neginr commited on
Commit
f79cadb
·
verified ·
1 Parent(s): 4fabe4c

Training in progress, epoch 4

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a99adaec7a87d81d8fea3e4ad3b0de54c47ed02606d4307c64ad9a53e857fbf5
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e99d1f87fb90d6766be7b98adfd43911b9a19c28ddb34360e76898345603bc60
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35e1bcc157a658aad1d89f16ca0d06391fd0d0eb7735aa3f81dacb35d682220b
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19b4196c62054e1512558db0475a534fcbf37a1992de4367978ee2cf51083f06
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fa1a0c670c2aeff2506e5ef5d11d4e0bfa78e4e5359920d15abd7a36c6cd51c
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2261b1c765209858efa6858f3f4ba98fb43c10629671f937f04eaa608aaaf843
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77fc7dcf59a353a5e5fe84c3a95c0bd858d6a6c2163ed69f7c4330c3b8f90d01
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95fd38106cb76e72e892ce2efa775e53251c5bc96c45704008ab2b624f37f2bf
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -993,3 +993,250 @@
993
  {"current_steps": 746, "total_steps": 1235, "loss": 0.4136, "lr": 1.6261262506050282e-05, "epoch": 3.020242914979757, "percentage": 60.4, "elapsed_time": "4:56:09", "remaining_time": "3:14:07"}
994
  {"current_steps": 747, "total_steps": 1235, "loss": 0.4219, "lr": 1.620572014799777e-05, "epoch": 3.0242914979757085, "percentage": 60.49, "elapsed_time": "4:56:32", "remaining_time": "3:13:43"}
995
  {"current_steps": 748, "total_steps": 1235, "loss": 0.4204, "lr": 1.6150208128905857e-05, "epoch": 3.02834008097166, "percentage": 60.57, "elapsed_time": "4:56:54", "remaining_time": "3:13:18"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
993
  {"current_steps": 746, "total_steps": 1235, "loss": 0.4136, "lr": 1.6261262506050282e-05, "epoch": 3.020242914979757, "percentage": 60.4, "elapsed_time": "4:56:09", "remaining_time": "3:14:07"}
994
  {"current_steps": 747, "total_steps": 1235, "loss": 0.4219, "lr": 1.620572014799777e-05, "epoch": 3.0242914979757085, "percentage": 60.49, "elapsed_time": "4:56:32", "remaining_time": "3:13:43"}
995
  {"current_steps": 748, "total_steps": 1235, "loss": 0.4204, "lr": 1.6150208128905857e-05, "epoch": 3.02834008097166, "percentage": 60.57, "elapsed_time": "4:56:54", "remaining_time": "3:13:18"}
996
+ {"current_steps": 749, "total_steps": 1235, "loss": 0.4156, "lr": 1.6094726892647147e-05, "epoch": 3.032388663967611, "percentage": 60.65, "elapsed_time": "4:57:18", "remaining_time": "3:12:54"}
997
+ {"current_steps": 750, "total_steps": 1235, "loss": 0.4189, "lr": 1.6039276882848135e-05, "epoch": 3.0364372469635628, "percentage": 60.73, "elapsed_time": "4:57:40", "remaining_time": "3:12:29"}
998
+ {"current_steps": 751, "total_steps": 1235, "loss": 0.4212, "lr": 1.5983858542885635e-05, "epoch": 3.0404858299595143, "percentage": 60.81, "elapsed_time": "4:58:03", "remaining_time": "3:12:05"}
999
+ {"current_steps": 752, "total_steps": 1235, "loss": 0.4221, "lr": 1.5928472315883203e-05, "epoch": 3.0445344129554655, "percentage": 60.89, "elapsed_time": "4:58:26", "remaining_time": "3:11:41"}
1000
+ {"current_steps": 753, "total_steps": 1235, "loss": 0.4062, "lr": 1.5873118644707633e-05, "epoch": 3.048582995951417, "percentage": 60.97, "elapsed_time": "4:58:49", "remaining_time": "3:11:17"}
1001
+ {"current_steps": 754, "total_steps": 1235, "loss": 0.4019, "lr": 1.5817797971965413e-05, "epoch": 3.0526315789473686, "percentage": 61.05, "elapsed_time": "4:59:13", "remaining_time": "3:10:53"}
1002
+ {"current_steps": 755, "total_steps": 1235, "loss": 0.4268, "lr": 1.576251073999917e-05, "epoch": 3.0566801619433197, "percentage": 61.13, "elapsed_time": "4:59:37", "remaining_time": "3:10:29"}
1003
+ {"current_steps": 756, "total_steps": 1235, "loss": 0.4008, "lr": 1.5707257390884126e-05, "epoch": 3.0607287449392713, "percentage": 61.21, "elapsed_time": "5:00:01", "remaining_time": "3:10:05"}
1004
+ {"current_steps": 757, "total_steps": 1235, "loss": 0.4082, "lr": 1.5652038366424595e-05, "epoch": 3.064777327935223, "percentage": 61.3, "elapsed_time": "5:00:24", "remaining_time": "3:09:41"}
1005
+ {"current_steps": 758, "total_steps": 1235, "loss": 0.4197, "lr": 1.5596854108150424e-05, "epoch": 3.068825910931174, "percentage": 61.38, "elapsed_time": "5:00:48", "remaining_time": "3:09:17"}
1006
+ {"current_steps": 759, "total_steps": 1235, "loss": 0.4152, "lr": 1.5541705057313476e-05, "epoch": 3.0728744939271255, "percentage": 61.46, "elapsed_time": "5:01:11", "remaining_time": "3:08:53"}
1007
+ {"current_steps": 760, "total_steps": 1235, "loss": 0.4268, "lr": 1.5486591654884086e-05, "epoch": 3.076923076923077, "percentage": 61.54, "elapsed_time": "5:01:34", "remaining_time": "3:08:29"}
1008
+ {"current_steps": 761, "total_steps": 1235, "loss": 0.4226, "lr": 1.543151434154755e-05, "epoch": 3.080971659919028, "percentage": 61.62, "elapsed_time": "5:01:57", "remaining_time": "3:08:04"}
1009
+ {"current_steps": 762, "total_steps": 1235, "loss": 0.4063, "lr": 1.5376473557700615e-05, "epoch": 3.08502024291498, "percentage": 61.7, "elapsed_time": "5:02:21", "remaining_time": "3:07:40"}
1010
+ {"current_steps": 763, "total_steps": 1235, "loss": 0.4031, "lr": 1.5321469743447893e-05, "epoch": 3.0890688259109313, "percentage": 61.78, "elapsed_time": "5:02:43", "remaining_time": "3:07:16"}
1011
+ {"current_steps": 764, "total_steps": 1235, "loss": 0.4199, "lr": 1.5266503338598434e-05, "epoch": 3.0931174089068825, "percentage": 61.86, "elapsed_time": "5:03:05", "remaining_time": "3:06:51"}
1012
+ {"current_steps": 765, "total_steps": 1235, "loss": 0.4098, "lr": 1.5211574782662149e-05, "epoch": 3.097165991902834, "percentage": 61.94, "elapsed_time": "5:03:30", "remaining_time": "3:06:27"}
1013
+ {"current_steps": 766, "total_steps": 1235, "loss": 0.3994, "lr": 1.5156684514846307e-05, "epoch": 3.1012145748987856, "percentage": 62.02, "elapsed_time": "5:03:53", "remaining_time": "3:06:03"}
1014
+ {"current_steps": 767, "total_steps": 1235, "loss": 0.4117, "lr": 1.5101832974052012e-05, "epoch": 3.1052631578947367, "percentage": 62.11, "elapsed_time": "5:04:17", "remaining_time": "3:05:39"}
1015
+ {"current_steps": 768, "total_steps": 1235, "loss": 0.4245, "lr": 1.5047020598870737e-05, "epoch": 3.1093117408906883, "percentage": 62.19, "elapsed_time": "5:04:40", "remaining_time": "3:05:15"}
1016
+ {"current_steps": 769, "total_steps": 1235, "loss": 0.412, "lr": 1.4992247827580778e-05, "epoch": 3.11336032388664, "percentage": 62.27, "elapsed_time": "5:05:03", "remaining_time": "3:04:51"}
1017
+ {"current_steps": 770, "total_steps": 1235, "loss": 0.4144, "lr": 1.493751509814374e-05, "epoch": 3.117408906882591, "percentage": 62.35, "elapsed_time": "5:05:26", "remaining_time": "3:04:27"}
1018
+ {"current_steps": 771, "total_steps": 1235, "loss": 0.4075, "lr": 1.4882822848201073e-05, "epoch": 3.1214574898785425, "percentage": 62.43, "elapsed_time": "5:05:49", "remaining_time": "3:04:03"}
1019
+ {"current_steps": 772, "total_steps": 1235, "loss": 0.4063, "lr": 1.4828171515070553e-05, "epoch": 3.125506072874494, "percentage": 62.51, "elapsed_time": "5:06:12", "remaining_time": "3:03:38"}
1020
+ {"current_steps": 773, "total_steps": 1235, "loss": 0.3898, "lr": 1.4773561535742793e-05, "epoch": 3.1295546558704452, "percentage": 62.59, "elapsed_time": "5:06:36", "remaining_time": "3:03:15"}
1021
+ {"current_steps": 774, "total_steps": 1235, "loss": 0.4069, "lr": 1.4718993346877715e-05, "epoch": 3.133603238866397, "percentage": 62.67, "elapsed_time": "5:06:59", "remaining_time": "3:02:50"}
1022
+ {"current_steps": 775, "total_steps": 1235, "loss": 0.4084, "lr": 1.466446738480111e-05, "epoch": 3.1376518218623484, "percentage": 62.75, "elapsed_time": "5:07:23", "remaining_time": "3:02:26"}
1023
+ {"current_steps": 776, "total_steps": 1235, "loss": 0.4047, "lr": 1.460998408550112e-05, "epoch": 3.1417004048582995, "percentage": 62.83, "elapsed_time": "5:07:46", "remaining_time": "3:02:02"}
1024
+ {"current_steps": 777, "total_steps": 1235, "loss": 0.4272, "lr": 1.4555543884624751e-05, "epoch": 3.145748987854251, "percentage": 62.91, "elapsed_time": "5:08:09", "remaining_time": "3:01:38"}
1025
+ {"current_steps": 778, "total_steps": 1235, "loss": 0.4105, "lr": 1.4501147217474402e-05, "epoch": 3.1497975708502026, "percentage": 63.0, "elapsed_time": "5:08:33", "remaining_time": "3:01:14"}
1026
+ {"current_steps": 779, "total_steps": 1235, "loss": 0.4208, "lr": 1.444679451900437e-05, "epoch": 3.1538461538461537, "percentage": 63.08, "elapsed_time": "5:08:57", "remaining_time": "3:00:50"}
1027
+ {"current_steps": 780, "total_steps": 1235, "loss": 0.4039, "lr": 1.4392486223817397e-05, "epoch": 3.1578947368421053, "percentage": 63.16, "elapsed_time": "5:09:20", "remaining_time": "3:00:26"}
1028
+ {"current_steps": 781, "total_steps": 1235, "loss": 0.4089, "lr": 1.4338222766161143e-05, "epoch": 3.161943319838057, "percentage": 63.24, "elapsed_time": "5:09:43", "remaining_time": "3:00:02"}
1029
+ {"current_steps": 782, "total_steps": 1235, "loss": 0.4129, "lr": 1.4284004579924777e-05, "epoch": 3.165991902834008, "percentage": 63.32, "elapsed_time": "5:10:06", "remaining_time": "2:59:38"}
1030
+ {"current_steps": 783, "total_steps": 1235, "loss": 0.4032, "lr": 1.4229832098635479e-05, "epoch": 3.1700404858299596, "percentage": 63.4, "elapsed_time": "5:10:29", "remaining_time": "2:59:14"}
1031
+ {"current_steps": 784, "total_steps": 1235, "loss": 0.3953, "lr": 1.4175705755454963e-05, "epoch": 3.174089068825911, "percentage": 63.48, "elapsed_time": "5:10:52", "remaining_time": "2:58:50"}
1032
+ {"current_steps": 785, "total_steps": 1235, "loss": 0.4001, "lr": 1.412162598317602e-05, "epoch": 3.1781376518218623, "percentage": 63.56, "elapsed_time": "5:11:16", "remaining_time": "2:58:26"}
1033
+ {"current_steps": 786, "total_steps": 1235, "loss": 0.401, "lr": 1.406759321421907e-05, "epoch": 3.182186234817814, "percentage": 63.64, "elapsed_time": "5:11:39", "remaining_time": "2:58:01"}
1034
+ {"current_steps": 787, "total_steps": 1235, "loss": 0.4172, "lr": 1.401360788062871e-05, "epoch": 3.1862348178137654, "percentage": 63.72, "elapsed_time": "5:12:02", "remaining_time": "2:57:37"}
1035
+ {"current_steps": 788, "total_steps": 1235, "loss": 0.4265, "lr": 1.3959670414070204e-05, "epoch": 3.1902834008097165, "percentage": 63.81, "elapsed_time": "5:12:26", "remaining_time": "2:57:13"}
1036
+ {"current_steps": 789, "total_steps": 1235, "loss": 0.402, "lr": 1.3905781245826108e-05, "epoch": 3.194331983805668, "percentage": 63.89, "elapsed_time": "5:12:49", "remaining_time": "2:56:49"}
1037
+ {"current_steps": 790, "total_steps": 1235, "loss": 0.4244, "lr": 1.3851940806792778e-05, "epoch": 3.1983805668016196, "percentage": 63.97, "elapsed_time": "5:13:13", "remaining_time": "2:56:26"}
1038
+ {"current_steps": 791, "total_steps": 1235, "loss": 0.4147, "lr": 1.379814952747693e-05, "epoch": 3.2024291497975708, "percentage": 64.05, "elapsed_time": "5:13:36", "remaining_time": "2:56:02"}
1039
+ {"current_steps": 792, "total_steps": 1235, "loss": 0.4091, "lr": 1.3744407837992193e-05, "epoch": 3.2064777327935223, "percentage": 64.13, "elapsed_time": "5:14:00", "remaining_time": "2:55:38"}
1040
+ {"current_steps": 793, "total_steps": 1235, "loss": 0.4255, "lr": 1.3690716168055692e-05, "epoch": 3.2105263157894735, "percentage": 64.21, "elapsed_time": "5:14:23", "remaining_time": "2:55:13"}
1041
+ {"current_steps": 794, "total_steps": 1235, "loss": 0.4188, "lr": 1.363707494698459e-05, "epoch": 3.214574898785425, "percentage": 64.29, "elapsed_time": "5:14:47", "remaining_time": "2:54:50"}
1042
+ {"current_steps": 795, "total_steps": 1235, "loss": 0.4145, "lr": 1.358348460369265e-05, "epoch": 3.2186234817813766, "percentage": 64.37, "elapsed_time": "5:15:10", "remaining_time": "2:54:26"}
1043
+ {"current_steps": 796, "total_steps": 1235, "loss": 0.4224, "lr": 1.352994556668684e-05, "epoch": 3.2226720647773277, "percentage": 64.45, "elapsed_time": "5:15:33", "remaining_time": "2:54:02"}
1044
+ {"current_steps": 797, "total_steps": 1235, "loss": 0.423, "lr": 1.3476458264063865e-05, "epoch": 3.2267206477732793, "percentage": 64.53, "elapsed_time": "5:15:56", "remaining_time": "2:53:37"}
1045
+ {"current_steps": 798, "total_steps": 1235, "loss": 0.4164, "lr": 1.342302312350678e-05, "epoch": 3.230769230769231, "percentage": 64.62, "elapsed_time": "5:16:19", "remaining_time": "2:53:13"}
1046
+ {"current_steps": 799, "total_steps": 1235, "loss": 0.411, "lr": 1.3369640572281537e-05, "epoch": 3.234817813765182, "percentage": 64.7, "elapsed_time": "5:16:42", "remaining_time": "2:52:49"}
1047
+ {"current_steps": 800, "total_steps": 1235, "loss": 0.4107, "lr": 1.3316311037233596e-05, "epoch": 3.2388663967611335, "percentage": 64.78, "elapsed_time": "5:17:05", "remaining_time": "2:52:25"}
1048
+ {"current_steps": 801, "total_steps": 1235, "loss": 0.4089, "lr": 1.326303494478451e-05, "epoch": 3.242914979757085, "percentage": 64.86, "elapsed_time": "5:17:29", "remaining_time": "2:52:01"}
1049
+ {"current_steps": 802, "total_steps": 1235, "loss": 0.4198, "lr": 1.3209812720928472e-05, "epoch": 3.246963562753036, "percentage": 64.94, "elapsed_time": "5:17:52", "remaining_time": "2:51:37"}
1050
+ {"current_steps": 803, "total_steps": 1235, "loss": 0.4081, "lr": 1.315664479122898e-05, "epoch": 3.251012145748988, "percentage": 65.02, "elapsed_time": "5:18:15", "remaining_time": "2:51:13"}
1051
+ {"current_steps": 804, "total_steps": 1235, "loss": 0.4177, "lr": 1.3103531580815378e-05, "epoch": 3.2550607287449393, "percentage": 65.1, "elapsed_time": "5:18:38", "remaining_time": "2:50:49"}
1052
+ {"current_steps": 805, "total_steps": 1235, "loss": 0.398, "lr": 1.3050473514379488e-05, "epoch": 3.2591093117408905, "percentage": 65.18, "elapsed_time": "5:19:02", "remaining_time": "2:50:25"}
1053
+ {"current_steps": 806, "total_steps": 1235, "loss": 0.4288, "lr": 1.2997471016172188e-05, "epoch": 3.263157894736842, "percentage": 65.26, "elapsed_time": "5:19:26", "remaining_time": "2:50:01"}
1054
+ {"current_steps": 807, "total_steps": 1235, "loss": 0.435, "lr": 1.2944524510000042e-05, "epoch": 3.2672064777327936, "percentage": 65.34, "elapsed_time": "5:19:49", "remaining_time": "2:49:37"}
1055
+ {"current_steps": 808, "total_steps": 1235, "loss": 0.4217, "lr": 1.2891634419221908e-05, "epoch": 3.2712550607287447, "percentage": 65.43, "elapsed_time": "5:20:12", "remaining_time": "2:49:13"}
1056
+ {"current_steps": 809, "total_steps": 1235, "loss": 0.426, "lr": 1.2838801166745545e-05, "epoch": 3.2753036437246963, "percentage": 65.51, "elapsed_time": "5:20:36", "remaining_time": "2:48:49"}
1057
+ {"current_steps": 810, "total_steps": 1235, "loss": 0.4211, "lr": 1.2786025175024216e-05, "epoch": 3.279352226720648, "percentage": 65.59, "elapsed_time": "5:20:59", "remaining_time": "2:48:25"}
1058
+ {"current_steps": 811, "total_steps": 1235, "loss": 0.4134, "lr": 1.2733306866053357e-05, "epoch": 3.283400809716599, "percentage": 65.67, "elapsed_time": "5:21:22", "remaining_time": "2:48:01"}
1059
+ {"current_steps": 812, "total_steps": 1235, "loss": 0.399, "lr": 1.2680646661367163e-05, "epoch": 3.2874493927125505, "percentage": 65.75, "elapsed_time": "5:21:46", "remaining_time": "2:47:37"}
1060
+ {"current_steps": 813, "total_steps": 1235, "loss": 0.4136, "lr": 1.2628044982035219e-05, "epoch": 3.291497975708502, "percentage": 65.83, "elapsed_time": "5:22:10", "remaining_time": "2:47:13"}
1061
+ {"current_steps": 814, "total_steps": 1235, "loss": 0.4244, "lr": 1.2575502248659155e-05, "epoch": 3.2955465587044532, "percentage": 65.91, "elapsed_time": "5:22:33", "remaining_time": "2:46:49"}
1062
+ {"current_steps": 815, "total_steps": 1235, "loss": 0.4241, "lr": 1.2523018881369269e-05, "epoch": 3.299595141700405, "percentage": 65.99, "elapsed_time": "5:22:57", "remaining_time": "2:46:25"}
1063
+ {"current_steps": 816, "total_steps": 1235, "loss": 0.4258, "lr": 1.2470595299821176e-05, "epoch": 3.3036437246963564, "percentage": 66.07, "elapsed_time": "5:23:20", "remaining_time": "2:46:01"}
1064
+ {"current_steps": 817, "total_steps": 1235, "loss": 0.4078, "lr": 1.2418231923192416e-05, "epoch": 3.3076923076923075, "percentage": 66.15, "elapsed_time": "5:23:43", "remaining_time": "2:45:37"}
1065
+ {"current_steps": 818, "total_steps": 1235, "loss": 0.3981, "lr": 1.2365929170179165e-05, "epoch": 3.311740890688259, "percentage": 66.23, "elapsed_time": "5:24:06", "remaining_time": "2:45:13"}
1066
+ {"current_steps": 819, "total_steps": 1235, "loss": 0.3998, "lr": 1.2313687458992848e-05, "epoch": 3.3157894736842106, "percentage": 66.32, "elapsed_time": "5:24:30", "remaining_time": "2:44:49"}
1067
+ {"current_steps": 820, "total_steps": 1235, "loss": 0.43, "lr": 1.2261507207356785e-05, "epoch": 3.3198380566801617, "percentage": 66.4, "elapsed_time": "5:24:53", "remaining_time": "2:44:25"}
1068
+ {"current_steps": 821, "total_steps": 1235, "loss": 0.427, "lr": 1.220938883250288e-05, "epoch": 3.3238866396761133, "percentage": 66.48, "elapsed_time": "5:25:17", "remaining_time": "2:44:01"}
1069
+ {"current_steps": 822, "total_steps": 1235, "loss": 0.4075, "lr": 1.215733275116827e-05, "epoch": 3.327935222672065, "percentage": 66.56, "elapsed_time": "5:25:41", "remaining_time": "2:43:38"}
1070
+ {"current_steps": 823, "total_steps": 1235, "loss": 0.4224, "lr": 1.2105339379592005e-05, "epoch": 3.331983805668016, "percentage": 66.64, "elapsed_time": "5:26:04", "remaining_time": "2:43:14"}
1071
+ {"current_steps": 824, "total_steps": 1235, "loss": 0.4098, "lr": 1.2053409133511681e-05, "epoch": 3.3360323886639676, "percentage": 66.72, "elapsed_time": "5:26:27", "remaining_time": "2:42:49"}
1072
+ {"current_steps": 825, "total_steps": 1235, "loss": 0.4078, "lr": 1.2001542428160173e-05, "epoch": 3.340080971659919, "percentage": 66.8, "elapsed_time": "5:26:50", "remaining_time": "2:42:25"}
1073
+ {"current_steps": 826, "total_steps": 1235, "loss": 0.4151, "lr": 1.1949739678262278e-05, "epoch": 3.3441295546558703, "percentage": 66.88, "elapsed_time": "5:27:14", "remaining_time": "2:42:02"}
1074
+ {"current_steps": 827, "total_steps": 1235, "loss": 0.4163, "lr": 1.189800129803139e-05, "epoch": 3.348178137651822, "percentage": 66.96, "elapsed_time": "5:27:37", "remaining_time": "2:41:37"}
1075
+ {"current_steps": 828, "total_steps": 1235, "loss": 0.4222, "lr": 1.1846327701166228e-05, "epoch": 3.3522267206477734, "percentage": 67.04, "elapsed_time": "5:28:01", "remaining_time": "2:41:14"}
1076
+ {"current_steps": 829, "total_steps": 1235, "loss": 0.4147, "lr": 1.1794719300847493e-05, "epoch": 3.3562753036437245, "percentage": 67.13, "elapsed_time": "5:28:24", "remaining_time": "2:40:50"}
1077
+ {"current_steps": 830, "total_steps": 1235, "loss": 0.4255, "lr": 1.1743176509734582e-05, "epoch": 3.360323886639676, "percentage": 67.21, "elapsed_time": "5:28:47", "remaining_time": "2:40:26"}
1078
+ {"current_steps": 831, "total_steps": 1235, "loss": 0.4077, "lr": 1.1691699739962275e-05, "epoch": 3.3643724696356276, "percentage": 67.29, "elapsed_time": "5:29:11", "remaining_time": "2:40:02"}
1079
+ {"current_steps": 832, "total_steps": 1235, "loss": 0.4157, "lr": 1.1640289403137456e-05, "epoch": 3.3684210526315788, "percentage": 67.37, "elapsed_time": "5:29:33", "remaining_time": "2:39:37"}
1080
+ {"current_steps": 833, "total_steps": 1235, "loss": 0.4199, "lr": 1.1588945910335802e-05, "epoch": 3.3724696356275303, "percentage": 67.45, "elapsed_time": "5:29:56", "remaining_time": "2:39:13"}
1081
+ {"current_steps": 834, "total_steps": 1235, "loss": 0.4183, "lr": 1.1537669672098517e-05, "epoch": 3.376518218623482, "percentage": 67.53, "elapsed_time": "5:30:20", "remaining_time": "2:38:49"}
1082
+ {"current_steps": 835, "total_steps": 1235, "loss": 0.4221, "lr": 1.1486461098429036e-05, "epoch": 3.380566801619433, "percentage": 67.61, "elapsed_time": "5:30:43", "remaining_time": "2:38:25"}
1083
+ {"current_steps": 836, "total_steps": 1235, "loss": 0.4115, "lr": 1.1435320598789747e-05, "epoch": 3.3846153846153846, "percentage": 67.69, "elapsed_time": "5:31:06", "remaining_time": "2:38:01"}
1084
+ {"current_steps": 837, "total_steps": 1235, "loss": 0.4143, "lr": 1.1384248582098736e-05, "epoch": 3.388663967611336, "percentage": 67.77, "elapsed_time": "5:31:30", "remaining_time": "2:37:38"}
1085
+ {"current_steps": 838, "total_steps": 1235, "loss": 0.4286, "lr": 1.1333245456726467e-05, "epoch": 3.3927125506072873, "percentage": 67.85, "elapsed_time": "5:31:53", "remaining_time": "2:37:13"}
1086
+ {"current_steps": 839, "total_steps": 1235, "loss": 0.4394, "lr": 1.128231163049258e-05, "epoch": 3.396761133603239, "percentage": 67.94, "elapsed_time": "5:32:17", "remaining_time": "2:36:50"}
1087
+ {"current_steps": 840, "total_steps": 1235, "loss": 0.4136, "lr": 1.123144751066259e-05, "epoch": 3.4008097165991904, "percentage": 68.02, "elapsed_time": "5:32:41", "remaining_time": "2:36:26"}
1088
+ {"current_steps": 841, "total_steps": 1235, "loss": 0.4122, "lr": 1.1180653503944657e-05, "epoch": 3.4048582995951415, "percentage": 68.1, "elapsed_time": "5:33:04", "remaining_time": "2:36:02"}
1089
+ {"current_steps": 842, "total_steps": 1235, "loss": 0.4083, "lr": 1.1129930016486287e-05, "epoch": 3.408906882591093, "percentage": 68.18, "elapsed_time": "5:33:28", "remaining_time": "2:35:38"}
1090
+ {"current_steps": 843, "total_steps": 1235, "loss": 0.4255, "lr": 1.107927745387114e-05, "epoch": 3.4129554655870447, "percentage": 68.26, "elapsed_time": "5:33:50", "remaining_time": "2:35:14"}
1091
+ {"current_steps": 844, "total_steps": 1235, "loss": 0.4173, "lr": 1.1028696221115766e-05, "epoch": 3.417004048582996, "percentage": 68.34, "elapsed_time": "5:34:14", "remaining_time": "2:34:50"}
1092
+ {"current_steps": 845, "total_steps": 1235, "loss": 0.3983, "lr": 1.0978186722666341e-05, "epoch": 3.4210526315789473, "percentage": 68.42, "elapsed_time": "5:34:38", "remaining_time": "2:34:27"}
1093
+ {"current_steps": 846, "total_steps": 1235, "loss": 0.4078, "lr": 1.0927749362395475e-05, "epoch": 3.425101214574899, "percentage": 68.5, "elapsed_time": "5:35:02", "remaining_time": "2:34:03"}
1094
+ {"current_steps": 847, "total_steps": 1235, "loss": 0.4171, "lr": 1.0877384543598954e-05, "epoch": 3.42914979757085, "percentage": 68.58, "elapsed_time": "5:35:26", "remaining_time": "2:33:39"}
1095
+ {"current_steps": 848, "total_steps": 1235, "loss": 0.4155, "lr": 1.0827092668992529e-05, "epoch": 3.4331983805668016, "percentage": 68.66, "elapsed_time": "5:35:49", "remaining_time": "2:33:15"}
1096
+ {"current_steps": 849, "total_steps": 1235, "loss": 0.4303, "lr": 1.077687414070869e-05, "epoch": 3.437246963562753, "percentage": 68.74, "elapsed_time": "5:36:12", "remaining_time": "2:32:51"}
1097
+ {"current_steps": 850, "total_steps": 1235, "loss": 0.4238, "lr": 1.0726729360293451e-05, "epoch": 3.4412955465587043, "percentage": 68.83, "elapsed_time": "5:36:34", "remaining_time": "2:32:27"}
1098
+ {"current_steps": 851, "total_steps": 1235, "loss": 0.4154, "lr": 1.0676658728703147e-05, "epoch": 3.445344129554656, "percentage": 68.91, "elapsed_time": "5:36:58", "remaining_time": "2:32:03"}
1099
+ {"current_steps": 852, "total_steps": 1235, "loss": 0.4237, "lr": 1.0626662646301198e-05, "epoch": 3.4493927125506074, "percentage": 68.99, "elapsed_time": "5:37:22", "remaining_time": "2:31:39"}
1100
+ {"current_steps": 853, "total_steps": 1235, "loss": 0.4084, "lr": 1.0576741512854958e-05, "epoch": 3.4534412955465585, "percentage": 69.07, "elapsed_time": "5:37:44", "remaining_time": "2:31:15"}
1101
+ {"current_steps": 854, "total_steps": 1235, "loss": 0.4135, "lr": 1.052689572753247e-05, "epoch": 3.45748987854251, "percentage": 69.15, "elapsed_time": "5:38:08", "remaining_time": "2:30:51"}
1102
+ {"current_steps": 855, "total_steps": 1235, "loss": 0.4256, "lr": 1.0477125688899328e-05, "epoch": 3.4615384615384617, "percentage": 69.23, "elapsed_time": "5:38:32", "remaining_time": "2:30:27"}
1103
+ {"current_steps": 856, "total_steps": 1235, "loss": 0.4183, "lr": 1.0427431794915406e-05, "epoch": 3.465587044534413, "percentage": 69.31, "elapsed_time": "5:38:54", "remaining_time": "2:30:03"}
1104
+ {"current_steps": 857, "total_steps": 1235, "loss": 0.4223, "lr": 1.0377814442931769e-05, "epoch": 3.4696356275303644, "percentage": 69.39, "elapsed_time": "5:39:18", "remaining_time": "2:29:39"}
1105
+ {"current_steps": 858, "total_steps": 1235, "loss": 0.4195, "lr": 1.0328274029687439e-05, "epoch": 3.473684210526316, "percentage": 69.47, "elapsed_time": "5:39:42", "remaining_time": "2:29:15"}
1106
+ {"current_steps": 859, "total_steps": 1235, "loss": 0.4142, "lr": 1.0278810951306253e-05, "epoch": 3.477732793522267, "percentage": 69.55, "elapsed_time": "5:40:05", "remaining_time": "2:28:52"}
1107
+ {"current_steps": 860, "total_steps": 1235, "loss": 0.4179, "lr": 1.0229425603293647e-05, "epoch": 3.4817813765182186, "percentage": 69.64, "elapsed_time": "5:40:28", "remaining_time": "2:28:27"}
1108
+ {"current_steps": 861, "total_steps": 1235, "loss": 0.4241, "lr": 1.0180118380533558e-05, "epoch": 3.48582995951417, "percentage": 69.72, "elapsed_time": "5:40:51", "remaining_time": "2:28:03"}
1109
+ {"current_steps": 862, "total_steps": 1235, "loss": 0.431, "lr": 1.0130889677285225e-05, "epoch": 3.4898785425101213, "percentage": 69.8, "elapsed_time": "5:41:15", "remaining_time": "2:27:40"}
1110
+ {"current_steps": 863, "total_steps": 1235, "loss": 0.4035, "lr": 1.008173988718005e-05, "epoch": 3.493927125506073, "percentage": 69.88, "elapsed_time": "5:41:38", "remaining_time": "2:27:16"}
1111
+ {"current_steps": 864, "total_steps": 1235, "loss": 0.4126, "lr": 1.0032669403218439e-05, "epoch": 3.4979757085020244, "percentage": 69.96, "elapsed_time": "5:42:02", "remaining_time": "2:26:52"}
1112
+ {"current_steps": 865, "total_steps": 1235, "loss": 0.4193, "lr": 9.983678617766677e-06, "epoch": 3.5020242914979756, "percentage": 70.04, "elapsed_time": "5:42:25", "remaining_time": "2:26:28"}
1113
+ {"current_steps": 866, "total_steps": 1235, "loss": 0.411, "lr": 9.934767922553788e-06, "epoch": 3.506072874493927, "percentage": 70.12, "elapsed_time": "5:42:48", "remaining_time": "2:26:04"}
1114
+ {"current_steps": 867, "total_steps": 1235, "loss": 0.4207, "lr": 9.885937708668371e-06, "epoch": 3.5101214574898787, "percentage": 70.2, "elapsed_time": "5:43:12", "remaining_time": "2:25:40"}
1115
+ {"current_steps": 868, "total_steps": 1235, "loss": 0.4166, "lr": 9.837188366555524e-06, "epoch": 3.51417004048583, "percentage": 70.28, "elapsed_time": "5:43:35", "remaining_time": "2:25:16"}
1116
+ {"current_steps": 869, "total_steps": 1235, "loss": 0.4117, "lr": 9.788520286013691e-06, "epoch": 3.5182186234817814, "percentage": 70.36, "elapsed_time": "5:43:58", "remaining_time": "2:24:52"}
1117
+ {"current_steps": 870, "total_steps": 1235, "loss": 0.4063, "lr": 9.739933856191537e-06, "epoch": 3.522267206477733, "percentage": 70.45, "elapsed_time": "5:44:21", "remaining_time": "2:24:28"}
1118
+ {"current_steps": 871, "total_steps": 1235, "loss": 0.4222, "lr": 9.691429465584866e-06, "epoch": 3.526315789473684, "percentage": 70.53, "elapsed_time": "5:44:45", "remaining_time": "2:24:04"}
1119
+ {"current_steps": 872, "total_steps": 1235, "loss": 0.429, "lr": 9.643007502033492e-06, "epoch": 3.5303643724696356, "percentage": 70.61, "elapsed_time": "5:45:08", "remaining_time": "2:23:40"}
1120
+ {"current_steps": 873, "total_steps": 1235, "loss": 0.4044, "lr": 9.594668352718152e-06, "epoch": 3.534412955465587, "percentage": 70.69, "elapsed_time": "5:45:32", "remaining_time": "2:23:17"}
1121
+ {"current_steps": 874, "total_steps": 1235, "loss": 0.4145, "lr": 9.546412404157383e-06, "epoch": 3.5384615384615383, "percentage": 70.77, "elapsed_time": "5:45:56", "remaining_time": "2:22:53"}
1122
+ {"current_steps": 875, "total_steps": 1235, "loss": 0.4178, "lr": 9.498240042204471e-06, "epoch": 3.54251012145749, "percentage": 70.85, "elapsed_time": "5:46:20", "remaining_time": "2:22:29"}
1123
+ {"current_steps": 876, "total_steps": 1235, "loss": 0.4167, "lr": 9.450151652044339e-06, "epoch": 3.5465587044534415, "percentage": 70.93, "elapsed_time": "5:46:43", "remaining_time": "2:22:05"}
1124
+ {"current_steps": 877, "total_steps": 1235, "loss": 0.3882, "lr": 9.402147618190472e-06, "epoch": 3.5506072874493926, "percentage": 71.01, "elapsed_time": "5:47:06", "remaining_time": "2:21:41"}
1125
+ {"current_steps": 878, "total_steps": 1235, "loss": 0.4288, "lr": 9.354228324481841e-06, "epoch": 3.554655870445344, "percentage": 71.09, "elapsed_time": "5:47:30", "remaining_time": "2:21:17"}
1126
+ {"current_steps": 879, "total_steps": 1235, "loss": 0.4293, "lr": 9.306394154079852e-06, "epoch": 3.5587044534412957, "percentage": 71.17, "elapsed_time": "5:47:53", "remaining_time": "2:20:54"}
1127
+ {"current_steps": 880, "total_steps": 1235, "loss": 0.4141, "lr": 9.258645489465254e-06, "epoch": 3.562753036437247, "percentage": 71.26, "elapsed_time": "5:48:15", "remaining_time": "2:20:29"}
1128
+ {"current_steps": 881, "total_steps": 1235, "loss": 0.4257, "lr": 9.21098271243509e-06, "epoch": 3.5668016194331984, "percentage": 71.34, "elapsed_time": "5:48:39", "remaining_time": "2:20:05"}
1129
+ {"current_steps": 882, "total_steps": 1235, "loss": 0.4174, "lr": 9.163406204099659e-06, "epoch": 3.57085020242915, "percentage": 71.42, "elapsed_time": "5:49:02", "remaining_time": "2:19:41"}
1130
+ {"current_steps": 883, "total_steps": 1235, "loss": 0.4138, "lr": 9.115916344879452e-06, "epoch": 3.574898785425101, "percentage": 71.5, "elapsed_time": "5:49:25", "remaining_time": "2:19:17"}
1131
+ {"current_steps": 884, "total_steps": 1235, "loss": 0.4048, "lr": 9.068513514502126e-06, "epoch": 3.5789473684210527, "percentage": 71.58, "elapsed_time": "5:49:48", "remaining_time": "2:18:53"}
1132
+ {"current_steps": 885, "total_steps": 1235, "loss": 0.419, "lr": 9.021198091999439e-06, "epoch": 3.582995951417004, "percentage": 71.66, "elapsed_time": "5:50:11", "remaining_time": "2:18:29"}
1133
+ {"current_steps": 886, "total_steps": 1235, "loss": 0.4127, "lr": 8.973970455704251e-06, "epoch": 3.5870445344129553, "percentage": 71.74, "elapsed_time": "5:50:35", "remaining_time": "2:18:05"}
1134
+ {"current_steps": 887, "total_steps": 1235, "loss": 0.4089, "lr": 8.926830983247495e-06, "epoch": 3.591093117408907, "percentage": 71.82, "elapsed_time": "5:50:58", "remaining_time": "2:17:41"}
1135
+ {"current_steps": 888, "total_steps": 1235, "loss": 0.4263, "lr": 8.879780051555116e-06, "epoch": 3.5951417004048585, "percentage": 71.9, "elapsed_time": "5:51:22", "remaining_time": "2:17:18"}
1136
+ {"current_steps": 889, "total_steps": 1235, "loss": 0.4289, "lr": 8.83281803684512e-06, "epoch": 3.5991902834008096, "percentage": 71.98, "elapsed_time": "5:51:45", "remaining_time": "2:16:54"}
1137
+ {"current_steps": 890, "total_steps": 1235, "loss": 0.4249, "lr": 8.785945314624532e-06, "epoch": 3.603238866396761, "percentage": 72.06, "elapsed_time": "5:52:09", "remaining_time": "2:16:30"}
1138
+ {"current_steps": 891, "total_steps": 1235, "loss": 0.4189, "lr": 8.739162259686385e-06, "epoch": 3.6072874493927127, "percentage": 72.15, "elapsed_time": "5:52:33", "remaining_time": "2:16:06"}
1139
+ {"current_steps": 892, "total_steps": 1235, "loss": 0.4242, "lr": 8.692469246106734e-06, "epoch": 3.611336032388664, "percentage": 72.23, "elapsed_time": "5:52:56", "remaining_time": "2:15:43"}
1140
+ {"current_steps": 893, "total_steps": 1235, "loss": 0.4082, "lr": 8.645866647241677e-06, "epoch": 3.6153846153846154, "percentage": 72.31, "elapsed_time": "5:53:19", "remaining_time": "2:15:19"}
1141
+ {"current_steps": 894, "total_steps": 1235, "loss": 0.4134, "lr": 8.599354835724348e-06, "epoch": 3.619433198380567, "percentage": 72.39, "elapsed_time": "5:53:43", "remaining_time": "2:14:55"}
1142
+ {"current_steps": 895, "total_steps": 1235, "loss": 0.4086, "lr": 8.552934183461958e-06, "epoch": 3.623481781376518, "percentage": 72.47, "elapsed_time": "5:54:07", "remaining_time": "2:14:31"}
1143
+ {"current_steps": 896, "total_steps": 1235, "loss": 0.4233, "lr": 8.506605061632805e-06, "epoch": 3.6275303643724697, "percentage": 72.55, "elapsed_time": "5:54:30", "remaining_time": "2:14:07"}
1144
+ {"current_steps": 897, "total_steps": 1235, "loss": 0.4208, "lr": 8.460367840683308e-06, "epoch": 3.6315789473684212, "percentage": 72.63, "elapsed_time": "5:54:54", "remaining_time": "2:13:43"}
1145
+ {"current_steps": 898, "total_steps": 1235, "loss": 0.4178, "lr": 8.414222890325065e-06, "epoch": 3.6356275303643724, "percentage": 72.71, "elapsed_time": "5:55:18", "remaining_time": "2:13:20"}
1146
+ {"current_steps": 899, "total_steps": 1235, "loss": 0.4322, "lr": 8.368170579531855e-06, "epoch": 3.639676113360324, "percentage": 72.79, "elapsed_time": "5:55:42", "remaining_time": "2:12:56"}
1147
+ {"current_steps": 900, "total_steps": 1235, "loss": 0.4092, "lr": 8.322211276536733e-06, "epoch": 3.6437246963562755, "percentage": 72.87, "elapsed_time": "5:56:05", "remaining_time": "2:12:32"}
1148
+ {"current_steps": 901, "total_steps": 1235, "loss": 0.399, "lr": 8.27634534882907e-06, "epoch": 3.6477732793522266, "percentage": 72.96, "elapsed_time": "5:56:28", "remaining_time": "2:12:08"}
1149
+ {"current_steps": 902, "total_steps": 1235, "loss": 0.4197, "lr": 8.230573163151585e-06, "epoch": 3.651821862348178, "percentage": 73.04, "elapsed_time": "5:56:51", "remaining_time": "2:11:44"}
1150
+ {"current_steps": 903, "total_steps": 1235, "loss": 0.4137, "lr": 8.184895085497466e-06, "epoch": 3.6558704453441297, "percentage": 73.12, "elapsed_time": "5:57:14", "remaining_time": "2:11:20"}
1151
+ {"current_steps": 904, "total_steps": 1235, "loss": 0.4069, "lr": 8.139311481107401e-06, "epoch": 3.659919028340081, "percentage": 73.2, "elapsed_time": "5:57:37", "remaining_time": "2:10:56"}
1152
+ {"current_steps": 905, "total_steps": 1235, "loss": 0.4189, "lr": 8.093822714466686e-06, "epoch": 3.6639676113360324, "percentage": 73.28, "elapsed_time": "5:58:01", "remaining_time": "2:10:32"}
1153
+ {"current_steps": 906, "total_steps": 1235, "loss": 0.4218, "lr": 8.048429149302271e-06, "epoch": 3.668016194331984, "percentage": 73.36, "elapsed_time": "5:58:22", "remaining_time": "2:10:08"}
1154
+ {"current_steps": 907, "total_steps": 1235, "loss": 0.4157, "lr": 8.003131148579902e-06, "epoch": 3.672064777327935, "percentage": 73.44, "elapsed_time": "5:58:45", "remaining_time": "2:09:44"}
1155
+ {"current_steps": 908, "total_steps": 1235, "loss": 0.4173, "lr": 7.957929074501182e-06, "epoch": 3.6761133603238867, "percentage": 73.52, "elapsed_time": "5:59:08", "remaining_time": "2:09:20"}
1156
+ {"current_steps": 909, "total_steps": 1235, "loss": 0.4104, "lr": 7.912823288500695e-06, "epoch": 3.6801619433198383, "percentage": 73.6, "elapsed_time": "5:59:31", "remaining_time": "2:08:56"}
1157
+ {"current_steps": 910, "total_steps": 1235, "loss": 0.4209, "lr": 7.867814151243102e-06, "epoch": 3.6842105263157894, "percentage": 73.68, "elapsed_time": "5:59:55", "remaining_time": "2:08:32"}
1158
+ {"current_steps": 911, "total_steps": 1235, "loss": 0.4167, "lr": 7.822902022620267e-06, "epoch": 3.688259109311741, "percentage": 73.77, "elapsed_time": "6:00:18", "remaining_time": "2:08:08"}
1159
+ {"current_steps": 912, "total_steps": 1235, "loss": 0.4089, "lr": 7.778087261748377e-06, "epoch": 3.6923076923076925, "percentage": 73.85, "elapsed_time": "6:00:42", "remaining_time": "2:07:44"}
1160
+ {"current_steps": 913, "total_steps": 1235, "loss": 0.4086, "lr": 7.733370226965056e-06, "epoch": 3.6963562753036436, "percentage": 73.93, "elapsed_time": "6:01:05", "remaining_time": "2:07:21"}
1161
+ {"current_steps": 914, "total_steps": 1235, "loss": 0.417, "lr": 7.688751275826527e-06, "epoch": 3.700404858299595, "percentage": 74.01, "elapsed_time": "6:01:29", "remaining_time": "2:06:57"}
1162
+ {"current_steps": 915, "total_steps": 1235, "loss": 0.4181, "lr": 7.644230765104735e-06, "epoch": 3.7044534412955468, "percentage": 74.09, "elapsed_time": "6:01:53", "remaining_time": "2:06:33"}
1163
+ {"current_steps": 916, "total_steps": 1235, "loss": 0.4159, "lr": 7.599809050784502e-06, "epoch": 3.708502024291498, "percentage": 74.17, "elapsed_time": "6:02:16", "remaining_time": "2:06:09"}
1164
+ {"current_steps": 917, "total_steps": 1235, "loss": 0.4109, "lr": 7.555486488060661e-06, "epoch": 3.7125506072874495, "percentage": 74.25, "elapsed_time": "6:02:39", "remaining_time": "2:05:45"}
1165
+ {"current_steps": 918, "total_steps": 1235, "loss": 0.4232, "lr": 7.511263431335249e-06, "epoch": 3.716599190283401, "percentage": 74.33, "elapsed_time": "6:03:03", "remaining_time": "2:05:22"}
1166
+ {"current_steps": 919, "total_steps": 1235, "loss": 0.4077, "lr": 7.467140234214656e-06, "epoch": 3.720647773279352, "percentage": 74.41, "elapsed_time": "6:03:26", "remaining_time": "2:04:58"}
1167
+ {"current_steps": 920, "total_steps": 1235, "loss": 0.4234, "lr": 7.423117249506777e-06, "epoch": 3.7246963562753037, "percentage": 74.49, "elapsed_time": "6:03:49", "remaining_time": "2:04:34"}
1168
+ {"current_steps": 921, "total_steps": 1235, "loss": 0.42, "lr": 7.379194829218231e-06, "epoch": 3.7287449392712553, "percentage": 74.57, "elapsed_time": "6:04:13", "remaining_time": "2:04:10"}
1169
+ {"current_steps": 922, "total_steps": 1235, "loss": 0.4173, "lr": 7.335373324551518e-06, "epoch": 3.7327935222672064, "percentage": 74.66, "elapsed_time": "6:04:37", "remaining_time": "2:03:46"}
1170
+ {"current_steps": 923, "total_steps": 1235, "loss": 0.4042, "lr": 7.291653085902224e-06, "epoch": 3.736842105263158, "percentage": 74.74, "elapsed_time": "6:05:00", "remaining_time": "2:03:22"}
1171
+ {"current_steps": 924, "total_steps": 1235, "loss": 0.4259, "lr": 7.248034462856213e-06, "epoch": 3.7408906882591095, "percentage": 74.82, "elapsed_time": "6:05:24", "remaining_time": "2:02:59"}
1172
+ {"current_steps": 925, "total_steps": 1235, "loss": 0.4121, "lr": 7.20451780418683e-06, "epoch": 3.7449392712550607, "percentage": 74.9, "elapsed_time": "6:05:48", "remaining_time": "2:02:35"}
1173
+ {"current_steps": 926, "total_steps": 1235, "loss": 0.4266, "lr": 7.161103457852128e-06, "epoch": 3.748987854251012, "percentage": 74.98, "elapsed_time": "6:06:11", "remaining_time": "2:02:11"}
1174
+ {"current_steps": 927, "total_steps": 1235, "loss": 0.4082, "lr": 7.117791770992046e-06, "epoch": 3.753036437246964, "percentage": 75.06, "elapsed_time": "6:06:34", "remaining_time": "2:01:47"}
1175
+ {"current_steps": 928, "total_steps": 1235, "loss": 0.417, "lr": 7.074583089925688e-06, "epoch": 3.757085020242915, "percentage": 75.14, "elapsed_time": "6:06:57", "remaining_time": "2:01:23"}
1176
+ {"current_steps": 929, "total_steps": 1235, "loss": 0.4088, "lr": 7.0314777601485155e-06, "epoch": 3.7611336032388665, "percentage": 75.22, "elapsed_time": "6:07:21", "remaining_time": "2:01:00"}
1177
+ {"current_steps": 930, "total_steps": 1235, "loss": 0.4172, "lr": 6.988476126329604e-06, "epoch": 3.765182186234818, "percentage": 75.3, "elapsed_time": "6:07:44", "remaining_time": "2:00:36"}
1178
+ {"current_steps": 931, "total_steps": 1235, "loss": 0.4003, "lr": 6.945578532308857e-06, "epoch": 3.769230769230769, "percentage": 75.38, "elapsed_time": "6:08:08", "remaining_time": "2:00:12"}
1179
+ {"current_steps": 932, "total_steps": 1235, "loss": 0.4039, "lr": 6.902785321094301e-06, "epoch": 3.7732793522267207, "percentage": 75.47, "elapsed_time": "6:08:31", "remaining_time": "1:59:48"}
1180
+ {"current_steps": 933, "total_steps": 1235, "loss": 0.4004, "lr": 6.8600968348593115e-06, "epoch": 3.7773279352226723, "percentage": 75.55, "elapsed_time": "6:08:55", "remaining_time": "1:59:24"}
1181
+ {"current_steps": 934, "total_steps": 1235, "loss": 0.4208, "lr": 6.817513414939892e-06, "epoch": 3.7813765182186234, "percentage": 75.63, "elapsed_time": "6:09:18", "remaining_time": "1:59:01"}
1182
+ {"current_steps": 935, "total_steps": 1235, "loss": 0.42, "lr": 6.775035401831924e-06, "epoch": 3.785425101214575, "percentage": 75.71, "elapsed_time": "6:09:42", "remaining_time": "1:58:37"}
1183
+ {"current_steps": 936, "total_steps": 1235, "loss": 0.4227, "lr": 6.732663135188473e-06, "epoch": 3.7894736842105265, "percentage": 75.79, "elapsed_time": "6:10:06", "remaining_time": "1:58:13"}
1184
+ {"current_steps": 937, "total_steps": 1235, "loss": 0.4246, "lr": 6.690396953817055e-06, "epoch": 3.7935222672064777, "percentage": 75.87, "elapsed_time": "6:10:28", "remaining_time": "1:57:49"}
1185
+ {"current_steps": 938, "total_steps": 1235, "loss": 0.4234, "lr": 6.648237195676927e-06, "epoch": 3.7975708502024292, "percentage": 75.95, "elapsed_time": "6:10:52", "remaining_time": "1:57:25"}
1186
+ {"current_steps": 939, "total_steps": 1235, "loss": 0.3982, "lr": 6.606184197876395e-06, "epoch": 3.801619433198381, "percentage": 76.03, "elapsed_time": "6:11:17", "remaining_time": "1:57:02"}
1187
+ {"current_steps": 940, "total_steps": 1235, "loss": 0.4085, "lr": 6.564238296670109e-06, "epoch": 3.805668016194332, "percentage": 76.11, "elapsed_time": "6:11:41", "remaining_time": "1:56:38"}
1188
+ {"current_steps": 941, "total_steps": 1235, "loss": 0.4261, "lr": 6.52239982745638e-06, "epoch": 3.8097165991902835, "percentage": 76.19, "elapsed_time": "6:12:04", "remaining_time": "1:56:15"}
1189
+ {"current_steps": 942, "total_steps": 1235, "loss": 0.438, "lr": 6.480669124774484e-06, "epoch": 3.813765182186235, "percentage": 76.28, "elapsed_time": "6:12:29", "remaining_time": "1:55:51"}
1190
+ {"current_steps": 943, "total_steps": 1235, "loss": 0.4234, "lr": 6.439046522302013e-06, "epoch": 3.817813765182186, "percentage": 76.36, "elapsed_time": "6:12:51", "remaining_time": "1:55:27"}
1191
+ {"current_steps": 944, "total_steps": 1235, "loss": 0.4189, "lr": 6.397532352852191e-06, "epoch": 3.8218623481781377, "percentage": 76.44, "elapsed_time": "6:13:15", "remaining_time": "1:55:03"}
1192
+ {"current_steps": 945, "total_steps": 1235, "loss": 0.4008, "lr": 6.356126948371202e-06, "epoch": 3.8259109311740893, "percentage": 76.52, "elapsed_time": "6:13:39", "remaining_time": "1:54:40"}
1193
+ {"current_steps": 946, "total_steps": 1235, "loss": 0.4086, "lr": 6.314830639935559e-06, "epoch": 3.8299595141700404, "percentage": 76.6, "elapsed_time": "6:14:02", "remaining_time": "1:54:16"}
1194
+ {"current_steps": 947, "total_steps": 1235, "loss": 0.4176, "lr": 6.273643757749448e-06, "epoch": 3.834008097165992, "percentage": 76.68, "elapsed_time": "6:14:26", "remaining_time": "1:53:52"}
1195
+ {"current_steps": 948, "total_steps": 1235, "loss": 0.4124, "lr": 6.2325666311420856e-06, "epoch": 3.8380566801619436, "percentage": 76.76, "elapsed_time": "6:14:49", "remaining_time": "1:53:28"}
1196
+ {"current_steps": 949, "total_steps": 1235, "loss": 0.4002, "lr": 6.1915995885650675e-06, "epoch": 3.8421052631578947, "percentage": 76.84, "elapsed_time": "6:15:13", "remaining_time": "1:53:04"}
1197
+ {"current_steps": 950, "total_steps": 1235, "loss": 0.4116, "lr": 6.150742957589784e-06, "epoch": 3.8461538461538463, "percentage": 76.92, "elapsed_time": "6:15:37", "remaining_time": "1:52:41"}
1198
+ {"current_steps": 951, "total_steps": 1235, "loss": 0.4161, "lr": 6.109997064904774e-06, "epoch": 3.850202429149798, "percentage": 77.0, "elapsed_time": "6:16:00", "remaining_time": "1:52:17"}
1199
+ {"current_steps": 952, "total_steps": 1235, "loss": 0.4237, "lr": 6.069362236313092e-06, "epoch": 3.854251012145749, "percentage": 77.09, "elapsed_time": "6:16:24", "remaining_time": "1:51:53"}
1200
+ {"current_steps": 953, "total_steps": 1235, "loss": 0.4157, "lr": 6.0288387967297565e-06, "epoch": 3.8582995951417005, "percentage": 77.17, "elapsed_time": "6:16:47", "remaining_time": "1:51:29"}
1201
+ {"current_steps": 954, "total_steps": 1235, "loss": 0.4132, "lr": 5.988427070179108e-06, "epoch": 3.862348178137652, "percentage": 77.25, "elapsed_time": "6:17:10", "remaining_time": "1:51:05"}
1202
+ {"current_steps": 955, "total_steps": 1235, "loss": 0.3971, "lr": 5.948127379792234e-06, "epoch": 3.866396761133603, "percentage": 77.33, "elapsed_time": "6:17:33", "remaining_time": "1:50:41"}
1203
+ {"current_steps": 956, "total_steps": 1235, "loss": 0.4254, "lr": 5.90794004780439e-06, "epoch": 3.8704453441295548, "percentage": 77.41, "elapsed_time": "6:17:57", "remaining_time": "1:50:18"}
1204
+ {"current_steps": 957, "total_steps": 1235, "loss": 0.4092, "lr": 5.867865395552405e-06, "epoch": 3.8744939271255063, "percentage": 77.49, "elapsed_time": "6:18:20", "remaining_time": "1:49:54"}
1205
+ {"current_steps": 958, "total_steps": 1235, "loss": 0.4109, "lr": 5.8279037434721364e-06, "epoch": 3.8785425101214575, "percentage": 77.57, "elapsed_time": "6:18:44", "remaining_time": "1:49:30"}
1206
+ {"current_steps": 959, "total_steps": 1235, "loss": 0.4087, "lr": 5.788055411095892e-06, "epoch": 3.882591093117409, "percentage": 77.65, "elapsed_time": "6:19:07", "remaining_time": "1:49:06"}
1207
+ {"current_steps": 960, "total_steps": 1235, "loss": 0.4031, "lr": 5.7483207170498625e-06, "epoch": 3.8866396761133606, "percentage": 77.73, "elapsed_time": "6:19:30", "remaining_time": "1:48:42"}
1208
+ {"current_steps": 961, "total_steps": 1235, "loss": 0.4011, "lr": 5.708699979051613e-06, "epoch": 3.8906882591093117, "percentage": 77.81, "elapsed_time": "6:19:54", "remaining_time": "1:48:19"}
1209
+ {"current_steps": 962, "total_steps": 1235, "loss": 0.4111, "lr": 5.66919351390751e-06, "epoch": 3.8947368421052633, "percentage": 77.89, "elapsed_time": "6:20:17", "remaining_time": "1:47:55"}
1210
+ {"current_steps": 963, "total_steps": 1235, "loss": 0.3955, "lr": 5.629801637510188e-06, "epoch": 3.898785425101215, "percentage": 77.98, "elapsed_time": "6:20:40", "remaining_time": "1:47:31"}
1211
+ {"current_steps": 964, "total_steps": 1235, "loss": 0.4066, "lr": 5.590524664836043e-06, "epoch": 3.902834008097166, "percentage": 78.06, "elapsed_time": "6:21:02", "remaining_time": "1:47:07"}
1212
+ {"current_steps": 965, "total_steps": 1235, "loss": 0.4012, "lr": 5.551362909942708e-06, "epoch": 3.9068825910931175, "percentage": 78.14, "elapsed_time": "6:21:26", "remaining_time": "1:46:43"}
1213
+ {"current_steps": 966, "total_steps": 1235, "loss": 0.4002, "lr": 5.51231668596653e-06, "epoch": 3.910931174089069, "percentage": 78.22, "elapsed_time": "6:21:49", "remaining_time": "1:46:19"}
1214
+ {"current_steps": 967, "total_steps": 1235, "loss": 0.4172, "lr": 5.47338630512007e-06, "epoch": 3.91497975708502, "percentage": 78.3, "elapsed_time": "6:22:12", "remaining_time": "1:45:55"}
1215
+ {"current_steps": 968, "total_steps": 1235, "loss": 0.4177, "lr": 5.434572078689617e-06, "epoch": 3.919028340080972, "percentage": 78.38, "elapsed_time": "6:22:36", "remaining_time": "1:45:31"}
1216
+ {"current_steps": 969, "total_steps": 1235, "loss": 0.4206, "lr": 5.395874317032694e-06, "epoch": 3.9230769230769234, "percentage": 78.46, "elapsed_time": "6:22:59", "remaining_time": "1:45:08"}
1217
+ {"current_steps": 970, "total_steps": 1235, "loss": 0.4152, "lr": 5.357293329575573e-06, "epoch": 3.9271255060728745, "percentage": 78.54, "elapsed_time": "6:23:22", "remaining_time": "1:44:44"}
1218
+ {"current_steps": 971, "total_steps": 1235, "loss": 0.4095, "lr": 5.318829424810797e-06, "epoch": 3.931174089068826, "percentage": 78.62, "elapsed_time": "6:23:45", "remaining_time": "1:44:20"}
1219
+ {"current_steps": 972, "total_steps": 1235, "loss": 0.4188, "lr": 5.280482910294728e-06, "epoch": 3.9352226720647776, "percentage": 78.7, "elapsed_time": "6:24:09", "remaining_time": "1:43:56"}
1220
+ {"current_steps": 973, "total_steps": 1235, "loss": 0.414, "lr": 5.242254092645078e-06, "epoch": 3.9392712550607287, "percentage": 78.79, "elapsed_time": "6:24:33", "remaining_time": "1:43:32"}
1221
+ {"current_steps": 974, "total_steps": 1235, "loss": 0.4173, "lr": 5.2041432775384445e-06, "epoch": 3.9433198380566803, "percentage": 78.87, "elapsed_time": "6:24:56", "remaining_time": "1:43:09"}
1222
+ {"current_steps": 975, "total_steps": 1235, "loss": 0.4269, "lr": 5.166150769707892e-06, "epoch": 3.9473684210526314, "percentage": 78.95, "elapsed_time": "6:25:20", "remaining_time": "1:42:45"}
1223
+ {"current_steps": 976, "total_steps": 1235, "loss": 0.4155, "lr": 5.128276872940503e-06, "epoch": 3.951417004048583, "percentage": 79.03, "elapsed_time": "6:25:44", "remaining_time": "1:42:21"}
1224
+ {"current_steps": 977, "total_steps": 1235, "loss": 0.4135, "lr": 5.090521890074953e-06, "epoch": 3.9554655870445345, "percentage": 79.11, "elapsed_time": "6:26:07", "remaining_time": "1:41:57"}
1225
+ {"current_steps": 978, "total_steps": 1235, "loss": 0.4295, "lr": 5.0528861229990675e-06, "epoch": 3.9595141700404857, "percentage": 79.19, "elapsed_time": "6:26:30", "remaining_time": "1:41:33"}
1226
+ {"current_steps": 979, "total_steps": 1235, "loss": 0.4227, "lr": 5.015369872647442e-06, "epoch": 3.9635627530364372, "percentage": 79.27, "elapsed_time": "6:26:53", "remaining_time": "1:41:10"}
1227
+ {"current_steps": 980, "total_steps": 1235, "loss": 0.423, "lr": 4.9779734389990195e-06, "epoch": 3.967611336032389, "percentage": 79.35, "elapsed_time": "6:27:17", "remaining_time": "1:40:46"}
1228
+ {"current_steps": 981, "total_steps": 1235, "loss": 0.4023, "lr": 4.940697121074675e-06, "epoch": 3.97165991902834, "percentage": 79.43, "elapsed_time": "6:27:40", "remaining_time": "1:40:22"}
1229
+ {"current_steps": 982, "total_steps": 1235, "loss": 0.4154, "lr": 4.903541216934864e-06, "epoch": 3.9757085020242915, "percentage": 79.51, "elapsed_time": "6:28:04", "remaining_time": "1:39:58"}
1230
+ {"current_steps": 983, "total_steps": 1235, "loss": 0.4228, "lr": 4.8665060236772e-06, "epoch": 3.979757085020243, "percentage": 79.6, "elapsed_time": "6:28:26", "remaining_time": "1:39:34"}
1231
+ {"current_steps": 984, "total_steps": 1235, "loss": 0.4116, "lr": 4.829591837434102e-06, "epoch": 3.983805668016194, "percentage": 79.68, "elapsed_time": "6:28:50", "remaining_time": "1:39:11"}
1232
+ {"current_steps": 985, "total_steps": 1235, "loss": 0.4119, "lr": 4.792798953370424e-06, "epoch": 3.9878542510121457, "percentage": 79.76, "elapsed_time": "6:29:14", "remaining_time": "1:38:47"}
1233
+ {"current_steps": 986, "total_steps": 1235, "loss": 0.423, "lr": 4.756127665681083e-06, "epoch": 3.9919028340080973, "percentage": 79.84, "elapsed_time": "6:29:37", "remaining_time": "1:38:23"}
1234
+ {"current_steps": 987, "total_steps": 1235, "loss": 0.4175, "lr": 4.719578267588725e-06, "epoch": 3.9959514170040484, "percentage": 79.92, "elapsed_time": "6:30:01", "remaining_time": "1:38:00"}
1235
+ {"current_steps": 988, "total_steps": 1235, "loss": 0.4099, "lr": 4.6831510513413525e-06, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "6:30:24", "remaining_time": "1:37:36"}
1236
+ {"current_steps": 989, "total_steps": 1235, "loss": 0.3614, "lr": 4.6468463082100176e-06, "epoch": 4.004048582995951, "percentage": 80.08, "elapsed_time": "6:32:31", "remaining_time": "1:37:38"}
1237
+ {"current_steps": 990, "total_steps": 1235, "loss": 0.3813, "lr": 4.610664328486485e-06, "epoch": 4.008097165991903, "percentage": 80.16, "elapsed_time": "6:32:55", "remaining_time": "1:37:14"}
1238
+ {"current_steps": 991, "total_steps": 1235, "loss": 0.3771, "lr": 4.5746054014809e-06, "epoch": 4.012145748987854, "percentage": 80.24, "elapsed_time": "6:33:18", "remaining_time": "1:36:50"}
1239
+ {"current_steps": 992, "total_steps": 1235, "loss": 0.3705, "lr": 4.5386698155194766e-06, "epoch": 4.016194331983805, "percentage": 80.32, "elapsed_time": "6:33:41", "remaining_time": "1:36:26"}
1240
+ {"current_steps": 993, "total_steps": 1235, "loss": 0.3682, "lr": 4.502857857942204e-06, "epoch": 4.020242914979757, "percentage": 80.4, "elapsed_time": "6:34:05", "remaining_time": "1:36:02"}
1241
+ {"current_steps": 994, "total_steps": 1235, "loss": 0.3735, "lr": 4.467169815100549e-06, "epoch": 4.0242914979757085, "percentage": 80.49, "elapsed_time": "6:34:28", "remaining_time": "1:35:38"}
1242
+ {"current_steps": 995, "total_steps": 1235, "loss": 0.3625, "lr": 4.431605972355137e-06, "epoch": 4.02834008097166, "percentage": 80.57, "elapsed_time": "6:34:52", "remaining_time": "1:35:14"}