diff --git "a/run-2024-10-28T15:22:08+00:00.log" "b/run-2024-10-28T15:22:08+00:00.log"
--- "a/run-2024-10-28T15:22:08+00:00.log"
+++ "b/run-2024-10-28T15:22:08+00:00.log"
@@ -1110,4 +1110,1069 @@ Non-default generation parameters: {'max_length': 200, 'early_stopping': True, '
 
 75%|███████▌  | 46429/61904 [1:42:46<1071:42:26, 249.31s/it]
 75%|███████▌  | 46430/61904 [1:42:48<752:13:49, 175.01s/it] 
 75%|███████▌  | 46431/61904 [1:42:49<528:27:03, 122.95s/it]
 75%|███████▌  | 46432/61904 [1:42:51<371:51:40, 86.52s/it] 
 75%|███████▌  | 46433/61904 [1:42:52<262:06:56, 60.99s/it]
 75%|███████▌  | 46434/61904 [1:42:53<185:19:45, 43.13s/it]
 75%|███████▌  | 46435/61904 [1:42:55<131:31:54, 30.61s/it]
 75%|███████▌  | 46436/61904 [1:42:56<93:45:21, 21.82s/it] 
 75%|███████▌  | 46437/61904 [1:42:58<67:32:22, 15.72s/it]
 75%|███████▌  | 46438/61904 [1:42:59<49:09:39, 11.44s/it]
 75%|███████▌  | 46439/61904 [1:43:01<36:13:35,  8.43s/it]
 75%|███████▌  | 46440/61904 [1:43:02<27:10:21,  6.33s/it]
                                                          
{'loss': 2.4527, 'learning_rate': 1.2506158433813043e-07, 'epoch': 12.0}
 
 75%|███████▌  | 46440/61904 [1:43:02<27:10:21,  6.33s/it]
 75%|███████▌  | 46441/61904 [1:43:03<20:55:43,  4.87s/it]
 75%|███████▌  | 46442/61904 [1:43:05<16:29:49,  3.84s/it]
 75%|███████▌  | 46443/61904 [1:43:06<13:28:42,  3.14s/it]
 75%|███████▌  | 46444/61904 [1:43:08<11:29:30,  2.68s/it]
 75%|███████▌  | 46445/61904 [1:43:09<9:53:21,  2.30s/it] 
 75%|███████▌  | 46446/61904 [1:43:11<8:38:04,  2.01s/it]
 75%|███████▌  | 46447/61904 [1:43:12<8:09:47,  1.90s/it]
 75%|███████▌  | 46448/61904 [1:43:14<7:37:23,  1.78s/it]
 75%|███████▌  | 46449/61904 [1:43:15<7:16:07,  1.69s/it]
 75%|███████▌  | 46450/61904 [1:43:17<6:55:58,  1.61s/it]
 75%|███████▌  | 46451/61904 [1:43:18<6:49:45,  1.59s/it]
 75%|███████▌  | 46452/61904 [1:43:20<6:34:49,  1.53s/it]
 75%|███████▌  | 46453/61904 [1:43:21<6:30:23,  1.52s/it]
 75%|███████▌  | 46454/61904 [1:43:23<6:24:05,  1.49s/it]
 75%|███████▌  | 46455/61904 [1:43:24<6:11:39,  1.44s/it]
 75%|███████▌  | 46456/61904 [1:43:25<6:00:46,  1.40s/it]
 75%|███████▌  | 46457/61904 [1:43:27<6:07:43,  1.43s/it]
 75%|███████▌  | 46458/61904 [1:43:28<5:58:29,  1.39s/it]
 75%|███████▌  | 46459/61904 [1:43:30<6:02:24,  1.41s/it]
 75%|███████▌  | 46460/61904 [1:43:31<6:05:42,  1.42s/it]
                                                         
{'loss': 2.436, 'learning_rate': 1.250291715285881e-07, 'epoch': 12.01}
 
 75%|███████▌  | 46460/61904 [1:43:31<6:05:42,  1.42s/it]
 75%|███████▌  | 46461/61904 [1:43:32<5:59:07,  1.40s/it]
 75%|███████▌  | 46462/61904 [1:43:34<6:19:38,  1.48s/it]
 75%|███████▌  | 46463/61904 [1:43:35<6:04:33,  1.42s/it]
 75%|███████▌  | 46464/61904 [1:43:37<6:06:03,  1.42s/it]
 75%|███████▌  | 46465/61904 [1:43:38<5:56:54,  1.39s/it]
 75%|███████▌  | 46466/61904 [1:43:40<6:05:41,  1.42s/it]
 75%|███████▌  | 46467/61904 [1:43:41<6:33:40,  1.53s/it]
 75%|███████▌  | 46468/61904 [1:43:43<6:11:53,  1.45s/it]
 75%|███████▌  | 46469/61904 [1:43:44<6:02:19,  1.41s/it]
 75%|███████▌  | 46470/61904 [1:43:45<5:58:53,  1.40s/it]
 75%|███████▌  | 46471/61904 [1:43:47<6:09:47,  1.44s/it]
 75%|███████▌  | 46472/61904 [1:43:48<6:04:29,  1.42s/it]
 75%|███████▌  | 46473/61904 [1:43:49<5:57:32,  1.39s/it]
 75%|███████▌  | 46474/61904 [1:43:51<6:04:04,  1.42s/it]
 75%|███████▌  | 46475/61904 [1:43:52<6:07:06,  1.43s/it]
 75%|███████▌  | 46476/61904 [1:43:54<6:03:32,  1.41s/it]
 75%|███████▌  | 46477/61904 [1:43:55<6:01:12,  1.40s/it]
 75%|███████▌  | 46478/61904 [1:43:57<6:06:32,  1.43s/it]
 75%|███████▌  | 46479/61904 [1:43:58<6:13:43,  1.45s/it]
 75%|███████▌  | 46480/61904 [1:44:00<6:08:51,  1.43s/it]
                                                         
{'loss': 2.4514, 'learning_rate': 1.2499675871904575e-07, 'epoch': 12.01}
-
 75%|███████▌  | 46480/61904 [1:44:00<6:08:51,  1.43s/it]
 75%|███████▌  | 46481/61904 [1:44:01<6:03:09,  1.41s/it]
 75%|███████▌  | 46482/61904 [1:44:02<6:12:59,  1.45s/it]
 75%|███████▌  | 46483/61904 [1:44:04<6:12:53,  1.45s/it]
 75%|███████▌  | 46484/61904 [1:44:05<6:09:21,  1.44s/it]
 75%|███████▌  | 46485/61904 [1:44:07<6:21:03,  1.48s/it]
\ No newline at end of file
+
 75%|███████▌  | 46480/61904 [1:44:00<6:08:51,  1.43s/it]
 75%|███████▌  | 46481/61904 [1:44:01<6:03:09,  1.41s/it]
 75%|███████▌  | 46482/61904 [1:44:02<6:12:59,  1.45s/it]
 75%|███████▌  | 46483/61904 [1:44:04<6:12:53,  1.45s/it]
 75%|███████▌  | 46484/61904 [1:44:05<6:09:21,  1.44s/it]
 75%|███████▌  | 46485/61904 [1:44:07<6:21:03,  1.48s/it]
 75%|███████▌  | 46486/61904 [1:44:08<6:22:24,  1.49s/it]
 75%|███████▌  | 46487/61904 [1:44:10<6:06:39,  1.43s/it]
 75%|███████▌  | 46488/61904 [1:44:11<6:05:38,  1.42s/it]
 75%|███████▌  | 46489/61904 [1:44:13<6:15:42,  1.46s/it]
 75%|███████▌  | 46490/61904 [1:44:14<6:24:35,  1.50s/it]
 75%|███████▌  | 46491/61904 [1:44:16<6:21:28,  1.48s/it]
 75%|███████▌  | 46492/61904 [1:44:17<6:14:18,  1.46s/it]
 75%|███████▌  | 46493/61904 [1:44:18<6:01:39,  1.41s/it]
 75%|███████▌  | 46494/61904 [1:44:20<6:01:36,  1.41s/it]
 75%|███████▌  | 46495/61904 [1:44:21<5:58:13,  1.39s/it]
 75%|███████▌  | 46496/61904 [1:44:23<5:58:53,  1.40s/it]
 75%|███████▌  | 46497/61904 [1:44:24<6:00:11,  1.40s/it]
 75%|███████▌  | 46498/61904 [1:44:25<6:10:38,  1.44s/it]
 75%|███████▌  | 46499/61904 [1:44:27<6:10:45,  1.44s/it]
 75%|███████▌  | 46500/61904 [1:44:28<6:08:40,  1.44s/it]
                                                         
{'loss': 2.4921, 'learning_rate': 1.2496434590950344e-07, 'epoch': 12.02}
+
 75%|███████▌  | 46500/61904 [1:44:28<6:08:40,  1.44s/it]
 75%|███████▌  | 46501/61904 [1:44:30<6:11:17,  1.45s/it]
 75%|███████▌  | 46502/61904 [1:44:31<6:08:40,  1.44s/it]
 75%|███████▌  | 46503/61904 [1:44:33<6:09:02,  1.44s/it]
 75%|███████▌  | 46504/61904 [1:44:34<6:03:57,  1.42s/it]
 75%|███████▌  | 46505/61904 [1:44:36<6:23:08,  1.49s/it]
 75%|███████▌  | 46506/61904 [1:44:37<6:20:43,  1.48s/it]
 75%|███████▌  | 46507/61904 [1:44:39<6:11:00,  1.45s/it]
 75%|███████▌  | 46508/61904 [1:44:40<6:13:40,  1.46s/it]
 75%|███████▌  | 46509/61904 [1:44:41<6:04:44,  1.42s/it]
 75%|███████▌  | 46510/61904 [1:44:43<6:05:34,  1.42s/it]
 75%|███████▌  | 46511/61904 [1:44:44<6:00:37,  1.41s/it]
 75%|███████▌  | 46512/61904 [1:44:46<5:57:16,  1.39s/it]
 75%|███████▌  | 46513/61904 [1:44:47<6:11:53,  1.45s/it]
 75%|███████▌  | 46514/61904 [1:44:49<6:09:06,  1.44s/it]
 75%|███████▌  | 46515/61904 [1:44:50<5:57:08,  1.39s/it]
 75%|███████▌  | 46516/61904 [1:44:51<5:56:15,  1.39s/it]
 75%|███████▌  | 46517/61904 [1:44:53<6:25:19,  1.50s/it]
 75%|███████▌  | 46518/61904 [1:44:54<6:21:17,  1.49s/it]
 75%|███████▌  | 46519/61904 [1:44:56<6:16:53,  1.47s/it]
 75%|███████▌  | 46520/61904 [1:44:57<6:13:41,  1.46s/it]
                                                         
{'loss': 2.4637, 'learning_rate': 1.249319330999611e-07, 'epoch': 12.02}
+
 75%|███████▌  | 46520/61904 [1:44:57<6:13:41,  1.46s/it]
 75%|███████▌  | 46521/61904 [1:44:59<6:14:15,  1.46s/it]
 75%|███████▌  | 46522/61904 [1:45:00<6:10:10,  1.44s/it]
 75%|███████▌  | 46523/61904 [1:45:01<6:02:10,  1.41s/it]
 75%|███████▌  | 46524/61904 [1:45:03<5:58:39,  1.40s/it]
 75%|███████▌  | 46525/61904 [1:45:04<6:10:47,  1.45s/it]
 75%|███████▌  | 46526/61904 [1:45:06<6:22:39,  1.49s/it]
 75%|███████▌  | 46527/61904 [1:45:07<6:09:06,  1.44s/it]
 75%|███████▌  | 46528/61904 [1:45:09<6:13:14,  1.46s/it]
 75%|███████▌  | 46529/61904 [1:45:10<6:09:25,  1.44s/it]
 75%|███████▌  | 46530/61904 [1:45:12<6:05:26,  1.43s/it]
 75%|███████▌  | 46531/61904 [1:45:13<6:05:07,  1.43s/it]
 75%|███████▌  | 46532/61904 [1:45:15<6:13:37,  1.46s/it]
 75%|███████▌  | 46533/61904 [1:45:16<6:06:48,  1.43s/it]
 75%|███████▌  | 46534/61904 [1:45:17<6:16:55,  1.47s/it]
 75%|███████▌  | 46535/61904 [1:45:19<6:08:03,  1.44s/it]
 75%|███████▌  | 46536/61904 [1:45:20<6:09:34,  1.44s/it]
 75%|███████▌  | 46537/61904 [1:45:22<6:07:05,  1.43s/it]
 75%|███████▌  | 46538/61904 [1:45:23<6:06:29,  1.43s/it]
 75%|███████▌  | 46539/61904 [1:45:24<5:56:15,  1.39s/it]
 75%|███████▌  | 46540/61904 [1:45:26<6:12:00,  1.45s/it]
                                                         
{'loss': 2.4924, 'learning_rate': 1.2489952029041876e-07, 'epoch': 12.03}
+
 75%|███████▌  | 46540/61904 [1:45:26<6:12:00,  1.45s/it]
 75%|███████▌  | 46541/61904 [1:45:27<5:59:37,  1.40s/it]
 75%|████��██▌  | 46542/61904 [1:45:29<6:15:03,  1.46s/it]
 75%|███████▌  | 46543/61904 [1:45:30<6:06:06,  1.43s/it]
 75%|███████▌  | 46544/61904 [1:45:32<6:11:26,  1.45s/it]
 75%|███████▌  | 46545/61904 [1:45:33<6:08:02,  1.44s/it]
 75%|███████▌  | 46546/61904 [1:45:35<6:06:27,  1.43s/it]
 75%|███████▌  | 46547/61904 [1:45:36<6:07:01,  1.43s/it]
 75%|███████▌  | 46548/61904 [1:45:37<6:05:03,  1.43s/it]
 75%|███████▌  | 46549/61904 [1:45:39<6:00:49,  1.41s/it]
 75%|███████▌  | 46550/61904 [1:45:40<6:03:49,  1.42s/it]
 75%|███████▌  | 46551/61904 [1:45:42<6:02:40,  1.42s/it]
 75%|███████▌  | 46552/61904 [1:45:43<6:00:43,  1.41s/it]
 75%|███████▌  | 46553/61904 [1:45:44<5:58:25,  1.40s/it]
 75%|███████▌  | 46554/61904 [1:45:46<6:02:38,  1.42s/it]
 75%|███████▌  | 46555/61904 [1:45:48<6:16:35,  1.47s/it]
 75%|███████▌  | 46556/61904 [1:45:49<6:05:02,  1.43s/it]
 75%|███████▌  | 46557/61904 [1:45:50<6:14:31,  1.46s/it]
 75%|███████▌  | 46558/61904 [1:45:52<6:08:42,  1.44s/it]
 75%|███████▌  | 46559/61904 [1:45:53<6:00:12,  1.41s/it]
 75%|███████▌  | 46560/61904 [1:45:54<5:58:42,  1.40s/it]
                                                         
{'loss': 2.4788, 'learning_rate': 1.2486710748087643e-07, 'epoch': 12.03}
+
 75%|███████▌  | 46560/61904 [1:45:54<5:58:42,  1.40s/it]
 75%|███████▌  | 46561/61904 [1:45:56<6:04:12,  1.42s/it]
 75%|███████▌  | 46562/61904 [1:45:57<6:02:27,  1.42s/it]
 75%|███████▌  | 46563/61904 [1:45:59<5:59:00,  1.40s/it]
 75%|███████▌  | 46564/61904 [1:46:00<5:54:51,  1.39s/it]
 75%|███████▌  | 46565/61904 [1:46:02<5:58:12,  1.40s/it]
 75%|███████▌  | 46566/61904 [1:46:03<5:55:26,  1.39s/it]
 75%|███████▌  | 46567/61904 [1:46:04<5:44:22,  1.35s/it]
 75%|███████▌  | 46568/61904 [1:46:06<5:58:16,  1.40s/it]
 75%|███████▌  | 46569/61904 [1:46:07<5:56:17,  1.39s/it]
 75%|███████▌  | 46570/61904 [1:46:09<6:10:59,  1.45s/it]
 75%|███████▌  | 46571/61904 [1:46:10<6:14:12,  1.46s/it]
 75%|███████▌  | 46572/61904 [1:46:12<6:08:31,  1.44s/it]
 75%|███████▌  | 46573/61904 [1:46:13<6:07:39,  1.44s/it]
 75%|███████▌  | 46574/61904 [1:46:14<5:58:34,  1.40s/it]
 75%|███████▌  | 46575/61904 [1:46:16<5:58:23,  1.40s/it]
 75%|███████▌  | 46576/61904 [1:46:17<6:02:21,  1.42s/it]
 75%|███████▌  | 46577/61904 [1:46:19<6:04:54,  1.43s/it]
 75%|███████▌  | 46578/61904 [1:46:20<6:07:04,  1.44s/it]
 75%|███████▌  | 46579/61904 [1:46:21<6:03:50,  1.42s/it]
 75%|███████▌  | 46580/61904 [1:46:23<6:02:05,  1.42s/it]
                                                         
{'loss': 2.5291, 'learning_rate': 1.2483469467133411e-07, 'epoch': 12.04}
+
 75%|███████▌  | 46580/61904 [1:46:23<6:02:05,  1.42s/it]
 75%|███████▌  | 46581/61904 [1:46:24<6:07:38,  1.44s/it]
 75%|███████▌  | 46582/61904 [1:46:26<6:05:22,  1.43s/it]
 75%|███████▌  | 46583/61904 [1:46:27<6:10:57,  1.45s/it]
 75%|███████▌  | 46584/61904 [1:46:29<6:05:36,  1.43s/it]
 75%|███████▌  | 46585/61904 [1:46:30<5:59:31,  1.41s/it]
 75%|███████▌  | 46586/61904 [1:46:31<5:59:57,  1.41s/it]
 75%|███████▌  | 46587/61904 [1:46:33<5:57:22,  1.40s/it]
 75%|███████▌  | 46588/61904 [1:46:34<5:46:18,  1.36s/it]
 75%|███████▌  | 46589/61904 [1:46:35<5:41:29,  1.34s/it]
 75%|███████▌  | 46590/61904 [1:46:37<5:44:10,  1.35s/it]
 75%|███████▌  | 46591/61904 [1:46:38<5:57:07,  1.40s/it]
 75%|███████▌  | 46592/61904 [1:46:40<5:51:20,  1.38s/it]
 75%|███████▌  | 46593/61904 [1:46:41<5:55:09,  1.39s/it]
 75%|███████▌  | 46594/61904 [1:46:42<6:02:39,  1.42s/it]
 75%|███████▌  | 46595/61904 [1:46:44<5:47:30,  1.36s/it]
 75%|███████▌  | 46596/61904 [1:46:45<5:36:09,  1.32s/it]
 75%|███████▌  | 46597/61904 [1:46:46<5:46:23,  1.36s/it]
 75%|███████▌  | 46598/61904 [1:46:48<5:52:13,  1.38s/it]
 75%|███████▌  | 46599/61904 [1:46:49<5:39:41,  1.33s/it]
 75%|███████▌  | 46600/61904 [1:46:50<5:46:27,  1.36s/it]
                                                         
{'loss': 2.4419, 'learning_rate': 1.2480228186179178e-07, 'epoch': 12.04}
+
 75%|███████▌  | 46600/61904 [1:46:50<5:46:27,  1.36s/it]
 75%|███████▌  | 46601/61904 [1:46:52<5:42:02,  1.34s/it]
 75%|███████▌  | 46602/61904 [1:46:53<5:43:13,  1.35s/it]
 75%|███████▌  | 46603/61904 [1:46:54<5:49:50,  1.37s/it]
 75%|███████▌  | 46604/61904 [1:46:56<5:50:05,  1.37s/it]
 75%|███████▌  | 46605/61904 [1:46:57<5:59:08,  1.41s/it]
 75%|███████▌  | 46606/61904 [1:46:59<5:58:19,  1.41s/it]
 75%|███████▌  | 46607/61904 [1:47:00<5:59:03,  1.41s/it]
 75%|███████▌  | 46608/61904 [1:47:02<5:58:48,  1.41s/it]
 75%|███████▌  | 46609/61904 [1:47:03<5:54:27,  1.39s/it]
 75%|███████▌  | 46610/61904 [1:47:04<5:54:56,  1.39s/it]
 75%|███████▌  | 46611/61904 [1:47:06<5:55:00,  1.39s/it]
 75%|███████▌  | 46612/61904 [1:47:07<5:55:50,  1.40s/it]
 75%|███████▌  | 46613/61904 [1:47:09<6:07:40,  1.44s/it]
 75%|███████▌  | 46614/61904 [1:47:10<5:56:11,  1.40s/it]
 75%|███████▌  | 46615/61904 [1:47:11<5:53:06,  1.39s/it]
 75%|███████▌  | 46616/61904 [1:47:13<5:45:49,  1.36s/it]
 75%|███████▌  | 46617/61904 [1:47:14<5:47:19,  1.36s/it]
 75%|███████▌  | 46618/61904 [1:47:15<5:48:59,  1.37s/it]
 75%|███████▌  | 46619/61904 [1:47:17<5:41:33,  1.34s/it]
 75%|███████▌  | 46620/61904 [1:47:18<5:43:26,  1.35s/it]
                                                         
{'loss': 2.4768, 'learning_rate': 1.2476986905224944e-07, 'epoch': 12.05}
+
 75%|███████▌  | 46620/61904 [1:47:18<5:43:26,  1.35s/it]
 75%|███████▌  | 46621/61904 [1:47:20<6:00:42,  1.42s/it]
 75%|███████▌  | 46622/61904 [1:47:21<5:56:09,  1.40s/it]
 75%|███████▌  | 46623/61904 [1:47:22<5:54:02,  1.39s/it]
 75%|███████▌  | 46624/61904 [1:47:24<6:04:44,  1.43s/it]
 75%|███████▌  | 46625/61904 [1:47:25<5:57:42,  1.40s/it]
 75%|███████▌  | 46626/61904 [1:47:26<5:47:52,  1.37s/it]
 75%|███████▌  | 46627/61904 [1:47:28<5:48:03,  1.37s/it]
 75%|███████▌  | 46628/61904 [1:47:29<5:50:06,  1.38s/it]
 75%|███████▌  | 46629/61904 [1:47:31<5:52:05,  1.38s/it]
 75%|███████▌  | 46630/61904 [1:47:32<5:59:10,  1.41s/it]
 75%|███████▌  | 46631/61904 [1:47:33<5:58:20,  1.41s/it]
 75%|███████▌  | 46632/61904 [1:47:35<5:57:40,  1.41s/it]
 75%|███████▌  | 46633/61904 [1:47:36<6:10:56,  1.46s/it]
 75%|███████▌  | 46634/61904 [1:47:38<6:00:49,  1.42s/it]
 75%|███████▌  | 46635/61904 [1:47:39<5:56:56,  1.40s/it]
 75%|███████▌  | 46636/61904 [1:47:41<5:57:03,  1.40s/it]
 75%|███████▌  | 46637/61904 [1:47:42<6:06:48,  1.44s/it]
 75%|███████▌  | 46638/61904 [1:47:43<6:00:37,  1.42s/it]
 75%|███████▌  | 46639/61904 [1:47:45<5:59:13,  1.41s/it]
 75%|███████▌  | 46640/61904 [1:47:46<5:59:19,  1.41s/it]
                                                         
{'loss': 2.444, 'learning_rate': 1.2473745624270713e-07, 'epoch': 12.05}
+
 75%|███████▌  | 46640/61904 [1:47:46<5:59:19,  1.41s/it]
 75%|███████▌  | 46641/61904 [1:47:48<6:00:59,  1.42s/it]
 75%|███████▌  | 46642/61904 [1:47:49<5:58:31,  1.41s/it]
 75%|███████▌  | 46643/61904 [1:47:50<5:57:50,  1.41s/it]
 75%|███████▌  | 46644/61904 [1:47:52<5:56:55,  1.40s/it]
 75%|███████▌  | 46645/61904 [1:47:53<5:58:31,  1.41s/it]
 75%|███████▌  | 46646/61904 [1:47:55<5:56:02,  1.40s/it]
 75%|███████▌  | 46647/61904 [1:47:56<5:51:30,  1.38s/it]
 75%|███████▌  | 46648/61904 [1:47:57<5:57:10,  1.40s/it]
 75%|███████▌  | 46649/61904 [1:47:59<5:49:00,  1.37s/it]
 75%|███████▌  | 46650/61904 [1:48:00<5:41:21,  1.34s/it]
 75%|███████▌  | 46651/61904 [1:48:01<5:42:51,  1.35s/it]
 75%|███████▌  | 46652/61904 [1:48:03<5:42:20,  1.35s/it]
 75%|███████▌  | 46653/61904 [1:48:04<5:45:19,  1.36s/it]
 75%|███████▌  | 46654/61904 [1:48:06<5:44:52,  1.36s/it]
 75%|███████▌  | 46655/61904 [1:48:07<5:40:47,  1.34s/it]
 75%|███████▌  | 46656/61904 [1:48:08<5:44:12,  1.35s/it]
 75%|███████▌  | 46657/61904 [1:48:09<5:39:10,  1.33s/it]
 75%|███████▌  | 46658/61904 [1:48:11<5:37:16,  1.33s/it]
 75%|███████▌  | 46659/61904 [1:48:12<5:43:01,  1.35s/it]
 75%|███████▌  | 46660/61904 [1:48:14<5:44:18,  1.36s/it]
                                                         
{'loss': 2.5193, 'learning_rate': 1.247050434331648e-07, 'epoch': 12.06}
+
 75%|███████▌  | 46660/61904 [1:48:14<5:44:18,  1.36s/it]
 75%|███████▌  | 46661/61904 [1:48:15<5:47:35,  1.37s/it]
 75%|███████▌  | 46662/61904 [1:48:16<5:43:49,  1.35s/it]
 75%|███████▌  | 46663/61904 [1:48:18<5:37:23,  1.33s/it]
 75%|███████▌  | 46664/61904 [1:48:19<5:49:00,  1.37s/it]
 75%|███████▌  | 46665/61904 [1:48:21<5:56:11,  1.40s/it]
 75%|███████▌  | 46666/61904 [1:48:22<5:53:06,  1.39s/it]
 75%|███████▌  | 46667/61904 [1:48:23<5:45:40,  1.36s/it]
 75%|███████▌  | 46668/61904 [1:48:25<5:45:13,  1.36s/it]
 75%|███████▌  | 46669/61904 [1:48:26<5:40:49,  1.34s/it]
 75%|███████▌  | 46670/61904 [1:48:27<5:44:02,  1.36s/it]
 75%|███████▌  | 46671/61904 [1:48:28<5:34:14,  1.32s/it]
 75%|███████▌  | 46672/61904 [1:48:30<5:37:33,  1.33s/it]
 75%|███████▌  | 46673/61904 [1:48:31<5:40:23,  1.34s/it]
 75%|███████▌  | 46674/61904 [1:48:33<5:48:38,  1.37s/it]
 75%|███████▌  | 46675/61904 [1:48:34<5:45:59,  1.36s/it]
 75%|███████▌  | 46676/61904 [1:48:35<5:46:10,  1.36s/it]
 75%|███████▌  | 46677/61904 [1:48:37<5:39:58,  1.34s/it]
 75%|███████▌  | 46678/61904 [1:48:38<5:45:21,  1.36s/it]
 75%|███████▌  | 46679/61904 [1:48:39<5:51:25,  1.38s/it]
 75%|███████▌  | 46680/61904 [1:48:41<5:53:15,  1.39s/it]
                                                         
{'loss': 2.5019, 'learning_rate': 1.2467263062362245e-07, 'epoch': 12.06}
+
 75%|███████▌  | 46680/61904 [1:48:41<5:53:15,  1.39s/it]
 75%|███████▌  | 46681/61904 [1:48:42<5:56:19,  1.40s/it]
 75%|███████▌  | 46682/61904 [1:48:44<5:54:24,  1.40s/it]
 75%|███████▌  | 46683/61904 [1:48:45<5:51:31,  1.39s/it]
 75%|███████▌  | 46684/61904 [1:48:46<5:50:17,  1.38s/it]
 75%|███████▌  | 46685/61904 [1:48:48<5:42:19,  1.35s/it]
 75%|███████▌  | 46686/61904 [1:48:49<5:47:02,  1.37s/it]
 75%|███████▌  | 46687/61904 [1:48:50<5:48:39,  1.37s/it]
 75%|███████▌  | 46688/61904 [1:48:52<5:46:11,  1.37s/it]
 75%|███████▌  | 46689/61904 [1:48:53<5:42:59,  1.35s/it]
 75%|███████▌  | 46690/61904 [1:48:55<5:53:49,  1.40s/it]
 75%|███████▌  | 46691/61904 [1:48:56<6:08:28,  1.45s/it]
 75%|███████▌  | 46692/61904 [1:48:58<5:59:25,  1.42s/it]
 75%|███████▌  | 46693/61904 [1:48:59<5:59:06,  1.42s/it]
 75%|███████▌  | 46694/61904 [1:49:00<5:51:16,  1.39s/it]
 75%|███████▌  | 46695/61904 [1:49:02<6:01:22,  1.43s/it]
 75%|███████▌  | 46696/61904 [1:49:03<6:05:16,  1.44s/it]
 75%|███████▌  | 46697/61904 [1:49:05<6:15:06,  1.48s/it]
 75%|███████▌  | 46698/61904 [1:49:06<6:11:09,  1.46s/it]
 75%|███████▌  | 46699/61904 [1:49:08<6:01:31,  1.43s/it]
 75%|███████▌  | 46700/61904 [1:49:09<6:00:29,  1.42s/it]
                                                         
{'loss': 2.465, 'learning_rate': 1.246402178140801e-07, 'epoch': 12.07}
+
 75%|███████▌  | 46700/61904 [1:49:09<6:00:29,  1.42s/it]
 75%|███████▌  | 46701/61904 [1:49:10<6:00:07,  1.42s/it]
 75%|███████▌  | 46702/61904 [1:49:12<5:55:28,  1.40s/it]
 75%|███████▌  | 46703/61904 [1:49:13<6:05:00,  1.44s/it]
 75%|███████▌  | 46704/61904 [1:49:15<5:53:33,  1.40s/it]
 75%|███████▌  | 46705/61904 [1:49:16<5:59:37,  1.42s/it]
 75%|███████▌  | 46706/61904 [1:49:17<5:51:42,  1.39s/it]
 75%|███████▌  | 46707/61904 [1:49:19<5:55:32,  1.40s/it]
 75%|███████▌  | 46708/61904 [1:49:20<5:50:30,  1.38s/it]
 75%|███████▌  | 46709/61904 [1:49:22<5:45:57,  1.37s/it]
 75%|███████▌  | 46710/61904 [1:49:23<5:43:59,  1.36s/it]
 75%|███████▌  | 46711/61904 [1:49:24<5:40:39,  1.35s/it]
 75%|███████▌  | 46712/61904 [1:49:26<5:50:28,  1.38s/it]
 75%|███████▌  | 46713/61904 [1:49:27<6:01:09,  1.43s/it]
 75%|███████▌  | 46714/61904 [1:49:29<6:00:04,  1.42s/it]
 75%|███████▌  | 46715/61904 [1:49:30<5:57:19,  1.41s/it]
 75%|███████▌  | 46716/61904 [1:49:31<5:54:29,  1.40s/it]
 75%|███████▌  | 46717/61904 [1:49:33<5:50:10,  1.38s/it]
 75%|███████▌  | 46718/61904 [1:49:34<5:56:46,  1.41s/it]
 75%|███████▌  | 46719/61904 [1:49:36<6:13:27,  1.48s/it]
 75%|███████▌  | 46720/61904 [1:49:37<5:59:33,  1.42s/it]
                                                         
{'loss': 2.4508, 'learning_rate': 1.246078050045378e-07, 'epoch': 12.08}
+
 75%|███████▌  | 46720/61904 [1:49:37<5:59:33,  1.42s/it]
 75%|███████▌  | 46721/61904 [1:49:39<6:07:08,  1.45s/it]
 75%|███████▌  | 46722/61904 [1:49:40<5:50:30,  1.39s/it]
 75%|███████▌  | 46723/61904 [1:49:41<5:53:12,  1.40s/it]
 75%|███████▌  | 46724/61904 [1:49:43<5:56:53,  1.41s/it]
 75%|███████▌  | 46725/61904 [1:49:44<6:01:31,  1.43s/it]
 75%|███████▌  | 46726/61904 [1:49:46<5:59:08,  1.42s/it]
 75%|███████▌  | 46727/61904 [1:49:47<5:56:15,  1.41s/it]
 75%|███████▌  | 46728/61904 [1:49:48<5:57:15,  1.41s/it]
 75%|███████▌  | 46729/61904 [1:49:50<6:01:39,  1.43s/it]
 75%|███████▌  | 46730/61904 [1:49:51<5:50:56,  1.39s/it]
 75%|███████▌  | 46731/61904 [1:49:52<5:47:59,  1.38s/it]
 75%|███████▌  | 46732/61904 [1:49:54<5:45:13,  1.37s/it]
 75%|███████▌  | 46733/61904 [1:49:55<5:42:49,  1.36s/it]
 75%|███████▌  | 46734/61904 [1:49:57<5:44:52,  1.36s/it]
 75%|███████▌  | 46735/61904 [1:49:58<5:51:30,  1.39s/it]
 75%|███████▌  | 46736/61904 [1:49:59<5:59:07,  1.42s/it]
 75%|███████▌  | 46737/61904 [1:50:01<5:56:13,  1.41s/it]
 76%|███████▌  | 46738/61904 [1:50:02<5:59:27,  1.42s/it]
 76%|███████▌  | 46739/61904 [1:50:04<5:56:20,  1.41s/it]
 76%|███████▌  | 46740/61904 [1:50:05<6:00:43,  1.43s/it]
                                                         
{'loss': 2.4784, 'learning_rate': 1.2457539219499546e-07, 'epoch': 12.08}
+
 76%|███████▌  | 46740/61904 [1:50:05<6:00:43,  1.43s/it]
 76%|███████▌  | 46741/61904 [1:50:07<5:53:39,  1.40s/it]
 76%|███████▌  | 46742/61904 [1:50:08<5:50:28,  1.39s/it]
 76%|███████▌  | 46743/61904 [1:50:09<5:45:29,  1.37s/it]
 76%|███████▌  | 46744/61904 [1:50:11<5:55:15,  1.41s/it]
 76%|███████▌  | 46745/61904 [1:50:12<5:45:26,  1.37s/it]
 76%|███████▌  | 46746/61904 [1:50:13<5:46:17,  1.37s/it]
 76%|███████▌  | 46747/61904 [1:50:15<5:35:09,  1.33s/it]
 76%|███████▌  | 46748/61904 [1:50:16<5:33:05,  1.32s/it]
 76%|███████▌  | 46749/61904 [1:50:17<5:26:46,  1.29s/it]
 76%|███████▌  | 46750/61904 [1:50:18<5:30:01,  1.31s/it]
 76%|███████▌  | 46751/61904 [1:50:20<5:31:01,  1.31s/it]
 76%|███████▌  | 46752/61904 [1:50:21<5:37:36,  1.34s/it]
 76%|███████▌  | 46753/61904 [1:50:23<5:40:02,  1.35s/it]
 76%|███████▌  | 46754/61904 [1:50:24<5:45:10,  1.37s/it]
 76%|███████▌  | 46755/61904 [1:50:25<5:43:32,  1.36s/it]
 76%|███████▌  | 46756/61904 [1:50:27<5:48:34,  1.38s/it]
 76%|███████▌  | 46757/61904 [1:50:28<5:54:40,  1.40s/it]
 76%|███████▌  | 46758/61904 [1:50:30<5:52:31,  1.40s/it]
 76%|███████▌  | 46759/61904 [1:50:31<5:54:37,  1.40s/it]
 76%|███████▌  | 46760/61904 [1:50:32<5:55:32,  1.41s/it]
                                                         
{'loss': 2.5013, 'learning_rate': 1.2454297938545312e-07, 'epoch': 12.09}
+
 76%|███████▌  | 46760/61904 [1:50:32<5:55:32,  1.41s/it]
 76%|███████▌  | 46761/61904 [1:50:34<6:02:00,  1.43s/it]
 76%|███████▌  | 46762/61904 [1:50:35<5:53:00,  1.40s/it]
 76%|███████▌  | 46763/61904 [1:50:37<5:49:34,  1.39s/it]
 76%|███████▌  | 46764/61904 [1:50:38<5:44:49,  1.37s/it]
 76%|███████▌  | 46765/61904 [1:50:39<5:43:58,  1.36s/it]
 76%|███████▌  | 46766/61904 [1:50:41<5:45:05,  1.37s/it]
 76%|███████▌  | 46767/61904 [1:50:42<5:50:07,  1.39s/it]
 76%|███████▌  | 46768/61904 [1:50:43<5:39:59,  1.35s/it]
 76%|███████▌  | 46769/61904 [1:50:45<5:41:29,  1.35s/it]
 76%|███████▌  | 46770/61904 [1:50:46<5:44:37,  1.37s/it]
 76%|███████▌  | 46771/61904 [1:50:47<5:44:28,  1.37s/it]
 76%|███████▌  | 46772/61904 [1:50:49<5:43:21,  1.36s/it]
 76%|███████▌  | 46773/61904 [1:50:50<5:39:23,  1.35s/it]
 76%|███████▌  | 46774/61904 [1:50:51<5:41:30,  1.35s/it]
 76%|███████▌  | 46775/61904 [1:50:53<5:41:27,  1.35s/it]
 76%|███████▌  | 46776/61904 [1:50:54<5:49:45,  1.39s/it]
 76%|███████▌  | 46777/61904 [1:50:56<6:01:44,  1.43s/it]
 76%|███████▌  | 46778/61904 [1:50:57<5:51:56,  1.40s/it]
 76%|███████▌  | 46779/61904 [1:50:59<6:00:09,  1.43s/it]
 76%|███████▌  | 46780/61904 [1:51:00<6:02:33,  1.44s/it]
                                                         
{'loss': 2.3997, 'learning_rate': 1.2451056657591079e-07, 'epoch': 12.09}
+
 76%|███████▌  | 46780/61904 [1:51:00<6:02:33,  1.44s/it]
 76%|███████▌  | 46781/61904 [1:51:02<6:01:14,  1.43s/it]
 76%|███████▌  | 46782/61904 [1:51:03<5:57:38,  1.42s/it]
 76%|███████▌  | 46783/61904 [1:51:04<6:01:10,  1.43s/it]
 76%|███████▌  | 46784/61904 [1:51:06<5:56:09,  1.41s/it]
 76%|███████▌  | 46785/61904 [1:51:07<5:42:04,  1.36s/it]
 76%|███████▌  | 46786/61904 [1:51:08<5:39:16,  1.35s/it]
 76%|███████▌  | 46787/61904 [1:51:10<5:42:21,  1.36s/it]
 76%|███████▌  | 46788/61904 [1:51:11<5:55:32,  1.41s/it]
 76%|███████▌  | 46789/61904 [1:51:13<5:47:18,  1.38s/it]
 76%|███████▌  | 46790/61904 [1:51:14<5:55:30,  1.41s/it]
 76%|███████▌  | 46791/61904 [1:51:15<5:53:52,  1.40s/it]
 76%|███████▌  | 46792/61904 [1:51:17<5:51:01,  1.39s/it]
 76%|███████▌  | 46793/61904 [1:51:18<5:42:22,  1.36s/it]
 76%|███████▌  | 46794/61904 [1:51:19<5:47:21,  1.38s/it]
 76%|███████▌  | 46795/61904 [1:51:21<5:54:39,  1.41s/it]
 76%|███████▌  | 46796/61904 [1:51:22<5:57:21,  1.42s/it]
 76%|███████▌  | 46797/61904 [1:51:24<6:00:43,  1.43s/it]
 76%|███████▌  | 46798/61904 [1:51:25<5:56:05,  1.41s/it]
 76%|███████▌  | 46799/61904 [1:51:27<5:58:21,  1.42s/it]
 76%|███████▌  | 46800/61904 [1:51:28<5:47:03,  1.38s/it]
                                                         
{'loss': 2.4475, 'learning_rate': 1.2447815376636847e-07, 'epoch': 12.1}
+
 76%|███████▌  | 46800/61904 [1:51:28<5:47:03,  1.38s/it]
 76%|███████▌  | 46801/61904 [1:51:29<5:54:31,  1.41s/it]
 76%|███████▌  | 46802/61904 [1:51:31<5:49:56,  1.39s/it]
 76%|███████▌  | 46803/61904 [1:51:32<5:53:42,  1.41s/it]
 76%|███████▌  | 46804/61904 [1:51:34<5:49:09,  1.39s/it]
 76%|███████▌  | 46805/61904 [1:51:35<6:01:22,  1.44s/it]
 76%|███████▌  | 46806/61904 [1:51:36<5:54:10,  1.41s/it]
 76%|███████▌  | 46807/61904 [1:51:38<5:45:44,  1.37s/it]
 76%|███████▌  | 46808/61904 [1:51:39<6:02:09,  1.44s/it]
 76%|███████▌  | 46809/61904 [1:51:41<6:02:46,  1.44s/it]
 76%|███████▌  | 46810/61904 [1:51:42<5:58:56,  1.43s/it]
 76%|███████▌  | 46811/61904 [1:51:44<5:56:48,  1.42s/it]
 76%|███████▌  | 46812/61904 [1:51:45<5:53:03,  1.40s/it]
 76%|███████▌  | 46813/61904 [1:51:46<5:45:47,  1.37s/it]
 76%|███████▌  | 46814/61904 [1:51:48<5:46:19,  1.38s/it]
 76%|███████▌  | 46815/61904 [1:51:49<6:04:08,  1.45s/it]
 76%|███████▌  | 46816/61904 [1:51:51<6:02:11,  1.44s/it]
 76%|███████▌  | 46817/61904 [1:51:52<6:02:38,  1.44s/it]
 76%|███████▌  | 46818/61904 [1:51:54<6:25:33,  1.53s/it]
 76%|███████▌  | 46819/61904 [1:51:55<6:12:40,  1.48s/it]
 76%|███████▌  | 46820/61904 [1:51:57<6:05:58,  1.46s/it]
                                                         
{'loss': 2.4564, 'learning_rate': 1.2444574095682614e-07, 'epoch': 12.1}
+
 76%|███████▌  | 46820/61904 [1:51:57<6:05:58,  1.46s/it]
 76%|███████▌  | 46821/61904 [1:51:58<6:04:16,  1.45s/it]
 76%|███████▌  | 46822/61904 [1:51:59<6:03:12,  1.44s/it]
 76%|███████▌  | 46823/61904 [1:52:01<5:53:26,  1.41s/it]
 76%|███████▌  | 46824/61904 [1:52:02<5:45:46,  1.38s/it]
 76%|███████▌  | 46825/61904 [1:52:03<5:45:25,  1.37s/it]
 76%|███████▌  | 46826/61904 [1:52:05<5:41:53,  1.36s/it]
 76%|███████▌  | 46827/61904 [1:52:06<5:50:52,  1.40s/it]
 76%|███████▌  | 46828/61904 [1:52:08<5:41:21,  1.36s/it]
 76%|███████▌  | 46829/61904 [1:52:09<5:47:04,  1.38s/it]
 76%|███████▌  | 46830/61904 [1:52:10<5:50:42,  1.40s/it]
 76%|███████▌  | 46831/61904 [1:52:12<5:44:29,  1.37s/it]
 76%|███████▌  | 46832/61904 [1:52:13<5:55:57,  1.42s/it]
 76%|███████▌  | 46833/61904 [1:52:15<5:49:41,  1.39s/it]
 76%|███████▌  | 46834/61904 [1:52:16<6:02:13,  1.44s/it]
 76%|███████▌  | 46835/61904 [1:52:18<5:59:16,  1.43s/it]
 76%|███████▌  | 46836/61904 [1:52:19<5:54:40,  1.41s/it]
 76%|███████▌  | 46837/61904 [1:52:20<5:57:48,  1.42s/it]
 76%|███████▌  | 46838/61904 [1:52:22<5:59:39,  1.43s/it]
 76%|███████▌  | 46839/61904 [1:52:23<5:54:59,  1.41s/it]
 76%|███████▌  | 46840/61904 [1:52:25<5:49:27,  1.39s/it]
                                                         
{'loss': 2.5028, 'learning_rate': 1.244133281472838e-07, 'epoch': 12.11}
+
 76%|███████▌  | 46840/61904 [1:52:25<5:49:27,  1.39s/it]
 76%|███████▌  | 46841/61904 [1:52:26<5:49:52,  1.39s/it]
 76%|███████▌  | 46842/61904 [1:52:27<5:43:05,  1.37s/it]
 76%|███████▌  | 46843/61904 [1:52:29<5:41:36,  1.36s/it]
 76%|███████▌  | 46844/61904 [1:52:30<5:43:58,  1.37s/it]
 76%|███████▌  | 46845/61904 [1:52:31<5:37:26,  1.34s/it]
 76%|███████▌  | 46846/61904 [1:52:32<5:28:33,  1.31s/it]
 76%|███████▌  | 46847/61904 [1:52:34<5:47:30,  1.38s/it]
 76%|███████▌  | 46848/61904 [1:52:35<5:49:33,  1.39s/it]
 76%|███████▌  | 46849/61904 [1:52:37<6:01:50,  1.44s/it]
 76%|███████▌  | 46850/61904 [1:52:38<5:55:29,  1.42s/it]
 76%|███████▌  | 46851/61904 [1:52:40<5:50:07,  1.40s/it]
 76%|███████▌  | 46852/61904 [1:52:41<5:47:12,  1.38s/it]
 76%|███████▌  | 46853/61904 [1:52:42<5:44:27,  1.37s/it]
 76%|███████▌  | 46854/61904 [1:52:44<5:40:32,  1.36s/it]
 76%|███████▌  | 46855/61904 [1:52:45<5:35:14,  1.34s/it]
 76%|███████▌  | 46856/61904 [1:52:46<5:38:54,  1.35s/it]
 76%|███████▌  | 46857/61904 [1:52:48<5:49:32,  1.39s/it]
 76%|███████▌  | 46858/61904 [1:52:49<5:53:15,  1.41s/it]
 76%|███████▌  | 46859/61904 [1:52:51<5:40:27,  1.36s/it]
 76%|███████▌  | 46860/61904 [1:52:52<5:34:53,  1.34s/it]
                                                         
{'loss': 2.4969, 'learning_rate': 1.2438091533774146e-07, 'epoch': 12.11}
+
 76%|███████▌  | 46860/61904 [1:52:52<5:34:53,  1.34s/it]
 76%|███████▌  | 46861/61904 [1:52:53<5:46:10,  1.38s/it]
 76%|███████▌  | 46862/61904 [1:52:55<5:47:06,  1.38s/it]
 76%|███████▌  | 46863/61904 [1:52:56<5:41:07,  1.36s/it]
 76%|███████▌  | 46864/61904 [1:52:57<5:42:38,  1.37s/it]
 76%|███████▌  | 46865/61904 [1:52:59<5:53:20,  1.41s/it]
 76%|███████▌  | 46866/61904 [1:53:00<5:42:03,  1.36s/it]
 76%|███████▌  | 46867/61904 [1:53:02<5:50:29,  1.40s/it]
 76%|███████▌  | 46868/61904 [1:53:03<5:59:30,  1.43s/it]
 76%|███████▌  | 46869/61904 [1:53:04<5:47:05,  1.39s/it]
 76%|███████▌  | 46870/61904 [1:53:06<5:39:03,  1.35s/it]
 76%|███████▌  | 46871/61904 [1:53:07<5:45:58,  1.38s/it]
 76%|███████▌  | 46872/61904 [1:53:09<5:39:43,  1.36s/it]
 76%|███████▌  | 46873/61904 [1:53:10<5:44:14,  1.37s/it]
 76%|███████▌  | 46874/61904 [1:53:11<5:43:44,  1.37s/it]
 76%|███████▌  | 46875/61904 [1:53:13<5:53:27,  1.41s/it]
 76%|███████▌  | 46876/61904 [1:53:14<5:49:31,  1.40s/it]
 76%|███████▌  | 46877/61904 [1:53:15<5:44:56,  1.38s/it]
 76%|███████▌  | 46878/61904 [1:53:17<5:48:25,  1.39s/it]
 76%|███████▌  | 46879/61904 [1:53:18<6:00:33,  1.44s/it]
 76%|███████▌  | 46880/61904 [1:53:20<5:51:46,  1.40s/it]
                                                         
{'loss': 2.4488, 'learning_rate': 1.2434850252819915e-07, 'epoch': 12.12}
+
 76%|███████▌  | 46880/61904 [1:53:20<5:51:46,  1.40s/it]
 76%|███████▌  | 46881/61904 [1:53:21<5:43:55,  1.37s/it]
 76%|███████▌  | 46882/61904 [1:53:23<5:50:21,  1.40s/it]
 76%|███████▌  | 46883/61904 [1:53:24<5:47:43,  1.39s/it]
 76%|███████▌  | 46884/61904 [1:53:25<5:44:39,  1.38s/it]
 76%|███████▌  | 46885/61904 [1:53:27<5:38:14,  1.35s/it]
 76%|███████▌  | 46886/61904 [1:53:28<5:36:10,  1.34s/it]
 76%|███████▌  | 46887/61904 [1:53:29<5:35:45,  1.34s/it]
 76%|███████▌  | 46888/61904 [1:53:30<5:29:59,  1.32s/it]
 76%|███████▌  | 46889/61904 [1:53:32<5:31:12,  1.32s/it]
 76%|███████▌  | 46890/61904 [1:53:33<5:31:47,  1.33s/it]
 76%|███████▌  | 46891/61904 [1:53:35<5:35:52,  1.34s/it]
 76%|███████▌  | 46892/61904 [1:53:36<5:44:38,  1.38s/it]
 76%|███████▌  | 46893/61904 [1:53:37<5:48:50,  1.39s/it]
 76%|███████▌  | 46894/61904 [1:53:39<5:55:21,  1.42s/it]
 76%|███████▌  | 46895/61904 [1:53:40<5:53:34,  1.41s/it]
 76%|███████▌  | 46896/61904 [1:53:42<5:50:16,  1.40s/it]
 76%|███████▌  | 46897/61904 [1:53:43<5:58:47,  1.43s/it]
 76%|███████▌  | 46898/61904 [1:53:44<5:48:57,  1.40s/it]
 76%|███████▌  | 46899/61904 [1:53:46<5:55:52,  1.42s/it]
 76%|███████▌  | 46900/61904 [1:53:47<5:56:20,  1.43s/it]
                                                         
{'loss': 2.4779, 'learning_rate': 1.243160897186568e-07, 'epoch': 12.12}
+
 76%|███████▌  | 46900/61904 [1:53:47<5:56:20,  1.43s/it]
 76%|███████▌  | 46901/61904 [1:53:49<5:51:18,  1.40s/it]
 76%|███████▌  | 46902/61904 [1:53:50<5:38:24,  1.35s/it]
 76%|███████▌  | 46903/61904 [1:53:51<5:33:30,  1.33s/it]
 76%|███████▌  | 46904/61904 [1:53:53<5:41:27,  1.37s/it]
 76%|███████▌  | 46905/61904 [1:53:54<5:39:03,  1.36s/it]
 76%|███████▌  | 46906/61904 [1:53:55<5:39:56,  1.36s/it]
 76%|███████▌  | 46907/61904 [1:53:57<5:58:19,  1.43s/it]
 76%|███████▌  | 46908/61904 [1:53:58<5:53:54,  1.42s/it]
 76%|███████▌  | 46909/61904 [1:54:00<5:54:39,  1.42s/it]
 76%|███████▌  | 46910/61904 [1:54:01<5:53:32,  1.41s/it]
 76%|███████▌  | 46911/61904 [1:54:03<5:56:25,  1.43s/it]
 76%|███████▌  | 46912/61904 [1:54:04<5:54:47,  1.42s/it]
 76%|███████▌  | 46913/61904 [1:54:05<5:48:45,  1.40s/it]
 76%|███████▌  | 46914/61904 [1:54:07<5:42:30,  1.37s/it]
 76%|███████▌  | 46915/61904 [1:54:08<5:40:25,  1.36s/it]
 76%|███████▌  | 46916/61904 [1:54:09<5:38:20,  1.35s/it]
 76%|███████▌  | 46917/61904 [1:54:11<5:44:51,  1.38s/it]
 76%|███████▌  | 46918/61904 [1:54:12<5:39:45,  1.36s/it]
 76%|███████▌  | 46919/61904 [1:54:14<6:03:05,  1.45s/it]
 76%|███████▌  | 46920/61904 [1:54:15<6:02:08,  1.45s/it]
                                                         
{'loss': 2.4605, 'learning_rate': 1.2428367690911447e-07, 'epoch': 12.13}
+
 76%|███████▌  | 46920/61904 [1:54:15<6:02:08,  1.45s/it]
 76%|███████▌  | 46921/61904 [1:54:17<5:47:07,  1.39s/it]
 76%|███████▌  | 46922/61904 [1:54:18<5:47:58,  1.39s/it]
 76%|███████▌  | 46923/61904 [1:54:19<5:53:15,  1.41s/it]
 76%|███████▌  | 46924/61904 [1:54:21<5:52:33,  1.41s/it]
 76%|███████▌  | 46925/61904 [1:54:22<5:49:15,  1.40s/it]
 76%|███████▌  | 46926/61904 [1:54:24<5:44:27,  1.38s/it]
 76%|███████▌  | 46927/61904 [1:54:25<5:44:36,  1.38s/it]
 76%|███████▌  | 46928/61904 [1:54:26<5:51:21,  1.41s/it]
 76%|███████▌  | 46929/61904 [1:54:28<5:44:37,  1.38s/it]
 76%|███████▌  | 46930/61904 [1:54:29<5:58:56,  1.44s/it]
 76%|███████▌  | 46931/61904 [1:54:31<5:59:56,  1.44s/it]
 76%|███████▌  | 46932/61904 [1:54:32<5:55:09,  1.42s/it]
 76%|███████▌  | 46933/61904 [1:54:34<5:59:50,  1.44s/it]
 76%|███████▌  | 46934/61904 [1:54:35<5:49:06,  1.40s/it]
 76%|███████▌  | 46935/61904 [1:54:36<5:43:25,  1.38s/it]
 76%|███████▌  | 46936/61904 [1:54:38<5:49:23,  1.40s/it]
 76%|███████▌  | 46937/61904 [1:54:39<6:11:43,  1.49s/it]
 76%|███████▌  | 46938/61904 [1:54:41<6:02:34,  1.45s/it]
 76%|███████▌  | 46939/61904 [1:54:42<5:55:03,  1.42s/it]
 76%|███████▌  | 46940/61904 [1:54:43<5:51:05,  1.41s/it]
                                                         
{'loss': 2.4592, 'learning_rate': 1.2425126409957216e-07, 'epoch': 12.13}
+
 76%|███████▌  | 46940/61904 [1:54:43<5:51:05,  1.41s/it]
 76%|███████▌  | 46941/61904 [1:54:45<5:55:13,  1.42s/it]
 76%|███████▌  | 46942/61904 [1:54:46<5:51:26,  1.41s/it]
 76%|███████▌  | 46943/61904 [1:54:48<5:41:13,  1.37s/it]
 76%|███████▌  | 46944/61904 [1:54:49<5:38:31,  1.36s/it]
 76%|███████▌  | 46945/61904 [1:54:50<5:41:34,  1.37s/it]
 76%|███████▌  | 46946/61904 [1:54:52<5:51:53,  1.41s/it]
 76%|███████▌  | 46947/61904 [1:54:53<5:57:26,  1.43s/it]
 76%|███████▌  | 46948/61904 [1:54:55<6:00:06,  1.44s/it]
 76%|███████▌  | 46949/61904 [1:54:56<5:55:20,  1.43s/it]
 76%|███████▌  | 46950/61904 [1:54:58<6:08:02,  1.48s/it]
 76%|███████▌  | 46951/61904 [1:54:59<6:02:55,  1.46s/it]
 76%|███████▌  | 46952/61904 [1:55:01<6:00:02,  1.44s/it]
 76%|███████▌  | 46953/61904 [1:55:02<5:57:31,  1.43s/it]
 76%|███████▌  | 46954/61904 [1:55:03<5:52:29,  1.41s/it]
 76%|███████▌  | 46955/61904 [1:55:05<5:57:48,  1.44s/it]
 76%|███████▌  | 46956/61904 [1:55:06<6:00:06,  1.45s/it]
 76%|███████▌  | 46957/61904 [1:55:08<5:58:00,  1.44s/it]
 76%|███████▌  | 46958/61904 [1:55:09<5:53:31,  1.42s/it]
 76%|███████▌  | 46959/61904 [1:55:11<5:55:36,  1.43s/it]
 76%|███████▌  | 46960/61904 [1:55:12<5:41:42,  1.37s/it]
                                                         
{'loss': 2.5115, 'learning_rate': 1.2421885129002982e-07, 'epoch': 12.14}
+
 76%|███████▌  | 46960/61904 [1:55:12<5:41:42,  1.37s/it]
 76%|███████▌  | 46961/61904 [1:55:13<5:32:35,  1.34s/it]
 76%|███████▌  | 46962/61904 [1:55:14<5:37:45,  1.36s/it]
 76%|███████▌  | 46963/61904 [1:55:16<5:49:47,  1.40s/it]
 76%|███████▌  | 46964/61904 [1:55:17<5:35:45,  1.35s/it]
 76%|███████▌  | 46965/61904 [1:55:19<5:44:32,  1.38s/it]
 76%|███████▌  | 46966/61904 [1:55:20<5:44:55,  1.39s/it]
 76%|███████▌  | 46967/61904 [1:55:21<5:43:57,  1.38s/it]
 76%|███████▌  | 46968/61904 [1:55:23<5:34:34,  1.34s/it]
 76%|███████▌  | 46969/61904 [1:55:24<5:35:23,  1.35s/it]
 76%|███████▌  | 46970/61904 [1:55:25<5:36:09,  1.35s/it]
 76%|███████▌  | 46971/61904 [1:55:27<5:38:39,  1.36s/it]
 76%|███████▌  | 46972/61904 [1:55:28<5:39:00,  1.36s/it]
 76%|███████▌  | 46973/61904 [1:55:30<5:43:11,  1.38s/it]
 76%|███████▌  | 46974/61904 [1:55:31<5:50:45,  1.41s/it]
 76%|███████▌  | 46975/61904 [1:55:32<5:50:21,  1.41s/it]
 76%|███████▌  | 46976/61904 [1:55:34<6:15:41,  1.51s/it]
 76%|███████▌  | 46977/61904 [1:55:36<6:10:17,  1.49s/it]
 76%|███████▌  | 46978/61904 [1:55:37<6:13:18,  1.50s/it]
 76%|███████▌  | 46979/61904 [1:55:38<6:00:52,  1.45s/it]
 76%|███████▌  | 46980/61904 [1:55:40<6:02:01,  1.46s/it]
                                                         
{'loss': 2.494, 'learning_rate': 1.2418643848048748e-07, 'epoch': 12.14}
+
 76%|███████▌  | 46980/61904 [1:55:40<6:02:01,  1.46s/it]
 76%|███████▌  | 46981/61904 [1:55:41<5:58:23,  1.44s/it]
 76%|███████▌  | 46982/61904 [1:55:43<6:08:44,  1.48s/it]
 76%|███████▌  | 46983/61904 [1:55:44<5:57:30,  1.44s/it]
 76%|███████▌  | 46984/61904 [1:55:46<5:47:42,  1.40s/it]
 76%|███████▌  | 46985/61904 [1:55:47<5:55:39,  1.43s/it]
 76%|███████▌  | 46986/61904 [1:55:48<5:54:45,  1.43s/it]
 76%|███████▌  | 46987/61904 [1:55:50<5:52:42,  1.42s/it]
 76%|███████▌  | 46988/61904 [1:55:51<5:47:43,  1.40s/it]
 76%|███████▌  | 46989/61904 [1:55:53<5:48:37,  1.40s/it]
 76%|███████▌  | 46990/61904 [1:55:54<5:45:21,  1.39s/it]
 76%|███████▌  | 46991/61904 [1:55:56<6:20:00,  1.53s/it]
 76%|███████▌  | 46992/61904 [1:55:57<6:12:34,  1.50s/it]
 76%|███████▌  | 46993/61904 [1:55:59<6:00:39,  1.45s/it]
 76%|███████▌  | 46994/61904 [1:56:00<5:57:28,  1.44s/it]
 76%|███████▌  | 46995/61904 [1:56:01<5:41:05,  1.37s/it]
 76%|███████▌  | 46996/61904 [1:56:03<5:47:31,  1.40s/it]
 76%|███████▌  | 46997/61904 [1:56:04<5:43:24,  1.38s/it]
 76%|███████▌  | 46998/61904 [1:56:06<5:55:39,  1.43s/it]
 76%|███████▌  | 46999/61904 [1:56:07<5:52:14,  1.42s/it]
 76%|███████▌  | 47000/61904 [1:56:08<5:46:06,  1.39s/it]
                                                         
{'loss': 2.4545, 'learning_rate': 1.2415402567094515e-07, 'epoch': 12.15}
+
 76%|███████▌  | 47000/61904 [1:56:08<5:46:06,  1.39s/it]
 76%|███████▌  | 47001/61904 [1:56:10<5:46:53,  1.40s/it]
 76%|███████▌  | 47002/61904 [1:56:11<5:46:47,  1.40s/it]
 76%|███████▌  | 47003/61904 [1:56:12<5:45:01,  1.39s/it]
 76%|███████▌  | 47004/61904 [1:56:14<5:53:48,  1.42s/it]
 76%|███████▌  | 47005/61904 [1:56:15<5:47:00,  1.40s/it]
 76%|███████▌  | 47006/61904 [1:56:17<5:43:07,  1.38s/it]
 76%|███████▌  | 47007/61904 [1:56:18<5:45:03,  1.39s/it]
 76%|███████▌  | 47008/61904 [1:56:19<5:44:12,  1.39s/it]
 76%|███████▌  | 47009/61904 [1:56:21<5:47:24,  1.40s/it]
 76%|███████▌  | 47010/61904 [1:56:22<5:44:39,  1.39s/it]
 76%|███████▌  | 47011/61904 [1:56:24<5:49:17,  1.41s/it]
 76%|███████▌  | 47012/61904 [1:56:25<5:44:45,  1.39s/it]
 76%|███████▌  | 47013/61904 [1:56:27<6:00:47,  1.45s/it]
 76%|███████▌  | 47014/61904 [1:56:28<5:45:48,  1.39s/it]
 76%|███████▌  | 47015/61904 [1:56:29<5:54:56,  1.43s/it]
 76%|███████▌  | 47016/61904 [1:56:31<5:41:22,  1.38s/it]
 76%|███████▌  | 47017/61904 [1:56:32<5:45:20,  1.39s/it]
 76%|███████▌  | 47018/61904 [1:56:33<5:42:05,  1.38s/it]
 76%|███████▌  | 47019/61904 [1:56:35<5:34:47,  1.35s/it]
 76%|███████▌  | 47020/61904 [1:56:36<5:41:58,  1.38s/it]
                                                         
{'loss': 2.5211, 'learning_rate': 1.2412161286140283e-07, 'epoch': 12.15}
+
 76%|███████▌  | 47020/61904 [1:56:36<5:41:58,  1.38s/it]
 76%|███████▌  | 47021/61904 [1:56:37<5:27:51,  1.32s/it]
 76%|███████▌  | 47022/61904 [1:56:39<5:33:37,  1.35s/it]
 76%|███████▌  | 47023/61904 [1:56:40<5:41:31,  1.38s/it]
 76%|███████▌  | 47024/61904 [1:56:42<5:46:20,  1.40s/it]
 76%|███████▌  | 47025/61904 [1:56:43<5:49:23,  1.41s/it]
 76%|███████▌  | 47026/61904 [1:56:45<5:51:24,  1.42s/it]
 76%|███████▌  | 47027/61904 [1:56:46<5:39:47,  1.37s/it]
 76%|███████▌  | 47028/61904 [1:56:47<5:47:30,  1.40s/it]
 76%|███████▌  | 47029/61904 [1:56:49<5:51:21,  1.42s/it]
 76%|███████▌  | 47030/61904 [1:56:50<5:49:48,  1.41s/it]
 76%|███████▌  | 47031/61904 [1:56:52<5:52:38,  1.42s/it]
 76%|███████▌  | 47032/61904 [1:56:53<5:51:28,  1.42s/it]
 76%|███████▌  | 47033/61904 [1:56:54<5:50:34,  1.41s/it]
 76%|███████▌  | 47034/61904 [1:56:56<5:46:17,  1.40s/it]
 76%|███████▌  | 47035/61904 [1:56:57<5:46:06,  1.40s/it]
 76%|███████▌  | 47036/61904 [1:56:59<5:43:03,  1.38s/it]
 76%|███████▌  | 47037/61904 [1:57:00<5:34:51,  1.35s/it]
 76%|███████▌  | 47038/61904 [1:57:01<5:36:55,  1.36s/it]
 76%|███████▌  | 47039/61904 [1:57:03<5:47:12,  1.40s/it]
 76%|███████▌  | 47040/61904 [1:57:04<5:44:55,  1.39s/it]
                                                         
{'loss': 2.4661, 'learning_rate': 1.240892000518605e-07, 'epoch': 12.16}
+
 76%|███████▌  | 47040/61904 [1:57:04<5:44:55,  1.39s/it]
 76%|███████▌  | 47041/61904 [1:57:06<5:51:37,  1.42s/it]
 76%|███████▌  | 47042/61904 [1:57:07<5:50:14,  1.41s/it]
 76%|███████▌  | 47043/61904 [1:57:08<5:53:40,  1.43s/it]
 76%|███████▌  | 47044/61904 [1:57:10<5:50:47,  1.42s/it]
 76%|███████▌  | 47045/61904 [1:57:11<5:46:18,  1.40s/it]
 76%|███████▌  | 47046/61904 [1:57:12<5:43:42,  1.39s/it]
 76%|███████▌  | 47047/61904 [1:57:14<5:43:36,  1.39s/it]
 76%|███████▌  | 47048/61904 [1:57:15<5:33:04,  1.35s/it]
 76%|███████▌  | 47049/61904 [1:57:17<5:41:01,  1.38s/it]
 76%|███████▌  | 47050/61904 [1:57:18<5:46:58,  1.40s/it]
 76%|███████▌  | 47051/61904 [1:57:19<5:51:05,  1.42s/it]
 76%|███████▌  | 47052/61904 [1:57:21<5:53:58,  1.43s/it]
 76%|███████▌  | 47053/61904 [1:57:22<5:52:05,  1.42s/it]
 76%|███████▌  | 47054/61904 [1:57:24<6:14:53,  1.51s/it]
 76%|███████▌  | 47055/61904 [1:57:25<6:05:56,  1.48s/it]
 76%|███████▌  | 47056/61904 [1:57:27<6:02:43,  1.47s/it]
 76%|███████▌  | 47057/61904 [1:57:28<5:58:08,  1.45s/it]
 76%|███████▌  | 47058/61904 [1:57:30<5:44:14,  1.39s/it]
 76%|███████▌  | 47059/61904 [1:57:31<5:42:52,  1.39s/it]
 76%|███████▌  | 47060/61904 [1:57:32<5:41:38,  1.38s/it]
                                                         
{'loss': 2.4593, 'learning_rate': 1.2405678724231816e-07, 'epoch': 12.16}
+
 76%|███████▌  | 47060/61904 [1:57:32<5:41:38,  1.38s/it]
 76%|███████▌  | 47061/61904 [1:57:34<5:36:53,  1.36s/it]
 76%|███████▌  | 47062/61904 [1:57:35<5:29:32,  1.33s/it]
 76%|███████▌  | 47063/61904 [1:57:36<5:39:15,  1.37s/it]
 76%|███████▌  | 47064/61904 [1:57:38<5:33:07,  1.35s/it]
 76%|███████▌  | 47065/61904 [1:57:39<5:28:22,  1.33s/it]
 76%|███████▌  | 47066/61904 [1:57:40<5:41:02,  1.38s/it]
 76%|███████▌  | 47067/61904 [1:57:42<5:36:23,  1.36s/it]
 76%|███████▌  | 47068/61904 [1:57:43<5:33:05,  1.35s/it]
 76%|███████▌  | 47069/61904 [1:57:44<5:36:30,  1.36s/it]
 76%|███████▌  | 47070/61904 [1:57:46<5:33:40,  1.35s/it]
 76%|███████▌  | 47071/61904 [1:57:47<5:27:36,  1.33s/it]
 76%|███████▌  | 47072/61904 [1:57:49<5:37:18,  1.36s/it]
 76%|███████▌  | 47073/61904 [1:57:50<5:39:07,  1.37s/it]
 76%|███████▌  | 47074/61904 [1:57:51<5:40:42,  1.38s/it]
 76%|███████▌  | 47075/61904 [1:57:53<5:57:24,  1.45s/it]
 76%|███████▌  | 47076/61904 [1:57:54<6:02:10,  1.47s/it]
 76%|███████▌  | 47077/61904 [1:57:56<5:53:49,  1.43s/it]
 76%|███████▌  | 47078/61904 [1:57:57<5:46:33,  1.40s/it]
 76%|███████▌  | 47079/61904 [1:57:58<5:42:53,  1.39s/it]
 76%|███████▌  | 47080/61904 [1:58:00<5:31:44,  1.34s/it]
                                                         
{'loss': 2.555, 'learning_rate': 1.2402437443277582e-07, 'epoch': 12.17}
+
 76%|███████▌  | 47080/61904 [1:58:00<5:31:44,  1.34s/it]
 76%|███████▌  | 47081/61904 [1:58:01<5:30:02,  1.34s/it]
 76%|███████▌  | 47082/61904 [1:58:02<5:34:41,  1.35s/it]
 76%|███████▌  | 47083/61904 [1:58:04<5:29:12,  1.33s/it]
 76%|███████▌  | 47084/61904 [1:58:05<5:33:04,  1.35s/it]
 76%|███████▌  | 47085/61904 [1:58:06<5:39:08,  1.37s/it]
 76%|███████▌  | 47086/61904 [1:58:08<5:33:16,  1.35s/it]
 76%|███████▌  | 47087/61904 [1:58:09<5:31:39,  1.34s/it]
 76%|███████▌  | 47088/61904 [1:58:10<5:19:53,  1.30s/it]
 76%|███████▌  | 47089/61904 [1:58:12<5:23:49,  1.31s/it]
 76%|███████▌  | 47090/61904 [1:58:13<5:30:40,  1.34s/it]
 76%|███████▌  | 47091/61904 [1:58:14<5:26:19,  1.32s/it]
 76%|███████▌  | 47092/61904 [1:58:16<5:30:32,  1.34s/it]
 76%|███████▌  | 47093/61904 [1:58:17<5:31:01,  1.34s/it]
 76%|███████▌  | 47094/61904 [1:58:18<5:35:07,  1.36s/it]
 76%|███████▌  | 47095/61904 [1:58:20<5:28:46,  1.33s/it]
 76%|███████▌  | 47096/61904 [1:58:21<5:30:38,  1.34s/it]
 76%|███████▌  | 47097/61904 [1:58:23<5:52:48,  1.43s/it]
 76%|███████▌  | 47098/61904 [1:58:24<5:53:45,  1.43s/it]
 76%|███████▌  | 47099/61904 [1:58:26<5:54:48,  1.44s/it]
 76%|███████▌  | 47100/61904 [1:58:27<5:56:19,  1.44s/it]
                                                         
{'loss': 2.5006, 'learning_rate': 1.239919616232335e-07, 'epoch': 12.17}
+
 76%|███████▌  | 47100/61904 [1:58:27<5:56:19,  1.44s/it]
 76%|███████▌  | 47101/61904 [1:58:28<5:48:05,  1.41s/it]
 76%|███████▌  | 47102/61904 [1:58:30<5:47:38,  1.41s/it]
 76%|███████▌  | 47103/61904 [1:58:31<5:47:05,  1.41s/it]
 76%|███████▌  | 47104/61904 [1:58:33<5:46:48,  1.41s/it]
 76%|███████▌  | 47105/61904 [1:58:34<5:46:11,  1.40s/it]
 76%|███████▌  | 47106/61904 [1:58:35<5:43:29,  1.39s/it]
 76%|███████▌  | 47107/61904 [1:58:37<5:30:01,  1.34s/it]
 76%|███████▌  | 47108/61904 [1:58:38<5:25:24,  1.32s/it]
 76%|███████▌  | 47109/61904 [1:58:39<5:35:19,  1.36s/it]
 76%|███████▌  | 47110/61904 [1:58:41<5:36:21,  1.36s/it]
 76%|███████▌  | 47111/61904 [1:58:42<5:46:52,  1.41s/it]
 76%|███████▌  | 47112/61904 [1:58:43<5:38:20,  1.37s/it]
 76%|███████▌  | 47113/61904 [1:58:45<5:45:32,  1.40s/it]
 76%|███████▌  | 47114/61904 [1:58:46<5:50:20,  1.42s/it]
 76%|███████▌  | 47115/61904 [1:58:48<5:48:46,  1.42s/it]
 76%|███████▌  | 47116/61904 [1:58:49<5:44:51,  1.40s/it]
 76%|███████▌  | 47117/61904 [1:58:50<5:36:55,  1.37s/it]
 76%|███████▌  | 47118/61904 [1:58:52<5:37:45,  1.37s/it]
 76%|███████▌  | 47119/61904 [1:58:53<5:36:33,  1.37s/it]
 76%|███████▌  | 47120/61904 [1:58:55<5:36:52,  1.37s/it]
                                                         
{'loss': 2.4607, 'learning_rate': 1.2395954881369117e-07, 'epoch': 12.18}
+
 76%|███████▌  | 47120/61904 [1:58:55<5:36:52,  1.37s/it]
 76%|███████▌  | 47121/61904 [1:58:56<5:31:28,  1.35s/it]
 76%|███████▌  | 47122/61904 [1:58:57<5:30:07,  1.34s/it]
 76%|███████▌  | 47123/61904 [1:58:59<5:30:05,  1.34s/it]
 76%|███████▌  | 47124/61904 [1:59:00<5:28:29,  1.33s/it]
 76%|███████▌  | 47125/61904 [1:59:01<5:31:17,  1.34s/it]
 76%|███████▌  | 47126/61904 [1:59:03<5:37:40,  1.37s/it]
 76%|███████▌  | 47127/61904 [1:59:04<5:38:16,  1.37s/it]
 76%|███████▌  | 47128/61904 [1:59:05<5:39:18,  1.38s/it]
 76%|███████▌  | 47129/61904 [1:59:07<5:31:43,  1.35s/it]
 76%|███████▌  | 47130/61904 [1:59:08<5:38:50,  1.38s/it]
 76%|███████▌  | 47131/61904 [1:59:10<5:48:10,  1.41s/it]
 76%|███████▌  | 47132/61904 [1:59:11<5:45:37,  1.40s/it]
 76%|███████▌  | 47133/61904 [1:59:12<5:40:41,  1.38s/it]
 76%|███████▌  | 47134/61904 [1:59:14<5:32:48,  1.35s/it]
 76%|███████▌  | 47135/61904 [1:59:15<5:31:26,  1.35s/it]
 76%|███████▌  | 47136/61904 [1:59:17<5:44:21,  1.40s/it]
 76%|███████▌  | 47137/61904 [1:59:18<5:46:22,  1.41s/it]
 76%|███████▌  | 47138/61904 [1:59:19<5:38:40,  1.38s/it]
 76%|███████▌  | 47139/61904 [1:59:21<5:49:51,  1.42s/it]
 76%|███████▌  | 47140/61904 [1:59:22<5:43:03,  1.39s/it]
                                                         
{'loss': 2.4595, 'learning_rate': 1.2392713600414883e-07, 'epoch': 12.18}
+
 76%|███████▌  | 47140/61904 [1:59:22<5:43:03,  1.39s/it]
 76%|███████▌  | 47141/61904 [1:59:24<5:44:37,  1.40s/it]
 76%|███████▌  | 47142/61904 [1:59:25<5:54:26,  1.44s/it]
 76%|███████▌  | 47143/61904 [1:59:26<5:42:14,  1.39s/it]
 76%|███████▌  | 47144/61904 [1:59:28<5:36:20,  1.37s/it]
 76%|███████▌  | 47145/61904 [1:59:29<5:54:01,  1.44s/it]
 76%|███████▌  | 47146/61904 [1:59:31<5:57:13,  1.45s/it]
 76%|███████▌  | 47147/61904 [1:59:32<5:54:02,  1.44s/it]
 76%|███████▌  | 47148/61904 [1:59:34<5:52:30,  1.43s/it]
 76%|███████▌  | 47149/61904 [1:59:35<5:38:58,  1.38s/it]
 76%|███████▌  | 47150/61904 [1:59:36<5:48:23,  1.42s/it]
 76%|███████▌  | 47151/61904 [1:59:38<5:42:10,  1.39s/it]
 76%|███████▌  | 47152/61904 [1:59:39<5:37:24,  1.37s/it]
 76%|███████▌  | 47153/61904 [1:59:40<5:28:17,  1.34s/it]
 76%|███████▌  | 47154/61904 [1:59:42<5:35:39,  1.37s/it]
 76%|███████▌  | 47155/61904 [1:59:43<5:50:44,  1.43s/it]
 76%|███████▌  | 47156/61904 [1:59:45<5:42:32,  1.39s/it]
 76%|███████▌  | 47157/61904 [1:59:46<5:30:45,  1.35s/it]
 76%|███████▌  | 47158/61904 [1:59:47<5:23:56,  1.32s/it]
 76%|███████▌  | 47159/61904 [1:59:48<5:16:20,  1.29s/it]
 76%|███████▌  | 47160/61904 [1:59:50<5:18:59,  1.30s/it]
                                                         
{'loss': 2.444, 'learning_rate': 1.238947231946065e-07, 'epoch': 12.19}
+
 76%|███████▌  | 47160/61904 [1:59:50<5:18:59,  1.30s/it]
 76%|███████▌  | 47161/61904 [1:59:51<5:29:08,  1.34s/it]
 76%|███████▌  | 47162/61904 [1:59:52<5:24:51,  1.32s/it]
 76%|███████▌  | 47163/61904 [1:59:54<5:34:11,  1.36s/it]
 76%|███████▌  | 47164/61904 [1:59:55<5:28:52,  1.34s/it]
 76%|███████▌  | 47165/61904 [1:59:57<5:40:24,  1.39s/it]
 76%|███████▌  | 47166/61904 [1:59:58<5:38:18,  1.38s/it]
 76%|███████▌  | 47167/61904 [1:59:59<5:50:47,  1.43s/it]
 76%|███████▌  | 47168/61904 [2:00:01<5:42:58,  1.40s/it]
 76%|███████▌  | 47169/61904 [2:00:02<5:46:52,  1.41s/it]
 76%|███████▌  | 47170/61904 [2:00:04<5:44:05,  1.40s/it]
 76%|███████▌  | 47171/61904 [2:00:05<5:35:42,  1.37s/it]
 76%|███████▌  | 47172/61904 [2:00:06<5:32:23,  1.35s/it]
 76%|███████▌  | 47173/61904 [2:00:07<5:24:02,  1.32s/it]
 76%|███████▌  | 47174/61904 [2:00:09<5:20:58,  1.31s/it]
 76%|███████▌  | 47175/61904 [2:00:10<5:16:58,  1.29s/it]
 76%|███████▌  | 47176/61904 [2:00:11<5:18:40,  1.30s/it]
 76%|███████▌  | 47177/61904 [2:00:13<5:17:31,  1.29s/it]
 76%|███████▌  | 47178/61904 [2:00:14<5:30:44,  1.35s/it]
 76%|███████▌  | 47179/61904 [2:00:15<5:25:41,  1.33s/it]
 76%|███████▌  | 47180/61904 [2:00:17<5:28:08,  1.34s/it]
                                                         
{'loss': 2.4657, 'learning_rate': 1.2386231038506418e-07, 'epoch': 12.19}
+
 76%|███████▌  | 47180/61904 [2:00:17<5:28:08,  1.34s/it]
 76%|███████▌  | 47181/61904 [2:00:18<5:24:48,  1.32s/it]
 76%|███████▌  | 47182/61904 [2:00:19<5:22:40,  1.32s/it]
 76%|███████▌  | 47183/61904 [2:00:21<5:20:18,  1.31s/it]
 76%|███████▌  | 47184/61904 [2:00:22<5:35:28,  1.37s/it]
 76%|███████▌  | 47185/61904 [2:00:24<5:42:41,  1.40s/it]
 76%|███████▌  | 47186/61904 [2:00:25<5:40:15,  1.39s/it]
 76%|███████▌  | 47187/61904 [2:00:26<5:44:49,  1.41s/it]
 76%|███████▌  | 47188/61904 [2:00:28<5:42:37,  1.40s/it]
 76%|███████▌  | 47189/61904 [2:00:29<5:48:27,  1.42s/it]
 76%|███████▌  | 47190/61904 [2:00:31<5:43:34,  1.40s/it]
 76%|███████▌  | 47191/61904 [2:00:32<5:45:32,  1.41s/it]
 76%|███████▌  | 47192/61904 [2:00:33<5:46:31,  1.41s/it]
 76%|███████▌  | 47193/61904 [2:00:35<5:40:56,  1.39s/it]
 76%|███████▌  | 47194/61904 [2:00:36<5:44:28,  1.41s/it]
 76%|███████▌  | 47195/61904 [2:00:37<5:36:42,  1.37s/it]
 76%|███████▌  | 47196/61904 [2:00:39<5:34:53,  1.37s/it]
 76%|███████▌  | 47197/61904 [2:00:40<5:35:36,  1.37s/it]
 76%|███████▌  | 47198/61904 [2:00:42<5:38:52,  1.38s/it]
 76%|███████▌  | 47199/61904 [2:00:43<5:34:37,  1.37s/it]
 76%|███████▌  | 47200/61904 [2:00:44<5:31:30,  1.35s/it]
                                                         
{'loss': 2.454, 'learning_rate': 1.2382989757552184e-07, 'epoch': 12.2}
+
 76%|███████▌  | 47200/61904 [2:00:44<5:31:30,  1.35s/it]
 76%|███████▌  | 47201/61904 [2:00:46<5:35:22,  1.37s/it]
 76%|███████▋  | 47202/61904 [2:00:47<5:25:44,  1.33s/it]
 76%|███████▋  | 47203/61904 [2:00:48<5:28:50,  1.34s/it]
 76%|███████▋  | 47204/61904 [2:00:50<5:37:31,  1.38s/it]
 76%|███████▋  | 47205/61904 [2:00:51<5:48:37,  1.42s/it]
 76%|███████▋  | 47206/61904 [2:00:53<5:39:53,  1.39s/it]
 76%|███████▋  | 47207/61904 [2:00:54<5:36:57,  1.38s/it]
 76%|███████▋  | 47208/61904 [2:00:55<5:40:07,  1.39s/it]
 76%|███████▋  | 47209/61904 [2:00:57<5:29:10,  1.34s/it]
 76%|███████▋  | 47210/61904 [2:00:58<5:25:38,  1.33s/it]
 76%|███████▋  | 47211/61904 [2:00:59<5:36:34,  1.37s/it]
 76%|███████▋  | 47212/61904 [2:01:01<5:40:51,  1.39s/it]
 76%|███████▋  | 47213/61904 [2:01:02<5:38:06,  1.38s/it]
 76%|███████▋  | 47214/61904 [2:01:04<5:46:16,  1.41s/it]
 76%|███████▋  | 47215/61904 [2:01:05<5:47:12,  1.42s/it]
 76%|███████▋  | 47216/61904 [2:01:06<5:35:59,  1.37s/it]
 76%|███████▋  | 47217/61904 [2:01:08<5:24:50,  1.33s/it]
 76%|███████▋  | 47218/61904 [2:01:09<5:25:33,  1.33s/it]
 76%|███████▋  | 47219/61904 [2:01:10<5:28:43,  1.34s/it]
 76%|███████▋  | 47220/61904 [2:01:12<5:40:21,  1.39s/it]
                                                         
{'loss': 2.4939, 'learning_rate': 1.237974847659795e-07, 'epoch': 12.2}
+
 76%|███████▋  | 47220/61904 [2:01:12<5:40:21,  1.39s/it]
 76%|███████▋  | 47221/61904 [2:01:13<5:41:49,  1.40s/it]
 76%|███████▋  | 47222/61904 [2:01:15<5:42:06,  1.40s/it]
 76%|███████▋  | 47223/61904 [2:01:16<5:36:04,  1.37s/it]
 76%|███████▋  | 47224/61904 [2:01:17<5:31:56,  1.36s/it]
 76%|███████▋  | 47225/61904 [2:01:19<5:28:30,  1.34s/it]
 76%|███████▋  | 47226/61904 [2:01:20<5:26:31,  1.33s/it]
 76%|███████▋  | 47227/61904 [2:01:21<5:29:42,  1.35s/it]
 76%|███████▋  | 47228/61904 [2:01:22<5:22:56,  1.32s/it]
 76%|███████▋  | 47229/61904 [2:01:24<5:25:26,  1.33s/it]
 76%|███████▋  | 47230/61904 [2:01:25<5:18:11,  1.30s/it]
 76%|███████▋  | 47231/61904 [2:01:26<5:21:48,  1.32s/it]
 76%|███████▋  | 47232/61904 [2:01:28<5:32:43,  1.36s/it]
 76%|███████▋  | 47233/61904 [2:01:29<5:41:04,  1.39s/it]
 76%|███████▋  | 47234/61904 [2:01:31<5:41:00,  1.39s/it]
 76%|███████▋  | 47235/61904 [2:01:32<5:46:42,  1.42s/it]
 76%|███████▋  | 47236/61904 [2:01:34<5:39:08,  1.39s/it]
 76%|███████▋  | 47237/61904 [2:01:35<5:47:18,  1.42s/it]
 76%|███████▋  | 47238/61904 [2:01:36<5:44:55,  1.41s/it]
 76%|███████▋  | 47239/61904 [2:01:38<5:40:28,  1.39s/it]
 76%|███████▋  | 47240/61904 [2:01:39<5:35:25,  1.37s/it]
                                                         
{'loss': 2.4465, 'learning_rate': 1.237650719564372e-07, 'epoch': 12.21}
+
 76%|███████▋  | 47240/61904 [2:01:39<5:35:25,  1.37s/it]
 76%|███████▋  | 47241/61904 [2:01:41<5:41:01,  1.40s/it]
 76%|███████▋  | 47242/61904 [2:01:42<5:48:51,  1.43s/it]
 76%|███████▋  | 47243/61904 [2:01:43<5:37:44,  1.38s/it]
 76%|███████▋  | 47244/61904 [2:01:45<5:37:16,  1.38s/it]
 76%|███████▋  | 47245/61904 [2:01:46<5:38:31,  1.39s/it]
 76%|███████▋  | 47246/61904 [2:01:47<5:39:47,  1.39s/it]
 76%|███████▋  | 47247/61904 [2:01:49<5:48:12,  1.43s/it]
 76%|███████▋  | 47248/61904 [2:01:50<5:39:18,  1.39s/it]
 76%|███████▋  | 47249/61904 [2:01:52<5:37:40,  1.38s/it]
 76%|███████▋  | 47250/61904 [2:01:53<5:37:45,  1.38s/it]
 76%|███████▋  | 47251/61904 [2:01:54<5:38:24,  1.39s/it]
 76%|███████▋  | 47252/61904 [2:01:56<5:37:09,  1.38s/it]
 76%|███████▋  | 47253/61904 [2:01:57<5:27:46,  1.34s/it]
 76%|███████▋  | 47254/61904 [2:01:58<5:21:38,  1.32s/it]
 76%|███████▋  | 47255/61904 [2:02:00<5:30:12,  1.35s/it]
 76%|███████▋  | 47256/61904 [2:02:01<5:25:44,  1.33s/it]
 76%|███████▋  | 47257/61904 [2:02:03<5:40:14,  1.39s/it]
 76%|███████▋  | 47258/61904 [2:02:04<5:36:57,  1.38s/it]
 76%|███████▋  | 47259/61904 [2:02:05<5:36:56,  1.38s/it]
 76%|███████▋  | 47260/61904 [2:02:07<5:54:49,  1.45s/it]
                                                         
{'loss': 2.5464, 'learning_rate': 1.2373265914689486e-07, 'epoch': 12.21}
+
 76%|███████▋  | 47260/61904 [2:02:07<5:54:49,  1.45s/it]
 76%|███████▋  | 47261/61904 [2:02:08<5:47:13,  1.42s/it]
 76%|███████▋  | 47262/61904 [2:02:10<5:41:35,  1.40s/it]
 76%|███████▋  | 47263/61904 [2:02:11<5:35:38,  1.38s/it]
 76%|███████▋  | 47264/61904 [2:02:12<5:38:46,  1.39s/it]
 76%|███████▋  | 47265/61904 [2:02:14<5:29:44,  1.35s/it]
 76%|███████▋  | 47266/61904 [2:02:15<5:30:16,  1.35s/it]
 76%|███████▋  | 47267/61904 [2:02:16<5:34:06,  1.37s/it]
 76%|███████▋  | 47268/61904 [2:02:18<5:31:12,  1.36s/it]
 76%|███████▋  | 47269/61904 [2:02:19<5:33:03,  1.37s/it]
 76%|███████▋  | 47270/61904 [2:02:20<5:32:31,  1.36s/it]
 76%|███████▋  | 47271/61904 [2:02:22<5:34:16,  1.37s/it]
 76%|███████▋  | 47272/61904 [2:02:23<5:37:09,  1.38s/it]
 76%|███████▋  | 47273/61904 [2:02:25<5:42:52,  1.41s/it]
 76%|███████▋  | 47274/61904 [2:02:26<5:42:13,  1.40s/it]
 76%|███████▋  | 47275/61904 [2:02:28<5:42:10,  1.40s/it]
 76%|███████▋  | 47276/61904 [2:02:29<5:53:27,  1.45s/it]
 76%|███████▋  | 47277/61904 [2:02:30<5:47:35,  1.43s/it]
 76%|███████▋  | 47278/61904 [2:02:32<5:41:09,  1.40s/it]
 76%|███████▋  | 47279/61904 [2:02:33<5:34:48,  1.37s/it]
 76%|███████▋  | 47280/61904 [2:02:34<5:31:43,  1.36s/it]
                                                         
{'loss': 2.4521, 'learning_rate': 1.2370024633735252e-07, 'epoch': 12.22}
+
 76%|███████▋  | 47280/61904 [2:02:34<5:31:43,  1.36s/it]
 76%|███████▋  | 47281/61904 [2:02:36<5:44:22,  1.41s/it]
 76%|███████▋  | 47282/61904 [2:02:37<5:45:42,  1.42s/it]
 76%|███████▋  | 47283/61904 [2:02:39<5:53:28,  1.45s/it]
 76%|███████▋  | 47284/61904 [2:02:40<5:44:10,  1.41s/it]
 76%|███████▋  | 47285/61904 [2:02:42<5:35:02,  1.38s/it]
 76%|███████▋  | 47286/61904 [2:02:43<5:33:57,  1.37s/it]
 76%|███████▋  | 47287/61904 [2:02:44<5:36:49,  1.38s/it]
 76%|███████▋  | 47288/61904 [2:02:46<5:32:03,  1.36s/it]
 76%|███████▋  | 47289/61904 [2:02:47<5:24:40,  1.33s/it]
 76%|███████▋  | 47290/61904 [2:02:48<5:30:36,  1.36s/it]
 76%|███████▋  | 47291/61904 [2:02:50<5:27:10,  1.34s/it]
 76%|███████▋  | 47292/61904 [2:02:51<5:29:12,  1.35s/it]
 76%|███████▋  | 47293/61904 [2:02:52<5:22:36,  1.32s/it]
 76%|███████▋  | 47294/61904 [2:02:54<5:21:52,  1.32s/it]
 76%|███████▋  | 47295/61904 [2:02:55<5:29:45,  1.35s/it]
 76%|███████▋  | 47296/61904 [2:02:56<5:34:13,  1.37s/it]
 76%|███████▋  | 47297/61904 [2:02:58<5:35:25,  1.38s/it]
 76%|███████▋  | 47298/61904 [2:02:59<5:28:38,  1.35s/it]
 76%|███████▋  | 47299/61904 [2:03:01<5:48:42,  1.43s/it]
 76%|███████▋  | 47300/61904 [2:03:02<5:49:26,  1.44s/it]
                                                         
{'loss': 2.5132, 'learning_rate': 1.2366783352781018e-07, 'epoch': 12.23}
+
 76%|███████▋  | 47300/61904 [2:03:02<5:49:26,  1.44s/it]
 76%|███████▋  | 47301/61904 [2:03:04<5:48:15,  1.43s/it]
 76%|███████▋  | 47302/61904 [2:03:05<5:56:00,  1.46s/it]
 76%|███████▋  | 47303/61904 [2:03:06<5:47:12,  1.43s/it]
 76%|███████▋  | 47304/61904 [2:03:08<5:38:49,  1.39s/it]
 76%|███████▋  | 47305/61904 [2:03:09<5:28:32,  1.35s/it]
 76%|███████▋  | 47306/61904 [2:03:11<5:41:37,  1.40s/it]
 76%|███████▋  | 47307/61904 [2:03:12<5:34:16,  1.37s/it]
 76%|███████▋  | 47308/61904 [2:03:13<5:28:47,  1.35s/it]
 76%|███████▋  | 47309/61904 [2:03:15<5:42:03,  1.41s/it]
 76%|███████▋  | 47310/61904 [2:03:16<5:41:28,  1.40s/it]
 76%|███████▋  | 47311/61904 [2:03:17<5:28:45,  1.35s/it]
 76%|███████▋  | 47312/61904 [2:03:19<5:24:41,  1.34s/it]
 76%|███████▋  | 47313/61904 [2:03:20<5:26:52,  1.34s/it]
 76%|███████▋  | 47314/61904 [2:03:21<5:32:08,  1.37s/it]
 76%|███████▋  | 47315/61904 [2:03:23<5:41:11,  1.40s/it]
 76%|███████▋  | 47316/61904 [2:03:24<5:40:10,  1.40s/it]
 76%|███████▋  | 47317/61904 [2:03:26<5:42:31,  1.41s/it]
 76%|███████▋  | 47318/61904 [2:03:27<5:52:46,  1.45s/it]
 76%|███████▋  | 47319/61904 [2:03:29<6:01:17,  1.49s/it]
 76%|███████▋  | 47320/61904 [2:03:30<5:45:15,  1.42s/it]
                                                         
{'loss': 2.43, 'learning_rate': 1.2363542071826787e-07, 'epoch': 12.23}
+
 76%|███████▋  | 47320/61904 [2:03:30<5:45:15,  1.42s/it]
 76%|███████▋  | 47321/61904 [2:03:31<5:43:20,  1.41s/it]
 76%|███████▋  | 47322/61904 [2:03:33<5:33:51,  1.37s/it]
 76%|███████▋  | 47323/61904 [2:03:34<5:34:36,  1.38s/it]
 76%|███████▋  | 47324/61904 [2:03:36<5:42:45,  1.41s/it]
 76%|███████▋  | 47325/61904 [2:03:37<5:35:10,  1.38s/it]
 76%|███████▋  | 47326/61904 [2:03:38<5:23:15,  1.33s/it]
 76%|███████▋  | 47327/61904 [2:03:39<5:17:23,  1.31s/it]
 76%|███████▋  | 47328/61904 [2:03:41<5:22:20,  1.33s/it]
 76%|███████▋  | 47329/61904 [2:03:42<5:26:49,  1.35s/it]
 76%|███████▋  | 47330/61904 [2:03:44<5:33:13,  1.37s/it]
 76%|███████▋  | 47331/61904 [2:03:45<5:25:37,  1.34s/it]
 76%|███████▋  | 47332/61904 [2:03:46<5:40:43,  1.40s/it]
 76%|███████▋  | 47333/61904 [2:03:48<5:35:35,  1.38s/it]
 76%|███████▋  | 47334/61904 [2:03:49<5:41:09,  1.40s/it]
 76%|███████▋  | 47335/61904 [2:03:51<5:35:24,  1.38s/it]
 76%|███████▋  | 47336/61904 [2:03:52<5:45:01,  1.42s/it]
 76%|███████▋  | 47337/61904 [2:03:53<5:43:31,  1.41s/it]
 76%|███████▋  | 47338/61904 [2:03:55<5:35:02,  1.38s/it]
 76%|███████▋  | 47339/61904 [2:03:56<5:27:15,  1.35s/it]
 76%|███████▋  | 47340/61904 [2:03:57<5:25:29,  1.34s/it]
                                                         
{'loss': 2.4295, 'learning_rate': 1.2360300790872553e-07, 'epoch': 12.24}
+
 76%|███████▋  | 47340/61904 [2:03:57<5:25:29,  1.34s/it]
 76%|███████▋  | 47341/61904 [2:03:59<5:25:34,  1.34s/it]
 76%|███████▋  | 47342/61904 [2:04:00<5:26:42,  1.35s/it]
 76%|███████▋  | 47343/61904 [2:04:02<5:42:18,  1.41s/it]
 76%|███████▋  | 47344/61904 [2:04:03<5:51:38,  1.45s/it]
 76%|███████▋  | 47345/61904 [2:04:05<6:08:40,  1.52s/it]
 76%|███████▋  | 47346/61904 [2:04:06<5:59:45,  1.48s/it]
 76%|███████▋  | 47347/61904 [2:04:08<5:56:37,  1.47s/it]
 76%|███████▋  | 47348/61904 [2:04:09<5:57:08,  1.47s/it]
 76%|███████▋  | 47349/61904 [2:04:11<5:49:09,  1.44s/it]
 76%|███████▋  | 47350/61904 [2:04:12<5:42:55,  1.41s/it]
 76%|███████▋  | 47351/61904 [2:04:13<5:38:48,  1.40s/it]
 76%|███████▋  | 47352/61904 [2:04:15<5:47:12,  1.43s/it]
 76%|███████▋  | 47353/61904 [2:04:16<5:45:04,  1.42s/it]
 76%|███████▋  | 47354/61904 [2:04:17<5:32:24,  1.37s/it]
 76%|███████▋  | 47355/61904 [2:04:19<5:35:23,  1.38s/it]
 76%|███████▋  | 47356/61904 [2:04:20<5:34:20,  1.38s/it]
 77%|███████▋  | 47357/61904 [2:04:22<5:34:44,  1.38s/it]
 77%|███████▋  | 47358/61904 [2:04:23<5:43:27,  1.42s/it]
 77%|███████▋  | 47359/61904 [2:04:24<5:41:32,  1.41s/it]
 77%|███████▋  | 47360/61904 [2:04:26<5:42:44,  1.41s/it]
                                                         
{'loss': 2.5134, 'learning_rate': 1.235705950991832e-07, 'epoch': 12.24}
+
 77%|███████▋  | 47360/61904 [2:04:26<5:42:44,  1.41s/it]
 77%|███████▋  | 47361/61904 [2:04:27<5:35:40,  1.38s/it]
 77%|███████▋  | 47362/61904 [2:04:28<5:28:09,  1.35s/it]
 77%|███████▋  | 47363/61904 [2:04:30<6:05:47,  1.51s/it]
 77%|███████▋  | 47364/61904 [2:04:32<5:47:49,  1.44s/it]
 77%|███████▋  | 47365/61904 [2:04:33<5:47:06,  1.43s/it]
 77%|███████▋  | 47366/61904 [2:04:34<5:43:38,  1.42s/it]
 77%|███████▋  | 47367/61904 [2:04:36<5:38:49,  1.40s/it]
 77%|███████▋  | 47368/61904 [2:04:37<5:41:25,  1.41s/it]
 77%|███████▋  | 47369/61904 [2:04:38<5:30:53,  1.37s/it]
 77%|███████▋  | 47370/61904 [2:04:40<5:38:27,  1.40s/it]
 77%|███████▋  | 47371/61904 [2:04:41<5:44:20,  1.42s/it]
 77%|███████▋  | 47372/61904 [2:04:43<5:51:04,  1.45s/it]
 77%|███████▋  | 47373/61904 [2:04:44<5:44:00,  1.42s/it]
 77%|███████▋  | 47374/61904 [2:04:46<5:44:13,  1.42s/it]
 77%|███████▋  | 47375/61904 [2:04:47<5:47:03,  1.43s/it]
 77%|███████▋  | 47376/61904 [2:04:49<5:47:54,  1.44s/it]
 77%|███████▋  | 47377/61904 [2:04:50<5:47:50,  1.44s/it]
 77%|███████▋  | 47378/61904 [2:04:51<5:39:57,  1.40s/it]
 77%|███████▋  | 47379/61904 [2:04:53<5:32:21,  1.37s/it]
 77%|███████▋  | 47380/61904 [2:04:54<5:20:58,  1.33s/it]
                                                         
{'loss': 2.461, 'learning_rate': 1.2353818228964085e-07, 'epoch': 12.25}
+
 77%|███████▋  | 47380/61904 [2:04:54<5:20:58,  1.33s/it]
 77%|███████▋  | 47381/61904 [2:04:55<5:31:47,  1.37s/it]
 77%|███████▋  | 47382/61904 [2:04:57<5:30:23,  1.37s/it]
 77%|███████▋  | 47383/61904 [2:04:58<5:35:36,  1.39s/it]
 77%|███████▋  | 47384/61904 [2:04:59<5:27:08,  1.35s/it]
 77%|███████▋  | 47385/61904 [2:05:01<5:26:15,  1.35s/it]
 77%|███████▋  | 47386/61904 [2:05:02<5:20:44,  1.33s/it]
 77%|███████▋  | 47387/61904 [2:05:04<5:32:09,  1.37s/it]
 77%|███████▋  | 47388/61904 [2:05:05<5:30:04,  1.36s/it]
 77%|███████▋  | 47389/61904 [2:05:06<5:22:54,  1.33s/it]
 77%|███████▋  | 47390/61904 [2:05:08<5:26:10,  1.35s/it]
 77%|███████▋  | 47391/61904 [2:05:09<5:23:55,  1.34s/it]
 77%|███████▋  | 47392/61904 [2:05:10<5:29:12,  1.36s/it]
 77%|██��████▋  | 47393/61904 [2:05:12<5:22:35,  1.33s/it]
 77%|███████▋  | 47394/61904 [2:05:13<5:17:00,  1.31s/it]
 77%|███████▋  | 47395/61904 [2:05:14<5:36:46,  1.39s/it]
 77%|███████▋  | 47396/61904 [2:05:16<5:32:27,  1.37s/it]
 77%|███████▋  | 47397/61904 [2:05:17<5:30:46,  1.37s/it]
 77%|███████▋  | 47398/61904 [2:05:18<5:31:12,  1.37s/it]
 77%|███████▋  | 47399/61904 [2:05:20<5:45:54,  1.43s/it]
 77%|███████▋  | 47400/61904 [2:05:21<5:40:16,  1.41s/it]
                                                         
{'loss': 2.4942, 'learning_rate': 1.2350576948009854e-07, 'epoch': 12.25}
+
 77%|███████▋  | 47400/61904 [2:05:21<5:40:16,  1.41s/it]
 77%|███████▋  | 47401/61904 [2:05:23<5:51:24,  1.45s/it]
 77%|███████▋  | 47402/61904 [2:05:24<5:46:48,  1.43s/it]
 77%|███████▋  | 47403/61904 [2:05:26<5:43:58,  1.42s/it]
 77%|███████▋  | 47404/61904 [2:05:27<5:38:55,  1.40s/it]
 77%|███████▋  | 47405/61904 [2:05:29<5:45:50,  1.43s/it]
 77%|███████▋  | 47406/61904 [2:05:30<5:58:49,  1.49s/it]
 77%|███████▋  | 47407/61904 [2:05:32<5:52:11,  1.46s/it]
 77%|███████▋  | 47408/61904 [2:05:33<5:47:25,  1.44s/it]
 77%|███████▋  | 47409/61904 [2:05:34<5:46:48,  1.44s/it]
 77%|███████▋  | 47410/61904 [2:05:36<5:50:41,  1.45s/it]
 77%|███████▋  | 47411/61904 [2:05:37<5:37:49,  1.40s/it]
 77%|███████▋  | 47412/61904 [2:05:38<5:30:10,  1.37s/it]
 77%|███████▋  | 47413/61904 [2:05:40<5:26:28,  1.35s/it]
 77%|███████▋  | 47414/61904 [2:05:41<5:23:16,  1.34s/it]
 77%|███████▋  | 47415/61904 [2:05:43<5:31:09,  1.37s/it]
 77%|███████▋  | 47416/61904 [2:05:44<5:29:11,  1.36s/it]
 77%|███████▋  | 47417/61904 [2:05:45<5:36:43,  1.39s/it]
 77%|███████▋  | 47418/61904 [2:05:47<5:37:31,  1.40s/it]
 77%|███████▋  | 47419/61904 [2:05:48<5:33:51,  1.38s/it]
 77%|███████▋  | 47420/61904 [2:05:49<5:34:56,  1.39s/it]
                                                         
{'loss': 2.4607, 'learning_rate': 1.234733566705562e-07, 'epoch': 12.26}
+
 77%|███████▋  | 47420/61904 [2:05:49<5:34:56,  1.39s/it]
 77%|███████▋  | 47421/61904 [2:05:51<5:35:06,  1.39s/it]
 77%|███████▋  | 47422/61904 [2:05:52<5:32:36,  1.38s/it]
 77%|███████▋  | 47423/61904 [2:05:54<5:29:34,  1.37s/it]
 77%|███████▋  | 47424/61904 [2:05:55<5:44:50,  1.43s/it]
 77%|███████▋  | 47425/61904 [2:05:56<5:35:37,  1.39s/it]
 77%|███████▋  | 47426/61904 [2:05:58<5:27:24,  1.36s/it]
 77%|███████▋  | 47427/61904 [2:05:59<5:23:37,  1.34s/it]
 77%|███████▋  | 47428/61904 [2:06:00<5:23:50,  1.34s/it]
 77%|███████▋  | 47429/61904 [2:06:02<5:41:40,  1.42s/it]
 77%|███████▋  | 47430/61904 [2:06:03<5:35:25,  1.39s/it]
 77%|███████▋  | 47431/61904 [2:06:05<5:29:49,  1.37s/it]
 77%|███████▋  | 47432/61904 [2:06:06<5:29:25,  1.37s/it]
 77%|███████▋  | 47433/61904 [2:06:07<5:28:56,  1.36s/it]
 77%|███████▋  | 47434/61904 [2:06:09<5:30:54,  1.37s/it]
 77%|███████▋  | 47435/61904 [2:06:10<5:23:17,  1.34s/it]
 77%|███████▋  | 47436/61904 [2:06:11<5:21:22,  1.33s/it]
 77%|███████▋  | 47437/61904 [2:06:13<5:40:48,  1.41s/it]
 77%|███████▋  | 47438/61904 [2:06:14<5:43:36,  1.43s/it]
 77%|███████▋  | 47439/61904 [2:06:16<5:38:44,  1.41s/it]
 77%|███████▋  | 47440/61904 [2:06:17<5:38:20,  1.40s/it]
                                                         
{'loss': 2.4634, 'learning_rate': 1.2344094386101387e-07, 'epoch': 12.26}
+
 77%|███████▋  | 47440/61904 [2:06:17<5:38:20,  1.40s/it]
 77%|███████▋  | 47441/61904 [2:06:18<5:37:54,  1.40s/it]
 77%|███████▋  | 47442/61904 [2:06:20<5:40:47,  1.41s/it]
 77%|███████▋  | 47443/61904 [2:06:21<5:28:13,  1.36s/it]
 77%|███████▋  | 47444/61904 [2:06:22<5:18:02,  1.32s/it]
 77%|███████▋  | 47445/61904 [2:06:24<5:18:51,  1.32s/it]
 77%|███████▋  | 47446/61904 [2:06:25<5:40:10,  1.41s/it]
 77%|███████▋  | 47447/61904 [2:06:27<5:35:34,  1.39s/it]
 77%|███████▋  | 47448/61904 [2:06:28<5:42:17,  1.42s/it]
 77%|███████▋  | 47449/61904 [2:06:30<5:43:42,  1.43s/it]
 77%|███████▋  | 47450/61904 [2:06:31<5:40:14,  1.41s/it]
 77%|███████▋  | 47451/61904 [2:06:32<5:33:27,  1.38s/it]
 77%|███████▋  | 47452/61904 [2:06:34<5:29:29,  1.37s/it]
 77%|███████▋  | 47453/61904 [2:06:35<5:21:46,  1.34s/it]
 77%|███████▋  | 47454/61904 [2:06:36<5:33:27,  1.38s/it]
 77%|███████▋  | 47455/61904 [2:06:38<5:38:27,  1.41s/it]
 77%|███████▋  | 47456/61904 [2:06:39<5:30:14,  1.37s/it]
 77%|███████▋  | 47457/61904 [2:06:40<5:24:15,  1.35s/it]
 77%|███████▋  | 47458/61904 [2:06:42<5:37:22,  1.40s/it]
 77%|███████▋  | 47459/61904 [2:06:43<5:36:02,  1.40s/it]
 77%|███████▋  | 47460/61904 [2:06:45<5:29:54,  1.37s/it]
                                                         
{'loss': 2.4448, 'learning_rate': 1.2340853105147153e-07, 'epoch': 12.27}
+
 77%|███████▋  | 47460/61904 [2:06:45<5:29:54,  1.37s/it]
 77%|███████▋  | 47461/61904 [2:06:46<5:25:22,  1.35s/it]
 77%|███████▋  | 47462/61904 [2:06:47<5:28:20,  1.36s/it]
 77%|███████▋  | 47463/61904 [2:06:49<5:24:04,  1.35s/it]
 77%|███████▋  | 47464/61904 [2:06:50<5:25:00,  1.35s/it]
 77%|███████▋  | 47465/61904 [2:06:51<5:27:45,  1.36s/it]
 77%|███████▋  | 47466/61904 [2:06:53<5:26:42,  1.36s/it]
 77%|███████▋  | 47467/61904 [2:06:54<5:24:32,  1.35s/it]
 77%|███████▋  | 47468/61904 [2:06:55<5:23:35,  1.34s/it]
 77%|███████▋  | 47469/61904 [2:06:57<5:21:09,  1.33s/it]
 77%|███████▋  | 47470/61904 [2:06:58<5:19:16,  1.33s/it]
 77%|███████▋  | 47471/61904 [2:06:59<5:12:25,  1.30s/it]
 77%|███████▋  | 47472/61904 [2:07:01<5:30:54,  1.38s/it]
 77%|███████▋  | 47473/61904 [2:07:02<5:28:28,  1.37s/it]
 77%|███████▋  | 47474/61904 [2:07:04<5:32:08,  1.38s/it]
 77%|███████▋  | 47475/61904 [2:07:05<5:28:02,  1.36s/it]
 77%|███████▋  | 47476/61904 [2:07:06<5:29:43,  1.37s/it]
 77%|███████▋  | 47477/61904 [2:07:08<5:38:28,  1.41s/it]
 77%|███████▋  | 47478/61904 [2:07:09<5:45:29,  1.44s/it]
 77%|███████▋  | 47479/61904 [2:07:11<5:46:58,  1.44s/it]
 77%|███████▋  | 47480/61904 [2:07:12<5:41:01,  1.42s/it]
                                                         
{'loss': 2.4803, 'learning_rate': 1.2337611824192922e-07, 'epoch': 12.27}
+
 77%|███████▋  | 47480/61904 [2:07:12<5:41:01,  1.42s/it]
 77%|███████▋  | 47481/61904 [2:07:14<5:41:03,  1.42s/it]
 77%|███████▋  | 47482/61904 [2:07:15<5:30:44,  1.38s/it]
 77%|███████▋  | 47483/61904 [2:07:16<5:45:39,  1.44s/it]
 77%|███████▋  | 47484/61904 [2:07:18<5:41:31,  1.42s/it]
 77%|███████▋  | 47485/61904 [2:07:19<5:32:08,  1.38s/it]
 77%|███████▋  | 47486/61904 [2:07:20<5:33:52,  1.39s/it]
 77%|███████▋  | 47487/61904 [2:07:22<5:27:58,  1.36s/it]
 77%|███████▋  | 47488/61904 [2:07:23<5:35:03,  1.39s/it]
 77%|███████▋  | 47489/61904 [2:07:25<5:30:31,  1.38s/it]
 77%|███████▋  | 47490/61904 [2:07:26<5:19:27,  1.33s/it]
 77%|███████▋  | 47491/61904 [2:07:27<5:12:37,  1.30s/it]
 77%|███████▋  | 47492/61904 [2:07:28<5:11:47,  1.30s/it]
 77%|███████▋  | 47493/61904 [2:07:30<5:11:45,  1.30s/it]
 77%|███████▋  | 47494/61904 [2:07:31<5:22:07,  1.34s/it]
 77%|███████▋  | 47495/61904 [2:07:32<5:15:59,  1.32s/it]
 77%|███████▋  | 47496/61904 [2:07:34<5:23:05,  1.35s/it]
 77%|███████▋  | 47497/61904 [2:07:35<5:27:19,  1.36s/it]
 77%|███████▋  | 47498/61904 [2:07:37<5:28:49,  1.37s/it]
 77%|███████▋  | 47499/61904 [2:07:38<5:25:04,  1.35s/it]
 77%|███████▋  | 47500/61904 [2:07:39<5:40:39,  1.42s/it]
                                                         
{'loss': 2.4154, 'learning_rate': 1.2334370543238688e-07, 'epoch': 12.28}
+
 77%|███████▋  | 47500/61904 [2:07:39<5:40:39,  1.42s/it]
 77%|███████▋  | 47501/61904 [2:07:41<5:37:25,  1.41s/it]
 77%|███████▋  | 47502/61904 [2:07:42<5:34:07,  1.39s/it]
 77%|███████▋  | 47503/61904 [2:07:43<5:26:29,  1.36s/it]
 77%|███████▋  | 47504/61904 [2:07:45<5:23:46,  1.35s/it]
 77%|███████▋  | 47505/61904 [2:07:46<5:31:05,  1.38s/it]
 77%|███████▋  | 47506/61904 [2:07:48<5:29:04,  1.37s/it]
 77%|███████▋  | 47507/61904 [2:07:49<5:27:12,  1.36s/it]
 77%|███████▋  | 47508/61904 [2:07:50<5:36:25,  1.40s/it]
 77%|███████▋  | 47509/61904 [2:07:52<5:31:31,  1.38s/it]
 77%|███████▋  | 47510/61904 [2:07:53<5:24:03,  1.35s/it]
 77%|███████▋  | 47511/61904 [2:07:54<5:30:16,  1.38s/it]
 77%|███████▋  | 47512/61904 [2:07:56<5:27:03,  1.36s/it]
 77%|███████▋  | 47513/61904 [2:07:57<5:24:02,  1.35s/it]
 77%|███████▋  | 47514/61904 [2:07:59<5:31:37,  1.38s/it]
 77%|███████▋  | 47515/61904 [2:08:00<5:34:36,  1.40s/it]
 77%|███████▋  | 47516/61904 [2:08:01<5:27:22,  1.37s/it]
 77%|███████▋  | 47517/61904 [2:08:03<5:32:23,  1.39s/it]
 77%|███████▋  | 47518/61904 [2:08:04<5:24:12,  1.35s/it]
 77%|███████▋  | 47519/61904 [2:08:05<5:22:51,  1.35s/it]
 77%|███████▋  | 47520/61904 [2:08:07<5:27:58,  1.37s/it]
                                                         
{'loss': 2.5181, 'learning_rate': 1.2331129262284454e-07, 'epoch': 12.28}
+
 77%|███████▋  | 47520/61904 [2:08:07<5:27:58,  1.37s/it]
 77%|███████▋  | 47521/61904 [2:08:08<5:27:21,  1.37s/it]
 77%|███████▋  | 47522/61904 [2:08:10<5:43:49,  1.43s/it]
 77%|███████▋  | 47523/61904 [2:08:11<5:39:41,  1.42s/it]
 77%|███████▋  | 47524/61904 [2:08:12<5:39:23,  1.42s/it]
 77%|███████▋  | 47525/61904 [2:08:14<5:38:04,  1.41s/it]
 77%|███████▋  | 47526/61904 [2:08:15<5:32:41,  1.39s/it]
 77%|███████▋  | 47527/61904 [2:08:17<5:35:10,  1.40s/it]
 77%|███████▋  | 47528/61904 [2:08:18<5:39:49,  1.42s/it]
 77%|███████▋  | 47529/61904 [2:08:19<5:36:51,  1.41s/it]
 77%|███████▋  | 47530/61904 [2:08:21<5:24:21,  1.35s/it]
 77%|███████▋  | 47531/61904 [2:08:22<5:25:43,  1.36s/it]
 77%|███████▋  | 47532/61904 [2:08:23<5:25:35,  1.36s/it]
 77%|███████▋  | 47533/61904 [2:08:25<5:38:12,  1.41s/it]
 77%|███████▋  | 47534/61904 [2:08:26<5:33:05,  1.39s/it]
 77%|███████▋  | 47535/61904 [2:08:28<5:37:03,  1.41s/it]
 77%|███████▋  | 47536/61904 [2:08:29<5:35:21,  1.40s/it]
 77%|███████▋  | 47537/61904 [2:08:31<5:32:58,  1.39s/it]
 77%|███████▋  | 47538/61904 [2:08:32<5:29:57,  1.38s/it]
 77%|███████▋  | 47539/61904 [2:08:33<5:24:54,  1.36s/it]
 77%|███████▋  | 47540/61904 [2:08:35<5:36:35,  1.41s/it]
                                                         
{'loss': 2.5086, 'learning_rate': 1.2327887981330223e-07, 'epoch': 12.29}
+
 77%|███████▋  | 47540/61904 [2:08:35<5:36:35,  1.41s/it]
 77%|███████▋  | 47541/61904 [2:08:36<5:44:16,  1.44s/it]
 77%|███████▋  | 47542/61904 [2:08:38<5:36:34,  1.41s/it]
 77%|███████▋  | 47543/61904 [2:08:39<5:26:07,  1.36s/it]
 77%|███████▋  | 47544/61904 [2:08:40<5:22:09,  1.35s/it]
 77%|███████▋  | 47545/61904 [2:08:42<5:31:59,  1.39s/it]
 77%|███████▋  | 47546/61904 [2:08:43<5:31:57,  1.39s/it]
 77%|███████▋  | 47547/61904 [2:08:44<5:23:22,  1.35s/it]
 77%|███████▋  | 47548/61904 [2:08:46<5:30:34,  1.38s/it]
 77%|███████▋  | 47549/61904 [2:08:47<5:30:34,  1.38s/it]
 77%|███████▋  | 47550/61904 [2:08:48<5:31:20,  1.39s/it]
 77%|███████▋  | 47551/61904 [2:08:50<5:32:36,  1.39s/it]
 77%|███████▋  | 47552/61904 [2:08:51<5:22:31,  1.35s/it]
 77%|███████▋  | 47553/61904 [2:08:52<5:14:59,  1.32s/it]
 77%|███████▋  | 47554/61904 [2:08:54<5:20:18,  1.34s/it]
 77%|███████▋  | 47555/61904 [2:08:55<5:10:06,  1.30s/it]
 77%|███████▋  | 47556/61904 [2:08:56<5:15:11,  1.32s/it]
 77%|███████▋  | 47557/61904 [2:08:58<5:20:01,  1.34s/it]
 77%|███████▋  | 47558/61904 [2:08:59<5:18:21,  1.33s/it]
 77%|███████▋  | 47559/61904 [2:09:01<5:27:35,  1.37s/it]
 77%|███████▋  | 47560/61904 [2:09:02<5:23:10,  1.35s/it]
                                                         
{'loss': 2.4487, 'learning_rate': 1.232464670037599e-07, 'epoch': 12.29}
+
 77%|███████▋  | 47560/61904 [2:09:02<5:23:10,  1.35s/it]
 77%|███████▋  | 47561/61904 [2:09:03<5:34:23,  1.40s/it]
 77%|███████▋  | 47562/61904 [2:09:05<5:23:13,  1.35s/it]
 77%|███████▋  | 47563/61904 [2:09:06<5:20:33,  1.34s/it]
 77%|███████▋  | 47564/61904 [2:09:07<5:32:33,  1.39s/it]
 77%|███████▋  | 47565/61904 [2:09:09<5:30:49,  1.38s/it]
 77%|███████▋  | 47566/61904 [2:09:10<5:33:52,  1.40s/it]
 77%|███████▋  | 47567/61904 [2:09:12<5:34:25,  1.40s/it]
 77%|███████▋  | 47568/61904 [2:09:13<5:29:19,  1.38s/it]
 77%|███████▋  | 47569/61904 [2:09:14<5:24:53,  1.36s/it]
 77%|███████▋  | 47570/61904 [2:09:16<5:27:12,  1.37s/it]
 77%|███████▋  | 47571/61904 [2:09:17<5:27:51,  1.37s/it]
 77%|███████▋  | 47572/61904 [2:09:18<5:31:41,  1.39s/it]
 77%|███████▋  | 47573/61904 [2:09:20<5:40:53,  1.43s/it]
 77%|███████▋  | 47574/61904 [2:09:21<5:34:28,  1.40s/it]
 77%|███████▋  | 47575/61904 [2:09:23<5:23:36,  1.36s/it]
 77%|███████▋  | 47576/61904 [2:09:24<5:23:43,  1.36s/it]
 77%|███████▋  | 47577/61904 [2:09:25<5:23:28,  1.35s/it]
 77%|███████▋  | 47578/61904 [2:09:27<5:19:26,  1.34s/it]
 77%|███████▋  | 47579/61904 [2:09:28<5:20:05,  1.34s/it]
 77%|███████▋  | 47580/61904 [2:09:29<5:32:24,  1.39s/it]
                                                         
{'loss': 2.4109, 'learning_rate': 1.2321405419421755e-07, 'epoch': 12.3}
+
 77%|███████▋  | 47580/61904 [2:09:29<5:32:24,  1.39s/it]
 77%|███████▋  | 47581/61904 [2:09:31<5:26:25,  1.37s/it]
 77%|███████▋  | 47582/61904 [2:09:32<5:22:42,  1.35s/it]
 77%|███████▋  | 47583/61904 [2:09:33<5:23:54,  1.36s/it]
 77%|███████▋  | 47584/61904 [2:09:35<5:27:02,  1.37s/it]
 77%|███████▋  | 47585/61904 [2:09:36<5:25:49,  1.37s/it]
 77%|███████▋  | 47586/61904 [2:09:37<5:19:13,  1.34s/it]
 77%|███████▋  | 47587/61904 [2:09:39<5:28:26,  1.38s/it]
 77%|███████▋  | 47588/61904 [2:09:40<5:20:12,  1.34s/it]
 77%|███████▋  | 47589/61904 [2:09:42<5:23:22,  1.36s/it]
 77%|███████▋  | 47590/61904 [2:09:43<5:22:59,  1.35s/it]
 77%|███████▋  | 47591/61904 [2:09:44<5:28:52,  1.38s/it]
 77%|███████▋  | 47592/61904 [2:09:46<5:34:51,  1.40s/it]
 77%|███████▋  | 47593/61904 [2:09:47<5:26:03,  1.37s/it]
 77%|███████▋  | 47594/61904 [2:09:48<5:23:06,  1.35s/it]
 77%|███████▋  | 47595/61904 [2:09:50<5:19:11,  1.34s/it]
 77%|███████▋  | 47596/61904 [2:09:51<5:14:45,  1.32s/it]
 77%|███████▋  | 47597/61904 [2:09:52<5:23:33,  1.36s/it]
 77%|███████▋  | 47598/61904 [2:09:54<5:24:48,  1.36s/it]
 77%|███████▋  | 47599/61904 [2:09:55<5:35:55,  1.41s/it]
 77%|███████▋  | 47600/61904 [2:09:57<5:28:17,  1.38s/it]
                                                         
{'loss': 2.4675, 'learning_rate': 1.2318164138467521e-07, 'epoch': 12.3}
+
 77%|███████▋  | 47600/61904 [2:09:57<5:28:17,  1.38s/it]
 77%|███████▋  | 47601/61904 [2:09:58<5:23:41,  1.36s/it]
 77%|███████▋  | 47602/61904 [2:09:59<5:22:04,  1.35s/it]
 77%|███████▋  | 47603/61904 [2:10:01<5:33:00,  1.40s/it]
 77%|███████▋  | 47604/61904 [2:10:02<5:26:20,  1.37s/it]
 77%|███████▋  | 47605/61904 [2:10:03<5:26:16,  1.37s/it]
 77%|███████▋  | 47606/61904 [2:10:05<5:19:45,  1.34s/it]
 77%|███████▋  | 47607/61904 [2:10:06<5:30:58,  1.39s/it]
 77%|███████▋  | 47608/61904 [2:10:08<5:25:30,  1.37s/it]
 77%|███████▋  | 47609/61904 [2:10:09<5:32:10,  1.39s/it]
 77%|███████▋  | 47610/61904 [2:10:10<5:24:57,  1.36s/it]
 77%|███████▋  | 47611/61904 [2:10:12<5:32:03,  1.39s/it]
 77%|███████▋  | 47612/61904 [2:10:13<5:30:59,  1.39s/it]
 77%|███████▋  | 47613/61904 [2:10:14<5:26:49,  1.37s/it]
 77%|███████▋  | 47614/61904 [2:10:16<5:23:59,  1.36s/it]
 77%|███████▋  | 47615/61904 [2:10:17<5:18:28,  1.34s/it]
 77%|███████▋  | 47616/61904 [2:10:18<5:19:53,  1.34s/it]
 77%|███████▋  | 47617/61904 [2:10:20<5:19:23,  1.34s/it]
 77%|███████▋  | 47618/61904 [2:10:21<5:27:03,  1.37s/it]
 77%|███████▋  | 47619/61904 [2:10:23<5:24:49,  1.36s/it]
 77%|███████▋  | 47620/61904 [2:10:24<5:32:07,  1.40s/it]
                                                         
{'loss': 2.4326, 'learning_rate': 1.2314922857513288e-07, 'epoch': 12.31}
+
 77%|███████▋  | 47620/61904 [2:10:24<5:32:07,  1.40s/it]
 77%|███████▋  | 47621/61904 [2:10:25<5:22:36,  1.36s/it]
 77%|███████▋  | 47622/61904 [2:10:27<5:30:36,  1.39s/it]
 77%|███████▋  | 47623/61904 [2:10:28<5:25:40,  1.37s/it]
 77%|███████▋  | 47624/61904 [2:10:30<5:31:54,  1.39s/it]
 77%|███████▋  | 47625/61904 [2:10:31<5:36:50,  1.42s/it]
 77%|███████▋  | 47626/61904 [2:10:32<5:26:39,  1.37s/it]
 77%|███████▋  | 47627/61904 [2:10:34<5:24:36,  1.36s/it]
 77%|███████▋  | 47628/61904 [2:10:35<5:25:01,  1.37s/it]
 77%|███████▋  | 47629/61904 [2:10:36<5:25:44,  1.37s/it]
 77%|███████▋  | 47630/61904 [2:10:38<5:20:26,  1.35s/it]
 77%|███████▋  | 47631/61904 [2:10:39<5:35:30,  1.41s/it]
 77%|███████▋  | 47632/61904 [2:10:41<5:37:14,  1.42s/it]
 77%|███████▋  | 47633/61904 [2:10:42<5:33:32,  1.40s/it]
 77%|███████▋  | 47634/61904 [2:10:43<5:31:03,  1.39s/it]
 77%|███████▋  | 47635/61904 [2:10:45<5:34:53,  1.41s/it]
 77%|████��██▋  | 47636/61904 [2:10:46<5:39:44,  1.43s/it]
 77%|███████▋  | 47637/61904 [2:10:48<5:28:24,  1.38s/it]
 77%|███████▋  | 47638/61904 [2:10:49<5:27:52,  1.38s/it]
 77%|███████▋  | 47639/61904 [2:10:50<5:24:39,  1.37s/it]
 77%|███████▋  | 47640/61904 [2:10:52<5:23:04,  1.36s/it]
                                                         
{'loss': 2.441, 'learning_rate': 1.2311681576559056e-07, 'epoch': 12.31}
+
 77%|███████▋  | 47640/61904 [2:10:52<5:23:04,  1.36s/it]
 77%|███████▋  | 47641/61904 [2:10:53<5:25:48,  1.37s/it]
 77%|███████▋  | 47642/61904 [2:10:55<5:33:53,  1.40s/it]
 77%|███████▋  | 47643/61904 [2:10:56<5:25:57,  1.37s/it]
 77%|███████▋  | 47644/61904 [2:10:57<5:25:23,  1.37s/it]
 77%|███████▋  | 47645/61904 [2:10:59<5:28:24,  1.38s/it]
 77%|███████▋  | 47646/61904 [2:11:00<5:27:01,  1.38s/it]
 77%|███████▋  | 47647/61904 [2:11:01<5:27:06,  1.38s/it]
 77%|███████▋  | 47648/61904 [2:11:03<5:28:54,  1.38s/it]
 77%|███████▋  | 47649/61904 [2:11:04<5:24:27,  1.37s/it]
 77%|███████▋  | 47650/61904 [2:11:05<5:21:39,  1.35s/it]
 77%|███████▋  | 47651/61904 [2:11:07<5:33:35,  1.40s/it]
 77%|███████▋  | 47652/61904 [2:11:08<5:22:48,  1.36s/it]
 77%|███████▋  | 47653/61904 [2:11:09<5:21:22,  1.35s/it]
 77%|███████▋  | 47654/61904 [2:11:11<5:14:40,  1.32s/it]
 77%|███████▋  | 47655/61904 [2:11:12<5:14:19,  1.32s/it]
 77%|███████▋  | 47656/61904 [2:11:13<5:19:59,  1.35s/it]
 77%|███████▋  | 47657/61904 [2:11:15<5:35:12,  1.41s/it]
 77%|███████▋  | 47658/61904 [2:11:16<5:28:46,  1.38s/it]
 77%|███████▋  | 47659/61904 [2:11:18<5:21:38,  1.35s/it]
 77%|███████▋  | 47660/61904 [2:11:19<5:25:17,  1.37s/it]
                                                         
{'loss': 2.4154, 'learning_rate': 1.2308440295604823e-07, 'epoch': 12.32}
+
 77%|███████▋  | 47660/61904 [2:11:19<5:25:17,  1.37s/it]
 77%|███████▋  | 47661/61904 [2:11:20<5:29:02,  1.39s/it]
 77%|███████▋  | 47662/61904 [2:11:22<5:35:33,  1.41s/it]
 77%|███████▋  | 47663/61904 [2:11:23<5:32:22,  1.40s/it]
 77%|███████▋  | 47664/61904 [2:11:25<5:25:35,  1.37s/it]
 77%|███████▋  | 47665/61904 [2:11:26<5:20:04,  1.35s/it]
 77%|███████▋  | 47666/61904 [2:11:27<5:23:17,  1.36s/it]
 77%|███████▋  | 47667/61904 [2:11:29<5:18:03,  1.34s/it]
 77%|███████▋  | 47668/61904 [2:11:30<5:15:39,  1.33s/it]
 77%|███████▋  | 47669/61904 [2:11:31<5:20:27,  1.35s/it]
 77%|███████▋  | 47670/61904 [2:11:32<5:09:13,  1.30s/it]
 77%|███████▋  | 47671/61904 [2:11:34<5:18:50,  1.34s/it]
 77%|███████▋  | 47672/61904 [2:11:35<5:18:18,  1.34s/it]
 77%|███████▋  | 47673/61904 [2:11:37<5:21:07,  1.35s/it]
 77%|███████▋  | 47674/61904 [2:11:38<5:23:41,  1.36s/it]
 77%|███████▋  | 47675/61904 [2:11:40<5:35:53,  1.42s/it]
 77%|███████▋  | 47676/61904 [2:11:41<5:35:44,  1.42s/it]
 77%|███████▋  | 47677/61904 [2:11:42<5:28:03,  1.38s/it]
 77%|███████▋  | 47678/61904 [2:11:44<5:19:01,  1.35s/it]
 77%|███████▋  | 47679/61904 [2:11:45<5:30:19,  1.39s/it]
 77%|███████▋  | 47680/61904 [2:11:47<5:34:18,  1.41s/it]
                                                         
{'loss': 2.4491, 'learning_rate': 1.230519901465059e-07, 'epoch': 12.32}
+
 77%|███████▋  | 47680/61904 [2:11:47<5:34:18,  1.41s/it]
 77%|███████▋  | 47681/61904 [2:11:48<5:38:06,  1.43s/it]
 77%|███████▋  | 47682/61904 [2:11:49<5:28:29,  1.39s/it]
 77%|███████▋  | 47683/61904 [2:11:51<5:25:11,  1.37s/it]
 77%|███████▋  | 47684/61904 [2:11:52<5:32:08,  1.40s/it]
 77%|███████▋  | 47685/61904 [2:11:53<5:26:24,  1.38s/it]
 77%|███████▋  | 47686/61904 [2:11:55<5:18:27,  1.34s/it]
 77%|███████▋  | 47687/61904 [2:11:56<5:21:01,  1.35s/it]
 77%|███████▋  | 47688/61904 [2:11:57<5:21:39,  1.36s/it]
 77%|███████▋  | 47689/61904 [2:11:59<5:27:42,  1.38s/it]
 77%|███████▋  | 47690/61904 [2:12:00<5:13:45,  1.32s/it]
 77%|███████▋  | 47691/61904 [2:12:01<5:12:41,  1.32s/it]
 77%|███████▋  | 47692/61904 [2:12:03<5:14:27,  1.33s/it]
 77%|███████▋  | 47693/61904 [2:12:04<5:32:09,  1.40s/it]
 77%|███████▋  | 47694/61904 [2:12:06<5:21:21,  1.36s/it]
 77%|███████▋  | 47695/61904 [2:12:07<5:21:58,  1.36s/it]
 77%|███████▋  | 47696/61904 [2:12:08<5:22:04,  1.36s/it]
 77%|███████▋  | 47697/61904 [2:12:10<5:28:25,  1.39s/it]
 77%|███████▋  | 47698/61904 [2:12:11<5:18:42,  1.35s/it]
 77%|███████▋  | 47699/61904 [2:12:12<5:21:03,  1.36s/it]
 77%|███████▋  | 47700/61904 [2:12:14<5:15:05,  1.33s/it]
                                                         
{'loss': 2.4764, 'learning_rate': 1.2301957733696358e-07, 'epoch': 12.33}
+
 77%|███████▋  | 47700/61904 [2:12:14<5:15:05,  1.33s/it]
 77%|███████▋  | 47701/61904 [2:12:15<5:11:56,  1.32s/it]
 77%|███████▋  | 47702/61904 [2:12:16<5:19:59,  1.35s/it]
 77%|███████▋  | 47703/61904 [2:12:18<5:23:14,  1.37s/it]
 77%|███████▋  | 47704/61904 [2:12:19<5:16:45,  1.34s/it]
 77%|███████▋  | 47705/61904 [2:12:20<5:10:40,  1.31s/it]
 77%|███████▋  | 47706/61904 [2:12:22<5:12:24,  1.32s/it]
 77%|███████▋  | 47707/61904 [2:12:23<5:32:48,  1.41s/it]
 77%|███████▋  | 47708/61904 [2:12:25<5:36:50,  1.42s/it]
 77%|███████▋  | 47709/61904 [2:12:26<5:29:24,  1.39s/it]
 77%|███████▋  | 47710/61904 [2:12:27<5:21:04,  1.36s/it]
 77%|███████▋  | 47711/61904 [2:12:29<5:26:56,  1.38s/it]
 77%|███████▋  | 47712/61904 [2:12:30<5:32:13,  1.40s/it]
 77%|███████▋  | 47713/61904 [2:12:31<5:19:50,  1.35s/it]
 77%|███████▋  | 47714/61904 [2:12:33<5:15:46,  1.34s/it]
 77%|███████▋  | 47715/61904 [2:12:34<5:26:53,  1.38s/it]
 77%|███████▋  | 47716/61904 [2:12:35<5:20:07,  1.35s/it]
 77%|███████▋  | 47717/61904 [2:12:37<5:18:48,  1.35s/it]
 77%|███████▋  | 47718/61904 [2:12:38<5:28:47,  1.39s/it]
 77%|███████▋  | 47719/61904 [2:12:40<5:25:55,  1.38s/it]
 77%|███████▋  | 47720/61904 [2:12:41<5:25:25,  1.38s/it]
                                                         
{'loss': 2.4786, 'learning_rate': 1.2298716452742124e-07, 'epoch': 12.33}
+
 77%|███████▋  | 47720/61904 [2:12:41<5:25:25,  1.38s/it]
 77%|███████▋  | 47721/61904 [2:12:42<5:27:37,  1.39s/it]
 77%|███████▋  | 47722/61904 [2:12:44<5:27:56,  1.39s/it]
 77%|███████▋  | 47723/61904 [2:12:45<5:34:12,  1.41s/it]
 77%|███████▋  | 47724/61904 [2:12:47<5:33:16,  1.41s/it]
 77%|███████▋  | 47725/61904 [2:12:48<5:26:50,  1.38s/it]
 77%|███████▋  | 47726/61904 [2:12:50<5:52:14,  1.49s/it]
 77%|███████▋  | 47727/61904 [2:12:51<5:47:17,  1.47s/it]
 77%|███████▋  | 47728/61904 [2:12:53<5:45:24,  1.46s/it]
 77%|███████▋  | 47729/61904 [2:12:54<5:39:43,  1.44s/it]
 77%|███████▋  | 47730/61904 [2:12:55<5:34:08,  1.41s/it]
 77%|███████▋  | 47731/61904 [2:12:57<5:25:06,  1.38s/it]
 77%|███████▋  | 47732/61904 [2:12:58<5:21:30,  1.36s/it]
 77%|███████▋  | 47733/61904 [2:12:59<5:28:15,  1.39s/it]
 77%|███████▋  | 47734/61904 [2:13:01<5:16:29,  1.34s/it]
 77%|███████▋  | 47735/61904 [2:13:02<5:16:24,  1.34s/it]
 77%|███████▋  | 47736/61904 [2:13:03<5:14:20,  1.33s/it]
 77%|███████▋  | 47737/61904 [2:13:05<5:11:55,  1.32s/it]
 77%|███████▋  | 47738/61904 [2:13:06<5:03:31,  1.29s/it]
 77%|███████▋  | 47739/61904 [2:13:07<5:15:31,  1.34s/it]
 77%|███████▋  | 47740/61904 [2:13:09<5:24:51,  1.38s/it]
                                                         
{'loss': 2.4033, 'learning_rate': 1.229547517178789e-07, 'epoch': 12.34}
+
 77%|███████▋  | 47740/61904 [2:13:09<5:24:51,  1.38s/it]
 77%|███████▋  | 47741/61904 [2:13:10<5:20:58,  1.36s/it]
 77%|███████▋  | 47742/61904 [2:13:11<5:17:36,  1.35s/it]
 77%|███████▋  | 47743/61904 [2:13:13<5:16:54,  1.34s/it]
 77%|███████▋  | 47744/61904 [2:13:14<5:17:28,  1.35s/it]
 77%|███████▋  | 47745/61904 [2:13:15<5:20:34,  1.36s/it]
 77%|███████▋  | 47746/61904 [2:13:17<5:22:35,  1.37s/it]
 77%|███████▋  | 47747/61904 [2:13:18<5:23:56,  1.37s/it]
 77%|███████▋  | 47748/61904 [2:13:20<5:26:04,  1.38s/it]
 77%|███████▋  | 47749/61904 [2:13:21<5:27:57,  1.39s/it]
 77%|███████▋  | 47750/61904 [2:13:22<5:29:47,  1.40s/it]
 77%|███████▋  | 47751/61904 [2:13:24<5:18:37,  1.35s/it]
 77%|███████▋  | 47752/61904 [2:13:25<5:19:34,  1.35s/it]
 77%|███████▋  | 47753/61904 [2:13:26<5:15:48,  1.34s/it]
 77%|███████▋  | 47754/61904 [2:13:28<5:25:50,  1.38s/it]
 77%|███████▋  | 47755/61904 [2:13:29<5:37:19,  1.43s/it]
 77%|███████▋  | 47756/61904 [2:13:31<5:40:44,  1.45s/it]
 77%|███████▋  | 47757/61904 [2:13:32<5:37:20,  1.43s/it]
 77%|███████▋  | 47758/61904 [2:13:34<5:30:28,  1.40s/it]
 77%|███████▋  | 47759/61904 [2:13:35<5:21:31,  1.36s/it]
 77%|███████▋  | 47760/61904 [2:13:36<5:16:46,  1.34s/it]
                                                         
{'loss': 2.4742, 'learning_rate': 1.2292233890833656e-07, 'epoch': 12.34}
+
 77%|███████▋  | 47760/61904 [2:13:36<5:16:46,  1.34s/it]
 77%|███████▋  | 47761/61904 [2:13:37<5:13:19,  1.33s/it]
 77%|███████▋  | 47762/61904 [2:13:39<5:19:06,  1.35s/it]
 77%|███████▋  | 47763/61904 [2:13:40<5:13:52,  1.33s/it]
 77%|███████▋  | 47764/61904 [2:13:41<5:16:42,  1.34s/it]
 77%|███████▋  | 47765/61904 [2:13:43<5:38:05,  1.43s/it]
 77%|███████▋  | 47766/61904 [2:13:45<5:42:09,  1.45s/it]
 77%|███████▋  | 47767/61904 [2:13:46<5:39:37,  1.44s/it]
 77%|███████▋  | 47768/61904 [2:13:47<5:33:30,  1.42s/it]
 77%|███████▋  | 47769/61904 [2:13:49<5:32:39,  1.41s/it]
 77%|███████▋  | 47770/61904 [2:13:50<5:31:37,  1.41s/it]
 77%|███████▋  | 47771/61904 [2:13:52<5:27:34,  1.39s/it]
 77%|███████▋  | 47772/61904 [2:13:53<5:20:59,  1.36s/it]
 77%|███████▋  | 47773/61904 [2:13:54<5:15:15,  1.34s/it]
 77%|███████▋  | 47774/61904 [2:13:56<5:21:19,  1.36s/it]
 77%|███████▋  | 47775/61904 [2:13:57<5:11:30,  1.32s/it]
 77%|███████▋  | 47776/61904 [2:13:58<5:16:26,  1.34s/it]
 77%|███████▋  | 47777/61904 [2:14:00<5:24:22,  1.38s/it]
 77%|███████▋  | 47778/61904 [2:14:01<5:27:06,  1.39s/it]
 77%|███████▋  | 47779/61904 [2:14:02<5:25:14,  1.38s/it]
 77%|███████▋  | 47780/61904 [2:14:04<5:25:39,  1.38s/it]
                                                         
{'loss': 2.5316, 'learning_rate': 1.2288992609879422e-07, 'epoch': 12.35}
+
 77%|███████▋  | 47780/61904 [2:14:04<5:25:39,  1.38s/it]
 77%|███████▋  | 47781/61904 [2:14:05<5:23:04,  1.37s/it]
 77%|███████▋  | 47782/61904 [2:14:06<5:19:52,  1.36s/it]
 77%|███████▋  | 47783/61904 [2:14:08<5:10:16,  1.32s/it]
 77%|███████▋  | 47784/61904 [2:14:09<5:20:53,  1.36s/it]
 77%|███████▋  | 47785/61904 [2:14:11<5:20:27,  1.36s/it]
 77%|███████▋  | 47786/61904 [2:14:12<5:25:24,  1.38s/it]
 77%|███████▋  | 47787/61904 [2:14:13<5:24:54,  1.38s/it]
 77%|███████▋  | 47788/61904 [2:14:15<5:22:46,  1.37s/it]
 77%|███████▋  | 47789/61904 [2:14:16<5:21:58,  1.37s/it]
 77%|███████▋  | 47790/61904 [2:14:17<5:15:09,  1.34s/it]
 77%|███████▋  | 47791/61904 [2:14:19<5:15:36,  1.34s/it]
 77%|███████▋  | 47792/61904 [2:14:20<5:21:19,  1.37s/it]
 77%|███████▋  | 47793/61904 [2:14:21<5:16:44,  1.35s/it]
 77%|███████▋  | 47794/61904 [2:14:23<5:16:31,  1.35s/it]
 77%|███████▋  | 47795/61904 [2:14:24<5:17:51,  1.35s/it]
 77%|███████▋  | 47796/61904 [2:14:26<5:23:49,  1.38s/it]
 77%|███████▋  | 47797/61904 [2:14:27<5:16:02,  1.34s/it]
 77%|███████▋  | 47798/61904 [2:14:28<5:14:57,  1.34s/it]
 77%|███████▋  | 47799/61904 [2:14:29<5:11:42,  1.33s/it]
 77%|███████▋  | 47800/61904 [2:14:31<5:08:22,  1.31s/it]
                                                         
{'loss': 2.4717, 'learning_rate': 1.228575132892519e-07, 'epoch': 12.35}
+
 77%|███████▋  | 47800/61904 [2:14:31<5:08:22,  1.31s/it]
 77%|███████▋  | 47801/61904 [2:14:32<5:20:37,  1.36s/it]
 77%|███████▋  | 47802/61904 [2:14:33<5:13:00,  1.33s/it]
 77%|███████▋  | 47803/61904 [2:14:35<5:12:59,  1.33s/it]
 77%|███████▋  | 47804/61904 [2:14:36<5:17:22,  1.35s/it]
 77%|███████▋  | 47805/61904 [2:14:38<5:17:05,  1.35s/it]
 77%|███████▋  | 47806/61904 [2:14:39<5:20:16,  1.36s/it]
 77%|███████▋  | 47807/61904 [2:14:40<5:13:18,  1.33s/it]
 77%|███████▋  | 47808/61904 [2:14:41<5:11:35,  1.33s/it]
 77%|███████▋  | 47809/61904 [2:14:43<5:12:44,  1.33s/it]
 77%|███████▋  | 47810/61904 [2:14:44<5:11:52,  1.33s/it]
 77%|███████▋  | 47811/61904 [2:14:46<5:16:35,  1.35s/it]
 77%|███████▋  | 47812/61904 [2:14:47<5:20:18,  1.36s/it]
 77%|███████▋  | 47813/61904 [2:14:48<5:19:46,  1.36s/it]
 77%|███████▋  | 47814/61904 [2:14:50<5:29:11,  1.40s/it]
 77%|███████▋  | 47815/61904 [2:14:51<5:25:42,  1.39s/it]
 77%|███████▋  | 47816/61904 [2:14:53<5:23:42,  1.38s/it]
 77%|███████▋  | 47817/61904 [2:14:54<5:29:20,  1.40s/it]
 77%|███████▋  | 47818/61904 [2:14:55<5:20:49,  1.37s/it]
 77%|███████▋  | 47819/61904 [2:14:57<5:17:01,  1.35s/it]
 77%|███████▋  | 47820/61904 [2:14:58<5:21:10,  1.37s/it]
                                                         
{'loss': 2.4518, 'learning_rate': 1.2282510047970957e-07, 'epoch': 12.36}
+
 77%|███████▋  | 47820/61904 [2:14:58<5:21:10,  1.37s/it]
 77%|███████▋  | 47821/61904 [2:14:59<5:15:28,  1.34s/it]
 77%|███████▋  | 47822/61904 [2:15:01<5:10:07,  1.32s/it]
 77%|███████▋  | 47823/61904 [2:15:02<5:07:21,  1.31s/it]
 77%|███████▋  | 47824/61904 [2:15:03<5:06:53,  1.31s/it]
 77%|███████▋  | 47825/61904 [2:15:04<5:03:54,  1.30s/it]
 77%|███████▋  | 47826/61904 [2:15:06<5:15:16,  1.34s/it]
 77%|███████▋  | 47827/61904 [2:15:07<5:29:45,  1.41s/it]
 77%|███████▋  | 47828/61904 [2:15:09<5:23:53,  1.38s/it]
 77%|███████▋  | 47829/61904 [2:15:10<5:25:36,  1.39s/it]
 77%|███████▋  | 47830/61904 [2:15:12<5:26:51,  1.39s/it]
 77%|███████▋  | 47831/61904 [2:15:13<5:23:04,  1.38s/it]
 77%|███████▋  | 47832/61904 [2:15:14<5:35:52,  1.43s/it]
 77%|███████▋  | 47833/61904 [2:15:16<5:24:41,  1.38s/it]
 77%|███████▋  | 47834/61904 [2:15:17<5:31:47,  1.41s/it]
 77%|███████▋  | 47835/61904 [2:15:18<5:23:58,  1.38s/it]
 77%|███████▋  | 47836/61904 [2:15:20<5:14:12,  1.34s/it]
 77%|███████▋  | 47837/61904 [2:15:21<5:11:47,  1.33s/it]
 77%|███████▋  | 47838/61904 [2:15:22<5:15:16,  1.34s/it]
 77%|███████▋  | 47839/61904 [2:15:24<5:20:20,  1.37s/it]
 77%|███████▋  | 47840/61904 [2:15:25<5:20:02,  1.37s/it]
                                                         
{'loss': 2.4747, 'learning_rate': 1.2279268767016724e-07, 'epoch': 12.36}
+
 77%|███████▋  | 47840/61904 [2:15:25<5:20:02,  1.37s/it]
 77%|███████▋  | 47841/61904 [2:15:27<5:35:52,  1.43s/it]
 77%|███████▋  | 47842/61904 [2:15:28<5:31:10,  1.41s/it]
 77%|███████▋  | 47843/61904 [2:15:30<5:29:15,  1.41s/it]
 77%|███████▋  | 47844/61904 [2:15:31<5:28:34,  1.40s/it]
 77%|███████▋  | 47845/61904 [2:15:32<5:24:18,  1.38s/it]
 77%|███████▋  | 47846/61904 [2:15:34<5:17:42,  1.36s/it]
 77%|███████▋  | 47847/61904 [2:15:35<5:15:09,  1.35s/it]
 77%|███████▋  | 47848/61904 [2:15:36<5:23:23,  1.38s/it]
 77%|███████▋  | 47849/61904 [2:15:38<5:18:07,  1.36s/it]
 77%|███████▋  | 47850/61904 [2:15:39<5:15:15,  1.35s/it]
 77%|███████▋  | 47851/61904 [2:15:40<5:20:42,  1.37s/it]
 77%|███████▋  | 47852/61904 [2:15:42<5:15:49,  1.35s/it]
 77%|███████▋  | 47853/61904 [2:15:43<5:21:50,  1.37s/it]
 77%|███████▋  | 47854/61904 [2:15:45<5:23:45,  1.38s/it]
 77%|███████▋  | 47855/61904 [2:15:46<5:28:45,  1.40s/it]
 77%|███████▋  | 47856/61904 [2:15:47<5:26:40,  1.40s/it]
 77%|███████▋  | 47857/61904 [2:15:49<5:21:41,  1.37s/it]
 77%|███████▋  | 47858/61904 [2:15:50<5:32:56,  1.42s/it]
 77%|███████▋  | 47859/61904 [2:15:52<5:22:45,  1.38s/it]
 77%|███████▋  | 47860/61904 [2:15:53<5:16:35,  1.35s/it]
                                                         
{'loss': 2.4391, 'learning_rate': 1.2276027486062492e-07, 'epoch': 12.37}
+
 77%|███████▋  | 47860/61904 [2:15:53<5:16:35,  1.35s/it]
 77%|███████▋  | 47861/61904 [2:15:54<5:08:41,  1.32s/it]
 77%|███████▋  | 47862/61904 [2:15:55<5:09:51,  1.32s/it]
 77%|███████▋  | 47863/61904 [2:15:57<5:26:30,  1.40s/it]
 77%|███████▋  | 47864/61904 [2:15:58<5:29:52,  1.41s/it]
 77%|███████▋  | 47865/61904 [2:16:00<5:25:41,  1.39s/it]
 77%|███████▋  | 47866/61904 [2:16:01<5:27:30,  1.40s/it]
 77%|███████▋  | 47867/61904 [2:16:03<5:24:37,  1.39s/it]
 77%|███████▋  | 47868/61904 [2:16:04<5:23:58,  1.38s/it]
 77%|███████▋  | 47869/61904 [2:16:05<5:24:09,  1.39s/it]
 77%|███████▋  | 47870/61904 [2:16:07<5:22:11,  1.38s/it]
 77%|███████▋  | 47871/61904 [2:16:08<5:17:31,  1.36s/it]
 77%|███████▋  | 47872/61904 [2:16:09<5:13:15,  1.34s/it]
 77%|███████▋  | 47873/61904 [2:16:11<5:14:19,  1.34s/it]
 77%|███████▋  | 47874/61904 [2:16:12<5:11:48,  1.33s/it]
 77%|███████▋  | 47875/61904 [2:16:13<5:09:24,  1.32s/it]
 77%|███████▋  | 47876/61904 [2:16:15<5:22:11,  1.38s/it]
 77%|███████▋  | 47877/61904 [2:16:16<5:19:52,  1.37s/it]
 77%|███████▋  | 47878/61904 [2:16:17<5:18:28,  1.36s/it]
 77%|██████��▋  | 47879/61904 [2:16:19<5:26:14,  1.40s/it]
 77%|███████▋  | 47880/61904 [2:16:20<5:24:39,  1.39s/it]
                                                         
{'loss': 2.4076, 'learning_rate': 1.2272786205108259e-07, 'epoch': 12.38}
+
 77%|███████▋  | 47880/61904 [2:16:20<5:24:39,  1.39s/it]
 77%|███████▋  | 47881/61904 [2:16:22<5:20:50,  1.37s/it]
 77%|███████▋  | 47882/61904 [2:16:23<5:11:48,  1.33s/it]
 77%|███████▋  | 47883/61904 [2:16:24<5:18:20,  1.36s/it]
 77%|███████▋  | 47884/61904 [2:16:26<5:12:34,  1.34s/it]
 77%|███████▋  | 47885/61904 [2:16:27<5:16:49,  1.36s/it]
 77%|███████▋  | 47886/61904 [2:16:28<5:21:28,  1.38s/it]
 77%|███████▋  | 47887/61904 [2:16:30<5:20:19,  1.37s/it]
 77%|███████▋  | 47888/61904 [2:16:31<5:16:36,  1.36s/it]
 77%|███████▋  | 47889/61904 [2:16:32<5:16:06,  1.35s/it]
 77%|███████▋  | 47890/61904 [2:16:34<5:18:59,  1.37s/it]
 77%|███████▋  | 47891/61904 [2:16:35<5:17:05,  1.36s/it]
 77%|███████▋  | 47892/61904 [2:16:37<5:20:28,  1.37s/it]
 77%|███████▋  | 47893/61904 [2:16:38<5:36:38,  1.44s/it]
 77%|███████▋  | 47894/61904 [2:16:40<5:32:50,  1.43s/it]
 77%|███████▋  | 47895/61904 [2:16:41<5:25:40,  1.39s/it]
 77%|███████▋  | 47896/61904 [2:16:42<5:24:51,  1.39s/it]
 77%|███████▋  | 47897/61904 [2:16:44<5:19:03,  1.37s/it]
 77%|███████▋  | 47898/61904 [2:16:45<5:19:20,  1.37s/it]
 77%|███████▋  | 47899/61904 [2:16:46<5:16:01,  1.35s/it]
 77%|███████▋  | 47900/61904 [2:16:48<5:19:37,  1.37s/it]
                                                         
{'loss': 2.4275, 'learning_rate': 1.2269544924154025e-07, 'epoch': 12.38}
+
 77%|███████▋  | 47900/61904 [2:16:48<5:19:37,  1.37s/it]
 77%|███████▋  | 47901/61904 [2:16:49<5:12:39,  1.34s/it]
 77%|███████▋  | 47902/61904 [2:16:50<5:15:39,  1.35s/it]
 77%|███████▋  | 47903/61904 [2:16:52<5:19:59,  1.37s/it]
 77%|███████▋  | 47904/61904 [2:16:53<5:16:01,  1.35s/it]
 77%|███████▋  | 47905/61904 [2:16:54<5:21:23,  1.38s/it]
 77%|███████▋  | 47906/61904 [2:16:56<5:21:52,  1.38s/it]
 77%|███████▋  | 47907/61904 [2:16:57<5:22:28,  1.38s/it]
 77%|███████▋  | 47908/61904 [2:16:59<5:21:10,  1.38s/it]
 77%|███████▋  | 47909/61904 [2:17:00<5:23:58,  1.39s/it]
 77%|███████▋  | 47910/61904 [2:17:01<5:30:03,  1.42s/it]
 77%|███████▋  | 47911/61904 [2:17:03<5:30:06,  1.42s/it]
 77%|███████▋  | 47912/61904 [2:17:04<5:33:41,  1.43s/it]
 77%|███████▋  | 47913/61904 [2:17:06<5:25:41,  1.40s/it]
 77%|███████▋  | 47914/61904 [2:17:07<5:27:09,  1.40s/it]
 77%|███████▋  | 47915/61904 [2:17:08<5:27:15,  1.40s/it]
 77%|███████▋  | 47916/61904 [2:17:10<5:26:48,  1.40s/it]
 77%|███████▋  | 47917/61904 [2:17:11<5:29:22,  1.41s/it]
 77%|███████▋  | 47918/61904 [2:17:13<5:29:42,  1.41s/it]
 77%|███████▋  | 47919/61904 [2:17:14<5:34:50,  1.44s/it]
 77%|███████▋  | 47920/61904 [2:17:16<5:25:31,  1.40s/it]
                                                         
{'loss': 2.4593, 'learning_rate': 1.2266303643199794e-07, 'epoch': 12.39}
+
 77%|███████▋  | 47920/61904 [2:17:16<5:25:31,  1.40s/it]
 77%|███████▋  | 47921/61904 [2:17:17<5:24:21,  1.39s/it]
 77%|███████▋  | 47922/61904 [2:17:18<5:12:43,  1.34s/it]
 77%|███████▋  | 47923/61904 [2:17:20<5:21:23,  1.38s/it]
 77%|███████▋  | 47924/61904 [2:17:21<5:16:52,  1.36s/it]
 77%|███████▋  | 47925/61904 [2:17:22<5:08:04,  1.32s/it]
 77%|███████▋  | 47926/61904 [2:17:24<5:09:30,  1.33s/it]
 77%|███████▋  | 47927/61904 [2:17:25<5:13:59,  1.35s/it]
 77%|███████▋  | 47928/61904 [2:17:26<5:05:56,  1.31s/it]
 77%|███████▋  | 47929/61904 [2:17:27<5:04:57,  1.31s/it]
 77%|███████▋  | 47930/61904 [2:17:29<5:05:01,  1.31s/it]
 77%|███████▋  | 47931/61904 [2:17:30<5:14:39,  1.35s/it]
 77%|███████▋  | 47932/61904 [2:17:32<5:27:52,  1.41s/it]
 77%|███████▋  | 47933/61904 [2:17:33<5:21:31,  1.38s/it]
 77%|███████▋  | 47934/61904 [2:17:34<5:19:54,  1.37s/it]
 77%|███████▋  | 47935/61904 [2:17:36<5:16:16,  1.36s/it]
 77%|███████▋  | 47936/61904 [2:17:37<5:29:45,  1.42s/it]
 77%|███████▋  | 47937/61904 [2:17:39<5:44:54,  1.48s/it]
 77%|███████▋  | 47938/61904 [2:17:40<5:28:01,  1.41s/it]
 77%|███████▋  | 47939/61904 [2:17:42<5:31:00,  1.42s/it]
 77%|��██████▋  | 47940/61904 [2:17:43<5:28:36,  1.41s/it]
                                                         
{'loss': 2.4666, 'learning_rate': 1.226306236224556e-07, 'epoch': 12.39}
+
 77%|███████▋  | 47940/61904 [2:17:43<5:28:36,  1.41s/it]
 77%|███████▋  | 47941/61904 [2:17:44<5:23:10,  1.39s/it]
 77%|███████▋  | 47942/61904 [2:17:46<5:26:37,  1.40s/it]
 77%|███████▋  | 47943/61904 [2:17:47<5:27:23,  1.41s/it]
 77%|███████▋  | 47944/61904 [2:17:49<5:23:47,  1.39s/it]
 77%|███████▋  | 47945/61904 [2:17:50<5:19:04,  1.37s/it]
 77%|███████▋  | 47946/61904 [2:17:51<5:17:46,  1.37s/it]
 77%|███████▋  | 47947/61904 [2:17:52<5:09:43,  1.33s/it]
 77%|███████▋  | 47948/61904 [2:17:54<5:13:25,  1.35s/it]
 77%|███████▋  | 47949/61904 [2:17:55<5:15:32,  1.36s/it]
 77%|███████▋  | 47950/61904 [2:17:57<5:19:43,  1.37s/it]
 77%|███████▋  | 47951/61904 [2:17:58<5:18:32,  1.37s/it]
 77%|███████▋  | 47952/61904 [2:17:59<5:17:03,  1.36s/it]
 77%|███████▋  | 47953/61904 [2:18:01<5:10:50,  1.34s/it]
 77%|███████▋  | 47954/61904 [2:18:02<5:09:39,  1.33s/it]
 77%|███████▋  | 47955/61904 [2:18:03<5:06:53,  1.32s/it]
 77%|███████▋  | 47956/61904 [2:18:05<5:18:51,  1.37s/it]
 77%|███████▋  | 47957/61904 [2:18:06<5:17:55,  1.37s/it]
 77%|███████▋  | 47958/61904 [2:18:08<5:23:55,  1.39s/it]
 77%|███████▋  | 47959/61904 [2:18:09<5:17:54,  1.37s/it]
 77%|███████▋  | 47960/61904 [2:18:10<5:34:01,  1.44s/it]
                                                         
{'loss': 2.4939, 'learning_rate': 1.2259821081291326e-07, 'epoch': 12.4}
+
 77%|███████▋  | 47960/61904 [2:18:10<5:34:01,  1.44s/it]
 77%|███████▋  | 47961/61904 [2:18:12<5:23:54,  1.39s/it]
 77%|███████▋  | 47962/61904 [2:18:13<5:37:28,  1.45s/it]
 77%|███████▋  | 47963/61904 [2:18:15<5:30:50,  1.42s/it]
 77%|███████▋  | 47964/61904 [2:18:16<5:29:16,  1.42s/it]
 77%|███████▋  | 47965/61904 [2:18:17<5:20:09,  1.38s/it]
 77%|███████▋  | 47966/61904 [2:18:19<5:24:13,  1.40s/it]
 77%|███████▋  | 47967/61904 [2:18:20<5:25:21,  1.40s/it]
 77%|███████▋  | 47968/61904 [2:18:22<5:19:55,  1.38s/it]
 77%|███████▋  | 47969/61904 [2:18:23<5:12:05,  1.34s/it]
 77%|███████▋  | 47970/61904 [2:18:24<5:13:37,  1.35s/it]
 77%|███████▋  | 47971/61904 [2:18:26<5:29:22,  1.42s/it]
 77%|███████▋  | 47972/61904 [2:18:27<5:34:01,  1.44s/it]
 77%|███████▋  | 47973/61904 [2:18:29<5:26:36,  1.41s/it]
 77%|███████▋  | 47974/61904 [2:18:30<5:22:31,  1.39s/it]
 77%|███████▋  | 47975/61904 [2:18:31<5:21:17,  1.38s/it]
 78%|███████▊  | 47976/61904 [2:18:33<5:18:06,  1.37s/it]
 78%|███████▊  | 47977/61904 [2:18:34<5:27:17,  1.41s/it]
 78%|███████▊  | 47978/61904 [2:18:36<5:36:40,  1.45s/it]
 78%|███████▊  | 47979/61904 [2:18:37<5:23:07,  1.39s/it]
 78%|███████▊  | 47980/61904 [2:18:38<5:23:34,  1.39s/it]
                                                         
{'loss': 2.4933, 'learning_rate': 1.2256579800337092e-07, 'epoch': 12.4}
+
 78%|███████▊  | 47980/61904 [2:18:38<5:23:34,  1.39s/it]
 78%|███████▊  | 47981/61904 [2:18:40<5:15:24,  1.36s/it]
 78%|███████▊  | 47982/61904 [2:18:41<5:05:25,  1.32s/it]
 78%|███████▊  | 47983/61904 [2:18:42<5:01:50,  1.30s/it]
 78%|███████▊  | 47984/61904 [2:18:44<5:10:26,  1.34s/it]
 78%|███████▊  | 47985/61904 [2:18:45<5:14:44,  1.36s/it]
 78%|███████▊  | 47986/61904 [2:18:46<5:10:47,  1.34s/it]
 78%|███████▊  | 47987/61904 [2:18:48<5:16:43,  1.37s/it]
 78%|███████▊  | 47988/61904 [2:18:49<5:17:24,  1.37s/it]
 78%|███████▊  | 47989/61904 [2:18:50<5:11:56,  1.35s/it]
 78%|███████▊  | 47990/61904 [2:18:52<5:08:31,  1.33s/it]
 78%|███████▊  | 47991/61904 [2:18:53<5:11:47,  1.34s/it]
 78%|███████▊  | 47992/61904 [2:18:54<5:10:06,  1.34s/it]
 78%|███████▊  | 47993/61904 [2:18:56<5:13:06,  1.35s/it]
 78%|███████▊  | 47994/61904 [2:18:57<5:12:34,  1.35s/it]
 78%|███████▊  | 47995/61904 [2:18:58<5:13:28,  1.35s/it]
 78%|███████▊  | 47996/61904 [2:19:00<5:15:03,  1.36s/it]
 78%|███████▊  | 47997/61904 [2:19:01<5:17:34,  1.37s/it]
 78%|███████▊  | 47998/61904 [2:19:03<5:32:53,  1.44s/it]
 78%|███████▊  | 47999/61904 [2:19:04<5:26:17,  1.41s/it]
 78%|███████▊  | 48000/61904 [2:19:05<5:18:06,  1.37s/it]
                                                         
{'loss': 2.4298, 'learning_rate': 1.2253338519382858e-07, 'epoch': 12.41}
+
 78%|███████▊  | 48000/61904 [2:19:05<5:18:06,  1.37s/it]
 78%|███████▊  | 48001/61904 [2:19:07<5:19:52,  1.38s/it]
 78%|███████▊  | 48002/61904 [2:19:08<5:12:51,  1.35s/it]
 78%|███████▊  | 48003/61904 [2:19:09<5:16:29,  1.37s/it]
 78%|███████▊  | 48004/61904 [2:19:11<5:13:51,  1.35s/it]
 78%|███████▊  | 48005/61904 [2:19:12<5:32:53,  1.44s/it]
 78%|███████▊  | 48006/61904 [2:19:14<5:37:12,  1.46s/it]
 78%|███████▊  | 48007/61904 [2:19:15<5:29:13,  1.42s/it]
 78%|███████▊  | 48008/61904 [2:19:16<5:14:52,  1.36s/it]
 78%|███████▊  | 48009/61904 [2:19:18<5:16:00,  1.36s/it]
 78%|███████▊  | 48010/61904 [2:19:19<5:14:20,  1.36s/it]
 78%|███████▊  | 48011/61904 [2:19:21<5:15:05,  1.36s/it]
 78%|███████▊  | 48012/61904 [2:19:22<5:18:31,  1.38s/it]
 78%|███████▊  | 48013/61904 [2:19:24<5:35:34,  1.45s/it]
 78%|███████▊  | 48014/61904 [2:19:25<5:35:47,  1.45s/it]
 78%|███████▊  | 48015/61904 [2:19:26<5:19:44,  1.38s/it]
 78%|███████▊  | 48016/61904 [2:19:28<5:12:23,  1.35s/it]
 78%|███████▊  | 48017/61904 [2:19:29<5:06:36,  1.32s/it]
 78%|███████▊  | 48018/61904 [2:19:30<5:22:21,  1.39s/it]
 78%|███████▊  | 48019/61904 [2:19:32<5:18:02,  1.37s/it]
 78%|███████▊  | 48020/61904 [2:19:33<5:20:20,  1.38s/it]
                                                         
{'loss': 2.4923, 'learning_rate': 1.2250097238428627e-07, 'epoch': 12.41}
+
 78%|███████▊  | 48020/61904 [2:19:33<5:20:20,  1.38s/it]
 78%|███████▊  | 48021/61904 [2:19:35<5:25:57,  1.41s/it]
 78%|███████▊  | 48022/61904 [2:19:36<5:29:33,  1.42s/it]
 78%|███████▊  | 48023/61904 [2:19:37<5:19:58,  1.38s/it]
 78%|███████▊  | 48024/61904 [2:19:39<5:27:14,  1.41s/it]
 78%|███████▊  | 48025/61904 [2:19:40<5:28:32,  1.42s/it]
 78%|███████▊  | 48026/61904 [2:19:42<5:35:17,  1.45s/it]
 78%|███████▊  | 48027/61904 [2:19:43<5:21:45,  1.39s/it]
 78%|███████▊  | 48028/61904 [2:19:44<5:22:03,  1.39s/it]
 78%|███████▊  | 48029/61904 [2:19:46<5:13:52,  1.36s/it]
 78%|███████▊  | 48030/61904 [2:19:47<5:17:40,  1.37s/it]
 78%|███████▊  | 48031/61904 [2:19:48<5:09:12,  1.34s/it]
 78%|███████▊  | 48032/61904 [2:19:50<5:14:41,  1.36s/it]
 78%|███████▊  | 48033/61904 [2:19:51<5:19:19,  1.38s/it]
 78%|███████▊  | 48034/61904 [2:19:52<5:10:16,  1.34s/it]
 78%|███████▊  | 48035/61904 [2:19:54<5:22:03,  1.39s/it]
 78%|███████▊  | 48036/61904 [2:19:55<5:08:32,  1.33s/it]
 78%|███████▊  | 48037/61904 [2:19:56<5:07:12,  1.33s/it]
 78%|███████▊  | 48038/61904 [2:19:58<5:06:55,  1.33s/it]
 78%|███████▊  | 48039/61904 [2:19:59<5:09:06,  1.34s/it]
 78%|███████▊  | 48040/61904 [2:20:01<5:11:19,  1.35s/it]
                                                         
{'loss': 2.4368, 'learning_rate': 1.2246855957474393e-07, 'epoch': 12.42}
+
 78%|███████▊  | 48040/61904 [2:20:01<5:11:19,  1.35s/it]
 78%|███████▊  | 48041/61904 [2:20:02<5:18:36,  1.38s/it]
 78%|███████▊  | 48042/61904 [2:20:03<5:20:31,  1.39s/it]
 78%|███████▊  | 48043/61904 [2:20:05<5:19:06,  1.38s/it]
 78%|███████▊  | 48044/61904 [2:20:06<5:26:06,  1.41s/it]
 78%|███████▊  | 48045/61904 [2:20:08<5:23:00,  1.40s/it]
 78%|███████▊  | 48046/61904 [2:20:09<5:28:44,  1.42s/it]
 78%|███████▊  | 48047/61904 [2:20:10<5:21:22,  1.39s/it]
 78%|███████▊  | 48048/61904 [2:20:12<5:27:40,  1.42s/it]
 78%|███████▊  | 48049/61904 [2:20:13<5:19:01,  1.38s/it]
 78%|███████▊  | 48050/61904 [2:20:15<5:19:05,  1.38s/it]
 78%|███████▊  | 48051/61904 [2:20:16<5:20:13,  1.39s/it]
 78%|███████▊  | 48052/61904 [2:20:17<5:16:14,  1.37s/it]
 78%|███████▊  | 48053/61904 [2:20:19<5:19:15,  1.38s/it]
 78%|███████▊  | 48054/61904 [2:20:20<5:13:57,  1.36s/it]
 78%|███████▊  | 48055/61904 [2:20:21<5:11:24,  1.35s/it]
 78%|███████▊  | 48056/61904 [2:20:23<5:05:45,  1.32s/it]
 78%|███████▊  | 48057/61904 [2:20:24<5:02:26,  1.31s/it]
 78%|███████▊  | 48058/61904 [2:20:25<5:01:52,  1.31s/it]
 78%|███████▊  | 48059/61904 [2:20:27<5:16:38,  1.37s/it]
 78%|███████▊  | 48060/61904 [2:20:28<5:10:20,  1.35s/it]
                                                         
{'loss': 2.4882, 'learning_rate': 1.224361467652016e-07, 'epoch': 12.42}
+
 78%|███████▊  | 48060/61904 [2:20:28<5:10:20,  1.35s/it]
 78%|███████▊  | 48061/61904 [2:20:29<5:12:39,  1.36s/it]
 78%|███████▊  | 48062/61904 [2:20:31<5:14:36,  1.36s/it]
 78%|███████▊  | 48063/61904 [2:20:32<5:15:30,  1.37s/it]
 78%|███████▊  | 48064/61904 [2:20:34<5:22:43,  1.40s/it]
 78%|███████▊  | 48065/61904 [2:20:35<5:15:41,  1.37s/it]
 78%|███████▊  | 48066/61904 [2:20:36<5:20:24,  1.39s/it]
 78%|███████▊  | 48067/61904 [2:20:38<5:16:56,  1.37s/it]
 78%|███████▊  | 48068/61904 [2:20:39<5:16:45,  1.37s/it]
 78%|███████▊  | 48069/61904 [2:20:40<5:14:07,  1.36s/it]
 78%|███████▊  | 48070/61904 [2:20:42<5:17:21,  1.38s/it]
 78%|███████▊  | 48071/61904 [2:20:43<5:09:22,  1.34s/it]
 78%|███████▊  | 48072/61904 [2:20:44<5:09:51,  1.34s/it]
 78%|███████▊  | 48073/61904 [2:20:46<5:07:46,  1.34s/it]
 78%|███████▊  | 48074/61904 [2:20:47<5:14:01,  1.36s/it]
 78%|███████▊  | 48075/61904 [2:20:48<5:07:25,  1.33s/it]
 78%|███████▊  | 48076/61904 [2:20:50<5:07:25,  1.33s/it]
 78%|███████▊  | 48077/61904 [2:20:51<5:19:52,  1.39s/it]
 78%|███████▊  | 48078/61904 [2:20:53<5:15:37,  1.37s/it]
 78%|███████▊  | 48079/61904 [2:20:54<5:11:22,  1.35s/it]
 78%|███████▊  | 48080/61904 [2:20:55<5:19:48,  1.39s/it]
                                                         
{'loss': 2.4417, 'learning_rate': 1.2240373395565928e-07, 'epoch': 12.43}
+
 78%|███████▊  | 48080/61904 [2:20:55<5:19:48,  1.39s/it]
 78%|███████▊  | 48081/61904 [2:20:57<5:08:26,  1.34s/it]
 78%|███████▊  | 48082/61904 [2:20:58<5:17:32,  1.38s/it]
 78%|███████▊  | 48083/61904 [2:21:00<5:27:22,  1.42s/it]
 78%|███████▊  | 48084/61904 [2:21:01<5:33:11,  1.45s/it]
 78%|███████▊  | 48085/61904 [2:21:03<5:41:17,  1.48s/it]
 78%|███████▊  | 48086/61904 [2:21:04<5:38:05,  1.47s/it]
 78%|███████▊  | 48087/61904 [2:21:05<5:23:04,  1.40s/it]
 78%|███████▊  | 48088/61904 [2:21:07<5:31:20,  1.44s/it]
 78%|███████▊  | 48089/61904 [2:21:08<5:23:55,  1.41s/it]
 78%|███████▊  | 48090/61904 [2:21:10<5:19:27,  1.39s/it]
 78%|███████▊  | 48091/61904 [2:21:11<5:22:52,  1.40s/it]
 78%|███████▊  | 48092/61904 [2:21:12<5:29:42,  1.43s/it]
 78%|███████▊  | 48093/61904 [2:21:14<5:27:40,  1.42s/it]
 78%|███████▊  | 48094/61904 [2:21:15<5:19:18,  1.39s/it]
 78%|███████▊  | 48095/61904 [2:21:16<5:13:06,  1.36s/it]
 78%|███████▊  | 48096/61904 [2:21:18<5:11:43,  1.35s/it]
 78%|███████▊  | 48097/61904 [2:21:19<5:08:14,  1.34s/it]
 78%|███████▊  | 48098/61904 [2:21:20<5:06:06,  1.33s/it]
 78%|███████▊  | 48099/61904 [2:21:22<5:15:23,  1.37s/it]
 78%|███████▊  | 48100/61904 [2:21:23<5:20:00,  1.39s/it]
                                                         
{'loss': 2.4881, 'learning_rate': 1.2237132114611695e-07, 'epoch': 12.43}
+
 78%|███████▊  | 48100/61904 [2:21:23<5:20:00,  1.39s/it]
 78%|███████▊  | 48101/61904 [2:21:25<5:20:59,  1.40s/it]
 78%|███████▊  | 48102/61904 [2:21:26<5:14:30,  1.37s/it]
 78%|███████▊  | 48103/61904 [2:21:27<5:15:54,  1.37s/it]
 78%|███████▊  | 48104/61904 [2:21:29<5:15:18,  1.37s/it]
 78%|███████▊  | 48105/61904 [2:21:30<5:19:38,  1.39s/it]
 78%|███████▊  | 48106/61904 [2:21:31<5:08:10,  1.34s/it]
 78%|███████▊  | 48107/61904 [2:21:33<5:14:52,  1.37s/it]
 78%|███████▊  | 48108/61904 [2:21:34<5:16:19,  1.38s/it]
 78%|███████▊  | 48109/61904 [2:21:36<5:25:57,  1.42s/it]
 78%|███████▊  | 48110/61904 [2:21:37<5:25:15,  1.41s/it]
 78%|███████▊  | 48111/61904 [2:21:39<5:18:44,  1.39s/it]
 78%|███████▊  | 48112/61904 [2:21:40<5:15:55,  1.37s/it]
 78%|███████▊  | 48113/61904 [2:21:41<5:24:22,  1.41s/it]
 78%|███████▊  | 48114/61904 [2:21:43<5:27:54,  1.43s/it]
 78%|███████▊  | 48115/61904 [2:21:44<5:29:23,  1.43s/it]
 78%|███████▊  | 48116/61904 [2:21:46<5:22:13,  1.40s/it]
 78%|███████▊  | 48117/61904 [2:21:47<5:15:41,  1.37s/it]
 78%|███████▊  | 48118/61904 [2:21:48<5:12:36,  1.36s/it]
 78%|███████▊  | 48119/61904 [2:21:50<5:21:51,  1.40s/it]
 78%|███████▊  | 48120/61904 [2:21:51<5:16:33,  1.38s/it]
                                                         
{'loss': 2.4633, 'learning_rate': 1.223389083365746e-07, 'epoch': 12.44}
+
 78%|███████▊  | 48120/61904 [2:21:51<5:16:33,  1.38s/it]
 78%|███████▊  | 48121/61904 [2:21:53<5:23:47,  1.41s/it]
 78%|███████▊  | 48122/61904 [2:21:54<5:20:58,  1.40s/it]
 78%|███████▊  | 48123/61904 [2:21:55<5:23:36,  1.41s/it]
 78%|███████▊  | 48124/61904 [2:21:57<5:18:03,  1.38s/it]
 78%|███████▊  | 48125/61904 [2:21:58<5:09:11,  1.35s/it]
 78%|███████▊  | 48126/61904 [2:21:59<5:13:52,  1.37s/it]
 78%|███████▊  | 48127/61904 [2:22:01<5:13:06,  1.36s/it]
 78%|███████▊  | 48128/61904 [2:22:02<5:19:13,  1.39s/it]
 78%|███████▊  | 48129/61904 [2:22:04<5:32:43,  1.45s/it]
 78%|███████▊  | 48130/61904 [2:22:05<5:39:39,  1.48s/it]
 78%|███████▊  | 48131/61904 [2:22:07<5:28:00,  1.43s/it]
 78%|███████▊  | 48132/61904 [2:22:08<5:29:56,  1.44s/it]
 78%|███████▊  | 48133/61904 [2:22:09<5:26:08,  1.42s/it]
 78%|███████▊  | 48134/61904 [2:22:11<5:32:36,  1.45s/it]
 78%|███████▊  | 48135/61904 [2:22:12<5:31:39,  1.45s/it]
 78%|███████▊  | 48136/61904 [2:22:14<5:39:50,  1.48s/it]
 78%|███████▊  | 48137/61904 [2:22:15<5:34:04,  1.46s/it]
 78%|███████▊  | 48138/61904 [2:22:17<5:23:20,  1.41s/it]
 78%|███████▊  | 48139/61904 [2:22:18<5:12:27,  1.36s/it]
 78%|███████▊  | 48140/61904 [2:22:19<5:03:27,  1.32s/it]
                                                         
{'loss': 2.4914, 'learning_rate': 1.223064955270323e-07, 'epoch': 12.44}
+
 78%|███████▊  | 48140/61904 [2:22:19<5:03:27,  1.32s/it]
 78%|███████▊  | 48141/61904 [2:22:21<5:22:19,  1.41s/it]
 78%|███████▊  | 48142/61904 [2:22:22<5:10:02,  1.35s/it]
 78%|███████▊  | 48143/61904 [2:22:23<4:58:54,  1.30s/it]
 78%|███████▊  | 48144/61904 [2:22:25<5:01:18,  1.31s/it]
 78%|███████▊  | 48145/61904 [2:22:26<5:00:24,  1.31s/it]
 78%|███████▊  | 48146/61904 [2:22:27<5:03:34,  1.32s/it]
 78%|███████▊  | 48147/61904 [2:22:29<5:06:10,  1.34s/it]
 78%|███████▊  | 48148/61904 [2:22:30<5:04:07,  1.33s/it]
 78%|███████▊  | 48149/61904 [2:22:31<5:04:44,  1.33s/it]
 78%|███████▊  | 48150/61904 [2:22:33<5:07:51,  1.34s/it]
 78%|███████▊  | 48151/61904 [2:22:34<5:05:47,  1.33s/it]
 78%|███████▊  | 48152/61904 [2:22:35<5:05:01,  1.33s/it]
 78%|███████▊  | 48153/61904 [2:22:37<5:05:36,  1.33s/it]
 78%|███████▊  | 48154/61904 [2:22:38<5:08:10,  1.34s/it]
 78%|███████▊  | 48155/61904 [2:22:39<5:16:12,  1.38s/it]
 78%|███████▊  | 48156/61904 [2:22:41<5:18:12,  1.39s/it]
 78%|███████▊  | 48157/61904 [2:22:42<5:13:22,  1.37s/it]
 78%|███████▊  | 48158/61904 [2:22:43<5:12:25,  1.36s/it]
 78%|███████▊  | 48159/61904 [2:22:45<5:03:54,  1.33s/it]
 78%|███████▊  | 48160/61904 [2:22:46<5:05:50,  1.34s/it]
                                                         
{'loss': 2.4236, 'learning_rate': 1.2227408271748993e-07, 'epoch': 12.45}
+
 78%|███████▊  | 48160/61904 [2:22:46<5:05:50,  1.34s/it]
 78%|███████▊  | 48161/61904 [2:22:47<5:10:10,  1.35s/it]
 78%|███████▊  | 48162/61904 [2:22:49<5:13:56,  1.37s/it]
 78%|███████▊  | 48163/61904 [2:22:50<5:24:19,  1.42s/it]
 78%|███████▊  | 48164/61904 [2:22:52<5:20:25,  1.40s/it]
 78%|███████▊  | 48165/61904 [2:22:53<5:13:46,  1.37s/it]
 78%|███████▊  | 48166/61904 [2:22:54<5:06:50,  1.34s/it]
 78%|███████▊  | 48167/61904 [2:22:55<4:56:29,  1.29s/it]
 78%|███████▊  | 48168/61904 [2:22:57<4:56:57,  1.30s/it]
 78%|███████▊  | 48169/61904 [2:22:58<5:03:34,  1.33s/it]
 78%|███████▊  | 48170/61904 [2:23:00<5:03:37,  1.33s/it]
 78%|███████▊  | 48171/61904 [2:23:01<5:05:01,  1.33s/it]
 78%|███████▊  | 48172/61904 [2:23:02<5:11:54,  1.36s/it]
 78%|███████▊  | 48173/61904 [2:23:04<5:10:55,  1.36s/it]
 78%|███████▊  | 48174/61904 [2:23:05<5:25:40,  1.42s/it]
 78%|███████▊  | 48175/61904 [2:23:07<5:25:08,  1.42s/it]
 78%|███████▊  | 48176/61904 [2:23:08<5:21:22,  1.40s/it]
 78%|███████▊  | 48177/61904 [2:23:09<5:17:32,  1.39s/it]
 78%|███████▊  | 48178/61904 [2:23:11<5:18:45,  1.39s/it]
 78%|███████▊  | 48179/61904 [2:23:12<5:10:43,  1.36s/it]
 78%|███████▊  | 48180/61904 [2:23:13<5:14:56,  1.38s/it]
                                                         
{'loss': 2.4603, 'learning_rate': 1.2224166990794762e-07, 'epoch': 12.45}
+
 78%|███████▊  | 48180/61904 [2:23:13<5:14:56,  1.38s/it]
 78%|███████▊  | 48181/61904 [2:23:15<5:09:05,  1.35s/it]
 78%|███████▊  | 48182/61904 [2:23:16<5:06:37,  1.34s/it]
 78%|███████▊  | 48183/61904 [2:23:17<5:12:28,  1.37s/it]
 78%|███████▊  | 48184/61904 [2:23:19<5:11:02,  1.36s/it]
 78%|███████▊  | 48185/61904 [2:23:20<5:03:24,  1.33s/it]
 78%|███████▊  | 48186/61904 [2:23:21<5:03:44,  1.33s/it]
 78%|███████▊  | 48187/61904 [2:23:23<5:07:02,  1.34s/it]
 78%|███████▊  | 48188/61904 [2:23:24<5:11:00,  1.36s/it]
 78%|███████▊  | 48189/61904 [2:23:26<5:09:11,  1.35s/it]
 78%|███████▊  | 48190/61904 [2:23:27<5:20:35,  1.40s/it]
 78%|███████▊  | 48191/61904 [2:23:28<5:14:11,  1.37s/it]
 78%|███████▊  | 48192/61904 [2:23:30<5:07:30,  1.35s/it]
 78%|███████▊  | 48193/61904 [2:23:31<5:04:51,  1.33s/it]
 78%|███████▊  | 48194/61904 [2:23:32<5:11:01,  1.36s/it]
 78%|███████▊  | 48195/61904 [2:23:34<5:13:39,  1.37s/it]
 78%|███████▊  | 48196/61904 [2:23:35<5:17:14,  1.39s/it]
 78%|███████▊  | 48197/61904 [2:23:37<5:21:42,  1.41s/it]
 78%|███████▊  | 48198/61904 [2:23:38<5:12:07,  1.37s/it]
 78%|███████▊  | 48199/61904 [2:23:39<5:14:26,  1.38s/it]
 78%|███████▊  | 48200/61904 [2:23:41<5:16:37,  1.39s/it]
                                                         
{'loss': 2.5019, 'learning_rate': 1.2220925709840528e-07, 'epoch': 12.46}
+
 78%|███████▊  | 48200/61904 [2:23:41<5:16:37,  1.39s/it]
 78%|███████▊  | 48201/61904 [2:23:42<5:23:39,  1.42s/it]
 78%|███████▊  | 48202/61904 [2:23:44<5:16:49,  1.39s/it]
 78%|███████▊  | 48203/61904 [2:23:45<5:16:49,  1.39s/it]
 78%|███████▊  | 48204/61904 [2:23:46<5:09:06,  1.35s/it]
 78%|███████▊  | 48205/61904 [2:23:48<5:18:01,  1.39s/it]
 78%|███████▊  | 48206/61904 [2:23:49<5:15:43,  1.38s/it]
 78%|███████▊  | 48207/61904 [2:23:50<5:21:26,  1.41s/it]
 78%|███████▊  | 48208/61904 [2:23:52<5:19:44,  1.40s/it]
 78%|███████▊  | 48209/61904 [2:23:53<5:29:18,  1.44s/it]
 78%|███████▊  | 48210/61904 [2:23:55<5:22:31,  1.41s/it]
 78%|███████▊  | 48211/61904 [2:23:56<5:12:48,  1.37s/it]
 78%|███████▊  | 48212/61904 [2:23:57<5:17:52,  1.39s/it]
 78%|███████▊  | 48213/61904 [2:23:59<5:19:59,  1.40s/it]
 78%|███████▊  | 48214/61904 [2:24:00<5:13:02,  1.37s/it]
 78%|███████▊  | 48215/61904 [2:24:01<5:04:54,  1.34s/it]
 78%|███████▊  | 48216/61904 [2:24:03<5:01:03,  1.32s/it]
 78%|███████▊  | 48217/61904 [2:24:04<5:04:02,  1.33s/it]
 78%|███████▊  | 48218/61904 [2:24:05<5:03:20,  1.33s/it]
 78%|███████▊  | 48219/61904 [2:24:07<5:15:18,  1.38s/it]
 78%|███████▊  | 48220/61904 [2:24:08<5:19:03,  1.40s/it]
                                                         
{'loss': 2.4368, 'learning_rate': 1.2217684428886294e-07, 'epoch': 12.46}
+
 78%|███████▊  | 48220/61904 [2:24:08<5:19:03,  1.40s/it]
 78%|███████▊  | 48221/61904 [2:24:10<5:11:04,  1.36s/it]
 78%|███████▊  | 48222/61904 [2:24:11<5:16:14,  1.39s/it]
 78%|███████▊  | 48223/61904 [2:24:12<5:15:03,  1.38s/it]
 78%|███████▊  | 48224/61904 [2:24:14<5:20:49,  1.41s/it]
 78%|███████▊  | 48225/61904 [2:24:15<5:19:05,  1.40s/it]
 78%|███████▊  | 48226/61904 [2:24:17<5:20:51,  1.41s/it]
 78%|███████▊  | 48227/61904 [2:24:18<5:19:42,  1.40s/it]
 78%|███████▊  | 48228/61904 [2:24:20<5:22:26,  1.41s/it]
 78%|███████▊  | 48229/61904 [2:24:21<5:13:43,  1.38s/it]
 78%|███████▊  | 48230/61904 [2:24:22<5:12:28,  1.37s/it]
 78%|███████▊  | 48231/61904 [2:24:24<5:15:21,  1.38s/it]
 78%|███████▊  | 48232/61904 [2:24:25<5:11:30,  1.37s/it]
 78%|███████▊  | 48233/61904 [2:24:26<5:14:35,  1.38s/it]
 78%|███████▊  | 48234/61904 [2:24:28<5:19:14,  1.40s/it]
 78%|███████▊  | 48235/61904 [2:24:29<5:19:08,  1.40s/it]
 78%|███████▊  | 48236/61904 [2:24:31<5:22:09,  1.41s/it]
 78%|███████▊  | 48237/61904 [2:24:32<5:20:19,  1.41s/it]
 78%|███████▊  | 48238/61904 [2:24:33<5:15:28,  1.39s/it]
 78%|███████▊  | 48239/61904 [2:24:35<5:13:59,  1.38s/it]
 78%|███████▊  | 48240/61904 [2:24:36<5:14:00,  1.38s/it]
                                                         
{'loss': 2.5019, 'learning_rate': 1.2214443147932063e-07, 'epoch': 12.47}
+
 78%|███████▊  | 48240/61904 [2:24:36<5:14:00,  1.38s/it]
 78%|███████▊  | 48241/61904 [2:24:37<5:12:34,  1.37s/it]
 78%|███████▊  | 48242/61904 [2:24:39<5:15:19,  1.38s/it]
 78%|███████▊  | 48243/61904 [2:24:40<5:06:05,  1.34s/it]
 78%|███████▊  | 48244/61904 [2:24:41<5:06:12,  1.34s/it]
 78%|███████▊  | 48245/61904 [2:24:43<5:07:40,  1.35s/it]
 78%|███████▊  | 48246/61904 [2:24:44<5:15:28,  1.39s/it]
 78%|███████▊  | 48247/61904 [2:24:46<5:18:13,  1.40s/it]
 78%|███████▊  | 48248/61904 [2:24:47<5:10:06,  1.36s/it]
 78%|███████▊  | 48249/61904 [2:24:49<5:28:30,  1.44s/it]
 78%|███████▊  | 48250/61904 [2:24:50<5:21:43,  1.41s/it]
 78%|███████▊  | 48251/61904 [2:24:52<5:27:17,  1.44s/it]
 78%|███████▊  | 48252/61904 [2:24:53<5:17:44,  1.40s/it]
 78%|███████▊  | 48253/61904 [2:24:54<5:22:20,  1.42s/it]
 78%|███████▊  | 48254/61904 [2:24:56<5:16:18,  1.39s/it]
 78%|███████▊  | 48255/61904 [2:24:57<5:12:59,  1.38s/it]
 78%|███████▊  | 48256/61904 [2:24:58<5:05:34,  1.34s/it]
 78%|███████▊  | 48257/61904 [2:25:00<5:18:23,  1.40s/it]
 78%|███████▊  | 48258/61904 [2:25:01<5:12:51,  1.38s/it]
 78%|███████▊  | 48259/61904 [2:25:02<5:11:13,  1.37s/it]
 78%|███████▊  | 48260/61904 [2:25:04<5:11:11,  1.37s/it]
                                                         
{'loss': 2.4857, 'learning_rate': 1.221120186697783e-07, 'epoch': 12.47}
+
 78%|███████▊  | 48260/61904 [2:25:04<5:11:11,  1.37s/it]
 78%|███████▊  | 48261/61904 [2:25:05<5:13:25,  1.38s/it]
 78%|███████▊  | 48262/61904 [2:25:07<5:12:04,  1.37s/it]
 78%|███████▊  | 48263/61904 [2:25:08<5:06:01,  1.35s/it]
 78%|███████▊  | 48264/61904 [2:25:09<5:00:58,  1.32s/it]
 78%|███████▊  | 48265/61904 [2:25:10<5:03:46,  1.34s/it]
 78%|███████▊  | 48266/61904 [2:25:12<5:02:03,  1.33s/it]
 78%|███████▊  | 48267/61904 [2:25:13<5:05:01,  1.34s/it]
 78%|███████▊  | 48268/61904 [2:25:14<4:58:32,  1.31s/it]
 78%|███████▊  | 48269/61904 [2:25:16<4:53:44,  1.29s/it]
 78%|███████▊  | 48270/61904 [2:25:17<5:01:40,  1.33s/it]
 78%|███████▊  | 48271/61904 [2:25:18<5:04:40,  1.34s/it]
 78%|███████▊  | 48272/61904 [2:25:20<5:17:30,  1.40s/it]
 78%|███████▊  | 48273/61904 [2:25:21<5:19:52,  1.41s/it]
 78%|███████▊  | 48274/61904 [2:25:23<5:26:58,  1.44s/it]
 78%|███████▊  | 48275/61904 [2:25:24<5:28:17,  1.45s/it]
 78%|███████▊  | 48276/61904 [2:25:26<5:22:27,  1.42s/it]
 78%|███████▊  | 48277/61904 [2:25:27<5:18:49,  1.40s/it]
 78%|███████▊  | 48278/61904 [2:25:28<5:12:50,  1.38s/it]
 78%|███████▊  | 48279/61904 [2:25:30<5:05:51,  1.35s/it]
 78%|███████▊  | 48280/61904 [2:25:31<5:05:56,  1.35s/it]
                                                         
{'loss': 2.4496, 'learning_rate': 1.2207960586023596e-07, 'epoch': 12.48}
+
 78%|███████▊  | 48280/61904 [2:25:31<5:05:56,  1.35s/it]
 78%|███████▊  | 48281/61904 [2:25:32<4:58:06,  1.31s/it]
 78%|███████▊  | 48282/61904 [2:25:34<5:01:33,  1.33s/it]
 78%|███████▊  | 48283/61904 [2:25:35<4:58:58,  1.32s/it]
 78%|███████▊  | 48284/61904 [2:25:36<4:59:22,  1.32s/it]
 78%|███████▊  | 48285/61904 [2:25:38<5:24:15,  1.43s/it]
 78%|███████▊  | 48286/61904 [2:25:39<5:17:31,  1.40s/it]
 78%|███████▊  | 48287/61904 [2:25:41<5:18:50,  1.40s/it]
 78%|███████▊  | 48288/61904 [2:25:42<5:05:46,  1.35s/it]
 78%|███████▊  | 48289/61904 [2:25:43<5:00:20,  1.32s/it]
 78%|███████▊  | 48290/61904 [2:25:44<4:57:23,  1.31s/it]
 78%|███████▊  | 48291/61904 [2:25:46<4:56:23,  1.31s/it]
 78%|███████▊  | 48292/61904 [2:25:47<5:01:41,  1.33s/it]
 78%|███████▊  | 48293/61904 [2:25:49<5:16:11,  1.39s/it]
 78%|███████▊  | 48294/61904 [2:25:50<5:14:55,  1.39s/it]
 78%|███████▊  | 48295/61904 [2:25:52<5:21:18,  1.42s/it]
 78%|███████▊  | 48296/61904 [2:25:53<5:22:17,  1.42s/it]
 78%|███████▊  | 48297/61904 [2:25:54<5:22:08,  1.42s/it]
 78%|███████▊  | 48298/61904 [2:25:56<5:16:15,  1.39s/it]
 78%|███████▊  | 48299/61904 [2:25:57<5:14:48,  1.39s/it]
 78%|███████▊  | 48300/61904 [2:25:59<5:29:38,  1.45s/it]
                                                         
{'loss': 2.5045, 'learning_rate': 1.2204719305069364e-07, 'epoch': 12.48}
+
 78%|███████▊  | 48300/61904 [2:25:59<5:29:38,  1.45s/it]
 78%|███████▊  | 48301/61904 [2:26:00<5:32:29,  1.47s/it]
 78%|███████▊  | 48302/61904 [2:26:02<5:25:08,  1.43s/it]
 78%|███████▊  | 48303/61904 [2:26:03<5:20:48,  1.42s/it]
 78%|███████▊  | 48304/61904 [2:26:04<5:28:43,  1.45s/it]
 78%|███████▊  | 48305/61904 [2:26:06<5:31:14,  1.46s/it]
 78%|███████▊  | 48306/61904 [2:26:07<5:32:17,  1.47s/it]
 78%|███████▊  | 48307/61904 [2:26:09<5:28:01,  1.45s/it]
 78%|███████▊  | 48308/61904 [2:26:10<5:25:56,  1.44s/it]
 78%|███████▊  | 48309/61904 [2:26:12<5:26:31,  1.44s/it]
 78%|███████▊  | 48310/61904 [2:26:13<5:24:44,  1.43s/it]
 78%|███████▊  | 48311/61904 [2:26:14<5:23:40,  1.43s/it]
 78%|███████▊  | 48312/61904 [2:26:16<5:15:39,  1.39s/it]
 78%|███████▊  | 48313/61904 [2:26:17<5:19:54,  1.41s/it]
 78%|███████▊  | 48314/61904 [2:26:19<5:18:26,  1.41s/it]
 78%|███████▊  | 48315/61904 [2:26:20<5:08:21,  1.36s/it]
 78%|███████▊  | 48316/61904 [2:26:21<5:07:02,  1.36s/it]
 78%|███████▊  | 48317/61904 [2:26:23<5:14:38,  1.39s/it]
 78%|███████▊  | 48318/61904 [2:26:24<5:08:36,  1.36s/it]
 78%|███████▊  | 48319/61904 [2:26:25<5:09:51,  1.37s/it]
 78%|███████▊  | 48320/61904 [2:26:27<5:05:37,  1.35s/it]
                                                         
{'loss': 2.4589, 'learning_rate': 1.2201478024115128e-07, 'epoch': 12.49}
+
 78%|███████▊  | 48320/61904 [2:26:27<5:05:37,  1.35s/it]
 78%|███████▊  | 48321/61904 [2:26:28<4:59:26,  1.32s/it]
 78%|███████▊  | 48322/61904 [2:26:29<4:58:49,  1.32s/it]
 78%|███████▊  | 48323/61904 [2:26:31<4:58:34,  1.32s/it]
 78%|███████▊  | 48324/61904 [2:26:32<5:09:23,  1.37s/it]
 78%|███████▊  | 48325/61904 [2:26:34<5:14:56,  1.39s/it]
 78%|███████▊  | 48326/61904 [2:26:35<5:08:10,  1.36s/it]
 78%|███████▊  | 48327/61904 [2:26:36<5:18:55,  1.41s/it]
 78%|███████▊  | 48328/61904 [2:26:38<5:13:37,  1.39s/it]
 78%|███████▊  | 48329/61904 [2:26:39<5:26:19,  1.44s/it]
 78%|███████▊  | 48330/61904 [2:26:41<5:38:36,  1.50s/it]
 78%|███████▊  | 48331/61904 [2:26:42<5:30:52,  1.46s/it]
 78%|███████▊  | 48332/61904 [2:26:44<5:21:03,  1.42s/it]
 78%|███████▊  | 48333/61904 [2:26:45<5:26:10,  1.44s/it]
 78%|███████▊  | 48334/61904 [2:26:46<5:15:27,  1.39s/it]
 78%|███████▊  | 48335/61904 [2:26:48<5:08:01,  1.36s/it]
 78%|███████▊  | 48336/61904 [2:26:49<5:07:36,  1.36s/it]
 78%|███████▊  | 48337/61904 [2:26:50<5:08:19,  1.36s/it]
 78%|███████▊  | 48338/61904 [2:26:52<5:03:50,  1.34s/it]
 78%|███████▊  | 48339/61904 [2:26:53<5:10:54,  1.38s/it]
 78%|███████▊  | 48340/61904 [2:26:54<5:10:40,  1.37s/it]
                                                         
{'loss': 2.4778, 'learning_rate': 1.2198236743160897e-07, 'epoch': 12.49}
+
 78%|███████▊  | 48340/61904 [2:26:54<5:10:40,  1.37s/it]
 78%|███████▊  | 48341/61904 [2:26:56<5:11:32,  1.38s/it]
 78%|███████▊  | 48342/61904 [2:26:57<5:09:10,  1.37s/it]
 78%|███████▊  | 48343/61904 [2:26:59<5:07:28,  1.36s/it]
 78%|███████▊  | 48344/61904 [2:27:00<5:02:58,  1.34s/it]
 78%|███████▊  | 48345/61904 [2:27:01<5:07:11,  1.36s/it]
 78%|███████▊  | 48346/61904 [2:27:03<5:13:53,  1.39s/it]
 78%|███████▊  | 48347/61904 [2:27:04<5:01:38,  1.33s/it]
 78%|███████▊  | 48348/61904 [2:27:05<5:09:55,  1.37s/it]
 78%|███████▊  | 48349/61904 [2:27:07<5:08:55,  1.37s/it]
 78%|███████▊  | 48350/61904 [2:27:08<5:27:11,  1.45s/it]
 78%|███████▊  | 48351/61904 [2:27:10<5:18:26,  1.41s/it]
 78%|███████▊  | 48352/61904 [2:27:11<5:14:40,  1.39s/it]
 78%|███████▊  | 48353/61904 [2:27:12<5:11:50,  1.38s/it]
 78%|███████▊  | 48354/61904 [2:27:14<5:15:16,  1.40s/it]
 78%|███████▊  | 48355/61904 [2:27:15<5:12:50,  1.39s/it]
 78%|███████▊  | 48356/61904 [2:27:16<5:06:34,  1.36s/it]
 78%|███████▊  | 48357/61904 [2:27:18<5:04:34,  1.35s/it]
 78%|███████▊  | 48358/61904 [2:27:19<5:11:17,  1.38s/it]
 78%|███████▊  | 48359/61904 [2:27:21<5:15:31,  1.40s/it]
 78%|███████▊  | 48360/61904 [2:27:22<5:13:45,  1.39s/it]
                                                         
{'loss': 2.4297, 'learning_rate': 1.2194995462206663e-07, 'epoch': 12.5}
+
 78%|███████▊  | 48360/61904 [2:27:22<5:13:45,  1.39s/it]
 78%|███████▊  | 48361/61904 [2:27:23<5:06:21,  1.36s/it]
 78%|███████▊  | 48362/61904 [2:27:25<5:10:25,  1.38s/it]
 78%|███████▊  | 48363/61904 [2:27:26<5:02:23,  1.34s/it]
 78%|███████▊  | 48364/61904 [2:27:27<4:59:16,  1.33s/it]
 78%|███████▊  | 48365/61904 [2:27:29<5:10:33,  1.38s/it]
 78%|███████▊  | 48366/61904 [2:27:30<5:15:58,  1.40s/it]
 78%|███████▊  | 48367/61904 [2:27:32<5:11:31,  1.38s/it]
 78%|███████▊  | 48368/61904 [2:27:33<5:09:53,  1.37s/it]
 78%|███████▊  | 48369/61904 [2:27:34<5:15:35,  1.40s/it]
 78%|███████▊  | 48370/61904 [2:27:36<5:08:52,  1.37s/it]
 78%|███████▊  | 48371/61904 [2:27:37<5:16:38,  1.40s/it]
 78%|███████▊  | 48372/61904 [2:27:39<5:10:01,  1.37s/it]
 78%|███████▊  | 48373/61904 [2:27:40<5:03:11,  1.34s/it]
 78%|███████▊  | 48374/61904 [2:27:41<5:08:40,  1.37s/it]
 78%|███████▊  | 48375/61904 [2:27:43<5:03:32,  1.35s/it]
 78%|███████▊  | 48376/61904 [2:27:44<5:11:22,  1.38s/it]
 78%|███████▊  | 48377/61904 [2:27:45<5:07:53,  1.37s/it]
 78%|███████▊  | 48378/61904 [2:27:47<4:58:42,  1.33s/it]
 78%|███████▊  | 48379/61904 [2:27:48<4:55:06,  1.31s/it]
 78%|███████▊  | 48380/61904 [2:27:49<5:06:57,  1.36s/it]
                                                         
{'loss': 2.395, 'learning_rate': 1.219175418125243e-07, 'epoch': 12.5}
+
 78%|███████▊  | 48380/61904 [2:27:49<5:06:57,  1.36s/it]
 78%|███████▊  | 48381/61904 [2:27:51<5:03:01,  1.34s/it]
 78%|███████▊  | 48382/61904 [2:27:52<5:02:28,  1.34s/it]
 78%|███████▊  | 48383/61904 [2:27:53<5:08:02,  1.37s/it]
 78%|███████▊  | 48384/61904 [2:27:55<5:14:33,  1.40s/it]
 78%|███████▊  | 48385/61904 [2:27:56<5:17:06,  1.41s/it]
 78%|███████▊  | 48386/61904 [2:27:58<5:13:22,  1.39s/it]
 78%|███████▊  | 48387/61904 [2:27:59<5:04:44,  1.35s/it]
 78%|███████▊  | 48388/61904 [2:28:00<5:06:43,  1.36s/it]
 78%|███████▊  | 48389/61904 [2:28:02<5:07:54,  1.37s/it]
 78%|███████▊  | 48390/61904 [2:28:03<5:10:49,  1.38s/it]
 78%|███████▊  | 48391/61904 [2:28:04<5:07:51,  1.37s/it]
 78%|███████▊  | 48392/61904 [2:28:06<5:08:52,  1.37s/it]
 78%|███████▊  | 48393/61904 [2:28:07<5:05:21,  1.36s/it]
 78%|███████▊  | 48394/61904 [2:28:09<5:12:03,  1.39s/it]
 78%|███████▊  | 48395/61904 [2:28:10<5:07:29,  1.37s/it]
 78%|███████▊  | 48396/61904 [2:28:11<5:14:27,  1.40s/it]
 78%|███████▊  | 48397/61904 [2:28:13<5:21:09,  1.43s/it]
 78%|███████▊  | 48398/61904 [2:28:14<5:18:54,  1.42s/it]
 78%|███████▊  | 48399/61904 [2:28:16<5:15:40,  1.40s/it]
 78%|███████▊  | 48400/61904 [2:28:17<5:13:55,  1.39s/it]
                                                         
{'loss': 2.4515, 'learning_rate': 1.2188512900298198e-07, 'epoch': 12.51}
+
 78%|███████▊  | 48400/61904 [2:28:17<5:13:55,  1.39s/it]
 78%|███████▊  | 48401/61904 [2:28:18<5:10:38,  1.38s/it]
 78%|███████▊  | 48402/61904 [2:28:20<5:12:10,  1.39s/it]
 78%|███████▊  | 48403/61904 [2:28:21<5:05:20,  1.36s/it]
 78%|███████▊  | 48404/61904 [2:28:22<5:06:18,  1.36s/it]
 78%|███████▊  | 48405/61904 [2:28:24<5:11:56,  1.39s/it]
 78%|███████▊  | 48406/61904 [2:28:25<5:05:31,  1.36s/it]
 78%|███████▊  | 48407/61904 [2:28:26<5:05:38,  1.36s/it]
 78%|███████▊  | 48408/61904 [2:28:28<5:06:01,  1.36s/it]
 78%|███████▊  | 48409/61904 [2:28:29<5:02:08,  1.34s/it]
 78%|███████▊  | 48410/61904 [2:28:30<5:01:44,  1.34s/it]
 78%|███████▊  | 48411/61904 [2:28:32<5:04:15,  1.35s/it]
 78%|███████▊  | 48412/61904 [2:28:33<5:10:35,  1.38s/it]
 78%|███████▊  | 48413/61904 [2:28:35<5:11:08,  1.38s/it]
 78%|███████▊  | 48414/61904 [2:28:36<5:13:32,  1.39s/it]
 78%|███████▊  | 48415/61904 [2:28:37<5:13:00,  1.39s/it]
 78%|███████▊  | 48416/61904 [2:28:39<5:19:48,  1.42s/it]
 78%|███████▊  | 48417/61904 [2:28:40<5:25:20,  1.45s/it]
 78%|███████▊  | 48418/61904 [2:28:42<5:42:57,  1.53s/it]
 78%|███████▊  | 48419/61904 [2:28:44<5:31:57,  1.48s/it]
 78%|███████▊  | 48420/61904 [2:28:45<5:22:51,  1.44s/it]
                                                         
{'loss': 2.4912, 'learning_rate': 1.2185271619343964e-07, 'epoch': 12.51}
+
 78%|███████▊  | 48420/61904 [2:28:45<5:22:51,  1.44s/it]
 78%|███████▊  | 48421/61904 [2:28:47<5:35:43,  1.49s/it]
 78%|███████▊  | 48422/61904 [2:28:48<5:34:37,  1.49s/it]
 78%|███████▊  | 48423/61904 [2:28:49<5:33:14,  1.48s/it]
 78%|███████▊  | 48424/61904 [2:28:51<5:18:47,  1.42s/it]
 78%|███████▊  | 48425/61904 [2:28:52<5:17:35,  1.41s/it]
 78%|███████▊  | 48426/61904 [2:28:54<5:30:07,  1.47s/it]
 78%|███████▊  | 48427/61904 [2:28:55<5:25:33,  1.45s/it]
 78%|███████▊  | 48428/61904 [2:28:57<5:18:36,  1.42s/it]
 78%|███████▊  | 48429/61904 [2:28:58<5:17:48,  1.42s/it]
 78%|███████▊  | 48430/61904 [2:28:59<5:28:46,  1.46s/it]
 78%|███████▊  | 48431/61904 [2:29:01<5:11:13,  1.39s/it]
 78%|███████▊  | 48432/61904 [2:29:02<5:12:00,  1.39s/it]
 78%|███████▊  | 48433/61904 [2:29:04<5:18:07,  1.42s/it]
 78%|███████▊  | 48434/61904 [2:29:05<5:07:50,  1.37s/it]
 78%|███████▊  | 48435/61904 [2:29:06<5:00:19,  1.34s/it]
 78%|███████▊  | 48436/61904 [2:29:08<5:14:57,  1.40s/it]
 78%|███████▊  | 48437/61904 [2:29:09<5:20:17,  1.43s/it]
 78%|███████▊  | 48438/61904 [2:29:10<5:14:49,  1.40s/it]
 78%|███████▊  | 48439/61904 [2:29:12<5:10:48,  1.38s/it]
 78%|███████▊  | 48440/61904 [2:29:13<5:15:32,  1.41s/it]
                                                         
{'loss': 2.4681, 'learning_rate': 1.218203033838973e-07, 'epoch': 12.52}
+
 78%|███████▊  | 48440/61904 [2:29:13<5:15:32,  1.41s/it]
 78%|███████▊  | 48441/61904 [2:29:15<5:21:36,  1.43s/it]
 78%|███████▊  | 48442/61904 [2:29:16<5:27:59,  1.46s/it]
 78%|███████▊  | 48443/61904 [2:29:18<5:18:32,  1.42s/it]
 78%|███████▊  | 48444/61904 [2:29:19<5:11:20,  1.39s/it]
 78%|███████▊  | 48445/61904 [2:29:20<5:03:02,  1.35s/it]
 78%|███████▊  | 48446/61904 [2:29:21<4:58:18,  1.33s/it]
 78%|███████▊  | 48447/61904 [2:29:23<5:06:29,  1.37s/it]
 78%|███████▊  | 48448/61904 [2:29:24<5:07:47,  1.37s/it]
 78%|███████▊  | 48449/61904 [2:29:26<5:07:15,  1.37s/it]
 78%|███████▊  | 48450/61904 [2:29:27<5:09:14,  1.38s/it]
 78%|███████▊  | 48451/61904 [2:29:28<5:10:20,  1.38s/it]
 78%|███████▊  | 48452/61904 [2:29:30<5:03:35,  1.35s/it]
 78%|███████▊  | 48453/61904 [2:29:31<5:06:04,  1.37s/it]
 78%|███████▊  | 48454/61904 [2:29:33<5:11:39,  1.39s/it]
 78%|███████▊  | 48455/61904 [2:29:34<5:17:43,  1.42s/it]
 78%|███████▊  | 48456/61904 [2:29:35<5:14:44,  1.40s/it]
 78%|███████▊  | 48457/61904 [2:29:37<5:10:49,  1.39s/it]
 78%|███████▊  | 48458/61904 [2:29:38<5:11:11,  1.39s/it]
 78%|███████▊  | 48459/61904 [2:29:40<5:16:27,  1.41s/it]
 78%|███████▊  | 48460/61904 [2:29:41<5:16:51,  1.41s/it]
                                                         
{'loss': 2.4598, 'learning_rate': 1.21787890574355e-07, 'epoch': 12.53}
+
 78%|███████▊  | 48460/61904 [2:29:41<5:16:51,  1.41s/it]
 78%|███████▊  | 48461/61904 [2:29:42<5:08:39,  1.38s/it]
 78%|███████▊  | 48462/61904 [2:29:44<5:13:21,  1.40s/it]
 78%|███████▊  | 48463/61904 [2:29:45<5:07:34,  1.37s/it]
 78%|███████▊  | 48464/61904 [2:29:46<5:05:04,  1.36s/it]
 78%|███████▊  | 48465/61904 [2:29:48<5:04:09,  1.36s/it]
 78%|███████▊  | 48466/61904 [2:29:49<5:06:43,  1.37s/it]
 78%|███████▊  | 48467/61904 [2:29:51<5:00:53,  1.34s/it]
 78%|███████▊  | 48468/61904 [2:29:52<4:59:03,  1.34s/it]
 78%|███████▊  | 48469/61904 [2:29:53<5:01:14,  1.35s/it]
 78%|███████▊  | 48470/61904 [2:29:55<5:01:27,  1.35s/it]
 78%|███████▊  | 48471/61904 [2:29:56<4:54:49,  1.32s/it]
 78%|███████▊  | 48472/61904 [2:29:57<4:56:13,  1.32s/it]
 78%|███████▊  | 48473/61904 [2:29:58<4:49:08,  1.29s/it]
 78%|███████▊  | 48474/61904 [2:30:00<4:50:14,  1.30s/it]
 78%|███████▊  | 48475/61904 [2:30:01<4:50:11,  1.30s/it]
 78%|███████▊  | 48476/61904 [2:30:02<4:56:04,  1.32s/it]
 78%|███████▊  | 48477/61904 [2:30:04<4:59:54,  1.34s/it]
 78%|███████▊  | 48478/61904 [2:30:05<5:03:31,  1.36s/it]
 78%|███████▊  | 48479/61904 [2:30:06<4:58:13,  1.33s/it]
 78%|███████▊  | 48480/61904 [2:30:08<5:06:40,  1.37s/it]
                                                         
{'loss': 2.4792, 'learning_rate': 1.2175547776481265e-07, 'epoch': 12.53}
+
 78%|███████▊  | 48480/61904 [2:30:08<5:06:40,  1.37s/it]
 78%|███████▊  | 48481/61904 [2:30:09<4:59:35,  1.34s/it]
 78%|███████▊  | 48482/61904 [2:30:10<5:00:59,  1.35s/it]
 78%|███████▊  | 48483/61904 [2:30:12<5:03:52,  1.36s/it]
 78%|█████���█▊  | 48484/61904 [2:30:13<5:14:02,  1.40s/it]
 78%|███████▊  | 48485/61904 [2:30:15<5:12:16,  1.40s/it]
 78%|███████▊  | 48486/61904 [2:30:16<5:16:11,  1.41s/it]
 78%|███████▊  | 48487/61904 [2:30:17<5:04:07,  1.36s/it]
 78%|███████▊  | 48488/61904 [2:30:19<5:08:51,  1.38s/it]
 78%|███████▊  | 48489/61904 [2:30:20<5:09:34,  1.38s/it]
 78%|███████▊  | 48490/61904 [2:30:22<5:06:13,  1.37s/it]
 78%|███████▊  | 48491/61904 [2:30:23<5:11:00,  1.39s/it]
 78%|███████▊  | 48492/61904 [2:30:24<5:10:56,  1.39s/it]
 78%|███████▊  | 48493/61904 [2:30:26<5:06:12,  1.37s/it]
 78%|███████▊  | 48494/61904 [2:30:27<5:11:37,  1.39s/it]
 78%|███████▊  | 48495/61904 [2:30:28<5:00:43,  1.35s/it]
 78%|███████▊  | 48496/61904 [2:30:30<4:53:57,  1.32s/it]
 78%|███████▊  | 48497/61904 [2:30:31<5:12:53,  1.40s/it]
 78%|███████▊  | 48498/61904 [2:30:33<5:05:54,  1.37s/it]
 78%|███████▊  | 48499/61904 [2:30:34<5:09:36,  1.39s/it]
 78%|███████▊  | 48500/61904 [2:30:35<5:13:35,  1.40s/it]
                                                         
{'loss': 2.4331, 'learning_rate': 1.2172306495527032e-07, 'epoch': 12.54}
+
 78%|███████▊  | 48500/61904 [2:30:35<5:13:35,  1.40s/it]
 78%|███████▊  | 48501/61904 [2:30:37<5:17:59,  1.42s/it]
 78%|███████▊  | 48502/61904 [2:30:38<5:10:00,  1.39s/it]
 78%|███████▊  | 48503/61904 [2:30:40<5:21:14,  1.44s/it]
 78%|███████▊  | 48504/61904 [2:30:41<5:12:19,  1.40s/it]
 78%|███████▊  | 48505/61904 [2:30:43<5:14:44,  1.41s/it]
 78%|███████▊  | 48506/61904 [2:30:44<5:15:33,  1.41s/it]
 78%|███████▊  | 48507/61904 [2:30:45<5:15:02,  1.41s/it]
 78%|███████▊  | 48508/61904 [2:30:47<5:06:33,  1.37s/it]
 78%|███████▊  | 48509/61904 [2:30:48<5:01:05,  1.35s/it]
 78%|███████▊  | 48510/61904 [2:30:49<5:07:16,  1.38s/it]
 78%|███████▊  | 48511/61904 [2:30:51<5:01:39,  1.35s/it]
 78%|███████▊  | 48512/61904 [2:30:52<5:05:21,  1.37s/it]
 78%|███████▊  | 48513/61904 [2:30:53<5:03:30,  1.36s/it]
 78%|███████▊  | 48514/61904 [2:30:55<5:03:26,  1.36s/it]
 78%|███████▊  | 48515/61904 [2:30:56<4:56:33,  1.33s/it]
 78%|███████▊  | 48516/61904 [2:30:57<4:44:15,  1.27s/it]
 78%|███████▊  | 48517/61904 [2:30:58<4:47:53,  1.29s/it]
 78%|███████▊  | 48518/61904 [2:31:00<4:56:14,  1.33s/it]
 78%|███████▊  | 48519/61904 [2:31:01<4:51:21,  1.31s/it]
 78%|███████▊  | 48520/61904 [2:31:02<4:47:32,  1.29s/it]
                                                         
{'loss': 2.4537, 'learning_rate': 1.21690652145728e-07, 'epoch': 12.54}
+
 78%|███████▊  | 48520/61904 [2:31:02<4:47:32,  1.29s/it]
 78%|███████▊  | 48521/61904 [2:31:04<4:51:11,  1.31s/it]
 78%|███████▊  | 48522/61904 [2:31:05<5:02:27,  1.36s/it]
 78%|███████▊  | 48523/61904 [2:31:07<5:03:55,  1.36s/it]
 78%|███████▊  | 48524/61904 [2:31:08<5:17:49,  1.43s/it]
 78%|███████▊  | 48525/61904 [2:31:09<5:10:10,  1.39s/it]
 78%|███████▊  | 48526/61904 [2:31:11<5:10:16,  1.39s/it]
 78%|███████▊  | 48527/61904 [2:31:12<5:03:18,  1.36s/it]
 78%|███████▊  | 48528/61904 [2:31:14<5:05:46,  1.37s/it]
 78%|███████▊  | 48529/61904 [2:31:15<4:59:34,  1.34s/it]
 78%|███████▊  | 48530/61904 [2:31:16<5:08:32,  1.38s/it]
 78%|███████▊  | 48531/61904 [2:31:18<5:01:40,  1.35s/it]
 78%|███████▊  | 48532/61904 [2:31:19<5:01:23,  1.35s/it]
 78%|███████▊  | 48533/61904 [2:31:20<5:02:06,  1.36s/it]
 78%|███████▊  | 48534/61904 [2:31:22<5:02:17,  1.36s/it]
 78%|███████▊  | 48535/61904 [2:31:23<5:05:34,  1.37s/it]
 78%|███████▊  | 48536/61904 [2:31:25<5:11:35,  1.40s/it]
 78%|███████▊  | 48537/61904 [2:31:26<5:07:02,  1.38s/it]
 78%|███████▊  | 48538/61904 [2:31:27<4:59:02,  1.34s/it]
 78%|███████▊  | 48539/61904 [2:31:29<5:05:42,  1.37s/it]
 78%|███████▊  | 48540/61904 [2:31:30<4:55:59,  1.33s/it]
                                                         
{'loss': 2.5384, 'learning_rate': 1.2165823933618564e-07, 'epoch': 12.55}
+
 78%|███████▊  | 48540/61904 [2:31:30<4:55:59,  1.33s/it]
 78%|███████▊  | 48541/61904 [2:31:31<4:56:40,  1.33s/it]
 78%|███████▊  | 48542/61904 [2:31:33<4:59:22,  1.34s/it]
 78%|███████▊  | 48543/61904 [2:31:34<4:57:54,  1.34s/it]
 78%|███████▊  | 48544/61904 [2:31:35<4:55:25,  1.33s/it]
 78%|███████▊  | 48545/61904 [2:31:37<4:58:07,  1.34s/it]
 78%|███████▊  | 48546/61904 [2:31:38<5:01:11,  1.35s/it]
 78%|███████▊  | 48547/61904 [2:31:39<4:54:03,  1.32s/it]
 78%|███████▊  | 48548/61904 [2:31:41<5:00:17,  1.35s/it]
 78%|███████▊  | 48549/61904 [2:31:42<4:58:42,  1.34s/it]
 78%|███████▊  | 48550/61904 [2:31:43<5:11:19,  1.40s/it]
 78%|███████▊  | 48551/61904 [2:31:45<5:05:58,  1.37s/it]
 78%|███████▊  | 48552/61904 [2:31:46<5:00:24,  1.35s/it]
 78%|███████▊  | 48553/61904 [2:31:47<5:04:03,  1.37s/it]
 78%|███████▊  | 48554/61904 [2:31:49<5:10:01,  1.39s/it]
 78%|███████▊  | 48555/61904 [2:31:50<5:05:34,  1.37s/it]
 78%|███████▊  | 48556/61904 [2:31:52<5:01:20,  1.35s/it]
 78%|███████▊  | 48557/61904 [2:31:53<5:03:21,  1.36s/it]
 78%|███████▊  | 48558/61904 [2:31:54<5:00:44,  1.35s/it]
 78%|███████▊  | 48559/61904 [2:31:56<5:02:06,  1.36s/it]
 78%|███████▊  | 48560/61904 [2:31:57<5:04:53,  1.37s/it]
                                                         
{'loss': 2.5251, 'learning_rate': 1.2162582652664333e-07, 'epoch': 12.55}
+
 78%|███████▊  | 48560/61904 [2:31:57<5:04:53,  1.37s/it]
 78%|███████▊  | 48561/61904 [2:31:58<5:02:54,  1.36s/it]
 78%|███████▊  | 48562/61904 [2:32:00<5:01:50,  1.36s/it]
 78%|███████▊  | 48563/61904 [2:32:01<4:59:14,  1.35s/it]
 78%|███████▊  | 48564/61904 [2:32:02<4:57:29,  1.34s/it]
 78%|███████▊  | 48565/61904 [2:32:04<4:58:03,  1.34s/it]
 78%|███████▊  | 48566/61904 [2:32:05<4:56:49,  1.34s/it]
 78%|███████▊  | 48567/61904 [2:32:07<5:09:52,  1.39s/it]
 78%|███████▊  | 48568/61904 [2:32:08<5:05:30,  1.37s/it]
 78%|███████▊  | 48569/61904 [2:32:09<5:09:47,  1.39s/it]
 78%|███████▊  | 48570/61904 [2:32:11<5:06:38,  1.38s/it]
 78%|███████▊  | 48571/61904 [2:32:12<5:03:16,  1.36s/it]
 78%|███████▊  | 48572/61904 [2:32:14<5:15:55,  1.42s/it]
 78%|███████▊  | 48573/61904 [2:32:15<5:25:26,  1.46s/it]
 78%|███████▊  | 48574/61904 [2:32:16<5:20:49,  1.44s/it]
 78%|███████▊  | 48575/61904 [2:32:18<5:13:01,  1.41s/it]
 78%|███████▊  | 48576/61904 [2:32:19<5:17:49,  1.43s/it]
 78%|███████▊  | 48577/61904 [2:32:21<5:07:14,  1.38s/it]
 78%|███████▊  | 48578/61904 [2:32:22<4:57:25,  1.34s/it]
 78%|███████▊  | 48579/61904 [2:32:23<5:01:46,  1.36s/it]
 78%|███████▊  | 48580/61904 [2:32:25<5:10:15,  1.40s/it]
                                                         
{'loss': 2.4403, 'learning_rate': 1.21593413717101e-07, 'epoch': 12.56}
+
 78%|███████▊  | 48580/61904 [2:32:25<5:10:15,  1.40s/it]
 78%|███████▊  | 48581/61904 [2:32:26<5:04:40,  1.37s/it]
 78%|███████▊  | 48582/61904 [2:32:27<5:00:47,  1.35s/it]
 78%|███████▊  | 48583/61904 [2:32:29<4:59:17,  1.35s/it]
 78%|███████▊  | 48584/61904 [2:32:30<4:58:57,  1.35s/it]
 78%|███████▊  | 48585/61904 [2:32:31<4:59:46,  1.35s/it]
 78%|███████▊  | 48586/61904 [2:32:33<5:02:46,  1.36s/it]
 78%|███████▊  | 48587/61904 [2:32:34<5:09:07,  1.39s/it]
 78%|███████▊  | 48588/61904 [2:32:36<5:20:42,  1.45s/it]
 78%|███████▊  | 48589/61904 [2:32:37<5:08:38,  1.39s/it]
 78%|███████▊  | 48590/61904 [2:32:39<5:14:13,  1.42s/it]
 78%|███████▊  | 48591/61904 [2:32:40<5:13:26,  1.41s/it]
 78%|███████▊  | 48592/61904 [2:32:41<5:06:35,  1.38s/it]
 78%|███████▊  | 48593/61904 [2:32:43<5:19:29,  1.44s/it]
 78%|███████▊  | 48594/61904 [2:32:44<5:10:28,  1.40s/it]
 79%|███████▊  | 48595/61904 [2:32:46<5:16:09,  1.43s/it]
 79%|███████▊  | 48596/61904 [2:32:47<5:12:33,  1.41s/it]
 79%|███████▊  | 48597/61904 [2:32:48<5:04:14,  1.37s/it]
 79%|███████▊  | 48598/61904 [2:32:50<4:55:59,  1.33s/it]
 79%|███████▊  | 48599/61904 [2:32:51<4:51:52,  1.32s/it]
 79%|███████▊  | 48600/61904 [2:32:52<4:58:16,  1.35s/it]
                                                         
{'loss': 2.4652, 'learning_rate': 1.2156100090755865e-07, 'epoch': 12.56}
+
 79%|███████▊  | 48600/61904 [2:32:52<4:58:16,  1.35s/it]
 79%|███████▊  | 48601/61904 [2:32:54<5:02:32,  1.36s/it]
 79%|███████▊  | 48602/61904 [2:32:55<5:17:30,  1.43s/it]
 79%|███████▊  | 48603/61904 [2:32:57<5:14:59,  1.42s/it]
 79%|███████▊  | 48604/61904 [2:32:58<5:03:15,  1.37s/it]
 79%|███████▊  | 48605/61904 [2:32:59<5:04:05,  1.37s/it]
 79%|███████▊  | 48606/61904 [2:33:01<5:06:55,  1.38s/it]
 79%|███████▊  | 48607/61904 [2:33:02<4:59:54,  1.35s/it]
 79%|███████▊  | 48608/61904 [2:33:03<4:57:01,  1.34s/it]
 79%|███████▊  | 48609/61904 [2:33:05<5:04:43,  1.38s/it]
 79%|███████▊  | 48610/61904 [2:33:06<4:57:53,  1.34s/it]
 79%|███████▊  | 48611/61904 [2:33:07<4:53:11,  1.32s/it]
 79%|███████▊  | 48612/61904 [2:33:09<4:59:17,  1.35s/it]
 79%|███████▊  | 48613/61904 [2:33:10<4:56:35,  1.34s/it]
 79%|███████▊  | 48614/61904 [2:33:11<5:00:33,  1.36s/it]
 79%|███████▊  | 48615/61904 [2:33:13<4:52:36,  1.32s/it]
 79%|███████▊  | 48616/61904 [2:33:14<4:52:31,  1.32s/it]
 79%|███████▊  | 48617/61904 [2:33:15<4:56:51,  1.34s/it]
 79%|███████▊  | 48618/61904 [2:33:17<5:05:55,  1.38s/it]
 79%|███████▊  | 48619/61904 [2:33:18<5:06:34,  1.38s/it]
 79%|███████▊  | 48620/61904 [2:33:20<5:09:43,  1.40s/it]
                                                         
{'loss': 2.5051, 'learning_rate': 1.2152858809801634e-07, 'epoch': 12.57}
+
 79%|███████▊  | 48620/61904 [2:33:20<5:09:43,  1.40s/it]
 79%|███████▊  | 48621/61904 [2:33:21<5:13:53,  1.42s/it]
 79%|███████▊  | 48622/61904 [2:33:23<5:16:35,  1.43s/it]
 79%|███████▊  | 48623/61904 [2:33:24<5:14:19,  1.42s/it]
 79%|███████▊  | 48624/61904 [2:33:25<5:10:44,  1.40s/it]
 79%|███████▊  | 48625/61904 [2:33:27<5:07:23,  1.39s/it]
 79%|███████▊  | 48626/61904 [2:33:28<5:22:32,  1.46s/it]
 79%|███████▊  | 48627/61904 [2:33:30<5:12:49,  1.41s/it]
 79%|███████▊  | 48628/61904 [2:33:31<5:07:40,  1.39s/it]
 79%|███████▊  | 48629/61904 [2:33:32<5:00:47,  1.36s/it]
 79%|███████▊  | 48630/61904 [2:33:34<5:00:01,  1.36s/it]
 79%|███████▊  | 48631/61904 [2:33:35<5:04:13,  1.38s/it]
 79%|███████▊  | 48632/61904 [2:33:36<5:00:34,  1.36s/it]
 79%|███████▊  | 48633/61904 [2:33:38<4:53:24,  1.33s/it]
 79%|███████▊  | 48634/61904 [2:33:39<4:52:00,  1.32s/it]
 79%|███████▊  | 48635/61904 [2:33:40<4:52:46,  1.32s/it]
 79%|███████▊  | 48636/61904 [2:33:42<4:55:22,  1.34s/it]
 79%|███████▊  | 48637/61904 [2:33:43<4:56:18,  1.34s/it]
 79%|███████▊  | 48638/61904 [2:33:44<4:51:37,  1.32s/it]
 79%|███████▊  | 48639/61904 [2:33:46<5:05:11,  1.38s/it]
 79%|███████▊  | 48640/61904 [2:33:47<4:58:04,  1.35s/it]
                                                         
{'loss': 2.4572, 'learning_rate': 1.21496175288474e-07, 'epoch': 12.57}
+
 79%|███████▊  | 48640/61904 [2:33:47<4:58:04,  1.35s/it]
 79%|███████▊  | 48641/61904 [2:33:48<4:55:43,  1.34s/it]
 79%|███████▊  | 48642/61904 [2:33:50<5:06:18,  1.39s/it]
 79%|███████▊  | 48643/61904 [2:33:51<5:06:25,  1.39s/it]
 79%|███████▊  | 48644/61904 [2:33:52<4:58:22,  1.35s/it]
 79%|███████▊  | 48645/61904 [2:33:54<4:59:17,  1.35s/it]
 79%|███████▊  | 48646/61904 [2:33:55<5:13:54,  1.42s/it]
 79%|███████▊  | 48647/61904 [2:33:57<5:04:57,  1.38s/it]
 79%|███████▊  | 48648/61904 [2:33:58<5:02:42,  1.37s/it]
 79%|███████▊  | 48649/61904 [2:33:59<5:11:23,  1.41s/it]
 79%|███████▊  | 48650/61904 [2:34:01<5:07:22,  1.39s/it]
 79%|███████▊  | 48651/61904 [2:34:02<5:02:35,  1.37s/it]
 79%|███████▊  | 48652/61904 [2:34:04<5:03:45,  1.38s/it]
 79%|███████▊  | 48653/61904 [2:34:05<4:58:47,  1.35s/it]
 79%|███████▊  | 48654/61904 [2:34:06<4:54:27,  1.33s/it]
 79%|███████▊  | 48655/61904 [2:34:07<4:52:30,  1.32s/it]
 79%|███████▊  | 48656/61904 [2:34:09<4:48:09,  1.31s/it]
 79%|███████▊  | 48657/61904 [2:34:10<4:42:31,  1.28s/it]
 79%|███████▊  | 48658/61904 [2:34:11<4:41:56,  1.28s/it]
 79%|███████▊  | 48659/61904 [2:34:13<4:48:38,  1.31s/it]
 79%|███████▊  | 48660/61904 [2:34:14<4:53:03,  1.33s/it]
                                                         
{'loss': 2.4891, 'learning_rate': 1.2146376247893166e-07, 'epoch': 12.58}
+
 79%|███████▊  | 48660/61904 [2:34:14<4:53:03,  1.33s/it]
 79%|███████▊  | 48661/61904 [2:34:15<4:51:37,  1.32s/it]
 79%|███████▊  | 48662/61904 [2:34:17<4:59:56,  1.36s/it]
 79%|███████▊  | 48663/61904 [2:34:18<5:09:54,  1.40s/it]
 79%|███████▊  | 48664/61904 [2:34:19<5:02:49,  1.37s/it]
 79%|███████▊  | 48665/61904 [2:34:21<5:04:37,  1.38s/it]
 79%|███████▊  | 48666/61904 [2:34:22<5:10:15,  1.41s/it]
 79%|███████▊  | 48667/61904 [2:34:24<5:07:01,  1.39s/it]
 79%|███████▊  | 48668/61904 [2:34:25<4:57:25,  1.35s/it]
 79%|███████▊  | 48669/61904 [2:34:26<4:48:40,  1.31s/it]
 79%|███████▊  | 48670/61904 [2:34:28<4:59:59,  1.36s/it]
 79%|███████▊  | 48671/61904 [2:34:29<4:55:20,  1.34s/it]
 79%|███████▊  | 48672/61904 [2:34:30<4:55:40,  1.34s/it]
 79%|███████▊  | 48673/61904 [2:34:32<5:05:51,  1.39s/it]
 79%|███████▊  | 48674/61904 [2:34:33<5:06:19,  1.39s/it]
 79%|███████▊  | 48675/61904 [2:34:35<5:06:52,  1.39s/it]
 79%|███████▊  | 48676/61904 [2:34:36<5:02:29,  1.37s/it]
 79%|███████▊  | 48677/61904 [2:34:37<5:02:42,  1.37s/it]
 79%|███████▊  | 48678/61904 [2:34:39<4:58:44,  1.36s/it]
 79%|███████▊  | 48679/61904 [2:34:40<5:15:46,  1.43s/it]
 79%|███████▊  | 48680/61904 [2:34:42<5:12:50,  1.42s/it]
                                                         
{'loss': 2.5186, 'learning_rate': 1.2143134966938935e-07, 'epoch': 12.58}
+
 79%|███████▊  | 48680/61904 [2:34:42<5:12:50,  1.42s/it]
 79%|███████▊  | 48681/61904 [2:34:43<5:10:27,  1.41s/it]
 79%|███████▊  | 48682/61904 [2:34:44<4:57:52,  1.35s/it]
 79%|███████▊  | 48683/61904 [2:34:46<5:01:23,  1.37s/it]
 79%|███████▊  | 48684/61904 [2:34:47<5:11:32,  1.41s/it]
 79%|███████▊  | 48685/61904 [2:34:48<5:03:18,  1.38s/it]
 79%|███████▊  | 48686/61904 [2:34:50<4:59:08,  1.36s/it]
 79%|███████▊  | 48687/61904 [2:34:51<4:57:43,  1.35s/it]
 79%|███████▊  | 48688/61904 [2:34:52<4:59:24,  1.36s/it]
 79%|███████▊  | 48689/61904 [2:34:54<5:01:40,  1.37s/it]
 79%|███████▊  | 48690/61904 [2:34:55<5:02:56,  1.38s/it]
 79%|███████▊  | 48691/61904 [2:34:56<4:52:51,  1.33s/it]
 79%|███████▊  | 48692/61904 [2:34:58<4:58:08,  1.35s/it]
 79%|███████▊  | 48693/61904 [2:34:59<4:56:50,  1.35s/it]
 79%|███████▊  | 48694/61904 [2:35:01<5:01:10,  1.37s/it]
 79%|███████▊  | 48695/61904 [2:35:02<4:57:49,  1.35s/it]
 79%|███████▊  | 48696/61904 [2:35:03<5:00:08,  1.36s/it]
 79%|███████▊  | 48697/61904 [2:35:05<4:51:08,  1.32s/it]
 79%|███████▊  | 48698/61904 [2:35:06<4:58:12,  1.35s/it]
 79%|███████▊  | 48699/61904 [2:35:07<5:00:59,  1.37s/it]
 79%|███████▊  | 48700/61904 [2:35:09<5:02:35,  1.38s/it]
                                                         
{'loss': 2.4751, 'learning_rate': 1.21398936859847e-07, 'epoch': 12.59}
+
 79%|███████▊  | 48700/61904 [2:35:09<5:02:35,  1.38s/it]
 79%|███████▊  | 48701/61904 [2:35:10<4:57:00,  1.35s/it]
 79%|███████▊  | 48702/61904 [2:35:11<4:55:57,  1.35s/it]
 79%|███████▊  | 48703/61904 [2:35:13<4:55:37,  1.34s/it]
 79%|███████▊  | 48704/61904 [2:35:14<4:58:09,  1.36s/it]
 79%|███████▊  | 48705/61904 [2:35:15<4:53:57,  1.34s/it]
 79%|███████▊  | 48706/61904 [2:35:17<5:03:01,  1.38s/it]
 79%|███████▊  | 48707/61904 [2:35:18<5:04:25,  1.38s/it]
 79%|███████▊  | 48708/61904 [2:35:20<5:01:48,  1.37s/it]
 79%|███████▊  | 48709/61904 [2:35:21<4:58:54,  1.36s/it]
 79%|███████▊  | 48710/61904 [2:35:22<4:57:23,  1.35s/it]
 79%|███████▊  | 48711/61904 [2:35:24<4:51:43,  1.33s/it]
 79%|███████▊  | 48712/61904 [2:35:25<4:58:11,  1.36s/it]
 79%|███████▊  | 48713/61904 [2:35:26<4:53:02,  1.33s/it]
 79%|███████▊  | 48714/61904 [2:35:28<5:04:20,  1.38s/it]
 79%|███████▊  | 48715/61904 [2:35:29<4:53:53,  1.34s/it]
 79%|███████▊  | 48716/61904 [2:35:30<4:52:50,  1.33s/it]
 79%|███████▊  | 48717/61904 [2:35:32<4:57:58,  1.36s/it]
 79%|███████▊  | 48718/61904 [2:35:33<4:59:05,  1.36s/it]
 79%|███████▊  | 48719/61904 [2:35:35<5:11:14,  1.42s/it]
 79%|███████▊  | 48720/61904 [2:35:36<5:14:47,  1.43s/it]
                                                         
{'loss': 2.4716, 'learning_rate': 1.2136652405030468e-07, 'epoch': 12.59}
+
 79%|███████▊  | 48720/61904 [2:35:36<5:14:47,  1.43s/it]
 79%|███████▊  | 48721/61904 [2:35:37<5:09:24,  1.41s/it]
 79%|███████▊  | 48722/61904 [2:35:39<5:20:30,  1.46s/it]
 79%|███████▊  | 48723/61904 [2:35:41<5:22:46,  1.47s/it]
 79%|███████▊  | 48724/61904 [2:35:42<5:19:48,  1.46s/it]
 79%|███████▊  | 48725/61904 [2:35:43<5:15:43,  1.44s/it]
 79%|███████▊  | 48726/61904 [2:35:45<5:12:30,  1.42s/it]
 79%|███████▊  | 48727/61904 [2:35:46<5:13:36,  1.43s/it]
 79%|███████▊  | 48728/61904 [2:35:48<5:12:46,  1.42s/it]
 79%|███████▊  | 48729/61904 [2:35:49<5:03:15,  1.38s/it]
 79%|███████▊  | 48730/61904 [2:35:50<5:02:48,  1.38s/it]
 79%|███████▊  | 48731/61904 [2:35:51<4:54:08,  1.34s/it]
 79%|███████▊  | 48732/61904 [2:35:53<4:57:07,  1.35s/it]
 79%|███████▊  | 48733/61904 [2:35:54<4:57:04,  1.35s/it]
 79%|███████▊  | 48734/61904 [2:35:56<4:57:27,  1.36s/it]
 79%|███████▊  | 48735/61904 [2:35:57<4:55:43,  1.35s/it]
 79%|███████▊  | 48736/61904 [2:35:58<5:02:23,  1.38s/it]
 79%|███████▊  | 48737/61904 [2:36:00<5:07:25,  1.40s/it]
 79%|███████▊  | 48738/61904 [2:36:01<4:56:08,  1.35s/it]
 79%|███████▊  | 48739/61904 [2:36:02<4:56:12,  1.35s/it]
 79%|███████▊  | 48740/61904 [2:36:04<4:55:21,  1.35s/it]
                                                         
{'loss': 2.4849, 'learning_rate': 1.2133411124076234e-07, 'epoch': 12.6}
+
 79%|███████▊  | 48740/61904 [2:36:04<4:55:21,  1.35s/it]
 79%|███████▊  | 48741/61904 [2:36:05<4:53:35,  1.34s/it]
 79%|███████▊  | 48742/61904 [2:36:06<4:57:06,  1.35s/it]
 79%|███████▊  | 48743/61904 [2:36:08<4:54:46,  1.34s/it]
 79%|███████▊  | 48744/61904 [2:36:09<4:47:46,  1.31s/it]
 79%|███████▊  | 48745/61904 [2:36:11<5:06:27,  1.40s/it]
 79%|███████▊  | 48746/61904 [2:36:12<5:10:38,  1.42s/it]
 79%|███████▊  | 48747/61904 [2:36:13<5:01:07,  1.37s/it]
 79%|███████▊  | 48748/61904 [2:36:15<4:59:27,  1.37s/it]
 79%|███████▊  | 48749/61904 [2:36:16<4:54:02,  1.34s/it]
 79%|███████▉  | 48750/61904 [2:36:17<5:00:53,  1.37s/it]
 79%|███████▉  | 48751/61904 [2:36:19<5:01:34,  1.38s/it]
 79%|███████▉  | 48752/61904 [2:36:20<4:55:41,  1.35s/it]
 79%|███████▉  | 48753/61904 [2:36:22<5:04:57,  1.39s/it]
 79%|███████▉  | 48754/61904 [2:36:23<5:01:52,  1.38s/it]
 79%|███████▉  | 48755/61904 [2:36:24<4:59:46,  1.37s/it]
 79%|███████▉  | 48756/61904 [2:36:26<5:03:29,  1.38s/it]
 79%|███████▉  | 48757/61904 [2:36:27<5:02:07,  1.38s/it]
 79%|███████▉  | 48758/61904 [2:36:28<4:59:55,  1.37s/it]
 79%|███████▉  | 48759/61904 [2:36:30<5:08:01,  1.41s/it]
 79%|███████▉  | 48760/61904 [2:36:31<5:02:50,  1.38s/it]
                                                         
{'loss': 2.4891, 'learning_rate': 1.2130169843122e-07, 'epoch': 12.6}
+
 79%|███████▉  | 48760/61904 [2:36:31<5:02:50,  1.38s/it]
 79%|███████▉  | 48761/61904 [2:36:33<5:02:27,  1.38s/it]
 79%|███████▉  | 48762/61904 [2:36:34<5:10:31,  1.42s/it]
 79%|███████▉  | 48763/61904 [2:36:36<5:09:31,  1.41s/it]
 79%|███████▉  | 48764/61904 [2:36:37<5:07:05,  1.40s/it]
 79%|███████▉  | 48765/61904 [2:36:38<5:05:59,  1.40s/it]
 79%|███████▉  | 48766/61904 [2:36:40<5:08:37,  1.41s/it]
 79%|███████▉  | 48767/61904 [2:36:41<5:05:24,  1.39s/it]
 79%|███████▉  | 48768/61904 [2:36:42<4:57:40,  1.36s/it]
 79%|███████▉  | 48769/61904 [2:36:44<4:58:12,  1.36s/it]
 79%|███████▉  | 48770/61904 [2:36:45<4:55:52,  1.35s/it]
 79%|███████▉  | 48771/61904 [2:36:46<4:56:44,  1.36s/it]
 79%|███████▉  | 48772/61904 [2:36:48<4:53:27,  1.34s/it]
 79%|███████▉  | 48773/61904 [2:36:49<5:00:09,  1.37s/it]
 79%|███████▉  | 48774/61904 [2:36:51<5:04:43,  1.39s/it]
 79%|███████▉  | 48775/61904 [2:36:52<5:07:58,  1.41s/it]
 79%|███████▉  | 48776/61904 [2:36:54<5:18:19,  1.45s/it]
 79%|███████▉  | 48777/61904 [2:36:55<5:07:19,  1.40s/it]
 79%|███████▉  | 48778/61904 [2:36:56<5:08:45,  1.41s/it]
 79%|███████▉  | 48779/61904 [2:36:58<5:01:34,  1.38s/it]
 79%|███████▉  | 48780/61904 [2:36:59<4:50:37,  1.33s/it]
                                                         
{'loss': 2.4776, 'learning_rate': 1.212692856216777e-07, 'epoch': 12.61}
+
 79%|███████▉  | 48780/61904 [2:36:59<4:50:37,  1.33s/it]
 79%|███████▉  | 48781/61904 [2:37:00<4:45:44,  1.31s/it]
 79%|███████▉  | 48782/61904 [2:37:01<4:45:05,  1.30s/it]
 79%|███████▉  | 48783/61904 [2:37:03<4:51:41,  1.33s/it]
 79%|███████▉  | 48784/61904 [2:37:04<4:50:22,  1.33s/it]
 79%|███████▉  | 48785/61904 [2:37:06<4:56:17,  1.36s/it]
 79%|███████▉  | 48786/61904 [2:37:07<4:53:29,  1.34s/it]
 79%|███████▉  | 48787/61904 [2:37:08<5:06:40,  1.40s/it]
 79%|████��██▉  | 48788/61904 [2:37:10<5:00:29,  1.37s/it]
 79%|███████▉  | 48789/61904 [2:37:11<4:57:00,  1.36s/it]
 79%|███████▉  | 48790/61904 [2:37:12<5:02:39,  1.38s/it]
 79%|███████▉  | 48791/61904 [2:37:14<5:02:04,  1.38s/it]
 79%|███████▉  | 48792/61904 [2:37:15<5:07:14,  1.41s/it]
 79%|███████▉  | 48793/61904 [2:37:17<5:18:07,  1.46s/it]
 79%|███████▉  | 48794/61904 [2:37:18<5:14:30,  1.44s/it]
 79%|███████▉  | 48795/61904 [2:37:20<5:02:36,  1.39s/it]
 79%|███████▉  | 48796/61904 [2:37:21<4:58:57,  1.37s/it]
 79%|███████▉  | 48797/61904 [2:37:22<4:54:32,  1.35s/it]
 79%|███████▉  | 48798/61904 [2:37:24<4:56:40,  1.36s/it]
 79%|███████▉  | 48799/61904 [2:37:25<5:09:08,  1.42s/it]
 79%|███████▉  | 48800/61904 [2:37:26<5:04:14,  1.39s/it]
                                                         
{'loss': 2.5003, 'learning_rate': 1.2123687281213535e-07, 'epoch': 12.61}
+
 79%|███████▉  | 48800/61904 [2:37:26<5:04:14,  1.39s/it]
 79%|███████▉  | 48801/61904 [2:37:28<5:05:15,  1.40s/it]
 79%|███████▉  | 48802/61904 [2:37:29<5:05:26,  1.40s/it]
 79%|███████▉  | 48803/61904 [2:37:30<4:52:43,  1.34s/it]
 79%|███████▉  | 48804/61904 [2:37:32<4:47:15,  1.32s/it]
 79%|███████▉  | 48805/61904 [2:37:33<4:47:36,  1.32s/it]
 79%|███████▉  | 48806/61904 [2:37:34<4:46:02,  1.31s/it]
 79%|███████▉  | 48807/61904 [2:37:36<4:42:27,  1.29s/it]
 79%|███████▉  | 48808/61904 [2:37:37<4:54:16,  1.35s/it]
 79%|███████▉  | 48809/61904 [2:37:38<4:46:36,  1.31s/it]
 79%|███████▉  | 48810/61904 [2:37:40<4:59:57,  1.37s/it]
 79%|███████▉  | 48811/61904 [2:37:41<5:01:27,  1.38s/it]
 79%|███████▉  | 48812/61904 [2:37:43<5:08:46,  1.42s/it]
 79%|███████▉  | 48813/61904 [2:37:44<4:58:29,  1.37s/it]
 79%|███████▉  | 48814/61904 [2:37:45<4:53:15,  1.34s/it]
 79%|███████▉  | 48815/61904 [2:37:46<4:45:58,  1.31s/it]
 79%|███████▉  | 48816/61904 [2:37:48<4:46:12,  1.31s/it]
 79%|███████▉  | 48817/61904 [2:37:49<4:47:24,  1.32s/it]
 79%|███████▉  | 48818/61904 [2:37:50<4:50:17,  1.33s/it]
 79%|███████▉  | 48819/61904 [2:37:52<4:53:21,  1.35s/it]
 79%|███████▉  | 48820/61904 [2:37:53<4:54:09,  1.35s/it]
                                                         
{'loss': 2.4541, 'learning_rate': 1.21204460002593e-07, 'epoch': 12.62}
+
 79%|███████▉  | 48820/61904 [2:37:53<4:54:09,  1.35s/it]
 79%|███████▉  | 48821/61904 [2:37:55<5:07:29,  1.41s/it]
 79%|███████▉  | 48822/61904 [2:37:56<5:05:26,  1.40s/it]
 79%|███████▉  | 48823/61904 [2:37:57<5:00:59,  1.38s/it]
 79%|███████▉  | 48824/61904 [2:37:59<5:08:29,  1.42s/it]
 79%|███████▉  | 48825/61904 [2:38:00<4:59:33,  1.37s/it]
 79%|███████▉  | 48826/61904 [2:38:02<5:03:07,  1.39s/it]
 79%|███████▉  | 48827/61904 [2:38:03<5:04:43,  1.40s/it]
 79%|███████▉  | 48828/61904 [2:38:04<5:01:31,  1.38s/it]
 79%|███████▉  | 48829/61904 [2:38:06<4:57:20,  1.36s/it]
 79%|███████▉  | 48830/61904 [2:38:07<4:52:06,  1.34s/it]
 79%|███████▉  | 48831/61904 [2:38:09<4:59:59,  1.38s/it]
 79%|███████▉  | 48832/61904 [2:38:10<4:59:31,  1.37s/it]
 79%|███████▉  | 48833/61904 [2:38:11<5:02:56,  1.39s/it]
 79%|███████▉  | 48834/61904 [2:38:13<5:03:10,  1.39s/it]
 79%|███████▉  | 48835/61904 [2:38:14<4:58:25,  1.37s/it]
 79%|███████▉  | 48836/61904 [2:38:15<4:59:55,  1.38s/it]
 79%|███████▉  | 48837/61904 [2:38:17<4:53:41,  1.35s/it]
 79%|███████▉  | 48838/61904 [2:38:18<5:00:52,  1.38s/it]
 79%|███████▉  | 48839/61904 [2:38:20<4:59:20,  1.37s/it]
 79%|███████▉  | 48840/61904 [2:38:21<5:03:39,  1.39s/it]
                                                         
{'loss': 2.3995, 'learning_rate': 1.211720471930507e-07, 'epoch': 12.62}
+
 79%|███████▉  | 48840/61904 [2:38:21<5:03:39,  1.39s/it]
 79%|███████▉  | 48841/61904 [2:38:22<5:06:32,  1.41s/it]
 79%|███████▉  | 48842/61904 [2:38:24<5:01:59,  1.39s/it]
 79%|███████▉  | 48843/61904 [2:38:25<4:58:54,  1.37s/it]
 79%|███████▉  | 48844/61904 [2:38:27<5:33:24,  1.53s/it]
 79%|███████▉  | 48845/61904 [2:38:28<5:28:53,  1.51s/it]
 79%|███████▉  | 48846/61904 [2:38:30<5:29:51,  1.52s/it]
 79%|███████▉  | 48847/61904 [2:38:31<5:16:23,  1.45s/it]
 79%|███████▉  | 48848/61904 [2:38:33<5:16:41,  1.46s/it]
 79%|███████▉  | 48849/61904 [2:38:34<5:09:43,  1.42s/it]
 79%|███████▉  | 48850/61904 [2:38:36<5:16:15,  1.45s/it]
 79%|███████▉  | 48851/61904 [2:38:37<5:11:26,  1.43s/it]
 79%|███████▉  | 48852/61904 [2:38:38<5:00:53,  1.38s/it]
 79%|███████▉  | 48853/61904 [2:38:40<5:07:36,  1.41s/it]
 79%|███████▉  | 48854/61904 [2:38:41<5:02:36,  1.39s/it]
 79%|███████▉  | 48855/61904 [2:38:42<5:00:43,  1.38s/it]
 79%|███████▉  | 48856/61904 [2:38:44<4:58:19,  1.37s/it]
 79%|███████▉  | 48857/61904 [2:38:45<4:58:14,  1.37s/it]
 79%|███████▉  | 48858/61904 [2:38:47<5:00:15,  1.38s/it]
 79%|███████▉  | 48859/61904 [2:38:48<5:17:06,  1.46s/it]
 79%|███████▉  | 48860/61904 [2:38:50<5:14:18,  1.45s/it]
                                                         
{'loss': 2.4991, 'learning_rate': 1.2113963438350836e-07, 'epoch': 12.63}
+
 79%|███████▉  | 48860/61904 [2:38:50<5:14:18,  1.45s/it]
 79%|███████▉  | 48861/61904 [2:38:51<5:07:21,  1.41s/it]
 79%|███████▉  | 48862/61904 [2:38:52<5:01:51,  1.39s/it]
 79%|███████▉  | 48863/61904 [2:38:54<4:58:06,  1.37s/it]
 79%|███████▉  | 48864/61904 [2:38:55<4:53:00,  1.35s/it]
 79%|███████▉  | 48865/61904 [2:38:56<4:49:59,  1.33s/it]
 79%|███████▉  | 48866/61904 [2:38:58<4:54:58,  1.36s/it]
 79%|███████▉  | 48867/61904 [2:38:59<5:06:54,  1.41s/it]
 79%|███████▉  | 48868/61904 [2:39:01<5:19:46,  1.47s/it]
 79%|███████▉  | 48869/61904 [2:39:02<5:14:25,  1.45s/it]
 79%|███████▉  | 48870/61904 [2:39:04<5:11:04,  1.43s/it]
 79%|███████▉  | 48871/61904 [2:39:05<5:08:58,  1.42s/it]
 79%|███████▉  | 48872/61904 [2:39:06<5:00:45,  1.38s/it]
 79%|███████▉  | 48873/61904 [2:39:08<5:00:44,  1.38s/it]
 79%|███████▉  | 48874/61904 [2:39:09<4:57:38,  1.37s/it]
 79%|███████▉  | 48875/61904 [2:39:10<5:04:52,  1.40s/it]
 79%|███████▉  | 48876/61904 [2:39:12<4:50:58,  1.34s/it]
 79%|███████▉  | 48877/61904 [2:39:13<4:58:36,  1.38s/it]
 79%|███████▉  | 48878/61904 [2:39:15<4:59:20,  1.38s/it]
 79%|███████▉  | 48879/61904 [2:39:16<4:59:33,  1.38s/it]
 79%|███████▉  | 48880/61904 [2:39:17<4:52:56,  1.35s/it]
                                                         
{'loss': 2.4393, 'learning_rate': 1.2110722157396602e-07, 'epoch': 12.63}
+
 79%|███████▉  | 48880/61904 [2:39:17<4:52:56,  1.35s/it]
 79%|███████▉  | 48881/61904 [2:39:19<5:04:04,  1.40s/it]
 79%|███████▉  | 48882/61904 [2:39:20<5:02:21,  1.39s/it]
 79%|███████▉  | 48883/61904 [2:39:21<5:02:45,  1.40s/it]
 79%|███████▉  | 48884/61904 [2:39:23<4:55:16,  1.36s/it]
 79%|███████▉  | 48885/61904 [2:39:24<4:53:55,  1.35s/it]
 79%|███████▉  | 48886/61904 [2:39:25<4:54:11,  1.36s/it]
 79%|███████▉  | 48887/61904 [2:39:27<5:02:28,  1.39s/it]
 79%|███████▉  | 48888/61904 [2:39:28<5:03:57,  1.40s/it]
 79%|███████▉  | 48889/61904 [2:39:30<4:55:28,  1.36s/it]
 79%|███████▉  | 48890/61904 [2:39:31<5:08:04,  1.42s/it]
 79%|███████▉  | 48891/61904 [2:39:33<5:03:08,  1.40s/it]
 79%|███████▉  | 48892/61904 [2:39:34<5:05:56,  1.41s/it]
 79%|███████▉  | 48893/61904 [2:39:35<4:55:41,  1.36s/it]
 79%|███████▉  | 48894/61904 [2:39:37<5:05:33,  1.41s/it]
 79%|███████▉  | 48895/61904 [2:39:38<5:04:12,  1.40s/it]
 79%|███████▉  | 48896/61904 [2:39:40<5:14:25,  1.45s/it]
 79%|███████▉  | 48897/61904 [2:39:41<5:17:21,  1.46s/it]
 79%|███████▉  | 48898/61904 [2:39:43<5:10:51,  1.43s/it]
 79%|███████▉  | 48899/61904 [2:39:44<5:11:33,  1.44s/it]
 79%|███████▉  | 48900/61904 [2:39:45<5:06:56,  1.42s/it]
                                                         
{'loss': 2.4266, 'learning_rate': 1.2107480876442369e-07, 'epoch': 12.64}
+
 79%|███████▉  | 48900/61904 [2:39:45<5:06:56,  1.42s/it]
 79%|███████▉  | 48901/61904 [2:39:47<5:01:04,  1.39s/it]
 79%|███████▉  | 48902/61904 [2:39:48<5:03:04,  1.40s/it]
 79%|███████▉  | 48903/61904 [2:39:50<5:06:44,  1.42s/it]
 79%|███████▉  | 48904/61904 [2:39:51<5:05:27,  1.41s/it]
 79%|███████▉  | 48905/61904 [2:39:52<5:03:01,  1.40s/it]
 79%|███████▉  | 48906/61904 [2:39:54<5:05:15,  1.41s/it]
 79%|███████▉  | 48907/61904 [2:39:55<4:59:34,  1.38s/it]
 79%|███████▉  | 48908/61904 [2:39:56<5:02:15,  1.40s/it]
 79%|███████▉  | 48909/61904 [2:39:58<5:00:40,  1.39s/it]
 79%|███████▉  | 48910/61904 [2:39:59<5:05:07,  1.41s/it]
 79%|███████▉  | 48911/61904 [2:40:01<4:58:16,  1.38s/it]
 79%|███████▉  | 48912/61904 [2:40:02<4:58:47,  1.38s/it]
 79%|███████▉  | 48913/61904 [2:40:04<5:08:58,  1.43s/it]
 79%|███████▉  | 48914/61904 [2:40:05<5:09:12,  1.43s/it]
 79%|███████▉  | 48915/61904 [2:40:06<5:10:42,  1.44s/it]
 79%|███████▉  | 48916/61904 [2:40:08<5:08:18,  1.42s/it]
 79%|███████▉  | 48917/61904 [2:40:09<5:06:27,  1.42s/it]
 79%|███████▉  | 48918/61904 [2:40:11<5:06:43,  1.42s/it]
 79%|███████▉  | 48919/61904 [2:40:12<5:10:12,  1.43s/it]
 79%|███████▉  | 48920/61904 [2:40:14<5:10:26,  1.43s/it]
                                                         
{'loss': 2.4504, 'learning_rate': 1.2104239595488135e-07, 'epoch': 12.64}
+
 79%|███████▉  | 48920/61904 [2:40:14<5:10:26,  1.43s/it]
 79%|███████▉  | 48921/61904 [2:40:15<5:02:59,  1.40s/it]
 79%|███████▉  | 48922/61904 [2:40:16<4:57:11,  1.37s/it]
 79%|███████▉  | 48923/61904 [2:40:18<4:58:03,  1.38s/it]
 79%|███████▉  | 48924/61904 [2:40:19<4:53:30,  1.36s/it]
 79%|███████▉  | 48925/61904 [2:40:20<4:47:50,  1.33s/it]
 79%|███████▉  | 48926/61904 [2:40:22<4:50:28,  1.34s/it]
 79%|███████▉  | 48927/61904 [2:40:23<4:46:29,  1.32s/it]
 79%|███████▉  | 48928/61904 [2:40:24<4:48:55,  1.34s/it]
 79%|███████▉  | 48929/61904 [2:40:26<4:55:03,  1.36s/it]
 79%|███████▉  | 48930/61904 [2:40:27<4:57:06,  1.37s/it]
 79%|███████▉  | 48931/61904 [2:40:28<5:01:40,  1.40s/it]
 79%|███████▉  | 48932/61904 [2:40:30<4:57:05,  1.37s/it]
 79%|███████▉  | 48933/61904 [2:40:31<4:56:09,  1.37s/it]
 79%|███████▉  | 48934/61904 [2:40:33<5:02:14,  1.40s/it]
 79%|███████▉  | 48935/61904 [2:40:34<5:08:08,  1.43s/it]
 79%|███████▉  | 48936/61904 [2:40:35<5:04:52,  1.41s/it]
 79%|███████▉  | 48937/61904 [2:40:37<5:04:52,  1.41s/it]
 79%|███████▉  | 48938/61904 [2:40:38<4:57:30,  1.38s/it]
 79%|███████▉  | 48939/61904 [2:40:40<4:57:01,  1.37s/it]
 79%|███████▉  | 48940/61904 [2:40:41<5:01:08,  1.39s/it]
                                                         
{'loss': 2.4426, 'learning_rate': 1.2100998314533904e-07, 'epoch': 12.65}
+
 79%|███████▉  | 48940/61904 [2:40:41<5:01:08,  1.39s/it]
 79%|███████▉  | 48941/61904 [2:40:42<5:04:48,  1.41s/it]
 79%|███████▉  | 48942/61904 [2:40:44<5:00:41,  1.39s/it]
 79%|███████▉  | 48943/61904 [2:40:45<4:59:27,  1.39s/it]
 79%|███████▉  | 48944/61904 [2:40:47<5:08:06,  1.43s/it]
 79%|███████▉  | 48945/61904 [2:40:48<5:05:22,  1.41s/it]
 79%|███████▉  | 48946/61904 [2:40:50<5:12:13,  1.45s/it]
 79%|███████▉  | 48947/61904 [2:40:51<5:06:10,  1.42s/it]
 79%|███████▉  | 48948/61904 [2:40:52<5:06:15,  1.42s/it]
 79%|███████▉  | 48949/61904 [2:40:54<5:09:55,  1.44s/it]
 79%|███████▉  | 48950/61904 [2:40:55<5:04:40,  1.41s/it]
 79%|███████▉  | 48951/61904 [2:40:57<4:59:47,  1.39s/it]
 79%|███████▉  | 48952/61904 [2:40:58<4:55:56,  1.37s/it]
 79%|███████▉  | 48953/61904 [2:40:59<5:14:10,  1.46s/it]
 79%|███████▉  | 48954/61904 [2:41:01<5:03:05,  1.40s/it]
 79%|███████▉  | 48955/61904 [2:41:02<4:55:29,  1.37s/it]
 79%|███████▉  | 48956/61904 [2:41:04<5:01:26,  1.40s/it]
 79%|███████▉  | 48957/61904 [2:41:05<4:56:36,  1.37s/it]
 79%|███████▉  | 48958/61904 [2:41:06<5:01:49,  1.40s/it]
 79%|███████▉  | 48959/61904 [2:41:08<4:56:32,  1.37s/it]
 79%|███████▉  | 48960/61904 [2:41:09<4:56:47,  1.38s/it]
                                                         
{'loss': 2.4279, 'learning_rate': 1.209775703357967e-07, 'epoch': 12.65}
+
 79%|███████▉  | 48960/61904 [2:41:09<4:56:47,  1.38s/it]
 79%|███████▉  | 48961/61904 [2:41:10<4:59:06,  1.39s/it]
 79%|███████▉  | 48962/61904 [2:41:12<4:59:25,  1.39s/it]
 79%|███████▉  | 48963/61904 [2:41:13<5:17:25,  1.47s/it]
 79%|███████▉  | 48964/61904 [2:41:15<5:01:23,  1.40s/it]
 79%|███████▉  | 48965/61904 [2:41:16<5:03:03,  1.41s/it]
 79%|███████▉  | 48966/61904 [2:41:18<5:05:36,  1.42s/it]
 79%|███████▉  | 48967/61904 [2:41:19<4:56:30,  1.38s/it]
 79%|███████▉  | 48968/61904 [2:41:20<4:51:37,  1.35s/it]
 79%|███████▉  | 48969/61904 [2:41:22<4:58:21,  1.38s/it]
 79%|███████▉  | 48970/61904 [2:41:23<4:58:56,  1.39s/it]
 79%|███████▉  | 48971/61904 [2:41:25<5:11:31,  1.45s/it]
 79%|███████▉  | 48972/61904 [2:41:26<5:12:06,  1.45s/it]
 79%|███████▉  | 48973/61904 [2:41:27<5:10:09,  1.44s/it]
 79%|███████▉  | 48974/61904 [2:41:29<5:07:34,  1.43s/it]
 79%|███████▉  | 48975/61904 [2:41:30<5:03:36,  1.41s/it]
 79%|███████▉  | 48976/61904 [2:41:32<4:57:01,  1.38s/it]
 79%|███████▉  | 48977/61904 [2:41:33<4:48:46,  1.34s/it]
 79%|███████▉  | 48978/61904 [2:41:34<4:46:49,  1.33s/it]
 79%|███████▉  | 48979/61904 [2:41:35<4:42:53,  1.31s/it]
 79%|███████▉  | 48980/61904 [2:41:37<4:56:12,  1.38s/it]
                                                         
{'loss': 2.4973, 'learning_rate': 1.2094515752625436e-07, 'epoch': 12.66}
+
 79%|███████▉  | 48980/61904 [2:41:37<4:56:12,  1.38s/it]
 79%|███████▉  | 48981/61904 [2:41:38<5:00:18,  1.39s/it]
 79%|███████▉  | 48982/61904 [2:41:40<5:02:47,  1.41s/it]
 79%|███████▉  | 48983/61904 [2:41:41<4:59:42,  1.39s/it]
 79%|███████▉  | 48984/61904 [2:41:42<4:57:20,  1.38s/it]
 79%|███████▉  | 48985/61904 [2:41:44<5:00:51,  1.40s/it]
 79%|███████▉  | 48986/61904 [2:41:45<4:59:33,  1.39s/it]
 79%|███████▉  | 48987/61904 [2:41:47<5:03:20,  1.41s/it]
 79%|███████▉  | 48988/61904 [2:41:48<5:02:39,  1.41s/it]
 79%|███████▉  | 48989/61904 [2:41:49<4:51:42,  1.36s/it]
 79%|███████▉  | 48990/61904 [2:41:51<4:51:04,  1.35s/it]
 79%|███████▉  | 48991/61904 [2:41:52<4:49:28,  1.35s/it]
 79%|███████▉  | 48992/61904 [2:41:53<4:46:09,  1.33s/it]
 79%|███████▉  | 48993/61904 [2:41:55<4:41:37,  1.31s/it]
 79%|███████▉  | 48994/61904 [2:41:56<4:44:53,  1.32s/it]
 79%|███████▉  | 48995/61904 [2:41:57<4:41:22,  1.31s/it]
 79%|███████▉  | 48996/61904 [2:41:59<4:47:20,  1.34s/it]
 79%|███████▉  | 48997/61904 [2:42:00<4:55:17,  1.37s/it]
 79%|███████▉  | 48998/61904 [2:42:01<4:58:27,  1.39s/it]
 79%|███████▉  | 48999/61904 [2:42:03<5:07:30,  1.43s/it]
 79%|███████▉  | 49000/61904 [2:42:04<5:03:15,  1.41s/it]
                                                         
{'loss': 2.4447, 'learning_rate': 1.2091274471671205e-07, 'epoch': 12.66}
+
 79%|███████▉  | 49000/61904 [2:42:04<5:03:15,  1.41s/it]
 79%|███████▉  | 49001/61904 [2:42:06<4:59:25,  1.39s/it]
 79%|███████▉  | 49002/61904 [2:42:07<5:05:05,  1.42s/it]
 79%|███████▉  | 49003/61904 [2:42:09<5:15:39,  1.47s/it]
 79%|███████▉  | 49004/61904 [2:42:10<5:02:22,  1.41s/it]
 79%|███████▉  | 49005/61904 [2:42:11<4:56:25,  1.38s/it]
 79%|███████▉  | 49006/61904 [2:42:13<4:58:12,  1.39s/it]
 79%|███████▉  | 49007/61904 [2:42:14<4:50:27,  1.35s/it]
 79%|███████▉  | 49008/61904 [2:42:15<4:49:02,  1.34s/it]
 79%|███████▉  | 49009/61904 [2:42:17<4:44:42,  1.32s/it]
 79%|███████▉  | 49010/61904 [2:42:18<4:44:14,  1.32s/it]
 79%|███████▉  | 49011/61904 [2:42:19<4:50:53,  1.35s/it]
 79%|███████▉  | 49012/61904 [2:42:21<4:56:39,  1.38s/it]
 79%|███████▉  | 49013/61904 [2:42:22<4:55:22,  1.37s/it]
 79%|███████▉  | 49014/61904 [2:42:24<5:02:13,  1.41s/it]
 79%|███████▉  | 49015/61904 [2:42:25<5:02:29,  1.41s/it]
 79%|███████▉  | 49016/61904 [2:42:27<5:07:35,  1.43s/it]
 79%|███████▉  | 49017/61904 [2:42:28<4:57:23,  1.38s/it]
 79%|███████▉  | 49018/61904 [2:42:29<5:04:12,  1.42s/it]
 79%|███████▉  | 49019/61904 [2:42:31<4:59:14,  1.39s/it]
 79%|███████▉  | 49020/61904 [2:42:32<4:52:14,  1.36s/it]
                                                         
{'loss': 2.497, 'learning_rate': 1.208803319071697e-07, 'epoch': 12.67}
+
 79%|███████▉  | 49020/61904 [2:42:32<4:52:14,  1.36s/it]
 79%|███████▉  | 49021/61904 [2:42:33<4:55:54,  1.38s/it]
 79%|███████▉  | 49022/61904 [2:42:35<4:50:10,  1.35s/it]
 79%|███████▉  | 49023/61904 [2:42:36<4:58:37,  1.39s/it]
 79%|███████▉  | 49024/61904 [2:42:38<5:13:05,  1.46s/it]
 79%|███████▉  | 49025/61904 [2:42:39<5:07:49,  1.43s/it]
 79%|███████▉  | 49026/61904 [2:42:40<5:00:14,  1.40s/it]
 79%|███████▉  | 49027/61904 [2:42:42<5:04:06,  1.42s/it]
 79%|███████▉  | 49028/61904 [2:42:43<5:04:09,  1.42s/it]
 79%|███████▉  | 49029/61904 [2:42:45<5:03:35,  1.41s/it]
 79%|███████▉  | 49030/61904 [2:42:46<5:06:31,  1.43s/it]
 79%|███████���  | 49031/61904 [2:42:48<5:02:15,  1.41s/it]
 79%|███████▉  | 49032/61904 [2:42:49<4:55:58,  1.38s/it]
 79%|███████▉  | 49033/61904 [2:42:50<4:52:40,  1.36s/it]
 79%|███████▉  | 49034/61904 [2:42:52<4:54:28,  1.37s/it]
 79%|███████▉  | 49035/61904 [2:42:53<4:58:41,  1.39s/it]
 79%|███████▉  | 49036/61904 [2:42:54<4:50:05,  1.35s/it]
 79%|███████▉  | 49037/61904 [2:42:56<4:45:56,  1.33s/it]
 79%|███████▉  | 49038/61904 [2:42:57<4:47:31,  1.34s/it]
 79%|███████▉  | 49039/61904 [2:42:58<4:50:50,  1.36s/it]
 79%|███████▉  | 49040/61904 [2:43:00<4:57:48,  1.39s/it]
                                                         
{'loss': 2.4223, 'learning_rate': 1.2084791909762737e-07, 'epoch': 12.67}
+
 79%|███████▉  | 49040/61904 [2:43:00<4:57:48,  1.39s/it]
 79%|███████▉  | 49041/61904 [2:43:01<4:54:38,  1.37s/it]
 79%|███████▉  | 49042/61904 [2:43:03<5:03:57,  1.42s/it]
 79%|███████▉  | 49043/61904 [2:43:04<4:56:50,  1.38s/it]
 79%|███████▉  | 49044/61904 [2:43:05<4:59:52,  1.40s/it]
 79%|███████▉  | 49045/61904 [2:43:07<5:04:15,  1.42s/it]
 79%|███████▉  | 49046/61904 [2:43:08<5:06:29,  1.43s/it]
 79%|███████▉  | 49047/61904 [2:43:10<4:57:57,  1.39s/it]
 79%|███████▉  | 49048/61904 [2:43:11<4:59:41,  1.40s/it]
 79%|███████▉  | 49049/61904 [2:43:12<4:54:01,  1.37s/it]
 79%|███████▉  | 49050/61904 [2:43:14<5:03:45,  1.42s/it]
 79%|███████▉  | 49051/61904 [2:43:15<4:58:32,  1.39s/it]
 79%|███████▉  | 49052/61904 [2:43:17<4:57:56,  1.39s/it]
 79%|███████▉  | 49053/61904 [2:43:18<5:11:26,  1.45s/it]
 79%|███████▉  | 49054/61904 [2:43:20<5:14:57,  1.47s/it]
 79%|███████▉  | 49055/61904 [2:43:21<5:04:06,  1.42s/it]
 79%|███████▉  | 49056/61904 [2:43:22<5:06:33,  1.43s/it]
 79%|███████▉  | 49057/61904 [2:43:24<5:00:18,  1.40s/it]
 79%|███████▉  | 49058/61904 [2:43:25<4:59:11,  1.40s/it]
 79%|███████▉  | 49059/61904 [2:43:27<4:56:46,  1.39s/it]
 79%|███████▉  | 49060/61904 [2:43:28<4:47:43,  1.34s/it]
                                                         
{'loss': 2.447, 'learning_rate': 1.2081550628808503e-07, 'epoch': 12.68}
+
 79%|███████▉  | 49060/61904 [2:43:28<4:47:43,  1.34s/it]
 79%|███████▉  | 49061/61904 [2:43:29<4:46:21,  1.34s/it]
 79%|███████▉  | 49062/61904 [2:43:30<4:46:03,  1.34s/it]
 79%|███████▉  | 49063/61904 [2:43:32<4:51:47,  1.36s/it]
 79%|███████▉  | 49064/61904 [2:43:33<4:51:23,  1.36s/it]
 79%|███████▉  | 49065/61904 [2:43:35<5:01:07,  1.41s/it]
 79%|███████▉  | 49066/61904 [2:43:36<4:52:41,  1.37s/it]
 79%|███████▉  | 49067/61904 [2:43:37<4:54:22,  1.38s/it]
 79%|███████▉  | 49068/61904 [2:43:39<4:54:47,  1.38s/it]
 79%|███████▉  | 49069/61904 [2:43:40<4:59:34,  1.40s/it]
 79%|███████▉  | 49070/61904 [2:43:42<5:00:41,  1.41s/it]
 79%|███████▉  | 49071/61904 [2:43:43<5:03:57,  1.42s/it]
 79%|███████▉  | 49072/61904 [2:43:45<5:03:32,  1.42s/it]
 79%|███████▉  | 49073/61904 [2:43:46<5:07:13,  1.44s/it]
 79%|███████▉  | 49074/61904 [2:43:47<4:59:25,  1.40s/it]
 79%|███████▉  | 49075/61904 [2:43:49<5:06:54,  1.44s/it]
 79%|███████▉  | 49076/61904 [2:43:50<5:02:40,  1.42s/it]
 79%|███████▉  | 49077/61904 [2:43:51<4:50:00,  1.36s/it]
 79%|███████▉  | 49078/61904 [2:43:53<4:47:18,  1.34s/it]
 79%|███████▉  | 49079/61904 [2:43:54<4:44:17,  1.33s/it]
 79%|███████▉  | 49080/61904 [2:43:55<4:43:45,  1.33s/it]
                                                         
{'loss': 2.4652, 'learning_rate': 1.2078309347854272e-07, 'epoch': 12.69}
+
 79%|███████▉  | 49080/61904 [2:43:55<4:43:45,  1.33s/it]
 79%|███████▉  | 49081/61904 [2:43:57<4:38:48,  1.30s/it]
 79%|███████▉  | 49082/61904 [2:43:58<4:41:39,  1.32s/it]
 79%|███████▉  | 49083/61904 [2:43:59<4:41:38,  1.32s/it]
 79%|███████▉  | 49084/61904 [2:44:01<4:46:52,  1.34s/it]
 79%|███████▉  | 49085/61904 [2:44:02<4:52:42,  1.37s/it]
 79%|███████▉  | 49086/61904 [2:44:03<4:46:24,  1.34s/it]
 79%|███████▉  | 49087/61904 [2:44:05<4:47:48,  1.35s/it]
 79%|███████▉  | 49088/61904 [2:44:06<4:53:10,  1.37s/it]
 79%|███████▉  | 49089/61904 [2:44:08<4:58:36,  1.40s/it]
 79%|███████▉  | 49090/61904 [2:44:09<4:54:16,  1.38s/it]
 79%|███████▉  | 49091/61904 [2:44:10<4:57:04,  1.39s/it]
 79%|█��█████▉  | 49092/61904 [2:44:12<4:57:00,  1.39s/it]
 79%|███████▉  | 49093/61904 [2:44:13<5:03:42,  1.42s/it]
 79%|███████▉  | 49094/61904 [2:44:15<5:00:20,  1.41s/it]
 79%|███████▉  | 49095/61904 [2:44:16<4:57:44,  1.39s/it]
 79%|███████▉  | 49096/61904 [2:44:17<4:51:15,  1.36s/it]
 79%|███████▉  | 49097/61904 [2:44:19<4:45:33,  1.34s/it]
 79%|███████▉  | 49098/61904 [2:44:20<4:47:36,  1.35s/it]
 79%|███████▉  | 49099/61904 [2:44:21<4:44:05,  1.33s/it]
 79%|███████▉  | 49100/61904 [2:44:23<4:45:49,  1.34s/it]
                                                         
{'loss': 2.4167, 'learning_rate': 1.2075068066900038e-07, 'epoch': 12.69}
+
 79%|███████▉  | 49100/61904 [2:44:23<4:45:49,  1.34s/it]
 79%|███████▉  | 49101/61904 [2:44:24<4:43:01,  1.33s/it]
 79%|███████▉  | 49102/61904 [2:44:25<4:42:32,  1.32s/it]
 79%|███████▉  | 49103/61904 [2:44:27<4:49:59,  1.36s/it]
 79%|███████▉  | 49104/61904 [2:44:28<4:56:01,  1.39s/it]
 79%|███████▉  | 49105/61904 [2:44:30<4:55:09,  1.38s/it]
 79%|███████▉  | 49106/61904 [2:44:31<4:45:09,  1.34s/it]
 79%|███████▉  | 49107/61904 [2:44:32<4:47:19,  1.35s/it]
 79%|███████▉  | 49108/61904 [2:44:33<4:48:41,  1.35s/it]
 79%|███████▉  | 49109/61904 [2:44:35<4:59:22,  1.40s/it]
 79%|███████▉  | 49110/61904 [2:44:36<4:50:54,  1.36s/it]
 79%|███████▉  | 49111/61904 [2:44:38<4:51:32,  1.37s/it]
 79%|███████▉  | 49112/61904 [2:44:39<4:48:02,  1.35s/it]
 79%|███████▉  | 49113/61904 [2:44:40<4:43:55,  1.33s/it]
 79%|███████▉  | 49114/61904 [2:44:42<4:45:29,  1.34s/it]
 79%|███████▉  | 49115/61904 [2:44:43<4:51:58,  1.37s/it]
 79%|███████▉  | 49116/61904 [2:44:44<4:54:01,  1.38s/it]
 79%|███████▉  | 49117/61904 [2:44:46<4:56:05,  1.39s/it]
 79%|███████▉  | 49118/61904 [2:44:47<4:54:17,  1.38s/it]
 79%|███████▉  | 49119/61904 [2:44:49<5:01:12,  1.41s/it]
 79%|███████▉  | 49120/61904 [2:44:50<4:56:11,  1.39s/it]
                                                         
{'loss': 2.4103, 'learning_rate': 1.2071826785945805e-07, 'epoch': 12.7}
+
 79%|███████▉  | 49120/61904 [2:44:50<4:56:11,  1.39s/it]
 79%|███████▉  | 49121/61904 [2:44:51<4:51:19,  1.37s/it]
 79%|███████▉  | 49122/61904 [2:44:53<4:44:32,  1.34s/it]
 79%|███████▉  | 49123/61904 [2:44:54<4:41:45,  1.32s/it]
 79%|███████▉  | 49124/61904 [2:44:55<4:44:06,  1.33s/it]
 79%|███████▉  | 49125/61904 [2:44:57<4:40:16,  1.32s/it]
 79%|███████▉  | 49126/61904 [2:44:58<4:40:01,  1.31s/it]
 79%|███████▉  | 49127/61904 [2:44:59<4:43:51,  1.33s/it]
 79%|███████▉  | 49128/61904 [2:45:01<4:50:06,  1.36s/it]
 79%|███████▉  | 49129/61904 [2:45:02<4:49:19,  1.36s/it]
 79%|███████▉  | 49130/61904 [2:45:03<4:50:18,  1.36s/it]
 79%|███████▉  | 49131/61904 [2:45:05<4:55:22,  1.39s/it]
 79%|███████▉  | 49132/61904 [2:45:06<4:57:47,  1.40s/it]
 79%|███████▉  | 49133/61904 [2:45:08<4:58:05,  1.40s/it]
 79%|███████▉  | 49134/61904 [2:45:09<4:50:35,  1.37s/it]
 79%|███████▉  | 49135/61904 [2:45:10<4:55:41,  1.39s/it]
 79%|███████▉  | 49136/61904 [2:45:12<4:53:41,  1.38s/it]
 79%|███████▉  | 49137/61904 [2:45:13<5:02:58,  1.42s/it]
 79%|███████▉  | 49138/61904 [2:45:15<5:06:23,  1.44s/it]
 79%|███████▉  | 49139/61904 [2:45:16<5:00:03,  1.41s/it]
 79%|███████▉  | 49140/61904 [2:45:17<4:50:23,  1.37s/it]
                                                         
{'loss': 2.4225, 'learning_rate': 1.206858550499157e-07, 'epoch': 12.7}
+
 79%|███████▉  | 49140/61904 [2:45:17<4:50:23,  1.37s/it]
 79%|███████▉  | 49141/61904 [2:45:19<4:43:17,  1.33s/it]
 79%|███████▉  | 49142/61904 [2:45:20<4:54:28,  1.38s/it]
 79%|███████▉  | 49143/61904 [2:45:22<5:02:36,  1.42s/it]
 79%|███████▉  | 49144/61904 [2:45:23<4:58:59,  1.41s/it]
 79%|███████▉  | 49145/61904 [2:45:24<4:51:35,  1.37s/it]
 79%|███████▉  | 49146/61904 [2:45:26<4:49:52,  1.36s/it]
 79%|███████▉  | 49147/61904 [2:45:27<4:50:08,  1.36s/it]
 79%|███████▉  | 49148/61904 [2:45:28<4:41:19,  1.32s/it]
 79%|███████▉  | 49149/61904 [2:45:30<5:00:38,  1.41s/it]
 79%|███████▉  | 49150/61904 [2:45:31<5:02:17,  1.42s/it]
 79%|███████▉  | 49151/61904 [2:45:33<4:56:48,  1.40s/it]
 79%|███████▉  | 49152/61904 [2:45:34<4:52:07,  1.37s/it]
 79%|███████▉  | 49153/61904 [2:45:35<4:58:21,  1.40s/it]
 79%|███████▉  | 49154/61904 [2:45:37<4:55:36,  1.39s/it]
 79%|███████▉  | 49155/61904 [2:45:38<5:00:14,  1.41s/it]
 79%|███████▉  | 49156/61904 [2:45:40<5:09:56,  1.46s/it]
 79%|███████▉  | 49157/61904 [2:45:41<4:57:56,  1.40s/it]
 79%|███████▉  | 49158/61904 [2:45:43<5:04:16,  1.43s/it]
 79%|███████▉  | 49159/61904 [2:45:44<5:04:00,  1.43s/it]
 79%|███████▉  | 49160/61904 [2:45:45<4:59:56,  1.41s/it]
                                                         
{'loss': 2.4668, 'learning_rate': 1.206534422403734e-07, 'epoch': 12.71}
+
 79%|███████▉  | 49160/61904 [2:45:45<4:59:56,  1.41s/it]
 79%|███████▉  | 49161/61904 [2:45:47<5:00:44,  1.42s/it]
 79%|███████▉  | 49162/61904 [2:45:48<4:56:09,  1.39s/it]
 79%|███████▉  | 49163/61904 [2:45:49<4:50:17,  1.37s/it]
 79%|███████▉  | 49164/61904 [2:45:51<4:51:36,  1.37s/it]
 79%|███████▉  | 49165/61904 [2:45:52<4:50:14,  1.37s/it]
 79%|███████▉  | 49166/61904 [2:45:54<4:48:18,  1.36s/it]
 79%|███████▉  | 49167/61904 [2:45:55<4:39:09,  1.32s/it]
 79%|███████▉  | 49168/61904 [2:45:56<4:44:45,  1.34s/it]
 79%|███████▉  | 49169/61904 [2:45:57<4:35:47,  1.30s/it]
 79%|███████▉  | 49170/61904 [2:45:59<4:40:05,  1.32s/it]
 79%|███████▉  | 49171/61904 [2:46:00<4:43:42,  1.34s/it]
 79%|███████▉  | 49172/61904 [2:46:02<4:51:13,  1.37s/it]
 79%|███████▉  | 49173/61904 [2:46:03<5:01:04,  1.42s/it]
 79%|███████▉  | 49174/61904 [2:46:04<4:52:26,  1.38s/it]
 79%|███████▉  | 49175/61904 [2:46:06<4:45:17,  1.34s/it]
 79%|███████▉  | 49176/61904 [2:46:07<4:45:38,  1.35s/it]
 79%|███████▉  | 49177/61904 [2:46:08<4:52:52,  1.38s/it]
 79%|███████▉  | 49178/61904 [2:46:10<5:05:57,  1.44s/it]
 79%|███████▉  | 49179/61904 [2:46:11<4:56:16,  1.40s/it]
 79%|███████▉  | 49180/61904 [2:46:13<4:58:57,  1.41s/it]
                                                         
{'loss': 2.4861, 'learning_rate': 1.2062102943083106e-07, 'epoch': 12.71}
+
 79%|███████▉  | 49180/61904 [2:46:13<4:58:57,  1.41s/it]
 79%|███████▉  | 49181/61904 [2:46:14<5:01:27,  1.42s/it]
 79%|███████▉  | 49182/61904 [2:46:16<4:58:15,  1.41s/it]
 79%|███████▉  | 49183/61904 [2:46:17<4:51:38,  1.38s/it]
 79%|███████▉  | 49184/61904 [2:46:18<4:51:18,  1.37s/it]
 79%|███████▉  | 49185/61904 [2:46:20<4:58:27,  1.41s/it]
 79%|███████▉  | 49186/61904 [2:46:21<4:51:41,  1.38s/it]
 79%|███████▉  | 49187/61904 [2:46:23<4:58:34,  1.41s/it]
 79%|███████▉  | 49188/61904 [2:46:24<5:05:53,  1.44s/it]
 79%|███████▉  | 49189/61904 [2:46:25<4:59:33,  1.41s/it]
 79%|███████▉  | 49190/61904 [2:46:27<5:04:02,  1.43s/it]
 79%|███████▉  | 49191/61904 [2:46:28<4:55:11,  1.39s/it]
 79%|███████▉  | 49192/61904 [2:46:30<5:03:43,  1.43s/it]
 79%|███████▉  | 49193/61904 [2:46:31<4:51:13,  1.37s/it]
 79%|███████▉  | 49194/61904 [2:46:32<4:56:57,  1.40s/it]
 79%|███████▉  | 49195/61904 [2:46:34<4:50:52,  1.37s/it]
 79%|███████▉  | 49196/61904 [2:46:35<4:52:56,  1.38s/it]
 79%|███████▉  | 49197/61904 [2:46:37<4:54:38,  1.39s/it]
 79%|███████▉  | 49198/61904 [2:46:38<5:09:08,  1.46s/it]
 79%|███████▉  | 49199/61904 [2:46:40<5:04:29,  1.44s/it]
 79%|███████▉  | 49200/61904 [2:46:41<5:01:58,  1.43s/it]
                                                         
{'loss': 2.433, 'learning_rate': 1.2058861662128872e-07, 'epoch': 12.72}
+
 79%|███████▉  | 49200/61904 [2:46:41<5:01:58,  1.43s/it]
 79%|███████▉  | 49201/61904 [2:46:42<5:00:51,  1.42s/it]
 79%|███████▉  | 49202/61904 [2:46:44<5:13:50,  1.48s/it]
 79%|███████▉  | 49203/61904 [2:46:45<5:03:54,  1.44s/it]
 79%|███████▉  | 49204/61904 [2:46:47<5:02:38,  1.43s/it]
 79%|███████▉  | 49205/61904 [2:46:48<4:55:37,  1.40s/it]
 79%|███████▉  | 49206/61904 [2:46:49<4:52:20,  1.38s/it]
 79%|███████▉  | 49207/61904 [2:46:51<4:58:41,  1.41s/it]
 79%|███████▉  | 49208/61904 [2:46:52<4:52:58,  1.38s/it]
 79%|███████▉  | 49209/61904 [2:46:54<4:53:35,  1.39s/it]
 79%|███████▉  | 49210/61904 [2:46:55<5:01:38,  1.43s/it]
 79%|███████▉  | 49211/61904 [2:46:56<4:50:56,  1.38s/it]
 79%|███████▉  | 49212/61904 [2:46:58<4:54:44,  1.39s/it]
 79%|███████▉  | 49213/61904 [2:46:59<4:51:08,  1.38s/it]
 80%|███████▉  | 49214/61904 [2:47:01<4:52:26,  1.38s/it]
 80%|███████▉  | 49215/61904 [2:47:02<4:56:54,  1.40s/it]
 80%|███████▉  | 49216/61904 [2:47:03<4:54:02,  1.39s/it]
 80%|███████▉  | 49217/61904 [2:47:05<4:56:01,  1.40s/it]
 80%|███████▉  | 49218/61904 [2:47:06<4:53:41,  1.39s/it]
 80%|███████▉  | 49219/61904 [2:47:08<4:57:17,  1.41s/it]
 80%|███████▉  | 49220/61904 [2:47:09<4:57:00,  1.40s/it]
                                                         
{'loss': 2.4395, 'learning_rate': 1.205562038117464e-07, 'epoch': 12.72}
+
 80%|███████▉  | 49220/61904 [2:47:09<4:57:00,  1.40s/it]
 80%|███████▉  | 49221/61904 [2:47:10<4:58:05,  1.41s/it]
 80%|███████▉  | 49222/61904 [2:47:12<4:55:01,  1.40s/it]
 80%|███████▉  | 49223/61904 [2:47:13<4:51:00,  1.38s/it]
 80%|███████▉  | 49224/61904 [2:47:15<4:57:39,  1.41s/it]
 80%|███████▉  | 49225/61904 [2:47:16<4:55:52,  1.40s/it]
 80%|███████▉  | 49226/61904 [2:47:17<4:47:17,  1.36s/it]
 80%|███████▉  | 49227/61904 [2:47:19<4:43:50,  1.34s/it]
 80%|███████▉  | 49228/61904 [2:47:20<4:44:36,  1.35s/it]
 80%|███████▉  | 49229/61904 [2:47:21<4:40:27,  1.33s/it]
 80%|███████▉  | 49230/61904 [2:47:23<4:42:58,  1.34s/it]
 80%|███████▉  | 49231/61904 [2:47:24<4:44:50,  1.35s/it]
 80%|███████▉  | 49232/61904 [2:47:25<4:48:29,  1.37s/it]
 80%|███████▉  | 49233/61904 [2:47:27<4:45:49,  1.35s/it]
 80%|███████▉  | 49234/61904 [2:47:28<4:51:56,  1.38s/it]
 80%|███████▉  | 49235/61904 [2:47:30<4:54:02,  1.39s/it]
 80%|███████▉  | 49236/61904 [2:47:31<4:46:51,  1.36s/it]
 80%|███████▉  | 49237/61904 [2:47:32<5:05:15,  1.45s/it]
 80%|███████▉  | 49238/61904 [2:47:34<4:52:28,  1.39s/it]
 80%|███████▉  | 49239/61904 [2:47:35<4:49:01,  1.37s/it]
 80%|███████▉  | 49240/61904 [2:47:36<4:42:35,  1.34s/it]
                                                         
{'loss': 2.4702, 'learning_rate': 1.2052379100220407e-07, 'epoch': 12.73}
+
 80%|███████▉  | 49240/61904 [2:47:36<4:42:35,  1.34s/it]
 80%|███████▉  | 49241/61904 [2:47:38<4:38:07,  1.32s/it]
 80%|███████▉  | 49242/61904 [2:47:39<4:49:45,  1.37s/it]
 80%|███████▉  | 49243/61904 [2:47:40<4:42:28,  1.34s/it]
 80%|███████▉  | 49244/61904 [2:47:42<4:43:05,  1.34s/it]
 80%|███████▉  | 49245/61904 [2:47:43<4:45:33,  1.35s/it]
 80%|███████▉  | 49246/61904 [2:47:44<4:50:02,  1.37s/it]
 80%|███████▉  | 49247/61904 [2:47:46<4:49:05,  1.37s/it]
 80%|███████▉  | 49248/61904 [2:47:47<4:48:29,  1.37s/it]
 80%|███████▉  | 49249/61904 [2:47:49<4:49:25,  1.37s/it]
 80%|███████▉  | 49250/61904 [2:47:50<4:56:29,  1.41s/it]
 80%|███████▉  | 49251/61904 [2:47:51<4:43:25,  1.34s/it]
 80%|███████▉  | 49252/61904 [2:47:53<4:43:31,  1.34s/it]
 80%|███████▉  | 49253/61904 [2:47:54<4:50:18,  1.38s/it]
 80%|███████▉  | 49254/61904 [2:47:55<4:48:21,  1.37s/it]
 80%|███████▉  | 49255/61904 [2:47:57<4:44:53,  1.35s/it]
 80%|███████▉  | 49256/61904 [2:47:58<4:57:28,  1.41s/it]
 80%|███████▉  | 49257/61904 [2:48:00<4:49:11,  1.37s/it]
 80%|███████▉  | 49258/61904 [2:48:01<4:58:16,  1.42s/it]
 80%|███████▉  | 49259/61904 [2:48:02<4:50:06,  1.38s/it]
 80%|███████▉  | 49260/61904 [2:48:04<4:47:44,  1.37s/it]
                                                         
{'loss': 2.4585, 'learning_rate': 1.2049137819266173e-07, 'epoch': 12.73}
+
 80%|███████▉  | 49260/61904 [2:48:04<4:47:44,  1.37s/it]
 80%|███████▉  | 49261/61904 [2:48:05<4:47:46,  1.37s/it]
 80%|███████▉  | 49262/61904 [2:48:06<4:47:48,  1.37s/it]
 80%|███████▉  | 49263/61904 [2:48:08<4:47:20,  1.36s/it]
 80%|███████▉  | 49264/61904 [2:48:09<4:46:02,  1.36s/it]
 80%|███████▉  | 49265/61904 [2:48:11<4:59:48,  1.42s/it]
 80%|███████▉  | 49266/61904 [2:48:12<4:56:26,  1.41s/it]
 80%|███████▉  | 49267/61904 [2:48:13<4:48:32,  1.37s/it]
 80%|███████▉  | 49268/61904 [2:48:15<4:46:09,  1.36s/it]
 80%|███████▉  | 49269/61904 [2:48:16<4:46:13,  1.36s/it]
 80%|███████▉  | 49270/61904 [2:48:17<4:44:05,  1.35s/it]
 80%|███████▉  | 49271/61904 [2:48:19<4:48:44,  1.37s/it]
 80%|███████▉  | 49272/61904 [2:48:20<4:43:38,  1.35s/it]
 80%|███████▉  | 49273/61904 [2:48:22<5:05:08,  1.45s/it]
 80%|███████▉  | 49274/61904 [2:48:23<5:06:18,  1.46s/it]
 80%|███████▉  | 49275/61904 [2:48:25<5:03:59,  1.44s/it]
 80%|███████▉  | 49276/61904 [2:48:26<4:53:18,  1.39s/it]
 80%|███████▉  | 49277/61904 [2:48:27<4:46:45,  1.36s/it]
 80%|███████▉  | 49278/61904 [2:48:29<4:54:35,  1.40s/it]
 80%|███████▉  | 49279/61904 [2:48:30<4:57:49,  1.42s/it]
 80%|███████▉  | 49280/61904 [2:48:32<5:09:48,  1.47s/it]
                                                         
{'loss': 2.414, 'learning_rate': 1.204589653831194e-07, 'epoch': 12.74}
+
 80%|███████▉  | 49280/61904 [2:48:32<5:09:48,  1.47s/it]
 80%|███████▉  | 49281/61904 [2:48:33<5:05:37,  1.45s/it]
 80%|███████▉  | 49282/61904 [2:48:35<5:03:20,  1.44s/it]
 80%|███████▉  | 49283/61904 [2:48:36<4:53:57,  1.40s/it]
 80%|███████▉  | 49284/61904 [2:48:37<4:46:16,  1.36s/it]
 80%|███████▉  | 49285/61904 [2:48:38<4:43:36,  1.35s/it]
 80%|███████▉  | 49286/61904 [2:48:40<4:36:15,  1.31s/it]
 80%|███████▉  | 49287/61904 [2:48:41<4:51:37,  1.39s/it]
 80%|███████▉  | 49288/61904 [2:48:43<5:03:48,  1.44s/it]
 80%|███████▉  | 49289/61904 [2:48:44<5:04:04,  1.45s/it]
 80%|███████▉  | 49290/61904 [2:48:46<4:53:50,  1.40s/it]
 80%|███████▉  | 49291/61904 [2:48:47<4:47:30,  1.37s/it]
 80%|███████▉  | 49292/61904 [2:48:48<4:45:19,  1.36s/it]
 80%|███████▉  | 49293/61904 [2:48:50<4:57:05,  1.41s/it]
 80%|███████▉  | 49294/61904 [2:48:51<4:52:19,  1.39s/it]
 80%|███████▉  | 49295/61904 [2:48:52<4:48:22,  1.37s/it]
 80%|███████▉  | 49296/61904 [2:48:54<4:49:33,  1.38s/it]
 80%|███████▉  | 49297/61904 [2:48:55<4:53:44,  1.40s/it]
 80%|███████▉  | 49298/61904 [2:48:57<4:53:50,  1.40s/it]
 80%|███████▉  | 49299/61904 [2:48:58<4:57:55,  1.42s/it]
 80%|███████▉  | 49300/61904 [2:48:59<4:49:16,  1.38s/it]
                                                         
{'loss': 2.4743, 'learning_rate': 1.2042655257357706e-07, 'epoch': 12.74}
+
 80%|███████▉  | 49300/61904 [2:48:59<4:49:16,  1.38s/it]
 80%|███████▉  | 49301/61904 [2:49:01<4:46:52,  1.37s/it]
 80%|███████▉  | 49302/61904 [2:49:02<4:47:18,  1.37s/it]
 80%|███████▉  | 49303/61904 [2:49:04<4:50:22,  1.38s/it]
 80%|███████▉  | 49304/61904 [2:49:05<4:53:14,  1.40s/it]
 80%|███████▉  | 49305/61904 [2:49:06<4:40:36,  1.34s/it]
 80%|███████▉  | 49306/61904 [2:49:07<4:33:30,  1.30s/it]
 80%|███████▉  | 49307/61904 [2:49:09<4:41:46,  1.34s/it]
 80%|███████▉  | 49308/61904 [2:49:10<4:43:20,  1.35s/it]
 80%|███████▉  | 49309/61904 [2:49:12<4:45:38,  1.36s/it]
 80%|███████▉  | 49310/61904 [2:49:13<4:45:27,  1.36s/it]
 80%|███████▉  | 49311/61904 [2:49:14<4:44:32,  1.36s/it]
 80%|███████▉  | 49312/61904 [2:49:16<4:48:06,  1.37s/it]
 80%|███████▉  | 49313/61904 [2:49:17<4:48:05,  1.37s/it]
 80%|███████▉  | 49314/61904 [2:49:18<4:41:59,  1.34s/it]
 80%|███████▉  | 49315/61904 [2:49:20<4:42:00,  1.34s/it]
 80%|███████▉  | 49316/61904 [2:49:21<4:36:21,  1.32s/it]
 80%|███████▉  | 49317/61904 [2:49:22<4:35:25,  1.31s/it]
 80%|███████▉  | 49318/61904 [2:49:24<4:39:58,  1.33s/it]
 80%|███████▉  | 49319/61904 [2:49:25<4:38:46,  1.33s/it]
 80%|███████▉  | 49320/61904 [2:49:26<4:42:56,  1.35s/it]
                                                         
{'loss': 2.4963, 'learning_rate': 1.2039413976403474e-07, 'epoch': 12.75}
+
 80%|███████▉  | 49320/61904 [2:49:26<4:42:56,  1.35s/it]
 80%|███████▉  | 49321/61904 [2:49:28<4:46:47,  1.37s/it]
 80%|███████▉  | 49322/61904 [2:49:29<4:47:43,  1.37s/it]
 80%|███████▉  | 49323/61904 [2:49:30<4:47:33,  1.37s/it]
 80%|███████▉  | 49324/61904 [2:49:32<4:58:25,  1.42s/it]
 80%|███████▉  | 49325/61904 [2:49:33<4:50:21,  1.38s/it]
 80%|███████▉  | 49326/61904 [2:49:35<4:53:21,  1.40s/it]
 80%|███████▉  | 49327/61904 [2:49:36<4:51:13,  1.39s/it]
 80%|███████▉  | 49328/61904 [2:49:37<4:45:11,  1.36s/it]
 80%|███████▉  | 49329/61904 [2:49:39<4:43:55,  1.35s/it]
 80%|███████▉  | 49330/61904 [2:49:40<4:39:41,  1.33s/it]
 80%|███████▉  | 49331/61904 [2:49:41<4:43:02,  1.35s/it]
 80%|███████▉  | 49332/61904 [2:49:43<4:37:22,  1.32s/it]
 80%|███████▉  | 49333/61904 [2:49:44<4:34:40,  1.31s/it]
 80%|███████▉  | 49334/61904 [2:49:45<4:39:52,  1.34s/it]
 80%|███████▉  | 49335/61904 [2:49:47<4:45:56,  1.36s/it]
 80%|███████▉  | 49336/61904 [2:49:48<4:38:57,  1.33s/it]
 80%|███████▉  | 49337/61904 [2:49:49<4:37:37,  1.33s/it]
 80%|███████▉  | 49338/61904 [2:49:51<4:38:50,  1.33s/it]
 80%|███████▉  | 49339/61904 [2:49:52<4:49:02,  1.38s/it]
 80%|███████▉  | 49340/61904 [2:49:54<4:51:57,  1.39s/it]
                                                         
{'loss': 2.4157, 'learning_rate': 1.203617269544924e-07, 'epoch': 12.75}
+
 80%|███████▉  | 49340/61904 [2:49:54<4:51:57,  1.39s/it]
 80%|███████▉  | 49341/61904 [2:49:55<4:55:12,  1.41s/it]
 80%|███████▉  | 49342/61904 [2:49:56<4:42:08,  1.35s/it]
 80%|███████▉  | 49343/61904 [2:49:58<4:43:15,  1.35s/it]
 80%|███████▉  | 49344/61904 [2:49:59<4:43:39,  1.36s/it]
 80%|███████▉  | 49345/61904 [2:50:00<4:45:03,  1.36s/it]
 80%|███████▉  | 49346/61904 [2:50:02<4:47:04,  1.37s/it]
 80%|███████▉  | 49347/61904 [2:50:03<4:46:01,  1.37s/it]
 80%|███████▉  | 49348/61904 [2:50:05<4:47:58,  1.38s/it]
 80%|███████▉  | 49349/61904 [2:50:06<4:43:14,  1.35s/it]
 80%|███████▉  | 49350/61904 [2:50:07<4:52:52,  1.40s/it]
 80%|███████▉  | 49351/61904 [2:50:09<4:44:41,  1.36s/it]
 80%|███████▉  | 49352/61904 [2:50:10<4:39:09,  1.33s/it]
 80%|███████▉  | 49353/61904 [2:50:11<4:43:02,  1.35s/it]
 80%|███████▉  | 49354/61904 [2:50:13<4:47:04,  1.37s/it]
 80%|███████▉  | 49355/61904 [2:50:14<4:41:41,  1.35s/it]
 80%|███████▉  | 49356/61904 [2:50:15<4:42:47,  1.35s/it]
 80%|███████▉  | 49357/61904 [2:50:17<4:44:43,  1.36s/it]
 80%|███████▉  | 49358/61904 [2:50:18<4:43:40,  1.36s/it]
 80%|███████▉  | 49359/61904 [2:50:19<4:43:48,  1.36s/it]
 80%|███████▉  | 49360/61904 [2:50:21<4:40:41,  1.34s/it]
                                                         
{'loss': 2.4355, 'learning_rate': 1.2032931414495007e-07, 'epoch': 12.76}
+
 80%|███████▉  | 49360/61904 [2:50:21<4:40:41,  1.34s/it]
 80%|███████▉  | 49361/61904 [2:50:22<4:39:44,  1.34s/it]
 80%|███████▉  | 49362/61904 [2:50:23<4:35:52,  1.32s/it]
 80%|███████▉  | 49363/61904 [2:50:25<4:39:22,  1.34s/it]
 80%|███████▉  | 49364/61904 [2:50:26<4:41:40,  1.35s/it]
 80%|███████▉  | 49365/61904 [2:50:27<4:43:54,  1.36s/it]
 80%|███████▉  | 49366/61904 [2:50:29<4:44:34,  1.36s/it]
 80%|███████▉  | 49367/61904 [2:50:30<4:48:39,  1.38s/it]
 80%|███████▉  | 49368/61904 [2:50:32<4:46:35,  1.37s/it]
 80%|███████▉  | 49369/61904 [2:50:33<4:43:03,  1.35s/it]
 80%|███████▉  | 49370/61904 [2:50:34<4:37:08,  1.33s/it]
 80%|███████▉  | 49371/61904 [2:50:36<4:40:39,  1.34s/it]
 80%|███████▉  | 49372/61904 [2:50:37<4:48:58,  1.38s/it]
 80%|███████▉  | 49373/61904 [2:50:38<4:45:55,  1.37s/it]
 80%|███████▉  | 49374/61904 [2:50:40<4:39:31,  1.34s/it]
 80%|███████▉  | 49375/61904 [2:50:41<4:39:01,  1.34s/it]
 80%|███████▉  | 49376/61904 [2:50:42<4:37:35,  1.33s/it]
 80%|███████▉  | 49377/61904 [2:50:44<4:38:23,  1.33s/it]
 80%|███████▉  | 49378/61904 [2:50:45<4:50:19,  1.39s/it]
 80%|███████▉  | 49379/61904 [2:50:47<4:49:27,  1.39s/it]
 80%|███████▉  | 49380/61904 [2:50:48<4:56:40,  1.42s/it]
                                                         
{'loss': 2.4174, 'learning_rate': 1.2029690133540776e-07, 'epoch': 12.76}
+
 80%|███████▉  | 49380/61904 [2:50:48<4:56:40,  1.42s/it]
 80%|███████▉  | 49381/61904 [2:50:49<4:56:13,  1.42s/it]
 80%|███████▉  | 49382/61904 [2:50:51<5:09:34,  1.48s/it]
 80%|███████▉  | 49383/61904 [2:50:52<4:58:07,  1.43s/it]
 80%|███████▉  | 49384/61904 [2:50:54<4:58:51,  1.43s/it]
 80%|███████▉  | 49385/61904 [2:50:55<4:47:59,  1.38s/it]
 80%|███████▉  | 49386/61904 [2:50:57<4:56:55,  1.42s/it]
 80%|███████▉  | 49387/61904 [2:50:58<5:00:55,  1.44s/it]
 80%|███████▉  | 49388/61904 [2:50:59<4:52:51,  1.40s/it]
 80%|███████▉  | 49389/61904 [2:51:01<4:56:24,  1.42s/it]
 80%|███████▉  | 49390/61904 [2:51:02<4:51:16,  1.40s/it]
 80%|███████▉  | 49391/61904 [2:51:04<5:07:11,  1.47s/it]
 80%|███████▉  | 49392/61904 [2:51:05<4:59:04,  1.43s/it]
 80%|███████▉  | 49393/61904 [2:51:07<5:05:32,  1.47s/it]
 80%|███████▉  | 49394/61904 [2:51:08<5:06:30,  1.47s/it]
 80%|███████▉  | 49395/61904 [2:51:10<4:56:31,  1.42s/it]
 80%|███████▉  | 49396/61904 [2:51:11<4:53:49,  1.41s/it]
 80%|███████▉  | 49397/61904 [2:51:13<5:04:48,  1.46s/it]
 80%|███████▉  | 49398/61904 [2:51:14<4:54:56,  1.42s/it]
 80%|███████▉  | 49399/61904 [2:51:15<4:50:27,  1.39s/it]
 80%|███████▉  | 49400/61904 [2:51:17<5:07:21,  1.47s/it]
                                                         
{'loss': 2.4903, 'learning_rate': 1.2026448852586542e-07, 'epoch': 12.77}
+
 80%|███████▉  | 49400/61904 [2:51:17<5:07:21,  1.47s/it]
 80%|███████▉  | 49401/61904 [2:51:18<5:01:19,  1.45s/it]
 80%|███████▉  | 49402/61904 [2:51:20<5:15:07,  1.51s/it]
 80%|███████▉  | 49403/61904 [2:51:21<5:10:56,  1.49s/it]
 80%|███████▉  | 49404/61904 [2:51:23<5:07:46,  1.48s/it]
 80%|███████▉  | 49405/61904 [2:51:24<4:57:07,  1.43s/it]
 80%|███████▉  | 49406/61904 [2:51:26<4:58:14,  1.43s/it]
 80%|███████▉  | 49407/61904 [2:51:27<4:44:39,  1.37s/it]
 80%|███████▉  | 49408/61904 [2:51:28<4:37:13,  1.33s/it]
 80%|███████▉  | 49409/61904 [2:51:29<4:36:09,  1.33s/it]
 80%|███████▉  | 49410/61904 [2:51:31<4:38:25,  1.34s/it]
 80%|███████▉  | 49411/61904 [2:51:32<4:35:36,  1.32s/it]
 80%|███████▉  | 49412/61904 [2:51:33<4:35:53,  1.33s/it]
 80%|███████▉  | 49413/61904 [2:51:35<4:42:29,  1.36s/it]
 80%|███████▉  | 49414/61904 [2:51:36<4:40:09,  1.35s/it]
 80%|███████▉  | 49415/61904 [2:51:37<4:35:20,  1.32s/it]
 80%|███████▉  | 49416/61904 [2:51:39<4:45:57,  1.37s/it]
 80%|███████▉  | 49417/61904 [2:51:40<4:47:56,  1.38s/it]
 80%|███████▉  | 49418/61904 [2:51:41<4:41:00,  1.35s/it]
 80%|███████▉  | 49419/61904 [2:51:43<4:44:16,  1.37s/it]
 80%|███████▉  | 49420/61904 [2:51:44<4:40:23,  1.35s/it]
                                                         
{'loss': 2.4285, 'learning_rate': 1.2023207571632308e-07, 'epoch': 12.77}
+
 80%|███████▉  | 49420/61904 [2:51:44<4:40:23,  1.35s/it]
 80%|███████▉  | 49421/61904 [2:51:45<4:35:11,  1.32s/it]
 80%|███████▉  | 49422/61904 [2:51:47<4:32:00,  1.31s/it]
 80%|███████▉  | 49423/61904 [2:51:48<4:44:28,  1.37s/it]
 80%|███████▉  | 49424/61904 [2:51:50<4:43:39,  1.36s/it]
 80%|███████▉  | 49425/61904 [2:51:51<4:45:39,  1.37s/it]
 80%|███████▉  | 49426/61904 [2:51:52<4:47:12,  1.38s/it]
 80%|███████▉  | 49427/61904 [2:51:54<4:48:20,  1.39s/it]
 80%|███████▉  | 49428/61904 [2:51:55<4:37:25,  1.33s/it]
 80%|███████▉  | 49429/61904 [2:51:56<4:35:37,  1.33s/it]
 80%|███████▉  | 49430/61904 [2:51:58<4:30:41,  1.30s/it]
 80%|███████▉  | 49431/61904 [2:51:59<4:45:00,  1.37s/it]
 80%|███████▉  | 49432/61904 [2:52:01<4:48:54,  1.39s/it]
 80%|███████▉  | 49433/61904 [2:52:02<4:43:22,  1.36s/it]
 80%|███████▉  | 49434/61904 [2:52:03<4:47:13,  1.38s/it]
 80%|███████▉  | 49435/61904 [2:52:05<4:41:50,  1.36s/it]
 80%|███████▉  | 49436/61904 [2:52:06<4:54:24,  1.42s/it]
 80%|███████▉  | 49437/61904 [2:52:07<4:51:28,  1.40s/it]
 80%|███████▉  | 49438/61904 [2:52:09<4:52:25,  1.41s/it]
 80%|███████▉  | 49439/61904 [2:52:10<4:49:01,  1.39s/it]
 80%|███████▉  | 49440/61904 [2:52:12<4:52:14,  1.41s/it]
                                                         
{'loss': 2.5139, 'learning_rate': 1.2019966290678074e-07, 'epoch': 12.78}
+
 80%|███████▉  | 49440/61904 [2:52:12<4:52:14,  1.41s/it]
 80%|███████▉  | 49441/61904 [2:52:13<5:01:09,  1.45s/it]
 80%|███████▉  | 49442/61904 [2:52:15<5:01:07,  1.45s/it]
 80%|███████▉  | 49443/61904 [2:52:16<5:01:45,  1.45s/it]
 80%|███████▉  | 49444/61904 [2:52:17<4:52:33,  1.41s/it]
 80%|███████▉  | 49445/61904 [2:52:19<4:51:04,  1.40s/it]
 80%|███████▉  | 49446/61904 [2:52:20<4:55:38,  1.42s/it]
 80%|███████▉  | 49447/61904 [2:52:22<4:57:21,  1.43s/it]
 80%|███████▉  | 49448/61904 [2:52:23<4:45:37,  1.38s/it]
 80%|███████▉  | 49449/61904 [2:52:24<4:41:08,  1.35s/it]
 80%|███████▉  | 49450/61904 [2:52:26<4:39:14,  1.35s/it]
 80%|███████▉  | 49451/61904 [2:52:27<4:40:24,  1.35s/it]
 80%|███████▉  | 49452/61904 [2:52:28<4:41:49,  1.36s/it]
 80%|███████▉  | 49453/61904 [2:52:30<4:38:14,  1.34s/it]
 80%|███████▉  | 49454/61904 [2:52:31<4:27:21,  1.29s/it]
 80%|███████▉  | 49455/61904 [2:52:32<4:24:42,  1.28s/it]
 80%|███████▉  | 49456/61904 [2:52:33<4:26:48,  1.29s/it]
 80%|███████▉  | 49457/61904 [2:52:35<4:45:44,  1.38s/it]
 80%|███████▉  | 49458/61904 [2:52:36<4:46:04,  1.38s/it]
 80%|███████▉  | 49459/61904 [2:52:38<4:42:21,  1.36s/it]
 80%|███████▉  | 49460/61904 [2:52:39<4:36:53,  1.34s/it]
                                                         
{'loss': 2.4306, 'learning_rate': 1.2016725009723843e-07, 'epoch': 12.78}
+
 80%|███████▉  | 49460/61904 [2:52:39<4:36:53,  1.34s/it]
 80%|███████▉  | 49461/61904 [2:52:40<4:44:05,  1.37s/it]
 80%|███████▉  | 49462/61904 [2:52:42<4:44:17,  1.37s/it]
 80%|███████▉  | 49463/61904 [2:52:44<5:09:30,  1.49s/it]
 80%|███████▉  | 49464/61904 [2:52:45<5:02:35,  1.46s/it]
 80%|███████▉  | 49465/61904 [2:52:46<5:01:14,  1.45s/it]
 80%|███████▉  | 49466/61904 [2:52:48<4:46:28,  1.38s/it]
 80%|███████▉  | 49467/61904 [2:52:49<4:45:08,  1.38s/it]
 80%|███████▉  | 49468/61904 [2:52:50<4:47:47,  1.39s/it]
 80%|███████▉  | 49469/61904 [2:52:52<4:42:22,  1.36s/it]
 80%|███████▉  | 49470/61904 [2:52:53<4:42:59,  1.37s/it]
 80%|███████▉  | 49471/61904 [2:52:54<4:41:02,  1.36s/it]
 80%|███████▉  | 49472/61904 [2:52:56<4:38:11,  1.34s/it]
 80%|███████▉  | 49473/61904 [2:52:57<4:35:40,  1.33s/it]
 80%|███████▉  | 49474/61904 [2:52:58<4:43:07,  1.37s/it]
 80%|███████▉  | 49475/61904 [2:53:00<4:47:58,  1.39s/it]
 80%|███████▉  | 49476/61904 [2:53:01<4:40:27,  1.35s/it]
 80%|███████▉  | 49477/61904 [2:53:03<4:40:58,  1.36s/it]
 80%|███████▉  | 49478/61904 [2:53:04<4:46:04,  1.38s/it]
 80%|███████▉  | 49479/61904 [2:53:05<4:47:05,  1.39s/it]
 80%|███████▉  | 49480/61904 [2:53:07<4:48:37,  1.39s/it]
                                                         
{'loss': 2.4208, 'learning_rate': 1.201348372876961e-07, 'epoch': 12.79}
+
 80%|███████▉  | 49480/61904 [2:53:07<4:48:37,  1.39s/it]
 80%|███████▉  | 49481/61904 [2:53:08<4:51:29,  1.41s/it]
 80%|███████▉  | 49482/61904 [2:53:10<4:59:10,  1.45s/it]
 80%|███████▉  | 49483/61904 [2:53:11<5:08:24,  1.49s/it]
 80%|███████▉  | 49484/61904 [2:53:13<5:13:14,  1.51s/it]
 80%|███████▉  | 49485/61904 [2:53:15<5:20:10,  1.55s/it]
 80%|███████▉  | 49486/61904 [2:53:16<5:01:54,  1.46s/it]
 80%|███████▉  | 49487/61904 [2:53:17<4:56:44,  1.43s/it]
 80%|███████▉  | 49488/61904 [2:53:18<4:44:55,  1.38s/it]
 80%|███████▉  | 49489/61904 [2:53:20<5:02:46,  1.46s/it]
 80%|███████▉  | 49490/61904 [2:53:22<5:00:57,  1.45s/it]
 80%|███████▉  | 49491/61904 [2:53:23<4:56:56,  1.44s/it]
 80%|███████▉  | 49492/61904 [2:53:24<5:02:10,  1.46s/it]
 80%|███████▉  | 49493/61904 [2:53:26<4:56:20,  1.43s/it]
 80%|███████▉  | 49494/61904 [2:53:27<4:51:19,  1.41s/it]
 80%|███████▉  | 49495/61904 [2:53:28<4:48:01,  1.39s/it]
 80%|███████▉  | 49496/61904 [2:53:30<4:45:11,  1.38s/it]
 80%|███████▉  | 49497/61904 [2:53:31<4:42:05,  1.36s/it]
 80%|███████▉  | 49498/61904 [2:53:33<4:46:26,  1.39s/it]
 80%|███████▉  | 49499/61904 [2:53:34<4:50:34,  1.41s/it]
 80%|███████▉  | 49500/61904 [2:53:35<4:50:00,  1.40s/it]
                                                         
{'loss': 2.4154, 'learning_rate': 1.2010242447815375e-07, 'epoch': 12.79}
+
 80%|███████▉  | 49500/61904 [2:53:35<4:50:00,  1.40s/it]
 80%|███████▉  | 49501/61904 [2:53:37<4:52:24,  1.41s/it]
 80%|███████▉  | 49502/61904 [2:53:38<4:46:21,  1.39s/it]
 80%|███████▉  | 49503/61904 [2:53:40<4:43:50,  1.37s/it]
 80%|███████▉  | 49504/61904 [2:53:41<4:41:10,  1.36s/it]
 80%|███████▉  | 49505/61904 [2:53:42<4:46:06,  1.38s/it]
 80%|███████▉  | 49506/61904 [2:53:44<4:42:06,  1.37s/it]
 80%|███████▉  | 49507/61904 [2:53:45<4:43:24,  1.37s/it]
 80%|███████▉  | 49508/61904 [2:53:47<4:55:05,  1.43s/it]
 80%|███████▉  | 49509/61904 [2:53:48<4:48:52,  1.40s/it]
 80%|███████▉  | 49510/61904 [2:53:49<4:51:54,  1.41s/it]
 80%|███████▉  | 49511/61904 [2:53:51<4:46:43,  1.39s/it]
 80%|███████▉  | 49512/61904 [2:53:52<4:39:53,  1.36s/it]
 80%|███████▉  | 49513/61904 [2:53:53<4:42:02,  1.37s/it]
 80%|███████▉  | 49514/61904 [2:53:55<4:49:44,  1.40s/it]
 80%|███████▉  | 49515/61904 [2:53:56<4:42:45,  1.37s/it]
 80%|███████▉  | 49516/61904 [2:53:57<4:34:57,  1.33s/it]
 80%|███████▉  | 49517/61904 [2:53:59<4:33:43,  1.33s/it]
 80%|███████▉  | 49518/61904 [2:54:00<4:44:19,  1.38s/it]
 80%|███████▉  | 49519/61904 [2:54:02<4:41:51,  1.37s/it]
 80%|███████▉  | 49520/61904 [2:54:03<4:35:38,  1.34s/it]
                                                         
{'loss': 2.4862, 'learning_rate': 1.2007001166861142e-07, 'epoch': 12.8}
+
 80%|███████▉  | 49520/61904 [2:54:03<4:35:38,  1.34s/it]
 80%|███████▉  | 49521/61904 [2:54:04<4:34:29,  1.33s/it]
 80%|███████▉  | 49522/61904 [2:54:05<4:33:25,  1.32s/it]
 80%|███████▉  | 49523/61904 [2:54:07<4:40:29,  1.36s/it]
 80%|████████  | 49524/61904 [2:54:08<4:36:14,  1.34s/it]
 80%|████████  | 49525/61904 [2:54:09<4:25:22,  1.29s/it]
 80%|████████  | 49526/61904 [2:54:11<4:24:38,  1.28s/it]
 80%|████████  | 49527/61904 [2:54:12<4:30:46,  1.31s/it]
 80%|████████  | 49528/61904 [2:54:13<4:28:27,  1.30s/it]
 80%|████████  | 49529/61904 [2:54:15<4:26:30,  1.29s/it]
 80%|████████  | 49530/61904 [2:54:16<4:28:43,  1.30s/it]
 80%|████████  | 49531/61904 [2:54:17<4:44:11,  1.38s/it]
 80%|████████  | 49532/61904 [2:54:19<4:50:13,  1.41s/it]
 80%|████████  | 49533/61904 [2:54:20<4:45:46,  1.39s/it]
 80%|████████  | 49534/61904 [2:54:22<4:48:55,  1.40s/it]
 80%|████████  | 49535/61904 [2:54:23<4:44:15,  1.38s/it]
 80%|████████  | 49536/61904 [2:54:24<4:43:06,  1.37s/it]
 80%|████████  | 49537/61904 [2:54:26<4:39:19,  1.36s/it]
 80%|████████  | 49538/61904 [2:54:27<4:34:53,  1.33s/it]
 80%|████████  | 49539/61904 [2:54:28<4:29:39,  1.31s/it]
 80%|████████  | 49540/61904 [2:54:30<4:30:23,  1.31s/it]
                                                         
{'loss': 2.4184, 'learning_rate': 1.200375988590691e-07, 'epoch': 12.8}
+
 80%|████████  | 49540/61904 [2:54:30<4:30:23,  1.31s/it]
 80%|████████  | 49541/61904 [2:54:31<4:33:16,  1.33s/it]
 80%|████████  | 49542/61904 [2:54:32<4:40:03,  1.36s/it]
 80%|████████  | 49543/61904 [2:54:34<4:35:08,  1.34s/it]
 80%|████████  | 49544/61904 [2:54:35<4:43:43,  1.38s/it]
 80%|████████  | 49545/61904 [2:54:36<4:45:08,  1.38s/it]
 80%|████████  | 49546/61904 [2:54:38<4:50:59,  1.41s/it]
 80%|████████  | 49547/61904 [2:54:39<4:48:10,  1.40s/it]
 80%|████████  | 49548/61904 [2:54:41<4:49:44,  1.41s/it]
 80%|████████  | 49549/61904 [2:54:42<4:44:39,  1.38s/it]
 80%|████████  | 49550/61904 [2:54:44<4:55:12,  1.43s/it]
 80%|████████  | 49551/61904 [2:54:45<5:07:06,  1.49s/it]
 80%|████████  | 49552/61904 [2:54:47<4:55:43,  1.44s/it]
 80%|████████  | 49553/61904 [2:54:48<4:52:43,  1.42s/it]
 80%|████████  | 49554/61904 [2:54:49<4:53:09,  1.42s/it]
 80%|████████  | 49555/61904 [2:54:51<4:53:01,  1.42s/it]
 80%|████████  | 49556/61904 [2:54:52<4:44:32,  1.38s/it]
 80%|████████  | 49557/61904 [2:54:53<4:41:44,  1.37s/it]
 80%|████████  | 49558/61904 [2:54:55<4:38:52,  1.36s/it]
 80%|████████  | 49559/61904 [2:54:56<4:39:50,  1.36s/it]
 80%|████████  | 49560/61904 [2:54:57<4:38:31,  1.35s/it]
                                                         
{'loss': 2.374, 'learning_rate': 1.2000518604952677e-07, 'epoch': 12.81}
+
 80%|████████  | 49560/61904 [2:54:57<4:38:31,  1.35s/it]
 80%|████████  | 49561/61904 [2:54:59<4:41:59,  1.37s/it]
 80%|████████  | 49562/61904 [2:55:00<4:42:34,  1.37s/it]
 80%|████████  | 49563/61904 [2:55:02<4:49:39,  1.41s/it]
 80%|████████  | 49564/61904 [2:55:03<4:49:52,  1.41s/it]
 80%|████████  | 49565/61904 [2:55:05<4:51:09,  1.42s/it]
 80%|████████  | 49566/61904 [2:55:06<4:45:05,  1.39s/it]
 80%|████████  | 49567/61904 [2:55:07<4:49:12,  1.41s/it]
 80%|████████  | 49568/61904 [2:55:09<4:43:52,  1.38s/it]
 80%|████████  | 49569/61904 [2:55:10<4:45:11,  1.39s/it]
 80%|████████  | 49570/61904 [2:55:11<4:40:42,  1.37s/it]
 80%|████████  | 49571/61904 [2:55:13<4:43:48,  1.38s/it]
 80%|████████  | 49572/61904 [2:55:14<4:38:26,  1.35s/it]
 80%|████████  | 49573/61904 [2:55:16<4:44:06,  1.38s/it]
 80%|████████  | 49574/61904 [2:55:17<4:41:57,  1.37s/it]
 80%|████████  | 49575/61904 [2:55:18<4:41:26,  1.37s/it]
 80%|████████  | 49576/61904 [2:55:20<4:37:22,  1.35s/it]
 80%|████████  | 49577/61904 [2:55:21<4:42:00,  1.37s/it]
 80%|███████��  | 49578/61904 [2:55:22<4:43:07,  1.38s/it]
 80%|████████  | 49579/61904 [2:55:24<4:48:41,  1.41s/it]
 80%|████████  | 49580/61904 [2:55:25<4:51:28,  1.42s/it]
                                                         
{'loss': 2.4885, 'learning_rate': 1.1997277323998443e-07, 'epoch': 12.81}
+
 80%|████████  | 49580/61904 [2:55:25<4:51:28,  1.42s/it]
 80%|████████  | 49581/61904 [2:55:27<4:48:49,  1.41s/it]
 80%|████████  | 49582/61904 [2:55:28<4:41:01,  1.37s/it]
 80%|████████  | 49583/61904 [2:55:29<4:43:27,  1.38s/it]
 80%|████████  | 49584/61904 [2:55:31<4:54:11,  1.43s/it]
 80%|████████  | 49585/61904 [2:55:32<4:42:42,  1.38s/it]
 80%|████████  | 49586/61904 [2:55:34<4:45:38,  1.39s/it]
 80%|████████  | 49587/61904 [2:55:35<4:51:55,  1.42s/it]
 80%|████████  | 49588/61904 [2:55:36<4:49:12,  1.41s/it]
 80%|████████  | 49589/61904 [2:55:38<4:53:20,  1.43s/it]
 80%|████████  | 49590/61904 [2:55:39<4:45:59,  1.39s/it]
 80%|████████  | 49591/61904 [2:55:41<4:42:17,  1.38s/it]
 80%|████████  | 49592/61904 [2:55:42<4:33:47,  1.33s/it]
 80%|████████  | 49593/61904 [2:55:43<4:31:39,  1.32s/it]
 80%|████████  | 49594/61904 [2:55:45<4:39:44,  1.36s/it]
 80%|████████  | 49595/61904 [2:55:46<4:41:00,  1.37s/it]
 80%|████████  | 49596/61904 [2:55:47<4:42:17,  1.38s/it]
 80%|████████  | 49597/61904 [2:55:49<4:49:00,  1.41s/it]
 80%|████████  | 49598/61904 [2:55:50<4:49:40,  1.41s/it]
 80%|████████  | 49599/61904 [2:55:52<4:42:48,  1.38s/it]
 80%|████████  | 49600/61904 [2:55:53<4:51:57,  1.42s/it]
                                                         
{'loss': 2.4429, 'learning_rate': 1.199403604304421e-07, 'epoch': 12.82}
+
 80%|████████  | 49600/61904 [2:55:53<4:51:57,  1.42s/it]
 80%|████████  | 49601/61904 [2:55:55<5:01:58,  1.47s/it]
 80%|████████  | 49602/61904 [2:55:56<4:58:08,  1.45s/it]
 80%|████████  | 49603/61904 [2:55:57<4:48:14,  1.41s/it]
 80%|████████  | 49604/61904 [2:55:59<4:49:36,  1.41s/it]
 80%|████████  | 49605/61904 [2:56:00<4:48:37,  1.41s/it]
 80%|████████  | 49606/61904 [2:56:02<4:44:52,  1.39s/it]
 80%|████████  | 49607/61904 [2:56:03<4:51:44,  1.42s/it]
 80%|████████  | 49608/61904 [2:56:04<4:41:00,  1.37s/it]
 80%|████████  | 49609/61904 [2:56:06<4:44:00,  1.39s/it]
 80%|████████  | 49610/61904 [2:56:07<4:44:26,  1.39s/it]
 80%|████████  | 49611/61904 [2:56:09<4:49:46,  1.41s/it]
 80%|████████  | 49612/61904 [2:56:10<4:47:19,  1.40s/it]
 80%|████████  | 49613/61904 [2:56:11<4:41:52,  1.38s/it]
 80%|████████  | 49614/61904 [2:56:13<4:44:49,  1.39s/it]
 80%|████████  | 49615/61904 [2:56:14<4:52:34,  1.43s/it]
 80%|████████  | 49616/61904 [2:56:16<4:43:56,  1.39s/it]
 80%|████████  | 49617/61904 [2:56:17<4:44:59,  1.39s/it]
 80%|████████  | 49618/61904 [2:56:18<4:48:19,  1.41s/it]
 80%|████████  | 49619/61904 [2:56:20<4:39:35,  1.37s/it]
 80%|████████  | 49620/61904 [2:56:21<4:40:32,  1.37s/it]
                                                         
{'loss': 2.3834, 'learning_rate': 1.1990794762089978e-07, 'epoch': 12.82}
+
 80%|████████  | 49620/61904 [2:56:21<4:40:32,  1.37s/it]
 80%|████████  | 49621/61904 [2:56:22<4:42:46,  1.38s/it]
 80%|████████  | 49622/61904 [2:56:24<4:46:25,  1.40s/it]
 80%|████████  | 49623/61904 [2:56:25<4:49:53,  1.42s/it]
 80%|████████  | 49624/61904 [2:56:27<4:42:00,  1.38s/it]
 80%|████████  | 49625/61904 [2:56:28<4:36:22,  1.35s/it]
 80%|████████  | 49626/61904 [2:56:29<4:31:31,  1.33s/it]
 80%|████████  | 49627/61904 [2:56:31<4:33:26,  1.34s/it]
 80%|████████  | 49628/61904 [2:56:32<4:42:51,  1.38s/it]
 80%|████████  | 49629/61904 [2:56:33<4:36:25,  1.35s/it]
 80%|████████  | 49630/61904 [2:56:35<4:36:38,  1.35s/it]
 80%|████████  | 49631/61904 [2:56:36<4:42:19,  1.38s/it]
 80%|████████  | 49632/61904 [2:56:38<4:55:19,  1.44s/it]
 80%|████████  | 49633/61904 [2:56:39<4:44:30,  1.39s/it]
 80%|████████  | 49634/61904 [2:56:40<4:51:36,  1.43s/it]
 80%|████████  | 49635/61904 [2:56:42<4:50:15,  1.42s/it]
 80%|████████  | 49636/61904 [2:56:43<4:44:03,  1.39s/it]
 80%|████████  | 49637/61904 [2:56:45<4:40:58,  1.37s/it]
 80%|████████  | 49638/61904 [2:56:46<4:57:17,  1.45s/it]
 80%|████████  | 49639/61904 [2:56:47<4:46:50,  1.40s/it]
 80%|████████  | 49640/61904 [2:56:49<4:50:29,  1.42s/it]
                                                         
{'loss': 2.415, 'learning_rate': 1.1987553481135744e-07, 'epoch': 12.83}
+
 80%|████████  | 49640/61904 [2:56:49<4:50:29,  1.42s/it]
 80%|████████  | 49641/61904 [2:56:50<4:35:37,  1.35s/it]
 80%|████████  | 49642/61904 [2:56:52<4:42:25,  1.38s/it]
 80%|████████  | 49643/61904 [2:56:53<4:43:17,  1.39s/it]
 80%|████████  | 49644/61904 [2:56:54<4:33:10,  1.34s/it]
 80%|████████  | 49645/61904 [2:56:55<4:28:25,  1.31s/it]
 80%|████████  | 49646/61904 [2:56:57<4:34:11,  1.34s/it]
 80%|████████  | 49647/61904 [2:56:58<4:38:06,  1.36s/it]
 80%|████████  | 49648/61904 [2:57:00<4:42:55,  1.39s/it]
 80%|████████  | 49649/61904 [2:57:01<4:34:34,  1.34s/it]
 80%|████████  | 49650/61904 [2:57:02<4:35:52,  1.35s/it]
 80%|████████  | 49651/61904 [2:57:04<4:44:35,  1.39s/it]
 80%|████████  | 49652/61904 [2:57:05<4:43:36,  1.39s/it]
 80%|████████  | 49653/61904 [2:57:07<4:53:01,  1.44s/it]
 80%|████████  | 49654/61904 [2:57:08<4:46:09,  1.40s/it]
 80%|████████  | 49655/61904 [2:57:09<4:38:27,  1.36s/it]
 80%|████████  | 49656/61904 [2:57:11<4:30:37,  1.33s/it]
 80%|████████  | 49657/61904 [2:57:12<4:30:31,  1.33s/it]
 80%|████████  | 49658/61904 [2:57:13<4:28:25,  1.32s/it]
 80%|████████  | 49659/61904 [2:57:15<4:30:20,  1.32s/it]
 80%|████████  | 49660/61904 [2:57:16<4:29:24,  1.32s/it]
                                                         
{'loss': 2.5206, 'learning_rate': 1.198431220018151e-07, 'epoch': 12.84}
+
 80%|████████  | 49660/61904 [2:57:16<4:29:24,  1.32s/it]
 80%|████████  | 49661/61904 [2:57:17<4:26:28,  1.31s/it]
 80%|████████  | 49662/61904 [2:57:18<4:27:12,  1.31s/it]
 80%|████████  | 49663/61904 [2:57:20<4:32:51,  1.34s/it]
 80%|████████  | 49664/61904 [2:57:21<4:33:41,  1.34s/it]
 80%|████████  | 49665/61904 [2:57:22<4:30:34,  1.33s/it]
 80%|████████  | 49666/61904 [2:57:24<4:31:22,  1.33s/it]
 80%|████████  | 49667/61904 [2:57:25<4:34:22,  1.35s/it]
 80%|████████  | 49668/61904 [2:57:27<4:39:12,  1.37s/it]
 80%|████████  | 49669/61904 [2:57:28<4:43:01,  1.39s/it]
 80%|████████  | 49670/61904 [2:57:30<4:49:23,  1.42s/it]
 80%|████████  | 49671/61904 [2:57:31<4:48:08,  1.41s/it]
 80%|████████  | 49672/61904 [2:57:32<4:42:46,  1.39s/it]
 80%|████████  | 49673/61904 [2:57:34<4:42:27,  1.39s/it]
 80%|████████  | 49674/61904 [2:57:35<4:37:03,  1.36s/it]
 80%|████████  | 49675/61904 [2:57:36<4:38:11,  1.36s/it]
 80%|████████  | 49676/61904 [2:57:38<4:33:55,  1.34s/it]
 80%|████████  | 49677/61904 [2:57:39<4:28:31,  1.32s/it]
 80%|████████  | 49678/61904 [2:57:40<4:32:32,  1.34s/it]
 80%|████████  | 49679/61904 [2:57:42<4:30:33,  1.33s/it]
 80%|████████  | 49680/61904 [2:57:43<4:27:47,  1.31s/it]
                                                         
{'loss': 2.4883, 'learning_rate': 1.198107091922728e-07, 'epoch': 12.84}
+
 80%|████████  | 49680/61904 [2:57:43<4:27:47,  1.31s/it]
 80%|████████  | 49681/61904 [2:57:44<4:29:36,  1.32s/it]
 80%|████████  | 49682/61904 [2:57:46<4:41:30,  1.38s/it]
 80%|████████  | 49683/61904 [2:57:47<4:40:39,  1.38s/it]
 80%|████████  | 49684/61904 [2:57:48<4:37:34,  1.36s/it]
 80%|████████  | 49685/61904 [2:57:50<4:40:55,  1.38s/it]
 80%|████████  | 49686/61904 [2:57:51<4:32:51,  1.34s/it]
 80%|████████  | 49687/61904 [2:57:52<4:35:32,  1.35s/it]
 80%|████████  | 49688/61904 [2:57:54<4:34:08,  1.35s/it]
 80%|████████  | 49689/61904 [2:57:55<4:37:51,  1.36s/it]
 80%|████████  | 49690/61904 [2:57:56<4:32:03,  1.34s/it]
 80%|████████  | 49691/61904 [2:57:58<4:43:16,  1.39s/it]
 80%|████████  | 49692/61904 [2:57:59<4:37:34,  1.36s/it]
 80%|████████  | 49693/61904 [2:58:01<4:47:31,  1.41s/it]
 80%|████████  | 49694/61904 [2:58:02<4:40:31,  1.38s/it]
 80%|████████  | 49695/61904 [2:58:04<4:50:04,  1.43s/it]
 80%|████████  | 49696/61904 [2:58:05<4:44:13,  1.40s/it]
 80%|████████  | 49697/61904 [2:58:06<4:45:16,  1.40s/it]
 80%|████████  | 49698/61904 [2:58:08<4:41:43,  1.38s/it]
 80%|████████  | 49699/61904 [2:58:09<4:42:07,  1.39s/it]
 80%|████████  | 49700/61904 [2:58:10<4:37:21,  1.36s/it]
                                                         
{'loss': 2.4729, 'learning_rate': 1.1977829638273045e-07, 'epoch': 12.85}
+
 80%|████████  | 49700/61904 [2:58:10<4:37:21,  1.36s/it]
 80%|████████  | 49701/61904 [2:58:12<4:31:10,  1.33s/it]
 80%|████████  | 49702/61904 [2:58:13<4:32:35,  1.34s/it]
 80%|████████  | 49703/61904 [2:58:14<4:36:31,  1.36s/it]
 80%|████████  | 49704/61904 [2:58:16<4:38:46,  1.37s/it]
 80%|████████  | 49705/61904 [2:58:17<4:40:21,  1.38s/it]
 80%|████████  | 49706/61904 [2:58:18<4:31:01,  1.33s/it]
 80%|████████  | 49707/61904 [2:58:20<4:35:41,  1.36s/it]
 80%|████████  | 49708/61904 [2:58:21<4:39:29,  1.37s/it]
 80%|████████  | 49709/61904 [2:58:23<4:35:00,  1.35s/it]
 80%|████████  | 49710/61904 [2:58:24<4:33:35,  1.35s/it]
 80%|████████  | 49711/61904 [2:58:25<4:35:34,  1.36s/it]
 80%|████████  | 49712/61904 [2:58:27<4:33:53,  1.35s/it]
 80%|████████  | 49713/61904 [2:58:28<4:37:14,  1.36s/it]
 80%|████████  | 49714/61904 [2:58:29<4:31:28,  1.34s/it]
 80%|████████  | 49715/61904 [2:58:31<4:32:30,  1.34s/it]
 80%|████████  | 49716/61904 [2:58:32<4:35:55,  1.36s/it]
 80%|████████  | 49717/61904 [2:58:33<4:26:19,  1.31s/it]
 80%|████████  | 49718/61904 [2:58:35<4:36:36,  1.36s/it]
 80%|████████  | 49719/61904 [2:58:36<4:37:25,  1.37s/it]
 80%|████████  | 49720/61904 [2:58:38<4:42:34,  1.39s/it]
                                                         
{'loss': 2.3815, 'learning_rate': 1.1974588357318811e-07, 'epoch': 12.85}
+
 80%|████████  | 49720/61904 [2:58:38<4:42:34,  1.39s/it]
 80%|████████  | 49721/61904 [2:58:39<4:37:15,  1.37s/it]
 80%|████████  | 49722/61904 [2:58:40<4:39:09,  1.37s/it]
 80%|████████  | 49723/61904 [2:58:42<4:51:17,  1.43s/it]
 80%|████████  | 49724/61904 [2:58:43<4:44:14,  1.40s/it]
 80%|████████  | 49725/61904 [2:58:44<4:37:53,  1.37s/it]
 80%|████████  | 49726/61904 [2:58:46<4:38:05,  1.37s/it]
 80%|████████  | 49727/61904 [2:58:47<4:34:56,  1.35s/it]
 80%|████████  | 49728/61904 [2:58:48<4:29:55,  1.33s/it]
 80%|████████  | 49729/61904 [2:58:50<4:27:25,  1.32s/it]
 80%|████████  | 49730/61904 [2:58:51<4:34:43,  1.35s/it]
 80%|████████  | 49731/61904 [2:58:52<4:32:46,  1.34s/it]
 80%|████████  | 49732/61904 [2:58:54<4:36:10,  1.36s/it]
 80%|████████  | 49733/61904 [2:58:55<4:48:10,  1.42s/it]
 80%|████████  | 49734/61904 [2:58:57<4:44:06,  1.40s/it]
 80%|████████  | 49735/61904 [2:58:58<5:02:00,  1.49s/it]
 80%|████████  | 49736/61904 [2:59:00<4:53:36,  1.45s/it]
 80%|████████  | 49737/61904 [2:59:01<4:45:09,  1.41s/it]
 80%|████████  | 49738/61904 [2:59:03<4:50:25,  1.43s/it]
 80%|████████  | 49739/61904 [2:59:04<4:56:41,  1.46s/it]
 80%|████████  | 49740/61904 [2:59:05<4:47:18,  1.42s/it]
                                                         
{'loss': 2.453, 'learning_rate': 1.1971347076364578e-07, 'epoch': 12.86}
+
 80%|████████  | 49740/61904 [2:59:05<4:47:18,  1.42s/it]
 80%|████████  | 49741/61904 [2:59:07<4:53:44,  1.45s/it]
 80%|████████  | 49742/61904 [2:59:08<4:53:42,  1.45s/it]
 80%|████████  | 49743/61904 [2:59:10<4:39:26,  1.38s/it]
 80%|████████  | 49744/61904 [2:59:11<4:42:54,  1.40s/it]
 80%|████████  | 49745/61904 [2:59:12<4:37:09,  1.37s/it]
 80%|████████  | 49746/61904 [2:59:14<4:32:09,  1.34s/it]
 80%|████████  | 49747/61904 [2:59:15<4:38:55,  1.38s/it]
 80%|████████  | 49748/61904 [2:59:16<4:34:32,  1.36s/it]
 80%|████████  | 49749/61904 [2:59:18<4:44:10,  1.40s/it]
 80%|████████  | 49750/61904 [2:59:19<4:48:11,  1.42s/it]
 80%|████████  | 49751/61904 [2:59:21<4:39:05,  1.38s/it]
 80%|████████  | 49752/61904 [2:59:22<4:34:52,  1.36s/it]
 80%|████████  | 49753/61904 [2:59:23<4:29:25,  1.33s/it]
 80%|████████  | 49754/61904 [2:59:25<4:33:37,  1.35s/it]
 80%|████████  | 49755/61904 [2:59:26<4:26:04,  1.31s/it]
 80%|████████  | 49756/61904 [2:59:27<4:26:43,  1.32s/it]
 80%|████████  | 49757/61904 [2:59:29<4:32:14,  1.34s/it]
 80%|████████  | 49758/61904 [2:59:30<4:31:52,  1.34s/it]
 80%|████████  | 49759/61904 [2:59:31<4:42:00,  1.39s/it]
 80%|████████  | 49760/61904 [2:59:33<4:40:38,  1.39s/it]
                                                         
{'loss': 2.4414, 'learning_rate': 1.1968105795410346e-07, 'epoch': 12.86}
+
 80%|████████  | 49760/61904 [2:59:33<4:40:38,  1.39s/it]
 80%|████████  | 49761/61904 [2:59:34<4:33:14,  1.35s/it]
 80%|████████  | 49762/61904 [2:59:36<4:48:07,  1.42s/it]
 80%|████████  | 49763/61904 [2:59:37<4:50:49,  1.44s/it]
 80%|████████  | 49764/61904 [2:59:38<4:42:15,  1.40s/it]
 80%|████████  | 49765/61904 [2:59:40<4:31:01,  1.34s/it]
 80%|████████  | 49766/61904 [2:59:41<4:37:05,  1.37s/it]
 80%|████████  | 49767/61904 [2:59:42<4:30:25,  1.34s/it]
 80%|████████  | 49768/61904 [2:59:44<4:31:12,  1.34s/it]
 80%|████████  | 49769/61904 [2:59:45<4:31:10,  1.34s/it]
 80%|████████  | 49770/61904 [2:59:47<4:36:53,  1.37s/it]
 80%|████████  | 49771/61904 [2:59:48<4:34:26,  1.36s/it]
 80%|████████  | 49772/61904 [2:59:49<4:29:29,  1.33s/it]
 80%|████████  | 49773/61904 [2:59:51<4:37:44,  1.37s/it]
 80%|████████  | 49774/61904 [2:59:52<4:37:30,  1.37s/it]
 80%|████████  | 49775/61904 [2:59:53<4:42:15,  1.40s/it]
 80%|████████  | 49776/61904 [2:59:55<4:40:03,  1.39s/it]
 80%|████████  | 49777/61904 [2:59:56<4:45:52,  1.41s/it]
 80%|████████  | 49778/61904 [2:59:58<4:36:36,  1.37s/it]
 80%|████████  | 49779/61904 [2:59:59<4:36:53,  1.37s/it]
 80%|████████  | 49780/61904 [3:00:00<4:35:44,  1.36s/it]
                                                         
{'loss': 2.5048, 'learning_rate': 1.1964864514456113e-07, 'epoch': 12.87}
+
 80%|████████  | 49780/61904 [3:00:00<4:35:44,  1.36s/it]
 80%|████████  | 49781/61904 [3:00:02<4:46:08,  1.42s/it]
 80%|████████  | 49782/61904 [3:00:03<4:46:51,  1.42s/it]
 80%|████████  | 49783/61904 [3:00:05<4:40:08,  1.39s/it]
 80%|████████  | 49784/61904 [3:00:06<4:37:19,  1.37s/it]
 80%|████████  | 49785/61904 [3:00:07<4:37:17,  1.37s/it]
 80%|████████  | 49786/61904 [3:00:09<4:37:21,  1.37s/it]
 80%|████████  | 49787/61904 [3:00:10<4:40:39,  1.39s/it]
 80%|████████  | 49788/61904 [3:00:11<4:39:31,  1.38s/it]
 80%|████████  | 49789/61904 [3:00:13<4:32:18,  1.35s/it]
 80%|████████  | 49790/61904 [3:00:14<4:29:28,  1.33s/it]
 80%|████████  | 49791/61904 [3:00:15<4:32:02,  1.35s/it]
 80%|████████  | 49792/61904 [3:00:17<4:30:44,  1.34s/it]
 80%|████████  | 49793/61904 [3:00:18<4:26:47,  1.32s/it]
 80%|████████  | 49794/61904 [3:00:19<4:32:14,  1.35s/it]
 80%|████████  | 49795/61904 [3:00:21<4:38:31,  1.38s/it]
 80%|████████  | 49796/61904 [3:00:22<4:35:48,  1.37s/it]
 80%|████████  | 49797/61904 [3:00:23<4:32:05,  1.35s/it]
 80%|████████  | 49798/61904 [3:00:25<4:42:25,  1.40s/it]
 80%|████████  | 49799/61904 [3:00:26<4:29:37,  1.34s/it]
 80%|████████  | 49800/61904 [3:00:28<4:29:37,  1.34s/it]
                                                         
{'loss': 2.4836, 'learning_rate': 1.196162323350188e-07, 'epoch': 12.87}
+
 80%|████████  | 49800/61904 [3:00:28<4:29:37,  1.34s/it]
 80%|████████  | 49801/61904 [3:00:29<4:31:14,  1.34s/it]
 80%|████████  | 49802/61904 [3:00:30<4:32:01,  1.35s/it]
 80%|████████  | 49803/61904 [3:00:31<4:26:50,  1.32s/it]
 80%|████████  | 49804/61904 [3:00:33<4:34:36,  1.36s/it]
 80%|████████  | 49805/61904 [3:00:34<4:29:05,  1.33s/it]
 80%|████████  | 49806/61904 [3:00:36<4:28:38,  1.33s/it]
 80%|████████  | 49807/61904 [3:00:37<4:25:49,  1.32s/it]
 80%|████████  | 49808/61904 [3:00:38<4:32:06,  1.35s/it]
 80%|████████  | 49809/61904 [3:00:40<4:35:44,  1.37s/it]
 80%|████████  | 49810/61904 [3:00:41<4:45:06,  1.41s/it]
 80%|████████  | 49811/61904 [3:00:42<4:38:47,  1.38s/it]
 80%|████████  | 49812/61904 [3:00:44<4:37:21,  1.38s/it]
 80%|████████  | 49813/61904 [3:00:45<4:33:02,  1.35s/it]
 80%|████████  | 49814/61904 [3:00:47<4:36:16,  1.37s/it]
 80%|████████  | 49815/61904 [3:00:48<4:34:29,  1.36s/it]
 80%|████████  | 49816/61904 [3:00:49<4:34:20,  1.36s/it]
 80%|████████  | 49817/61904 [3:00:51<4:37:44,  1.38s/it]
 80%|████████  | 49818/61904 [3:00:52<4:40:04,  1.39s/it]
 80%|████████  | 49819/61904 [3:00:53<4:36:15,  1.37s/it]
 80%|████████  | 49820/61904 [3:00:55<4:40:36,  1.39s/it]
                                                         
{'loss': 2.4018, 'learning_rate': 1.1958381952547645e-07, 'epoch': 12.88}
+
 80%|████████  | 49820/61904 [3:00:55<4:40:36,  1.39s/it]
 80%|████████  | 49821/61904 [3:00:56<4:34:12,  1.36s/it]
 80%|████████  | 49822/61904 [3:00:58<4:32:29,  1.35s/it]
 80%|████████  | 49823/61904 [3:00:59<4:39:15,  1.39s/it]
 80%|████████  | 49824/61904 [3:01:00<4:29:39,  1.34s/it]
 80%|████████  | 49825/61904 [3:01:02<4:32:46,  1.35s/it]
 80%|████████  | 49826/61904 [3:01:03<4:29:38,  1.34s/it]
 80%|████████  | 49827/61904 [3:01:04<4:32:52,  1.36s/it]
 80%|████████  | 49828/61904 [3:01:06<4:37:55,  1.38s/it]
 80%|████████  | 49829/61904 [3:01:07<4:38:58,  1.39s/it]
 80%|████████  | 49830/61904 [3:01:09<4:38:27,  1.38s/it]
 80%|████████  | 49831/61904 [3:01:10<4:36:19,  1.37s/it]
 80%|████████  | 49832/61904 [3:01:11<4:44:31,  1.41s/it]
 81%|████████  | 49833/61904 [3:01:13<4:39:05,  1.39s/it]
 81%|████████  | 49834/61904 [3:01:14<4:33:25,  1.36s/it]
 81%|████████  | 49835/61904 [3:01:15<4:34:59,  1.37s/it]
 81%|████████  | 49836/61904 [3:01:17<4:35:00,  1.37s/it]
 81%|████████  | 49837/61904 [3:01:18<4:36:19,  1.37s/it]
 81%|████████  | 49838/61904 [3:01:20<4:39:01,  1.39s/it]
 81%|████████  | 49839/61904 [3:01:21<4:35:15,  1.37s/it]
 81%|████████  | 49840/61904 [3:01:22<4:30:54,  1.35s/it]
                                                         
{'loss': 2.4562, 'learning_rate': 1.1955140671593414e-07, 'epoch': 12.88}
+
 81%|████████  | 49840/61904 [3:01:22<4:30:54,  1.35s/it]
 81%|████████  | 49841/61904 [3:01:24<4:37:01,  1.38s/it]
 81%|████████  | 49842/61904 [3:01:25<4:47:36,  1.43s/it]
 81%|████████  | 49843/61904 [3:01:27<4:43:25,  1.41s/it]
 81%|████████  | 49844/61904 [3:01:28<4:44:28,  1.42s/it]
 81%|████████  | 49845/61904 [3:01:29<4:44:31,  1.42s/it]
 81%|████████  | 49846/61904 [3:01:31<4:37:14,  1.38s/it]
 81%|████████  | 49847/61904 [3:01:32<4:30:43,  1.35s/it]
 81%|████████  | 49848/61904 [3:01:33<4:28:43,  1.34s/it]
 81%|████████  | 49849/61904 [3:01:35<4:48:49,  1.44s/it]
 81%|████████  | 49850/61904 [3:01:36<4:39:03,  1.39s/it]
 81%|████████  | 49851/61904 [3:01:38<4:34:15,  1.37s/it]
 81%|████████  | 49852/61904 [3:01:39<4:32:19,  1.36s/it]
 81%|████████  | 49853/61904 [3:01:40<4:35:20,  1.37s/it]
 81%|████████  | 49854/61904 [3:01:42<4:37:02,  1.38s/it]
 81%|████████  | 49855/61904 [3:01:43<4:41:00,  1.40s/it]
 81%|████████  | 49856/61904 [3:01:44<4:32:04,  1.35s/it]
 81%|████████  | 49857/61904 [3:01:46<4:27:02,  1.33s/it]
 81%|████████  | 49858/61904 [3:01:47<4:36:48,  1.38s/it]
 81%|████████  | 49859/61904 [3:01:48<4:34:13,  1.37s/it]
 81%|████████  | 49860/61904 [3:01:50<4:31:54,  1.35s/it]
                                                         
{'loss': 2.4431, 'learning_rate': 1.195189939063918e-07, 'epoch': 12.89}
+
 81%|████████  | 49860/61904 [3:01:50<4:31:54,  1.35s/it]
 81%|████████  | 49861/61904 [3:01:51<4:37:07,  1.38s/it]
 81%|████████  | 49862/61904 [3:01:53<4:33:46,  1.36s/it]
 81%|████████  | 49863/61904 [3:01:54<4:34:06,  1.37s/it]
 81%|████████  | 49864/61904 [3:01:55<4:32:37,  1.36s/it]
 81%|████████  | 49865/61904 [3:01:57<4:39:00,  1.39s/it]
 81%|████████  | 49866/61904 [3:01:58<4:38:03,  1.39s/it]
 81%|████████  | 49867/61904 [3:02:00<4:39:59,  1.40s/it]
 81%|████████  | 49868/61904 [3:02:01<4:43:18,  1.41s/it]
 81%|████████  | 49869/61904 [3:02:02<4:40:29,  1.40s/it]
 81%|████████  | 49870/61904 [3:02:04<4:47:11,  1.43s/it]
 81%|████████  | 49871/61904 [3:02:05<4:39:49,  1.40s/it]
 81%|████████  | 49872/61904 [3:02:07<4:40:06,  1.40s/it]
 81%|████████  | 49873/61904 [3:02:08<4:44:56,  1.42s/it]
 81%|████████  | 49874/61904 [3:02:09<4:40:11,  1.40s/it]
 81%|████████  | 49875/61904 [3:02:11<4:40:41,  1.40s/it]
 81%|████████  | 49876/61904 [3:02:12<4:35:55,  1.38s/it]
 81%|████████  | 49877/61904 [3:02:14<4:50:57,  1.45s/it]
 81%|████████  | 49878/61904 [3:02:15<4:46:26,  1.43s/it]
 81%|████████  | 49879/61904 [3:02:17<4:50:38,  1.45s/it]
 81%|████████  | 49880/61904 [3:02:18<4:37:35,  1.39s/it]
                                                         
{'loss': 2.4554, 'learning_rate': 1.1948658109684946e-07, 'epoch': 12.89}
+
 81%|████████  | 49880/61904 [3:02:18<4:37:35,  1.39s/it]
 81%|████████  | 49881/61904 [3:02:19<4:33:50,  1.37s/it]
 81%|████████  | 49882/61904 [3:02:20<4:28:46,  1.34s/it]
 81%|████████  | 49883/61904 [3:02:22<4:29:51,  1.35s/it]
 81%|████████  | 49884/61904 [3:02:23<4:24:59,  1.32s/it]
 81%|████████  | 49885/61904 [3:02:24<4:26:54,  1.33s/it]
 81%|████████  | 49886/61904 [3:02:26<4:23:11,  1.31s/it]
 81%|████████  | 49887/61904 [3:02:27<4:24:44,  1.32s/it]
 81%|████████  | 49888/61904 [3:02:29<4:35:06,  1.37s/it]
 81%|████████  | 49889/61904 [3:02:30<4:36:36,  1.38s/it]
 81%|████████  | 49890/61904 [3:02:31<4:31:13,  1.35s/it]
 81%|████████  | 49891/61904 [3:02:32<4:25:20,  1.33s/it]
 81%|████████  | 49892/61904 [3:02:34<4:26:36,  1.33s/it]
 81%|████████  | 49893/61904 [3:02:35<4:38:27,  1.39s/it]
 81%|████████  | 49894/61904 [3:02:37<4:31:04,  1.35s/it]
 81%|████████  | 49895/61904 [3:02:38<4:38:47,  1.39s/it]
 81%|████████  | 49896/61904 [3:02:40<4:40:16,  1.40s/it]
 81%|████████  | 49897/61904 [3:02:41<4:34:49,  1.37s/it]
 81%|████████  | 49898/61904 [3:02:42<4:37:55,  1.39s/it]
 81%|████████  | 49899/61904 [3:02:44<4:37:41,  1.39s/it]
 81%|████████  | 49900/61904 [3:02:45<4:40:07,  1.40s/it]
                                                         
{'loss': 2.4341, 'learning_rate': 1.1945416828730712e-07, 'epoch': 12.9}
+
 81%|████████  | 49900/61904 [3:02:45<4:40:07,  1.40s/it]
 81%|████████  | 49901/61904 [3:02:46<4:33:31,  1.37s/it]
 81%|████████  | 49902/61904 [3:02:48<4:32:40,  1.36s/it]
 81%|████████  | 49903/61904 [3:02:49<4:39:39,  1.40s/it]
 81%|████████  | 49904/61904 [3:02:51<4:43:38,  1.42s/it]
 81%|████████  | 49905/61904 [3:02:52<4:35:40,  1.38s/it]
 81%|████████  | 49906/61904 [3:02:53<4:37:34,  1.39s/it]
 81%|████████  | 49907/61904 [3:02:55<4:50:49,  1.45s/it]
 81%|████████  | 49908/61904 [3:02:56<4:40:25,  1.40s/it]
 81%|████████  | 49909/61904 [3:02:58<4:37:19,  1.39s/it]
 81%|████████  | 49910/61904 [3:02:59<4:38:17,  1.39s/it]
 81%|████████  | 49911/61904 [3:03:00<4:37:21,  1.39s/it]
 81%|████████  | 49912/61904 [3:03:02<4:30:36,  1.35s/it]
 81%|████████  | 49913/61904 [3:03:03<4:31:53,  1.36s/it]
 81%|████████  | 49914/61904 [3:03:04<4:29:59,  1.35s/it]
 81%|████████  | 49915/61904 [3:03:06<4:29:35,  1.35s/it]
 81%|████████  | 49916/61904 [3:03:07<4:27:44,  1.34s/it]
 81%|████████  | 49917/61904 [3:03:08<4:26:40,  1.33s/it]
 81%|████████  | 49918/61904 [3:03:10<4:21:07,  1.31s/it]
 81%|████████  | 49919/61904 [3:03:11<4:16:23,  1.28s/it]
 81%|████████  | 49920/61904 [3:03:12<4:32:57,  1.37s/it]
                                                         
{'loss': 2.4189, 'learning_rate': 1.194217554777648e-07, 'epoch': 12.9}
+
 81%|████████  | 49920/61904 [3:03:12<4:32:57,  1.37s/it]
 81%|████████  | 49921/61904 [3:03:14<4:25:30,  1.33s/it]
 81%|████████  | 49922/61904 [3:03:15<4:32:48,  1.37s/it]
 81%|████████  | 49923/61904 [3:03:16<4:30:18,  1.35s/it]
 81%|████████  | 49924/61904 [3:03:18<4:34:37,  1.38s/it]
 81%|████████  | 49925/61904 [3:03:19<4:35:51,  1.38s/it]
 81%|████████  | 49926/61904 [3:03:21<4:34:23,  1.37s/it]
 81%|████████  | 49927/61904 [3:03:22<4:28:33,  1.35s/it]
 81%|████████  | 49928/61904 [3:03:23<4:28:31,  1.35s/it]
 81%|████████  | 49929/61904 [3:03:25<4:28:23,  1.34s/it]
 81%|████████  | 49930/61904 [3:03:26<4:30:22,  1.35s/it]
 81%|████████  | 49931/61904 [3:03:27<4:40:55,  1.41s/it]
 81%|████████  | 49932/61904 [3:03:29<4:44:19,  1.42s/it]
 81%|████████  | 49933/61904 [3:03:30<4:36:16,  1.38s/it]
 81%|████████  | 49934/61904 [3:03:32<4:41:59,  1.41s/it]
 81%|████████  | 49935/61904 [3:03:33<4:35:55,  1.38s/it]
 81%|████████  | 49936/61904 [3:03:35<4:44:07,  1.42s/it]
 81%|████████  | 49937/61904 [3:03:36<4:44:06,  1.42s/it]
 81%|████████  | 49938/61904 [3:03:37<4:41:31,  1.41s/it]
 81%|████████  | 49939/61904 [3:03:39<4:39:16,  1.40s/it]
 81%|████████  | 49940/61904 [3:03:40<4:43:48,  1.42s/it]
                                                         
{'loss': 2.4739, 'learning_rate': 1.1938934266822247e-07, 'epoch': 12.91}
+
 81%|████���███  | 49940/61904 [3:03:40<4:43:48,  1.42s/it]
 81%|████████  | 49941/61904 [3:03:41<4:36:01,  1.38s/it]
 81%|████████  | 49942/61904 [3:03:43<4:47:05,  1.44s/it]
 81%|████████  | 49943/61904 [3:03:44<4:44:03,  1.42s/it]
 81%|████████  | 49944/61904 [3:03:46<4:45:56,  1.43s/it]
 81%|████████  | 49945/61904 [3:03:47<4:41:22,  1.41s/it]
 81%|████████  | 49946/61904 [3:03:49<4:36:54,  1.39s/it]
 81%|████████  | 49947/61904 [3:03:50<4:36:43,  1.39s/it]
 81%|████████  | 49948/61904 [3:03:51<4:37:21,  1.39s/it]
 81%|████████  | 49949/61904 [3:03:53<4:42:34,  1.42s/it]
 81%|████████  | 49950/61904 [3:03:54<4:33:51,  1.37s/it]
 81%|████████  | 49951/61904 [3:03:56<4:35:12,  1.38s/it]
 81%|████████  | 49952/61904 [3:03:57<4:25:43,  1.33s/it]
 81%|████████  | 49953/61904 [3:03:58<4:37:41,  1.39s/it]
 81%|████████  | 49954/61904 [3:04:00<4:40:35,  1.41s/it]
 81%|████████  | 49955/61904 [3:04:01<4:39:43,  1.40s/it]
 81%|████████  | 49956/61904 [3:04:03<4:41:10,  1.41s/it]
 81%|████████  | 49957/61904 [3:04:04<4:34:42,  1.38s/it]
 81%|████████  | 49958/61904 [3:04:05<4:25:49,  1.34s/it]
 81%|████████  | 49959/61904 [3:04:06<4:30:00,  1.36s/it]
 81%|████████  | 49960/61904 [3:04:08<4:25:45,  1.34s/it]
                                                         
{'loss': 2.3941, 'learning_rate': 1.1935692985868014e-07, 'epoch': 12.91}
+
 81%|████████  | 49960/61904 [3:04:08<4:25:45,  1.34s/it]
 81%|████████  | 49961/61904 [3:04:09<4:33:53,  1.38s/it]
 81%|████████  | 49962/61904 [3:04:11<4:34:08,  1.38s/it]
 81%|████████  | 49963/61904 [3:04:12<4:27:06,  1.34s/it]
 81%|████████  | 49964/61904 [3:04:13<4:38:04,  1.40s/it]
 81%|████████  | 49965/61904 [3:04:15<4:25:06,  1.33s/it]
 81%|████████  | 49966/61904 [3:04:16<4:29:04,  1.35s/it]
 81%|████████  | 49967/61904 [3:04:17<4:23:45,  1.33s/it]
 81%|████████  | 49968/61904 [3:04:19<4:28:35,  1.35s/it]
 81%|████████  | 49969/61904 [3:04:20<4:25:02,  1.33s/it]
 81%|████████  | 49970/61904 [3:04:21<4:28:18,  1.35s/it]
 81%|████████  | 49971/61904 [3:04:23<4:37:41,  1.40s/it]
 81%|████████  | 49972/61904 [3:04:24<4:45:18,  1.43s/it]
 81%|████████  | 49973/61904 [3:04:26<4:31:29,  1.37s/it]
 81%|████████  | 49974/61904 [3:04:27<4:29:37,  1.36s/it]
 81%|████████  | 49975/61904 [3:04:28<4:37:31,  1.40s/it]
 81%|████████  | 49976/61904 [3:04:30<4:25:45,  1.34s/it]
 81%|████████  | 49977/61904 [3:04:31<4:30:02,  1.36s/it]
 81%|████████  | 49978/61904 [3:04:32<4:31:04,  1.36s/it]
 81%|████████  | 49979/61904 [3:04:34<4:29:40,  1.36s/it]
 81%|████████  | 49980/61904 [3:04:35<4:27:53,  1.35s/it]
                                                         
{'loss': 2.4357, 'learning_rate': 1.1932451704913782e-07, 'epoch': 12.92}
+
 81%|████████  | 49980/61904 [3:04:35<4:27:53,  1.35s/it]
 81%|████████  | 49981/61904 [3:04:36<4:29:35,  1.36s/it]
 81%|████████  | 49982/61904 [3:04:38<4:30:27,  1.36s/it]
 81%|████████  | 49983/61904 [3:04:39<4:33:54,  1.38s/it]
 81%|████████  | 49984/61904 [3:04:40<4:25:46,  1.34s/it]
 81%|████████  | 49985/61904 [3:04:42<4:18:47,  1.30s/it]
 81%|████████  | 49986/61904 [3:04:43<4:26:04,  1.34s/it]
 81%|████████  | 49987/61904 [3:04:44<4:29:09,  1.36s/it]
 81%|████████  | 49988/61904 [3:04:46<4:39:27,  1.41s/it]
 81%|████████  | 49989/61904 [3:04:47<4:37:54,  1.40s/it]
 81%|████████  | 49990/61904 [3:04:49<4:33:44,  1.38s/it]
 81%|████████  | 49991/61904 [3:04:50<4:36:14,  1.39s/it]
 81%|████████  | 49992/61904 [3:04:52<4:37:24,  1.40s/it]
 81%|████████  | 49993/61904 [3:04:53<4:31:45,  1.37s/it]
 81%|████████  | 49994/61904 [3:04:54<4:26:59,  1.35s/it]
 81%|████████  | 49995/61904 [3:04:56<4:31:59,  1.37s/it]
 81%|████████  | 49996/61904 [3:04:57<4:26:45,  1.34s/it]
 81%|████████  | 49997/61904 [3:04:58<4:24:43,  1.33s/it]
 81%|████████  | 49998/61904 [3:04:59<4:20:01,  1.31s/it]
 81%|████████  | 49999/61904 [3:05:01<4:29:02,  1.36s/it]
 81%|████████  | 50000/61904 [3:05:02<4:31:36,  1.37s/it]
                                                         
{'loss': 2.4676, 'learning_rate': 1.1929210423959549e-07, 'epoch': 12.92}
+
 81%|████████  | 50000/61904 [3:05:02<4:31:36,  1.37s/it]
 81%|████████  | 50001/61904 [3:05:04<4:32:08,  1.37s/it]
 81%|████████  | 50002/61904 [3:05:05<4:31:15,  1.37s/it]
 81%|████████  | 50003/61904 [3:05:06<4:28:19,  1.35s/it]
 81%|████████  | 50004/61904 [3:05:08<4:34:15,  1.38s/it]
 81%|████████  | 50005/61904 [3:05:09<4:30:55,  1.37s/it]
 81%|████████  | 50006/61904 [3:05:11<4:33:51,  1.38s/it]
 81%|████████  | 50007/61904 [3:05:12<4:31:38,  1.37s/it]
 81%|████████  | 50008/61904 [3:05:13<4:29:00,  1.36s/it]
 81%|████████  | 50009/61904 [3:05:15<4:29:06,  1.36s/it]
 81%|████████  | 50010/61904 [3:05:16<4:23:35,  1.33s/it]
 81%|████████  | 50011/61904 [3:05:17<4:23:52,  1.33s/it]
 81%|████████  | 50012/61904 [3:05:19<4:27:53,  1.35s/it]
 81%|████████  | 50013/61904 [3:05:20<4:25:23,  1.34s/it]
 81%|████████  | 50014/61904 [3:05:21<4:25:10,  1.34s/it]
 81%|████████  | 50015/61904 [3:05:23<4:21:57,  1.32s/it]
 81%|████████  | 50016/61904 [3:05:24<4:28:53,  1.36s/it]
 81%|████████  | 50017/61904 [3:05:25<4:31:47,  1.37s/it]
 81%|████████  | 50018/61904 [3:05:27<4:28:53,  1.36s/it]
 81%|████████  | 50019/61904 [3:05:28<4:32:16,  1.37s/it]
 81%|████████  | 50020/61904 [3:05:29<4:27:30,  1.35s/it]
                                                         
{'loss': 2.4551, 'learning_rate': 1.1925969143005315e-07, 'epoch': 12.93}
+
 81%|████████  | 50020/61904 [3:05:29<4:27:30,  1.35s/it]
 81%|████████  | 50021/61904 [3:05:31<4:21:07,  1.32s/it]
 81%|████████  | 50022/61904 [3:05:32<4:17:31,  1.30s/it]
 81%|████████  | 50023/61904 [3:05:33<4:21:44,  1.32s/it]
 81%|████████  | 50024/61904 [3:05:35<4:20:34,  1.32s/it]
 81%|████████  | 50025/61904 [3:05:36<4:19:31,  1.31s/it]
 81%|████████  | 50026/61904 [3:05:37<4:18:46,  1.31s/it]
 81%|████████  | 50027/61904 [3:05:39<4:27:26,  1.35s/it]
 81%|████████  | 50028/61904 [3:05:40<4:18:25,  1.31s/it]
 81%|████████  | 50029/61904 [3:05:41<4:22:35,  1.33s/it]
 81%|████████  | 50030/61904 [3:05:43<4:30:29,  1.37s/it]
 81%|████████  | 50031/61904 [3:05:44<4:32:10,  1.38s/it]
 81%|████████  | 50032/61904 [3:05:45<4:28:40,  1.36s/it]
 81%|████████  | 50033/61904 [3:05:47<4:27:51,  1.35s/it]
 81%|████████  | 50034/61904 [3:05:48<4:29:17,  1.36s/it]
 81%|████████  | 50035/61904 [3:05:50<4:32:44,  1.38s/it]
 81%|████████  | 50036/61904 [3:05:51<4:33:11,  1.38s/it]
 81%|████████  | 50037/61904 [3:05:52<4:32:56,  1.38s/it]
 81%|████████  | 50038/61904 [3:05:54<4:32:29,  1.38s/it]
 81%|████████  | 50039/61904 [3:05:55<4:33:23,  1.38s/it]
 81%|████████  | 50040/61904 [3:05:56<4:26:32,  1.35s/it]
                                                         
{'loss': 2.4811, 'learning_rate': 1.192272786205108e-07, 'epoch': 12.93}
+
 81%|████████  | 50040/61904 [3:05:56<4:26:32,  1.35s/it]
 81%|████████  | 50041/61904 [3:05:58<4:28:36,  1.36s/it]
 81%|████████  | 50042/61904 [3:05:59<4:29:42,  1.36s/it]
 81%|████████  | 50043/61904 [3:06:00<4:33:21,  1.38s/it]
 81%|████████  | 50044/61904 [3:06:02<4:22:51,  1.33s/it]
 81%|████████  | 50045/61904 [3:06:03<4:33:12,  1.38s/it]
 81%|████████  | 50046/61904 [3:06:05<4:38:20,  1.41s/it]
 81%|████████  | 50047/61904 [3:06:06<4:23:47,  1.33s/it]
 81%|████████  | 50048/61904 [3:06:07<4:19:33,  1.31s/it]
 81%|████████  | 50049/61904 [3:06:08<4:16:24,  1.30s/it]
 81%|████████  | 50050/61904 [3:06:10<4:12:32,  1.28s/it]
 81%|████████  | 50051/61904 [3:06:11<4:15:30,  1.29s/it]
 81%|████████  | 50052/61904 [3:06:12<4:12:59,  1.28s/it]
 81%|████████  | 50053/61904 [3:06:13<4:13:18,  1.28s/it]
 81%|████████  | 50054/61904 [3:06:15<4:15:23,  1.29s/it]
 81%|████████  | 50055/61904 [3:06:16<4:13:20,  1.28s/it]
 81%|████████  | 50056/61904 [3:06:17<4:15:53,  1.30s/it]
 81%|████████  | 50057/61904 [3:06:19<4:22:59,  1.33s/it]
 81%|████████  | 50058/61904 [3:06:20<4:36:37,  1.40s/it]
 81%|████████  | 50059/61904 [3:06:22<4:46:12,  1.45s/it]
 81%|████████  | 50060/61904 [3:06:23<4:42:01,  1.43s/it]
                                                         
{'loss': 2.4513, 'learning_rate': 1.191948658109685e-07, 'epoch': 12.94}
+
 81%|████████  | 50060/61904 [3:06:23<4:42:01,  1.43s/it]
 81%|████████  | 50061/61904 [3:06:25<4:36:55,  1.40s/it]
 81%|████████  | 50062/61904 [3:06:26<4:25:51,  1.35s/it]
 81%|████████  | 50063/61904 [3:06:27<4:30:41,  1.37s/it]
 81%|████████  | 50064/61904 [3:06:29<4:36:09,  1.40s/it]
 81%|████████  | 50065/61904 [3:06:30<4:29:37,  1.37s/it]
 81%|████████  | 50066/61904 [3:06:32<4:40:31,  1.42s/it]
 81%|████████  | 50067/61904 [3:06:33<4:33:18,  1.39s/it]
 81%|████████  | 50068/61904 [3:06:34<4:35:34,  1.40s/it]
 81%|████████  | 50069/61904 [3:06:36<4:30:47,  1.37s/it]
 81%|████████  | 50070/61904 [3:06:37<4:36:40,  1.40s/it]
 81%|████████  | 50071/61904 [3:06:38<4:34:41,  1.39s/it]
 81%|████████  | 50072/61904 [3:06:40<4:33:05,  1.38s/it]
 81%|████████  | 50073/61904 [3:06:41<4:29:23,  1.37s/it]
 81%|████████  | 50074/61904 [3:06:42<4:24:54,  1.34s/it]
 81%|████████  | 50075/61904 [3:06:44<4:22:31,  1.33s/it]
 81%|████████  | 50076/61904 [3:06:45<4:30:06,  1.37s/it]
 81%|████████  | 50077/61904 [3:06:47<4:31:42,  1.38s/it]
 81%|████████  | 50078/61904 [3:06:48<4:24:37,  1.34s/it]
 81%|████████  | 50079/61904 [3:06:49<4:30:01,  1.37s/it]
 81%|████████  | 50080/61904 [3:06:51<4:24:18,  1.34s/it]
                                                         
{'loss': 2.4607, 'learning_rate': 1.1916245300142616e-07, 'epoch': 12.94}
+
 81%|████████  | 50080/61904 [3:06:51<4:24:18,  1.34s/it]
 81%|████████  | 50081/61904 [3:06:52<4:35:27,  1.40s/it]
 81%|████████  | 50082/61904 [3:06:54<4:39:58,  1.42s/it]
 81%|████████  | 50083/61904 [3:06:55<4:27:32,  1.36s/it]
 81%|████████  | 50084/61904 [3:06:56<4:23:11,  1.34s/it]
 81%|████████  | 50085/61904 [3:06:57<4:18:08,  1.31s/it]
 81%|████████  | 50086/61904 [3:06:59<4:21:21,  1.33s/it]
 81%|████████  | 50087/61904 [3:07:00<4:22:01,  1.33s/it]
 81%|████████  | 50088/61904 [3:07:01<4:25:39,  1.35s/it]
 81%|████████  | 50089/61904 [3:07:03<4:34:19,  1.39s/it]
 81%|████████  | 50090/61904 [3:07:04<4:34:36,  1.39s/it]
 81%|████████  | 50091/61904 [3:07:06<4:25:01,  1.35s/it]
 81%|████████  | 50092/61904 [3:07:07<4:33:19,  1.39s/it]
 81%|████████  | 50093/61904 [3:07:08<4:28:03,  1.36s/it]
 81%|████████  | 50094/61904 [3:07:10<4:37:03,  1.41s/it]
 81%|████████  | 50095/61904 [3:07:11<4:34:37,  1.40s/it]
 81%|████████  | 50096/61904 [3:07:12<4:23:41,  1.34s/it]
 81%|████████  | 50097/61904 [3:07:14<4:24:00,  1.34s/it]
 81%|████████  | 50098/61904 [3:07:15<4:27:49,  1.36s/it]
 81%|████████  | 50099/61904 [3:07:17<4:26:50,  1.36s/it]
 81%|████████  | 50100/61904 [3:07:18<4:30:54,  1.38s/it]
                                                         
{'loss': 2.482, 'learning_rate': 1.1913004019188382e-07, 'epoch': 12.95}
+
 81%|████████  | 50100/61904 [3:07:18<4:30:54,  1.38s/it]
 81%|████████  | 50101/61904 [3:07:19<4:19:59,  1.32s/it]
 81%|████████  | 50102/61904 [3:07:21<4:26:37,  1.36s/it]
 81%|████████  | 50103/61904 [3:07:22<4:21:28,  1.33s/it]
 81%|████████  | 50104/61904 [3:07:23<4:29:54,  1.37s/it]
 81%|████████  | 50105/61904 [3:07:25<4:30:08,  1.37s/it]
 81%|████████  | 50106/61904 [3:07:26<4:35:40,  1.40s/it]
 81%|████████  | 50107/61904 [3:07:28<4:34:40,  1.40s/it]
 81%|████████  | 50108/61904 [3:07:29<4:42:41,  1.44s/it]
 81%|████████  | 50109/61904 [3:07:31<4:44:44,  1.45s/it]
 81%|████████  | 50110/61904 [3:07:32<4:37:33,  1.41s/it]
 81%|████████  | 50111/61904 [3:07:33<4:39:50,  1.42s/it]
 81%|████████  | 50112/61904 [3:07:35<4:27:11,  1.36s/it]
 81%|████████  | 50113/61904 [3:07:36<4:28:07,  1.36s/it]
 81%|████████  | 50114/61904 [3:07:37<4:29:48,  1.37s/it]
 81%|████████  | 50115/61904 [3:07:39<4:19:55,  1.32s/it]
 81%|████████  | 50116/61904 [3:07:40<4:14:18,  1.29s/it]
 81%|████████  | 50117/61904 [3:07:41<4:17:09,  1.31s/it]
 81%|████████  | 50118/61904 [3:07:42<4:17:11,  1.31s/it]
 81%|████████  | 50119/61904 [3:07:44<4:15:30,  1.30s/it]
 81%|████████  | 50120/61904 [3:07:45<4:21:30,  1.33s/it]
                                                         
{'loss': 2.4465, 'learning_rate': 1.1909762738234151e-07, 'epoch': 12.95}
+
 81%|████████  | 50120/61904 [3:07:45<4:21:30,  1.33s/it]
 81%|████████  | 50121/61904 [3:07:47<4:30:49,  1.38s/it]
 81%|████████  | 50122/61904 [3:07:48<4:33:38,  1.39s/it]
 81%|████████  | 50123/61904 [3:07:49<4:30:57,  1.38s/it]
 81%|████████  | 50124/61904 [3:07:51<4:30:50,  1.38s/it]
 81%|████████  | 50125/61904 [3:07:52<4:28:14,  1.37s/it]
 81%|████████  | 50126/61904 [3:07:53<4:23:54,  1.34s/it]
 81%|████████  | 50127/61904 [3:07:55<4:24:38,  1.35s/it]
 81%|████████  | 50128/61904 [3:07:56<4:21:05,  1.33s/it]
 81%|████████  | 50129/61904 [3:07:57<4:24:09,  1.35s/it]
 81%|████████  | 50130/61904 [3:07:59<4:23:32,  1.34s/it]
 81%|████████  | 50131/61904 [3:08:00<4:21:49,  1.33s/it]
 81%|████████  | 50132/61904 [3:08:01<4:23:20,  1.34s/it]
 81%|████████  | 50133/61904 [3:08:03<4:25:52,  1.36s/it]
 81%|████████  | 50134/61904 [3:08:05<4:48:42,  1.47s/it]
 81%|████████  | 50135/61904 [3:08:06<4:47:45,  1.47s/it]
 81%|████████  | 50136/61904 [3:08:07<4:43:37,  1.45s/it]
 81%|████████  | 50137/61904 [3:08:09<4:30:35,  1.38s/it]
 81%|████████  | 50138/61904 [3:08:10<4:31:24,  1.38s/it]
 81%|████████  | 50139/61904 [3:08:11<4:30:37,  1.38s/it]
 81%|████████  | 50140/61904 [3:08:13<4:29:12,  1.37s/it]
                                                         
{'loss': 2.4672, 'learning_rate': 1.1906521457279917e-07, 'epoch': 12.96}
+
 81%|████████  | 50140/61904 [3:08:13<4:29:12,  1.37s/it]
 81%|████████  | 50141/61904 [3:08:14<4:29:43,  1.38s/it]
 81%|████████  | 50142/61904 [3:08:15<4:22:27,  1.34s/it]
 81%|████████  | 50143/61904 [3:08:17<4:23:18,  1.34s/it]
 81%|████████  | 50144/61904 [3:08:18<4:30:04,  1.38s/it]
 81%|████████  | 50145/61904 [3:08:20<4:31:00,  1.38s/it]
 81%|████████  | 50146/61904 [3:08:21<4:28:54,  1.37s/it]
 81%|████████  | 50147/61904 [3:08:22<4:26:59,  1.36s/it]
 81%|████████  | 50148/61904 [3:08:24<4:30:23,  1.38s/it]
 81%|████████  | 50149/61904 [3:08:25<4:33:24,  1.40s/it]
 81%|████████  | 50150/61904 [3:08:27<4:38:29,  1.42s/it]
 81%|████████  | 50151/61904 [3:08:28<4:32:17,  1.39s/it]
 81%|████████  | 50152/61904 [3:08:29<4:31:23,  1.39s/it]
 81%|████████  | 50153/61904 [3:08:31<4:41:04,  1.44s/it]
 81%|████████  | 50154/61904 [3:08:32<4:38:32,  1.42s/it]
 81%|████████  | 50155/61904 [3:08:34<4:36:29,  1.41s/it]
 81%|████████  | 50156/61904 [3:08:35<4:49:40,  1.48s/it]
 81%|████████  | 50157/61904 [3:08:37<4:37:42,  1.42s/it]
 81%|████████  | 50158/61904 [3:08:38<4:36:50,  1.41s/it]
 81%|████████  | 50159/61904 [3:08:39<4:31:17,  1.39s/it]
 81%|████████  | 50160/61904 [3:08:41<4:44:55,  1.46s/it]
                                                         
{'loss': 2.421, 'learning_rate': 1.1903280176325683e-07, 'epoch': 12.96}
+
 81%|████████  | 50160/61904 [3:08:41<4:44:55,  1.46s/it]
 81%|████████  | 50161/61904 [3:08:42<4:50:58,  1.49s/it]
 81%|████████  | 50162/61904 [3:08:44<4:42:59,  1.45s/it]
 81%|████████  | 50163/61904 [3:08:45<4:42:48,  1.45s/it]
 81%|████████  | 50164/61904 [3:08:47<4:45:57,  1.46s/it]
 81%|████████  | 50165/61904 [3:08:49<5:12:41,  1.60s/it]
 81%|████████  | 50166/61904 [3:08:50<4:58:55,  1.53s/it]
 81%|████████  | 50167/61904 [3:08:51<4:50:57,  1.49s/it]
 81%|████████  | 50168/61904 [3:08:53<4:45:02,  1.46s/it]
 81%|████████  | 50169/61904 [3:08:54<4:35:40,  1.41s/it]
 81%|████████  | 50170/61904 [3:08:55<4:22:24,  1.34s/it]
 81%|████████  | 50171/61904 [3:08:57<4:35:39,  1.41s/it]
 81%|████████  | 50172/61904 [3:08:58<4:27:58,  1.37s/it]
 81%|████████  | 50173/61904 [3:08:59<4:23:25,  1.35s/it]
 81%|████████  | 50174/61904 [3:09:01<4:21:15,  1.34s/it]
 81%|████████  | 50175/61904 [3:09:02<4:24:48,  1.35s/it]
 81%|████████  | 50176/61904 [3:09:04<4:29:28,  1.38s/it]
 81%|████████  | 50177/61904 [3:09:05<4:28:00,  1.37s/it]
 81%|████████  | 50178/61904 [3:09:06<4:28:51,  1.38s/it]
 81%|████████  | 50179/61904 [3:09:08<4:26:25,  1.36s/it]
 81%|████████  | 50180/61904 [3:09:09<4:30:24,  1.38s/it]
                                                         
{'loss': 2.4271, 'learning_rate': 1.190003889537145e-07, 'epoch': 12.97}
+
 81%|████████  | 50180/61904 [3:09:09<4:30:24,  1.38s/it]
 81%|████████  | 50181/61904 [3:09:10<4:31:21,  1.39s/it]
 81%|████████  | 50182/61904 [3:09:12<4:25:35,  1.36s/it]
 81%|██████��█  | 50183/61904 [3:09:13<4:28:45,  1.38s/it]
 81%|████████  | 50184/61904 [3:09:14<4:21:39,  1.34s/it]
 81%|████████  | 50185/61904 [3:09:16<4:20:20,  1.33s/it]
 81%|████████  | 50186/61904 [3:09:17<4:20:46,  1.34s/it]
 81%|████████  | 50187/61904 [3:09:18<4:25:24,  1.36s/it]
 81%|████████  | 50188/61904 [3:09:20<4:22:36,  1.34s/it]
 81%|████████  | 50189/61904 [3:09:21<4:21:55,  1.34s/it]
 81%|████████  | 50190/61904 [3:09:22<4:20:52,  1.34s/it]
 81%|████████  | 50191/61904 [3:09:24<4:25:09,  1.36s/it]
 81%|████████  | 50192/61904 [3:09:25<4:22:25,  1.34s/it]
 81%|████████  | 50193/61904 [3:09:27<4:32:32,  1.40s/it]
 81%|████████  | 50194/61904 [3:09:28<4:29:20,  1.38s/it]
 81%|████████  | 50195/61904 [3:09:29<4:22:57,  1.35s/it]
 81%|████████  | 50196/61904 [3:09:31<4:19:19,  1.33s/it]
 81%|████████  | 50197/61904 [3:09:32<4:32:32,  1.40s/it]
 81%|████████  | 50198/61904 [3:09:33<4:27:51,  1.37s/it]
 81%|████████  | 50199/61904 [3:09:35<4:29:14,  1.38s/it]
 81%|████████  | 50200/61904 [3:09:36<4:27:43,  1.37s/it]
                                                         
{'loss': 2.4226, 'learning_rate': 1.1896797614417218e-07, 'epoch': 12.97}
+
 81%|████████  | 50200/61904 [3:09:36<4:27:43,  1.37s/it]
 81%|████████  | 50201/61904 [3:09:38<4:33:35,  1.40s/it]
 81%|████████  | 50202/61904 [3:09:39<4:26:53,  1.37s/it]
 81%|████████  | 50203/61904 [3:09:40<4:20:08,  1.33s/it]
 81%|████████  | 50204/61904 [3:09:42<4:23:52,  1.35s/it]
 81%|████████  | 50205/61904 [3:09:43<4:22:28,  1.35s/it]
 81%|████████  | 50206/61904 [3:09:44<4:26:10,  1.37s/it]
 81%|████████  | 50207/61904 [3:09:46<4:23:59,  1.35s/it]
 81%|████████  | 50208/61904 [3:09:47<4:29:00,  1.38s/it]
 81%|████████  | 50209/61904 [3:09:49<4:28:28,  1.38s/it]
 81%|████████  | 50210/61904 [3:09:50<4:27:09,  1.37s/it]
 81%|████████  | 50211/61904 [3:09:51<4:31:26,  1.39s/it]
 81%|████████  | 50212/61904 [3:09:53<4:41:57,  1.45s/it]
 81%|████████  | 50213/61904 [3:09:54<4:41:48,  1.45s/it]
 81%|████████  | 50214/61904 [3:09:56<4:33:42,  1.40s/it]
 81%|████████  | 50215/61904 [3:09:57<4:41:20,  1.44s/it]
 81%|████████  | 50216/61904 [3:09:59<4:43:05,  1.45s/it]
 81%|████████  | 50217/61904 [3:10:00<4:40:14,  1.44s/it]
 81%|████████  | 50218/61904 [3:10:01<4:26:53,  1.37s/it]
 81%|████████  | 50219/61904 [3:10:03<4:26:30,  1.37s/it]
 81%|████████  | 50220/61904 [3:10:04<4:27:01,  1.37s/it]
                                                         
{'loss': 2.4162, 'learning_rate': 1.1893556333462985e-07, 'epoch': 12.98}
+
 81%|████████  | 50220/61904 [3:10:04<4:27:01,  1.37s/it]
 81%|████████  | 50221/61904 [3:10:05<4:30:49,  1.39s/it]
 81%|████████  | 50222/61904 [3:10:07<4:26:33,  1.37s/it]
 81%|████████  | 50223/61904 [3:10:08<4:32:39,  1.40s/it]
 81%|████████  | 50224/61904 [3:10:10<4:28:35,  1.38s/it]
 81%|████████  | 50225/61904 [3:10:11<4:31:24,  1.39s/it]
 81%|████████  | 50226/61904 [3:10:12<4:30:10,  1.39s/it]
 81%|████████  | 50227/61904 [3:10:14<4:33:04,  1.40s/it]
 81%|████████  | 50228/61904 [3:10:15<4:38:22,  1.43s/it]
 81%|████████  | 50229/61904 [3:10:17<4:41:36,  1.45s/it]
 81%|████████  | 50230/61904 [3:10:18<4:36:48,  1.42s/it]
 81%|████████  | 50231/61904 [3:10:20<4:37:00,  1.42s/it]
 81%|████████  | 50232/61904 [3:10:21<4:35:24,  1.42s/it]
 81%|████████  | 50233/61904 [3:10:22<4:30:04,  1.39s/it]
 81%|████████  | 50234/61904 [3:10:24<4:26:04,  1.37s/it]
 81%|████████  | 50235/61904 [3:10:25<4:26:01,  1.37s/it]
 81%|████████  | 50236/61904 [3:10:26<4:30:27,  1.39s/it]
 81%|████████  | 50237/61904 [3:10:28<4:41:57,  1.45s/it]
 81%|████████  | 50238/61904 [3:10:29<4:38:01,  1.43s/it]
 81%|████████  | 50239/61904 [3:10:31<4:24:50,  1.36s/it]
 81%|████████  | 50240/61904 [3:10:32<4:42:11,  1.45s/it]
                                                         
{'loss': 2.509, 'learning_rate': 1.1890315052508751e-07, 'epoch': 12.99}
+
 81%|████████  | 50240/61904 [3:10:32<4:42:11,  1.45s/it]
 81%|████████  | 50241/61904 [3:10:34<4:33:49,  1.41s/it]
 81%|████████  | 50242/61904 [3:10:35<4:31:44,  1.40s/it]
 81%|████████  | 50243/61904 [3:10:36<4:29:26,  1.39s/it]
 81%|████████  | 50244/61904 [3:10:38<4:27:33,  1.38s/it]
 81%|████████  | 50245/61904 [3:10:39<4:38:56,  1.44s/it]
 81%|████████  | 50246/61904 [3:10:41<4:32:11,  1.40s/it]
 81%|████████  | 50247/61904 [3:10:42<4:36:50,  1.42s/it]
 81%|████████  | 50248/61904 [3:10:43<4:35:00,  1.42s/it]
 81%|████████  | 50249/61904 [3:10:45<4:25:13,  1.37s/it]
 81%|████████  | 50250/61904 [3:10:46<4:21:37,  1.35s/it]
 81%|████████  | 50251/61904 [3:10:47<4:21:41,  1.35s/it]
 81%|████████  | 50252/61904 [3:10:49<4:22:15,  1.35s/it]
 81%|████████  | 50253/61904 [3:10:50<4:31:49,  1.40s/it]
 81%|████████  | 50254/61904 [3:10:51<4:25:38,  1.37s/it]
 81%|████████  | 50255/61904 [3:10:53<4:29:31,  1.39s/it]
 81%|████████  | 50256/61904 [3:10:54<4:38:35,  1.44s/it]
 81%|████████  | 50257/61904 [3:10:56<4:29:43,  1.39s/it]
 81%|████████  | 50258/61904 [3:10:57<4:35:47,  1.42s/it]
 81%|████████  | 50259/61904 [3:10:59<4:30:21,  1.39s/it]
 81%|████████  | 50260/61904 [3:11:00<4:26:02,  1.37s/it]
                                                         
{'loss': 2.4553, 'learning_rate': 1.1887073771554518e-07, 'epoch': 12.99}
+
 81%|████████  | 50260/61904 [3:11:00<4:26:02,  1.37s/it]
 81%|████████  | 50261/61904 [3:11:01<4:27:27,  1.38s/it]
 81%|████████  | 50262/61904 [3:11:03<4:31:11,  1.40s/it]
 81%|████████  | 50263/61904 [3:11:04<4:24:37,  1.36s/it]
 81%|████████  | 50264/61904 [3:11:06<4:33:11,  1.41s/it]
 81%|████████  | 50265/61904 [3:11:07<4:21:38,  1.35s/it]
 81%|████████  | 50266/61904 [3:11:08<4:30:51,  1.40s/it]
 81%|████████  | 50267/61904 [3:11:10<4:29:10,  1.39s/it]
 81%|████████  | 50268/61904 [3:11:11<4:38:12,  1.43s/it]
 81%|████████  | 50269/61904 [3:11:13<4:46:41,  1.48s/it]
 81%|████████  | 50270/61904 [3:11:14<4:40:25,  1.45s/it]
 81%|████████  | 50271/61904 [3:11:16<4:38:16,  1.44s/it]
 81%|████████  | 50272/61904 [3:11:17<4:28:34,  1.39s/it]
 81%|████████  | 50273/61904 [3:11:18<4:32:14,  1.40s/it]
 81%|████████  | 50274/61904 [3:11:20<4:30:32,  1.40s/it]
 81%|████████  | 50275/61904 [3:11:21<4:39:56,  1.44s/it]
 81%|████████  | 50276/61904 [3:11:22<4:29:56,  1.39s/it]
 81%|████████  | 50277/61904 [3:11:24<4:26:11,  1.37s/it]
 81%|████████  | 50278/61904 [3:11:25<4:22:31,  1.35s/it]
 81%|████████  | 50279/61904 [3:11:26<4:22:43,  1.36s/it]
 81%|████████  | 50280/61904 [3:11:28<4:40:49,  1.45s/it]
                                                         
{'loss': 2.4558, 'learning_rate': 1.1883832490600286e-07, 'epoch': 13.0}
+
 81%|████████  | 50280/61904 [3:11:28<4:40:49,  1.45s/it]
 81%|████████  | 50281/61904 [3:11:29<4:30:59,  1.40s/it]
 81%|████████  | 50282/61904 [3:11:31<4:35:58,  1.42s/it]
 81%|████████  | 50283/61904 [3:11:32<4:28:34,  1.39s/it]
 81%|████████  | 50284/61904 [3:11:34<4:25:46,  1.37s/it]
 81%|████████  | 50285/61904 [3:11:35<4:18:56,  1.34s/it]
 81%|████████  | 50286/61904 [3:11:36<4:18:29,  1.33s/it]
 81%|████████  | 50287/61904 [3:11:38<4:31:02,  1.40s/it]
 81%|████████  | 50288/61904 [3:11:39<4:30:42,  1.40s/it]
 81%|████████  | 50289/61904 [3:11:40<4:24:24,  1.37s/it]
 81%|████████  | 50290/61904 [3:11:42<4:23:29,  1.36s/it]
 81%|████████  | 50291/61904 [3:11:43<4:26:52,  1.38s/it]
 81%|████████  | 50292/61904 [3:11:45<4:31:56,  1.41s/it]
 81%|████████  | 50293/61904 [3:11:46<4:34:31,  1.42s/it]
 81%|████████  | 50294/61904 [3:11:48<4:39:07,  1.44s/it]
 81%|████████  | 50295/61904 [3:11:49<4:38:51,  1.44s/it]
 81%|████████  | 50296/61904 [3:11:50<4:35:51,  1.43s/it]
 81%|████████▏ | 50297/61904 [3:11:52<4:28:06,  1.39s/it]
 81%|████████▏ | 50298/61904 [3:11:53<4:26:24,  1.38s/it]Generation Kwargs:
+{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}
+
+
  0%|          | 0/861 [00:00<?, ?it/s]
+
  0%|          | 2/861 [00:01<08:30,  1.68it/s]
+
  0%|          | 3/861 [00:02<15:17,  1.07s/it]
+
  0%|          | 4/861 [00:03<14:05,  1.01it/s]
+
  1%|          | 5/861 [00:04<14:14,  1.00it/s]
+
  1%|          | 6/861 [00:06<15:30,  1.09s/it]
+
  1%|          | 7/861 [00:06<12:41,  1.12it/s]
+
  1%|          | 8/861 [00:07<11:56,  1.19it/s]
+
  1%|          | 9/861 [00:07<11:24,  1.24it/s]
+
  1%|          | 10/861 [00:08<11:21,  1.25it/s]
+
  1%|▏         | 11/861 [00:10<14:10,  1.00s/it]
+
  1%|▏         | 12/861 [00:11<15:12,  1.08s/it]
+
  2%|▏         | 13/861 [00:12<14:03,  1.01it/s]
+
  2%|▏         | 14/861 [00:12<11:03,  1.28it/s]
+
  2%|▏         | 15/861 [00:13<09:58,  1.41it/s]
+
  2%|▏         | 16/861 [00:13<08:25,  1.67it/s]
+
  2%|▏         | 17/861 [00:14<11:23,  1.23it/s]
+
  2%|▏         | 18/861 [00:15<09:18,  1.51it/s]
+
  2%|▏         | 19/861 [00:16<14:05,  1.00s/it]
+
  2%|▏         | 20/861 [00:18<14:33,  1.04s/it]
+
  2%|▏         | 21/861 [00:19<16:54,  1.21s/it]
+
  3%|▎         | 22/861 [00:21<17:47,  1.27s/it]
+
  3%|▎         | 23/861 [00:21<13:47,  1.01it/s]
+
  3%|▎         | 24/861 [00:22<16:13,  1.16s/it]
+
  3%|▎         | 25/861 [00:23<14:43,  1.06s/it]
+
  3%|▎         | 26/861 [00:24<15:10,  1.09s/it]
+
  3%|▎         | 27/861 [00:26<16:09,  1.16s/it]
+
  3%|▎         | 28/861 [00:28<20:58,  1.51s/it]
+
  3%|▎         | 29/861 [00:28<16:04,  1.16s/it]
+
  3%|▎         | 30/861 [00:30<16:30,  1.19s/it]
+
  4%|▎         | 31/861 [00:30<13:44,  1.01it/s]
+
  4%|▎         | 32/861 [00:31<11:17,  1.22it/s]
+
  4%|▍         | 33/861 [00:32<12:14,  1.13it/s]
+
  4%|▍         | 34/861 [00:33<12:14,  1.13it/s]
+
  4%|▍         | 35/861 [00:35<17:12,  1.25s/it]
+
  4%|▍         | 36/861 [00:35<15:19,  1.11s/it]
+
  4%|▍         | 37/861 [00:36<14:28,  1.05s/it]
+
  4%|▍         | 38/861 [00:38<15:20,  1.12s/it]
+
  5%|▍         | 39/861 [00:38<13:36,  1.01it/s]
+
  5%|▍         | 40/861 [00:39<12:29,  1.10it/s]
+
  5%|▍         | 41/861 [00:39<10:05,  1.35it/s]
+
  5%|▍         | 42/861 [00:41<11:47,  1.16it/s]
+
  5%|▍         | 43/861 [00:42<12:49,  1.06it/s]
+
  5%|▌         | 44/861 [00:42<12:23,  1.10it/s]
+
  5%|▌         | 45/861 [00:43<12:14,  1.11it/s]
+
  5%|▌         | 46/861 [00:45<16:34,  1.22s/it]
+
  5%|▌         | 47/861 [00:47<16:51,  1.24s/it]
+
  6%|▌         | 48/861 [00:48<18:24,  1.36s/it]
+
  6%|▌         | 49/861 [00:49<17:53,  1.32s/it]
+
  6%|▌         | 50/861 [00:50<13:13,  1.02it/s]
+
  6%|▌         | 51/861 [00:51<13:40,  1.01s/it]
+
  6%|▌         | 52/861 [00:51<12:23,  1.09it/s]
+
  6%|▌         | 53/861 [00:52<11:13,  1.20it/s]
+
  6%|▋         | 54/861 [00:52<08:47,  1.53it/s]
+
  6%|▋         | 55/861 [00:53<08:24,  1.60it/s]
+
  7%|▋         | 56/861 [00:54<09:18,  1.44it/s]
+
  7%|▋         | 57/861 [00:54<07:44,  1.73it/s]
+
  7%|▋         | 58/861 [00:54<06:35,  2.03it/s]
+
  7%|▋         | 59/861 [00:55<08:07,  1.65it/s]
+
  7%|▋         | 60/861 [00:56<07:46,  1.72it/s]
+
  7%|▋         | 61/861 [00:56<06:59,  1.91it/s]
+
  7%|▋         | 62/861 [00:57<06:21,  2.09it/s]
+
  7%|▋         | 63/861 [00:57<06:19,  2.10it/s]
+
  7%|▋         | 64/861 [00:57<06:08,  2.16it/s]
+
  8%|▊         | 65/861 [00:58<06:08,  2.16it/s]
+
  8%|▊         | 66/861 [00:58<06:14,  2.13it/s]
+
  8%|▊         | 67/861 [00:59<07:36,  1.74it/s]
+
  8%|▊         | 68/861 [01:00<09:02,  1.46it/s]
+
  8%|▊         | 69/861 [01:01<10:25,  1.27it/s]
+
  8%|▊         | 70/861 [01:03<12:57,  1.02it/s]
+
  8%|▊         | 71/861 [01:04<14:28,  1.10s/it]
+
  8%|▊         | 72/861 [01:05<13:37,  1.04s/it]
+
  8%|▊         | 73/861 [01:05<10:32,  1.25it/s]
+
  9%|▊         | 74/861 [01:06<09:31,  1.38it/s]
+
  9%|▊         | 75/861 [01:07<11:08,  1.18it/s]
+
  9%|▉         | 76/861 [01:07<09:43,  1.35it/s]
+
  9%|▉         | 77/861 [01:08<10:58,  1.19it/s]
+
  9%|▉         | 78/861 [01:09<10:32,  1.24it/s]
+
  9%|▉         | 79/861 [01:10<11:38,  1.12it/s]
+
  9%|▉         | 80/861 [01:11<10:14,  1.27it/s]
+
  9%|▉         | 81/861 [01:12<10:48,  1.20it/s]
+
 10%|▉         | 82/861 [01:12<09:21,  1.39it/s]
+
 10%|▉         | 83/861 [01:13<09:17,  1.39it/s]
+
 10%|▉         | 84/861 [01:14<11:13,  1.15it/s]
+
 10%|▉         | 85/861 [01:15<10:14,  1.26it/s]
+
 10%|▉         | 86/861 [01:15<09:02,  1.43it/s]
+
 10%|█         | 87/861 [01:16<10:46,  1.20it/s]
+
 10%|█         | 88/861 [01:16<08:14,  1.56it/s]
+
 10%|█         | 89/861 [01:17<08:15,  1.56it/s]
+
 10%|█         | 90/861 [01:19<13:49,  1.08s/it]
+
 11%|█         | 91/861 [01:20<11:58,  1.07it/s]
+
 11%|█         | 92/861 [01:21<11:46,  1.09it/s]
+
 11%|█         | 93/861 [01:22<12:03,  1.06it/s]
+
 11%|█         | 94/861 [01:22<09:28,  1.35it/s]
+
 11%|█         | 95/861 [01:23<09:12,  1.39it/s]
+
 11%|█         | 96/861 [01:24<10:11,  1.25it/s]
+
 11%|█▏        | 97/861 [01:25<11:57,  1.07it/s]
+
 11%|█▏        | 98/861 [01:26<12:02,  1.06it/s]
+
 11%|█▏        | 99/861 [01:28<14:43,  1.16s/it]
+
 12%|█▏        | 100/861 [01:28<12:23,  1.02it/s]
+
 12%|█▏        | 101/861 [01:29<10:38,  1.19it/s]
+
 12%|█▏        | 102/861 [01:29<09:26,  1.34it/s]
+
 12%|█▏        | 103/861 [01:29<08:03,  1.57it/s]
+
 12%|█▏        | 104/861 [01:31<11:39,  1.08it/s]
+
 12%|█▏        | 105/861 [01:32<12:12,  1.03it/s]
+
 12%|█▏        | 106/861 [01:33<10:44,  1.17it/s]
+
 12%|█▏        | 107/861 [01:33<09:26,  1.33it/s]
+
 13%|█▎        | 108/861 [01:33<07:31,  1.67it/s]
+
 13%|█▎        | 109/861 [01:34<06:12,  2.02it/s]
+
 13%|█▎        | 110/861 [01:35<07:22,  1.70it/s]
+
 13%|█▎        | 111/861 [01:36<09:41,  1.29it/s]
+
 13%|█▎        | 112/861 [01:36<07:54,  1.58it/s]
+
 13%|█▎        | 113/861 [01:37<08:15,  1.51it/s]
+
 13%|█▎        | 114/861 [01:38<08:36,  1.45it/s]
+
 13%|█▎        | 115/861 [01:38<07:40,  1.62it/s]
+
 13%|█▎        | 116/861 [01:38<06:38,  1.87it/s]
+
 14%|█▎        | 117/861 [01:40<09:30,  1.30it/s]
+
 14%|█▎        | 118/861 [01:40<09:31,  1.30it/s]
+
 14%|█▍        | 119/861 [01:41<08:55,  1.39it/s]
+
 14%|█▍        | 120/861 [01:41<07:00,  1.76it/s]
+
 14%|█▍        | 121/861 [01:42<08:38,  1.43it/s]
+
 14%|█▍        | 122/861 [01:43<10:35,  1.16it/s]
+
 14%|█▍        | 123/861 [01:44<10:02,  1.23it/s]
+
 14%|█▍        | 124/861 [01:46<12:43,  1.04s/it]
+
 15%|█▍        | 125/861 [01:46<11:29,  1.07it/s]
+
 15%|█▍        | 126/861 [01:48<12:32,  1.02s/it]
+
 15%|█▍        | 127/861 [01:49<13:10,  1.08s/it]
+
 15%|█▍        | 128/861 [01:49<11:02,  1.11it/s]
+
 15%|█▍        | 129/861 [01:50<11:39,  1.05it/s]
+
 15%|█▌        | 130/861 [01:51<11:17,  1.08it/s]
+
 15%|█▌        | 131/861 [01:52<10:38,  1.14it/s]
+
 15%|█▌        | 132/861 [01:53<10:45,  1.13it/s]
+
 15%|█▌        | 133/861 [01:54<10:49,  1.12it/s]
+
 16%|█▌        | 134/861 [01:54<08:16,  1.46it/s]
+
 16%|█▌        | 135/861 [01:54<07:16,  1.66it/s]
+
 16%|█▌        | 136/861 [01:55<07:08,  1.69it/s]
+
 16%|█▌        | 137/861 [01:55<06:17,  1.92it/s]
+
 16%|█▌        | 138/861 [01:56<05:59,  2.01it/s]
+
 16%|█▌        | 139/861 [01:56<05:28,  2.20it/s]
+
 16%|█▋        | 140/861 [01:57<05:12,  2.30it/s]
+
 16%|█▋        | 141/861 [01:57<05:01,  2.39it/s]
+
 16%|█▋        | 142/861 [01:57<04:58,  2.41it/s]
+
 17%|█▋        | 143/861 [01:59<08:23,  1.43it/s]
+
 17%|█▋        | 144/861 [02:00<09:53,  1.21it/s]
+
 17%|█▋        | 145/861 [02:00<08:39,  1.38it/s]
+
 17%|█▋        | 146/861 [02:01<08:22,  1.42it/s]
+
 17%|█▋        | 147/861 [02:02<08:43,  1.36it/s]
+
 17%|█▋        | 148/861 [02:02<06:56,  1.71it/s]
+
 17%|█▋        | 149/861 [02:02<06:13,  1.90it/s]
+
 17%|█▋        | 150/861 [02:04<10:06,  1.17it/s]
+
 18%|█▊        | 151/861 [02:06<12:52,  1.09s/it]
+
 18%|█▊        | 152/861 [02:07<12:48,  1.08s/it]
+
 18%|█▊        | 153/861 [02:08<12:10,  1.03s/it]
+
 18%|█▊        | 154/861 [02:08<09:49,  1.20it/s]
+
 18%|█▊        | 155/861 [02:10<12:32,  1.07s/it]
+
 18%|█▊        | 156/861 [02:11<12:50,  1.09s/it]
+
 18%|█▊        | 157/861 [02:12<11:32,  1.02it/s]
+
 18%|█▊        | 158/861 [02:12<11:16,  1.04it/s]
+
 18%|█▊        | 159/861 [02:13<09:59,  1.17it/s]
+
 19%|█▊        | 160/861 [02:14<09:48,  1.19it/s]
+
 19%|█▊        | 161/861 [02:16<13:35,  1.16s/it]
+
 19%|█▉        | 162/861 [02:16<10:25,  1.12it/s]
+
 19%|█▉        | 163/861 [02:16<08:08,  1.43it/s]
+
 19%|█▉        | 164/861 [02:18<10:13,  1.14it/s]
+
 19%|█▉        | 165/861 [02:18<09:43,  1.19it/s]
+
 19%|█▉        | 166/861 [02:19<09:44,  1.19it/s]
+
 19%|█▉        | 167/861 [02:19<07:25,  1.56it/s]
+
 20%|█▉        | 168/861 [02:20<06:51,  1.68it/s]
+
 20%|█▉        | 169/861 [02:21<08:01,  1.44it/s]
+
 20%|█▉        | 170/861 [02:22<08:22,  1.38it/s]
+
 20%|█▉        | 171/861 [02:22<08:15,  1.39it/s]
+
 20%|█▉        | 172/861 [02:23<07:24,  1.55it/s]
+
 20%|██        | 173/861 [02:23<07:32,  1.52it/s]
+
 20%|██        | 174/861 [02:25<10:56,  1.05it/s]
+
 20%|██        | 175/861 [02:26<10:21,  1.10it/s]
+
 20%|██        | 176/861 [02:26<07:56,  1.44it/s]
+
 21%|██        | 177/861 [02:27<07:51,  1.45it/s]
+
 21%|██        | 178/861 [02:28<08:38,  1.32it/s]
+
 21%|██        | 179/861 [02:28<08:32,  1.33it/s]
+
 21%|██        | 180/861 [02:29<08:09,  1.39it/s]
+
 21%|██        | 181/861 [02:29<07:01,  1.61it/s]
+
 21%|██        | 182/861 [02:30<06:20,  1.78it/s]
+
 21%|██▏       | 183/861 [02:31<07:29,  1.51it/s]
+
 21%|██▏       | 184/861 [02:32<08:56,  1.26it/s]
+
 21%|██▏       | 185/861 [02:32<07:55,  1.42it/s]
+
 22%|██▏       | 186/861 [02:33<06:47,  1.66it/s]
+
 22%|██▏       | 187/861 [02:34<07:57,  1.41it/s]
+
 22%|██▏       | 188/861 [02:35<08:37,  1.30it/s]
+
 22%|██▏       | 189/861 [02:36<11:08,  1.00it/s]
+
 22%|██▏       | 190/861 [02:38<12:43,  1.14s/it]
+
 22%|██▏       | 191/861 [02:38<10:25,  1.07it/s]
+
 22%|██▏       | 192/861 [02:39<09:51,  1.13it/s]
+
 22%|██▏       | 193/861 [02:40<10:59,  1.01it/s]
+
 23%|██▎       | 194/861 [02:41<09:23,  1.18it/s]
+
 23%|██▎       | 195/861 [02:41<08:00,  1.39it/s]
+
 23%|██▎       | 196/861 [02:41<07:08,  1.55it/s]
+
 23%|██▎       | 197/861 [02:42<06:35,  1.68it/s]
+
 23%|██▎       | 198/861 [02:42<05:45,  1.92it/s]
+
 23%|██▎       | 199/861 [02:44<08:16,  1.33it/s]
+
 23%|██▎       | 200/861 [02:45<09:10,  1.20it/s]
+
 23%|██▎       | 201/861 [02:46<09:53,  1.11it/s]
+
 23%|██▎       | 202/861 [02:47<10:31,  1.04it/s]
+
 24%|██▎       | 203/861 [02:47<08:17,  1.32it/s]
+
 24%|██▎       | 204/861 [02:47<06:22,  1.72it/s]
+
 24%|██▍       | 205/861 [02:48<05:48,  1.88it/s]
+
 24%|██▍       | 206/861 [02:48<06:20,  1.72it/s]
+
 24%|██▍       | 207/861 [02:49<07:01,  1.55it/s]
+
 24%|██▍       | 208/861 [02:50<07:13,  1.51it/s]
+
 24%|██▍       | 209/861 [02:50<06:59,  1.55it/s]
+
 24%|██▍       | 210/861 [02:51<07:29,  1.45it/s]
+
 25%|██▍       | 211/861 [02:53<09:52,  1.10it/s]
+
 25%|██▍       | 212/861 [02:54<09:48,  1.10it/s]
+
 25%|██▍       | 213/861 [02:54<08:27,  1.28it/s]
+
 25%|██▍       | 214/861 [02:55<07:43,  1.40it/s]
+
 25%|██▍       | 215/861 [02:55<08:16,  1.30it/s]
+
 25%|██▌       | 216/861 [02:56<07:10,  1.50it/s]
+
 25%|██▌       | 217/861 [02:56<05:53,  1.82it/s]
+
 25%|██▌       | 218/861 [02:57<05:20,  2.00it/s]
+
 25%|██▌       | 219/861 [02:58<06:54,  1.55it/s]
+
 26%|██▌       | 220/861 [02:58<07:06,  1.50it/s]
+
 26%|██▌       | 221/861 [02:59<06:30,  1.64it/s]
+
 26%|██▌       | 222/861 [03:00<08:36,  1.24it/s]
+
 26%|██▌       | 223/861 [03:01<09:13,  1.15it/s]
+
 26%|██▌       | 224/861 [03:02<08:20,  1.27it/s]
+
 26%|██▌       | 225/861 [03:03<10:08,  1.05it/s]
+
 26%|██▌       | 226/861 [03:05<11:57,  1.13s/it]
+
 26%|██▋       | 227/861 [03:05<10:59,  1.04s/it]
+
 26%|██▋       | 228/861 [03:06<10:49,  1.03s/it]
+
 27%|██▋       | 229/861 [03:07<09:18,  1.13it/s]
+
 27%|██▋       | 230/861 [03:08<09:36,  1.09it/s]
+
 27%|██▋       | 231/861 [03:10<14:43,  1.40s/it]
+
 27%|██▋       | 232/861 [03:11<10:50,  1.03s/it]
+
 27%|██▋       | 233/861 [03:11<09:52,  1.06it/s]
+
 27%|██▋       | 234/861 [03:12<08:42,  1.20it/s]
+
 27%|██▋       | 235/861 [03:13<08:54,  1.17it/s]
+
 27%|██▋       | 236/861 [03:13<08:23,  1.24it/s]
+
 28%|██▊       | 237/861 [03:14<08:08,  1.28it/s]
+
 28%|██▊       | 238/861 [03:15<06:39,  1.56it/s]
+
 28%|██▊       | 239/861 [03:16<08:07,  1.28it/s]
+
 28%|██▊       | 240/861 [03:16<08:07,  1.27it/s]
+
 28%|██▊       | 241/861 [03:18<10:05,  1.02it/s]
+
 28%|██▊       | 242/861 [03:18<08:42,  1.18it/s]
+
 28%|██▊       | 243/861 [03:20<09:36,  1.07it/s]
+
 28%|██▊       | 244/861 [03:20<09:03,  1.13it/s]
+
 28%|██▊       | 245/861 [03:22<10:32,  1.03s/it]
+
 29%|██▊       | 246/861 [03:23<10:07,  1.01it/s]
+
 29%|██▊       | 247/861 [03:23<08:09,  1.25it/s]
+
 29%|██▉       | 248/861 [03:23<06:14,  1.64it/s]
+
 29%|██▉       | 249/861 [03:24<05:59,  1.70it/s]
+
 29%|██▉       | 250/861 [03:25<07:14,  1.41it/s]
+
 29%|██▉       | 251/861 [03:25<07:36,  1.34it/s]
+
 29%|██▉       | 252/861 [03:26<07:23,  1.37it/s]
+
 29%|██▉       | 253/861 [03:27<06:51,  1.48it/s]
+
 30%|██▉       | 254/861 [03:27<05:37,  1.80it/s]
+
 30%|██▉       | 255/861 [03:28<06:13,  1.62it/s]
+
 30%|██▉       | 256/861 [03:29<08:21,  1.21it/s]
+
 30%|██▉       | 257/861 [03:30<09:04,  1.11it/s]
+
 30%|██▉       | 258/861 [03:31<09:28,  1.06it/s]
+
 30%|███       | 259/861 [03:32<10:04,  1.00s/it]
+
 30%|███       | 260/861 [03:33<09:32,  1.05it/s]
+
 30%|███       | 261/861 [03:36<13:45,  1.38s/it]
+
 30%|███       | 262/861 [03:36<11:26,  1.15s/it]
+
 31%|███       | 263/861 [03:36<08:30,  1.17it/s]
+
 31%|███       | 264/861 [03:37<08:13,  1.21it/s]
+
 31%|███       | 265/861 [03:38<07:07,  1.39it/s]
+
 31%|███       | 266/861 [03:38<05:54,  1.68it/s]
+
 31%|███       | 267/861 [03:38<05:38,  1.75it/s]
+
 31%|███       | 268/861 [03:39<05:59,  1.65it/s]
+
 31%|███       | 269/861 [03:40<06:07,  1.61it/s]
+
 31%|███▏      | 270/861 [03:40<06:40,  1.48it/s]
+
 31%|███▏      | 271/861 [03:41<06:55,  1.42it/s]
+
 32%|███▏      | 272/861 [03:42<08:30,  1.15it/s]
+
 32%|███▏      | 273/861 [03:43<08:46,  1.12it/s]
+
 32%|███▏      | 274/861 [03:45<10:18,  1.05s/it]
+
 32%|███▏      | 275/861 [03:45<07:43,  1.26it/s]
+
 32%|███▏      | 276/861 [03:46<08:16,  1.18it/s]
+
 32%|███▏      | 277/861 [03:47<09:52,  1.01s/it]
+
 32%|███▏      | 278/861 [03:49<10:41,  1.10s/it]
+
 32%|███▏      | 279/861 [03:50<09:55,  1.02s/it]
+
 33%|███▎      | 280/861 [03:51<09:53,  1.02s/it]
+
 33%|███▎      | 281/861 [03:52<10:57,  1.13s/it]
+
 33%|███▎      | 282/861 [03:53<09:58,  1.03s/it]
+
 33%|███▎      | 283/861 [03:54<08:58,  1.07it/s]
+
 33%|███▎      | 284/861 [03:54<07:24,  1.30it/s]
+
 33%|███▎      | 285/861 [03:55<06:58,  1.38it/s]
+
 33%|███▎      | 286/861 [03:57<11:11,  1.17s/it]
+
 33%|███▎      | 287/861 [03:59<13:06,  1.37s/it]
+
 33%|███▎      | 288/861 [04:00<11:53,  1.25s/it]
+
 34%|███▎      | 289/861 [04:00<09:21,  1.02it/s]
+
 34%|███▎      | 290/861 [04:01<08:19,  1.14it/s]
+
 34%|███▍      | 291/861 [04:01<07:59,  1.19it/s]
+
 34%|███▍      | 292/861 [04:02<08:55,  1.06it/s]
+
 34%|███▍      | 293/861 [04:03<08:53,  1.07it/s]
+
 34%|███▍      | 294/861 [04:05<09:24,  1.00it/s]
+
 34%|███▍      | 295/861 [04:05<07:12,  1.31it/s]
+
 34%|███▍      | 296/861 [04:05<06:53,  1.37it/s]
+
 34%|███▍      | 297/861 [04:07<08:37,  1.09it/s]
+
 35%|███▍      | 298/861 [04:08<09:32,  1.02s/it]
+
 35%|███▍      | 299/861 [04:10<12:15,  1.31s/it]
+
 35%|███▍      | 300/861 [04:11<10:27,  1.12s/it]
+
 35%|███▍      | 301/861 [04:13<13:53,  1.49s/it]
+
 35%|███▌      | 302/861 [04:13<10:24,  1.12s/it]
+
 35%|███▌      | 303/861 [04:15<11:16,  1.21s/it]
+
 35%|███▌      | 304/861 [04:16<10:45,  1.16s/it]
+
 35%|███▌      | 305/861 [04:17<11:46,  1.27s/it]
+
 36%|███▌      | 306/861 [04:19<12:40,  1.37s/it]
+
 36%|███▌      | 307/861 [04:21<14:14,  1.54s/it]
+
 36%|███▌      | 308/861 [04:21<10:27,  1.13s/it]
+
 36%|███▌      | 309/861 [04:21<08:13,  1.12it/s]
+
 36%|███▌      | 310/861 [04:22<07:31,  1.22it/s]
+
 36%|███▌      | 311/861 [04:23<07:56,  1.15it/s]
+
 36%|███▌      | 312/861 [04:24<08:29,  1.08it/s]
+
 36%|███▋      | 313/861 [04:26<10:14,  1.12s/it]
+
 36%|███▋      | 314/861 [04:27<09:48,  1.08s/it]
+
 37%|███▋      | 315/861 [04:27<08:29,  1.07it/s]
+
 37%|███▋      | 316/861 [04:28<09:08,  1.01s/it]
+
 37%|███▋      | 317/861 [04:29<06:59,  1.30it/s]
+
 37%|███▋      | 318/861 [04:29<05:36,  1.62it/s]
+
 37%|███▋      | 319/861 [04:31<08:31,  1.06it/s]
+
 37%|███▋      | 320/861 [04:31<08:03,  1.12it/s]
+
 37%|███▋      | 321/861 [04:33<09:28,  1.05s/it]
+
 37%|███▋      | 322/861 [04:35<11:36,  1.29s/it]
+
 38%|███▊      | 323/861 [04:35<10:15,  1.14s/it]
+
 38%|███▊      | 324/861 [04:37<10:55,  1.22s/it]
+
 38%|███▊      | 325/861 [04:38<11:06,  1.24s/it]
+
 38%|███▊      | 326/861 [04:38<08:13,  1.08it/s]
+
 38%|███▊      | 327/861 [04:39<08:22,  1.06it/s]
+
 38%|███▊      | 328/861 [04:40<08:32,  1.04it/s]
+
 38%|███▊      | 329/861 [04:41<08:08,  1.09it/s]
+
 38%|███▊      | 330/861 [04:42<07:36,  1.16it/s]
+
 38%|███▊      | 331/861 [04:45<13:48,  1.56s/it]
+
 39%|███▊      | 332/861 [04:46<11:59,  1.36s/it]
+
 39%|███▊      | 333/861 [04:47<12:22,  1.41s/it]
+
 39%|███▉      | 334/861 [04:49<12:22,  1.41s/it]
+
 39%|███▉      | 335/861 [04:50<11:00,  1.26s/it]
+
 39%|███▉      | 336/861 [04:51<11:36,  1.33s/it]
+
 39%|███▉      | 337/861 [04:52<09:42,  1.11s/it]
+
 39%|███▉      | 338/861 [04:54<12:16,  1.41s/it]
+
 39%|███▉      | 339/861 [04:55<11:04,  1.27s/it]
+
 39%|███▉      | 340/861 [04:55<08:45,  1.01s/it]
+
 40%|███▉      | 341/861 [04:56<06:52,  1.26it/s]
+
 40%|███▉      | 342/861 [04:56<06:33,  1.32it/s]
+
 40%|███▉      | 343/861 [04:57<06:52,  1.26it/s]
+
 40%|███▉      | 344/861 [04:58<06:01,  1.43it/s]
+
 40%|████      | 345/861 [04:59<07:00,  1.23it/s]
+
 40%|████      | 346/861 [05:00<07:24,  1.16it/s]
+
 40%|████      | 347/861 [05:00<06:15,  1.37it/s]
+
 40%|████      | 348/861 [05:01<05:56,  1.44it/s]
+
 41%|████      | 349/861 [05:01<05:59,  1.43it/s]
+
 41%|████      | 350/861 [05:02<06:38,  1.28it/s]
+
 41%|████      | 351/861 [05:03<06:19,  1.34it/s]
+
 41%|████      | 352/861 [05:04<06:24,  1.32it/s]
+
 41%|████      | 353/861 [05:04<06:13,  1.36it/s]
+
 41%|████      | 354/861 [05:05<05:56,  1.42it/s]
+
 41%|████      | 355/861 [05:06<05:14,  1.61it/s]
+
 41%|████▏     | 356/861 [05:06<04:44,  1.78it/s]
+
 41%|████▏     | 357/861 [05:06<04:02,  2.07it/s]
+
 42%|████▏     | 358/861 [05:07<04:47,  1.75it/s]
+
 42%|████▏     | 359/861 [05:09<07:31,  1.11it/s]
+
 42%|████▏     | 360/861 [05:10<08:04,  1.03it/s]
+
 42%|████▏     | 361/861 [05:11<07:45,  1.07it/s]
+
 42%|████▏     | 362/861 [05:12<08:06,  1.03it/s]
+
 42%|████▏     | 363/861 [05:12<07:11,  1.15it/s]
+
 42%|████▏     | 364/861 [05:13<06:36,  1.25it/s]
+
 42%|████▏     | 365/861 [05:15<09:36,  1.16s/it]
+
 43%|████▎     | 366/861 [05:16<09:08,  1.11s/it]
+
 43%|████▎     | 367/861 [05:18<10:35,  1.29s/it]
+
 43%|████▎     | 368/861 [05:19<09:36,  1.17s/it]
+
 43%|████▎     | 369/861 [05:19<08:29,  1.04s/it]
+
 43%|████▎     | 370/861 [05:20<07:28,  1.10it/s]
+
 43%|████▎     | 371/861 [05:21<07:06,  1.15it/s]
+
 43%|████▎     | 372/861 [05:22<07:35,  1.07it/s]
+
 43%|████▎     | 373/861 [05:22<06:49,  1.19it/s]
+
 43%|████▎     | 374/861 [05:25<10:05,  1.24s/it]
+
 44%|████▎     | 375/861 [05:26<11:18,  1.40s/it]
+
 44%|████▎     | 376/861 [05:27<09:36,  1.19s/it]
+
 44%|████▍     | 377/861 [05:29<11:06,  1.38s/it]
+
 44%|████▍     | 378/861 [05:31<12:31,  1.56s/it]
+
 44%|████▍     | 379/861 [05:31<09:10,  1.14s/it]
+
 44%|████▍     | 380/861 [05:32<08:42,  1.09s/it]
+
 44%|████▍     | 381/861 [05:33<08:23,  1.05s/it]
+
 44%|████▍     | 382/861 [05:34<07:25,  1.07it/s]
+
 44%|████▍     | 383/861 [05:35<07:35,  1.05it/s]
+
 45%|████▍     | 384/861 [05:35<07:08,  1.11it/s]
+
 45%|████▍     | 385/861 [05:36<05:49,  1.36it/s]
+
 45%|████▍     | 386/861 [05:37<07:29,  1.06it/s]
+
 45%|████▍     | 387/861 [05:39<08:36,  1.09s/it]
+
 45%|████▌     | 388/861 [05:39<07:42,  1.02it/s]
+
 45%|████▌     | 389/861 [05:40<06:25,  1.22it/s]
+
 45%|████▌     | 390/861 [05:40<05:59,  1.31it/s]
+
 45%|████▌     | 391/861 [05:41<06:12,  1.26it/s]
+
 46%|████▌     | 392/861 [05:42<06:25,  1.22it/s]
+
 46%|████▌     | 393/861 [05:43<07:28,  1.04it/s]
+
 46%|████▌     | 394/861 [05:45<08:08,  1.05s/it]
+
 46%|████▌     | 395/861 [05:45<07:01,  1.11it/s]
+
 46%|████▌     | 396/861 [05:46<05:56,  1.30it/s]
+
 46%|████▌     | 397/861 [05:46<04:35,  1.68it/s]
+
 46%|████▌     | 398/861 [05:47<04:48,  1.61it/s]
+
 46%|████▋     | 399/861 [05:48<05:42,  1.35it/s]
+
 46%|████▋     | 400/861 [05:49<06:23,  1.20it/s]
+
 47%|████▋     | 401/861 [05:49<05:28,  1.40it/s]
+
 47%|████▋     | 402/861 [05:50<05:41,  1.34it/s]
+
 47%|████▋     | 403/861 [05:51<05:33,  1.37it/s]
+
 47%|████▋     | 404/861 [05:52<06:16,  1.21it/s]
+
 47%|████▋     | 405/861 [05:52<05:13,  1.45it/s]
+
 47%|████▋     | 406/861 [05:53<06:11,  1.23it/s]
+
 47%|████▋     | 407/861 [05:54<06:37,  1.14it/s]
+
 47%|████▋     | 408/861 [05:55<06:03,  1.25it/s]
+
 48%|████▊     | 409/861 [05:55<05:23,  1.40it/s]
+
 48%|████▊     | 410/861 [05:56<05:26,  1.38it/s]
+
 48%|████▊     | 411/861 [05:56<04:34,  1.64it/s]
+
 48%|████▊     | 412/861 [05:57<05:23,  1.39it/s]
+
 48%|████▊     | 413/861 [05:58<05:22,  1.39it/s]
+
 48%|████▊     | 414/861 [05:59<04:53,  1.52it/s]
+
 48%|████▊     | 415/861 [05:59<04:19,  1.72it/s]
+
 48%|████▊     | 416/861 [06:00<04:14,  1.75it/s]
+
 48%|████▊     | 417/861 [06:00<04:36,  1.61it/s]
+
 49%|████▊     | 418/861 [06:01<04:16,  1.73it/s]
+
 49%|████▊     | 419/861 [06:02<04:58,  1.48it/s]
+
 49%|████▉     | 420/861 [06:02<04:53,  1.50it/s]
+
 49%|████▉     | 421/861 [06:03<04:31,  1.62it/s]
+
 49%|████▉     | 422/861 [06:03<03:50,  1.90it/s]
+
 49%|████▉     | 423/861 [06:04<04:47,  1.52it/s]
+
 49%|████▉     | 424/861 [06:05<04:24,  1.66it/s]
+
 49%|████▉     | 425/861 [06:05<04:39,  1.56it/s]
+
 49%|████▉     | 426/861 [06:07<05:58,  1.21it/s]
+
 50%|████▉     | 427/861 [06:07<05:56,  1.22it/s]
+
 50%|████▉     | 428/861 [06:08<05:38,  1.28it/s]
+
 50%|████▉     | 429/861 [06:09<06:01,  1.19it/s]
+
 50%|████▉     | 430/861 [06:10<06:17,  1.14it/s]
+
 50%|█████     | 431/861 [06:11<07:21,  1.03s/it]
+
 50%|█████     | 432/861 [06:13<08:12,  1.15s/it]
+
 50%|█████     | 433/861 [06:14<08:22,  1.17s/it]
+
 50%|█████     | 434/861 [06:14<06:51,  1.04it/s]
+
 51%|█████     | 435/861 [06:15<05:09,  1.37it/s]
+
 51%|█████     | 436/861 [06:15<04:12,  1.68it/s]
+
 51%|█████     | 437/861 [06:15<04:00,  1.76it/s]
+
 51%|█████     | 438/861 [06:16<03:29,  2.02it/s]
+
 51%|█████     | 439/861 [06:16<03:49,  1.84it/s]
+
 51%|█████     | 440/861 [06:17<03:18,  2.12it/s]
+
 51%|█████     | 441/861 [06:17<03:00,  2.33it/s]
+
 51%|█████▏    | 442/861 [06:18<03:14,  2.15it/s]
+
 51%|█████▏    | 443/861 [06:18<03:17,  2.11it/s]
+
 52%|█████▏    | 444/861 [06:19<03:32,  1.96it/s]
+
 52%|█████▏    | 445/861 [06:19<03:09,  2.20it/s]
+
 52%|█████▏    | 446/861 [06:19<02:59,  2.31it/s]
+
 52%|█████▏    | 447/861 [06:20<04:02,  1.71it/s]
+
 52%|█████▏    | 448/861 [06:22<05:19,  1.29it/s]
+
 52%|█████▏    | 449/861 [06:22<04:58,  1.38it/s]
+
 52%|█████▏    | 450/861 [06:23<05:42,  1.20it/s]
+
 52%|█████▏    | 451/861 [06:24<04:59,  1.37it/s]
+
 52%|█████▏    | 452/861 [06:24<04:48,  1.42it/s]
+
 53%|█████▎    | 453/861 [06:25<04:18,  1.58it/s]
+
 53%|█████▎    | 454/861 [06:26<04:21,  1.55it/s]
+
 53%|█████▎    | 455/861 [06:26<03:43,  1.82it/s]
+
 53%|█████▎    | 456/861 [06:26<03:42,  1.82it/s]
+
 53%|█████▎    | 457/861 [06:27<03:48,  1.77it/s]
+
 53%|█████▎    | 458/861 [06:28<04:16,  1.57it/s]
+
 53%|█████▎    | 459/861 [06:28<03:37,  1.85it/s]
+
 53%|█████▎    | 460/861 [06:29<04:07,  1.62it/s]
+
 54%|█████▎    | 461/861 [06:30<04:48,  1.38it/s]
+
 54%|█████▎    | 462/861 [06:30<04:21,  1.52it/s]
+
 54%|█████▍    | 463/861 [06:31<04:01,  1.65it/s]
+
 54%|█████▍    | 464/861 [06:31<03:37,  1.82it/s]
+
 54%|█████▍    | 465/861 [06:31<02:58,  2.22it/s]
+
 54%|█████▍    | 466/861 [06:32<03:08,  2.10it/s]
+
 54%|█████▍    | 467/861 [06:33<04:20,  1.51it/s]
+
 54%|█████▍    | 468/861 [06:33<03:38,  1.80it/s]
+
 54%|█████▍    | 469/861 [06:34<03:35,  1.82it/s]
+
 55%|█████▍    | 470/861 [06:34<03:00,  2.17it/s]
+
 55%|█████▍    | 471/861 [06:35<03:24,  1.91it/s]
+
 55%|█████▍    | 472/861 [06:35<03:19,  1.95it/s]
+
 55%|█████▍    | 473/861 [06:36<02:57,  2.18it/s]
+
 55%|█████▌    | 474/861 [06:36<02:39,  2.43it/s]
+
 55%|█████▌    | 475/861 [06:37<03:01,  2.13it/s]
+
 55%|█████▌    | 476/861 [06:37<02:49,  2.27it/s]
+
 55%|█████▌    | 477/861 [06:38<03:15,  1.96it/s]
+
 56%|█████▌    | 478/861 [06:38<03:09,  2.02it/s]
+
 56%|█████▌    | 479/861 [06:38<02:40,  2.38it/s]
+
 56%|█████▌    | 480/861 [06:39<03:11,  1.99it/s]
+
 56%|█████▌    | 481/861 [06:39<02:47,  2.27it/s]
+
 56%|█████▌    | 482/861 [06:40<02:31,  2.51it/s]
+
 56%|█████▌    | 483/861 [06:40<02:14,  2.81it/s]
+
 56%|█████▌    | 484/861 [06:40<02:18,  2.73it/s]
+
 56%|█████▋    | 485/861 [06:41<02:06,  2.97it/s]
+
 56%|█████▋    | 486/861 [06:41<01:55,  3.25it/s]
+
 57%|█████▋    | 487/861 [06:41<02:31,  2.47it/s]
+
 57%|█████▋    | 488/861 [06:42<02:12,  2.81it/s]
+
 57%|█████▋    | 489/861 [06:42<02:15,  2.74it/s]
+
 57%|█████▋    | 490/861 [06:42<02:03,  3.01it/s]
+
 57%|█████▋    | 491/861 [06:43<02:06,  2.92it/s]
+
 57%|█████▋    | 492/861 [06:43<02:18,  2.67it/s]
+
 57%|█████▋    | 493/861 [06:44<02:22,  2.58it/s]
+
 57%|█████▋    | 494/861 [06:44<02:09,  2.83it/s]
+
 57%|█████▋    | 495/861 [06:45<03:12,  1.90it/s]
+
 58%|█████▊    | 496/861 [06:46<03:46,  1.61it/s]
+
 58%|█████▊    | 497/861 [06:46<03:03,  1.98it/s]
+
 58%|█████▊    | 498/861 [06:46<02:56,  2.05it/s]
+
 58%|█████▊    | 499/861 [06:47<02:31,  2.39it/s]
+
 58%|█████▊    | 500/861 [06:47<02:43,  2.20it/s]
+
 58%|█████▊    | 501/861 [06:47<02:21,  2.55it/s]
+
 58%|█████▊    | 502/861 [06:48<02:51,  2.09it/s]
+
 58%|█████▊    | 503/861 [06:48<02:48,  2.12it/s]
+
 59%|█████▊    | 504/861 [06:49<02:48,  2.12it/s]
+
 59%|█████▊    | 505/861 [06:49<02:29,  2.39it/s]
+
 59%|█████▉    | 506/861 [06:50<02:13,  2.65it/s]
+
 59%|█████▉    | 507/861 [06:50<01:59,  2.95it/s]
+
 59%|█████▉    | 508/861 [06:51<02:51,  2.06it/s]
+
 59%|█████▉    | 509/861 [06:52<03:38,  1.61it/s]
+
 59%|█████▉    | 510/861 [06:52<03:27,  1.69it/s]
+
 59%|█████▉    | 511/861 [06:53<03:26,  1.70it/s]
+
 59%|█████▉    | 512/861 [06:53<03:25,  1.69it/s]
+
 60%|█████▉    | 513/861 [06:54<03:17,  1.76it/s]
+
 60%|█████▉    | 514/861 [06:54<03:06,  1.87it/s]
+
 60%|█████▉    | 515/861 [06:54<02:28,  2.34it/s]
+
 60%|█████▉    | 516/861 [06:55<02:04,  2.77it/s]
+
 60%|██████    | 517/861 [06:55<01:54,  3.01it/s]
+
 60%|██████    | 518/861 [06:55<02:11,  2.60it/s]
+
 60%|██████    | 519/861 [06:56<02:53,  1.97it/s]
+
 60%|██████    | 520/861 [06:57<03:06,  1.83it/s]
+
 61%|██████    | 521/861 [06:57<02:37,  2.16it/s]
+
 61%|██████    | 522/861 [06:58<02:54,  1.94it/s]
+
 61%|██████    | 523/861 [06:59<03:44,  1.51it/s]
+
 61%|██████    | 524/861 [07:00<04:45,  1.18it/s]
+
 61%|██████    | 525/861 [07:00<03:59,  1.40it/s]
+
 61%|██████    | 526/861 [07:01<03:51,  1.45it/s]
+
 61%|██████    | 527/861 [07:02<03:48,  1.46it/s]
+
 61%|██████▏   | 528/861 [07:02<03:42,  1.50it/s]
+
 61%|██████▏   | 529/861 [07:03<03:09,  1.75it/s]
+
 62%|██████▏   | 530/861 [07:03<02:47,  1.97it/s]
+
 62%|██████▏   | 531/861 [07:03<02:42,  2.03it/s]
+
 62%|██████▏   | 532/861 [07:04<02:56,  1.86it/s]
+
 62%|██████▏   | 533/861 [07:05<02:43,  2.00it/s]
+
 62%|██████▏   | 534/861 [07:05<02:49,  1.93it/s]
+
 62%|██████▏   | 535/861 [07:06<02:50,  1.92it/s]
+
 62%|██████▏   | 536/861 [07:06<03:02,  1.78it/s]
+
 62%|██████▏   | 537/861 [07:08<04:28,  1.21it/s]
+
 62%|██████▏   | 538/861 [07:08<03:45,  1.43it/s]
+
 63%|██████▎   | 539/861 [07:10<05:26,  1.01s/it]
+
 63%|██████▎   | 540/861 [07:11<05:15,  1.02it/s]
+
 63%|██████▎   | 541/861 [07:11<04:23,  1.21it/s]
+
 63%|██████▎   | 542/861 [07:11<03:28,  1.53it/s]
+
 63%|██████▎   | 543/861 [07:12<03:34,  1.49it/s]
+
 63%|██████▎   | 544/861 [07:13<03:20,  1.58it/s]
+
 63%|██████▎   | 545/861 [07:14<04:49,  1.09it/s]
+
 63%|██████▎   | 546/861 [07:15<05:07,  1.02it/s]
+
 64%|██████▎   | 547/861 [07:16<04:32,  1.15it/s]
+
 64%|██████▎   | 548/861 [07:17<05:14,  1.00s/it]
+
 64%|██████▍   | 549/861 [07:18<05:15,  1.01s/it]
+
 64%|██████▍   | 550/861 [07:19<04:49,  1.07it/s]
+
 64%|██████▍   | 551/861 [07:20<04:25,  1.17it/s]
+
 64%|██████▍   | 552/861 [07:21<04:10,  1.23it/s]
+
 64%|██████▍   | 553/861 [07:22<04:54,  1.05it/s]
+
 64%|██████▍   | 554/861 [07:23<04:57,  1.03it/s]
+
 64%|██████▍   | 555/861 [07:24<05:57,  1.17s/it]
+
 65%|██████▍   | 556/861 [07:26<06:05,  1.20s/it]
+
 65%|██████▍   | 557/861 [07:27<06:36,  1.30s/it]
+
 65%|██████▍   | 558/861 [07:29<06:56,  1.38s/it]
+
 65%|██████▍   | 559/861 [07:30<06:39,  1.32s/it]
+
 65%|██████▌   | 560/861 [07:31<06:36,  1.32s/it]
+
 65%|██████▌   | 561/861 [07:32<05:49,  1.16s/it]
+
 65%|██████▌   | 562/861 [07:33<05:35,  1.12s/it]
+
 65%|██████▌   | 563/861 [07:34<05:26,  1.10s/it]
+
 66%|██████▌   | 564/861 [07:35<05:02,  1.02s/it]
+
 66%|██████▌   | 565/861 [07:36<04:41,  1.05it/s]
+
 66%|██████▌   | 566/861 [07:37<05:22,  1.09s/it]
+
 66%|██████▌   | 567/861 [07:39<05:45,  1.18s/it]
+
 66%|██████▌   | 568/861 [07:40<05:52,  1.20s/it]
+
 66%|██████▌   | 569/861 [07:41<05:25,  1.12s/it]
+
 66%|██████▌   | 570/861 [07:41<04:47,  1.01it/s]
+
 66%|██████▋   | 571/861 [07:43<05:11,  1.07s/it]
+
 66%|██████▋   | 572/861 [07:44<05:13,  1.09s/it]
+
 67%|██████▋   | 573/861 [07:44<04:28,  1.07it/s]
+
 67%|██████▋   | 574/861 [07:46<05:05,  1.06s/it]
+
 67%|██████▋   | 575/861 [07:47<04:52,  1.02s/it]
+
 67%|██████▋   | 576/861 [07:49<06:05,  1.28s/it]
+
 67%|██████▋   | 577/861 [07:50<06:33,  1.39s/it]
+
 67%|██████▋   | 578/861 [07:52<06:40,  1.41s/it]
+
 67%|██████▋   | 579/861 [07:54<07:30,  1.60s/it]
+
 67%|██████▋   | 580/861 [07:55<06:54,  1.47s/it]
+
 67%|██████▋   | 581/861 [07:56<06:11,  1.33s/it]
+
 68%|██████▊   | 582/861 [07:58<07:12,  1.55s/it]
+
 68%|██████▊   | 583/861 [07:59<06:40,  1.44s/it]
+
 68%|██████▊   | 584/861 [08:00<05:54,  1.28s/it]
+
 68%|██████▊   | 585/861 [08:01<05:14,  1.14s/it]
+
 68%|██████▊   | 586/861 [08:02<04:29,  1.02it/s]
+
 68%|██████▊   | 587/861 [08:03<04:49,  1.06s/it]
+
 68%|██████▊   | 588/861 [08:04<04:39,  1.03s/it]
+
 68%|██████▊   | 589/861 [08:05<04:20,  1.04it/s]
+
 69%|██████▊   | 590/861 [08:06<05:03,  1.12s/it]
+
 69%|██████▊   | 591/861 [08:07<04:15,  1.06it/s]
+
 69%|██████▉   | 592/861 [08:08<04:25,  1.01it/s]
+
 69%|██████▉   | 593/861 [08:09<05:03,  1.13s/it]
+
 69%|██████▉   | 594/861 [08:10<05:18,  1.19s/it]
+
 69%|██████▉   | 595/861 [08:11<04:32,  1.02s/it]
+
 69%|██████▉   | 596/861 [08:11<03:42,  1.19it/s]
+
 69%|██████▉   | 597/861 [08:12<03:21,  1.31it/s]
+
 69%|██████▉   | 598/861 [08:13<03:14,  1.35it/s]
+
 70%|██████▉   | 599/861 [08:14<03:26,  1.27it/s]
+
 70%|██████▉   | 600/861 [08:14<03:15,  1.33it/s]
+
 70%|██████▉   | 601/861 [08:15<03:06,  1.39it/s]
+
 70%|██████▉   | 602/861 [08:17<04:25,  1.03s/it]
+
 70%|███████   | 603/861 [08:18<04:49,  1.12s/it]
+
 70%|███████   | 604/861 [08:19<04:38,  1.08s/it]
+
 70%|███████   | 605/861 [08:20<04:05,  1.04it/s]
+
 70%|███████   | 606/861 [08:21<04:01,  1.06it/s]
+
 70%|███████   | 607/861 [08:21<03:53,  1.09it/s]
+
 71%|███████   | 608/861 [08:22<03:28,  1.21it/s]
+
 71%|███████   | 609/861 [08:23<03:40,  1.15it/s]
+
 71%|███████   | 610/861 [08:25<04:58,  1.19s/it]
+
 71%|███████   | 611/861 [08:26<05:01,  1.20s/it]
+
 71%|███████   | 612/861 [08:27<04:38,  1.12s/it]
+
 71%|███████   | 613/861 [08:28<03:53,  1.06it/s]
+
 71%|███████▏  | 614/861 [08:29<04:24,  1.07s/it]
+
 71%|███████▏  | 615/861 [08:30<04:40,  1.14s/it]
+
 72%|███████▏  | 616/861 [08:33<06:07,  1.50s/it]
+
 72%|███████▏  | 617/861 [08:34<06:11,  1.52s/it]
+
 72%|███████▏  | 618/861 [08:35<05:45,  1.42s/it]
+
 72%|███████▏  | 619/861 [08:37<05:26,  1.35s/it]
+
 72%|███████▏  | 620/861 [08:39<06:03,  1.51s/it]
+
 72%|███████▏  | 621/861 [08:40<05:39,  1.41s/it]
+
 72%|███████▏  | 622/861 [08:40<04:31,  1.14s/it]
+
 72%|███████▏  | 623/861 [08:42<05:32,  1.40s/it]
+
 72%|███████▏  | 624/861 [08:43<04:35,  1.16s/it]
+
 73%|███████▎  | 625/861 [08:43<03:56,  1.00s/it]
+
 73%|███████▎  | 626/861 [08:44<03:39,  1.07it/s]
+
 73%|███████▎  | 627/861 [08:45<03:20,  1.17it/s]
+
 73%|███████▎  | 628/861 [08:46<03:52,  1.00it/s]
+
 73%|███████▎  | 629/861 [08:47<04:02,  1.05s/it]
+
 73%|███████▎  | 630/861 [08:48<03:31,  1.09it/s]
+
 73%|███████▎  | 631/861 [08:48<02:49,  1.36it/s]
+
 73%|███████▎  | 632/861 [08:50<04:04,  1.07s/it]
+
 74%|███████▎  | 633/861 [08:51<03:54,  1.03s/it]
+
 74%|███████▎  | 634/861 [08:53<04:50,  1.28s/it]
+
 74%|███████▍  | 635/861 [08:54<04:39,  1.24s/it]
+
 74%|███████▍  | 636/861 [08:55<04:05,  1.09s/it]
+
 74%|███████▍  | 637/861 [08:56<03:42,  1.01it/s]
+
 74%|███████▍  | 638/861 [08:57<03:35,  1.04it/s]
+
 74%|███████▍  | 639/861 [08:58<04:04,  1.10s/it]
+
 74%|███████▍  | 640/861 [08:59<03:41,  1.00s/it]
+
 74%|███████▍  | 641/861 [09:00<03:29,  1.05it/s]
+
 75%|███████▍  | 642/861 [09:01<03:46,  1.04s/it]
+
 75%|███████▍  | 643/861 [09:01<03:22,  1.08it/s]
+
 75%|███████▍  | 644/861 [09:02<03:22,  1.07it/s]
+
 75%|███████▍  | 645/861 [09:03<02:46,  1.30it/s]
+
 75%|███████▌  | 646/861 [09:03<02:33,  1.40it/s]
+
 75%|███████▌  | 647/861 [09:04<02:23,  1.49it/s]
+
 75%|███████▌  | 648/861 [09:05<02:37,  1.35it/s]
+
 75%|███████▌  | 649/861 [09:05<02:28,  1.43it/s]
+
 75%|███████▌  | 650/861 [09:06<02:10,  1.62it/s]
+
 76%|███████▌  | 651/861 [09:06<01:53,  1.84it/s]
+
 76%|███████▌  | 652/861 [09:07<02:14,  1.56it/s]
+
 76%|███████▌  | 653/861 [09:08<02:03,  1.69it/s]
+
 76%|███████▌  | 654/861 [09:08<02:05,  1.65it/s]
+
 76%|███████▌  | 655/861 [09:09<01:49,  1.88it/s]
+
 76%|███████▌  | 656/861 [09:09<01:37,  2.10it/s]
+
 76%|███████▋  | 657/861 [09:09<01:35,  2.14it/s]
+
 76%|███████▋  | 658/861 [09:10<02:12,  1.53it/s]
+
 77%|███████▋  | 659/861 [09:11<02:10,  1.55it/s]
+
 77%|███████▋  | 660/861 [09:12<02:23,  1.41it/s]
+
 77%|███████▋  | 661/861 [09:12<02:02,  1.63it/s]
+
 77%|███████▋  | 662/861 [09:13<02:16,  1.46it/s]
+
 77%|███████▋  | 663/861 [09:15<03:38,  1.10s/it]
+
 77%|███████▋  | 664/861 [09:16<03:03,  1.08it/s]
+
 77%|███████▋  | 665/861 [09:16<02:28,  1.32it/s]
+
 77%|███████▋  | 666/861 [09:16<01:59,  1.63it/s]
+
 77%|███████▋  | 667/861 [09:17<02:08,  1.50it/s]
+
 78%|███████▊  | 668/861 [09:18<01:58,  1.62it/s]
+
 78%|███████▊  | 669/861 [09:18<01:43,  1.86it/s]
+
 78%|███████▊  | 670/861 [09:19<01:51,  1.71it/s]
+
 78%|███████▊  | 671/861 [09:19<01:32,  2.05it/s]
+
 78%|███████▊  | 672/861 [09:20<02:26,  1.29it/s]
+
 78%|███████▊  | 673/861 [09:21<02:15,  1.39it/s]
+
 78%|███████▊  | 674/861 [09:21<01:48,  1.73it/s]
+
 78%|███████▊  | 675/861 [09:23<02:40,  1.16it/s]
+
 79%|███████▊  | 676/861 [09:23<02:14,  1.37it/s]
+
 79%|███████▊  | 677/861 [09:24<01:58,  1.55it/s]
+
 79%|███████▊  | 678/861 [09:24<01:46,  1.71it/s]
+
 79%|███████▉  | 679/861 [09:24<01:30,  2.00it/s]
+
 79%|███████▉  | 680/861 [09:25<01:16,  2.35it/s]
+
 79%|███████▉  | 681/861 [09:25<01:16,  2.34it/s]
+
 79%|███████▉  | 682/861 [09:26<01:37,  1.83it/s]
+
 79%|███████▉  | 683/861 [09:26<01:33,  1.91it/s]
+
 79%|███████▉  | 684/861 [09:27<01:46,  1.67it/s]
+
 80%|███████▉  | 685/861 [09:28<01:46,  1.66it/s]
+
 80%|███████▉  | 686/861 [09:28<01:37,  1.79it/s]
+
 80%|███████▉  | 687/861 [09:30<02:45,  1.05it/s]
+
 80%|███████▉  | 688/861 [09:30<02:12,  1.30it/s]
+
 80%|████████  | 689/861 [09:31<02:09,  1.32it/s]
+
 80%|████████  | 690/861 [09:32<01:50,  1.55it/s]
+
 80%|████████  | 691/861 [09:32<01:42,  1.65it/s]
+
 80%|████████  | 692/861 [09:33<01:32,  1.83it/s]
+
 80%|████████  | 693/861 [09:33<01:43,  1.62it/s]
+
 81%|████████  | 694/861 [09:34<01:30,  1.85it/s]
+
 81%|████████  | 695/861 [09:34<01:27,  1.90it/s]
+
 81%|████████  | 696/861 [09:34<01:13,  2.26it/s]
+
 81%|████████  | 697/861 [09:35<01:18,  2.10it/s]
+
 81%|████████  | 698/861 [09:36<01:36,  1.69it/s]
+
 81%|████████  | 699/861 [09:37<01:43,  1.56it/s]
+
 81%|████████▏ | 700/861 [09:37<01:49,  1.48it/s]
+
 81%|████████▏ | 701/861 [09:38<01:56,  1.38it/s]
+
 82%|████████▏ | 702/861 [09:39<01:55,  1.38it/s]
+
 82%|████████▏ | 703/861 [09:39<01:39,  1.59it/s]
+
 82%|████████▏ | 704/861 [09:40<01:35,  1.64it/s]
+
 82%|████████▏ | 705/861 [09:40<01:23,  1.87it/s]
+
 82%|████████▏ | 706/861 [09:41<01:18,  1.97it/s]
+
 82%|████████▏ | 707/861 [09:41<01:11,  2.15it/s]
+
 82%|████████▏ | 708/861 [09:41<01:04,  2.38it/s]
+
 82%|████████▏ | 709/861 [09:42<01:02,  2.43it/s]
+
 82%|████████▏ | 710/861 [09:43<01:36,  1.57it/s]
+
 83%|████████▎ | 711/861 [09:44<01:33,  1.60it/s]
+
 83%|████████▎ | 712/861 [09:44<01:21,  1.82it/s]
+
 83%|████████▎ | 713/861 [09:44<01:09,  2.12it/s]
+
 83%|████████▎ | 714/861 [09:45<01:20,  1.83it/s]
+
 83%|████████▎ | 715/861 [09:46<01:42,  1.43it/s]
+
 83%|████████▎ | 716/861 [09:47<01:55,  1.26it/s]
+
 83%|████████▎ | 717/861 [09:47<01:43,  1.39it/s]
+
 83%|████████▎ | 718/861 [09:49<02:03,  1.16it/s]
+
 84%|████████▎ | 719/861 [09:49<01:47,  1.32it/s]
+
 84%|████████▎ | 720/861 [09:50<01:35,  1.48it/s]
+
 84%|████████▎ | 721/861 [09:50<01:28,  1.58it/s]
+
 84%|████████▍ | 722/861 [09:51<01:27,  1.59it/s]
+
 84%|████████▍ | 723/861 [09:51<01:15,  1.82it/s]
+
 84%|████████▍ | 724/861 [09:52<01:14,  1.85it/s]
+
 84%|████████▍ | 725/861 [09:52<01:13,  1.84it/s]
+
 84%|████████▍ | 726/861 [09:53<01:28,  1.53it/s]
+
 84%|████████▍ | 727/861 [09:55<01:58,  1.13it/s]
+
 85%|████████▍ | 728/861 [09:56<02:02,  1.09it/s]
+
 85%|████████▍ | 729/861 [09:56<01:44,  1.27it/s]
+
 85%|████████▍ | 730/861 [09:56<01:26,  1.52it/s]
+
 85%|████████▍ | 731/861 [09:58<02:15,  1.04s/it]
+
 85%|████████▌ | 732/861 [09:59<01:53,  1.14it/s]
+
 85%|████████▌ | 733/861 [10:00<01:43,  1.24it/s]
+
 85%|████████▌ | 734/861 [10:00<01:20,  1.57it/s]
+
 85%|████████▌ | 735/861 [10:00<01:13,  1.72it/s]
+
 85%|████████▌ | 736/861 [10:01<01:13,  1.70it/s]
+
 86%|████████▌ | 737/861 [10:01<01:13,  1.68it/s]
+
 86%|████████▌ | 738/861 [10:02<01:09,  1.77it/s]
+
 86%|████████▌ | 739/861 [10:02<01:02,  1.97it/s]
+
 86%|████████▌ | 740/861 [10:03<01:05,  1.85it/s]
+
 86%|████████▌ | 741/861 [10:03<01:03,  1.88it/s]
+
 86%|████████▌ | 742/861 [10:04<01:15,  1.57it/s]
+
 86%|████████▋ | 743/861 [10:05<01:13,  1.60it/s]
+
 86%|████████▋ | 744/861 [10:05<01:05,  1.77it/s]
+
 87%|████████▋ | 745/861 [10:06<01:18,  1.49it/s]
+
 87%|████████▋ | 746/861 [10:06<01:01,  1.86it/s]
+
 87%|████████▋ | 747/861 [10:07<01:08,  1.68it/s]
+
 87%|████████▋ | 748/861 [10:08<01:05,  1.74it/s]
+
 87%|████████▋ | 749/861 [10:09<01:20,  1.39it/s]
+
 87%|████████▋ | 750/861 [10:09<01:03,  1.75it/s]
+
 87%|████████▋ | 751/861 [10:09<00:51,  2.15it/s]
+
 87%|████████▋ | 752/861 [10:10<01:14,  1.46it/s]
+
 87%|████████▋ | 753/861 [10:11<01:12,  1.50it/s]
+
 88%|████████▊ | 754/861 [10:11<01:02,  1.71it/s]
+
 88%|████████▊ | 755/861 [10:12<00:56,  1.86it/s]
+
 88%|████████▊ | 756/861 [10:12<00:51,  2.06it/s]
+
 88%|████████▊ | 757/861 [10:13<01:05,  1.60it/s]
+
 88%|████████▊ | 758/861 [10:14<01:04,  1.59it/s]
+
 88%|████████▊ | 759/861 [10:14<01:00,  1.69it/s]
+
 88%|████████▊ | 760/861 [10:15<01:11,  1.42it/s]
+
 88%|████████▊ | 761/861 [10:17<01:32,  1.08it/s]
+
 89%|████████▊ | 762/861 [10:17<01:15,  1.31it/s]
+
 89%|████████▊ | 763/861 [10:18<01:09,  1.40it/s]
+
 89%|████████▊ | 764/861 [10:19<01:14,  1.29it/s]
+
 89%|████████▉ | 765/861 [10:19<01:12,  1.32it/s]
+
 89%|████████▉ | 766/861 [10:20<01:09,  1.37it/s]
+
 89%|████████▉ | 767/861 [10:24<02:36,  1.66s/it]
+
 89%|████████▉ | 768/861 [10:25<02:08,  1.38s/it]
+
 89%|████████▉ | 769/861 [10:26<01:56,  1.27s/it]
+
 89%|████████▉ | 770/861 [10:26<01:31,  1.00s/it]
+
 90%|████████▉ | 771/861 [10:26<01:16,  1.18it/s]
+
 90%|████████▉ | 772/861 [10:27<01:09,  1.29it/s]
+
 90%|████████▉ | 773/861 [10:29<01:47,  1.23s/it]
+
 90%|████████▉ | 774/861 [10:30<01:36,  1.11s/it]
+
 90%|█████████ | 775/861 [10:31<01:27,  1.01s/it]
+
 90%|█████████ | 776/861 [10:32<01:23,  1.02it/s]
+
 90%|█████████ | 777/861 [10:33<01:16,  1.09it/s]
+
 90%|█████████ | 778/861 [10:33<01:12,  1.14it/s]
+
 90%|█████████ | 779/861 [10:35<01:37,  1.19s/it]
+
 91%|█████████ | 780/861 [10:37<01:52,  1.39s/it]
+
 91%|█████████ | 781/861 [10:40<02:17,  1.72s/it]
+
 91%|█████████ | 782/861 [10:41<02:10,  1.65s/it]
+
 91%|█████████ | 783/861 [10:42<01:46,  1.37s/it]
+
 91%|█████████ | 784/861 [10:43<01:31,  1.18s/it]
+
 91%|█████████ | 785/861 [10:43<01:19,  1.04s/it]
+
 91%|█████████▏| 786/861 [10:44<01:13,  1.03it/s]
+
 91%|█████████▏| 787/861 [10:45<01:02,  1.18it/s]
+
 92%|█████████▏| 788/861 [10:45<00:59,  1.22it/s]
+
 92%|█████████▏| 789/861 [10:46<00:59,  1.21it/s]
+
 92%|█████████▏| 790/861 [10:47<00:57,  1.23it/s]
+
 92%|█████████▏| 791/861 [10:48<00:50,  1.37it/s]
+
 92%|█████████▏| 792/861 [10:48<00:49,  1.40it/s]
+
 92%|█████████▏| 793/861 [10:49<00:51,  1.31it/s]
+
 92%|█████████▏| 794/861 [10:50<00:48,  1.37it/s]
+
 92%|█████████▏| 795/861 [10:50<00:45,  1.45it/s]
+
 92%|█████████▏| 796/861 [10:51<00:37,  1.72it/s]
+
 93%|█████████▎| 797/861 [10:52<00:43,  1.49it/s]
+
 93%|█████████▎| 798/861 [10:52<00:37,  1.70it/s]
+
 93%|█████████▎| 799/861 [10:53<00:33,  1.82it/s]
+
 93%|█████████▎| 800/861 [10:53<00:35,  1.70it/s]
+
 93%|█████████▎| 801/861 [10:54<00:47,  1.26it/s]
+
 93%|█████████▎| 802/861 [10:55<00:40,  1.45it/s]
+
 93%|█████████▎| 803/861 [10:56<00:48,  1.19it/s]
+
 93%|█████████▎| 804/861 [10:58<00:58,  1.03s/it]
+
 93%|█████████▎| 805/861 [10:59<01:03,  1.13s/it]
+
 94%|█████████▎| 806/861 [10:59<00:49,  1.10it/s]
+
 94%|█████████▎| 807/861 [11:01<00:53,  1.01it/s]
+
 94%|█████████▍| 808/861 [11:02<00:59,  1.12s/it]
+
 94%|█████████▍| 809/861 [11:02<00:46,  1.13it/s]
+
 94%|█████████▍| 810/861 [11:03<00:38,  1.32it/s]
+
 94%|█████████▍| 811/861 [11:03<00:36,  1.38it/s]
+
 94%|█████████▍| 812/861 [11:04<00:33,  1.47it/s]
+
 94%|█████████▍| 813/861 [11:05<00:40,  1.17it/s]
+
 95%|█████████▍| 814/861 [11:06<00:43,  1.09it/s]
+
 95%|█████████▍| 815/861 [11:07<00:42,  1.08it/s]
+
 95%|█████████▍| 816/861 [11:08<00:37,  1.20it/s]
+
 95%|█████████▍| 817/861 [11:09<00:34,  1.27it/s]
+
 95%|█████████▌| 818/861 [11:10<00:37,  1.15it/s]
+
 95%|█████████▌| 819/861 [11:10<00:33,  1.27it/s]
+
 95%|█████████▌| 820/861 [11:11<00:34,  1.19it/s]
+
 95%|█████████▌| 821/861 [11:12<00:37,  1.07it/s]
+
 95%|█████████▌| 822/861 [11:14<00:43,  1.11s/it]
+
 96%|█████████▌| 823/861 [11:15<00:39,  1.04s/it]
+
 96%|█████████▌| 824/861 [11:15<00:31,  1.17it/s]
+
 96%|█████████▌| 825/861 [11:16<00:27,  1.29it/s]
+
 96%|█████████▌| 826/861 [11:17<00:37,  1.06s/it]
+
 96%|█████████▌| 827/861 [11:19<00:37,  1.10s/it]
+
 96%|█████████▌| 828/861 [11:19<00:28,  1.15it/s]
+
 96%|█████████▋| 829/861 [11:20<00:31,  1.02it/s]
+
 96%|█████████▋| 830/861 [11:21<00:31,  1.03s/it]
+
 97%|█████████▋| 831/861 [11:23<00:36,  1.20s/it]
+
 97%|█████████▋| 832/861 [11:24<00:29,  1.01s/it]
+
 97%|█████████▋| 833/861 [11:24<00:24,  1.14it/s]
+
 97%|█████████▋| 834/861 [11:25<00:24,  1.09it/s]
+
 97%|█████████▋| 835/861 [11:26<00:23,  1.11it/s]
+
 97%|█████████▋| 836/861 [11:27<00:22,  1.12it/s]
+
 97%|█████████▋| 837/861 [11:28<00:23,  1.04it/s]
+
 97%|█████████▋| 838/861 [11:29<00:23,  1.04s/it]
+
 97%|█████████▋| 839/861 [11:30<00:19,  1.12it/s]
+
 98%|█████████▊| 840/861 [11:30<00:15,  1.32it/s]
+
 98%|█████████▊| 841/861 [11:31<00:14,  1.33it/s]
+
 98%|█████████▊| 842/861 [11:31<00:13,  1.44it/s]
+
 98%|█████████▊| 843/861 [11:32<00:12,  1.42it/s]
+
 98%|█████████▊| 844/861 [11:33<00:11,  1.47it/s]
+
 98%|█████████▊| 845/861 [11:34<00:13,  1.17it/s]
+
 98%|█████████▊| 846/861 [11:35<00:11,  1.33it/s]
+
 98%|█████████▊| 847/861 [11:36<00:11,  1.23it/s]
+
 98%|█████████▊| 848/861 [11:37<00:12,  1.07it/s]
+
 99%|█████████▊| 849/861 [11:38<00:11,  1.00it/s]
+
 99%|█████████▊| 850/861 [11:39<00:09,  1.14it/s]
+
 99%|█████████▉| 851/861 [11:39<00:07,  1.26it/s]
+
 99%|█████████▉| 852/861 [11:40<00:06,  1.35it/s]
+
 99%|█████████▉| 853/861 [11:40<00:05,  1.38it/s]
+
 99%|█████████▉| 854/861 [11:41<00:04,  1.42it/s]
+
 99%|█████████▉| 855/861 [11:42<00:04,  1.27it/s]
+
 99%|█████████▉| 856/861 [11:43<00:04,  1.02it/s]
+
100%|█████████▉| 857/861 [11:44<00:03,  1.02it/s]
+
100%|█████████▉| 858/861 [11:45<00:02,  1.07it/s]
+
100%|█████████▉| 859/861 [11:46<00:01,  1.13it/s]
+
100%|█████████▉| 860/861 [11:47<00:00,  1.06it/s]
+
100%|██████████| 861/861 [11:48<00:00,  1.04it/s]{'score': 12.814386132355898, 'counts': [17920, 8355, 4270, 2172], 'totals': [50259, 48537, 46815, 45093], 'precisions': [35.65530551741976, 17.213672044007666, 9.121008223859874, 4.816712128268246], 'bp': 1.0, 'sys_len': 50259, 'ref_len': 32555}
+
                                                         
+
                                                 
{'eval_loss': 2.433004140853882, 'eval_bleu': 12.8144, 'eval_gen_len': 37.2979, 'eval_runtime': 806.1399, 'eval_samples_per_second': 2.136, 'eval_steps_per_second': 1.068, 'epoch': 13.0}
+
 81%|████████▏ | 50298/61904 [3:25:19<4:26:24,  1.38s/it]
+
100%|██████████| 861/861 [13:25<00:00,  1.04it/s]
+
                                                 [WARNING|configuration_utils.py:448] 2024-10-28 18:50:59,604 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
+Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}
+/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
+  self.pid = os.fork()
+
 81%|████████▏ | 50299/61904 [3:25:39<801:28:38, 248.63s/it]
 81%|████████▏ | 50300/61904 [3:25:40<562:17:08, 174.44s/it]
                                                            
{'loss': 2.4458, 'learning_rate': 1.1880591209646052e-07, 'epoch': 13.0}
+
 81%|████████▏ | 50300/61904 [3:25:40<562:17:08, 174.44s/it]
 81%|████████▏ | 50301/61904 [3:25:41<395:00:00, 122.55s/it]
 81%|████████▏ | 50302/61904 [3:25:43<277:48:17, 86.20s/it] 
 81%|████████▏ | 50303/61904 [3:25:44<195:50:25, 60.77s/it]
 81%|████████▏ | 50304/61904 [3:25:46<138:34:48, 43.01s/it]
 81%|████████▏ | 50305/61904 [3:25:47<98:20:57, 30.52s/it] 
 81%|████████▏ | 50306/61904 [3:25:49<70:17:02, 21.82s/it]
 81%|████████▏ | 50307/61904 [3:25:50<50:36:28, 15.71s/it]
 81%|████████▏ | 50308/61904 [3:25:52<37:05:05, 11.51s/it]
 81%|████████▏ | 50309/61904 [3:25:53<27:20:55,  8.49s/it]
 81%|████████▏ | 50310/61904 [3:25:55<20:43:34,  6.44s/it]
 81%|████████▏ | 50311/61904 [3:25:56<15:51:23,  4.92s/it]
 81%|████████▏ | 50312/61904 [3:25:58<12:40:13,  3.93s/it]
 81%|████████▏ | 50313/61904 [3:25:59<10:05:09,  3.13s/it]
 81%|████████▏ | 50314/61904 [3:26:01<8:21:01,  2.59s/it] 
 81%|████████▏ | 50315/61904 [3:26:02<7:11:31,  2.23s/it]
 81%|████████▏ | 50316/61904 [3:26:03<6:28:10,  2.01s/it]
 81%|████████▏ | 50317/61904 [3:26:05<5:57:31,  1.85s/it]
 81%|████████▏ | 50318/61904 [3:26:06<5:26:54,  1.69s/it]
 81%|████████▏ | 50319/61904 [3:26:08<5:07:49,  1.59s/it]
 81%|████████▏ | 50320/61904 [3:26:09<4:54:45,  1.53s/it]
                                                         
{'loss': 2.4137, 'learning_rate': 1.1877349928691818e-07, 'epoch': 13.01}
+
 81%|████████▏ | 50320/61904 [3:26:09<4:54:45,  1.53s/it]
 81%|████████▏ | 50321/61904 [3:26:10<4:50:45,  1.51s/it]
 81%|████████▏ | 50322/61904 [3:26:12<4:58:52,  1.55s/it]
 81%|████████▏ | 50323/61904 [3:26:13<4:52:51,  1.52s/it]
 81%|████████▏ | 50324/61904 [3:26:15<4:43:36,  1.47s/it]
 81%|████████▏ | 50325/61904 [3:26:16<4:43:21,  1.47s/it]
 81%|████████▏ | 50326/61904 [3:26:18<4:30:04,  1.40s/it]
 81%|████████▏ | 50327/61904 [3:26:19<4:27:21,  1.39s/it]
 81%|████████▏ | 50328/61904 [3:26:20<4:33:28,  1.42s/it]
 81%|████████▏ | 50329/61904 [3:26:22<4:44:52,  1.48s/it]
 81%|████████▏ | 50330/61904 [3:26:23<4:39:17,  1.45s/it]
 81%|████████▏ | 50331/61904 [3:26:25<4:29:00,  1.39s/it]
 81%|████████▏ | 50332/61904 [3:26:26<4:35:12,  1.43s/it]
 81%|████████▏ | 50333/61904 [3:26:27<4:29:27,  1.40s/it]
 81%|████████▏ | 50334/61904 [3:26:29<4:30:29,  1.40s/it]
 81%|████████▏ | 50335/61904 [3:26:30<4:32:54,  1.42s/it]
 81%|████████▏ | 50336/61904 [3:26:32<4:30:00,  1.40s/it]
 81%|████████▏ | 50337/61904 [3:26:33<4:28:53,  1.39s/it]
 81%|████████▏ | 50338/61904 [3:26:34<4:28:09,  1.39s/it]
 81%|████████▏ | 50339/61904 [3:26:36<4:24:50,  1.37s/it]
 81%|████████▏ | 50340/61904 [3:26:37<4:30:35,  1.40s/it]
                                                         
{'loss': 2.4151, 'learning_rate': 1.1874108647737586e-07, 'epoch': 13.01}
+
 81%|████████▏ | 50340/61904 [3:26:37<4:30:35,  1.40s/it]
 81%|████████▏ | 50341/61904 [3:26:39<4:35:51,  1.43s/it]
 81%|████████▏ | 50342/61904 [3:26:40<4:39:49,  1.45s/it]
 81%|███���████▏ | 50343/61904 [3:26:42<4:40:57,  1.46s/it]
 81%|████████▏ | 50344/61904 [3:26:43<4:39:15,  1.45s/it]
\ No newline at end of file