diff --git "a/run-2024-10-25T01:17:54+00:00.log" "b/run-2024-10-25T01:17:54+00:00.log" --- "a/run-2024-10-25T01:17:54+00:00.log" +++ "b/run-2024-10-25T01:17:54+00:00.log" @@ -1106,4 +1106,1070 @@ Non-default generation parameters: {'max_length': 200, 'early_stopping': True, ' self.pid = os.fork() 6%|▋ | 3870/61904 [2:01:52<9730:10:48, 603.59s/it] 6%|▋ | 3871/61904 [2:01:54<6817:16:16, 422.90s/it] 6%|▋ | 3872/61904 [2:01:55<4778:34:57, 296.44s/it] 6%|▋ | 3873/61904 [2:01:57<3352:37:10, 207.98s/it] 6%|▋ | 3874/61904 [2:01:58<2354:23:50, 146.06s/it] 6%|▋ | 3875/61904 [2:02:00<1655:35:21, 102.71s/it] 6%|▋ | 3876/61904 [2:02:01<1166:37:02, 72.38s/it] 6%|▋ | 3877/61904 [2:02:03<822:42:15, 51.04s/it] 6%|▋ | 3878/61904 [2:02:04<583:02:18, 36.17s/it] 6%|▋ | 3879/61904 [2:02:06<414:54:48, 25.74s/it] 6%|▋ | 3880/61904 [2:02:07<297:12:41, 18.44s/it] {'loss': 3.0219, 'learning_rate': 1.9403604304421105e-07, 'epoch': 1.0} 6%|▋ | 3880/61904 [2:02:07<297:12:41, 18.44s/it] 6%|▋ | 3881/61904 [2:02:08<214:38:11, 13.32s/it] 6%|▋ | 3882/61904 [2:02:10<157:09:50, 9.75s/it] 6%|▋ | 3883/61904 [2:02:11<116:33:26, 7.23s/it] 6%|▋ | 3884/61904 [2:02:13<88:43:15, 5.50s/it] 6%|▋ | 3885/61904 [2:02:14<69:09:26, 4.29s/it] 6%|▋ | 3886/61904 [2:02:15<55:16:04, 3.43s/it] 6%|▋ | 3887/61904 [2:02:17<45:40:38, 2.83s/it] 6%|▋ | 3888/61904 [2:02:19<39:43:49, 2.47s/it] 6%|▋ | 3889/61904 [2:02:20<35:31:27, 2.20s/it] 6%|▋ | 3890/61904 [2:02:22<31:52:09, 1.98s/it] 6%|▋ | 3891/61904 [2:02:23<29:19:44, 1.82s/it] 6%|▋ | 3892/61904 [2:02:24<26:55:09, 1.67s/it] 6%|▋ | 3893/61904 [2:02:26<26:00:11, 1.61s/it] 6%|▋ | 3894/61904 [2:02:27<25:00:24, 1.55s/it] 6%|▋ | 3895/61904 [2:02:29<23:50:16, 1.48s/it] 6%|▋ | 3896/61904 [2:02:30<23:19:09, 1.45s/it] 6%|▋ | 3897/61904 [2:02:31<23:37:07, 1.47s/it] 6%|▋ | 3898/61904 [2:02:33<22:55:14, 1.42s/it] 6%|▋ | 3899/61904 [2:02:34<22:33:14, 1.40s/it] 6%|▋ | 3900/61904 [2:02:35<21:50:24, 1.36s/it] {'loss': 3.0378, 'learning_rate': 1.9400363023466873e-07, 'epoch': 1.01} - 6%|▋ | 3900/61904 [2:02:35<21:50:24, 1.36s/it] 6%|▋ | 3901/61904 [2:02:37<21:52:31, 1.36s/it] 6%|▋ | 3902/61904 [2:02:38<21:48:03, 1.35s/it] 6%|▋ | 3903/61904 [2:02:39<21:42:57, 1.35s/it] 6%|▋ | 3904/61904 [2:02:41<22:11:27, 1.38s/it] 6%|▋ | 3905/61904 [2:02:42<21:41:42, 1.35s/it] 6%|▋ | 3906/61904 [2:02:43<21:16:43, 1.32s/it] 6%|▋ | 3907/61904 [2:02:45<20:43:01, 1.29s/it] 6%|▋ | 3908/61904 [2:02:46<21:13:35, 1.32s/it] 6%|▋ | 3909/61904 [2:02:47<21:24:06, 1.33s/it] \ No newline at end of file + 6%|▋ | 3900/61904 [2:02:35<21:50:24, 1.36s/it] 6%|▋ | 3901/61904 [2:02:37<21:52:31, 1.36s/it] 6%|▋ | 3902/61904 [2:02:38<21:48:03, 1.35s/it] 6%|▋ | 3903/61904 [2:02:39<21:42:57, 1.35s/it] 6%|▋ | 3904/61904 [2:02:41<22:11:27, 1.38s/it] 6%|▋ | 3905/61904 [2:02:42<21:41:42, 1.35s/it] 6%|▋ | 3906/61904 [2:02:43<21:16:43, 1.32s/it] 6%|▋ | 3907/61904 [2:02:45<20:43:01, 1.29s/it] 6%|▋ | 3908/61904 [2:02:46<21:13:35, 1.32s/it] 6%|▋ | 3909/61904 [2:02:47<21:24:06, 1.33s/it] 6%|▋ | 3910/61904 [2:02:49<21:56:10, 1.36s/it] 6%|▋ | 3911/61904 [2:02:50<21:15:30, 1.32s/it] 6%|▋ | 3912/61904 [2:02:51<20:59:11, 1.30s/it] 6%|▋ | 3913/61904 [2:02:53<21:08:25, 1.31s/it] 6%|▋ | 3914/61904 [2:02:54<21:16:06, 1.32s/it] 6%|▋ | 3915/61904 [2:02:55<21:57:50, 1.36s/it] 6%|▋ | 3916/61904 [2:02:57<21:42:19, 1.35s/it] 6%|▋ | 3917/61904 [2:02:58<21:24:50, 1.33s/it] 6%|▋ | 3918/61904 [2:02:59<21:49:14, 1.35s/it] 6%|▋ | 3919/61904 [2:03:01<21:56:23, 1.36s/it] 6%|▋ | 3920/61904 [2:03:02<22:05:47, 1.37s/it] {'loss': 3.058, 'learning_rate': 1.939712174251264e-07, 'epoch': 1.01} + 6%|▋ | 3920/61904 [2:03:02<22:05:47, 1.37s/it] 6%|▋ | 3921/61904 [2:03:04<22:24:28, 1.39s/it] 6%|▋ | 3922/61904 [2:03:05<23:03:21, 1.43s/it] 6%|▋ | 3923/61904 [2:03:07<22:55:23, 1.42s/it] 6%|▋ | 3924/61904 [2:03:08<22:46:08, 1.41s/it] 6%|▋ | 3925/61904 [2:03:09<23:12:58, 1.44s/it] 6%|▋ | 3926/61904 [2:03:11<23:29:19, 1.46s/it] 6%|▋ | 3927/61904 [2:03:12<23:42:16, 1.47s/it] 6%|▋ | 3928/61904 [2:03:14<23:23:38, 1.45s/it] 6%|▋ | 3929/61904 [2:03:15<22:52:03, 1.42s/it] 6%|▋ | 3930/61904 [2:03:17<23:11:51, 1.44s/it] 6%|▋ | 3931/61904 [2:03:18<23:44:14, 1.47s/it] 6%|▋ | 3932/61904 [2:03:20<23:02:58, 1.43s/it] 6%|▋ | 3933/61904 [2:03:21<23:12:23, 1.44s/it] 6%|▋ | 3934/61904 [2:03:22<22:28:11, 1.40s/it] 6%|▋ | 3935/61904 [2:03:24<22:43:57, 1.41s/it] 6%|▋ | 3936/61904 [2:03:25<22:28:19, 1.40s/it] 6%|▋ | 3937/61904 [2:03:26<22:07:19, 1.37s/it] 6%|▋ | 3938/61904 [2:03:28<21:53:10, 1.36s/it] 6%|▋ | 3939/61904 [2:03:29<21:55:22, 1.36s/it] 6%|▋ | 3940/61904 [2:03:31<22:58:28, 1.43s/it] {'loss': 3.0479, 'learning_rate': 1.9393880461558406e-07, 'epoch': 1.02} + 6%|▋ | 3940/61904 [2:03:31<22:58:28, 1.43s/it] 6%|▋ | 3941/61904 [2:03:32<22:53:19, 1.42s/it] 6%|▋ | 3942/61904 [2:03:34<22:54:48, 1.42s/it] 6%|▋ | 3943/61904 [2:03:35<23:18:06, 1.45s/it] 6%|▋ | 3944/61904 [2:03:36<22:31:05, 1.40s/it] 6%|▋ | 3945/61904 [2:03:38<22:43:44, 1.41s/it] 6%|▋ | 3946/61904 [2:03:39<22:23:20, 1.39s/it] 6%|▋ | 3947/61904 [2:03:40<22:02:40, 1.37s/it] 6%|▋ | 3948/61904 [2:03:42<22:08:22, 1.38s/it] 6%|▋ | 3949/61904 [2:03:43<22:32:03, 1.40s/it] 6%|▋ | 3950/61904 [2:03:45<22:23:07, 1.39s/it] 6%|▋ | 3951/61904 [2:03:46<22:21:24, 1.39s/it] 6%|▋ | 3952/61904 [2:03:48<22:52:13, 1.42s/it] 6%|▋ | 3953/61904 [2:03:49<22:22:43, 1.39s/it] 6%|▋ | 3954/61904 [2:03:50<22:49:08, 1.42s/it] 6%|▋ | 3955/61904 [2:03:52<23:14:56, 1.44s/it] 6%|▋ | 3956/61904 [2:03:53<22:53:25, 1.42s/it] 6%|▋ | 3957/61904 [2:03:55<22:30:06, 1.40s/it] 6%|▋ | 3958/61904 [2:03:56<22:24:57, 1.39s/it] 6%|▋ | 3959/61904 [2:03:57<21:56:54, 1.36s/it] 6%|▋ | 3960/61904 [2:03:59<22:28:38, 1.40s/it] {'loss': 3.0733, 'learning_rate': 1.9390639180604175e-07, 'epoch': 1.02} + 6%|▋ | 3960/61904 [2:03:59<22:28:38, 1.40s/it] 6%|▋ | 3961/61904 [2:04:00<22:36:24, 1.40s/it] 6%|▋ | 3962/61904 [2:04:02<22:47:41, 1.42s/it] 6%|▋ | 3963/61904 [2:04:03<22:46:27, 1.42s/it] 6%|▋ | 3964/61904 [2:04:05<23:52:30, 1.48s/it] 6%|▋ | 3965/61904 [2:04:06<23:07:17, 1.44s/it] 6%|▋ | 3966/61904 [2:04:07<22:36:55, 1.41s/it] 6%|▋ | 3967/61904 [2:04:09<22:17:53, 1.39s/it] 6%|▋ | 3968/61904 [2:04:10<22:38:11, 1.41s/it] 6%|▋ | 3969/61904 [2:04:12<22:58:46, 1.43s/it] 6%|▋ | 3970/61904 [2:04:13<23:42:38, 1.47s/it] 6%|▋ | 3971/61904 [2:04:14<22:56:23, 1.43s/it] 6%|▋ | 3972/61904 [2:04:16<23:26:12, 1.46s/it] 6%|▋ | 3973/61904 [2:04:17<23:23:45, 1.45s/it] 6%|▋ | 3974/61904 [2:04:19<23:04:30, 1.43s/it] 6%|▋ | 3975/61904 [2:04:20<23:10:17, 1.44s/it] 6%|▋ | 3976/61904 [2:04:22<22:52:36, 1.42s/it] 6%|▋ | 3977/61904 [2:04:23<21:57:00, 1.36s/it] 6%|▋ | 3978/61904 [2:04:24<22:09:20, 1.38s/it] 6%|▋ | 3979/61904 [2:04:26<21:30:43, 1.34s/it] 6%|▋ | 3980/61904 [2:04:27<21:42:28, 1.35s/it] {'loss': 3.0543, 'learning_rate': 1.938739789964994e-07, 'epoch': 1.03} + 6%|▋ | 3980/61904 [2:04:27<21:42:28, 1.35s/it] 6%|▋ | 3981/61904 [2:04:28<21:29:11, 1.34s/it] 6%|▋ | 3982/61904 [2:04:30<21:13:45, 1.32s/it] 6%|▋ | 3983/61904 [2:04:31<21:06:47, 1.31s/it] 6%|▋ | 3984/61904 [2:04:32<21:40:11, 1.35s/it] 6%|▋ | 3985/61904 [2:04:34<22:27:45, 1.40s/it] 6%|▋ | 3986/61904 [2:04:35<22:00:15, 1.37s/it] 6%|▋ | 3987/61904 [2:04:36<22:18:08, 1.39s/it] 6%|▋ | 3988/61904 [2:04:38<21:44:03, 1.35s/it] 6%|▋ | 3989/61904 [2:04:39<22:14:30, 1.38s/it] 6%|▋ | 3990/61904 [2:04:40<21:36:17, 1.34s/it] 6%|▋ | 3991/61904 [2:04:42<22:10:06, 1.38s/it] 6%|▋ | 3992/61904 [2:04:43<22:10:03, 1.38s/it] 6%|▋ | 3993/61904 [2:04:45<21:51:15, 1.36s/it] 6%|▋ | 3994/61904 [2:04:46<21:45:57, 1.35s/it] 6%|▋ | 3995/61904 [2:04:47<22:08:16, 1.38s/it] 6%|▋ | 3996/61904 [2:04:49<21:43:23, 1.35s/it] 6%|▋ | 3997/61904 [2:04:50<21:30:02, 1.34s/it] 6%|▋ | 3998/61904 [2:04:51<20:54:57, 1.30s/it] 6%|▋ | 3999/61904 [2:04:53<21:06:21, 1.31s/it] 6%|▋ | 4000/61904 [2:04:54<20:55:21, 1.30s/it] {'loss': 2.9607, 'learning_rate': 1.9384156618695707e-07, 'epoch': 1.03} + 6%|▋ | 4000/61904 [2:04:54<20:55:21, 1.30s/it] 6%|▋ | 4001/61904 [2:04:55<21:17:26, 1.32s/it] 6%|▋ | 4002/61904 [2:04:57<21:26:32, 1.33s/it] 6%|▋ | 4003/61904 [2:04:58<21:34:45, 1.34s/it] 6%|▋ | 4004/61904 [2:04:59<21:26:44, 1.33s/it] 6%|▋ | 4005/61904 [2:05:01<21:21:24, 1.33s/it] 6%|▋ | 4006/61904 [2:05:02<21:36:33, 1.34s/it] 6%|▋ | 4007/61904 [2:05:03<21:32:07, 1.34s/it] 6%|▋ | 4008/61904 [2:05:05<22:21:38, 1.39s/it] 6%|▋ | 4009/61904 [2:05:06<22:52:23, 1.42s/it] 6%|▋ | 4010/61904 [2:05:08<22:53:08, 1.42s/it] 6%|▋ | 4011/61904 [2:05:09<21:45:13, 1.35s/it] 6%|▋ | 4012/61904 [2:05:10<21:08:42, 1.31s/it] 6%|▋ | 4013/61904 [2:05:11<21:00:42, 1.31s/it] 6%|▋ | 4014/61904 [2:05:13<20:42:28, 1.29s/it] 6%|▋ | 4015/61904 [2:05:14<20:40:17, 1.29s/it] 6%|▋ | 4016/61904 [2:05:15<21:31:11, 1.34s/it] 6%|▋ | 4017/61904 [2:05:17<21:48:42, 1.36s/it] 6%|▋ | 4018/61904 [2:05:18<21:36:45, 1.34s/it] 6%|▋ | 4019/61904 [2:05:19<21:45:36, 1.35s/it] 6%|▋ | 4020/61904 [2:05:21<21:47:18, 1.36s/it] {'loss': 2.9848, 'learning_rate': 1.9380915337741476e-07, 'epoch': 1.04} + 6%|▋ | 4020/61904 [2:05:21<21:47:18, 1.36s/it] 6%|▋ | 4021/61904 [2:05:22<21:59:02, 1.37s/it] 6%|▋ | 4022/61904 [2:05:24<22:07:03, 1.38s/it] 6%|▋ | 4023/61904 [2:05:25<22:43:30, 1.41s/it] 7%|▋ | 4024/61904 [2:05:26<22:37:10, 1.41s/it] 7%|▋ | 4025/61904 [2:05:28<22:10:17, 1.38s/it] 7%|▋ | 4026/61904 [2:05:29<21:54:58, 1.36s/it] 7%|▋ | 4027/61904 [2:05:30<21:37:39, 1.35s/it] 7%|▋ | 4028/61904 [2:05:32<21:15:59, 1.32s/it] 7%|▋ | 4029/61904 [2:05:33<20:56:53, 1.30s/it] 7%|▋ | 4030/61904 [2:05:34<21:55:25, 1.36s/it] 7%|▋ | 4031/61904 [2:05:36<22:15:11, 1.38s/it] 7%|▋ | 4032/61904 [2:05:37<21:24:57, 1.33s/it] 7%|▋ | 4033/61904 [2:05:38<21:40:47, 1.35s/it] 7%|▋ | 4034/61904 [2:05:40<21:36:55, 1.34s/it] 7%|▋ | 4035/61904 [2:05:41<21:18:27, 1.33s/it] 7%|▋ | 4036/61904 [2:05:42<21:27:05, 1.33s/it] 7%|▋ | 4037/61904 [2:05:44<21:27:35, 1.34s/it] 7%|▋ | 4038/61904 [2:05:45<21:43:47, 1.35s/it] 7%|▋ | 4039/61904 [2:05:47<22:10:17, 1.38s/it] 7%|▋ | 4040/61904 [2:05:48<21:41:40, 1.35s/it] {'loss': 3.0765, 'learning_rate': 1.937767405678724e-07, 'epoch': 1.04} + 7%|▋ | 4040/61904 [2:05:48<21:41:40, 1.35s/it] 7%|▋ | 4041/61904 [2:05:50<23:09:44, 1.44s/it] 7%|▋ | 4042/61904 [2:05:51<22:40:56, 1.41s/it] 7%|▋ | 4043/61904 [2:05:52<21:46:40, 1.35s/it] 7%|▋ | 4044/61904 [2:05:53<21:27:39, 1.34s/it] 7%|▋ | 4045/61904 [2:05:55<22:40:59, 1.41s/it] 7%|▋ | 4046/61904 [2:05:56<22:55:18, 1.43s/it] 7%|▋ | 4047/61904 [2:05:58<23:58:12, 1.49s/it] 7%|▋ | 4048/61904 [2:06:00<23:55:53, 1.49s/it] 7%|▋ | 4049/61904 [2:06:01<23:16:07, 1.45s/it] 7%|▋ | 4050/61904 [2:06:02<22:09:33, 1.38s/it] 7%|▋ | 4051/61904 [2:06:04<22:05:46, 1.37s/it] 7%|▋ | 4052/61904 [2:06:05<22:27:30, 1.40s/it] 7%|▋ | 4053/61904 [2:06:06<22:12:26, 1.38s/it] 7%|▋ | 4054/61904 [2:06:08<22:20:25, 1.39s/it] 7%|▋ | 4055/61904 [2:06:09<21:38:51, 1.35s/it] 7%|▋ | 4056/61904 [2:06:10<21:17:06, 1.32s/it] 7%|▋ | 4057/61904 [2:06:12<21:17:15, 1.32s/it] 7%|▋ | 4058/61904 [2:06:13<21:30:52, 1.34s/it] 7%|▋ | 4059/61904 [2:06:14<22:15:32, 1.39s/it] 7%|▋ | 4060/61904 [2:06:16<22:41:30, 1.41s/it] {'loss': 2.9827, 'learning_rate': 1.9374432775833008e-07, 'epoch': 1.05} + 7%|▋ | 4060/61904 [2:06:16<22:41:30, 1.41s/it] 7%|▋ | 4061/61904 [2:06:17<22:20:38, 1.39s/it] 7%|▋ | 4062/61904 [2:06:19<22:01:34, 1.37s/it] 7%|▋ | 4063/61904 [2:06:20<21:41:03, 1.35s/it] 7%|▋ | 4064/61904 [2:06:21<22:11:22, 1.38s/it] 7%|▋ | 4065/61904 [2:06:23<21:44:59, 1.35s/it] 7%|▋ | 4066/61904 [2:06:24<21:27:05, 1.34s/it] 7%|▋ | 4067/61904 [2:06:25<21:03:10, 1.31s/it] 7%|▋ | 4068/61904 [2:06:27<22:09:03, 1.38s/it] 7%|▋ | 4069/61904 [2:06:28<22:35:37, 1.41s/it] 7%|▋ | 4070/61904 [2:06:29<21:54:23, 1.36s/it] 7%|▋ | 4071/61904 [2:06:31<22:20:21, 1.39s/it] 7%|▋ | 4072/61904 [2:06:32<22:11:46, 1.38s/it] 7%|▋ | 4073/61904 [2:06:34<23:03:34, 1.44s/it] 7%|▋ | 4074/61904 [2:06:35<22:48:32, 1.42s/it] 7%|▋ | 4075/61904 [2:06:36<22:01:28, 1.37s/it] 7%|▋ | 4076/61904 [2:06:38<21:22:01, 1.33s/it] 7%|▋ | 4077/61904 [2:06:39<20:48:31, 1.30s/it] 7%|▋ | 4078/61904 [2:06:40<21:00:06, 1.31s/it] 7%|▋ | 4079/61904 [2:06:42<21:55:31, 1.37s/it] 7%|▋ | 4080/61904 [2:06:43<21:51:36, 1.36s/it] {'loss': 3.0336, 'learning_rate': 1.9371191494878777e-07, 'epoch': 1.05} + 7%|▋ | 4080/61904 [2:06:43<21:51:36, 1.36s/it] 7%|▋ | 4081/61904 [2:06:44<21:41:30, 1.35s/it] 7%|▋ | 4082/61904 [2:06:46<21:31:30, 1.34s/it] 7%|▋ | 4083/61904 [2:06:47<21:09:19, 1.32s/it] 7%|▋ | 4084/61904 [2:06:48<21:15:43, 1.32s/it] 7%|▋ | 4085/61904 [2:06:50<21:08:02, 1.32s/it] 7%|▋ | 4086/61904 [2:06:51<22:17:13, 1.39s/it] 7%|▋ | 4087/61904 [2:06:52<21:51:32, 1.36s/it] 7%|▋ | 4088/61904 [2:06:54<21:30:08, 1.34s/it] 7%|▋ | 4089/61904 [2:06:55<21:44:07, 1.35s/it] 7%|▋ | 4090/61904 [2:06:57<22:15:49, 1.39s/it] 7%|▋ | 4091/61904 [2:06:58<22:16:48, 1.39s/it] 7%|▋ | 4092/61904 [2:06:59<22:30:20, 1.40s/it] 7%|▋ | 4093/61904 [2:07:01<22:37:42, 1.41s/it] 7%|▋ | 4094/61904 [2:07:02<22:52:55, 1.42s/it] 7%|▋ | 4095/61904 [2:07:04<22:43:29, 1.42s/it] 7%|▋ | 4096/61904 [2:07:05<22:13:14, 1.38s/it] 7%|▋ | 4097/61904 [2:07:06<21:45:57, 1.36s/it] 7%|▋ | 4098/61904 [2:07:08<21:42:27, 1.35s/it] 7%|▋ | 4099/61904 [2:07:09<21:59:22, 1.37s/it] 7%|▋ | 4100/61904 [2:07:10<21:55:34, 1.37s/it] {'loss': 3.0382, 'learning_rate': 1.936795021392454e-07, 'epoch': 1.06} + 7%|▋ | 4100/61904 [2:07:10<21:55:34, 1.37s/it] 7%|▋ | 4101/61904 [2:07:12<22:06:10, 1.38s/it] 7%|▋ | 4102/61904 [2:07:13<22:03:33, 1.37s/it] 7%|▋ | 4103/61904 [2:07:15<21:59:59, 1.37s/it] 7%|▋ | 4104/61904 [2:07:16<21:40:10, 1.35s/it] 7%|▋ | 4105/61904 [2:07:17<22:00:13, 1.37s/it] 7%|▋ | 4106/61904 [2:07:19<21:20:43, 1.33s/it] 7%|▋ | 4107/61904 [2:07:20<20:58:03, 1.31s/it] 7%|▋ | 4108/61904 [2:07:21<21:26:21, 1.34s/it] 7%|▋ | 4109/61904 [2:07:23<21:22:39, 1.33s/it] 7%|▋ | 4110/61904 [2:07:24<21:48:04, 1.36s/it] 7%|▋ | 4111/61904 [2:07:25<22:07:34, 1.38s/it] 7%|▋ | 4112/61904 [2:07:27<22:30:23, 1.40s/it] 7%|▋ | 4113/61904 [2:07:28<21:13:54, 1.32s/it] 7%|▋ | 4114/61904 [2:07:29<21:29:11, 1.34s/it] 7%|▋ | 4115/61904 [2:07:31<21:40:06, 1.35s/it] 7%|▋ | 4116/61904 [2:07:32<21:14:45, 1.32s/it] 7%|▋ | 4117/61904 [2:07:33<21:00:34, 1.31s/it] 7%|▋ | 4118/61904 [2:07:35<21:48:57, 1.36s/it] 7%|▋ | 4119/61904 [2:07:36<21:31:49, 1.34s/it] 7%|▋ | 4120/61904 [2:07:37<21:01:30, 1.31s/it] {'loss': 2.9706, 'learning_rate': 1.936470893297031e-07, 'epoch': 1.06} + 7%|▋ | 4120/61904 [2:07:37<21:01:30, 1.31s/it] 7%|▋ | 4121/61904 [2:07:39<21:49:28, 1.36s/it] 7%|▋ | 4122/61904 [2:07:40<22:14:23, 1.39s/it] 7%|▋ | 4123/61904 [2:07:42<22:07:11, 1.38s/it] 7%|▋ | 4124/61904 [2:07:43<22:27:40, 1.40s/it] 7%|▋ | 4125/61904 [2:07:44<22:16:20, 1.39s/it] 7%|▋ | 4126/61904 [2:07:46<22:01:35, 1.37s/it] 7%|▋ | 4127/61904 [2:07:47<22:19:50, 1.39s/it] 7%|▋ | 4128/61904 [2:07:49<22:29:44, 1.40s/it] 7%|▋ | 4129/61904 [2:07:50<21:39:44, 1.35s/it] 7%|▋ | 4130/61904 [2:07:51<20:56:42, 1.31s/it] 7%|▋ | 4131/61904 [2:07:52<21:19:34, 1.33s/it] 7%|▋ | 4132/61904 [2:07:54<21:45:46, 1.36s/it] 7%|▋ | 4133/61904 [2:07:55<21:29:18, 1.34s/it] 7%|▋ | 4134/61904 [2:07:56<21:44:27, 1.35s/it] 7%|▋ | 4135/61904 [2:07:58<21:41:01, 1.35s/it] 7%|▋ | 4136/61904 [2:07:59<21:33:48, 1.34s/it] 7%|▋ | 4137/61904 [2:08:00<21:28:00, 1.34s/it] 7%|▋ | 4138/61904 [2:08:02<21:58:07, 1.37s/it] 7%|▋ | 4139/61904 [2:08:03<21:23:07, 1.33s/it] 7%|▋ | 4140/61904 [2:08:05<21:53:59, 1.36s/it] {'loss': 2.9261, 'learning_rate': 1.9361467652016076e-07, 'epoch': 1.07} + 7%|▋ | 4140/61904 [2:08:05<21:53:59, 1.36s/it] 7%|▋ | 4141/61904 [2:08:06<21:56:30, 1.37s/it] 7%|▋ | 4142/61904 [2:08:07<21:49:41, 1.36s/it] 7%|▋ | 4143/61904 [2:08:09<22:18:08, 1.39s/it] 7%|▋ | 4144/61904 [2:08:10<22:01:49, 1.37s/it] 7%|▋ | 4145/61904 [2:08:11<21:39:54, 1.35s/it] 7%|▋ | 4146/61904 [2:08:13<22:08:55, 1.38s/it] 7%|▋ | 4147/61904 [2:08:14<21:39:57, 1.35s/it] 7%|▋ | 4148/61904 [2:08:16<22:00:04, 1.37s/it] 7%|▋ | 4149/61904 [2:08:17<22:40:35, 1.41s/it] 7%|▋ | 4150/61904 [2:08:18<22:08:09, 1.38s/it] 7%|▋ | 4151/61904 [2:08:20<22:34:32, 1.41s/it] 7%|▋ | 4152/61904 [2:08:21<22:14:39, 1.39s/it] 7%|▋ | 4153/61904 [2:08:23<23:07:12, 1.44s/it] 7%|▋ | 4154/61904 [2:08:24<23:00:06, 1.43s/it] 7%|▋ | 4155/61904 [2:08:25<22:18:00, 1.39s/it] 7%|▋ | 4156/61904 [2:08:27<22:07:57, 1.38s/it] 7%|▋ | 4157/61904 [2:08:28<22:09:30, 1.38s/it] 7%|▋ | 4158/61904 [2:08:30<22:44:00, 1.42s/it] 7%|▋ | 4159/61904 [2:08:31<22:28:16, 1.40s/it] 7%|▋ | 4160/61904 [2:08:32<21:46:07, 1.36s/it] {'loss': 3.0358, 'learning_rate': 1.9358226371061842e-07, 'epoch': 1.08} + 7%|▋ | 4160/61904 [2:08:32<21:46:07, 1.36s/it] 7%|▋ | 4161/61904 [2:08:34<22:02:47, 1.37s/it] 7%|▋ | 4162/61904 [2:08:35<21:42:05, 1.35s/it] 7%|▋ | 4163/61904 [2:08:36<22:09:05, 1.38s/it] 7%|▋ | 4164/61904 [2:08:38<22:34:24, 1.41s/it] 7%|▋ | 4165/61904 [2:08:39<21:51:12, 1.36s/it] 7%|▋ | 4166/61904 [2:08:41<22:04:09, 1.38s/it] 7%|▋ | 4167/61904 [2:08:42<21:44:09, 1.36s/it] 7%|▋ | 4168/61904 [2:08:43<21:34:25, 1.35s/it] 7%|▋ | 4169/61904 [2:08:45<21:28:40, 1.34s/it] 7%|▋ | 4170/61904 [2:08:46<21:42:51, 1.35s/it] 7%|▋ | 4171/61904 [2:08:47<22:23:57, 1.40s/it] 7%|▋ | 4172/61904 [2:08:49<22:28:35, 1.40s/it] 7%|▋ | 4173/61904 [2:08:50<22:28:48, 1.40s/it] 7%|▋ | 4174/61904 [2:08:52<22:28:48, 1.40s/it] 7%|▋ | 4175/61904 [2:08:53<22:33:18, 1.41s/it] 7%|▋ | 4176/61904 [2:08:54<21:59:24, 1.37s/it] 7%|▋ | 4177/61904 [2:08:56<21:43:55, 1.36s/it] 7%|▋ | 4178/61904 [2:08:57<21:07:11, 1.32s/it] 7%|▋ | 4179/61904 [2:08:58<20:54:37, 1.30s/it] 7%|▋ | 4180/61904 [2:08:59<20:23:55, 1.27s/it] {'loss': 3.0442, 'learning_rate': 1.935498509010761e-07, 'epoch': 1.08} + 7%|▋ | 4180/61904 [2:08:59<20:23:55, 1.27s/it] 7%|▋ | 4181/61904 [2:09:01<20:27:07, 1.28s/it] 7%|▋ | 4182/61904 [2:09:02<20:34:21, 1.28s/it] 7%|▋ | 4183/61904 [2:09:03<21:26:16, 1.34s/it] 7%|▋ | 4184/61904 [2:09:05<21:46:35, 1.36s/it] 7%|▋ | 4185/61904 [2:09:06<22:21:38, 1.39s/it] 7%|▋ | 4186/61904 [2:09:08<22:54:57, 1.43s/it] 7%|▋ | 4187/61904 [2:09:09<22:47:34, 1.42s/it] 7%|▋ | 4188/61904 [2:09:10<22:00:11, 1.37s/it] 7%|▋ | 4189/61904 [2:09:12<21:23:26, 1.33s/it] 7%|▋ | 4190/61904 [2:09:13<21:10:41, 1.32s/it] 7%|▋ | 4191/61904 [2:09:14<21:17:50, 1.33s/it] 7%|▋ | 4192/61904 [2:09:16<21:35:01, 1.35s/it] 7%|▋ | 4193/61904 [2:09:17<21:39:38, 1.35s/it] 7%|▋ | 4194/61904 [2:09:18<21:32:45, 1.34s/it] 7%|▋ | 4195/61904 [2:09:20<21:05:35, 1.32s/it] 7%|▋ | 4196/61904 [2:09:21<21:26:44, 1.34s/it] 7%|▋ | 4197/61904 [2:09:23<22:14:16, 1.39s/it] 7%|▋ | 4198/61904 [2:09:24<22:27:25, 1.40s/it] 7%|▋ | 4199/61904 [2:09:25<22:08:12, 1.38s/it] 7%|▋ | 4200/61904 [2:09:27<22:17:34, 1.39s/it] {'loss': 2.9493, 'learning_rate': 1.9351743809153377e-07, 'epoch': 1.09} + 7%|▋ | 4200/61904 [2:09:27<22:17:34, 1.39s/it] 7%|▋ | 4201/61904 [2:09:28<22:10:11, 1.38s/it] 7%|▋ | 4202/61904 [2:09:29<21:51:06, 1.36s/it] 7%|▋ | 4203/61904 [2:09:31<21:32:50, 1.34s/it] 7%|▋ | 4204/61904 [2:09:32<21:15:41, 1.33s/it] 7%|▋ | 4205/61904 [2:09:33<21:15:54, 1.33s/it] 7%|▋ | 4206/61904 [2:09:35<21:25:38, 1.34s/it] 7%|▋ | 4207/61904 [2:09:36<21:45:13, 1.36s/it] 7%|▋ | 4208/61904 [2:09:37<21:35:05, 1.35s/it] 7%|▋ | 4209/61904 [2:09:39<23:00:06, 1.44s/it] 7%|▋ | 4210/61904 [2:09:40<22:50:10, 1.42s/it] 7%|▋ | 4211/61904 [2:09:42<22:36:45, 1.41s/it] 7%|▋ | 4212/61904 [2:09:43<23:18:40, 1.45s/it] 7%|▋ | 4213/61904 [2:09:45<22:43:37, 1.42s/it] 7%|▋ | 4214/61904 [2:09:46<22:43:26, 1.42s/it] 7%|▋ | 4215/61904 [2:09:48<22:50:22, 1.43s/it] 7%|▋ | 4216/61904 [2:09:49<22:04:26, 1.38s/it] 7%|▋ | 4217/61904 [2:09:50<21:39:35, 1.35s/it] 7%|▋ | 4218/61904 [2:09:52<21:51:24, 1.36s/it] 7%|▋ | 4219/61904 [2:09:53<22:04:32, 1.38s/it] 7%|▋ | 4220/61904 [2:09:54<22:17:52, 1.39s/it] {'loss': 2.9963, 'learning_rate': 1.9348502528199143e-07, 'epoch': 1.09} + 7%|▋ | 4220/61904 [2:09:54<22:17:52, 1.39s/it] 7%|▋ | 4221/61904 [2:09:56<23:32:17, 1.47s/it] 7%|▋ | 4222/61904 [2:09:57<23:04:38, 1.44s/it] 7%|▋ | 4223/61904 [2:09:59<22:46:57, 1.42s/it] 7%|▋ | 4224/61904 [2:10:00<22:45:06, 1.42s/it] 7%|▋ | 4225/61904 [2:10:02<23:06:48, 1.44s/it] 7%|▋ | 4226/61904 [2:10:03<22:33:04, 1.41s/it] 7%|▋ | 4227/61904 [2:10:05<23:41:34, 1.48s/it] 7%|▋ | 4228/61904 [2:10:06<24:04:48, 1.50s/it] 7%|▋ | 4229/61904 [2:10:08<23:51:13, 1.49s/it] 7%|▋ | 4230/61904 [2:10:09<23:30:12, 1.47s/it] 7%|▋ | 4231/61904 [2:10:10<22:32:24, 1.41s/it] 7%|▋ | 4232/61904 [2:10:12<21:22:40, 1.33s/it] 7%|▋ | 4233/61904 [2:10:13<21:44:56, 1.36s/it] 7%|▋ | 4234/61904 [2:10:14<21:45:09, 1.36s/it] 7%|▋ | 4235/61904 [2:10:16<21:48:25, 1.36s/it] 7%|▋ | 4236/61904 [2:10:17<22:07:42, 1.38s/it] 7%|▋ | 4237/61904 [2:10:18<22:00:59, 1.37s/it] 7%|▋ | 4238/61904 [2:10:20<21:59:38, 1.37s/it] 7%|▋ | 4239/61904 [2:10:21<21:29:53, 1.34s/it] 7%|▋ | 4240/61904 [2:10:23<21:54:32, 1.37s/it] {'loss': 3.0102, 'learning_rate': 1.9345261247244912e-07, 'epoch': 1.1} + 7%|▋ | 4240/61904 [2:10:23<21:54:32, 1.37s/it] 7%|▋ | 4241/61904 [2:10:24<21:46:10, 1.36s/it] 7%|▋ | 4242/61904 [2:10:25<21:56:07, 1.37s/it] 7%|▋ | 4243/61904 [2:10:27<21:28:02, 1.34s/it] 7%|▋ | 4244/61904 [2:10:28<21:02:51, 1.31s/it] 7%|▋ | 4245/61904 [2:10:29<21:06:14, 1.32s/it] 7%|▋ | 4246/61904 [2:10:30<21:14:03, 1.33s/it] 7%|▋ | 4247/61904 [2:10:32<21:48:24, 1.36s/it] 7%|▋ | 4248/61904 [2:10:33<21:36:39, 1.35s/it] 7%|▋ | 4249/61904 [2:10:35<22:40:34, 1.42s/it] 7%|▋ | 4250/61904 [2:10:36<23:21:29, 1.46s/it] 7%|▋ | 4251/61904 [2:10:38<22:36:02, 1.41s/it] 7%|▋ | 4252/61904 [2:10:39<22:35:02, 1.41s/it] 7%|▋ | 4253/61904 [2:10:40<21:52:54, 1.37s/it] 7%|▋ | 4254/61904 [2:10:42<21:21:40, 1.33s/it] 7%|▋ | 4255/61904 [2:10:43<21:28:02, 1.34s/it] 7%|▋ | 4256/61904 [2:10:44<21:33:44, 1.35s/it] 7%|▋ | 4257/61904 [2:10:46<20:58:43, 1.31s/it] 7%|▋ | 4258/61904 [2:10:47<20:54:26, 1.31s/it] 7%|▋ | 4259/61904 [2:10:48<20:51:39, 1.30s/it] 7%|▋ | 4260/61904 [2:10:50<21:14:50, 1.33s/it] {'loss': 2.9861, 'learning_rate': 1.9342019966290675e-07, 'epoch': 1.1} + 7%|▋ | 4260/61904 [2:10:50<21:14:50, 1.33s/it] 7%|▋ | 4261/61904 [2:10:51<21:24:25, 1.34s/it] 7%|▋ | 4262/61904 [2:10:52<21:45:08, 1.36s/it] 7%|▋ | 4263/61904 [2:10:54<21:39:24, 1.35s/it] 7%|▋ | 4264/61904 [2:10:55<21:33:26, 1.35s/it] 7%|▋ | 4265/61904 [2:10:56<21:51:20, 1.37s/it] 7%|▋ | 4266/61904 [2:10:58<21:31:19, 1.34s/it] 7%|▋ | 4267/61904 [2:10:59<21:16:09, 1.33s/it] 7%|▋ | 4268/61904 [2:11:00<21:13:16, 1.33s/it] 7%|▋ | 4269/61904 [2:11:02<21:15:14, 1.33s/it] 7%|▋ | 4270/61904 [2:11:03<20:59:51, 1.31s/it] 7%|▋ | 4271/61904 [2:11:04<20:53:33, 1.31s/it] 7%|▋ | 4272/61904 [2:11:06<22:25:31, 1.40s/it] 7%|▋ | 4273/61904 [2:11:07<21:55:58, 1.37s/it] 7%|▋ | 4274/61904 [2:11:09<22:29:24, 1.40s/it] 7%|▋ | 4275/61904 [2:11:10<22:13:02, 1.39s/it] 7%|▋ | 4276/61904 [2:11:11<22:36:34, 1.41s/it] 7%|▋ | 4277/61904 [2:11:13<21:58:58, 1.37s/it] 7%|▋ | 4278/61904 [2:11:14<23:16:53, 1.45s/it] 7%|▋ | 4279/61904 [2:11:16<22:30:53, 1.41s/it] 7%|▋ | 4280/61904 [2:11:17<22:32:06, 1.41s/it] {'loss': 3.0209, 'learning_rate': 1.9338778685336444e-07, 'epoch': 1.11} + 7%|▋ | 4280/61904 [2:11:17<22:32:06, 1.41s/it] 7%|▋ | 4281/61904 [2:11:18<22:07:16, 1.38s/it] 7%|▋ | 4282/61904 [2:11:20<21:19:24, 1.33s/it] 7%|▋ | 4283/61904 [2:11:21<22:04:09, 1.38s/it] 7%|▋ | 4284/61904 [2:11:22<22:16:57, 1.39s/it] 7%|▋ | 4285/61904 [2:11:24<22:25:41, 1.40s/it] 7%|▋ | 4286/61904 [2:11:25<22:54:56, 1.43s/it] 7%|▋ | 4287/61904 [2:11:27<22:48:45, 1.43s/it] 7%|▋ | 4288/61904 [2:11:28<22:13:29, 1.39s/it] 7%|▋ | 4289/61904 [2:11:30<22:35:36, 1.41s/it] 7%|▋ | 4290/61904 [2:11:31<22:22:52, 1.40s/it] 7%|▋ | 4291/61904 [2:11:32<22:34:00, 1.41s/it] 7%|▋ | 4292/61904 [2:11:34<22:02:46, 1.38s/it] 7%|▋ | 4293/61904 [2:11:35<21:57:59, 1.37s/it] 7%|▋ | 4294/61904 [2:11:36<22:07:55, 1.38s/it] 7%|▋ | 4295/61904 [2:11:38<21:44:04, 1.36s/it] 7%|▋ | 4296/61904 [2:11:39<22:02:47, 1.38s/it] 7%|▋ | 4297/61904 [2:11:40<21:42:20, 1.36s/it] 7%|▋ | 4298/61904 [2:11:42<21:13:16, 1.33s/it] 7%|▋ | 4299/61904 [2:11:43<21:34:06, 1.35s/it] 7%|▋ | 4300/61904 [2:11:45<21:42:07, 1.36s/it] {'loss': 2.9864, 'learning_rate': 1.933553740438221e-07, 'epoch': 1.11} + 7%|▋ | 4300/61904 [2:11:45<21:42:07, 1.36s/it] 7%|▋ | 4301/61904 [2:11:46<23:03:25, 1.44s/it] 7%|▋ | 4302/61904 [2:11:47<22:13:14, 1.39s/it] 7%|▋ | 4303/61904 [2:11:49<21:33:06, 1.35s/it] 7%|▋ | 4304/61904 [2:11:50<21:24:29, 1.34s/it] 7%|▋ | 4305/61904 [2:11:51<21:11:49, 1.32s/it] 7%|▋ | 4306/61904 [2:11:53<21:34:39, 1.35s/it] 7%|▋ | 4307/61904 [2:11:54<21:45:06, 1.36s/it] 7%|▋ | 4308/61904 [2:11:55<21:26:38, 1.34s/it] 7%|▋ | 4309/61904 [2:11:57<21:55:39, 1.37s/it] 7%|▋ | 4310/61904 [2:11:58<21:24:26, 1.34s/it] 7%|▋ | 4311/61904 [2:11:59<21:25:22, 1.34s/it] 7%|▋ | 4312/61904 [2:12:01<21:14:41, 1.33s/it] 7%|▋ | 4313/61904 [2:12:02<22:28:00, 1.40s/it] 7%|▋ | 4314/61904 [2:12:04<21:52:49, 1.37s/it] 7%|▋ | 4315/61904 [2:12:05<22:09:22, 1.39s/it] 7%|▋ | 4316/61904 [2:12:06<21:24:52, 1.34s/it] 7%|▋ | 4317/61904 [2:12:08<21:05:21, 1.32s/it] 7%|▋ | 4318/61904 [2:12:09<20:49:37, 1.30s/it] 7%|▋ | 4319/61904 [2:12:10<20:54:54, 1.31s/it] 7%|▋ | 4320/61904 [2:12:12<21:35:32, 1.35s/it] {'loss': 2.9766, 'learning_rate': 1.9332296123427977e-07, 'epoch': 1.12} + 7%|▋ | 4320/61904 [2:12:12<21:35:32, 1.35s/it] 7%|▋ | 4321/61904 [2:12:13<21:37:06, 1.35s/it] 7%|▋ | 4322/61904 [2:12:14<22:00:41, 1.38s/it] 7%|▋ | 4323/61904 [2:12:16<22:19:53, 1.40s/it] 7%|▋ | 4324/61904 [2:12:17<22:19:41, 1.40s/it] 7%|▋ | 4325/61904 [2:12:18<21:42:02, 1.36s/it] 7%|▋ | 4326/61904 [2:12:20<22:03:50, 1.38s/it] 7%|▋ | 4327/61904 [2:12:21<21:52:51, 1.37s/it] 7%|▋ | 4328/61904 [2:12:23<22:38:16, 1.42s/it] 7%|▋ | 4329/61904 [2:12:24<22:28:58, 1.41s/it] 7%|▋ | 4330/61904 [2:12:26<22:37:18, 1.41s/it] 7%|▋ | 4331/61904 [2:12:27<22:22:28, 1.40s/it] 7%|▋ | 4332/61904 [2:12:28<22:03:34, 1.38s/it] 7%|▋ | 4333/61904 [2:12:30<22:06:58, 1.38s/it] 7%|▋ | 4334/61904 [2:12:31<22:12:35, 1.39s/it] 7%|▋ | 4335/61904 [2:12:32<21:58:49, 1.37s/it] 7%|▋ | 4336/61904 [2:12:34<22:14:24, 1.39s/it] 7%|▋ | 4337/61904 [2:12:35<22:01:58, 1.38s/it] 7%|▋ | 4338/61904 [2:12:36<21:26:43, 1.34s/it] 7%|▋ | 4339/61904 [2:12:38<21:06:48, 1.32s/it] 7%|▋ | 4340/61904 [2:12:39<21:56:27, 1.37s/it] {'loss': 3.0403, 'learning_rate': 1.9329054842473745e-07, 'epoch': 1.12} + 7%|▋ | 4340/61904 [2:12:39<21:56:27, 1.37s/it] 7%|▋ | 4341/61904 [2:12:41<22:23:00, 1.40s/it] 7%|▋ | 4342/61904 [2:12:42<22:20:15, 1.40s/it] 7%|▋ | 4343/61904 [2:12:43<22:03:43, 1.38s/it] 7%|▋ | 4344/61904 [2:12:45<21:46:07, 1.36s/it] 7%|▋ | 4345/61904 [2:12:46<21:56:03, 1.37s/it] 7%|▋ | 4346/61904 [2:12:47<21:42:57, 1.36s/it] 7%|▋ | 4347/61904 [2:12:49<21:51:25, 1.37s/it] 7%|▋ | 4348/61904 [2:12:50<22:04:13, 1.38s/it] 7%|▋ | 4349/61904 [2:12:52<21:54:32, 1.37s/it] 7%|▋ | 4350/61904 [2:12:53<23:06:46, 1.45s/it] 7%|▋ | 4351/61904 [2:12:55<22:33:51, 1.41s/it] 7%|▋ | 4352/61904 [2:12:56<22:23:25, 1.40s/it] 7%|▋ | 4353/61904 [2:12:57<21:26:10, 1.34s/it] 7%|▋ | 4354/61904 [2:12:58<21:17:51, 1.33s/it] 7%|▋ | 4355/61904 [2:13:00<20:41:47, 1.29s/it] 7%|▋ | 4356/61904 [2:13:01<21:47:42, 1.36s/it] 7%|▋ | 4357/61904 [2:13:03<22:11:15, 1.39s/it] 7%|▋ | 4358/61904 [2:13:04<21:34:22, 1.35s/it] 7%|▋ | 4359/61904 [2:13:05<21:24:18, 1.34s/it] 7%|▋ | 4360/61904 [2:13:06<21:19:11, 1.33s/it] {'loss': 2.9861, 'learning_rate': 1.9325813561519512e-07, 'epoch': 1.13} + 7%|▋ | 4360/61904 [2:13:06<21:19:11, 1.33s/it] 7%|▋ | 4361/61904 [2:13:08<21:17:27, 1.33s/it] 7%|▋ | 4362/61904 [2:13:09<21:08:59, 1.32s/it] 7%|▋ | 4363/61904 [2:13:10<21:28:44, 1.34s/it] 7%|▋ | 4364/61904 [2:13:12<22:16:29, 1.39s/it] 7%|▋ | 4365/61904 [2:13:13<22:10:12, 1.39s/it] 7%|▋ | 4366/61904 [2:13:15<22:17:03, 1.39s/it] 7%|▋ | 4367/61904 [2:13:16<22:30:48, 1.41s/it] 7%|▋ | 4368/61904 [2:13:18<22:13:36, 1.39s/it] 7%|▋ | 4369/61904 [2:13:19<21:44:00, 1.36s/it] 7%|▋ | 4370/61904 [2:13:20<21:27:29, 1.34s/it] 7%|▋ | 4371/61904 [2:13:21<21:13:04, 1.33s/it] 7%|▋ | 4372/61904 [2:13:23<21:40:55, 1.36s/it] 7%|▋ | 4373/61904 [2:13:24<21:08:55, 1.32s/it] 7%|▋ | 4374/61904 [2:13:25<20:36:51, 1.29s/it] 7%|▋ | 4375/61904 [2:13:27<20:53:08, 1.31s/it] 7%|▋ | 4376/61904 [2:13:28<20:35:46, 1.29s/it] 7%|▋ | 4377/61904 [2:13:29<20:59:22, 1.31s/it] 7%|▋ | 4378/61904 [2:13:31<21:01:22, 1.32s/it] 7%|▋ | 4379/61904 [2:13:32<21:55:11, 1.37s/it] 7%|▋ | 4380/61904 [2:13:33<21:25:00, 1.34s/it] {'loss': 3.0244, 'learning_rate': 1.9322572280565278e-07, 'epoch': 1.13} + 7%|▋ | 4380/61904 [2:13:33<21:25:00, 1.34s/it] 7%|▋ | 4381/61904 [2:13:35<21:24:08, 1.34s/it] 7%|▋ | 4382/61904 [2:13:36<21:45:59, 1.36s/it] 7%|▋ | 4383/61904 [2:13:38<21:46:27, 1.36s/it] 7%|▋ | 4384/61904 [2:13:39<21:34:10, 1.35s/it] 7%|▋ | 4385/61904 [2:13:40<21:31:16, 1.35s/it] 7%|▋ | 4386/61904 [2:13:41<21:16:20, 1.33s/it] 7%|▋ | 4387/61904 [2:13:43<21:21:03, 1.34s/it] 7%|▋ | 4388/61904 [2:13:44<21:36:43, 1.35s/it] 7%|▋ | 4389/61904 [2:13:45<21:08:33, 1.32s/it] 7%|▋ | 4390/61904 [2:13:47<21:53:35, 1.37s/it] 7%|▋ | 4391/61904 [2:13:48<21:40:14, 1.36s/it] 7%|▋ | 4392/61904 [2:13:50<21:25:54, 1.34s/it] 7%|▋ | 4393/61904 [2:13:51<21:05:17, 1.32s/it] 7%|▋ | 4394/61904 [2:13:52<21:38:24, 1.35s/it] 7%|▋ | 4395/61904 [2:13:54<21:55:10, 1.37s/it] 7%|▋ | 4396/61904 [2:13:55<21:43:11, 1.36s/it] 7%|▋ | 4397/61904 [2:13:56<22:02:49, 1.38s/it] 7%|▋ | 4398/61904 [2:13:58<22:08:40, 1.39s/it] 7%|▋ | 4399/61904 [2:13:59<23:03:52, 1.44s/it] 7%|▋ | 4400/61904 [2:14:01<22:22:07, 1.40s/it] {'loss': 2.9827, 'learning_rate': 1.9319330999611047e-07, 'epoch': 1.14} + 7%|▋ | 4400/61904 [2:14:01<22:22:07, 1.40s/it] 7%|▋ | 4401/61904 [2:14:02<21:43:03, 1.36s/it] 7%|▋ | 4402/61904 [2:14:03<21:05:27, 1.32s/it] 7%|▋ | 4403/61904 [2:14:05<21:09:37, 1.32s/it] 7%|▋ | 4404/61904 [2:14:06<21:05:00, 1.32s/it] 7%|▋ | 4405/61904 [2:14:07<21:06:13, 1.32s/it] 7%|▋ | 4406/61904 [2:14:09<21:19:15, 1.33s/it] 7%|▋ | 4407/61904 [2:14:10<21:28:22, 1.34s/it] 7%|▋ | 4408/61904 [2:14:11<21:42:57, 1.36s/it] 7%|▋ | 4409/61904 [2:14:13<21:34:22, 1.35s/it] 7%|▋ | 4410/61904 [2:14:14<21:56:08, 1.37s/it] 7%|▋ | 4411/61904 [2:14:15<22:04:11, 1.38s/it] 7%|▋ | 4412/61904 [2:14:17<21:46:11, 1.36s/it] 7%|▋ | 4413/61904 [2:14:18<21:55:05, 1.37s/it] 7%|▋ | 4414/61904 [2:14:20<22:47:12, 1.43s/it] 7%|▋ | 4415/61904 [2:14:21<22:56:53, 1.44s/it] 7%|▋ | 4416/61904 [2:14:23<22:33:57, 1.41s/it] 7%|▋ | 4417/61904 [2:14:24<22:20:15, 1.40s/it] 7%|▋ | 4418/61904 [2:14:25<21:48:57, 1.37s/it] 7%|▋ | 4419/61904 [2:14:27<22:07:48, 1.39s/it] 7%|▋ | 4420/61904 [2:14:28<21:45:12, 1.36s/it] {'loss': 3.0343, 'learning_rate': 1.931608971865681e-07, 'epoch': 1.14} + 7%|▋ | 4420/61904 [2:14:28<21:45:12, 1.36s/it] 7%|▋ | 4421/61904 [2:14:29<21:36:25, 1.35s/it] 7%|▋ | 4422/61904 [2:14:31<21:58:25, 1.38s/it] 7%|▋ | 4423/61904 [2:14:32<22:08:30, 1.39s/it] 7%|▋ | 4424/61904 [2:14:33<21:40:59, 1.36s/it] 7%|▋ | 4425/61904 [2:14:35<22:40:35, 1.42s/it] 7%|▋ | 4426/61904 [2:14:36<22:17:47, 1.40s/it] 7%|▋ | 4427/61904 [2:14:38<22:35:02, 1.41s/it] 7%|▋ | 4428/61904 [2:14:39<22:25:16, 1.40s/it] 7%|▋ | 4429/61904 [2:14:40<21:52:11, 1.37s/it] 7%|▋ | 4430/61904 [2:14:42<22:05:42, 1.38s/it] 7%|▋ | 4431/61904 [2:14:43<22:25:42, 1.40s/it] 7%|▋ | 4432/61904 [2:14:45<21:43:43, 1.36s/it] 7%|▋ | 4433/61904 [2:14:46<21:57:12, 1.38s/it] 7%|▋ | 4434/61904 [2:14:47<22:13:45, 1.39s/it] 7%|▋ | 4435/61904 [2:14:49<22:13:31, 1.39s/it] 7%|▋ | 4436/61904 [2:14:50<22:01:58, 1.38s/it] 7%|▋ | 4437/61904 [2:14:51<21:30:21, 1.35s/it] 7%|▋ | 4438/61904 [2:14:53<21:36:22, 1.35s/it] 7%|▋ | 4439/61904 [2:14:54<22:02:43, 1.38s/it] 7%|▋ | 4440/61904 [2:14:56<21:38:46, 1.36s/it] {'loss': 2.9305, 'learning_rate': 1.931284843770258e-07, 'epoch': 1.15} + 7%|▋ | 4440/61904 [2:14:56<21:38:46, 1.36s/it] 7%|▋ | 4441/61904 [2:14:57<21:56:39, 1.37s/it] 7%|▋ | 4442/61904 [2:14:58<22:12:12, 1.39s/it] 7%|▋ | 4443/61904 [2:15:00<21:40:47, 1.36s/it] 7%|▋ | 4444/61904 [2:15:01<20:56:45, 1.31s/it] 7%|▋ | 4445/61904 [2:15:02<20:45:58, 1.30s/it] 7%|▋ | 4446/61904 [2:15:03<20:22:37, 1.28s/it] 7%|▋ | 4447/61904 [2:15:05<21:32:53, 1.35s/it] 7%|▋ | 4448/61904 [2:15:06<22:19:03, 1.40s/it] 7%|▋ | 4449/61904 [2:15:08<22:01:30, 1.38s/it] 7%|▋ | 4450/61904 [2:15:09<22:13:29, 1.39s/it] 7%|▋ | 4451/61904 [2:15:11<23:22:41, 1.46s/it] 7%|▋ | 4452/61904 [2:15:12<22:25:04, 1.40s/it] 7%|▋ | 4453/61904 [2:15:13<22:13:44, 1.39s/it] 7%|▋ | 4454/61904 [2:15:15<21:52:45, 1.37s/it] 7%|▋ | 4455/61904 [2:15:16<22:22:30, 1.40s/it] 7%|▋ | 4456/61904 [2:15:17<21:37:57, 1.36s/it] 7%|▋ | 4457/61904 [2:15:19<22:02:06, 1.38s/it] 7%|▋ | 4458/61904 [2:15:20<22:04:25, 1.38s/it] 7%|▋ | 4459/61904 [2:15:22<22:23:54, 1.40s/it] 7%|▋ | 4460/61904 [2:15:23<21:58:13, 1.38s/it] {'loss': 2.9797, 'learning_rate': 1.9309607156748348e-07, 'epoch': 1.15} + 7%|▋ | 4460/61904 [2:15:23<21:58:13, 1.38s/it] 7%|▋ | 4461/61904 [2:15:24<21:28:13, 1.35s/it] 7%|▋ | 4462/61904 [2:15:26<21:01:15, 1.32s/it] 7%|▋ | 4463/61904 [2:15:27<21:09:26, 1.33s/it] 7%|▋ | 4464/61904 [2:15:28<21:16:45, 1.33s/it] 7%|▋ | 4465/61904 [2:15:30<21:42:16, 1.36s/it] 7%|▋ | 4466/61904 [2:15:31<21:30:41, 1.35s/it] 7%|▋ | 4467/61904 [2:15:33<22:13:21, 1.39s/it] 7%|▋ | 4468/61904 [2:15:34<22:05:18, 1.38s/it] 7%|▋ | 4469/61904 [2:15:35<21:48:59, 1.37s/it] 7%|▋ | 4470/61904 [2:15:37<21:56:48, 1.38s/it] 7%|▋ | 4471/61904 [2:15:38<22:04:14, 1.38s/it] 7%|▋ | 4472/61904 [2:15:40<22:33:57, 1.41s/it] 7%|▋ | 4473/61904 [2:15:41<22:56:28, 1.44s/it] 7%|▋ | 4474/61904 [2:15:42<22:55:59, 1.44s/it] 7%|▋ | 4475/61904 [2:15:44<22:48:25, 1.43s/it] 7%|▋ | 4476/61904 [2:15:45<22:19:31, 1.40s/it] 7%|▋ | 4477/61904 [2:15:47<22:01:17, 1.38s/it] 7%|▋ | 4478/61904 [2:15:48<21:57:46, 1.38s/it] 7%|▋ | 4479/61904 [2:15:49<21:24:26, 1.34s/it] 7%|▋ | 4480/61904 [2:15:51<21:41:19, 1.36s/it] {'loss': 2.9846, 'learning_rate': 1.930636587579411e-07, 'epoch': 1.16} + 7%|▋ | 4480/61904 [2:15:51<21:41:19, 1.36s/it] 7%|▋ | 4481/61904 [2:15:52<22:26:07, 1.41s/it] 7%|▋ | 4482/61904 [2:15:54<23:08:01, 1.45s/it] 7%|▋ | 4483/61904 [2:15:55<22:39:12, 1.42s/it] 7%|▋ | 4484/61904 [2:15:56<22:25:16, 1.41s/it] 7%|▋ | 4485/61904 [2:15:58<22:15:46, 1.40s/it] 7%|▋ | 4486/61904 [2:15:59<22:23:21, 1.40s/it] 7%|▋ | 4487/61904 [2:16:00<22:11:37, 1.39s/it] 7%|▋ | 4488/61904 [2:16:02<22:11:46, 1.39s/it] 7%|▋ | 4489/61904 [2:16:03<21:47:55, 1.37s/it] 7%|▋ | 4490/61904 [2:16:04<20:59:23, 1.32s/it] 7%|▋ | 4491/61904 [2:16:06<21:03:04, 1.32s/it] 7%|▋ | 4492/61904 [2:16:07<21:09:09, 1.33s/it] 7%|▋ | 4493/61904 [2:16:08<21:17:57, 1.34s/it] 7%|▋ | 4494/61904 [2:16:10<20:58:37, 1.32s/it] 7%|▋ | 4495/61904 [2:16:11<20:42:59, 1.30s/it] 7%|▋ | 4496/61904 [2:16:12<21:02:42, 1.32s/it] 7%|▋ | 4497/61904 [2:16:14<21:13:38, 1.33s/it] 7%|▋ | 4498/61904 [2:16:15<22:18:21, 1.40s/it] 7%|▋ | 4499/61904 [2:16:17<21:53:25, 1.37s/it] 7%|▋ | 4500/61904 [2:16:18<22:28:44, 1.41s/it] {'loss': 3.0176, 'learning_rate': 1.930312459483988e-07, 'epoch': 1.16} + 7%|▋ | 4500/61904 [2:16:18<22:28:44, 1.41s/it] 7%|▋ | 4501/61904 [2:16:19<22:34:53, 1.42s/it] 7%|▋ | 4502/61904 [2:16:21<22:20:21, 1.40s/it] 7%|▋ | 4503/61904 [2:16:22<22:37:50, 1.42s/it] 7%|▋ | 4504/61904 [2:16:24<22:25:50, 1.41s/it] 7%|▋ | 4505/61904 [2:16:25<22:01:01, 1.38s/it] 7%|▋ | 4506/61904 [2:16:27<22:47:46, 1.43s/it] 7%|▋ | 4507/61904 [2:16:28<22:30:14, 1.41s/it] 7%|▋ | 4508/61904 [2:16:29<21:58:34, 1.38s/it] 7%|▋ | 4509/61904 [2:16:31<21:47:02, 1.37s/it] 7%|▋ | 4510/61904 [2:16:32<21:47:14, 1.37s/it] 7%|▋ | 4511/61904 [2:16:33<21:49:55, 1.37s/it] 7%|▋ | 4512/61904 [2:16:35<22:07:38, 1.39s/it] 7%|▋ | 4513/61904 [2:16:36<21:41:32, 1.36s/it] 7%|▋ | 4514/61904 [2:16:37<21:15:17, 1.33s/it] 7%|▋ | 4515/61904 [2:16:39<21:29:30, 1.35s/it] 7%|▋ | 4516/61904 [2:16:40<21:35:31, 1.35s/it] 7%|▋ | 4517/61904 [2:16:41<21:31:14, 1.35s/it] 7%|▋ | 4518/61904 [2:16:43<21:43:46, 1.36s/it] 7%|▋ | 4519/61904 [2:16:44<21:39:19, 1.36s/it] 7%|▋ | 4520/61904 [2:16:45<21:33:02, 1.35s/it] {'loss': 2.9897, 'learning_rate': 1.9299883313885646e-07, 'epoch': 1.17} + 7%|▋ | 4520/61904 [2:16:45<21:33:02, 1.35s/it] 7%|▋ | 4521/61904 [2:16:47<21:25:23, 1.34s/it] 7%|▋ | 4522/61904 [2:16:48<21:18:08, 1.34s/it] 7%|▋ | 4523/61904 [2:16:50<22:12:54, 1.39s/it] 7%|▋ | 4524/61904 [2:16:51<21:44:37, 1.36s/it] 7%|▋ | 4525/61904 [2:16:52<21:44:16, 1.36s/it] 7%|▋ | 4526/61904 [2:16:54<21:20:38, 1.34s/it] 7%|▋ | 4527/61904 [2:16:55<21:53:23, 1.37s/it] 7%|▋ | 4528/61904 [2:16:56<22:17:59, 1.40s/it] 7%|▋ | 4529/61904 [2:16:58<22:15:33, 1.40s/it] 7%|▋ | 4530/61904 [2:16:59<21:51:47, 1.37s/it] 7%|▋ | 4531/61904 [2:17:01<22:03:52, 1.38s/it] 7%|▋ | 4532/61904 [2:17:02<21:27:44, 1.35s/it] 7%|▋ | 4533/61904 [2:17:03<22:03:23, 1.38s/it] 7%|▋ | 4534/61904 [2:17:05<21:57:36, 1.38s/it] 7%|▋ | 4535/61904 [2:17:06<21:37:36, 1.36s/it] 7%|▋ | 4536/61904 [2:17:07<21:35:45, 1.36s/it] 7%|▋ | 4537/61904 [2:17:09<21:35:54, 1.36s/it] 7%|▋ | 4538/61904 [2:17:10<21:25:01, 1.34s/it] 7%|▋ | 4539/61904 [2:17:12<23:06:47, 1.45s/it] 7%|▋ | 4540/61904 [2:17:13<23:17:04, 1.46s/it] {'loss': 3.0404, 'learning_rate': 1.9296642032931413e-07, 'epoch': 1.17} + 7%|▋ | 4540/61904 [2:17:13<23:17:04, 1.46s/it] 7%|▋ | 4541/61904 [2:17:15<23:02:02, 1.45s/it] 7%|▋ | 4542/61904 [2:17:16<22:07:39, 1.39s/it] 7%|▋ | 4543/61904 [2:17:17<23:00:07, 1.44s/it] 7%|▋ | 4544/61904 [2:17:19<22:06:45, 1.39s/it] 7%|▋ | 4545/61904 [2:17:20<22:53:21, 1.44s/it] 7%|▋ | 4546/61904 [2:17:22<22:59:12, 1.44s/it] 7%|▋ | 4547/61904 [2:17:23<22:42:44, 1.43s/it] 7%|▋ | 4548/61904 [2:17:24<21:55:47, 1.38s/it] 7%|▋ | 4549/61904 [2:17:26<22:00:26, 1.38s/it] 7%|▋ | 4550/61904 [2:17:27<22:23:50, 1.41s/it] 7%|▋ | 4551/61904 [2:17:29<22:06:58, 1.39s/it] 7%|▋ | 4552/61904 [2:17:30<22:00:03, 1.38s/it] 7%|▋ | 4553/61904 [2:17:31<21:24:46, 1.34s/it] 7%|▋ | 4554/61904 [2:17:33<21:38:10, 1.36s/it] 7%|▋ | 4555/61904 [2:17:34<21:17:13, 1.34s/it] 7%|▋ | 4556/61904 [2:17:35<21:13:20, 1.33s/it] 7%|▋ | 4557/61904 [2:17:37<21:26:11, 1.35s/it] 7%|▋ | 4558/61904 [2:17:38<20:49:07, 1.31s/it] 7%|▋ | 4559/61904 [2:17:39<21:36:35, 1.36s/it] 7%|▋ | 4560/61904 [2:17:41<22:27:16, 1.41s/it] {'loss': 2.9724, 'learning_rate': 1.9293400751977181e-07, 'epoch': 1.18} + 7%|▋ | 4560/61904 [2:17:41<22:27:16, 1.41s/it] 7%|▋ | 4561/61904 [2:17:42<21:51:20, 1.37s/it] 7%|▋ | 4562/61904 [2:17:44<22:16:32, 1.40s/it] 7%|▋ | 4563/61904 [2:17:45<22:49:36, 1.43s/it] 7%|▋ | 4564/61904 [2:17:46<22:33:27, 1.42s/it] 7%|▋ | 4565/61904 [2:17:48<21:45:44, 1.37s/it] 7%|▋ | 4566/61904 [2:17:49<22:11:50, 1.39s/it] 7%|▋ | 4567/61904 [2:17:51<22:09:44, 1.39s/it] 7%|▋ | 4568/61904 [2:17:52<21:44:47, 1.37s/it] 7%|▋ | 4569/61904 [2:17:53<21:40:02, 1.36s/it] 7%|▋ | 4570/61904 [2:17:54<21:28:46, 1.35s/it] 7%|▋ | 4571/61904 [2:17:56<21:46:35, 1.37s/it] 7%|▋ | 4572/61904 [2:17:57<22:01:35, 1.38s/it] 7%|▋ | 4573/61904 [2:17:59<22:05:00, 1.39s/it] 7%|▋ | 4574/61904 [2:18:00<21:24:23, 1.34s/it] 7%|▋ | 4575/61904 [2:18:01<21:10:12, 1.33s/it] 7%|▋ | 4576/61904 [2:18:03<22:15:51, 1.40s/it] 7%|▋ | 4577/61904 [2:18:04<22:36:08, 1.42s/it] 7%|▋ | 4578/61904 [2:18:06<21:59:05, 1.38s/it] 7%|▋ | 4579/61904 [2:18:07<22:03:43, 1.39s/it] 7%|▋ | 4580/61904 [2:18:08<21:55:41, 1.38s/it] {'loss': 3.019, 'learning_rate': 1.9290159471022948e-07, 'epoch': 1.18} + 7%|▋ | 4580/61904 [2:18:08<21:55:41, 1.38s/it] 7%|▋ | 4581/61904 [2:18:10<21:24:16, 1.34s/it] 7%|▋ | 4582/61904 [2:18:11<21:36:31, 1.36s/it] 7%|▋ | 4583/61904 [2:18:12<21:48:19, 1.37s/it] 7%|▋ | 4584/61904 [2:18:14<21:43:50, 1.36s/it] 7%|▋ | 4585/61904 [2:18:15<21:35:41, 1.36s/it] 7%|▋ | 4586/61904 [2:18:16<21:37:25, 1.36s/it] 7%|▋ | 4587/61904 [2:18:18<21:18:30, 1.34s/it] 7%|▋ | 4588/61904 [2:18:19<20:56:15, 1.32s/it] 7%|▋ | 4589/61904 [2:18:20<21:01:17, 1.32s/it] 7%|▋ | 4590/61904 [2:18:22<20:38:33, 1.30s/it] 7%|▋ | 4591/61904 [2:18:23<21:12:26, 1.33s/it] 7%|▋ | 4592/61904 [2:18:24<21:50:06, 1.37s/it] 7%|▋ | 4593/61904 [2:18:26<21:58:07, 1.38s/it] 7%|▋ | 4594/61904 [2:18:27<21:27:49, 1.35s/it] 7%|▋ | 4595/61904 [2:18:28<21:30:36, 1.35s/it] 7%|▋ | 4596/61904 [2:18:30<21:49:14, 1.37s/it] 7%|▋ | 4597/61904 [2:18:31<22:25:39, 1.41s/it] 7%|▋ | 4598/61904 [2:18:33<21:46:08, 1.37s/it] 7%|▋ | 4599/61904 [2:18:34<22:03:22, 1.39s/it] 7%|▋ | 4600/61904 [2:18:35<21:56:58, 1.38s/it] {'loss': 2.9637, 'learning_rate': 1.9286918190068714e-07, 'epoch': 1.19} + 7%|▋ | 4600/61904 [2:18:35<21:56:58, 1.38s/it] 7%|▋ | 4601/61904 [2:18:37<22:21:37, 1.40s/it] 7%|▋ | 4602/61904 [2:18:38<22:15:30, 1.40s/it] 7%|▋ | 4603/61904 [2:18:40<21:52:38, 1.37s/it] 7%|▋ | 4604/61904 [2:18:41<21:44:57, 1.37s/it] 7%|▋ | 4605/61904 [2:18:42<21:12:49, 1.33s/it] 7%|▋ | 4606/61904 [2:18:43<20:39:02, 1.30s/it] 7%|▋ | 4607/61904 [2:18:45<20:59:22, 1.32s/it] 7%|▋ | 4608/61904 [2:18:46<21:50:36, 1.37s/it] 7%|▋ | 4609/61904 [2:18:48<21:58:31, 1.38s/it] 7%|▋ | 4610/61904 [2:18:49<22:05:17, 1.39s/it] 7%|▋ | 4611/61904 [2:18:50<21:51:56, 1.37s/it] 7%|▋ | 4612/61904 [2:18:52<22:19:43, 1.40s/it] 7%|▋ | 4613/61904 [2:18:53<21:35:44, 1.36s/it] 7%|▋ | 4614/61904 [2:18:54<21:21:37, 1.34s/it] 7%|▋ | 4615/61904 [2:18:56<21:09:42, 1.33s/it] 7%|▋ | 4616/61904 [2:18:57<21:03:11, 1.32s/it] 7%|▋ | 4617/61904 [2:18:59<21:52:39, 1.37s/it] 7%|▋ | 4618/61904 [2:19:00<22:52:14, 1.44s/it] 7%|▋ | 4619/61904 [2:19:01<22:09:36, 1.39s/it] 7%|▋ | 4620/61904 [2:19:03<21:46:16, 1.37s/it] {'loss': 3.0281, 'learning_rate': 1.9283676909114483e-07, 'epoch': 1.19} + 7%|▋ | 4620/61904 [2:19:03<21:46:16, 1.37s/it] 7%|▋ | 4621/61904 [2:19:04<21:54:22, 1.38s/it] 7%|▋ | 4622/61904 [2:19:05<21:21:44, 1.34s/it] 7%|▋ | 4623/61904 [2:19:07<21:29:59, 1.35s/it] 7%|▋ | 4624/61904 [2:19:08<20:45:18, 1.30s/it] 7%|▋ | 4625/61904 [2:19:09<20:46:42, 1.31s/it] 7%|▋ | 4626/61904 [2:19:11<21:12:32, 1.33s/it] 7%|▋ | 4627/61904 [2:19:12<22:15:30, 1.40s/it] 7%|▋ | 4628/61904 [2:19:14<22:13:58, 1.40s/it] 7%|▋ | 4629/61904 [2:19:15<21:32:19, 1.35s/it] 7%|▋ | 4630/61904 [2:19:16<21:33:47, 1.36s/it] 7%|▋ | 4631/61904 [2:19:18<21:10:21, 1.33s/it] 7%|▋ | 4632/61904 [2:19:19<21:26:26, 1.35s/it] 7%|▋ | 4633/61904 [2:19:20<21:51:33, 1.37s/it] 7%|▋ | 4634/61904 [2:19:22<22:21:41, 1.41s/it] 7%|▋ | 4635/61904 [2:19:23<22:23:01, 1.41s/it] 7%|▋ | 4636/61904 [2:19:25<22:01:17, 1.38s/it] 7%|▋ | 4637/61904 [2:19:26<22:21:48, 1.41s/it] 7%|▋ | 4638/61904 [2:19:27<22:14:47, 1.40s/it] 7%|▋ | 4639/61904 [2:19:29<21:37:20, 1.36s/it] 7%|▋ | 4640/61904 [2:19:30<21:17:27, 1.34s/it] {'loss': 2.9964, 'learning_rate': 1.9280435628160246e-07, 'epoch': 1.2} + 7%|▋ | 4640/61904 [2:19:30<21:17:27, 1.34s/it] 7%|▋ | 4641/61904 [2:19:31<22:11:01, 1.39s/it] 7%|▋ | 4642/61904 [2:19:33<22:28:01, 1.41s/it] 8%|▊ | 4643/61904 [2:19:34<22:14:21, 1.40s/it] 8%|▊ | 4644/61904 [2:19:36<21:35:39, 1.36s/it] 8%|▊ | 4645/61904 [2:19:37<21:09:47, 1.33s/it] 8%|▊ | 4646/61904 [2:19:38<21:11:20, 1.33s/it] 8%|▊ | 4647/61904 [2:19:39<20:55:46, 1.32s/it] 8%|▊ | 4648/61904 [2:19:41<21:39:46, 1.36s/it] 8%|▊ | 4649/61904 [2:19:42<21:39:01, 1.36s/it] 8%|▊ | 4650/61904 [2:19:44<21:27:03, 1.35s/it] 8%|▊ | 4651/61904 [2:19:45<21:43:27, 1.37s/it] 8%|▊ | 4652/61904 [2:19:46<21:29:08, 1.35s/it] 8%|▊ | 4653/61904 [2:19:48<21:29:29, 1.35s/it] 8%|▊ | 4654/61904 [2:19:49<22:12:54, 1.40s/it] 8%|▊ | 4655/61904 [2:19:51<22:06:05, 1.39s/it] 8%|▊ | 4656/61904 [2:19:52<21:16:25, 1.34s/it] 8%|▊ | 4657/61904 [2:19:53<21:41:26, 1.36s/it] 8%|▊ | 4658/61904 [2:19:54<20:53:01, 1.31s/it] 8%|▊ | 4659/61904 [2:19:56<20:26:35, 1.29s/it] 8%|▊ | 4660/61904 [2:19:57<21:16:15, 1.34s/it] {'loss': 3.0762, 'learning_rate': 1.9277194347206015e-07, 'epoch': 1.2} + 8%|▊ | 4660/61904 [2:19:57<21:16:15, 1.34s/it] 8%|▊ | 4661/61904 [2:19:58<21:42:33, 1.37s/it] 8%|▊ | 4662/61904 [2:20:00<22:04:44, 1.39s/it] 8%|▊ | 4663/61904 [2:20:01<21:27:42, 1.35s/it] 8%|▊ | 4664/61904 [2:20:03<21:15:59, 1.34s/it] 8%|▊ | 4665/61904 [2:20:04<21:05:09, 1.33s/it] 8%|▊ | 4666/61904 [2:20:05<21:40:34, 1.36s/it] 8%|▊ | 4667/61904 [2:20:07<21:47:04, 1.37s/it] 8%|▊ | 4668/61904 [2:20:08<21:45:05, 1.37s/it] 8%|▊ | 4669/61904 [2:20:09<21:15:51, 1.34s/it] 8%|▊ | 4670/61904 [2:20:11<21:12:07, 1.33s/it] 8%|▊ | 4671/61904 [2:20:12<21:27:17, 1.35s/it] 8%|▊ | 4672/61904 [2:20:13<21:28:36, 1.35s/it] 8%|▊ | 4673/61904 [2:20:15<21:44:44, 1.37s/it] 8%|▊ | 4674/61904 [2:20:16<21:54:31, 1.38s/it] 8%|▊ | 4675/61904 [2:20:18<22:29:30, 1.41s/it] 8%|▊ | 4676/61904 [2:20:19<21:56:26, 1.38s/it] 8%|▊ | 4677/61904 [2:20:20<21:53:22, 1.38s/it] 8%|▊ | 4678/61904 [2:20:22<21:27:00, 1.35s/it] 8%|▊ | 4679/61904 [2:20:23<21:42:12, 1.37s/it] 8%|▊ | 4680/61904 [2:20:24<21:42:22, 1.37s/it] {'loss': 3.035, 'learning_rate': 1.9273953066251784e-07, 'epoch': 1.21} + 8%|▊ | 4680/61904 [2:20:24<21:42:22, 1.37s/it] 8%|▊ | 4681/61904 [2:20:26<21:23:17, 1.35s/it] 8%|▊ | 4682/61904 [2:20:27<21:15:06, 1.34s/it] 8%|▊ | 4683/61904 [2:20:28<21:47:51, 1.37s/it] 8%|▊ | 4684/61904 [2:20:30<21:35:41, 1.36s/it] 8%|▊ | 4685/61904 [2:20:31<21:05:02, 1.33s/it] 8%|▊ | 4686/61904 [2:20:32<20:54:27, 1.32s/it] 8%|▊ | 4687/61904 [2:20:34<21:35:58, 1.36s/it] 8%|▊ | 4688/61904 [2:20:35<21:44:32, 1.37s/it] 8%|▊ | 4689/61904 [2:20:36<21:29:11, 1.35s/it] 8%|▊ | 4690/61904 [2:20:38<21:25:36, 1.35s/it] 8%|▊ | 4691/61904 [2:20:39<21:11:22, 1.33s/it] 8%|▊ | 4692/61904 [2:20:41<22:11:02, 1.40s/it] 8%|▊ | 4693/61904 [2:20:42<21:39:49, 1.36s/it] 8%|▊ | 4694/61904 [2:20:43<21:29:14, 1.35s/it] 8%|▊ | 4695/61904 [2:20:45<21:19:35, 1.34s/it] 8%|▊ | 4696/61904 [2:20:46<21:24:04, 1.35s/it] 8%|▊ | 4697/61904 [2:20:47<21:14:19, 1.34s/it] 8%|▊ | 4698/61904 [2:20:49<21:46:15, 1.37s/it] 8%|▊ | 4699/61904 [2:20:50<20:50:12, 1.31s/it] 8%|▊ | 4700/61904 [2:20:51<21:44:16, 1.37s/it] {'loss': 2.9578, 'learning_rate': 1.9270711785297547e-07, 'epoch': 1.21} + 8%|▊ | 4700/61904 [2:20:51<21:44:16, 1.37s/it] 8%|▊ | 4701/61904 [2:20:53<22:23:48, 1.41s/it] 8%|▊ | 4702/61904 [2:20:54<22:18:15, 1.40s/it] 8%|▊ | 4703/61904 [2:20:56<22:05:46, 1.39s/it] 8%|▊ | 4704/61904 [2:20:57<21:25:45, 1.35s/it] 8%|▊ | 4705/61904 [2:20:58<21:30:53, 1.35s/it] 8%|▊ | 4706/61904 [2:21:00<21:42:50, 1.37s/it] 8%|▊ | 4707/61904 [2:21:01<22:37:51, 1.42s/it] 8%|▊ | 4708/61904 [2:21:03<22:40:35, 1.43s/it] 8%|▊ | 4709/61904 [2:21:04<21:54:08, 1.38s/it] 8%|▊ | 4710/61904 [2:21:05<21:37:11, 1.36s/it] 8%|▊ | 4711/61904 [2:21:07<21:24:57, 1.35s/it] 8%|▊ | 4712/61904 [2:21:08<21:25:45, 1.35s/it] 8%|▊ | 4713/61904 [2:21:09<21:49:33, 1.37s/it] 8%|▊ | 4714/61904 [2:21:11<21:04:39, 1.33s/it] 8%|▊ | 4715/61904 [2:21:12<20:51:39, 1.31s/it] 8%|▊ | 4716/61904 [2:21:13<20:43:54, 1.31s/it] 8%|▊ | 4717/61904 [2:21:14<20:22:51, 1.28s/it] 8%|▊ | 4718/61904 [2:21:16<21:37:13, 1.36s/it] 8%|▊ | 4719/61904 [2:21:17<22:01:22, 1.39s/it] 8%|▊ | 4720/61904 [2:21:19<21:37:49, 1.36s/it] {'loss': 2.9568, 'learning_rate': 1.9267470504343316e-07, 'epoch': 1.22} + 8%|▊ | 4720/61904 [2:21:19<21:37:49, 1.36s/it] 8%|▊ | 4721/61904 [2:21:20<22:01:31, 1.39s/it] 8%|▊ | 4722/61904 [2:21:21<22:05:30, 1.39s/it] 8%|▊ | 4723/61904 [2:21:23<21:53:40, 1.38s/it] 8%|▊ | 4724/61904 [2:21:24<21:50:26, 1.38s/it] 8%|▊ | 4725/61904 [2:21:26<22:07:15, 1.39s/it] 8%|▊ | 4726/61904 [2:21:27<21:28:45, 1.35s/it] 8%|▊ | 4727/61904 [2:21:28<21:14:30, 1.34s/it] 8%|▊ | 4728/61904 [2:21:30<21:33:21, 1.36s/it] 8%|▊ | 4729/61904 [2:21:31<21:28:31, 1.35s/it] 8%|▊ | 4730/61904 [2:21:32<21:36:15, 1.36s/it] 8%|▊ | 4731/61904 [2:21:34<21:12:02, 1.33s/it] 8%|▊ | 4732/61904 [2:21:35<21:01:41, 1.32s/it] 8%|▊ | 4733/61904 [2:21:36<22:11:27, 1.40s/it] 8%|▊ | 4734/61904 [2:21:38<22:00:21, 1.39s/it] 8%|▊ | 4735/61904 [2:21:39<21:58:17, 1.38s/it] 8%|▊ | 4736/61904 [2:21:41<22:27:02, 1.41s/it] 8%|▊ | 4737/61904 [2:21:42<22:07:53, 1.39s/it] 8%|▊ | 4738/61904 [2:21:43<21:54:42, 1.38s/it] 8%|▊ | 4739/61904 [2:21:45<22:06:37, 1.39s/it] 8%|▊ | 4740/61904 [2:21:46<22:01:29, 1.39s/it] {'loss': 3.0495, 'learning_rate': 1.9264229223389082e-07, 'epoch': 1.22} + 8%|▊ | 4740/61904 [2:21:46<22:01:29, 1.39s/it] 8%|▊ | 4741/61904 [2:21:47<21:17:59, 1.34s/it] 8%|▊ | 4742/61904 [2:21:49<21:37:46, 1.36s/it] 8%|▊ | 4743/61904 [2:21:50<21:18:51, 1.34s/it] 8%|▊ | 4744/61904 [2:21:52<21:37:13, 1.36s/it] 8%|▊ | 4745/61904 [2:21:53<21:51:15, 1.38s/it] 8%|▊ | 4746/61904 [2:21:54<22:11:41, 1.40s/it] 8%|▊ | 4747/61904 [2:21:56<22:29:16, 1.42s/it] 8%|▊ | 4748/61904 [2:21:57<22:32:02, 1.42s/it] 8%|▊ | 4749/61904 [2:21:59<21:47:03, 1.37s/it] 8%|▊ | 4750/61904 [2:22:00<21:00:05, 1.32s/it] 8%|▊ | 4751/61904 [2:22:01<20:59:59, 1.32s/it] 8%|▊ | 4752/61904 [2:22:02<21:14:49, 1.34s/it] 8%|▊ | 4753/61904 [2:22:04<21:30:12, 1.35s/it] 8%|▊ | 4754/61904 [2:22:05<22:06:06, 1.39s/it] 8%|▊ | 4755/61904 [2:22:07<21:18:02, 1.34s/it] 8%|▊ | 4756/61904 [2:22:08<21:09:40, 1.33s/it] 8%|▊ | 4757/61904 [2:22:09<21:31:56, 1.36s/it] 8%|▊ | 4758/61904 [2:22:11<22:02:04, 1.39s/it] 8%|▊ | 4759/61904 [2:22:12<22:07:00, 1.39s/it] 8%|▊ | 4760/61904 [2:22:13<21:35:31, 1.36s/it] {'loss': 3.0054, 'learning_rate': 1.9260987942434848e-07, 'epoch': 1.23} + 8%|▊ | 4760/61904 [2:22:13<21:35:31, 1.36s/it] 8%|▊ | 4761/61904 [2:22:15<21:31:53, 1.36s/it] 8%|▊ | 4762/61904 [2:22:16<21:29:31, 1.35s/it] 8%|▊ | 4763/61904 [2:22:17<21:43:27, 1.37s/it] 8%|▊ | 4764/61904 [2:22:19<22:45:37, 1.43s/it] 8%|▊ | 4765/61904 [2:22:20<22:20:41, 1.41s/it] 8%|▊ | 4766/61904 [2:22:22<21:57:45, 1.38s/it] 8%|▊ | 4767/61904 [2:22:23<21:56:58, 1.38s/it] 8%|▊ | 4768/61904 [2:22:25<21:59:53, 1.39s/it] 8%|▊ | 4769/61904 [2:22:26<22:14:39, 1.40s/it] 8%|▊ | 4770/61904 [2:22:27<22:29:35, 1.42s/it] 8%|▊ | 4771/61904 [2:22:29<21:49:51, 1.38s/it] 8%|▊ | 4772/61904 [2:22:30<21:12:53, 1.34s/it] 8%|▊ | 4773/61904 [2:22:31<21:25:23, 1.35s/it] 8%|▊ | 4774/61904 [2:22:33<21:07:49, 1.33s/it] 8%|▊ | 4775/61904 [2:22:34<21:46:59, 1.37s/it] 8%|▊ | 4776/61904 [2:22:35<21:20:53, 1.35s/it] 8%|▊ | 4777/61904 [2:22:37<21:31:39, 1.36s/it] 8%|▊ | 4778/61904 [2:22:38<21:15:08, 1.34s/it] 8%|▊ | 4779/61904 [2:22:39<21:20:34, 1.35s/it] 8%|▊ | 4780/61904 [2:22:41<21:36:58, 1.36s/it] {'loss': 3.0101, 'learning_rate': 1.9257746661480617e-07, 'epoch': 1.24} + 8%|▊ | 4780/61904 [2:22:41<21:36:58, 1.36s/it] 8%|▊ | 4781/61904 [2:22:42<21:40:10, 1.37s/it] 8%|▊ | 4782/61904 [2:22:44<21:32:28, 1.36s/it] 8%|▊ | 4783/61904 [2:22:45<21:28:58, 1.35s/it] 8%|▊ | 4784/61904 [2:22:46<21:48:14, 1.37s/it] 8%|▊ | 4785/61904 [2:22:48<22:02:46, 1.39s/it] 8%|▊ | 4786/61904 [2:22:49<21:34:52, 1.36s/it] 8%|▊ | 4787/61904 [2:22:50<21:37:26, 1.36s/it] 8%|▊ | 4788/61904 [2:22:52<21:26:03, 1.35s/it] 8%|▊ | 4789/61904 [2:22:53<21:30:58, 1.36s/it] 8%|▊ | 4790/61904 [2:22:54<21:17:07, 1.34s/it] 8%|▊ | 4791/61904 [2:22:56<20:59:54, 1.32s/it] 8%|▊ | 4792/61904 [2:22:57<22:05:53, 1.39s/it] 8%|▊ | 4793/61904 [2:22:59<22:02:24, 1.39s/it] 8%|▊ | 4794/61904 [2:23:00<22:00:23, 1.39s/it] 8%|▊ | 4795/61904 [2:23:01<22:06:26, 1.39s/it] 8%|▊ | 4796/61904 [2:23:03<22:05:01, 1.39s/it] 8%|▊ | 4797/61904 [2:23:04<21:40:23, 1.37s/it] 8%|▊ | 4798/61904 [2:23:05<21:24:10, 1.35s/it] 8%|▊ | 4799/61904 [2:23:07<22:17:01, 1.40s/it] 8%|▊ | 4800/61904 [2:23:08<22:54:21, 1.44s/it] {'loss': 2.9621, 'learning_rate': 1.9254505380526384e-07, 'epoch': 1.24} + 8%|▊ | 4800/61904 [2:23:08<22:54:21, 1.44s/it] 8%|▊ | 4801/61904 [2:23:10<22:02:01, 1.39s/it] 8%|▊ | 4802/61904 [2:23:11<21:11:24, 1.34s/it] 8%|▊ | 4803/61904 [2:23:12<20:51:17, 1.31s/it] 8%|▊ | 4804/61904 [2:23:13<20:11:26, 1.27s/it] 8%|▊ | 4805/61904 [2:23:15<21:00:56, 1.32s/it] 8%|▊ | 4806/61904 [2:23:16<21:10:07, 1.33s/it] 8%|▊ | 4807/61904 [2:23:17<21:03:23, 1.33s/it] 8%|▊ | 4808/61904 [2:23:19<20:40:15, 1.30s/it] 8%|▊ | 4809/61904 [2:23:20<21:04:34, 1.33s/it] 8%|▊ | 4810/61904 [2:23:21<20:47:07, 1.31s/it] 8%|▊ | 4811/61904 [2:23:23<20:32:08, 1.29s/it] 8%|▊ | 4812/61904 [2:23:24<22:01:01, 1.39s/it] 8%|▊ | 4813/61904 [2:23:26<22:45:26, 1.44s/it] 8%|▊ | 4814/61904 [2:23:27<22:01:21, 1.39s/it] 8%|▊ | 4815/61904 [2:23:28<21:13:55, 1.34s/it] 8%|▊ | 4816/61904 [2:23:30<21:25:13, 1.35s/it] 8%|▊ | 4817/61904 [2:23:31<21:04:12, 1.33s/it] 8%|▊ | 4818/61904 [2:23:32<21:20:18, 1.35s/it] 8%|▊ | 4819/61904 [2:23:34<22:11:33, 1.40s/it] 8%|▊ | 4820/61904 [2:23:35<22:18:50, 1.41s/it] {'loss': 3.0161, 'learning_rate': 1.925126409957215e-07, 'epoch': 1.25} + 8%|▊ | 4820/61904 [2:23:35<22:18:50, 1.41s/it] 8%|▊ | 4821/61904 [2:23:37<22:06:47, 1.39s/it] 8%|▊ | 4822/61904 [2:23:38<22:06:39, 1.39s/it] 8%|▊ | 4823/61904 [2:23:40<23:18:43, 1.47s/it] 8%|▊ | 4824/61904 [2:23:41<23:42:21, 1.50s/it] 8%|▊ | 4825/61904 [2:23:43<22:58:50, 1.45s/it] 8%|▊ | 4826/61904 [2:23:44<22:38:02, 1.43s/it] 8%|▊ | 4827/61904 [2:23:45<22:14:50, 1.40s/it] 8%|▊ | 4828/61904 [2:23:47<21:53:18, 1.38s/it] 8%|▊ | 4829/61904 [2:23:48<22:23:43, 1.41s/it] 8%|▊ | 4830/61904 [2:23:50<22:39:28, 1.43s/it] 8%|▊ | 4831/61904 [2:23:51<21:34:54, 1.36s/it] 8%|▊ | 4832/61904 [2:23:52<21:29:25, 1.36s/it] 8%|▊ | 4833/61904 [2:23:53<21:26:58, 1.35s/it] 8%|▊ | 4834/61904 [2:23:55<21:36:42, 1.36s/it] 8%|▊ | 4835/61904 [2:23:56<22:05:27, 1.39s/it] 8%|▊ | 4836/61904 [2:23:58<21:26:56, 1.35s/it] 8%|▊ | 4837/61904 [2:23:59<21:16:14, 1.34s/it] 8%|▊ | 4838/61904 [2:24:01<22:29:34, 1.42s/it] 8%|▊ | 4839/61904 [2:24:02<22:28:40, 1.42s/it] 8%|▊ | 4840/61904 [2:24:03<22:26:06, 1.42s/it] {'loss': 2.9672, 'learning_rate': 1.9248022818617919e-07, 'epoch': 1.25} + 8%|▊ | 4840/61904 [2:24:03<22:26:06, 1.42s/it] 8%|▊ | 4841/61904 [2:24:05<21:35:47, 1.36s/it] 8%|▊ | 4842/61904 [2:24:06<21:34:30, 1.36s/it] 8%|▊ | 4843/61904 [2:24:07<21:14:24, 1.34s/it] 8%|▊ | 4844/61904 [2:24:09<21:52:01, 1.38s/it] 8%|▊ | 4845/61904 [2:24:10<22:16:10, 1.41s/it] 8%|▊ | 4846/61904 [2:24:11<21:30:57, 1.36s/it] 8%|▊ | 4847/61904 [2:24:13<21:52:15, 1.38s/it] 8%|▊ | 4848/61904 [2:24:14<21:18:06, 1.34s/it] 8%|▊ | 4849/61904 [2:24:15<21:14:32, 1.34s/it] 8%|▊ | 4850/61904 [2:24:17<21:44:58, 1.37s/it] 8%|▊ | 4851/61904 [2:24:18<22:21:10, 1.41s/it] 8%|▊ | 4852/61904 [2:24:20<21:12:36, 1.34s/it] 8%|▊ | 4853/61904 [2:24:21<21:03:06, 1.33s/it] 8%|▊ | 4854/61904 [2:24:22<22:15:39, 1.40s/it] 8%|▊ | 4855/61904 [2:24:24<22:43:41, 1.43s/it] 8%|▊ | 4856/61904 [2:24:25<21:57:33, 1.39s/it] 8%|▊ | 4857/61904 [2:24:26<21:20:59, 1.35s/it] 8%|▊ | 4858/61904 [2:24:28<20:56:14, 1.32s/it] 8%|▊ | 4859/61904 [2:24:29<21:18:10, 1.34s/it] 8%|▊ | 4860/61904 [2:24:31<21:25:45, 1.35s/it] {'loss': 2.9749, 'learning_rate': 1.9244781537663682e-07, 'epoch': 1.26} + 8%|▊ | 4860/61904 [2:24:31<21:25:45, 1.35s/it] 8%|▊ | 4861/61904 [2:24:32<21:03:30, 1.33s/it] 8%|▊ | 4862/61904 [2:24:33<20:47:43, 1.31s/it] 8%|▊ | 4863/61904 [2:24:34<20:34:48, 1.30s/it] 8%|▊ | 4864/61904 [2:24:36<20:37:18, 1.30s/it] 8%|▊ | 4865/61904 [2:24:37<21:10:36, 1.34s/it] 8%|▊ | 4866/61904 [2:24:39<22:00:43, 1.39s/it] 8%|▊ | 4867/61904 [2:24:40<23:15:19, 1.47s/it] 8%|▊ | 4868/61904 [2:24:41<22:09:32, 1.40s/it] 8%|▊ | 4869/61904 [2:24:43<22:07:03, 1.40s/it] 8%|▊ | 4870/61904 [2:24:44<22:03:47, 1.39s/it] 8%|▊ | 4871/61904 [2:24:46<22:03:07, 1.39s/it] 8%|▊ | 4872/61904 [2:24:47<21:55:08, 1.38s/it] 8%|▊ | 4873/61904 [2:24:48<21:54:33, 1.38s/it] 8%|▊ | 4874/61904 [2:24:50<21:47:11, 1.38s/it] 8%|▊ | 4875/61904 [2:24:51<21:03:28, 1.33s/it] 8%|▊ | 4876/61904 [2:24:52<21:15:13, 1.34s/it] 8%|▊ | 4877/61904 [2:24:54<21:17:17, 1.34s/it] 8%|▊ | 4878/61904 [2:24:55<21:18:52, 1.35s/it] 8%|▊ | 4879/61904 [2:24:57<22:03:15, 1.39s/it] 8%|▊ | 4880/61904 [2:24:58<21:38:20, 1.37s/it] {'loss': 2.9898, 'learning_rate': 1.924154025670945e-07, 'epoch': 1.26} + 8%|▊ | 4880/61904 [2:24:58<21:38:20, 1.37s/it] 8%|▊ | 4881/61904 [2:24:59<21:21:07, 1.35s/it] 8%|▊ | 4882/61904 [2:25:01<21:38:28, 1.37s/it] 8%|▊ | 4883/61904 [2:25:02<21:43:09, 1.37s/it] 8%|▊ | 4884/61904 [2:25:03<22:04:15, 1.39s/it] 8%|▊ | 4885/61904 [2:25:05<21:21:46, 1.35s/it] 8%|▊ | 4886/61904 [2:25:06<22:22:03, 1.41s/it] 8%|▊ | 4887/61904 [2:25:07<21:33:15, 1.36s/it] 8%|▊ | 4888/61904 [2:25:09<21:04:57, 1.33s/it] 8%|▊ | 4889/61904 [2:25:10<21:01:45, 1.33s/it] 8%|▊ | 4890/61904 [2:25:11<21:01:02, 1.33s/it] 8%|▊ | 4891/61904 [2:25:13<21:14:20, 1.34s/it] 8%|▊ | 4892/61904 [2:25:14<21:16:55, 1.34s/it] 8%|▊ | 4893/61904 [2:25:15<20:59:44, 1.33s/it] 8%|▊ | 4894/61904 [2:25:17<21:01:56, 1.33s/it] 8%|▊ | 4895/61904 [2:25:18<21:44:01, 1.37s/it] 8%|▊ | 4896/61904 [2:25:19<21:30:25, 1.36s/it] 8%|▊ | 4897/61904 [2:25:21<21:33:00, 1.36s/it] 8%|▊ | 4898/61904 [2:25:22<21:17:28, 1.34s/it] 8%|▊ | 4899/61904 [2:25:24<21:46:41, 1.38s/it] 8%|▊ | 4900/61904 [2:25:25<21:13:02, 1.34s/it] {'loss': 2.9917, 'learning_rate': 1.9238298975755217e-07, 'epoch': 1.27} + 8%|▊ | 4900/61904 [2:25:25<21:13:02, 1.34s/it] 8%|▊ | 4901/61904 [2:25:26<21:21:17, 1.35s/it] 8%|▊ | 4902/61904 [2:25:28<21:16:05, 1.34s/it] 8%|▊ | 4903/61904 [2:25:29<20:46:16, 1.31s/it] 8%|▊ | 4904/61904 [2:25:30<21:14:25, 1.34s/it] 8%|▊ | 4905/61904 [2:25:31<20:22:45, 1.29s/it] 8%|▊ | 4906/61904 [2:25:33<20:39:19, 1.30s/it] 8%|▊ | 4907/61904 [2:25:34<20:04:38, 1.27s/it] 8%|▊ | 4908/61904 [2:25:35<21:14:35, 1.34s/it] 8%|▊ | 4909/61904 [2:25:37<21:37:31, 1.37s/it] 8%|▊ | 4910/61904 [2:25:38<21:41:50, 1.37s/it] 8%|▊ | 4911/61904 [2:25:39<20:37:35, 1.30s/it] 8%|▊ | 4912/61904 [2:25:41<21:09:38, 1.34s/it] 8%|▊ | 4913/61904 [2:25:42<21:52:04, 1.38s/it] 8%|▊ | 4914/61904 [2:25:44<21:58:25, 1.39s/it] 8%|▊ | 4915/61904 [2:25:45<21:34:04, 1.36s/it] 8%|▊ | 4916/61904 [2:25:46<21:33:40, 1.36s/it] 8%|▊ | 4917/61904 [2:25:48<21:02:58, 1.33s/it] 8%|▊ | 4918/61904 [2:25:49<21:22:22, 1.35s/it] 8%|▊ | 4919/61904 [2:25:50<21:40:43, 1.37s/it] 8%|▊ | 4920/61904 [2:25:52<21:47:58, 1.38s/it] {'loss': 2.9675, 'learning_rate': 1.9235057694800983e-07, 'epoch': 1.27} + 8%|▊ | 4920/61904 [2:25:52<21:47:58, 1.38s/it] 8%|▊ | 4921/61904 [2:25:53<22:29:38, 1.42s/it] 8%|▊ | 4922/61904 [2:25:55<22:23:03, 1.41s/it] 8%|▊ | 4923/61904 [2:25:56<21:46:19, 1.38s/it] 8%|▊ | 4924/61904 [2:25:57<21:55:00, 1.38s/it] 8%|▊ | 4925/61904 [2:25:59<21:47:43, 1.38s/it] 8%|▊ | 4926/61904 [2:26:00<21:55:51, 1.39s/it] 8%|▊ | 4927/61904 [2:26:01<21:19:49, 1.35s/it] 8%|▊ | 4928/61904 [2:26:03<21:50:35, 1.38s/it] 8%|▊ | 4929/61904 [2:26:04<21:46:58, 1.38s/it] 8%|▊ | 4930/61904 [2:26:06<22:49:23, 1.44s/it] 8%|▊ | 4931/61904 [2:26:07<22:27:24, 1.42s/it] 8%|▊ | 4932/61904 [2:26:08<21:50:34, 1.38s/it] 8%|▊ | 4933/61904 [2:26:10<21:04:26, 1.33s/it] 8%|▊ | 4934/61904 [2:26:11<20:50:19, 1.32s/it] 8%|▊ | 4935/61904 [2:26:12<20:48:59, 1.32s/it] 8%|▊ | 4936/61904 [2:26:14<20:39:47, 1.31s/it] 8%|▊ | 4937/61904 [2:26:15<22:35:21, 1.43s/it] 8%|▊ | 4938/61904 [2:26:17<22:11:22, 1.40s/it] 8%|▊ | 4939/61904 [2:26:18<21:58:54, 1.39s/it] 8%|▊ | 4940/61904 [2:26:19<21:57:31, 1.39s/it] {'loss': 2.9495, 'learning_rate': 1.9231816413846752e-07, 'epoch': 1.28} + 8%|▊ | 4940/61904 [2:26:19<21:57:31, 1.39s/it] 8%|▊ | 4941/61904 [2:26:21<21:41:13, 1.37s/it] 8%|▊ | 4942/61904 [2:26:22<21:29:11, 1.36s/it] 8%|▊ | 4943/61904 [2:26:23<21:37:42, 1.37s/it] 8%|▊ | 4944/61904 [2:26:25<21:03:59, 1.33s/it] 8%|▊ | 4945/61904 [2:26:26<21:02:57, 1.33s/it] 8%|▊ | 4946/61904 [2:26:27<21:19:01, 1.35s/it] 8%|▊ | 4947/61904 [2:26:29<21:57:41, 1.39s/it] 8%|▊ | 4948/61904 [2:26:30<22:15:37, 1.41s/it] 8%|▊ | 4949/61904 [2:26:32<21:47:31, 1.38s/it] 8%|▊ | 4950/61904 [2:26:33<21:46:58, 1.38s/it] 8%|▊ | 4951/61904 [2:26:34<21:28:11, 1.36s/it] 8%|▊ | 4952/61904 [2:26:36<21:05:50, 1.33s/it] 8%|▊ | 4953/61904 [2:26:37<21:27:58, 1.36s/it] 8%|▊ | 4954/61904 [2:26:38<21:20:10, 1.35s/it] 8%|▊ | 4955/61904 [2:26:40<20:58:30, 1.33s/it] 8%|▊ | 4956/61904 [2:26:41<20:53:45, 1.32s/it] 8%|▊ | 4957/61904 [2:26:42<20:50:07, 1.32s/it] 8%|▊ | 4958/61904 [2:26:44<21:30:23, 1.36s/it] 8%|▊ | 4959/61904 [2:26:45<21:26:18, 1.36s/it] 8%|▊ | 4960/61904 [2:26:47<22:02:03, 1.39s/it] {'loss': 3.0443, 'learning_rate': 1.9228575132892518e-07, 'epoch': 1.28} + 8%|▊ | 4960/61904 [2:26:47<22:02:03, 1.39s/it] 8%|▊ | 4961/61904 [2:26:48<21:39:48, 1.37s/it] 8%|▊ | 4962/61904 [2:26:49<21:53:28, 1.38s/it] 8%|▊ | 4963/61904 [2:26:50<20:48:55, 1.32s/it] 8%|▊ | 4964/61904 [2:26:52<20:16:19, 1.28s/it] 8%|▊ | 4965/61904 [2:26:53<21:03:48, 1.33s/it] 8%|▊ | 4966/61904 [2:26:54<20:58:57, 1.33s/it] 8%|▊ | 4967/61904 [2:26:56<20:53:09, 1.32s/it] 8%|▊ | 4968/61904 [2:26:57<21:09:48, 1.34s/it] 8%|▊ | 4969/61904 [2:26:58<20:59:32, 1.33s/it] 8%|▊ | 4970/61904 [2:27:00<20:48:26, 1.32s/it] 8%|▊ | 4971/61904 [2:27:01<21:36:35, 1.37s/it] 8%|▊ | 4972/61904 [2:27:02<21:40:05, 1.37s/it] 8%|▊ | 4973/61904 [2:27:04<21:40:29, 1.37s/it] 8%|▊ | 4974/61904 [2:27:05<21:16:11, 1.35s/it] 8%|▊ | 4975/61904 [2:27:06<20:51:34, 1.32s/it] 8%|▊ | 4976/61904 [2:27:08<20:14:22, 1.28s/it] 8%|▊ | 4977/61904 [2:27:09<21:05:25, 1.33s/it] 8%|▊ | 4978/61904 [2:27:11<21:50:51, 1.38s/it] 8%|▊ | 4979/61904 [2:27:12<21:19:37, 1.35s/it] 8%|▊ | 4980/61904 [2:27:13<21:00:20, 1.33s/it] {'loss': 2.9756, 'learning_rate': 1.9225333851938284e-07, 'epoch': 1.29} + 8%|▊ | 4980/61904 [2:27:13<21:00:20, 1.33s/it] 8%|▊ | 4981/61904 [2:27:15<21:26:11, 1.36s/it] 8%|▊ | 4982/61904 [2:27:16<21:25:26, 1.35s/it] 8%|▊ | 4983/61904 [2:27:17<21:06:51, 1.34s/it] 8%|▊ | 4984/61904 [2:27:19<21:22:05, 1.35s/it] 8%|▊ | 4985/61904 [2:27:20<21:02:54, 1.33s/it] 8%|▊ | 4986/61904 [2:27:21<21:10:57, 1.34s/it] 8%|▊ | 4987/61904 [2:27:23<21:34:27, 1.36s/it] 8%|▊ | 4988/61904 [2:27:24<22:18:04, 1.41s/it] 8%|▊ | 4989/61904 [2:27:25<21:44:48, 1.38s/it] 8%|▊ | 4990/61904 [2:27:27<22:19:37, 1.41s/it] 8%|▊ | 4991/61904 [2:27:28<22:09:40, 1.40s/it] 8%|▊ | 4992/61904 [2:27:30<21:37:36, 1.37s/it] 8%|▊ | 4993/61904 [2:27:31<22:25:12, 1.42s/it] 8%|▊ | 4994/61904 [2:27:33<22:29:45, 1.42s/it] 8%|▊ | 4995/61904 [2:27:34<21:35:18, 1.37s/it] 8%|▊ | 4996/61904 [2:27:35<21:24:36, 1.35s/it] 8%|▊ | 4997/61904 [2:27:37<21:45:39, 1.38s/it] 8%|▊ | 4998/61904 [2:27:38<21:32:01, 1.36s/it] 8%|▊ | 4999/61904 [2:27:39<21:11:15, 1.34s/it] 8%|▊ | 5000/61904 [2:27:41<21:26:18, 1.36s/it] {'loss': 2.9824, 'learning_rate': 1.9222092570984053e-07, 'epoch': 1.29} + 8%|▊ | 5000/61904 [2:27:41<21:26:18, 1.36s/it] 8%|▊ | 5001/61904 [2:27:42<21:36:10, 1.37s/it] 8%|▊ | 5002/61904 [2:27:43<21:20:19, 1.35s/it] 8%|▊ | 5003/61904 [2:27:45<21:16:36, 1.35s/it] 8%|▊ | 5004/61904 [2:27:46<21:00:32, 1.33s/it] 8%|▊ | 5005/61904 [2:27:47<20:58:06, 1.33s/it] 8%|▊ | 5006/61904 [2:27:49<21:08:47, 1.34s/it] 8%|▊ | 5007/61904 [2:27:50<21:22:52, 1.35s/it] 8%|▊ | 5008/61904 [2:27:51<21:33:13, 1.36s/it] 8%|▊ | 5009/61904 [2:27:53<21:04:34, 1.33s/it] 8%|▊ | 5010/61904 [2:27:54<20:31:37, 1.30s/it] 8%|▊ | 5011/61904 [2:27:55<21:05:14, 1.33s/it] 8%|▊ | 5012/61904 [2:27:57<21:33:34, 1.36s/it] 8%|▊ | 5013/61904 [2:27:58<20:58:01, 1.33s/it] 8%|▊ | 5014/61904 [2:27:59<21:34:56, 1.37s/it] 8%|▊ | 5015/61904 [2:28:01<21:51:29, 1.38s/it] 8%|▊ | 5016/61904 [2:28:02<21:27:19, 1.36s/it] 8%|▊ | 5017/61904 [2:28:03<20:44:08, 1.31s/it] 8%|▊ | 5018/61904 [2:28:05<21:04:06, 1.33s/it] 8%|▊ | 5019/61904 [2:28:06<21:10:04, 1.34s/it] 8%|▊ | 5020/61904 [2:28:07<21:04:35, 1.33s/it] {'loss': 3.0607, 'learning_rate': 1.9218851290029817e-07, 'epoch': 1.3} + 8%|▊ | 5020/61904 [2:28:07<21:04:35, 1.33s/it] 8%|▊ | 5021/61904 [2:28:09<20:44:46, 1.31s/it] 8%|▊ | 5022/61904 [2:28:10<21:06:32, 1.34s/it] 8%|▊ | 5023/61904 [2:28:11<21:07:57, 1.34s/it] 8%|▊ | 5024/61904 [2:28:13<21:56:48, 1.39s/it] 8%|▊ | 5025/61904 [2:28:14<22:21:56, 1.42s/it] 8%|▊ | 5026/61904 [2:28:16<22:11:59, 1.41s/it] 8%|▊ | 5027/61904 [2:28:17<22:07:14, 1.40s/it] 8%|▊ | 5028/61904 [2:28:18<21:45:00, 1.38s/it] 8%|▊ | 5029/61904 [2:28:20<21:35:56, 1.37s/it] 8%|▊ | 5030/61904 [2:28:21<20:37:19, 1.31s/it] 8%|▊ | 5031/61904 [2:28:22<21:07:45, 1.34s/it] 8%|▊ | 5032/61904 [2:28:24<21:43:49, 1.38s/it] 8%|▊ | 5033/61904 [2:28:25<21:41:46, 1.37s/it] 8%|▊ | 5034/61904 [2:28:27<22:12:23, 1.41s/it] 8%|▊ | 5035/61904 [2:28:28<21:51:31, 1.38s/it] 8%|▊ | 5036/61904 [2:28:29<22:16:34, 1.41s/it] 8%|▊ | 5037/61904 [2:28:31<22:33:57, 1.43s/it] 8%|▊ | 5038/61904 [2:28:32<21:54:38, 1.39s/it] 8%|▊ | 5039/61904 [2:28:34<21:20:31, 1.35s/it] 8%|▊ | 5040/61904 [2:28:35<21:38:06, 1.37s/it] {'loss': 3.0266, 'learning_rate': 1.9215610009075586e-07, 'epoch': 1.3} + 8%|▊ | 5040/61904 [2:28:35<21:38:06, 1.37s/it] 8%|▊ | 5041/61904 [2:28:36<21:56:01, 1.39s/it] 8%|▊ | 5042/61904 [2:28:38<22:30:02, 1.42s/it] 8%|▊ | 5043/61904 [2:28:39<22:09:01, 1.40s/it] 8%|▊ | 5044/61904 [2:28:41<22:47:25, 1.44s/it] 8%|▊ | 5045/61904 [2:28:42<22:46:43, 1.44s/it] 8%|▊ | 5046/61904 [2:28:44<23:08:01, 1.46s/it] 8%|▊ | 5047/61904 [2:28:45<22:16:08, 1.41s/it] 8%|▊ | 5048/61904 [2:28:46<21:42:39, 1.37s/it] 8%|▊ | 5049/61904 [2:28:48<21:39:08, 1.37s/it] 8%|▊ | 5050/61904 [2:28:49<21:09:43, 1.34s/it] 8%|▊ | 5051/61904 [2:28:51<23:13:56, 1.47s/it] 8%|▊ | 5052/61904 [2:28:52<22:22:50, 1.42s/it] 8%|▊ | 5053/61904 [2:28:53<21:56:49, 1.39s/it] 8%|▊ | 5054/61904 [2:28:55<21:42:42, 1.37s/it] 8%|▊ | 5055/61904 [2:28:56<21:37:03, 1.37s/it] 8%|▊ | 5056/61904 [2:28:57<21:28:02, 1.36s/it] 8%|▊ | 5057/61904 [2:28:59<21:42:09, 1.37s/it] 8%|▊ | 5058/61904 [2:29:00<21:35:52, 1.37s/it] 8%|▊ | 5059/61904 [2:29:02<22:10:27, 1.40s/it] 8%|▊ | 5060/61904 [2:29:03<22:25:28, 1.42s/it] {'loss': 2.9212, 'learning_rate': 1.9212368728121355e-07, 'epoch': 1.31} + 8%|▊ | 5060/61904 [2:29:03<22:25:28, 1.42s/it] 8%|▊ | 5061/61904 [2:29:04<21:54:47, 1.39s/it] 8%|▊ | 5062/61904 [2:29:06<21:06:00, 1.34s/it] 8%|▊ | 5063/61904 [2:29:07<20:43:57, 1.31s/it] 8%|▊ | 5064/61904 [2:29:08<21:36:59, 1.37s/it] 8%|▊ | 5065/61904 [2:29:10<22:51:36, 1.45s/it] 8%|▊ | 5066/61904 [2:29:11<22:24:20, 1.42s/it] 8%|▊ | 5067/61904 [2:29:13<21:55:31, 1.39s/it] 8%|▊ | 5068/61904 [2:29:14<21:39:49, 1.37s/it] 8%|▊ | 5069/61904 [2:29:15<21:08:58, 1.34s/it] 8%|▊ | 5070/61904 [2:29:17<21:03:42, 1.33s/it] 8%|▊ | 5071/61904 [2:29:18<22:27:50, 1.42s/it] 8%|▊ | 5072/61904 [2:29:20<22:26:13, 1.42s/it] 8%|▊ | 5073/61904 [2:29:21<21:40:06, 1.37s/it] 8%|▊ | 5074/61904 [2:29:22<21:22:22, 1.35s/it] 8%|▊ | 5075/61904 [2:29:24<21:41:36, 1.37s/it] 8%|▊ | 5076/61904 [2:29:25<21:37:07, 1.37s/it] 8%|▊ | 5077/61904 [2:29:26<21:29:45, 1.36s/it] 8%|▊ | 5078/61904 [2:29:28<21:20:39, 1.35s/it] 8%|▊ | 5079/61904 [2:29:29<21:27:45, 1.36s/it] 8%|▊ | 5080/61904 [2:29:30<21:02:03, 1.33s/it] {'loss': 3.0226, 'learning_rate': 1.9209127447167118e-07, 'epoch': 1.31} + 8%|▊ | 5080/61904 [2:29:30<21:02:03, 1.33s/it] 8%|▊ | 5081/61904 [2:29:32<20:44:02, 1.31s/it] 8%|▊ | 5082/61904 [2:29:33<20:58:37, 1.33s/it] 8%|▊ | 5083/61904 [2:29:34<21:27:19, 1.36s/it] 8%|▊ | 5084/61904 [2:29:36<21:00:40, 1.33s/it] 8%|▊ | 5085/61904 [2:29:37<21:00:43, 1.33s/it] 8%|▊ | 5086/61904 [2:29:38<21:11:30, 1.34s/it] 8%|▊ | 5087/61904 [2:29:40<21:19:32, 1.35s/it] 8%|▊ | 5088/61904 [2:29:41<21:24:18, 1.36s/it] 8%|▊ | 5089/61904 [2:29:42<20:58:17, 1.33s/it] 8%|▊ | 5090/61904 [2:29:44<22:01:46, 1.40s/it] 8%|▊ | 5091/61904 [2:29:45<22:06:58, 1.40s/it] 8%|▊ | 5092/61904 [2:29:47<21:19:19, 1.35s/it] 8%|▊ | 5093/61904 [2:29:48<22:05:00, 1.40s/it] 8%|▊ | 5094/61904 [2:29:49<21:31:20, 1.36s/it] 8%|▊ | 5095/61904 [2:29:51<21:10:15, 1.34s/it] 8%|▊ | 5096/61904 [2:29:52<20:57:46, 1.33s/it] 8%|▊ | 5097/61904 [2:29:53<20:32:25, 1.30s/it] 8%|▊ | 5098/61904 [2:29:54<20:01:09, 1.27s/it] 8%|▊ | 5099/61904 [2:29:56<21:07:34, 1.34s/it] 8%|▊ | 5100/61904 [2:29:57<21:44:58, 1.38s/it] {'loss': 2.9282, 'learning_rate': 1.9205886166212887e-07, 'epoch': 1.32} + 8%|▊ | 5100/61904 [2:29:57<21:44:58, 1.38s/it] 8%|▊ | 5101/61904 [2:29:59<21:48:33, 1.38s/it] 8%|▊ | 5102/61904 [2:30:00<22:23:23, 1.42s/it] 8%|▊ | 5103/61904 [2:30:02<22:55:53, 1.45s/it] 8%|▊ | 5104/61904 [2:30:03<22:48:39, 1.45s/it] 8%|▊ | 5105/61904 [2:30:05<23:12:57, 1.47s/it] 8%|▊ | 5106/61904 [2:30:06<23:05:31, 1.46s/it] 8%|▊ | 5107/61904 [2:30:07<22:22:06, 1.42s/it] 8%|▊ | 5108/61904 [2:30:09<21:55:56, 1.39s/it] 8%|▊ | 5109/61904 [2:30:10<21:02:47, 1.33s/it] 8%|▊ | 5110/61904 [2:30:11<20:45:37, 1.32s/it] 8%|▊ | 5111/61904 [2:30:12<20:12:52, 1.28s/it] 8%|▊ | 5112/61904 [2:30:14<21:25:31, 1.36s/it] 8%|▊ | 5113/61904 [2:30:15<21:12:39, 1.34s/it] 8%|▊ | 5114/61904 [2:30:17<20:53:10, 1.32s/it] 8%|▊ | 5115/61904 [2:30:18<20:59:45, 1.33s/it] 8%|▊ | 5116/61904 [2:30:19<20:33:06, 1.30s/it] 8%|▊ | 5117/61904 [2:30:20<20:20:30, 1.29s/it] 8%|▊ | 5118/61904 [2:30:22<20:47:59, 1.32s/it] 8%|▊ | 5119/61904 [2:30:23<20:24:00, 1.29s/it] 8%|▊ | 5120/61904 [2:30:24<20:52:25, 1.32s/it] {'loss': 2.9725, 'learning_rate': 1.9202644885258653e-07, 'epoch': 1.32} + 8%|▊ | 5120/61904 [2:30:24<20:52:25, 1.32s/it] 8%|▊ | 5121/61904 [2:30:26<20:39:22, 1.31s/it] 8%|▊ | 5122/61904 [2:30:27<20:54:15, 1.33s/it] 8%|▊ | 5123/61904 [2:30:28<20:32:24, 1.30s/it] 8%|▊ | 5124/61904 [2:30:30<20:49:31, 1.32s/it] 8%|▊ | 5125/61904 [2:30:31<21:31:20, 1.36s/it] 8%|▊ | 5126/61904 [2:30:33<22:07:42, 1.40s/it] 8%|▊ | 5127/61904 [2:30:34<21:50:42, 1.39s/it] 8%|▊ | 5128/61904 [2:30:35<21:47:29, 1.38s/it] 8%|▊ | 5129/61904 [2:30:37<21:12:00, 1.34s/it] 8%|▊ | 5130/61904 [2:30:38<20:23:06, 1.29s/it] 8%|▊ | 5131/61904 [2:30:39<20:32:47, 1.30s/it] 8%|▊ | 5132/61904 [2:30:40<20:31:41, 1.30s/it] 8%|▊ | 5133/61904 [2:30:42<20:46:08, 1.32s/it] 8%|▊ | 5134/61904 [2:30:43<21:19:26, 1.35s/it] 8%|▊ | 5135/61904 [2:30:45<22:01:05, 1.40s/it] 8%|▊ | 5136/61904 [2:30:46<21:56:24, 1.39s/it] 8%|▊ | 5137/61904 [2:30:48<22:11:10, 1.41s/it] 8%|▊ | 5138/61904 [2:30:49<21:19:19, 1.35s/it] 8%|▊ | 5139/61904 [2:30:50<21:21:20, 1.35s/it] 8%|▊ | 5140/61904 [2:30:51<21:09:16, 1.34s/it] {'loss': 2.9777, 'learning_rate': 1.919940360430442e-07, 'epoch': 1.33} + 8%|▊ | 5140/61904 [2:30:51<21:09:16, 1.34s/it] 8%|▊ | 5141/61904 [2:30:53<20:55:11, 1.33s/it] 8%|▊ | 5142/61904 [2:30:54<21:36:05, 1.37s/it] 8%|▊ | 5143/61904 [2:30:56<21:37:23, 1.37s/it] 8%|▊ | 5144/61904 [2:30:57<21:49:29, 1.38s/it] 8%|▊ | 5145/61904 [2:30:58<21:19:18, 1.35s/it] 8%|▊ | 5146/61904 [2:31:00<21:15:48, 1.35s/it] 8%|▊ | 5147/61904 [2:31:01<21:12:13, 1.34s/it] 8%|▊ | 5148/61904 [2:31:02<21:09:10, 1.34s/it] 8%|▊ | 5149/61904 [2:31:04<21:31:53, 1.37s/it] 8%|▊ | 5150/61904 [2:31:05<22:01:45, 1.40s/it] 8%|▊ | 5151/61904 [2:31:07<22:03:19, 1.40s/it] 8%|▊ | 5152/61904 [2:31:08<21:30:05, 1.36s/it] 8%|▊ | 5153/61904 [2:31:09<21:52:49, 1.39s/it] 8%|▊ | 5154/61904 [2:31:11<21:57:27, 1.39s/it] 8%|▊ | 5155/61904 [2:31:12<21:06:32, 1.34s/it] 8%|▊ | 5156/61904 [2:31:13<20:59:00, 1.33s/it] 8%|▊ | 5157/61904 [2:31:15<20:59:06, 1.33s/it] 8%|▊ | 5158/61904 [2:31:16<21:52:57, 1.39s/it] 8%|▊ | 5159/61904 [2:31:17<21:50:59, 1.39s/it] 8%|▊ | 5160/61904 [2:31:19<21:31:24, 1.37s/it] {'loss': 2.9426, 'learning_rate': 1.9196162323350188e-07, 'epoch': 1.33} + 8%|▊ | 5160/61904 [2:31:19<21:31:24, 1.37s/it] 8%|▊ | 5161/61904 [2:31:20<21:20:04, 1.35s/it] 8%|▊ | 5162/61904 [2:31:21<20:50:23, 1.32s/it] 8%|▊ | 5163/61904 [2:31:23<21:38:43, 1.37s/it] 8%|▊ | 5164/61904 [2:31:24<21:49:37, 1.38s/it] 8%|▊ | 5165/61904 [2:31:26<21:29:05, 1.36s/it] 8%|▊ | 5166/61904 [2:31:27<22:06:14, 1.40s/it] 8%|▊ | 5167/61904 [2:31:28<21:38:12, 1.37s/it] 8%|▊ | 5168/61904 [2:31:30<21:18:57, 1.35s/it] 8%|▊ | 5169/61904 [2:31:31<20:46:26, 1.32s/it] 8%|▊ | 5170/61904 [2:31:32<20:30:15, 1.30s/it] 8%|▊ | 5171/61904 [2:31:33<20:39:36, 1.31s/it] 8%|▊ | 5172/61904 [2:31:35<20:32:05, 1.30s/it] 8%|▊ | 5173/61904 [2:31:36<20:38:59, 1.31s/it] 8%|▊ | 5174/61904 [2:31:38<21:11:05, 1.34s/it] 8%|▊ | 5175/61904 [2:31:39<20:58:28, 1.33s/it] 8%|▊ | 5176/61904 [2:31:40<21:35:49, 1.37s/it] 8%|▊ | 5177/61904 [2:31:42<21:33:55, 1.37s/it] 8%|▊ | 5178/61904 [2:31:43<21:47:24, 1.38s/it] 8%|▊ | 5179/61904 [2:31:44<21:53:52, 1.39s/it] 8%|▊ | 5180/61904 [2:31:46<22:53:38, 1.45s/it] {'loss': 2.9584, 'learning_rate': 1.9192921042395954e-07, 'epoch': 1.34} + 8%|▊ | 5180/61904 [2:31:46<22:53:38, 1.45s/it] 8%|▊ | 5181/61904 [2:31:47<22:11:58, 1.41s/it] 8%|▊ | 5182/61904 [2:31:49<21:29:39, 1.36s/it] 8%|▊ | 5183/61904 [2:31:50<21:39:14, 1.37s/it] 8%|▊ | 5184/61904 [2:31:51<21:51:19, 1.39s/it] 8%|▊ | 5185/61904 [2:31:53<21:14:16, 1.35s/it] 8%|▊ | 5186/61904 [2:31:54<22:09:46, 1.41s/it] 8%|▊ | 5187/61904 [2:31:56<21:47:25, 1.38s/it] 8%|▊ | 5188/61904 [2:31:57<22:22:38, 1.42s/it] 8%|▊ | 5189/61904 [2:31:58<21:43:12, 1.38s/it] 8%|▊ | 5190/61904 [2:32:00<21:22:23, 1.36s/it] 8%|▊ | 5191/61904 [2:32:01<21:23:27, 1.36s/it] 8%|▊ | 5192/61904 [2:32:02<21:10:30, 1.34s/it] 8%|▊ | 5193/61904 [2:32:04<21:16:53, 1.35s/it] 8%|▊ | 5194/61904 [2:32:05<21:54:07, 1.39s/it] 8%|▊ | 5195/61904 [2:32:07<21:53:19, 1.39s/it] 8%|▊ | 5196/61904 [2:32:08<21:39:40, 1.38s/it] 8%|▊ | 5197/61904 [2:32:09<21:28:01, 1.36s/it] 8%|▊ | 5198/61904 [2:32:11<21:38:24, 1.37s/it] 8%|▊ | 5199/61904 [2:32:12<21:54:22, 1.39s/it] 8%|▊ | 5200/61904 [2:32:14<22:17:52, 1.42s/it] {'loss': 2.9244, 'learning_rate': 1.918967976144172e-07, 'epoch': 1.34} + 8%|▊ | 5200/61904 [2:32:14<22:17:52, 1.42s/it] 8%|▊ | 5201/61904 [2:32:15<21:36:50, 1.37s/it] 8%|▊ | 5202/61904 [2:32:16<21:08:41, 1.34s/it] 8%|▊ | 5203/61904 [2:32:18<22:16:41, 1.41s/it] 8%|▊ | 5204/61904 [2:32:19<21:48:31, 1.38s/it] 8%|▊ | 5205/61904 [2:32:20<21:12:46, 1.35s/it] 8%|▊ | 5206/61904 [2:32:22<20:51:30, 1.32s/it] 8%|▊ | 5207/61904 [2:32:23<20:42:15, 1.31s/it] 8%|▊ | 5208/61904 [2:32:24<21:03:59, 1.34s/it] 8%|▊ | 5209/61904 [2:32:26<21:12:57, 1.35s/it] 8%|▊ | 5210/61904 [2:32:27<21:33:38, 1.37s/it] 8%|▊ | 5211/61904 [2:32:28<21:22:56, 1.36s/it] 8%|▊ | 5212/61904 [2:32:30<21:26:37, 1.36s/it] 8%|▊ | 5213/61904 [2:32:31<21:13:52, 1.35s/it] 8%|▊ | 5214/61904 [2:32:32<20:41:25, 1.31s/it] 8%|▊ | 5215/61904 [2:32:34<20:43:17, 1.32s/it] 8%|▊ | 5216/61904 [2:32:35<20:57:29, 1.33s/it] 8%|▊ | 5217/61904 [2:32:36<21:31:28, 1.37s/it] 8%|▊ | 5218/61904 [2:32:38<21:26:18, 1.36s/it] 8%|▊ | 5219/61904 [2:32:39<21:56:27, 1.39s/it] 8%|▊ | 5220/61904 [2:32:41<21:33:57, 1.37s/it] {'loss': 3.0344, 'learning_rate': 1.918643848048749e-07, 'epoch': 1.35} + 8%|▊ | 5220/61904 [2:32:41<21:33:57, 1.37s/it] 8%|▊ | 5221/61904 [2:32:42<20:56:44, 1.33s/it] 8%|▊ | 5222/61904 [2:32:43<21:32:33, 1.37s/it] 8%|▊ | 5223/61904 [2:32:45<21:50:40, 1.39s/it] 8%|▊ | 5224/61904 [2:32:46<22:36:54, 1.44s/it] 8%|▊ | 5225/61904 [2:32:48<22:38:42, 1.44s/it] 8%|▊ | 5226/61904 [2:32:49<22:04:33, 1.40s/it] 8%|▊ | 5227/61904 [2:32:50<21:21:26, 1.36s/it] 8%|▊ | 5228/61904 [2:32:52<21:17:09, 1.35s/it] 8%|▊ | 5229/61904 [2:32:53<21:04:14, 1.34s/it] 8%|▊ | 5230/61904 [2:32:54<21:07:13, 1.34s/it] 8%|▊ | 5231/61904 [2:32:56<21:28:45, 1.36s/it] 8%|▊ | 5232/61904 [2:32:57<22:13:41, 1.41s/it] 8%|▊ | 5233/61904 [2:32:59<22:29:31, 1.43s/it] 8%|▊ | 5234/61904 [2:33:00<22:48:40, 1.45s/it] 8%|▊ | 5235/61904 [2:33:02<22:32:18, 1.43s/it] 8%|▊ | 5236/61904 [2:33:03<21:47:42, 1.38s/it] 8%|▊ | 5237/61904 [2:33:04<21:51:10, 1.39s/it] 8%|▊ | 5238/61904 [2:33:06<22:03:47, 1.40s/it] 8%|▊ | 5239/61904 [2:33:07<22:52:37, 1.45s/it] 8%|▊ | 5240/61904 [2:33:08<21:41:49, 1.38s/it] {'loss': 2.9877, 'learning_rate': 1.9183197199533253e-07, 'epoch': 1.35} + 8%|▊ | 5240/61904 [2:33:08<21:41:49, 1.38s/it] 8%|▊ | 5241/61904 [2:33:10<22:36:10, 1.44s/it] 8%|▊ | 5242/61904 [2:33:11<22:08:03, 1.41s/it] 8%|▊ | 5243/61904 [2:33:13<22:06:04, 1.40s/it] 8%|▊ | 5244/61904 [2:33:14<22:10:41, 1.41s/it] 8%|▊ | 5245/61904 [2:33:15<21:38:51, 1.38s/it] 8%|▊ | 5246/61904 [2:33:17<22:26:07, 1.43s/it] 8%|▊ | 5247/61904 [2:33:18<21:48:09, 1.39s/it] 8%|▊ | 5248/61904 [2:33:20<21:10:39, 1.35s/it] 8%|▊ | 5249/61904 [2:33:21<21:27:58, 1.36s/it] 8%|▊ | 5250/61904 [2:33:22<21:36:28, 1.37s/it] 8%|▊ | 5251/61904 [2:33:24<21:05:20, 1.34s/it] 8%|▊ | 5252/61904 [2:33:25<20:43:45, 1.32s/it] 8%|▊ | 5253/61904 [2:33:26<21:22:01, 1.36s/it] 8%|▊ | 5254/61904 [2:33:28<20:54:43, 1.33s/it] 8%|▊ | 5255/61904 [2:33:29<20:46:49, 1.32s/it] 8%|▊ | 5256/61904 [2:33:30<21:07:40, 1.34s/it] 8%|▊ | 5257/61904 [2:33:31<20:39:32, 1.31s/it] 8%|▊ | 5258/61904 [2:33:33<21:16:21, 1.35s/it] 8%|▊ | 5259/61904 [2:33:34<21:08:42, 1.34s/it] 8%|▊ | 5260/61904 [2:33:36<20:43:16, 1.32s/it] {'loss': 2.9763, 'learning_rate': 1.9179955918579022e-07, 'epoch': 1.36} + 8%|▊ | 5260/61904 [2:33:36<20:43:16, 1.32s/it] 8%|▊ | 5261/61904 [2:33:37<20:24:27, 1.30s/it] 9%|▊ | 5262/61904 [2:33:38<20:46:21, 1.32s/it] 9%|▊ | 5263/61904 [2:33:39<20:30:55, 1.30s/it] 9%|▊ | 5264/61904 [2:33:41<21:44:41, 1.38s/it] 9%|▊ | 5265/61904 [2:33:42<21:11:47, 1.35s/it] 9%|▊ | 5266/61904 [2:33:44<22:09:38, 1.41s/it] 9%|▊ | 5267/61904 [2:33:45<21:24:59, 1.36s/it] 9%|▊ | 5268/61904 [2:33:46<21:14:56, 1.35s/it] 9%|▊ | 5269/61904 [2:33:48<20:37:12, 1.31s/it] 9%|▊ | 5270/61904 [2:33:49<20:49:21, 1.32s/it] 9%|▊ | 5271/61904 [2:33:50<21:00:55, 1.34s/it] 9%|▊ | 5272/61904 [2:33:52<20:51:03, 1.33s/it] 9%|▊ | 5273/61904 [2:33:53<23:20:13, 1.48s/it] 9%|▊ | 5274/61904 [2:33:55<23:44:27, 1.51s/it] 9%|▊ | 5275/61904 [2:33:56<22:51:18, 1.45s/it] 9%|▊ | 5276/61904 [2:33:58<22:09:13, 1.41s/it] 9%|▊ | 5277/61904 [2:33:59<21:16:14, 1.35s/it] 9%|▊ | 5278/61904 [2:34:00<20:47:06, 1.32s/it] 9%|▊ | 5279/61904 [2:34:01<20:45:50, 1.32s/it] 9%|▊ | 5280/61904 [2:34:03<21:12:44, 1.35s/it] {'loss': 2.9684, 'learning_rate': 1.917671463762479e-07, 'epoch': 1.36} + 9%|▊ | 5280/61904 [2:34:03<21:12:44, 1.35s/it] 9%|▊ | 5281/61904 [2:34:04<21:30:45, 1.37s/it] 9%|▊ | 5282/61904 [2:34:06<21:29:07, 1.37s/it] 9%|▊ | 5283/61904 [2:34:07<21:20:55, 1.36s/it] 9%|▊ | 5284/61904 [2:34:08<21:08:04, 1.34s/it] 9%|▊ | 5285/61904 [2:34:10<21:00:45, 1.34s/it] 9%|▊ | 5286/61904 [2:34:11<20:50:59, 1.33s/it] 9%|▊ | 5287/61904 [2:34:12<21:31:40, 1.37s/it] 9%|▊ | 5288/61904 [2:34:14<21:22:40, 1.36s/it] 9%|▊ | 5289/61904 [2:34:15<22:41:00, 1.44s/it] 9%|▊ | 5290/61904 [2:34:17<22:00:31, 1.40s/it] 9%|▊ | 5291/61904 [2:34:18<21:19:57, 1.36s/it] 9%|▊ | 5292/61904 [2:34:19<21:33:30, 1.37s/it] 9%|▊ | 5293/61904 [2:34:21<20:53:57, 1.33s/it] 9%|▊ | 5294/61904 [2:34:22<20:33:32, 1.31s/it] 9%|▊ | 5295/61904 [2:34:23<20:51:15, 1.33s/it] 9%|▊ | 5296/61904 [2:34:24<20:44:00, 1.32s/it] 9%|▊ | 5297/61904 [2:34:26<20:59:12, 1.33s/it] 9%|▊ | 5298/61904 [2:34:27<21:25:42, 1.36s/it] 9%|▊ | 5299/61904 [2:34:29<21:39:17, 1.38s/it] 9%|▊ | 5300/61904 [2:34:30<21:54:20, 1.39s/it] {'loss': 3.0331, 'learning_rate': 1.9173473356670554e-07, 'epoch': 1.37} + 9%|▊ | 5300/61904 [2:34:30<21:54:20, 1.39s/it] 9%|▊ | 5301/61904 [2:34:31<21:49:14, 1.39s/it] 9%|▊ | 5302/61904 [2:34:33<21:43:36, 1.38s/it] 9%|▊ | 5303/61904 [2:34:34<21:32:50, 1.37s/it] 9%|▊ | 5304/61904 [2:34:35<20:53:59, 1.33s/it] 9%|▊ | 5305/61904 [2:34:37<20:54:52, 1.33s/it] 9%|▊ | 5306/61904 [2:34:38<21:06:16, 1.34s/it] 9%|▊ | 5307/61904 [2:34:40<21:33:52, 1.37s/it] 9%|▊ | 5308/61904 [2:34:41<21:32:50, 1.37s/it] 9%|▊ | 5309/61904 [2:34:42<21:36:49, 1.37s/it] 9%|▊ | 5310/61904 [2:34:44<21:26:52, 1.36s/it] 9%|▊ | 5311/61904 [2:34:45<21:20:02, 1.36s/it] 9%|▊ | 5312/61904 [2:34:46<21:47:48, 1.39s/it] 9%|▊ | 5313/61904 [2:34:48<21:06:37, 1.34s/it] 9%|▊ | 5314/61904 [2:34:49<20:52:38, 1.33s/it] 9%|▊ | 5315/61904 [2:34:50<20:44:29, 1.32s/it] 9%|▊ | 5316/61904 [2:34:52<20:20:27, 1.29s/it] 9%|▊ | 5317/61904 [2:34:53<20:24:47, 1.30s/it] 9%|▊ | 5318/61904 [2:34:54<20:18:04, 1.29s/it] 9%|▊ | 5319/61904 [2:34:56<20:58:25, 1.33s/it] 9%|▊ | 5320/61904 [2:34:57<20:27:25, 1.30s/it] {'loss': 3.0052, 'learning_rate': 1.9170232075716323e-07, 'epoch': 1.37} + 9%|▊ | 5320/61904 [2:34:57<20:27:25, 1.30s/it] 9%|▊ | 5321/61904 [2:34:58<20:10:17, 1.28s/it] 9%|▊ | 5322/61904 [2:34:59<20:15:13, 1.29s/it] 9%|▊ | 5323/61904 [2:35:01<20:08:47, 1.28s/it] 9%|▊ | 5324/61904 [2:35:02<20:05:44, 1.28s/it] 9%|▊ | 5325/61904 [2:35:03<20:20:07, 1.29s/it] 9%|▊ | 5326/61904 [2:35:04<20:27:40, 1.30s/it] 9%|▊ | 5327/61904 [2:35:06<20:44:51, 1.32s/it] 9%|▊ | 5328/61904 [2:35:07<20:46:35, 1.32s/it] 9%|▊ | 5329/61904 [2:35:09<21:17:40, 1.36s/it] 9%|▊ | 5330/61904 [2:35:10<21:16:01, 1.35s/it] 9%|▊ | 5331/61904 [2:35:11<21:36:56, 1.38s/it] 9%|▊ | 5332/61904 [2:35:13<21:02:44, 1.34s/it] 9%|▊ | 5333/61904 [2:35:14<21:37:16, 1.38s/it] 9%|▊ | 5334/61904 [2:35:15<21:21:26, 1.36s/it] 9%|▊ | 5335/61904 [2:35:17<21:04:45, 1.34s/it] 9%|▊ | 5336/61904 [2:35:18<21:49:11, 1.39s/it] 9%|▊ | 5337/61904 [2:35:20<21:51:21, 1.39s/it] 9%|▊ | 5338/61904 [2:35:21<21:37:57, 1.38s/it] 9%|▊ | 5339/61904 [2:35:22<21:49:52, 1.39s/it] 9%|▊ | 5340/61904 [2:35:24<22:29:59, 1.43s/it] {'loss': 2.9511, 'learning_rate': 1.916699079476209e-07, 'epoch': 1.38} + 9%|▊ | 5340/61904 [2:35:24<22:29:59, 1.43s/it] 9%|▊ | 5341/61904 [2:35:25<22:34:58, 1.44s/it] 9%|▊ | 5342/61904 [2:35:27<22:43:17, 1.45s/it] 9%|▊ | 5343/61904 [2:35:28<22:24:40, 1.43s/it] 9%|▊ | 5344/61904 [2:35:29<21:26:50, 1.37s/it] 9%|▊ | 5345/61904 [2:35:31<21:36:40, 1.38s/it] 9%|▊ | 5346/61904 [2:35:32<20:53:47, 1.33s/it] 9%|▊ | 5347/61904 [2:35:33<20:55:23, 1.33s/it] 9%|▊ | 5348/61904 [2:35:35<21:36:47, 1.38s/it] 9%|▊ | 5349/61904 [2:35:36<21:44:27, 1.38s/it] 9%|▊ | 5350/61904 [2:35:38<21:38:19, 1.38s/it] 9%|▊ | 5351/61904 [2:35:39<21:38:03, 1.38s/it] 9%|▊ | 5352/61904 [2:35:40<21:59:28, 1.40s/it] 9%|▊ | 5353/61904 [2:35:42<21:08:21, 1.35s/it] 9%|▊ | 5354/61904 [2:35:43<21:09:27, 1.35s/it] 9%|▊ | 5355/61904 [2:35:44<21:33:45, 1.37s/it] 9%|▊ | 5356/61904 [2:35:46<22:15:06, 1.42s/it] 9%|▊ | 5357/61904 [2:35:47<21:46:18, 1.39s/it] 9%|▊ | 5358/61904 [2:35:49<21:25:59, 1.36s/it] 9%|▊ | 5359/61904 [2:35:50<21:19:48, 1.36s/it] 9%|▊ | 5360/61904 [2:35:51<20:56:21, 1.33s/it] {'loss': 2.9444, 'learning_rate': 1.9163749513807855e-07, 'epoch': 1.39} + 9%|▊ | 5360/61904 [2:35:51<20:56:21, 1.33s/it] 9%|▊ | 5361/61904 [2:35:53<21:02:56, 1.34s/it] 9%|▊ | 5362/61904 [2:35:54<21:09:26, 1.35s/it] 9%|▊ | 5363/61904 [2:35:56<22:29:11, 1.43s/it] 9%|▊ | 5364/61904 [2:35:57<22:27:36, 1.43s/it] 9%|▊ | 5365/61904 [2:35:58<21:41:11, 1.38s/it] 9%|▊ | 5366/61904 [2:36:00<21:31:51, 1.37s/it] 9%|▊ | 5367/61904 [2:36:01<21:08:48, 1.35s/it] 9%|▊ | 5368/61904 [2:36:02<20:52:57, 1.33s/it] 9%|▊ | 5369/61904 [2:36:04<21:06:29, 1.34s/it] 9%|▊ | 5370/61904 [2:36:05<21:06:16, 1.34s/it] 9%|▊ | 5371/61904 [2:36:06<21:02:53, 1.34s/it] 9%|▊ | 5372/61904 [2:36:08<20:42:44, 1.32s/it] 9%|▊ | 5373/61904 [2:36:09<20:46:24, 1.32s/it] 9%|▊ | 5374/61904 [2:36:10<21:22:03, 1.36s/it] 9%|▊ | 5375/61904 [2:36:12<21:00:27, 1.34s/it] 9%|▊ | 5376/61904 [2:36:13<21:33:54, 1.37s/it] 9%|▊ | 5377/61904 [2:36:14<21:39:29, 1.38s/it] 9%|▊ | 5378/61904 [2:36:16<21:36:45, 1.38s/it] 9%|▊ | 5379/61904 [2:36:17<20:57:48, 1.34s/it] 9%|▊ | 5380/61904 [2:36:18<21:16:52, 1.36s/it] {'loss': 2.9757, 'learning_rate': 1.9160508232853624e-07, 'epoch': 1.39} + 9%|▊ | 5380/61904 [2:36:18<21:16:52, 1.36s/it] 9%|▊ | 5381/61904 [2:36:20<21:25:32, 1.36s/it] 9%|▊ | 5382/61904 [2:36:21<21:38:45, 1.38s/it] 9%|▊ | 5383/61904 [2:36:22<20:47:35, 1.32s/it] 9%|▊ | 5384/61904 [2:36:24<20:34:35, 1.31s/it] 9%|▊ | 5385/61904 [2:36:25<21:09:58, 1.35s/it] 9%|▊ | 5386/61904 [2:36:26<20:38:07, 1.31s/it] 9%|▊ | 5387/61904 [2:36:28<20:13:13, 1.29s/it] 9%|▊ | 5388/61904 [2:36:29<20:29:08, 1.30s/it] 9%|▊ | 5389/61904 [2:36:30<21:04:01, 1.34s/it] 9%|▊ | 5390/61904 [2:36:32<21:58:36, 1.40s/it] 9%|▊ | 5391/61904 [2:36:33<21:24:50, 1.36s/it] 9%|▊ | 5392/61904 [2:36:35<21:53:18, 1.39s/it] 9%|▊ | 5393/61904 [2:36:36<22:27:05, 1.43s/it] 9%|▊ | 5394/61904 [2:36:37<21:17:19, 1.36s/it] 9%|▊ | 5395/61904 [2:36:39<20:47:06, 1.32s/it] 9%|▊ | 5396/61904 [2:36:40<21:01:02, 1.34s/it] 9%|▊ | 5397/61904 [2:36:41<20:21:18, 1.30s/it] 9%|▊ | 5398/61904 [2:36:42<20:22:41, 1.30s/it] 9%|▊ | 5399/61904 [2:36:44<20:54:24, 1.33s/it] 9%|▊ | 5400/61904 [2:36:45<20:57:44, 1.34s/it] {'loss': 3.0247, 'learning_rate': 1.915726695189939e-07, 'epoch': 1.4} + 9%|▊ | 5400/61904 [2:36:45<20:57:44, 1.34s/it] 9%|▊ | 5401/61904 [2:36:47<21:07:10, 1.35s/it] 9%|▊ | 5402/61904 [2:36:48<20:57:27, 1.34s/it] 9%|▊ | 5403/61904 [2:36:49<21:41:05, 1.38s/it] 9%|▊ | 5404/61904 [2:36:51<21:04:22, 1.34s/it] 9%|▊ | 5405/61904 [2:36:52<20:30:50, 1.31s/it] 9%|▊ | 5406/61904 [2:36:53<20:40:32, 1.32s/it] 9%|▊ | 5407/61904 [2:36:55<21:09:22, 1.35s/it] 9%|▊ | 5408/61904 [2:36:56<21:43:29, 1.38s/it] 9%|▊ | 5409/61904 [2:36:57<21:36:20, 1.38s/it] 9%|▊ | 5410/61904 [2:36:59<21:36:56, 1.38s/it] 9%|▊ | 5411/61904 [2:37:00<21:13:25, 1.35s/it] 9%|▊ | 5412/61904 [2:37:01<21:06:56, 1.35s/it] 9%|▊ | 5413/61904 [2:37:03<20:49:16, 1.33s/it] 9%|▊ | 5414/61904 [2:37:04<21:26:44, 1.37s/it] 9%|▊ | 5415/61904 [2:37:05<20:50:13, 1.33s/it] 9%|▊ | 5416/61904 [2:37:07<22:46:48, 1.45s/it] 9%|▉ | 5417/61904 [2:37:09<22:19:06, 1.42s/it] 9%|▉ | 5418/61904 [2:37:10<21:45:29, 1.39s/it] 9%|▉ | 5419/61904 [2:37:11<21:34:15, 1.37s/it] 9%|▉ | 5420/61904 [2:37:13<21:49:52, 1.39s/it] {'loss': 3.0173, 'learning_rate': 1.9154025670945156e-07, 'epoch': 1.4} + 9%|▉ | 5420/61904 [2:37:13<21:49:52, 1.39s/it] 9%|▉ | 5421/61904 [2:37:14<22:10:06, 1.41s/it] 9%|▉ | 5422/61904 [2:37:15<21:46:15, 1.39s/it] 9%|▉ | 5423/61904 [2:37:17<21:44:27, 1.39s/it] 9%|▉ | 5424/61904 [2:37:18<21:33:06, 1.37s/it] 9%|▉ | 5425/61904 [2:37:20<22:14:55, 1.42s/it] 9%|▉ | 5426/61904 [2:37:21<22:19:41, 1.42s/it] 9%|▉ | 5427/61904 [2:37:23<22:46:34, 1.45s/it] 9%|▉ | 5428/61904 [2:37:24<23:16:30, 1.48s/it] 9%|▉ | 5429/61904 [2:37:26<23:05:23, 1.47s/it] 9%|▉ | 5430/61904 [2:37:27<22:37:02, 1.44s/it] 9%|▉ | 5431/61904 [2:37:28<22:26:08, 1.43s/it] 9%|▉ | 5432/61904 [2:37:30<22:45:25, 1.45s/it] 9%|▉ | 5433/61904 [2:37:31<22:01:38, 1.40s/it] 9%|▉ | 5434/61904 [2:37:33<21:47:19, 1.39s/it] 9%|▉ | 5435/61904 [2:37:34<21:29:25, 1.37s/it] 9%|▉ | 5436/61904 [2:37:35<21:00:36, 1.34s/it] 9%|▉ | 5437/61904 [2:37:36<20:54:47, 1.33s/it] 9%|▉ | 5438/61904 [2:37:38<21:21:12, 1.36s/it] 9%|▉ | 5439/61904 [2:37:39<21:16:13, 1.36s/it] 9%|▉ | 5440/61904 [2:37:41<21:31:29, 1.37s/it] {'loss': 2.9848, 'learning_rate': 1.9150784389990925e-07, 'epoch': 1.41} + 9%|▉ | 5440/61904 [2:37:41<21:31:29, 1.37s/it] 9%|▉ | 5441/61904 [2:37:42<21:00:14, 1.34s/it] 9%|▉ | 5442/61904 [2:37:43<21:12:06, 1.35s/it] 9%|▉ | 5443/61904 [2:37:45<20:44:45, 1.32s/it] 9%|▉ | 5444/61904 [2:37:46<20:53:07, 1.33s/it] 9%|▉ | 5445/61904 [2:37:47<20:54:21, 1.33s/it] 9%|▉ | 5446/61904 [2:37:49<21:00:50, 1.34s/it] 9%|▉ | 5447/61904 [2:37:50<21:12:11, 1.35s/it] 9%|▉ | 5448/61904 [2:37:51<21:31:45, 1.37s/it] 9%|▉ | 5449/61904 [2:37:53<21:39:37, 1.38s/it] 9%|▉ | 5450/61904 [2:37:54<21:25:40, 1.37s/it] 9%|▉ | 5451/61904 [2:37:56<21:52:11, 1.39s/it] 9%|▉ | 5452/61904 [2:37:57<21:42:33, 1.38s/it] 9%|▉ | 5453/61904 [2:37:59<23:23:23, 1.49s/it] 9%|▉ | 5454/61904 [2:38:00<22:25:02, 1.43s/it] 9%|▉ | 5455/61904 [2:38:01<22:11:28, 1.42s/it] 9%|▉ | 5456/61904 [2:38:03<22:50:04, 1.46s/it] 9%|▉ | 5457/61904 [2:38:04<21:44:28, 1.39s/it] 9%|▉ | 5458/61904 [2:38:06<21:59:32, 1.40s/it] 9%|▉ | 5459/61904 [2:38:07<22:16:20, 1.42s/it] 9%|▉ | 5460/61904 [2:38:08<21:29:17, 1.37s/it] {'loss': 2.9544, 'learning_rate': 1.914754310903669e-07, 'epoch': 1.41} + 9%|▉ | 5460/61904 [2:38:08<21:29:17, 1.37s/it] 9%|▉ | 5461/61904 [2:38:10<21:24:49, 1.37s/it] 9%|▉ | 5462/61904 [2:38:11<21:52:50, 1.40s/it] 9%|▉ | 5463/61904 [2:38:12<21:37:34, 1.38s/it] 9%|▉ | 5464/61904 [2:38:14<21:06:45, 1.35s/it] 9%|▉ | 5465/61904 [2:38:15<20:38:43, 1.32s/it] 9%|▉ | 5466/61904 [2:38:16<21:17:34, 1.36s/it] 9%|▉ | 5467/61904 [2:38:18<20:53:28, 1.33s/it] 9%|▉ | 5468/61904 [2:38:19<20:37:37, 1.32s/it] 9%|▉ | 5469/61904 [2:38:20<20:32:32, 1.31s/it] 9%|▉ | 5470/61904 [2:38:22<21:50:07, 1.39s/it] 9%|▉ | 5471/61904 [2:38:23<21:18:29, 1.36s/it] 9%|▉ | 5472/61904 [2:38:24<20:54:36, 1.33s/it] 9%|▉ | 5473/61904 [2:38:26<21:02:25, 1.34s/it] 9%|▉ | 5474/61904 [2:38:27<20:19:28, 1.30s/it] 9%|▉ | 5475/61904 [2:38:28<20:45:59, 1.32s/it] 9%|▉ | 5476/61904 [2:38:30<20:23:44, 1.30s/it] 9%|▉ | 5477/61904 [2:38:31<20:55:08, 1.33s/it] 9%|▉ | 5478/61904 [2:38:32<21:25:22, 1.37s/it] 9%|▉ | 5479/61904 [2:38:34<21:04:20, 1.34s/it] 9%|▉ | 5480/61904 [2:38:35<21:03:05, 1.34s/it] {'loss': 2.9586, 'learning_rate': 1.9144301828082458e-07, 'epoch': 1.42} + 9%|▉ | 5480/61904 [2:38:35<21:03:05, 1.34s/it] 9%|▉ | 5481/61904 [2:38:37<21:23:41, 1.37s/it] 9%|▉ | 5482/61904 [2:38:38<20:58:08, 1.34s/it] 9%|▉ | 5483/61904 [2:38:39<21:18:59, 1.36s/it] 9%|▉ | 5484/61904 [2:38:41<21:46:55, 1.39s/it] 9%|▉ | 5485/61904 [2:38:42<21:31:30, 1.37s/it] 9%|▉ | 5486/61904 [2:38:43<21:32:43, 1.37s/it] 9%|▉ | 5487/61904 [2:38:45<21:09:54, 1.35s/it] 9%|▉ | 5488/61904 [2:38:46<20:47:30, 1.33s/it] 9%|▉ | 5489/61904 [2:38:47<21:04:59, 1.35s/it] 9%|▉ | 5490/61904 [2:38:49<20:58:18, 1.34s/it] 9%|▉ | 5491/61904 [2:38:50<20:50:39, 1.33s/it] 9%|▉ | 5492/61904 [2:38:51<20:43:43, 1.32s/it] 9%|▉ | 5493/61904 [2:38:53<21:19:33, 1.36s/it] 9%|▉ | 5494/61904 [2:38:54<20:52:23, 1.33s/it] 9%|▉ | 5495/61904 [2:38:55<20:27:56, 1.31s/it] 9%|▉ | 5496/61904 [2:38:57<20:28:25, 1.31s/it] 9%|▉ | 5497/61904 [2:38:58<21:21:44, 1.36s/it] 9%|▉ | 5498/61904 [2:38:59<21:43:37, 1.39s/it] 9%|▉ | 5499/61904 [2:39:01<21:39:20, 1.38s/it] 9%|▉ | 5500/61904 [2:39:02<21:26:42, 1.37s/it] {'loss': 2.9663, 'learning_rate': 1.9141060547128224e-07, 'epoch': 1.42} + 9%|▉ | 5500/61904 [2:39:02<21:26:42, 1.37s/it] 9%|▉ | 5501/61904 [2:39:04<21:25:17, 1.37s/it] 9%|▉ | 5502/61904 [2:39:05<21:20:08, 1.36s/it] 9%|▉ | 5503/61904 [2:39:06<21:28:06, 1.37s/it] 9%|▉ | 5504/61904 [2:39:08<21:05:10, 1.35s/it] 9%|▉ | 5505/61904 [2:39:09<20:57:46, 1.34s/it] 9%|▉ | 5506/61904 [2:39:10<22:06:12, 1.41s/it] 9%|▉ | 5507/61904 [2:39:12<22:03:06, 1.41s/it] 9%|▉ | 5508/61904 [2:39:13<22:12:51, 1.42s/it] 9%|▉ | 5509/61904 [2:39:15<22:23:49, 1.43s/it] 9%|▉ | 5510/61904 [2:39:16<22:19:43, 1.43s/it] 9%|▉ | 5511/61904 [2:39:18<21:50:48, 1.39s/it] 9%|▉ | 5512/61904 [2:39:19<22:59:25, 1.47s/it] 9%|▉ | 5513/61904 [2:39:21<22:51:37, 1.46s/it] 9%|▉ | 5514/61904 [2:39:22<23:13:49, 1.48s/it] 9%|▉ | 5515/61904 [2:39:23<22:41:33, 1.45s/it] 9%|▉ | 5516/61904 [2:39:25<22:12:11, 1.42s/it] 9%|▉ | 5517/61904 [2:39:26<22:11:16, 1.42s/it] 9%|▉ | 5518/61904 [2:39:28<21:55:02, 1.40s/it] 9%|▉ | 5519/61904 [2:39:29<22:00:44, 1.41s/it] 9%|▉ | 5520/61904 [2:39:30<21:53:36, 1.40s/it] {'loss': 2.9736, 'learning_rate': 1.913781926617399e-07, 'epoch': 1.43} + 9%|▉ | 5520/61904 [2:39:30<21:53:36, 1.40s/it] 9%|▉ | 5521/61904 [2:39:32<21:32:35, 1.38s/it] 9%|▉ | 5522/61904 [2:39:33<22:06:56, 1.41s/it] 9%|▉ | 5523/61904 [2:39:35<22:21:33, 1.43s/it] 9%|▉ | 5524/61904 [2:39:36<23:07:41, 1.48s/it] 9%|▉ | 5525/61904 [2:39:38<22:25:35, 1.43s/it] 9%|▉ | 5526/61904 [2:39:39<23:18:05, 1.49s/it] 9%|▉ | 5527/61904 [2:39:41<22:54:25, 1.46s/it] 9%|▉ | 5528/61904 [2:39:42<23:39:59, 1.51s/it] 9%|▉ | 5529/61904 [2:39:44<23:18:45, 1.49s/it] 9%|▉ | 5530/61904 [2:39:45<22:42:55, 1.45s/it] 9%|▉ | 5531/61904 [2:39:47<23:24:10, 1.49s/it] 9%|▉ | 5532/61904 [2:39:48<22:26:04, 1.43s/it] 9%|▉ | 5533/61904 [2:39:49<21:50:23, 1.39s/it] 9%|▉ | 5534/61904 [2:39:51<23:21:25, 1.49s/it] 9%|▉ | 5535/61904 [2:39:52<22:28:16, 1.44s/it] 9%|▉ | 5536/61904 [2:39:54<22:48:09, 1.46s/it] 9%|▉ | 5537/61904 [2:39:55<22:28:39, 1.44s/it] 9%|▉ | 5538/61904 [2:39:57<22:32:21, 1.44s/it] 9%|▉ | 5539/61904 [2:39:58<22:15:10, 1.42s/it] 9%|▉ | 5540/61904 [2:39:59<21:16:20, 1.36s/it] {'loss': 2.9392, 'learning_rate': 1.913457798521976e-07, 'epoch': 1.43} + 9%|▉ | 5540/61904 [2:39:59<21:16:20, 1.36s/it] 9%|▉ | 5541/61904 [2:40:00<20:52:07, 1.33s/it] 9%|▉ | 5542/61904 [2:40:02<21:19:31, 1.36s/it] 9%|▉ | 5543/61904 [2:40:03<20:56:46, 1.34s/it] 9%|▉ | 5544/61904 [2:40:05<20:56:07, 1.34s/it] 9%|▉ | 5545/61904 [2:40:06<20:56:28, 1.34s/it] 9%|▉ | 5546/61904 [2:40:07<21:13:39, 1.36s/it] 9%|▉ | 5547/61904 [2:40:09<21:04:53, 1.35s/it] 9%|▉ | 5548/61904 [2:40:10<21:31:35, 1.38s/it] 9%|▉ | 5549/61904 [2:40:11<21:14:32, 1.36s/it] 9%|▉ | 5550/61904 [2:40:13<21:14:25, 1.36s/it] 9%|▉ | 5551/61904 [2:40:14<20:52:01, 1.33s/it] 9%|▉ | 5552/61904 [2:40:15<21:19:24, 1.36s/it] 9%|▉ | 5553/61904 [2:40:17<20:47:15, 1.33s/it] 9%|▉ | 5554/61904 [2:40:18<20:53:25, 1.33s/it] 9%|▉ | 5555/61904 [2:40:20<22:15:43, 1.42s/it] 9%|▉ | 5556/61904 [2:40:21<21:52:54, 1.40s/it] 9%|▉ | 5557/61904 [2:40:22<21:30:07, 1.37s/it] 9%|▉ | 5558/61904 [2:40:24<21:51:07, 1.40s/it] 9%|▉ | 5559/61904 [2:40:25<21:27:10, 1.37s/it] 9%|▉ | 5560/61904 [2:40:26<21:28:02, 1.37s/it] {'loss': 2.9724, 'learning_rate': 1.9131336704265525e-07, 'epoch': 1.44} + 9%|▉ | 5560/61904 [2:40:26<21:28:02, 1.37s/it] 9%|▉ | 5561/61904 [2:40:28<21:14:31, 1.36s/it] 9%|▉ | 5562/61904 [2:40:29<20:51:53, 1.33s/it] 9%|▉ | 5563/61904 [2:40:30<20:19:57, 1.30s/it] 9%|▉ | 5564/61904 [2:40:32<21:35:31, 1.38s/it] 9%|▉ | 5565/61904 [2:40:33<21:54:31, 1.40s/it] 9%|▉ | 5566/61904 [2:40:35<21:47:19, 1.39s/it] 9%|▉ | 5567/61904 [2:40:36<22:14:07, 1.42s/it] 9%|▉ | 5568/61904 [2:40:38<22:04:46, 1.41s/it] 9%|▉ | 5569/61904 [2:40:39<21:37:10, 1.38s/it] 9%|▉ | 5570/61904 [2:40:40<21:21:00, 1.36s/it] 9%|▉ | 5571/61904 [2:40:42<21:27:10, 1.37s/it] 9%|▉ | 5572/61904 [2:40:43<21:08:21, 1.35s/it] 9%|▉ | 5573/61904 [2:40:44<21:35:34, 1.38s/it] 9%|▉ | 5574/61904 [2:40:46<21:12:30, 1.36s/it] 9%|▉ | 5575/61904 [2:40:47<20:54:43, 1.34s/it] 9%|▉ | 5576/61904 [2:40:48<21:14:36, 1.36s/it] 9%|▉ | 5577/61904 [2:40:50<21:08:00, 1.35s/it] 9%|▉ | 5578/61904 [2:40:51<22:10:55, 1.42s/it] 9%|▉ | 5579/61904 [2:40:52<21:28:12, 1.37s/it] 9%|▉ | 5580/61904 [2:40:54<21:12:04, 1.36s/it] {'loss': 2.9819, 'learning_rate': 1.912809542331129e-07, 'epoch': 1.44} + 9%|▉ | 5580/61904 [2:40:54<21:12:04, 1.36s/it] 9%|▉ | 5581/61904 [2:40:55<21:28:55, 1.37s/it] 9%|▉ | 5582/61904 [2:40:57<21:23:36, 1.37s/it] 9%|▉ | 5583/61904 [2:40:58<21:00:08, 1.34s/it] 9%|▉ | 5584/61904 [2:40:59<21:06:17, 1.35s/it] 9%|▉ | 5585/61904 [2:41:01<21:00:29, 1.34s/it] 9%|▉ | 5586/61904 [2:41:02<21:28:38, 1.37s/it] 9%|▉ | 5587/61904 [2:41:03<21:16:54, 1.36s/it] 9%|▉ | 5588/61904 [2:41:05<21:27:46, 1.37s/it] 9%|▉ | 5589/61904 [2:41:06<21:31:45, 1.38s/it] 9%|▉ | 5590/61904 [2:41:07<21:30:56, 1.38s/it] 9%|▉ | 5591/61904 [2:41:09<21:35:14, 1.38s/it] 9%|▉ | 5592/61904 [2:41:10<21:52:49, 1.40s/it] 9%|▉ | 5593/61904 [2:41:12<21:43:38, 1.39s/it] 9%|▉ | 5594/61904 [2:41:13<21:30:54, 1.38s/it] 9%|▉ | 5595/61904 [2:41:14<21:20:23, 1.36s/it] 9%|▉ | 5596/61904 [2:41:16<21:12:34, 1.36s/it] 9%|▉ | 5597/61904 [2:41:17<21:08:11, 1.35s/it] 9%|▉ | 5598/61904 [2:41:18<21:20:15, 1.36s/it] 9%|▉ | 5599/61904 [2:41:20<22:35:50, 1.44s/it] 9%|▉ | 5600/61904 [2:41:21<21:58:58, 1.41s/it] {'loss': 2.8861, 'learning_rate': 1.912485414235706e-07, 'epoch': 1.45} + 9%|▉ | 5600/61904 [2:41:21<21:58:58, 1.41s/it] 9%|▉ | 5601/61904 [2:41:23<21:59:43, 1.41s/it] 9%|▉ | 5602/61904 [2:41:24<21:36:19, 1.38s/it] 9%|▉ | 5603/61904 [2:41:26<21:51:48, 1.40s/it] 9%|▉ | 5604/61904 [2:41:27<21:16:01, 1.36s/it] 9%|▉ | 5605/61904 [2:41:28<21:07:42, 1.35s/it] 9%|▉ | 5606/61904 [2:41:30<21:53:01, 1.40s/it] 9%|▉ | 5607/61904 [2:41:31<21:17:32, 1.36s/it] 9%|▉ | 5608/61904 [2:41:33<22:33:52, 1.44s/it] 9%|▉ | 5609/61904 [2:41:34<21:39:21, 1.38s/it] 9%|▉ | 5610/61904 [2:41:35<21:34:26, 1.38s/it] 9%|▉ | 5611/61904 [2:41:37<22:00:46, 1.41s/it] 9%|▉ | 5612/61904 [2:41:38<22:12:31, 1.42s/it] 9%|▉ | 5613/61904 [2:41:39<21:10:04, 1.35s/it] 9%|▉ | 5614/61904 [2:41:41<21:47:16, 1.39s/it] 9%|▉ | 5615/61904 [2:41:42<22:08:04, 1.42s/it] 9%|▉ | 5616/61904 [2:41:44<22:33:25, 1.44s/it] 9%|▉ | 5617/61904 [2:41:45<22:50:15, 1.46s/it] 9%|▉ | 5618/61904 [2:41:47<22:35:54, 1.45s/it] 9%|▉ | 5619/61904 [2:41:48<21:16:49, 1.36s/it] 9%|▉ | 5620/61904 [2:41:49<22:00:24, 1.41s/it] {'loss': 2.9408, 'learning_rate': 1.9121612861402824e-07, 'epoch': 1.45} + 9%|▉ | 5620/61904 [2:41:49<22:00:24, 1.41s/it] 9%|▉ | 5621/61904 [2:41:51<21:44:34, 1.39s/it] 9%|▉ | 5622/61904 [2:41:52<21:51:10, 1.40s/it] 9%|▉ | 5623/61904 [2:41:54<22:12:05, 1.42s/it] 9%|▉ | 5624/61904 [2:41:55<21:45:00, 1.39s/it] 9%|▉ | 5625/61904 [2:41:56<21:15:53, 1.36s/it] 9%|▉ | 5626/61904 [2:41:58<21:12:22, 1.36s/it] 9%|▉ | 5627/61904 [2:41:59<20:27:03, 1.31s/it] 9%|▉ | 5628/61904 [2:42:00<20:41:20, 1.32s/it] 9%|▉ | 5629/61904 [2:42:01<20:58:09, 1.34s/it] 9%|▉ | 5630/61904 [2:42:03<21:43:40, 1.39s/it] 9%|▉ | 5631/61904 [2:42:04<20:53:00, 1.34s/it] 9%|▉ | 5632/61904 [2:42:06<20:59:06, 1.34s/it] 9%|▉ | 5633/61904 [2:42:07<21:05:39, 1.35s/it] 9%|▉ | 5634/61904 [2:42:08<20:46:33, 1.33s/it] 9%|▉ | 5635/61904 [2:42:09<20:34:11, 1.32s/it] 9%|▉ | 5636/61904 [2:42:11<19:48:23, 1.27s/it] 9%|▉ | 5637/61904 [2:42:12<20:30:09, 1.31s/it] 9%|▉ | 5638/61904 [2:42:13<20:33:13, 1.32s/it] 9%|▉ | 5639/61904 [2:42:15<21:22:46, 1.37s/it] 9%|▉ | 5640/61904 [2:42:16<21:42:57, 1.39s/it] {'loss': 3.0236, 'learning_rate': 1.9118371580448592e-07, 'epoch': 1.46} + 9%|▉ | 5640/61904 [2:42:16<21:42:57, 1.39s/it] 9%|▉ | 5641/61904 [2:42:18<21:52:24, 1.40s/it] 9%|▉ | 5642/61904 [2:42:19<21:25:24, 1.37s/it] 9%|▉ | 5643/61904 [2:42:20<20:57:02, 1.34s/it] 9%|▉ | 5644/61904 [2:42:22<21:48:48, 1.40s/it] 9%|▉ | 5645/61904 [2:42:23<21:41:58, 1.39s/it] 9%|▉ | 5646/61904 [2:42:25<21:42:40, 1.39s/it] 9%|▉ | 5647/61904 [2:42:26<21:03:21, 1.35s/it] 9%|▉ | 5648/61904 [2:42:27<21:14:22, 1.36s/it] 9%|▉ | 5649/61904 [2:42:28<20:39:09, 1.32s/it] 9%|▉ | 5650/61904 [2:42:30<20:26:15, 1.31s/it] 9%|▉ | 5651/61904 [2:42:31<20:11:04, 1.29s/it] 9%|▉ | 5652/61904 [2:42:32<20:18:03, 1.30s/it] 9%|▉ | 5653/61904 [2:42:34<19:53:35, 1.27s/it] 9%|▉ | 5654/61904 [2:42:35<20:55:43, 1.34s/it] 9%|▉ | 5655/61904 [2:42:36<20:27:38, 1.31s/it] 9%|▉ | 5656/61904 [2:42:37<20:14:25, 1.30s/it] 9%|▉ | 5657/61904 [2:42:39<20:05:05, 1.29s/it] 9%|▉ | 5658/61904 [2:42:40<20:26:23, 1.31s/it] 9%|▉ | 5659/61904 [2:42:42<21:19:38, 1.37s/it] 9%|▉ | 5660/61904 [2:42:43<20:36:32, 1.32s/it] {'loss': 2.9481, 'learning_rate': 1.911513029949436e-07, 'epoch': 1.46} + 9%|▉ | 5660/61904 [2:42:43<20:36:32, 1.32s/it] 9%|▉ | 5661/61904 [2:42:44<21:43:28, 1.39s/it] 9%|▉ | 5662/61904 [2:42:46<21:45:03, 1.39s/it] 9%|▉ | 5663/61904 [2:42:47<21:30:28, 1.38s/it] 9%|▉ | 5664/61904 [2:42:48<20:56:13, 1.34s/it] 9%|▉ | 5665/61904 [2:42:50<20:36:30, 1.32s/it] 9%|▉ | 5666/61904 [2:42:51<21:03:15, 1.35s/it] 9%|▉ | 5667/61904 [2:42:53<21:35:36, 1.38s/it] 9%|▉ | 5668/61904 [2:42:54<21:37:41, 1.38s/it] 9%|▉ | 5669/61904 [2:42:55<21:41:04, 1.39s/it] 9%|▉ | 5670/61904 [2:42:57<21:07:31, 1.35s/it] 9%|▉ | 5671/61904 [2:42:58<20:58:19, 1.34s/it] 9%|▉ | 5672/61904 [2:42:59<20:14:14, 1.30s/it] 9%|▉ | 5673/61904 [2:43:00<20:31:52, 1.31s/it] 9%|▉ | 5674/61904 [2:43:02<21:16:24, 1.36s/it] 9%|▉ | 5675/61904 [2:43:03<21:26:31, 1.37s/it] 9%|▉ | 5676/61904 [2:43:05<20:47:25, 1.33s/it] 9%|▉ | 5677/61904 [2:43:06<20:54:40, 1.34s/it] 9%|▉ | 5678/61904 [2:43:07<20:41:12, 1.32s/it] 9%|▉ | 5679/61904 [2:43:09<20:52:39, 1.34s/it] 9%|▉ | 5680/61904 [2:43:10<20:58:39, 1.34s/it] {'loss': 2.9892, 'learning_rate': 1.9111889018540125e-07, 'epoch': 1.47} + 9%|▉ | 5680/61904 [2:43:10<20:58:39, 1.34s/it] 9%|▉ | 5681/61904 [2:43:11<20:33:07, 1.32s/it] 9%|▉ | 5682/61904 [2:43:13<21:03:34, 1.35s/it] 9%|▉ | 5683/61904 [2:43:14<20:42:24, 1.33s/it] 9%|▉ | 5684/61904 [2:43:15<21:29:04, 1.38s/it] 9%|▉ | 5685/61904 [2:43:17<21:24:05, 1.37s/it] 9%|▉ | 5686/61904 [2:43:18<21:08:56, 1.35s/it] 9%|▉ | 5687/61904 [2:43:19<21:04:59, 1.35s/it] 9%|▉ | 5688/61904 [2:43:21<21:36:42, 1.38s/it] 9%|▉ | 5689/61904 [2:43:22<21:35:50, 1.38s/it] 9%|▉ | 5690/61904 [2:43:24<21:17:54, 1.36s/it] 9%|▉ | 5691/61904 [2:43:25<20:56:17, 1.34s/it] 9%|▉ | 5692/61904 [2:43:26<21:30:57, 1.38s/it] 9%|▉ | 5693/61904 [2:43:28<21:57:09, 1.41s/it] 9%|▉ | 5694/61904 [2:43:29<21:34:21, 1.38s/it] 9%|▉ | 5695/61904 [2:43:30<21:16:09, 1.36s/it] 9%|▉ | 5696/61904 [2:43:32<20:50:04, 1.33s/it] 9%|▉ | 5697/61904 [2:43:33<21:01:09, 1.35s/it] 9%|▉ | 5698/61904 [2:43:34<20:38:10, 1.32s/it] 9%|▉ | 5699/61904 [2:43:36<21:00:41, 1.35s/it] 9%|▉ | 5700/61904 [2:43:37<21:11:25, 1.36s/it] {'loss': 2.9723, 'learning_rate': 1.9108647737585894e-07, 'epoch': 1.47} + 9%|▉ | 5700/61904 [2:43:37<21:11:25, 1.36s/it] 9%|▉ | 5701/61904 [2:43:39<21:23:51, 1.37s/it] 9%|▉ | 5702/61904 [2:43:40<21:40:56, 1.39s/it] 9%|▉ | 5703/61904 [2:43:41<21:24:20, 1.37s/it] 9%|▉ | 5704/61904 [2:43:43<21:20:58, 1.37s/it] 9%|▉ | 5705/61904 [2:43:44<21:40:49, 1.39s/it] 9%|▉ | 5706/61904 [2:43:45<21:23:58, 1.37s/it] 9%|▉ | 5707/61904 [2:43:47<21:09:09, 1.36s/it] 9%|▉ | 5708/61904 [2:43:48<22:07:09, 1.42s/it] 9%|▉ | 5709/61904 [2:43:50<22:04:54, 1.41s/it] 9%|▉ | 5710/61904 [2:43:51<21:45:05, 1.39s/it] 9%|▉ | 5711/61904 [2:43:52<21:36:11, 1.38s/it] 9%|▉ | 5712/61904 [2:43:54<21:44:57, 1.39s/it] 9%|▉ | 5713/61904 [2:43:55<21:32:05, 1.38s/it] 9%|▉ | 5714/61904 [2:43:57<21:39:13, 1.39s/it] 9%|▉ | 5715/61904 [2:43:58<22:04:13, 1.41s/it] 9%|▉ | 5716/61904 [2:43:59<21:35:02, 1.38s/it] 9%|▉ | 5717/61904 [2:44:01<22:01:35, 1.41s/it] 9%|▉ | 5718/61904 [2:44:02<21:39:55, 1.39s/it] 9%|▉ | 5719/61904 [2:44:04<21:30:24, 1.38s/it] 9%|▉ | 5720/61904 [2:44:05<21:59:44, 1.41s/it] {'loss': 2.8791, 'learning_rate': 1.910540645663166e-07, 'epoch': 1.48} + 9%|▉ | 5720/61904 [2:44:05<21:59:44, 1.41s/it] 9%|▉ | 5721/61904 [2:44:06<21:36:42, 1.38s/it] 9%|▉ | 5722/61904 [2:44:08<21:18:19, 1.37s/it] 9%|▉ | 5723/61904 [2:44:09<22:08:22, 1.42s/it] 9%|▉ | 5724/61904 [2:44:11<22:05:20, 1.42s/it] 9%|▉ | 5725/61904 [2:44:12<21:27:23, 1.37s/it] 9%|▉ | 5726/61904 [2:44:13<21:24:33, 1.37s/it] 9%|▉ | 5727/61904 [2:44:14<20:53:37, 1.34s/it] 9%|▉ | 5728/61904 [2:44:16<21:28:15, 1.38s/it] 9%|▉ | 5729/61904 [2:44:18<22:37:35, 1.45s/it] 9%|▉ | 5730/61904 [2:44:19<22:31:05, 1.44s/it] 9%|▉ | 5731/61904 [2:44:20<21:56:28, 1.41s/it] 9%|▉ | 5732/61904 [2:44:22<21:33:10, 1.38s/it] 9%|▉ | 5733/61904 [2:44:23<21:42:32, 1.39s/it] 9%|▉ | 5734/61904 [2:44:24<20:50:48, 1.34s/it] 9%|▉ | 5735/61904 [2:44:26<21:12:50, 1.36s/it] 9%|▉ | 5736/61904 [2:44:27<21:26:20, 1.37s/it] 9%|▉ | 5737/61904 [2:44:28<21:15:20, 1.36s/it] 9%|▉ | 5738/61904 [2:44:30<20:38:10, 1.32s/it] 9%|▉ | 5739/61904 [2:44:31<20:36:47, 1.32s/it] 9%|▉ | 5740/61904 [2:44:32<20:31:42, 1.32s/it] {'loss': 2.9381, 'learning_rate': 1.9102165175677426e-07, 'epoch': 1.48} + 9%|▉ | 5740/61904 [2:44:32<20:31:42, 1.32s/it] 9%|▉ | 5741/61904 [2:44:34<20:29:41, 1.31s/it] 9%|▉ | 5742/61904 [2:44:35<20:46:00, 1.33s/it] 9%|▉ | 5743/61904 [2:44:36<20:52:56, 1.34s/it] 9%|▉ | 5744/61904 [2:44:38<21:16:07, 1.36s/it] 9%|▉ | 5745/61904 [2:44:39<20:45:11, 1.33s/it] 9%|▉ | 5746/61904 [2:44:40<20:51:56, 1.34s/it] 9%|▉ | 5747/61904 [2:44:42<20:51:54, 1.34s/it] 9%|▉ | 5748/61904 [2:44:43<21:41:10, 1.39s/it] 9%|▉ | 5749/61904 [2:44:45<21:16:56, 1.36s/it] 9%|▉ | 5750/61904 [2:44:46<21:10:46, 1.36s/it] 9%|▉ | 5751/61904 [2:44:47<20:49:41, 1.34s/it] 9%|▉ | 5752/61904 [2:44:48<20:56:15, 1.34s/it] 9%|▉ | 5753/61904 [2:44:50<21:37:30, 1.39s/it] 9%|▉ | 5754/61904 [2:44:51<21:44:27, 1.39s/it] 9%|▉ | 5755/61904 [2:44:53<21:09:40, 1.36s/it] 9%|▉ | 5756/61904 [2:44:54<21:05:52, 1.35s/it] 9%|▉ | 5757/61904 [2:44:56<21:59:04, 1.41s/it] 9%|▉ | 5758/61904 [2:44:57<21:43:33, 1.39s/it] 9%|▉ | 5759/61904 [2:44:58<21:57:05, 1.41s/it] 9%|▉ | 5760/61904 [2:45:00<21:19:46, 1.37s/it] {'loss': 2.8873, 'learning_rate': 1.9098923894723195e-07, 'epoch': 1.49} + 9%|▉ | 5760/61904 [2:45:00<21:19:46, 1.37s/it] 9%|▉ | 5761/61904 [2:45:01<21:09:38, 1.36s/it] 9%|▉ | 5762/61904 [2:45:02<20:57:10, 1.34s/it] 9%|▉ | 5763/61904 [2:45:04<20:47:20, 1.33s/it] 9%|▉ | 5764/61904 [2:45:05<20:33:39, 1.32s/it] 9%|▉ | 5765/61904 [2:45:06<20:55:07, 1.34s/it] 9%|▉ | 5766/61904 [2:45:08<20:57:26, 1.34s/it] 9%|▉ | 5767/61904 [2:45:09<21:33:33, 1.38s/it] 9%|▉ | 5768/61904 [2:45:10<21:15:37, 1.36s/it] 9%|▉ | 5769/61904 [2:45:12<21:39:31, 1.39s/it] 9%|▉ | 5770/61904 [2:45:13<21:17:53, 1.37s/it] 9%|▉ | 5771/61904 [2:45:15<21:48:45, 1.40s/it] 9%|▉ | 5772/61904 [2:45:16<22:13:47, 1.43s/it] 9%|▉ | 5773/61904 [2:45:18<22:57:00, 1.47s/it] 9%|▉ | 5774/61904 [2:45:19<21:51:27, 1.40s/it] 9%|▉ | 5775/61904 [2:45:20<21:39:22, 1.39s/it] 9%|▉ | 5776/61904 [2:45:22<21:08:41, 1.36s/it] 9%|▉ | 5777/61904 [2:45:23<20:53:18, 1.34s/it] 9%|▉ | 5778/61904 [2:45:24<20:38:33, 1.32s/it] 9%|▉ | 5779/61904 [2:45:26<21:26:16, 1.38s/it] 9%|▉ | 5780/61904 [2:45:27<21:10:52, 1.36s/it] {'loss': 2.8586, 'learning_rate': 1.909568261376896e-07, 'epoch': 1.49} + 9%|▉ | 5780/61904 [2:45:27<21:10:52, 1.36s/it] 9%|▉ | 5781/61904 [2:45:29<22:02:45, 1.41s/it] 9%|▉ | 5782/61904 [2:45:30<22:42:30, 1.46s/it] 9%|▉ | 5783/61904 [2:45:32<22:59:15, 1.47s/it] 9%|▉ | 5784/61904 [2:45:33<22:34:00, 1.45s/it] 9%|▉ | 5785/61904 [2:45:34<21:54:50, 1.41s/it] 9%|▉ | 5786/61904 [2:45:36<22:18:39, 1.43s/it] 9%|▉ | 5787/61904 [2:45:37<21:52:08, 1.40s/it] 9%|▉ | 5788/61904 [2:45:38<21:48:27, 1.40s/it] 9%|▉ | 5789/61904 [2:45:40<21:01:18, 1.35s/it] 9%|▉ | 5790/61904 [2:45:41<20:26:19, 1.31s/it] 9%|▉ | 5791/61904 [2:45:42<20:53:31, 1.34s/it] 9%|▉ | 5792/61904 [2:45:44<20:06:12, 1.29s/it] 9%|▉ | 5793/61904 [2:45:45<20:48:59, 1.34s/it] 9%|▉ | 5794/61904 [2:45:46<21:16:14, 1.36s/it] 9%|▉ | 5795/61904 [2:45:48<21:22:59, 1.37s/it] 9%|▉ | 5796/61904 [2:45:49<21:08:22, 1.36s/it] 9%|▉ | 5797/61904 [2:45:50<20:29:16, 1.31s/it] 9%|▉ | 5798/61904 [2:45:52<20:15:45, 1.30s/it] 9%|▉ | 5799/61904 [2:45:53<20:41:04, 1.33s/it] 9%|▉ | 5800/61904 [2:45:54<20:20:32, 1.31s/it] {'loss': 2.9308, 'learning_rate': 1.9092441332814727e-07, 'epoch': 1.5} + 9%|▉ | 5800/61904 [2:45:54<20:20:32, 1.31s/it] 9%|▉ | 5801/61904 [2:45:56<21:14:59, 1.36s/it] 9%|▉ | 5802/61904 [2:45:57<20:53:49, 1.34s/it] 9%|▉ | 5803/61904 [2:45:58<20:56:20, 1.34s/it] 9%|▉ | 5804/61904 [2:46:00<21:27:34, 1.38s/it] 9%|▉ | 5805/61904 [2:46:01<21:08:21, 1.36s/it] 9%|▉ | 5806/61904 [2:46:03<21:16:33, 1.37s/it] 9%|▉ | 5807/61904 [2:46:04<21:22:26, 1.37s/it] 9%|▉ | 5808/61904 [2:46:05<21:23:45, 1.37s/it] 9%|▉ | 5809/61904 [2:46:07<21:19:48, 1.37s/it] 9%|▉ | 5810/61904 [2:46:08<22:01:06, 1.41s/it] 9%|▉ | 5811/61904 [2:46:10<22:15:49, 1.43s/it] 9%|▉ | 5812/61904 [2:46:11<21:39:13, 1.39s/it] 9%|▉ | 5813/61904 [2:46:12<21:33:30, 1.38s/it] 9%|▉ | 5814/61904 [2:46:14<21:59:52, 1.41s/it] 9%|▉ | 5815/61904 [2:46:15<21:55:55, 1.41s/it] 9%|▉ | 5816/61904 [2:46:17<21:46:23, 1.40s/it] 9%|▉ | 5817/61904 [2:46:18<21:13:11, 1.36s/it] 9%|▉ | 5818/61904 [2:46:19<21:21:45, 1.37s/it] 9%|▉ | 5819/61904 [2:46:20<20:30:31, 1.32s/it] 9%|▉ | 5820/61904 [2:46:22<21:31:22, 1.38s/it] {'loss': 2.9222, 'learning_rate': 1.9089200051860496e-07, 'epoch': 1.5} + 9%|▉ | 5820/61904 [2:46:22<21:31:22, 1.38s/it] 9%|▉ | 5821/61904 [2:46:23<20:43:50, 1.33s/it] 9%|▉ | 5822/61904 [2:46:24<20:39:04, 1.33s/it] 9%|▉ | 5823/61904 [2:46:26<20:14:47, 1.30s/it] 9%|▉ | 5824/61904 [2:46:27<20:31:41, 1.32s/it] 9%|▉ | 5825/61904 [2:46:28<20:50:17, 1.34s/it] 9%|▉ | 5826/61904 [2:46:30<20:51:30, 1.34s/it] 9%|▉ | 5827/61904 [2:46:31<20:48:29, 1.34s/it] 9%|▉ | 5828/61904 [2:46:32<20:35:57, 1.32s/it] 9%|▉ | 5829/61904 [2:46:34<20:35:53, 1.32s/it] 9%|▉ | 5830/61904 [2:46:35<20:43:40, 1.33s/it] 9%|▉ | 5831/61904 [2:46:36<20:34:35, 1.32s/it] 9%|▉ | 5832/61904 [2:46:38<21:25:41, 1.38s/it] 9%|▉ | 5833/61904 [2:46:39<20:24:59, 1.31s/it] 9%|▉ | 5834/61904 [2:46:40<20:32:43, 1.32s/it] 9%|▉ | 5835/61904 [2:46:42<20:17:23, 1.30s/it] 9%|▉ | 5836/61904 [2:46:43<20:21:22, 1.31s/it] 9%|▉ | 5837/61904 [2:46:45<21:48:48, 1.40s/it] 9%|▉ | 5838/61904 [2:46:46<21:57:12, 1.41s/it] 9%|▉ | 5839/61904 [2:46:47<21:38:03, 1.39s/it] 9%|▉ | 5840/61904 [2:46:49<21:19:56, 1.37s/it] {'loss': 2.9787, 'learning_rate': 1.908595877090626e-07, 'epoch': 1.51} + 9%|▉ | 5840/61904 [2:46:49<21:19:56, 1.37s/it] 9%|▉ | 5841/61904 [2:46:50<21:08:10, 1.36s/it] 9%|▉ | 5842/61904 [2:46:51<21:22:22, 1.37s/it] 9%|▉ | 5843/61904 [2:46:53<21:03:15, 1.35s/it] 9%|▉ | 5844/61904 [2:46:54<21:15:53, 1.37s/it] 9%|▉ | 5845/61904 [2:46:56<21:25:58, 1.38s/it] 9%|▉ | 5846/61904 [2:46:57<21:41:12, 1.39s/it] 9%|▉ | 5847/61904 [2:46:58<21:06:41, 1.36s/it] 9%|▉ | 5848/61904 [2:47:00<21:18:03, 1.37s/it] 9%|▉ | 5849/61904 [2:47:01<21:07:15, 1.36s/it] 9%|▉ | 5850/61904 [2:47:02<20:34:41, 1.32s/it] 9%|▉ | 5851/61904 [2:47:04<20:57:35, 1.35s/it] 9%|▉ | 5852/61904 [2:47:05<20:39:38, 1.33s/it] 9%|▉ | 5853/61904 [2:47:06<20:57:46, 1.35s/it] 9%|▉ | 5854/61904 [2:47:08<20:38:57, 1.33s/it] 9%|▉ | 5855/61904 [2:47:09<20:38:27, 1.33s/it] 9%|▉ | 5856/61904 [2:47:10<20:51:14, 1.34s/it] 9%|▉ | 5857/61904 [2:47:12<20:44:33, 1.33s/it] 9%|▉ | 5858/61904 [2:47:13<20:52:49, 1.34s/it] 9%|▉ | 5859/61904 [2:47:14<20:41:18, 1.33s/it] 9%|▉ | 5860/61904 [2:47:16<20:35:21, 1.32s/it] {'loss': 2.9207, 'learning_rate': 1.9082717489952028e-07, 'epoch': 1.51} + 9%|▉ | 5860/61904 [2:47:16<20:35:21, 1.32s/it] 9%|▉ | 5861/61904 [2:47:17<20:41:13, 1.33s/it] 9%|▉ | 5862/61904 [2:47:18<20:19:39, 1.31s/it] 9%|▉ | 5863/61904 [2:47:20<20:47:00, 1.34s/it] 9%|▉ | 5864/61904 [2:47:21<20:41:38, 1.33s/it] 9%|▉ | 5865/61904 [2:47:22<21:35:15, 1.39s/it] 9%|▉ | 5866/61904 [2:47:24<21:11:43, 1.36s/it] 9%|▉ | 5867/61904 [2:47:25<21:14:11, 1.36s/it] 9%|▉ | 5868/61904 [2:47:26<21:08:10, 1.36s/it] 9%|▉ | 5869/61904 [2:47:28<21:40:06, 1.39s/it] 9%|▉ | 5870/61904 [2:47:29<21:28:23, 1.38s/it] 9%|▉ | 5871/61904 [2:47:31<21:53:24, 1.41s/it] 9%|▉ | 5872/61904 [2:47:32<22:03:44, 1.42s/it] 9%|▉ | 5873/61904 [2:47:34<22:08:05, 1.42s/it] 9%|▉ | 5874/61904 [2:47:35<22:25:58, 1.44s/it] 9%|▉ | 5875/61904 [2:47:36<22:12:48, 1.43s/it] 9%|▉ | 5876/61904 [2:47:38<21:45:45, 1.40s/it] 9%|▉ | 5877/61904 [2:47:39<21:59:04, 1.41s/it] 9%|▉ | 5878/61904 [2:47:41<22:10:04, 1.42s/it] 9%|▉ | 5879/61904 [2:47:42<21:28:52, 1.38s/it] 9%|▉ | 5880/61904 [2:47:43<21:50:28, 1.40s/it] {'loss': 2.9304, 'learning_rate': 1.9079476208997797e-07, 'epoch': 1.52} + 9%|▉ | 5880/61904 [2:47:43<21:50:28, 1.40s/it] 10%|▉ | 5881/61904 [2:47:45<21:06:19, 1.36s/it] 10%|▉ | 5882/61904 [2:47:46<20:34:06, 1.32s/it] 10%|▉ | 5883/61904 [2:47:47<20:46:05, 1.33s/it] 10%|▉ | 5884/61904 [2:47:49<20:46:33, 1.34s/it] 10%|▉ | 5885/61904 [2:47:50<20:40:52, 1.33s/it] 10%|▉ | 5886/61904 [2:47:51<20:48:04, 1.34s/it] 10%|▉ | 5887/61904 [2:47:53<20:47:57, 1.34s/it] 10%|▉ | 5888/61904 [2:47:54<20:44:34, 1.33s/it] 10%|▉ | 5889/61904 [2:47:55<20:30:32, 1.32s/it] 10%|▉ | 5890/61904 [2:47:57<21:07:20, 1.36s/it] 10%|▉ | 5891/61904 [2:47:58<21:25:35, 1.38s/it] 10%|▉ | 5892/61904 [2:48:00<22:08:05, 1.42s/it] 10%|▉ | 5893/61904 [2:48:01<22:24:14, 1.44s/it] 10%|▉ | 5894/61904 [2:48:02<21:50:55, 1.40s/it] 10%|▉ | 5895/61904 [2:48:04<21:27:54, 1.38s/it] 10%|▉ | 5896/61904 [2:48:05<22:09:31, 1.42s/it] 10%|▉ | 5897/61904 [2:48:07<22:44:07, 1.46s/it] 10%|▉ | 5898/61904 [2:48:08<22:23:40, 1.44s/it] 10%|▉ | 5899/61904 [2:48:09<21:46:45, 1.40s/it] 10%|▉ | 5900/61904 [2:48:11<21:26:43, 1.38s/it] {'loss': 2.942, 'learning_rate': 1.907623492804356e-07, 'epoch': 1.52} + 10%|▉ | 5900/61904 [2:48:11<21:26:43, 1.38s/it] 10%|▉ | 5901/61904 [2:48:12<21:07:34, 1.36s/it] 10%|▉ | 5902/61904 [2:48:14<21:33:41, 1.39s/it] 10%|▉ | 5903/61904 [2:48:15<22:01:35, 1.42s/it] 10%|▉ | 5904/61904 [2:48:17<22:34:13, 1.45s/it] 10%|▉ | 5905/61904 [2:48:18<21:35:51, 1.39s/it] 10%|▉ | 5906/61904 [2:48:19<21:50:56, 1.40s/it] 10%|▉ | 5907/61904 [2:48:21<21:43:55, 1.40s/it] 10%|▉ | 5908/61904 [2:48:22<21:23:40, 1.38s/it] 10%|▉ | 5909/61904 [2:48:23<20:45:17, 1.33s/it] 10%|▉ | 5910/61904 [2:48:24<20:23:58, 1.31s/it] 10%|▉ | 5911/61904 [2:48:26<20:51:34, 1.34s/it] 10%|▉ | 5912/61904 [2:48:27<20:32:00, 1.32s/it] 10%|▉ | 5913/61904 [2:48:28<20:33:09, 1.32s/it] 10%|▉ | 5914/61904 [2:48:30<20:42:23, 1.33s/it] 10%|▉ | 5915/61904 [2:48:31<20:09:08, 1.30s/it] 10%|▉ | 5916/61904 [2:48:32<20:05:22, 1.29s/it] 10%|▉ | 5917/61904 [2:48:34<20:29:36, 1.32s/it] 10%|▉ | 5918/61904 [2:48:35<20:32:33, 1.32s/it] 10%|▉ | 5919/61904 [2:48:36<20:49:33, 1.34s/it] 10%|▉ | 5920/61904 [2:48:38<20:38:07, 1.33s/it] {'loss': 2.9672, 'learning_rate': 1.907299364708933e-07, 'epoch': 1.53} + 10%|▉ | 5920/61904 [2:48:38<20:38:07, 1.33s/it] 10%|▉ | 5921/61904 [2:48:39<20:48:35, 1.34s/it] 10%|▉ | 5922/61904 [2:48:40<20:22:03, 1.31s/it] 10%|▉ | 5923/61904 [2:48:42<19:52:41, 1.28s/it] 10%|▉ | 5924/61904 [2:48:43<20:14:53, 1.30s/it] 10%|▉ | 5925/61904 [2:48:44<20:30:17, 1.32s/it] 10%|▉ | 5926/61904 [2:48:46<21:36:29, 1.39s/it] 10%|▉ | 5927/61904 [2:48:47<21:31:23, 1.38s/it] 10%|▉ | 5928/61904 [2:48:49<21:59:06, 1.41s/it] 10%|▉ | 5929/61904 [2:48:50<22:12:40, 1.43s/it] 10%|▉ | 5930/61904 [2:48:51<21:39:31, 1.39s/it] 10%|▉ | 5931/61904 [2:48:53<21:33:24, 1.39s/it] 10%|▉ | 5932/61904 [2:48:54<21:33:07, 1.39s/it] 10%|▉ | 5933/61904 [2:48:55<21:02:04, 1.35s/it] 10%|▉ | 5934/61904 [2:48:57<21:33:46, 1.39s/it] 10%|▉ | 5935/61904 [2:48:58<21:43:13, 1.40s/it] 10%|▉ | 5936/61904 [2:49:00<20:53:40, 1.34s/it] 10%|▉ | 5937/61904 [2:49:01<21:15:22, 1.37s/it] 10%|▉ | 5938/61904 [2:49:02<21:26:23, 1.38s/it] 10%|▉ | 5939/61904 [2:49:04<20:47:15, 1.34s/it] 10%|▉ | 5940/61904 [2:49:05<21:03:44, 1.35s/it] {'loss': 2.9461, 'learning_rate': 1.9069752366135096e-07, 'epoch': 1.54} + 10%|▉ | 5940/61904 [2:49:05<21:03:44, 1.35s/it] 10%|▉ | 5941/61904 [2:49:06<20:57:24, 1.35s/it] 10%|▉ | 5942/61904 [2:49:08<20:57:58, 1.35s/it] 10%|▉ | 5943/61904 [2:49:09<20:43:02, 1.33s/it] 10%|▉ | 5944/61904 [2:49:10<20:14:58, 1.30s/it] 10%|▉ | 5945/61904 [2:49:12<20:25:04, 1.31s/it] 10%|▉ | 5946/61904 [2:49:13<20:46:31, 1.34s/it] 10%|▉ | 5947/61904 [2:49:14<20:16:53, 1.30s/it] 10%|▉ | 5948/61904 [2:49:16<20:16:53, 1.30s/it] 10%|▉ | 5949/61904 [2:49:17<20:37:52, 1.33s/it] 10%|▉ | 5950/61904 [2:49:18<21:28:24, 1.38s/it] 10%|▉ | 5951/61904 [2:49:20<20:53:45, 1.34s/it] 10%|▉ | 5952/61904 [2:49:21<22:03:29, 1.42s/it] 10%|▉ | 5953/61904 [2:49:23<22:24:11, 1.44s/it] 10%|▉ | 5954/61904 [2:49:24<21:32:22, 1.39s/it] 10%|▉ | 5955/61904 [2:49:25<21:12:29, 1.36s/it] 10%|▉ | 5956/61904 [2:49:27<21:19:35, 1.37s/it] 10%|▉ | 5957/61904 [2:49:28<21:34:27, 1.39s/it] 10%|▉ | 5958/61904 [2:49:29<21:24:11, 1.38s/it] 10%|▉ | 5959/61904 [2:49:31<21:26:11, 1.38s/it] 10%|▉ | 5960/61904 [2:49:32<21:37:58, 1.39s/it] {'loss': 2.9206, 'learning_rate': 1.9066511085180862e-07, 'epoch': 1.54} + 10%|▉ | 5960/61904 [2:49:32<21:37:58, 1.39s/it] 10%|▉ | 5961/61904 [2:49:34<21:44:36, 1.40s/it] 10%|▉ | 5962/61904 [2:49:35<21:37:47, 1.39s/it] 10%|▉ | 5963/61904 [2:49:36<21:23:15, 1.38s/it] 10%|▉ | 5964/61904 [2:49:38<21:17:45, 1.37s/it] 10%|▉ | 5965/61904 [2:49:39<21:25:10, 1.38s/it] 10%|▉ | 5966/61904 [2:49:41<21:46:28, 1.40s/it] 10%|▉ | 5967/61904 [2:49:42<21:27:44, 1.38s/it] 10%|▉ | 5968/61904 [2:49:43<21:57:38, 1.41s/it] 10%|▉ | 5969/61904 [2:49:45<21:17:08, 1.37s/it] 10%|▉ | 5970/61904 [2:49:46<21:11:20, 1.36s/it] 10%|▉ | 5971/61904 [2:49:47<20:47:13, 1.34s/it] 10%|▉ | 5972/61904 [2:49:49<20:58:23, 1.35s/it] 10%|▉ | 5973/61904 [2:49:50<21:30:25, 1.38s/it] 10%|▉ | 5974/61904 [2:49:51<21:05:45, 1.36s/it] 10%|▉ | 5975/61904 [2:49:53<21:18:26, 1.37s/it] 10%|▉ | 5976/61904 [2:49:54<21:06:20, 1.36s/it] 10%|▉ | 5977/61904 [2:49:55<20:39:59, 1.33s/it] 10%|▉ | 5978/61904 [2:49:57<20:54:07, 1.35s/it] 10%|▉ | 5979/61904 [2:49:58<21:35:05, 1.39s/it] 10%|▉ | 5980/61904 [2:50:00<21:09:25, 1.36s/it] {'loss': 3.0094, 'learning_rate': 1.906326980422663e-07, 'epoch': 1.55} + 10%|▉ | 5980/61904 [2:50:00<21:09:25, 1.36s/it] 10%|▉ | 5981/61904 [2:50:01<20:47:09, 1.34s/it] 10%|▉ | 5982/61904 [2:50:02<21:17:50, 1.37s/it] 10%|▉ | 5983/61904 [2:50:04<21:14:17, 1.37s/it] 10%|▉ | 5984/61904 [2:50:05<20:25:28, 1.31s/it] 10%|▉ | 5985/61904 [2:50:06<21:10:08, 1.36s/it] 10%|▉ | 5986/61904 [2:50:08<20:57:06, 1.35s/it] 10%|▉ | 5987/61904 [2:50:09<20:59:23, 1.35s/it] 10%|▉ | 5988/61904 [2:50:10<21:04:27, 1.36s/it] 10%|▉ | 5989/61904 [2:50:12<21:29:08, 1.38s/it] 10%|▉ | 5990/61904 [2:50:13<21:08:14, 1.36s/it] 10%|▉ | 5991/61904 [2:50:15<21:02:23, 1.35s/it] 10%|▉ | 5992/61904 [2:50:16<21:11:52, 1.36s/it] 10%|▉ | 5993/61904 [2:50:17<20:55:40, 1.35s/it] 10%|▉ | 5994/61904 [2:50:18<20:27:12, 1.32s/it] 10%|▉ | 5995/61904 [2:50:20<21:07:51, 1.36s/it] 10%|▉ | 5996/61904 [2:50:21<21:28:10, 1.38s/it] 10%|▉ | 5997/61904 [2:50:23<20:49:07, 1.34s/it] 10%|▉ | 5998/61904 [2:50:24<21:15:24, 1.37s/it] 10%|▉ | 5999/61904 [2:50:25<21:05:27, 1.36s/it] 10%|▉ | 6000/61904 [2:50:27<22:06:56, 1.42s/it] {'loss': 2.9333, 'learning_rate': 1.9060028523272397e-07, 'epoch': 1.55} + 10%|▉ | 6000/61904 [2:50:27<22:06:56, 1.42s/it] 10%|▉ | 6001/61904 [2:50:28<21:35:17, 1.39s/it] 10%|▉ | 6002/61904 [2:50:30<21:16:48, 1.37s/it] 10%|▉ | 6003/61904 [2:50:31<21:03:39, 1.36s/it] 10%|▉ | 6004/61904 [2:50:32<20:53:57, 1.35s/it] 10%|▉ | 6005/61904 [2:50:34<21:35:09, 1.39s/it] 10%|▉ | 6006/61904 [2:50:35<21:08:01, 1.36s/it] 10%|▉ | 6007/61904 [2:50:36<21:21:38, 1.38s/it] 10%|▉ | 6008/61904 [2:50:38<22:07:06, 1.42s/it] 10%|▉ | 6009/61904 [2:50:39<21:42:53, 1.40s/it] 10%|▉ | 6010/61904 [2:50:41<21:34:14, 1.39s/it] 10%|▉ | 6011/61904 [2:50:42<21:27:38, 1.38s/it] 10%|▉ | 6012/61904 [2:50:43<21:27:30, 1.38s/it] 10%|▉ | 6013/61904 [2:50:45<20:37:56, 1.33s/it] 10%|▉ | 6014/61904 [2:50:46<20:54:37, 1.35s/it] 10%|▉ | 6015/61904 [2:50:47<20:42:20, 1.33s/it] 10%|▉ | 6016/61904 [2:50:49<20:16:36, 1.31s/it] 10%|▉ | 6017/61904 [2:50:50<20:30:35, 1.32s/it] 10%|▉ | 6018/61904 [2:50:52<21:47:42, 1.40s/it] 10%|▉ | 6019/61904 [2:50:53<22:05:26, 1.42s/it] 10%|▉ | 6020/61904 [2:50:54<21:22:30, 1.38s/it] {'loss': 2.8769, 'learning_rate': 1.9056787242318163e-07, 'epoch': 1.56} + 10%|▉ | 6020/61904 [2:50:54<21:22:30, 1.38s/it] 10%|▉ | 6021/61904 [2:50:56<21:03:54, 1.36s/it] 10%|▉ | 6022/61904 [2:50:57<21:21:22, 1.38s/it] 10%|▉ | 6023/61904 [2:50:58<21:05:26, 1.36s/it] 10%|▉ | 6024/61904 [2:51:00<20:53:31, 1.35s/it] 10%|▉ | 6025/61904 [2:51:01<20:35:27, 1.33s/it] 10%|▉ | 6026/61904 [2:51:02<21:32:45, 1.39s/it] 10%|▉ | 6027/61904 [2:51:04<21:55:30, 1.41s/it] 10%|▉ | 6028/61904 [2:51:05<21:46:25, 1.40s/it] 10%|▉ | 6029/61904 [2:51:07<21:24:04, 1.38s/it] 10%|▉ | 6030/61904 [2:51:08<21:39:02, 1.39s/it] 10%|▉ | 6031/61904 [2:51:09<21:45:01, 1.40s/it] 10%|▉ | 6032/61904 [2:51:11<22:31:21, 1.45s/it] 10%|▉ | 6033/61904 [2:51:12<21:55:38, 1.41s/it] 10%|▉ | 6034/61904 [2:51:14<21:51:17, 1.41s/it] 10%|▉ | 6035/61904 [2:51:15<20:57:13, 1.35s/it] 10%|▉ | 6036/61904 [2:51:16<20:57:55, 1.35s/it] 10%|▉ | 6037/61904 [2:51:18<20:50:35, 1.34s/it] 10%|▉ | 6038/61904 [2:51:19<20:37:23, 1.33s/it] 10%|▉ | 6039/61904 [2:51:20<20:20:06, 1.31s/it] 10%|▉ | 6040/61904 [2:51:22<21:34:37, 1.39s/it] {'loss': 2.8884, 'learning_rate': 1.9053545961363932e-07, 'epoch': 1.56} + 10%|▉ | 6040/61904 [2:51:22<21:34:37, 1.39s/it] 10%|▉ | 6041/61904 [2:51:23<21:25:03, 1.38s/it] 10%|▉ | 6042/61904 [2:51:24<21:10:20, 1.36s/it] 10%|▉ | 6043/61904 [2:51:26<22:06:28, 1.42s/it] 10%|▉ | 6044/61904 [2:51:27<22:07:10, 1.43s/it] 10%|▉ | 6045/61904 [2:51:29<22:36:53, 1.46s/it] 10%|▉ | 6046/61904 [2:51:30<22:11:15, 1.43s/it] 10%|▉ | 6047/61904 [2:51:32<21:56:26, 1.41s/it] 10%|▉ | 6048/61904 [2:51:33<21:53:44, 1.41s/it] 10%|▉ | 6049/61904 [2:51:34<21:12:19, 1.37s/it] 10%|▉ | 6050/61904 [2:51:36<21:36:31, 1.39s/it] 10%|▉ | 6051/61904 [2:51:37<22:37:37, 1.46s/it] 10%|▉ | 6052/61904 [2:51:39<22:08:18, 1.43s/it] 10%|▉ | 6053/61904 [2:51:40<22:09:35, 1.43s/it] 10%|▉ | 6054/61904 [2:51:42<22:18:00, 1.44s/it] 10%|▉ | 6055/61904 [2:51:43<21:53:56, 1.41s/it] 10%|▉ | 6056/61904 [2:51:45<22:12:00, 1.43s/it] 10%|▉ | 6057/61904 [2:51:46<22:12:18, 1.43s/it] 10%|▉ | 6058/61904 [2:51:48<22:45:48, 1.47s/it] 10%|▉ | 6059/61904 [2:51:49<21:51:16, 1.41s/it] 10%|▉ | 6060/61904 [2:51:50<21:19:20, 1.37s/it] {'loss': 2.9742, 'learning_rate': 1.9050304680409696e-07, 'epoch': 1.57} + 10%|▉ | 6060/61904 [2:51:50<21:19:20, 1.37s/it] 10%|▉ | 6061/61904 [2:51:51<21:08:26, 1.36s/it] 10%|▉ | 6062/61904 [2:51:53<21:24:51, 1.38s/it] 10%|▉ | 6063/61904 [2:51:54<21:26:30, 1.38s/it] 10%|▉ | 6064/61904 [2:51:56<22:01:12, 1.42s/it] 10%|▉ | 6065/61904 [2:51:57<21:45:51, 1.40s/it] 10%|▉ | 6066/61904 [2:51:58<21:16:37, 1.37s/it] 10%|▉ | 6067/61904 [2:52:00<21:51:59, 1.41s/it] 10%|▉ | 6068/61904 [2:52:01<21:49:20, 1.41s/it] 10%|▉ | 6069/61904 [2:52:03<21:18:51, 1.37s/it] 10%|▉ | 6070/61904 [2:52:04<21:28:48, 1.38s/it] 10%|▉ | 6071/61904 [2:52:05<21:05:03, 1.36s/it] 10%|▉ | 6072/61904 [2:52:07<21:27:32, 1.38s/it] 10%|▉ | 6073/61904 [2:52:08<20:44:03, 1.34s/it] 10%|▉ | 6074/61904 [2:52:09<21:04:14, 1.36s/it] 10%|▉ | 6075/61904 [2:52:11<20:56:41, 1.35s/it] 10%|▉ | 6076/61904 [2:52:12<20:48:35, 1.34s/it] 10%|▉ | 6077/61904 [2:52:13<21:05:10, 1.36s/it] 10%|▉ | 6078/61904 [2:52:15<20:24:56, 1.32s/it] 10%|▉ | 6079/61904 [2:52:16<20:42:28, 1.34s/it] 10%|▉ | 6080/61904 [2:52:17<20:39:58, 1.33s/it] {'loss': 3.0092, 'learning_rate': 1.9047063399455464e-07, 'epoch': 1.57} + 10%|▉ | 6080/61904 [2:52:17<20:39:58, 1.33s/it] 10%|▉ | 6081/61904 [2:52:19<21:42:55, 1.40s/it] 10%|▉ | 6082/61904 [2:52:20<22:03:07, 1.42s/it] 10%|▉ | 6083/61904 [2:52:22<21:21:37, 1.38s/it] 10%|▉ | 6084/61904 [2:52:23<21:31:49, 1.39s/it] 10%|▉ | 6085/61904 [2:52:24<20:47:04, 1.34s/it] 10%|▉ | 6086/61904 [2:52:26<20:19:41, 1.31s/it] 10%|▉ | 6087/61904 [2:52:27<20:41:24, 1.33s/it] 10%|▉ | 6088/61904 [2:52:28<20:11:46, 1.30s/it] 10%|▉ | 6089/61904 [2:52:30<20:16:49, 1.31s/it] 10%|▉ | 6090/61904 [2:52:31<20:32:00, 1.32s/it] 10%|▉ | 6091/61904 [2:52:32<20:14:53, 1.31s/it] 10%|▉ | 6092/61904 [2:52:33<20:28:45, 1.32s/it] 10%|▉ | 6093/61904 [2:52:35<20:12:42, 1.30s/it] 10%|▉ | 6094/61904 [2:52:36<20:14:32, 1.31s/it] 10%|▉ | 6095/61904 [2:52:38<20:58:03, 1.35s/it] 10%|▉ | 6096/61904 [2:52:39<20:46:15, 1.34s/it] 10%|▉ | 6097/61904 [2:52:40<20:23:50, 1.32s/it] 10%|▉ | 6098/61904 [2:52:41<20:42:31, 1.34s/it] 10%|▉ | 6099/61904 [2:52:43<20:17:53, 1.31s/it] 10%|▉ | 6100/61904 [2:52:44<19:35:37, 1.26s/it] {'loss': 2.9553, 'learning_rate': 1.904382211850123e-07, 'epoch': 1.58} + 10%|▉ | 6100/61904 [2:52:44<19:35:37, 1.26s/it] 10%|▉ | 6101/61904 [2:52:45<21:11:08, 1.37s/it] 10%|▉ | 6102/61904 [2:52:47<21:37:26, 1.40s/it] 10%|▉ | 6103/61904 [2:52:48<21:39:05, 1.40s/it] 10%|▉ | 6104/61904 [2:52:50<21:03:45, 1.36s/it] 10%|▉ | 6105/61904 [2:52:51<21:02:24, 1.36s/it] 10%|▉ | 6106/61904 [2:52:52<21:17:03, 1.37s/it] 10%|▉ | 6107/61904 [2:52:54<21:33:20, 1.39s/it] 10%|▉ | 6108/61904 [2:52:55<21:11:13, 1.37s/it] 10%|▉ | 6109/61904 [2:52:56<20:53:05, 1.35s/it] 10%|▉ | 6110/61904 [2:52:58<21:11:19, 1.37s/it] 10%|▉ | 6111/61904 [2:52:59<21:26:15, 1.38s/it] 10%|▉ | 6112/61904 [2:53:01<21:25:35, 1.38s/it] 10%|▉ | 6113/61904 [2:53:02<21:11:42, 1.37s/it] 10%|▉ | 6114/61904 [2:53:03<21:06:02, 1.36s/it] 10%|▉ | 6115/61904 [2:53:05<21:09:02, 1.36s/it] 10%|▉ | 6116/61904 [2:53:06<21:15:22, 1.37s/it] 10%|▉ | 6117/61904 [2:53:07<20:55:11, 1.35s/it] 10%|▉ | 6118/61904 [2:53:09<20:56:26, 1.35s/it] 10%|▉ | 6119/61904 [2:53:10<20:43:39, 1.34s/it] 10%|▉ | 6120/61904 [2:53:12<21:31:15, 1.39s/it] {'loss': 2.8705, 'learning_rate': 1.9040580837546997e-07, 'epoch': 1.58} + 10%|▉ | 6120/61904 [2:53:12<21:31:15, 1.39s/it] 10%|▉ | 6121/61904 [2:53:13<21:04:01, 1.36s/it] 10%|▉ | 6122/61904 [2:53:14<20:41:53, 1.34s/it] 10%|▉ | 6123/61904 [2:53:15<20:48:52, 1.34s/it] 10%|▉ | 6124/61904 [2:53:17<21:02:41, 1.36s/it] 10%|▉ | 6125/61904 [2:53:18<20:30:38, 1.32s/it] 10%|▉ | 6126/61904 [2:53:20<21:45:34, 1.40s/it] 10%|▉ | 6127/61904 [2:53:21<21:48:32, 1.41s/it] 10%|▉ | 6128/61904 [2:53:23<21:56:21, 1.42s/it] 10%|▉ | 6129/61904 [2:53:24<22:11:03, 1.43s/it] 10%|▉ | 6130/61904 [2:53:25<21:23:32, 1.38s/it] 10%|▉ | 6131/61904 [2:53:27<21:25:28, 1.38s/it] 10%|▉ | 6132/61904 [2:53:28<21:14:28, 1.37s/it] 10%|▉ | 6133/61904 [2:53:29<21:06:11, 1.36s/it] 10%|▉ | 6134/61904 [2:53:31<20:48:09, 1.34s/it] 10%|▉ | 6135/61904 [2:53:32<21:58:59, 1.42s/it] 10%|▉ | 6136/61904 [2:53:33<21:06:21, 1.36s/it] 10%|▉ | 6137/61904 [2:53:35<20:41:05, 1.34s/it] 10%|▉ | 6138/61904 [2:53:36<20:53:42, 1.35s/it] 10%|▉ | 6139/61904 [2:53:38<21:36:40, 1.40s/it] 10%|▉ | 6140/61904 [2:53:39<21:38:34, 1.40s/it] {'loss': 2.9877, 'learning_rate': 1.9037339556592766e-07, 'epoch': 1.59} + 10%|▉ | 6140/61904 [2:53:39<21:38:34, 1.40s/it] 10%|▉ | 6141/61904 [2:53:40<21:38:25, 1.40s/it] 10%|▉ | 6142/61904 [2:53:42<21:14:37, 1.37s/it] 10%|▉ | 6143/61904 [2:53:43<21:42:18, 1.40s/it] 10%|▉ | 6144/61904 [2:53:45<21:20:53, 1.38s/it] 10%|▉ | 6145/61904 [2:53:46<20:44:18, 1.34s/it] 10%|▉ | 6146/61904 [2:53:47<21:16:06, 1.37s/it] 10%|▉ | 6147/61904 [2:53:49<21:18:15, 1.38s/it] 10%|▉ | 6148/61904 [2:53:50<21:13:20, 1.37s/it] 10%|▉ | 6149/61904 [2:53:52<21:52:03, 1.41s/it] 10%|▉ | 6150/61904 [2:53:53<22:00:18, 1.42s/it] 10%|▉ | 6151/61904 [2:53:54<21:06:42, 1.36s/it] 10%|▉ | 6152/61904 [2:53:55<20:53:14, 1.35s/it] 10%|▉ | 6153/61904 [2:53:57<21:13:21, 1.37s/it] 10%|▉ | 6154/61904 [2:53:58<21:00:46, 1.36s/it] 10%|▉ | 6155/61904 [2:54:00<21:02:33, 1.36s/it] 10%|▉ | 6156/61904 [2:54:01<20:54:15, 1.35s/it] 10%|▉ | 6157/61904 [2:54:02<20:47:44, 1.34s/it] 10%|▉ | 6158/61904 [2:54:04<20:48:48, 1.34s/it] 10%|▉ | 6159/61904 [2:54:05<21:08:04, 1.36s/it] 10%|▉ | 6160/61904 [2:54:06<20:23:13, 1.32s/it] {'loss': 2.966, 'learning_rate': 1.9034098275638532e-07, 'epoch': 1.59} + 10%|▉ | 6160/61904 [2:54:06<20:23:13, 1.32s/it] 10%|▉ | 6161/61904 [2:54:08<20:25:06, 1.32s/it] 10%|▉ | 6162/61904 [2:54:09<21:10:47, 1.37s/it] 10%|▉ | 6163/61904 [2:54:10<21:16:24, 1.37s/it] 10%|▉ | 6164/61904 [2:54:12<20:58:04, 1.35s/it] 10%|▉ | 6165/61904 [2:54:13<21:30:24, 1.39s/it] 10%|▉ | 6166/61904 [2:54:15<21:18:46, 1.38s/it] 10%|▉ | 6167/61904 [2:54:16<21:30:17, 1.39s/it] 10%|▉ | 6168/61904 [2:54:17<21:09:25, 1.37s/it] 10%|▉ | 6169/61904 [2:54:19<20:41:30, 1.34s/it] 10%|▉ | 6170/61904 [2:54:20<21:06:34, 1.36s/it] 10%|▉ | 6171/61904 [2:54:21<20:52:44, 1.35s/it] 10%|▉ | 6172/61904 [2:54:23<20:51:34, 1.35s/it] 10%|▉ | 6173/61904 [2:54:24<20:32:54, 1.33s/it] 10%|▉ | 6174/61904 [2:54:25<20:28:23, 1.32s/it] 10%|▉ | 6175/61904 [2:54:27<20:31:32, 1.33s/it] 10%|▉ | 6176/61904 [2:54:28<20:47:57, 1.34s/it] 10%|▉ | 6177/61904 [2:54:29<20:42:06, 1.34s/it] 10%|▉ | 6178/61904 [2:54:31<20:22:46, 1.32s/it] 10%|▉ | 6179/61904 [2:54:32<19:58:17, 1.29s/it] 10%|▉ | 6180/61904 [2:54:33<19:48:35, 1.28s/it] {'loss': 2.9414, 'learning_rate': 1.9030856994684298e-07, 'epoch': 1.6} + 10%|▉ | 6180/61904 [2:54:33<19:48:35, 1.28s/it] 10%|▉ | 6181/61904 [2:54:34<20:30:48, 1.33s/it] 10%|▉ | 6182/61904 [2:54:36<20:54:09, 1.35s/it] 10%|▉ | 6183/61904 [2:54:37<20:58:42, 1.36s/it] 10%|▉ | 6184/61904 [2:54:39<20:56:56, 1.35s/it] 10%|▉ | 6185/61904 [2:54:40<20:49:03, 1.35s/it] 10%|▉ | 6186/61904 [2:54:41<20:22:00, 1.32s/it] 10%|▉ | 6187/61904 [2:54:43<20:36:07, 1.33s/it] 10%|▉ | 6188/61904 [2:54:44<20:30:17, 1.32s/it] 10%|▉ | 6189/61904 [2:54:45<20:19:51, 1.31s/it] 10%|▉ | 6190/61904 [2:54:46<20:16:26, 1.31s/it] 10%|█ | 6191/61904 [2:54:48<20:01:42, 1.29s/it] 10%|█ | 6192/61904 [2:54:49<20:05:57, 1.30s/it] 10%|█ | 6193/61904 [2:54:50<20:33:08, 1.33s/it] 10%|█ | 6194/61904 [2:54:52<20:07:16, 1.30s/it] 10%|█ | 6195/61904 [2:54:53<20:19:04, 1.31s/it] 10%|█ | 6196/61904 [2:54:54<21:03:23, 1.36s/it] 10%|█ | 6197/61904 [2:54:56<20:51:15, 1.35s/it] 10%|█ | 6198/61904 [2:54:57<21:08:22, 1.37s/it] 10%|█ | 6199/61904 [2:54:58<20:38:29, 1.33s/it] 10%|█ | 6200/61904 [2:55:00<20:33:11, 1.33s/it] {'loss': 2.9618, 'learning_rate': 1.9027615713730067e-07, 'epoch': 1.6} + 10%|█ | 6200/61904 [2:55:00<20:33:11, 1.33s/it] 10%|█ | 6201/61904 [2:55:01<20:40:45, 1.34s/it] 10%|█ | 6202/61904 [2:55:02<20:49:39, 1.35s/it] 10%|█ | 6203/61904 [2:55:04<21:37:26, 1.40s/it] 10%|█ | 6204/61904 [2:55:05<21:59:57, 1.42s/it] 10%|█ | 6205/61904 [2:55:07<21:54:32, 1.42s/it] 10%|█ | 6206/61904 [2:55:08<22:01:37, 1.42s/it] 10%|█ | 6207/61904 [2:55:10<21:25:23, 1.38s/it] 10%|█ | 6208/61904 [2:55:11<21:37:58, 1.40s/it] 10%|█ | 6209/61904 [2:55:12<21:13:53, 1.37s/it] 10%|█ | 6210/61904 [2:55:14<21:14:01, 1.37s/it] 10%|█ | 6211/61904 [2:55:15<20:26:59, 1.32s/it] 10%|█ | 6212/61904 [2:55:16<21:10:14, 1.37s/it] 10%|█ | 6213/61904 [2:55:18<21:06:55, 1.36s/it] 10%|█ | 6214/61904 [2:55:19<21:27:30, 1.39s/it] 10%|█ | 6215/61904 [2:55:20<21:04:45, 1.36s/it] 10%|█ | 6216/61904 [2:55:22<21:11:47, 1.37s/it] 10%|█ | 6217/61904 [2:55:23<20:42:47, 1.34s/it] 10%|█ | 6218/61904 [2:55:25<21:17:59, 1.38s/it] 10%|█ | 6219/61904 [2:55:26<21:14:09, 1.37s/it] 10%|█ | 6220/61904 [2:55:27<20:54:05, 1.35s/it] {'loss': 2.9328, 'learning_rate': 1.902437443277583e-07, 'epoch': 1.61} + 10%|█ | 6220/61904 [2:55:27<20:54:05, 1.35s/it] 10%|█ | 6221/61904 [2:55:29<21:12:10, 1.37s/it] 10%|█ | 6222/61904 [2:55:30<20:43:35, 1.34s/it] 10%|█ | 6223/61904 [2:55:31<20:33:07, 1.33s/it] 10%|█ | 6224/61904 [2:55:33<20:42:15, 1.34s/it] 10%|█ | 6225/61904 [2:55:34<21:36:44, 1.40s/it] 10%|█ | 6226/61904 [2:55:35<21:12:55, 1.37s/it] 10%|█ | 6227/61904 [2:55:37<20:51:00, 1.35s/it] 10%|█ | 6228/61904 [2:55:38<20:56:31, 1.35s/it] 10%|█ | 6229/61904 [2:55:39<20:23:55, 1.32s/it] 10%|█ | 6230/61904 [2:55:41<20:59:40, 1.36s/it] 10%|█ | 6231/61904 [2:55:42<20:19:06, 1.31s/it] 10%|█ | 6232/61904 [2:55:43<20:39:34, 1.34s/it] 10%|█ | 6233/61904 [2:55:45<20:13:43, 1.31s/it] 10%|█ | 6234/61904 [2:55:46<21:58:55, 1.42s/it] 10%|█ | 6235/61904 [2:55:48<22:12:13, 1.44s/it] 10%|█ | 6236/61904 [2:55:49<21:39:31, 1.40s/it] 10%|█ | 6237/61904 [2:55:50<21:06:01, 1.36s/it] 10%|█ | 6238/61904 [2:55:52<21:23:24, 1.38s/it] 10%|█ | 6239/61904 [2:55:53<21:40:31, 1.40s/it] 10%|█ | 6240/61904 [2:55:55<22:06:13, 1.43s/it] {'loss': 2.8855, 'learning_rate': 1.90211331518216e-07, 'epoch': 1.61} + 10%|█ | 6240/61904 [2:55:55<22:06:13, 1.43s/it] 10%|█ | 6241/61904 [2:55:56<21:35:14, 1.40s/it] 10%|█ | 6242/61904 [2:55:58<21:45:36, 1.41s/it] 10%|█ | 6243/61904 [2:55:59<21:42:47, 1.40s/it] 10%|█ | 6244/61904 [2:56:00<21:36:33, 1.40s/it] 10%|█ | 6245/61904 [2:56:02<22:05:34, 1.43s/it] 10%|█ | 6246/61904 [2:56:03<22:22:42, 1.45s/it] 10%|█ | 6247/61904 [2:56:05<21:54:30, 1.42s/it] 10%|█ | 6248/61904 [2:56:06<21:26:41, 1.39s/it] 10%|█ | 6249/61904 [2:56:07<21:01:58, 1.36s/it] 10%|█ | 6250/61904 [2:56:09<20:36:20, 1.33s/it] 10%|█ | 6251/61904 [2:56:10<20:57:29, 1.36s/it] 10%|█ | 6252/61904 [2:56:11<21:46:04, 1.41s/it] 10%|█ | 6253/61904 [2:56:13<21:16:13, 1.38s/it] 10%|█ | 6254/61904 [2:56:14<21:25:12, 1.39s/it] 10%|█ | 6255/61904 [2:56:16<21:21:05, 1.38s/it] 10%|█ | 6256/61904 [2:56:17<21:16:44, 1.38s/it] 10%|█ | 6257/61904 [2:56:18<21:25:25, 1.39s/it] 10%|█ | 6258/61904 [2:56:20<21:13:44, 1.37s/it] 10%|█ | 6259/61904 [2:56:21<21:25:53, 1.39s/it] 10%|█ | 6260/61904 [2:56:22<21:25:28, 1.39s/it] {'loss': 2.9168, 'learning_rate': 1.9017891870867368e-07, 'epoch': 1.62} + 10%|█ | 6260/61904 [2:56:22<21:25:28, 1.39s/it] 10%|█ | 6261/61904 [2:56:24<21:22:08, 1.38s/it] 10%|█ | 6262/61904 [2:56:25<20:38:49, 1.34s/it] 10%|█ | 6263/61904 [2:56:26<20:36:44, 1.33s/it] 10%|█ | 6264/61904 [2:56:28<21:59:09, 1.42s/it] 10%|█ | 6265/61904 [2:56:29<21:38:46, 1.40s/it] 10%|█ | 6266/61904 [2:56:31<21:22:16, 1.38s/it] 10%|█ | 6267/61904 [2:56:32<21:04:27, 1.36s/it] 10%|█ | 6268/61904 [2:56:33<20:29:54, 1.33s/it] 10%|█ | 6269/61904 [2:56:35<21:04:56, 1.36s/it] 10%|█ | 6270/61904 [2:56:36<21:27:14, 1.39s/it] 10%|█ | 6271/61904 [2:56:38<22:29:54, 1.46s/it] 10%|█ | 6272/61904 [2:56:39<23:09:42, 1.50s/it] 10%|█ | 6273/61904 [2:56:41<22:55:49, 1.48s/it] 10%|█ | 6274/61904 [2:56:42<22:33:32, 1.46s/it] 10%|█ | 6275/61904 [2:56:44<22:04:45, 1.43s/it] 10%|█ | 6276/61904 [2:56:45<22:28:14, 1.45s/it] 10%|█ | 6277/61904 [2:56:46<22:01:34, 1.43s/it] 10%|█ | 6278/61904 [2:56:48<21:26:26, 1.39s/it] 10%|█ | 6279/61904 [2:56:49<21:03:49, 1.36s/it] 10%|█ | 6280/61904 [2:56:50<20:52:42, 1.35s/it] {'loss': 2.9443, 'learning_rate': 1.9014650589913132e-07, 'epoch': 1.62} + 10%|█ | 6280/61904 [2:56:50<20:52:42, 1.35s/it] 10%|█ | 6281/61904 [2:56:52<20:57:45, 1.36s/it] 10%|█ | 6282/61904 [2:56:53<20:51:39, 1.35s/it] 10%|█ | 6283/61904 [2:56:54<20:48:16, 1.35s/it] 10%|█ | 6284/61904 [2:56:56<21:41:51, 1.40s/it] 10%|█ | 6285/61904 [2:56:57<21:30:21, 1.39s/it] 10%|█ | 6286/61904 [2:56:59<21:35:54, 1.40s/it] 10%|█ | 6287/61904 [2:57:00<21:01:43, 1.36s/it] 10%|█ | 6288/61904 [2:57:01<20:58:24, 1.36s/it] 10%|█ | 6289/61904 [2:57:03<20:34:13, 1.33s/it] 10%|█ | 6290/61904 [2:57:04<20:42:21, 1.34s/it] 10%|█ | 6291/61904 [2:57:05<21:12:41, 1.37s/it] 10%|█ | 6292/61904 [2:57:07<20:59:52, 1.36s/it] 10%|█ | 6293/61904 [2:57:08<20:26:57, 1.32s/it] 10%|█ | 6294/61904 [2:57:09<20:31:40, 1.33s/it] 10%|█ | 6295/61904 [2:57:11<20:47:38, 1.35s/it] 10%|█ | 6296/61904 [2:57:12<20:24:44, 1.32s/it] 10%|█ | 6297/61904 [2:57:13<20:36:11, 1.33s/it] 10%|█ | 6298/61904 [2:57:15<21:04:13, 1.36s/it] 10%|█ | 6299/61904 [2:57:16<21:06:23, 1.37s/it] 10%|█ | 6300/61904 [2:57:18<20:56:29, 1.36s/it] {'loss': 2.9139, 'learning_rate': 1.90114093089589e-07, 'epoch': 1.63} + 10%|█ | 6300/61904 [2:57:18<20:56:29, 1.36s/it] 10%|█ | 6301/61904 [2:57:19<20:54:59, 1.35s/it] 10%|█ | 6302/61904 [2:57:20<20:47:43, 1.35s/it] 10%|█ | 6303/61904 [2:57:21<20:32:46, 1.33s/it] 10%|█ | 6304/61904 [2:57:23<20:39:14, 1.34s/it] 10%|█ | 6305/61904 [2:57:24<20:38:02, 1.34s/it] 10%|█ | 6306/61904 [2:57:26<21:12:05, 1.37s/it] 10%|█ | 6307/61904 [2:57:27<21:26:41, 1.39s/it] 10%|█ | 6308/61904 [2:57:28<20:55:40, 1.36s/it] 10%|█ | 6309/61904 [2:57:30<21:16:18, 1.38s/it] 10%|█ | 6310/61904 [2:57:31<21:10:34, 1.37s/it] 10%|█ | 6311/61904 [2:57:32<20:46:49, 1.35s/it] 10%|█ | 6312/61904 [2:57:34<20:36:51, 1.33s/it] 10%|█ | 6313/61904 [2:57:35<20:27:37, 1.32s/it] 10%|█ | 6314/61904 [2:57:36<20:28:43, 1.33s/it] 10%|█ | 6315/61904 [2:57:38<20:56:52, 1.36s/it] 10%|█ | 6316/61904 [2:57:39<21:23:24, 1.39s/it] 10%|█ | 6317/61904 [2:57:41<21:28:20, 1.39s/it] 10%|█ | 6318/61904 [2:57:42<21:38:22, 1.40s/it] 10%|█ | 6319/61904 [2:57:43<21:32:04, 1.39s/it] 10%|█ | 6320/61904 [2:57:45<21:25:49, 1.39s/it] {'loss': 2.9343, 'learning_rate': 1.9008168028004667e-07, 'epoch': 1.63} + 10%|█ | 6320/61904 [2:57:45<21:25:49, 1.39s/it] 10%|█ | 6321/61904 [2:57:46<21:06:33, 1.37s/it] 10%|█ | 6322/61904 [2:57:48<21:23:09, 1.39s/it] 10%|█ | 6323/61904 [2:57:49<21:00:10, 1.36s/it] 10%|█ | 6324/61904 [2:57:50<20:46:26, 1.35s/it] 10%|█ | 6325/61904 [2:57:51<20:44:02, 1.34s/it] 10%|█ | 6326/61904 [2:57:53<20:32:38, 1.33s/it] 10%|█ | 6327/61904 [2:57:54<20:54:56, 1.35s/it] 10%|█ | 6328/61904 [2:57:56<20:44:23, 1.34s/it] 10%|█ | 6329/61904 [2:57:57<20:29:04, 1.33s/it] 10%|█ | 6330/61904 [2:57:58<20:12:45, 1.31s/it] 10%|█ | 6331/61904 [2:58:00<20:46:09, 1.35s/it] 10%|█ | 6332/61904 [2:58:01<21:01:34, 1.36s/it] 10%|█ | 6333/61904 [2:58:02<21:02:03, 1.36s/it] 10%|█ | 6334/61904 [2:58:04<20:30:16, 1.33s/it] 10%|█ | 6335/61904 [2:58:05<20:37:00, 1.34s/it] 10%|█ | 6336/61904 [2:58:06<20:28:34, 1.33s/it] 10%|█ | 6337/61904 [2:58:08<20:37:16, 1.34s/it] 10%|█ | 6338/61904 [2:58:09<20:39:36, 1.34s/it] 10%|█ | 6339/61904 [2:58:10<21:27:38, 1.39s/it] 10%|█ | 6340/61904 [2:58:12<21:05:05, 1.37s/it] {'loss': 2.9279, 'learning_rate': 1.9004926747050433e-07, 'epoch': 1.64} + 10%|█ | 6340/61904 [2:58:12<21:05:05, 1.37s/it] 10%|█ | 6341/61904 [2:58:13<21:18:03, 1.38s/it] 10%|█ | 6342/61904 [2:58:15<21:40:15, 1.40s/it] 10%|█ | 6343/61904 [2:58:16<21:30:43, 1.39s/it] 10%|█ | 6344/61904 [2:58:17<21:26:41, 1.39s/it] 10%|█ | 6345/61904 [2:58:19<21:21:01, 1.38s/it] 10%|█ | 6346/61904 [2:58:20<21:08:33, 1.37s/it] 10%|█ | 6347/61904 [2:58:21<20:44:34, 1.34s/it] 10%|█ | 6348/61904 [2:58:23<20:31:43, 1.33s/it] 10%|█ | 6349/61904 [2:58:24<20:59:32, 1.36s/it] 10%|█ | 6350/61904 [2:58:25<20:58:16, 1.36s/it] 10%|█ | 6351/61904 [2:58:27<20:57:12, 1.36s/it] 10%|█ | 6352/61904 [2:58:28<21:06:45, 1.37s/it] 10%|█ | 6353/61904 [2:58:30<21:34:38, 1.40s/it] 10%|█ | 6354/61904 [2:58:31<21:39:53, 1.40s/it] 10%|█ | 6355/61904 [2:58:32<21:14:09, 1.38s/it] 10%|█ | 6356/61904 [2:58:34<21:19:37, 1.38s/it] 10%|█ | 6357/61904 [2:58:35<20:52:50, 1.35s/it] 10%|█ | 6358/61904 [2:58:36<21:01:38, 1.36s/it] 10%|█ | 6359/61904 [2:58:38<20:46:41, 1.35s/it] 10%|█ | 6360/61904 [2:58:39<21:48:31, 1.41s/it] {'loss': 2.8902, 'learning_rate': 1.9001685466096202e-07, 'epoch': 1.64} + 10%|█ | 6360/61904 [2:58:39<21:48:31, 1.41s/it] 10%|█ | 6361/61904 [2:58:41<21:45:57, 1.41s/it] 10%|█ | 6362/61904 [2:58:42<21:19:06, 1.38s/it] 10%|█ | 6363/61904 [2:58:43<21:08:53, 1.37s/it] 10%|█ | 6364/61904 [2:58:45<20:40:23, 1.34s/it] 10%|█ | 6365/61904 [2:58:46<20:30:21, 1.33s/it] 10%|█ | 6366/61904 [2:58:47<20:35:32, 1.33s/it] 10%|█ | 6367/61904 [2:58:49<20:55:04, 1.36s/it] 10%|█ | 6368/61904 [2:58:50<21:37:51, 1.40s/it] 10%|█ | 6369/61904 [2:58:52<21:49:28, 1.41s/it] 10%|█ | 6370/61904 [2:58:53<21:31:39, 1.40s/it] 10%|█ | 6371/61904 [2:58:54<21:04:06, 1.37s/it] 10%|█ | 6372/61904 [2:58:56<21:14:46, 1.38s/it] 10%|█ | 6373/61904 [2:58:57<21:38:13, 1.40s/it] 10%|█ | 6374/61904 [2:58:58<21:18:26, 1.38s/it] 10%|█ | 6375/61904 [2:59:00<21:40:44, 1.41s/it] 10%|█ | 6376/61904 [2:59:02<22:22:30, 1.45s/it] 10%|█ | 6377/61904 [2:59:03<21:50:17, 1.42s/it] 10%|█ | 6378/61904 [2:59:04<22:22:00, 1.45s/it] 10%|█ | 6379/61904 [2:59:06<21:55:53, 1.42s/it] 10%|█ | 6380/61904 [2:59:07<21:53:37, 1.42s/it] {'loss': 2.9188, 'learning_rate': 1.8998444185141968e-07, 'epoch': 1.65} + 10%|█ | 6380/61904 [2:59:07<21:53:37, 1.42s/it] 10%|█ | 6381/61904 [2:59:09<21:38:50, 1.40s/it] 10%|█ | 6382/61904 [2:59:10<22:17:42, 1.45s/it] 10%|█ | 6383/61904 [2:59:11<22:09:22, 1.44s/it] 10%|█ | 6384/61904 [2:59:13<21:33:52, 1.40s/it] 10%|█ | 6385/61904 [2:59:14<21:23:45, 1.39s/it] 10%|█ | 6386/61904 [2:59:15<21:14:09, 1.38s/it] 10%|█ | 6387/61904 [2:59:17<20:47:23, 1.35s/it] 10%|█ | 6388/61904 [2:59:18<21:35:24, 1.40s/it] 10%|█ | 6389/61904 [2:59:20<21:49:52, 1.42s/it] 10%|█ | 6390/61904 [2:59:21<21:09:06, 1.37s/it] 10%|█ | 6391/61904 [2:59:22<21:32:09, 1.40s/it] 10%|█ | 6392/61904 [2:59:24<21:25:56, 1.39s/it] 10%|█ | 6393/61904 [2:59:25<20:46:48, 1.35s/it] 10%|█ | 6394/61904 [2:59:27<21:05:22, 1.37s/it] 10%|█ | 6395/61904 [2:59:28<20:47:13, 1.35s/it] 10%|█ | 6396/61904 [2:59:29<21:14:32, 1.38s/it] 10%|█ | 6397/61904 [2:59:31<21:47:56, 1.41s/it] 10%|█ | 6398/61904 [2:59:32<22:33:09, 1.46s/it] 10%|█ | 6399/61904 [2:59:34<23:14:31, 1.51s/it] 10%|█ | 6400/61904 [2:59:35<21:59:50, 1.43s/it] {'loss': 2.9314, 'learning_rate': 1.8995202904187734e-07, 'epoch': 1.65} + 10%|█ | 6400/61904 [2:59:35<21:59:50, 1.43s/it] 10%|█ | 6401/61904 [2:59:37<23:25:50, 1.52s/it] 10%|█ | 6402/61904 [2:59:38<22:31:47, 1.46s/it] 10%|█ | 6403/61904 [2:59:40<22:37:04, 1.47s/it] 10%|█ | 6404/61904 [2:59:41<22:25:25, 1.45s/it] 10%|█ | 6405/61904 [2:59:43<22:03:06, 1.43s/it] 10%|█ | 6406/61904 [2:59:44<21:55:02, 1.42s/it] 10%|█ | 6407/61904 [2:59:45<21:44:45, 1.41s/it] 10%|█ | 6408/61904 [2:59:47<21:35:56, 1.40s/it] 10%|█ | 6409/61904 [2:59:48<21:31:58, 1.40s/it] 10%|█ | 6410/61904 [2:59:49<21:25:55, 1.39s/it] 10%|█ | 6411/61904 [2:59:51<22:16:21, 1.44s/it] 10%|█ | 6412/61904 [2:59:52<21:23:05, 1.39s/it] 10%|█ | 6413/61904 [2:59:54<21:13:43, 1.38s/it] 10%|█ | 6414/61904 [2:59:55<21:52:36, 1.42s/it] 10%|█ | 6415/61904 [2:59:56<21:06:46, 1.37s/it] 10%|█ | 6416/61904 [2:59:58<21:09:24, 1.37s/it] 10%|█ | 6417/61904 [2:59:59<21:08:43, 1.37s/it] 10%|█ | 6418/61904 [3:00:01<21:18:52, 1.38s/it] 10%|█ | 6419/61904 [3:00:02<21:21:27, 1.39s/it] 10%|█ | 6420/61904 [3:00:03<20:41:14, 1.34s/it] {'loss': 2.9729, 'learning_rate': 1.8991961623233503e-07, 'epoch': 1.66} + 10%|█ | 6420/61904 [3:00:03<20:41:14, 1.34s/it] 10%|█ | 6421/61904 [3:00:05<20:38:18, 1.34s/it] 10%|█ | 6422/61904 [3:00:06<22:02:41, 1.43s/it] 10%|█ | 6423/61904 [3:00:08<21:57:42, 1.43s/it] 10%|█ | 6424/61904 [3:00:09<21:38:33, 1.40s/it] 10%|█ | 6425/61904 [3:00:10<20:48:41, 1.35s/it] 10%|█ | 6426/61904 [3:00:12<20:54:15, 1.36s/it] 10%|█ | 6427/61904 [3:00:13<21:25:03, 1.39s/it] 10%|█ | 6428/61904 [3:00:14<21:21:43, 1.39s/it] 10%|█ | 6429/61904 [3:00:16<22:21:09, 1.45s/it] 10%|█ | 6430/61904 [3:00:17<21:42:02, 1.41s/it] 10%|█ | 6431/61904 [3:00:19<21:50:06, 1.42s/it] 10%|█ | 6432/61904 [3:00:20<22:10:18, 1.44s/it] 10%|█ | 6433/61904 [3:00:22<22:22:34, 1.45s/it] 10%|█ | 6434/61904 [3:00:23<22:04:31, 1.43s/it] 10%|█ | 6435/61904 [3:00:25<22:11:22, 1.44s/it] 10%|█ | 6436/61904 [3:00:26<21:30:52, 1.40s/it] 10%|█ | 6437/61904 [3:00:27<21:35:43, 1.40s/it] 10%|█ | 6438/61904 [3:00:29<21:50:07, 1.42s/it] 10%|█ | 6439/61904 [3:00:30<21:25:01, 1.39s/it] 10%|█ | 6440/61904 [3:00:31<21:35:14, 1.40s/it] {'loss': 2.9336, 'learning_rate': 1.8988720342279266e-07, 'epoch': 1.66} + 10%|█ | 6440/61904 [3:00:31<21:35:14, 1.40s/it] 10%|█ | 6441/61904 [3:00:33<21:43:44, 1.41s/it] 10%|█ | 6442/61904 [3:00:34<21:20:29, 1.39s/it] 10%|█ | 6443/61904 [3:00:36<21:45:50, 1.41s/it] 10%|█ | 6444/61904 [3:00:37<21:45:29, 1.41s/it] 10%|█ | 6445/61904 [3:00:38<21:23:55, 1.39s/it] 10%|█ | 6446/61904 [3:00:40<21:53:33, 1.42s/it] 10%|█ | 6447/61904 [3:00:41<21:31:55, 1.40s/it] 10%|█ | 6448/61904 [3:00:43<21:00:01, 1.36s/it] 10%|█ | 6449/61904 [3:00:44<21:03:11, 1.37s/it] 10%|█ | 6450/61904 [3:00:45<21:26:23, 1.39s/it] 10%|█ | 6451/61904 [3:00:47<21:29:53, 1.40s/it] 10%|█ | 6452/61904 [3:00:48<21:30:38, 1.40s/it] 10%|█ | 6453/61904 [3:00:50<22:28:26, 1.46s/it] 10%|█ | 6454/61904 [3:00:51<21:57:14, 1.43s/it] 10%|█ | 6455/61904 [3:00:52<21:25:30, 1.39s/it] 10%|█ | 6456/61904 [3:00:54<21:32:14, 1.40s/it] 10%|█ | 6457/61904 [3:00:55<22:02:46, 1.43s/it] 10%|█ | 6458/61904 [3:00:57<21:50:10, 1.42s/it] 10%|█ | 6459/61904 [3:00:58<21:54:09, 1.42s/it] 10%|█ | 6460/61904 [3:01:00<21:39:27, 1.41s/it] {'loss': 2.9242, 'learning_rate': 1.8985479061325035e-07, 'epoch': 1.67} + 10%|█ | 6460/61904 [3:01:00<21:39:27, 1.41s/it] 10%|█ | 6461/61904 [3:01:01<22:44:08, 1.48s/it] 10%|█ | 6462/61904 [3:01:03<21:59:07, 1.43s/it] 10%|█ | 6463/61904 [3:01:04<22:08:47, 1.44s/it] 10%|█ | 6464/61904 [3:01:05<21:35:41, 1.40s/it] 10%|█ | 6465/61904 [3:01:07<21:26:32, 1.39s/it] 10%|█ | 6466/61904 [3:01:08<21:13:07, 1.38s/it] 10%|█ | 6467/61904 [3:01:09<20:54:00, 1.36s/it] 10%|█ | 6468/61904 [3:01:11<21:07:13, 1.37s/it] 10%|█ | 6469/61904 [3:01:12<21:36:09, 1.40s/it] 10%|█ | 6470/61904 [3:01:14<22:01:50, 1.43s/it] 10%|█ | 6471/61904 [3:01:15<22:06:36, 1.44s/it] 10%|█ | 6472/61904 [3:01:16<21:33:42, 1.40s/it] 10%|█ | 6473/61904 [3:01:18<21:35:05, 1.40s/it] 10%|█ | 6474/61904 [3:01:19<21:29:23, 1.40s/it] 10%|█ | 6475/61904 [3:01:21<21:19:37, 1.39s/it] 10%|█ | 6476/61904 [3:01:22<21:10:33, 1.38s/it] 10%|█ | 6477/61904 [3:01:23<21:03:04, 1.37s/it] 10%|█ | 6478/61904 [3:01:25<21:24:52, 1.39s/it] 10%|█ | 6479/61904 [3:01:26<21:33:02, 1.40s/it] 10%|█ | 6480/61904 [3:01:28<21:14:08, 1.38s/it] {'loss': 3.0066, 'learning_rate': 1.8982237780370804e-07, 'epoch': 1.67} + 10%|█ | 6480/61904 [3:01:28<21:14:08, 1.38s/it] 10%|█ | 6481/61904 [3:01:29<21:24:18, 1.39s/it] 10%|█ | 6482/61904 [3:01:30<21:11:12, 1.38s/it] 10%|█ | 6483/61904 [3:01:31<20:29:29, 1.33s/it] 10%|█ | 6484/61904 [3:01:33<20:11:10, 1.31s/it] 10%|█ | 6485/61904 [3:01:34<20:39:19, 1.34s/it] 10%|█ | 6486/61904 [3:01:36<20:55:46, 1.36s/it] 10%|█ | 6487/61904 [3:01:37<21:21:37, 1.39s/it] 10%|█ | 6488/61904 [3:01:38<21:44:11, 1.41s/it] 10%|█ | 6489/61904 [3:01:40<21:36:14, 1.40s/it] 10%|█ | 6490/61904 [3:01:41<21:12:16, 1.38s/it] 10%|█ | 6491/61904 [3:01:43<21:18:05, 1.38s/it] 10%|█ | 6492/61904 [3:01:44<21:26:34, 1.39s/it] 10%|█ | 6493/61904 [3:01:45<21:19:38, 1.39s/it] 10%|█ | 6494/61904 [3:01:47<21:42:10, 1.41s/it] 10%|█ | 6495/61904 [3:01:48<21:19:13, 1.39s/it] 10%|█ | 6496/61904 [3:01:50<21:13:34, 1.38s/it] 10%|█ | 6497/61904 [3:01:51<21:23:34, 1.39s/it] 10%|█ | 6498/61904 [3:01:52<20:59:12, 1.36s/it] 10%|█ | 6499/61904 [3:01:54<20:39:46, 1.34s/it] 11%|█ | 6500/61904 [3:01:55<20:22:53, 1.32s/it] {'loss': 2.9272, 'learning_rate': 1.8978996499416568e-07, 'epoch': 1.68} + 11%|█ | 6500/61904 [3:01:55<20:22:53, 1.32s/it] 11%|█ | 6501/61904 [3:01:56<21:35:38, 1.40s/it] 11%|█ | 6502/61904 [3:01:58<22:04:59, 1.43s/it] 11%|█ | 6503/61904 [3:01:59<21:59:08, 1.43s/it] 11%|█ | 6504/61904 [3:02:01<21:24:07, 1.39s/it] 11%|█ | 6505/61904 [3:02:02<21:31:15, 1.40s/it] 11%|█ | 6506/61904 [3:02:03<21:10:50, 1.38s/it] 11%|█ | 6507/61904 [3:02:05<21:33:53, 1.40s/it] 11%|█ | 6508/61904 [3:02:06<20:54:40, 1.36s/it] 11%|█ | 6509/61904 [3:02:07<20:48:22, 1.35s/it] 11%|█ | 6510/61904 [3:02:09<21:02:43, 1.37s/it] 11%|█ | 6511/61904 [3:02:10<21:15:49, 1.38s/it] 11%|█ | 6512/61904 [3:02:12<21:10:31, 1.38s/it] 11%|█ | 6513/61904 [3:02:13<21:11:12, 1.38s/it] 11%|█ | 6514/61904 [3:02:15<21:53:03, 1.42s/it] 11%|█ | 6515/61904 [3:02:16<21:39:27, 1.41s/it] 11%|█ | 6516/61904 [3:02:17<21:15:50, 1.38s/it] 11%|█ | 6517/61904 [3:02:19<21:28:50, 1.40s/it] 11%|█ | 6518/61904 [3:02:20<20:42:49, 1.35s/it] 11%|█ | 6519/61904 [3:02:21<21:19:27, 1.39s/it] 11%|█ | 6520/61904 [3:02:23<21:24:39, 1.39s/it] {'loss': 2.8841, 'learning_rate': 1.8975755218462336e-07, 'epoch': 1.68} + 11%|█ | 6520/61904 [3:02:23<21:24:39, 1.39s/it] 11%|█ | 6521/61904 [3:02:24<21:33:09, 1.40s/it] 11%|█ | 6522/61904 [3:02:26<21:38:36, 1.41s/it] 11%|█ | 6523/61904 [3:02:27<21:46:11, 1.42s/it] 11%|█ | 6524/61904 [3:02:28<21:43:55, 1.41s/it] 11%|█ | 6525/61904 [3:02:30<20:56:10, 1.36s/it] 11%|█ | 6526/61904 [3:02:31<21:39:37, 1.41s/it] 11%|█ | 6527/61904 [3:02:33<22:02:13, 1.43s/it] 11%|█ | 6528/61904 [3:02:34<21:41:57, 1.41s/it] 11%|█ | 6529/61904 [3:02:35<21:23:04, 1.39s/it] 11%|█ | 6530/61904 [3:02:37<21:34:00, 1.40s/it] 11%|█ | 6531/61904 [3:02:38<21:30:12, 1.40s/it] 11%|█ | 6532/61904 [3:02:40<22:02:39, 1.43s/it] 11%|█ | 6533/61904 [3:02:41<21:35:00, 1.40s/it] 11%|█ | 6534/61904 [3:02:43<21:49:34, 1.42s/it] 11%|█ | 6535/61904 [3:02:44<21:36:14, 1.40s/it] 11%|█ | 6536/61904 [3:02:45<21:08:11, 1.37s/it] 11%|█ | 6537/61904 [3:02:46<20:43:17, 1.35s/it] 11%|█ | 6538/61904 [3:02:48<21:05:55, 1.37s/it] 11%|█ | 6539/61904 [3:02:49<20:39:12, 1.34s/it] 11%|█ | 6540/61904 [3:02:51<20:41:07, 1.35s/it] {'loss': 2.9365, 'learning_rate': 1.8972513937508103e-07, 'epoch': 1.69} + 11%|█ | 6540/61904 [3:02:51<20:41:07, 1.35s/it] 11%|█ | 6541/61904 [3:02:52<21:24:55, 1.39s/it] 11%|█ | 6542/61904 [3:02:54<22:00:30, 1.43s/it] 11%|█ | 6543/61904 [3:02:55<22:09:29, 1.44s/it] 11%|█ | 6544/61904 [3:02:56<21:58:23, 1.43s/it] 11%|█ | 6545/61904 [3:02:58<21:55:42, 1.43s/it] 11%|█ | 6546/61904 [3:02:59<21:29:12, 1.40s/it] 11%|█ | 6547/61904 [3:03:01<21:27:09, 1.40s/it] 11%|█ | 6548/61904 [3:03:02<21:12:01, 1.38s/it] 11%|█ | 6549/61904 [3:03:03<20:30:46, 1.33s/it] 11%|█ | 6550/61904 [3:03:05<20:40:39, 1.34s/it] 11%|█ | 6551/61904 [3:03:06<21:24:47, 1.39s/it] 11%|█ | 6552/61904 [3:03:07<21:11:47, 1.38s/it] 11%|█ | 6553/61904 [3:03:09<21:41:25, 1.41s/it] 11%|█ | 6554/61904 [3:03:10<20:59:14, 1.37s/it] 11%|█ | 6555/61904 [3:03:11<20:33:06, 1.34s/it] 11%|█ | 6556/61904 [3:03:13<20:33:51, 1.34s/it] 11%|█ | 6557/61904 [3:03:14<20:33:22, 1.34s/it] 11%|█ | 6558/61904 [3:03:15<20:37:10, 1.34s/it] 11%|█ | 6559/61904 [3:03:17<21:12:22, 1.38s/it] 11%|█ | 6560/61904 [3:03:18<21:14:41, 1.38s/it] {'loss': 2.9948, 'learning_rate': 1.896927265655387e-07, 'epoch': 1.7} + 11%|█ | 6560/61904 [3:03:18<21:14:41, 1.38s/it] 11%|█ | 6561/61904 [3:03:20<21:11:43, 1.38s/it] 11%|█ | 6562/61904 [3:03:21<21:11:03, 1.38s/it] 11%|█ | 6563/61904 [3:03:22<20:51:17, 1.36s/it] 11%|█ | 6564/61904 [3:03:24<20:57:20, 1.36s/it] 11%|█ | 6565/61904 [3:03:25<22:14:30, 1.45s/it] 11%|█ | 6566/61904 [3:03:27<21:38:58, 1.41s/it] 11%|█ | 6567/61904 [3:03:28<21:52:21, 1.42s/it] 11%|█ | 6568/61904 [3:03:29<21:30:28, 1.40s/it] 11%|█ | 6569/61904 [3:03:31<21:23:59, 1.39s/it] 11%|█ | 6570/61904 [3:03:32<21:06:54, 1.37s/it] 11%|█ | 6571/61904 [3:03:33<20:52:33, 1.36s/it] 11%|█ | 6572/61904 [3:03:35<21:46:13, 1.42s/it] 11%|█ | 6573/61904 [3:03:36<21:40:32, 1.41s/it] 11%|█ | 6574/61904 [3:03:38<21:12:41, 1.38s/it] 11%|█ | 6575/61904 [3:03:39<21:05:42, 1.37s/it] 11%|█ | 6576/61904 [3:03:40<20:41:38, 1.35s/it] 11%|█ | 6577/61904 [3:03:42<21:26:55, 1.40s/it] 11%|█ | 6578/61904 [3:03:43<20:54:44, 1.36s/it] 11%|█ | 6579/61904 [3:03:45<20:52:33, 1.36s/it] 11%|█ | 6580/61904 [3:03:46<20:54:53, 1.36s/it] {'loss': 2.9, 'learning_rate': 1.8966031375599638e-07, 'epoch': 1.7} + 11%|█ | 6580/61904 [3:03:46<20:54:53, 1.36s/it] 11%|█ | 6581/61904 [3:03:47<20:43:31, 1.35s/it] 11%|█ | 6582/61904 [3:03:49<21:31:29, 1.40s/it] 11%|█ | 6583/61904 [3:03:50<21:38:46, 1.41s/it] 11%|█ | 6584/61904 [3:03:52<21:57:32, 1.43s/it] 11%|█ | 6585/61904 [3:03:53<21:23:00, 1.39s/it] 11%|█ | 6586/61904 [3:03:54<21:18:20, 1.39s/it] 11%|█ | 6587/61904 [3:03:56<21:24:07, 1.39s/it] 11%|█ | 6588/61904 [3:03:57<20:59:33, 1.37s/it] 11%|█ | 6589/61904 [3:03:58<21:29:06, 1.40s/it] 11%|█ | 6590/61904 [3:04:00<21:14:24, 1.38s/it] 11%|█ | 6591/61904 [3:04:01<21:24:00, 1.39s/it] 11%|█ | 6592/61904 [3:04:03<21:15:36, 1.38s/it] 11%|█ | 6593/61904 [3:04:04<21:23:04, 1.39s/it] 11%|█ | 6594/61904 [3:04:05<21:31:49, 1.40s/it] 11%|█ | 6595/61904 [3:04:07<21:34:58, 1.40s/it] 11%|█ | 6596/61904 [3:04:08<20:49:24, 1.36s/it] 11%|█ | 6597/61904 [3:04:09<20:57:43, 1.36s/it] 11%|█ | 6598/61904 [3:04:11<20:47:39, 1.35s/it] 11%|█ | 6599/61904 [3:04:12<20:46:15, 1.35s/it] 11%|█ | 6600/61904 [3:04:14<20:55:20, 1.36s/it] {'loss': 2.9318, 'learning_rate': 1.8962790094645404e-07, 'epoch': 1.71} + 11%|█ | 6600/61904 [3:04:14<20:55:20, 1.36s/it] 11%|█ | 6601/61904 [3:04:15<20:22:30, 1.33s/it] 11%|█ | 6602/61904 [3:04:16<20:57:05, 1.36s/it] 11%|█ | 6603/61904 [3:04:18<21:00:08, 1.37s/it] 11%|█ | 6604/61904 [3:04:19<20:41:56, 1.35s/it] 11%|█ | 6605/61904 [3:04:20<20:21:38, 1.33s/it] 11%|█ | 6606/61904 [3:04:21<20:07:50, 1.31s/it] 11%|█ | 6607/61904 [3:04:23<20:15:50, 1.32s/it] 11%|█ | 6608/61904 [3:04:24<20:06:54, 1.31s/it] 11%|█ | 6609/61904 [3:04:25<19:55:07, 1.30s/it] 11%|█ | 6610/61904 [3:04:27<20:06:28, 1.31s/it] 11%|█ | 6611/61904 [3:04:28<19:42:32, 1.28s/it] 11%|█ | 6612/61904 [3:04:29<19:42:37, 1.28s/it] 11%|█ | 6613/61904 [3:04:31<20:00:52, 1.30s/it] 11%|█ | 6614/61904 [3:04:32<20:11:29, 1.31s/it] 11%|█ | 6615/61904 [3:04:33<20:42:53, 1.35s/it] 11%|█ | 6616/61904 [3:04:35<20:23:10, 1.33s/it] 11%|█ | 6617/61904 [3:04:36<21:00:51, 1.37s/it] 11%|█ | 6618/61904 [3:04:38<21:37:24, 1.41s/it] 11%|█ | 6619/61904 [3:04:39<21:47:19, 1.42s/it] 11%|█ | 6620/61904 [3:04:40<21:07:10, 1.38s/it] {'loss': 2.8761, 'learning_rate': 1.895954881369117e-07, 'epoch': 1.71} + 11%|█ | 6620/61904 [3:04:40<21:07:10, 1.38s/it] 11%|█ | 6621/61904 [3:04:42<20:55:46, 1.36s/it] 11%|█ | 6622/61904 [3:04:43<20:55:41, 1.36s/it] 11%|█ | 6623/61904 [3:04:44<20:29:58, 1.33s/it] 11%|█ | 6624/61904 [3:04:46<20:24:14, 1.33s/it] 11%|█ | 6625/61904 [3:04:47<20:21:35, 1.33s/it] 11%|█ | 6626/61904 [3:04:48<20:44:36, 1.35s/it] 11%|█ | 6627/61904 [3:04:50<20:15:25, 1.32s/it] 11%|█ | 6628/61904 [3:04:51<21:04:18, 1.37s/it] 11%|█ | 6629/61904 [3:04:53<21:56:14, 1.43s/it] 11%|█ | 6630/61904 [3:04:54<22:18:30, 1.45s/it] 11%|█ | 6631/61904 [3:04:56<22:15:49, 1.45s/it] 11%|█ | 6632/61904 [3:04:57<21:51:51, 1.42s/it] 11%|█ | 6633/61904 [3:04:58<21:19:17, 1.39s/it] 11%|█ | 6634/61904 [3:05:00<20:51:40, 1.36s/it] 11%|█ | 6635/61904 [3:05:01<20:55:26, 1.36s/it] 11%|█ | 6636/61904 [3:05:02<21:14:06, 1.38s/it] 11%|█ | 6637/61904 [3:05:04<20:54:42, 1.36s/it] 11%|█ | 6638/61904 [3:05:05<20:46:34, 1.35s/it] 11%|█ | 6639/61904 [3:05:06<21:11:05, 1.38s/it] 11%|█ | 6640/61904 [3:05:08<20:27:57, 1.33s/it] {'loss': 2.9628, 'learning_rate': 1.895630753273694e-07, 'epoch': 1.72} + 11%|█ | 6640/61904 [3:05:08<20:27:57, 1.33s/it] 11%|█ | 6641/61904 [3:05:09<20:50:22, 1.36s/it] 11%|█ | 6642/61904 [3:05:10<20:23:12, 1.33s/it] 11%|█ | 6643/61904 [3:05:12<21:21:45, 1.39s/it] 11%|█ | 6644/61904 [3:05:13<20:37:44, 1.34s/it] 11%|█ | 6645/61904 [3:05:14<20:47:51, 1.35s/it] 11%|█ | 6646/61904 [3:05:16<20:40:44, 1.35s/it] 11%|█ | 6647/61904 [3:05:17<21:39:40, 1.41s/it] 11%|█ | 6648/61904 [3:05:19<21:36:44, 1.41s/it] 11%|█ | 6649/61904 [3:05:20<21:15:22, 1.38s/it] 11%|█ | 6650/61904 [3:05:21<21:10:02, 1.38s/it] 11%|█ | 6651/61904 [3:05:23<21:13:04, 1.38s/it] 11%|█ | 6652/61904 [3:05:24<21:31:38, 1.40s/it] 11%|█ | 6653/61904 [3:05:26<22:08:28, 1.44s/it] 11%|█ | 6654/61904 [3:05:27<20:59:52, 1.37s/it] 11%|█ | 6655/61904 [3:05:28<20:31:40, 1.34s/it] 11%|█ | 6656/61904 [3:05:30<20:39:15, 1.35s/it] 11%|█ | 6657/61904 [3:05:31<20:34:24, 1.34s/it] 11%|█ | 6658/61904 [3:05:32<20:43:17, 1.35s/it] 11%|█ | 6659/61904 [3:05:34<21:16:26, 1.39s/it] 11%|█ | 6660/61904 [3:05:35<20:50:49, 1.36s/it] {'loss': 2.9114, 'learning_rate': 1.8953066251782702e-07, 'epoch': 1.72} + 11%|█ | 6660/61904 [3:05:35<20:50:49, 1.36s/it] 11%|█ | 6661/61904 [3:05:37<21:14:49, 1.38s/it] 11%|█ | 6662/61904 [3:05:38<21:03:58, 1.37s/it] 11%|█ | 6663/61904 [3:05:39<21:13:24, 1.38s/it] 11%|█ | 6664/61904 [3:05:41<21:29:22, 1.40s/it] 11%|█ | 6665/61904 [3:05:42<20:51:26, 1.36s/it] 11%|█ | 6666/61904 [3:05:43<21:13:34, 1.38s/it] 11%|█ | 6667/61904 [3:05:45<20:52:04, 1.36s/it] 11%|█ | 6668/61904 [3:05:46<20:42:47, 1.35s/it] 11%|█ | 6669/61904 [3:05:47<20:42:37, 1.35s/it] 11%|█ | 6670/61904 [3:05:49<20:34:36, 1.34s/it] 11%|█ | 6671/61904 [3:05:50<21:12:32, 1.38s/it] 11%|█ | 6672/61904 [3:05:52<20:50:52, 1.36s/it] 11%|█ | 6673/61904 [3:05:53<20:24:51, 1.33s/it] 11%|█ | 6674/61904 [3:05:54<21:07:46, 1.38s/it] 11%|█ | 6675/61904 [3:05:56<21:02:19, 1.37s/it] 11%|█ | 6676/61904 [3:05:57<21:07:31, 1.38s/it] 11%|█ | 6677/61904 [3:05:58<21:05:45, 1.38s/it] 11%|█ | 6678/61904 [3:06:00<21:31:44, 1.40s/it] 11%|█ | 6679/61904 [3:06:01<21:42:44, 1.42s/it] 11%|█ | 6680/61904 [3:06:03<21:25:01, 1.40s/it] {'loss': 2.9338, 'learning_rate': 1.894982497082847e-07, 'epoch': 1.73} + 11%|█ | 6680/61904 [3:06:03<21:25:01, 1.40s/it] 11%|█ | 6681/61904 [3:06:04<21:01:51, 1.37s/it] 11%|█ | 6682/61904 [3:06:05<20:58:25, 1.37s/it] 11%|█ | 6683/61904 [3:06:07<20:25:57, 1.33s/it] 11%|█ | 6684/61904 [3:06:08<20:50:16, 1.36s/it] 11%|█ | 6685/61904 [3:06:09<20:40:33, 1.35s/it] 11%|█ | 6686/61904 [3:06:11<20:34:59, 1.34s/it] 11%|█ | 6687/61904 [3:06:12<20:47:44, 1.36s/it] 11%|█ | 6688/61904 [3:06:13<20:45:54, 1.35s/it] 11%|█ | 6689/61904 [3:06:15<20:30:01, 1.34s/it] 11%|█ | 6690/61904 [3:06:16<20:49:50, 1.36s/it] 11%|█ | 6691/61904 [3:06:18<21:15:43, 1.39s/it] 11%|█ | 6692/61904 [3:06:19<22:03:14, 1.44s/it] 11%|█ | 6693/61904 [3:06:20<21:42:18, 1.42s/it] 11%|█ | 6694/61904 [3:06:22<21:16:19, 1.39s/it] 11%|█ | 6695/61904 [3:06:23<21:25:50, 1.40s/it] 11%|█ | 6696/61904 [3:06:25<20:58:15, 1.37s/it] 11%|█ | 6697/61904 [3:06:26<21:43:29, 1.42s/it] 11%|█ | 6698/61904 [3:06:27<21:04:34, 1.37s/it] 11%|█ | 6699/61904 [3:06:29<20:25:41, 1.33s/it] 11%|█ | 6700/61904 [3:06:30<20:12:30, 1.32s/it] {'loss': 2.9956, 'learning_rate': 1.8946583689874237e-07, 'epoch': 1.73} + 11%|█ | 6700/61904 [3:06:30<20:12:30, 1.32s/it] 11%|█ | 6701/61904 [3:06:31<20:46:50, 1.36s/it] 11%|█ | 6702/61904 [3:06:33<20:46:55, 1.36s/it] 11%|█ | 6703/61904 [3:06:34<21:16:57, 1.39s/it] 11%|█ | 6704/61904 [3:06:35<21:05:53, 1.38s/it] 11%|█ | 6705/61904 [3:06:37<21:05:23, 1.38s/it] 11%|█ | 6706/61904 [3:06:38<21:12:56, 1.38s/it] 11%|█ | 6707/61904 [3:06:40<21:07:34, 1.38s/it] 11%|█ | 6708/61904 [3:06:41<21:10:35, 1.38s/it] 11%|█ | 6709/61904 [3:06:42<21:01:08, 1.37s/it] 11%|█ | 6710/61904 [3:06:44<21:06:41, 1.38s/it] 11%|█ | 6711/61904 [3:06:45<21:25:55, 1.40s/it] 11%|█ | 6712/61904 [3:06:47<21:14:52, 1.39s/it] 11%|█ | 6713/61904 [3:06:48<20:26:43, 1.33s/it] 11%|█ | 6714/61904 [3:06:49<20:30:57, 1.34s/it] 11%|█ | 6715/61904 [3:06:50<19:59:48, 1.30s/it] 11%|█ | 6716/61904 [3:06:52<20:58:16, 1.37s/it] 11%|█ | 6717/61904 [3:06:53<20:15:38, 1.32s/it] 11%|█ | 6718/61904 [3:06:54<19:50:23, 1.29s/it] 11%|█ | 6719/61904 [3:06:56<20:11:35, 1.32s/it] 11%|█ | 6720/61904 [3:06:57<20:30:27, 1.34s/it] {'loss': 2.9089, 'learning_rate': 1.8943342408920004e-07, 'epoch': 1.74} + 11%|█ | 6720/61904 [3:06:57<20:30:27, 1.34s/it] 11%|█ | 6721/61904 [3:06:58<20:07:09, 1.31s/it] 11%|█ | 6722/61904 [3:07:00<20:17:36, 1.32s/it] 11%|█ | 6723/61904 [3:07:01<19:41:45, 1.28s/it] 11%|█ | 6724/61904 [3:07:02<19:39:30, 1.28s/it] 11%|█ | 6725/61904 [3:07:03<19:43:16, 1.29s/it] 11%|█ | 6726/61904 [3:07:05<20:16:38, 1.32s/it] 11%|█ | 6727/61904 [3:07:06<20:06:30, 1.31s/it] 11%|█ | 6728/61904 [3:07:07<20:22:12, 1.33s/it] 11%|█ | 6729/61904 [3:07:09<20:41:20, 1.35s/it] 11%|█ | 6730/61904 [3:07:10<20:06:08, 1.31s/it] 11%|█ | 6731/61904 [3:07:11<20:29:34, 1.34s/it] 11%|█ | 6732/61904 [3:07:13<19:59:41, 1.30s/it] 11%|█ | 6733/61904 [3:07:14<20:13:28, 1.32s/it] 11%|█ | 6734/61904 [3:07:15<20:24:11, 1.33s/it] 11%|█ | 6735/61904 [3:07:17<20:28:53, 1.34s/it] 11%|█ | 6736/61904 [3:07:18<20:18:20, 1.33s/it] 11%|█ | 6737/61904 [3:07:19<20:34:58, 1.34s/it] 11%|█ | 6738/61904 [3:07:21<21:10:05, 1.38s/it] 11%|█ | 6739/61904 [3:07:22<20:51:55, 1.36s/it] 11%|█ | 6740/61904 [3:07:24<21:23:07, 1.40s/it] {'loss': 2.9213, 'learning_rate': 1.8940101127965772e-07, 'epoch': 1.74} + 11%|█ | 6740/61904 [3:07:24<21:23:07, 1.40s/it] 11%|█ | 6741/61904 [3:07:25<21:02:01, 1.37s/it] 11%|█ | 6742/61904 [3:07:26<21:22:16, 1.39s/it] 11%|█ | 6743/61904 [3:07:28<21:23:41, 1.40s/it] 11%|█ | 6744/61904 [3:07:29<20:38:27, 1.35s/it] 11%|█ | 6745/61904 [3:07:31<21:02:30, 1.37s/it] 11%|█ | 6746/61904 [3:07:32<21:01:31, 1.37s/it] 11%|█ | 6747/61904 [3:07:33<21:28:06, 1.40s/it] 11%|█ | 6748/61904 [3:07:35<21:24:48, 1.40s/it] 11%|█ | 6749/61904 [3:07:36<21:21:15, 1.39s/it] 11%|█ | 6750/61904 [3:07:38<21:09:27, 1.38s/it] 11%|█ | 6751/61904 [3:07:39<20:32:08, 1.34s/it] 11%|█ | 6752/61904 [3:07:40<20:43:01, 1.35s/it] 11%|█ | 6753/61904 [3:07:41<20:39:33, 1.35s/it] 11%|█ | 6754/61904 [3:07:43<21:01:26, 1.37s/it] 11%|█ | 6755/61904 [3:07:44<20:56:31, 1.37s/it] 11%|█ | 6756/61904 [3:07:46<20:32:25, 1.34s/it] 11%|█ | 6757/61904 [3:07:47<20:03:32, 1.31s/it] 11%|█ | 6758/61904 [3:07:48<20:17:28, 1.32s/it] 11%|█ | 6759/61904 [3:07:49<20:13:37, 1.32s/it] 11%|█ | 6760/61904 [3:07:51<20:03:58, 1.31s/it] {'loss': 2.9461, 'learning_rate': 1.8936859847011539e-07, 'epoch': 1.75} + 11%|█ | 6760/61904 [3:07:51<20:03:58, 1.31s/it] 11%|█ | 6761/61904 [3:07:52<20:20:32, 1.33s/it] 11%|█ | 6762/61904 [3:07:53<19:47:34, 1.29s/it] 11%|█ | 6763/61904 [3:07:55<19:48:38, 1.29s/it] 11%|█ | 6764/61904 [3:07:56<19:48:48, 1.29s/it] 11%|█ | 6765/61904 [3:07:57<19:59:10, 1.30s/it] 11%|█ | 6766/61904 [3:07:59<20:33:29, 1.34s/it] 11%|█ | 6767/61904 [3:08:00<19:59:03, 1.30s/it] 11%|█ | 6768/61904 [3:08:01<20:03:34, 1.31s/it] 11%|█ | 6769/61904 [3:08:03<20:18:53, 1.33s/it] 11%|█ | 6770/61904 [3:08:04<20:52:54, 1.36s/it] 11%|█ | 6771/61904 [3:08:05<20:41:53, 1.35s/it] 11%|█ | 6772/61904 [3:08:07<21:34:20, 1.41s/it] 11%|█ | 6773/61904 [3:08:08<21:06:07, 1.38s/it] 11%|█ | 6774/61904 [3:08:10<21:32:21, 1.41s/it] 11%|█ | 6775/61904 [3:08:11<21:21:08, 1.39s/it] 11%|█ | 6776/61904 [3:08:12<20:55:34, 1.37s/it] 11%|█ | 6777/61904 [3:08:14<21:00:36, 1.37s/it] 11%|█ | 6778/61904 [3:08:15<20:52:36, 1.36s/it] 11%|█ | 6779/61904 [3:08:16<20:29:01, 1.34s/it] 11%|█ | 6780/61904 [3:08:18<20:35:44, 1.35s/it] {'loss': 2.9103, 'learning_rate': 1.8933618566057305e-07, 'epoch': 1.75} + 11%|█ | 6780/61904 [3:08:18<20:35:44, 1.35s/it] 11%|█ | 6781/61904 [3:08:19<20:27:48, 1.34s/it] 11%|█ | 6782/61904 [3:08:20<20:20:46, 1.33s/it] 11%|█ | 6783/61904 [3:08:22<20:32:59, 1.34s/it] 11%|█ | 6784/61904 [3:08:23<20:10:44, 1.32s/it] 11%|█ | 6785/61904 [3:08:24<20:01:50, 1.31s/it] 11%|█ | 6786/61904 [3:08:26<19:59:55, 1.31s/it] 11%|█ | 6787/61904 [3:08:27<20:28:50, 1.34s/it] 11%|█ | 6788/61904 [3:08:28<20:35:21, 1.34s/it] 11%|█ | 6789/61904 [3:08:30<20:37:33, 1.35s/it] 11%|█ | 6790/61904 [3:08:31<20:47:50, 1.36s/it] 11%|█ | 6791/61904 [3:08:32<20:35:55, 1.35s/it] 11%|█ | 6792/61904 [3:08:34<20:30:26, 1.34s/it] 11%|█ | 6793/61904 [3:08:35<20:18:15, 1.33s/it] 11%|█ | 6794/61904 [3:08:36<20:42:59, 1.35s/it] 11%|█ | 6795/61904 [3:08:38<20:21:49, 1.33s/it] 11%|█ | 6796/61904 [3:08:39<20:58:06, 1.37s/it] 11%|█ | 6797/61904 [3:08:40<20:29:49, 1.34s/it] 11%|█ | 6798/61904 [3:08:42<20:40:47, 1.35s/it] 11%|█ | 6799/61904 [3:08:43<20:20:36, 1.33s/it] 11%|█ | 6800/61904 [3:08:44<20:42:08, 1.35s/it] {'loss': 2.9025, 'learning_rate': 1.8930377285103074e-07, 'epoch': 1.76} + 11%|█ | 6800/61904 [3:08:44<20:42:08, 1.35s/it] 11%|█ | 6801/61904 [3:08:46<21:00:00, 1.37s/it] 11%|█ | 6802/61904 [3:08:47<21:06:59, 1.38s/it] 11%|█ | 6803/61904 [3:08:49<22:04:38, 1.44s/it] 11%|█ | 6804/61904 [3:08:50<21:30:00, 1.40s/it] 11%|█ | 6805/61904 [3:08:51<20:51:54, 1.36s/it] 11%|█ | 6806/61904 [3:08:53<20:57:41, 1.37s/it] 11%|█ | 6807/61904 [3:08:54<20:08:44, 1.32s/it] 11%|█ | 6808/61904 [3:08:55<20:04:02, 1.31s/it] 11%|█ | 6809/61904 [3:08:57<20:02:32, 1.31s/it] 11%|█ | 6810/61904 [3:08:58<20:03:27, 1.31s/it] 11%|█ | 6811/61904 [3:08:59<19:48:01, 1.29s/it] 11%|█ | 6812/61904 [3:09:01<20:35:21, 1.35s/it] 11%|█ | 6813/61904 [3:09:02<21:44:01, 1.42s/it] 11%|█ | 6814/61904 [3:09:04<21:44:17, 1.42s/it] 11%|█ | 6815/61904 [3:09:05<21:41:10, 1.42s/it] 11%|█ | 6816/61904 [3:09:06<21:04:34, 1.38s/it] 11%|█ | 6817/61904 [3:09:08<20:21:30, 1.33s/it] 11%|█ | 6818/61904 [3:09:09<20:11:56, 1.32s/it] 11%|█ | 6819/61904 [3:09:10<20:07:19, 1.32s/it] 11%|█ | 6820/61904 [3:09:12<20:05:10, 1.31s/it] {'loss': 2.9723, 'learning_rate': 1.8927136004148837e-07, 'epoch': 1.76} + 11%|█ | 6820/61904 [3:09:12<20:05:10, 1.31s/it] 11%|█ | 6821/61904 [3:09:13<20:28:19, 1.34s/it] 11%|█ | 6822/61904 [3:09:14<20:56:27, 1.37s/it] 11%|█ | 6823/61904 [3:09:16<21:13:11, 1.39s/it] 11%|█ | 6824/61904 [3:09:17<21:52:12, 1.43s/it] 11%|█ | 6825/61904 [3:09:19<21:07:51, 1.38s/it] 11%|█ | 6826/61904 [3:09:20<20:40:13, 1.35s/it] 11%|█ | 6827/61904 [3:09:21<20:33:41, 1.34s/it] 11%|█ | 6828/61904 [3:09:23<20:30:05, 1.34s/it] 11%|█ | 6829/61904 [3:09:24<20:22:13, 1.33s/it] 11%|█ | 6830/61904 [3:09:25<20:40:59, 1.35s/it] 11%|█ | 6831/61904 [3:09:27<20:33:52, 1.34s/it] 11%|█ | 6832/61904 [3:09:28<20:56:49, 1.37s/it] 11%|█ | 6833/61904 [3:09:29<21:20:32, 1.40s/it] 11%|█ | 6834/61904 [3:09:31<22:09:46, 1.45s/it] 11%|█ | 6835/61904 [3:09:32<21:53:17, 1.43s/it] 11%|█ | 6836/61904 [3:09:34<21:25:52, 1.40s/it] 11%|█ | 6837/61904 [3:09:35<21:27:54, 1.40s/it] 11%|█ | 6838/61904 [3:09:36<20:52:00, 1.36s/it] 11%|█ | 6839/61904 [3:09:38<20:34:27, 1.35s/it] 11%|█ | 6840/61904 [3:09:39<20:19:16, 1.33s/it] {'loss': 2.9768, 'learning_rate': 1.8923894723194606e-07, 'epoch': 1.77} + 11%|█ | 6840/61904 [3:09:39<20:19:16, 1.33s/it] 11%|█ | 6841/61904 [3:09:40<20:00:24, 1.31s/it] 11%|█ | 6842/61904 [3:09:42<19:45:51, 1.29s/it] 11%|█ | 6843/61904 [3:09:43<19:57:28, 1.30s/it] 11%|█ | 6844/61904 [3:09:44<20:00:17, 1.31s/it] 11%|█ | 6845/61904 [3:09:45<19:58:17, 1.31s/it] 11%|█ | 6846/61904 [3:09:47<20:05:32, 1.31s/it] 11%|█ | 6847/61904 [3:09:48<20:24:38, 1.33s/it] 11%|█ | 6848/61904 [3:09:49<19:30:15, 1.28s/it] 11%|█ | 6849/61904 [3:09:51<19:17:13, 1.26s/it] 11%|█ | 6850/61904 [3:09:52<19:59:30, 1.31s/it] 11%|█ | 6851/61904 [3:09:53<20:15:09, 1.32s/it] 11%|█ | 6852/61904 [3:09:55<20:22:26, 1.33s/it] 11%|█ | 6853/61904 [3:09:56<20:20:26, 1.33s/it] 11%|█ | 6854/61904 [3:09:57<20:08:47, 1.32s/it] 11%|█ | 6855/61904 [3:09:59<20:54:33, 1.37s/it] 11%|█ | 6856/61904 [3:10:00<20:58:53, 1.37s/it] 11%|█ | 6857/61904 [3:10:02<21:04:37, 1.38s/it] 11%|█ | 6858/61904 [3:10:03<20:59:37, 1.37s/it] 11%|█ | 6859/61904 [3:10:04<20:35:43, 1.35s/it] 11%|█ | 6860/61904 [3:10:06<22:00:00, 1.44s/it] {'loss': 2.8984, 'learning_rate': 1.8920653442240375e-07, 'epoch': 1.77} + 11%|█ | 6860/61904 [3:10:06<22:00:00, 1.44s/it] 11%|█ | 6861/61904 [3:10:07<21:37:22, 1.41s/it] 11%|█ | 6862/61904 [3:10:09<21:43:40, 1.42s/it] 11%|█ | 6863/61904 [3:10:10<21:04:00, 1.38s/it] 11%|█ | 6864/61904 [3:10:11<20:48:37, 1.36s/it] 11%|█ | 6865/61904 [3:10:13<20:24:12, 1.33s/it] 11%|█ | 6866/61904 [3:10:14<20:50:30, 1.36s/it] 11%|█ | 6867/61904 [3:10:15<20:43:59, 1.36s/it] 11%|█ | 6868/61904 [3:10:17<20:37:21, 1.35s/it] 11%|█ | 6869/61904 [3:10:18<20:28:50, 1.34s/it] 11%|█ | 6870/61904 [3:10:19<21:27:23, 1.40s/it] 11%|█ | 6871/61904 [3:10:21<21:13:20, 1.39s/it] 11%|█ | 6872/61904 [3:10:22<20:44:11, 1.36s/it] 11%|█ | 6873/61904 [3:10:23<20:47:49, 1.36s/it] 11%|█ | 6874/61904 [3:10:25<20:53:23, 1.37s/it] 11%|█ | 6875/61904 [3:10:26<20:43:15, 1.36s/it] 11%|█ | 6876/61904 [3:10:27<20:16:25, 1.33s/it] 11%|█ | 6877/61904 [3:10:29<21:02:54, 1.38s/it] 11%|█ | 6878/61904 [3:10:30<21:08:13, 1.38s/it] 11%|█ | 6879/61904 [3:10:32<20:57:43, 1.37s/it] 11%|█ | 6880/61904 [3:10:33<21:10:43, 1.39s/it] {'loss': 2.9167, 'learning_rate': 1.8917412161286138e-07, 'epoch': 1.78} + 11%|█ | 6880/61904 [3:10:33<21:10:43, 1.39s/it] 11%|█ | 6881/61904 [3:10:35<21:16:38, 1.39s/it] 11%|█ | 6882/61904 [3:10:36<21:22:17, 1.40s/it] 11%|█ | 6883/61904 [3:10:38<22:07:33, 1.45s/it] 11%|█ | 6884/61904 [3:10:39<21:25:52, 1.40s/it] 11%|█ | 6885/61904 [3:10:40<20:56:39, 1.37s/it] 11%|█ | 6886/61904 [3:10:42<21:14:18, 1.39s/it] 11%|█ | 6887/61904 [3:10:43<21:17:42, 1.39s/it] 11%|█ | 6888/61904 [3:10:44<21:28:43, 1.41s/it] 11%|█ | 6889/61904 [3:10:46<22:23:49, 1.47s/it] 11%|█ | 6890/61904 [3:10:47<22:08:49, 1.45s/it] 11%|█ | 6891/61904 [3:10:49<22:01:44, 1.44s/it] 11%|█ | 6892/61904 [3:10:50<21:38:08, 1.42s/it] 11%|█ | 6893/61904 [3:10:52<21:39:42, 1.42s/it] 11%|█ | 6894/61904 [3:10:53<21:14:40, 1.39s/it] 11%|█ | 6895/61904 [3:10:54<21:46:46, 1.43s/it] 11%|█ | 6896/61904 [3:10:56<21:10:33, 1.39s/it] 11%|█ | 6897/61904 [3:10:57<20:44:53, 1.36s/it] 11%|█ | 6898/61904 [3:10:58<20:38:26, 1.35s/it] 11%|█ | 6899/61904 [3:11:00<19:58:04, 1.31s/it] 11%|█ | 6900/61904 [3:11:01<20:06:21, 1.32s/it] {'loss': 2.9561, 'learning_rate': 1.8914170880331907e-07, 'epoch': 1.78} + 11%|█ | 6900/61904 [3:11:01<20:06:21, 1.32s/it] 11%|█ | 6901/61904 [3:11:02<20:03:27, 1.31s/it] 11%|█ | 6902/61904 [3:11:04<20:42:43, 1.36s/it] 11%|█ | 6903/61904 [3:11:05<20:46:22, 1.36s/it] 11%|█ | 6904/61904 [3:11:07<21:46:29, 1.43s/it] 11%|█ | 6905/61904 [3:11:08<20:58:54, 1.37s/it] 11%|█ | 6906/61904 [3:11:09<20:31:55, 1.34s/it] 11%|█ | 6907/61904 [3:11:11<21:27:39, 1.40s/it] 11%|█ | 6908/61904 [3:11:12<20:44:19, 1.36s/it] 11%|█ | 6909/61904 [3:11:13<20:41:42, 1.35s/it] 11%|█ | 6910/61904 [3:11:15<20:25:37, 1.34s/it] 11%|█ | 6911/61904 [3:11:16<20:25:03, 1.34s/it] 11%|█ | 6912/61904 [3:11:17<20:41:58, 1.36s/it] 11%|█ | 6913/61904 [3:11:19<20:47:43, 1.36s/it] 11%|█ | 6914/61904 [3:11:20<20:36:58, 1.35s/it] 11%|█ | 6915/61904 [3:11:21<21:03:21, 1.38s/it] 11%|█ | 6916/61904 [3:11:23<21:28:29, 1.41s/it] 11%|█ | 6917/61904 [3:11:24<21:14:37, 1.39s/it] 11%|█ | 6918/61904 [3:11:26<21:25:16, 1.40s/it] 11%|█ | 6919/61904 [3:11:27<22:01:30, 1.44s/it] 11%|█ | 6920/61904 [3:11:29<22:07:20, 1.45s/it] {'loss': 2.8689, 'learning_rate': 1.8910929599377673e-07, 'epoch': 1.79} + 11%|█ | 6920/61904 [3:11:29<22:07:20, 1.45s/it] 11%|█ | 6921/61904 [3:11:30<21:30:32, 1.41s/it] 11%|█ | 6922/61904 [3:11:31<20:59:03, 1.37s/it] 11%|█ | 6923/61904 [3:11:33<20:53:49, 1.37s/it] 11%|█ | 6924/61904 [3:11:34<20:26:16, 1.34s/it] 11%|█ | 6925/61904 [3:11:35<20:19:11, 1.33s/it] 11%|█ | 6926/61904 [3:11:37<20:32:40, 1.35s/it] 11%|█ | 6927/61904 [3:11:38<20:19:20, 1.33s/it] 11%|█ | 6928/61904 [3:11:39<20:22:42, 1.33s/it] 11%|█ | 6929/61904 [3:11:41<20:33:24, 1.35s/it] 11%|█ | 6930/61904 [3:11:42<20:20:24, 1.33s/it] 11%|█ | 6931/61904 [3:11:43<20:13:28, 1.32s/it] 11%|█ | 6932/61904 [3:11:45<20:56:25, 1.37s/it] 11%|█ | 6933/61904 [3:11:46<20:42:12, 1.36s/it] 11%|█ | 6934/61904 [3:11:47<20:35:44, 1.35s/it] 11%|█ | 6935/61904 [3:11:49<19:59:51, 1.31s/it] 11%|█ | 6936/61904 [3:11:50<20:43:07, 1.36s/it] 11%|█ | 6937/61904 [3:11:51<21:07:37, 1.38s/it] 11%|█ | 6938/61904 [3:11:53<21:24:33, 1.40s/it] 11%|█ | 6939/61904 [3:11:54<20:42:35, 1.36s/it] 11%|█ | 6940/61904 [3:11:55<20:28:31, 1.34s/it] {'loss': 2.9081, 'learning_rate': 1.890768831842344e-07, 'epoch': 1.79} + 11%|█ | 6940/61904 [3:11:55<20:28:31, 1.34s/it] 11%|█ | 6941/61904 [3:11:57<20:11:29, 1.32s/it] 11%|█ | 6942/61904 [3:11:58<20:12:31, 1.32s/it] 11%|█ | 6943/61904 [3:11:59<19:42:18, 1.29s/it] 11%|█ | 6944/61904 [3:12:01<20:11:13, 1.32s/it] 11%|█ | 6945/61904 [3:12:02<20:15:43, 1.33s/it] 11%|█ | 6946/61904 [3:12:03<19:55:38, 1.31s/it] 11%|█ | 6947/61904 [3:12:05<19:49:30, 1.30s/it] 11%|█ | 6948/61904 [3:12:06<20:19:41, 1.33s/it] 11%|█ | 6949/61904 [3:12:07<20:00:28, 1.31s/it] 11%|█ | 6950/61904 [3:12:09<20:41:13, 1.36s/it] 11%|█ | 6951/61904 [3:12:10<21:28:28, 1.41s/it] 11%|█ | 6952/61904 [3:12:11<20:44:11, 1.36s/it] 11%|█ | 6953/61904 [3:12:13<20:34:26, 1.35s/it] 11%|█ | 6954/61904 [3:12:14<20:27:27, 1.34s/it] 11%|█ | 6955/61904 [3:12:16<20:35:41, 1.35s/it] 11%|█ | 6956/61904 [3:12:17<20:56:38, 1.37s/it] 11%|█ | 6957/61904 [3:12:18<20:45:58, 1.36s/it] 11%|█ | 6958/61904 [3:12:20<20:58:57, 1.37s/it] 11%|█ | 6959/61904 [3:12:21<20:43:06, 1.36s/it] 11%|█ | 6960/61904 [3:12:22<20:00:12, 1.31s/it] {'loss': 2.8818, 'learning_rate': 1.8904447037469208e-07, 'epoch': 1.8} + 11%|█ | 6960/61904 [3:12:22<20:00:12, 1.31s/it] 11%|█ | 6961/61904 [3:12:24<20:26:00, 1.34s/it] 11%|█ | 6962/61904 [3:12:25<21:00:27, 1.38s/it] 11%|█ | 6963/61904 [3:12:26<20:48:50, 1.36s/it] 11%|█ | 6964/61904 [3:12:28<20:40:32, 1.35s/it] 11%|█▏ | 6965/61904 [3:12:29<20:49:11, 1.36s/it] 11%|█▏ | 6966/61904 [3:12:31<21:25:54, 1.40s/it] 11%|█▏ | 6967/61904 [3:12:32<20:53:22, 1.37s/it] 11%|█▏ | 6968/61904 [3:12:33<20:09:42, 1.32s/it] 11%|█▏ | 6969/61904 [3:12:34<20:13:51, 1.33s/it] 11%|█▏ | 6970/61904 [3:12:36<21:09:56, 1.39s/it] 11%|█▏ | 6971/61904 [3:12:37<20:53:10, 1.37s/it] 11%|█▏ | 6972/61904 [3:12:39<20:32:02, 1.35s/it] 11%|█▏ | 6973/61904 [3:12:40<20:23:30, 1.34s/it] 11%|█▏ | 6974/61904 [3:12:41<20:43:47, 1.36s/it] 11%|█▏ | 6975/61904 [3:12:43<20:05:36, 1.32s/it] 11%|█▏ | 6976/61904 [3:12:44<20:26:24, 1.34s/it] 11%|█▏ | 6977/61904 [3:12:45<21:14:57, 1.39s/it] 11%|█▏ | 6978/61904 [3:12:47<20:20:30, 1.33s/it] 11%|█▏ | 6979/61904 [3:12:48<20:08:01, 1.32s/it] 11%|█▏ | 6980/61904 [3:12:49<20:02:50, 1.31s/it] {'loss': 2.9503, 'learning_rate': 1.8901205756514975e-07, 'epoch': 1.8} + 11%|█▏ | 6980/61904 [3:12:49<20:02:50, 1.31s/it] 11%|█▏ | 6981/61904 [3:12:51<19:57:26, 1.31s/it] 11%|█▏ | 6982/61904 [3:12:52<20:16:16, 1.33s/it] 11%|█▏ | 6983/61904 [3:12:53<20:10:55, 1.32s/it] 11%|█▏ | 6984/61904 [3:12:54<19:48:01, 1.30s/it] 11%|█▏ | 6985/61904 [3:12:56<20:08:51, 1.32s/it] 11%|█▏ | 6986/61904 [3:12:57<20:14:50, 1.33s/it] 11%|█▏ | 6987/61904 [3:12:58<20:15:19, 1.33s/it] 11%|█▏ | 6988/61904 [3:13:00<20:03:32, 1.31s/it] 11%|█▏ | 6989/61904 [3:13:01<20:21:45, 1.33s/it] 11%|█▏ | 6990/61904 [3:13:03<20:31:56, 1.35s/it] 11%|█▏ | 6991/61904 [3:13:04<20:40:32, 1.36s/it] 11%|█▏ | 6992/61904 [3:13:05<21:18:17, 1.40s/it] 11%|█▏ | 6993/61904 [3:13:07<20:46:43, 1.36s/it] 11%|█▏ | 6994/61904 [3:13:08<20:48:03, 1.36s/it] 11%|█▏ | 6995/61904 [3:13:09<20:14:01, 1.33s/it] 11%|█▏ | 6996/61904 [3:13:11<20:16:01, 1.33s/it] 11%|█▏ | 6997/61904 [3:13:12<19:50:32, 1.30s/it] 11%|█▏ | 6998/61904 [3:13:13<20:05:44, 1.32s/it] 11%|█▏ | 6999/61904 [3:13:15<20:48:13, 1.36s/it] 11%|█▏ | 7000/61904 [3:13:16<20:55:11, 1.37s/it] {'loss': 2.985, 'learning_rate': 1.889796447556074e-07, 'epoch': 1.81} + 11%|█▏ | 7000/61904 [3:13:16<20:55:11, 1.37s/it] 11%|█▏ | 7001/61904 [3:13:17<20:46:56, 1.36s/it] 11%|█▏ | 7002/61904 [3:13:19<20:28:35, 1.34s/it] 11%|█▏ | 7003/61904 [3:13:20<19:51:35, 1.30s/it] 11%|█▏ | 7004/61904 [3:13:21<20:44:04, 1.36s/it] 11%|█▏ | 7005/61904 [3:13:23<20:17:46, 1.33s/it] 11%|█▏ | 7006/61904 [3:13:24<20:45:39, 1.36s/it] 11%|█▏ | 7007/61904 [3:13:26<21:17:10, 1.40s/it] 11%|█▏ | 7008/61904 [3:13:27<20:26:06, 1.34s/it] 11%|█▏ | 7009/61904 [3:13:28<20:27:48, 1.34s/it] 11%|█▏ | 7010/61904 [3:13:29<20:16:48, 1.33s/it] 11%|█▏ | 7011/61904 [3:13:31<20:28:24, 1.34s/it] 11%|█▏ | 7012/61904 [3:13:32<20:15:35, 1.33s/it] 11%|█▏ | 7013/61904 [3:13:33<20:04:07, 1.32s/it] 11%|█▏ | 7014/61904 [3:13:35<19:48:23, 1.30s/it] 11%|█▏ | 7015/61904 [3:13:36<19:41:52, 1.29s/it] 11%|█▏ | 7016/61904 [3:13:37<20:01:08, 1.31s/it] 11%|█▏ | 7017/61904 [3:13:39<20:03:25, 1.32s/it] 11%|█▏ | 7018/61904 [3:13:40<20:11:46, 1.32s/it] 11%|█▏ | 7019/61904 [3:13:41<19:59:07, 1.31s/it] 11%|█▏ | 7020/61904 [3:13:43<20:04:26, 1.32s/it] {'loss': 2.9812, 'learning_rate': 1.889472319460651e-07, 'epoch': 1.81} + 11%|█▏ | 7020/61904 [3:13:43<20:04:26, 1.32s/it] 11%|█▏ | 7021/61904 [3:13:44<20:16:59, 1.33s/it] 11%|█▏ | 7022/61904 [3:13:45<20:34:47, 1.35s/it] 11%|█▏ | 7023/61904 [3:13:47<20:36:03, 1.35s/it] 11%|█▏ | 7024/61904 [3:13:48<21:07:17, 1.39s/it] 11%|█▏ | 7025/61904 [3:13:49<20:46:51, 1.36s/it] 11%|█▏ | 7026/61904 [3:13:51<20:46:28, 1.36s/it] 11%|█▏ | 7027/61904 [3:13:52<20:20:39, 1.33s/it] 11%|█▏ | 7028/61904 [3:13:54<20:46:12, 1.36s/it] 11%|█▏ | 7029/61904 [3:13:55<21:05:38, 1.38s/it] 11%|█▏ | 7030/61904 [3:13:56<21:21:50, 1.40s/it] 11%|█▏ | 7031/61904 [3:13:58<21:01:25, 1.38s/it] 11%|█▏ | 7032/61904 [3:13:59<20:50:26, 1.37s/it] 11%|█▏ | 7033/61904 [3:14:00<20:22:56, 1.34s/it] 11%|█▏ | 7034/61904 [3:14:02<20:42:41, 1.36s/it] 11%|█▏ | 7035/61904 [3:14:03<20:29:33, 1.34s/it] 11%|█▏ | 7036/61904 [3:14:04<20:43:58, 1.36s/it] 11%|█▏ | 7037/61904 [3:14:06<21:24:41, 1.40s/it] 11%|█▏ | 7038/61904 [3:14:08<22:12:36, 1.46s/it] 11%|█▏ | 7039/61904 [3:14:09<21:47:42, 1.43s/it] 11%|█▏ | 7040/61904 [3:14:10<22:01:31, 1.45s/it] {'loss': 2.9244, 'learning_rate': 1.8891481913652273e-07, 'epoch': 1.82} + 11%|█▏ | 7040/61904 [3:14:10<22:01:31, 1.45s/it] 11%|█▏ | 7041/61904 [3:14:12<21:27:28, 1.41s/it] 11%|█▏ | 7042/61904 [3:14:13<21:06:57, 1.39s/it] 11%|█▏ | 7043/61904 [3:14:14<21:14:53, 1.39s/it] 11%|█▏ | 7044/61904 [3:14:16<20:50:33, 1.37s/it] 11%|█▏ | 7045/61904 [3:14:17<20:32:45, 1.35s/it] 11%|█▏ | 7046/61904 [3:14:18<20:10:13, 1.32s/it] 11%|█▏ | 7047/61904 [3:14:20<20:28:56, 1.34s/it] 11%|█▏ | 7048/61904 [3:14:21<20:21:58, 1.34s/it] 11%|█▏ | 7049/61904 [3:14:22<20:25:46, 1.34s/it] 11%|█▏ | 7050/61904 [3:14:24<20:08:30, 1.32s/it] 11%|█▏ | 7051/61904 [3:14:25<20:11:07, 1.32s/it] 11%|█▏ | 7052/61904 [3:14:26<19:47:12, 1.30s/it] 11%|█▏ | 7053/61904 [3:14:27<19:29:04, 1.28s/it] 11%|█▏ | 7054/61904 [3:14:29<20:00:12, 1.31s/it] 11%|█▏ | 7055/61904 [3:14:30<20:17:05, 1.33s/it] 11%|█▏ | 7056/61904 [3:14:32<20:07:28, 1.32s/it] 11%|█▏ | 7057/61904 [3:14:33<20:05:35, 1.32s/it] 11%|█▏ | 7058/61904 [3:14:34<20:24:18, 1.34s/it] 11%|█▏ | 7059/61904 [3:14:36<20:21:19, 1.34s/it] 11%|█▏ | 7060/61904 [3:14:37<20:39:54, 1.36s/it] {'loss': 2.9199, 'learning_rate': 1.8888240632698042e-07, 'epoch': 1.82} + 11%|█▏ | 7060/61904 [3:14:37<20:39:54, 1.36s/it] 11%|█▏ | 7061/61904 [3:14:38<20:38:21, 1.35s/it] 11%|█▏ | 7062/61904 [3:14:40<20:48:57, 1.37s/it] 11%|█▏ | 7063/61904 [3:14:41<20:27:45, 1.34s/it] 11%|█▏ | 7064/61904 [3:14:42<20:49:44, 1.37s/it] 11%|█▏ | 7065/61904 [3:14:44<20:22:44, 1.34s/it] 11%|█▏ | 7066/61904 [3:14:45<21:00:33, 1.38s/it] 11%|█▏ | 7067/61904 [3:14:47<20:50:18, 1.37s/it] 11%|█▏ | 7068/61904 [3:14:48<20:32:48, 1.35s/it] 11%|█▏ | 7069/61904 [3:14:49<20:06:37, 1.32s/it] 11%|█▏ | 7070/61904 [3:14:50<20:30:52, 1.35s/it] 11%|█▏ | 7071/61904 [3:14:52<20:20:23, 1.34s/it] 11%|█▏ | 7072/61904 [3:14:53<20:01:54, 1.32s/it] 11%|█▏ | 7073/61904 [3:14:55<20:37:30, 1.35s/it] 11%|█▏ | 7074/61904 [3:14:56<20:25:09, 1.34s/it] 11%|█▏ | 7075/61904 [3:14:57<20:10:47, 1.32s/it] 11%|█▏ | 7076/61904 [3:14:58<20:06:58, 1.32s/it] 11%|█▏ | 7077/61904 [3:15:00<21:12:36, 1.39s/it] 11%|█▏ | 7078/61904 [3:15:01<21:40:31, 1.42s/it] 11%|█▏ | 7079/61904 [3:15:03<21:31:31, 1.41s/it] 11%|█▏ | 7080/61904 [3:15:04<21:40:46, 1.42s/it] {'loss': 2.9121, 'learning_rate': 1.8884999351743808e-07, 'epoch': 1.83} + 11%|█▏ | 7080/61904 [3:15:04<21:40:46, 1.42s/it] 11%|█▏ | 7081/61904 [3:15:06<21:26:01, 1.41s/it] 11%|█▏ | 7082/61904 [3:15:07<22:26:41, 1.47s/it] 11%|█▏ | 7083/61904 [3:15:09<22:17:39, 1.46s/it] 11%|█▏ | 7084/61904 [3:15:10<22:43:06, 1.49s/it] 11%|█▏ | 7085/61904 [3:15:12<22:03:57, 1.45s/it] 11%|█▏ | 7086/61904 [3:15:13<21:52:58, 1.44s/it] 11%|█▏ | 7087/61904 [3:15:14<21:05:03, 1.38s/it] 11%|█▏ | 7088/61904 [3:15:16<20:54:14, 1.37s/it] 11%|█▏ | 7089/61904 [3:15:17<21:06:22, 1.39s/it] 11%|█▏ | 7090/61904 [3:15:18<21:09:07, 1.39s/it] 11%|█▏ | 7091/61904 [3:15:20<21:12:40, 1.39s/it] 11%|█▏ | 7092/61904 [3:15:21<20:33:25, 1.35s/it] 11%|█▏ | 7093/61904 [3:15:23<21:01:10, 1.38s/it] 11%|█▏ | 7094/61904 [3:15:24<20:46:39, 1.36s/it] 11%|█▏ | 7095/61904 [3:15:25<20:43:18, 1.36s/it] 11%|█▏ | 7096/61904 [3:15:26<20:04:53, 1.32s/it] 11%|█▏ | 7097/61904 [3:15:28<21:18:25, 1.40s/it] 11%|█▏ | 7098/61904 [3:15:29<21:14:39, 1.40s/it] 11%|█▏ | 7099/61904 [3:15:31<20:53:07, 1.37s/it] 11%|█▏ | 7100/61904 [3:15:32<20:37:46, 1.36s/it] {'loss': 2.9476, 'learning_rate': 1.8881758070789574e-07, 'epoch': 1.83} + 11%|█▏ | 7100/61904 [3:15:32<20:37:46, 1.36s/it] 11%|█▏ | 7101/61904 [3:15:34<21:05:25, 1.39s/it] 11%|█▏ | 7102/61904 [3:15:35<20:50:10, 1.37s/it] 11%|█▏ | 7103/61904 [3:15:36<20:46:08, 1.36s/it] 11%|█▏ | 7104/61904 [3:15:38<20:59:54, 1.38s/it] 11%|█▏ | 7105/61904 [3:15:39<20:48:26, 1.37s/it] 11%|█▏ | 7106/61904 [3:15:41<21:48:51, 1.43s/it] 11%|█▏ | 7107/61904 [3:15:42<21:07:28, 1.39s/it] 11%|█▏ | 7108/61904 [3:15:43<20:45:52, 1.36s/it] 11%|█▏ | 7109/61904 [3:15:44<20:28:18, 1.34s/it] 11%|█▏ | 7110/61904 [3:15:46<20:49:41, 1.37s/it] 11%|█▏ | 7111/61904 [3:15:47<21:12:19, 1.39s/it] 11%|█▏ | 7112/61904 [3:15:49<20:40:33, 1.36s/it] 11%|█▏ | 7113/61904 [3:15:50<20:38:00, 1.36s/it] 11%|█▏ | 7114/61904 [3:15:52<21:40:33, 1.42s/it] 11%|█▏ | 7115/61904 [3:15:53<22:11:47, 1.46s/it] 11%|█▏ | 7116/61904 [3:15:54<21:44:14, 1.43s/it] 11%|█▏ | 7117/61904 [3:15:56<22:04:32, 1.45s/it] 11%|█▏ | 7118/61904 [3:15:57<21:42:19, 1.43s/it] 12%|█▏ | 7119/61904 [3:15:59<21:49:42, 1.43s/it] 12%|█▏ | 7120/61904 [3:16:00<21:15:05, 1.40s/it] {'loss': 2.9117, 'learning_rate': 1.8878516789835343e-07, 'epoch': 1.84} + 12%|█▏ | 7120/61904 [3:16:00<21:15:05, 1.40s/it] 12%|█▏ | 7121/61904 [3:16:01<21:19:10, 1.40s/it] 12%|█▏ | 7122/61904 [3:16:03<21:15:52, 1.40s/it] 12%|█▏ | 7123/61904 [3:16:04<21:22:44, 1.40s/it] 12%|█▏ | 7124/61904 [3:16:06<22:03:56, 1.45s/it] 12%|█▏ | 7125/61904 [3:16:07<21:08:43, 1.39s/it] 12%|█▏ | 7126/61904 [3:16:08<20:45:57, 1.36s/it] 12%|█▏ | 7127/61904 [3:16:10<20:24:25, 1.34s/it] 12%|█▏ | 7128/61904 [3:16:11<20:30:51, 1.35s/it] 12%|█▏ | 7129/61904 [3:16:12<20:24:47, 1.34s/it] 12%|█▏ | 7130/61904 [3:16:14<20:58:35, 1.38s/it] 12%|█▏ | 7131/61904 [3:16:15<20:33:44, 1.35s/it] 12%|█▏ | 7132/61904 [3:16:17<20:42:55, 1.36s/it] 12%|█▏ | 7133/61904 [3:16:18<21:03:28, 1.38s/it] 12%|█▏ | 7134/61904 [3:16:19<21:30:01, 1.41s/it] 12%|█▏ | 7135/61904 [3:16:21<20:28:28, 1.35s/it] 12%|█▏ | 7136/61904 [3:16:22<20:57:42, 1.38s/it] 12%|█▏ | 7137/61904 [3:16:24<21:46:41, 1.43s/it] 12%|█▏ | 7138/61904 [3:16:25<21:41:05, 1.43s/it] 12%|█▏ | 7139/61904 [3:16:26<20:55:15, 1.38s/it] 12%|█▏ | 7140/61904 [3:16:28<20:32:18, 1.35s/it] {'loss': 2.8593, 'learning_rate': 1.887527550888111e-07, 'epoch': 1.85} + 12%|█▏ | 7140/61904 [3:16:28<20:32:18, 1.35s/it] 12%|█▏ | 7141/61904 [3:16:29<20:35:30, 1.35s/it] 12%|█▏ | 7142/61904 [3:16:30<20:15:34, 1.33s/it] 12%|█▏ | 7143/61904 [3:16:32<20:31:00, 1.35s/it] 12%|█▏ | 7144/61904 [3:16:33<20:36:34, 1.35s/it] 12%|█▏ | 7145/61904 [3:16:34<20:30:21, 1.35s/it] 12%|█▏ | 7146/61904 [3:16:36<21:35:37, 1.42s/it] 12%|█▏ | 7147/61904 [3:16:37<20:56:03, 1.38s/it] 12%|█▏ | 7148/61904 [3:16:39<20:58:22, 1.38s/it] 12%|█▏ | 7149/61904 [3:16:40<21:18:54, 1.40s/it] 12%|█▏ | 7150/61904 [3:16:41<21:01:40, 1.38s/it] 12%|█▏ | 7151/61904 [3:16:43<21:11:06, 1.39s/it] 12%|█▏ | 7152/61904 [3:16:44<21:17:03, 1.40s/it] 12%|█▏ | 7153/61904 [3:16:46<20:52:11, 1.37s/it] 12%|█▏ | 7154/61904 [3:16:47<20:52:59, 1.37s/it] 12%|█▏ | 7155/61904 [3:16:48<20:11:02, 1.33s/it] 12%|█▏ | 7156/61904 [3:16:49<20:14:56, 1.33s/it] 12%|█▏ | 7157/61904 [3:16:51<21:24:50, 1.41s/it] 12%|█▏ | 7158/61904 [3:16:52<21:21:10, 1.40s/it] 12%|█▏ | 7159/61904 [3:16:54<21:02:26, 1.38s/it] 12%|█▏ | 7160/61904 [3:16:55<20:29:16, 1.35s/it] {'loss': 2.9515, 'learning_rate': 1.8872034227926876e-07, 'epoch': 1.85} + 12%|█▏ | 7160/61904 [3:16:55<20:29:16, 1.35s/it] 12%|█▏ | 7161/61904 [3:16:56<20:15:53, 1.33s/it] 12%|█▏ | 7162/61904 [3:16:58<20:05:52, 1.32s/it] 12%|█▏ | 7163/61904 [3:16:59<20:12:58, 1.33s/it] 12%|█▏ | 7164/61904 [3:17:00<20:01:02, 1.32s/it] 12%|█▏ | 7165/61904 [3:17:02<20:01:14, 1.32s/it] 12%|█▏ | 7166/61904 [3:17:03<20:02:07, 1.32s/it] 12%|█▏ | 7167/61904 [3:17:04<19:51:56, 1.31s/it] 12%|█▏ | 7168/61904 [3:17:06<20:05:04, 1.32s/it] 12%|█▏ | 7169/61904 [3:17:07<19:48:43, 1.30s/it] 12%|█▏ | 7170/61904 [3:17:08<19:38:30, 1.29s/it] 12%|█▏ | 7171/61904 [3:17:10<20:18:51, 1.34s/it] 12%|█▏ | 7172/61904 [3:17:11<19:52:35, 1.31s/it] 12%|█▏ | 7173/61904 [3:17:12<19:42:09, 1.30s/it] 12%|█▏ | 7174/61904 [3:17:14<20:52:37, 1.37s/it] 12%|█▏ | 7175/61904 [3:17:15<20:27:10, 1.35s/it] 12%|█▏ | 7176/61904 [3:17:16<20:46:40, 1.37s/it] 12%|█▏ | 7177/61904 [3:17:18<20:29:31, 1.35s/it] 12%|█▏ | 7178/61904 [3:17:19<20:24:39, 1.34s/it] 12%|█▏ | 7179/61904 [3:17:20<21:12:31, 1.40s/it] 12%|█▏ | 7180/61904 [3:17:22<21:33:57, 1.42s/it] {'loss': 2.8816, 'learning_rate': 1.8868792946972644e-07, 'epoch': 1.86} + 12%|█▏ | 7180/61904 [3:17:22<21:33:57, 1.42s/it] 12%|█▏ | 7181/61904 [3:17:23<21:36:06, 1.42s/it] 12%|█▏ | 7182/61904 [3:17:25<21:19:59, 1.40s/it] 12%|█▏ | 7183/61904 [3:17:26<21:10:29, 1.39s/it] 12%|█▏ | 7184/61904 [3:17:27<21:10:35, 1.39s/it] 12%|█▏ | 7185/61904 [3:17:29<20:48:54, 1.37s/it] 12%|█▏ | 7186/61904 [3:17:30<20:50:12, 1.37s/it] 12%|█▏ | 7187/61904 [3:17:31<20:33:33, 1.35s/it] 12%|█▏ | 7188/61904 [3:17:33<20:00:18, 1.32s/it] 12%|█▏ | 7189/61904 [3:17:34<20:48:33, 1.37s/it] 12%|█▏ | 7190/61904 [3:17:36<21:10:11, 1.39s/it] 12%|█▏ | 7191/61904 [3:17:37<21:18:47, 1.40s/it] 12%|█▏ | 7192/61904 [3:17:38<21:24:55, 1.41s/it] 12%|█▏ | 7193/61904 [3:17:40<21:05:44, 1.39s/it] 12%|█▏ | 7194/61904 [3:17:41<20:26:35, 1.35s/it] 12%|█▏ | 7195/61904 [3:17:43<21:38:03, 1.42s/it] 12%|█▏ | 7196/61904 [3:17:44<22:08:46, 1.46s/it] 12%|█▏ | 7197/61904 [3:17:45<21:21:59, 1.41s/it] 12%|█▏ | 7198/61904 [3:17:47<21:33:25, 1.42s/it] 12%|█▏ | 7199/61904 [3:17:48<21:31:50, 1.42s/it] 12%|█▏ | 7200/61904 [3:17:50<21:12:06, 1.40s/it] {'loss': 2.8811, 'learning_rate': 1.8865551666018408e-07, 'epoch': 1.86} + 12%|█▏ | 7200/61904 [3:17:50<21:12:06, 1.40s/it] 12%|█▏ | 7201/61904 [3:17:51<21:27:00, 1.41s/it] 12%|█▏ | 7202/61904 [3:17:52<20:57:12, 1.38s/it] 12%|█▏ | 7203/61904 [3:17:54<20:30:20, 1.35s/it] 12%|█▏ | 7204/61904 [3:17:55<20:49:43, 1.37s/it] 12%|█▏ | 7205/61904 [3:17:57<21:08:41, 1.39s/it] 12%|█▏ | 7206/61904 [3:17:58<20:45:19, 1.37s/it] 12%|█▏ | 7207/61904 [3:17:59<20:36:14, 1.36s/it] 12%|█▏ | 7208/61904 [3:18:01<20:37:50, 1.36s/it] 12%|█▏ | 7209/61904 [3:18:02<20:25:08, 1.34s/it] 12%|█▏ | 7210/61904 [3:18:03<20:16:55, 1.33s/it] 12%|█▏ | 7211/61904 [3:18:05<20:52:16, 1.37s/it] 12%|█▏ | 7212/61904 [3:18:06<20:18:56, 1.34s/it] 12%|█▏ | 7213/61904 [3:18:07<20:34:11, 1.35s/it] 12%|█▏ | 7214/61904 [3:18:09<20:37:38, 1.36s/it] 12%|█▏ | 7215/61904 [3:18:10<20:50:31, 1.37s/it] 12%|█▏ | 7216/61904 [3:18:11<20:28:14, 1.35s/it] 12%|█▏ | 7217/61904 [3:18:13<20:27:58, 1.35s/it] 12%|█▏ | 7218/61904 [3:18:14<20:09:49, 1.33s/it] 12%|█▏ | 7219/61904 [3:18:15<20:33:33, 1.35s/it] 12%|█▏ | 7220/61904 [3:18:17<20:24:56, 1.34s/it] {'loss': 2.8955, 'learning_rate': 1.8862310385064177e-07, 'epoch': 1.87} + 12%|█▏ | 7220/61904 [3:18:17<20:24:56, 1.34s/it] 12%|█▏ | 7221/61904 [3:18:18<20:26:33, 1.35s/it] 12%|█▏ | 7222/61904 [3:18:19<20:23:33, 1.34s/it] 12%|█▏ | 7223/61904 [3:18:21<19:44:56, 1.30s/it] 12%|█▏ | 7224/61904 [3:18:22<20:01:17, 1.32s/it] 12%|█▏ | 7225/61904 [3:18:23<20:11:24, 1.33s/it] 12%|█▏ | 7226/61904 [3:18:25<19:50:56, 1.31s/it] 12%|█▏ | 7227/61904 [3:18:26<20:01:13, 1.32s/it] 12%|█▏ | 7228/61904 [3:18:27<20:30:04, 1.35s/it] 12%|█▏ | 7229/61904 [3:18:29<20:26:35, 1.35s/it] 12%|█▏ | 7230/61904 [3:18:30<20:23:03, 1.34s/it] 12%|█▏ | 7231/61904 [3:18:31<20:21:41, 1.34s/it] 12%|█▏ | 7232/61904 [3:18:33<19:59:32, 1.32s/it] 12%|█▏ | 7233/61904 [3:18:34<20:23:32, 1.34s/it] 12%|█▏ | 7234/61904 [3:18:35<20:33:22, 1.35s/it] 12%|█▏ | 7235/61904 [3:18:37<20:55:48, 1.38s/it] 12%|█▏ | 7236/61904 [3:18:38<20:35:25, 1.36s/it] 12%|█▏ | 7237/61904 [3:18:40<20:34:41, 1.36s/it] 12%|█▏ | 7238/61904 [3:18:41<22:33:23, 1.49s/it] 12%|█▏ | 7239/61904 [3:18:43<21:40:02, 1.43s/it] 12%|█▏ | 7240/61904 [3:18:44<21:18:27, 1.40s/it] {'loss': 2.8895, 'learning_rate': 1.8859069104109943e-07, 'epoch': 1.87} + 12%|█▏ | 7240/61904 [3:18:44<21:18:27, 1.40s/it] 12%|█▏ | 7241/61904 [3:18:45<20:55:53, 1.38s/it] 12%|█▏ | 7242/61904 [3:18:47<22:42:37, 1.50s/it] 12%|█▏ | 7243/61904 [3:18:48<21:43:30, 1.43s/it] 12%|█▏ | 7244/61904 [3:18:50<21:44:51, 1.43s/it] 12%|█▏ | 7245/61904 [3:18:51<21:39:52, 1.43s/it] 12%|█▏ | 7246/61904 [3:18:52<21:02:37, 1.39s/it] 12%|█▏ | 7247/61904 [3:18:54<20:41:27, 1.36s/it] 12%|█▏ | 7248/61904 [3:18:55<21:10:24, 1.39s/it] 12%|█▏ | 7249/61904 [3:18:57<21:03:59, 1.39s/it] 12%|█▏ | 7250/61904 [3:18:58<20:48:11, 1.37s/it] 12%|█▏ | 7251/61904 [3:18:59<20:25:24, 1.35s/it] 12%|█▏ | 7252/61904 [3:19:01<21:05:42, 1.39s/it] 12%|█▏ | 7253/61904 [3:19:02<20:32:01, 1.35s/it] 12%|█▏ | 7254/61904 [3:19:03<21:20:28, 1.41s/it] 12%|█▏ | 7255/61904 [3:19:05<20:57:30, 1.38s/it] 12%|█▏ | 7256/61904 [3:19:06<20:28:47, 1.35s/it] 12%|█▏ | 7257/61904 [3:19:07<19:41:39, 1.30s/it] 12%|█▏ | 7258/61904 [3:19:09<20:25:53, 1.35s/it] 12%|█▏ | 7259/61904 [3:19:10<20:20:43, 1.34s/it] 12%|█▏ | 7260/61904 [3:19:12<21:23:21, 1.41s/it] {'loss': 2.8621, 'learning_rate': 1.885582782315571e-07, 'epoch': 1.88} + 12%|█▏ | 7260/61904 [3:19:12<21:23:21, 1.41s/it] 12%|█▏ | 7261/61904 [3:19:13<20:49:31, 1.37s/it] 12%|█▏ | 7262/61904 [3:19:14<20:41:43, 1.36s/it] 12%|█▏ | 7263/61904 [3:19:16<20:57:45, 1.38s/it] 12%|█▏ | 7264/61904 [3:19:17<20:57:04, 1.38s/it] 12%|█▏ | 7265/61904 [3:19:18<20:54:43, 1.38s/it] 12%|█▏ | 7266/61904 [3:19:20<20:35:33, 1.36s/it] 12%|█▏ | 7267/61904 [3:19:21<20:59:14, 1.38s/it] 12%|█▏ | 7268/61904 [3:19:23<21:32:27, 1.42s/it] 12%|█▏ | 7269/61904 [3:19:24<20:31:17, 1.35s/it] 12%|█▏ | 7270/61904 [3:19:25<20:24:11, 1.34s/it] 12%|█▏ | 7271/61904 [3:19:27<20:21:06, 1.34s/it] 12%|█▏ | 7272/61904 [3:19:28<20:20:04, 1.34s/it] 12%|█▏ | 7273/61904 [3:19:29<20:46:19, 1.37s/it] 12%|█▏ | 7274/61904 [3:19:31<21:24:16, 1.41s/it] 12%|█▏ | 7275/61904 [3:19:32<21:33:21, 1.42s/it] 12%|█▏ | 7276/61904 [3:19:33<20:30:47, 1.35s/it] 12%|█▏ | 7277/61904 [3:19:35<21:01:56, 1.39s/it] 12%|█▏ | 7278/61904 [3:19:36<20:19:50, 1.34s/it] 12%|█▏ | 7279/61904 [3:19:38<20:32:10, 1.35s/it] 12%|█▏ | 7280/61904 [3:19:39<20:58:40, 1.38s/it] {'loss': 2.8738, 'learning_rate': 1.8852586542201478e-07, 'epoch': 1.88} + 12%|█▏ | 7280/61904 [3:19:39<20:58:40, 1.38s/it] 12%|█▏ | 7281/61904 [3:19:40<20:58:00, 1.38s/it] 12%|█▏ | 7282/61904 [3:19:42<20:45:23, 1.37s/it] 12%|█▏ | 7283/61904 [3:19:43<20:52:43, 1.38s/it] 12%|█▏ | 7284/61904 [3:19:44<20:34:04, 1.36s/it] 12%|█▏ | 7285/61904 [3:19:46<21:13:18, 1.40s/it] 12%|█▏ | 7286/61904 [3:19:47<20:47:58, 1.37s/it] 12%|█▏ | 7287/61904 [3:19:48<20:20:50, 1.34s/it] 12%|█▏ | 7288/61904 [3:19:50<20:43:05, 1.37s/it] 12%|█▏ | 7289/61904 [3:19:51<20:51:17, 1.37s/it] 12%|█▏ | 7290/61904 [3:19:53<20:44:59, 1.37s/it] 12%|█▏ | 7291/61904 [3:19:54<20:23:50, 1.34s/it] 12%|█▏ | 7292/61904 [3:19:55<20:38:18, 1.36s/it] 12%|█▏ | 7293/61904 [3:19:57<20:52:15, 1.38s/it] 12%|█▏ | 7294/61904 [3:19:58<20:50:09, 1.37s/it] 12%|█▏ | 7295/61904 [3:19:59<20:27:33, 1.35s/it] 12%|█▏ | 7296/61904 [3:20:01<20:12:11, 1.33s/it] 12%|█▏ | 7297/61904 [3:20:02<20:02:01, 1.32s/it] 12%|█▏ | 7298/61904 [3:20:03<20:35:47, 1.36s/it] 12%|█▏ | 7299/61904 [3:20:05<20:38:06, 1.36s/it] 12%|█▏ | 7300/61904 [3:20:06<20:33:40, 1.36s/it] {'loss': 2.9246, 'learning_rate': 1.8849345261247244e-07, 'epoch': 1.89} + 12%|█▏ | 7300/61904 [3:20:06<20:33:40, 1.36s/it] 12%|█▏ | 7301/61904 [3:20:08<21:02:50, 1.39s/it] 12%|█▏ | 7302/61904 [3:20:09<20:32:37, 1.35s/it] 12%|█▏ | 7303/61904 [3:20:10<20:27:12, 1.35s/it] 12%|█▏ | 7304/61904 [3:20:11<19:49:23, 1.31s/it] 12%|█▏ | 7305/61904 [3:20:13<20:03:50, 1.32s/it] 12%|█▏ | 7306/61904 [3:20:14<20:21:50, 1.34s/it] 12%|█▏ | 7307/61904 [3:20:16<21:04:20, 1.39s/it] 12%|█▏ | 7308/61904 [3:20:17<20:40:35, 1.36s/it] 12%|█▏ | 7309/61904 [3:20:18<20:36:44, 1.36s/it] 12%|█▏ | 7310/61904 [3:20:20<20:39:02, 1.36s/it] 12%|█▏ | 7311/61904 [3:20:21<20:09:32, 1.33s/it] 12%|█▏ | 7312/61904 [3:20:22<20:21:30, 1.34s/it] 12%|█▏ | 7313/61904 [3:20:24<21:38:50, 1.43s/it] 12%|█▏ | 7314/61904 [3:20:25<21:12:24, 1.40s/it] 12%|█▏ | 7315/61904 [3:20:27<21:23:25, 1.41s/it] 12%|█▏ | 7316/61904 [3:20:28<21:47:20, 1.44s/it] 12%|█▏ | 7317/61904 [3:20:30<21:14:13, 1.40s/it] 12%|█▏ | 7318/61904 [3:20:31<21:17:06, 1.40s/it] 12%|█▏ | 7319/61904 [3:20:32<21:35:53, 1.42s/it] 12%|█▏ | 7320/61904 [3:20:34<21:23:30, 1.41s/it] {'loss': 2.898, 'learning_rate': 1.884610398029301e-07, 'epoch': 1.89} + 12%|█▏ | 7320/61904 [3:20:34<21:23:30, 1.41s/it] 12%|█▏ | 7321/61904 [3:20:35<20:34:43, 1.36s/it] 12%|█▏ | 7322/61904 [3:20:36<20:31:06, 1.35s/it] 12%|█▏ | 7323/61904 [3:20:38<20:48:45, 1.37s/it] 12%|█▏ | 7324/61904 [3:20:39<20:42:29, 1.37s/it] 12%|█▏ | 7325/61904 [3:20:40<20:24:08, 1.35s/it] 12%|█▏ | 7326/61904 [3:20:42<19:58:45, 1.32s/it] 12%|█▏ | 7327/61904 [3:20:43<20:52:53, 1.38s/it] 12%|█▏ | 7328/61904 [3:20:45<20:51:08, 1.38s/it] 12%|█▏ | 7329/61904 [3:20:46<20:49:11, 1.37s/it] 12%|█▏ | 7330/61904 [3:20:47<20:43:31, 1.37s/it] 12%|█▏ | 7331/61904 [3:20:49<20:23:24, 1.35s/it] 12%|█▏ | 7332/61904 [3:20:50<20:19:43, 1.34s/it] 12%|█▏ | 7333/61904 [3:20:51<20:35:01, 1.36s/it] 12%|█▏ | 7334/61904 [3:20:53<20:18:28, 1.34s/it] 12%|█▏ | 7335/61904 [3:20:54<19:56:38, 1.32s/it] 12%|█▏ | 7336/61904 [3:20:55<19:49:15, 1.31s/it] 12%|█▏ | 7337/61904 [3:20:56<19:30:20, 1.29s/it] 12%|█▏ | 7338/61904 [3:20:58<19:17:24, 1.27s/it] 12%|█▏ | 7339/61904 [3:20:59<19:39:54, 1.30s/it] 12%|█▏ | 7340/61904 [3:21:00<20:07:00, 1.33s/it] {'loss': 2.9362, 'learning_rate': 1.884286269933878e-07, 'epoch': 1.9} + 12%|█▏ | 7340/61904 [3:21:00<20:07:00, 1.33s/it] 12%|█▏ | 7341/61904 [3:21:02<20:18:51, 1.34s/it] 12%|█▏ | 7342/61904 [3:21:03<20:36:12, 1.36s/it] 12%|█▏ | 7343/61904 [3:21:05<20:47:53, 1.37s/it] 12%|█▏ | 7344/61904 [3:21:06<20:04:07, 1.32s/it] 12%|█▏ | 7345/61904 [3:21:07<20:44:57, 1.37s/it] 12%|█▏ | 7346/61904 [3:21:09<21:16:07, 1.40s/it] 12%|█▏ | 7347/61904 [3:21:10<21:02:17, 1.39s/it] 12%|█▏ | 7348/61904 [3:21:11<20:58:48, 1.38s/it] 12%|█▏ | 7349/61904 [3:21:13<21:01:41, 1.39s/it] 12%|█▏ | 7350/61904 [3:21:14<21:08:18, 1.39s/it] 12%|█▏ | 7351/61904 [3:21:16<21:09:24, 1.40s/it] 12%|█▏ | 7352/61904 [3:21:17<21:16:42, 1.40s/it] 12%|█▏ | 7353/61904 [3:21:18<20:53:55, 1.38s/it] 12%|█▏ | 7354/61904 [3:21:20<21:11:52, 1.40s/it] 12%|█▏ | 7355/61904 [3:21:21<21:12:13, 1.40s/it] 12%|█▏ | 7356/61904 [3:21:23<20:51:36, 1.38s/it] 12%|█▏ | 7357/61904 [3:21:24<21:02:49, 1.39s/it] 12%|█▏ | 7358/61904 [3:21:25<20:40:45, 1.36s/it] 12%|█▏ | 7359/61904 [3:21:27<20:11:33, 1.33s/it] 12%|█▏ | 7360/61904 [3:21:28<20:07:48, 1.33s/it] {'loss': 2.9173, 'learning_rate': 1.8839621418384545e-07, 'epoch': 1.9} + 12%|█▏ | 7360/61904 [3:21:28<20:07:48, 1.33s/it] 12%|█▏ | 7361/61904 [3:21:29<20:11:50, 1.33s/it] 12%|█▏ | 7362/61904 [3:21:31<20:13:19, 1.33s/it] 12%|█▏ | 7363/61904 [3:21:32<20:45:28, 1.37s/it] 12%|█▏ | 7364/61904 [3:21:34<21:23:05, 1.41s/it] 12%|█▏ | 7365/61904 [3:21:35<21:15:02, 1.40s/it] 12%|█▏ | 7366/61904 [3:21:36<21:14:51, 1.40s/it] 12%|█▏ | 7367/61904 [3:21:38<20:50:36, 1.38s/it] 12%|█▏ | 7368/61904 [3:21:39<20:32:53, 1.36s/it] 12%|█▏ | 7369/61904 [3:21:40<20:49:13, 1.37s/it] 12%|█▏ | 7370/61904 [3:21:42<20:50:25, 1.38s/it] 12%|█▏ | 7371/61904 [3:21:43<20:48:53, 1.37s/it] 12%|█▏ | 7372/61904 [3:21:44<20:48:05, 1.37s/it] 12%|█▏ | 7373/61904 [3:21:46<20:37:37, 1.36s/it] 12%|█▏ | 7374/61904 [3:21:47<20:54:39, 1.38s/it] 12%|█▏ | 7375/61904 [3:21:49<20:37:56, 1.36s/it] 12%|█▏ | 7376/61904 [3:21:50<20:21:34, 1.34s/it] 12%|█▏ | 7377/61904 [3:21:51<20:06:18, 1.33s/it] 12%|█▏ | 7378/61904 [3:21:52<19:56:57, 1.32s/it] 12%|█▏ | 7379/61904 [3:21:54<20:23:17, 1.35s/it] 12%|█▏ | 7380/61904 [3:21:55<20:07:55, 1.33s/it] {'loss': 2.9209, 'learning_rate': 1.8836380137430312e-07, 'epoch': 1.91} + 12%|█▏ | 7380/61904 [3:21:55<20:07:55, 1.33s/it] 12%|█▏ | 7381/61904 [3:21:57<20:41:55, 1.37s/it] 12%|█▏ | 7382/61904 [3:21:58<20:51:51, 1.38s/it] 12%|█▏ | 7383/61904 [3:21:59<20:56:13, 1.38s/it] 12%|█▏ | 7384/61904 [3:22:01<20:14:47, 1.34s/it] 12%|█▏ | 7385/61904 [3:22:02<20:32:24, 1.36s/it] 12%|█▏ | 7386/61904 [3:22:03<20:18:35, 1.34s/it] 12%|█▏ | 7387/61904 [3:22:05<20:23:34, 1.35s/it] 12%|█▏ | 7388/61904 [3:22:06<20:09:16, 1.33s/it] 12%|█▏ | 7389/61904 [3:22:07<20:22:51, 1.35s/it] 12%|█▏ | 7390/61904 [3:22:09<20:10:20, 1.33s/it] 12%|█▏ | 7391/61904 [3:22:10<19:47:24, 1.31s/it] 12%|█▏ | 7392/61904 [3:22:11<19:43:34, 1.30s/it] 12%|█▏ | 7393/61904 [3:22:13<19:58:38, 1.32s/it] 12%|█▏ | 7394/61904 [3:22:14<20:06:19, 1.33s/it] 12%|█▏ | 7395/61904 [3:22:15<19:23:59, 1.28s/it] 12%|█▏ | 7396/61904 [3:22:16<19:39:45, 1.30s/it] 12%|█▏ | 7397/61904 [3:22:18<19:27:40, 1.29s/it] 12%|█▏ | 7398/61904 [3:22:19<19:39:58, 1.30s/it] 12%|█▏ | 7399/61904 [3:22:20<20:10:48, 1.33s/it] 12%|█▏ | 7400/61904 [3:22:22<19:52:34, 1.31s/it] {'loss': 2.9294, 'learning_rate': 1.883313885647608e-07, 'epoch': 1.91} + 12%|█▏ | 7400/61904 [3:22:22<19:52:34, 1.31s/it] 12%|█▏ | 7401/61904 [3:22:23<20:46:08, 1.37s/it] 12%|█▏ | 7402/61904 [3:22:25<20:49:57, 1.38s/it] 12%|█▏ | 7403/61904 [3:22:26<20:17:54, 1.34s/it] 12%|█▏ | 7404/61904 [3:22:27<20:08:36, 1.33s/it] 12%|█▏ | 7405/61904 [3:22:29<20:35:51, 1.36s/it] 12%|█▏ | 7406/61904 [3:22:30<21:07:16, 1.40s/it] 12%|█▏ | 7407/61904 [3:22:31<20:51:36, 1.38s/it] 12%|█▏ | 7408/61904 [3:22:33<20:20:01, 1.34s/it] 12%|█▏ | 7409/61904 [3:22:34<20:15:51, 1.34s/it] 12%|█▏ | 7410/61904 [3:22:35<20:04:59, 1.33s/it] 12%|█▏ | 7411/61904 [3:22:37<20:32:54, 1.36s/it] 12%|█▏ | 7412/61904 [3:22:38<20:43:40, 1.37s/it] 12%|█▏ | 7413/61904 [3:22:39<20:43:47, 1.37s/it] 12%|█▏ | 7414/61904 [3:22:41<21:07:48, 1.40s/it] 12%|█▏ | 7415/61904 [3:22:42<21:20:00, 1.41s/it] 12%|█▏ | 7416/61904 [3:22:44<20:51:08, 1.38s/it] 12%|█▏ | 7417/61904 [3:22:45<20:10:04, 1.33s/it] 12%|█▏ | 7418/61904 [3:22:46<20:41:15, 1.37s/it] 12%|█▏ | 7419/61904 [3:22:48<20:14:07, 1.34s/it] 12%|█▏ | 7420/61904 [3:22:49<20:51:25, 1.38s/it] {'loss': 2.9321, 'learning_rate': 1.8829897575521844e-07, 'epoch': 1.92} + 12%|█▏ | 7420/61904 [3:22:49<20:51:25, 1.38s/it] 12%|█▏ | 7421/61904 [3:22:50<20:37:31, 1.36s/it] 12%|█▏ | 7422/61904 [3:22:52<20:21:46, 1.35s/it] 12%|█▏ | 7423/61904 [3:22:53<20:40:32, 1.37s/it] 12%|█▏ | 7424/61904 [3:22:55<21:03:00, 1.39s/it] 12%|█▏ | 7425/61904 [3:22:56<20:48:37, 1.38s/it] 12%|█▏ | 7426/61904 [3:22:57<20:49:16, 1.38s/it] 12%|█▏ | 7427/61904 [3:22:59<21:07:12, 1.40s/it] 12%|█▏ | 7428/61904 [3:23:00<21:19:47, 1.41s/it] 12%|█▏ | 7429/61904 [3:23:02<21:06:58, 1.40s/it] 12%|█▏ | 7430/61904 [3:23:03<20:43:45, 1.37s/it] 12%|█▏ | 7431/61904 [3:23:04<20:07:29, 1.33s/it] 12%|█▏ | 7432/61904 [3:23:06<20:48:28, 1.38s/it] 12%|█▏ | 7433/61904 [3:23:07<20:39:26, 1.37s/it] 12%|█▏ | 7434/61904 [3:23:08<21:12:40, 1.40s/it] 12%|█▏ | 7435/61904 [3:23:10<23:09:35, 1.53s/it] 12%|█▏ | 7436/61904 [3:23:12<22:20:43, 1.48s/it] 12%|█▏ | 7437/61904 [3:23:13<21:37:05, 1.43s/it] 12%|█▏ | 7438/61904 [3:23:14<21:24:12, 1.41s/it] 12%|█▏ | 7439/61904 [3:23:16<22:02:58, 1.46s/it] 12%|█▏ | 7440/61904 [3:23:17<21:18:53, 1.41s/it] {'loss': 2.8453, 'learning_rate': 1.8826656294567613e-07, 'epoch': 1.92} + 12%|█▏ | 7440/61904 [3:23:17<21:18:53, 1.41s/it] 12%|█▏ | 7441/61904 [3:23:18<20:50:05, 1.38s/it] 12%|█▏ | 7442/61904 [3:23:20<20:46:00, 1.37s/it] 12%|█▏ | 7443/61904 [3:23:21<20:43:45, 1.37s/it] 12%|█▏ | 7444/61904 [3:23:23<20:44:05, 1.37s/it] 12%|█▏ | 7445/61904 [3:23:24<21:02:08, 1.39s/it] 12%|█▏ | 7446/61904 [3:23:25<21:16:08, 1.41s/it] 12%|█▏ | 7447/61904 [3:23:27<21:03:38, 1.39s/it] 12%|█▏ | 7448/61904 [3:23:28<20:46:36, 1.37s/it] 12%|█▏ | 7449/61904 [3:23:29<20:26:11, 1.35s/it] 12%|█▏ | 7450/61904 [3:23:31<20:26:28, 1.35s/it] 12%|█▏ | 7451/61904 [3:23:32<20:23:07, 1.35s/it] 12%|█▏ | 7452/61904 [3:23:33<20:12:41, 1.34s/it] 12%|█▏ | 7453/61904 [3:23:35<20:43:37, 1.37s/it] 12%|█▏ | 7454/61904 [3:23:36<20:14:02, 1.34s/it] 12%|█▏ | 7455/61904 [3:23:37<20:07:46, 1.33s/it] 12%|█▏ | 7456/61904 [3:23:39<20:15:24, 1.34s/it] 12%|█▏ | 7457/61904 [3:23:40<20:14:04, 1.34s/it] 12%|█▏ | 7458/61904 [3:23:42<21:09:49, 1.40s/it] 12%|█▏ | 7459/61904 [3:23:43<21:33:54, 1.43s/it] 12%|█▏ | 7460/61904 [3:23:44<20:50:03, 1.38s/it] {'loss': 2.8941, 'learning_rate': 1.882341501361338e-07, 'epoch': 1.93} + 12%|█▏ | 7460/61904 [3:23:44<20:50:03, 1.38s/it] 12%|█▏ | 7461/61904 [3:23:46<21:06:12, 1.40s/it] 12%|█▏ | 7462/61904 [3:23:47<21:01:21, 1.39s/it] 12%|█▏ | 7463/61904 [3:23:49<20:43:13, 1.37s/it] 12%|█▏ | 7464/61904 [3:23:50<21:05:32, 1.39s/it] 12%|█▏ | 7465/61904 [3:23:51<21:10:46, 1.40s/it] 12%|█▏ | 7466/61904 [3:23:53<21:34:41, 1.43s/it] 12%|█▏ | 7467/61904 [3:23:54<21:33:59, 1.43s/it] 12%|█▏ | 7468/61904 [3:23:56<21:13:12, 1.40s/it] 12%|█▏ | 7469/61904 [3:23:57<20:46:40, 1.37s/it] 12%|█▏ | 7470/61904 [3:23:58<20:26:51, 1.35s/it] 12%|█▏ | 7471/61904 [3:24:00<20:17:02, 1.34s/it] 12%|█▏ | 7472/61904 [3:24:01<20:33:55, 1.36s/it] 12%|█▏ | 7473/61904 [3:24:03<21:08:31, 1.40s/it] 12%|█▏ | 7474/61904 [3:24:04<21:46:27, 1.44s/it] 12%|█▏ | 7475/61904 [3:24:05<20:54:42, 1.38s/it] 12%|█▏ | 7476/61904 [3:24:07<20:49:00, 1.38s/it] 12%|█▏ | 7477/61904 [3:24:08<20:14:19, 1.34s/it] 12%|█▏ | 7478/61904 [3:24:09<20:07:42, 1.33s/it] 12%|█▏ | 7479/61904 [3:24:10<19:46:11, 1.31s/it] 12%|█▏ | 7480/61904 [3:24:12<19:46:29, 1.31s/it] {'loss': 2.932, 'learning_rate': 1.8820173732659145e-07, 'epoch': 1.93} + 12%|█▏ | 7480/61904 [3:24:12<19:46:29, 1.31s/it] 12%|█▏ | 7481/61904 [3:24:13<19:37:46, 1.30s/it] 12%|█▏ | 7482/61904 [3:24:14<19:10:37, 1.27s/it] 12%|█▏ | 7483/61904 [3:24:16<20:11:36, 1.34s/it] 12%|█▏ | 7484/61904 [3:24:17<20:08:20, 1.33s/it] 12%|█▏ | 7485/61904 [3:24:19<20:35:35, 1.36s/it] 12%|█▏ | 7486/61904 [3:24:20<20:45:22, 1.37s/it] 12%|█▏ | 7487/61904 [3:24:21<20:37:01, 1.36s/it] 12%|█▏ | 7488/61904 [3:24:23<20:51:11, 1.38s/it] 12%|█▏ | 7489/61904 [3:24:24<20:52:32, 1.38s/it] 12%|█▏ | 7490/61904 [3:24:25<20:55:07, 1.38s/it] 12%|█▏ | 7491/61904 [3:24:27<21:14:00, 1.40s/it] 12%|█▏ | 7492/61904 [3:24:28<21:15:38, 1.41s/it] 12%|█▏ | 7493/61904 [3:24:30<21:01:38, 1.39s/it] 12%|█▏ | 7494/61904 [3:24:31<20:18:08, 1.34s/it] 12%|█▏ | 7495/61904 [3:24:32<20:14:36, 1.34s/it] 12%|█▏ | 7496/61904 [3:24:34<21:03:20, 1.39s/it] 12%|█▏ | 7497/61904 [3:24:35<20:53:42, 1.38s/it] 12%|█▏ | 7498/61904 [3:24:37<21:34:03, 1.43s/it] 12%|█▏ | 7499/61904 [3:24:38<20:50:13, 1.38s/it] 12%|█▏ | 7500/61904 [3:24:39<20:10:40, 1.34s/it] {'loss': 2.9291, 'learning_rate': 1.8816932451704914e-07, 'epoch': 1.94} + 12%|█▏ | 7500/61904 [3:24:39<20:10:40, 1.34s/it] 12%|█▏ | 7501/61904 [3:24:40<19:42:38, 1.30s/it] 12%|█▏ | 7502/61904 [3:24:42<20:27:11, 1.35s/it] 12%|█▏ | 7503/61904 [3:24:43<20:46:45, 1.38s/it] 12%|█▏ | 7504/61904 [3:24:45<20:59:32, 1.39s/it] 12%|█▏ | 7505/61904 [3:24:46<21:05:59, 1.40s/it] 12%|█▏ | 7506/61904 [3:24:47<20:44:10, 1.37s/it] 12%|█▏ | 7507/61904 [3:24:49<20:54:46, 1.38s/it] 12%|█▏ | 7508/61904 [3:24:50<20:10:43, 1.34s/it] 12%|█▏ | 7509/61904 [3:24:51<20:23:26, 1.35s/it] 12%|█▏ | 7510/61904 [3:24:53<19:56:25, 1.32s/it] 12%|█▏ | 7511/61904 [3:24:54<20:36:33, 1.36s/it] 12%|█▏ | 7512/61904 [3:24:55<20:14:50, 1.34s/it] 12%|█▏ | 7513/61904 [3:24:57<20:43:08, 1.37s/it] 12%|█▏ | 7514/61904 [3:24:58<20:15:55, 1.34s/it] 12%|█▏ | 7515/61904 [3:25:00<20:44:05, 1.37s/it] 12%|█▏ | 7516/61904 [3:25:01<21:11:55, 1.40s/it] 12%|█▏ | 7517/61904 [3:25:02<20:23:03, 1.35s/it] 12%|█▏ | 7518/61904 [3:25:04<20:30:09, 1.36s/it] 12%|█▏ | 7519/61904 [3:25:05<20:39:22, 1.37s/it] 12%|█▏ | 7520/61904 [3:25:07<20:59:35, 1.39s/it] {'loss': 2.9375, 'learning_rate': 1.881369117075068e-07, 'epoch': 1.94} + 12%|█▏ | 7520/61904 [3:25:07<20:59:35, 1.39s/it] 12%|█▏ | 7521/61904 [3:25:08<20:33:07, 1.36s/it] 12%|█▏ | 7522/61904 [3:25:09<20:44:04, 1.37s/it] 12%|█▏ | 7523/61904 [3:25:11<20:41:44, 1.37s/it] 12%|█▏ | 7524/61904 [3:25:12<20:46:24, 1.38s/it] 12%|█▏ | 7525/61904 [3:25:13<20:37:32, 1.37s/it] 12%|█▏ | 7526/61904 [3:25:15<20:25:52, 1.35s/it] 12%|█▏ | 7527/61904 [3:25:16<20:33:54, 1.36s/it] 12%|█▏ | 7528/61904 [3:25:17<20:27:33, 1.35s/it] 12%|█▏ | 7529/61904 [3:25:19<20:48:03, 1.38s/it] 12%|█▏ | 7530/61904 [3:25:20<20:16:55, 1.34s/it] 12%|█▏ | 7531/61904 [3:25:21<20:03:11, 1.33s/it] 12%|█▏ | 7532/61904 [3:25:23<19:43:49, 1.31s/it] 12%|█▏ | 7533/61904 [3:25:24<19:39:33, 1.30s/it] 12%|█▏ | 7534/61904 [3:25:25<19:21:40, 1.28s/it] 12%|█▏ | 7535/61904 [3:25:27<19:56:02, 1.32s/it] 12%|█▏ | 7536/61904 [3:25:28<20:46:17, 1.38s/it] 12%|█▏ | 7537/61904 [3:25:29<20:33:33, 1.36s/it] 12%|█▏ | 7538/61904 [3:25:31<20:53:55, 1.38s/it] 12%|█▏ | 7539/61904 [3:25:32<20:43:36, 1.37s/it] 12%|█▏ | 7540/61904 [3:25:33<19:59:23, 1.32s/it] {'loss': 2.9291, 'learning_rate': 1.8810449889796446e-07, 'epoch': 1.95} + 12%|█▏ | 7540/61904 [3:25:33<19:59:23, 1.32s/it] 12%|█▏ | 7541/61904 [3:25:35<20:08:17, 1.33s/it] 12%|█▏ | 7542/61904 [3:25:36<19:40:59, 1.30s/it] 12%|█▏ | 7543/61904 [3:25:37<20:29:20, 1.36s/it] 12%|█▏ | 7544/61904 [3:25:39<20:35:43, 1.36s/it] 12%|█▏ | 7545/61904 [3:25:40<19:54:07, 1.32s/it] 12%|█▏ | 7546/61904 [3:25:41<19:49:39, 1.31s/it] 12%|█▏ | 7547/61904 [3:25:43<20:13:08, 1.34s/it] 12%|█▏ | 7548/61904 [3:25:44<19:44:03, 1.31s/it] 12%|█▏ | 7549/61904 [3:25:45<20:35:43, 1.36s/it] 12%|█▏ | 7550/61904 [3:25:47<20:25:54, 1.35s/it] 12%|█▏ | 7551/61904 [3:25:48<19:57:25, 1.32s/it] 12%|█▏ | 7552/61904 [3:25:49<20:11:17, 1.34s/it] 12%|█▏ | 7553/61904 [3:25:51<20:28:25, 1.36s/it] 12%|█▏ | 7554/61904 [3:25:52<20:49:21, 1.38s/it] 12%|█▏ | 7555/61904 [3:25:54<20:24:00, 1.35s/it] 12%|█▏ | 7556/61904 [3:25:55<20:06:34, 1.33s/it] 12%|█▏ | 7557/61904 [3:25:56<20:44:05, 1.37s/it] 12%|█▏ | 7558/61904 [3:25:58<20:13:18, 1.34s/it] 12%|█▏ | 7559/61904 [3:25:59<20:02:56, 1.33s/it] 12%|█▏ | 7560/61904 [3:26:00<20:22:32, 1.35s/it] {'loss': 2.8834, 'learning_rate': 1.8807208608842215e-07, 'epoch': 1.95} + 12%|█▏ | 7560/61904 [3:26:00<20:22:32, 1.35s/it] 12%|█▏ | 7561/61904 [3:26:01<19:52:34, 1.32s/it] 12%|█▏ | 7562/61904 [3:26:03<19:35:55, 1.30s/it] 12%|█▏ | 7563/61904 [3:26:04<19:49:40, 1.31s/it] 12%|█▏ | 7564/61904 [3:26:05<20:14:30, 1.34s/it] 12%|█▏ | 7565/61904 [3:26:07<20:12:31, 1.34s/it] 12%|█▏ | 7566/61904 [3:26:08<20:22:56, 1.35s/it] 12%|█▏ | 7567/61904 [3:26:09<20:11:50, 1.34s/it] 12%|█▏ | 7568/61904 [3:26:11<20:21:59, 1.35s/it] 12%|█▏ | 7569/61904 [3:26:12<20:16:41, 1.34s/it] 12%|█▏ | 7570/61904 [3:26:13<20:03:30, 1.33s/it] 12%|█▏ | 7571/61904 [3:26:15<20:29:19, 1.36s/it] 12%|█▏ | 7572/61904 [3:26:16<20:23:21, 1.35s/it] 12%|█▏ | 7573/61904 [3:26:18<20:24:07, 1.35s/it] 12%|█▏ | 7574/61904 [3:26:19<20:07:15, 1.33s/it] 12%|█▏ | 7575/61904 [3:26:20<20:09:35, 1.34s/it] 12%|█▏ | 7576/61904 [3:26:22<19:55:16, 1.32s/it] 12%|█▏ | 7577/61904 [3:26:23<19:54:07, 1.32s/it] 12%|█▏ | 7578/61904 [3:26:24<20:06:56, 1.33s/it] 12%|█▏ | 7579/61904 [3:26:26<20:09:42, 1.34s/it] 12%|█▏ | 7580/61904 [3:26:27<20:37:02, 1.37s/it] {'loss': 2.9606, 'learning_rate': 1.880396732788798e-07, 'epoch': 1.96} + 12%|█▏ | 7580/61904 [3:26:27<20:37:02, 1.37s/it] 12%|█▏ | 7581/61904 [3:26:28<21:02:00, 1.39s/it] 12%|█▏ | 7582/61904 [3:26:30<20:43:33, 1.37s/it] 12%|█▏ | 7583/61904 [3:26:31<21:40:31, 1.44s/it] 12%|█▏ | 7584/61904 [3:26:33<21:28:19, 1.42s/it] 12%|█▏ | 7585/61904 [3:26:34<21:22:03, 1.42s/it] 12%|█▏ | 7586/61904 [3:26:36<21:14:41, 1.41s/it] 12%|█▏ | 7587/61904 [3:26:37<20:41:20, 1.37s/it] 12%|█▏ | 7588/61904 [3:26:38<21:05:55, 1.40s/it] 12%|█▏ | 7589/61904 [3:26:40<20:19:24, 1.35s/it] 12%|█▏ | 7590/61904 [3:26:41<20:06:05, 1.33s/it] 12%|█▏ | 7591/61904 [3:26:42<20:25:08, 1.35s/it] 12%|█▏ | 7592/61904 [3:26:44<20:15:48, 1.34s/it] 12%|█▏ | 7593/61904 [3:26:45<20:23:33, 1.35s/it] 12%|█▏ | 7594/61904 [3:26:46<21:08:37, 1.40s/it] 12%|█▏ | 7595/61904 [3:26:48<22:03:54, 1.46s/it] 12%|█▏ | 7596/61904 [3:26:49<21:26:13, 1.42s/it] 12%|█▏ | 7597/61904 [3:26:51<21:43:56, 1.44s/it] 12%|█▏ | 7598/61904 [3:26:52<21:19:23, 1.41s/it] 12%|█▏ | 7599/61904 [3:26:53<20:39:58, 1.37s/it] 12%|█▏ | 7600/61904 [3:26:55<20:35:55, 1.37s/it] {'loss': 2.8769, 'learning_rate': 1.8800726046933748e-07, 'epoch': 1.96} + 12%|█▏ | 7600/61904 [3:26:55<20:35:55, 1.37s/it] 12%|█▏ | 7601/61904 [3:26:56<20:34:03, 1.36s/it] 12%|█▏ | 7602/61904 [3:26:58<21:17:01, 1.41s/it] 12%|█▏ | 7603/61904 [3:26:59<20:44:28, 1.38s/it] 12%|█▏ | 7604/61904 [3:27:00<20:39:33, 1.37s/it] 12%|█▏ | 7605/61904 [3:27:02<20:53:00, 1.38s/it] 12%|█▏ | 7606/61904 [3:27:03<20:34:23, 1.36s/it] 12%|█▏ | 7607/61904 [3:27:05<21:15:16, 1.41s/it] 12%|█▏ | 7608/61904 [3:27:06<20:58:31, 1.39s/it] 12%|█▏ | 7609/61904 [3:27:08<21:47:31, 1.44s/it] 12%|█▏ | 7610/61904 [3:27:09<20:47:58, 1.38s/it] 12%|█▏ | 7611/61904 [3:27:10<22:02:09, 1.46s/it] 12%|█▏ | 7612/61904 [3:27:12<21:56:38, 1.46s/it] 12%|█▏ | 7613/61904 [3:27:13<20:42:29, 1.37s/it] 12%|█▏ | 7614/61904 [3:27:14<20:59:59, 1.39s/it] 12%|█▏ | 7615/61904 [3:27:16<20:47:28, 1.38s/it] 12%|█▏ | 7616/61904 [3:27:17<20:26:25, 1.36s/it] 12%|█▏ | 7617/61904 [3:27:18<20:10:07, 1.34s/it] 12%|█▏ | 7618/61904 [3:27:20<20:10:20, 1.34s/it] 12%|█▏ | 7619/61904 [3:27:21<19:48:50, 1.31s/it] 12%|█▏ | 7620/61904 [3:27:22<19:49:44, 1.32s/it] {'loss': 2.9195, 'learning_rate': 1.8797484765979514e-07, 'epoch': 1.97} + 12%|█▏ | 7620/61904 [3:27:22<19:49:44, 1.32s/it] 12%|█▏ | 7621/61904 [3:27:24<20:17:28, 1.35s/it] 12%|█▏ | 7622/61904 [3:27:25<20:09:06, 1.34s/it] 12%|█▏ | 7623/61904 [3:27:26<20:06:17, 1.33s/it] 12%|█▏ | 7624/61904 [3:27:28<20:36:54, 1.37s/it] 12%|█▏ | 7625/61904 [3:27:29<19:58:49, 1.33s/it] 12%|█▏ | 7626/61904 [3:27:30<20:07:54, 1.34s/it] 12%|█▏ | 7627/61904 [3:27:32<20:26:50, 1.36s/it] 12%|█▏ | 7628/61904 [3:27:33<20:52:51, 1.38s/it] 12%|█▏ | 7629/61904 [3:27:34<20:15:07, 1.34s/it] 12%|█▏ | 7630/61904 [3:27:36<20:36:09, 1.37s/it] 12%|█▏ | 7631/61904 [3:27:37<20:40:39, 1.37s/it] 12%|█▏ | 7632/61904 [3:27:39<20:42:30, 1.37s/it] 12%|█▏ | 7633/61904 [3:27:40<20:13:34, 1.34s/it] 12%|█▏ | 7634/61904 [3:27:41<20:12:44, 1.34s/it] 12%|█▏ | 7635/61904 [3:27:43<20:08:30, 1.34s/it] 12%|█▏ | 7636/61904 [3:27:44<20:18:56, 1.35s/it] 12%|█▏ | 7637/61904 [3:27:45<19:51:57, 1.32s/it] 12%|█▏ | 7638/61904 [3:27:47<20:07:10, 1.33s/it] 12%|█▏ | 7639/61904 [3:27:48<20:27:44, 1.36s/it] 12%|█▏ | 7640/61904 [3:27:49<20:27:29, 1.36s/it] {'loss': 2.9, 'learning_rate': 1.879424348502528e-07, 'epoch': 1.97} + 12%|█▏ | 7640/61904 [3:27:49<20:27:29, 1.36s/it] 12%|█▏ | 7641/61904 [3:27:51<20:53:48, 1.39s/it] 12%|█▏ | 7642/61904 [3:27:52<19:59:35, 1.33s/it] 12%|█▏ | 7643/61904 [3:27:53<19:37:17, 1.30s/it] 12%|█▏ | 7644/61904 [3:27:55<19:45:11, 1.31s/it] 12%|█▏ | 7645/61904 [3:27:56<19:37:48, 1.30s/it] 12%|█▏ | 7646/61904 [3:27:57<20:02:37, 1.33s/it] 12%|█▏ | 7647/61904 [3:27:59<21:31:42, 1.43s/it] 12%|█▏ | 7648/61904 [3:28:00<21:47:33, 1.45s/it] 12%|█▏ | 7649/61904 [3:28:02<21:29:47, 1.43s/it] 12%|█▏ | 7650/61904 [3:28:03<21:00:52, 1.39s/it] 12%|█▏ | 7651/61904 [3:28:05<21:17:56, 1.41s/it] 12%|█▏ | 7652/61904 [3:28:06<21:05:58, 1.40s/it] 12%|█▏ | 7653/61904 [3:28:07<21:27:58, 1.42s/it] 12%|█▏ | 7654/61904 [3:28:09<21:39:39, 1.44s/it] 12%|█▏ | 7655/61904 [3:28:10<21:10:25, 1.41s/it] 12%|█▏ | 7656/61904 [3:28:12<20:54:49, 1.39s/it] 12%|█▏ | 7657/61904 [3:28:13<21:24:58, 1.42s/it] 12%|█▏ | 7658/61904 [3:28:15<21:28:46, 1.43s/it] 12%|█▏ | 7659/61904 [3:28:16<21:26:15, 1.42s/it] 12%|█▏ | 7660/61904 [3:28:17<20:47:49, 1.38s/it] {'loss': 2.9407, 'learning_rate': 1.879100220407105e-07, 'epoch': 1.98} + 12%|█▏ | 7660/61904 [3:28:17<20:47:49, 1.38s/it] 12%|█▏ | 7661/61904 [3:28:19<20:39:50, 1.37s/it] 12%|█▏ | 7662/61904 [3:28:20<20:16:14, 1.35s/it] 12%|█▏ | 7663/61904 [3:28:21<20:51:02, 1.38s/it] 12%|█▏ | 7664/61904 [3:28:23<21:07:21, 1.40s/it] 12%|█▏ | 7665/61904 [3:28:24<22:01:21, 1.46s/it] 12%|█▏ | 7666/61904 [3:28:26<21:52:43, 1.45s/it] 12%|█▏ | 7667/61904 [3:28:27<21:05:29, 1.40s/it] 12%|█▏ | 7668/61904 [3:28:29<21:15:09, 1.41s/it] 12%|█▏ | 7669/61904 [3:28:30<20:59:34, 1.39s/it] 12%|█▏ | 7670/61904 [3:28:31<21:14:25, 1.41s/it] 12%|█▏ | 7671/61904 [3:28:33<21:12:22, 1.41s/it] 12%|█▏ | 7672/61904 [3:28:34<20:57:07, 1.39s/it] 12%|█▏ | 7673/61904 [3:28:36<21:14:46, 1.41s/it] 12%|█▏ | 7674/61904 [3:28:37<22:01:25, 1.46s/it] 12%|█▏ | 7675/61904 [3:28:38<21:18:09, 1.41s/it] 12%|█▏ | 7676/61904 [3:28:40<20:47:24, 1.38s/it] 12%|█▏ | 7677/61904 [3:28:41<20:51:24, 1.38s/it] 12%|█▏ | 7678/61904 [3:28:42<20:50:21, 1.38s/it] 12%|█▏ | 7679/61904 [3:28:44<21:10:18, 1.41s/it] 12%|█▏ | 7680/61904 [3:28:45<21:02:21, 1.40s/it] {'loss': 2.9094, 'learning_rate': 1.8787760923116815e-07, 'epoch': 1.98} + 12%|█▏ | 7680/61904 [3:28:45<21:02:21, 1.40s/it] 12%|█▏ | 7681/61904 [3:28:47<21:44:07, 1.44s/it] 12%|█▏ | 7682/61904 [3:28:48<21:10:33, 1.41s/it] 12%|█▏ | 7683/61904 [3:28:49<20:21:45, 1.35s/it] 12%|█▏ | 7684/61904 [3:28:51<20:59:24, 1.39s/it] 12%|█▏ | 7685/61904 [3:28:52<20:41:15, 1.37s/it] 12%|█▏ | 7686/61904 [3:28:54<20:41:25, 1.37s/it] 12%|█▏ | 7687/61904 [3:28:55<20:16:23, 1.35s/it] 12%|█▏ | 7688/61904 [3:28:56<20:34:37, 1.37s/it] 12%|█▏ | 7689/61904 [3:28:58<20:31:12, 1.36s/it] 12%|█▏ | 7690/61904 [3:28:59<20:09:15, 1.34s/it] 12%|█▏ | 7691/61904 [3:29:00<20:22:23, 1.35s/it] 12%|█▏ | 7692/61904 [3:29:02<20:19:23, 1.35s/it] 12%|█▏ | 7693/61904 [3:29:03<20:03:09, 1.33s/it] 12%|█▏ | 7694/61904 [3:29:04<20:10:41, 1.34s/it] 12%|█▏ | 7695/61904 [3:29:05<19:27:05, 1.29s/it] 12%|█▏ | 7696/61904 [3:29:07<19:32:12, 1.30s/it] 12%|█▏ | 7697/61904 [3:29:08<20:23:11, 1.35s/it] 12%|█▏ | 7698/61904 [3:29:10<20:19:45, 1.35s/it] 12%|█▏ | 7699/61904 [3:29:11<20:00:00, 1.33s/it] 12%|█▏ | 7700/61904 [3:29:12<19:35:24, 1.30s/it] {'loss': 2.9574, 'learning_rate': 1.878451964216258e-07, 'epoch': 1.99} + 12%|█▏ | 7700/61904 [3:29:12<19:35:24, 1.30s/it] 12%|█▏ | 7701/61904 [3:29:14<20:45:36, 1.38s/it] 12%|█▏ | 7702/61904 [3:29:15<20:35:44, 1.37s/it] 12%|█▏ | 7703/61904 [3:29:16<20:22:40, 1.35s/it] 12%|█▏ | 7704/61904 [3:29:18<20:30:48, 1.36s/it] 12%|█▏ | 7705/61904 [3:29:19<20:19:40, 1.35s/it] 12%|█▏ | 7706/61904 [3:29:20<20:37:10, 1.37s/it] 12%|█▏ | 7707/61904 [3:29:22<20:20:22, 1.35s/it] 12%|█▏ | 7708/61904 [3:29:23<20:05:48, 1.33s/it] 12%|█▏ | 7709/61904 [3:29:24<20:16:09, 1.35s/it] 12%|█▏ | 7710/61904 [3:29:26<20:04:16, 1.33s/it] 12%|█▏ | 7711/61904 [3:29:27<19:54:13, 1.32s/it] 12%|█▏ | 7712/61904 [3:29:28<19:31:22, 1.30s/it] 12%|█▏ | 7713/61904 [3:29:30<19:54:32, 1.32s/it] 12%|█▏ | 7714/61904 [3:29:31<20:18:07, 1.35s/it] 12%|█▏ | 7715/61904 [3:29:32<19:53:36, 1.32s/it] 12%|█▏ | 7716/61904 [3:29:34<19:48:06, 1.32s/it] 12%|█▏ | 7717/61904 [3:29:35<19:39:34, 1.31s/it] 12%|█▏ | 7718/61904 [3:29:36<19:59:20, 1.33s/it] 12%|█▏ | 7719/61904 [3:29:38<20:07:53, 1.34s/it] 12%|█▏ | 7720/61904 [3:29:39<20:50:27, 1.38s/it] {'loss': 2.8978, 'learning_rate': 1.878127836120835e-07, 'epoch': 2.0} + 12%|█▏ | 7720/61904 [3:29:39<20:50:27, 1.38s/it] 12%|█▏ | 7721/61904 [3:29:41<21:25:25, 1.42s/it] 12%|█▏ | 7722/61904 [3:29:42<20:49:10, 1.38s/it] 12%|█▏ | 7723/61904 [3:29:43<21:22:57, 1.42s/it] 12%|█▏ | 7724/61904 [3:29:45<21:26:54, 1.43s/it] 12%|█▏ | 7725/61904 [3:29:46<21:32:59, 1.43s/it] 12%|█▏ | 7726/61904 [3:29:48<20:48:12, 1.38s/it] 12%|█▏ | 7727/61904 [3:29:49<20:32:38, 1.37s/it] 12%|█▏ | 7728/61904 [3:29:50<20:03:03, 1.33s/it] 12%|█▏ | 7729/61904 [3:29:52<20:27:46, 1.36s/it] 12%|█▏ | 7730/61904 [3:29:53<21:33:43, 1.43s/it] 12%|█▏ | 7731/61904 [3:29:55<22:02:19, 1.46s/it] 12%|█▏ | 7732/61904 [3:29:56<21:35:08, 1.43s/it] 12%|█▏ | 7733/61904 [3:29:57<20:54:28, 1.39s/it] 12%|█▏ | 7734/61904 [3:29:59<21:43:16, 1.44s/it] 12%|█▏ | 7735/61904 [3:30:00<21:09:00, 1.41s/it] 12%|█▏ | 7736/61904 [3:30:02<21:09:44, 1.41s/it] 12%|█▏ | 7737/61904 [3:30:03<21:03:14, 1.40s/it] 12%|█▎ | 7738/61904 [3:30:05<21:06:24, 1.40s/it] 13%|█▎ | 7739/61904 [3:30:06<21:12:27, 1.41s/it]Generation Kwargs: +{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5} + + 0%| | 0/861 [00:00> 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() + 13%|█▎ | 7740/61904 [4:03:13<8981:53:45, 596.98s/it] {'loss': 2.8846, 'learning_rate': 1.8778037080254114e-07, 'epoch': 2.0} + 13%|█▎ | 7740/61904 [4:03:13<8981:53:45, 596.98s/it] 13%|█▎ | 7741/61904 [4:03:14<6294:35:44, 418.38s/it] 13%|█▎ | 7742/61904 [4:03:16<4412:32:50, 293.29s/it] 13%|█▎ | 7743/61904 [4:03:17<3095:55:39, 205.78s/it] 13%|█▎ | 7744/61904 [4:03:19<2173:25:21, 144.47s/it] 13%|█▎ | 7745/61904 [4:03:20<1527:26:31, 101.53s/it] 13%|█▎ | 7746/61904 [4:03:21<1075:47:08, 71.51s/it] 13%|█▎ | 7747/61904 [4:03:23<759:00:34, 50.45s/it] 13%|█▎ | 7748/61904 [4:03:24<537:19:22, 35.72s/it] 13%|█▎ | 7749/61904 [4:03:26<383:04:52, 25.47s/it] 13%|█▎ | 7750/61904 [4:03:27<274:40:16, 18.26s/it] 13%|█▎ | 7751/61904 [4:03:28<198:03:11, 13.17s/it] 13%|█▎ | 7752/61904 [4:03:30<144:57:18, 9.64s/it] 13%|█▎ | 7753/61904 [4:03:31<107:21:09, 7.14s/it] 13%|█▎ | 7754/61904 [4:03:33<81:43:30, 5.43s/it] 13%|█▎ | 7755/61904 [4:03:34<63:53:19, 4.25s/it] 13%|█▎ | 7756/61904 [4:03:35<50:55:00, 3.39s/it] 13%|█▎ | 7757/61904 [4:03:37<41:40:24, 2.77s/it] 13%|█▎ | 7758/61904 [4:03:38<35:20:56, 2.35s/it] 13%|█▎ | 7759/61904 [4:03:40<31:42:49, 2.11s/it] 13%|█▎ | 7760/61904 [4:03:41<28:36:23, 1.90s/it] {'loss': 2.954, 'learning_rate': 1.8774795799299882e-07, 'epoch': 2.01} + 13%|█▎ | 7760/61904 [4:03:41<28:36:23, 1.90s/it] 13%|█▎ | 7761/61904 [4:03:42<25:49:01, 1.72s/it] 13%|█▎ | 7762/61904 [4:03:44<24:44:08, 1.64s/it] 13%|█▎ | 7763/61904 [4:03:45<23:22:02, 1.55s/it] 13%|█▎ | 7764/61904 [4:03:47<22:52:41, 1.52s/it] 13%|█▎ | 7765/61904 [4:03:48<21:59:31, 1.46s/it] 13%|█▎ | 7766/61904 [4:03:49<21:38:15, 1.44s/it] 13%|█▎ | 7767/61904 [4:03:51<21:01:04, 1.40s/it] 13%|█▎ | 7768/61904 [4:03:52<21:06:03, 1.40s/it] 13%|█▎ | 7769/61904 [4:03:53<20:51:05, 1.39s/it] 13%|█▎ | 7770/61904 [4:03:55<20:26:06, 1.36s/it] 13%|█▎ | 7771/61904 [4:03:56<21:34:45, 1.44s/it] 13%|█▎ | 7772/61904 [4:03:58<21:46:10, 1.45s/it] 13%|█▎ | 7773/61904 [4:03:59<21:50:34, 1.45s/it] 13%|█▎ | 7774/61904 [4:04:01<21:52:49, 1.46s/it] 13%|█▎ | 7775/61904 [4:04:02<21:18:00, 1.42s/it] 13%|█▎ | 7776/61904 [4:04:03<21:13:53, 1.41s/it] 13%|█▎ | 7777/61904 [4:04:05<20:48:41, 1.38s/it] 13%|█▎ | 7778/61904 [4:04:06<20:11:15, 1.34s/it] 13%|█▎ | 7779/61904 [4:04:08<22:02:09, 1.47s/it] 13%|█▎ | 7780/61904 [4:04:09<22:08:46, 1.47s/it] {'loss': 2.9074, 'learning_rate': 1.8771554518345649e-07, 'epoch': 2.01} + 13%|█▎ | 7780/61904 [4:04:09<22:08:46, 1.47s/it] \ No newline at end of file