███████▌  | 43274/57600 [7:36:29<2:33:18,  1.56it/s]
 75%|███████▌  | 43275/57600 [7:36:30<2:27:58,  1.61it/s]
 75%|███████▌  | 43276/57600 [7:36:30<2:29:24,  1.60it/s]
 75%|███████▌  | 43277/57600 [7:36:31<2:32:20,  1.57it/s]
 75%|███████▌  | 43278/57600 [7:36:31<2:29:47,  1.59it/s]
 75%|███████▌  | 43279/57600 [7:36:32<2:29:20,  1.60it/s]
 75%|███████▌  | 43280/57600 [7:36:33<2:29:24,  1.60it/s]
                                                         
{'loss': 1.1423, 'learning_rate': 3.2452961672473864e-07, 'epoch': 477.7}
+
 75%|███████▌  | 43280/57600 [7:36:33<2:29:24,  1.60it/s]
 75%|███████▌  | 43281/57600 [7:36:33<2:28:42,  1.60it/s]
 75%|███████▌  | 43282/57600 [7:36:34<2:26:40,  1.63it/s]
 75%|███████▌  | 43283/57600 [7:36:35<2:24:49,  1.65it/s]
 75%|███████▌  | 43284/57600 [7:36:35<2:25:06,  1.64it/s]
 75%|███████▌  | 43285/57600 [7:36:36<2:27:26,  1.62it/s]
 75%|███████▌  | 43286/57600 [7:36:36<2:27:49,  1.61it/s]
 75%|███████▌  | 43287/57600 [7:36:37<2:28:49,  1.60it/s]
 75%|███████▌  | 43288/57600 [7:36:38<2:27:57,  1.61it/s]
 75%|███████▌  | 43289/57600 [7:36:38<2:31:36,  1.57it/s]
 75%|███████▌  | 43290/57600 [7:36:39<2:30:22,  1.59it/s]
 75%|███████▌  | 43291/57600 [7:36:40<2:28:19,  1.61it/s]
 75%|███████▌  | 43292/57600 [7:36:40<2:32:44,  1.56it/s]
 75%|███████▌  | 43293/57600 [7:36:41<2:38:13,  1.51it/s]
 75%|███████▌  | 43294/57600 [7:36:42<2:33:35,  1.55it/s]
 75%|███████▌  | 43295/57600 [7:36:42<2:38:09,  1.51it/s]
 75%|███████▌  | 43296/57600 [7:36:43<2:41:58,  1.47it/s]
 75%|███████▌  | 43297/57600 [7:36:44<2:36:39,  1.52it/s]
 75%|███████▌  | 43298/57600 [7:36:44<2:34:30,  1.54it/s]
 75%|███████▌  | 43299/57600 [7:36:45<2:36:34,  1.52it/s]
 75%|███████▌  | 43300/57600 [7:36:46<2:35:49,  1.53it/s]
                                                         
{'loss': 1.1531, 'learning_rate': 3.242160278745644e-07, 'epoch': 477.92}
+
 75%|███████▌  | 43300/57600 [7:36:46<2:35:49,  1.53it/s]
 75%|███████▌  | 43301/57600 [7:36:46<2:39:18,  1.50it/s]
 75%|███████▌  | 43302/57600 [7:36:47<2:38:50,  1.50it/s]
 75%|███████▌  | 43303/57600 [7:36:48<2:36:48,  1.52it/s]
 75%|███████▌  | 43304/57600 [7:36:48<2:34:47,  1.54it/s]
 75%|███████▌  | 43305/57600 [7:36:49<2:32:52,  1.56it/s]
 75%|███████▌  | 43306/57600 [7:36:49<2:31:30,  1.57it/s]
 75%|███████▌  | 43307/57600 [7:36:50<2:43:23,  1.46it/s]
 75%|███████▌  | 43308/57600 [7:36:51<2:46:54,  1.43it/s]
 75%|███████▌  | 43309/57600 [7:36:52<2:45:47,  1.44it/s]
 75%|███████▌  | 43310/57600 [7:36:52<2:44:29,  1.45it/s]
 75%|███████▌  | 43311/57600 [7:36:53<2:48:43,  1.41it/s]
 75%|███████▌  | 43312/57600 [7:36:54<2:47:38,  1.42it/s]
 75%|███████▌  | 43313/57600 [7:36:54<2:40:07,  1.49it/s]
 75%|███████▌  | 43314/57600 [7:36:55<2:38:43,  1.50it/s]
 75%|███████▌  | 43315/57600 [7:36:56<2:36:07,  1.52it/s]
 75%|███████▌  | 43316/57600 [7:36:56<2:46:00,  1.43it/s]
 75%|███████▌  | 43317/57600 [7:36:57<2:46:27,  1.43it/s]
 75%|███████▌  | 43318/57600 [7:36:58<2:40:45,  1.48it/s]
 75%|███████▌  | 43319/57600 [7:36:58<2:45:10,  1.44it/s]
 75%|███████▌  | 43320/57600 [7:36:59<2:43:33,  1.46it/s]
                                                         
{'loss': 1.1217, 'learning_rate': 3.2390243902439025e-07, 'epoch': 478.15}
+
 75%|███████▌  | 43320/57600 [7:36:59<2:43:33,  1.46it/s]
 75%|███████▌  | 43321/57600 [7:37:00<2:40:14,  1.49it/s]
 75%|███████▌  | 43322/57600 [7:37:00<2:34:58,  1.54it/s]
 75%|███████▌  | 43323/57600 [7:37:01<2:36:55,  1.52it/s]
 75%|███████▌  | 43324/57600 [7:37:02<2:36:36,  1.52it/s]
 75%|███████▌  | 43325/57600 [7:37:02<2:34:22,  1.54it/s]
 75%|███████▌  | 43326/57600 [7:37:03<2:35:37,  1.53it/s]
 75%|███████▌  | 43327/57600 [7:37:04<2:32:50,  1.56it/s]
 75%|███████▌  | 43328/57600 [7:37:04<2:32:08,  1.56it/s]
 75%|███████▌  | 43329/57600 [7:37:05<2:31:37,  1.57it/s]
 75%|███████▌  | 43330/57600 [7:37:06<2:31:14,  1.57it/s]
 75%|███████▌  | 43331/57600 [7:37:06<2:32:41,  1.56it/s]
 75%|███████▌  | 43332/57600 [7:37:07<2:32:16,  1.56it/s]
 75%|███████▌  | 43333/57600 [7:37:07<2:35:26,  1.53it/s]
 75%|███████▌  | 43334/57600 [7:37:08<2:29:12,  1.59it/s]
 75%|███████▌  | 43335/57600 [7:37:09<2:30:35,  1.58it/s]
 75%|███████▌  | 43336/57600 [7:37:09<2:30:22,  1.58it/s]
 75%|███████▌  | 43337/57600 [7:37:10<2:28:40,  1.60it/s]
 75%|███████▌  | 43338/57600 [7:37:11<2:30:18,  1.58it/s]
 75%|███████▌  | 43339/57600 [7:37:11<2:31:50,  1.57it/s]
 75%|███████▌  | 43340/57600 [7:37:12<2:34:16,  1.54it/s]
                                                         
{'loss': 1.1308, 'learning_rate': 3.2358885017421605e-07, 'epoch': 478.37}
+
 75%|███████▌  | 43340/57600 [7:37:12<2:34:16,  1.54it/s]
 75%|███████▌  | 43341/57600 [7:37:13<2:38:41,  1.50it/s]
 75%|███████▌  | 43342/57600 [7:37:13<2:37:43,  1.51it/s]
 75%|███████▌  | 43343/57600 [7:37:14<2:31:59,  1.56it/s]
 75%|███████▌  | 43344/57600 [7:37:15<2:34:24,  1.54it/s]
 75%|███████▌  | 43345/57600 [7:37:15<2:37:12,  1.51it/s]
 75%|███████▌  | 43346/57600 [7:37:16<2:37:47,  1.51it/s]
 75%|███████▌  | 43347/57600 [7:37:17<2:43:20,  1.45it/s]
 75%|███████▌  | 43348/57600 [7:37:17<2:40:49,  1.48it/s]
 75%|███████▌  | 43349/57600 [7:37:18<2:39:06,  1.49it/s]
 75%|███████▌  | 43350/57600 [7:37:19<2:34:52,  1.53it/s]
 75%|███████▌  | 43351/57600 [7:37:19<2:31:04,  1.57it/s]
 75%|███████▌  | 43352/57600 [7:37:20<2:33:23,  1.55it/s]
 75%|███████▌  | 43353/57600 [7:37:20<2:30:57,  1.57it/s]
 75%|███████▌  | 43354/57600 [7:37:21<2:36:01,  1.52it/s]
 75%|███████▌  | 43355/57600 [7:37:22<2:35:14,  1.53it/s]
 75%|███████▌  | 43356/57600 [7:37:22<2:34:33,  1.54it/s]
 75%|███████▌  | 43357/57600 [7:37:23<2:32:09,  1.56it/s]
 75%|███████▌  | 43358/57600 [7:37:24<2:32:03,  1.56it/s]
 75%|███████▌  | 43359/57600 [7:37:24<2:37:29,  1.51it/s]
 75%|███████▌  | 43360/57600 [7:37:25<2:41:57,  1.47it/s]
                                                         
{'loss': 1.1318, 'learning_rate': 3.2327526132404175e-07, 'epoch': 478.59}
+
 75%|███████▌  | 43360/57600 [7:37:25<2:41:57,  1.47it/s]
 75%|███████▌  | 43361/57600 [7:37:26<2:42:38,  1.46it/s]
 75%|███████▌  | 43362/57600 [7:37:26<2:36:56,  1.51it/s]
 75%|███████▌  | 43363/57600 [7:37:27<2:44:43,  1.44it/s]
 75%|███████▌  | 43364/57600 [7:37:28<2:53:01,  1.37it/s]
 75%|███████▌  | 43365/57600 [7:37:29<2:50:55,  1.39it/s]
 75%|███████▌  | 43366/57600 [7:37:29<2:40:58,  1.47it/s]
 75%|███████▌  | 43367/57600 [7:37:30<2:38:59,  1.49it/s]
 75%|███████▌  | 43368/57600 [7:37:31<2:33:34,  1.54it/s]
 75%|███████▌  | 43369/57600 [7:37:31<2:33:40,  1.54it/s]
 75%|███████▌  | 43370/57600 [7:37:32<2:34:51,  1.53it/s]
 75%|███████▌  | 43371/57600 [7:37:33<2:34:19,  1.54it/s]
 75%|███████▌  | 43372/57600 [7:37:33<2:31:23,  1.57it/s]
 75%|███████▌  | 43373/57600 [7:37:34<2:39:33,  1.49it/s]
 75%|███████▌  | 43374/57600 [7:37:35<2:37:47,  1.50it/s]
 75%|███████▌  | 43375/57600 [7:37:35<2:44:46,  1.44it/s]
 75%|███████▌  | 43376/57600 [7:37:36<2:46:59,  1.42it/s]
 75%|███████▌  | 43377/57600 [7:37:37<2:45:40,  1.43it/s]
 75%|███████▌  | 43378/57600 [7:37:37<2:42:49,  1.46it/s]
 75%|███████▌  | 43379/57600 [7:37:38<2:40:19,  1.48it/s]
 75%|███████▌  | 43380/57600 [7:37:39<2:36:08,  1.52it/s]
                                                         
{'loss': 1.1465, 'learning_rate': 3.229616724738676e-07, 'epoch': 478.81}
+
 75%|███████▌  | 43380/57600 [7:37:39<2:36:08,  1.52it/s]
 75%|███████▌  | 43381/57600 [7:37:39<2:34:12,  1.54it/s]
 75%|███████▌  | 43382/57600 [7:37:40<2:35:49,  1.52it/s]
 75%|███████▌  | 43383/57600 [7:37:41<2:35:28,  1.52it/s]
 75%|███████▌  | 43384/57600 [7:37:41<2:38:23,  1.50it/s]
 75%|███████▌  | 43385/57600 [7:37:42<2:38:28,  1.49it/s]
 75%|███████▌  | 43386/57600 [7:37:43<2:42:50,  1.45it/s]
 75%|███████▌  | 43387/57600 [7:37:43<2:47:22,  1.42it/s]
 75%|███████▌  | 43388/57600 [7:37:44<2:41:40,  1.47it/s]
 75%|███████▌  | 43389/57600 [7:37:45<2:36:41,  1.51it/s]
 75%|███████▌  | 43390/57600 [7:37:45<2:40:53,  1.47it/s]
 75%|███████▌  | 43391/57600 [7:37:46<2:37:50,  1.50it/s]
 75%|███████▌  | 43392/57600 [7:37:47<2:36:50,  1.51it/s]
 75%|███████���  | 43393/57600 [7:37:47<2:40:18,  1.48it/s]
 75%|███████▌  | 43394/57600 [7:37:48<2:36:57,  1.51it/s]
 75%|███████▌  | 43395/57600 [7:37:49<2:31:55,  1.56it/s]
 75%|███████▌  | 43396/57600 [7:37:49<2:28:12,  1.60it/s]
 75%|███████▌  | 43397/57600 [7:37:50<2:30:27,  1.57it/s]
 75%|███████▌  | 43398/57600 [7:37:51<2:39:21,  1.49it/s]
 75%|███████▌  | 43399/57600 [7:37:51<2:32:16,  1.55it/s]
 75%|███████▌  | 43400/57600 [7:37:52<2:41:29,  1.47it/s]
                                                         
{'loss': 1.1182, 'learning_rate': 3.226480836236934e-07, 'epoch': 479.03}
+
 75%|███████▌  | 43400/57600 [7:37:52<2:41:29,  1.47it/s]
 75%|███████▌  | 43401/57600 [7:37:53<2:35:50,  1.52it/s]
 75%|███████▌  | 43402/57600 [7:37:53<2:35:41,  1.52it/s]
 75%|███████▌  | 43403/57600 [7:37:54<2:40:54,  1.47it/s]
 75%|███████▌  | 43404/57600 [7:37:55<2:40:25,  1.47it/s]
 75%|███████▌  | 43405/57600 [7:37:55<2:37:47,  1.50it/s]
 75%|███████▌  | 43406/57600 [7:37:56<2:42:01,  1.46it/s]
 75%|███████▌  | 43407/57600 [7:37:57<2:35:09,  1.52it/s]
 75%|███████▌  | 43408/57600 [7:37:57<2:32:20,  1.55it/s]
 75%|███████▌  | 43409/57600 [7:37:58<2:32:52,  1.55it/s]
 75%|███████▌  | 43410/57600 [7:37:58<2:32:03,  1.56it/s]
 75%|███████▌  | 43411/57600 [7:37:59<2:37:40,  1.50it/s]
 75%|███████▌  | 43412/57600 [7:38:00<2:42:12,  1.46it/s]
 75%|███████▌  | 43413/57600 [7:38:01<2:35:37,  1.52it/s]
 75%|███████▌  | 43414/57600 [7:38:01<2:34:43,  1.53it/s]
 75%|███████▌  | 43415/57600 [7:38:02<2:32:46,  1.55it/s]
 75%|███████▌  | 43416/57600 [7:38:02<2:32:47,  1.55it/s]
 75%|███████▌  | 43417/57600 [7:38:03<2:27:51,  1.60it/s]
 75%|███████▌  | 43418/57600 [7:38:04<2:29:02,  1.59it/s]
 75%|███████▌  | 43419/57600 [7:38:04<2:28:33,  1.59it/s]
 75%|███████▌  | 43420/57600 [7:38:05<2:26:10,  1.62it/s]
                                                         
{'loss': 1.106, 'learning_rate': 3.2233449477351917e-07, 'epoch': 479.25}
+
 75%|███████▌  | 43420/57600 [7:38:05<2:26:10,  1.62it/s]
 75%|███████▌  | 43421/57600 [7:38:06<2:25:31,  1.62it/s]
 75%|███████▌  | 43422/57600 [7:38:06<2:25:19,  1.63it/s]
 75%|███████▌  | 43423/57600 [7:38:07<2:25:20,  1.63it/s]
 75%|███████▌  | 43424/57600 [7:38:07<2:25:56,  1.62it/s]
 75%|███████▌  | 43425/57600 [7:38:08<2:23:32,  1.65it/s]
 75%|███████▌  | 43426/57600 [7:38:09<2:22:21,  1.66it/s]
 75%|███████▌  | 43427/57600 [7:38:09<2:25:53,  1.62it/s]
 75%|███████▌  | 43428/57600 [7:38:10<2:22:17,  1.66it/s]
 75%|███████▌  | 43429/57600 [7:38:10<2:21:59,  1.66it/s]
 75%|███████▌  | 43430/57600 [7:38:11<2:26:00,  1.62it/s]
 75%|███████▌  | 43431/57600 [7:38:12<2:26:23,  1.61it/s]
 75%|███████▌  | 43432/57600 [7:38:12<2:26:14,  1.61it/s]
 75%|███████▌  | 43433/57600 [7:38:13<2:26:33,  1.61it/s]
 75%|███████▌  | 43434/57600 [7:38:13<2:26:44,  1.61it/s]
 75%|███████▌  | 43435/57600 [7:38:14<2:26:12,  1.61it/s]
 75%|███████▌  | 43436/57600 [7:38:15<2:26:55,  1.61it/s]
 75%|███████▌  | 43437/57600 [7:38:15<2:25:48,  1.62it/s]
 75%|███████▌  | 43438/57600 [7:38:16<2:25:07,  1.63it/s]
 75%|███████▌  | 43439/57600 [7:38:17<2:25:19,  1.62it/s]
 75%|███████▌  | 43440/57600 [7:38:17<2:27:24,  1.60it/s]
                                                         
{'loss': 1.1445, 'learning_rate': 3.2202090592334487e-07, 'epoch': 479.47}
+
 75%|███████▌  | 43440/57600 [7:38:17<2:27:24,  1.60it/s]
 75%|███████▌  | 43441/57600 [7:38:18<2:23:54,  1.64it/s]
 75%|███████▌  | 43442/57600 [7:38:18<2:21:37,  1.67it/s]
 75%|███████▌  | 43443/57600 [7:38:19<2:26:18,  1.61it/s]
 75%|███████▌  | 43444/57600 [7:38:20<2:24:58,  1.63it/s]
 75%|███████▌  | 43445/57600 [7:38:20<2:27:07,  1.60it/s]
 75%|███████▌  | 43446/57600 [7:38:21<2:29:47,  1.57it/s]
 75%|███████▌  | 43447/57600 [7:38:22<2:30:46,  1.56it/s]
 75%|███████▌  | 43448/57600 [7:38:22<2:31:17,  1.56it/s]
 75%|███████▌  | 43449/57600 [7:38:23<2:29:47,  1.57it/s]
 75%|███████▌  | 43450/57600 [7:38:23<2:27:39,  1.60it/s]
 75%|███████▌  | 43451/57600 [7:38:24<2:31:37,  1.56it/s]
 75%|███████▌  | 43452/57600 [7:38:25<2:30:43,  1.56it/s]
 75%|███████▌  | 43453/57600 [7:38:25<2:25:47,  1.62it/s]
 75%|███████▌  | 43454/57600 [7:38:26<2:29:26,  1.58it/s]
 75%|███████▌  | 43455/57600 [7:38:27<2:33:50,  1.53it/s]
 75%|███████▌  | 43456/57600 [7:38:27<2:32:42,  1.54it/s]
 75%|███████▌  | 43457/57600 [7:38:28<2:30:57,  1.56it/s]
 75%|███████▌  | 43458/57600 [7:38:29<2:32:43,  1.54it/s]
 75%|███████▌  | 43459/57600 [7:38:29<2:35:41,  1.51it/s]
 75%|███████▌  | 43460/57600 [7:38:30<2:27:12,  1.60it/s]
                                                         
{'loss': 1.1517, 'learning_rate': 3.217073170731707e-07, 'epoch': 479.69}
+
 75%|███████▌  | 43460/57600 [7:38:30<2:27:12,  1.60it/s]
 75%|███████▌  | 43461/57600 [7:38:31<2:31:22,  1.56it/s]
 75%|███████▌  | 43462/57600 [7:38:31<2:29:41,  1.57it/s]
 75%|███████▌  | 43463/57600 [7:38:32<2:30:38,  1.56it/s]
 75%|███████▌  | 43464/57600 [7:38:32<2:26:55,  1.60it/s]
 75%|███████▌  | 43465/57600 [7:38:33<2:24:36,  1.63it/s]
 75%|███████▌  | 43466/57600 [7:38:34<2:23:40,  1.64it/s]
 75%|███████▌  | 43467/57600 [7:38:34<2:27:54,  1.59it/s]
 75%|███████▌  | 43468/57600 [7:38:35<2:29:44,  1.57it/s]
 75%|███████▌  | 43469/57600 [7:38:36<2:29:36,  1.57it/s]
 75%|███████▌  | 43470/57600 [7:38:36<2:31:49,  1.55it/s]
 75%|███████▌  | 43471/57600 [7:38:37<2:28:18,  1.59it/s]
 75%|███████▌  | 43472/57600 [7:38:37<2:24:30,  1.63it/s]
 75%|███████▌  | 43473/57600 [7:38:38<2:23:03,  1.65it/s]
 75%|███████▌  | 43474/57600 [7:38:39<2:23:43,  1.64it/s]
 75%|███████▌  | 43475/57600 [7:38:39<2:22:24,  1.65it/s]
 75%|███████▌  | 43476/57600 [7:38:40<2:22:30,  1.65it/s]
 75%|███████▌  | 43477/57600 [7:38:40<2:21:09,  1.67it/s]
 75%|███████▌  | 43478/57600 [7:38:41<2:20:48,  1.67it/s]
 75%|███████▌  | 43479/57600 [7:38:42<2:23:28,  1.64it/s]
 75%|███████▌  | 43480/57600 [7:38:42<2:24:56,  1.62it/s]
                                                         
{'loss': 1.1624, 'learning_rate': 3.2139372822299653e-07, 'epoch': 479.91}
+
 75%|███████▌  | 43480/57600 [7:38:42<2:24:56,  1.62it/s]
 75%|███████▌  | 43481/57600 [7:38:43<2:21:02,  1.67it/s]
 75%|███████▌  | 43482/57600 [7:38:43<2:22:42,  1.65it/s]
 75%|███████▌  | 43483/57600 [7:38:44<2:27:26,  1.60it/s]
 75%|███████▌  | 43484/57600 [7:38:45<2:28:23,  1.59it/s]
 75%|███████▌  | 43485/57600 [7:38:45<2:36:14,  1.51it/s]
 75%|███████▌  | 43486/57600 [7:38:46<2:38:32,  1.48it/s]
 75%|███████▌  | 43487/57600 [7:38:47<2:34:04,  1.53it/s]
 76%|███████▌  | 43488/57600 [7:38:47<2:34:34,  1.52it/s]
 76%|███████▌  | 43489/57600 [7:38:48<2:34:40,  1.52it/s]
 76%|███████▌  | 43490/57600 [7:38:49<2:32:14,  1.54it/s]
 76%|███████▌  | 43491/57600 [7:38:49<2:37:17,  1.50it/s]
 76%|███████▌  | 43492/57600 [7:38:50<2:39:23,  1.48it/s]
 76%|███████▌  | 43493/57600 [7:38:51<2:30:39,  1.56it/s]
 76%|███████▌  | 43494/57600 [7:38:51<2:31:46,  1.55it/s]
 76%|███████▌  | 43495/57600 [7:38:52<2:27:35,  1.59it/s]
 76%|███████▌  | 43496/57600 [7:38:53<2:28:58,  1.58it/s]
 76%|███████▌  | 43497/57600 [7:38:53<2:24:58,  1.62it/s]
 76%|███████▌  | 43498/57600 [7:38:54<2:24:50,  1.62it/s]
 76%|███████▌  | 43499/57600 [7:38:54<2:28:13,  1.59it/s]
 76%|███████▌  | 43500/57600 [7:38:55<2:25:03,  1.62it/s]
                                                         
{'loss': 1.1148, 'learning_rate': 3.2108013937282223e-07, 'epoch': 480.13}
+
 76%|███████▌  | 43500/57600 [7:38:55<2:25:03,  1.62it/s]
 76%|███████▌  | 43501/57600 [7:38:56<2:25:20,  1.62it/s]
 76%|███████▌  | 43502/57600 [7:38:56<2:24:07,  1.63it/s]
 76%|███████▌  | 43503/57600 [7:38:57<2:25:59,  1.61it/s]
 76%|███████▌  | 43504/57600 [7:38:58<2:26:18,  1.61it/s]
 76%|███████▌  | 43505/57600 [7:38:58<2:25:58,  1.61it/s]
 76%|███████▌  | 43506/57600 [7:38:59<2:27:59,  1.59it/s]
 76%|███████▌  | 43507/57600 [7:38:59<2:30:06,  1.56it/s]
 76%|███████▌  | 43508/57600 [7:39:00<2:31:44,  1.55it/s]
 76%|███████▌  | 43509/57600 [7:39:01<2:27:48,  1.59it/s]
 76%|███████▌  | 43510/57600 [7:39:01<2:23:38,  1.63it/s]
 76%|███████▌  | 43511/57600 [7:39:02<2:29:43,  1.57it/s]
 76%|███████▌  | 43512/57600 [7:39:03<2:32:30,  1.54it/s]
 76%|███████▌  | 43513/57600 [7:39:03<2:26:11,  1.61it/s]
 76%|███████▌  | 43514/57600 [7:39:04<2:23:16,  1.64it/s]
 76%|███████▌  | 43515/57600 [7:39:04<2:23:15,  1.64it/s]
 76%|███████▌  | 43516/57600 [7:39:05<2:25:06,  1.62it/s]
 76%|███████▌  | 43517/57600 [7:39:06<2:30:25,  1.56it/s]
 76%|███████▌  | 43518/57600 [7:39:06<2:34:56,  1.51it/s]
 76%|███████▌  | 43519/57600 [7:39:07<2:32:49,  1.54it/s]
 76%|███████▌  | 43520/57600 [7:39:08<2:30:22,  1.56it/s]
                                                         
{'loss': 1.1493, 'learning_rate': 3.207665505226481e-07, 'epoch': 480.35}
+
 76%|███████▌  | 43520/57600 [7:39:08<2:30:22,  1.56it/s]
 76%|███████▌  | 43521/57600 [7:39:08<2:31:03,  1.55it/s]
 76%|███████▌  | 43522/57600 [7:39:09<2:29:57,  1.56it/s]
 76%|███████▌  | 43523/57600 [7:39:10<2:35:42,  1.51it/s]
 76%|███████▌  | 43524/57600 [7:39:10<2:35:04,  1.51it/s]
 76%|███████▌  | 43525/57600 [7:39:11<2:36:02,  1.50it/s]
 76%|███████▌  | 43526/57600 [7:39:12<2:40:00,  1.47it/s]
 76%|███████▌  | 43527/57600 [7:39:12<2:33:50,  1.52it/s]
 76%|███████▌  | 43528/57600 [7:39:13<2:34:01,  1.52it/s]
 76%|███████▌  | 43529/57600 [7:39:14<2:34:26,  1.52it/s]
 76%|███████▌  | 43530/57600 [7:39:14<2:28:46,  1.58it/s]
 76%|███████▌  | 43531/57600 [7:39:15<2:25:18,  1.61it/s]
 76%|███████▌  | 43532/57600 [7:39:15<2:22:14,  1.65it/s]
 76%|███████▌  | 43533/57600 [7:39:16<2:23:14,  1.64it/s]
 76%|███████▌  | 43534/57600 [7:39:17<2:21:56,  1.65it/s]
 76%|███████▌  | 43535/57600 [7:39:17<2:22:00,  1.65it/s]
 76%|███████▌  | 43536/57600 [7:39:18<2:26:08,  1.60it/s]
 76%|███████▌  | 43537/57600 [7:39:18<2:23:31,  1.63it/s]
 76%|███████▌  | 43538/57600 [7:39:19<2:21:31,  1.66it/s]
 76%|███████▌  | 43539/57600 [7:39:20<2:19:53,  1.68it/s]
 76%|███████▌  | 43540/57600 [7:39:20<2:21:00,  1.66it/s]
                                                         
{'loss': 1.1442, 'learning_rate': 3.2045296167247384e-07, 'epoch': 480.57}
+
 76%|███████▌  | 43540/57600 [7:39:20<2:21:00,  1.66it/s]
 76%|███████▌  | 43541/57600 [7:39:21<2:25:30,  1.61it/s]
 76%|███████▌  | 43542/57600 [7:39:22<2:23:28,  1.63it/s]
 76%|███████▌  | 43543/57600 [7:39:22<2:24:27,  1.62it/s]
 76%|███████▌  | 43544/57600 [7:39:23<2:23:19,  1.63it/s]
 76%|███████▌  | 43545/57600 [7:39:23<2:24:02,  1.63it/s]
 76%|███████▌  | 43546/57600 [7:39:24<2:22:01,  1.65it/s]
 76%|███████▌  | 43547/57600 [7:39:25<2:20:43,  1.66it/s]
 76%|███████▌  | 43548/57600 [7:39:25<2:22:07,  1.65it/s]
 76%|███████▌  | 43549/57600 [7:39:26<2:21:41,  1.65it/s]
 76%|███████▌  | 43550/57600 [7:39:26<2:20:50,  1.66it/s]
 76%|███████▌  | 43551/57600 [7:39:27<2:18:25,  1.69it/s]
 76%|███████▌  | 43552/57600 [7:39:28<2:23:09,  1.64it/s]
 76%|███████▌  | 43553/57600 [7:39:28<2:25:45,  1.61it/s]
 76%|███████▌  | 43554/57600 [7:39:29<2:25:00,  1.61it/s]
 76%|███████▌  | 43555/57600 [7:39:30<2:30:09,  1.56it/s]
 76%|███████▌  | 43556/57600 [7:39:30<2:25:32,  1.61it/s]
 76%|███████▌  | 43557/57600 [7:39:31<2:25:27,  1.61it/s]
 76%|███████▌  | 43558/57600 [7:39:31<2:25:21,  1.61it/s]
 76%|███████▌  | 43559/57600 [7:39:32<2:25:28,  1.61it/s]
 76%|███████▌  | 43560/57600 [7:39:33<2:26:11,  1.60it/s]
                                                         
{'loss': 1.1218, 'learning_rate': 3.2013937282229964e-07, 'epoch': 480.79}
+
 76%|███████▌  | 43560/57600 [7:39:33<2:26:11,  1.60it/s]
 76%|███████▌  | 43561/57600 [7:39:33<2:26:57,  1.59it/s]
 76%|███████▌  | 43562/57600 [7:39:34<2:28:24,  1.58it/s]
 76%|███████▌  | 43563/57600 [7:39:34<2:25:56,  1.60it/s]
 76%|███████▌  | 43564/57600 [7:39:35<2:28:11,  1.58it/s]
 76%|███████▌  | 43565/57600 [7:39:36<2:31:18,  1.55it/s]
 76%|███████▌  | 43566/57600 [7:39:36<2:26:29,  1.60it/s]
 76%|███████▌  | 43567/57600 [7:39:37<2:27:27,  1.59it/s]
 76%|███████▌  | 43568/57600 [7:39:38<2:23:57,  1.62it/s]
 76%|███████▌  | 43569/57600 [7:39:38<2:23:04,  1.63it/s]
 76%|███████▌  | 43570/57600 [7:39:39<2:24:51,  1.61it/s]
 76%|███████▌  | 43571/57600 [7:39:39<2:24:16,  1.62it/s]
 76%|███████▌  | 43572/57600 [7:39:40<2:21:06,  1.66it/s]
 76%|███████▌  | 43573/57600 [7:39:41<2:23:05,  1.63it/s]
 76%|███████▌  | 43574/57600 [7:39:41<2:25:07,  1.61it/s]
 76%|███████▌  | 43575/57600 [7:39:42<2:24:08,  1.62it/s]
 76%|███████▌  | 43576/57600 [7:39:43<2:34:47,  1.51it/s]
 76%|███████▌  | 43577/57600 [7:39:43<2:38:05,  1.48it/s]
 76%|███████▌  | 43578/57600 [7:39:44<2:35:29,  1.50it/s]
 76%|███████▌  | 43579/57600 [7:39:45<2:39:25,  1.47it/s]
 76%|███████▌  | 43580/57600 [7:39:45<2:34:29,  1.51it/s]
                                                         
{'loss': 1.1261, 'learning_rate': 3.1982578397212534e-07, 'epoch': 481.02}
+
 76%|███████▌  | 43580/57600 [7:39:45<2:34:29,  1.51it/s]
 76%|███████▌  | 43581/57600 [7:39:46<2:37:00,  1.49it/s]
 76%|███████▌  | 43582/57600 [7:39:47<2:34:10,  1.52it/s]
 76%|███████▌  | 43583/57600 [7:39:47<2:42:27,  1.44it/s]
 76%|███████▌  | 43584/57600 [7:39:48<2:38:18,  1.48it/s]
 76%|███████▌  | 43585/57600 [7:39:49<2:31:54,  1.54it/s]
 76%|███████▌  | 43586/57600 [7:39:49<2:30:30,  1.55it/s]
 76%|███████▌  | 43587/57600 [7:39:50<2:29:44,  1.56it/s]
 76%|███████▌  | 43588/57600 [7:39:51<2:30:58,  1.55it/s]
 76%|███████▌  | 43589/57600 [7:39:51<2:27:42,  1.58it/s]
 76%|███████▌  | 43590/57600 [7:39:52<2:29:11,  1.57it/s]
 76%|███████▌  | 43591/57600 [7:39:52<2:26:51,  1.59it/s]
 76%|███████▌  | 43592/57600 [7:39:53<2:26:29,  1.59it/s]
 76%|███████▌  | 43593/57600 [7:39:54<2:29:37,  1.56it/s]
 76%|███████▌  | 43594/57600 [7:39:54<2:30:59,  1.55it/s]
 76%|███████▌  | 43595/57600 [7:39:55<2:25:39,  1.60it/s]
 76%|███████▌  | 43596/57600 [7:39:56<2:28:12,  1.57it/s]
 76%|███████▌  | 43597/57600 [7:39:56<2:27:13,  1.59it/s]
 76%|███████▌  | 43598/57600 [7:39:57<2:27:50,  1.58it/s]
 76%|███████▌  | 43599/57600 [7:39:58<2:26:37,  1.59it/s]
 76%|███████▌  | 43600/57600 [7:39:58<2:23:57,  1.62it/s]
                                                         
{'loss': 1.1063, 'learning_rate': 3.195121951219512e-07, 'epoch': 481.24}
+
 76%|███████▌  | 43600/57600 [7:39:58<2:23:57,  1.62it/s]
 76%|███████▌  | 43601/57600 [7:39:59<2:25:20,  1.61it/s]
 76%|███████▌  | 43602/57600 [7:39:59<2:22:37,  1.64it/s]
 76%|███████▌  | 43603/57600 [7:40:00<2:33:36,  1.52it/s]
 76%|███████▌  | 43604/57600 [7:40:01<2:33:15,  1.52it/s]
 76%|███████▌  | 43605/57600 [7:40:01<2:28:12,  1.57it/s]
 76%|███████▌  | 43606/57600 [7:40:02<2:25:33,  1.60it/s]
 76%|███████▌  | 43607/57600 [7:40:03<2:21:26,  1.65it/s]
 76%|███████▌  | 43608/57600 [7:40:03<2:18:35,  1.68it/s]
 76%|███████▌  | 43609/57600 [7:40:04<2:20:05,  1.66it/s]
 76%|███████▌  | 43610/57600 [7:40:04<2:22:29,  1.64it/s]
 76%|███████▌  | 43611/57600 [7:40:05<2:25:18,  1.60it/s]
 76%|███████▌  | 43612/57600 [7:40:06<2:23:02,  1.63it/s]
 76%|███████▌  | 43613/57600 [7:40:06<2:22:08,  1.64it/s]
 76%|███████▌  | 43614/57600 [7:40:07<2:26:18,  1.59it/s]
 76%|███████▌  | 43615/57600 [7:40:07<2:23:58,  1.62it/s]
 76%|███████▌  | 43616/57600 [7:40:08<2:23:15,  1.63it/s]
 76%|███████▌  | 43617/57600 [7:40:09<2:24:17,  1.62it/s]
 76%|███████▌  | 43618/57600 [7:40:09<2:21:51,  1.64it/s]
 76%|███████▌  | 43619/57600 [7:40:10<2:22:22,  1.64it/s]
 76%|███████▌  | 43620/57600 [7:40:10<2:21:03,  1.65it/s]
                                                         
{'loss': 1.1305, 'learning_rate': 3.1919860627177706e-07, 'epoch': 481.46}
+
 76%|███████▌  | 43620/57600 [7:40:10<2:21:03,  1.65it/s]
 76%|███████▌  | 43621/57600 [7:40:11<2:19:01,  1.68it/s]
 76%|███████▌  | 43622/57600 [7:40:12<2:20:02,  1.66it/s]
 76%|███████▌  | 43623/57600 [7:40:12<2:19:35,  1.67it/s]
 76%|███████▌  | 43624/57600 [7:40:13<2:23:59,  1.62it/s]
 76%|███████▌  | 43625/57600 [7:40:13<2:18:45,  1.68it/s]
 76%|███████▌  | 43626/57600 [7:40:14<2:18:30,  1.68it/s]
 76%|███████▌  | 43627/57600 [7:40:15<2:19:02,  1.67it/s]
 76%|███████▌  | 43628/57600 [7:40:15<2:25:48,  1.60it/s]
 76%|███████▌  | 43629/57600 [7:40:16<2:28:39,  1.57it/s]
 76%|███████▌  | 43630/57600 [7:40:17<2:34:35,  1.51it/s]
 76%|███████▌  | 43631/57600 [7:40:17<2:35:39,  1.50it/s]
 76%|███████▌  | 43632/57600 [7:40:18<2:30:41,  1.54it/s]
 76%|███████▌  | 43633/57600 [7:40:19<2:25:14,  1.60it/s]
 76%|███████▌  | 43634/57600 [7:40:19<2:27:24,  1.58it/s]
 76%|███████▌  | 43635/57600 [7:40:20<2:32:22,  1.53it/s]
 76%|█████��█▌  | 43636/57600 [7:40:21<2:29:30,  1.56it/s]
 76%|███████▌  | 43637/57600 [7:40:21<2:28:47,  1.56it/s]
 76%|███████▌  | 43638/57600 [7:40:22<2:30:52,  1.54it/s]
 76%|███████▌  | 43639/57600 [7:40:22<2:27:49,  1.57it/s]
 76%|███████▌  | 43640/57600 [7:40:23<2:24:26,  1.61it/s]
                                                         
{'loss': 1.1276, 'learning_rate': 3.1888501742160276e-07, 'epoch': 481.68}
+
 76%|███████▌  | 43640/57600 [7:40:23<2:24:26,  1.61it/s]
 76%|███████▌  | 43641/57600 [7:40:24<2:29:34,  1.56it/s]
 76%|███████▌  | 43642/57600 [7:40:24<2:30:29,  1.55it/s]
 76%|███████▌  | 43643/57600 [7:40:25<2:33:21,  1.52it/s]
 76%|███████▌  | 43644/57600 [7:40:26<2:31:05,  1.54it/s]
 76%|███████▌  | 43645/57600 [7:40:26<2:27:49,  1.57it/s]
 76%|███████▌  | 43646/57600 [7:40:27<2:25:06,  1.60it/s]
 76%|███████▌  | 43647/57600 [7:40:28<2:22:37,  1.63it/s]
 76%|███████▌  | 43648/57600 [7:40:28<2:24:16,  1.61it/s]
 76%|███████▌  | 43649/57600 [7:40:29<2:23:03,  1.63it/s]
 76%|███████▌  | 43650/57600 [7:40:29<2:21:44,  1.64it/s]
 76%|███████▌  | 43651/57600 [7:40:30<2:22:47,  1.63it/s]
 76%|███████▌  | 43652/57600 [7:40:31<2:19:02,  1.67it/s]
 76%|███████▌  | 43653/57600 [7:40:31<2:22:27,  1.63it/s]
 76%|███████▌  | 43654/57600 [7:40:32<2:26:42,  1.58it/s]
 76%|███████▌  | 43655/57600 [7:40:33<2:28:19,  1.57it/s]
 76%|███████▌  | 43656/57600 [7:40:33<2:24:22,  1.61it/s]
 76%|███████▌  | 43657/57600 [7:40:34<2:26:45,  1.58it/s]
 76%|███████▌  | 43658/57600 [7:40:34<2:25:08,  1.60it/s]
 76%|███████▌  | 43659/57600 [7:40:35<2:23:02,  1.62it/s]
 76%|███████▌  | 43660/57600 [7:40:36<2:27:30,  1.58it/s]
                                                         
{'loss': 1.1197, 'learning_rate': 3.1857142857142856e-07, 'epoch': 481.9}
+
 76%|███████▌  | 43660/57600 [7:40:36<2:27:30,  1.58it/s]
 76%|███████▌  | 43661/57600 [7:40:36<2:26:54,  1.58it/s]
 76%|███████▌  | 43662/57600 [7:40:37<2:29:52,  1.55it/s]
 76%|███████▌  | 43663/57600 [7:40:38<2:28:18,  1.57it/s]
 76%|███████▌  | 43664/57600 [7:40:38<2:22:37,  1.63it/s]
 76%|███████▌  | 43665/57600 [7:40:39<2:20:02,  1.66it/s]
 76%|███████▌  | 43666/57600 [7:40:39<2:21:15,  1.64it/s]
 76%|███████▌  | 43667/57600 [7:40:40<2:22:59,  1.62it/s]
 76%|███████▌  | 43668/57600 [7:40:41<2:26:52,  1.58it/s]
 76%|███████▌  | 43669/57600 [7:40:41<2:35:20,  1.49it/s]
 76%|███████▌  | 43670/57600 [7:40:42<2:40:43,  1.44it/s]
 76%|███████▌  | 43671/57600 [7:40:43<2:36:41,  1.48it/s]
 76%|███████▌  | 43672/57600 [7:40:43<2:30:10,  1.55it/s]
 76%|███████▌  | 43673/57600 [7:40:44<2:28:52,  1.56it/s]
 76%|███████▌  | 43674/57600 [7:40:45<2:33:40,  1.51it/s]
 76%|███████▌  | 43675/57600 [7:40:45<2:26:09,  1.59it/s]
 76%|███████▌  | 43676/57600 [7:40:46<2:26:06,  1.59it/s]
 76%|███████▌  | 43677/57600 [7:40:46<2:24:30,  1.61it/s]
 76%|███████▌  | 43678/57600 [7:40:47<2:24:14,  1.61it/s]
 76%|███████▌  | 43679/57600 [7:40:48<2:25:23,  1.60it/s]
 76%|███████▌  | 43680/57600 [7:40:48<2:21:32,  1.64it/s]
                                                         
{'loss': 1.1389, 'learning_rate': 3.182578397212543e-07, 'epoch': 482.12}
+
 76%|███████▌  | 43680/57600 [7:40:48<2:21:32,  1.64it/s]
 76%|███████▌  | 43681/57600 [7:40:49<2:21:33,  1.64it/s]
 76%|███████▌  | 43682/57600 [7:40:50<2:24:11,  1.61it/s]
 76%|███████▌  | 43683/57600 [7:40:50<2:24:57,  1.60it/s]
 76%|███████▌  | 43684/57600 [7:40:51<2:26:13,  1.59it/s]
 76%|███████▌  | 43685/57600 [7:40:51<2:27:24,  1.57it/s]
 76%|███████▌  | 43686/57600 [7:40:52<2:26:29,  1.58it/s]
 76%|███████▌  | 43687/57600 [7:40:53<2:21:01,  1.64it/s]
 76%|███████▌  | 43688/57600 [7:40:53<2:24:39,  1.60it/s]
 76%|███████▌  | 43689/57600 [7:40:54<2:20:25,  1.65it/s]
 76%|███████▌  | 43690/57600 [7:40:55<2:23:29,  1.62it/s]
 76%|███████▌  | 43691/57600 [7:40:55<2:24:40,  1.60it/s]
 76%|███████▌  | 43692/57600 [7:40:56<2:22:16,  1.63it/s]
 76%|███████▌  | 43693/57600 [7:40:56<2:19:07,  1.67it/s]
 76%|███████▌  | 43694/57600 [7:40:57<2:19:15,  1.66it/s]
 76%|███████▌  | 43695/57600 [7:40:58<2:20:44,  1.65it/s]
 76%|███████▌  | 43696/57600 [7:40:58<2:18:59,  1.67it/s]
 76%|███████▌  | 43697/57600 [7:40:59<2:19:47,  1.66it/s]
 76%|███████▌  | 43698/57600 [7:40:59<2:23:03,  1.62it/s]
 76%|███████▌  | 43699/57600 [7:41:00<2:21:32,  1.64it/s]
 76%|███████▌  | 43700/57600 [7:41:01<2:30:04,  1.54it/s]
                                                         
{'loss': 1.1509, 'learning_rate': 3.1794425087108017e-07, 'epoch': 482.34}
+
 76%|███████▌  | 43700/57600 [7:41:01<2:30:04,  1.54it/s]
 76%|███████▌  | 43701/57600 [7:41:01<2:31:33,  1.53it/s]
 76%|███████▌  | 43702/57600 [7:41:02<2:30:26,  1.54it/s]
 76%|███████▌  | 43703/57600 [7:41:03<2:27:16,  1.57it/s]
 76%|███████▌  | 43704/57600 [7:41:03<2:28:00,  1.56it/s]
 76%|███████▌  | 43705/57600 [7:41:04<2:32:08,  1.52it/s]
 76%|███████▌  | 43706/57600 [7:41:05<2:28:16,  1.56it/s]
 76%|███████▌  | 43707/57600 [7:41:05<2:25:56,  1.59it/s]
 76%|███████▌  | 43708/57600 [7:41:06<2:28:46,  1.56it/s]
 76%|███████▌  | 43709/57600 [7:41:06<2:24:08,  1.61it/s]
 76%|███████▌  | 43710/57600 [7:41:07<2:24:08,  1.61it/s]
 76%|███████▌  | 43711/57600 [7:41:08<2:24:50,  1.60it/s]
 76%|███████▌  | 43712/57600 [7:41:08<2:27:34,  1.57it/s]
 76%|███████▌  | 43713/57600 [7:41:09<2:31:56,  1.52it/s]
 76%|███████▌  | 43714/57600 [7:41:10<2:29:10,  1.55it/s]
 76%|███████▌  | 43715/57600 [7:41:10<2:28:34,  1.56it/s]
 76%|███████▌  | 43716/57600 [7:41:11<2:25:25,  1.59it/s]
 76%|███████▌  | 43717/57600 [7:41:12<2:29:03,  1.55it/s]
 76%|███████▌  | 43718/57600 [7:41:12<2:27:45,  1.57it/s]
 76%|███████▌  | 43719/57600 [7:41:13<2:24:09,  1.60it/s]
 76%|███████▌  | 43720/57600 [7:41:13<2:25:24,  1.59it/s]
                                                         
{'loss': 1.1369, 'learning_rate': 3.1763066202090587e-07, 'epoch': 482.56}
+
 76%|███████▌  | 43720/57600 [7:41:13<2:25:24,  1.59it/s]
 76%|███████▌  | 43721/57600 [7:41:14<2:23:10,  1.62it/s]
 76%|███████▌  | 43722/57600 [7:41:15<2:20:37,  1.64it/s]
 76%|███████▌  | 43723/57600 [7:41:15<2:18:00,  1.68it/s]
 76%|███████▌  | 43724/57600 [7:41:16<2:23:03,  1.62it/s]
 76%|███████▌  | 43725/57600 [7:41:16<2:19:41,  1.66it/s]
 76%|███████▌  | 43726/57600 [7:41:17<2:19:21,  1.66it/s]
 76%|███████▌  | 43727/57600 [7:41:18<2:24:26,  1.60it/s]
 76%|███████▌  | 43728/57600 [7:41:18<2:27:07,  1.57it/s]
 76%|███████▌  | 43729/57600 [7:41:19<2:33:08,  1.51it/s]
 76%|███████▌  | 43730/57600 [7:41:20<2:29:26,  1.55it/s]
 76%|███████▌  | 43731/57600 [7:41:20<2:25:52,  1.58it/s]
 76%|███████▌  | 43732/57600 [7:41:21<2:20:13,  1.65it/s]
 76%|███████▌  | 43733/57600 [7:41:21<2:21:59,  1.63it/s]
 76%|███████▌  | 43734/57600 [7:41:22<2:21:28,  1.63it/s]
 76%|███████▌  | 43735/57600 [7:41:23<2:21:46,  1.63it/s]
 76%|███████▌  | 43736/57600 [7:41:23<2:21:07,  1.64it/s]
 76%|███████▌  | 43737/57600 [7:41:24<2:19:34,  1.66it/s]
 76%|███████▌  | 43738/57600 [7:41:25<2:20:00,  1.65it/s]
 76%|███████▌  | 43739/57600 [7:41:25<2:25:10,  1.59it/s]
 76%|███████▌  | 43740/57600 [7:41:26<2:29:54,  1.54it/s]
                                                         
{'loss': 1.1159, 'learning_rate': 3.173170731707317e-07, 'epoch': 482.78}
+
 76%|███████▌  | 43740/57600 [7:41:26<2:29:54,  1.54it/s]
 76%|███████▌  | 43741/57600 [7:41:27<2:28:21,  1.56it/s]
 76%|███████▌  | 43742/57600 [7:41:27<2:28:01,  1.56it/s]
 76%|███████▌  | 43743/57600 [7:41:28<2:23:21,  1.61it/s]
 76%|███████▌  | 43744/57600 [7:41:28<2:23:34,  1.61it/s]
 76%|███████▌  | 43745/57600 [7:41:29<2:27:03,  1.57it/s]
 76%|███████▌  | 43746/57600 [7:41:30<2:24:19,  1.60it/s]
 76%|███████▌  | 43747/57600 [7:41:30<2:28:08,  1.56it/s]
 76%|███████▌  | 43748/57600 [7:41:31<2:29:58,  1.54it/s]
 76%|███████▌  | 43749/57600 [7:41:32<2:34:33,  1.49it/s]
 76%|███████▌  | 43750/57600 [7:41:32<2:31:31,  1.52it/s]
 76%|███████▌  | 43751/57600 [7:41:33<2:31:05,  1.53it/s]
 76%|███████▌  | 43752/57600 [7:41:34<2:32:25,  1.51it/s]
 76%|███████▌  | 43753/57600 [7:41:34<2:30:55,  1.53it/s]
 76%|███████▌  | 43754/57600 [7:41:35<2:27:56,  1.56it/s]
 76%|███████▌  | 43755/57600 [7:41:35<2:24:50,  1.59it/s]
 76%|███████▌  | 43756/57600 [7:41:36<2:22:29,  1.62it/s]
 76%|███████▌  | 43757/57600 [7:41:37<2:22:41,  1.62it/s]
 76%|███████▌  | 43758/57600 [7:41:37<2:24:20,  1.60it/s]
 76%|███████▌  | 43759/57600 [7:41:38<2:23:27,  1.61it/s]
 76%|███████▌  | 43760/57600 [7:41:39<2:32:04,  1.52it/s]
                                                         
{'loss': 1.1181, 'learning_rate': 3.1700348432055753e-07, 'epoch': 483.0}
+
 76%|███████▌  | 43760/57600 [7:41:39<2:32:04,  1.52it/s]
 76%|███████▌  | 43761/57600 [7:41:39<2:32:39,  1.51it/s]
 76%|███████▌  | 43762/57600 [7:41:40<2:35:28,  1.48it/s]
 76%|███████▌  | 43763/57600 [7:41:41<2:28:17,  1.56it/s]
 76%|███████▌  | 43764/57600 [7:41:41<2:27:51,  1.56it/s]
 76%|███████▌  | 43765/57600 [7:41:42<2:25:03,  1.59it/s]
 76%|███████▌  | 43766/57600 [7:41:43<2:27:26,  1.56it/s]
 76%|███████▌  | 43767/57600 [7:41:43<2:28:53,  1.55it/s]
 76%|███████▌  | 43768/57600 [7:41:44<2:23:23,  1.61it/s]
 76%|███████▌  | 43769/57600 [7:41:44<2:20:28,  1.64it/s]
 76%|███████▌  | 43770/57600 [7:41:45<2:20:35,  1.64it/s]
 76%|███████▌  | 43771/57600 [7:41:46<2:22:56,  1.61it/s]
 76%|███████▌  | 43772/57600 [7:41:46<2:28:34,  1.55it/s]
 76%|███████▌  | 43773/57600 [7:41:47<2:28:20,  1.55it/s]
 76%|███████▌  | 43774/57600 [7:41:48<2:27:15,  1.56it/s]
 76%|███████▌  | 43775/57600 [7:41:48<2:25:49,  1.58it/s]
 76%|███████▌  | 43776/57600 [7:41:49<2:24:20,  1.60it/s]
 76%|███████▌  | 43777/57600 [7:41:49<2:22:02,  1.62it/s]
 76%|███████▌  | 43778/57600 [7:41:50<2:20:13,  1.64it/s]
 76%|███████▌  | 43779/57600 [7:41:51<2:19:33,  1.65it/s]
 76%|███████▌  | 43780/57600 [7:41:51<2:24:24,  1.59it/s]
                                                         
{'loss': 1.1249, 'learning_rate': 3.1668989547038323e-07, 'epoch': 483.22}
+
 76%|███████▌  | 43780/57600 [7:41:51<2:24:24,  1.59it/s]
 76%|███████▌  | 43781/57600 [7:41:52<2:22:50,  1.61it/s]
 76%|███████▌  | 43782/57600 [7:41:53<2:23:51,  1.60it/s]
 76%|███████▌  | 43783/57600 [7:41:53<2:28:26,  1.55it/s]
 76%|███████▌  | 43784/57600 [7:41:54<2:27:44,  1.56it/s]
 76%|███████▌  | 43785/57600 [7:41:54<2:23:34,  1.60it/s]
 76%|███████▌  | 43786/57600 [7:41:55<2:22:15,  1.62it/s]
 76%|███████▌  | 43787/57600 [7:41:56<2:22:52,  1.61it/s]
 76%|███████▌  | 43788/57600 [7:41:56<2:22:24,  1.62it/s]
 76%|███████▌  | 43789/57600 [7:41:57<2:20:25,  1.64it/s]
 76%|███████▌  | 43790/57600 [7:41:57<2:21:05,  1.63it/s]
 76%|███████▌  | 43791/57600 [7:41:58<2:19:40,  1.65it/s]
 76%|███████▌  | 43792/57600 [7:41:59<2:25:25,  1.58it/s]
 76%|███████▌  | 43793/57600 [7:41:59<2:25:18,  1.58it/s]
 76%|███████▌  | 43794/57600 [7:42:00<2:25:51,  1.58it/s]
 76%|███████▌  | 43795/57600 [7:42:01<2:26:12,  1.57it/s]
 76%|███████▌  | 43796/57600 [7:42:01<2:25:43,  1.58it/s]
 76%|███████▌  | 43797/57600 [7:42:02<2:24:29,  1.59it/s]
 76%|███████▌  | 43798/57600 [7:42:03<2:28:08,  1.55it/s]
 76%|███████▌  | 43799/57600 [7:42:03<2:28:47,  1.55it/s]
 76%|███████▌  | 43800/57600 [7:42:04<2:26:58,  1.56it/s]
                                                         
{'loss': 1.1342, 'learning_rate': 3.1637630662020904e-07, 'epoch': 483.44}
+
 76%|███████▌  | 43800/57600 [7:42:04<2:26:58,  1.56it/s]
 76%|███████▌  | 43801/57600 [7:42:05<2:27:08,  1.56it/s]
 76%|███████▌  | 43802/57600 [7:42:05<2:24:45,  1.59it/s]
 76%|███████▌  | 43803/57600 [7:42:06<2:21:51,  1.62it/s]
 76%|███████▌  | 43804/57600 [7:42:06<2:21:56,  1.62it/s]
 76%|███████▌  | 43805/57600 [7:42:07<2:17:13,  1.68it/s]
 76%|███████▌  | 43806/57600 [7:42:08<2:24:56,  1.59it/s]
 76%|███████▌  | 43807/57600 [7:42:08<2:22:32,  1.61it/s]
 76%|███████▌  | 43808/57600 [7:42:09<2:19:02,  1.65it/s]
 76%|███████▌  | 43809/57600 [7:42:09<2:22:04,  1.62it/s]
 76%|███████▌  | 43810/57600 [7:42:10<2:26:20,  1.57it/s]
 76%|███████▌  | 43811/57600 [7:42:11<2:28:13,  1.55it/s]
 76%|███████▌  | 43812/57600 [7:42:11<2:26:49,  1.57it/s]
 76%|███████▌  | 43813/57600 [7:42:12<2:34:26,  1.49it/s]
 76%|███████▌  | 43814/57600 [7:42:13<2:33:03,  1.50it/s]
 76%|███████▌  | 43815/57600 [7:42:13<2:29:12,  1.54it/s]
 76%|███████▌  | 43816/57600 [7:42:14<2:28:05,  1.55it/s]
 76%|███████▌  | 43817/57600 [7:42:15<2:23:13,  1.60it/s]
 76%|███████▌  | 43818/57600 [7:42:15<2:24:06,  1.59it/s]
 76%|███████▌  | 43819/57600 [7:42:16<2:22:40,  1.61it/s]
 76%|███████▌  | 43820/57600 [7:42:16<2:23:13,  1.60it/s]
                                                         
{'loss': 1.1113, 'learning_rate': 3.160627177700348e-07, 'epoch': 483.66}
+
 76%|███████▌  | 43820/57600 [7:42:16<2:23:13,  1.60it/s]
 76%|███████▌  | 43821/57600 [7:42:17<2:20:46,  1.63it/s]
 76%|███████▌  | 43822/57600 [7:42:18<2:18:41,  1.66it/s]
 76%|███████▌  | 43823/57600 [7:42:18<2:23:11,  1.60it/s]
 76%|███████▌  | 43824/57600 [7:42:19<2:21:21,  1.62it/s]
 76%|███████▌  | 43825/57600 [7:42:20<2:22:27,  1.61it/s]
 76%|███████▌  | 43826/57600 [7:42:20<2:26:25,  1.57it/s]
 76%|███████▌  | 43827/57600 [7:42:21<2:25:22,  1.58it/s]
 76%|███████▌  | 43828/57600 [7:42:21<2:27:21,  1.56it/s]
 76%|███████▌  | 43829/57600 [7:42:22<2:27:38,  1.55it/s]
 76%|███████▌  | 43830/57600 [7:42:23<2:24:30,  1.59it/s]
 76%|███████▌  | 43831/57600 [7:42:23<2:20:26,  1.63it/s]
 76%|███████▌  | 43832/57600 [7:42:24<2:25:15,  1.58it/s]
 76%|███████▌  | 43833/57600 [7:42:25<2:30:20,  1.53it/s]
 76%|███████▌  | 43834/57600 [7:42:25<2:27:14,  1.56it/s]
 76%|███████▌  | 43835/57600 [7:42:26<2:26:49,  1.56it/s]
 76%|███████▌  | 43836/57600 [7:42:27<2:22:32,  1.61it/s]
 76%|███████▌  | 43837/57600 [7:42:27<2:19:15,  1.65it/s]
 76%|███████▌  | 43838/57600 [7:42:28<2:21:56,  1.62it/s]
 76%|███████▌  | 43839/57600 [7:42:28<2:22:03,  1.61it/s]
 76%|███████▌  | 43840/57600 [7:42:29<2:22:20,  1.61it/s]
                                                         
{'loss': 1.1048, 'learning_rate': 3.1574912891986065e-07, 'epoch': 483.89}
+
 76%|███████▌  | 43840/57600 [7:42:29<2:22:20,  1.61it/s]
 76%|███████▌  | 43841/57600 [7:42:30<2:26:19,  1.57it/s]
 76%|███████▌  | 43842/57600 [7:42:30<2:23:24,  1.60it/s]
 76%|███████▌  | 43843/57600 [7:42:31<2:27:37,  1.55it/s]
 76%|███████▌  | 43844/57600 [7:42:32<2:23:26,  1.60it/s]
 76%|███████▌  | 43845/57600 [7:42:32<2:19:59,  1.64it/s]
 76%|███████▌  | 43846/57600 [7:42:33<2:20:02,  1.64it/s]
 76%|███████▌  | 43847/57600 [7:42:33<2:17:42,  1.66it/s]
 76%|███████▌  | 43848/57600 [7:42:34<2:21:03,  1.62it/s]
 76%|███████▌  | 43849/57600 [7:42:35<2:20:53,  1.63it/s]
 76%|███████▌  | 43850/57600 [7:42:35<2:22:04,  1.61it/s]
 76%|███████▌  | 43851/57600 [7:42:36<2:31:05,  1.52it/s]
 76%|███████▌  | 43852/57600 [7:42:37<2:28:19,  1.54it/s]
 76%|███████▌  | 43853/57600 [7:42:37<2:24:16,  1.59it/s]
 76%|███████▌  | 43854/57600 [7:42:38<2:20:23,  1.63it/s]
 76%|███████▌  | 43855/57600 [7:42:38<2:23:13,  1.60it/s]
 76%|███████▌  | 43856/57600 [7:42:39<2:28:33,  1.54it/s]
 76%|███████▌  | 43857/57600 [7:42:40<2:25:40,  1.57it/s]
 76%|███████▌  | 43858/57600 [7:42:40<2:21:03,  1.62it/s]
 76%|███████▌  | 43859/57600 [7:42:41<2:22:32,  1.61it/s]
 76%|███████▌  | 43860/57600 [7:42:42<2:28:24,  1.54it/s]
                                                         
{'loss': 1.1291, 'learning_rate': 3.154355400696865e-07, 'epoch': 484.11}
+
 76%|███████▌  | 43860/57600 [7:42:42<2:28:24,  1.54it/s]
 76%|███████▌  | 43861/57600 [7:42:42<2:23:16,  1.60it/s]
 76%|███████▌  | 43862/57600 [7:42:43<2:25:43,  1.57it/s]
 76%|███████▌  | 43863/57600 [7:42:43<2:22:18,  1.61it/s]
 76%|███████▌  | 43864/57600 [7:42:44<2:21:11,  1.62it/s]
 76%|███████▌  | 43865/57600 [7:42:45<2:23:49,  1.59it/s]
 76%|███████▌  | 43866/57600 [7:42:45<2:24:08,  1.59it/s]
 76%|███████▌  | 43867/57600 [7:42:46<2:24:50,  1.58it/s]
 76%|███████▌  | 43868/57600 [7:42:47<2:22:32,  1.61it/s]
 76%|███████▌  | 43869/57600 [7:42:47<2:23:11,  1.60it/s]
 76%|███████▌  | 43870/57600 [7:42:48<2:22:07,  1.61it/s]
 76%|███████▌  | 43871/57600 [7:42:48<2:22:32,  1.61it/s]
 76%|███████▌  | 43872/57600 [7:42:49<2:22:48,  1.60it/s]
 76%|███████▌  | 43873/57600 [7:42:50<2:20:42,  1.63it/s]
 76%|███████▌  | 43874/57600 [7:42:50<2:23:45,  1.59it/s]
 76%|███████▌  | 43875/57600 [7:42:51<2:26:36,  1.56it/s]
 76%|███████▌  | 43876/57600 [7:42:52<2:23:45,  1.59it/s]
 76%|███████▌  | 43877/57600 [7:42:52<2:29:51,  1.53it/s]
 76%|███████▌  | 43878/57600 [7:42:53<2:27:15,  1.55it/s]
 76%|████���██▌  | 43879/57600 [7:42:53<2:20:33,  1.63it/s]
 76%|███████▌  | 43880/57600 [7:42:54<2:22:16,  1.61it/s]
                                                         
{'loss': 1.1107, 'learning_rate': 3.1512195121951215e-07, 'epoch': 484.33}
+
 76%|███████▌  | 43880/57600 [7:42:54<2:22:16,  1.61it/s]
 76%|███████▌  | 43881/57600 [7:42:55<2:22:45,  1.60it/s]
 76%|███████▌  | 43882/57600 [7:42:55<2:25:11,  1.57it/s]
 76%|███████▌  | 43883/57600 [7:42:56<2:22:40,  1.60it/s]
 76%|███████▌  | 43884/57600 [7:42:57<2:17:33,  1.66it/s]
 76%|███████▌  | 43885/57600 [7:42:57<2:19:58,  1.63it/s]
 76%|███████▌  | 43886/57600 [7:42:58<2:21:11,  1.62it/s]
 76%|███████▌  | 43887/57600 [7:42:58<2:23:26,  1.59it/s]
 76%|███████▌  | 43888/57600 [7:42:59<2:21:06,  1.62it/s]
 76%|███████▌  | 43889/57600 [7:43:00<2:21:35,  1.61it/s]
 76%|███████▌  | 43890/57600 [7:43:00<2:25:15,  1.57it/s]
 76%|███████▌  | 43891/57600 [7:43:01<2:25:04,  1.57it/s]
 76%|███████▌  | 43892/57600 [7:43:02<2:20:22,  1.63it/s]
 76%|███████▌  | 43893/57600 [7:43:02<2:21:35,  1.61it/s]
 76%|███████▌  | 43894/57600 [7:43:03<2:20:48,  1.62it/s]
 76%|███████▌  | 43895/57600 [7:43:03<2:25:58,  1.56it/s]
 76%|███████▌  | 43896/57600 [7:43:04<2:23:28,  1.59it/s]
 76%|███████▌  | 43897/57600 [7:43:05<2:27:04,  1.55it/s]
 76%|███████▌  | 43898/57600 [7:43:05<2:27:27,  1.55it/s]
 76%|███████▌  | 43899/57600 [7:43:06<2:27:31,  1.55it/s]
 76%|███████▌  | 43900/57600 [7:43:07<2:28:44,  1.54it/s]
                                                         
{'loss': 1.1534, 'learning_rate': 3.14808362369338e-07, 'epoch': 484.55}
+
 76%|███████▌  | 43900/57600 [7:43:07<2:28:44,  1.54it/s]
 76%|███████▌  | 43901/57600 [7:43:07<2:27:54,  1.54it/s]
 76%|███████▌  | 43902/57600 [7:43:08<2:26:33,  1.56it/s]
 76%|███████▌  | 43903/57600 [7:43:09<2:26:24,  1.56it/s]
 76%|███████▌  | 43904/57600 [7:43:09<2:25:57,  1.56it/s]
 76%|███████▌  | 43905/57600 [7:43:10<2:26:51,  1.55it/s]
 76%|███████▌  | 43906/57600 [7:43:10<2:22:27,  1.60it/s]
 76%|███████▌  | 43907/57600 [7:43:11<2:24:08,  1.58it/s]
 76%|███████▌  | 43908/57600 [7:43:12<2:20:24,  1.63it/s]
 76%|███████▌  | 43909/57600 [7:43:12<2:23:24,  1.59it/s]
 76%|███████▌  | 43910/57600 [7:43:13<2:28:49,  1.53it/s]
 76%|███████▌  | 43911/57600 [7:43:14<2:32:04,  1.50it/s]
 76%|███████▌  | 43912/57600 [7:43:14<2:26:38,  1.56it/s]
 76%|███████▌  | 43913/57600 [7:43:15<2:24:52,  1.57it/s]
 76%|███████▌  | 43914/57600 [7:43:16<2:26:19,  1.56it/s]
 76%|███████▌  | 43915/57600 [7:43:16<2:22:51,  1.60it/s]
 76%|███████▌  | 43916/57600 [7:43:17<2:20:03,  1.63it/s]
 76%|███████▌  | 43917/57600 [7:43:17<2:19:03,  1.64it/s]
 76%|███████▌  | 43918/57600 [7:43:18<2:22:12,  1.60it/s]
 76%|███████▌  | 43919/57600 [7:43:19<2:28:16,  1.54it/s]
 76%|███████▋  | 43920/57600 [7:43:19<2:26:19,  1.56it/s]
                                                         
{'loss': 1.116, 'learning_rate': 3.1449477351916376e-07, 'epoch': 484.77}
+
 76%|███████▋  | 43920/57600 [7:43:19<2:26:19,  1.56it/s]
 76%|███████▋  | 43921/57600 [7:43:20<2:24:40,  1.58it/s]
 76%|███████▋  | 43922/57600 [7:43:21<2:18:31,  1.65it/s]
 76%|███████▋  | 43923/57600 [7:43:21<2:21:34,  1.61it/s]
 76%|███████▋  | 43924/57600 [7:43:22<2:23:26,  1.59it/s]
 76%|███████▋  | 43925/57600 [7:43:23<2:30:08,  1.52it/s]
 76%|███████▋  | 43926/57600 [7:43:23<2:24:23,  1.58it/s]
 76%|███████▋  | 43927/57600 [7:43:24<2:25:12,  1.57it/s]
 76%|███████▋  | 43928/57600 [7:43:24<2:24:32,  1.58it/s]
 76%|███████▋  | 43929/57600 [7:43:25<2:22:36,  1.60it/s]
 76%|███████▋  | 43930/57600 [7:43:26<2:25:18,  1.57it/s]
 76%|███████▋  | 43931/57600 [7:43:26<2:24:14,  1.58it/s]
 76%|███████▋  | 43932/57600 [7:43:27<2:21:56,  1.60it/s]
 76%|███████▋  | 43933/57600 [7:43:28<2:20:37,  1.62it/s]
 76%|███████▋  | 43934/57600 [7:43:28<2:19:01,  1.64it/s]
 76%|███████▋  | 43935/57600 [7:43:29<2:19:59,  1.63it/s]
 76%|███████▋  | 43936/57600 [7:43:29<2:19:24,  1.63it/s]
 76%|███████▋  | 43937/57600 [7:43:30<2:17:49,  1.65it/s]
 76%|███████▋  | 43938/57600 [7:43:31<2:21:30,  1.61it/s]
 76%|███████▋  | 43939/57600 [7:43:31<2:22:37,  1.60it/s]
 76%|███████▋  | 43940/57600 [7:43:32<2:19:13,  1.64it/s]
                                                         
{'loss': 1.147, 'learning_rate': 3.1418118466898956e-07, 'epoch': 484.99}
+
 76%|███████▋  | 43940/57600 [7:43:32<2:19:13,  1.64it/s]
 76%|███████▋  | 43941/57600 [7:43:32<2:22:58,  1.59it/s]
 76%|███████▋  | 43942/57600 [7:43:33<2:29:19,  1.52it/s]
 76%|███████▋  | 43943/57600 [7:43:34<2:31:05,  1.51it/s]
 76%|███████▋  | 43944/57600 [7:43:34<2:23:54,  1.58it/s]
 76%|███████▋  | 43945/57600 [7:43:35<2:28:57,  1.53it/s]
 76%|███████▋  | 43946/57600 [7:43:36<2:26:15,  1.56it/s]
 76%|███████▋  | 43947/57600 [7:43:36<2:24:50,  1.57it/s]
 76%|███████▋  | 43948/57600 [7:43:37<2:20:11,  1.62it/s]
 76%|███████▋  | 43949/57600 [7:43:38<2:20:11,  1.62it/s]
 76%|███████▋  | 43950/57600 [7:43:38<2:19:30,  1.63it/s]
 76%|███████▋  | 43951/57600 [7:43:39<2:15:53,  1.67it/s]
 76%|███████▋  | 43952/57600 [7:43:39<2:18:11,  1.65it/s]
 76%|███████▋  | 43953/57600 [7:43:40<2:19:34,  1.63it/s]
 76%|███████▋  | 43954/57600 [7:43:41<2:23:52,  1.58it/s]
 76%|███████▋  | 43955/57600 [7:43:41<2:24:57,  1.57it/s]
 76%|███████▋  | 43956/57600 [7:43:42<2:27:26,  1.54it/s]
 76%|███████▋  | 43957/57600 [7:43:43<2:28:40,  1.53it/s]
 76%|███████▋  | 43958/57600 [7:43:43<2:24:11,  1.58it/s]
 76%|███████▋  | 43959/57600 [7:43:44<2:25:09,  1.57it/s]
 76%|███████▋  | 43960/57600 [7:43:45<2:24:20,  1.57it/s]
                                                         
{'loss': 1.1347, 'learning_rate': 3.1386759581881526e-07, 'epoch': 485.21}
+
 76%|███████▋  | 43960/57600 [7:43:45<2:24:20,  1.57it/s]
 76%|███████▋  | 43961/57600 [7:43:45<2:28:53,  1.53it/s]
 76%|███████▋  | 43962/57600 [7:43:46<2:24:20,  1.57it/s]
 76%|███████▋  | 43963/57600 [7:43:47<2:27:09,  1.54it/s]
 76%|███████▋  | 43964/57600 [7:43:47<2:24:40,  1.57it/s]
 76%|███████▋  | 43965/57600 [7:43:48<2:20:40,  1.62it/s]
 76%|███████▋  | 43966/57600 [7:43:48<2:19:09,  1.63it/s]
 76%|███████▋  | 43967/57600 [7:43:49<2:20:54,  1.61it/s]
 76%|███████▋  | 43968/57600 [7:43:50<2:19:56,  1.62it/s]
 76%|███████▋  | 43969/57600 [7:43:50<2:16:27,  1.66it/s]
 76%|███████▋  | 43970/57600 [7:43:51<2:16:49,  1.66it/s]
 76%|███████▋  | 43971/57600 [7:43:51<2:17:27,  1.65it/s]
 76%|███████▋  | 43972/57600 [7:43:52<2:15:12,  1.68it/s]
 76%|███████▋  | 43973/57600 [7:43:52<2:14:53,  1.68it/s]
 76%|███████▋  | 43974/57600 [7:43:53<2:21:40,  1.60it/s]
 76%|███████▋  | 43975/57600 [7:43:54<2:28:33,  1.53it/s]
 76%|███████▋  | 43976/57600 [7:43:55<2:29:14,  1.52it/s]
 76%|███████▋  | 43977/57600 [7:43:55<2:22:58,  1.59it/s]
 76%|███████▋  | 43978/57600 [7:43:56<2:23:08,  1.59it/s]
 76%|███████▋  | 43979/57600 [7:43:56<2:25:41,  1.56it/s]
 76%|███████▋  | 43980/57600 [7:43:57<2:25:38,  1.56it/s]
                                                         
{'loss': 1.1253, 'learning_rate': 3.135540069686412e-07, 'epoch': 485.43}
+
 76%|███████▋  | 43980/57600 [7:43:57<2:25:38,  1.56it/s]
 76%|███████▋  | 43981/57600 [7:43:58<2:27:37,  1.54it/s]
 76%|███████▋  | 43982/57600 [7:43:58<2:27:50,  1.54it/s]
 76%|███████▋  | 43983/57600 [7:43:59<2:24:44,  1.57it/s]
 76%|███████▋  | 43984/57600 [7:44:00<2:21:46,  1.60it/s]
 76%|███████▋  | 43985/57600 [7:44:00<2:18:43,  1.64it/s]
 76%|███████▋  | 43986/57600 [7:44:01<2:24:39,  1.57it/s]
 76%|███████▋  | 43987/57600 [7:44:01<2:23:25,  1.58it/s]
 76%|███████▋  | 43988/57600 [7:44:02<2:20:27,  1.62it/s]
 76%|███████▋  | 43989/57600 [7:44:03<2:25:18,  1.56it/s]
 76%|███████▋  | 43990/57600 [7:44:03<2:24:10,  1.57it/s]
 76%|███████▋  | 43991/57600 [7:44:04<2:29:10,  1.52it/s]
 76%|███████▋  | 43992/57600 [7:44:05<2:23:50,  1.58it/s]
 76%|███████▋  | 43993/57600 [7:44:05<2:24:26,  1.57it/s]
 76%|███████▋  | 43994/57600 [7:44:06<2:26:28,  1.55it/s]
 76%|███████▋  | 43995/57600 [7:44:07<2:27:30,  1.54it/s]
 76%|███████▋  | 43996/57600 [7:44:07<2:21:41,  1.60it/s]
 76%|███████▋  | 43997/57600 [7:44:08<2:20:16,  1.62it/s]
 76%|███████▋  | 43998/57600 [7:44:08<2:22:05,  1.60it/s]
 76%|███████▋  | 43999/57600 [7:44:09<2:20:06,  1.62it/s]
 76%|███████▋  | 44000/57600 [7:44:10<2:20:02,  1.62it/s]
                                                         
{'loss': 1.1149, 'learning_rate': 3.1324041811846693e-07, 'epoch': 485.65}
+
 76%|███████▋  | 44000/57600 [7:44:10<2:20:02,  1.62it/s]
 76%|███████▋  | 44001/57600 [7:44:10<2:17:05,  1.65it/s]
 76%|███████▋  | 44002/57600 [7:44:11<2:16:16,  1.66it/s]
 76%|███████▋  | 44003/57600 [7:44:11<2:16:52,  1.66it/s]
 76%|███████▋  | 44004/57600 [7:44:12<2:16:17,  1.66it/s]
 76%|███████▋  | 44005/57600 [7:44:13<2:19:03,  1.63it/s]
 76%|███████▋  | 44006/57600 [7:44:13<2:23:50,  1.58it/s]
 76%|███████▋  | 44007/57600 [7:44:14<2:23:03,  1.58it/s]
 76%|███████▋  | 44008/57600 [7:44:15<2:20:00,  1.62it/s]
 76%|███████▋  | 44009/57600 [7:44:15<2:18:51,  1.63it/s]
 76%|███████▋  | 44010/57600 [7:44:16<2:26:40,  1.54it/s]
 76%|███████▋  | 44011/57600 [7:44:17<2:23:31,  1.58it/s]
 76%|███████▋  | 44012/57600 [7:44:17<2:25:01,  1.56it/s]
 76%|███████▋  | 44013/57600 [7:44:18<2:24:30,  1.57it/s]
 76%|███████▋  | 44014/57600 [7:44:18<2:23:33,  1.58it/s]
 76%|███████▋  | 44015/57600 [7:44:19<2:27:20,  1.54it/s]
 76%|███████▋  | 44016/57600 [7:44:20<2:24:12,  1.57it/s]
 76%|███████▋  | 44017/57600 [7:44:20<2:23:21,  1.58it/s]
 76%|███████▋  | 44018/57600 [7:44:21<2:24:24,  1.57it/s]
 76%|███████▋  | 44019/57600 [7:44:22<2:24:33,  1.57it/s]
 76%|███████▋  | 44020/57600 [7:44:22<2:18:12,  1.64it/s]
                                                         
{'loss': 1.1594, 'learning_rate': 3.129268292682926e-07, 'epoch': 485.87}
+
 76%|███████▋  | 44020/57600 [7:44:22<2:18:12,  1.64it/s]
 76%|███████▋  | 44021/57600 [7:44:23<2:19:11,  1.63it/s]
 76%|███████▋  | 44022/57600 [7:44:23<2:20:24,  1.61it/s]
 76%|███████▋  | 44023/57600 [7:44:24<2:16:59,  1.65it/s]
 76%|███████▋  | 44024/57600 [7:44:25<2:18:44,  1.63it/s]
 76%|███████▋  | 44025/57600 [7:44:25<2:22:21,  1.59it/s]
 76%|███████▋  | 44026/57600 [7:44:26<2:22:27,  1.59it/s]
 76%|███████▋  | 44027/57600 [7:44:27<2:20:30,  1.61it/s]
 76%|███████▋  | 44028/57600 [7:44:27<2:20:44,  1.61it/s]
 76%|███████▋  | 44029/57600 [7:44:28<2:18:48,  1.63it/s]
 76%|███████▋  | 44030/57600 [7:44:29<2:28:17,  1.53it/s]
 76%|███████▋  | 44031/57600 [7:44:29<2:23:42,  1.57it/s]
 76%|███████▋  | 44032/57600 [7:44:30<2:26:46,  1.54it/s]
 76%|███████▋  | 44033/57600 [7:44:30<2:22:47,  1.58it/s]
 76%|███████▋  | 44034/57600 [7:44:31<2:19:31,  1.62it/s]
 76%|███████▋  | 44035/57600 [7:44:32<2:18:54,  1.63it/s]
 76%|███████▋  | 44036/57600 [7:44:32<2:17:12,  1.65it/s]
 76%|███████▋  | 44037/57600 [7:44:33<2:17:30,  1.64it/s]
 76%|███████▋  | 44038/57600 [7:44:33<2:20:06,  1.61it/s]
 76%|███████▋  | 44039/57600 [7:44:34<2:17:14,  1.65it/s]
 76%|███████▋  | 44040/57600 [7:44:35<2:15:40,  1.67it/s]
                                                         
{'loss': 1.1279, 'learning_rate': 3.126132404181185e-07, 'epoch': 486.09}
+
 76%|███████▋  | 44040/57600 [7:44:35<2:15:40,  1.67it/s]
 76%|███████▋  | 44041/57600 [7:44:35<2:19:36,  1.62it/s]
 76%|███████▋  | 44042/57600 [7:44:36<2:17:26,  1.64it/s]
 76%|███████▋  | 44043/57600 [7:44:37<2:22:55,  1.58it/s]
 76%|███████▋  | 44044/57600 [7:44:37<2:21:29,  1.60it/s]
 76%|███████▋  | 44045/57600 [7:44:38<2:18:50,  1.63it/s]
 76%|███████▋  | 44046/57600 [7:44:38<2:16:14,  1.66it/s]
 76%|███████▋  | 44047/57600 [7:44:39<2:17:36,  1.64it/s]
 76%|███████▋  | 44048/57600 [7:44:39<2:15:25,  1.67it/s]
 76%|███████▋  | 44049/57600 [7:44:40<2:16:11,  1.66it/s]
 76%|███████▋  | 44050/57600 [7:44:41<2:20:18,  1.61it/s]
 76%|███████▋  | 44051/57600 [7:44:41<2:22:09,  1.59it/s]
 76%|███████▋  | 44052/57600 [7:44:42<2:22:02,  1.59it/s]
 76%|███████▋  | 44053/57600 [7:44:43<2:19:42,  1.62it/s]
 76%|███████▋  | 44054/57600 [7:44:43<2:24:35,  1.56it/s]
 76%|███████▋  | 44055/57600 [7:44:44<2:27:55,  1.53it/s]
 76%|███████▋  | 44056/57600 [7:44:45<2:24:18,  1.56it/s]
 76%|███████▋  | 44057/57600 [7:44:45<2:24:28,  1.56it/s]
 76%|███████▋  | 44058/57600 [7:44:46<2:24:51,  1.56it/s]
 76%|███████▋  | 44059/57600 [7:44:47<2:23:10,  1.58it/s]
 76%|███████▋  | 44060/57600 [7:44:47<2:21:29,  1.59it/s]
                                                         
{'loss': 1.1097, 'learning_rate': 3.1229965156794424e-07, 'epoch': 486.31}
+
 76%|███████▋  | 44060/57600 [7:44:47<2:21:29,  1.59it/s]
 76%|███████▋  | 44061/57600 [7:44:48<2:23:47,  1.57it/s]
 76%|███████▋  | 44062/57600 [7:44:48<2:23:26,  1.57it/s]
 76%|███████▋  | 44063/57600 [7:44:49<2:26:10,  1.54it/s]
 76%|███████▋  | 44064/57600 [7:44:50<2:25:53,  1.55it/s]
 77%|███████▋  | 44065/57600 [7:44:50<2:25:26,  1.55it/s]
 77%|███████▋  | 44066/57600 [7:44:51<2:29:45,  1.51it/s]
 77%|███████▋  | 44067/57600 [7:44:52<2:24:45,  1.56it/s]
 77%|███████▋  | 44068/57600 [7:44:52<2:25:22,  1.55it/s]
 77%|███████▋  | 44069/57600 [7:44:53<2:25:09,  1.55it/s]
 77%|███████▋  | 44070/57600 [7:44:54<2:27:03,  1.53it/s]
 77%|███████▋  | 44071/57600 [7:44:54<2:29:04,  1.51it/s]
 77%|███████▋  | 44072/57600 [7:44:55<2:25:55,  1.55it/s]
 77%|███████▋  | 44073/57600 [7:44:56<2:24:33,  1.56it/s]
 77%|███████▋  | 44074/57600 [7:44:56<2:21:02,  1.60it/s]
 77%|███████▋  | 44075/57600 [7:44:57<2:20:32,  1.60it/s]
 77%|███████▋  | 44076/57600 [7:44:57<2:18:26,  1.63it/s]
 77%|███████▋  | 44077/57600 [7:44:58<2:19:48,  1.61it/s]
 77%|███████▋  | 44078/57600 [7:44:59<2:22:11,  1.58it/s]
 77%|███████▋  | 44079/57600 [7:44:59<2:18:38,  1.63it/s]
 77%|███████▋  | 44080/57600 [7:45:00<2:19:55,  1.61it/s]
                                                         
{'loss': 1.0929, 'learning_rate': 3.1198606271777004e-07, 'epoch': 486.53}
+
 77%|███████▋  | 44080/57600 [7:45:00<2:19:55,  1.61it/s]
 77%|███████▋  | 44081/57600 [7:45:00<2:18:28,  1.63it/s]
 77%|███████▋  | 44082/57600 [7:45:01<2:20:58,  1.60it/s]
 77%|███████▋  | 44083/57600 [7:45:02<2:18:23,  1.63it/s]
 77%|███████▋  | 44084/57600 [7:45:02<2:21:03,  1.60it/s]
 77%|███████▋  | 44085/57600 [7:45:03<2:24:29,  1.56it/s]
 77%|███████▋  | 44086/57600 [7:45:04<2:20:23,  1.60it/s]
 77%|███████▋  | 44087/57600 [7:45:04<2:18:10,  1.63it/s]
 77%|███████▋  | 44088/57600 [7:45:05<2:18:04,  1.63it/s]
 77%|███████▋  | 44089/57600 [7:45:05<2:20:59,  1.60it/s]
 77%|███████▋  | 44090/57600 [7:45:06<2:20:12,  1.61it/s]
 77%|███████▋  | 44091/57600 [7:45:07<2:22:39,  1.58it/s]
 77%|███████▋  | 44092/57600 [7:45:07<2:24:13,  1.56it/s]
 77%|███████▋  | 44093/57600 [7:45:08<2:23:13,  1.57it/s]
 77%|███████▋  | 44094/57600 [7:45:09<2:30:19,  1.50it/s]
 77%|███████▋  | 44095/57600 [7:45:10<2:32:51,  1.47it/s]
 77%|███████▋  | 44096/57600 [7:45:10<2:29:28,  1.51it/s]
 77%|███████▋  | 44097/57600 [7:45:11<2:26:29,  1.54it/s]
 77%|███████▋  | 44098/57600 [7:45:11<2:25:37,  1.55it/s]
 77%|███████▋  | 44099/57600 [7:45:12<2:26:48,  1.53it/s]
 77%|███████▋  | 44100/57600 [7:45:13<2:24:45,  1.55it/s]
                                                         
{'loss': 1.1549, 'learning_rate': 3.1167247386759574e-07, 'epoch': 486.75}
+
 77%|███████▋  | 44100/57600 [7:45:13<2:24:45,  1.55it/s]
 77%|███████▋  | 44101/57600 [7:45:13<2:21:35,  1.59it/s]
 77%|███████▋  | 44102/57600 [7:45:14<2:19:57,  1.61it/s]
 77%|███████▋  | 44103/57600 [7:45:15<2:21:35,  1.59it/s]
 77%|███████▋  | 44104/57600 [7:45:15<2:20:16,  1.60it/s]
 77%|███████▋  | 44105/57600 [7:45:16<2:28:27,  1.52it/s]
 77%|███████▋  | 44106/57600 [7:45:16<2:25:43,  1.54it/s]
 77%|███████▋  | 44107/57600 [7:45:17<2:22:27,  1.58it/s]
 77%|███████▋  | 44108/57600 [7:45:18<2:25:49,  1.54it/s]
 77%|███████▋  | 44109/57600 [7:45:18<2:22:52,  1.57it/s]
 77%|███████▋  | 44110/57600 [7:45:19<2:21:52,  1.58it/s]
 77%|███████▋  | 44111/57600 [7:45:20<2:24:25,  1.56it/s]
 77%|███████▋  | 44112/57600 [7:45:20<2:22:36,  1.58it/s]
 77%|███████▋  | 44113/57600 [7:45:21<2:21:10,  1.59it/s]
 77%|███████▋  | 44114/57600 [7:45:22<2:23:23,  1.57it/s]
 77%|███████▋  | 44115/57600 [7:45:22<2:29:43,  1.50it/s]
 77%|███████▋  | 44116/57600 [7:45:23<2:23:50,  1.56it/s]
 77%|███████▋  | 44117/57600 [7:45:24<2:23:56,  1.56it/s]
 77%|███████▋  | 44118/57600 [7:45:24<2:24:50,  1.55it/s]
 77%|███████▋  | 44119/57600 [7:45:25<2:22:21,  1.58it/s]
 77%|███████▋  | 44120/57600 [7:45:25<2:18:57,  1.62it/s]
                                                         
{'loss': 1.1118, 'learning_rate': 3.113588850174216e-07, 'epoch': 486.98}
+
 77%|███████▋  | 44120/57600 [7:45:25<2:18:57,  1.62it/s]
 77%|███████▋  | 44121/57600 [7:45:26<2:18:30,  1.62it/s]
 77%|███████▋  | 44122/57600 [7:45:27<2:18:42,  1.62it/s]
 77%|███████▋  | 44123/57600 [7:45:27<2:22:32,  1.58it/s]
 77%|███████▋  | 44124/57600 [7:45:28<2:25:08,  1.55it/s]
 77%|███████▋  | 44125/57600 [7:45:29<2:24:49,  1.55it/s]
 77%|███████▋  | 44126/57600 [7:45:29<2:24:46,  1.55it/s]
 77%|███████▋  | 44127/57600 [7:45:30<2:29:39,  1.50it/s]
 77%|███████▋  | 44128/57600 [7:45:31<2:25:12,  1.55it/s]
 77%|███████▋  | 44129/57600 [7:45:31<2:26:19,  1.53it/s]
 77%|███████▋  | 44130/57600 [7:45:32<2:23:53,  1.56it/s]
 77%|███████▋  | 44131/57600 [7:45:33<2:28:04,  1.52it/s]
 77%|███████▋  | 44132/57600 [7:45:33<2:28:14,  1.51it/s]
 77%|███████▋  | 44133/57600 [7:45:34<2:26:00,  1.54it/s]
 77%|███████▋  | 44134/57600 [7:45:34<2:23:07,  1.57it/s]
 77%|███████▋  | 44135/57600 [7:45:35<2:24:44,  1.55it/s]
 77%|███████▋  | 44136/57600 [7:45:36<2:26:50,  1.53it/s]
 77%|███████▋  | 44137/57600 [7:45:36<2:23:56,  1.56it/s]
 77%|███████▋  | 44138/57600 [7:45:37<2:26:14,  1.53it/s]
 77%|███████▋  | 44139/57600 [7:45:38<2:21:18,  1.59it/s]
 77%|███████▋  | 44140/57600 [7:45:38<2:17:42,  1.63it/s]
                                                         
{'loss': 1.1265, 'learning_rate': 3.1104529616724745e-07, 'epoch': 487.2}
+
 77%|███████▋  | 44140/57600 [7:45:38<2:17:42,  1.63it/s]
 77%|███████▋  | 44141/57600 [7:45:39<2:18:31,  1.62it/s]
 77%|███████▋  | 44142/57600 [7:45:39<2:19:05,  1.61it/s]
 77%|███████▋  | 44143/57600 [7:45:40<2:19:04,  1.61it/s]
 77%|███████▋  | 44144/57600 [7:45:41<2:17:47,  1.63it/s]
 77%|███████▋  | 44145/57600 [7:45:41<2:16:30,  1.64it/s]
 77%|███████▋  | 44146/57600 [7:45:42<2:15:50,  1.65it/s]
 77%|███████▋  | 44147/57600 [7:45:43<2:18:30,  1.62it/s]
 77%|███████▋  | 44148/57600 [7:45:43<2:22:04,  1.58it/s]
 77%|███████▋  | 44149/57600 [7:45:44<2:17:50,  1.63it/s]
 77%|███████▋  | 44150/57600 [7:45:44<2:20:29,  1.60it/s]
 77%|███████▋  | 44151/57600 [7:45:45<2:17:57,  1.62it/s]
 77%|███████▋  | 44152/57600 [7:45:46<2:16:56,  1.64it/s]
 77%|███████▋  | 44153/57600 [7:45:46<2:21:08,  1.59it/s]
 77%|███████▋  | 44154/57600 [7:45:47<2:19:25,  1.61it/s]
 77%|███████▋  | 44155/57600 [7:45:47<2:17:49,  1.63it/s]
 77%|███████▋  | 44156/57600 [7:45:48<2:24:49,  1.55it/s]
 77%|███████▋  | 44157/57600 [7:45:49<2:18:30,  1.62it/s]
 77%|███████▋  | 44158/57600 [7:45:49<2:20:05,  1.60it/s]
 77%|███████▋  | 44159/57600 [7:45:50<2:16:48,  1.64it/s]
 77%|███████▋  | 44160/57600 [7:45:51<2:21:30,  1.58it/s]
                                                         
{'loss': 1.1465, 'learning_rate': 3.1073170731707315e-07, 'epoch': 487.42}
+
 77%|███████▋  | 44160/57600 [7:45:51<2:21:30,  1.58it/s]
 77%|███████▋  | 44161/57600 [7:45:51<2:23:12,  1.56it/s]
 77%|███████▋  | 44162/57600 [7:45:52<2:20:14,  1.60it/s]
 77%|███████▋  | 44163/57600 [7:45:53<2:20:13,  1.60it/s]
 77%|███████▋  | 44164/57600 [7:45:53<2:23:24,  1.56it/s]
 77%|███████▋  | 44165/57600 [7:45:54<2:19:48,  1.60it/s]
 77%|███████▋  | 44166/57600 [7:45:54<2:18:27,  1.62it/s]
 77%|███████▋  | 44167/57600 [7:45:55<2:19:37,  1.60it/s]
 77%|███████▋  | 44168/57600 [7:45:56<2:18:24,  1.62it/s]
 77%|███████▋  | 44169/57600 [7:45:56<2:18:29,  1.62it/s]
 77%|███████▋  | 44170/57600 [7:45:57<2:21:51,  1.58it/s]
 77%|███████▋  | 44171/57600 [7:45:58<2:18:59,  1.61it/s]
 77%|███████▋  | 44172/57600 [7:45:58<2:17:43,  1.62it/s]
 77%|███████▋  | 44173/57600 [7:45:59<2:16:56,  1.63it/s]
 77%|███████▋  | 44174/57600 [7:45:59<2:17:48,  1.62it/s]
 77%|███████▋  | 44175/57600 [7:46:00<2:17:55,  1.62it/s]
 77%|███████▋  | 44176/57600 [7:46:01<2:22:26,  1.57it/s]
 77%|███████▋  | 44177/57600 [7:46:01<2:20:13,  1.60it/s]
 77%|███████▋  | 44178/57600 [7:46:02<2:23:45,  1.56it/s]
 77%|███████▋  | 44179/57600 [7:46:03<2:21:08,  1.58it/s]
 77%|███████▋  | 44180/57600 [7:46:03<2:20:49,  1.59it/s]
                                                         
{'loss': 1.1336, 'learning_rate': 3.1041811846689896e-07, 'epoch': 487.64}
+
 77%|█���█████▋  | 44180/57600 [7:46:03<2:20:49,  1.59it/s]
 77%|███████▋  | 44181/57600 [7:46:04<2:15:08,  1.66it/s]
 77%|███████▋  | 44182/57600 [7:46:04<2:16:17,  1.64it/s]
 77%|███████▋  | 44183/57600 [7:46:05<2:15:41,  1.65it/s]
 77%|███████▋  | 44184/57600 [7:46:06<2:17:01,  1.63it/s]
 77%|███████▋  | 44185/57600 [7:46:06<2:17:08,  1.63it/s]
 77%|███████▋  | 44186/57600 [7:46:07<2:21:24,  1.58it/s]
 77%|███████▋  | 44187/57600 [7:46:07<2:20:08,  1.60it/s]
 77%|███████▋  | 44188/57600 [7:46:08<2:17:56,  1.62it/s]
 77%|███████▋  | 44189/57600 [7:46:09<2:21:27,  1.58it/s]
 77%|███████▋  | 44190/57600 [7:46:09<2:18:35,  1.61it/s]
 77%|███████▋  | 44191/57600 [7:46:10<2:16:14,  1.64it/s]
 77%|███████▋  | 44192/57600 [7:46:11<2:15:28,  1.65it/s]
 77%|███████▋  | 44193/57600 [7:46:11<2:14:48,  1.66it/s]
 77%|███████▋  | 44194/57600 [7:46:12<2:17:27,  1.63it/s]
 77%|███████▋  | 44195/57600 [7:46:12<2:20:09,  1.59it/s]
 77%|███████▋  | 44196/57600 [7:46:13<2:23:24,  1.56it/s]
 77%|███████▋  | 44197/57600 [7:46:14<2:24:32,  1.55it/s]
 77%|███████▋  | 44198/57600 [7:46:14<2:23:06,  1.56it/s]
 77%|███████▋  | 44199/57600 [7:46:15<2:20:15,  1.59it/s]
 77%|███████▋  | 44200/57600 [7:46:16<2:19:44,  1.60it/s]
                                                         
{'loss': 1.1667, 'learning_rate': 3.101045296167247e-07, 'epoch': 487.86}
+
 77%|███████▋  | 44200/57600 [7:46:16<2:19:44,  1.60it/s]
 77%|███████▋  | 44201/57600 [7:46:16<2:20:08,  1.59it/s]
 77%|███████▋  | 44202/57600 [7:46:17<2:19:52,  1.60it/s]
 77%|███████▋  | 44203/57600 [7:46:17<2:17:52,  1.62it/s]
 77%|███████▋  | 44204/57600 [7:46:18<2:20:15,  1.59it/s]
 77%|███████▋  | 44205/57600 [7:46:19<2:19:20,  1.60it/s]
 77%|███████▋  | 44206/57600 [7:46:19<2:23:46,  1.55it/s]
 77%|███████▋  | 44207/57600 [7:46:20<2:22:04,  1.57it/s]
 77%|███████▋  | 44208/57600 [7:46:21<2:23:50,  1.55it/s]
 77%|███████▋  | 44209/57600 [7:46:21<2:21:24,  1.58it/s]
 77%|███████▋  | 44210/57600 [7:46:22<2:19:53,  1.60it/s]
 77%|███████▋  | 44211/57600 [7:46:23<2:22:47,  1.56it/s]
 77%|███████▋  | 44212/57600 [7:46:23<2:19:00,  1.61it/s]
 77%|███████▋  | 44213/57600 [7:46:24<2:23:54,  1.55it/s]
 77%|███████▋  | 44214/57600 [7:46:24<2:21:25,  1.58it/s]
 77%|███████▋  | 44215/57600 [7:46:25<2:17:23,  1.62it/s]
 77%|███████▋  | 44216/57600 [7:46:26<2:19:13,  1.60it/s]
 77%|███████▋  | 44217/57600 [7:46:26<2:21:14,  1.58it/s]
 77%|███████▋  | 44218/57600 [7:46:27<2:14:40,  1.66it/s]
 77%|███████▋  | 44219/57600 [7:46:27<2:11:58,  1.69it/s]
 77%|███████▋  | 44220/57600 [7:46:28<2:16:02,  1.64it/s]
                                                         
{'loss': 1.1588, 'learning_rate': 3.097909407665505e-07, 'epoch': 488.08}
+
 77%|███████▋  | 44220/57600 [7:46:28<2:16:02,  1.64it/s]
 77%|███████▋  | 44221/57600 [7:46:29<2:21:27,  1.58it/s]
 77%|███████▋  | 44222/57600 [7:46:30<2:29:35,  1.49it/s]
 77%|███████▋  | 44223/57600 [7:46:30<2:24:04,  1.55it/s]
 77%|███████▋  | 44224/57600 [7:46:31<2:22:59,  1.56it/s]
 77%|███████▋  | 44225/57600 [7:46:31<2:23:33,  1.55it/s]
 77%|███████▋  | 44226/57600 [7:46:32<2:25:53,  1.53it/s]
 77%|███████▋  | 44227/57600 [7:46:33<2:21:39,  1.57it/s]
 77%|███████▋  | 44228/57600 [7:46:33<2:21:02,  1.58it/s]
 77%|███████▋  | 44229/57600 [7:46:34<2:20:17,  1.59it/s]
 77%|███████▋  | 44230/57600 [7:46:35<2:19:39,  1.60it/s]
 77%|███████▋  | 44231/57600 [7:46:35<2:25:05,  1.54it/s]
 77%|███████▋  | 44232/57600 [7:46:36<2:23:52,  1.55it/s]
 77%|███████▋  | 44233/57600 [7:46:37<2:26:57,  1.52it/s]
 77%|███████▋  | 44234/57600 [7:46:37<2:23:14,  1.56it/s]
 77%|███████▋  | 44235/57600 [7:46:38<2:24:48,  1.54it/s]
 77%|███████▋  | 44236/57600 [7:46:38<2:23:12,  1.56it/s]
 77%|███████▋  | 44237/57600 [7:46:39<2:21:31,  1.57it/s]
 77%|███████▋  | 44238/57600 [7:46:40<2:17:46,  1.62it/s]
 77%|███████▋  | 44239/57600 [7:46:40<2:17:18,  1.62it/s]
 77%|███████▋  | 44240/57600 [7:46:41<2:20:32,  1.58it/s]
                                                         
{'loss': 1.096, 'learning_rate': 3.094773519163762e-07, 'epoch': 488.3}
+
 77%|███████▋  | 44240/57600 [7:46:41<2:20:32,  1.58it/s]
 77%|███████▋  | 44241/57600 [7:46:42<2:17:33,  1.62it/s]
 77%|███████▋  | 44242/57600 [7:46:42<2:14:17,  1.66it/s]
 77%|███████▋  | 44243/57600 [7:46:43<2:13:50,  1.66it/s]
 77%|███████▋  | 44244/57600 [7:46:43<2:13:25,  1.67it/s]
 77%|███████▋  | 44245/57600 [7:46:44<2:18:22,  1.61it/s]
 77%|███████▋  | 44246/57600 [7:46:45<2:24:00,  1.55it/s]
 77%|███████▋  | 44247/57600 [7:46:45<2:22:09,  1.57it/s]
 77%|███████▋  | 44248/57600 [7:46:46<2:20:33,  1.58it/s]
 77%|███████▋  | 44249/57600 [7:46:47<2:19:03,  1.60it/s]
 77%|███████▋  | 44250/57600 [7:46:47<2:17:29,  1.62it/s]
 77%|███████▋  | 44251/57600 [7:46:48<2:12:59,  1.67it/s]
 77%|███████▋  | 44252/57600 [7:46:48<2:13:39,  1.66it/s]
 77%|███████▋  | 44253/57600 [7:46:49<2:14:07,  1.66it/s]
 77%|███████▋  | 44254/57600 [7:46:50<2:21:20,  1.57it/s]
 77%|███████▋  | 44255/57600 [7:46:50<2:20:05,  1.59it/s]
 77%|███████▋  | 44256/57600 [7:46:51<2:19:56,  1.59it/s]
 77%|███████▋  | 44257/57600 [7:46:51<2:18:12,  1.61it/s]
 77%|███████▋  | 44258/57600 [7:46:52<2:17:14,  1.62it/s]
 77%|███████▋  | 44259/57600 [7:46:53<2:20:45,  1.58it/s]
 77%|███████▋  | 44260/57600 [7:46:53<2:19:30,  1.59it/s]
                                                         
{'loss': 1.1389, 'learning_rate': 3.0916376306620207e-07, 'epoch': 488.52}
+
 77%|███████▋  | 44260/57600 [7:46:53<2:19:30,  1.59it/s]
 77%|███████▋  | 44261/57600 [7:46:54<2:23:14,  1.55it/s]
 77%|███████▋  | 44262/57600 [7:46:55<2:20:22,  1.58it/s]
 77%|███████▋  | 44263/57600 [7:46:55<2:19:48,  1.59it/s]
 77%|███████▋  | 44264/57600 [7:46:56<2:24:27,  1.54it/s]
 77%|███████▋  | 44265/57600 [7:46:57<2:22:32,  1.56it/s]
 77%|███████▋  | 44266/57600 [7:46:57<2:23:21,  1.55it/s]
 77%|███████▋  | 44267/57600 [7:46:58<2:27:01,  1.51it/s]
 77%|███████▋  | 44268/57600 [7:46:59<2:26:38,  1.52it/s]
 77%|███████▋  | 44269/57600 [7:46:59<2:23:09,  1.55it/s]
 77%|███████▋  | 44270/57600 [7:47:00<2:24:17,  1.54it/s]
 77%|███████▋  | 44271/57600 [7:47:00<2:21:21,  1.57it/s]
 77%|███████▋  | 44272/57600 [7:47:01<2:19:22,  1.59it/s]
 77%|███████▋  | 44273/57600 [7:47:02<2:20:49,  1.58it/s]
 77%|███████▋  | 44274/57600 [7:47:02<2:22:19,  1.56it/s]
 77%|███████▋  | 44275/57600 [7:47:03<2:19:02,  1.60it/s]
 77%|███████▋  | 44276/57600 [7:47:04<2:15:47,  1.64it/s]
 77%|███████▋  | 44277/57600 [7:47:04<2:17:17,  1.62it/s]
 77%|███████▋  | 44278/57600 [7:47:05<2:18:01,  1.61it/s]
 77%|███████▋  | 44279/57600 [7:47:05<2:18:55,  1.60it/s]
 77%|███████▋  | 44280/57600 [7:47:06<2:18:56,  1.60it/s]
                                                         
{'loss': 1.1224, 'learning_rate': 3.0885017421602793e-07, 'epoch': 488.74}
+
 77%|███████▋  | 44280/57600 [7:47:06<2:18:56,  1.60it/s]
 77%|███████▋  | 44281/57600 [7:47:07<2:18:12,  1.61it/s]
 77%|███████▋  | 44282/57600 [7:47:07<2:20:35,  1.58it/s]
 77%|███████▋  | 44283/57600 [7:47:08<2:18:59,  1.60it/s]
 77%|███████▋  | 44284/57600 [7:47:09<2:19:57,  1.59it/s]
 77%|███████▋  | 44285/57600 [7:47:09<2:19:31,  1.59it/s]
 77%|███████▋  | 44286/57600 [7:47:10<2:19:27,  1.59it/s]
 77%|███████▋  | 44287/57600 [7:47:10<2:15:37,  1.64it/s]
 77%|███████▋  | 44288/57600 [7:47:11<2:17:09,  1.62it/s]
 77%|███████▋  | 44289/57600 [7:47:12<2:13:41,  1.66it/s]
 77%|███████▋  | 44290/57600 [7:47:12<2:16:25,  1.63it/s]
 77%|███████▋  | 44291/57600 [7:47:13<2:13:32,  1.66it/s]
 77%|███████▋  | 44292/57600 [7:47:13<2:14:19,  1.65it/s]
 77%|███████▋  | 44293/57600 [7:47:14<2:17:31,  1.61it/s]
 77%|███████▋  | 44294/57600 [7:47:15<2:12:57,  1.67it/s]
 77%|███████▋  | 44295/57600 [7:47:15<2:20:52,  1.57it/s]
 77%|███████▋  | 44296/57600 [7:47:16<2:21:54,  1.56it/s]
 77%|███████▋  | 44297/57600 [7:47:17<2:17:55,  1.61it/s]
 77%|███████▋  | 44298/57600 [7:47:17<2:14:46,  1.64it/s]
 77%|███████▋  | 44299/57600 [7:47:18<2:15:17,  1.64it/s]
 77%|███████▋  | 44300/57600 [7:47:18<2:12:22,  1.67it/s]
                                                         
{'loss': 1.1364, 'learning_rate': 3.0853658536585363e-07, 'epoch': 488.96}
+
 77%|███████▋  | 44300/57600 [7:47:18<2:12:22,  1.67it/s]
 77%|███████▋  | 44301/57600 [7:47:19<2:15:40,  1.63it/s]
 77%|███████▋  | 44302/57600 [7:47:20<2:12:41,  1.67it/s]
 77%|███████▋  | 44303/57600 [7:47:20<2:16:39,  1.62it/s]
 77%|███████▋  | 44304/57600 [7:47:21<2:23:42,  1.54it/s]
 77%|███████▋  | 44305/57600 [7:47:22<2:21:07,  1.57it/s]
 77%|███████▋  | 44306/57600 [7:47:22<2:19:34,  1.59it/s]
 77%|███████▋  | 44307/57600 [7:47:23<2:20:32,  1.58it/s]
 77%|███████▋  | 44308/57600 [7:47:23<2:17:04,  1.62it/s]
 77%|███████▋  | 44309/57600 [7:47:24<2:13:38,  1.66it/s]
 77%|███████▋  | 44310/57600 [7:47:25<2:12:26,  1.67it/s]
 77%|███████▋  | 44311/57600 [7:47:25<2:15:39,  1.63it/s]
 77%|███████▋  | 44312/57600 [7:47:26<2:12:03,  1.68it/s]
 77%|███████▋  | 44313/57600 [7:47:26<2:14:02,  1.65it/s]
 77%|███████▋  | 44314/57600 [7:47:27<2:17:04,  1.62it/s]
 77%|███████▋  | 44315/57600 [7:47:28<2:17:22,  1.61it/s]
 77%|███████▋  | 44316/57600 [7:47:28<2:16:53,  1.62it/s]
 77%|███████▋  | 44317/57600 [7:47:29<2:16:12,  1.63it/s]
 77%|███████▋  | 44318/57600 [7:47:29<2:17:43,  1.61it/s]
 77%|███████▋  | 44319/57600 [7:47:30<2:15:19,  1.64it/s]
 77%|███████▋  | 44320/57600 [7:47:31<2:13:30,  1.66it/s]
                                                         
{'loss': 1.1456, 'learning_rate': 3.0822299651567943e-07, 'epoch': 489.18}
+
 77%|███████▋  | 44320/57600 [7:47:31<2:13:30,  1.66it/s]
 77%|███████▋  | 44321/57600 [7:47:31<2:14:05,  1.65it/s]
 77%|███████▋  | 44322/57600 [7:47:32<2:21:54,  1.56it/s]
 77%|███████▋  | 44323/57600 [7:47:33<2:22:38,  1.55it/s]
 77%|███████▋  | 44324/57600 [7:47:33<2:19:49,  1.58it/s]
 77%|███████▋  | 44325/57600 [7:47:34<2:22:08,  1.56it/s]
 77%|███████▋  | 44326/57600 [7:47:35<2:21:46,  1.56it/s]
 77%|███████▋  | 44327/57600 [7:47:35<2:20:10,  1.58it/s]
 77%|███████▋  | 44328/57600 [7:47:36<2:20:44,  1.57it/s]
 77%|███████▋  | 44329/57600 [7:47:36<2:20:24,  1.58it/s]
 77%|███████▋  | 44330/57600 [7:47:37<2:19:46,  1.58it/s]
 77%|███████▋  | 44331/57600 [7:47:38<2:24:34,  1.53it/s]
 77%|███████▋  | 44332/57600 [7:47:38<2:22:09,  1.56it/s]
 77%|███████▋  | 44333/57600 [7:47:39<2:18:19,  1.60it/s]
 77%|███████▋  | 44334/57600 [7:47:40<2:19:06,  1.59it/s]
 77%|███████▋  | 44335/57600 [7:47:40<2:21:01,  1.57it/s]
 77%|███████▋  | 44336/57600 [7:47:41<2:20:38,  1.57it/s]
 77%|███████▋  | 44337/57600 [7:47:42<2:20:31,  1.57it/s]
 77%|███████▋  | 44338/57600 [7:47:42<2:19:43,  1.58it/s]
 77%|███████▋  | 44339/57600 [7:47:43<2:19:44,  1.58it/s]
 77%|███████▋  | 44340/57600 [7:47:43<2:20:32,  1.57it/s]
                                                         
{'loss': 1.1101, 'learning_rate': 3.079094076655052e-07, 'epoch': 489.4}
+
 77%|███████▋  | 44340/57600 [7:47:43<2:20:32,  1.57it/s]
 77%|███████▋  | 44341/57600 [7:47:44<2:21:08,  1.57it/s]
 77%|███████▋  | 44342/57600 [7:47:45<2:22:13,  1.55it/s]
 77%|███████▋  | 44343/57600 [7:47:45<2:24:24,  1.53it/s]
 77%|███████▋  | 44344/57600 [7:47:46<2:26:26,  1.51it/s]
 77%|███████▋  | 44345/57600 [7:47:47<2:22:36,  1.55it/s]
 77%|███████▋  | 44346/57600 [7:47:47<2:18:18,  1.60it/s]
 77%|███████▋  | 44347/57600 [7:47:48<2:18:30,  1.59it/s]
 77%|███████▋  | 44348/57600 [7:47:48<2:13:59,  1.65it/s]
 77%|███████▋  | 44349/57600 [7:47:49<2:13:01,  1.66it/s]
 77%|███████▋  | 44350/57600 [7:47:50<2:13:26,  1.65it/s]
 77%|███████▋  | 44351/57600 [7:47:50<2:14:26,  1.64it/s]
 77%|███████▋  | 44352/57600 [7:47:51<2:17:02,  1.61it/s]
 77%|███████▋  | 44353/57600 [7:47:52<2:17:14,  1.61it/s]
 77%|███████▋  | 44354/57600 [7:47:52<2:15:36,  1.63it/s]
 77%|███████▋  | 44355/57600 [7:47:53<2:15:51,  1.62it/s]
 77%|███████▋  | 44356/57600 [7:47:53<2:14:16,  1.64it/s]
 77%|███████▋  | 44357/57600 [7:47:54<2:15:35,  1.63it/s]
 77%|███████▋  | 44358/57600 [7:47:55<2:15:54,  1.62it/s]
 77%|███████▋  | 44359/57600 [7:47:55<2:19:07,  1.59it/s]
 77%|███████▋  | 44360/57600 [7:47:56<2:19:29,  1.58it/s]
                                                         
{'loss': 1.1395, 'learning_rate': 3.0759581881533104e-07, 'epoch': 489.62}
+
 77%|███████▋  | 44360/57600 [7:47:56<2:19:29,  1.58it/s]
 77%|███████▋  | 44361/57600 [7:47:57<2:22:47,  1.55it/s]
 77%|███████���  | 44362/57600 [7:47:57<2:21:28,  1.56it/s]
 77%|███████▋  | 44363/57600 [7:47:58<2:18:06,  1.60it/s]
 77%|███████▋  | 44364/57600 [7:47:58<2:16:50,  1.61it/s]
 77%|███████▋  | 44365/57600 [7:47:59<2:16:22,  1.62it/s]
 77%|███████▋  | 44366/57600 [7:48:00<2:18:56,  1.59it/s]
 77%|███████▋  | 44367/57600 [7:48:00<2:19:52,  1.58it/s]
 77%|███████▋  | 44368/57600 [7:48:01<2:19:00,  1.59it/s]
 77%|███████▋  | 44369/57600 [7:48:02<2:20:48,  1.57it/s]
 77%|███████▋  | 44370/57600 [7:48:02<2:18:58,  1.59it/s]
 77%|███████▋  | 44371/57600 [7:48:03<2:22:14,  1.55it/s]
 77%|███████▋  | 44372/57600 [7:48:04<2:20:38,  1.57it/s]
 77%|███████▋  | 44373/57600 [7:48:04<2:20:23,  1.57it/s]
 77%|███████▋  | 44374/57600 [7:48:05<2:18:12,  1.59it/s]
 77%|███████▋  | 44375/57600 [7:48:05<2:17:20,  1.60it/s]
 77%|███████▋  | 44376/57600 [7:48:06<2:17:53,  1.60it/s]
 77%|███████▋  | 44377/57600 [7:48:07<2:16:29,  1.61it/s]
 77%|███████▋  | 44378/57600 [7:48:07<2:13:54,  1.65it/s]
 77%|███████▋  | 44379/57600 [7:48:08<2:15:15,  1.63it/s]
 77%|███████▋  | 44380/57600 [7:48:08<2:17:01,  1.61it/s]
                                                         
{'loss': 1.1361, 'learning_rate': 3.0728222996515674e-07, 'epoch': 489.85}
+
 77%|███████▋  | 44380/57600 [7:48:08<2:17:01,  1.61it/s]
 77%|███████▋  | 44381/57600 [7:48:09<2:17:32,  1.60it/s]
 77%|███████▋  | 44382/57600 [7:48:10<2:15:07,  1.63it/s]
 77%|███████▋  | 44383/57600 [7:48:10<2:17:57,  1.60it/s]
 77%|███████▋  | 44384/57600 [7:48:11<2:19:40,  1.58it/s]
 77%|███████▋  | 44385/57600 [7:48:12<2:16:37,  1.61it/s]
 77%|███████▋  | 44386/57600 [7:48:12<2:15:02,  1.63it/s]
 77%|███████▋  | 44387/57600 [7:48:13<2:15:33,  1.62it/s]
 77%|███████▋  | 44388/57600 [7:48:13<2:17:07,  1.61it/s]
 77%|███████▋  | 44389/57600 [7:48:14<2:18:46,  1.59it/s]
 77%|███████▋  | 44390/57600 [7:48:15<2:21:47,  1.55it/s]
 77%|███████▋  | 44391/57600 [7:48:15<2:23:19,  1.54it/s]
 77%|███████▋  | 44392/57600 [7:48:16<2:19:54,  1.57it/s]
 77%|███████▋  | 44393/57600 [7:48:17<2:21:46,  1.55it/s]
 77%|███████▋  | 44394/57600 [7:48:17<2:18:43,  1.59it/s]
 77%|███████▋  | 44395/57600 [7:48:18<2:20:32,  1.57it/s]
 77%|███████▋  | 44396/57600 [7:48:19<2:18:17,  1.59it/s]
 77%|███████▋  | 44397/57600 [7:48:19<2:17:06,  1.60it/s]
 77%|███████▋  | 44398/57600 [7:48:20<2:17:53,  1.60it/s]
 77%|███████▋  | 44399/57600 [7:48:20<2:17:10,  1.60it/s]
 77%|███████▋  | 44400/57600 [7:48:21<2:18:09,  1.59it/s]
                                                         
{'loss': 1.1494, 'learning_rate': 3.0696864111498255e-07, 'epoch': 490.07}
+
 77%|███████▋  | 44400/57600 [7:48:21<2:18:09,  1.59it/s]
 77%|███████▋  | 44401/57600 [7:48:22<2:18:21,  1.59it/s]
 77%|███████▋  | 44402/57600 [7:48:22<2:19:29,  1.58it/s]
 77%|███████▋  | 44403/57600 [7:48:23<2:17:29,  1.60it/s]
 77%|███████▋  | 44404/57600 [7:48:24<2:20:03,  1.57it/s]
 77%|███████▋  | 44405/57600 [7:48:24<2:16:09,  1.62it/s]
 77%|███████▋  | 44406/57600 [7:48:25<2:15:10,  1.63it/s]
 77%|███████▋  | 44407/57600 [7:48:25<2:17:54,  1.59it/s]
 77%|███████▋  | 44408/57600 [7:48:26<2:17:56,  1.59it/s]
 77%|███████▋  | 44409/57600 [7:48:27<2:21:27,  1.55it/s]
 77%|███████▋  | 44410/57600 [7:48:27<2:19:44,  1.57it/s]
 77%|███████▋  | 44411/57600 [7:48:28<2:22:04,  1.55it/s]
 77%|███████▋  | 44412/57600 [7:48:29<2:22:50,  1.54it/s]
 77%|███████▋  | 44413/57600 [7:48:29<2:21:23,  1.55it/s]
 77%|███████▋  | 44414/57600 [7:48:30<2:17:51,  1.59it/s]
 77%|███████▋  | 44415/57600 [7:48:31<2:13:58,  1.64it/s]
 77%|███████▋  | 44416/57600 [7:48:31<2:15:10,  1.63it/s]
 77%|███████▋  | 44417/57600 [7:48:32<2:17:50,  1.59it/s]
 77%|███████▋  | 44418/57600 [7:48:32<2:18:59,  1.58it/s]
 77%|███████▋  | 44419/57600 [7:48:33<2:17:04,  1.60it/s]
 77%|███████▋  | 44420/57600 [7:48:34<2:16:15,  1.61it/s]
                                                         
{'loss': 1.1222, 'learning_rate': 3.066550522648084e-07, 'epoch': 490.29}
+
 77%|███████▋  | 44420/57600 [7:48:34<2:16:15,  1.61it/s]
 77%|███████▋  | 44421/57600 [7:48:34<2:17:41,  1.60it/s]
 77%|███████▋  | 44422/57600 [7:48:35<2:16:04,  1.61it/s]
 77%|��██████▋  | 44423/57600 [7:48:36<2:16:02,  1.61it/s]
 77%|███████▋  | 44424/57600 [7:48:36<2:15:39,  1.62it/s]
 77%|███████▋  | 44425/57600 [7:48:37<2:18:21,  1.59it/s]
 77%|███████▋  | 44426/57600 [7:48:37<2:13:27,  1.65it/s]
 77%|███████▋  | 44427/57600 [7:48:38<2:14:31,  1.63it/s]
 77%|███████▋  | 44428/57600 [7:48:39<2:16:30,  1.61it/s]
 77%|███████▋  | 44429/57600 [7:48:39<2:13:43,  1.64it/s]
 77%|███████▋  | 44430/57600 [7:48:40<2:20:53,  1.56it/s]
 77%|███████▋  | 44431/57600 [7:48:40<2:17:52,  1.59it/s]
 77%|███████▋  | 44432/57600 [7:48:41<2:17:30,  1.60it/s]
 77%|███████▋  | 44433/57600 [7:48:42<2:19:05,  1.58it/s]
 77%|███████▋  | 44434/57600 [7:48:42<2:17:20,  1.60it/s]
 77%|███████▋  | 44435/57600 [7:48:43<2:20:07,  1.57it/s]
 77%|███████▋  | 44436/57600 [7:48:44<2:16:58,  1.60it/s]
 77%|███████▋  | 44437/57600 [7:48:44<2:17:53,  1.59it/s]
 77%|███████▋  | 44438/57600 [7:48:45<2:19:19,  1.57it/s]
 77%|███████▋  | 44439/57600 [7:48:46<2:17:14,  1.60it/s]
 77%|███████▋  | 44440/57600 [7:48:46<2:15:00,  1.62it/s]
                                                         
{'loss': 1.1303, 'learning_rate': 3.063414634146341e-07, 'epoch': 490.51}
+
 77%|███████▋  | 44440/57600 [7:48:46<2:15:00,  1.62it/s]
 77%|███████▋  | 44441/57600 [7:48:47<2:14:56,  1.63it/s]
 77%|███████▋  | 44442/57600 [7:48:47<2:22:41,  1.54it/s]
 77%|███████▋  | 44443/57600 [7:48:48<2:24:48,  1.51it/s]
 77%|███████▋  | 44444/57600 [7:48:49<2:22:15,  1.54it/s]
 77%|███████▋  | 44445/57600 [7:48:49<2:22:40,  1.54it/s]
 77%|███████▋  | 44446/57600 [7:48:50<2:22:56,  1.53it/s]
 77%|███████▋  | 44447/57600 [7:48:51<2:27:15,  1.49it/s]
 77%|███████▋  | 44448/57600 [7:48:51<2:24:50,  1.51it/s]
 77%|███████▋  | 44449/57600 [7:48:52<2:23:30,  1.53it/s]
 77%|███████▋  | 44450/57600 [7:48:53<2:21:58,  1.54it/s]
 77%|███████▋  | 44451/57600 [7:48:53<2:20:49,  1.56it/s]
 77%|███████▋  | 44452/57600 [7:48:54<2:19:34,  1.57it/s]
 77%|███████▋  | 44453/57600 [7:48:55<2:19:45,  1.57it/s]
 77%|███████▋  | 44454/57600 [7:48:55<2:24:16,  1.52it/s]
 77%|███████▋  | 44455/57600 [7:48:56<2:24:01,  1.52it/s]
 77%|███████▋  | 44456/57600 [7:48:57<2:21:08,  1.55it/s]
 77%|███████▋  | 44457/57600 [7:48:57<2:20:58,  1.55it/s]
 77%|███████▋  | 44458/57600 [7:48:58<2:28:16,  1.48it/s]
 77%|███████▋  | 44459/57600 [7:48:59<2:23:47,  1.52it/s]
 77%|███████▋  | 44460/57600 [7:48:59<2:25:43,  1.50it/s]
                                                         
{'loss': 1.095, 'learning_rate': 3.060278745644599e-07, 'epoch': 490.73}
+
 77%|███████▋  | 44460/57600 [7:48:59<2:25:43,  1.50it/s]
 77%|███████▋  | 44461/57600 [7:49:00<2:22:00,  1.54it/s]
 77%|███████▋  | 44462/57600 [7:49:01<2:26:02,  1.50it/s]
 77%|███████▋  | 44463/57600 [7:49:01<2:28:03,  1.48it/s]
 77%|███████▋  | 44464/57600 [7:49:02<2:26:33,  1.49it/s]
 77%|███████▋  | 44465/57600 [7:49:03<2:25:01,  1.51it/s]
 77%|███████▋  | 44466/57600 [7:49:03<2:22:14,  1.54it/s]
 77%|███████▋  | 44467/57600 [7:49:04<2:18:20,  1.58it/s]
 77%|███████▋  | 44468/57600 [7:49:04<2:16:15,  1.61it/s]
 77%|███████▋  | 44469/57600 [7:49:05<2:14:21,  1.63it/s]
 77%|███████▋  | 44470/57600 [7:49:06<2:10:46,  1.67it/s]
 77%|███████▋  | 44471/57600 [7:49:06<2:14:18,  1.63it/s]
 77%|███████▋  | 44472/57600 [7:49:07<2:12:26,  1.65it/s]
 77%|███████▋  | 44473/57600 [7:49:07<2:10:58,  1.67it/s]
 77%|███████▋  | 44474/57600 [7:49:08<2:10:27,  1.68it/s]
 77%|███████▋  | 44475/57600 [7:49:09<2:12:23,  1.65it/s]
 77%|███████▋  | 44476/57600 [7:49:09<2:12:45,  1.65it/s]
 77%|███████▋  | 44477/57600 [7:49:10<2:13:02,  1.64it/s]
 77%|███████▋  | 44478/57600 [7:49:10<2:13:28,  1.64it/s]
 77%|███████▋  | 44479/57600 [7:49:11<2:12:02,  1.66it/s]
 77%|███████▋  | 44480/57600 [7:49:12<2:12:24,  1.65it/s]
                                                         
{'loss': 1.1407, 'learning_rate': 3.0571428571428566e-07, 'epoch': 490.95}
+
 77%|███████▋  | 44480/57600 [7:49:12<2:12:24,  1.65it/s]
 77%|███████▋  | 44481/57600 [7:49:12<2:13:05,  1.64it/s]
 77%|███████▋  | 44482/57600 [7:49:13<2:13:32,  1.64it/s]
 77%|███████▋  | 44483/57600 [7:49:13<2:12:48,  1.65it/s]
 77%|███████▋  | 44484/57600 [7:49:14<2:13:42,  1.63it/s]
 77%|███████▋  | 44485/57600 [7:49:15<2:17:18,  1.59it/s]
 77%|███████▋  | 44486/57600 [7:49:15<2:18:51,  1.57it/s]
 77%|███████▋  | 44487/57600 [7:49:16<2:18:30,  1.58it/s]
 77%|███████▋  | 44488/57600 [7:49:17<2:15:43,  1.61it/s]
 77%|███████▋  | 44489/57600 [7:49:17<2:12:30,  1.65it/s]
 77%|███████▋  | 44490/57600 [7:49:18<2:10:56,  1.67it/s]
 77%|███████▋  | 44491/57600 [7:49:18<2:08:38,  1.70it/s]
 77%|███████▋  | 44492/57600 [7:49:19<2:06:28,  1.73it/s]
 77%|███████▋  | 44493/57600 [7:49:20<2:09:29,  1.69it/s]
 77%|███████▋  | 44494/57600 [7:49:20<2:13:27,  1.64it/s]
 77%|███████▋  | 44495/57600 [7:49:21<2:13:05,  1.64it/s]
 77%|███████▋  | 44496/57600 [7:49:21<2:16:39,  1.60it/s]
 77%|███████▋  | 44497/57600 [7:49:22<2:17:21,  1.59it/s]
 77%|███████▋  | 44498/57600 [7:49:23<2:15:16,  1.61it/s]
 77%|███████▋  | 44499/57600 [7:49:23<2:16:48,  1.60it/s]
 77%|███████▋  | 44500/57600 [7:49:24<2:23:07,  1.53it/s]
                                                         
{'loss': 1.132, 'learning_rate': 3.054006968641115e-07, 'epoch': 491.17}
+
 77%|███████▋  | 44500/57600 [7:49:24<2:23:07,  1.53it/s]
 77%|███████▋  | 44501/57600 [7:49:25<2:21:55,  1.54it/s]
 77%|███████▋  | 44502/57600 [7:49:25<2:23:05,  1.53it/s]
 77%|███████▋  | 44503/57600 [7:49:26<2:22:40,  1.53it/s]
 77%|███████▋  | 44504/57600 [7:49:27<2:26:18,  1.49it/s]
 77%|███████▋  | 44505/57600 [7:49:27<2:22:10,  1.54it/s]
 77%|███████▋  | 44506/57600 [7:49:28<2:26:33,  1.49it/s]
 77%|███████▋  | 44507/57600 [7:49:29<2:22:33,  1.53it/s]
 77%|███████▋  | 44508/57600 [7:49:29<2:22:19,  1.53it/s]
 77%|███████▋  | 44509/57600 [7:49:30<2:23:11,  1.52it/s]
 77%|███████▋  | 44510/57600 [7:49:31<2:21:43,  1.54it/s]
 77%|███████▋  | 44511/57600 [7:49:31<2:24:32,  1.51it/s]
 77%|███████▋  | 44512/57600 [7:49:32<2:20:23,  1.55it/s]
 77%|███████▋  | 44513/57600 [7:49:32<2:17:24,  1.59it/s]
 77%|███████▋  | 44514/57600 [7:49:33<2:17:45,  1.58it/s]
 77%|███████▋  | 44515/57600 [7:49:34<2:22:52,  1.53it/s]
 77%|███████▋  | 44516/57600 [7:49:34<2:23:54,  1.52it/s]
 77%|███████▋  | 44517/57600 [7:49:35<2:26:00,  1.49it/s]
 77%|███████▋  | 44518/57600 [7:49:36<2:19:51,  1.56it/s]
 77%|███████▋  | 44519/57600 [7:49:36<2:19:40,  1.56it/s]
 77%|███████▋  | 44520/57600 [7:49:37<2:21:02,  1.55it/s]
                                                         
{'loss': 1.104, 'learning_rate': 3.050871080139372e-07, 'epoch': 491.39}
+
 77%|███████▋  | 44520/57600 [7:49:37<2:21:02,  1.55it/s]
 77%|███████▋  | 44521/57600 [7:49:38<2:17:19,  1.59it/s]
 77%|███████▋  | 44522/57600 [7:49:38<2:15:11,  1.61it/s]
 77%|███████▋  | 44523/57600 [7:49:39<2:13:13,  1.64it/s]
 77%|███████▋  | 44524/57600 [7:49:39<2:08:21,  1.70it/s]
 77%|███████▋  | 44525/57600 [7:49:40<2:06:13,  1.73it/s]
 77%|███████▋  | 44526/57600 [7:49:41<2:09:36,  1.68it/s]
 77%|███████▋  | 44527/57600 [7:49:41<2:16:06,  1.60it/s]
 77%|███████▋  | 44528/57600 [7:49:42<2:14:13,  1.62it/s]
 77%|███████▋  | 44529/57600 [7:49:42<2:12:03,  1.65it/s]
 77%|███████▋  | 44530/57600 [7:49:43<2:14:49,  1.62it/s]
 77%|███████▋  | 44531/57600 [7:49:44<2:16:56,  1.59it/s]
 77%|███████▋  | 44532/57600 [7:49:44<2:14:53,  1.61it/s]
 77%|███████▋  | 44533/57600 [7:49:45<2:17:22,  1.59it/s]
 77%|███████▋  | 44534/57600 [7:49:46<2:17:50,  1.58it/s]
 77%|███████▋  | 44535/57600 [7:49:46<2:20:08,  1.55it/s]
 77%|███████▋  | 44536/57600 [7:49:47<2:18:58,  1.57it/s]
 77%|███████▋  | 44537/57600 [7:49:48<2:17:15,  1.59it/s]
 77%|███████▋  | 44538/57600 [7:49:48<2:13:49,  1.63it/s]
 77%|███████▋  | 44539/57600 [7:49:49<2:18:06,  1.58it/s]
 77%|███████▋  | 44540/57600 [7:49:49<2:20:42,  1.55it/s]
                                                         
{'loss': 1.121, 'learning_rate': 3.04773519163763e-07, 'epoch': 491.61}
+
 77%|███████▋  | 44540/57600 [7:49:49<2:20:42,  1.55it/s]
 77%|███████▋  | 44541/57600 [7:49:50<2:20:29,  1.55it/s]
 77%|███████▋  | 44542/57600 [7:49:51<2:22:53,  1.52it/s]
 77%|███████▋  | 44543/57600 [7:49:51<2:17:26,  1.58it/s]
 77%|███████▋  | 44544/57600 [7:49:52<2:16:46,  1.59it/s]
 77%|███████▋  | 44545/57600 [7:49:53<2:22:34,  1.53it/s]
 77%|███████▋  | 44546/57600 [7:49:53<2:17:00,  1.59it/s]
 77%|███████▋  | 44547/57600 [7:49:54<2:18:06,  1.58it/s]
 77%|███████▋  | 44548/57600 [7:49:55<2:16:13,  1.60it/s]
 77%|███████▋  | 44549/57600 [7:49:55<2:16:22,  1.59it/s]
 77%|███████▋  | 44550/57600 [7:49:56<2:15:32,  1.60it/s]
 77%|███████▋  | 44551/57600 [7:49:56<2:12:29,  1.64it/s]
 77%|███████▋  | 44552/57600 [7:49:57<2:16:53,  1.59it/s]
 77%|███████▋  | 44553/57600 [7:49:58<2:16:52,  1.59it/s]
 77%|███████▋  | 44554/57600 [7:49:58<2:16:46,  1.59it/s]
 77%|███████▋  | 44555/57600 [7:49:59<2:14:28,  1.62it/s]
 77%|███████▋  | 44556/57600 [7:49:59<2:13:55,  1.62it/s]
 77%|███████▋  | 44557/57600 [7:50:00<2:11:13,  1.66it/s]
 77%|███████▋  | 44558/57600 [7:50:01<2:11:04,  1.66it/s]
 77%|███████▋  | 44559/57600 [7:50:01<2:12:32,  1.64it/s]
 77%|███████▋  | 44560/57600 [7:50:02<2:15:01,  1.61it/s]
                                                         
{'loss': 1.1607, 'learning_rate': 3.0445993031358883e-07, 'epoch': 491.83}
+
 77%|███████▋  | 44560/57600 [7:50:02<2:15:01,  1.61it/s]
 77%|███████▋  | 44561/57600 [7:50:03<2:18:02,  1.57it/s]
 77%|███████▋  | 44562/57600 [7:50:03<2:21:53,  1.53it/s]
 77%|███████▋  | 44563/57600 [7:50:04<2:21:28,  1.54it/s]
 77%|███████▋  | 44564/57600 [7:50:05<2:20:39,  1.54it/s]
 77%|███████▋  | 44565/57600 [7:50:05<2:16:09,  1.60it/s]
 77%|███████▋  | 44566/57600 [7:50:06<2:15:41,  1.60it/s]
 77%|███████▋  | 44567/57600 [7:50:06<2:16:08,  1.60it/s]
 77%|███████▋  | 44568/57600 [7:50:07<2:18:05,  1.57it/s]
 77%|███████▋  | 44569/57600 [7:50:08<2:15:31,  1.60it/s]
 77%|███████▋  | 44570/57600 [7:50:08<2:14:42,  1.61it/s]
 77%|███████▋  | 44571/57600 [7:50:09<2:12:50,  1.63it/s]
 77%|███████▋  | 44572/57600 [7:50:09<2:11:36,  1.65it/s]
 77%|███████▋  | 44573/57600 [7:50:10<2:13:47,  1.62it/s]
 77%|███████▋  | 44574/57600 [7:50:11<2:16:05,  1.60it/s]
 77%|███████▋  | 44575/57600 [7:50:11<2:21:08,  1.54it/s]
 77%|███████▋  | 44576/57600 [7:50:12<2:26:42,  1.48it/s]
 77%|███████▋  | 44577/57600 [7:50:13<2:22:10,  1.53it/s]
 77%|███████▋  | 44578/57600 [7:50:13<2:24:03,  1.51it/s]
 77%|███████▋  | 44579/57600 [7:50:14<2:22:44,  1.52it/s]
 77%|███████▋  | 44580/57600 [7:50:15<2:21:27,  1.53it/s]
                                                         
{'loss': 1.0907, 'learning_rate': 3.0414634146341463e-07, 'epoch': 492.05}
+
 77%|███████▋  | 44580/57600 [7:50:15<2:21:27,  1.53it/s]
 77%|███████▋  | 44581/57600 [7:50:15<2:20:44,  1.54it/s]
 77%|███████▋  | 44582/57600 [7:50:16<2:19:26,  1.56it/s]
 77%|███████▋  | 44583/57600 [7:50:17<2:19:00,  1.56it/s]
 77%|███████▋  | 44584/57600 [7:50:17<2:20:24,  1.55it/s]
 77%|███████▋  | 44585/57600 [7:50:18<2:15:26,  1.60it/s]
 77%|███████▋  | 44586/57600 [7:50:19<2:15:47,  1.60it/s]
 77%|███████▋  | 44587/57600 [7:50:19<2:15:10,  1.60it/s]
 77%|███████▋  | 44588/57600 [7:50:20<2:14:48,  1.61it/s]
 77%|███████▋  | 44589/57600 [7:50:20<2:19:32,  1.55it/s]
 77%|███████▋  | 44590/57600 [7:50:21<2:17:51,  1.57it/s]
 77%|███████▋  | 44591/57600 [7:50:22<2:14:00,  1.62it/s]
 77%|███████▋  | 44592/57600 [7:50:22<2:16:32,  1.59it/s]
 77%|███████▋  | 44593/57600 [7:50:23<2:17:04,  1.58it/s]
 77%|███████▋  | 44594/57600 [7:50:24<2:17:12,  1.58it/s]
 77%|███████▋  | 44595/57600 [7:50:24<2:21:21,  1.53it/s]
 77%|███████▋  | 44596/57600 [7:50:25<2:20:24,  1.54it/s]
 77%|███████▋  | 44597/57600 [7:50:26<2:19:35,  1.55it/s]
 77%|███████▋  | 44598/57600 [7:50:26<2:16:30,  1.59it/s]
 77%|███████▋  | 44599/57600 [7:50:27<2:17:10,  1.58it/s]
 77%|███████▋  | 44600/57600 [7:50:27<2:17:17,  1.58it/s]
                                                         
{'loss': 1.116, 'learning_rate': 3.0383275261324044e-07, 'epoch': 492.27}
+
 77%|███████▋  | 44600/57600 [7:50:27<2:17:17,  1.58it/s]
 77%|███████▋  | 44601/57600 [7:50:28<2:15:01,  1.60it/s]
 77%|███████▋  | 44602/57600 [7:50:29<2:12:33,  1.63it/s]
 77%|███████▋  | 44603/57600 [7:50:29<2:12:25,  1.64it/s]
 77%|███████▋  | 44604/57600 [7:50:30<2:11:04,  1.65it/s]
 77%|███████▋  | 44605/57600 [7:50:30<2:11:06,  1.65it/s]
 77%|███████▋  | 44606/57600 [7:50:31<2:16:43,  1.58it/s]
 77%|███████▋  | 44607/57600 [7:50:32<2:15:04,  1.60it/s]
 77%|███████▋  | 44608/57600 [7:50:32<2:19:18,  1.55it/s]
 77%|███████▋  | 44609/57600 [7:50:33<2:20:31,  1.54it/s]
 77%|███████▋  | 44610/57600 [7:50:34<2:26:18,  1.48it/s]
 77%|███████▋  | 44611/57600 [7:50:34<2:21:50,  1.53it/s]
 77%|███████▋  | 44612/57600 [7:50:35<2:19:53,  1.55it/s]
 77%|███████▋  | 44613/57600 [7:50:36<2:18:24,  1.56it/s]
 77%|███████▋  | 44614/57600 [7:50:36<2:16:14,  1.59it/s]
 77%|███████▋  | 44615/57600 [7:50:37<2:13:01,  1.63it/s]
 77%|███████▋  | 44616/57600 [7:50:38<2:15:40,  1.60it/s]
 77%|███████▋  | 44617/57600 [7:50:38<2:19:00,  1.56it/s]
 77%|███████▋  | 44618/57600 [7:50:39<2:15:46,  1.59it/s]
 77%|███████▋  | 44619/57600 [7:50:39<2:14:38,  1.61it/s]
 77%|███████▋  | 44620/57600 [7:50:40<2:16:22,  1.59it/s]
                                                         
{'loss': 1.1573, 'learning_rate': 3.0351916376306614e-07, 'epoch': 492.49}
+
 77%|███████▋  | 44620/57600 [7:50:40<2:16:22,  1.59it/s]
 77%|███████▋  | 44621/57600 [7:50:41<2:16:40,  1.58it/s]
 77%|███████▋  | 44622/57600 [7:50:41<2:15:56,  1.59it/s]
 77%|███████▋  | 44623/57600 [7:50:42<2:12:46,  1.63it/s]
 77%|███████▋  | 44624/57600 [7:50:43<2:13:32,  1.62it/s]
 77%|███████▋  | 44625/57600 [7:50:43<2:12:46,  1.63it/s]
 77%|███████▋  | 44626/57600 [7:50:44<2:15:23,  1.60it/s]
 77%|███████▋  | 44627/57600 [7:50:44<2:13:17,  1.62it/s]
 77%|███████▋  | 44628/57600 [7:50:45<2:12:43,  1.63it/s]
 77%|███████▋  | 44629/57600 [7:50:46<2:10:33,  1.66it/s]
 77%|███████▋  | 44630/57600 [7:50:46<2:17:24,  1.57it/s]
 77%|███████▋  | 44631/57600 [7:50:47<2:15:25,  1.60it/s]
 77%|███████▋  | 44632/57600 [7:50:47<2:12:09,  1.64it/s]
 77%|███████▋  | 44633/57600 [7:50:48<2:14:36,  1.61it/s]
 77%|███████▋  | 44634/57600 [7:50:49<2:16:59,  1.58it/s]
 77%|███████▋  | 44635/57600 [7:50:49<2:17:16,  1.57it/s]
 77%|███████▋  | 44636/57600 [7:50:50<2:18:34,  1.56it/s]
 77%|███████▋  | 44637/57600 [7:50:51<2:17:57,  1.57it/s]
 77%|███████▋  | 44638/57600 [7:50:51<2:18:30,  1.56it/s]
 77%|███████▋  | 44639/57600 [7:50:52<2:15:13,  1.60it/s]
 78%|███████▊  | 44640/57600 [7:50:53<2:19:05,  1.55it/s]
                                                         
{'loss': 1.112, 'learning_rate': 3.03205574912892e-07, 'epoch': 492.72}
+
 78%|███████▊  | 44640/57600 [7:50:53<2:19:05,  1.55it/s]
 78%|███████▊  | 44641/57600 [7:50:53<2:13:25,  1.62it/s]
 78%|███████▊  | 44642/57600 [7:50:54<2:12:52,  1.63it/s]
 78%|███████▊  | 44643/57600 [7:50:54<2:17:22,  1.57it/s]
 78%|███████▊  | 44644/57600 [7:50:55<2:22:10,  1.52it/s]
 78%|███████▊  | 44645/57600 [7:50:56<2:20:42,  1.53it/s]
 78%|███████▊  | 44646/57600 [7:50:56<2:19:44,  1.54it/s]
 78%|███████▊  | 44647/57600 [7:50:57<2:18:57,  1.55it/s]
 78%|███████▊  | 44648/57600 [7:50:58<2:14:13,  1.61it/s]
 78%|███████▊  | 44649/57600 [7:50:58<2:16:26,  1.58it/s]
 78%|███████▊  | 44650/57600 [7:50:59<2:19:10,  1.55it/s]
 78%|███████▊  | 44651/57600 [7:51:00<2:12:40,  1.63it/s]
 78%|███████▊  | 44652/57600 [7:51:00<2:14:22,  1.61it/s]
 78%|███████▊  | 44653/57600 [7:51:01<2:11:25,  1.64it/s]
 78%|███████▊  | 44654/57600 [7:51:01<2:14:48,  1.60it/s]
 78%|███████▊  | 44655/57600 [7:51:02<2:14:54,  1.60it/s]
 78%|███████▊  | 44656/57600 [7:51:03<2:15:56,  1.59it/s]
 78%|███████▊  | 44657/57600 [7:51:03<2:18:10,  1.56it/s]
 78%|███████▊  | 44658/57600 [7:51:04<2:16:18,  1.58it/s]
 78%|███████▊  | 44659/57600 [7:51:05<2:16:15,  1.58it/s]
 78%|███████▊  | 44660/57600 [7:51:05<2:16:49,  1.58it/s]
                                                         
{'loss': 1.1136, 'learning_rate': 3.0289198606271775e-07, 'epoch': 492.94}
+
 78%|███████▊  | 44660/57600 [7:51:05<2:16:49,  1.58it/s]
 78%|███████▊  | 44661/57600 [7:51:06<2:19:22,  1.55it/s]
 78%|███████▊  | 44662/57600 [7:51:07<2:21:18,  1.53it/s]
 78%|███████▊  | 44663/57600 [7:51:07<2:21:28,  1.52it/s]
 78%|███████▊  | 44664/57600 [7:51:08<2:16:18,  1.58it/s]
 78%|███████▊  | 44665/57600 [7:51:08<2:15:27,  1.59it/s]
 78%|███████▊  | 44666/57600 [7:51:09<2:20:25,  1.54it/s]
 78%|███████▊  | 44667/57600 [7:51:10<2:15:03,  1.60it/s]
 78%|███████▊  | 44668/57600 [7:51:10<2:12:09,  1.63it/s]
 78%|███████▊  | 44669/57600 [7:51:11<2:10:42,  1.65it/s]
 78%|███████▊  | 44670/57600 [7:51:12<2:13:30,  1.61it/s]
 78%|███████▊  | 44671/57600 [7:51:12<2:12:58,  1.62it/s]
 78%|███████▊  | 44672/57600 [7:51:13<2:09:35,  1.66it/s]
 78%|███████▊  | 44673/57600 [7:51:13<2:15:07,  1.59it/s]
 78%|███████▊  | 44674/57600 [7:51:14<2:17:09,  1.57it/s]
 78%|███████▊  | 44675/57600 [7:51:15<2:22:06,  1.52it/s]
 78%|███████▊  | 44676/57600 [7:51:15<2:20:37,  1.53it/s]
 78%|███████▊  | 44677/57600 [7:51:16<2:18:10,  1.56it/s]
 78%|███████▊  | 44678/57600 [7:51:17<2:17:55,  1.56it/s]
 78%|███████▊  | 44679/57600 [7:51:17<2:16:36,  1.58it/s]
 78%|███████▊  | 44680/57600 [7:51:18<2:16:51,  1.57it/s]
                                                         
{'loss': 1.1287, 'learning_rate': 3.025783972125435e-07, 'epoch': 493.16}
+
 78%|███████▊  | 44680/57600 [7:51:18<2:16:51,  1.57it/s]
 78%|███████▊  | 44681/57600 [7:51:18<2:13:41,  1.61it/s]
 78%|███████▊  | 44682/57600 [7:51:19<2:11:50,  1.63it/s]
 78%|███████▊  | 44683/57600 [7:51:20<2:13:54,  1.61it/s]
 78%|███████▊  | 44684/57600 [7:51:20<2:12:40,  1.62it/s]
 78%|███████▊  | 44685/57600 [7:51:21<2:08:35,  1.67it/s]
 78%|███████▊  | 44686/57600 [7:51:22<2:11:44,  1.63it/s]
 78%|███████▊  | 44687/57600 [7:51:22<2:16:35,  1.58it/s]
 78%|███████▊  | 44688/57600 [7:51:23<2:14:07,  1.60it/s]
 78%|███████▊  | 44689/57600 [7:51:23<2:11:46,  1.63it/s]
 78%|███████▊  | 44690/57600 [7:51:24<2:13:31,  1.61it/s]
 78%|███████▊  | 44691/57600 [7:51:25<2:12:49,  1.62it/s]
 78%|███████▊  | 44692/57600 [7:51:25<2:14:03,  1.60it/s]
 78%|███████▊  | 44693/57600 [7:51:26<2:14:22,  1.60it/s]
 78%|███████▊  | 44694/57600 [7:51:26<2:10:27,  1.65it/s]
 78%|███████▊  | 44695/57600 [7:51:27<2:10:24,  1.65it/s]
 78%|███████▊  | 44696/57600 [7:51:28<2:09:01,  1.67it/s]
 78%|███████▊  | 44697/57600 [7:51:28<2:06:29,  1.70it/s]
 78%|███████▊  | 44698/57600 [7:51:29<2:13:55,  1.61it/s]
 78%|███████▊  | 44699/57600 [7:51:30<2:15:33,  1.59it/s]
 78%|███████▊  | 44700/57600 [7:51:30<2:14:13,  1.60it/s]
                                                         
{'loss': 1.1367, 'learning_rate': 3.0226480836236936e-07, 'epoch': 493.38}
+
 78%|███████▊  | 44700/57600 [7:51:30<2:14:13,  1.60it/s]
 78%|███████▊  | 44701/57600 [7:51:31<2:14:25,  1.60it/s]
 78%|███████▊  | 44702/57600 [7:51:31<2:16:48,  1.57it/s]
 78%|███████▊  | 44703/57600 [7:51:32<2:19:02,  1.55it/s]
 78%|███████▊  | 44704/57600 [7:51:33<2:17:12,  1.57it/s]
 78%|███████▊  | 44705/57600 [7:51:33<2:14:12,  1.60it/s]
 78%|███████▊  | 44706/57600 [7:51:34<2:19:52,  1.54it/s]
 78%|███████▊  | 44707/57600 [7:51:35<2:20:35,  1.53it/s]
 78%|███████▊  | 44708/57600 [7:51:35<2:21:04,  1.52it/s]
 78%|███████▊  | 44709/57600 [7:51:36<2:17:32,  1.56it/s]
 78%|███████▊  | 44710/57600 [7:51:37<2:18:57,  1.55it/s]
 78%|███████▊  | 44711/57600 [7:51:37<2:17:07,  1.57it/s]
 78%|███████▊  | 44712/57600 [7:51:38<2:15:23,  1.59it/s]
 78%|███████▊  | 44713/57600 [7:51:39<2:15:38,  1.58it/s]
 78%|███████▊  | 44714/57600 [7:51:39<2:12:03,  1.63it/s]
 78%|███████▊  | 44715/57600 [7:51:40<2:13:38,  1.61it/s]
 78%|███████▊  | 44716/57600 [7:51:40<2:17:30,  1.56it/s]
 78%|███████▊  | 44717/57600 [7:51:41<2:17:15,  1.56it/s]
 78%|███████▊  | 44718/57600 [7:51:42<2:22:23,  1.51it/s]
 78%|███████▊  | 44719/57600 [7:51:42<2:21:40,  1.52it/s]
 78%|███████▊  | 44720/57600 [7:51:43<2:19:27,  1.54it/s]
                                                         
{'loss': 1.134, 'learning_rate': 3.019512195121951e-07, 'epoch': 493.6}
+
 78%|███████▊  | 44720/57600 [7:51:43<2:19:27,  1.54it/s]
 78%|███████▊  | 44721/57600 [7:51:44<2:19:10,  1.54it/s]
 78%|███████▊  | 44722/57600 [7:51:44<2:18:57,  1.54it/s]
 78%|███████▊  | 44723/57600 [7:51:45<2:17:52,  1.56it/s]
 78%|███████▊  | 44724/57600 [7:51:46<2:16:53,  1.57it/s]
 78%|███████▊  | 44725/57600 [7:51:46<2:16:52,  1.57it/s]
 78%|███████▊  | 44726/57600 [7:51:47<2:13:41,  1.60it/s]
 78%|███████▊  | 44727/57600 [7:51:47<2:15:32,  1.58it/s]
 78%|███████▊  | 44728/57600 [7:51:48<2:12:32,  1.62it/s]
 78%|███████▊  | 44729/57600 [7:51:49<2:15:45,  1.58it/s]
 78%|███████▊  | 44730/57600 [7:51:49<2:13:17,  1.61it/s]
 78%|███████▊  | 44731/57600 [7:51:50<2:16:55,  1.57it/s]
 78%|███████▊  | 44732/57600 [7:51:51<2:14:17,  1.60it/s]
 78%|███████▊  | 44733/57600 [7:51:51<2:13:00,  1.61it/s]
 78%|███████▊  | 44734/57600 [7:51:52<2:15:17,  1.58it/s]
 78%|███████▊  | 44735/57600 [7:51:52<2:12:50,  1.61it/s]
 78%|███████▊  | 44736/57600 [7:51:53<2:13:45,  1.60it/s]
 78%|███████▊  | 44737/57600 [7:51:54<2:18:34,  1.55it/s]
 78%|███████▊  | 44738/57600 [7:51:54<2:14:45,  1.59it/s]
 78%|███████▊  | 44739/57600 [7:51:55<2:15:45,  1.58it/s]
 78%|███████▊  | 44740/57600 [7:51:56<2:20:28,  1.53it/s]
                                                         
{'loss': 1.1078, 'learning_rate': 3.016376306620209e-07, 'epoch': 493.82}
+
 78%|███████▊  | 44740/57600 [7:51:56<2:20:28,  1.53it/s]
 78%|███████▊  | 44741/57600 [7:51:56<2:18:31,  1.55it/s]
 78%|███████▊  | 44742/57600 [7:51:57<2:20:00,  1.53it/s]
 78%|███████▊  | 44743/57600 [7:51:58<2:17:48,  1.55it/s]
 78%|███████▊  | 44744/57600 [7:51:58<2:15:29,  1.58it/s]
 78%|███████▊  | 44745/57600 [7:51:59<2:17:52,  1.55it/s]
 78%|███████▊  | 44746/57600 [7:52:00<2:15:56,  1.58it/s]
 78%|███████▊  | 44747/57600 [7:52:00<2:13:54,  1.60it/s]
 78%|███████▊  | 44748/57600 [7:52:01<2:11:12,  1.63it/s]
 78%|███████▊  | 44749/57600 [7:52:01<2:12:54,  1.61it/s]
 78%|███████▊  | 44750/57600 [7:52:02<2:16:20,  1.57it/s]
 78%|███████▊  | 44751/57600 [7:52:03<2:22:00,  1.51it/s]
 78%|███████▊  | 44752/57600 [7:52:03<2:16:43,  1.57it/s]
 78%|███████▊  | 44753/57600 [7:52:04<2:14:00,  1.60it/s]
 78%|███████▊  | 44754/57600 [7:52:05<2:14:46,  1.59it/s]
 78%|███████▊  | 44755/57600 [7:52:05<2:13:07,  1.61it/s]
 78%|███████▊  | 44756/57600 [7:52:06<2:11:52,  1.62it/s]
 78%|███████▊  | 44757/57600 [7:52:07<2:25:13,  1.47it/s]
 78%|███████▊  | 44758/57600 [7:52:07<2:18:48,  1.54it/s]
 78%|███████▊  | 44759/57600 [7:52:08<2:15:22,  1.58it/s]
 78%|███████▊  | 44760/57600 [7:52:08<2:15:23,  1.58it/s]
                                                         
{'loss': 1.1159, 'learning_rate': 3.013240418118466e-07, 'epoch': 494.04}
+
 78%|███████▊  | 44760/57600 [7:52:08<2:15:23,  1.58it/s]
 78%|███████▊  | 44761/57600 [7:52:09<2:15:05,  1.58it/s]
 78%|███████▊  | 44762/57600 [7:52:10<2:12:31,  1.61it/s]
 78%|███████▊  | 44763/57600 [7:52:10<2:08:27,  1.67it/s]
 78%|███████▊  | 44764/57600 [7:52:11<2:07:51,  1.67it/s]
 78%|███████▊  | 44765/57600 [7:52:11<2:08:10,  1.67it/s]
 78%|███████▊  | 44766/57600 [7:52:12<2:09:39,  1.65it/s]
 78%|███████▊  | 44767/57600 [7:52:13<2:09:39,  1.65it/s]
 78%|███████▊  | 44768/57600 [7:52:13<2:10:05,  1.64it/s]
 78%|███████▊  | 44769/57600 [7:52:14<2:08:14,  1.67it/s]
 78%|███████▊  | 44770/57600 [7:52:14<2:09:50,  1.65it/s]
 78%|███████▊  | 44771/57600 [7:52:15<2:08:36,  1.66it/s]
 78%|███████▊  | 44772/57600 [7:52:16<2:13:26,  1.60it/s]
 78%|███████▊  | 44773/57600 [7:52:16<2:19:25,  1.53it/s]
 78%|███████▊  | 44774/57600 [7:52:17<2:17:41,  1.55it/s]
 78%|███████▊  | 44775/57600 [7:52:18<2:15:02,  1.58it/s]
 78%|███████▊  | 44776/57600 [7:52:18<2:18:16,  1.55it/s]
 78%|███████▊  | 44777/57600 [7:52:19<2:14:32,  1.59it/s]
 78%|███████▊  | 44778/57600 [7:52:20<2:15:32,  1.58it/s]
 78%|███████▊  | 44779/57600 [7:52:20<2:11:40,  1.62it/s]
 78%|███████▊  | 44780/57600 [7:52:21<2:13:04,  1.61it/s]
                                                         
{'loss': 1.1747, 'learning_rate': 3.0101045296167247e-07, 'epoch': 494.26}
+
 78%|███████▊  | 44780/57600 [7:52:21<2:13:04,  1.61it/s]
 78%|███████▊  | 44781/57600 [7:52:21<2:10:47,  1.63it/s]
 78%|███████▊  | 44782/57600 [7:52:22<2:09:24,  1.65it/s]
 78%|███████▊  | 44783/57600 [7:52:23<2:09:50,  1.65it/s]
 78%|███████▊  | 44784/57600 [7:52:23<2:11:07,  1.63it/s]
 78%|███████▊  | 44785/57600 [7:52:24<2:09:24,  1.65it/s]
 78%|███████▊  | 44786/57600 [7:52:24<2:14:22,  1.59it/s]
 78%|███████▊  | 44787/57600 [7:52:25<2:20:33,  1.52it/s]
 78%|███████▊  | 44788/57600 [7:52:26<2:24:57,  1.47it/s]
 78%|███████▊  | 44789/57600 [7:52:27<2:24:38,  1.48it/s]
 78%|███████▊  | 44790/57600 [7:52:27<2:21:59,  1.50it/s]
 78%|███████▊  | 44791/57600 [7:52:28<2:27:53,  1.44it/s]
 78%|███████▊  | 44792/57600 [7:52:29<2:30:02,  1.42it/s]
 78%|███████▊  | 44793/57600 [7:52:29<2:23:34,  1.49it/s]
 78%|███████▊  | 44794/57600 [7:52:30<2:22:01,  1.50it/s]
 78%|███████▊  | 44795/57600 [7:52:31<2:17:50,  1.55it/s]
 78%|███████▊  | 44796/57600 [7:52:31<2:20:28,  1.52it/s]
 78%|███████▊  | 44797/57600 [7:52:32<2:18:26,  1.54it/s]
 78%|███████▊  | 44798/57600 [7:52:32<2:13:53,  1.59it/s]
 78%|███████▊  | 44799/57600 [7:52:33<2:14:37,  1.58it/s]
 78%|███████▊  | 44800/57600 [7:52:34<2:14:04,  1.59it/s]
                                                         
{'loss': 1.1123, 'learning_rate': 3.0069686411149833e-07, 'epoch': 494.48}
+
 78%|███████▊  | 44800/57600 [7:52:34<2:14:04,  1.59it/s]
 78%|███████▊  | 44801/57600 [7:52:34<2:10:30,  1.63it/s]
 78%|███████▊  | 44802/57600 [7:52:35<2:05:27,  1.70it/s]
 78%|███████▊  | 44803/57600 [7:52:35<2:08:13,  1.66it/s]
 78%|███████▊  | 44804/57600 [7:52:36<2:14:24,  1.59it/s]
 78%|███████▊  | 44805/57600 [7:52:37<2:12:32,  1.61it/s]
 78%|███████▊  | 44806/57600 [7:52:37<2:08:59,  1.65it/s]
 78%|███████▊  | 44807/57600 [7:52:38<2:10:12,  1.64it/s]
 78%|███████▊  | 44808/57600 [7:52:39<2:12:11,  1.61it/s]
 78%|███████▊  | 44809/57600 [7:52:39<2:16:54,  1.56it/s]
 78%|███████▊  | 44810/57600 [7:52:40<2:14:59,  1.58it/s]
 78%|███████▊  | 44811/57600 [7:52:41<2:16:07,  1.57it/s]
 78%|███████▊  | 44812/57600 [7:52:41<2:18:40,  1.54it/s]
 78%|███████▊  | 44813/57600 [7:52:42<2:16:00,  1.57it/s]
 78%|███████▊  | 44814/57600 [7:52:43<2:18:34,  1.54it/s]
 78%|███████▊  | 44815/57600 [7:52:43<2:20:53,  1.51it/s]
 78%|███████▊  | 44816/57600 [7:52:44<2:17:53,  1.55it/s]
 78%|███████▊  | 44817/57600 [7:52:44<2:19:08,  1.53it/s]
 78%|███████▊  | 44818/57600 [7:52:45<2:16:35,  1.56it/s]
 78%|███████▊  | 44819/57600 [7:52:46<2:18:06,  1.54it/s]
 78%|███████▊  | 44820/57600 [7:52:46<2:16:33,  1.56it/s]
                                                         
{'loss': 1.1273, 'learning_rate': 3.00383275261324e-07, 'epoch': 494.7}
+
 78%|███████▊  | 44820/57600 [7:52:46<2:16:33,  1.56it/s]
 78%|███████▊  | 44821/57600 [7:52:47<2:12:23,  1.61it/s]
 78%|███████▊  | 44822/57600 [7:52:48<2:12:10,  1.61it/s]
 78%|███████▊  | 44823/57600 [7:52:48<2:10:27,  1.63it/s]
 78%|███████▊  | 44824/57600 [7:52:49<2:11:25,  1.62it/s]
 78%|███████▊  | 44825/57600 [7:52:49<2:11:10,  1.62it/s]
 78%|███████▊  | 44826/57600 [7:52:50<2:09:33,  1.64it/s]
 78%|███████▊  | 44827/57600 [7:52:51<2:10:25,  1.63it/s]
 78%|███████▊  | 44828/57600 [7:52:51<2:14:04,  1.59it/s]
 78%|███████▊  | 44829/57600 [7:52:52<2:14:32,  1.58it/s]
 78%|███████▊  | 44830/57600 [7:52:53<2:18:08,  1.54it/s]
 78%|███████▊  | 44831/57600 [7:52:53<2:14:38,  1.58it/s]
 78%|███████▊  | 44832/57600 [7:52:54<2:12:45,  1.60it/s]
 78%|███████▊  | 44833/57600 [7:52:54<2:08:40,  1.65it/s]
 78%|███████▊  | 44834/57600 [7:52:55<2:10:38,  1.63it/s]
 78%|███████▊  | 44835/57600 [7:52:56<2:10:04,  1.64it/s]
 78%|███████▊  | 44836/57600 [7:52:56<2:12:16,  1.61it/s]
 78%|███████▊  | 44837/57600 [7:52:57<2:09:25,  1.64it/s]
 78%|███████▊  | 44838/57600 [7:52:57<2:09:35,  1.64it/s]
 78%|███████▊  | 44839/57600 [7:52:58<2:08:52,  1.65it/s]
 78%|███████▊  | 44840/57600 [7:52:59<2:06:57,  1.68it/s]
                                                         
{'loss': 1.1231, 'learning_rate': 3.0006968641114983e-07, 'epoch': 494.92}
+
 78%|███████▊  | 44840/57600 [7:52:59<2:06:57,  1.68it/s]
 78%|███████▊  | 44841/57600 [7:52:59<2:08:49,  1.65it/s]
 78%|███████▊  | 44842/57600 [7:53:00<2:16:24,  1.56it/s]
 78%|███████▊  | 44843/57600 [7:53:01<2:16:55,  1.55it/s]
 78%|███████▊  | 44844/57600 [7:53:01<2:15:40,  1.57it/s]
 78%|███████▊  | 44845/57600 [7:53:02<2:11:27,  1.62it/s]
 78%|███████▊  | 44846/57600 [7:53:02<2:13:25,  1.59it/s]
 78%|███████▊  | 44847/57600 [7:53:03<2:11:08,  1.62it/s]
 78%|███████▊  | 44848/57600 [7:53:04<2:14:43,  1.58it/s]
 78%|███████▊  | 44849/57600 [7:53:04<2:14:29,  1.58it/s]
 78%|███████▊  | 44850/57600 [7:53:05<2:14:09,  1.58it/s]
 78%|███████▊  | 44851/57600 [7:53:06<2:15:02,  1.57it/s]
 78%|███████▊  | 44852/57600 [7:53:06<2:17:27,  1.55it/s]
 78%|███████▊  | 44853/57600 [7:53:07<2:14:04,  1.58it/s]
 78%|███████▊  | 44854/57600 [7:53:08<2:13:59,  1.59it/s]
 78%|███████▊  | 44855/57600 [7:53:08<2:15:24,  1.57it/s]
 78%|███████▊  | 44856/57600 [7:53:09<2:17:44,  1.54it/s]
 78%|███████▊  | 44857/57600 [7:53:09<2:15:20,  1.57it/s]
 78%|███████▊  | 44858/57600 [7:53:10<2:11:43,  1.61it/s]
 78%|███████▊  | 44859/57600 [7:53:11<2:16:02,  1.56it/s]
 78%|███████▊  | 44860/57600 [7:53:11<2:18:53,  1.53it/s]
                                                         
{'loss': 1.1174, 'learning_rate': 2.997560975609756e-07, 'epoch': 495.14}
+
 78%|███████▊  | 44860/57600 [7:53:11<2:18:53,  1.53it/s]
 78%|███████▊  | 44861/57600 [7:53:12<2:13:50,  1.59it/s]
 78%|███████▊  | 44862/57600 [7:53:13<2:14:43,  1.58it/s]
 78%|███████▊  | 44863/57600 [7:53:13<2:15:41,  1.56it/s]
 78%|███████▊  | 44864/57600 [7:53:14<2:11:10,  1.62it/s]
 78%|███████▊  | 44865/57600 [7:53:14<2:11:19,  1.62it/s]
 78%|███████▊  | 44866/57600 [7:53:15<2:10:26,  1.63it/s]
 78%|███████▊  | 44867/57600 [7:53:16<2:10:09,  1.63it/s]
 78%|███████▊  | 44868/57600 [7:53:16<2:11:12,  1.62it/s]
 78%|███████▊  | 44869/57600 [7:53:17<2:11:40,  1.61it/s]
 78%|███████▊  | 44870/57600 [7:53:18<2:10:43,  1.62it/s]
 78%|███████▊  | 44871/57600 [7:53:18<2:09:28,  1.64it/s]
 78%|███████▊  | 44872/57600 [7:53:19<2:09:43,  1.64it/s]
 78%|███████▊  | 44873/57600 [7:53:19<2:06:21,  1.68it/s]
 78%|███████▊  | 44874/57600 [7:53:20<2:13:03,  1.59it/s]
 78%|███████▊  | 44875/57600 [7:53:21<2:17:01,  1.55it/s]
 78%|███████▊  | 44876/57600 [7:53:21<2:15:49,  1.56it/s]
 78%|███████▊  | 44877/57600 [7:53:22<2:12:27,  1.60it/s]
 78%|███████▊  | 44878/57600 [7:53:23<2:11:15,  1.62it/s]
 78%|███████▊  | 44879/57600 [7:53:23<2:17:00,  1.55it/s]
 78%|███████▊  | 44880/57600 [7:53:24<2:14:23,  1.58it/s]
                                                         
{'loss': 1.1085, 'learning_rate': 2.994425087108014e-07, 'epoch': 495.36}
+
 78%|███████▊  | 44880/57600 [7:53:24<2:14:23,  1.58it/s]
 78%|███████▊  | 44881/57600 [7:53:25<2:14:50,  1.57it/s]
 78%|███████▊  | 44882/57600 [7:53:25<2:13:26,  1.59it/s]
 78%|███████▊  | 44883/57600 [7:53:26<2:15:18,  1.57it/s]
 78%|███████▊  | 44884/57600 [7:53:26<2:17:58,  1.54it/s]
 78%|███████▊  | 44885/57600 [7:53:27<2:14:51,  1.57it/s]
 78%|███████▊  | 44886/57600 [7:53:28<2:13:12,  1.59it/s]
 78%|███████▊  | 44887/57600 [7:53:28<2:14:18,  1.58it/s]
 78%|███████▊  | 44888/57600 [7:53:29<2:13:21,  1.59it/s]
 78%|███████▊  | 44889/57600 [7:53:30<2:09:48,  1.63it/s]
 78%|███████▊  | 44890/57600 [7:53:30<2:09:32,  1.64it/s]
 78%|███████▊  | 44891/57600 [7:53:31<2:13:29,  1.59it/s]
 78%|███████▊  | 44892/57600 [7:53:31<2:15:09,  1.57it/s]
 78%|███████▊  | 44893/57600 [7:53:32<2:10:43,  1.62it/s]
 78%|███████▊  | 44894/57600 [7:53:33<2:08:59,  1.64it/s]
 78%|███████▊  | 44895/57600 [7:53:33<2:07:31,  1.66it/s]
 78%|███████▊  | 44896/57600 [7:53:34<2:11:14,  1.61it/s]
 78%|███████▊  | 44897/57600 [7:53:35<2:12:50,  1.59it/s]
 78%|███████▊  | 44898/57600 [7:53:35<2:11:45,  1.61it/s]
 78%|███████▊  | 44899/57600 [7:53:36<2:14:53,  1.57it/s]
 78%|███████▊  | 44900/57600 [7:53:36<2:11:56,  1.60it/s]
                                                         
{'loss': 1.1319, 'learning_rate': 2.9912891986062714e-07, 'epoch': 495.58}
+
 78%|███████▊  | 44900/57600 [7:53:36<2:11:56,  1.60it/s]
 78%|███████▊  | 44901/57600 [7:53:37<2:10:36,  1.62it/s]
 78%|███████▊  | 44902/57600 [7:53:38<2:09:14,  1.64it/s]
 78%|███████▊  | 44903/57600 [7:53:38<2:11:03,  1.61it/s]
 78%|███████▊  | 44904/57600 [7:53:39<2:13:33,  1.58it/s]
 78%|███████▊  | 44905/57600 [7:53:40<2:16:42,  1.55it/s]
 78%|███████▊  | 44906/57600 [7:53:40<2:14:41,  1.57it/s]
 78%|███████▊  | 44907/57600 [7:53:41<2:12:07,  1.60it/s]
 78%|███████▊  | 44908/57600 [7:53:41<2:10:39,  1.62it/s]
 78%|██���████▊  | 44909/57600 [7:53:42<2:10:17,  1.62it/s]
 78%|███████▊  | 44910/57600 [7:53:43<2:11:59,  1.60it/s]
 78%|███████▊  | 44911/57600 [7:53:43<2:10:19,  1.62it/s]
 78%|███████▊  | 44912/57600 [7:53:44<2:14:13,  1.58it/s]
 78%|███████▊  | 44913/57600 [7:53:45<2:21:52,  1.49it/s]
 78%|███████▊  | 44914/57600 [7:53:45<2:16:20,  1.55it/s]
 78%|███████▊  | 44915/57600 [7:53:46<2:16:09,  1.55it/s]
 78%|███████▊  | 44916/57600 [7:53:47<2:16:31,  1.55it/s]
 78%|███████▊  | 44917/57600 [7:53:47<2:17:39,  1.54it/s]
 78%|███████▊  | 44918/57600 [7:53:48<2:15:43,  1.56it/s]
 78%|███████▊  | 44919/57600 [7:53:48<2:15:46,  1.56it/s]
 78%|███████▊  | 44920/57600 [7:53:49<2:14:51,  1.57it/s]
                                                         
{'loss': 1.138, 'learning_rate': 2.9881533101045294e-07, 'epoch': 495.81}
+
 78%|███████▊  | 44920/57600 [7:53:49<2:14:51,  1.57it/s]
 78%|███████▊  | 44921/57600 [7:53:50<2:16:32,  1.55it/s]
 78%|███████▊  | 44922/57600 [7:53:50<2:12:49,  1.59it/s]
 78%|███████▊  | 44923/57600 [7:53:51<2:12:42,  1.59it/s]
 78%|███████▊  | 44924/57600 [7:53:52<2:09:41,  1.63it/s]
 78%|███████▊  | 44925/57600 [7:53:52<2:13:41,  1.58it/s]
 78%|███████▊  | 44926/57600 [7:53:53<2:13:41,  1.58it/s]
 78%|███████▊  | 44927/57600 [7:53:53<2:09:48,  1.63it/s]
 78%|███████▊  | 44928/57600 [7:53:54<2:11:41,  1.60it/s]
 78%|███████▊  | 44929/57600 [7:53:55<2:09:32,  1.63it/s]
 78%|███████▊  | 44930/57600 [7:53:55<2:09:23,  1.63it/s]
 78%|███████▊  | 44931/57600 [7:53:56<2:12:33,  1.59it/s]
 78%|███████▊  | 44932/57600 [7:53:57<2:13:45,  1.58it/s]
 78%|███████▊  | 44933/57600 [7:53:57<2:16:07,  1.55it/s]
 78%|███████▊  | 44934/57600 [7:53:58<2:22:17,  1.48it/s]
 78%|███████▊  | 44935/57600 [7:53:59<2:18:25,  1.52it/s]
 78%|███████▊  | 44936/57600 [7:53:59<2:22:08,  1.48it/s]
 78%|███████▊  | 44937/57600 [7:54:00<2:15:53,  1.55it/s]
 78%|███████▊  | 44938/57600 [7:54:01<2:17:06,  1.54it/s]
 78%|███████▊  | 44939/57600 [7:54:01<2:16:08,  1.55it/s]
 78%|███████▊  | 44940/57600 [7:54:02<2:14:41,  1.57it/s]
                                                         
{'loss': 1.1056, 'learning_rate': 2.985017421602788e-07, 'epoch': 496.03}
+
 78%|███████▊  | 44940/57600 [7:54:02<2:14:41,  1.57it/s]
 78%|███████▊  | 44941/57600 [7:54:03<2:17:54,  1.53it/s]
 78%|███████▊  | 44942/57600 [7:54:03<2:15:47,  1.55it/s]
 78%|███████▊  | 44943/57600 [7:54:04<2:16:49,  1.54it/s]
 78%|███████▊  | 44944/57600 [7:54:04<2:18:32,  1.52it/s]
 78%|███████▊  | 44945/57600 [7:54:05<2:16:45,  1.54it/s]
 78%|███████▊  | 44946/57600 [7:54:06<2:17:19,  1.54it/s]
 78%|███████▊  | 44947/57600 [7:54:06<2:19:36,  1.51it/s]
 78%|███████▊  | 44948/57600 [7:54:07<2:16:52,  1.54it/s]
 78%|███████▊  | 44949/57600 [7:54:08<2:12:10,  1.60it/s]
 78%|███████▊  | 44950/57600 [7:54:08<2:16:05,  1.55it/s]
 78%|███████▊  | 44951/57600 [7:54:09<2:18:33,  1.52it/s]
 78%|███████▊  | 44952/57600 [7:54:10<2:17:39,  1.53it/s]
 78%|███████▊  | 44953/57600 [7:54:10<2:15:35,  1.55it/s]
 78%|███████▊  | 44954/57600 [7:54:11<2:14:44,  1.56it/s]
 78%|███████▊  | 44955/57600 [7:54:12<2:12:50,  1.59it/s]
 78%|███████▊  | 44956/57600 [7:54:12<2:12:40,  1.59it/s]
 78%|███████▊  | 44957/57600 [7:54:13<2:17:52,  1.53it/s]
 78%|███████▊  | 44958/57600 [7:54:13<2:17:21,  1.53it/s]
 78%|███████▊  | 44959/57600 [7:54:14<2:16:09,  1.55it/s]
 78%|███████▊  | 44960/57600 [7:54:15<2:16:14,  1.55it/s]
                                                         
{'loss': 1.0901, 'learning_rate': 2.981881533101045e-07, 'epoch': 496.25}
+
 78%|███████▊  | 44960/57600 [7:54:15<2:16:14,  1.55it/s]
 78%|███████▊  | 44961/57600 [7:54:15<2:13:08,  1.58it/s]
 78%|███████▊  | 44962/57600 [7:54:16<2:14:52,  1.56it/s]
 78%|███████▊  | 44963/57600 [7:54:17<2:15:18,  1.56it/s]
 78%|███████▊  | 44964/57600 [7:54:17<2:16:33,  1.54it/s]
 78%|███████▊  | 44965/57600 [7:54:18<2:19:40,  1.51it/s]
 78%|███████▊  | 44966/57600 [7:54:19<2:15:31,  1.55it/s]
 78%|███████▊  | 44967/57600 [7:54:19<2:13:35,  1.58it/s]
 78%|███████▊  | 44968/57600 [7:54:20<2:16:18,  1.54it/s]
 78%|███████▊  | 44969/57600 [7:54:21<2:17:39,  1.53it/s]
 78%|███████▊  | 44970/57600 [7:54:21<2:17:03,  1.54it/s]
 78%|███████▊  | 44971/57600 [7:54:22<2:14:18,  1.57it/s]
 78%|███████▊  | 44972/57600 [7:54:23<2:16:32,  1.54it/s]
 78%|███████▊  | 44973/57600 [7:54:23<2:11:58,  1.59it/s]
 78%|███████▊  | 44974/57600 [7:54:24<2:17:28,  1.53it/s]
 78%|███████▊  | 44975/57600 [7:54:24<2:13:38,  1.57it/s]
 78%|███████▊  | 44976/57600 [7:54:25<2:11:33,  1.60it/s]
 78%|███████▊  | 44977/57600 [7:54:26<2:14:24,  1.57it/s]
 78%|███████▊  | 44978/57600 [7:54:26<2:16:10,  1.54it/s]
 78%|███████▊  | 44979/57600 [7:54:27<2:14:56,  1.56it/s]
 78%|███████▊  | 44980/57600 [7:54:28<2:13:43,  1.57it/s]
                                                         
{'loss': 1.11, 'learning_rate': 2.978745644599303e-07, 'epoch': 496.47}
+
 78%|███████▊  | 44980/57600 [7:54:28<2:13:43,  1.57it/s]
 78%|███████▊  | 44981/57600 [7:54:28<2:09:35,  1.62it/s]
 78%|███████▊  | 44982/57600 [7:54:29<2:09:42,  1.62it/s]
 78%|███████▊  | 44983/57600 [7:54:29<2:06:14,  1.67it/s]
 78%|███████▊  | 44984/57600 [7:54:30<2:04:29,  1.69it/s]
 78%|███████▊  | 44985/57600 [7:54:31<2:04:14,  1.69it/s]
 78%|███████▊  | 44986/57600 [7:54:31<2:10:51,  1.61it/s]
 78%|███████▊  | 44987/57600 [7:54:32<2:08:35,  1.63it/s]
 78%|███████▊  | 44988/57600 [7:54:32<2:08:37,  1.63it/s]
 78%|███████▊  | 44989/57600 [7:54:33<2:10:20,  1.61it/s]
 78%|███████▊  | 44990/57600 [7:54:34<2:12:18,  1.59it/s]
 78%|███████▊  | 44991/57600 [7:54:34<2:10:27,  1.61it/s]
 78%|███████▊  | 44992/57600 [7:54:35<2:10:25,  1.61it/s]
 78%|███████▊  | 44993/57600 [7:54:36<2:12:34,  1.58it/s]
 78%|███████▊  | 44994/57600 [7:54:36<2:16:33,  1.54it/s]
 78%|███████▊  | 44995/57600 [7:54:37<2:15:33,  1.55it/s]
 78%|███████▊  | 44996/57600 [7:54:37<2:12:30,  1.59it/s]
 78%|███████▊  | 44997/57600 [7:54:38<2:13:28,  1.57it/s]
 78%|███████▊  | 44998/57600 [7:54:39<2:11:11,  1.60it/s]
 78%|███████▊  | 44999/57600 [7:54:39<2:11:59,  1.59it/s]
 78%|███████▊  | 45000/57600 [7:54:40<2:11:42,  1.59it/s]
                                                         
{'loss': 1.1398, 'learning_rate': 2.9756097560975606e-07, 'epoch': 496.69}
+
 78%|███████▊  | 45000/57600 [7:54:40<2:11:42,  1.59it/s]
 78%|███████▊  | 45001/57600 [7:54:41<2:10:01,  1.61it/s]
 78%|███████▊  | 45002/57600 [7:54:41<2:09:36,  1.62it/s]
 78%|███████▊  | 45003/57600 [7:54:42<2:07:34,  1.65it/s]
 78%|███████▊  | 45004/57600 [7:54:42<2:08:51,  1.63it/s]
 78%|███████▊  | 45005/57600 [7:54:43<2:09:04,  1.63it/s]
 78%|███████▊  | 45006/57600 [7:54:44<2:07:16,  1.65it/s]
 78%|███████▊  | 45007/57600 [7:54:44<2:05:23,  1.67it/s]
 78%|███████▊  | 45008/57600 [7:54:45<2:05:45,  1.67it/s]
 78%|███████▊  | 45009/57600 [7:54:46<2:11:23,  1.60it/s]
 78%|███████▊  | 45010/57600 [7:54:46<2:09:24,  1.62it/s]
 78%|███████▊  | 45011/57600 [7:54:47<2:10:40,  1.61it/s]
 78%|███████▊  | 45012/57600 [7:54:47<2:13:55,  1.57it/s]
 78%|███████▊  | 45013/57600 [7:54:48<2:10:34,  1.61it/s]
 78%|███████▊  | 45014/57600 [7:54:49<2:10:02,  1.61it/s]
 78%|███████▊  | 45015/57600 [7:54:49<2:07:05,  1.65it/s]
 78%|███████▊  | 45016/57600 [7:54:50<2:08:39,  1.63it/s]
 78%|███████▊  | 45017/57600 [7:54:50<2:09:02,  1.63it/s]
 78%|███████▊  | 45018/57600 [7:54:51<2:12:25,  1.58it/s]
 78%|███████▊  | 45019/57600 [7:54:52<2:12:07,  1.59it/s]
 78%|███████▊  | 45020/57600 [7:54:52<2:11:23,  1.60it/s]
                                                         
{'loss': 1.1342, 'learning_rate': 2.972473867595819e-07, 'epoch': 496.91}
+
 78%|███████▊  | 45020/57600 [7:54:52<2:11:23,  1.60it/s]
 78%|███████▊  | 45021/57600 [7:54:53<2:12:27,  1.58it/s]
 78%|███████▊  | 45022/57600 [7:54:54<2:12:55,  1.58it/s]
 78%|███████▊  | 45023/57600 [7:54:54<2:12:58,  1.58it/s]
 78%|███████▊  | 45024/57600 [7:54:55<2:11:28,  1.59it/s]
 78%|███████▊  | 45025/57600 [7:54:56<2:13:39,  1.57it/s]
 78%|███████▊  | 45026/57600 [7:54:56<2:13:14,  1.57it/s]
 78%|███████▊  | 45027/57600 [7:54:57<2:13:32,  1.57it/s]
 78%|███████▊  | 45028/57600 [7:54:57<2:12:04,  1.59it/s]
 78%|███████▊  | 45029/57600 [7:54:58<2:16:59,  1.53it/s]
 78%|███████▊  | 45030/57600 [7:54:59<2:13:28,  1.57it/s]
 78%|███████▊  | 45031/57600 [7:54:59<2:11:23,  1.59it/s]
 78%|███████▊  | 45032/57600 [7:55:00<2:09:54,  1.61it/s]
 78%|███████▊  | 45033/57600 [7:55:01<2:08:28,  1.63it/s]
 78%|███████▊  | 45034/57600 [7:55:01<2:06:01,  1.66it/s]
 78%|███████▊  | 45035/57600 [7:55:02<2:05:59,  1.66it/s]
 78%|███████▊  | 45036/57600 [7:55:02<2:03:48,  1.69it/s]
 78%|███████▊  | 45037/57600 [7:55:03<2:07:15,  1.65it/s]
 78%|███████▊  | 45038/57600 [7:55:04<2:11:13,  1.60it/s]
 78%|███████▊  | 45039/57600 [7:55:04<2:06:57,  1.65it/s]
 78%|███████▊  | 45040/57600 [7:55:05<2:03:54,  1.69it/s]
                                                         
{'loss': 1.1409, 'learning_rate': 2.969337979094076e-07, 'epoch': 497.13}
+
 78%|███████▊  | 45040/57600 [7:55:05<2:03:54,  1.69it/s]
 78%|███████▊  | 45041/57600 [7:55:05<2:03:11,  1.70it/s]
 78%|███████▊  | 45042/57600 [7:55:06<2:10:23,  1.61it/s]
 78%|███████▊  | 45043/57600 [7:55:07<2:14:30,  1.56it/s]
 78%|███████▊  | 45044/57600 [7:55:07<2:16:52,  1.53it/s]
 78%|███████▊  | 45045/57600 [7:55:08<2:18:56,  1.51it/s]
 78%|███████▊  | 45046/57600 [7:55:09<2:17:33,  1.52it/s]
 78%|███████▊  | 45047/57600 [7:55:09<2:17:55,  1.52it/s]
 78%|███████▊  | 45048/57600 [7:55:10<2:18:06,  1.51it/s]
 78%|███████▊  | 45049/57600 [7:55:11<2:16:26,  1.53it/s]
 78%|███████▊  | 45050/57600 [7:55:11<2:12:44,  1.58it/s]
 78%|███████▊  | 45051/57600 [7:55:12<2:16:04,  1.54it/s]
 78%|███████▊  | 45052/57600 [7:55:13<2:14:46,  1.55it/s]
 78%|███████▊  | 45053/57600 [7:55:13<2:13:21,  1.57it/s]
 78%|███████▊  | 45054/57600 [7:55:14<2:10:50,  1.60it/s]
 78%|███████▊  | 45055/57600 [7:55:14<2:10:43,  1.60it/s]
 78%|███████▊  | 45056/57600 [7:55:15<2:16:28,  1.53it/s]
 78%|███████▊  | 45057/57600 [7:55:16<2:14:23,  1.56it/s]
 78%|███████▊  | 45058/57600 [7:55:16<2:20:03,  1.49it/s]
 78%|███████▊  | 45059/57600 [7:55:17<2:17:49,  1.52it/s]
 78%|███████▊  | 45060/57600 [7:55:18<2:15:41,  1.54it/s]
                                                         
{'loss': 1.0931, 'learning_rate': 2.966202090592334e-07, 'epoch': 497.35}
+
 78%|███████▊  | 45060/57600 [7:55:18<2:15:41,  1.54it/s]
 78%|███████▊  | 45061/57600 [7:55:18<2:19:02,  1.50it/s]
 78%|███████▊  | 45062/57600 [7:55:19<2:16:23,  1.53it/s]
 78%|███████▊  | 45063/57600 [7:55:20<2:16:16,  1.53it/s]
 78%|███████▊  | 45064/57600 [7:55:20<2:12:20,  1.58it/s]
 78%|███████▊  | 45065/57600 [7:55:21<2:08:09,  1.63it/s]
 78%|███████▊  | 45066/57600 [7:55:21<2:07:04,  1.64it/s]
 78%|███████▊  | 45067/57600 [7:55:22<2:08:19,  1.63it/s]
 78%|███████▊  | 45068/57600 [7:55:23<2:08:44,  1.62it/s]
 78%|███████▊  | 45069/57600 [7:55:23<2:09:45,  1.61it/s]
 78%|███████▊  | 45070/57600 [7:55:24<2:07:49,  1.63it/s]
 78%|███████▊  | 45071/57600 [7:55:25<2:07:38,  1.64it/s]
 78%|███████▊  | 45072/57600 [7:55:25<2:04:46,  1.67it/s]
 78%|███████▊  | 45073/57600 [7:55:26<2:02:26,  1.71it/s]
 78%|███████▊  | 45074/57600 [7:55:26<2:03:10,  1.69it/s]
 78%|███████▊  | 45075/57600 [7:55:27<2:08:16,  1.63it/s]
 78%|███████▊  | 45076/57600 [7:55:28<2:07:11,  1.64it/s]
 78%|███████▊  | 45077/57600 [7:55:28<2:10:56,  1.59it/s]
 78%|███████▊  | 45078/57600 [7:55:29<2:16:25,  1.53it/s]
 78%|███████▊  | 45079/57600 [7:55:29<2:10:15,  1.60it/s]
 78%|███████▊  | 45080/57600 [7:55:30<2:10:31,  1.60it/s]
                                                         
{'loss': 1.1652, 'learning_rate': 2.963066202090593e-07, 'epoch': 497.57}
+
 78%|███████▊  | 45080/57600 [7:55:30<2:10:31,  1.60it/s]
 78%|███████▊  | 45081/57600 [7:55:31<2:09:18,  1.61it/s]
 78%|███████▊  | 45082/57600 [7:55:31<2:06:10,  1.65it/s]
 78%|███████▊  | 45083/57600 [7:55:32<2:09:50,  1.61it/s]
 78%|███████▊  | 45084/57600 [7:55:33<2:11:37,  1.58it/s]
 78%|███████▊  | 45085/57600 [7:55:33<2:11:22,  1.59it/s]
 78%|███████▊  | 45086/57600 [7:55:34<2:15:30,  1.54it/s]
 78%|███████▊  | 45087/57600 [7:55:35<2:12:27,  1.57it/s]
 78%|███████▊  | 45088/57600 [7:55:35<2:09:49,  1.61it/s]
 78%|███████▊  | 45089/57600 [7:55:36<2:07:45,  1.63it/s]
 78%|███████▊  | 45090/57600 [7:55:36<2:06:44,  1.65it/s]
 78%|███████▊  | 45091/57600 [7:55:37<2:07:52,  1.63it/s]
 78%|███████▊  | 45092/57600 [7:55:38<2:13:35,  1.56it/s]
 78%|███████▊  | 45093/57600 [7:55:38<2:16:17,  1.53it/s]
 78%|███████▊  | 45094/57600 [7:55:39<2:16:52,  1.52it/s]
 78%|███████▊  | 45095/57600 [7:55:40<2:13:49,  1.56it/s]
 78%|███████▊  | 45096/57600 [7:55:40<2:08:44,  1.62it/s]
 78%|███████▊  | 45097/57600 [7:55:41<2:05:49,  1.66it/s]
 78%|███████▊  | 45098/57600 [7:55:41<2:07:53,  1.63it/s]
 78%|███████▊  | 45099/57600 [7:55:42<2:10:04,  1.60it/s]
 78%|███████▊  | 45100/57600 [7:55:43<2:08:44,  1.62it/s]
                                                         
{'loss': 1.1286, 'learning_rate': 2.9599303135888503e-07, 'epoch': 497.79}
+
 78%|███████▊  | 45100/57600 [7:55:43<2:08:44,  1.62it/s]
 78%|███████▊  | 45101/57600 [7:55:43<2:09:18,  1.61it/s]
 78%|███████▊  | 45102/57600 [7:55:44<2:10:40,  1.59it/s]
 78%|███████▊  | 45103/57600 [7:55:44<2:08:12,  1.62it/s]
 78%|███████▊  | 45104/57600 [7:55:45<2:05:39,  1.66it/s]
 78%|███████▊  | 45105/57600 [7:55:46<2:09:45,  1.60it/s]
 78%|███████▊  | 45106/57600 [7:55:46<2:08:13,  1.62it/s]
 78%|███████▊  | 45107/57600 [7:55:47<2:08:37,  1.62it/s]
 78%|███████▊  | 45108/57600 [7:55:48<2:04:52,  1.67it/s]
 78%|███████▊  | 45109/57600 [7:55:48<2:09:22,  1.61it/s]
 78%|███████▊  | 45110/57600 [7:55:49<2:12:02,  1.58it/s]
 78%|███████▊  | 45111/57600 [7:55:49<2:11:38,  1.58it/s]
 78%|███████▊  | 45112/57600 [7:55:50<2:14:56,  1.54it/s]
 78%|███████▊  | 45113/57600 [7:55:51<2:09:18,  1.61it/s]
 78%|███████▊  | 45114/57600 [7:55:51<2:09:32,  1.61it/s]
 78%|███████▊  | 45115/57600 [7:55:52<2:05:16,  1.66it/s]
 78%|███████▊  | 45116/57600 [7:55:52<2:05:36,  1.66it/s]
 78%|███████▊  | 45117/57600 [7:55:53<2:12:47,  1.57it/s]
 78%|███████▊  | 45118/57600 [7:55:54<2:12:33,  1.57it/s]
 78%|███████▊  | 45119/57600 [7:55:55<2:19:21,  1.49it/s]
 78%|███████▊  | 45120/57600 [7:55:55<2:11:38,  1.58it/s]
                                                         
{'loss': 1.1267, 'learning_rate': 2.956794425087108e-07, 'epoch': 498.01}
+
 78%|███████▊  | 45120/57600 [7:55:55<2:11:38,  1.58it/s]
 78%|███████▊  | 45121/57600 [7:55:56<2:12:09,  1.57it/s]
 78%|███████▊  | 45122/57600 [7:55:56<2:12:33,  1.57it/s]
 78%|███████▊  | 45123/57600 [7:55:57<2:14:22,  1.55it/s]
 78%|███████▊  | 45124/57600 [7:55:58<2:11:04,  1.59it/s]
 78%|███████▊  | 45125/57600 [7:55:58<2:09:01,  1.61it/s]
 78%|███████▊  | 45126/57600 [7:55:59<2:08:27,  1.62it/s]
 78%|███████▊  | 45127/57600 [7:56:00<2:09:28,  1.61it/s]
 78%|███████▊  | 45128/57600 [7:56:00<2:08:46,  1.61it/s]
 78%|███████▊  | 45129/57600 [7:56:01<2:07:49,  1.63it/s]
 78%|███████▊  | 45130/57600 [7:56:01<2:15:12,  1.54it/s]
 78%|███████▊  | 45131/57600 [7:56:02<2:12:35,  1.57it/s]
 78%|███████▊  | 45132/57600 [7:56:03<2:13:34,  1.56it/s]
 78%|███████▊  | 45133/57600 [7:56:03<2:12:38,  1.57it/s]
 78%|███████▊  | 45134/57600 [7:56:04<2:10:18,  1.59it/s]
 78%|███████▊  | 45135/57600 [7:56:05<2:12:54,  1.56it/s]
 78%|███████▊  | 45136/57600 [7:56:05<2:15:32,  1.53it/s]
 78%|███████▊  | 45137/57600 [7:56:06<2:17:37,  1.51it/s]
 78%|███████▊  | 45138/57600 [7:56:07<2:14:06,  1.55it/s]
 78%|███████▊  | 45139/57600 [7:56:07<2:13:45,  1.55it/s]
 78%|███████▊  | 45140/57600 [7:56:08<2:14:02,  1.55it/s]
                                                         
{'loss': 1.1027, 'learning_rate': 2.9536585365853653e-07, 'epoch': 498.23}
+
 78%|███████▊  | 45140/57600 [7:56:08<2:14:02,  1.55it/s]
 78%|███████▊  | 45141/57600 [7:56:08<2:10:16,  1.59it/s]
 78%|███████▊  | 45142/57600 [7:56:09<2:06:25,  1.64it/s]
 78%|███████▊  | 45143/57600 [7:56:10<2:07:23,  1.63it/s]
 78%|███████▊  | 45144/57600 [7:56:10<2:05:34,  1.65it/s]
 78%|███████▊  | 45145/57600 [7:56:11<2:05:36,  1.65it/s]
 78%|███████▊  | 45146/57600 [7:56:12<2:07:20,  1.63it/s]
 78%|███████▊  | 45147/57600 [7:56:12<2:06:55,  1.64it/s]
 78%|███████▊  | 45148/57600 [7:56:13<2:04:32,  1.67it/s]
 78%|███████▊  | 45149/57600 [7:56:13<2:04:23,  1.67it/s]
 78%|███████▊  | 45150/57600 [7:56:14<2:10:19,  1.59it/s]
 78%|███████▊  | 45151/57600 [7:56:15<2:07:03,  1.63it/s]
 78%|██��████▊  | 45152/57600 [7:56:15<2:09:37,  1.60it/s]
 78%|███████▊  | 45153/57600 [7:56:16<2:09:49,  1.60it/s]
 78%|███████▊  | 45154/57600 [7:56:16<2:07:17,  1.63it/s]
 78%|███████▊  | 45155/57600 [7:56:17<2:08:35,  1.61it/s]
 78%|███████▊  | 45156/57600 [7:56:18<2:10:41,  1.59it/s]
 78%|███████▊  | 45157/57600 [7:56:18<2:13:54,  1.55it/s]
 78%|███████▊  | 45158/57600 [7:56:19<2:09:28,  1.60it/s]
 78%|███████▊  | 45159/57600 [7:56:20<2:12:24,  1.57it/s]
 78%|███████▊  | 45160/57600 [7:56:20<2:08:24,  1.61it/s]
                                                         
{'loss': 1.1416, 'learning_rate': 2.950522648083624e-07, 'epoch': 498.45}
+
 78%|███████▊  | 45160/57600 [7:56:20<2:08:24,  1.61it/s]
 78%|███████▊  | 45161/57600 [7:56:21<2:07:27,  1.63it/s]
 78%|███████▊  | 45162/57600 [7:56:21<2:07:31,  1.63it/s]
 78%|███████▊  | 45163/57600 [7:56:22<2:04:37,  1.66it/s]
 78%|███████▊  | 45164/57600 [7:56:23<2:08:22,  1.61it/s]
 78%|███████▊  | 45165/57600 [7:56:23<2:09:01,  1.61it/s]
 78%|███████▊  | 45166/57600 [7:56:24<2:10:20,  1.59it/s]
 78%|███████▊  | 45167/57600 [7:56:25<2:12:29,  1.56it/s]
 78%|███████▊  | 45168/57600 [7:56:25<2:09:35,  1.60it/s]
 78%|███████▊  | 45169/57600 [7:56:26<2:06:05,  1.64it/s]
 78%|███████▊  | 45170/57600 [7:56:26<2:12:03,  1.57it/s]
 78%|███████▊  | 45171/57600 [7:56:27<2:11:59,  1.57it/s]
 78%|███████▊  | 45172/57600 [7:56:28<2:11:33,  1.57it/s]
 78%|███████▊  | 45173/57600 [7:56:28<2:10:32,  1.59it/s]
 78%|███████▊  | 45174/57600 [7:56:29<2:09:02,  1.60it/s]
 78%|███████▊  | 45175/57600 [7:56:30<2:07:12,  1.63it/s]
 78%|███████▊  | 45176/57600 [7:56:30<2:14:34,  1.54it/s]
 78%|███████▊  | 45177/57600 [7:56:31<2:12:06,  1.57it/s]
 78%|███████▊  | 45178/57600 [7:56:32<2:17:48,  1.50it/s]
 78%|███████▊  | 45179/57600 [7:56:32<2:13:06,  1.56it/s]
 78%|███████▊  | 45180/57600 [7:56:33<2:11:56,  1.57it/s]
                                                         
{'loss': 1.0954, 'learning_rate': 2.947386759581881e-07, 'epoch': 498.68}
+
 78%|███████▊  | 45180/57600 [7:56:33<2:11:56,  1.57it/s]
 78%|███████▊  | 45181/57600 [7:56:33<2:10:28,  1.59it/s]
 78%|███████▊  | 45182/57600 [7:56:34<2:07:34,  1.62it/s]
 78%|███████▊  | 45183/57600 [7:56:35<2:08:13,  1.61it/s]
 78%|███████▊  | 45184/57600 [7:56:35<2:04:32,  1.66it/s]
 78%|███████▊  | 45185/57600 [7:56:36<2:12:08,  1.57it/s]
 78%|███████▊  | 45186/57600 [7:56:37<2:12:44,  1.56it/s]
 78%|███████▊  | 45187/57600 [7:56:37<2:07:33,  1.62it/s]
 78%|███████▊  | 45188/57600 [7:56:38<2:11:07,  1.58it/s]
 78%|███████▊  | 45189/57600 [7:56:38<2:09:34,  1.60it/s]
 78%|███████▊  | 45190/57600 [7:56:39<2:06:18,  1.64it/s]
 78%|███████▊  | 45191/57600 [7:56:40<2:07:23,  1.62it/s]
 78%|███████▊  | 45192/57600 [7:56:40<2:07:14,  1.63it/s]
 78%|███████▊  | 45193/57600 [7:56:41<2:05:07,  1.65it/s]
 78%|███████▊  | 45194/57600 [7:56:41<2:06:51,  1.63it/s]
 78%|███████▊  | 45195/57600 [7:56:42<2:04:26,  1.66it/s]
 78%|███████▊  | 45196/57600 [7:56:43<2:05:17,  1.65it/s]
 78%|███████▊  | 45197/57600 [7:56:43<2:08:47,  1.61it/s]
 78%|███████▊  | 45198/57600 [7:56:44<2:05:42,  1.64it/s]
 78%|███████▊  | 45199/57600 [7:56:45<2:10:22,  1.59it/s]
 78%|███████▊  | 45200/57600 [7:56:45<2:15:21,  1.53it/s]
                                                         
{'loss': 1.1428, 'learning_rate': 2.944250871080139e-07, 'epoch': 498.9}
+
 78%|███████▊  | 45200/57600 [7:56:45<2:15:21,  1.53it/s]
 78%|███████▊  | 45201/57600 [7:56:46<2:11:52,  1.57it/s]
 78%|███████▊  | 45202/57600 [7:56:47<2:10:54,  1.58it/s]
 78%|███████▊  | 45203/57600 [7:56:47<2:13:38,  1.55it/s]
 78%|███████▊  | 45204/57600 [7:56:48<2:10:43,  1.58it/s]
 78%|███████▊  | 45205/57600 [7:56:48<2:08:51,  1.60it/s]
 78%|███████▊  | 45206/57600 [7:56:49<2:10:41,  1.58it/s]
 78%|███████▊  | 45207/57600 [7:56:50<2:14:48,  1.53it/s]
 78%|███████▊  | 45208/57600 [7:56:50<2:15:49,  1.52it/s]
 78%|███████▊  | 45209/57600 [7:56:51<2:16:01,  1.52it/s]
 78%|███████▊  | 45210/57600 [7:56:52<2:17:57,  1.50it/s]
 78%|███████▊  | 45211/57600 [7:56:52<2:13:33,  1.55it/s]
 78%|███████▊  | 45212/57600 [7:56:53<2:10:27,  1.58it/s]
 78%|███████▊  | 45213/57600 [7:56:54<2:10:31,  1.58it/s]
 78%|███████▊  | 45214/57600 [7:56:54<2:11:00,  1.58it/s]
 78%|███████▊  | 45215/57600 [7:56:55<2:07:46,  1.62it/s]
 78%|███████▊  | 45216/57600 [7:56:55<2:09:29,  1.59it/s]
 79%|███████▊  | 45217/57600 [7:56:56<2:11:45,  1.57it/s]
 79%|███████▊  | 45218/57600 [7:56:57<2:12:01,  1.56it/s]
 79%|███████▊  | 45219/57600 [7:56:57<2:09:56,  1.59it/s]
 79%|███████▊  | 45220/57600 [7:56:58<2:16:54,  1.51it/s]
                                                         
{'loss': 1.1246, 'learning_rate': 2.9411149825783975e-07, 'epoch': 499.12}
+
 79%|███████▊  | 45220/57600 [7:56:58<2:16:54,  1.51it/s]
 79%|███████▊  | 45221/57600 [7:56:59<2:13:23,  1.55it/s]
 79%|███████▊  | 45222/57600 [7:56:59<2:11:19,  1.57it/s]
 79%|███████▊  | 45223/57600 [7:57:00<2:11:03,  1.57it/s]
 79%|███████▊  | 45224/57600 [7:57:01<2:11:05,  1.57it/s]
 79%|███████▊  | 45225/57600 [7:57:01<2:08:30,  1.61it/s]
 79%|███████▊  | 45226/57600 [7:57:02<2:07:18,  1.62it/s]
 79%|███████▊  | 45227/57600 [7:57:02<2:06:36,  1.63it/s]
 79%|███████▊  | 45228/57600 [7:57:03<2:10:09,  1.58it/s]
 79%|███████▊  | 45229/57600 [7:57:04<2:07:35,  1.62it/s]
 79%|███████▊  | 45230/57600 [7:57:04<2:09:42,  1.59it/s]
 79%|███████▊  | 45231/57600 [7:57:05<2:10:16,  1.58it/s]
 79%|███████▊  | 45232/57600 [7:57:06<2:07:57,  1.61it/s]
 79%|███████▊  | 45233/57600 [7:57:06<2:06:09,  1.63it/s]
 79%|███████▊  | 45234/57600 [7:57:07<2:07:48,  1.61it/s]
 79%|███████▊  | 45235/57600 [7:57:07<2:07:05,  1.62it/s]
 79%|███████▊  | 45236/57600 [7:57:08<2:08:14,  1.61it/s]
 79%|███████▊  | 45237/57600 [7:57:09<2:11:23,  1.57it/s]
 79%|███████▊  | 45238/57600 [7:57:09<2:08:02,  1.61it/s]
 79%|███████▊  | 45239/57600 [7:57:10<2:07:24,  1.62it/s]
 79%|███████▊  | 45240/57600 [7:57:11<2:06:24,  1.63it/s]
                                                         
{'loss': 1.1236, 'learning_rate': 2.937979094076655e-07, 'epoch': 499.34}
+
 79%|███████▊  | 45240/57600 [7:57:11<2:06:24,  1.63it/s]
 79%|███████▊  | 45241/57600 [7:57:11<2:08:29,  1.60it/s]
 79%|███████▊  | 45242/57600 [7:57:12<2:08:14,  1.61it/s]
 79%|███████▊  | 45243/57600 [7:57:12<2:07:02,  1.62it/s]
 79%|███████▊  | 45244/57600 [7:57:13<2:09:13,  1.59it/s]
 79%|███████▊  | 45245/57600 [7:57:14<2:14:40,  1.53it/s]
 79%|███████▊  | 45246/57600 [7:57:14<2:15:19,  1.52it/s]
 79%|███████▊  | 45247/57600 [7:57:15<2:18:06,  1.49it/s]
 79%|███████▊  | 45248/57600 [7:57:16<2:14:11,  1.53it/s]
 79%|███████▊  | 45249/57600 [7:57:16<2:10:36,  1.58it/s]
 79%|███████▊  | 45250/57600 [7:57:17<2:08:52,  1.60it/s]
 79%|███████▊  | 45251/57600 [7:57:18<2:07:44,  1.61it/s]
 79%|███████▊  | 45252/57600 [7:57:18<2:04:41,  1.65it/s]
 79%|███████▊  | 45253/57600 [7:57:19<2:07:29,  1.61it/s]
 79%|███████▊  | 45254/57600 [7:57:19<2:06:01,  1.63it/s]
 79%|███████▊  | 45255/57600 [7:57:20<2:09:37,  1.59it/s]
 79%|███████▊  | 45256/57600 [7:57:21<2:07:07,  1.62it/s]
 79%|███████▊  | 45257/57600 [7:57:21<2:07:38,  1.61it/s]
 79%|███████▊  | 45258/57600 [7:57:22<2:09:01,  1.59it/s]
 79%|███████▊  | 45259/57600 [7:57:22<2:07:39,  1.61it/s]
 79%|███████▊  | 45260/57600 [7:57:23<2:17:37,  1.49it/s]
                                                         
{'loss': 1.1216, 'learning_rate': 2.9348432055749126e-07, 'epoch': 499.56}
+
 79%|███████▊  | 45260/57600 [7:57:23<2:17:37,  1.49it/s]
 79%|███████▊  | 45261/57600 [7:57:24<2:18:12,  1.49it/s]
 79%|███████▊  | 45262/57600 [7:57:25<2:14:38,  1.53it/s]
 79%|███████▊  | 45263/57600 [7:57:25<2:10:29,  1.58it/s]
 79%|███████▊  | 45264/57600 [7:57:26<2:10:52,  1.57it/s]
 79%|███████▊  | 45265/57600 [7:57:26<2:10:17,  1.58it/s]
 79%|███████▊  | 45266/57600 [7:57:27<2:09:07,  1.59it/s]
 79%|███████▊  | 45267/57600 [7:57:28<2:09:42,  1.58it/s]
 79%|███████▊  | 45268/57600 [7:57:28<2:10:12,  1.58it/s]
 79%|███████▊  | 45269/57600 [7:57:29<2:15:01,  1.52it/s]
 79%|███████▊  | 45270/57600 [7:57:30<2:14:43,  1.53it/s]
 79%|███████▊  | 45271/57600 [7:57:30<2:09:17,  1.59it/s]
 79%|███████▊  | 45272/57600 [7:57:31<2:06:20,  1.63it/s]
 79%|███████▊  | 45273/57600 [7:57:32<2:11:20,  1.56it/s]
 79%|███████▊  | 45274/57600 [7:57:32<2:08:02,  1.60it/s]
 79%|███████▊  | 45275/57600 [7:57:33<2:08:31,  1.60it/s]
 79%|███████▊  | 45276/57600 [7:57:33<2:14:23,  1.53it/s]
 79%|███████▊  | 45277/57600 [7:57:34<2:09:15,  1.59it/s]
 79%|███████▊  | 45278/57600 [7:57:35<2:10:00,  1.58it/s]
 79%|███████▊  | 45279/57600 [7:57:35<2:06:14,  1.63it/s]
 79%|███████▊  | 45280/57600 [7:57:36<2:09:31,  1.59it/s]
                                                         
{'loss': 1.1215, 'learning_rate': 2.93170731707317e-07, 'epoch': 499.78}
+
 79%|███████▊  | 45280/57600 [7:57:36<2:09:31,  1.59it/s]
 79%|███████▊  | 45281/57600 [7:57:37<2:08:11,  1.60it/s]
 79%|███████▊  | 45282/57600 [7:57:37<2:07:02,  1.62it/s]
 79%|███████▊  | 45283/57600 [7:57:38<2:04:55,  1.64it/s]
 79%|███████▊  | 45284/57600 [7:57:38<2:06:30,  1.62it/s]
 79%|███████▊  | 45285/57600 [7:57:39<2:08:23,  1.60it/s]
 79%|███████▊  | 45286/57600 [7:57:40<2:05:06,  1.64it/s]
 79%|███████▊  | 45287/57600 [7:57:40<2:05:05,  1.64it/s]
 79%|███████▊  | 45288/57600 [7:57:41<2:08:17,  1.60it/s]
 79%|███████▊  | 45289/57600 [7:57:41<2:07:38,  1.61it/s]
 79%|███████▊  | 45290/57600 [7:57:42<2:06:08,  1.63it/s]
 79%|███████▊  | 45291/57600 [7:57:43<2:07:52,  1.60it/s]
 79%|███████▊  | 45292/57600 [7:57:43<2:08:18,  1.60it/s]
 79%|███████▊  | 45293/57600 [7:57:44<2:10:00,  1.58it/s]
 79%|███████▊  | 45294/57600 [7:57:45<2:07:31,  1.61it/s]
 79%|███████▊  | 45295/57600 [7:57:45<2:07:14,  1.61it/s]
 79%|███████▊  | 45296/57600 [7:57:46<2:06:11,  1.62it/s]
 79%|███████▊  | 45297/57600 [7:57:46<2:04:19,  1.65it/s]
 79%|███████▊  | 45298/57600 [7:57:47<2:07:11,  1.61it/s]
 79%|███████▊  | 45299/57600 [7:57:48<2:12:14,  1.55it/s]
 79%|███████▊  | 45300/57600 [7:57:48<2:10:16,  1.57it/s]
                                                         
{'loss': 1.1316, 'learning_rate': 2.9285714285714287e-07, 'epoch': 500.0}
+
 79%|███████▊  | 45300/57600 [7:57:48<2:10:16,  1.57it/s]
 79%|███████▊  | 45301/57600 [7:57:49<2:19:59,  1.46it/s]
 79%|███████▊  | 45302/57600 [7:57:50<2:15:35,  1.51it/s]
 79%|███████▊  | 45303/57600 [7:57:50<2:14:27,  1.52it/s]
 79%|███████▊  | 45304/57600 [7:57:51<2:09:16,  1.59it/s]
 79%|███████▊  | 45305/57600 [7:57:52<2:08:19,  1.60it/s]
 79%|███████▊  | 45306/57600 [7:57:52<2:09:31,  1.58it/s]
 79%|███████▊  | 45307/57600 [7:57:53<2:07:14,  1.61it/s]
 79%|███████▊  | 45308/57600 [7:57:53<2:03:58,  1.65it/s]
 79%|███████▊  | 45309/57600 [7:57:54<2:06:22,  1.62it/s]
 79%|███████▊  | 45310/57600 [7:57:55<2:03:51,  1.65it/s]
 79%|███████▊  | 45311/57600 [7:57:55<2:05:52,  1.63it/s]
 79%|███████▊  | 45312/57600 [7:57:56<2:03:49,  1.65it/s]
 79%|███████▊  | 45313/57600 [7:57:56<2:07:26,  1.61it/s]
 79%|███████▊  | 45314/57600 [7:57:57<2:08:46,  1.59it/s]
 79%|███████▊  | 45315/57600 [7:57:58<2:07:11,  1.61it/s]
 79%|███████▊  | 45316/57600 [7:57:58<2:06:42,  1.62it/s]
 79%|███████▊  | 45317/57600 [7:57:59<2:14:10,  1.53it/s]
 79%|███████▊  | 45318/57600 [7:58:00<2:14:58,  1.52it/s]
 79%|███████▊  | 45319/57600 [7:58:00<2:12:04,  1.55it/s]
 79%|███████▊  | 45320/57600 [7:58:01<2:11:01,  1.56it/s]
                                                         
{'loss': 1.1448, 'learning_rate': 2.925435540069686e-07, 'epoch': 500.22}
+
 79%|███████▊  | 45320/57600 [7:58:01<2:11:01,  1.56it/s]
 79%|███████▊  | 45321/57600 [7:58:02<2:08:04,  1.60it/s]
 79%|███████▊  | 45322/57600 [7:58:02<2:07:18,  1.61it/s]
 79%|███████▊  | 45323/57600 [7:58:03<2:04:44,  1.64it/s]
 79%|███████▊  | 45324/57600 [7:58:03<2:05:16,  1.63it/s]
 79%|███████▊  | 45325/57600 [7:58:04<2:02:38,  1.67it/s]
 79%|███████▊  | 45326/57600 [7:58:05<2:03:44,  1.65it/s]
 79%|███████▊  | 45327/57600 [7:58:05<2:06:01,  1.62it/s]
 79%|███████▊  | 45328/57600 [7:58:06<2:06:32,  1.62it/s]
 79%|███████▊  | 45329/57600 [7:58:06<2:05:10,  1.63it/s]
 79%|███████▊  | 45330/57600 [7:58:07<2:06:33,  1.62it/s]
 79%|███████▊  | 45331/57600 [7:58:08<2:07:38,  1.60it/s]
 79%|███████▊  | 45332/57600 [7:58:08<2:07:31,  1.60it/s]
 79%|███████▊  | 45333/57600 [7:58:09<2:03:57,  1.65it/s]
 79%|███████▊  | 45334/57600 [7:58:10<2:09:50,  1.57it/s]
 79%|███████▊  | 45335/57600 [7:58:10<2:08:21,  1.59it/s]
 79%|███████▊  | 45336/57600 [7:58:11<2:09:26,  1.58it/s]
 79%|███████▊  | 45337/57600 [7:58:12<2:09:52,  1.57it/s]
 79%|███████▊  | 45338/57600 [7:58:12<2:09:16,  1.58it/s]
 79%|███████▊  | 45339/57600 [7:58:13<2:06:24,  1.62it/s]
 79%|███████▊  | 45340/57600 [7:58:13<2:07:31,  1.60it/s]
                                                         
{'loss': 1.1379, 'learning_rate': 2.922299651567944e-07, 'epoch': 500.44}
+
 79%|███████▊  | 45340/57600 [7:58:13<2:07:31,  1.60it/s]
 79%|███████▊  | 45341/57600 [7:58:14<2:04:25,  1.64it/s]
 79%|███████▊  | 45342/57600 [7:58:15<2:04:37,  1.64it/s]
 79%|███████▊  | 45343/57600 [7:58:15<2:07:45,  1.60it/s]
 79%|███████▊  | 45344/57600 [7:58:16<2:04:57,  1.63it/s]
 79%|███████▊  | 45345/57600 [7:58:16<2:07:24,  1.60it/s]
 79%|███████▊  | 45346/57600 [7:58:17<2:07:10,  1.61it/s]
 79%|███████▊  | 45347/57600 [7:58:18<2:04:13,  1.64it/s]
 79%|███████▊  | 45348/57600 [7:58:18<2:05:09,  1.63it/s]
 79%|███████▊  | 45349/57600 [7:58:19<2:03:24,  1.65it/s]
 79%|███████▊  | 45350/57600 [7:58:20<2:07:05,  1.61it/s]
 79%|███████▊  | 45351/57600 [7:58:20<2:06:17,  1.62it/s]
 79%|███████▊  | 45352/57600 [7:58:21<2:05:40,  1.62it/s]
 79%|███████▊  | 45353/57600 [7:58:21<2:07:36,  1.60it/s]
 79%|███████▊  | 45354/57600 [7:58:22<2:12:16,  1.54it/s]
 79%|███████▊  | 45355/57600 [7:58:23<2:11:32,  1.55it/s]
 79%|███████▊  | 45356/57600 [7:58:23<2:08:31,  1.59it/s]
 79%|███████▊  | 45357/57600 [7:58:24<2:05:36,  1.62it/s]
 79%|███████▊  | 45358/57600 [7:58:25<2:12:59,  1.53it/s]
 79%|███████▊  | 45359/57600 [7:58:25<2:12:07,  1.54it/s]
 79%|███████▉  | 45360/57600 [7:58:26<2:12:01,  1.55it/s]
                                                         
{'loss': 1.1104, 'learning_rate': 2.9191637630662023e-07, 'epoch': 500.66}
+
 79%|███████▉  | 45360/57600 [7:58:26<2:12:01,  1.55it/s]
 79%|███████▉  | 45361/57600 [7:58:27<2:11:53,  1.55it/s]
 79%|███████▉  | 45362/57600 [7:58:27<2:10:31,  1.56it/s]
 79%|███████▉  | 45363/57600 [7:58:28<2:11:52,  1.55it/s]
 79%|███████▉  | 45364/57600 [7:58:29<2:14:06,  1.52it/s]
 79%|███████▉  | 45365/57600 [7:58:29<2:12:37,  1.54it/s]
 79%|███████▉  | 45366/57600 [7:58:30<2:10:00,  1.57it/s]
 79%|███████▉  | 45367/57600 [7:58:30<2:09:46,  1.57it/s]
 79%|███████▉  | 45368/57600 [7:58:31<2:12:37,  1.54it/s]
 79%|███████▉  | 45369/57600 [7:58:32<2:12:12,  1.54it/s]
 79%|███████▉  | 45370/57600 [7:58:32<2:09:04,  1.58it/s]
 79%|███████▉  | 45371/57600 [7:58:33<2:13:01,  1.53it/s]
 79%|███████▉  | 45372/57600 [7:58:34<2:12:08,  1.54it/s]
 79%|███████▉  | 45373/57600 [7:58:34<2:13:14,  1.53it/s]
 79%|███████▉  | 45374/57600 [7:58:35<2:12:37,  1.54it/s]
 79%|███████▉  | 45375/57600 [7:58:36<2:10:14,  1.56it/s]
 79%|███████▉  | 45376/57600 [7:58:36<2:12:14,  1.54it/s]
 79%|███████▉  | 45377/57600 [7:58:37<2:11:22,  1.55it/s]
 79%|███████▉  | 45378/57600 [7:58:37<2:07:02,  1.60it/s]
 79%|███████▉  | 45379/57600 [7:58:38<2:11:52,  1.54it/s]
 79%|███████▉  | 45380/57600 [7:58:39<2:10:45,  1.56it/s]
                                                         
{'loss': 1.1084, 'learning_rate': 2.9160278745644593e-07, 'epoch': 500.88}
+
 79%|███████▉  | 45380/57600 [7:58:39<2:10:45,  1.56it/s]
 79%|███████▉  | 45381/57600 [7:58:39<2:07:22,  1.60it/s]
 79%|███████▉  | 45382/57600 [7:58:40<2:09:52,  1.57it/s]
 79%|███████▉  | 45383/57600 [7:58:41<2:07:09,  1.60it/s]
 79%|███████▉  | 45384/57600 [7:58:41<2:10:17,  1.56it/s]
 79%|███████▉  | 45385/57600 [7:58:42<2:07:17,  1.60it/s]
 79%|███████▉  | 45386/57600 [7:58:42<2:04:53,  1.63it/s]
 79%|███████▉  | 45387/57600 [7:58:43<2:04:37,  1.63it/s]
 79%|███████▉  | 45388/57600 [7:58:44<2:07:25,  1.60it/s]
 79%|███████▉  | 45389/57600 [7:58:44<2:09:51,  1.57it/s]
 79%|███████▉  | 45390/57600 [7:58:45<2:09:52,  1.57it/s]
 79%|███████▉  | 45391/57600 [7:58:46<2:17:33,  1.48it/s]
 79%|███████▉  | 45392/57600 [7:58:46<2:14:31,  1.51it/s]
 79%|███████▉  | 45393/57600 [7:58:47<2:10:22,  1.56it/s]
 79%|███████▉  | 45394/57600 [7:58:48<2:11:29,  1.55it/s]
 79%|██��████▉  | 45395/57600 [7:58:48<2:11:08,  1.55it/s]
 79%|███████▉  | 45396/57600 [7:58:49<2:08:56,  1.58it/s]
 79%|███████▉  | 45397/57600 [7:58:50<2:09:41,  1.57it/s]
 79%|███████▉  | 45398/57600 [7:58:50<2:07:35,  1.59it/s]
 79%|███████▉  | 45399/57600 [7:58:51<2:05:45,  1.62it/s]
 79%|███████▉  | 45400/57600 [7:58:52<2:11:29,  1.55it/s]
                                                         
{'loss': 1.1076, 'learning_rate': 2.912891986062718e-07, 'epoch': 501.1}
+
 79%|███████▉  | 45400/57600 [7:58:52<2:11:29,  1.55it/s]
 79%|███████▉  | 45401/57600 [7:58:52<2:09:51,  1.57it/s]
 79%|███████▉  | 45402/57600 [7:58:53<2:06:03,  1.61it/s]
 79%|███████▉  | 45403/57600 [7:58:53<2:07:08,  1.60it/s]
 79%|███████▉  | 45404/57600 [7:58:54<2:06:59,  1.60it/s]
 79%|███████▉  | 45405/57600 [7:58:55<2:09:44,  1.57it/s]
 79%|███████▉  | 45406/57600 [7:58:55<2:06:39,  1.60it/s]
 79%|███████▉  | 45407/57600 [7:58:56<2:08:44,  1.58it/s]
 79%|███████▉  | 45408/57600 [7:58:57<2:09:51,  1.56it/s]
 79%|███████▉  | 45409/57600 [7:58:57<2:12:12,  1.54it/s]
 79%|███████▉  | 45410/57600 [7:58:58<2:15:13,  1.50it/s]
 79%|███████▉  | 45411/57600 [7:58:59<2:14:01,  1.52it/s]
 79%|███████▉  | 45412/57600 [7:58:59<2:08:07,  1.59it/s]
 79%|███████▉  | 45413/57600 [7:59:00<2:09:15,  1.57it/s]
 79%|███████▉  | 45414/57600 [7:59:00<2:09:47,  1.56it/s]
 79%|███████▉  | 45415/57600 [7:59:01<2:07:56,  1.59it/s]
 79%|███████▉  | 45416/57600 [7:59:02<2:05:43,  1.62it/s]
 79%|███████▉  | 45417/57600 [7:59:02<2:04:54,  1.63it/s]
 79%|███████▉  | 45418/57600 [7:59:03<2:04:54,  1.63it/s]
 79%|███████▉  | 45419/57600 [7:59:04<2:08:24,  1.58it/s]
 79%|███████▉  | 45420/57600 [7:59:04<2:09:52,  1.56it/s]
                                                         
{'loss': 1.1087, 'learning_rate': 2.909756097560975e-07, 'epoch': 501.32}
+
 79%|███████▉  | 45420/57600 [7:59:04<2:09:52,  1.56it/s]
 79%|███████▉  | 45421/57600 [7:59:05<2:08:21,  1.58it/s]
 79%|███████▉  | 45422/57600 [7:59:05<2:10:41,  1.55it/s]
 79%|███████▉  | 45423/57600 [7:59:06<2:15:09,  1.50it/s]
 79%|███████▉  | 45424/57600 [7:59:07<2:10:59,  1.55it/s]
 79%|███████▉  | 45425/57600 [7:59:07<2:07:29,  1.59it/s]
 79%|███████▉  | 45426/57600 [7:59:08<2:08:14,  1.58it/s]
 79%|███████▉  | 45427/57600 [7:59:09<2:08:22,  1.58it/s]
 79%|███████▉  | 45428/57600 [7:59:09<2:12:22,  1.53it/s]
 79%|███████▉  | 45429/57600 [7:59:10<2:12:22,  1.53it/s]
 79%|███████▉  | 45430/57600 [7:59:11<2:06:42,  1.60it/s]
 79%|███████▉  | 45431/57600 [7:59:11<2:08:03,  1.58it/s]
 79%|███████▉  | 45432/57600 [7:59:12<2:07:47,  1.59it/s]
 79%|███████▉  | 45433/57600 [7:59:12<2:07:05,  1.60it/s]
 79%|███████▉  | 45434/57600 [7:59:13<2:11:38,  1.54it/s]
 79%|███████▉  | 45435/57600 [7:59:14<2:10:33,  1.55it/s]
 79%|███████▉  | 45436/57600 [7:59:14<2:08:13,  1.58it/s]
 79%|███████▉  | 45437/57600 [7:59:15<2:07:28,  1.59it/s]
 79%|███████▉  | 45438/57600 [7:59:16<2:06:09,  1.61it/s]
 79%|███████▉  | 45439/57600 [7:59:16<2:06:22,  1.60it/s]
 79%|███████▉  | 45440/57600 [7:59:17<2:05:25,  1.62it/s]
                                                         
{'loss': 1.1351, 'learning_rate': 2.9066202090592334e-07, 'epoch': 501.55}
+
 79%|███████▉  | 45440/57600 [7:59:17<2:05:25,  1.62it/s]
 79%|███████▉  | 45441/57600 [7:59:18<2:10:50,  1.55it/s]
 79%|███████▉  | 45442/57600 [7:59:18<2:10:00,  1.56it/s]
 79%|███████▉  | 45443/57600 [7:59:19<2:09:52,  1.56it/s]
 79%|███████▉  | 45444/57600 [7:59:20<2:12:55,  1.52it/s]
 79%|███████▉  | 45445/57600 [7:59:20<2:11:21,  1.54it/s]
 79%|███████▉  | 45446/57600 [7:59:21<2:14:11,  1.51it/s]
 79%|███████▉  | 45447/57600 [7:59:21<2:13:17,  1.52it/s]
 79%|███████▉  | 45448/57600 [7:59:22<2:09:56,  1.56it/s]
 79%|███████▉  | 45449/57600 [7:59:23<2:07:50,  1.58it/s]
 79%|███████▉  | 45450/57600 [7:59:23<2:06:07,  1.61it/s]
 79%|███████▉  | 45451/57600 [7:59:24<2:06:18,  1.60it/s]
 79%|███████▉  | 45452/57600 [7:59:25<2:07:31,  1.59it/s]
 79%|███████▉  | 45453/57600 [7:59:25<2:06:53,  1.60it/s]
 79%|███████▉  | 45454/57600 [7:59:26<2:05:14,  1.62it/s]
 79%|███████▉  | 45455/57600 [7:59:26<2:03:00,  1.65it/s]
 79%|███████▉  | 45456/57600 [7:59:27<2:03:57,  1.63it/s]
 79%|███████▉  | 45457/57600 [7:59:28<2:03:25,  1.64it/s]
 79%|███████▉  | 45458/57600 [7:59:28<2:04:36,  1.62it/s]
 79%|███████▉  | 45459/57600 [7:59:29<2:04:16,  1.63it/s]
 79%|███████▉  | 45460/57600 [7:59:30<2:09:54,  1.56it/s]
                                                         
{'loss': 1.1006, 'learning_rate': 2.903484320557491e-07, 'epoch': 501.77}
+
 79%|███████▉  | 45460/57600 [7:59:30<2:09:54,  1.56it/s]
 79%|███████▉  | 45461/57600 [7:59:30<2:06:38,  1.60it/s]
 79%|███████▉  | 45462/57600 [7:59:31<2:06:32,  1.60it/s]
 79%|███████▉  | 45463/57600 [7:59:31<2:08:26,  1.57it/s]
 79%|███████▉  | 45464/57600 [7:59:32<2:11:47,  1.53it/s]
 79%|███████▉  | 45465/57600 [7:59:33<2:06:39,  1.60it/s]
 79%|███████▉  | 45466/57600 [7:59:33<2:07:53,  1.58it/s]
 79%|███████▉  | 45467/57600 [7:59:34<2:09:39,  1.56it/s]
 79%|███████▉  | 45468/57600 [7:59:35<2:07:36,  1.58it/s]
 79%|███████▉  | 45469/57600 [7:59:35<2:03:03,  1.64it/s]
 79%|███████▉  | 45470/57600 [7:59:36<2:02:25,  1.65it/s]
 79%|███████▉  | 45471/57600 [7:59:36<2:05:26,  1.61it/s]
 79%|███████▉  | 45472/57600 [7:59:37<2:01:45,  1.66it/s]
 79%|███████▉  | 45473/57600 [7:59:38<2:03:58,  1.63it/s]
 79%|███████▉  | 45474/57600 [7:59:38<2:02:33,  1.65it/s]
 79%|███████▉  | 45475/57600 [7:59:39<2:05:31,  1.61it/s]
 79%|███████▉  | 45476/57600 [7:59:39<2:06:12,  1.60it/s]
 79%|███████▉  | 45477/57600 [7:59:40<2:07:50,  1.58it/s]
 79%|███████▉  | 45478/57600 [7:59:41<2:06:54,  1.59it/s]
 79%|███████▉  | 45479/57600 [7:59:41<2:06:01,  1.60it/s]
 79%|███████▉  | 45480/57600 [7:59:42<2:08:53,  1.57it/s]
                                                         
{'loss': 1.1596, 'learning_rate': 2.900348432055749e-07, 'epoch': 501.99}
+
 79%|███████▉  | 45480/57600 [7:59:42<2:08:53,  1.57it/s]
 79%|███████▉  | 45481/57600 [7:59:43<2:10:36,  1.55it/s]
 79%|███████▉  | 45482/57600 [7:59:43<2:14:32,  1.50it/s]
 79%|███████▉  | 45483/57600 [7:59:44<2:13:25,  1.51it/s]
 79%|███████▉  | 45484/57600 [7:59:45<2:16:36,  1.48it/s]
 79%|███████▉  | 45485/57600 [7:59:45<2:10:54,  1.54it/s]
 79%|███████▉  | 45486/57600 [7:59:46<2:11:23,  1.54it/s]
 79%|███████▉  | 45487/57600 [7:59:47<2:08:02,  1.58it/s]
 79%|███████▉  | 45488/57600 [7:59:47<2:09:12,  1.56it/s]
 79%|███████▉  | 45489/57600 [7:59:48<2:10:14,  1.55it/s]
 79%|███████▉  | 45490/57600 [7:59:48<2:05:27,  1.61it/s]
 79%|███████▉  | 45491/57600 [7:59:49<2:02:47,  1.64it/s]
 79%|███████▉  | 45492/57600 [7:59:50<2:01:49,  1.66it/s]
 79%|███████▉  | 45493/57600 [7:59:50<2:03:05,  1.64it/s]
 79%|███████▉  | 45494/57600 [7:59:51<2:01:38,  1.66it/s]
 79%|███████▉  | 45495/57600 [7:59:52<2:03:48,  1.63it/s]
 79%|███████▉  | 45496/57600 [7:59:52<2:03:52,  1.63it/s]
 79%|███████▉  | 45497/57600 [7:59:53<2:04:37,  1.62it/s]
 79%|███████▉  | 45498/57600 [7:59:53<2:08:04,  1.57it/s]
 79%|███████▉  | 45499/57600 [7:59:54<2:08:30,  1.57it/s]
 79%|███████▉  | 45500/57600 [7:59:55<2:07:38,  1.58it/s]
                                                         
{'loss': 1.162, 'learning_rate': 2.897212543554007e-07, 'epoch': 502.21}
+
 79%|███████▉  | 45500/57600 [7:59:55<2:07:38,  1.58it/s]
 79%|███████▉  | 45501/57600 [7:59:55<2:06:22,  1.60it/s]
 79%|███████▉  | 45502/57600 [7:59:56<2:04:30,  1.62it/s]
 79%|███████▉  | 45503/57600 [7:59:57<2:07:08,  1.59it/s]
 79%|███████▉  | 45504/57600 [7:59:57<2:06:58,  1.59it/s]
 79%|███████▉  | 45505/57600 [7:59:58<2:11:00,  1.54it/s]
 79%|███████▉  | 45506/57600 [7:59:59<2:09:46,  1.55it/s]
 79%|███████▉  | 45507/57600 [7:59:59<2:07:13,  1.58it/s]
 79%|███████▉  | 45508/57600 [8:00:00<2:07:40,  1.58it/s]
 79%|███████▉  | 45509/57600 [8:00:00<2:09:11,  1.56it/s]
 79%|███████▉  | 45510/57600 [8:00:01<2:06:58,  1.59it/s]
 79%|███████▉  | 45511/57600 [8:00:02<2:09:35,  1.55it/s]
 79%|███████▉  | 45512/57600 [8:00:02<2:06:35,  1.59it/s]
 79%|███████▉  | 45513/57600 [8:00:03<2:05:25,  1.61it/s]
 79%|███████▉  | 45514/57600 [8:00:04<2:11:19,  1.53it/s]
 79%|███████▉  | 45515/57600 [8:00:04<2:07:58,  1.57it/s]
 79%|███████▉  | 45516/57600 [8:00:05<2:03:31,  1.63it/s]
 79%|███████▉  | 45517/57600 [8:00:05<2:08:55,  1.56it/s]
 79%|███████▉  | 45518/57600 [8:00:06<2:10:07,  1.55it/s]
 79%|███████▉  | 45519/57600 [8:00:07<2:08:59,  1.56it/s]
 79%|███████▉  | 45520/57600 [8:00:07<2:08:54,  1.56it/s]
                                                         
{'loss': 1.1339, 'learning_rate': 2.8940766550522646e-07, 'epoch': 502.43}
+
 79%|███████▉  | 45520/57600 [8:00:07<2:08:54,  1.56it/s]
 79%|███████▉  | 45521/57600 [8:00:08<2:07:12,  1.58it/s]
 79%|███████▉  | 45522/57600 [8:00:09<2:10:45,  1.54it/s]
 79%|███████▉  | 45523/57600 [8:00:09<2:10:02,  1.55it/s]
 79%|███████▉  | 45524/57600 [8:00:10<2:06:10,  1.60it/s]
 79%|███████▉  | 45525/57600 [8:00:10<2:02:00,  1.65it/s]
 79%|███████▉  | 45526/57600 [8:00:11<2:00:10,  1.67it/s]
 79%|███████▉  | 45527/57600 [8:00:12<2:00:59,  1.66it/s]
 79%|███████▉  | 45528/57600 [8:00:12<2:03:49,  1.62it/s]
 79%|███████▉  | 45529/57600 [8:00:13<2:07:52,  1.57it/s]
 79%|███████▉  | 45530/57600 [8:00:14<2:06:14,  1.59it/s]
 79%|███████▉  | 45531/57600 [8:00:14<2:02:43,  1.64it/s]
 79%|███████▉  | 45532/57600 [8:00:15<2:05:02,  1.61it/s]
 79%|███████▉  | 45533/57600 [8:00:16<2:08:35,  1.56it/s]
 79%|███████▉  | 45534/57600 [8:00:16<2:13:43,  1.50it/s]
 79%|███████▉  | 45535/57600 [8:00:17<2:09:07,  1.56it/s]
 79%|███████▉  | 45536/57600 [8:00:17<2:08:37,  1.56it/s]
 79%|███████▉  | 45537/57600 [8:00:18<2:05:38,  1.60it/s]
 79%|███████▉  | 45538/57600 [8:00:19<2:04:06,  1.62it/s]
 79%|███████▉  | 45539/57600 [8:00:19<2:13:57,  1.50it/s]
 79%|███████▉  | 45540/57600 [8:00:20<2:11:04,  1.53it/s]
                                                         
{'loss': 1.1219, 'learning_rate': 2.890940766550523e-07, 'epoch': 502.65}
+
 79%|███████▉  | 45540/57600 [8:00:20<2:11:04,  1.53it/s]
 79%|███████▉  | 45541/57600 [8:00:21<2:06:52,  1.58it/s]
 79%|███████▉  | 45542/57600 [8:00:21<2:08:07,  1.57it/s]
 79%|███████▉  | 45543/57600 [8:00:22<2:06:00,  1.59it/s]
 79%|███████▉  | 45544/57600 [8:00:23<2:08:33,  1.56it/s]
 79%|███████▉  | 45545/57600 [8:00:23<2:13:35,  1.50it/s]
 79%|███████▉  | 45546/57600 [8:00:24<2:11:06,  1.53it/s]
 79%|███████▉  | 45547/57600 [8:00:25<2:11:42,  1.53it/s]
 79%|███████▉  | 45548/57600 [8:00:25<2:12:13,  1.52it/s]
 79%|███████▉  | 45549/57600 [8:00:26<2:10:07,  1.54it/s]
 79%|███████▉  | 45550/57600 [8:00:26<2:07:38,  1.57it/s]
 79%|███████▉  | 45551/57600 [8:00:27<2:03:41,  1.62it/s]
 79%|███████▉  | 45552/57600 [8:00:28<2:01:42,  1.65it/s]
 79%|███████▉  | 45553/57600 [8:00:28<2:01:34,  1.65it/s]
 79%|███████▉  | 45554/57600 [8:00:29<2:01:43,  1.65it/s]
 79%|███████▉  | 45555/57600 [8:00:29<2:00:18,  1.67it/s]
 79%|███████▉  | 45556/57600 [8:00:30<1:59:16,  1.68it/s]
 79%|███████▉  | 45557/57600 [8:00:31<2:02:11,  1.64it/s]
 79%|███████▉  | 45558/57600 [8:00:31<2:08:44,  1.56it/s]
 79%|███████▉  | 45559/57600 [8:00:32<2:10:21,  1.54it/s]
 79%|███████▉  | 45560/57600 [8:00:33<2:12:47,  1.51it/s]
                                                         
{'loss': 1.1373, 'learning_rate': 2.88780487804878e-07, 'epoch': 502.87}
+
 79%|███████▉  | 45560/57600 [8:00:33<2:12:47,  1.51it/s]
 79%|███████▉  | 45561/57600 [8:00:33<2:08:47,  1.56it/s]
 79%|███████▉  | 45562/57600 [8:00:34<2:06:05,  1.59it/s]
 79%|███████▉  | 45563/57600 [8:00:35<2:06:19,  1.59it/s]
 79%|███████▉  | 45564/57600 [8:00:35<2:05:03,  1.60it/s]
 79%|███████▉  | 45565/57600 [8:00:36<2:04:15,  1.61it/s]
 79%|███████▉  | 45566/57600 [8:00:36<2:01:56,  1.64it/s]
 79%|███████▉  | 45567/57600 [8:00:37<2:00:22,  1.67it/s]
 79%|███████▉  | 45568/57600 [8:00:38<2:01:44,  1.65it/s]
 79%|███████▉  | 45569/57600 [8:00:38<2:02:51,  1.63it/s]
 79%|███████▉  | 45570/57600 [8:00:39<2:02:11,  1.64it/s]
 79%|███████▉  | 45571/57600 [8:00:39<2:01:18,  1.65it/s]
 79%|███████▉  | 45572/57600 [8:00:40<2:08:24,  1.56it/s]
 79%|███████▉  | 45573/57600 [8:00:41<2:11:38,  1.52it/s]
 79%|███████▉  | 45574/57600 [8:00:41<2:07:21,  1.57it/s]
 79%|███████▉  | 45575/57600 [8:00:42<2:05:42,  1.59it/s]
 79%|███████▉  | 45576/57600 [8:00:43<2:06:08,  1.59it/s]
 79%|███████▉  | 45577/57600 [8:00:43<2:08:36,  1.56it/s]
 79%|███████▉  | 45578/57600 [8:00:44<2:07:19,  1.57it/s]
 79%|███████▉  | 45579/57600 [8:00:45<2:06:57,  1.58it/s]
 79%|███████▉  | 45580/57600 [8:00:45<2:06:36,  1.58it/s]
                                                         
{'loss': 1.129, 'learning_rate': 2.884668989547038e-07, 'epoch': 503.09}
+
 79%|███████▉  | 45580/57600 [8:00:45<2:06:36,  1.58it/s]
 79%|███████▉  | 45581/57600 [8:00:46<2:05:48,  1.59it/s]
 79%|███████▉  | 45582/57600 [8:00:46<2:09:05,  1.55it/s]
 79%|███████▉  | 45583/57600 [8:00:47<2:06:28,  1.58it/s]
 79%|███████▉  | 45584/57600 [8:00:48<2:06:03,  1.59it/s]
 79%|███████▉  | 45585/57600 [8:00:48<2:03:52,  1.62it/s]
 79%|███████▉  | 45586/57600 [8:00:49<2:02:48,  1.63it/s]
 79%|███████▉  | 45587/57600 [8:00:49<2:02:32,  1.63it/s]
 79%|███████▉  | 45588/57600 [8:00:50<2:02:28,  1.63it/s]
 79%|███████▉  | 45589/57600 [8:00:51<2:05:11,  1.60it/s]
 79%|███████▉  | 45590/57600 [8:00:51<2:08:27,  1.56it/s]
 79%|███████▉  | 45591/57600 [8:00:52<2:11:49,  1.52it/s]
 79%|███████▉  | 45592/57600 [8:00:53<2:11:03,  1.53it/s]
 79%|███████▉  | 45593/57600 [8:00:53<2:06:00,  1.59it/s]
 79%|███████▉  | 45594/57600 [8:00:54<2:04:13,  1.61it/s]
 79%|███████▉  | 45595/57600 [8:00:55<2:00:00,  1.67it/s]
 79%|███████▉  | 45596/57600 [8:00:55<1:59:09,  1.68it/s]
 79%|███████▉  | 45597/57600 [8:00:56<2:02:25,  1.63it/s]
 79%|███████▉  | 45598/57600 [8:00:56<2:01:43,  1.64it/s]
 79%|███████▉  | 45599/57600 [8:00:57<2:06:08,  1.59it/s]
 79%|███████▉  | 45600/57600 [8:00:58<2:08:11,  1.56it/s]
                                                         
{'loss': 1.1331, 'learning_rate': 2.8815331010452957e-07, 'epoch': 503.31}
+
 79%|███████▉  | 45600/57600 [8:00:58<2:08:11,  1.56it/s]
 79%|███████▉  | 45601/57600 [8:00:58<2:06:27,  1.58it/s]
 79%|███████▉  | 45602/57600 [8:00:59<2:05:25,  1.59it/s]
 79%|███████▉  | 45603/57600 [8:01:00<2:04:14,  1.61it/s]
 79%|███████▉  | 45604/57600 [8:01:00<1:59:03,  1.68it/s]
 79%|███████▉  | 45605/57600 [8:01:01<2:03:39,  1.62it/s]
 79%|███████▉  | 45606/57600 [8:01:01<2:08:17,  1.56it/s]
 79%|███████▉  | 45607/57600 [8:01:02<2:04:45,  1.60it/s]
 79%|███████▉  | 45608/57600 [8:01:03<2:06:02,  1.59it/s]
 79%|███████▉  | 45609/57600 [8:01:03<2:07:04,  1.57it/s]
 79%|███████▉  | 45610/57600 [8:01:04<2:06:23,  1.58it/s]
 79%|███████▉  | 45611/57600 [8:01:05<2:04:57,  1.60it/s]
 79%|███████▉  | 45612/57600 [8:01:05<2:05:51,  1.59it/s]
 79%|███████▉  | 45613/57600 [8:01:06<2:08:23,  1.56it/s]
 79%|███████▉  | 45614/57600 [8:01:06<2:05:29,  1.59it/s]
 79%|███████▉  | 45615/57600 [8:01:07<2:05:26,  1.59it/s]
 79%|███████▉  | 45616/57600 [8:01:08<2:04:19,  1.61it/s]
 79%|███████▉  | 45617/57600 [8:01:08<2:02:24,  1.63it/s]
 79%|███████▉  | 45618/57600 [8:01:09<2:00:48,  1.65it/s]
 79%|███████▉  | 45619/57600 [8:01:09<2:01:00,  1.65it/s]
 79%|███████▉  | 45620/57600 [8:01:10<2:02:41,  1.63it/s]
                                                         
{'loss': 1.1526, 'learning_rate': 2.878397212543554e-07, 'epoch': 503.53}
+
 79%|███████▉  | 45620/57600 [8:01:10<2:02:41,  1.63it/s]
 79%|███████▉  | 45621/57600 [8:01:11<2:07:37,  1.56it/s]
 79%|███████▉  | 45622/57600 [8:01:11<2:06:03,  1.58it/s]
 79%|███████▉  | 45623/57600 [8:01:12<2:09:27,  1.54it/s]
 79%|███████▉  | 45624/57600 [8:01:13<2:07:17,  1.57it/s]
 79%|███████▉  | 45625/57600 [8:01:13<2:06:50,  1.57it/s]
 79%|███████▉  | 45626/57600 [8:01:14<2:07:37,  1.56it/s]
 79%|███████▉  | 45627/57600 [8:01:15<2:07:57,  1.56it/s]
 79%|███████▉  | 45628/57600 [8:01:15<2:05:36,  1.59it/s]
 79%|███████▉  | 45629/57600 [8:01:16<2:06:28,  1.58it/s]
 79%|███████▉  | 45630/57600 [8:01:17<2:14:51,  1.48it/s]
 79%|███████▉  | 45631/57600 [8:01:17<2:08:35,  1.55it/s]
 79%|███████▉  | 45632/57600 [8:01:18<2:08:23,  1.55it/s]
 79%|███████▉  | 45633/57600 [8:01:19<2:09:40,  1.54it/s]
 79%|███████▉  | 45634/57600 [8:01:19<2:07:20,  1.57it/s]
 79%|███████▉  | 45635/57600 [8:01:20<2:12:21,  1.51it/s]
 79%|███████▉  | 45636/57600 [8:01:20<2:07:16,  1.57it/s]
 79%|███████▉  | 45637/57600 [8:01:21<2:04:31,  1.60it/s]
 79%|███��███▉  | 45638/57600 [8:01:22<2:05:02,  1.59it/s]
 79%|███████▉  | 45639/57600 [8:01:22<2:03:12,  1.62it/s]
 79%|███████▉  | 45640/57600 [8:01:23<2:07:36,  1.56it/s]
                                                         
{'loss': 1.0721, 'learning_rate': 2.875261324041812e-07, 'epoch': 503.75}
+
 79%|███████▉  | 45640/57600 [8:01:23<2:07:36,  1.56it/s]
 79%|███████▉  | 45641/57600 [8:01:24<2:07:02,  1.57it/s]
 79%|███████▉  | 45642/57600 [8:01:24<2:07:06,  1.57it/s]
 79%|███████▉  | 45643/57600 [8:01:25<2:08:18,  1.55it/s]
 79%|███████▉  | 45644/57600 [8:01:26<2:09:10,  1.54it/s]
 79%|███████▉  | 45645/57600 [8:01:26<2:10:10,  1.53it/s]
 79%|███████▉  | 45646/57600 [8:01:27<2:07:02,  1.57it/s]
 79%|███████▉  | 45647/57600 [8:01:27<2:05:34,  1.59it/s]
 79%|███████▉  | 45648/57600 [8:01:28<2:06:07,  1.58it/s]
 79%|███████▉  | 45649/57600 [8:01:29<2:07:30,  1.56it/s]
 79%|███████▉  | 45650/57600 [8:01:29<2:06:10,  1.58it/s]
 79%|███████▉  | 45651/57600 [8:01:30<2:04:35,  1.60it/s]
 79%|███████▉  | 45652/57600 [8:01:31<2:05:08,  1.59it/s]
 79%|███████▉  | 45653/57600 [8:01:31<2:05:00,  1.59it/s]
 79%|███████▉  | 45654/57600 [8:01:32<2:05:37,  1.58it/s]
 79%|███████▉  | 45655/57600 [8:01:32<2:02:49,  1.62it/s]
 79%|███████▉  | 45656/57600 [8:01:33<2:07:08,  1.57it/s]
 79%|███████▉  | 45657/57600 [8:01:34<2:11:35,  1.51it/s]
 79%|███████▉  | 45658/57600 [8:01:34<2:10:40,  1.52it/s]
 79%|███████▉  | 45659/57600 [8:01:35<2:06:33,  1.57it/s]
 79%|███████▉  | 45660/57600 [8:01:36<2:04:04,  1.60it/s]
                                                         
{'loss': 1.0899, 'learning_rate': 2.8721254355400693e-07, 'epoch': 503.97}
+
 79%|███████▉  | 45660/57600 [8:01:36<2:04:04,  1.60it/s]
 79%|███████▉  | 45661/57600 [8:01:36<2:03:54,  1.61it/s]
 79%|███████▉  | 45662/57600 [8:01:37<2:04:55,  1.59it/s]
 79%|███████▉  | 45663/57600 [8:01:38<2:12:18,  1.50it/s]
 79%|███████▉  | 45664/57600 [8:01:38<2:07:10,  1.56it/s]
 79%|███████▉  | 45665/57600 [8:01:39<2:03:52,  1.61it/s]
 79%|███████▉  | 45666/57600 [8:01:39<2:04:11,  1.60it/s]
 79%|███████▉  | 45667/57600 [8:01:40<2:04:16,  1.60it/s]
 79%|███████▉  | 45668/57600 [8:01:41<2:05:12,  1.59it/s]
 79%|███████▉  | 45669/57600 [8:01:41<2:03:53,  1.60it/s]
 79%|███████▉  | 45670/57600 [8:01:42<2:02:00,  1.63it/s]
 79%|███████▉  | 45671/57600 [8:01:43<2:04:00,  1.60it/s]
 79%|███████▉  | 45672/57600 [8:01:43<2:03:42,  1.61it/s]
 79%|███████▉  | 45673/57600 [8:01:44<2:09:03,  1.54it/s]
 79%|███████▉  | 45674/57600 [8:01:45<2:07:04,  1.56it/s]
 79%|███████▉  | 45675/57600 [8:01:45<2:04:35,  1.60it/s]
 79%|███████▉  | 45676/57600 [8:01:46<2:05:13,  1.59it/s]
 79%|███████▉  | 45677/57600 [8:01:46<2:03:52,  1.60it/s]
 79%|███████▉  | 45678/57600 [8:01:47<2:00:38,  1.65it/s]
 79%|███████▉  | 45679/57600 [8:01:48<2:03:42,  1.61it/s]
 79%|███████▉  | 45680/57600 [8:01:48<2:00:08,  1.65it/s]
                                                         
{'loss': 1.1029, 'learning_rate': 2.868989547038328e-07, 'epoch': 504.19}
+
 79%|███████▉  | 45680/57600 [8:01:48<2:00:08,  1.65it/s]
 79%|███████▉  | 45681/57600 [8:01:49<2:04:45,  1.59it/s]
 79%|███████▉  | 45682/57600 [8:01:49<2:04:55,  1.59it/s]
 79%|███████▉  | 45683/57600 [8:01:50<2:05:54,  1.58it/s]
 79%|███████▉  | 45684/57600 [8:01:51<2:03:55,  1.60it/s]
 79%|███████▉  | 45685/57600 [8:01:51<2:04:59,  1.59it/s]
 79%|███████▉  | 45686/57600 [8:01:52<2:08:05,  1.55it/s]
 79%|███████▉  | 45687/57600 [8:01:53<2:09:44,  1.53it/s]
 79%|███████▉  | 45688/57600 [8:01:53<2:07:13,  1.56it/s]
 79%|███████▉  | 45689/57600 [8:01:54<2:07:48,  1.55it/s]
 79%|███████▉  | 45690/57600 [8:01:55<2:04:23,  1.60it/s]
 79%|███████▉  | 45691/57600 [8:01:55<2:02:05,  1.63it/s]
 79%|███████▉  | 45692/57600 [8:01:56<2:05:30,  1.58it/s]
 79%|███████▉  | 45693/57600 [8:01:56<2:00:54,  1.64it/s]
 79%|███████▉  | 45694/57600 [8:01:57<1:58:37,  1.67it/s]
 79%|███████▉  | 45695/57600 [8:01:58<1:57:45,  1.68it/s]
 79%|███████▉  | 45696/57600 [8:01:58<1:58:26,  1.68it/s]
 79%|███████▉  | 45697/57600 [8:01:59<2:00:17,  1.65it/s]
 79%|███████▉  | 45698/57600 [8:01:59<2:00:02,  1.65it/s]
 79%|███████▉  | 45699/57600 [8:02:00<2:00:29,  1.65it/s]
 79%|███████▉  | 45700/57600 [8:02:01<2:03:12,  1.61it/s]
                                                         
{'loss': 1.1579, 'learning_rate': 2.865853658536585e-07, 'epoch': 504.42}
+
 79%|███████▉  | 45700/57600 [8:02:01<2:03:12,  1.61it/s]
 79%|███████▉  | 45701/57600 [8:02:01<2:07:08,  1.56it/s]
 79%|███████▉  | 45702/57600 [8:02:02<2:07:30,  1.56it/s]
 79%|███████▉  | 45703/57600 [8:02:03<2:03:24,  1.61it/s]
 79%|███████▉  | 45704/57600 [8:02:03<2:06:47,  1.56it/s]
 79%|███████▉  | 45705/57600 [8:02:04<2:08:02,  1.55it/s]
 79%|███████▉  | 45706/57600 [8:02:05<2:07:03,  1.56it/s]
 79%|███████▉  | 45707/57600 [8:02:05<2:07:09,  1.56it/s]
 79%|███████▉  | 45708/57600 [8:02:06<2:11:19,  1.51it/s]
 79%|███████▉  | 45709/57600 [8:02:06<2:06:43,  1.56it/s]
 79%|███████▉  | 45710/57600 [8:02:07<2:01:55,  1.63it/s]
 79%|███████▉  | 45711/57600 [8:02:08<2:04:54,  1.59it/s]
 79%|███████▉  | 45712/57600 [8:02:08<2:05:08,  1.58it/s]
 79%|███████▉  | 45713/57600 [8:02:09<2:04:05,  1.60it/s]
 79%|███████▉  | 45714/57600 [8:02:10<2:04:08,  1.60it/s]
 79%|███████▉  | 45715/57600 [8:02:10<2:02:49,  1.61it/s]
 79%|███████▉  | 45716/57600 [8:02:11<1:59:39,  1.66it/s]
 79%|███████▉  | 45717/57600 [8:02:11<2:04:07,  1.60it/s]
 79%|███████▉  | 45718/57600 [8:02:12<2:05:54,  1.57it/s]
 79%|███████▉  | 45719/57600 [8:02:13<2:05:07,  1.58it/s]
 79%|███████▉  | 45720/57600 [8:02:13<2:03:42,  1.60it/s]
                                                         
{'loss': 1.1225, 'learning_rate': 2.862717770034843e-07, 'epoch': 504.64}
+
 79%|███████▉  | 45720/57600 [8:02:13<2:03:42,  1.60it/s]
 79%|███████▉  | 45721/57600 [8:02:14<2:02:50,  1.61it/s]
 79%|███████▉  | 45722/57600 [8:02:15<2:02:16,  1.62it/s]
 79%|███████▉  | 45723/57600 [8:02:15<2:02:37,  1.61it/s]
 79%|███████▉  | 45724/57600 [8:02:16<2:01:10,  1.63it/s]
 79%|███████▉  | 45725/57600 [8:02:16<1:58:57,  1.66it/s]
 79%|███████▉  | 45726/57600 [8:02:17<1:58:41,  1.67it/s]
 79%|███████▉  | 45727/57600 [8:02:18<2:02:08,  1.62it/s]
 79%|███████▉  | 45728/57600 [8:02:18<2:04:04,  1.59it/s]
 79%|███████▉  | 45729/57600 [8:02:19<2:04:38,  1.59it/s]
 79%|███████▉  | 45730/57600 [8:02:20<2:07:41,  1.55it/s]
 79%|███████▉  | 45731/57600 [8:02:20<2:02:58,  1.61it/s]
 79%|███████▉  | 45732/57600 [8:02:21<2:03:18,  1.60it/s]
 79%|███████▉  | 45733/57600 [8:02:21<2:03:54,  1.60it/s]
 79%|███████▉  | 45734/57600 [8:02:22<2:02:33,  1.61it/s]
 79%|███████▉  | 45735/57600 [8:02:23<2:04:01,  1.59it/s]
 79%|███████▉  | 45736/57600 [8:02:23<2:00:29,  1.64it/s]
 79%|███████▉  | 45737/57600 [8:02:24<1:58:29,  1.67it/s]
 79%|███████▉  | 45738/57600 [8:02:24<1:59:46,  1.65it/s]
 79%|███████▉  | 45739/57600 [8:02:25<1:59:39,  1.65it/s]
 79%|███████▉  | 45740/57600 [8:02:26<1:58:43,  1.67it/s]
                                                         
{'loss': 1.1311, 'learning_rate': 2.8595818815331004e-07, 'epoch': 504.86}
+
 79%|███████▉  | 45740/57600 [8:02:26<1:58:43,  1.67it/s]
 79%|███████▉  | 45741/57600 [8:02:26<2:01:15,  1.63it/s]
 79%|███████▉  | 45742/57600 [8:02:27<2:02:21,  1.62it/s]
 79%|███████▉  | 45743/57600 [8:02:28<2:05:04,  1.58it/s]
 79%|███████▉  | 45744/57600 [8:02:28<2:06:32,  1.56it/s]
 79%|███████▉  | 45745/57600 [8:02:29<2:05:50,  1.57it/s]
 79%|███████▉  | 45746/57600 [8:02:30<2:09:19,  1.53it/s]
 79%|███████▉  | 45747/57600 [8:02:30<2:07:05,  1.55it/s]
 79%|███████▉  | 45748/57600 [8:02:31<2:07:35,  1.55it/s]
 79%|███████▉  | 45749/57600 [8:02:31<2:06:33,  1.56it/s]
 79%|███████▉  | 45750/57600 [8:02:32<2:08:02,  1.54it/s]
 79%|███████▉  | 45751/57600 [8:02:33<2:07:24,  1.55it/s]
 79%|███████▉  | 45752/57600 [8:02:33<2:04:23,  1.59it/s]
 79%|███████▉  | 45753/57600 [8:02:34<2:02:52,  1.61it/s]
 79%|███████▉  | 45754/57600 [8:02:35<2:05:34,  1.57it/s]
 79%|███████▉  | 45755/57600 [8:02:35<2:02:19,  1.61it/s]
 79%|███████▉  | 45756/57600 [8:02:36<2:02:28,  1.61it/s]
 79%|███████▉  | 45757/57600 [8:02:36<2:00:08,  1.64it/s]
 79%|███████▉  | 45758/57600 [8:02:37<2:03:28,  1.60it/s]
 79%|███████▉  | 45759/57600 [8:02:38<2:05:53,  1.57it/s]
 79%|███████▉  | 45760/57600 [8:02:38<2:04:59,  1.58it/s]
                                                         
{'loss': 1.1056, 'learning_rate': 2.856445993031359e-07, 'epoch': 505.08}
+
 79%|███████▉  | 45760/57600 [8:02:38<2:04:59,  1.58it/s]
 79%|███████▉  | 45761/57600 [8:02:39<2:06:54,  1.55it/s]
 79%|███████▉  | 45762/57600 [8:02:40<2:07:23,  1.55it/s]
 79%|███████▉  | 45763/57600 [8:02:40<2:03:54,  1.59it/s]
 79%|███████▉  | 45764/57600 [8:02:41<2:01:23,  1.63it/s]
 79%|███████▉  | 45765/57600 [8:02:41<2:00:04,  1.64it/s]
 79%|███████▉  | 45766/57600 [8:02:42<2:01:27,  1.62it/s]
 79%|███████▉  | 45767/57600 [8:02:43<2:03:27,  1.60it/s]
 79%|███████▉  | 45768/57600 [8:02:43<2:00:58,  1.63it/s]
 79%|███████▉  | 45769/57600 [8:02:44<2:05:08,  1.58it/s]
 79%|███████▉  | 45770/57600 [8:02:45<2:02:19,  1.61it/s]
 79%|███████▉  | 45771/57600 [8:02:45<2:05:11,  1.57it/s]
 79%|███████▉  | 45772/57600 [8:02:46<2:03:41,  1.59it/s]
 79%|███████▉  | 45773/57600 [8:02:46<2:02:24,  1.61it/s]
 79%|███████▉  | 45774/57600 [8:02:47<1:59:21,  1.65it/s]
 79%|███████▉  | 45775/57600 [8:02:48<2:04:01,  1.59it/s]
 79%|███████▉  | 45776/57600 [8:02:48<2:07:51,  1.54it/s]
 79%|███████▉  | 45777/57600 [8:02:49<2:04:00,  1.59it/s]
 79%|███████▉  | 45778/57600 [8:02:50<2:02:10,  1.61it/s]
 79%|███████▉  | 45779/57600 [8:02:50<1:58:54,  1.66it/s]
 79%|███████▉  | 45780/57600 [8:02:51<1:59:17,  1.65it/s]
                                                         
{'loss': 1.1246, 'learning_rate': 2.853310104529617e-07, 'epoch': 505.3}
+
 79%|███████▉  | 45780/57600 [8:02:51<1:59:17,  1.65it/s]
 79%|███████▉  | 45781/57600 [8:02:51<1:58:21,  1.66it/s]
 79%|███████▉  | 45782/57600 [8:02:52<1:59:47,  1.64it/s]
 79%|███████▉  | 45783/57600 [8:02:53<2:08:06,  1.54it/s]
 79%|███████▉  | 45784/57600 [8:02:53<2:06:50,  1.55it/s]
 79%|███████▉  | 45785/57600 [8:02:54<2:03:13,  1.60it/s]
 79%|███████▉  | 45786/57600 [8:02:54<1:59:52,  1.64it/s]
 79%|███████▉  | 45787/57600 [8:02:55<2:02:23,  1.61it/s]
 79%|███████▉  | 45788/57600 [8:02:56<2:03:55,  1.59it/s]
 79%|███████▉  | 45789/57600 [8:02:56<2:01:27,  1.62it/s]
 79%|███████▉  | 45790/57600 [8:02:57<2:02:21,  1.61it/s]
 79%|███████▉  | 45791/57600 [8:02:58<2:01:29,  1.62it/s]
 80%|███████▉  | 45792/57600 [8:02:58<2:02:15,  1.61it/s]
 80%|███████▉  | 45793/57600 [8:02:59<2:02:38,  1.60it/s]
 80%|███████▉  | 45794/57600 [8:02:59<2:01:05,  1.62it/s]
 80%|███████▉  | 45795/57600 [8:03:00<2:00:46,  1.63it/s]
 80%|███████▉  | 45796/57600 [8:03:01<1:58:50,  1.66it/s]
 80%|███████▉  | 45797/57600 [8:03:01<2:01:05,  1.62it/s]
 80%|███████▉  | 45798/57600 [8:03:02<2:02:58,  1.60it/s]
 80%|███████▉  | 45799/57600 [8:03:03<2:01:51,  1.61it/s]
 80%|███████▉  | 45800/57600 [8:03:03<2:00:23,  1.63it/s]
                                                         
{'loss': 1.1082, 'learning_rate': 2.850174216027874e-07, 'epoch': 505.52}
+
 80%|███████▉  | 45800/57600 [8:03:03<2:00:23,  1.63it/s]
 80%|███████▉  | 45801/57600 [8:03:04<1:57:42,  1.67it/s]
 80%|███████▉  | 45802/57600 [8:03:04<2:03:15,  1.60it/s]
 80%|███████▉  | 45803/57600 [8:03:05<2:00:59,  1.63it/s]
 80%|███████▉  | 45804/57600 [8:03:06<1:58:34,  1.66it/s]
 80%|███████▉  | 45805/57600 [8:03:06<2:02:30,  1.60it/s]
 80%|███████▉  | 45806/57600 [8:03:07<2:00:34,  1.63it/s]
 80%|███████▉  | 45807/57600 [8:03:07<2:01:57,  1.61it/s]
 80%|███████▉  | 45808/57600 [8:03:08<2:02:09,  1.61it/s]
 80%|███████▉  | 45809/57600 [8:03:09<2:05:25,  1.57it/s]
 80%|███████▉  | 45810/57600 [8:03:10<2:16:28,  1.44it/s]
 80%|███████▉  | 45811/57600 [8:03:10<2:12:50,  1.48it/s]
 80%|███████▉  | 45812/57600 [8:03:11<2:11:40,  1.49it/s]
 80%|███████▉  | 45813/57600 [8:03:11<2:08:35,  1.53it/s]
 80%|███████▉  | 45814/57600 [8:03:12<2:07:38,  1.54it/s]
 80%|███████▉  | 45815/57600 [8:03:13<2:05:12,  1.57it/s]
 80%|███████▉  | 45816/57600 [8:03:13<2:01:14,  1.62it/s]
 80%|███████▉  | 45817/57600 [8:03:14<2:01:32,  1.62it/s]
 80%|███████▉  | 45818/57600 [8:03:15<2:01:34,  1.62it/s]
 80%|███████▉  | 45819/57600 [8:03:15<2:00:34,  1.63it/s]
 80%|███████▉  | 45820/57600 [8:03:16<2:02:55,  1.60it/s]
                                                         
{'loss': 1.1291, 'learning_rate': 2.8470383275261326e-07, 'epoch': 505.74}
+
 80%|███████▉  | 45820/57600 [8:03:16<2:02:55,  1.60it/s]
 80%|███████▉  | 45821/57600 [8:03:16<2:05:00,  1.57it/s]
 80%|███████▉  | 45822/57600 [8:03:17<2:04:53,  1.57it/s]
 80%|███████▉  | 45823/57600 [8:03:18<2:04:45,  1.57it/s]
 80%|███████▉  | 45824/57600 [8:03:18<2:03:00,  1.60it/s]
 80%|███████▉  | 45825/57600 [8:03:19<2:03:57,  1.58it/s]
 80%|███████▉  | 45826/57600 [8:03:20<2:05:51,  1.56it/s]
 80%|███████▉  | 45827/57600 [8:03:20<2:07:19,  1.54it/s]
 80%|███████▉  | 45828/57600 [8:03:21<2:03:39,  1.59it/s]
 80%|███████▉  | 45829/57600 [8:03:22<2:05:14,  1.57it/s]
 80%|███████▉  | 45830/57600 [8:03:22<2:06:18,  1.55it/s]
 80%|███████▉  | 45831/57600 [8:03:23<2:05:52,  1.56it/s]
 80%|███████▉  | 45832/57600 [8:03:23<2:03:48,  1.58it/s]
 80%|███████▉  | 45833/57600 [8:03:24<2:03:16,  1.59it/s]
 80%|███████▉  | 45834/57600 [8:03:25<2:07:19,  1.54it/s]
 80%|███████▉  | 45835/57600 [8:03:25<2:04:34,  1.57it/s]
 80%|███████▉  | 45836/57600 [8:03:26<2:09:34,  1.51it/s]
 80%|███████▉  | 45837/57600 [8:03:27<2:05:01,  1.57it/s]
 80%|███████▉  | 45838/57600 [8:03:27<2:05:51,  1.56it/s]
 80%|███████▉  | 45839/57600 [8:03:28<2:09:12,  1.52it/s]
 80%|███████▉  | 45840/57600 [8:03:29<2:05:45,  1.56it/s]
                                                         
{'loss': 1.1112, 'learning_rate': 2.8439024390243896e-07, 'epoch': 505.96}
+
 80%|███████▉  | 45840/57600 [8:03:29<2:05:45,  1.56it/s]
 80%|███████▉  | 45841/57600 [8:03:29<2:04:15,  1.58it/s]
 80%|███████▉  | 45842/57600 [8:03:30<2:11:05,  1.49it/s]
 80%|███████▉  | 45843/57600 [8:03:31<2:10:00,  1.51it/s]
 80%|███████▉  | 45844/57600 [8:03:31<2:10:34,  1.50it/s]
 80%|███████▉  | 45845/57600 [8:03:32<2:08:26,  1.53it/s]
 80%|███████▉  | 45846/57600 [8:03:33<2:08:30,  1.52it/s]
 80%|███████▉  | 45847/57600 [8:03:33<2:06:28,  1.55it/s]
 80%|███████▉  | 45848/57600 [8:03:34<2:08:48,  1.52it/s]
 80%|███████▉  | 45849/57600 [8:03:35<2:05:20,  1.56it/s]
 80%|███████▉  | 45850/57600 [8:03:35<2:01:06,  1.62it/s]
 80%|███████▉  | 45851/57600 [8:03:36<2:03:44,  1.58it/s]
 80%|███████▉  | 45852/57600 [8:03:36<2:04:45,  1.57it/s]
 80%|███████▉  | 45853/57600 [8:03:37<2:08:03,  1.53it/s]
 80%|███████▉  | 45854/57600 [8:03:38<2:02:22,  1.60it/s]
 80%|███████▉  | 45855/57600 [8:03:38<2:01:39,  1.61it/s]
 80%|███████▉  | 45856/57600 [8:03:39<1:59:31,  1.64it/s]
 80%|███████▉  | 45857/57600 [8:03:39<2:01:27,  1.61it/s]
 80%|███████▉  | 45858/57600 [8:03:40<2:03:53,  1.58it/s]
 80%|███████▉  | 45859/57600 [8:03:41<1:59:42,  1.63it/s]
 80%|███████▉  | 45860/57600 [8:03:41<2:01:53,  1.61it/s]
                                                         
{'loss': 1.118, 'learning_rate': 2.8407665505226477e-07, 'epoch': 506.18}
+
 80%|███████▉  | 45860/57600 [8:03:41<2:01:53,  1.61it/s]
 80%|███████▉  | 45861/57600 [8:03:42<2:03:30,  1.58it/s]
 80%|███████▉  | 45862/57600 [8:03:43<2:03:19,  1.59it/s]
 80%|███████▉  | 45863/57600 [8:03:43<2:02:05,  1.60it/s]
 80%|███████▉  | 45864/57600 [8:03:44<2:04:01,  1.58it/s]
 80%|███████▉  | 45865/57600 [8:03:44<1:59:31,  1.64it/s]
 80%|███████▉  | 45866/57600 [8:03:45<1:59:25,  1.64it/s]
 80%|███████▉  | 45867/57600 [8:03:46<2:01:53,  1.60it/s]
 80%|███████▉  | 45868/57600 [8:03:46<2:06:44,  1.54it/s]
 80%|███████▉  | 45869/57600 [8:03:47<2:08:44,  1.52it/s]
 80%|███████▉  | 45870/57600 [8:03:48<2:07:16,  1.54it/s]
 80%|███████▉  | 45871/57600 [8:03:48<2:04:23,  1.57it/s]
 80%|███████▉  | 45872/57600 [8:03:49<2:01:47,  1.60it/s]
 80%|███████▉  | 45873/57600 [8:03:50<2:00:32,  1.62it/s]
 80%|███████▉  | 45874/57600 [8:03:50<1:59:20,  1.64it/s]
 80%|███████▉  | 45875/57600 [8:03:51<1:58:03,  1.66it/s]
 80%|███████▉  | 45876/57600 [8:03:51<2:03:36,  1.58it/s]
 80%|███████▉  | 45877/57600 [8:03:52<2:04:08,  1.57it/s]
 80%|███████▉  | 45878/57600 [8:03:53<2:00:21,  1.62it/s]
 80%|███████▉  | 45879/57600 [8:03:53<2:03:01,  1.59it/s]
 80%|███████▉  | 45880/57600 [8:03:54<2:00:54,  1.62it/s]
                                                         
{'loss': 1.1045, 'learning_rate': 2.837630662020906e-07, 'epoch': 506.4}
+
 80%|███████▉  | 45880/57600 [8:03:54<2:00:54,  1.62it/s]
 80%|███████▉  | 45881/57600 [8:03:55<1:59:48,  1.63it/s]
 80%|███████▉  | 45882/57600 [8:03:55<2:03:43,  1.58it/s]
 80%|███████▉  | 45883/57600 [8:03:56<2:08:20,  1.52it/s]
 80%|███████▉  | 45884/57600 [8:03:57<2:07:28,  1.53it/s]
 80%|███████▉  | 45885/57600 [8:03:57<2:04:25,  1.57it/s]
 80%|███████▉  | 45886/57600 [8:03:58<2:05:27,  1.56it/s]
 80%|███████▉  | 45887/57600 [8:03:58<2:04:10,  1.57it/s]
 80%|███████▉  | 45888/57600 [8:03:59<2:03:18,  1.58it/s]
 80%|███████▉  | 45889/57600 [8:04:00<2:03:16,  1.58it/s]
 80%|███████▉  | 45890/57600 [8:04:00<2:03:42,  1.58it/s]
 80%|███████▉  | 45891/57600 [8:04:01<2:05:30,  1.55it/s]
 80%|███████▉  | 45892/57600 [8:04:02<2:05:42,  1.55it/s]
 80%|███████▉  | 45893/57600 [8:04:02<2:02:12,  1.60it/s]
 80%|███████▉  | 45894/57600 [8:04:03<2:01:36,  1.60it/s]
 80%|███████▉  | 45895/57600 [8:04:03<2:01:44,  1.60it/s]
 80%|███████▉  | 45896/57600 [8:04:04<2:02:15,  1.60it/s]
 80%|███████▉  | 45897/57600 [8:04:05<1:58:51,  1.64it/s]
 80%|███████▉  | 45898/57600 [8:04:05<1:58:16,  1.65it/s]
 80%|███████▉  | 45899/57600 [8:04:06<2:00:59,  1.61it/s]
 80%|███████▉  | 45900/57600 [8:04:07<2:01:51,  1.60it/s]
                                                         
{'loss': 1.1366, 'learning_rate': 2.834494773519164e-07, 'epoch': 506.62}
+
 80%|███████▉  | 45900/57600 [8:04:07<2:01:51,  1.60it/s]
 80%|███████▉  | 45901/57600 [8:04:07<2:04:58,  1.56it/s]
 80%|███████▉  | 45902/57600 [8:04:08<2:02:06,  1.60it/s]
 80%|███████▉  | 45903/57600 [8:04:08<2:04:28,  1.57it/s]
 80%|███████▉  | 45904/57600 [8:04:09<2:01:59,  1.60it/s]
 80%|███████▉  | 45905/57600 [8:04:10<2:01:43,  1.60it/s]
 80%|███████▉  | 45906/57600 [8:04:10<1:59:07,  1.64it/s]
 80%|███████▉  | 45907/57600 [8:04:11<2:03:20,  1.58it/s]
 80%|███████▉  | 45908/57600 [8:04:12<2:06:40,  1.54it/s]
 80%|███████▉  | 45909/57600 [8:04:12<2:03:43,  1.57it/s]
 80%|███████▉  | 45910/57600 [8:04:13<2:05:43,  1.55it/s]
 80%|███████▉  | 45911/57600 [8:04:13<2:01:59,  1.60it/s]
 80%|███████▉  | 45912/57600 [8:04:14<2:03:34,  1.58it/s]
 80%|███████▉  | 45913/57600 [8:04:15<2:04:49,  1.56it/s]
 80%|███████▉  | 45914/57600 [8:04:15<2:02:04,  1.60it/s]
 80%|███████▉  | 45915/57600 [8:04:16<2:05:18,  1.55it/s]
 80%|███████▉  | 45916/57600 [8:04:17<2:02:14,  1.59it/s]
 80%|███████▉  | 45917/57600 [8:04:17<1:58:50,  1.64it/s]
 80%|███████▉  | 45918/57600 [8:04:18<1:58:49,  1.64it/s]
 80%|███████▉  | 45919/57600 [8:04:18<1:59:57,  1.62it/s]
 80%|███████▉  | 45920/57600 [8:04:19<2:02:14,  1.59it/s]
                                                         
{'loss': 1.1639, 'learning_rate': 2.831358885017422e-07, 'epoch': 506.84}
+
 80%|███████▉  | 45920/57600 [8:04:19<2:02:14,  1.59it/s]
 80%|███████▉  | 45921/57600 [8:04:20<2:04:48,  1.56it/s]
 80%|███████▉  | 45922/57600 [8:04:20<2:03:48,  1.57it/s]
 80%|███████▉  | 45923/57600 [8:04:21<2:01:44,  1.60it/s]
 80%|███████▉  | 45924/57600 [8:04:22<2:00:21,  1.62it/s]
 80%|███████▉  | 45925/57600 [8:04:22<2:05:21,  1.55it/s]
 80%|███████▉  | 45926/57600 [8:04:23<2:01:27,  1.60it/s]
 80%|███████▉  | 45927/57600 [8:04:24<1:59:56,  1.62it/s]
 80%|███████▉  | 45928/57600 [8:04:24<2:03:51,  1.57it/s]
 80%|███████▉  | 45929/57600 [8:04:25<2:02:53,  1.58it/s]
 80%|███████▉  | 45930/57600 [8:04:25<2:01:13,  1.60it/s]
 80%|███████▉  | 45931/57600 [8:04:26<1:59:19,  1.63it/s]
 80%|███████▉  | 45932/57600 [8:04:27<1:56:42,  1.67it/s]
 80%|███████▉  | 45933/57600 [8:04:27<2:01:13,  1.60it/s]
 80%|███████▉  | 45934/57600 [8:04:28<1:58:38,  1.64it/s]
 80%|███████▉  | 45935/57600 [8:04:29<2:03:06,  1.58it/s]
 80%|███████▉  | 45936/57600 [8:04:29<2:00:26,  1.61it/s]
 80%|███████▉  | 45937/57600 [8:04:30<1:56:29,  1.67it/s]
 80%|███████▉  | 45938/57600 [8:04:30<1:59:50,  1.62it/s]
 80%|███████▉  | 45939/57600 [8:04:31<1:56:25,  1.67it/s]
 80%|███████▉  | 45940/57600 [8:04:32<1:58:45,  1.64it/s]
                                                         
{'loss': 1.1473, 'learning_rate': 2.828222996515679e-07, 'epoch': 507.06}
+
 80%|███████▉  | 45940/57600 [8:04:32<1:58:45,  1.64it/s]
 80%|███████▉  | 45941/57600 [8:04:32<1:56:44,  1.66it/s]
 80%|███████▉  | 45942/57600 [8:04:33<1:57:08,  1.66it/s]
 80%|███████▉  | 45943/57600 [8:04:33<1:55:18,  1.68it/s]
 80%|███████▉  | 45944/57600 [8:04:34<1:59:02,  1.63it/s]
 80%|███████▉  | 45945/57600 [8:04:35<1:59:06,  1.63it/s]
 80%|███████▉  | 45946/57600 [8:04:35<1:57:26,  1.65it/s]
 80%|███████▉  | 45947/57600 [8:04:36<1:58:46,  1.64it/s]
 80%|███████▉  | 45948/57600 [8:04:36<1:56:43,  1.66it/s]
 80%|███████▉  | 45949/57600 [8:04:37<1:57:11,  1.66it/s]
 80%|███████▉  | 45950/57600 [8:04:38<2:04:31,  1.56it/s]
 80%|███████▉  | 45951/57600 [8:04:38<2:02:40,  1.58it/s]
 80%|███████▉  | 45952/57600 [8:04:39<2:03:26,  1.57it/s]
 80%|███████▉  | 45953/57600 [8:04:39<1:59:10,  1.63it/s]
 80%|███████▉  | 45954/57600 [8:04:40<1:59:29,  1.62it/s]
 80%|███████▉  | 45955/57600 [8:04:41<2:04:00,  1.56it/s]
 80%|███████▉  | 45956/57600 [8:04:41<1:59:20,  1.63it/s]
 80%|███████▉  | 45957/57600 [8:04:42<1:58:26,  1.64it/s]
 80%|███████▉  | 45958/57600 [8:04:43<2:00:49,  1.61it/s]
 80%|███████▉  | 45959/57600 [8:04:43<2:01:23,  1.60it/s]
 80%|███████▉  | 45960/57600 [8:04:44<2:00:03,  1.62it/s]
                                                         
{'loss': 1.1251, 'learning_rate': 2.8250871080139374e-07, 'epoch': 507.28}
+
 80%|███████▉  | 45960/57600 [8:04:44<2:00:03,  1.62it/s]
 80%|███████▉  | 45961/57600 [8:04:45<2:05:07,  1.55it/s]
 80%|███████▉  | 45962/57600 [8:04:45<2:08:15,  1.51it/s]
 80%|███████▉  | 45963/57600 [8:04:46<2:03:59,  1.56it/s]
 80%|███████▉  | 45964/57600 [8:04:47<2:05:12,  1.55it/s]
 80%|███████▉  | 45965/57600 [8:04:47<2:03:58,  1.56it/s]
 80%|███████▉  | 45966/57600 [8:04:48<2:03:30,  1.57it/s]
 80%|███████▉  | 45967/57600 [8:04:48<2:01:56,  1.59it/s]
 80%|███████▉  | 45968/57600 [8:04:49<2:01:10,  1.60it/s]
 80%|███████▉  | 45969/57600 [8:04:50<2:03:00,  1.58it/s]
 80%|███████▉  | 45970/57600 [8:04:50<2:04:04,  1.56it/s]
 80%|███████▉  | 45971/57600 [8:04:51<2:01:39,  1.59it/s]
 80%|███████▉  | 45972/57600 [8:04:51<1:59:48,  1.62it/s]
 80%|███████▉  | 45973/57600 [8:04:52<2:01:23,  1.60it/s]
 80%|███████▉  | 45974/57600 [8:04:53<1:59:17,  1.62it/s]
 80%|███████▉  | 45975/57600 [8:04:53<2:01:22,  1.60it/s]
 80%|███████▉  | 45976/57600 [8:04:54<2:06:59,  1.53it/s]
 80%|███████▉  | 45977/57600 [8:04:55<2:07:15,  1.52it/s]
 80%|███████▉  | 45978/57600 [8:04:55<2:06:22,  1.53it/s]
 80%|███████▉  | 45979/57600 [8:04:56<2:08:01,  1.51it/s]
 80%|███████▉  | 45980/57600 [8:04:57<2:06:06,  1.54it/s]
                                                         
{'loss': 1.0948, 'learning_rate': 2.821951219512195e-07, 'epoch': 507.51}
+
 80%|███████▉  | 45980/57600 [8:04:57<2:06:06,  1.54it/s]
 80%|███████▉  | 45981/57600 [8:04:57<2:09:11,  1.50it/s]
 80%|███████▉  | 45982/57600 [8:04:58<2:09:27,  1.50it/s]
 80%|███████▉  | 45983/57600 [8:04:59<2:04:30,  1.56it/s]
 80%|███████▉  | 45984/57600 [8:04:59<2:02:19,  1.58it/s]
 80%|███████▉  | 45985/57600 [8:05:00<2:02:23,  1.58it/s]
 80%|███████▉  | 45986/57600 [8:05:01<2:00:12,  1.61it/s]
 80%|███████▉  | 45987/57600 [8:05:01<1:56:15,  1.66it/s]
 80%|███████▉  | 45988/57600 [8:05:02<2:02:14,  1.58it/s]
 80%|███████▉  | 45989/57600 [8:05:02<1:57:52,  1.64it/s]
 80%|███████▉  | 45990/57600 [8:05:03<2:01:10,  1.60it/s]
 80%|███████▉  | 45991/57600 [8:05:04<2:05:23,  1.54it/s]
 80%|███████▉  | 45992/57600 [8:05:04<2:01:58,  1.59it/s]
 80%|███████▉  | 45993/57600 [8:05:05<1:57:39,  1.64it/s]
 80%|███████▉  | 45994/57600 [8:05:06<2:01:10,  1.60it/s]
 80%|███████▉  | 45995/57600 [8:05:06<2:01:23,  1.59it/s]
 80%|███████▉  | 45996/57600 [8:05:07<1:59:06,  1.62it/s]
 80%|███████▉  | 45997/57600 [8:05:07<2:01:04,  1.60it/s]
 80%|███████▉  | 45998/57600 [8:05:08<1:59:46,  1.61it/s]
 80%|███████▉  | 45999/57600 [8:05:09<2:04:25,  1.55it/s]
 80%|███████▉  | 46000/57600 [8:05:09<1:59:30,  1.62it/s]
                                                         
{'loss': 1.1439, 'learning_rate': 2.818815331010453e-07, 'epoch': 507.73}
+
 80%|███████▉  | 46000/57600 [8:05:09<1:59:30,  1.62it/s]
 80%|███████▉  | 46001/57600 [8:05:10<1:58:22,  1.63it/s]
 80%|███████▉  | 46002/57600 [8:05:10<1:55:30,  1.67it/s]
 80%|███████▉  | 46003/57600 [8:05:11<1:57:50,  1.64it/s]
 80%|███████▉  | 46004/57600 [8:05:12<2:03:09,  1.57it/s]
 80%|███████▉  | 46005/57600 [8:05:12<2:00:39,  1.60it/s]
 80%|███████▉  | 46006/57600 [8:05:13<1:58:19,  1.63it/s]
 80%|███████▉  | 46007/57600 [8:05:14<1:56:56,  1.65it/s]
 80%|███████▉  | 46008/57600 [8:05:14<1:57:17,  1.65it/s]
 80%|███████▉  | 46009/57600 [8:05:15<1:57:40,  1.64it/s]
 80%|███████▉  | 46010/57600 [8:05:15<1:56:20,  1.66it/s]
 80%|███████▉  | 46011/57600 [8:05:16<1:56:44,  1.65it/s]
 80%|███████▉  | 46012/57600 [8:05:17<1:59:46,  1.61it/s]
 80%|███████▉  | 46013/57600 [8:05:17<2:03:52,  1.56it/s]
 80%|███████▉  | 46014/57600 [8:05:18<2:00:41,  1.60it/s]
 80%|███████▉  | 46015/57600 [8:05:18<1:59:39,  1.61it/s]
 80%|███████▉  | 46016/57600 [8:05:19<1:58:43,  1.63it/s]
 80%|███████▉  | 46017/57600 [8:05:20<2:00:16,  1.61it/s]
 80%|███████▉  | 46018/57600 [8:05:20<1:57:18,  1.65it/s]
 80%|███████▉  | 46019/57600 [8:05:21<2:05:40,  1.54it/s]
 80%|███████▉  | 46020/57600 [8:05:22<2:03:57,  1.56it/s]
                                                         
{'loss': 1.148, 'learning_rate': 2.815679442508711e-07, 'epoch': 507.95}
+
 80%|███████▉  | 46020/57600 [8:05:22<2:03:57,  1.56it/s]
 80%|███████▉  | 46021/57600 [8:05:22<1:59:04,  1.62it/s]
 80%|███████▉  | 46022/57600 [8:05:23<2:04:23,  1.55it/s]
 80%|███████▉  | 46023/57600 [8:05:24<2:03:26,  1.56it/s]
 80%|███████▉  | 46024/57600 [8:05:24<2:03:39,  1.56it/s]
 80%|███████▉  | 46025/57600 [8:05:25<2:04:59,  1.54it/s]
 80%|███████▉  | 46026/57600 [8:05:26<2:05:15,  1.54it/s]
 80%|███████▉  | 46027/57600 [8:05:26<2:07:16,  1.52it/s]
 80%|███████▉  | 46028/57600 [8:05:27<2:06:53,  1.52it/s]
 80%|███████▉  | 46029/57600 [8:05:27<2:03:52,  1.56it/s]
 80%|███████▉  | 46030/57600 [8:05:28<2:05:55,  1.53it/s]
 80%|███████▉  | 46031/57600 [8:05:29<2:03:13,  1.56it/s]
 80%|███████▉  | 46032/57600 [8:05:29<1:59:55,  1.61it/s]
 80%|███████▉  | 46033/57600 [8:05:30<1:59:24,  1.61it/s]
 80%|███████▉  | 46034/57600 [8:05:31<1:58:42,  1.62it/s]
 80%|███████▉  | 46035/57600 [8:05:31<2:01:36,  1.59it/s]
 80%|███████▉  | 46036/57600 [8:05:32<2:01:17,  1.59it/s]
 80%|███████▉  | 46037/57600 [8:05:32<2:02:01,  1.58it/s]
 80%|███████▉  | 46038/57600 [8:05:33<1:59:27,  1.61it/s]
 80%|███████▉  | 46039/57600 [8:05:34<2:02:55,  1.57it/s]
 80%|███████▉  | 46040/57600 [8:05:34<2:03:40,  1.56it/s]
                                                         
{'loss': 1.1106, 'learning_rate': 2.8125435540069685e-07, 'epoch': 508.17}
+
 80%|███████▉  | 46040/57600 [8:05:34<2:03:40,  1.56it/s]
 80%|███████▉  | 46041/57600 [8:05:35<2:06:05,  1.53it/s]
 80%|███████▉  | 46042/57600 [8:05:36<2:05:40,  1.53it/s]
 80%|███████▉  | 46043/57600 [8:05:36<2:03:55,  1.55it/s]
 80%|███████▉  | 46044/57600 [8:05:37<2:03:19,  1.56it/s]
 80%|███████▉  | 46045/57600 [8:05:38<2:02:56,  1.57it/s]
 80%|███████▉  | 46046/57600 [8:05:38<2:00:24,  1.60it/s]
 80%|███████▉  | 46047/57600 [8:05:39<1:58:06,  1.63it/s]
 80%|███████▉  | 46048/57600 [8:05:39<1:58:57,  1.62it/s]
 80%|███████▉  | 46049/57600 [8:05:40<2:01:13,  1.59it/s]
 80%|███████▉  | 46050/57600 [8:05:41<1:59:28,  1.61it/s]
 80%|███████▉  | 46051/57600 [8:05:41<2:02:01,  1.58it/s]
 80%|███████▉  | 46052/57600 [8:05:42<2:02:19,  1.57it/s]
 80%|███████▉  | 46053/57600 [8:05:43<2:06:37,  1.52it/s]
 80%|███████▉  | 46054/57600 [8:05:43<2:02:41,  1.57it/s]
 80%|███████▉  | 46055/57600 [8:05:44<2:08:33,  1.50it/s]
 80%|███████▉  | 46056/57600 [8:05:45<2:05:54,  1.53it/s]
 80%|███████▉  | 46057/57600 [8:05:45<1:59:46,  1.61it/s]
 80%|███████▉  | 46058/57600 [8:05:46<1:59:22,  1.61it/s]
 80%|███████▉  | 46059/57600 [8:05:46<1:58:40,  1.62it/s]
 80%|███████▉  | 46060/57600 [8:05:47<1:58:11,  1.63it/s]
                                                         
{'loss': 1.1169, 'learning_rate': 2.8094076655052266e-07, 'epoch': 508.39}
+
 80%|███████▉  | 46060/57600 [8:05:47<1:58:11,  1.63it/s]
 80%|███████▉  | 46061/57600 [8:05:48<2:00:15,  1.60it/s]
 80%|███████▉  | 46062/57600 [8:05:48<1:58:56,  1.62it/s]
 80%|███████▉  | 46063/57600 [8:05:49<1:57:13,  1.64it/s]
 80%|███████▉  | 46064/57600 [8:05:49<1:54:24,  1.68it/s]
 80%|███████▉  | 46065/57600 [8:05:50<2:03:13,  1.56it/s]
 80%|███████▉  | 46066/57600 [8:05:51<2:00:45,  1.59it/s]
 80%|███████▉  | 46067/57600 [8:05:51<2:01:05,  1.59it/s]
 80%|███████▉  | 46068/57600 [8:05:52<1:59:57,  1.60it/s]
 80%|███████▉  | 46069/57600 [8:05:53<1:56:08,  1.65it/s]
 80%|███████▉  | 46070/57600 [8:05:53<2:01:03,  1.59it/s]
 80%|███████▉  | 46071/57600 [8:05:54<2:02:08,  1.57it/s]
 80%|███████▉  | 46072/57600 [8:05:55<1:58:25,  1.62it/s]
 80%|███████▉  | 46073/57600 [8:05:55<1:57:28,  1.64it/s]
 80%|███████▉  | 46074/57600 [8:05:56<1:56:57,  1.64it/s]
 80%|███████▉  | 46075/57600 [8:05:56<1:58:29,  1.62it/s]
 80%|███████▉  | 46076/57600 [8:05:57<1:58:45,  1.62it/s]
 80%|███████▉  | 46077/57600 [8:05:58<2:02:29,  1.57it/s]
 80%|███████▉  | 46078/57600 [8:05:58<1:59:06,  1.61it/s]
 80%|███████▉  | 46079/57600 [8:05:59<2:00:16,  1.60it/s]
 80%|████████  | 46080/57600 [8:06:00<2:04:34,  1.54it/s]
                                                         
{'loss': 1.1067, 'learning_rate': 2.806271777003484e-07, 'epoch': 508.61}
+
 80%|████████  | 46080/57600 [8:06:00<2:04:34,  1.54it/s]
 80%|████████  | 46081/57600 [8:06:00<2:06:14,  1.52it/s]
 80%|████████  | 46082/57600 [8:06:01<2:02:13,  1.57it/s]
 80%|████████  | 46083/57600 [8:06:02<2:04:36,  1.54it/s]
 80%|████████  | 46084/57600 [8:06:02<2:00:43,  1.59it/s]
 80%|████████  | 46085/57600 [8:06:03<1:57:06,  1.64it/s]
 80%|████████  | 46086/57600 [8:06:03<2:02:39,  1.56it/s]
 80%|████████  | 46087/57600 [8:06:04<2:02:15,  1.57it/s]
 80%|████████  | 46088/57600 [8:06:05<2:02:52,  1.56it/s]
 80%|████████  | 46089/57600 [8:06:05<2:01:29,  1.58it/s]
 80%|████████  | 46090/57600 [8:06:06<2:01:13,  1.58it/s]
 80%|████████  | 46091/57600 [8:06:07<2:00:06,  1.60it/s]
 80%|████████  | 46092/57600 [8:06:07<1:58:57,  1.61it/s]
 80%|████████  | 46093/57600 [8:06:08<2:00:50,  1.59it/s]
 80%|████████  | 46094/57600 [8:06:08<1:57:03,  1.64it/s]
 80%|████████  | 46095/57600 [8:06:09<1:58:10,  1.62it/s]
 80%|████████  | 46096/57600 [8:06:10<2:04:19,  1.54it/s]
 80%|████████  | 46097/57600 [8:06:10<2:00:30,  1.59it/s]
 80%|████████  | 46098/57600 [8:06:11<2:00:46,  1.59it/s]
 80%|████████  | 46099/57600 [8:06:11<1:58:21,  1.62it/s]
 80%|████████  | 46100/57600 [8:06:12<1:58:24,  1.62it/s]
                                                         
{'loss': 1.1447, 'learning_rate': 2.803135888501742e-07, 'epoch': 508.83}
+
 80%|████████  | 46100/57600 [8:06:12<1:58:24,  1.62it/s]
 80%|████████  | 46101/57600 [8:06:13<2:00:05,  1.60it/s]
 80%|████████  | 46102/57600 [8:06:13<2:04:40,  1.54it/s]
 80%|████████  | 46103/57600 [8:06:14<2:03:23,  1.55it/s]
 80%|████████  | 46104/57600 [8:06:15<1:58:40,  1.61it/s]
 80%|████████  | 46105/57600 [8:06:15<2:00:25,  1.59it/s]
 80%|████████  | 46106/57600 [8:06:16<2:03:13,  1.55it/s]
 80%|████████  | 46107/57600 [8:06:17<2:01:59,  1.57it/s]
 80%|████████  | 46108/57600 [8:06:17<2:00:57,  1.58it/s]
 80%|████████  | 46109/57600 [8:06:18<2:00:43,  1.59it/s]
 80%|████████  | 46110/57600 [8:06:18<2:00:11,  1.59it/s]
 80%|████████  | 46111/57600 [8:06:19<2:00:12,  1.59it/s]
 80%|████████  | 46112/57600 [8:06:20<1:59:13,  1.61it/s]
 80%|████████  | 46113/57600 [8:06:20<2:00:21,  1.59it/s]
 80%|████████  | 46114/57600 [8:06:21<2:04:40,  1.54it/s]
 80%|████████  | 46115/57600 [8:06:22<2:07:23,  1.50it/s]
 80%|████████  | 46116/57600 [8:06:22<2:10:48,  1.46it/s]
 80%|████████  | 46117/57600 [8:06:23<2:08:35,  1.49it/s]
 80%|████████  | 46118/57600 [8:06:24<2:04:49,  1.53it/s]
 80%|████████  | 46119/57600 [8:06:24<2:00:41,  1.59it/s]
 80%|████████  | 46120/57600 [8:06:25<1:58:54,  1.61it/s]
                                                         
{'loss': 1.121, 'learning_rate': 2.7999999999999997e-07, 'epoch': 509.05}
+
 80%|████████  | 46120/57600 [8:06:25<1:58:54,  1.61it/s]
 80%|████████  | 46121/57600 [8:06:26<1:59:43,  1.60it/s]
 80%|████████  | 46122/57600 [8:06:26<1:59:01,  1.61it/s]
 80%|████████  | 46123/57600 [8:06:27<1:59:18,  1.60it/s]
 80%|████████  | 46124/57600 [8:06:27<1:59:50,  1.60it/s]
 80%|████████  | 46125/57600 [8:06:28<2:00:37,  1.59it/s]
 80%|████████  | 46126/57600 [8:06:29<1:57:36,  1.63it/s]
 80%|████████  | 46127/57600 [8:06:29<1:57:29,  1.63it/s]
 80%|████████  | 46128/57600 [8:06:30<1:56:15,  1.64it/s]
 80%|████████  | 46129/57600 [8:06:30<1:57:39,  1.62it/s]
 80%|████████  | 46130/57600 [8:06:31<1:56:51,  1.64it/s]
 80%|████████  | 46131/57600 [8:06:32<1:57:30,  1.63it/s]
 80%|████████  | 46132/57600 [8:06:32<1:59:36,  1.60it/s]
 80%|████████  | 46133/57600 [8:06:33<1:58:54,  1.61it/s]
 80%|████████  | 46134/57600 [8:06:34<1:57:27,  1.63it/s]
 80%|████████  | 46135/57600 [8:06:34<1:59:18,  1.60it/s]
 80%|████████  | 46136/57600 [8:06:35<2:01:10,  1.58it/s]
 80%|████████  | 46137/57600 [8:06:36<2:03:26,  1.55it/s]
 80%|████████  | 46138/57600 [8:06:36<2:01:12,  1.58it/s]
 80%|████████  | 46139/57600 [8:06:37<2:00:16,  1.59it/s]
 80%|████████  | 46140/57600 [8:06:37<1:56:36,  1.64it/s]
                                                         
{'loss': 1.1101, 'learning_rate': 2.7968641114982577e-07, 'epoch': 509.27}
+
 80%|████████  | 46140/57600 [8:06:37<1:56:36,  1.64it/s]
 80%|████████  | 46141/57600 [8:06:38<1:54:17,  1.67it/s]
 80%|████████  | 46142/57600 [8:06:38<1:52:58,  1.69it/s]
 80%|████████  | 46143/57600 [8:06:39<1:55:43,  1.65it/s]
 80%|████████  | 46144/57600 [8:06:40<1:54:56,  1.66it/s]
 80%|████████  | 46145/57600 [8:06:40<1:56:29,  1.64it/s]
 80%|████████  | 46146/57600 [8:06:41<1:57:50,  1.62it/s]
 80%|████████  | 46147/57600 [8:06:42<1:59:21,  1.60it/s]
 80%|████████  | 46148/57600 [8:06:42<1:58:52,  1.61it/s]
 80%|████████  | 46149/57600 [8:06:43<1:58:33,  1.61it/s]
 80%|████████  | 46150/57600 [8:06:44<2:03:48,  1.54it/s]
 80%|████████  | 46151/57600 [8:06:44<2:01:53,  1.57it/s]
 80%|████████  | 46152/57600 [8:06:45<2:02:39,  1.56it/s]
 80%|████████  | 46153/57600 [8:06:45<2:01:02,  1.58it/s]
 80%|████████  | 46154/57600 [8:06:46<1:59:43,  1.59it/s]
 80%|████████  | 46155/57600 [8:06:47<2:03:34,  1.54it/s]
 80%|████████  | 46156/57600 [8:06:47<2:01:26,  1.57it/s]
 80%|████████  | 46157/57600 [8:06:48<1:58:47,  1.61it/s]
 80%|████████  | 46158/57600 [8:06:49<2:02:01,  1.56it/s]
 80%|████████  | 46159/57600 [8:06:49<2:01:28,  1.57it/s]
 80%|████████  | 46160/57600 [8:06:50<2:01:21,  1.57it/s]
                                                         
{'loss': 1.1322, 'learning_rate': 2.793728222996516e-07, 'epoch': 509.49}
+
 80%|████████  | 46160/57600 [8:06:50<2:01:21,  1.57it/s]
 80%|████████  | 46161/57600 [8:06:51<2:01:52,  1.56it/s]
 80%|████████  | 46162/57600 [8:06:51<2:00:02,  1.59it/s]
 80%|████████  | 46163/57600 [8:06:52<1:59:56,  1.59it/s]
 80%|████████  | 46164/57600 [8:06:52<1:56:47,  1.63it/s]
 80%|████████  | 46165/57600 [8:06:53<1:59:47,  1.59it/s]
 80%|████████  | 46166/57600 [8:06:54<1:59:29,  1.59it/s]
 80%|████████  | 46167/57600 [8:06:54<1:57:42,  1.62it/s]
 80%|████████  | 46168/57600 [8:06:55<1:58:58,  1.60it/s]
 80%|████████  | 46169/57600 [8:06:56<1:58:55,  1.60it/s]
 80%|████████  | 46170/57600 [8:06:56<1:58:34,  1.61it/s]
 80%|████████  | 46171/57600 [8:06:57<1:53:35,  1.68it/s]
 80%|████████  | 46172/57600 [8:06:57<1:53:22,  1.68it/s]
 80%|████████  | 46173/57600 [8:06:58<1:52:07,  1.70it/s]
 80%|████████  | 46174/57600 [8:06:59<1:59:03,  1.60it/s]
 80%|████████  | 46175/57600 [8:06:59<1:57:42,  1.62it/s]
 80%|████████  | 46176/57600 [8:07:00<2:00:50,  1.58it/s]
 80%|████████  | 46177/57600 [8:07:00<2:01:04,  1.57it/s]
 80%|████████  | 46178/57600 [8:07:01<1:58:50,  1.60it/s]
 80%|████████  | 46179/57600 [8:07:02<2:04:24,  1.53it/s]
 80%|████████  | 46180/57600 [8:07:02<2:02:01,  1.56it/s]
                                                         
{'loss': 1.1463, 'learning_rate': 2.7905923344947733e-07, 'epoch': 509.71}
+
 80%|████████  | 46180/57600 [8:07:02<2:02:01,  1.56it/s]
 80%|████████  | 46181/57600 [8:07:03<2:04:18,  1.53it/s]
 80%|█��██████  | 46182/57600 [8:07:04<2:04:22,  1.53it/s]
 80%|████████  | 46183/57600 [8:07:04<2:06:26,  1.50it/s]
 80%|████████  | 46184/57600 [8:07:05<2:03:57,  1.53it/s]
 80%|████████  | 46185/57600 [8:07:06<2:05:37,  1.51it/s]
 80%|████████  | 46186/57600 [8:07:06<2:06:17,  1.51it/s]
 80%|████████  | 46187/57600 [8:07:07<2:08:03,  1.49it/s]
 80%|████████  | 46188/57600 [8:07:08<2:05:36,  1.51it/s]
 80%|████████  | 46189/57600 [8:07:08<2:09:15,  1.47it/s]
 80%|████████  | 46190/57600 [8:07:09<2:08:36,  1.48it/s]
 80%|████████  | 46191/57600 [8:07:10<2:10:25,  1.46it/s]
 80%|████████  | 46192/57600 [8:07:10<2:02:16,  1.55it/s]
 80%|████████  | 46193/57600 [8:07:11<1:59:08,  1.60it/s]
 80%|████████  | 46194/57600 [8:07:12<1:55:41,  1.64it/s]
 80%|████████  | 46195/57600 [8:07:12<1:58:25,  1.61it/s]
 80%|████████  | 46196/57600 [8:07:13<1:57:48,  1.61it/s]
 80%|████████  | 46197/57600 [8:07:13<2:00:48,  1.57it/s]
 80%|████████  | 46198/57600 [8:07:14<2:02:52,  1.55it/s]
 80%|████████  | 46199/57600 [8:07:15<2:04:39,  1.52it/s]
 80%|████████  | 46200/57600 [8:07:15<1:59:53,  1.58it/s]
                                                         
{'loss': 1.1159, 'learning_rate': 2.787456445993032e-07, 'epoch': 509.93}
+
 80%|████████  | 46200/57600 [8:07:15<1:59:53,  1.58it/s]
 80%|████████  | 46201/57600 [8:07:16<2:03:55,  1.53it/s]
 80%|████████  | 46202/57600 [8:07:17<2:03:19,  1.54it/s]
 80%|████████  | 46203/57600 [8:07:17<2:02:02,  1.56it/s]
 80%|████████  | 46204/57600 [8:07:18<1:59:46,  1.59it/s]
 80%|████████  | 46205/57600 [8:07:19<2:00:51,  1.57it/s]
 80%|████████  | 46206/57600 [8:07:19<2:03:11,  1.54it/s]
 80%|████████  | 46207/57600 [8:07:20<2:06:48,  1.50it/s]
 80%|████████  | 46208/57600 [8:07:21<2:04:07,  1.53it/s]
 80%|████████  | 46209/57600 [8:07:21<2:05:06,  1.52it/s]
 80%|████████  | 46210/57600 [8:07:22<2:02:01,  1.56it/s]
 80%|████████  | 46211/57600 [8:07:22<1:59:36,  1.59it/s]
 80%|████████  | 46212/57600 [8:07:23<1:57:41,  1.61it/s]
 80%|████████  | 46213/57600 [8:07:24<1:59:16,  1.59it/s]
 80%|████████  | 46214/57600 [8:07:24<2:06:31,  1.50it/s]
 80%|████████  | 46215/57600 [8:07:25<2:02:04,  1.55it/s]
 80%|████████  | 46216/57600 [8:07:26<1:58:41,  1.60it/s]
 80%|████████  | 46217/57600 [8:07:26<1:58:51,  1.60it/s]
 80%|████████  | 46218/57600 [8:07:27<1:54:15,  1.66it/s]
 80%|████████  | 46219/57600 [8:07:27<1:56:31,  1.63it/s]
 80%|████████  | 46220/57600 [8:07:28<1:59:27,  1.59it/s]
                                                         
{'loss': 1.1214, 'learning_rate': 2.784320557491289e-07, 'epoch': 510.15}
+
 80%|████████  | 46220/57600 [8:07:28<1:59:27,  1.59it/s]
 80%|████████  | 46221/57600 [8:07:29<1:59:28,  1.59it/s]
 80%|████████  | 46222/57600 [8:07:29<2:01:17,  1.56it/s]
 80%|████████  | 46223/57600 [8:07:30<2:01:18,  1.56it/s]
 80%|████████  | 46224/57600 [8:07:31<2:01:23,  1.56it/s]
 80%|████████  | 46225/57600 [8:07:31<2:00:26,  1.57it/s]
 80%|████████  | 46226/57600 [8:07:32<2:02:33,  1.55it/s]
 80%|████████  | 46227/57600 [8:07:33<1:59:51,  1.58it/s]
 80%|████████  | 46228/57600 [8:07:33<2:00:37,  1.57it/s]
 80%|████████  | 46229/57600 [8:07:34<1:59:59,  1.58it/s]
 80%|████████  | 46230/57600 [8:07:34<1:58:56,  1.59it/s]
 80%|████████  | 46231/57600 [8:07:35<1:57:22,  1.61it/s]
 80%|████████  | 46232/57600 [8:07:36<1:56:16,  1.63it/s]
 80%|████████  | 46233/57600 [8:07:36<2:01:31,  1.56it/s]
 80%|████████  | 46234/57600 [8:07:37<1:57:55,  1.61it/s]
 80%|████████  | 46235/57600 [8:07:38<1:55:53,  1.63it/s]
 80%|████████  | 46236/57600 [8:07:38<2:00:53,  1.57it/s]
 80%|████████  | 46237/57600 [8:07:39<1:56:40,  1.62it/s]
 80%|████████  | 46238/57600 [8:07:39<1:56:07,  1.63it/s]
 80%|████████  | 46239/57600 [8:07:40<1:54:13,  1.66it/s]
 80%|████████  | 46240/57600 [8:07:41<1:54:03,  1.66it/s]
                                                         
{'loss': 1.1087, 'learning_rate': 2.781184668989547e-07, 'epoch': 510.38}
+
 80%|████████  | 46240/57600 [8:07:41<1:54:03,  1.66it/s]
 80%|████████  | 46241/57600 [8:07:41<1:58:46,  1.59it/s]
 80%|████████  | 46242/57600 [8:07:42<1:59:51,  1.58it/s]
 80%|████████  | 46243/57600 [8:07:43<2:01:29,  1.56it/s]
 80%|████████  | 46244/57600 [8:07:43<2:02:25,  1.55it/s]
 80%|████████  | 46245/57600 [8:07:44<1:59:17,  1.59it/s]
 80%|████████  | 46246/57600 [8:07:44<1:59:12,  1.59it/s]
 80%|████████  | 46247/57600 [8:07:45<2:01:20,  1.56it/s]
 80%|████████  | 46248/57600 [8:07:46<2:01:36,  1.56it/s]
 80%|████████  | 46249/57600 [8:07:47<2:05:19,  1.51it/s]
 80%|████████  | 46250/57600 [8:07:47<2:04:48,  1.52it/s]
 80%|████████  | 46251/57600 [8:07:48<2:08:00,  1.48it/s]
 80%|████████  | 46252/57600 [8:07:48<2:03:52,  1.53it/s]
 80%|████████  | 46253/57600 [8:07:49<1:59:33,  1.58it/s]
 80%|████████  | 46254/57600 [8:07:50<1:59:40,  1.58it/s]
 80%|████████  | 46255/57600 [8:07:50<2:04:40,  1.52it/s]
 80%|████████  | 46256/57600 [8:07:51<2:03:44,  1.53it/s]
 80%|████████  | 46257/57600 [8:07:52<2:01:55,  1.55it/s]
 80%|████████  | 46258/57600 [8:07:52<2:04:26,  1.52it/s]
 80%|████████  | 46259/57600 [8:07:53<2:00:26,  1.57it/s]
 80%|████████  | 46260/57600 [8:07:54<1:57:12,  1.61it/s]
                                                         
{'loss': 1.0912, 'learning_rate': 2.7780487804878044e-07, 'epoch': 510.6}
+
 80%|████████  | 46260/57600 [8:07:54<1:57:12,  1.61it/s]
 80%|████████  | 46261/57600 [8:07:54<1:58:29,  1.59it/s]
 80%|████████  | 46262/57600 [8:07:55<1:59:03,  1.59it/s]
 80%|████████  | 46263/57600 [8:07:55<2:00:09,  1.57it/s]
 80%|████████  | 46264/57600 [8:07:56<2:01:05,  1.56it/s]
 80%|████████  | 46265/57600 [8:07:57<2:02:25,  1.54it/s]
 80%|████████  | 46266/57600 [8:07:57<2:02:58,  1.54it/s]
 80%|████████  | 46267/57600 [8:07:58<2:03:21,  1.53it/s]
 80%|████████  | 46268/57600 [8:07:59<2:02:20,  1.54it/s]
 80%|████████  | 46269/57600 [8:07:59<2:03:10,  1.53it/s]
 80%|████████  | 46270/57600 [8:08:00<1:57:55,  1.60it/s]
 80%|████████  | 46271/57600 [8:08:01<1:58:17,  1.60it/s]
 80%|████████  | 46272/57600 [8:08:01<1:58:49,  1.59it/s]
 80%|████████  | 46273/57600 [8:08:02<1:59:14,  1.58it/s]
 80%|████████  | 46274/57600 [8:08:02<1:56:33,  1.62it/s]
 80%|████████  | 46275/57600 [8:08:03<1:56:44,  1.62it/s]
 80%|████████  | 46276/57600 [8:08:04<1:58:12,  1.60it/s]
 80%|████████  | 46277/57600 [8:08:04<1:59:34,  1.58it/s]
 80%|████████  | 46278/57600 [8:08:05<1:55:30,  1.63it/s]
 80%|████████  | 46279/57600 [8:08:06<1:56:57,  1.61it/s]
 80%|████████  | 46280/57600 [8:08:06<1:58:16,  1.60it/s]
                                                         
{'loss': 1.1016, 'learning_rate': 2.774912891986063e-07, 'epoch': 510.82}
+
 80%|████████  | 46280/57600 [8:08:06<1:58:16,  1.60it/s]
 80%|████████  | 46281/57600 [8:08:07<1:53:34,  1.66it/s]
 80%|████████  | 46282/57600 [8:08:07<1:53:34,  1.66it/s]
 80%|████████  | 46283/57600 [8:08:08<1:56:01,  1.63it/s]
 80%|████████  | 46284/57600 [8:08:09<1:55:49,  1.63it/s]
 80%|████████  | 46285/57600 [8:08:09<1:54:56,  1.64it/s]
 80%|████████  | 46286/57600 [8:08:10<1:58:33,  1.59it/s]
 80%|████████  | 46287/57600 [8:08:10<1:55:46,  1.63it/s]
 80%|████████  | 46288/57600 [8:08:11<1:59:28,  1.58it/s]
 80%|████████  | 46289/57600 [8:08:12<1:59:19,  1.58it/s]
 80%|████████  | 46290/57600 [8:08:12<1:58:59,  1.58it/s]
 80%|████████  | 46291/57600 [8:08:13<1:56:42,  1.61it/s]
 80%|████████  | 46292/57600 [8:08:14<1:55:12,  1.64it/s]
 80%|████████  | 46293/57600 [8:08:14<1:54:10,  1.65it/s]
 80%|████████  | 46294/57600 [8:08:15<1:55:54,  1.63it/s]
 80%|████████  | 46295/57600 [8:08:15<1:54:18,  1.65it/s]
 80%|████████  | 46296/57600 [8:08:16<1:55:57,  1.62it/s]
 80%|████████  | 46297/57600 [8:08:17<2:00:30,  1.56it/s]
 80%|████████  | 46298/57600 [8:08:17<1:58:33,  1.59it/s]
 80%|████████  | 46299/57600 [8:08:18<1:57:22,  1.60it/s]
 80%|████████  | 46300/57600 [8:08:19<2:01:18,  1.55it/s]
                                                         
{'loss': 1.1232, 'learning_rate': 2.7717770034843205e-07, 'epoch': 511.04}
+
 80%|████████  | 46300/57600 [8:08:19<2:01:18,  1.55it/s]
 80%|████████  | 46301/57600 [8:08:19<1:56:35,  1.62it/s]
 80%|████████  | 46302/57600 [8:08:20<1:55:13,  1.63it/s]
 80%|████████  | 46303/57600 [8:08:20<1:53:44,  1.66it/s]
 80%|████████  | 46304/57600 [8:08:21<1:56:02,  1.62it/s]
 80%|████████  | 46305/57600 [8:08:22<2:01:12,  1.55it/s]
 80%|████████  | 46306/57600 [8:08:22<1:58:47,  1.58it/s]
 80%|████████  | 46307/57600 [8:08:23<1:58:11,  1.59it/s]
 80%|████████  | 46308/57600 [8:08:24<1:57:54,  1.60it/s]
 80%|████████  | 46309/57600 [8:08:24<1:59:24,  1.58it/s]
 80%|████████  | 46310/57600 [8:08:25<2:00:36,  1.56it/s]
 80%|████████  | 46311/57600 [8:08:26<2:01:30,  1.55it/s]
 80%|████████  | 46312/57600 [8:08:26<2:00:35,  1.56it/s]
 80%|████████  | 46313/57600 [8:08:27<1:58:20,  1.59it/s]
 80%|████████  | 46314/57600 [8:08:27<1:55:23,  1.63it/s]
 80%|████████  | 46315/57600 [8:08:28<1:53:32,  1.66it/s]
 80%|████████  | 46316/57600 [8:08:29<1:53:20,  1.66it/s]
 80%|████████  | 46317/57600 [8:08:29<1:52:32,  1.67it/s]
 80%|████████  | 46318/57600 [8:08:30<1:56:53,  1.61it/s]
 80%|████████  | 46319/57600 [8:08:30<1:58:45,  1.58it/s]
 80%|████████  | 46320/57600 [8:08:31<1:56:50,  1.61it/s]
                                                         
{'loss': 1.1398, 'learning_rate': 2.768641114982578e-07, 'epoch': 511.26}
+
 80%|████████  | 46320/57600 [8:08:31<1:56:50,  1.61it/s]
 80%|████████  | 46321/57600 [8:08:32<1:54:16,  1.64it/s]
 80%|████████  | 46322/57600 [8:08:32<1:56:32,  1.61it/s]
 80%|████████  | 46323/57600 [8:08:33<1:56:12,  1.62it/s]
 80%|████████  | 46324/57600 [8:08:34<1:55:40,  1.62it/s]
 80%|████████  | 46325/57600 [8:08:34<1:55:15,  1.63it/s]
 80%|████████  | 46326/57600 [8:08:35<1:53:36,  1.65it/s]
 80%|████████  | 46327/57600 [8:08:35<1:58:04,  1.59it/s]
 80%|████████  | 46328/57600 [8:08:36<1:57:48,  1.59it/s]
 80%|████████  | 46329/57600 [8:08:37<1:58:42,  1.58it/s]
 80%|████████  | 46330/57600 [8:08:37<1:57:26,  1.60it/s]
 80%|████████  | 46331/57600 [8:08:38<1:57:57,  1.59it/s]
 80%|████████  | 46332/57600 [8:08:38<1:55:11,  1.63it/s]
 80%|████████  | 46333/57600 [8:08:39<1:56:08,  1.62it/s]
 80%|████████  | 46334/57600 [8:08:40<1:56:11,  1.62it/s]
 80%|████████  | 46335/57600 [8:08:40<1:52:20,  1.67it/s]
 80%|████████  | 46336/57600 [8:08:41<1:52:25,  1.67it/s]
 80%|████████  | 46337/57600 [8:08:42<1:56:54,  1.61it/s]
 80%|████████  | 46338/57600 [8:08:42<1:58:14,  1.59it/s]
 80%|████████  | 46339/57600 [8:08:43<2:02:23,  1.53it/s]
 80%|████████  | 46340/57600 [8:08:44<2:02:28,  1.53it/s]
                                                         
{'loss': 1.1016, 'learning_rate': 2.7655052264808366e-07, 'epoch': 511.48}
+
 80%|████████  | 46340/57600 [8:08:44<2:02:28,  1.53it/s]
 80%|████████  | 46341/57600 [8:08:44<1:59:37,  1.57it/s]
 80%|████████  | 46342/57600 [8:08:45<1:59:34,  1.57it/s]
 80%|████████  | 46343/57600 [8:08:45<2:00:09,  1.56it/s]
 80%|████████  | 46344/57600 [8:08:46<1:59:18,  1.57it/s]
 80%|████████  | 46345/57600 [8:08:47<2:05:11,  1.50it/s]
 80%|████████  | 46346/57600 [8:08:47<2:01:00,  1.55it/s]
 80%|████████  | 46347/57600 [8:08:48<2:04:48,  1.50it/s]
 80%|████████  | 46348/57600 [8:08:49<2:01:58,  1.54it/s]
 80%|████████  | 46349/57600 [8:08:49<2:02:32,  1.53it/s]
 80%|████████  | 46350/57600 [8:08:50<2:00:48,  1.55it/s]
 80%|████████  | 46351/57600 [8:08:51<1:56:37,  1.61it/s]
 80%|████████  | 46352/57600 [8:08:51<1:58:37,  1.58it/s]
 80%|████████  | 46353/57600 [8:08:52<1:59:26,  1.57it/s]
 80%|████████  | 46354/57600 [8:08:53<1:58:51,  1.58it/s]
 80%|████████  | 46355/57600 [8:08:53<2:00:19,  1.56it/s]
 80%|████████  | 46356/57600 [8:08:54<1:58:02,  1.59it/s]
 80%|████████  | 46357/57600 [8:08:54<1:58:09,  1.59it/s]
 80%|████████  | 46358/57600 [8:08:55<2:00:12,  1.56it/s]
 80%|████████  | 46359/57600 [8:08:56<1:58:49,  1.58it/s]
 80%|████████  | 46360/57600 [8:08:56<2:02:04,  1.53it/s]
                                                         
{'loss': 1.1341, 'learning_rate': 2.7623693379790936e-07, 'epoch': 511.7}
+
 80%|████████  | 46360/57600 [8:08:56<2:02:04,  1.53it/s]
 80%|████████  | 46361/57600 [8:08:57<2:04:53,  1.50it/s]
 80%|████████  | 46362/57600 [8:08:58<2:02:00,  1.54it/s]
 80%|████████  | 46363/57600 [8:08:58<2:04:32,  1.50it/s]
 80%|███████��  | 46364/57600 [8:08:59<2:03:53,  1.51it/s]
 80%|████████  | 46365/57600 [8:09:00<2:01:06,  1.55it/s]
 80%|████████  | 46366/57600 [8:09:00<1:57:49,  1.59it/s]
 80%|████████  | 46367/57600 [8:09:01<1:55:05,  1.63it/s]
 80%|████████  | 46368/57600 [8:09:01<1:57:20,  1.60it/s]
 81%|████████  | 46369/57600 [8:09:02<1:58:37,  1.58it/s]
 81%|████████  | 46370/57600 [8:09:03<1:56:26,  1.61it/s]
 81%|████████  | 46371/57600 [8:09:03<1:57:07,  1.60it/s]
 81%|████████  | 46372/57600 [8:09:04<1:56:53,  1.60it/s]
 81%|████████  | 46373/57600 [8:09:05<1:55:37,  1.62it/s]
 81%|████████  | 46374/57600 [8:09:05<1:58:47,  1.57it/s]
 81%|████████  | 46375/57600 [8:09:06<1:56:49,  1.60it/s]
 81%|████████  | 46376/57600 [8:09:06<1:55:55,  1.61it/s]
 81%|████████  | 46377/57600 [8:09:07<1:57:41,  1.59it/s]
 81%|████████  | 46378/57600 [8:09:08<1:56:15,  1.61it/s]
 81%|████████  | 46379/57600 [8:09:08<1:56:37,  1.60it/s]
 81%|████████  | 46380/57600 [8:09:09<1:52:30,  1.66it/s]
                                                         
{'loss': 1.1043, 'learning_rate': 2.7592334494773516e-07, 'epoch': 511.92}
+
 81%|████████  | 46380/57600 [8:09:09<1:52:30,  1.66it/s]
 81%|████████  | 46381/57600 [8:09:10<1:53:23,  1.65it/s]
 81%|████████  | 46382/57600 [8:09:10<1:51:55,  1.67it/s]
 81%|████████  | 46383/57600 [8:09:11<1:52:05,  1.67it/s]
 81%|████████  | 46384/57600 [8:09:11<1:56:17,  1.61it/s]
 81%|████████  | 46385/57600 [8:09:12<1:51:57,  1.67it/s]
 81%|████████  | 46386/57600 [8:09:13<2:00:11,  1.55it/s]
 81%|████████  | 46387/57600 [8:09:13<1:55:55,  1.61it/s]
 81%|████████  | 46388/57600 [8:09:14<2:01:41,  1.54it/s]
 81%|████████  | 46389/57600 [8:09:15<2:00:08,  1.56it/s]
 81%|████████  | 46390/57600 [8:09:15<1:59:32,  1.56it/s]
 81%|████████  | 46391/57600 [8:09:16<2:06:39,  1.47it/s]
 81%|████████  | 46392/57600 [8:09:17<2:03:23,  1.51it/s]
 81%|████████  | 46393/57600 [8:09:17<2:01:25,  1.54it/s]
 81%|████████  | 46394/57600 [8:09:18<2:05:31,  1.49it/s]
 81%|████████  | 46395/57600 [8:09:19<2:00:00,  1.56it/s]
 81%|████████  | 46396/57600 [8:09:19<1:55:22,  1.62it/s]
 81%|████████  | 46397/57600 [8:09:20<1:52:59,  1.65it/s]
 81%|████████  | 46398/57600 [8:09:20<1:52:35,  1.66it/s]
 81%|████████  | 46399/57600 [8:09:21<1:56:22,  1.60it/s]
 81%|████████  | 46400/57600 [8:09:22<1:59:51,  1.56it/s]
                                                         
{'loss': 1.1382, 'learning_rate': 2.756097560975609e-07, 'epoch': 512.14}
+
 81%|████████  | 46400/57600 [8:09:22<1:59:51,  1.56it/s]
 81%|████████  | 46401/57600 [8:09:22<2:01:10,  1.54it/s]
 81%|████████  | 46402/57600 [8:09:23<2:04:25,  1.50it/s]
 81%|████████  | 46403/57600 [8:09:24<2:01:39,  1.53it/s]
 81%|████████  | 46404/57600 [8:09:24<1:59:58,  1.56it/s]
 81%|████████  | 46405/57600 [8:09:25<1:59:46,  1.56it/s]
 81%|████████  | 46406/57600 [8:09:26<2:00:26,  1.55it/s]
 81%|████████  | 46407/57600 [8:09:26<2:07:05,  1.47it/s]
 81%|████████  | 46408/57600 [8:09:27<2:07:04,  1.47it/s]
 81%|████████  | 46409/57600 [8:09:28<2:01:26,  1.54it/s]
 81%|████████  | 46410/57600 [8:09:28<2:00:10,  1.55it/s]
 81%|████████  | 46411/57600 [8:09:29<2:01:23,  1.54it/s]
 81%|████████  | 46412/57600 [8:09:29<2:00:11,  1.55it/s]
 81%|████████  | 46413/57600 [8:09:30<1:57:00,  1.59it/s]
 81%|████████  | 46414/57600 [8:09:31<1:56:47,  1.60it/s]
 81%|████████  | 46415/57600 [8:09:31<1:54:00,  1.64it/s]
 81%|████████  | 46416/57600 [8:09:32<1:53:23,  1.64it/s]
 81%|████████  | 46417/57600 [8:09:32<1:51:40,  1.67it/s]
 81%|████████  | 46418/57600 [8:09:33<1:51:29,  1.67it/s]
 81%|████████  | 46419/57600 [8:09:34<1:53:03,  1.65it/s]
 81%|████████  | 46420/57600 [8:09:34<1:52:46,  1.65it/s]
                                                         
{'loss': 1.1341, 'learning_rate': 2.7529616724738683e-07, 'epoch': 512.36}
+
 81%|████████  | 46420/57600 [8:09:34<1:52:46,  1.65it/s]
 81%|████████  | 46421/57600 [8:09:35<1:53:56,  1.64it/s]
 81%|████████  | 46422/57600 [8:09:35<1:49:52,  1.70it/s]
 81%|████████  | 46423/57600 [8:09:36<1:54:08,  1.63it/s]
 81%|████████  | 46424/57600 [8:09:37<1:56:20,  1.60it/s]
 81%|████████  | 46425/57600 [8:09:37<1:56:06,  1.60it/s]
 81%|████████  | 46426/57600 [8:09:38<1:53:08,  1.65it/s]
 81%|████████  | 46427/57600 [8:09:39<1:52:04,  1.66it/s]
 81%|████████  | 46428/57600 [8:09:39<1:54:16,  1.63it/s]
 81%|████████  | 46429/57600 [8:09:40<1:54:37,  1.62it/s]
 81%|████████  | 46430/57600 [8:09:40<1:54:21,  1.63it/s]
 81%|████████  | 46431/57600 [8:09:41<1:59:07,  1.56it/s]
 81%|████████  | 46432/57600 [8:09:42<2:00:08,  1.55it/s]
 81%|████████  | 46433/57600 [8:09:42<2:01:46,  1.53it/s]
 81%|████████  | 46434/57600 [8:09:43<2:02:58,  1.51it/s]
 81%|████████  | 46435/57600 [8:09:44<1:59:20,  1.56it/s]
 81%|████████  | 46436/57600 [8:09:44<1:58:15,  1.57it/s]
 81%|████████  | 46437/57600 [8:09:45<1:58:11,  1.57it/s]
 81%|████████  | 46438/57600 [8:09:46<1:55:00,  1.62it/s]
 81%|████████  | 46439/57600 [8:09:46<1:59:14,  1.56it/s]
 81%|████████  | 46440/57600 [8:09:47<2:00:24,  1.54it/s]
                                                         
{'loss': 1.1054, 'learning_rate': 2.749825783972126e-07, 'epoch': 512.58}
+
 81%|████████  | 46440/57600 [8:09:47<2:00:24,  1.54it/s]
 81%|████████  | 46441/57600 [8:09:48<2:06:08,  1.47it/s]
 81%|████████  | 46442/57600 [8:09:48<2:01:11,  1.53it/s]
 81%|████████  | 46443/57600 [8:09:49<1:59:13,  1.56it/s]
 81%|████████  | 46444/57600 [8:09:49<1:58:31,  1.57it/s]
 81%|████████  | 46445/57600 [8:09:50<1:55:32,  1.61it/s]
 81%|████████  | 46446/57600 [8:09:51<1:54:02,  1.63it/s]
 81%|████████  | 46447/57600 [8:09:51<1:53:14,  1.64it/s]
 81%|████████  | 46448/57600 [8:09:52<1:52:46,  1.65it/s]
 81%|████████  | 46449/57600 [8:09:52<1:51:06,  1.67it/s]
 81%|████████  | 46450/57600 [8:09:53<1:52:40,  1.65it/s]
 81%|████████  | 46451/57600 [8:09:54<1:56:01,  1.60it/s]
 81%|████████  | 46452/57600 [8:09:54<1:58:36,  1.57it/s]
 81%|████████  | 46453/57600 [8:09:55<1:56:11,  1.60it/s]
 81%|████████  | 46454/57600 [8:09:56<1:55:00,  1.62it/s]
 81%|████████  | 46455/57600 [8:09:56<2:01:19,  1.53it/s]
 81%|████████  | 46456/57600 [8:09:57<1:59:30,  1.55it/s]
 81%|████████  | 46457/57600 [8:09:58<1:58:31,  1.57it/s]
 81%|████████  | 46458/57600 [8:09:58<2:01:23,  1.53it/s]
 81%|████████  | 46459/57600 [8:09:59<1:57:18,  1.58it/s]
 81%|████████  | 46460/57600 [8:09:59<1:57:14,  1.58it/s]
                                                         
{'loss': 1.1304, 'learning_rate': 2.746689895470383e-07, 'epoch': 512.8}
+
 81%|████████  | 46460/57600 [8:09:59<1:57:14,  1.58it/s]
 81%|████████  | 46461/57600 [8:10:00<1:57:00,  1.59it/s]
 81%|████████  | 46462/57600 [8:10:01<1:58:17,  1.57it/s]
 81%|████████  | 46463/57600 [8:10:01<2:02:12,  1.52it/s]
 81%|████████  | 46464/57600 [8:10:02<1:59:10,  1.56it/s]
 81%|████████  | 46465/57600 [8:10:03<2:01:55,  1.52it/s]
 81%|████████  | 46466/57600 [8:10:03<1:58:01,  1.57it/s]
 81%|████████  | 46467/57600 [8:10:04<1:56:16,  1.60it/s]
 81%|████████  | 46468/57600 [8:10:05<1:55:51,  1.60it/s]
 81%|████████  | 46469/57600 [8:10:05<1:56:21,  1.59it/s]
 81%|████████  | 46470/57600 [8:10:06<1:57:23,  1.58it/s]
 81%|████████  | 46471/57600 [8:10:06<1:53:36,  1.63it/s]
 81%|████████  | 46472/57600 [8:10:07<1:57:04,  1.58it/s]
 81%|████████  | 46473/57600 [8:10:08<1:58:38,  1.56it/s]
 81%|████████  | 46474/57600 [8:10:08<1:59:52,  1.55it/s]
 81%|████████  | 46475/57600 [8:10:09<1:55:38,  1.60it/s]
 81%|████████  | 46476/57600 [8:10:10<1:59:08,  1.56it/s]
 81%|████████  | 46477/57600 [8:10:10<1:57:43,  1.57it/s]
 81%|████████  | 46478/57600 [8:10:11<1:59:50,  1.55it/s]
 81%|████████  | 46479/57600 [8:10:12<1:59:56,  1.55it/s]
 81%|████████  | 46480/57600 [8:10:12<2:00:05,  1.54it/s]
                                                         
{'loss': 1.1042, 'learning_rate': 2.7435540069686414e-07, 'epoch': 513.02}
+
 81%|████████  | 46480/57600 [8:10:12<2:00:05,  1.54it/s]
 81%|████████  | 46481/57600 [8:10:13<1:59:48,  1.55it/s]
 81%|████████  | 46482/57600 [8:10:14<2:02:50,  1.51it/s]
 81%|████████  | 46483/57600 [8:10:14<2:08:28,  1.44it/s]
 81%|████████  | 46484/57600 [8:10:15<2:04:17,  1.49it/s]
 81%|████████  | 46485/57600 [8:10:16<2:01:21,  1.53it/s]
 81%|████████  | 46486/57600 [8:10:16<2:05:40,  1.47it/s]
 81%|████████  | 46487/57600 [8:10:17<1:59:33,  1.55it/s]
 81%|████████  | 46488/57600 [8:10:18<1:57:52,  1.57it/s]
 81%|████████  | 46489/57600 [8:10:18<1:57:03,  1.58it/s]
 81%|████████  | 46490/57600 [8:10:19<1:53:53,  1.63it/s]
 81%|████████  | 46491/57600 [8:10:19<1:54:11,  1.62it/s]
 81%|████████  | 46492/57600 [8:10:20<1:55:24,  1.60it/s]
 81%|████████  | 46493/57600 [8:10:21<1:58:09,  1.57it/s]
 81%|████████  | 46494/57600 [8:10:21<1:57:09,  1.58it/s]
 81%|████████  | 46495/57600 [8:10:22<1:56:03,  1.59it/s]
 81%|████████  | 46496/57600 [8:10:22<1:53:21,  1.63it/s]
 81%|████████  | 46497/57600 [8:10:23<1:54:51,  1.61it/s]
 81%|████████  | 46498/57600 [8:10:24<1:55:58,  1.60it/s]
 81%|████████  | 46499/57600 [8:10:24<1:57:38,  1.57it/s]
 81%|████████  | 46500/57600 [8:10:25<2:01:52,  1.52it/s]
                                                         
{'loss': 1.1057, 'learning_rate': 2.740418118466899e-07, 'epoch': 513.25}
+
 81%|████████  | 46500/57600 [8:10:25<2:01:52,  1.52it/s]
 81%|████████  | 46501/57600 [8:10:26<1:59:45,  1.54it/s]
 81%|████████  | 46502/57600 [8:10:26<1:59:10,  1.55it/s]
 81%|████████  | 46503/57600 [8:10:27<1:56:10,  1.59it/s]
 81%|████████  | 46504/57600 [8:10:28<1:56:54,  1.58it/s]
 81%|████████  | 46505/57600 [8:10:28<1:53:48,  1.62it/s]
 81%|████████  | 46506/57600 [8:10:29<1:55:58,  1.59it/s]
 81%|████████  | 46507/57600 [8:10:29<1:54:18,  1.62it/s]
 81%|████████  | 46508/57600 [8:10:30<1:57:58,  1.57it/s]
 81%|████████  | 46509/57600 [8:10:31<1:55:12,  1.60it/s]
 81%|████████  | 46510/57600 [8:10:31<1:53:48,  1.62it/s]
 81%|████████  | 46511/57600 [8:10:32<1:53:07,  1.63it/s]
 81%|████████  | 46512/57600 [8:10:33<1:53:38,  1.63it/s]
 81%|████████  | 46513/57600 [8:10:33<1:56:27,  1.59it/s]
 81%|████████  | 46514/57600 [8:10:34<1:53:26,  1.63it/s]
 81%|████████  | 46515/57600 [8:10:34<1:52:17,  1.65it/s]
 81%|████████  | 46516/57600 [8:10:35<1:50:59,  1.66it/s]
 81%|████████  | 46517/57600 [8:10:36<1:52:57,  1.64it/s]
 81%|████████  | 46518/57600 [8:10:36<1:53:17,  1.63it/s]
 81%|████████  | 46519/57600 [8:10:37<1:54:18,  1.62it/s]
 81%|████████  | 46520/57600 [8:10:37<1:53:08,  1.63it/s]
                                                         
{'loss': 1.1488, 'learning_rate': 2.7372822299651564e-07, 'epoch': 513.47}
+
 81%|████████  | 46520/57600 [8:10:37<1:53:08,  1.63it/s]
 81%|████████  | 46521/57600 [8:10:38<1:51:36,  1.65it/s]
 81%|████████  | 46522/57600 [8:10:39<1:51:27,  1.66it/s]
 81%|████████  | 46523/57600 [8:10:39<1:52:00,  1.65it/s]
 81%|████████  | 46524/57600 [8:10:40<1:52:02,  1.65it/s]
 81%|████████  | 46525/57600 [8:10:40<1:49:20,  1.69it/s]
 81%|████████  | 46526/57600 [8:10:41<1:52:49,  1.64it/s]
 81%|████████  | 46527/57600 [8:10:42<1:50:57,  1.66it/s]
 81%|████████  | 46528/57600 [8:10:42<1:53:37,  1.62it/s]
 81%|████████  | 46529/57600 [8:10:43<1:52:07,  1.65it/s]
 81%|████████  | 46530/57600 [8:10:43<1:51:59,  1.65it/s]
 81%|████████  | 46531/57600 [8:10:44<1:50:42,  1.67it/s]
 81%|████████  | 46532/57600 [8:10:45<1:52:25,  1.64it/s]
 81%|████████  | 46533/57600 [8:10:45<1:50:43,  1.67it/s]
 81%|████████  | 46534/57600 [8:10:46<1:54:13,  1.61it/s]
 81%|████████  | 46535/57600 [8:10:47<1:53:46,  1.62it/s]
 81%|████████  | 46536/57600 [8:10:47<1:50:56,  1.66it/s]
 81%|████████  | 46537/57600 [8:10:48<1:54:12,  1.61it/s]
 81%|████████  | 46538/57600 [8:10:48<1:51:20,  1.66it/s]
 81%|████████  | 46539/57600 [8:10:49<1:52:48,  1.63it/s]
 81%|████████  | 46540/57600 [8:10:50<1:51:05,  1.66it/s]
                                                         
{'loss': 1.1476, 'learning_rate': 2.734146341463414e-07, 'epoch': 513.69}
+
 81%|████████  | 46540/57600 [8:10:50<1:51:05,  1.66it/s]
 81%|████████  | 46541/57600 [8:10:50<1:52:36,  1.64it/s]
 81%|████████  | 46542/57600 [8:10:51<1:54:43,  1.61it/s]
 81%|████████  | 46543/57600 [8:10:51<1:52:15,  1.64it/s]
 81%|████████  | 46544/57600 [8:10:52<1:53:14,  1.63it/s]
 81%|████████  | 46545/57600 [8:10:53<1:54:27,  1.61it/s]
 81%|████████  | 46546/57600 [8:10:53<1:53:30,  1.62it/s]
 81%|████████  | 46547/57600 [8:10:54<1:54:39,  1.61it/s]
 81%|████████  | 46548/57600 [8:10:55<1:53:27,  1.62it/s]
 81%|████████  | 46549/57600 [8:10:55<1:58:24,  1.56it/s]
 81%|████████  | 46550/57600 [8:10:56<1:59:10,  1.55it/s]
 81%|████████  | 46551/57600 [8:10:57<2:00:05,  1.53it/s]
 81%|████████  | 46552/57600 [8:10:57<1:56:56,  1.57it/s]
 81%|████████  | 46553/57600 [8:10:58<1:56:26,  1.58it/s]
 81%|████████  | 46554/57600 [8:10:58<1:58:03,  1.56it/s]
 81%|████████  | 46555/57600 [8:10:59<2:00:39,  1.53it/s]
 81%|████████  | 46556/57600 [8:11:00<1:57:36,  1.57it/s]
 81%|████████  | 46557/57600 [8:11:00<1:55:51,  1.59it/s]
 81%|████████  | 46558/57600 [8:11:01<1:54:13,  1.61it/s]
 81%|████████  | 46559/57600 [8:11:02<1:52:41,  1.63it/s]
 81%|████████  | 46560/57600 [8:11:02<1:51:25,  1.65it/s]
                                                         
{'loss': 1.1214, 'learning_rate': 2.7310104529616725e-07, 'epoch': 513.91}
+
 81%|████████  | 46560/57600 [8:11:02<1:51:25,  1.65it/s]
 81%|████████  | 46561/57600 [8:11:03<1:54:44,  1.60it/s]
 81%|████████  | 46562/57600 [8:11:03<1:59:19,  1.54it/s]
 81%|████████  | 46563/57600 [8:11:04<1:57:40,  1.56it/s]
 81%|████████  | 46564/57600 [8:11:05<2:00:44,  1.52it/s]
 81%|████████  | 46565/57600 [8:11:05<1:56:18,  1.58it/s]
 81%|████████  | 46566/57600 [8:11:06<1:56:53,  1.57it/s]
 81%|████████  | 46567/57600 [8:11:07<1:58:44,  1.55it/s]
 81%|████████  | 46568/57600 [8:11:07<2:02:54,  1.50it/s]
 81%|████████  | 46569/57600 [8:11:08<2:03:36,  1.49it/s]
 81%|████████  | 46570/57600 [8:11:09<2:02:18,  1.50it/s]
 81%|████████  | 46571/57600 [8:11:09<1:59:44,  1.54it/s]
 81%|████████  | 46572/57600 [8:11:10<1:57:42,  1.56it/s]
 81%|████████  | 46573/57600 [8:11:11<1:54:52,  1.60it/s]
 81%|████████  | 46574/57600 [8:11:11<1:54:00,  1.61it/s]
 81%|████████  | 46575/57600 [8:11:12<1:52:36,  1.63it/s]
 81%|████████  | 46576/57600 [8:11:12<1:53:18,  1.62it/s]
 81%|████████  | 46577/57600 [8:11:13<1:51:26,  1.65it/s]
 81%|████████  | 46578/57600 [8:11:14<1:52:45,  1.63it/s]
 81%|████████  | 46579/57600 [8:11:14<1:51:42,  1.64it/s]
 81%|████████  | 46580/57600 [8:11:15<1:51:10,  1.65it/s]
                                                         
{'loss': 1.1173, 'learning_rate': 2.7278745644599305e-07, 'epoch': 514.13}
+
 81%|████████  | 46580/57600 [8:11:15<1:51:10,  1.65it/s]
 81%|████████  | 46581/57600 [8:11:15<1:51:29,  1.65it/s]
 81%|████████  | 46582/57600 [8:11:16<1:54:27,  1.60it/s]
 81%|████████  | 46583/57600 [8:11:17<1:57:00,  1.57it/s]
 81%|████████  | 46584/57600 [8:11:17<1:57:40,  1.56it/s]
 81%|████████  | 46585/57600 [8:11:18<1:57:06,  1.57it/s]
 81%|████████  | 46586/57600 [8:11:19<1:55:35,  1.59it/s]
 81%|████████  | 46587/57600 [8:11:19<1:54:38,  1.60it/s]
 81%|████████  | 46588/57600 [8:11:20<1:57:28,  1.56it/s]
 81%|████████  | 46589/57600 [8:11:21<1:57:34,  1.56it/s]
 81%|████████  | 46590/57600 [8:11:21<1:56:44,  1.57it/s]
 81%|████████  | 46591/57600 [8:11:22<1:55:18,  1.59it/s]
 81%|████████  | 46592/57600 [8:11:23<2:00:42,  1.52it/s]
 81%|████████  | 46593/57600 [8:11:23<1:57:28,  1.56it/s]
 81%|████████  | 46594/57600 [8:11:24<1:55:07,  1.59it/s]
 81%|████████  | 46595/57600 [8:11:24<1:54:30,  1.60it/s]
 81%|████████  | 46596/57600 [8:11:25<1:52:18,  1.63it/s]
 81%|████████  | 46597/57600 [8:11:26<1:55:31,  1.59it/s]
 81%|████████  | 46598/57600 [8:11:26<1:54:02,  1.61it/s]
 81%|████████  | 46599/57600 [8:11:27<1:51:30,  1.64it/s]
 81%|████████  | 46600/57600 [8:11:27<1:50:10,  1.66it/s]
                                                         
{'loss': 1.1241, 'learning_rate': 2.7247386759581875e-07, 'epoch': 514.35}
+
 81%|████████  | 46600/57600 [8:11:27<1:50:10,  1.66it/s]
 81%|████████  | 46601/57600 [8:11:28<1:48:12,  1.69it/s]
 81%|████████  | 46602/57600 [8:11:29<1:54:56,  1.59it/s]
 81%|████████  | 46603/57600 [8:11:29<1:56:57,  1.57it/s]
 81%|████████  | 46604/57600 [8:11:30<1:54:51,  1.60it/s]
 81%|████████  | 46605/57600 [8:11:30<1:52:17,  1.63it/s]
 81%|████████  | 46606/57600 [8:11:31<1:52:13,  1.63it/s]
 81%|██████���█  | 46607/57600 [8:11:32<1:55:25,  1.59it/s]
 81%|████████  | 46608/57600 [8:11:32<1:52:51,  1.62it/s]
 81%|████████  | 46609/57600 [8:11:33<1:54:23,  1.60it/s]
 81%|████████  | 46610/57600 [8:11:34<1:55:19,  1.59it/s]
 81%|████████  | 46611/57600 [8:11:34<1:51:58,  1.64it/s]
 81%|████████  | 46612/57600 [8:11:35<1:49:30,  1.67it/s]
 81%|████████  | 46613/57600 [8:11:35<1:50:54,  1.65it/s]
 81%|████████  | 46614/57600 [8:11:36<1:52:31,  1.63it/s]
 81%|████████  | 46615/57600 [8:11:37<1:54:01,  1.61it/s]
 81%|████████  | 46616/57600 [8:11:37<1:52:57,  1.62it/s]
 81%|████████  | 46617/57600 [8:11:38<1:58:02,  1.55it/s]
 81%|████████  | 46618/57600 [8:11:39<1:55:40,  1.58it/s]
 81%|████████  | 46619/57600 [8:11:39<1:56:16,  1.57it/s]
 81%|████████  | 46620/57600 [8:11:40<1:54:41,  1.60it/s]
                                                         
{'loss': 1.136, 'learning_rate': 2.721602787456446e-07, 'epoch': 514.57}
+
 81%|████████  | 46620/57600 [8:11:40<1:54:41,  1.60it/s]
 81%|████████  | 46621/57600 [8:11:40<1:51:56,  1.63it/s]
 81%|████████  | 46622/57600 [8:11:41<1:55:49,  1.58it/s]
 81%|████████  | 46623/57600 [8:11:42<1:54:05,  1.60it/s]
 81%|████████  | 46624/57600 [8:11:42<1:51:23,  1.64it/s]
 81%|████████  | 46625/57600 [8:11:43<1:51:13,  1.64it/s]
 81%|████████  | 46626/57600 [8:11:43<1:50:26,  1.66it/s]
 81%|████████  | 46627/57600 [8:11:44<1:53:18,  1.61it/s]
 81%|████████  | 46628/57600 [8:11:45<1:52:55,  1.62it/s]
 81%|████████  | 46629/57600 [8:11:45<1:53:18,  1.61it/s]
 81%|████████  | 46630/57600 [8:11:46<1:55:27,  1.58it/s]
 81%|████████  | 46631/57600 [8:11:47<1:53:37,  1.61it/s]
 81%|████████  | 46632/57600 [8:11:47<1:55:52,  1.58it/s]
 81%|████████  | 46633/57600 [8:11:48<1:54:13,  1.60it/s]
 81%|████████  | 46634/57600 [8:11:48<1:50:57,  1.65it/s]
 81%|████████  | 46635/57600 [8:11:49<1:50:40,  1.65it/s]
 81%|████████  | 46636/57600 [8:11:50<1:52:30,  1.62it/s]
 81%|████████  | 46637/57600 [8:11:50<1:52:31,  1.62it/s]
 81%|████████  | 46638/57600 [8:11:51<1:55:12,  1.59it/s]
 81%|████████  | 46639/57600 [8:11:52<1:53:27,  1.61it/s]
 81%|████████  | 46640/57600 [8:11:52<1:51:55,  1.63it/s]
                                                         
{'loss': 1.1653, 'learning_rate': 2.7184668989547036e-07, 'epoch': 514.79}
+
 81%|████████  | 46640/57600 [8:11:52<1:51:55,  1.63it/s]
 81%|████████  | 46641/57600 [8:11:53<1:54:33,  1.59it/s]
 81%|████████  | 46642/57600 [8:11:53<1:52:39,  1.62it/s]
 81%|████████  | 46643/57600 [8:11:54<1:51:54,  1.63it/s]
 81%|████████  | 46644/57600 [8:11:55<1:52:11,  1.63it/s]
 81%|████████  | 46645/57600 [8:11:55<1:52:09,  1.63it/s]
 81%|████████  | 46646/57600 [8:11:56<1:54:05,  1.60it/s]
 81%|████████  | 46647/57600 [8:11:57<2:00:27,  1.52it/s]
 81%|████████  | 46648/57600 [8:11:57<1:55:48,  1.58it/s]
 81%|████████  | 46649/57600 [8:11:58<1:56:31,  1.57it/s]
 81%|████████  | 46650/57600 [8:11:59<1:59:36,  1.53it/s]
 81%|████████  | 46651/57600 [8:11:59<1:58:33,  1.54it/s]
 81%|████████  | 46652/57600 [8:12:00<1:55:39,  1.58it/s]
 81%|████████  | 46653/57600 [8:12:00<1:56:24,  1.57it/s]
 81%|████████  | 46654/57600 [8:12:01<1:52:00,  1.63it/s]
 81%|████████  | 46655/57600 [8:12:02<1:54:11,  1.60it/s]
 81%|████████  | 46656/57600 [8:12:02<1:54:25,  1.59it/s]
 81%|████████  | 46657/57600 [8:12:03<1:54:56,  1.59it/s]
 81%|████████  | 46658/57600 [8:12:04<2:02:18,  1.49it/s]
 81%|████████  | 46659/57600 [8:12:04<1:58:32,  1.54it/s]
 81%|████████  | 46660/57600 [8:12:05<2:01:28,  1.50it/s]
                                                         
{'loss': 1.0816, 'learning_rate': 2.7153310104529617e-07, 'epoch': 515.01}
+
 81%|████████  | 46660/57600 [8:12:05<2:01:28,  1.50it/s]
 81%|████████  | 46661/57600 [8:12:06<2:03:02,  1.48it/s]
 81%|████████  | 46662/57600 [8:12:06<1:58:37,  1.54it/s]
 81%|████████  | 46663/57600 [8:12:07<1:57:17,  1.55it/s]
 81%|████████  | 46664/57600 [8:12:08<1:57:49,  1.55it/s]
 81%|████████  | 46665/57600 [8:12:08<1:57:20,  1.55it/s]
 81%|████████  | 46666/57600 [8:12:09<1:55:18,  1.58it/s]
 81%|████████  | 46667/57600 [8:12:09<1:57:26,  1.55it/s]
 81%|████████  | 46668/57600 [8:12:10<1:57:06,  1.56it/s]
 81%|████████  | 46669/57600 [8:12:11<1:57:10,  1.55it/s]
 81%|████████  | 46670/57600 [8:12:11<1:54:34,  1.59it/s]
 81%|████████  | 46671/57600 [8:12:12<1:53:45,  1.60it/s]
 81%|████████  | 46672/57600 [8:12:13<1:55:54,  1.57it/s]
 81%|████████  | 46673/57600 [8:12:13<1:56:26,  1.56it/s]
 81%|████████  | 46674/57600 [8:12:14<1:58:39,  1.53it/s]
 81%|████████  | 46675/57600 [8:12:15<1:54:56,  1.58it/s]
 81%|████████  | 46676/57600 [8:12:15<1:52:57,  1.61it/s]
 81%|████████  | 46677/57600 [8:12:16<2:01:34,  1.50it/s]
 81%|████████  | 46678/57600 [8:12:17<2:02:14,  1.49it/s]
 81%|████████  | 46679/57600 [8:12:17<1:59:39,  1.52it/s]
 81%|████████  | 46680/57600 [8:12:18<1:56:59,  1.56it/s]
                                                         
{'loss': 1.0901, 'learning_rate': 2.7121951219512187e-07, 'epoch': 515.23}
+
 81%|████████  | 46680/57600 [8:12:18<1:56:59,  1.56it/s]
 81%|████████  | 46681/57600 [8:12:19<1:57:44,  1.55it/s]
 81%|████████  | 46682/57600 [8:12:19<1:55:24,  1.58it/s]
 81%|████████  | 46683/57600 [8:12:20<1:53:30,  1.60it/s]
 81%|████████  | 46684/57600 [8:12:20<1:55:30,  1.58it/s]
 81%|████████  | 46685/57600 [8:12:21<1:52:02,  1.62it/s]
 81%|████████  | 46686/57600 [8:12:22<1:51:38,  1.63it/s]
 81%|████████  | 46687/57600 [8:12:22<1:52:27,  1.62it/s]
 81%|████████  | 46688/57600 [8:12:23<1:55:54,  1.57it/s]
 81%|████████  | 46689/57600 [8:12:24<1:56:28,  1.56it/s]
 81%|████████  | 46690/57600 [8:12:24<1:58:49,  1.53it/s]
 81%|████████  | 46691/57600 [8:12:25<1:58:50,  1.53it/s]
 81%|████████  | 46692/57600 [8:12:25<1:55:00,  1.58it/s]
 81%|████████  | 46693/57600 [8:12:26<1:54:22,  1.59it/s]
 81%|████████  | 46694/57600 [8:12:27<1:52:27,  1.62it/s]
 81%|████████  | 46695/57600 [8:12:27<1:52:35,  1.61it/s]
 81%|████████  | 46696/57600 [8:12:28<1:54:43,  1.58it/s]
 81%|████████  | 46697/57600 [8:12:29<1:52:35,  1.61it/s]
 81%|████████  | 46698/57600 [8:12:29<1:55:20,  1.58it/s]
 81%|████████  | 46699/57600 [8:12:30<1:56:06,  1.56it/s]
 81%|████████  | 46700/57600 [8:12:30<1:53:03,  1.61it/s]
                                                         
{'loss': 1.1228, 'learning_rate': 2.709059233449477e-07, 'epoch': 515.45}
+
 81%|████████  | 46700/57600 [8:12:30<1:53:03,  1.61it/s]
 81%|████████  | 46701/57600 [8:12:31<1:55:56,  1.57it/s]
 81%|████████  | 46702/57600 [8:12:32<1:56:48,  1.55it/s]
 81%|████████  | 46703/57600 [8:12:32<1:56:59,  1.55it/s]
 81%|████████  | 46704/57600 [8:12:33<1:55:02,  1.58it/s]
 81%|████████  | 46705/57600 [8:12:34<1:58:18,  1.53it/s]
 81%|████████  | 46706/57600 [8:12:34<1:56:37,  1.56it/s]
 81%|████████  | 46707/57600 [8:12:35<1:56:15,  1.56it/s]
 81%|████████  | 46708/57600 [8:12:36<1:53:09,  1.60it/s]
 81%|████████  | 46709/57600 [8:12:36<1:53:14,  1.60it/s]
 81%|████████  | 46710/57600 [8:12:37<1:51:15,  1.63it/s]
 81%|████████  | 46711/57600 [8:12:37<1:50:20,  1.64it/s]
 81%|████████  | 46712/57600 [8:12:38<1:52:37,  1.61it/s]
 81%|████████  | 46713/57600 [8:12:39<1:50:25,  1.64it/s]
 81%|████████  | 46714/57600 [8:12:39<1:53:18,  1.60it/s]
 81%|████████  | 46715/57600 [8:12:40<1:53:25,  1.60it/s]
 81%|████████  | 46716/57600 [8:12:40<1:53:15,  1.60it/s]
 81%|████████  | 46717/57600 [8:12:41<1:52:58,  1.61it/s]
 81%|████████  | 46718/57600 [8:12:42<1:50:31,  1.64it/s]
 81%|████████  | 46719/57600 [8:12:42<1:50:36,  1.64it/s]
 81%|████████  | 46720/57600 [8:12:43<1:51:58,  1.62it/s]
                                                         
{'loss': 1.1257, 'learning_rate': 2.705923344947736e-07, 'epoch': 515.67}
+
 81%|████████  | 46720/57600 [8:12:43<1:51:58,  1.62it/s]
 81%|████████  | 46721/57600 [8:12:44<1:53:01,  1.60it/s]
 81%|████████  | 46722/57600 [8:12:44<1:52:46,  1.61it/s]
 81%|████████  | 46723/57600 [8:12:45<1:49:09,  1.66it/s]
 81%|████████  | 46724/57600 [8:12:45<1:48:02,  1.68it/s]
 81%|████████  | 46725/57600 [8:12:46<1:47:55,  1.68it/s]
 81%|████████  | 46726/57600 [8:12:47<1:51:27,  1.63it/s]
 81%|████████  | 46727/57600 [8:12:47<1:51:53,  1.62it/s]
 81%|████████  | 46728/57600 [8:12:48<1:49:30,  1.65it/s]
 81%|████████  | 46729/57600 [8:12:48<1:54:59,  1.58it/s]
 81%|████████  | 46730/57600 [8:12:49<1:51:56,  1.62it/s]
 81%|████████  | 46731/57600 [8:12:50<1:51:44,  1.62it/s]
 81%|████████  | 46732/57600 [8:12:50<1:51:32,  1.62it/s]
 81%|████████  | 46733/57600 [8:12:51<1:50:32,  1.64it/s]
 81%|████████  | 46734/57600 [8:12:52<1:51:32,  1.62it/s]
 81%|████████  | 46735/57600 [8:12:52<1:50:26,  1.64it/s]
 81%|████████  | 46736/57600 [8:12:53<1:53:09,  1.60it/s]
 81%|████████  | 46737/57600 [8:12:53<1:56:46,  1.55it/s]
 81%|████████  | 46738/57600 [8:12:54<1:56:28,  1.55it/s]
 81%|████████  | 46739/57600 [8:12:55<1:55:50,  1.56it/s]
 81%|████████  | 46740/57600 [8:12:55<1:53:11,  1.60it/s]
                                                         
{'loss': 1.1466, 'learning_rate': 2.702787456445993e-07, 'epoch': 515.89}
+
 81%|████████  | 46740/57600 [8:12:55<1:53:11,  1.60it/s]
 81%|████████  | 46741/57600 [8:12:56<1:53:16,  1.60it/s]
 81%|████████  | 46742/57600 [8:12:57<1:52:31,  1.61it/s]
 81%|████████  | 46743/57600 [8:12:57<1:55:17,  1.57it/s]
 81%|████████  | 46744/57600 [8:12:58<1:53:42,  1.59it/s]
 81%|████████  | 46745/57600 [8:12:58<1:50:57,  1.63it/s]
 81%|████████  | 46746/57600 [8:12:59<1:51:38,  1.62it/s]
 81%|████████  | 46747/57600 [8:13:00<1:54:27,  1.58it/s]
 81%|████████  | 46748/57600 [8:13:00<1:52:22,  1.61it/s]
 81%|████████  | 46749/57600 [8:13:01<1:53:39,  1.59it/s]
 81%|████████  | 46750/57600 [8:13:02<1:56:00,  1.56it/s]
 81%|████████  | 46751/57600 [8:13:02<1:52:09,  1.61it/s]
 81%|████████  | 46752/57600 [8:13:03<1:49:30,  1.65it/s]
 81%|████████  | 46753/57600 [8:13:03<1:50:52,  1.63it/s]
 81%|████████  | 46754/57600 [8:13:04<1:52:50,  1.60it/s]
 81%|████████  | 46755/57600 [8:13:05<1:53:31,  1.59it/s]
 81%|████████  | 46756/57600 [8:13:05<1:56:11,  1.56it/s]
 81%|████████  | 46757/57600 [8:13:06<1:55:18,  1.57it/s]
 81%|████████  | 46758/57600 [8:13:07<1:51:41,  1.62it/s]
 81%|████████  | 46759/57600 [8:13:07<1:51:30,  1.62it/s]
 81%|████████  | 46760/57600 [8:13:08<1:53:43,  1.59it/s]
                                                         
{'loss': 1.135, 'learning_rate': 2.699651567944251e-07, 'epoch': 516.11}
+
 81%|████████  | 46760/57600 [8:13:08<1:53:43,  1.59it/s]
 81%|████████  | 46761/57600 [8:13:08<1:51:49,  1.62it/s]
 81%|████████  | 46762/57600 [8:13:09<1:52:22,  1.61it/s]
 81%|████████  | 46763/57600 [8:13:10<1:53:50,  1.59it/s]
 81%|████████  | 46764/57600 [8:13:10<1:52:58,  1.60it/s]
 81%|████████  | 46765/57600 [8:13:11<1:50:40,  1.63it/s]
 81%|████████  | 46766/57600 [8:13:12<1:50:15,  1.64it/s]
 81%|████████  | 46767/57600 [8:13:12<1:50:52,  1.63it/s]
 81%|████████  | 46768/57600 [8:13:13<1:50:34,  1.63it/s]
 81%|████████  | 46769/57600 [8:13:13<1:51:14,  1.62it/s]
 81%|████████  | 46770/57600 [8:13:14<1:50:42,  1.63it/s]
 81%|████████  | 46771/57600 [8:13:15<1:54:48,  1.57it/s]
 81%|████████  | 46772/57600 [8:13:15<1:52:41,  1.60it/s]
 81%|████████  | 46773/57600 [8:13:16<1:53:43,  1.59it/s]
 81%|████████  | 46774/57600 [8:13:17<1:55:02,  1.57it/s]
 81%|████████  | 46775/57600 [8:13:17<1:51:35,  1.62it/s]
 81%|████████  | 46776/57600 [8:13:18<1:52:19,  1.61it/s]
 81%|████████  | 46777/57600 [8:13:18<1:53:56,  1.58it/s]
 81%|████████  | 46778/57600 [8:13:19<1:54:20,  1.58it/s]
 81%|████████  | 46779/57600 [8:13:20<1:55:04,  1.57it/s]
 81%|████████  | 46780/57600 [8:13:20<1:52:00,  1.61it/s]
                                                         
{'loss': 1.1148, 'learning_rate': 2.6965156794425084e-07, 'epoch': 516.34}
+
 81%|████████  | 46780/57600 [8:13:20<1:52:00,  1.61it/s]
 81%|████████  | 46781/57600 [8:13:21<1:53:07,  1.59it/s]
 81%|████████  | 46782/57600 [8:13:22<1:51:09,  1.62it/s]
 81%|████████  | 46783/57600 [8:13:22<1:55:33,  1.56it/s]
 81%|████████  | 46784/57600 [8:13:23<1:53:05,  1.59it/s]
 81%|████████  | 46785/57600 [8:13:23<1:52:05,  1.61it/s]
 81%|████████  | 46786/57600 [8:13:24<1:54:45,  1.57it/s]
 81%|████████  | 46787/57600 [8:13:25<1:58:25,  1.52it/s]
 81%|████████  | 46788/57600 [8:13:25<1:55:46,  1.56it/s]
 81%|████████  | 46789/57600 [8:13:26<1:54:32,  1.57it/s]
 81%|████████  | 46790/57600 [8:13:27<1:52:39,  1.60it/s]
 81%|████████  | 46791/57600 [8:13:27<1:53:31,  1.59it/s]
 81%|████████  | 46792/57600 [8:13:28<1:51:37,  1.61it/s]
 81%|████████  | 46793/57600 [8:13:28<1:49:55,  1.64it/s]
 81%|████████  | 46794/57600 [8:13:29<1:51:34,  1.61it/s]
 81%|████████  | 46795/57600 [8:13:30<1:51:37,  1.61it/s]
 81%|████████  | 46796/57600 [8:13:30<1:52:47,  1.60it/s]
 81%|████████  | 46797/57600 [8:13:31<1:51:08,  1.62it/s]
 81%|████████  | 46798/57600 [8:13:32<1:55:38,  1.56it/s]
 81%|████████  | 46799/57600 [8:13:32<1:54:11,  1.58it/s]
 81%|████████▏ | 46800/57600 [8:13:33<1:55:51,  1.55it/s]
                                                         
{'loss': 1.1246, 'learning_rate': 2.6933797909407664e-07, 'epoch': 516.56}
+
 81%|████████▏ | 46800/57600 [8:13:33<1:55:51,  1.55it/s]Generation Kwargs:
+{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}
+
+
  0%|          | 0/6 [00:00<?, ?it/s]
+
 33%|███▎      | 2/6 [00:00<00:00, 10.89it/s]
+
 67%|██████▋   | 4/6 [00:00<00:00,  7.09it/s]
+
 83%|████████▎ | 5/6 [00:00<00:00,  4.54it/s]
+
100%|██████████| 6/6 [00:01<00:00,  3.19it/s]{'score': 47.88968541823464, 'counts': [143, 90, 62, 44], 'totals': [208, 178, 149, 121], 'precisions': [68.75, 50.561797752808985, 41.61073825503356, 36.36363636363637], 'bp': 1.0, 'sys_len': 208, 'ref_len': 207}
+
                                                         
+
                                             
{'eval_loss': 1.970095157623291, 'eval_bleu': 47.8897, 'eval_gen_len': 8.4667, 'eval_runtime': 3.2787, 'eval_samples_per_second': 9.15, 'eval_steps_per_second': 1.83, 'epoch': 516.56}
+
 81%|████████▏ | 46800/57600 [8:13:36<1:55:51,  1.55it/s]
+
100%|██████████| 6/6 [00:03<00:00,  3.19it/s]
+
                                             [WARNING|configuration_utils.py:448] 2024-10-02 15:07:49,569 >> 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}
+
 81%|████████▏ | 46801/57600 [8:14:00<25:21:44,  8.45s/it]
 81%|████████▏ | 46802/57600 [8:14:00<18:23:37,  6.13s/it]
 81%|████████▏ | 46803/57600 [8:14:01<13:29:29,  4.50s/it]
 81%|████████▏ | 46804/57600 [8:14:02<10:08:22,  3.38s/it]
 81%|████████▏ | 46805/57600 [8:14:03<7:46:35,  2.59s/it] 
 81%|████████▏ | 46806/57600 [8:14:03<6:03:29,  2.02s/it]
 81%|████████▏ | 46807/57600 [8:14:04<4:53:15,  1.63s/it]
 81%|████████▏ | 46808/57600 [8:14:05<4:01:25,  1.34s/it]
 81%|████████▏ | 46809/57600 [8:14:05<3:23:32,  1.13s/it]
 81%|████████▏ | 46810/57600 [8:14:06<2:57:29,  1.01it/s]
 81%|████████▏ | 46811/57600 [8:14:07<2:42:24,  1.11it/s]
 81%|████████▏ | 46812/57600 [8:14:07<2:30:06,  1.20it/s]
 81%|████████▏ | 46813/57600 [8:14:08<2:24:22,  1.25it/s]
 81%|████████▏ | 46814/57600 [8:14:09<2:21:49,  1.27it/s]
 81%|████████▏ | 46815/57600 [8:14:09<2:12:21,  1.36it/s]
 81%|████████▏ | 46816/57600 [8:14:10<2:11:33,  1.37it/s]
 81%|████████▏ | 46817/57600 [8:14:11<2:06:15,  1.42it/s]
 81%|████████▏ | 46818/57600 [8:14:11<2:00:41,  1.49it/s]
 81%|████████▏ | 46819/57600 [8:14:12<2:06:00,  1.43it/s]
 81%|████████▏ | 46820/57600 [8:14:13<2:07:52,  1.40it/s]
                                                         
{'loss': 1.0884, 'learning_rate': 2.6902439024390234e-07, 'epoch': 516.78}
+
 81%|████████▏ | 46820/57600 [8:14:13<2:07:52,  1.40it/s]
 81%|████████▏ | 46821/57600 [8:14:14<2:04:56,  1.44it/s]
 81%|████████▏ | 46822/57600 [8:14:14<2:01:52,  1.47it/s]
 81%|████████▏ | 46823/57600 [8:14:15<1:59:12,  1.51it/s]
 81%|████████▏ | 46824/57600 [8:14:15<1:53:31,  1.58it/s]
 81%|████████▏ | 46825/57600 [8:14:16<1:54:10,  1.57it/s]
 81%|████████▏ | 46826/57600 [8:14:17<2:00:40,  1.49it/s]
 81%|████████▏ | 46827/57600 [8:14:17<2:02:13,  1.47it/s]
 81%|████████▏ | 46828/57600 [8:14:18<2:04:56,  1.44it/s]
 81%|████████▏ | 46829/57600 [8:14:19<2:05:21,  1.43it/s]
 81%|████████▏ | 46830/57600 [8:14:20<2:08:13,  1.40it/s]
 81%|████████▏ | 46831/57600 [8:14:20<2:03:37,  1.45it/s]
 81%|████████▏ | 46832/57600 [8:14:21<2:02:33,  1.46it/s]
 81%|████████▏ | 46833/57600 [8:14:22<1:58:15,  1.52it/s]
 81%|████████▏ | 46834/57600 [8:14:22<1:55:26,  1.55it/s]
 81%|████████▏ | 46835/57600 [8:14:23<1:58:41,  1.51it/s]
 81%|████████▏ | 46836/57600 [8:14:23<1:53:55,  1.57it/s]
 81%|████████▏ | 46837/57600 [8:14:24<1:56:25,  1.54it/s]
 81%|████████▏ | 46838/57600 [8:14:25<1:54:00,  1.57it/s]
 81%|████████▏ | 46839/57600 [8:14:25<1:51:18,  1.61it/s]
 81%|████████▏ | 46840/57600 [8:14:26<1:51:48,  1.60it/s]
                                                         
{'loss': 1.0961, 'learning_rate': 2.687108013937282e-07, 'epoch': 517.0}
+
 81%|████████▏ | 46840/57600 [8:14:26<1:51:48,  1.60it/s]/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()
+
 81%|████████▏ | 46841/57600 [8:14:27<2:00:22,  1.49it/s]
 81%|████████▏ | 46842/57600 [8:14:27<1:59:00,  1.51it/s]
 81%|████████▏ | 46843/57600 [8:14:28<1:59:42,  1.50it/s]
 81%|████████▏ | 46844/57600 [8:14:29<2:00:59,  1.48it/s]
 81%|████████▏ | 46845/57600 [8:14:29<1:59:27,  1.50it/s]
 81%|████████▏ | 46846/57600 [8:14:30<2:01:29,  1.48it/s]
 81%|████████▏ | 46847/57600 [8:14:31<2:00:42,  1.48it/s]
 81%|████████▏ | 46848/57600 [8:14:31<2:01:04,  1.48it/s]
 81%|████████▏ | 46849/57600 [8:14:32<1:59:15,  1.50it/s]
 81%|████████▏ | 46850/57600 [8:14:33<1:58:48,  1.51it/s]
 81%|████████▏ | 46851/57600 [8:14:33<1:59:12,  1.50it/s]
 81%|████████▏ | 46852/57600 [8:14:34<1:57:38,  1.52it/s]
 81%|████████▏ | 46853/57600 [8:14:35<1:57:32,  1.52it/s]
 81%|████████▏ | 46854/57600 [8:14:35<1:59:43,  1.50it/s]
 81%|████████▏ | 46855/57600 [8:14:36<2:00:55,  1.48it/s]
 81%|████████▏ | 46856/57600 [8:14:37<2:03:25,  1.45it/s]
 81%|████████▏ | 46857/57600 [8:14:37<2:02:22,  1.46it/s]
 81%|████████▏ | 46858/57600 [8:14:38<2:03:18,  1.45it/s]
 81%|████████▏ | 46859/57600 [8:14:39<2:04:23,  1.44it/s]
 81%|████████▏ | 46860/57600 [8:14:39<2:00:33,  1.48it/s]
                                                         
{'loss': 1.0813, 'learning_rate': 2.6839721254355406e-07, 'epoch': 517.22}
+
 81%|████████▏ | 46860/57600 [8:14:39<2:00:33,  1.48it/s]
 81%|████████▏ | 46861/57600 [8:14:40<2:06:26,  1.42it/s]
\ No newline at end of file