neginr commited on
Commit
10185e5
·
verified ·
1 Parent(s): 2919610

Training in progress, epoch 5

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffc7531e0bb0d7409a57841b81f3b19bfdc90753d1379b00adfed1dc0fc02c48
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3993c80151145ecc92141adf12b8554c0cc3000a62436e058abbab736b0b0f02
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0969f688f2a6c2fc772af6480c5c8c4ec4d60bd10ee4715f5ef2a76256b843a5
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fc79930720af01313a4fcb920ca42da4dbf9c8ab3d94008c26bd2da2f8c6dc8
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e851426e6a4d2a2dcedbc00b4a9a0633a078abf6f356c06a367b2f06aa8b2f50
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:768a079cc7342bf20b4c526455ae56b15652031a955ea049c8a457c67d27aaf1
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cd2ce1fd9b6e0721b04764b502f3ef3036a8c14f9ce77982b0671da965bcdeb
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ad6d987b7f221669905ce17466070bc362ec200c695a361f7d890f37f01b945
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -993,3 +993,474 @@
993
  {"current_steps": 993, "total_steps": 1235, "loss": 0.3764, "lr": 4.502857857942204e-06, "epoch": 4.020242914979757, "percentage": 80.4, "elapsed_time": "6:38:21", "remaining_time": "1:37:04"}
994
  {"current_steps": 994, "total_steps": 1235, "loss": 0.3677, "lr": 4.467169815100549e-06, "epoch": 4.0242914979757085, "percentage": 80.49, "elapsed_time": "6:38:44", "remaining_time": "1:36:40"}
995
  {"current_steps": 995, "total_steps": 1235, "loss": 0.3703, "lr": 4.431605972355137e-06, "epoch": 4.02834008097166, "percentage": 80.57, "elapsed_time": "6:39:08", "remaining_time": "1:36:16"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
993
  {"current_steps": 993, "total_steps": 1235, "loss": 0.3764, "lr": 4.502857857942204e-06, "epoch": 4.020242914979757, "percentage": 80.4, "elapsed_time": "6:38:21", "remaining_time": "1:37:04"}
994
  {"current_steps": 994, "total_steps": 1235, "loss": 0.3677, "lr": 4.467169815100549e-06, "epoch": 4.0242914979757085, "percentage": 80.49, "elapsed_time": "6:38:44", "remaining_time": "1:36:40"}
995
  {"current_steps": 995, "total_steps": 1235, "loss": 0.3703, "lr": 4.431605972355137e-06, "epoch": 4.02834008097166, "percentage": 80.57, "elapsed_time": "6:39:08", "remaining_time": "1:36:16"}
996
+ {"current_steps": 996, "total_steps": 1235, "loss": 0.3751, "lr": 4.396166614073516e-06, "epoch": 4.032388663967612, "percentage": 80.65, "elapsed_time": "6:39:31", "remaining_time": "1:35:52"}
997
+ {"current_steps": 997, "total_steps": 1235, "loss": 0.3696, "lr": 4.360852023627846e-06, "epoch": 4.036437246963563, "percentage": 80.73, "elapsed_time": "6:39:54", "remaining_time": "1:35:27"}
998
+ {"current_steps": 998, "total_steps": 1235, "loss": 0.3825, "lr": 4.325662483392656e-06, "epoch": 4.040485829959514, "percentage": 80.81, "elapsed_time": "6:40:18", "remaining_time": "1:35:03"}
999
+ {"current_steps": 999, "total_steps": 1235, "loss": 0.3791, "lr": 4.29059827474257e-06, "epoch": 4.044534412955466, "percentage": 80.89, "elapsed_time": "6:40:41", "remaining_time": "1:34:39"}
1000
+ {"current_steps": 1000, "total_steps": 1235, "loss": 0.3787, "lr": 4.255659678050063e-06, "epoch": 4.048582995951417, "percentage": 80.97, "elapsed_time": "6:41:05", "remaining_time": "1:34:15"}
1001
+ {"current_steps": 1001, "total_steps": 1235, "loss": 0.3699, "lr": 4.22084697268323e-06, "epoch": 4.052631578947368, "percentage": 81.05, "elapsed_time": "6:41:28", "remaining_time": "1:33:51"}
1002
+ {"current_steps": 1002, "total_steps": 1235, "loss": 0.3676, "lr": 4.186160437003535e-06, "epoch": 4.05668016194332, "percentage": 81.13, "elapsed_time": "6:41:52", "remaining_time": "1:33:27"}
1003
+ {"current_steps": 1003, "total_steps": 1235, "loss": 0.3811, "lr": 4.151600348363582e-06, "epoch": 4.060728744939271, "percentage": 81.21, "elapsed_time": "6:42:16", "remaining_time": "1:33:02"}
1004
+ {"current_steps": 1004, "total_steps": 1235, "loss": 0.3814, "lr": 4.11716698310493e-06, "epoch": 4.064777327935222, "percentage": 81.3, "elapsed_time": "6:42:40", "remaining_time": "1:32:38"}
1005
+ {"current_steps": 1005, "total_steps": 1235, "loss": 0.3726, "lr": 4.082860616555848e-06, "epoch": 4.068825910931174, "percentage": 81.38, "elapsed_time": "6:43:03", "remaining_time": "1:32:14"}
1006
+ {"current_steps": 1006, "total_steps": 1235, "loss": 0.3971, "lr": 4.048681523029125e-06, "epoch": 4.0728744939271255, "percentage": 81.46, "elapsed_time": "6:43:27", "remaining_time": "1:31:50"}
1007
+ {"current_steps": 1007, "total_steps": 1235, "loss": 0.3826, "lr": 4.014629975819882e-06, "epoch": 4.076923076923077, "percentage": 81.54, "elapsed_time": "6:43:51", "remaining_time": "1:31:26"}
1008
+ {"current_steps": 1008, "total_steps": 1235, "loss": 0.3806, "lr": 3.9807062472033855e-06, "epoch": 4.080971659919029, "percentage": 81.62, "elapsed_time": "6:44:15", "remaining_time": "1:31:02"}
1009
+ {"current_steps": 1009, "total_steps": 1235, "loss": 0.3825, "lr": 3.94691060843287e-06, "epoch": 4.08502024291498, "percentage": 81.7, "elapsed_time": "6:44:39", "remaining_time": "1:30:38"}
1010
+ {"current_steps": 1010, "total_steps": 1235, "loss": 0.3819, "lr": 3.913243329737353e-06, "epoch": 4.089068825910931, "percentage": 81.78, "elapsed_time": "6:45:02", "remaining_time": "1:30:13"}
1011
+ {"current_steps": 1011, "total_steps": 1235, "loss": 0.3754, "lr": 3.879704680319503e-06, "epoch": 4.093117408906883, "percentage": 81.86, "elapsed_time": "6:45:26", "remaining_time": "1:29:49"}
1012
+ {"current_steps": 1012, "total_steps": 1235, "loss": 0.3714, "lr": 3.846294928353471e-06, "epoch": 4.097165991902834, "percentage": 81.94, "elapsed_time": "6:45:50", "remaining_time": "1:29:25"}
1013
+ {"current_steps": 1013, "total_steps": 1235, "loss": 0.3676, "lr": 3.8130143409827345e-06, "epoch": 4.101214574898785, "percentage": 82.02, "elapsed_time": "6:46:14", "remaining_time": "1:29:01"}
1014
+ {"current_steps": 1014, "total_steps": 1235, "loss": 0.3884, "lr": 3.7798631843179887e-06, "epoch": 4.105263157894737, "percentage": 82.11, "elapsed_time": "6:46:38", "remaining_time": "1:28:37"}
1015
+ {"current_steps": 1015, "total_steps": 1235, "loss": 0.3736, "lr": 3.7468417234349973e-06, "epoch": 4.109311740890688, "percentage": 82.19, "elapsed_time": "6:47:02", "remaining_time": "1:28:13"}
1016
+ {"current_steps": 1016, "total_steps": 1235, "loss": 0.3792, "lr": 3.7139502223724823e-06, "epoch": 4.113360323886639, "percentage": 82.27, "elapsed_time": "6:47:26", "remaining_time": "1:27:49"}
1017
+ {"current_steps": 1017, "total_steps": 1235, "loss": 0.3696, "lr": 3.6811889441300095e-06, "epoch": 4.117408906882591, "percentage": 82.35, "elapsed_time": "6:47:50", "remaining_time": "1:27:25"}
1018
+ {"current_steps": 1018, "total_steps": 1235, "loss": 0.3837, "lr": 3.648558150665886e-06, "epoch": 4.1214574898785425, "percentage": 82.43, "elapsed_time": "6:48:13", "remaining_time": "1:27:01"}
1019
+ {"current_steps": 1019, "total_steps": 1235, "loss": 0.3741, "lr": 3.616058102895075e-06, "epoch": 4.125506072874494, "percentage": 82.51, "elapsed_time": "6:48:36", "remaining_time": "1:26:36"}
1020
+ {"current_steps": 1020, "total_steps": 1235, "loss": 0.3835, "lr": 3.583689060687079e-06, "epoch": 4.129554655870446, "percentage": 82.59, "elapsed_time": "6:48:59", "remaining_time": "1:26:12"}
1021
+ {"current_steps": 1021, "total_steps": 1235, "loss": 0.3888, "lr": 3.5514512828639023e-06, "epoch": 4.133603238866397, "percentage": 82.67, "elapsed_time": "6:49:23", "remaining_time": "1:25:48"}
1022
+ {"current_steps": 1022, "total_steps": 1235, "loss": 0.3816, "lr": 3.51934502719796e-06, "epoch": 4.137651821862348, "percentage": 82.75, "elapsed_time": "6:49:47", "remaining_time": "1:25:24"}
1023
+ {"current_steps": 1023, "total_steps": 1235, "loss": 0.3812, "lr": 3.4873705504100185e-06, "epoch": 4.1417004048583, "percentage": 82.83, "elapsed_time": "6:50:10", "remaining_time": "1:25:00"}
1024
+ {"current_steps": 1024, "total_steps": 1235, "loss": 0.385, "lr": 3.4555281081671345e-06, "epoch": 4.145748987854251, "percentage": 82.91, "elapsed_time": "6:50:34", "remaining_time": "1:24:36"}
1025
+ {"current_steps": 1025, "total_steps": 1235, "loss": 0.3651, "lr": 3.4238179550806326e-06, "epoch": 4.149797570850202, "percentage": 83.0, "elapsed_time": "6:50:57", "remaining_time": "1:24:11"}
1026
+ {"current_steps": 1026, "total_steps": 1235, "loss": 0.3736, "lr": 3.3922403447040497e-06, "epoch": 4.153846153846154, "percentage": 83.08, "elapsed_time": "6:51:20", "remaining_time": "1:23:47"}
1027
+ {"current_steps": 1027, "total_steps": 1235, "loss": 0.3841, "lr": 3.3607955295311247e-06, "epoch": 4.157894736842105, "percentage": 83.16, "elapsed_time": "6:51:44", "remaining_time": "1:23:23"}
1028
+ {"current_steps": 1028, "total_steps": 1235, "loss": 0.3679, "lr": 3.32948376099375e-06, "epoch": 4.161943319838056, "percentage": 83.24, "elapsed_time": "6:52:07", "remaining_time": "1:22:59"}
1029
+ {"current_steps": 1029, "total_steps": 1235, "loss": 0.3846, "lr": 3.2983052894599976e-06, "epoch": 4.165991902834008, "percentage": 83.32, "elapsed_time": "6:52:31", "remaining_time": "1:22:35"}
1030
+ {"current_steps": 1030, "total_steps": 1235, "loss": 0.3768, "lr": 3.2672603642320945e-06, "epoch": 4.17004048582996, "percentage": 83.4, "elapsed_time": "6:52:55", "remaining_time": "1:22:10"}
1031
+ {"current_steps": 1031, "total_steps": 1235, "loss": 0.3608, "lr": 3.236349233544438e-06, "epoch": 4.174089068825911, "percentage": 83.48, "elapsed_time": "6:53:18", "remaining_time": "1:21:46"}
1032
+ {"current_steps": 1032, "total_steps": 1235, "loss": 0.381, "lr": 3.205572144561604e-06, "epoch": 4.178137651821863, "percentage": 83.56, "elapsed_time": "6:53:42", "remaining_time": "1:21:22"}
1033
+ {"current_steps": 1033, "total_steps": 1235, "loss": 0.3877, "lr": 3.174929343376374e-06, "epoch": 4.182186234817814, "percentage": 83.64, "elapsed_time": "6:54:06", "remaining_time": "1:20:58"}
1034
+ {"current_steps": 1034, "total_steps": 1235, "loss": 0.3909, "lr": 3.1444210750077777e-06, "epoch": 4.186234817813765, "percentage": 83.72, "elapsed_time": "6:54:30", "remaining_time": "1:20:34"}
1035
+ {"current_steps": 1035, "total_steps": 1235, "loss": 0.3806, "lr": 3.1140475833991046e-06, "epoch": 4.190283400809717, "percentage": 83.81, "elapsed_time": "6:54:53", "remaining_time": "1:20:10"}
1036
+ {"current_steps": 1036, "total_steps": 1235, "loss": 0.3578, "lr": 3.0838091114159895e-06, "epoch": 4.194331983805668, "percentage": 83.89, "elapsed_time": "6:55:16", "remaining_time": "1:19:46"}
1037
+ {"current_steps": 1037, "total_steps": 1235, "loss": 0.3649, "lr": 3.0537059008444524e-06, "epoch": 4.198380566801619, "percentage": 83.97, "elapsed_time": "6:55:40", "remaining_time": "1:19:22"}
1038
+ {"current_steps": 1038, "total_steps": 1235, "loss": 0.3752, "lr": 3.0237381923889563e-06, "epoch": 4.202429149797571, "percentage": 84.05, "elapsed_time": "6:56:04", "remaining_time": "1:18:57"}
1039
+ {"current_steps": 1039, "total_steps": 1235, "loss": 0.3648, "lr": 2.9939062256704997e-06, "epoch": 4.206477732793522, "percentage": 84.13, "elapsed_time": "6:56:28", "remaining_time": "1:18:33"}
1040
+ {"current_steps": 1040, "total_steps": 1235, "loss": 0.3723, "lr": 2.964210239224696e-06, "epoch": 4.2105263157894735, "percentage": 84.21, "elapsed_time": "6:56:51", "remaining_time": "1:18:09"}
1041
+ {"current_steps": 1041, "total_steps": 1235, "loss": 0.3782, "lr": 2.934650470499869e-06, "epoch": 4.2145748987854255, "percentage": 84.29, "elapsed_time": "6:57:15", "remaining_time": "1:17:45"}
1042
+ {"current_steps": 1042, "total_steps": 1235, "loss": 0.3774, "lr": 2.905227155855128e-06, "epoch": 4.218623481781377, "percentage": 84.37, "elapsed_time": "6:57:39", "remaining_time": "1:17:21"}
1043
+ {"current_steps": 1043, "total_steps": 1235, "loss": 0.3844, "lr": 2.875940530558519e-06, "epoch": 4.222672064777328, "percentage": 84.45, "elapsed_time": "6:58:02", "remaining_time": "1:16:57"}
1044
+ {"current_steps": 1044, "total_steps": 1235, "loss": 0.3776, "lr": 2.8467908287851154e-06, "epoch": 4.22672064777328, "percentage": 84.53, "elapsed_time": "6:58:26", "remaining_time": "1:16:33"}
1045
+ {"current_steps": 1045, "total_steps": 1235, "loss": 0.3719, "lr": 2.8177782836151603e-06, "epoch": 4.230769230769231, "percentage": 84.62, "elapsed_time": "6:58:50", "remaining_time": "1:16:09"}
1046
+ {"current_steps": 1046, "total_steps": 1235, "loss": 0.3829, "lr": 2.7889031270321874e-06, "epoch": 4.234817813765182, "percentage": 84.7, "elapsed_time": "6:59:14", "remaining_time": "1:15:45"}
1047
+ {"current_steps": 1047, "total_steps": 1235, "loss": 0.3749, "lr": 2.760165589921184e-06, "epoch": 4.238866396761134, "percentage": 84.78, "elapsed_time": "6:59:38", "remaining_time": "1:15:20"}
1048
+ {"current_steps": 1048, "total_steps": 1235, "loss": 0.3597, "lr": 2.7315659020667305e-06, "epoch": 4.242914979757085, "percentage": 84.86, "elapsed_time": "7:00:01", "remaining_time": "1:14:56"}
1049
+ {"current_steps": 1049, "total_steps": 1235, "loss": 0.3625, "lr": 2.703104292151164e-06, "epoch": 4.246963562753036, "percentage": 84.94, "elapsed_time": "7:00:25", "remaining_time": "1:14:32"}
1050
+ {"current_steps": 1050, "total_steps": 1235, "loss": 0.3644, "lr": 2.6747809877527607e-06, "epoch": 4.251012145748988, "percentage": 85.02, "elapsed_time": "7:00:48", "remaining_time": "1:14:08"}
1051
+ {"current_steps": 1051, "total_steps": 1235, "loss": 0.3871, "lr": 2.6465962153439082e-06, "epoch": 4.255060728744939, "percentage": 85.1, "elapsed_time": "7:01:12", "remaining_time": "1:13:44"}
1052
+ {"current_steps": 1052, "total_steps": 1235, "loss": 0.3762, "lr": 2.618550200289303e-06, "epoch": 4.2591093117408905, "percentage": 85.18, "elapsed_time": "7:01:35", "remaining_time": "1:13:20"}
1053
+ {"current_steps": 1053, "total_steps": 1235, "loss": 0.3698, "lr": 2.59064316684412e-06, "epoch": 4.2631578947368425, "percentage": 85.26, "elapsed_time": "7:01:58", "remaining_time": "1:12:56"}
1054
+ {"current_steps": 1054, "total_steps": 1235, "loss": 0.3719, "lr": 2.562875338152264e-06, "epoch": 4.267206477732794, "percentage": 85.34, "elapsed_time": "7:02:22", "remaining_time": "1:12:31"}
1055
+ {"current_steps": 1055, "total_steps": 1235, "loss": 0.3768, "lr": 2.5352469362445552e-06, "epoch": 4.271255060728745, "percentage": 85.43, "elapsed_time": "7:02:45", "remaining_time": "1:12:07"}
1056
+ {"current_steps": 1056, "total_steps": 1235, "loss": 0.3604, "lr": 2.5077581820369523e-06, "epoch": 4.275303643724697, "percentage": 85.51, "elapsed_time": "7:03:09", "remaining_time": "1:11:43"}
1057
+ {"current_steps": 1057, "total_steps": 1235, "loss": 0.3693, "lr": 2.480409295328803e-06, "epoch": 4.279352226720648, "percentage": 85.59, "elapsed_time": "7:03:32", "remaining_time": "1:11:19"}
1058
+ {"current_steps": 1058, "total_steps": 1235, "loss": 0.389, "lr": 2.45320049480108e-06, "epoch": 4.283400809716599, "percentage": 85.67, "elapsed_time": "7:03:56", "remaining_time": "1:10:55"}
1059
+ {"current_steps": 1059, "total_steps": 1235, "loss": 0.3707, "lr": 2.4261319980146293e-06, "epoch": 4.287449392712551, "percentage": 85.75, "elapsed_time": "7:04:19", "remaining_time": "1:10:31"}
1060
+ {"current_steps": 1060, "total_steps": 1235, "loss": 0.3807, "lr": 2.399204021408421e-06, "epoch": 4.291497975708502, "percentage": 85.83, "elapsed_time": "7:04:43", "remaining_time": "1:10:07"}
1061
+ {"current_steps": 1061, "total_steps": 1235, "loss": 0.3709, "lr": 2.3724167802978395e-06, "epoch": 4.295546558704453, "percentage": 85.91, "elapsed_time": "7:05:06", "remaining_time": "1:09:43"}
1062
+ {"current_steps": 1062, "total_steps": 1235, "loss": 0.391, "lr": 2.3457704888729625e-06, "epoch": 4.299595141700405, "percentage": 85.99, "elapsed_time": "7:05:29", "remaining_time": "1:09:18"}
1063
+ {"current_steps": 1063, "total_steps": 1235, "loss": 0.3588, "lr": 2.3192653601968162e-06, "epoch": 4.303643724696356, "percentage": 86.07, "elapsed_time": "7:05:53", "remaining_time": "1:08:54"}
1064
+ {"current_steps": 1064, "total_steps": 1235, "loss": 0.3637, "lr": 2.2929016062037057e-06, "epoch": 4.3076923076923075, "percentage": 86.15, "elapsed_time": "7:06:17", "remaining_time": "1:08:30"}
1065
+ {"current_steps": 1065, "total_steps": 1235, "loss": 0.3634, "lr": 2.2666794376975055e-06, "epoch": 4.3117408906882595, "percentage": 86.23, "elapsed_time": "7:06:40", "remaining_time": "1:08:06"}
1066
+ {"current_steps": 1066, "total_steps": 1235, "loss": 0.3716, "lr": 2.24059906434998e-06, "epoch": 4.315789473684211, "percentage": 86.32, "elapsed_time": "7:07:03", "remaining_time": "1:07:42"}
1067
+ {"current_steps": 1067, "total_steps": 1235, "loss": 0.3717, "lr": 2.214660694699091e-06, "epoch": 4.319838056680162, "percentage": 86.4, "elapsed_time": "7:07:27", "remaining_time": "1:07:18"}
1068
+ {"current_steps": 1068, "total_steps": 1235, "loss": 0.3828, "lr": 2.188864536147355e-06, "epoch": 4.323886639676114, "percentage": 86.48, "elapsed_time": "7:07:49", "remaining_time": "1:06:53"}
1069
+ {"current_steps": 1069, "total_steps": 1235, "loss": 0.3793, "lr": 2.1632107949601757e-06, "epoch": 4.327935222672065, "percentage": 86.56, "elapsed_time": "7:08:13", "remaining_time": "1:06:29"}
1070
+ {"current_steps": 1070, "total_steps": 1235, "loss": 0.3821, "lr": 2.137699676264171e-06, "epoch": 4.331983805668016, "percentage": 86.64, "elapsed_time": "7:08:36", "remaining_time": "1:06:05"}
1071
+ {"current_steps": 1071, "total_steps": 1235, "loss": 0.3553, "lr": 2.1123313840455738e-06, "epoch": 4.336032388663968, "percentage": 86.72, "elapsed_time": "7:09:00", "remaining_time": "1:05:41"}
1072
+ {"current_steps": 1072, "total_steps": 1235, "loss": 0.3856, "lr": 2.08710612114857e-06, "epoch": 4.340080971659919, "percentage": 86.8, "elapsed_time": "7:09:23", "remaining_time": "1:05:17"}
1073
+ {"current_steps": 1073, "total_steps": 1235, "loss": 0.3846, "lr": 2.0620240892736953e-06, "epoch": 4.34412955465587, "percentage": 86.88, "elapsed_time": "7:09:46", "remaining_time": "1:04:53"}
1074
+ {"current_steps": 1074, "total_steps": 1235, "loss": 0.376, "lr": 2.0370854889762e-06, "epoch": 4.348178137651822, "percentage": 86.96, "elapsed_time": "7:10:10", "remaining_time": "1:04:29"}
1075
+ {"current_steps": 1075, "total_steps": 1235, "loss": 0.3705, "lr": 2.0122905196644726e-06, "epoch": 4.352226720647773, "percentage": 87.04, "elapsed_time": "7:10:33", "remaining_time": "1:04:04"}
1076
+ {"current_steps": 1076, "total_steps": 1235, "loss": 0.3686, "lr": 1.987639379598427e-06, "epoch": 4.3562753036437245, "percentage": 87.13, "elapsed_time": "7:10:56", "remaining_time": "1:03:40"}
1077
+ {"current_steps": 1077, "total_steps": 1235, "loss": 0.3732, "lr": 1.963132265887919e-06, "epoch": 4.3603238866396765, "percentage": 87.21, "elapsed_time": "7:11:19", "remaining_time": "1:03:16"}
1078
+ {"current_steps": 1078, "total_steps": 1235, "loss": 0.3885, "lr": 1.9387693744911784e-06, "epoch": 4.364372469635628, "percentage": 87.29, "elapsed_time": "7:11:42", "remaining_time": "1:02:52"}
1079
+ {"current_steps": 1079, "total_steps": 1235, "loss": 0.368, "lr": 1.9145509002132368e-06, "epoch": 4.368421052631579, "percentage": 87.37, "elapsed_time": "7:12:05", "remaining_time": "1:02:28"}
1080
+ {"current_steps": 1080, "total_steps": 1235, "loss": 0.3585, "lr": 1.8904770367043723e-06, "epoch": 4.372469635627531, "percentage": 87.45, "elapsed_time": "7:12:29", "remaining_time": "1:02:04"}
1081
+ {"current_steps": 1081, "total_steps": 1235, "loss": 0.3618, "lr": 1.8665479764585504e-06, "epoch": 4.376518218623482, "percentage": 87.53, "elapsed_time": "7:12:51", "remaining_time": "1:01:39"}
1082
+ {"current_steps": 1082, "total_steps": 1235, "loss": 0.3727, "lr": 1.8427639108118977e-06, "epoch": 4.380566801619433, "percentage": 87.61, "elapsed_time": "7:13:15", "remaining_time": "1:01:15"}
1083
+ {"current_steps": 1083, "total_steps": 1235, "loss": 0.3686, "lr": 1.8191250299411755e-06, "epoch": 4.384615384615385, "percentage": 87.69, "elapsed_time": "7:13:39", "remaining_time": "1:00:51"}
1084
+ {"current_steps": 1084, "total_steps": 1235, "loss": 0.3806, "lr": 1.7956315228622446e-06, "epoch": 4.388663967611336, "percentage": 87.77, "elapsed_time": "7:14:03", "remaining_time": "1:00:27"}
1085
+ {"current_steps": 1085, "total_steps": 1235, "loss": 0.3771, "lr": 1.7722835774285553e-06, "epoch": 4.392712550607287, "percentage": 87.85, "elapsed_time": "7:14:27", "remaining_time": "1:00:03"}
1086
+ {"current_steps": 1086, "total_steps": 1235, "loss": 0.3771, "lr": 1.7490813803296624e-06, "epoch": 4.396761133603239, "percentage": 87.94, "elapsed_time": "7:14:50", "remaining_time": "0:59:39"}
1087
+ {"current_steps": 1087, "total_steps": 1235, "loss": 0.3709, "lr": 1.726025117089718e-06, "epoch": 4.40080971659919, "percentage": 88.02, "elapsed_time": "7:15:13", "remaining_time": "0:59:15"}
1088
+ {"current_steps": 1088, "total_steps": 1235, "loss": 0.3718, "lr": 1.70311497206598e-06, "epoch": 4.4048582995951415, "percentage": 88.1, "elapsed_time": "7:15:37", "remaining_time": "0:58:51"}
1089
+ {"current_steps": 1089, "total_steps": 1235, "loss": 0.3722, "lr": 1.6803511284473638e-06, "epoch": 4.4089068825910935, "percentage": 88.18, "elapsed_time": "7:16:01", "remaining_time": "0:58:27"}
1090
+ {"current_steps": 1090, "total_steps": 1235, "loss": 0.4004, "lr": 1.6577337682529538e-06, "epoch": 4.412955465587045, "percentage": 88.26, "elapsed_time": "7:16:24", "remaining_time": "0:58:03"}
1091
+ {"current_steps": 1091, "total_steps": 1235, "loss": 0.3753, "lr": 1.6352630723305617e-06, "epoch": 4.417004048582996, "percentage": 88.34, "elapsed_time": "7:16:49", "remaining_time": "0:57:39"}
1092
+ {"current_steps": 1092, "total_steps": 1235, "loss": 0.4214, "lr": 1.612939220355272e-06, "epoch": 4.421052631578947, "percentage": 88.42, "elapsed_time": "7:17:13", "remaining_time": "0:57:15"}
1093
+ {"current_steps": 1093, "total_steps": 1235, "loss": 0.386, "lr": 1.5907623908280112e-06, "epoch": 4.425101214574899, "percentage": 88.5, "elapsed_time": "7:17:36", "remaining_time": "0:56:51"}
1094
+ {"current_steps": 1094, "total_steps": 1235, "loss": 0.3779, "lr": 1.568732761074121e-06, "epoch": 4.42914979757085, "percentage": 88.58, "elapsed_time": "7:17:59", "remaining_time": "0:56:27"}
1095
+ {"current_steps": 1095, "total_steps": 1235, "loss": 0.3722, "lr": 1.5468505072419237e-06, "epoch": 4.433198380566802, "percentage": 88.66, "elapsed_time": "7:18:22", "remaining_time": "0:56:02"}
1096
+ {"current_steps": 1096, "total_steps": 1235, "loss": 0.3727, "lr": 1.5251158043013448e-06, "epoch": 4.437246963562753, "percentage": 88.74, "elapsed_time": "7:18:46", "remaining_time": "0:55:38"}
1097
+ {"current_steps": 1097, "total_steps": 1235, "loss": 0.3706, "lr": 1.5035288260424885e-06, "epoch": 4.441295546558704, "percentage": 88.83, "elapsed_time": "7:19:10", "remaining_time": "0:55:14"}
1098
+ {"current_steps": 1098, "total_steps": 1235, "loss": 0.369, "lr": 1.4820897450742623e-06, "epoch": 4.445344129554655, "percentage": 88.91, "elapsed_time": "7:19:33", "remaining_time": "0:54:50"}
1099
+ {"current_steps": 1099, "total_steps": 1235, "loss": 0.3645, "lr": 1.4607987328229767e-06, "epoch": 4.449392712550607, "percentage": 88.99, "elapsed_time": "7:19:57", "remaining_time": "0:54:26"}
1100
+ {"current_steps": 1100, "total_steps": 1235, "loss": 0.3773, "lr": 1.4396559595310056e-06, "epoch": 4.4534412955465585, "percentage": 89.07, "elapsed_time": "7:20:20", "remaining_time": "0:54:02"}
1101
+ {"current_steps": 1101, "total_steps": 1235, "loss": 0.375, "lr": 1.4186615942553973e-06, "epoch": 4.4574898785425106, "percentage": 89.15, "elapsed_time": "7:20:44", "remaining_time": "0:53:38"}
1102
+ {"current_steps": 1102, "total_steps": 1235, "loss": 0.3775, "lr": 1.3978158048665424e-06, "epoch": 4.461538461538462, "percentage": 89.23, "elapsed_time": "7:21:07", "remaining_time": "0:53:14"}
1103
+ {"current_steps": 1103, "total_steps": 1235, "loss": 0.391, "lr": 1.3771187580468115e-06, "epoch": 4.465587044534413, "percentage": 89.31, "elapsed_time": "7:21:31", "remaining_time": "0:52:50"}
1104
+ {"current_steps": 1104, "total_steps": 1235, "loss": 0.3807, "lr": 1.3565706192892392e-06, "epoch": 4.469635627530364, "percentage": 89.39, "elapsed_time": "7:21:55", "remaining_time": "0:52:26"}
1105
+ {"current_steps": 1105, "total_steps": 1235, "loss": 0.3755, "lr": 1.3361715528961993e-06, "epoch": 4.473684210526316, "percentage": 89.47, "elapsed_time": "7:22:19", "remaining_time": "0:52:02"}
1106
+ {"current_steps": 1106, "total_steps": 1235, "loss": 0.3759, "lr": 1.3159217219780817e-06, "epoch": 4.477732793522267, "percentage": 89.55, "elapsed_time": "7:22:42", "remaining_time": "0:51:38"}
1107
+ {"current_steps": 1107, "total_steps": 1235, "loss": 0.363, "lr": 1.2958212884519949e-06, "epoch": 4.481781376518219, "percentage": 89.64, "elapsed_time": "7:23:06", "remaining_time": "0:51:14"}
1108
+ {"current_steps": 1108, "total_steps": 1235, "loss": 0.3759, "lr": 1.2758704130404675e-06, "epoch": 4.48582995951417, "percentage": 89.72, "elapsed_time": "7:23:28", "remaining_time": "0:50:49"}
1109
+ {"current_steps": 1109, "total_steps": 1235, "loss": 0.3785, "lr": 1.2560692552701738e-06, "epoch": 4.489878542510121, "percentage": 89.8, "elapsed_time": "7:23:50", "remaining_time": "0:50:25"}
1110
+ {"current_steps": 1110, "total_steps": 1235, "loss": 0.3929, "lr": 1.2364179734706382e-06, "epoch": 4.493927125506072, "percentage": 89.88, "elapsed_time": "7:24:14", "remaining_time": "0:50:01"}
1111
+ {"current_steps": 1111, "total_steps": 1235, "loss": 0.3679, "lr": 1.2169167247729852e-06, "epoch": 4.497975708502024, "percentage": 89.96, "elapsed_time": "7:24:37", "remaining_time": "0:49:37"}
1112
+ {"current_steps": 1112, "total_steps": 1235, "loss": 0.3771, "lr": 1.1975656651086864e-06, "epoch": 4.502024291497976, "percentage": 90.04, "elapsed_time": "7:25:00", "remaining_time": "0:49:13"}
1113
+ {"current_steps": 1113, "total_steps": 1235, "loss": 0.3912, "lr": 1.1783649492082926e-06, "epoch": 4.506072874493928, "percentage": 90.12, "elapsed_time": "7:25:23", "remaining_time": "0:48:49"}
1114
+ {"current_steps": 1114, "total_steps": 1235, "loss": 0.3658, "lr": 1.1593147306002183e-06, "epoch": 4.510121457489879, "percentage": 90.2, "elapsed_time": "7:25:47", "remaining_time": "0:48:25"}
1115
+ {"current_steps": 1115, "total_steps": 1235, "loss": 0.3712, "lr": 1.140415161609505e-06, "epoch": 4.51417004048583, "percentage": 90.28, "elapsed_time": "7:26:11", "remaining_time": "0:48:01"}
1116
+ {"current_steps": 1116, "total_steps": 1235, "loss": 0.3696, "lr": 1.121666393356604e-06, "epoch": 4.518218623481781, "percentage": 90.36, "elapsed_time": "7:26:34", "remaining_time": "0:47:37"}
1117
+ {"current_steps": 1117, "total_steps": 1235, "loss": 0.3906, "lr": 1.1030685757561632e-06, "epoch": 4.522267206477733, "percentage": 90.45, "elapsed_time": "7:26:57", "remaining_time": "0:47:13"}
1118
+ {"current_steps": 1118, "total_steps": 1235, "loss": 0.3855, "lr": 1.0846218575158373e-06, "epoch": 4.526315789473684, "percentage": 90.53, "elapsed_time": "7:27:20", "remaining_time": "0:46:48"}
1119
+ {"current_steps": 1119, "total_steps": 1235, "loss": 0.3857, "lr": 1.066326386135097e-06, "epoch": 4.530364372469636, "percentage": 90.61, "elapsed_time": "7:27:44", "remaining_time": "0:46:24"}
1120
+ {"current_steps": 1120, "total_steps": 1235, "loss": 0.3774, "lr": 1.0481823079040398e-06, "epoch": 4.534412955465587, "percentage": 90.69, "elapsed_time": "7:28:07", "remaining_time": "0:46:00"}
1121
+ {"current_steps": 1121, "total_steps": 1235, "loss": 0.3709, "lr": 1.0301897679022344e-06, "epoch": 4.538461538461538, "percentage": 90.77, "elapsed_time": "7:28:30", "remaining_time": "0:45:36"}
1122
+ {"current_steps": 1122, "total_steps": 1235, "loss": 0.3779, "lr": 1.0123489099975491e-06, "epoch": 4.5425101214574894, "percentage": 90.85, "elapsed_time": "7:28:54", "remaining_time": "0:45:12"}
1123
+ {"current_steps": 1123, "total_steps": 1235, "loss": 0.3767, "lr": 9.9465987684501e-07, "epoch": 4.5465587044534415, "percentage": 90.93, "elapsed_time": "7:29:18", "remaining_time": "0:44:48"}
1124
+ {"current_steps": 1124, "total_steps": 1235, "loss": 0.3741, "lr": 9.771228098856534e-07, "epoch": 4.550607287449393, "percentage": 91.01, "elapsed_time": "7:29:41", "remaining_time": "0:44:24"}
1125
+ {"current_steps": 1125, "total_steps": 1235, "loss": 0.3822, "lr": 9.597378493454013e-07, "epoch": 4.554655870445345, "percentage": 91.09, "elapsed_time": "7:30:04", "remaining_time": "0:44:00"}
1126
+ {"current_steps": 1126, "total_steps": 1235, "loss": 0.3914, "lr": 9.425051342339353e-07, "epoch": 4.558704453441296, "percentage": 91.17, "elapsed_time": "7:30:28", "remaining_time": "0:43:36"}
1127
+ {"current_steps": 1127, "total_steps": 1235, "loss": 0.3939, "lr": 9.254248023435864e-07, "epoch": 4.562753036437247, "percentage": 91.26, "elapsed_time": "7:30:51", "remaining_time": "0:43:12"}
1128
+ {"current_steps": 1128, "total_steps": 1235, "loss": 0.3674, "lr": 9.084969902482288e-07, "epoch": 4.566801619433198, "percentage": 91.34, "elapsed_time": "7:31:15", "remaining_time": "0:42:48"}
1129
+ {"current_steps": 1129, "total_steps": 1235, "loss": 0.3903, "lr": 8.917218333021993e-07, "epoch": 4.57085020242915, "percentage": 91.42, "elapsed_time": "7:31:38", "remaining_time": "0:42:24"}
1130
+ {"current_steps": 1130, "total_steps": 1235, "loss": 0.3876, "lr": 8.750994656392109e-07, "epoch": 4.574898785425101, "percentage": 91.5, "elapsed_time": "7:32:02", "remaining_time": "0:42:00"}
1131
+ {"current_steps": 1131, "total_steps": 1235, "loss": 0.3827, "lr": 8.58630020171265e-07, "epoch": 4.578947368421053, "percentage": 91.58, "elapsed_time": "7:32:25", "remaining_time": "0:41:36"}
1132
+ {"current_steps": 1132, "total_steps": 1235, "loss": 0.3786, "lr": 8.423136285876099e-07, "epoch": 4.582995951417004, "percentage": 91.66, "elapsed_time": "7:32:49", "remaining_time": "0:41:12"}
1133
+ {"current_steps": 1133, "total_steps": 1235, "loss": 0.373, "lr": 8.26150421353682e-07, "epoch": 4.587044534412955, "percentage": 91.74, "elapsed_time": "7:33:13", "remaining_time": "0:40:48"}
1134
+ {"current_steps": 1134, "total_steps": 1235, "loss": 0.371, "lr": 8.101405277100549e-07, "epoch": 4.5910931174089065, "percentage": 91.82, "elapsed_time": "7:33:35", "remaining_time": "0:40:23"}
1135
+ {"current_steps": 1135, "total_steps": 1235, "loss": 0.3836, "lr": 7.942840756714077e-07, "epoch": 4.5951417004048585, "percentage": 91.9, "elapsed_time": "7:33:58", "remaining_time": "0:39:59"}
1136
+ {"current_steps": 1136, "total_steps": 1235, "loss": 0.376, "lr": 7.785811920255093e-07, "epoch": 4.59919028340081, "percentage": 91.98, "elapsed_time": "7:34:22", "remaining_time": "0:39:35"}
1137
+ {"current_steps": 1137, "total_steps": 1235, "loss": 0.378, "lr": 7.630320023322024e-07, "epoch": 4.603238866396762, "percentage": 92.06, "elapsed_time": "7:34:45", "remaining_time": "0:39:11"}
1138
+ {"current_steps": 1138, "total_steps": 1235, "loss": 0.3901, "lr": 7.476366309223903e-07, "epoch": 4.607287449392713, "percentage": 92.15, "elapsed_time": "7:35:09", "remaining_time": "0:38:47"}
1139
+ {"current_steps": 1139, "total_steps": 1235, "loss": 0.3852, "lr": 7.323952008970537e-07, "epoch": 4.611336032388664, "percentage": 92.23, "elapsed_time": "7:35:33", "remaining_time": "0:38:23"}
1140
+ {"current_steps": 1140, "total_steps": 1235, "loss": 0.3736, "lr": 7.173078341262618e-07, "epoch": 4.615384615384615, "percentage": 92.31, "elapsed_time": "7:35:56", "remaining_time": "0:37:59"}
1141
+ {"current_steps": 1141, "total_steps": 1235, "loss": 0.3817, "lr": 7.023746512481989e-07, "epoch": 4.619433198380567, "percentage": 92.39, "elapsed_time": "7:36:20", "remaining_time": "0:37:35"}
1142
+ {"current_steps": 1142, "total_steps": 1235, "loss": 0.3754, "lr": 6.875957716681902e-07, "epoch": 4.623481781376518, "percentage": 92.47, "elapsed_time": "7:36:43", "remaining_time": "0:37:11"}
1143
+ {"current_steps": 1143, "total_steps": 1235, "loss": 0.3613, "lr": 6.729713135577687e-07, "epoch": 4.62753036437247, "percentage": 92.55, "elapsed_time": "7:37:06", "remaining_time": "0:36:47"}
1144
+ {"current_steps": 1144, "total_steps": 1235, "loss": 0.3781, "lr": 6.585013938537143e-07, "epoch": 4.631578947368421, "percentage": 92.63, "elapsed_time": "7:37:30", "remaining_time": "0:36:23"}
1145
+ {"current_steps": 1145, "total_steps": 1235, "loss": 0.376, "lr": 6.441861282571115e-07, "epoch": 4.635627530364372, "percentage": 92.71, "elapsed_time": "7:37:54", "remaining_time": "0:35:59"}
1146
+ {"current_steps": 1146, "total_steps": 1235, "loss": 0.3758, "lr": 6.300256312324471e-07, "epoch": 4.6396761133603235, "percentage": 92.79, "elapsed_time": "7:38:17", "remaining_time": "0:35:35"}
1147
+ {"current_steps": 1147, "total_steps": 1235, "loss": 0.3698, "lr": 6.160200160066776e-07, "epoch": 4.6437246963562755, "percentage": 92.87, "elapsed_time": "7:38:40", "remaining_time": "0:35:11"}
1148
+ {"current_steps": 1148, "total_steps": 1235, "loss": 0.3784, "lr": 6.021693945683327e-07, "epoch": 4.647773279352227, "percentage": 92.96, "elapsed_time": "7:39:04", "remaining_time": "0:34:47"}
1149
+ {"current_steps": 1149, "total_steps": 1235, "loss": 0.3721, "lr": 5.884738776666044e-07, "epoch": 4.651821862348179, "percentage": 93.04, "elapsed_time": "7:39:27", "remaining_time": "0:34:23"}
1150
+ {"current_steps": 1150, "total_steps": 1235, "loss": 0.3903, "lr": 5.749335748104878e-07, "epoch": 4.65587044534413, "percentage": 93.12, "elapsed_time": "7:39:51", "remaining_time": "0:33:59"}
1151
+ {"current_steps": 1151, "total_steps": 1235, "loss": 0.387, "lr": 5.615485942678778e-07, "epoch": 4.659919028340081, "percentage": 93.2, "elapsed_time": "7:40:15", "remaining_time": "0:33:35"}
1152
+ {"current_steps": 1152, "total_steps": 1235, "loss": 0.3688, "lr": 5.483190430647289e-07, "epoch": 4.663967611336032, "percentage": 93.28, "elapsed_time": "7:40:38", "remaining_time": "0:33:11"}
1153
+ {"current_steps": 1153, "total_steps": 1235, "loss": 0.3712, "lr": 5.352450269841747e-07, "epoch": 4.668016194331984, "percentage": 93.36, "elapsed_time": "7:41:01", "remaining_time": "0:32:47"}
1154
+ {"current_steps": 1154, "total_steps": 1235, "loss": 0.3858, "lr": 5.22326650565701e-07, "epoch": 4.672064777327935, "percentage": 93.44, "elapsed_time": "7:41:25", "remaining_time": "0:32:23"}
1155
+ {"current_steps": 1155, "total_steps": 1235, "loss": 0.3774, "lr": 5.095640171043048e-07, "epoch": 4.676113360323887, "percentage": 93.52, "elapsed_time": "7:41:48", "remaining_time": "0:31:59"}
1156
+ {"current_steps": 1156, "total_steps": 1235, "loss": 0.3715, "lr": 4.969572286496594e-07, "epoch": 4.680161943319838, "percentage": 93.6, "elapsed_time": "7:42:11", "remaining_time": "0:31:35"}
1157
+ {"current_steps": 1157, "total_steps": 1235, "loss": 0.3755, "lr": 4.845063860053079e-07, "epoch": 4.684210526315789, "percentage": 93.68, "elapsed_time": "7:42:35", "remaining_time": "0:31:11"}
1158
+ {"current_steps": 1158, "total_steps": 1235, "loss": 0.367, "lr": 4.7221158872785997e-07, "epoch": 4.6882591093117405, "percentage": 93.77, "elapsed_time": "7:42:59", "remaining_time": "0:30:47"}
1159
+ {"current_steps": 1159, "total_steps": 1235, "loss": 0.369, "lr": 4.600729351261857e-07, "epoch": 4.6923076923076925, "percentage": 93.85, "elapsed_time": "7:43:23", "remaining_time": "0:30:23"}
1160
+ {"current_steps": 1160, "total_steps": 1235, "loss": 0.3736, "lr": 4.4809052226063355e-07, "epoch": 4.696356275303644, "percentage": 93.93, "elapsed_time": "7:43:47", "remaining_time": "0:29:59"}
1161
+ {"current_steps": 1161, "total_steps": 1235, "loss": 0.3866, "lr": 4.3626444594226046e-07, "epoch": 4.700404858299595, "percentage": 94.01, "elapsed_time": "7:44:10", "remaining_time": "0:29:35"}
1162
+ {"current_steps": 1162, "total_steps": 1235, "loss": 0.3724, "lr": 4.245948007320588e-07, "epoch": 4.704453441295547, "percentage": 94.09, "elapsed_time": "7:44:33", "remaining_time": "0:29:11"}
1163
+ {"current_steps": 1163, "total_steps": 1235, "loss": 0.3532, "lr": 4.130816799401971e-07, "epoch": 4.708502024291498, "percentage": 94.17, "elapsed_time": "7:44:56", "remaining_time": "0:28:47"}
1164
+ {"current_steps": 1164, "total_steps": 1235, "loss": 0.3696, "lr": 4.017251756252827e-07, "epoch": 4.712550607287449, "percentage": 94.25, "elapsed_time": "7:45:19", "remaining_time": "0:28:22"}
1165
+ {"current_steps": 1165, "total_steps": 1235, "loss": 0.3789, "lr": 3.9052537859362473e-07, "epoch": 4.716599190283401, "percentage": 94.33, "elapsed_time": "7:45:43", "remaining_time": "0:27:58"}
1166
+ {"current_steps": 1166, "total_steps": 1235, "loss": 0.3933, "lr": 3.7948237839849687e-07, "epoch": 4.720647773279352, "percentage": 94.41, "elapsed_time": "7:46:07", "remaining_time": "0:27:35"}
1167
+ {"current_steps": 1167, "total_steps": 1235, "loss": 0.3628, "lr": 3.6859626333943797e-07, "epoch": 4.724696356275303, "percentage": 94.49, "elapsed_time": "7:46:30", "remaining_time": "0:27:10"}
1168
+ {"current_steps": 1168, "total_steps": 1235, "loss": 0.3798, "lr": 3.578671204615347e-07, "epoch": 4.728744939271255, "percentage": 94.57, "elapsed_time": "7:46:54", "remaining_time": "0:26:46"}
1169
+ {"current_steps": 1169, "total_steps": 1235, "loss": 0.3693, "lr": 3.472950355547267e-07, "epoch": 4.732793522267206, "percentage": 94.66, "elapsed_time": "7:47:17", "remaining_time": "0:26:22"}
1170
+ {"current_steps": 1170, "total_steps": 1235, "loss": 0.3834, "lr": 3.3688009315312244e-07, "epoch": 4.7368421052631575, "percentage": 94.74, "elapsed_time": "7:47:40", "remaining_time": "0:25:58"}
1171
+ {"current_steps": 1171, "total_steps": 1235, "loss": 0.3617, "lr": 3.266223765343224e-07, "epoch": 4.7408906882591095, "percentage": 94.82, "elapsed_time": "7:48:03", "remaining_time": "0:25:34"}
1172
+ {"current_steps": 1172, "total_steps": 1235, "loss": 0.3875, "lr": 3.16521967718757e-07, "epoch": 4.744939271255061, "percentage": 94.9, "elapsed_time": "7:48:27", "remaining_time": "0:25:10"}
1173
+ {"current_steps": 1173, "total_steps": 1235, "loss": 0.3566, "lr": 3.0657894746902726e-07, "epoch": 4.748987854251012, "percentage": 94.98, "elapsed_time": "7:48:50", "remaining_time": "0:24:46"}
1174
+ {"current_steps": 1174, "total_steps": 1235, "loss": 0.3841, "lr": 2.9679339528925654e-07, "epoch": 4.753036437246964, "percentage": 95.06, "elapsed_time": "7:49:13", "remaining_time": "0:24:22"}
1175
+ {"current_steps": 1175, "total_steps": 1235, "loss": 0.3761, "lr": 2.871653894244597e-07, "epoch": 4.757085020242915, "percentage": 95.14, "elapsed_time": "7:49:36", "remaining_time": "0:23:58"}
1176
+ {"current_steps": 1176, "total_steps": 1235, "loss": 0.3773, "lr": 2.7769500685991266e-07, "epoch": 4.761133603238866, "percentage": 95.22, "elapsed_time": "7:50:01", "remaining_time": "0:23:34"}
1177
+ {"current_steps": 1177, "total_steps": 1235, "loss": 0.3952, "lr": 2.683823233205485e-07, "epoch": 4.765182186234818, "percentage": 95.3, "elapsed_time": "7:50:24", "remaining_time": "0:23:10"}
1178
+ {"current_steps": 1178, "total_steps": 1235, "loss": 0.3852, "lr": 2.592274132703287e-07, "epoch": 4.769230769230769, "percentage": 95.38, "elapsed_time": "7:50:47", "remaining_time": "0:22:46"}
1179
+ {"current_steps": 1179, "total_steps": 1235, "loss": 0.3775, "lr": 2.502303499116754e-07, "epoch": 4.77327935222672, "percentage": 95.47, "elapsed_time": "7:51:11", "remaining_time": "0:22:22"}
1180
+ {"current_steps": 1180, "total_steps": 1235, "loss": 0.3712, "lr": 2.413912051848666e-07, "epoch": 4.777327935222672, "percentage": 95.55, "elapsed_time": "7:51:34", "remaining_time": "0:21:58"}
1181
+ {"current_steps": 1181, "total_steps": 1235, "loss": 0.3727, "lr": 2.3271004976746613e-07, "epoch": 4.781376518218623, "percentage": 95.63, "elapsed_time": "7:51:58", "remaining_time": "0:21:34"}
1182
+ {"current_steps": 1182, "total_steps": 1235, "loss": 0.3898, "lr": 2.2418695307376393e-07, "epoch": 4.7854251012145745, "percentage": 95.71, "elapsed_time": "7:52:22", "remaining_time": "0:21:10"}
1183
+ {"current_steps": 1183, "total_steps": 1235, "loss": 0.3874, "lr": 2.1582198325420968e-07, "epoch": 4.7894736842105265, "percentage": 95.79, "elapsed_time": "7:52:45", "remaining_time": "0:20:46"}
1184
+ {"current_steps": 1184, "total_steps": 1235, "loss": 0.3778, "lr": 2.0761520719488447e-07, "epoch": 4.793522267206478, "percentage": 95.87, "elapsed_time": "7:53:09", "remaining_time": "0:20:22"}
1185
+ {"current_steps": 1185, "total_steps": 1235, "loss": 0.3858, "lr": 1.9956669051694798e-07, "epoch": 4.797570850202429, "percentage": 95.95, "elapsed_time": "7:53:33", "remaining_time": "0:19:58"}
1186
+ {"current_steps": 1186, "total_steps": 1235, "loss": 0.3735, "lr": 1.916764975761254e-07, "epoch": 4.801619433198381, "percentage": 96.03, "elapsed_time": "7:53:56", "remaining_time": "0:19:34"}
1187
+ {"current_steps": 1187, "total_steps": 1235, "loss": 0.3855, "lr": 1.839446914621923e-07, "epoch": 4.805668016194332, "percentage": 96.11, "elapsed_time": "7:54:19", "remaining_time": "0:19:10"}
1188
+ {"current_steps": 1188, "total_steps": 1235, "loss": 0.3825, "lr": 1.7637133399845962e-07, "epoch": 4.809716599190283, "percentage": 96.19, "elapsed_time": "7:54:42", "remaining_time": "0:18:46"}
1189
+ {"current_steps": 1189, "total_steps": 1235, "loss": 0.3761, "lr": 1.6895648574129397e-07, "epoch": 4.813765182186235, "percentage": 96.28, "elapsed_time": "7:55:06", "remaining_time": "0:18:22"}
1190
+ {"current_steps": 1190, "total_steps": 1235, "loss": 0.3826, "lr": 1.6170020597962465e-07, "epoch": 4.817813765182186, "percentage": 96.36, "elapsed_time": "7:55:30", "remaining_time": "0:17:58"}
1191
+ {"current_steps": 1191, "total_steps": 1235, "loss": 0.3616, "lr": 1.5460255273447078e-07, "epoch": 4.821862348178137, "percentage": 96.44, "elapsed_time": "7:55:53", "remaining_time": "0:17:34"}
1192
+ {"current_steps": 1192, "total_steps": 1235, "loss": 0.3667, "lr": 1.4766358275847715e-07, "epoch": 4.825910931174089, "percentage": 96.52, "elapsed_time": "7:56:17", "remaining_time": "0:17:10"}
1193
+ {"current_steps": 1193, "total_steps": 1235, "loss": 0.3796, "lr": 1.4088335153546573e-07, "epoch": 4.82995951417004, "percentage": 96.6, "elapsed_time": "7:56:40", "remaining_time": "0:16:46"}
1194
+ {"current_steps": 1194, "total_steps": 1235, "loss": 0.3665, "lr": 1.3426191327998496e-07, "epoch": 4.834008097165992, "percentage": 96.68, "elapsed_time": "7:57:03", "remaining_time": "0:16:22"}
1195
+ {"current_steps": 1195, "total_steps": 1235, "loss": 0.3715, "lr": 1.277993209368744e-07, "epoch": 4.838056680161944, "percentage": 96.76, "elapsed_time": "7:57:27", "remaining_time": "0:15:58"}
1196
+ {"current_steps": 1196, "total_steps": 1235, "loss": 0.3705, "lr": 1.214956261808542e-07, "epoch": 4.842105263157895, "percentage": 96.84, "elapsed_time": "7:57:51", "remaining_time": "0:15:34"}
1197
+ {"current_steps": 1197, "total_steps": 1235, "loss": 0.378, "lr": 1.1535087941609846e-07, "epoch": 4.846153846153846, "percentage": 96.92, "elapsed_time": "7:58:15", "remaining_time": "0:15:10"}
1198
+ {"current_steps": 1198, "total_steps": 1235, "loss": 0.3709, "lr": 1.0936512977583802e-07, "epoch": 4.850202429149798, "percentage": 97.0, "elapsed_time": "7:58:39", "remaining_time": "0:14:47"}
1199
+ {"current_steps": 1199, "total_steps": 1235, "loss": 0.3774, "lr": 1.0353842512196732e-07, "epoch": 4.854251012145749, "percentage": 97.09, "elapsed_time": "7:59:03", "remaining_time": "0:14:23"}
1200
+ {"current_steps": 1200, "total_steps": 1235, "loss": 0.3761, "lr": 9.787081204466253e-08, "epoch": 4.8582995951417, "percentage": 97.17, "elapsed_time": "7:59:27", "remaining_time": "0:13:59"}
1201
+ {"current_steps": 1201, "total_steps": 1235, "loss": 0.3731, "lr": 9.236233586200627e-08, "epoch": 4.862348178137652, "percentage": 97.25, "elapsed_time": "7:59:50", "remaining_time": "0:13:35"}
1202
+ {"current_steps": 1202, "total_steps": 1235, "loss": 0.3795, "lr": 8.70130406196279e-08, "epoch": 4.866396761133603, "percentage": 97.33, "elapsed_time": "8:00:14", "remaining_time": "0:13:11"}
1203
+ {"current_steps": 1203, "total_steps": 1235, "loss": 0.374, "lr": 8.182296909035047e-08, "epoch": 4.870445344129554, "percentage": 97.41, "elapsed_time": "8:00:37", "remaining_time": "0:12:47"}
1204
+ {"current_steps": 1204, "total_steps": 1235, "loss": 0.3845, "lr": 7.679216277384439e-08, "epoch": 4.874493927125506, "percentage": 97.49, "elapsed_time": "8:01:02", "remaining_time": "0:12:23"}
1205
+ {"current_steps": 1205, "total_steps": 1235, "loss": 0.3694, "lr": 7.19206618963053e-08, "epoch": 4.8785425101214575, "percentage": 97.57, "elapsed_time": "8:01:25", "remaining_time": "0:11:59"}
1206
+ {"current_steps": 1206, "total_steps": 1235, "loss": 0.3812, "lr": 6.720850541012347e-08, "epoch": 4.882591093117409, "percentage": 97.65, "elapsed_time": "8:01:49", "remaining_time": "0:11:35"}
1207
+ {"current_steps": 1207, "total_steps": 1235, "loss": 0.3809, "lr": 6.265573099357714e-08, "epoch": 4.886639676113361, "percentage": 97.73, "elapsed_time": "8:02:13", "remaining_time": "0:11:11"}
1208
+ {"current_steps": 1208, "total_steps": 1235, "loss": 0.3762, "lr": 5.826237505053067e-08, "epoch": 4.890688259109312, "percentage": 97.81, "elapsed_time": "8:02:36", "remaining_time": "0:10:47"}
1209
+ {"current_steps": 1209, "total_steps": 1235, "loss": 0.3754, "lr": 5.4028472710137e-08, "epoch": 4.894736842105263, "percentage": 97.89, "elapsed_time": "8:03:00", "remaining_time": "0:10:23"}
1210
+ {"current_steps": 1210, "total_steps": 1235, "loss": 0.3772, "lr": 4.9954057826571146e-08, "epoch": 4.898785425101215, "percentage": 97.98, "elapsed_time": "8:03:24", "remaining_time": "0:09:59"}
1211
+ {"current_steps": 1211, "total_steps": 1235, "loss": 0.3767, "lr": 4.6039162978743776e-08, "epoch": 4.902834008097166, "percentage": 98.06, "elapsed_time": "8:03:47", "remaining_time": "0:09:35"}
1212
+ {"current_steps": 1212, "total_steps": 1235, "loss": 0.3839, "lr": 4.228381947004812e-08, "epoch": 4.906882591093117, "percentage": 98.14, "elapsed_time": "8:04:10", "remaining_time": "0:09:11"}
1213
+ {"current_steps": 1213, "total_steps": 1235, "loss": 0.3812, "lr": 3.868805732811343e-08, "epoch": 4.910931174089069, "percentage": 98.22, "elapsed_time": "8:04:34", "remaining_time": "0:08:47"}
1214
+ {"current_steps": 1214, "total_steps": 1235, "loss": 0.3683, "lr": 3.525190530455636e-08, "epoch": 4.91497975708502, "percentage": 98.3, "elapsed_time": "8:04:57", "remaining_time": "0:08:23"}
1215
+ {"current_steps": 1215, "total_steps": 1235, "loss": 0.3876, "lr": 3.197539087475887e-08, "epoch": 4.919028340080971, "percentage": 98.38, "elapsed_time": "8:05:21", "remaining_time": "0:07:59"}
1216
+ {"current_steps": 1216, "total_steps": 1235, "loss": 0.3728, "lr": 2.8858540237641786e-08, "epoch": 4.923076923076923, "percentage": 98.46, "elapsed_time": "8:05:45", "remaining_time": "0:07:35"}
1217
+ {"current_steps": 1217, "total_steps": 1235, "loss": 0.3714, "lr": 2.5901378315458247e-08, "epoch": 4.9271255060728745, "percentage": 98.54, "elapsed_time": "8:06:08", "remaining_time": "0:07:11"}
1218
+ {"current_steps": 1218, "total_steps": 1235, "loss": 0.3866, "lr": 2.3103928753598347e-08, "epoch": 4.931174089068826, "percentage": 98.62, "elapsed_time": "8:06:32", "remaining_time": "0:06:47"}
1219
+ {"current_steps": 989, "total_steps": 1235, "loss": 0.36, "lr": 4.6468463082100176e-06, "epoch": 4.004048582995951, "percentage": 80.08, "elapsed_time": "0:00:31", "remaining_time": "0:00:07"}
1220
+ {"current_steps": 990, "total_steps": 1235, "loss": 0.3798, "lr": 4.610664328486485e-06, "epoch": 4.008097165991903, "percentage": 80.16, "elapsed_time": "0:00:55", "remaining_time": "0:00:13"}
1221
+ {"current_steps": 991, "total_steps": 1235, "loss": 0.397, "lr": 4.5746054014809e-06, "epoch": 4.012145748987854, "percentage": 80.24, "elapsed_time": "0:01:18", "remaining_time": "0:00:19"}
1222
+ {"current_steps": 992, "total_steps": 1235, "loss": 0.3822, "lr": 4.5386698155194766e-06, "epoch": 4.016194331983805, "percentage": 80.32, "elapsed_time": "0:01:42", "remaining_time": "0:00:25"}
1223
+ {"current_steps": 993, "total_steps": 1235, "loss": 0.3763, "lr": 4.502857857942204e-06, "epoch": 4.020242914979757, "percentage": 80.4, "elapsed_time": "0:02:06", "remaining_time": "0:00:30"}
1224
+ {"current_steps": 994, "total_steps": 1235, "loss": 0.3677, "lr": 4.467169815100549e-06, "epoch": 4.0242914979757085, "percentage": 80.49, "elapsed_time": "0:02:30", "remaining_time": "0:00:36"}
1225
+ {"current_steps": 995, "total_steps": 1235, "loss": 0.3703, "lr": 4.431605972355137e-06, "epoch": 4.02834008097166, "percentage": 80.57, "elapsed_time": "0:02:55", "remaining_time": "0:00:42"}
1226
+ {"current_steps": 996, "total_steps": 1235, "loss": 0.3751, "lr": 4.396166614073516e-06, "epoch": 4.032388663967612, "percentage": 80.65, "elapsed_time": "0:03:18", "remaining_time": "0:00:47"}
1227
+ {"current_steps": 997, "total_steps": 1235, "loss": 0.3695, "lr": 4.360852023627846e-06, "epoch": 4.036437246963563, "percentage": 80.73, "elapsed_time": "0:03:42", "remaining_time": "0:00:53"}
1228
+ {"current_steps": 998, "total_steps": 1235, "loss": 0.3825, "lr": 4.325662483392656e-06, "epoch": 4.040485829959514, "percentage": 80.81, "elapsed_time": "0:04:05", "remaining_time": "0:00:58"}
1229
+ {"current_steps": 999, "total_steps": 1235, "loss": 0.3791, "lr": 4.29059827474257e-06, "epoch": 4.044534412955466, "percentage": 80.89, "elapsed_time": "0:04:29", "remaining_time": "0:01:03"}
1230
+ {"current_steps": 1000, "total_steps": 1235, "loss": 0.3786, "lr": 4.255659678050063e-06, "epoch": 4.048582995951417, "percentage": 80.97, "elapsed_time": "0:04:54", "remaining_time": "0:01:09"}
1231
+ {"current_steps": 1001, "total_steps": 1235, "loss": 0.3699, "lr": 4.22084697268323e-06, "epoch": 4.052631578947368, "percentage": 81.05, "elapsed_time": "0:05:17", "remaining_time": "0:01:14"}
1232
+ {"current_steps": 1002, "total_steps": 1235, "loss": 0.3676, "lr": 4.186160437003535e-06, "epoch": 4.05668016194332, "percentage": 81.13, "elapsed_time": "0:05:42", "remaining_time": "0:01:19"}
1233
+ {"current_steps": 1003, "total_steps": 1235, "loss": 0.381, "lr": 4.151600348363582e-06, "epoch": 4.060728744939271, "percentage": 81.21, "elapsed_time": "0:06:06", "remaining_time": "0:01:24"}
1234
+ {"current_steps": 1004, "total_steps": 1235, "loss": 0.3814, "lr": 4.11716698310493e-06, "epoch": 4.064777327935222, "percentage": 81.3, "elapsed_time": "0:06:30", "remaining_time": "0:01:29"}
1235
+ {"current_steps": 1005, "total_steps": 1235, "loss": 0.3726, "lr": 4.082860616555848e-06, "epoch": 4.068825910931174, "percentage": 81.38, "elapsed_time": "0:06:54", "remaining_time": "0:01:34"}
1236
+ {"current_steps": 1006, "total_steps": 1235, "loss": 0.3971, "lr": 4.048681523029125e-06, "epoch": 4.0728744939271255, "percentage": 81.46, "elapsed_time": "0:07:18", "remaining_time": "0:01:39"}
1237
+ {"current_steps": 1007, "total_steps": 1235, "loss": 0.3825, "lr": 4.014629975819882e-06, "epoch": 4.076923076923077, "percentage": 81.54, "elapsed_time": "0:07:43", "remaining_time": "0:01:44"}
1238
+ {"current_steps": 1008, "total_steps": 1235, "loss": 0.3806, "lr": 3.9807062472033855e-06, "epoch": 4.080971659919029, "percentage": 81.62, "elapsed_time": "0:08:07", "remaining_time": "0:01:49"}
1239
+ {"current_steps": 1009, "total_steps": 1235, "loss": 0.3824, "lr": 3.94691060843287e-06, "epoch": 4.08502024291498, "percentage": 81.7, "elapsed_time": "0:08:31", "remaining_time": "0:01:54"}
1240
+ {"current_steps": 1010, "total_steps": 1235, "loss": 0.3819, "lr": 3.913243329737353e-06, "epoch": 4.089068825910931, "percentage": 81.78, "elapsed_time": "0:08:54", "remaining_time": "0:01:59"}
1241
+ {"current_steps": 1011, "total_steps": 1235, "loss": 0.3754, "lr": 3.879704680319503e-06, "epoch": 4.093117408906883, "percentage": 81.86, "elapsed_time": "0:09:18", "remaining_time": "0:02:03"}
1242
+ {"current_steps": 1012, "total_steps": 1235, "loss": 0.3714, "lr": 3.846294928353471e-06, "epoch": 4.097165991902834, "percentage": 81.94, "elapsed_time": "0:09:41", "remaining_time": "0:02:08"}
1243
+ {"current_steps": 1013, "total_steps": 1235, "loss": 0.3676, "lr": 3.8130143409827345e-06, "epoch": 4.101214574898785, "percentage": 82.02, "elapsed_time": "0:10:05", "remaining_time": "0:02:12"}
1244
+ {"current_steps": 1014, "total_steps": 1235, "loss": 0.3883, "lr": 3.7798631843179887e-06, "epoch": 4.105263157894737, "percentage": 82.11, "elapsed_time": "0:10:30", "remaining_time": "0:02:17"}
1245
+ {"current_steps": 1015, "total_steps": 1235, "loss": 0.3737, "lr": 3.7468417234349973e-06, "epoch": 4.109311740890688, "percentage": 82.19, "elapsed_time": "0:10:54", "remaining_time": "0:02:21"}
1246
+ {"current_steps": 1016, "total_steps": 1235, "loss": 0.3792, "lr": 3.7139502223724823e-06, "epoch": 4.113360323886639, "percentage": 82.27, "elapsed_time": "0:11:18", "remaining_time": "0:02:26"}
1247
+ {"current_steps": 1017, "total_steps": 1235, "loss": 0.3696, "lr": 3.6811889441300095e-06, "epoch": 4.117408906882591, "percentage": 82.35, "elapsed_time": "0:11:42", "remaining_time": "0:02:30"}
1248
+ {"current_steps": 1018, "total_steps": 1235, "loss": 0.3837, "lr": 3.648558150665886e-06, "epoch": 4.1214574898785425, "percentage": 82.43, "elapsed_time": "0:12:05", "remaining_time": "0:02:34"}
1249
+ {"current_steps": 1019, "total_steps": 1235, "loss": 0.3741, "lr": 3.616058102895075e-06, "epoch": 4.125506072874494, "percentage": 82.51, "elapsed_time": "0:12:29", "remaining_time": "0:02:38"}
1250
+ {"current_steps": 1020, "total_steps": 1235, "loss": 0.3836, "lr": 3.583689060687079e-06, "epoch": 4.129554655870446, "percentage": 82.59, "elapsed_time": "0:12:52", "remaining_time": "0:02:42"}
1251
+ {"current_steps": 1021, "total_steps": 1235, "loss": 0.3888, "lr": 3.5514512828639023e-06, "epoch": 4.133603238866397, "percentage": 82.67, "elapsed_time": "0:13:16", "remaining_time": "0:02:46"}
1252
+ {"current_steps": 1022, "total_steps": 1235, "loss": 0.3815, "lr": 3.51934502719796e-06, "epoch": 4.137651821862348, "percentage": 82.75, "elapsed_time": "0:13:39", "remaining_time": "0:02:50"}
1253
+ {"current_steps": 1023, "total_steps": 1235, "loss": 0.3812, "lr": 3.4873705504100185e-06, "epoch": 4.1417004048583, "percentage": 82.83, "elapsed_time": "0:14:03", "remaining_time": "0:02:54"}
1254
+ {"current_steps": 1024, "total_steps": 1235, "loss": 0.3849, "lr": 3.4555281081671345e-06, "epoch": 4.145748987854251, "percentage": 82.91, "elapsed_time": "0:14:27", "remaining_time": "0:02:58"}
1255
+ {"current_steps": 1025, "total_steps": 1235, "loss": 0.3651, "lr": 3.4238179550806326e-06, "epoch": 4.149797570850202, "percentage": 83.0, "elapsed_time": "0:14:50", "remaining_time": "0:03:02"}
1256
+ {"current_steps": 1026, "total_steps": 1235, "loss": 0.3736, "lr": 3.3922403447040497e-06, "epoch": 4.153846153846154, "percentage": 83.08, "elapsed_time": "0:15:14", "remaining_time": "0:03:06"}
1257
+ {"current_steps": 1027, "total_steps": 1235, "loss": 0.3841, "lr": 3.3607955295311247e-06, "epoch": 4.157894736842105, "percentage": 83.16, "elapsed_time": "0:15:38", "remaining_time": "0:03:10"}
1258
+ {"current_steps": 1028, "total_steps": 1235, "loss": 0.3679, "lr": 3.32948376099375e-06, "epoch": 4.161943319838056, "percentage": 83.24, "elapsed_time": "0:16:01", "remaining_time": "0:03:13"}
1259
+ {"current_steps": 1029, "total_steps": 1235, "loss": 0.3846, "lr": 3.2983052894599976e-06, "epoch": 4.165991902834008, "percentage": 83.32, "elapsed_time": "0:16:25", "remaining_time": "0:03:17"}
1260
+ {"current_steps": 1030, "total_steps": 1235, "loss": 0.3768, "lr": 3.2672603642320945e-06, "epoch": 4.17004048582996, "percentage": 83.4, "elapsed_time": "0:16:49", "remaining_time": "0:03:20"}
1261
+ {"current_steps": 1031, "total_steps": 1235, "loss": 0.3609, "lr": 3.236349233544438e-06, "epoch": 4.174089068825911, "percentage": 83.48, "elapsed_time": "0:17:12", "remaining_time": "0:03:24"}
1262
+ {"current_steps": 1032, "total_steps": 1235, "loss": 0.381, "lr": 3.205572144561604e-06, "epoch": 4.178137651821863, "percentage": 83.56, "elapsed_time": "0:17:36", "remaining_time": "0:03:27"}
1263
+ {"current_steps": 1033, "total_steps": 1235, "loss": 0.3877, "lr": 3.174929343376374e-06, "epoch": 4.182186234817814, "percentage": 83.64, "elapsed_time": "0:18:00", "remaining_time": "0:03:31"}
1264
+ {"current_steps": 1034, "total_steps": 1235, "loss": 0.3909, "lr": 3.1444210750077777e-06, "epoch": 4.186234817813765, "percentage": 83.72, "elapsed_time": "0:18:24", "remaining_time": "0:03:34"}
1265
+ {"current_steps": 1035, "total_steps": 1235, "loss": 0.3806, "lr": 3.1140475833991046e-06, "epoch": 4.190283400809717, "percentage": 83.81, "elapsed_time": "0:18:47", "remaining_time": "0:03:37"}
1266
+ {"current_steps": 1036, "total_steps": 1235, "loss": 0.3578, "lr": 3.0838091114159895e-06, "epoch": 4.194331983805668, "percentage": 83.89, "elapsed_time": "0:19:10", "remaining_time": "0:03:41"}
1267
+ {"current_steps": 1037, "total_steps": 1235, "loss": 0.3649, "lr": 3.0537059008444524e-06, "epoch": 4.198380566801619, "percentage": 83.97, "elapsed_time": "0:19:34", "remaining_time": "0:03:44"}
1268
+ {"current_steps": 1038, "total_steps": 1235, "loss": 0.3752, "lr": 3.0237381923889563e-06, "epoch": 4.202429149797571, "percentage": 84.05, "elapsed_time": "0:19:58", "remaining_time": "0:03:47"}
1269
+ {"current_steps": 1039, "total_steps": 1235, "loss": 0.3648, "lr": 2.9939062256704997e-06, "epoch": 4.206477732793522, "percentage": 84.13, "elapsed_time": "0:20:22", "remaining_time": "0:03:50"}
1270
+ {"current_steps": 1040, "total_steps": 1235, "loss": 0.3723, "lr": 2.964210239224696e-06, "epoch": 4.2105263157894735, "percentage": 84.21, "elapsed_time": "0:20:46", "remaining_time": "0:03:53"}
1271
+ {"current_steps": 1041, "total_steps": 1235, "loss": 0.3783, "lr": 2.934650470499869e-06, "epoch": 4.2145748987854255, "percentage": 84.29, "elapsed_time": "0:21:09", "remaining_time": "0:03:56"}
1272
+ {"current_steps": 1042, "total_steps": 1235, "loss": 0.3774, "lr": 2.905227155855128e-06, "epoch": 4.218623481781377, "percentage": 84.37, "elapsed_time": "0:21:33", "remaining_time": "0:03:59"}
1273
+ {"current_steps": 1043, "total_steps": 1235, "loss": 0.3843, "lr": 2.875940530558519e-06, "epoch": 4.222672064777328, "percentage": 84.45, "elapsed_time": "0:21:56", "remaining_time": "0:04:02"}
1274
+ {"current_steps": 1044, "total_steps": 1235, "loss": 0.3776, "lr": 2.8467908287851154e-06, "epoch": 4.22672064777328, "percentage": 84.53, "elapsed_time": "0:22:20", "remaining_time": "0:04:05"}
1275
+ {"current_steps": 1045, "total_steps": 1235, "loss": 0.3719, "lr": 2.8177782836151603e-06, "epoch": 4.230769230769231, "percentage": 84.62, "elapsed_time": "0:22:44", "remaining_time": "0:04:08"}
1276
+ {"current_steps": 1046, "total_steps": 1235, "loss": 0.3829, "lr": 2.7889031270321874e-06, "epoch": 4.234817813765182, "percentage": 84.7, "elapsed_time": "0:23:07", "remaining_time": "0:04:10"}
1277
+ {"current_steps": 1047, "total_steps": 1235, "loss": 0.3749, "lr": 2.760165589921184e-06, "epoch": 4.238866396761134, "percentage": 84.78, "elapsed_time": "0:23:32", "remaining_time": "0:04:13"}
1278
+ {"current_steps": 1048, "total_steps": 1235, "loss": 0.3597, "lr": 2.7315659020667305e-06, "epoch": 4.242914979757085, "percentage": 84.86, "elapsed_time": "0:23:55", "remaining_time": "0:04:16"}
1279
+ {"current_steps": 1049, "total_steps": 1235, "loss": 0.3624, "lr": 2.703104292151164e-06, "epoch": 4.246963562753036, "percentage": 84.94, "elapsed_time": "0:24:20", "remaining_time": "0:04:18"}
1280
+ {"current_steps": 1050, "total_steps": 1235, "loss": 0.3643, "lr": 2.6747809877527607e-06, "epoch": 4.251012145748988, "percentage": 85.02, "elapsed_time": "0:24:43", "remaining_time": "0:04:21"}
1281
+ {"current_steps": 1051, "total_steps": 1235, "loss": 0.387, "lr": 2.6465962153439082e-06, "epoch": 4.255060728744939, "percentage": 85.1, "elapsed_time": "0:25:07", "remaining_time": "0:04:23"}
1282
+ {"current_steps": 1052, "total_steps": 1235, "loss": 0.3762, "lr": 2.618550200289303e-06, "epoch": 4.2591093117408905, "percentage": 85.18, "elapsed_time": "0:25:30", "remaining_time": "0:04:26"}
1283
+ {"current_steps": 1053, "total_steps": 1235, "loss": 0.3698, "lr": 2.59064316684412e-06, "epoch": 4.2631578947368425, "percentage": 85.26, "elapsed_time": "0:25:54", "remaining_time": "0:04:28"}
1284
+ {"current_steps": 1054, "total_steps": 1235, "loss": 0.3719, "lr": 2.562875338152264e-06, "epoch": 4.267206477732794, "percentage": 85.34, "elapsed_time": "0:26:17", "remaining_time": "0:04:30"}
1285
+ {"current_steps": 1055, "total_steps": 1235, "loss": 0.3768, "lr": 2.5352469362445552e-06, "epoch": 4.271255060728745, "percentage": 85.43, "elapsed_time": "0:26:40", "remaining_time": "0:04:33"}
1286
+ {"current_steps": 1056, "total_steps": 1235, "loss": 0.3604, "lr": 2.5077581820369523e-06, "epoch": 4.275303643724697, "percentage": 85.51, "elapsed_time": "0:27:04", "remaining_time": "0:04:35"}
1287
+ {"current_steps": 1057, "total_steps": 1235, "loss": 0.3693, "lr": 2.480409295328803e-06, "epoch": 4.279352226720648, "percentage": 85.59, "elapsed_time": "0:27:28", "remaining_time": "0:04:37"}
1288
+ {"current_steps": 1058, "total_steps": 1235, "loss": 0.389, "lr": 2.45320049480108e-06, "epoch": 4.283400809716599, "percentage": 85.67, "elapsed_time": "0:27:51", "remaining_time": "0:04:39"}
1289
+ {"current_steps": 1059, "total_steps": 1235, "loss": 0.3707, "lr": 2.4261319980146293e-06, "epoch": 4.287449392712551, "percentage": 85.75, "elapsed_time": "0:28:15", "remaining_time": "0:04:41"}
1290
+ {"current_steps": 1060, "total_steps": 1235, "loss": 0.3807, "lr": 2.399204021408421e-06, "epoch": 4.291497975708502, "percentage": 85.83, "elapsed_time": "0:28:38", "remaining_time": "0:04:43"}
1291
+ {"current_steps": 1061, "total_steps": 1235, "loss": 0.3708, "lr": 2.3724167802978395e-06, "epoch": 4.295546558704453, "percentage": 85.91, "elapsed_time": "0:29:02", "remaining_time": "0:04:45"}
1292
+ {"current_steps": 1062, "total_steps": 1235, "loss": 0.391, "lr": 2.3457704888729625e-06, "epoch": 4.299595141700405, "percentage": 85.99, "elapsed_time": "0:29:25", "remaining_time": "0:04:47"}
1293
+ {"current_steps": 1063, "total_steps": 1235, "loss": 0.3587, "lr": 2.3192653601968162e-06, "epoch": 4.303643724696356, "percentage": 86.07, "elapsed_time": "0:29:48", "remaining_time": "0:04:49"}
1294
+ {"current_steps": 1064, "total_steps": 1235, "loss": 0.3636, "lr": 2.2929016062037057e-06, "epoch": 4.3076923076923075, "percentage": 86.15, "elapsed_time": "0:30:12", "remaining_time": "0:04:51"}
1295
+ {"current_steps": 1065, "total_steps": 1235, "loss": 0.3634, "lr": 2.2666794376975055e-06, "epoch": 4.3117408906882595, "percentage": 86.23, "elapsed_time": "0:30:36", "remaining_time": "0:04:53"}
1296
+ {"current_steps": 1066, "total_steps": 1235, "loss": 0.3716, "lr": 2.24059906434998e-06, "epoch": 4.315789473684211, "percentage": 86.32, "elapsed_time": "0:30:59", "remaining_time": "0:04:54"}
1297
+ {"current_steps": 1067, "total_steps": 1235, "loss": 0.3717, "lr": 2.214660694699091e-06, "epoch": 4.319838056680162, "percentage": 86.4, "elapsed_time": "0:31:22", "remaining_time": "0:04:56"}
1298
+ {"current_steps": 1068, "total_steps": 1235, "loss": 0.3827, "lr": 2.188864536147355e-06, "epoch": 4.323886639676114, "percentage": 86.48, "elapsed_time": "0:31:45", "remaining_time": "0:04:57"}
1299
+ {"current_steps": 1069, "total_steps": 1235, "loss": 0.3793, "lr": 2.1632107949601757e-06, "epoch": 4.327935222672065, "percentage": 86.56, "elapsed_time": "0:32:09", "remaining_time": "0:04:59"}
1300
+ {"current_steps": 1070, "total_steps": 1235, "loss": 0.3821, "lr": 2.137699676264171e-06, "epoch": 4.331983805668016, "percentage": 86.64, "elapsed_time": "0:32:32", "remaining_time": "0:05:01"}
1301
+ {"current_steps": 1071, "total_steps": 1235, "loss": 0.3554, "lr": 2.1123313840455738e-06, "epoch": 4.336032388663968, "percentage": 86.72, "elapsed_time": "0:32:56", "remaining_time": "0:05:02"}
1302
+ {"current_steps": 1072, "total_steps": 1235, "loss": 0.3856, "lr": 2.08710612114857e-06, "epoch": 4.340080971659919, "percentage": 86.8, "elapsed_time": "0:33:19", "remaining_time": "0:05:04"}
1303
+ {"current_steps": 1073, "total_steps": 1235, "loss": 0.3845, "lr": 2.0620240892736953e-06, "epoch": 4.34412955465587, "percentage": 86.88, "elapsed_time": "0:33:42", "remaining_time": "0:05:05"}
1304
+ {"current_steps": 1074, "total_steps": 1235, "loss": 0.3759, "lr": 2.0370854889762e-06, "epoch": 4.348178137651822, "percentage": 86.96, "elapsed_time": "0:34:06", "remaining_time": "0:05:06"}
1305
+ {"current_steps": 1075, "total_steps": 1235, "loss": 0.3705, "lr": 2.0122905196644726e-06, "epoch": 4.352226720647773, "percentage": 87.04, "elapsed_time": "0:34:29", "remaining_time": "0:05:08"}
1306
+ {"current_steps": 1076, "total_steps": 1235, "loss": 0.3686, "lr": 1.987639379598427e-06, "epoch": 4.3562753036437245, "percentage": 87.13, "elapsed_time": "0:34:52", "remaining_time": "0:05:09"}
1307
+ {"current_steps": 1077, "total_steps": 1235, "loss": 0.3731, "lr": 1.963132265887919e-06, "epoch": 4.3603238866396765, "percentage": 87.21, "elapsed_time": "0:35:16", "remaining_time": "0:05:10"}
1308
+ {"current_steps": 1078, "total_steps": 1235, "loss": 0.3885, "lr": 1.9387693744911784e-06, "epoch": 4.364372469635628, "percentage": 87.29, "elapsed_time": "0:35:39", "remaining_time": "0:05:11"}
1309
+ {"current_steps": 1079, "total_steps": 1235, "loss": 0.368, "lr": 1.9145509002132368e-06, "epoch": 4.368421052631579, "percentage": 87.37, "elapsed_time": "0:36:03", "remaining_time": "0:05:12"}
1310
+ {"current_steps": 1080, "total_steps": 1235, "loss": 0.3585, "lr": 1.8904770367043723e-06, "epoch": 4.372469635627531, "percentage": 87.45, "elapsed_time": "0:36:26", "remaining_time": "0:05:13"}
1311
+ {"current_steps": 1081, "total_steps": 1235, "loss": 0.3617, "lr": 1.8665479764585504e-06, "epoch": 4.376518218623482, "percentage": 87.53, "elapsed_time": "0:36:49", "remaining_time": "0:05:14"}
1312
+ {"current_steps": 1082, "total_steps": 1235, "loss": 0.3727, "lr": 1.8427639108118977e-06, "epoch": 4.380566801619433, "percentage": 87.61, "elapsed_time": "0:37:13", "remaining_time": "0:05:15"}
1313
+ {"current_steps": 1083, "total_steps": 1235, "loss": 0.3686, "lr": 1.8191250299411755e-06, "epoch": 4.384615384615385, "percentage": 87.69, "elapsed_time": "0:37:37", "remaining_time": "0:05:16"}
1314
+ {"current_steps": 1084, "total_steps": 1235, "loss": 0.3806, "lr": 1.7956315228622446e-06, "epoch": 4.388663967611336, "percentage": 87.77, "elapsed_time": "0:38:02", "remaining_time": "0:05:17"}
1315
+ {"current_steps": 1085, "total_steps": 1235, "loss": 0.3771, "lr": 1.7722835774285553e-06, "epoch": 4.392712550607287, "percentage": 87.85, "elapsed_time": "0:38:26", "remaining_time": "0:05:18"}
1316
+ {"current_steps": 1086, "total_steps": 1235, "loss": 0.3771, "lr": 1.7490813803296624e-06, "epoch": 4.396761133603239, "percentage": 87.94, "elapsed_time": "0:38:49", "remaining_time": "0:05:19"}
1317
+ {"current_steps": 1087, "total_steps": 1235, "loss": 0.3709, "lr": 1.726025117089718e-06, "epoch": 4.40080971659919, "percentage": 88.02, "elapsed_time": "0:39:12", "remaining_time": "0:05:20"}
1318
+ {"current_steps": 1088, "total_steps": 1235, "loss": 0.3718, "lr": 1.70311497206598e-06, "epoch": 4.4048582995951415, "percentage": 88.1, "elapsed_time": "0:39:36", "remaining_time": "0:05:21"}
1319
+ {"current_steps": 1089, "total_steps": 1235, "loss": 0.3722, "lr": 1.6803511284473638e-06, "epoch": 4.4089068825910935, "percentage": 88.18, "elapsed_time": "0:39:59", "remaining_time": "0:05:21"}
1320
+ {"current_steps": 1090, "total_steps": 1235, "loss": 0.4003, "lr": 1.6577337682529538e-06, "epoch": 4.412955465587045, "percentage": 88.26, "elapsed_time": "0:40:23", "remaining_time": "0:05:22"}
1321
+ {"current_steps": 1091, "total_steps": 1235, "loss": 0.3752, "lr": 1.6352630723305617e-06, "epoch": 4.417004048582996, "percentage": 88.34, "elapsed_time": "0:40:47", "remaining_time": "0:05:23"}
1322
+ {"current_steps": 1092, "total_steps": 1235, "loss": 0.4217, "lr": 1.612939220355272e-06, "epoch": 4.421052631578947, "percentage": 88.42, "elapsed_time": "0:41:11", "remaining_time": "0:05:23"}
1323
+ {"current_steps": 1093, "total_steps": 1235, "loss": 0.386, "lr": 1.5907623908280112e-06, "epoch": 4.425101214574899, "percentage": 88.5, "elapsed_time": "0:41:35", "remaining_time": "0:05:24"}
1324
+ {"current_steps": 1094, "total_steps": 1235, "loss": 0.3779, "lr": 1.568732761074121e-06, "epoch": 4.42914979757085, "percentage": 88.58, "elapsed_time": "0:41:58", "remaining_time": "0:05:24"}
1325
+ {"current_steps": 1095, "total_steps": 1235, "loss": 0.3722, "lr": 1.5468505072419237e-06, "epoch": 4.433198380566802, "percentage": 88.66, "elapsed_time": "0:42:21", "remaining_time": "0:05:24"}
1326
+ {"current_steps": 1096, "total_steps": 1235, "loss": 0.3726, "lr": 1.5251158043013448e-06, "epoch": 4.437246963562753, "percentage": 88.74, "elapsed_time": "0:42:45", "remaining_time": "0:05:25"}
1327
+ {"current_steps": 1097, "total_steps": 1235, "loss": 0.3705, "lr": 1.5035288260424885e-06, "epoch": 4.441295546558704, "percentage": 88.83, "elapsed_time": "0:43:09", "remaining_time": "0:05:25"}
1328
+ {"current_steps": 1098, "total_steps": 1235, "loss": 0.3689, "lr": 1.4820897450742623e-06, "epoch": 4.445344129554655, "percentage": 88.91, "elapsed_time": "0:43:33", "remaining_time": "0:05:26"}
1329
+ {"current_steps": 1099, "total_steps": 1235, "loss": 0.3646, "lr": 1.4607987328229767e-06, "epoch": 4.449392712550607, "percentage": 88.99, "elapsed_time": "0:43:56", "remaining_time": "0:05:26"}
1330
+ {"current_steps": 1100, "total_steps": 1235, "loss": 0.3773, "lr": 1.4396559595310056e-06, "epoch": 4.4534412955465585, "percentage": 89.07, "elapsed_time": "0:44:19", "remaining_time": "0:05:26"}
1331
+ {"current_steps": 1101, "total_steps": 1235, "loss": 0.3751, "lr": 1.4186615942553973e-06, "epoch": 4.4574898785425106, "percentage": 89.15, "elapsed_time": "0:44:43", "remaining_time": "0:05:26"}
1332
+ {"current_steps": 1102, "total_steps": 1235, "loss": 0.3776, "lr": 1.3978158048665424e-06, "epoch": 4.461538461538462, "percentage": 89.23, "elapsed_time": "0:45:07", "remaining_time": "0:05:26"}
1333
+ {"current_steps": 1103, "total_steps": 1235, "loss": 0.3911, "lr": 1.3771187580468115e-06, "epoch": 4.465587044534413, "percentage": 89.31, "elapsed_time": "0:45:31", "remaining_time": "0:05:26"}
1334
+ {"current_steps": 1104, "total_steps": 1235, "loss": 0.3806, "lr": 1.3565706192892392e-06, "epoch": 4.469635627530364, "percentage": 89.39, "elapsed_time": "0:45:55", "remaining_time": "0:05:26"}
1335
+ {"current_steps": 1105, "total_steps": 1235, "loss": 0.3755, "lr": 1.3361715528961993e-06, "epoch": 4.473684210526316, "percentage": 89.47, "elapsed_time": "0:46:19", "remaining_time": "0:05:27"}
1336
+ {"current_steps": 1106, "total_steps": 1235, "loss": 0.3759, "lr": 1.3159217219780817e-06, "epoch": 4.477732793522267, "percentage": 89.55, "elapsed_time": "0:46:43", "remaining_time": "0:05:26"}
1337
+ {"current_steps": 1107, "total_steps": 1235, "loss": 0.363, "lr": 1.2958212884519949e-06, "epoch": 4.481781376518219, "percentage": 89.64, "elapsed_time": "0:47:06", "remaining_time": "0:05:26"}
1338
+ {"current_steps": 1108, "total_steps": 1235, "loss": 0.3759, "lr": 1.2758704130404675e-06, "epoch": 4.48582995951417, "percentage": 89.72, "elapsed_time": "0:47:29", "remaining_time": "0:05:26"}
1339
+ {"current_steps": 1109, "total_steps": 1235, "loss": 0.3785, "lr": 1.2560692552701738e-06, "epoch": 4.489878542510121, "percentage": 89.8, "elapsed_time": "0:47:51", "remaining_time": "0:05:26"}
1340
+ {"current_steps": 1110, "total_steps": 1235, "loss": 0.3929, "lr": 1.2364179734706382e-06, "epoch": 4.493927125506072, "percentage": 89.88, "elapsed_time": "0:48:15", "remaining_time": "0:05:26"}
1341
+ {"current_steps": 1111, "total_steps": 1235, "loss": 0.3679, "lr": 1.2169167247729852e-06, "epoch": 4.497975708502024, "percentage": 89.96, "elapsed_time": "0:48:38", "remaining_time": "0:05:25"}
1342
+ {"current_steps": 1112, "total_steps": 1235, "loss": 0.3771, "lr": 1.1975656651086864e-06, "epoch": 4.502024291497976, "percentage": 90.04, "elapsed_time": "0:49:01", "remaining_time": "0:05:25"}
1343
+ {"current_steps": 1113, "total_steps": 1235, "loss": 0.3912, "lr": 1.1783649492082926e-06, "epoch": 4.506072874493928, "percentage": 90.12, "elapsed_time": "0:49:25", "remaining_time": "0:05:25"}
1344
+ {"current_steps": 1114, "total_steps": 1235, "loss": 0.3658, "lr": 1.1593147306002183e-06, "epoch": 4.510121457489879, "percentage": 90.2, "elapsed_time": "0:49:49", "remaining_time": "0:05:24"}
1345
+ {"current_steps": 1115, "total_steps": 1235, "loss": 0.3713, "lr": 1.140415161609505e-06, "epoch": 4.51417004048583, "percentage": 90.28, "elapsed_time": "0:50:12", "remaining_time": "0:05:24"}
1346
+ {"current_steps": 1116, "total_steps": 1235, "loss": 0.3697, "lr": 1.121666393356604e-06, "epoch": 4.518218623481781, "percentage": 90.36, "elapsed_time": "0:50:35", "remaining_time": "0:05:23"}
1347
+ {"current_steps": 1117, "total_steps": 1235, "loss": 0.3905, "lr": 1.1030685757561632e-06, "epoch": 4.522267206477733, "percentage": 90.45, "elapsed_time": "0:50:59", "remaining_time": "0:05:23"}
1348
+ {"current_steps": 1118, "total_steps": 1235, "loss": 0.3854, "lr": 1.0846218575158373e-06, "epoch": 4.526315789473684, "percentage": 90.53, "elapsed_time": "0:51:22", "remaining_time": "0:05:22"}
1349
+ {"current_steps": 1119, "total_steps": 1235, "loss": 0.3857, "lr": 1.066326386135097e-06, "epoch": 4.530364372469636, "percentage": 90.61, "elapsed_time": "0:51:46", "remaining_time": "0:05:21"}
1350
+ {"current_steps": 1120, "total_steps": 1235, "loss": 0.3774, "lr": 1.0481823079040398e-06, "epoch": 4.534412955465587, "percentage": 90.69, "elapsed_time": "0:52:09", "remaining_time": "0:05:21"}
1351
+ {"current_steps": 1121, "total_steps": 1235, "loss": 0.3709, "lr": 1.0301897679022344e-06, "epoch": 4.538461538461538, "percentage": 90.77, "elapsed_time": "0:52:33", "remaining_time": "0:05:20"}
1352
+ {"current_steps": 1122, "total_steps": 1235, "loss": 0.3778, "lr": 1.0123489099975491e-06, "epoch": 4.5425101214574894, "percentage": 90.85, "elapsed_time": "0:52:56", "remaining_time": "0:05:19"}
1353
+ {"current_steps": 1123, "total_steps": 1235, "loss": 0.3768, "lr": 9.9465987684501e-07, "epoch": 4.5465587044534415, "percentage": 90.93, "elapsed_time": "0:53:20", "remaining_time": "0:05:19"}
1354
+ {"current_steps": 1124, "total_steps": 1235, "loss": 0.3741, "lr": 9.771228098856534e-07, "epoch": 4.550607287449393, "percentage": 91.01, "elapsed_time": "0:53:43", "remaining_time": "0:05:18"}
1355
+ {"current_steps": 1125, "total_steps": 1235, "loss": 0.3822, "lr": 9.597378493454013e-07, "epoch": 4.554655870445345, "percentage": 91.09, "elapsed_time": "0:54:07", "remaining_time": "0:05:17"}
1356
+ {"current_steps": 1126, "total_steps": 1235, "loss": 0.3914, "lr": 9.425051342339353e-07, "epoch": 4.558704453441296, "percentage": 91.17, "elapsed_time": "0:54:30", "remaining_time": "0:05:16"}
1357
+ {"current_steps": 1127, "total_steps": 1235, "loss": 0.3939, "lr": 9.254248023435864e-07, "epoch": 4.562753036437247, "percentage": 91.26, "elapsed_time": "0:54:54", "remaining_time": "0:05:15"}
1358
+ {"current_steps": 1128, "total_steps": 1235, "loss": 0.3675, "lr": 9.084969902482288e-07, "epoch": 4.566801619433198, "percentage": 91.34, "elapsed_time": "0:55:18", "remaining_time": "0:05:14"}
1359
+ {"current_steps": 1129, "total_steps": 1235, "loss": 0.3904, "lr": 8.917218333021993e-07, "epoch": 4.57085020242915, "percentage": 91.42, "elapsed_time": "0:55:41", "remaining_time": "0:05:13"}
1360
+ {"current_steps": 1130, "total_steps": 1235, "loss": 0.3876, "lr": 8.750994656392109e-07, "epoch": 4.574898785425101, "percentage": 91.5, "elapsed_time": "0:56:05", "remaining_time": "0:05:12"}
1361
+ {"current_steps": 1131, "total_steps": 1235, "loss": 0.3827, "lr": 8.58630020171265e-07, "epoch": 4.578947368421053, "percentage": 91.58, "elapsed_time": "0:56:28", "remaining_time": "0:05:11"}
1362
+ {"current_steps": 1132, "total_steps": 1235, "loss": 0.3785, "lr": 8.423136285876099e-07, "epoch": 4.582995951417004, "percentage": 91.66, "elapsed_time": "0:56:52", "remaining_time": "0:05:10"}
1363
+ {"current_steps": 1133, "total_steps": 1235, "loss": 0.3729, "lr": 8.26150421353682e-07, "epoch": 4.587044534412955, "percentage": 91.74, "elapsed_time": "0:57:16", "remaining_time": "0:05:09"}
1364
+ {"current_steps": 1134, "total_steps": 1235, "loss": 0.371, "lr": 8.101405277100549e-07, "epoch": 4.5910931174089065, "percentage": 91.82, "elapsed_time": "0:57:38", "remaining_time": "0:05:08"}
1365
+ {"current_steps": 1135, "total_steps": 1235, "loss": 0.3836, "lr": 7.942840756714077e-07, "epoch": 4.5951417004048585, "percentage": 91.9, "elapsed_time": "0:58:01", "remaining_time": "0:05:06"}
1366
+ {"current_steps": 1136, "total_steps": 1235, "loss": 0.376, "lr": 7.785811920255093e-07, "epoch": 4.59919028340081, "percentage": 91.98, "elapsed_time": "0:58:25", "remaining_time": "0:05:05"}
1367
+ {"current_steps": 1137, "total_steps": 1235, "loss": 0.378, "lr": 7.630320023322024e-07, "epoch": 4.603238866396762, "percentage": 92.06, "elapsed_time": "0:58:48", "remaining_time": "0:05:04"}
1368
+ {"current_steps": 1138, "total_steps": 1235, "loss": 0.3901, "lr": 7.476366309223903e-07, "epoch": 4.607287449392713, "percentage": 92.15, "elapsed_time": "0:59:13", "remaining_time": "0:05:02"}
1369
+ {"current_steps": 1139, "total_steps": 1235, "loss": 0.3852, "lr": 7.323952008970537e-07, "epoch": 4.611336032388664, "percentage": 92.23, "elapsed_time": "0:59:36", "remaining_time": "0:05:01"}
1370
+ {"current_steps": 1140, "total_steps": 1235, "loss": 0.3735, "lr": 7.173078341262618e-07, "epoch": 4.615384615384615, "percentage": 92.31, "elapsed_time": "0:59:59", "remaining_time": "0:04:59"}
1371
+ {"current_steps": 1141, "total_steps": 1235, "loss": 0.3817, "lr": 7.023746512481989e-07, "epoch": 4.619433198380567, "percentage": 92.39, "elapsed_time": "1:00:23", "remaining_time": "0:04:58"}
1372
+ {"current_steps": 1142, "total_steps": 1235, "loss": 0.3755, "lr": 6.875957716681902e-07, "epoch": 4.623481781376518, "percentage": 92.47, "elapsed_time": "1:00:47", "remaining_time": "0:04:56"}
1373
+ {"current_steps": 1143, "total_steps": 1235, "loss": 0.3613, "lr": 6.729713135577687e-07, "epoch": 4.62753036437247, "percentage": 92.55, "elapsed_time": "1:01:10", "remaining_time": "0:04:55"}
1374
+ {"current_steps": 1144, "total_steps": 1235, "loss": 0.3781, "lr": 6.585013938537143e-07, "epoch": 4.631578947368421, "percentage": 92.63, "elapsed_time": "1:01:34", "remaining_time": "0:04:53"}
1375
+ {"current_steps": 1145, "total_steps": 1235, "loss": 0.376, "lr": 6.441861282571115e-07, "epoch": 4.635627530364372, "percentage": 92.71, "elapsed_time": "1:01:57", "remaining_time": "0:04:52"}
1376
+ {"current_steps": 1146, "total_steps": 1235, "loss": 0.3758, "lr": 6.300256312324471e-07, "epoch": 4.6396761133603235, "percentage": 92.79, "elapsed_time": "1:02:21", "remaining_time": "0:04:50"}
1377
+ {"current_steps": 1147, "total_steps": 1235, "loss": 0.3698, "lr": 6.160200160066776e-07, "epoch": 4.6437246963562755, "percentage": 92.87, "elapsed_time": "1:02:44", "remaining_time": "0:04:48"}
1378
+ {"current_steps": 1148, "total_steps": 1235, "loss": 0.3784, "lr": 6.021693945683327e-07, "epoch": 4.647773279352227, "percentage": 92.96, "elapsed_time": "1:03:08", "remaining_time": "0:04:47"}
1379
+ {"current_steps": 1149, "total_steps": 1235, "loss": 0.3722, "lr": 5.884738776666044e-07, "epoch": 4.651821862348179, "percentage": 93.04, "elapsed_time": "1:03:31", "remaining_time": "0:04:45"}
1380
+ {"current_steps": 1150, "total_steps": 1235, "loss": 0.3903, "lr": 5.749335748104878e-07, "epoch": 4.65587044534413, "percentage": 93.12, "elapsed_time": "1:03:56", "remaining_time": "0:04:43"}
1381
+ {"current_steps": 1151, "total_steps": 1235, "loss": 0.387, "lr": 5.615485942678778e-07, "epoch": 4.659919028340081, "percentage": 93.2, "elapsed_time": "1:04:19", "remaining_time": "0:04:41"}
1382
+ {"current_steps": 1152, "total_steps": 1235, "loss": 0.3688, "lr": 5.483190430647289e-07, "epoch": 4.663967611336032, "percentage": 93.28, "elapsed_time": "1:04:42", "remaining_time": "0:04:39"}
1383
+ {"current_steps": 1153, "total_steps": 1235, "loss": 0.3712, "lr": 5.352450269841747e-07, "epoch": 4.668016194331984, "percentage": 93.36, "elapsed_time": "1:05:05", "remaining_time": "0:04:37"}
1384
+ {"current_steps": 1154, "total_steps": 1235, "loss": 0.3858, "lr": 5.22326650565701e-07, "epoch": 4.672064777327935, "percentage": 93.44, "elapsed_time": "1:05:29", "remaining_time": "0:04:35"}
1385
+ {"current_steps": 1155, "total_steps": 1235, "loss": 0.3774, "lr": 5.095640171043048e-07, "epoch": 4.676113360323887, "percentage": 93.52, "elapsed_time": "1:05:51", "remaining_time": "0:04:33"}
1386
+ {"current_steps": 1156, "total_steps": 1235, "loss": 0.3714, "lr": 4.969572286496594e-07, "epoch": 4.680161943319838, "percentage": 93.6, "elapsed_time": "1:06:15", "remaining_time": "0:04:31"}
1387
+ {"current_steps": 1157, "total_steps": 1235, "loss": 0.3754, "lr": 4.845063860053079e-07, "epoch": 4.684210526315789, "percentage": 93.68, "elapsed_time": "1:06:39", "remaining_time": "0:04:29"}
1388
+ {"current_steps": 1158, "total_steps": 1235, "loss": 0.367, "lr": 4.7221158872785997e-07, "epoch": 4.6882591093117405, "percentage": 93.77, "elapsed_time": "1:07:02", "remaining_time": "0:04:27"}
1389
+ {"current_steps": 1159, "total_steps": 1235, "loss": 0.369, "lr": 4.600729351261857e-07, "epoch": 4.6923076923076925, "percentage": 93.85, "elapsed_time": "1:07:26", "remaining_time": "0:04:25"}
1390
+ {"current_steps": 1160, "total_steps": 1235, "loss": 0.3735, "lr": 4.4809052226063355e-07, "epoch": 4.696356275303644, "percentage": 93.93, "elapsed_time": "1:07:50", "remaining_time": "0:04:23"}
1391
+ {"current_steps": 1161, "total_steps": 1235, "loss": 0.3866, "lr": 4.3626444594226046e-07, "epoch": 4.700404858299595, "percentage": 94.01, "elapsed_time": "1:08:13", "remaining_time": "0:04:20"}
1392
+ {"current_steps": 1162, "total_steps": 1235, "loss": 0.3724, "lr": 4.245948007320588e-07, "epoch": 4.704453441295547, "percentage": 94.09, "elapsed_time": "1:08:37", "remaining_time": "0:04:18"}
1393
+ {"current_steps": 1163, "total_steps": 1235, "loss": 0.3532, "lr": 4.130816799401971e-07, "epoch": 4.708502024291498, "percentage": 94.17, "elapsed_time": "1:08:59", "remaining_time": "0:04:16"}
1394
+ {"current_steps": 1164, "total_steps": 1235, "loss": 0.3696, "lr": 4.017251756252827e-07, "epoch": 4.712550607287449, "percentage": 94.25, "elapsed_time": "1:09:22", "remaining_time": "0:04:13"}
1395
+ {"current_steps": 1165, "total_steps": 1235, "loss": 0.3789, "lr": 3.9052537859362473e-07, "epoch": 4.716599190283401, "percentage": 94.33, "elapsed_time": "1:09:46", "remaining_time": "0:04:11"}
1396
+ {"current_steps": 1166, "total_steps": 1235, "loss": 0.3933, "lr": 3.7948237839849687e-07, "epoch": 4.720647773279352, "percentage": 94.41, "elapsed_time": "1:10:10", "remaining_time": "0:04:09"}
1397
+ {"current_steps": 1167, "total_steps": 1235, "loss": 0.3628, "lr": 3.6859626333943797e-07, "epoch": 4.724696356275303, "percentage": 94.49, "elapsed_time": "1:10:33", "remaining_time": "0:04:06"}
1398
+ {"current_steps": 1168, "total_steps": 1235, "loss": 0.3798, "lr": 3.578671204615347e-07, "epoch": 4.728744939271255, "percentage": 94.57, "elapsed_time": "1:10:57", "remaining_time": "0:04:04"}
1399
+ {"current_steps": 1169, "total_steps": 1235, "loss": 0.3693, "lr": 3.472950355547267e-07, "epoch": 4.732793522267206, "percentage": 94.66, "elapsed_time": "1:11:20", "remaining_time": "0:04:01"}
1400
+ {"current_steps": 1170, "total_steps": 1235, "loss": 0.3834, "lr": 3.3688009315312244e-07, "epoch": 4.7368421052631575, "percentage": 94.74, "elapsed_time": "1:11:43", "remaining_time": "0:03:59"}
1401
+ {"current_steps": 1171, "total_steps": 1235, "loss": 0.3616, "lr": 3.266223765343224e-07, "epoch": 4.7408906882591095, "percentage": 94.82, "elapsed_time": "1:12:06", "remaining_time": "0:03:56"}
1402
+ {"current_steps": 1172, "total_steps": 1235, "loss": 0.3875, "lr": 3.16521967718757e-07, "epoch": 4.744939271255061, "percentage": 94.9, "elapsed_time": "1:12:30", "remaining_time": "0:03:53"}
1403
+ {"current_steps": 1173, "total_steps": 1235, "loss": 0.3566, "lr": 3.0657894746902726e-07, "epoch": 4.748987854251012, "percentage": 94.98, "elapsed_time": "1:12:53", "remaining_time": "0:03:51"}
1404
+ {"current_steps": 1174, "total_steps": 1235, "loss": 0.3841, "lr": 2.9679339528925654e-07, "epoch": 4.753036437246964, "percentage": 95.06, "elapsed_time": "1:13:16", "remaining_time": "0:03:48"}
1405
+ {"current_steps": 1175, "total_steps": 1235, "loss": 0.3761, "lr": 2.871653894244597e-07, "epoch": 4.757085020242915, "percentage": 95.14, "elapsed_time": "1:13:39", "remaining_time": "0:03:45"}
1406
+ {"current_steps": 1176, "total_steps": 1235, "loss": 0.3773, "lr": 2.7769500685991266e-07, "epoch": 4.761133603238866, "percentage": 95.22, "elapsed_time": "1:14:03", "remaining_time": "0:03:42"}
1407
+ {"current_steps": 1177, "total_steps": 1235, "loss": 0.3952, "lr": 2.683823233205485e-07, "epoch": 4.765182186234818, "percentage": 95.3, "elapsed_time": "1:14:27", "remaining_time": "0:03:40"}
1408
+ {"current_steps": 1178, "total_steps": 1235, "loss": 0.3852, "lr": 2.592274132703287e-07, "epoch": 4.769230769230769, "percentage": 95.38, "elapsed_time": "1:14:50", "remaining_time": "0:03:37"}
1409
+ {"current_steps": 1179, "total_steps": 1235, "loss": 0.3776, "lr": 2.502303499116754e-07, "epoch": 4.77327935222672, "percentage": 95.47, "elapsed_time": "1:15:13", "remaining_time": "0:03:34"}
1410
+ {"current_steps": 1180, "total_steps": 1235, "loss": 0.3712, "lr": 2.413912051848666e-07, "epoch": 4.777327935222672, "percentage": 95.55, "elapsed_time": "1:15:36", "remaining_time": "0:03:31"}
1411
+ {"current_steps": 1181, "total_steps": 1235, "loss": 0.3727, "lr": 2.3271004976746613e-07, "epoch": 4.781376518218623, "percentage": 95.63, "elapsed_time": "1:16:00", "remaining_time": "0:03:28"}
1412
+ {"current_steps": 1182, "total_steps": 1235, "loss": 0.3898, "lr": 2.2418695307376393e-07, "epoch": 4.7854251012145745, "percentage": 95.71, "elapsed_time": "1:16:25", "remaining_time": "0:03:25"}
1413
+ {"current_steps": 1183, "total_steps": 1235, "loss": 0.3874, "lr": 2.1582198325420968e-07, "epoch": 4.7894736842105265, "percentage": 95.79, "elapsed_time": "1:16:48", "remaining_time": "0:03:22"}
1414
+ {"current_steps": 1184, "total_steps": 1235, "loss": 0.3778, "lr": 2.0761520719488447e-07, "epoch": 4.793522267206478, "percentage": 95.87, "elapsed_time": "1:17:12", "remaining_time": "0:03:19"}
1415
+ {"current_steps": 1185, "total_steps": 1235, "loss": 0.3858, "lr": 1.9956669051694798e-07, "epoch": 4.797570850202429, "percentage": 95.95, "elapsed_time": "1:17:36", "remaining_time": "0:03:16"}
1416
+ {"current_steps": 1186, "total_steps": 1235, "loss": 0.3735, "lr": 1.916764975761254e-07, "epoch": 4.801619433198381, "percentage": 96.03, "elapsed_time": "1:17:59", "remaining_time": "0:03:13"}
1417
+ {"current_steps": 1187, "total_steps": 1235, "loss": 0.3855, "lr": 1.839446914621923e-07, "epoch": 4.805668016194332, "percentage": 96.11, "elapsed_time": "1:18:23", "remaining_time": "0:03:10"}
1418
+ {"current_steps": 1188, "total_steps": 1235, "loss": 0.3824, "lr": 1.7637133399845962e-07, "epoch": 4.809716599190283, "percentage": 96.19, "elapsed_time": "1:18:46", "remaining_time": "0:03:06"}
1419
+ {"current_steps": 1189, "total_steps": 1235, "loss": 0.3761, "lr": 1.6895648574129397e-07, "epoch": 4.813765182186235, "percentage": 96.28, "elapsed_time": "1:19:10", "remaining_time": "0:03:03"}
1420
+ {"current_steps": 1190, "total_steps": 1235, "loss": 0.3826, "lr": 1.6170020597962465e-07, "epoch": 4.817813765182186, "percentage": 96.36, "elapsed_time": "1:19:33", "remaining_time": "0:03:00"}
1421
+ {"current_steps": 1191, "total_steps": 1235, "loss": 0.3616, "lr": 1.5460255273447078e-07, "epoch": 4.821862348178137, "percentage": 96.44, "elapsed_time": "1:19:57", "remaining_time": "0:02:57"}
1422
+ {"current_steps": 1192, "total_steps": 1235, "loss": 0.3667, "lr": 1.4766358275847715e-07, "epoch": 4.825910931174089, "percentage": 96.52, "elapsed_time": "1:20:21", "remaining_time": "0:02:53"}
1423
+ {"current_steps": 1193, "total_steps": 1235, "loss": 0.3796, "lr": 1.4088335153546573e-07, "epoch": 4.82995951417004, "percentage": 96.6, "elapsed_time": "1:20:44", "remaining_time": "0:02:50"}
1424
+ {"current_steps": 1194, "total_steps": 1235, "loss": 0.3665, "lr": 1.3426191327998496e-07, "epoch": 4.834008097165992, "percentage": 96.68, "elapsed_time": "1:21:07", "remaining_time": "0:02:47"}
1425
+ {"current_steps": 1195, "total_steps": 1235, "loss": 0.3715, "lr": 1.277993209368744e-07, "epoch": 4.838056680161944, "percentage": 96.76, "elapsed_time": "1:21:31", "remaining_time": "0:02:43"}
1426
+ {"current_steps": 1196, "total_steps": 1235, "loss": 0.3705, "lr": 1.214956261808542e-07, "epoch": 4.842105263157895, "percentage": 96.84, "elapsed_time": "1:21:55", "remaining_time": "0:02:40"}
1427
+ {"current_steps": 1197, "total_steps": 1235, "loss": 0.378, "lr": 1.1535087941609846e-07, "epoch": 4.846153846153846, "percentage": 96.92, "elapsed_time": "1:22:18", "remaining_time": "0:02:36"}
1428
+ {"current_steps": 1198, "total_steps": 1235, "loss": 0.3709, "lr": 1.0936512977583802e-07, "epoch": 4.850202429149798, "percentage": 97.0, "elapsed_time": "1:22:42", "remaining_time": "0:02:33"}
1429
+ {"current_steps": 1199, "total_steps": 1235, "loss": 0.3773, "lr": 1.0353842512196732e-07, "epoch": 4.854251012145749, "percentage": 97.09, "elapsed_time": "1:23:06", "remaining_time": "0:02:29"}
1430
+ {"current_steps": 1200, "total_steps": 1235, "loss": 0.376, "lr": 9.787081204466253e-08, "epoch": 4.8582995951417, "percentage": 97.17, "elapsed_time": "1:23:30", "remaining_time": "0:02:26"}
1431
+ {"current_steps": 1201, "total_steps": 1235, "loss": 0.373, "lr": 9.236233586200627e-08, "epoch": 4.862348178137652, "percentage": 97.25, "elapsed_time": "1:23:54", "remaining_time": "0:02:22"}
1432
+ {"current_steps": 1202, "total_steps": 1235, "loss": 0.3795, "lr": 8.70130406196279e-08, "epoch": 4.866396761133603, "percentage": 97.33, "elapsed_time": "1:24:18", "remaining_time": "0:02:18"}
1433
+ {"current_steps": 1203, "total_steps": 1235, "loss": 0.374, "lr": 8.182296909035047e-08, "epoch": 4.870445344129554, "percentage": 97.41, "elapsed_time": "1:24:41", "remaining_time": "0:02:15"}
1434
+ {"current_steps": 1204, "total_steps": 1235, "loss": 0.3845, "lr": 7.679216277384439e-08, "epoch": 4.874493927125506, "percentage": 97.49, "elapsed_time": "1:25:05", "remaining_time": "0:02:11"}
1435
+ {"current_steps": 1205, "total_steps": 1235, "loss": 0.3694, "lr": 7.19206618963053e-08, "epoch": 4.8785425101214575, "percentage": 97.57, "elapsed_time": "1:25:28", "remaining_time": "0:02:07"}
1436
+ {"current_steps": 1206, "total_steps": 1235, "loss": 0.3812, "lr": 6.720850541012347e-08, "epoch": 4.882591093117409, "percentage": 97.65, "elapsed_time": "1:25:52", "remaining_time": "0:02:03"}
1437
+ {"current_steps": 1207, "total_steps": 1235, "loss": 0.3808, "lr": 6.265573099357714e-08, "epoch": 4.886639676113361, "percentage": 97.73, "elapsed_time": "1:26:16", "remaining_time": "0:02:00"}
1438
+ {"current_steps": 1208, "total_steps": 1235, "loss": 0.3761, "lr": 5.826237505053067e-08, "epoch": 4.890688259109312, "percentage": 97.81, "elapsed_time": "1:26:40", "remaining_time": "0:01:56"}
1439
+ {"current_steps": 1209, "total_steps": 1235, "loss": 0.3754, "lr": 5.4028472710137e-08, "epoch": 4.894736842105263, "percentage": 97.89, "elapsed_time": "1:27:03", "remaining_time": "0:01:52"}
1440
+ {"current_steps": 1210, "total_steps": 1235, "loss": 0.3772, "lr": 4.9954057826571146e-08, "epoch": 4.898785425101215, "percentage": 97.98, "elapsed_time": "1:27:27", "remaining_time": "0:01:48"}
1441
+ {"current_steps": 1211, "total_steps": 1235, "loss": 0.3767, "lr": 4.6039162978743776e-08, "epoch": 4.902834008097166, "percentage": 98.06, "elapsed_time": "1:27:51", "remaining_time": "0:01:44"}
1442
+ {"current_steps": 1212, "total_steps": 1235, "loss": 0.384, "lr": 4.228381947004812e-08, "epoch": 4.906882591093117, "percentage": 98.14, "elapsed_time": "1:28:14", "remaining_time": "0:01:40"}
1443
+ {"current_steps": 1213, "total_steps": 1235, "loss": 0.3812, "lr": 3.868805732811343e-08, "epoch": 4.910931174089069, "percentage": 98.22, "elapsed_time": "1:28:37", "remaining_time": "0:01:36"}
1444
+ {"current_steps": 1214, "total_steps": 1235, "loss": 0.3683, "lr": 3.525190530455636e-08, "epoch": 4.91497975708502, "percentage": 98.3, "elapsed_time": "1:29:01", "remaining_time": "0:01:32"}
1445
+ {"current_steps": 1215, "total_steps": 1235, "loss": 0.3875, "lr": 3.197539087475887e-08, "epoch": 4.919028340080971, "percentage": 98.38, "elapsed_time": "1:29:25", "remaining_time": "0:01:28"}
1446
+ {"current_steps": 1216, "total_steps": 1235, "loss": 0.3728, "lr": 2.8858540237641786e-08, "epoch": 4.923076923076923, "percentage": 98.46, "elapsed_time": "1:29:49", "remaining_time": "0:01:24"}
1447
+ {"current_steps": 1217, "total_steps": 1235, "loss": 0.3714, "lr": 2.5901378315458247e-08, "epoch": 4.9271255060728745, "percentage": 98.54, "elapsed_time": "1:30:12", "remaining_time": "0:01:20"}
1448
+ {"current_steps": 1218, "total_steps": 1235, "loss": 0.3865, "lr": 2.3103928753598347e-08, "epoch": 4.931174089068826, "percentage": 98.62, "elapsed_time": "1:30:35", "remaining_time": "0:01:15"}
1449
+ {"current_steps": 1219, "total_steps": 1235, "loss": 0.3648, "lr": 2.0466213920393718e-08, "epoch": 4.935222672064778, "percentage": 98.7, "elapsed_time": "1:30:59", "remaining_time": "0:01:11"}
1450
+ {"current_steps": 1220, "total_steps": 1235, "loss": 0.3788, "lr": 1.7988254906942115e-08, "epoch": 4.939271255060729, "percentage": 98.79, "elapsed_time": "1:31:22", "remaining_time": "0:01:07"}
1451
+ {"current_steps": 1221, "total_steps": 1235, "loss": 0.3705, "lr": 1.5670071526936447e-08, "epoch": 4.94331983805668, "percentage": 98.87, "elapsed_time": "1:31:46", "remaining_time": "0:01:03"}
1452
+ {"current_steps": 1222, "total_steps": 1235, "loss": 0.3637, "lr": 1.3511682316509344e-08, "epoch": 4.947368421052632, "percentage": 98.95, "elapsed_time": "1:32:10", "remaining_time": "0:00:58"}
1453
+ {"current_steps": 1223, "total_steps": 1235, "loss": 0.3712, "lr": 1.1513104534086605e-08, "epoch": 4.951417004048583, "percentage": 99.03, "elapsed_time": "1:32:33", "remaining_time": "0:00:54"}
1454
+ {"current_steps": 1224, "total_steps": 1235, "loss": 0.3872, "lr": 9.67435416023843e-09, "epoch": 4.955465587044534, "percentage": 99.11, "elapsed_time": "1:32:57", "remaining_time": "0:00:50"}
1455
+ {"current_steps": 1225, "total_steps": 1235, "loss": 0.3815, "lr": 7.995445897566178e-09, "epoch": 4.959514170040486, "percentage": 99.19, "elapsed_time": "1:33:21", "remaining_time": "0:00:45"}
1456
+ {"current_steps": 1226, "total_steps": 1235, "loss": 0.3728, "lr": 6.476393170578021e-09, "epoch": 4.963562753036437, "percentage": 99.27, "elapsed_time": "1:33:44", "remaining_time": "0:00:41"}
1457
+ {"current_steps": 1227, "total_steps": 1235, "loss": 0.3778, "lr": 5.11720812557348e-09, "epoch": 4.967611336032388, "percentage": 99.35, "elapsed_time": "1:34:06", "remaining_time": "0:00:36"}
1458
+ {"current_steps": 1228, "total_steps": 1235, "loss": 0.3751, "lr": 3.917901630563492e-09, "epoch": 4.97165991902834, "percentage": 99.43, "elapsed_time": "1:34:29", "remaining_time": "0:00:32"}
1459
+ {"current_steps": 1229, "total_steps": 1235, "loss": 0.379, "lr": 2.878483275170485e-09, "epoch": 4.9757085020242915, "percentage": 99.51, "elapsed_time": "1:34:53", "remaining_time": "0:00:27"}
1460
+ {"current_steps": 1230, "total_steps": 1235, "loss": 0.3656, "lr": 1.998961370555108e-09, "epoch": 4.979757085020243, "percentage": 99.6, "elapsed_time": "1:35:16", "remaining_time": "0:00:23"}
1461
+ {"current_steps": 1231, "total_steps": 1235, "loss": 0.3866, "lr": 1.2793429493518361e-09, "epoch": 4.983805668016195, "percentage": 99.68, "elapsed_time": "1:35:39", "remaining_time": "0:00:18"}
1462
+ {"current_steps": 1232, "total_steps": 1235, "loss": 0.3758, "lr": 7.196337656112384e-10, "epoch": 4.987854251012146, "percentage": 99.76, "elapsed_time": "1:36:03", "remaining_time": "0:00:14"}
1463
+ {"current_steps": 1233, "total_steps": 1235, "loss": 0.3762, "lr": 3.198382947511292e-10, "epoch": 4.991902834008097, "percentage": 99.84, "elapsed_time": "1:36:27", "remaining_time": "0:00:09"}
1464
+ {"current_steps": 1234, "total_steps": 1235, "loss": 0.3729, "lr": 7.995973352770137e-11, "epoch": 4.995951417004049, "percentage": 99.92, "elapsed_time": "1:36:51", "remaining_time": "0:00:04"}
1465
+ {"current_steps": 1235, "total_steps": 1235, "loss": 0.3746, "lr": 0.0, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:37:14", "remaining_time": "0:00:00"}
1466
+ {"current_steps": 1235, "total_steps": 1235, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:40:14", "remaining_time": "0:00:00"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3cc31287cd90d4a3207f16856d7aa530054692c0a04fda46b55c6884b05bac7
3
- size 7288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d6187aa1688670731d0670a748bd461cce90da66170e9f482630ca1fc0da00d
3
+ size 7352