gsmyrnis commited on
Commit
ca4156a
·
verified ·
1 Parent(s): 1dc7c54

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 sha256:2b5459408d5e85b7580509c55b20ee075e07e6053a6e59f47c15b88ee5454b7a
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3eef17533e5c21fe71dc778a07994ce245cdecc50aa32c585dca3210573c9bf
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2479eeb54182b50f2771bbe1a62ec338c6920bcd73c0a0c491f8f940f31b82d1
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:706a234b827932cae82085f037ce86026f3a37bef74361c1eba19c617b69ae01
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:968ec8afe40f14b512d8d9226e8ea532440c351aecda64fec65dd31942dc72e0
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd44816225b7fc614374ea6164c6080e63f2cdc1c5eb2a02c39e739b948da86e
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:d846c3640e23121bf67922807fa02a517bfed26161231cfcd9b9876dd580660f
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14ce98103bd7ce3fe1b47a939cddb293aa59f6d0d3b4b4d18a1d40db21cbd4ca
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -747,3 +747,250 @@
747
  {"current_steps": 747, "total_steps": 1235, "loss": 0.2797, "lr": 1.620572014799777e-05, "epoch": 3.0242914979757085, "percentage": 60.49, "elapsed_time": "3:53:18", "remaining_time": "2:32:24"}
748
  {"current_steps": 748, "total_steps": 1235, "loss": 0.3104, "lr": 1.6150208128905857e-05, "epoch": 3.02834008097166, "percentage": 60.57, "elapsed_time": "3:53:38", "remaining_time": "2:32:07"}
749
  {"current_steps": 749, "total_steps": 1235, "loss": 0.2962, "lr": 1.6094726892647147e-05, "epoch": 3.032388663967611, "percentage": 60.65, "elapsed_time": "3:53:58", "remaining_time": "2:31:49"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
747
  {"current_steps": 747, "total_steps": 1235, "loss": 0.2797, "lr": 1.620572014799777e-05, "epoch": 3.0242914979757085, "percentage": 60.49, "elapsed_time": "3:53:18", "remaining_time": "2:32:24"}
748
  {"current_steps": 748, "total_steps": 1235, "loss": 0.3104, "lr": 1.6150208128905857e-05, "epoch": 3.02834008097166, "percentage": 60.57, "elapsed_time": "3:53:38", "remaining_time": "2:32:07"}
749
  {"current_steps": 749, "total_steps": 1235, "loss": 0.2962, "lr": 1.6094726892647147e-05, "epoch": 3.032388663967611, "percentage": 60.65, "elapsed_time": "3:53:58", "remaining_time": "2:31:49"}
750
+ {"current_steps": 750, "total_steps": 1235, "loss": 0.2771, "lr": 1.6039276882848135e-05, "epoch": 3.0364372469635628, "percentage": 60.73, "elapsed_time": "3:54:17", "remaining_time": "2:31:30"}
751
+ {"current_steps": 751, "total_steps": 1235, "loss": 0.294, "lr": 1.5983858542885635e-05, "epoch": 3.0404858299595143, "percentage": 60.81, "elapsed_time": "3:54:39", "remaining_time": "2:31:13"}
752
+ {"current_steps": 752, "total_steps": 1235, "loss": 0.2773, "lr": 1.5928472315883203e-05, "epoch": 3.0445344129554655, "percentage": 60.89, "elapsed_time": "3:54:58", "remaining_time": "2:30:55"}
753
+ {"current_steps": 753, "total_steps": 1235, "loss": 0.2919, "lr": 1.5873118644707633e-05, "epoch": 3.048582995951417, "percentage": 60.97, "elapsed_time": "3:55:16", "remaining_time": "2:30:36"}
754
+ {"current_steps": 754, "total_steps": 1235, "loss": 0.2952, "lr": 1.5817797971965413e-05, "epoch": 3.0526315789473686, "percentage": 61.05, "elapsed_time": "3:55:32", "remaining_time": "2:30:15"}
755
+ {"current_steps": 755, "total_steps": 1235, "loss": 0.2924, "lr": 1.576251073999917e-05, "epoch": 3.0566801619433197, "percentage": 61.13, "elapsed_time": "3:55:49", "remaining_time": "2:29:55"}
756
+ {"current_steps": 756, "total_steps": 1235, "loss": 0.2986, "lr": 1.5707257390884126e-05, "epoch": 3.0607287449392713, "percentage": 61.21, "elapsed_time": "3:56:08", "remaining_time": "2:29:37"}
757
+ {"current_steps": 757, "total_steps": 1235, "loss": 0.2782, "lr": 1.5652038366424595e-05, "epoch": 3.064777327935223, "percentage": 61.3, "elapsed_time": "3:56:28", "remaining_time": "2:29:19"}
758
+ {"current_steps": 758, "total_steps": 1235, "loss": 0.2868, "lr": 1.5596854108150424e-05, "epoch": 3.068825910931174, "percentage": 61.38, "elapsed_time": "3:56:46", "remaining_time": "2:28:59"}
759
+ {"current_steps": 759, "total_steps": 1235, "loss": 0.2825, "lr": 1.5541705057313476e-05, "epoch": 3.0728744939271255, "percentage": 61.46, "elapsed_time": "3:57:06", "remaining_time": "2:28:41"}
760
+ {"current_steps": 760, "total_steps": 1235, "loss": 0.2897, "lr": 1.5486591654884086e-05, "epoch": 3.076923076923077, "percentage": 61.54, "elapsed_time": "3:57:21", "remaining_time": "2:28:20"}
761
+ {"current_steps": 761, "total_steps": 1235, "loss": 0.2827, "lr": 1.543151434154755e-05, "epoch": 3.080971659919028, "percentage": 61.62, "elapsed_time": "3:57:42", "remaining_time": "2:28:03"}
762
+ {"current_steps": 762, "total_steps": 1235, "loss": 0.2778, "lr": 1.5376473557700615e-05, "epoch": 3.08502024291498, "percentage": 61.7, "elapsed_time": "3:58:00", "remaining_time": "2:27:44"}
763
+ {"current_steps": 763, "total_steps": 1235, "loss": 0.2799, "lr": 1.5321469743447893e-05, "epoch": 3.0890688259109313, "percentage": 61.78, "elapsed_time": "3:58:17", "remaining_time": "2:27:24"}
764
+ {"current_steps": 764, "total_steps": 1235, "loss": 0.2771, "lr": 1.5266503338598434e-05, "epoch": 3.0931174089068825, "percentage": 61.86, "elapsed_time": "3:58:33", "remaining_time": "2:27:03"}
765
+ {"current_steps": 765, "total_steps": 1235, "loss": 0.279, "lr": 1.5211574782662149e-05, "epoch": 3.097165991902834, "percentage": 61.94, "elapsed_time": "3:58:50", "remaining_time": "2:26:44"}
766
+ {"current_steps": 766, "total_steps": 1235, "loss": 0.2928, "lr": 1.5156684514846307e-05, "epoch": 3.1012145748987856, "percentage": 62.02, "elapsed_time": "3:59:06", "remaining_time": "2:26:23"}
767
+ {"current_steps": 767, "total_steps": 1235, "loss": 0.2965, "lr": 1.5101832974052012e-05, "epoch": 3.1052631578947367, "percentage": 62.11, "elapsed_time": "3:59:23", "remaining_time": "2:26:04"}
768
+ {"current_steps": 768, "total_steps": 1235, "loss": 0.2811, "lr": 1.5047020598870737e-05, "epoch": 3.1093117408906883, "percentage": 62.19, "elapsed_time": "3:59:41", "remaining_time": "2:25:45"}
769
+ {"current_steps": 769, "total_steps": 1235, "loss": 0.3001, "lr": 1.4992247827580778e-05, "epoch": 3.11336032388664, "percentage": 62.27, "elapsed_time": "4:00:01", "remaining_time": "2:25:26"}
770
+ {"current_steps": 770, "total_steps": 1235, "loss": 0.3055, "lr": 1.493751509814374e-05, "epoch": 3.117408906882591, "percentage": 62.35, "elapsed_time": "4:00:20", "remaining_time": "2:25:08"}
771
+ {"current_steps": 771, "total_steps": 1235, "loss": 0.2853, "lr": 1.4882822848201073e-05, "epoch": 3.1214574898785425, "percentage": 62.43, "elapsed_time": "4:00:37", "remaining_time": "2:24:48"}
772
+ {"current_steps": 772, "total_steps": 1235, "loss": 0.2797, "lr": 1.4828171515070553e-05, "epoch": 3.125506072874494, "percentage": 62.51, "elapsed_time": "4:00:59", "remaining_time": "2:24:31"}
773
+ {"current_steps": 773, "total_steps": 1235, "loss": 0.2876, "lr": 1.4773561535742793e-05, "epoch": 3.1295546558704452, "percentage": 62.59, "elapsed_time": "4:01:15", "remaining_time": "2:24:11"}
774
+ {"current_steps": 774, "total_steps": 1235, "loss": 0.2812, "lr": 1.4718993346877715e-05, "epoch": 3.133603238866397, "percentage": 62.67, "elapsed_time": "4:01:32", "remaining_time": "2:23:51"}
775
+ {"current_steps": 775, "total_steps": 1235, "loss": 0.2629, "lr": 1.466446738480111e-05, "epoch": 3.1376518218623484, "percentage": 62.75, "elapsed_time": "4:01:50", "remaining_time": "2:23:32"}
776
+ {"current_steps": 776, "total_steps": 1235, "loss": 0.2934, "lr": 1.460998408550112e-05, "epoch": 3.1417004048582995, "percentage": 62.83, "elapsed_time": "4:02:11", "remaining_time": "2:23:15"}
777
+ {"current_steps": 777, "total_steps": 1235, "loss": 0.2764, "lr": 1.4555543884624751e-05, "epoch": 3.145748987854251, "percentage": 62.91, "elapsed_time": "4:02:26", "remaining_time": "2:22:54"}
778
+ {"current_steps": 778, "total_steps": 1235, "loss": 0.2834, "lr": 1.4501147217474402e-05, "epoch": 3.1497975708502026, "percentage": 63.0, "elapsed_time": "4:02:43", "remaining_time": "2:22:34"}
779
+ {"current_steps": 779, "total_steps": 1235, "loss": 0.2967, "lr": 1.444679451900437e-05, "epoch": 3.1538461538461537, "percentage": 63.08, "elapsed_time": "4:03:01", "remaining_time": "2:22:15"}
780
+ {"current_steps": 780, "total_steps": 1235, "loss": 0.2928, "lr": 1.4392486223817397e-05, "epoch": 3.1578947368421053, "percentage": 63.16, "elapsed_time": "4:03:18", "remaining_time": "2:21:55"}
781
+ {"current_steps": 781, "total_steps": 1235, "loss": 0.3067, "lr": 1.4338222766161143e-05, "epoch": 3.161943319838057, "percentage": 63.24, "elapsed_time": "4:03:40", "remaining_time": "2:21:39"}
782
+ {"current_steps": 782, "total_steps": 1235, "loss": 0.2978, "lr": 1.4284004579924777e-05, "epoch": 3.165991902834008, "percentage": 63.32, "elapsed_time": "4:04:02", "remaining_time": "2:21:21"}
783
+ {"current_steps": 783, "total_steps": 1235, "loss": 0.2873, "lr": 1.4229832098635479e-05, "epoch": 3.1700404858299596, "percentage": 63.4, "elapsed_time": "4:04:22", "remaining_time": "2:21:04"}
784
+ {"current_steps": 784, "total_steps": 1235, "loss": 0.2903, "lr": 1.4175705755454963e-05, "epoch": 3.174089068825911, "percentage": 63.48, "elapsed_time": "4:04:39", "remaining_time": "2:20:44"}
785
+ {"current_steps": 785, "total_steps": 1235, "loss": 0.2791, "lr": 1.412162598317602e-05, "epoch": 3.1781376518218623, "percentage": 63.56, "elapsed_time": "4:04:56", "remaining_time": "2:20:24"}
786
+ {"current_steps": 786, "total_steps": 1235, "loss": 0.2953, "lr": 1.406759321421907e-05, "epoch": 3.182186234817814, "percentage": 63.64, "elapsed_time": "4:05:17", "remaining_time": "2:20:07"}
787
+ {"current_steps": 787, "total_steps": 1235, "loss": 0.3047, "lr": 1.401360788062871e-05, "epoch": 3.1862348178137654, "percentage": 63.72, "elapsed_time": "4:05:38", "remaining_time": "2:19:49"}
788
+ {"current_steps": 788, "total_steps": 1235, "loss": 0.2887, "lr": 1.3959670414070204e-05, "epoch": 3.1902834008097165, "percentage": 63.81, "elapsed_time": "4:05:59", "remaining_time": "2:19:32"}
789
+ {"current_steps": 789, "total_steps": 1235, "loss": 0.2724, "lr": 1.3905781245826108e-05, "epoch": 3.194331983805668, "percentage": 63.89, "elapsed_time": "4:06:13", "remaining_time": "2:19:10"}
790
+ {"current_steps": 790, "total_steps": 1235, "loss": 0.2794, "lr": 1.3851940806792778e-05, "epoch": 3.1983805668016196, "percentage": 63.97, "elapsed_time": "4:06:35", "remaining_time": "2:18:53"}
791
+ {"current_steps": 791, "total_steps": 1235, "loss": 0.2788, "lr": 1.379814952747693e-05, "epoch": 3.2024291497975708, "percentage": 64.05, "elapsed_time": "4:06:52", "remaining_time": "2:18:34"}
792
+ {"current_steps": 792, "total_steps": 1235, "loss": 0.2924, "lr": 1.3744407837992193e-05, "epoch": 3.2064777327935223, "percentage": 64.13, "elapsed_time": "4:07:08", "remaining_time": "2:18:14"}
793
+ {"current_steps": 793, "total_steps": 1235, "loss": 0.2926, "lr": 1.3690716168055692e-05, "epoch": 3.2105263157894735, "percentage": 64.21, "elapsed_time": "4:07:26", "remaining_time": "2:17:54"}
794
+ {"current_steps": 794, "total_steps": 1235, "loss": 0.2799, "lr": 1.363707494698459e-05, "epoch": 3.214574898785425, "percentage": 64.29, "elapsed_time": "4:07:42", "remaining_time": "2:17:34"}
795
+ {"current_steps": 795, "total_steps": 1235, "loss": 0.287, "lr": 1.358348460369265e-05, "epoch": 3.2186234817813766, "percentage": 64.37, "elapsed_time": "4:08:04", "remaining_time": "2:17:17"}
796
+ {"current_steps": 796, "total_steps": 1235, "loss": 0.2839, "lr": 1.352994556668684e-05, "epoch": 3.2226720647773277, "percentage": 64.45, "elapsed_time": "4:08:21", "remaining_time": "2:16:58"}
797
+ {"current_steps": 797, "total_steps": 1235, "loss": 0.2893, "lr": 1.3476458264063865e-05, "epoch": 3.2267206477732793, "percentage": 64.53, "elapsed_time": "4:08:41", "remaining_time": "2:16:40"}
798
+ {"current_steps": 798, "total_steps": 1235, "loss": 0.2814, "lr": 1.342302312350678e-05, "epoch": 3.230769230769231, "percentage": 64.62, "elapsed_time": "4:09:00", "remaining_time": "2:16:21"}
799
+ {"current_steps": 799, "total_steps": 1235, "loss": 0.2752, "lr": 1.3369640572281537e-05, "epoch": 3.234817813765182, "percentage": 64.7, "elapsed_time": "4:09:20", "remaining_time": "2:16:03"}
800
+ {"current_steps": 800, "total_steps": 1235, "loss": 0.2735, "lr": 1.3316311037233596e-05, "epoch": 3.2388663967611335, "percentage": 64.78, "elapsed_time": "4:09:36", "remaining_time": "2:15:43"}
801
+ {"current_steps": 801, "total_steps": 1235, "loss": 0.2895, "lr": 1.326303494478451e-05, "epoch": 3.242914979757085, "percentage": 64.86, "elapsed_time": "4:09:54", "remaining_time": "2:15:24"}
802
+ {"current_steps": 802, "total_steps": 1235, "loss": 0.2873, "lr": 1.3209812720928472e-05, "epoch": 3.246963562753036, "percentage": 64.94, "elapsed_time": "4:10:12", "remaining_time": "2:15:05"}
803
+ {"current_steps": 803, "total_steps": 1235, "loss": 0.2829, "lr": 1.315664479122898e-05, "epoch": 3.251012145748988, "percentage": 65.02, "elapsed_time": "4:10:28", "remaining_time": "2:14:44"}
804
+ {"current_steps": 804, "total_steps": 1235, "loss": 0.2986, "lr": 1.3103531580815378e-05, "epoch": 3.2550607287449393, "percentage": 65.1, "elapsed_time": "4:10:43", "remaining_time": "2:14:24"}
805
+ {"current_steps": 805, "total_steps": 1235, "loss": 0.2733, "lr": 1.3050473514379488e-05, "epoch": 3.2591093117408905, "percentage": 65.18, "elapsed_time": "4:11:00", "remaining_time": "2:14:04"}
806
+ {"current_steps": 806, "total_steps": 1235, "loss": 0.2875, "lr": 1.2997471016172188e-05, "epoch": 3.263157894736842, "percentage": 65.26, "elapsed_time": "4:11:19", "remaining_time": "2:13:45"}
807
+ {"current_steps": 807, "total_steps": 1235, "loss": 0.3072, "lr": 1.2944524510000042e-05, "epoch": 3.2672064777327936, "percentage": 65.34, "elapsed_time": "4:11:36", "remaining_time": "2:13:26"}
808
+ {"current_steps": 808, "total_steps": 1235, "loss": 0.2744, "lr": 1.2891634419221908e-05, "epoch": 3.2712550607287447, "percentage": 65.43, "elapsed_time": "4:11:54", "remaining_time": "2:13:07"}
809
+ {"current_steps": 809, "total_steps": 1235, "loss": 0.3087, "lr": 1.2838801166745545e-05, "epoch": 3.2753036437246963, "percentage": 65.51, "elapsed_time": "4:12:13", "remaining_time": "2:12:48"}
810
+ {"current_steps": 810, "total_steps": 1235, "loss": 0.2946, "lr": 1.2786025175024216e-05, "epoch": 3.279352226720648, "percentage": 65.59, "elapsed_time": "4:12:30", "remaining_time": "2:12:29"}
811
+ {"current_steps": 811, "total_steps": 1235, "loss": 0.2803, "lr": 1.2733306866053357e-05, "epoch": 3.283400809716599, "percentage": 65.67, "elapsed_time": "4:12:50", "remaining_time": "2:12:11"}
812
+ {"current_steps": 812, "total_steps": 1235, "loss": 0.2763, "lr": 1.2680646661367163e-05, "epoch": 3.2874493927125505, "percentage": 65.75, "elapsed_time": "4:13:05", "remaining_time": "2:11:50"}
813
+ {"current_steps": 813, "total_steps": 1235, "loss": 0.2862, "lr": 1.2628044982035219e-05, "epoch": 3.291497975708502, "percentage": 65.83, "elapsed_time": "4:13:23", "remaining_time": "2:11:31"}
814
+ {"current_steps": 814, "total_steps": 1235, "loss": 0.2897, "lr": 1.2575502248659155e-05, "epoch": 3.2955465587044532, "percentage": 65.91, "elapsed_time": "4:13:42", "remaining_time": "2:11:13"}
815
+ {"current_steps": 815, "total_steps": 1235, "loss": 0.2836, "lr": 1.2523018881369269e-05, "epoch": 3.299595141700405, "percentage": 65.99, "elapsed_time": "4:13:57", "remaining_time": "2:10:52"}
816
+ {"current_steps": 816, "total_steps": 1235, "loss": 0.2915, "lr": 1.2470595299821176e-05, "epoch": 3.3036437246963564, "percentage": 66.07, "elapsed_time": "4:14:16", "remaining_time": "2:10:34"}
817
+ {"current_steps": 817, "total_steps": 1235, "loss": 0.3103, "lr": 1.2418231923192416e-05, "epoch": 3.3076923076923075, "percentage": 66.15, "elapsed_time": "4:14:35", "remaining_time": "2:10:15"}
818
+ {"current_steps": 818, "total_steps": 1235, "loss": 0.3016, "lr": 1.2365929170179165e-05, "epoch": 3.311740890688259, "percentage": 66.23, "elapsed_time": "4:14:54", "remaining_time": "2:09:56"}
819
+ {"current_steps": 819, "total_steps": 1235, "loss": 0.2944, "lr": 1.2313687458992848e-05, "epoch": 3.3157894736842106, "percentage": 66.32, "elapsed_time": "4:15:15", "remaining_time": "2:09:39"}
820
+ {"current_steps": 820, "total_steps": 1235, "loss": 0.2742, "lr": 1.2261507207356785e-05, "epoch": 3.3198380566801617, "percentage": 66.4, "elapsed_time": "4:15:30", "remaining_time": "2:09:18"}
821
+ {"current_steps": 821, "total_steps": 1235, "loss": 0.2847, "lr": 1.220938883250288e-05, "epoch": 3.3238866396761133, "percentage": 66.48, "elapsed_time": "4:15:46", "remaining_time": "2:08:58"}
822
+ {"current_steps": 822, "total_steps": 1235, "loss": 0.281, "lr": 1.215733275116827e-05, "epoch": 3.327935222672065, "percentage": 66.56, "elapsed_time": "4:16:00", "remaining_time": "2:08:37"}
823
+ {"current_steps": 823, "total_steps": 1235, "loss": 0.2923, "lr": 1.2105339379592005e-05, "epoch": 3.331983805668016, "percentage": 66.64, "elapsed_time": "4:16:21", "remaining_time": "2:08:19"}
824
+ {"current_steps": 824, "total_steps": 1235, "loss": 0.2925, "lr": 1.2053409133511681e-05, "epoch": 3.3360323886639676, "percentage": 66.72, "elapsed_time": "4:16:43", "remaining_time": "2:08:03"}
825
+ {"current_steps": 825, "total_steps": 1235, "loss": 0.3007, "lr": 1.2001542428160173e-05, "epoch": 3.340080971659919, "percentage": 66.8, "elapsed_time": "4:17:00", "remaining_time": "2:07:43"}
826
+ {"current_steps": 826, "total_steps": 1235, "loss": 0.2988, "lr": 1.1949739678262278e-05, "epoch": 3.3441295546558703, "percentage": 66.88, "elapsed_time": "4:17:19", "remaining_time": "2:07:24"}
827
+ {"current_steps": 827, "total_steps": 1235, "loss": 0.2897, "lr": 1.189800129803139e-05, "epoch": 3.348178137651822, "percentage": 66.96, "elapsed_time": "4:17:38", "remaining_time": "2:07:06"}
828
+ {"current_steps": 828, "total_steps": 1235, "loss": 0.2897, "lr": 1.1846327701166228e-05, "epoch": 3.3522267206477734, "percentage": 67.04, "elapsed_time": "4:18:02", "remaining_time": "2:06:50"}
829
+ {"current_steps": 829, "total_steps": 1235, "loss": 0.2901, "lr": 1.1794719300847493e-05, "epoch": 3.3562753036437245, "percentage": 67.13, "elapsed_time": "4:18:20", "remaining_time": "2:06:31"}
830
+ {"current_steps": 830, "total_steps": 1235, "loss": 0.2876, "lr": 1.1743176509734582e-05, "epoch": 3.360323886639676, "percentage": 67.21, "elapsed_time": "4:18:40", "remaining_time": "2:06:13"}
831
+ {"current_steps": 831, "total_steps": 1235, "loss": 0.2894, "lr": 1.1691699739962275e-05, "epoch": 3.3643724696356276, "percentage": 67.29, "elapsed_time": "4:19:00", "remaining_time": "2:05:55"}
832
+ {"current_steps": 832, "total_steps": 1235, "loss": 0.2903, "lr": 1.1640289403137456e-05, "epoch": 3.3684210526315788, "percentage": 67.37, "elapsed_time": "4:19:18", "remaining_time": "2:05:36"}
833
+ {"current_steps": 833, "total_steps": 1235, "loss": 0.303, "lr": 1.1588945910335802e-05, "epoch": 3.3724696356275303, "percentage": 67.45, "elapsed_time": "4:19:35", "remaining_time": "2:05:16"}
834
+ {"current_steps": 834, "total_steps": 1235, "loss": 0.2855, "lr": 1.1537669672098517e-05, "epoch": 3.376518218623482, "percentage": 67.53, "elapsed_time": "4:19:53", "remaining_time": "2:04:57"}
835
+ {"current_steps": 835, "total_steps": 1235, "loss": 0.3068, "lr": 1.1486461098429036e-05, "epoch": 3.380566801619433, "percentage": 67.61, "elapsed_time": "4:20:12", "remaining_time": "2:04:39"}
836
+ {"current_steps": 836, "total_steps": 1235, "loss": 0.302, "lr": 1.1435320598789747e-05, "epoch": 3.3846153846153846, "percentage": 67.69, "elapsed_time": "4:20:31", "remaining_time": "2:04:20"}
837
+ {"current_steps": 837, "total_steps": 1235, "loss": 0.2892, "lr": 1.1384248582098736e-05, "epoch": 3.388663967611336, "percentage": 67.77, "elapsed_time": "4:20:48", "remaining_time": "2:04:01"}
838
+ {"current_steps": 838, "total_steps": 1235, "loss": 0.2889, "lr": 1.1333245456726467e-05, "epoch": 3.3927125506072873, "percentage": 67.85, "elapsed_time": "4:21:10", "remaining_time": "2:03:43"}
839
+ {"current_steps": 839, "total_steps": 1235, "loss": 0.2901, "lr": 1.128231163049258e-05, "epoch": 3.396761133603239, "percentage": 67.94, "elapsed_time": "4:21:28", "remaining_time": "2:03:24"}
840
+ {"current_steps": 840, "total_steps": 1235, "loss": 0.303, "lr": 1.123144751066259e-05, "epoch": 3.4008097165991904, "percentage": 68.02, "elapsed_time": "4:21:49", "remaining_time": "2:03:07"}
841
+ {"current_steps": 841, "total_steps": 1235, "loss": 0.2999, "lr": 1.1180653503944657e-05, "epoch": 3.4048582995951415, "percentage": 68.1, "elapsed_time": "4:22:06", "remaining_time": "2:02:47"}
842
+ {"current_steps": 842, "total_steps": 1235, "loss": 0.2924, "lr": 1.1129930016486287e-05, "epoch": 3.408906882591093, "percentage": 68.18, "elapsed_time": "4:22:22", "remaining_time": "2:02:27"}
843
+ {"current_steps": 843, "total_steps": 1235, "loss": 0.2802, "lr": 1.107927745387114e-05, "epoch": 3.4129554655870447, "percentage": 68.26, "elapsed_time": "4:22:38", "remaining_time": "2:02:07"}
844
+ {"current_steps": 844, "total_steps": 1235, "loss": 0.3031, "lr": 1.1028696221115766e-05, "epoch": 3.417004048582996, "percentage": 68.34, "elapsed_time": "4:23:00", "remaining_time": "2:01:50"}
845
+ {"current_steps": 845, "total_steps": 1235, "loss": 0.295, "lr": 1.0978186722666341e-05, "epoch": 3.4210526315789473, "percentage": 68.42, "elapsed_time": "4:23:20", "remaining_time": "2:01:32"}
846
+ {"current_steps": 846, "total_steps": 1235, "loss": 0.2895, "lr": 1.0927749362395475e-05, "epoch": 3.425101214574899, "percentage": 68.5, "elapsed_time": "4:23:39", "remaining_time": "2:01:13"}
847
+ {"current_steps": 847, "total_steps": 1235, "loss": 0.2892, "lr": 1.0877384543598954e-05, "epoch": 3.42914979757085, "percentage": 68.58, "elapsed_time": "4:23:54", "remaining_time": "2:00:53"}
848
+ {"current_steps": 848, "total_steps": 1235, "loss": 0.2884, "lr": 1.0827092668992529e-05, "epoch": 3.4331983805668016, "percentage": 68.66, "elapsed_time": "4:24:11", "remaining_time": "2:00:34"}
849
+ {"current_steps": 849, "total_steps": 1235, "loss": 0.2815, "lr": 1.077687414070869e-05, "epoch": 3.437246963562753, "percentage": 68.74, "elapsed_time": "4:24:30", "remaining_time": "2:00:15"}
850
+ {"current_steps": 850, "total_steps": 1235, "loss": 0.2739, "lr": 1.0726729360293451e-05, "epoch": 3.4412955465587043, "percentage": 68.83, "elapsed_time": "4:24:48", "remaining_time": "1:59:56"}
851
+ {"current_steps": 851, "total_steps": 1235, "loss": 0.2814, "lr": 1.0676658728703147e-05, "epoch": 3.445344129554656, "percentage": 68.91, "elapsed_time": "4:25:08", "remaining_time": "1:59:38"}
852
+ {"current_steps": 852, "total_steps": 1235, "loss": 0.2942, "lr": 1.0626662646301198e-05, "epoch": 3.4493927125506074, "percentage": 68.99, "elapsed_time": "4:25:28", "remaining_time": "1:59:20"}
853
+ {"current_steps": 853, "total_steps": 1235, "loss": 0.2691, "lr": 1.0576741512854958e-05, "epoch": 3.4534412955465585, "percentage": 69.07, "elapsed_time": "4:25:46", "remaining_time": "1:59:01"}
854
+ {"current_steps": 854, "total_steps": 1235, "loss": 0.2853, "lr": 1.052689572753247e-05, "epoch": 3.45748987854251, "percentage": 69.15, "elapsed_time": "4:26:02", "remaining_time": "1:58:41"}
855
+ {"current_steps": 855, "total_steps": 1235, "loss": 0.2946, "lr": 1.0477125688899328e-05, "epoch": 3.4615384615384617, "percentage": 69.23, "elapsed_time": "4:26:23", "remaining_time": "1:58:23"}
856
+ {"current_steps": 856, "total_steps": 1235, "loss": 0.2854, "lr": 1.0427431794915406e-05, "epoch": 3.465587044534413, "percentage": 69.31, "elapsed_time": "4:26:40", "remaining_time": "1:58:04"}
857
+ {"current_steps": 857, "total_steps": 1235, "loss": 0.2797, "lr": 1.0377814442931769e-05, "epoch": 3.4696356275303644, "percentage": 69.39, "elapsed_time": "4:26:58", "remaining_time": "1:57:45"}
858
+ {"current_steps": 858, "total_steps": 1235, "loss": 0.2779, "lr": 1.0328274029687439e-05, "epoch": 3.473684210526316, "percentage": 69.47, "elapsed_time": "4:27:14", "remaining_time": "1:57:25"}
859
+ {"current_steps": 859, "total_steps": 1235, "loss": 0.293, "lr": 1.0278810951306253e-05, "epoch": 3.477732793522267, "percentage": 69.55, "elapsed_time": "4:27:34", "remaining_time": "1:57:07"}
860
+ {"current_steps": 860, "total_steps": 1235, "loss": 0.2894, "lr": 1.0229425603293647e-05, "epoch": 3.4817813765182186, "percentage": 69.64, "elapsed_time": "4:27:54", "remaining_time": "1:56:49"}
861
+ {"current_steps": 861, "total_steps": 1235, "loss": 0.29, "lr": 1.0180118380533558e-05, "epoch": 3.48582995951417, "percentage": 69.72, "elapsed_time": "4:28:13", "remaining_time": "1:56:30"}
862
+ {"current_steps": 862, "total_steps": 1235, "loss": 0.2856, "lr": 1.0130889677285225e-05, "epoch": 3.4898785425101213, "percentage": 69.8, "elapsed_time": "4:28:33", "remaining_time": "1:56:12"}
863
+ {"current_steps": 863, "total_steps": 1235, "loss": 0.2807, "lr": 1.008173988718005e-05, "epoch": 3.493927125506073, "percentage": 69.88, "elapsed_time": "4:28:52", "remaining_time": "1:55:53"}
864
+ {"current_steps": 864, "total_steps": 1235, "loss": 0.2806, "lr": 1.0032669403218439e-05, "epoch": 3.4979757085020244, "percentage": 69.96, "elapsed_time": "4:29:10", "remaining_time": "1:55:35"}
865
+ {"current_steps": 865, "total_steps": 1235, "loss": 0.2932, "lr": 9.983678617766677e-06, "epoch": 3.5020242914979756, "percentage": 70.04, "elapsed_time": "4:29:25", "remaining_time": "1:55:14"}
866
+ {"current_steps": 866, "total_steps": 1235, "loss": 0.297, "lr": 9.934767922553788e-06, "epoch": 3.506072874493927, "percentage": 70.12, "elapsed_time": "4:29:41", "remaining_time": "1:54:55"}
867
+ {"current_steps": 867, "total_steps": 1235, "loss": 0.2849, "lr": 9.885937708668371e-06, "epoch": 3.5101214574898787, "percentage": 70.2, "elapsed_time": "4:29:58", "remaining_time": "1:54:35"}
868
+ {"current_steps": 868, "total_steps": 1235, "loss": 0.2709, "lr": 9.837188366555524e-06, "epoch": 3.51417004048583, "percentage": 70.28, "elapsed_time": "4:30:15", "remaining_time": "1:54:16"}
869
+ {"current_steps": 869, "total_steps": 1235, "loss": 0.2882, "lr": 9.788520286013691e-06, "epoch": 3.5182186234817814, "percentage": 70.36, "elapsed_time": "4:30:34", "remaining_time": "1:53:57"}
870
+ {"current_steps": 870, "total_steps": 1235, "loss": 0.3022, "lr": 9.739933856191537e-06, "epoch": 3.522267206477733, "percentage": 70.45, "elapsed_time": "4:30:51", "remaining_time": "1:53:38"}
871
+ {"current_steps": 871, "total_steps": 1235, "loss": 0.2929, "lr": 9.691429465584866e-06, "epoch": 3.526315789473684, "percentage": 70.53, "elapsed_time": "4:31:09", "remaining_time": "1:53:19"}
872
+ {"current_steps": 872, "total_steps": 1235, "loss": 0.2938, "lr": 9.643007502033492e-06, "epoch": 3.5303643724696356, "percentage": 70.61, "elapsed_time": "4:31:27", "remaining_time": "1:53:00"}
873
+ {"current_steps": 873, "total_steps": 1235, "loss": 0.2897, "lr": 9.594668352718152e-06, "epoch": 3.534412955465587, "percentage": 70.69, "elapsed_time": "4:31:42", "remaining_time": "1:52:39"}
874
+ {"current_steps": 874, "total_steps": 1235, "loss": 0.2972, "lr": 9.546412404157383e-06, "epoch": 3.5384615384615383, "percentage": 70.77, "elapsed_time": "4:32:01", "remaining_time": "1:52:21"}
875
+ {"current_steps": 875, "total_steps": 1235, "loss": 0.3009, "lr": 9.498240042204471e-06, "epoch": 3.54251012145749, "percentage": 70.85, "elapsed_time": "4:32:24", "remaining_time": "1:52:04"}
876
+ {"current_steps": 876, "total_steps": 1235, "loss": 0.285, "lr": 9.450151652044339e-06, "epoch": 3.5465587044534415, "percentage": 70.93, "elapsed_time": "4:32:44", "remaining_time": "1:51:46"}
877
+ {"current_steps": 877, "total_steps": 1235, "loss": 0.2773, "lr": 9.402147618190472e-06, "epoch": 3.5506072874493926, "percentage": 71.01, "elapsed_time": "4:33:01", "remaining_time": "1:51:26"}
878
+ {"current_steps": 878, "total_steps": 1235, "loss": 0.2936, "lr": 9.354228324481841e-06, "epoch": 3.554655870445344, "percentage": 71.09, "elapsed_time": "4:33:21", "remaining_time": "1:51:08"}
879
+ {"current_steps": 879, "total_steps": 1235, "loss": 0.2814, "lr": 9.306394154079852e-06, "epoch": 3.5587044534412957, "percentage": 71.17, "elapsed_time": "4:33:40", "remaining_time": "1:50:50"}
880
+ {"current_steps": 880, "total_steps": 1235, "loss": 0.2892, "lr": 9.258645489465254e-06, "epoch": 3.562753036437247, "percentage": 71.26, "elapsed_time": "4:34:01", "remaining_time": "1:50:32"}
881
+ {"current_steps": 881, "total_steps": 1235, "loss": 0.2847, "lr": 9.21098271243509e-06, "epoch": 3.5668016194331984, "percentage": 71.34, "elapsed_time": "4:34:16", "remaining_time": "1:50:12"}
882
+ {"current_steps": 882, "total_steps": 1235, "loss": 0.2992, "lr": 9.163406204099659e-06, "epoch": 3.57085020242915, "percentage": 71.42, "elapsed_time": "4:34:34", "remaining_time": "1:49:53"}
883
+ {"current_steps": 883, "total_steps": 1235, "loss": 0.2885, "lr": 9.115916344879452e-06, "epoch": 3.574898785425101, "percentage": 71.5, "elapsed_time": "4:34:50", "remaining_time": "1:49:33"}
884
+ {"current_steps": 884, "total_steps": 1235, "loss": 0.2789, "lr": 9.068513514502126e-06, "epoch": 3.5789473684210527, "percentage": 71.58, "elapsed_time": "4:35:08", "remaining_time": "1:49:14"}
885
+ {"current_steps": 885, "total_steps": 1235, "loss": 0.2886, "lr": 9.021198091999439e-06, "epoch": 3.582995951417004, "percentage": 71.66, "elapsed_time": "4:35:28", "remaining_time": "1:48:56"}
886
+ {"current_steps": 886, "total_steps": 1235, "loss": 0.2814, "lr": 8.973970455704251e-06, "epoch": 3.5870445344129553, "percentage": 71.74, "elapsed_time": "4:35:46", "remaining_time": "1:48:37"}
887
+ {"current_steps": 887, "total_steps": 1235, "loss": 0.2775, "lr": 8.926830983247495e-06, "epoch": 3.591093117408907, "percentage": 71.82, "elapsed_time": "4:36:04", "remaining_time": "1:48:18"}
888
+ {"current_steps": 888, "total_steps": 1235, "loss": 0.2849, "lr": 8.879780051555116e-06, "epoch": 3.5951417004048585, "percentage": 71.9, "elapsed_time": "4:36:23", "remaining_time": "1:48:00"}
889
+ {"current_steps": 889, "total_steps": 1235, "loss": 0.2824, "lr": 8.83281803684512e-06, "epoch": 3.5991902834008096, "percentage": 71.98, "elapsed_time": "4:36:41", "remaining_time": "1:47:41"}
890
+ {"current_steps": 890, "total_steps": 1235, "loss": 0.3137, "lr": 8.785945314624532e-06, "epoch": 3.603238866396761, "percentage": 72.06, "elapsed_time": "4:37:00", "remaining_time": "1:47:22"}
891
+ {"current_steps": 891, "total_steps": 1235, "loss": 0.2987, "lr": 8.739162259686385e-06, "epoch": 3.6072874493927127, "percentage": 72.15, "elapsed_time": "4:37:21", "remaining_time": "1:47:04"}
892
+ {"current_steps": 892, "total_steps": 1235, "loss": 0.2905, "lr": 8.692469246106734e-06, "epoch": 3.611336032388664, "percentage": 72.23, "elapsed_time": "4:37:36", "remaining_time": "1:46:45"}
893
+ {"current_steps": 893, "total_steps": 1235, "loss": 0.2894, "lr": 8.645866647241677e-06, "epoch": 3.6153846153846154, "percentage": 72.31, "elapsed_time": "4:37:56", "remaining_time": "1:46:26"}
894
+ {"current_steps": 894, "total_steps": 1235, "loss": 0.2885, "lr": 8.599354835724348e-06, "epoch": 3.619433198380567, "percentage": 72.39, "elapsed_time": "4:38:16", "remaining_time": "1:46:08"}
895
+ {"current_steps": 895, "total_steps": 1235, "loss": 0.2928, "lr": 8.552934183461958e-06, "epoch": 3.623481781376518, "percentage": 72.47, "elapsed_time": "4:38:34", "remaining_time": "1:45:49"}
896
+ {"current_steps": 896, "total_steps": 1235, "loss": 0.2849, "lr": 8.506605061632805e-06, "epoch": 3.6275303643724697, "percentage": 72.55, "elapsed_time": "4:38:52", "remaining_time": "1:45:30"}
897
+ {"current_steps": 897, "total_steps": 1235, "loss": 0.2934, "lr": 8.460367840683308e-06, "epoch": 3.6315789473684212, "percentage": 72.63, "elapsed_time": "4:39:09", "remaining_time": "1:45:11"}
898
+ {"current_steps": 898, "total_steps": 1235, "loss": 0.278, "lr": 8.414222890325065e-06, "epoch": 3.6356275303643724, "percentage": 72.71, "elapsed_time": "4:39:24", "remaining_time": "1:44:51"}
899
+ {"current_steps": 899, "total_steps": 1235, "loss": 0.2849, "lr": 8.368170579531855e-06, "epoch": 3.639676113360324, "percentage": 72.79, "elapsed_time": "4:39:40", "remaining_time": "1:44:31"}
900
+ {"current_steps": 900, "total_steps": 1235, "loss": 0.2935, "lr": 8.322211276536733e-06, "epoch": 3.6437246963562755, "percentage": 72.87, "elapsed_time": "4:39:55", "remaining_time": "1:44:11"}
901
+ {"current_steps": 901, "total_steps": 1235, "loss": 0.2899, "lr": 8.27634534882907e-06, "epoch": 3.6477732793522266, "percentage": 72.96, "elapsed_time": "4:40:13", "remaining_time": "1:43:52"}
902
+ {"current_steps": 902, "total_steps": 1235, "loss": 0.2774, "lr": 8.230573163151585e-06, "epoch": 3.651821862348178, "percentage": 73.04, "elapsed_time": "4:40:28", "remaining_time": "1:43:32"}
903
+ {"current_steps": 903, "total_steps": 1235, "loss": 0.3013, "lr": 8.184895085497466e-06, "epoch": 3.6558704453441297, "percentage": 73.12, "elapsed_time": "4:40:46", "remaining_time": "1:43:13"}
904
+ {"current_steps": 904, "total_steps": 1235, "loss": 0.2886, "lr": 8.139311481107401e-06, "epoch": 3.659919028340081, "percentage": 73.2, "elapsed_time": "4:41:05", "remaining_time": "1:42:55"}
905
+ {"current_steps": 905, "total_steps": 1235, "loss": 0.2961, "lr": 8.093822714466686e-06, "epoch": 3.6639676113360324, "percentage": 73.28, "elapsed_time": "4:41:21", "remaining_time": "1:42:35"}
906
+ {"current_steps": 906, "total_steps": 1235, "loss": 0.2756, "lr": 8.048429149302271e-06, "epoch": 3.668016194331984, "percentage": 73.36, "elapsed_time": "4:41:37", "remaining_time": "1:42:15"}
907
+ {"current_steps": 907, "total_steps": 1235, "loss": 0.2935, "lr": 8.003131148579902e-06, "epoch": 3.672064777327935, "percentage": 73.44, "elapsed_time": "4:41:54", "remaining_time": "1:41:56"}
908
+ {"current_steps": 908, "total_steps": 1235, "loss": 0.2729, "lr": 7.957929074501182e-06, "epoch": 3.6761133603238867, "percentage": 73.52, "elapsed_time": "4:42:12", "remaining_time": "1:41:37"}
909
+ {"current_steps": 909, "total_steps": 1235, "loss": 0.2911, "lr": 7.912823288500695e-06, "epoch": 3.6801619433198383, "percentage": 73.6, "elapsed_time": "4:42:31", "remaining_time": "1:41:19"}
910
+ {"current_steps": 910, "total_steps": 1235, "loss": 0.2919, "lr": 7.867814151243102e-06, "epoch": 3.6842105263157894, "percentage": 73.68, "elapsed_time": "4:42:49", "remaining_time": "1:41:00"}
911
+ {"current_steps": 911, "total_steps": 1235, "loss": 0.2929, "lr": 7.822902022620267e-06, "epoch": 3.688259109311741, "percentage": 73.77, "elapsed_time": "4:43:06", "remaining_time": "1:40:41"}
912
+ {"current_steps": 912, "total_steps": 1235, "loss": 0.2854, "lr": 7.778087261748377e-06, "epoch": 3.6923076923076925, "percentage": 73.85, "elapsed_time": "4:43:26", "remaining_time": "1:40:22"}
913
+ {"current_steps": 913, "total_steps": 1235, "loss": 0.2876, "lr": 7.733370226965056e-06, "epoch": 3.6963562753036436, "percentage": 73.93, "elapsed_time": "4:43:40", "remaining_time": "1:40:02"}
914
+ {"current_steps": 914, "total_steps": 1235, "loss": 0.2832, "lr": 7.688751275826527e-06, "epoch": 3.700404858299595, "percentage": 74.01, "elapsed_time": "4:43:58", "remaining_time": "1:39:43"}
915
+ {"current_steps": 915, "total_steps": 1235, "loss": 0.2857, "lr": 7.644230765104735e-06, "epoch": 3.7044534412955468, "percentage": 74.09, "elapsed_time": "4:44:16", "remaining_time": "1:39:25"}
916
+ {"current_steps": 916, "total_steps": 1235, "loss": 0.2986, "lr": 7.599809050784502e-06, "epoch": 3.708502024291498, "percentage": 74.17, "elapsed_time": "4:44:36", "remaining_time": "1:39:07"}
917
+ {"current_steps": 917, "total_steps": 1235, "loss": 0.2875, "lr": 7.555486488060661e-06, "epoch": 3.7125506072874495, "percentage": 74.25, "elapsed_time": "4:44:54", "remaining_time": "1:38:47"}
918
+ {"current_steps": 918, "total_steps": 1235, "loss": 0.2875, "lr": 7.511263431335249e-06, "epoch": 3.716599190283401, "percentage": 74.33, "elapsed_time": "4:45:11", "remaining_time": "1:38:28"}
919
+ {"current_steps": 919, "total_steps": 1235, "loss": 0.2898, "lr": 7.467140234214656e-06, "epoch": 3.720647773279352, "percentage": 74.41, "elapsed_time": "4:45:30", "remaining_time": "1:38:10"}
920
+ {"current_steps": 920, "total_steps": 1235, "loss": 0.2804, "lr": 7.423117249506777e-06, "epoch": 3.7246963562753037, "percentage": 74.49, "elapsed_time": "4:45:47", "remaining_time": "1:37:51"}
921
+ {"current_steps": 921, "total_steps": 1235, "loss": 0.2812, "lr": 7.379194829218231e-06, "epoch": 3.7287449392712553, "percentage": 74.57, "elapsed_time": "4:46:09", "remaining_time": "1:37:33"}
922
+ {"current_steps": 922, "total_steps": 1235, "loss": 0.3041, "lr": 7.335373324551518e-06, "epoch": 3.7327935222672064, "percentage": 74.66, "elapsed_time": "4:46:26", "remaining_time": "1:37:14"}
923
+ {"current_steps": 923, "total_steps": 1235, "loss": 0.2971, "lr": 7.291653085902224e-06, "epoch": 3.736842105263158, "percentage": 74.74, "elapsed_time": "4:46:46", "remaining_time": "1:36:56"}
924
+ {"current_steps": 924, "total_steps": 1235, "loss": 0.2765, "lr": 7.248034462856213e-06, "epoch": 3.7408906882591095, "percentage": 74.82, "elapsed_time": "4:47:02", "remaining_time": "1:36:36"}
925
+ {"current_steps": 925, "total_steps": 1235, "loss": 0.2762, "lr": 7.20451780418683e-06, "epoch": 3.7449392712550607, "percentage": 74.9, "elapsed_time": "4:47:24", "remaining_time": "1:36:19"}
926
+ {"current_steps": 926, "total_steps": 1235, "loss": 0.2856, "lr": 7.161103457852128e-06, "epoch": 3.748987854251012, "percentage": 74.98, "elapsed_time": "4:47:42", "remaining_time": "1:36:00"}
927
+ {"current_steps": 927, "total_steps": 1235, "loss": 0.2738, "lr": 7.117791770992046e-06, "epoch": 3.753036437246964, "percentage": 75.06, "elapsed_time": "4:47:59", "remaining_time": "1:35:41"}
928
+ {"current_steps": 928, "total_steps": 1235, "loss": 0.3, "lr": 7.074583089925688e-06, "epoch": 3.757085020242915, "percentage": 75.14, "elapsed_time": "4:48:21", "remaining_time": "1:35:23"}
929
+ {"current_steps": 929, "total_steps": 1235, "loss": 0.2872, "lr": 7.0314777601485155e-06, "epoch": 3.7611336032388665, "percentage": 75.22, "elapsed_time": "4:48:41", "remaining_time": "1:35:05"}
930
+ {"current_steps": 930, "total_steps": 1235, "loss": 0.2689, "lr": 6.988476126329604e-06, "epoch": 3.765182186234818, "percentage": 75.3, "elapsed_time": "4:48:59", "remaining_time": "1:34:46"}
931
+ {"current_steps": 931, "total_steps": 1235, "loss": 0.2733, "lr": 6.945578532308857e-06, "epoch": 3.769230769230769, "percentage": 75.38, "elapsed_time": "4:49:21", "remaining_time": "1:34:28"}
932
+ {"current_steps": 932, "total_steps": 1235, "loss": 0.2866, "lr": 6.902785321094301e-06, "epoch": 3.7732793522267207, "percentage": 75.47, "elapsed_time": "4:49:36", "remaining_time": "1:34:09"}
933
+ {"current_steps": 933, "total_steps": 1235, "loss": 0.2986, "lr": 6.8600968348593115e-06, "epoch": 3.7773279352226723, "percentage": 75.55, "elapsed_time": "4:49:52", "remaining_time": "1:33:49"}
934
+ {"current_steps": 934, "total_steps": 1235, "loss": 0.2749, "lr": 6.817513414939892e-06, "epoch": 3.7813765182186234, "percentage": 75.63, "elapsed_time": "4:50:11", "remaining_time": "1:33:31"}
935
+ {"current_steps": 935, "total_steps": 1235, "loss": 0.29, "lr": 6.775035401831924e-06, "epoch": 3.785425101214575, "percentage": 75.71, "elapsed_time": "4:50:27", "remaining_time": "1:33:11"}
936
+ {"current_steps": 936, "total_steps": 1235, "loss": 0.2813, "lr": 6.732663135188473e-06, "epoch": 3.7894736842105265, "percentage": 75.79, "elapsed_time": "4:50:47", "remaining_time": "1:32:53"}
937
+ {"current_steps": 937, "total_steps": 1235, "loss": 0.2959, "lr": 6.690396953817055e-06, "epoch": 3.7935222672064777, "percentage": 75.87, "elapsed_time": "4:51:04", "remaining_time": "1:32:34"}
938
+ {"current_steps": 938, "total_steps": 1235, "loss": 0.2875, "lr": 6.648237195676927e-06, "epoch": 3.7975708502024292, "percentage": 75.95, "elapsed_time": "4:51:21", "remaining_time": "1:32:15"}
939
+ {"current_steps": 939, "total_steps": 1235, "loss": 0.2906, "lr": 6.606184197876395e-06, "epoch": 3.801619433198381, "percentage": 76.03, "elapsed_time": "4:51:41", "remaining_time": "1:31:56"}
940
+ {"current_steps": 940, "total_steps": 1235, "loss": 0.2778, "lr": 6.564238296670109e-06, "epoch": 3.805668016194332, "percentage": 76.11, "elapsed_time": "4:51:59", "remaining_time": "1:31:38"}
941
+ {"current_steps": 941, "total_steps": 1235, "loss": 0.2879, "lr": 6.52239982745638e-06, "epoch": 3.8097165991902835, "percentage": 76.19, "elapsed_time": "4:52:19", "remaining_time": "1:31:19"}
942
+ {"current_steps": 942, "total_steps": 1235, "loss": 0.2888, "lr": 6.480669124774484e-06, "epoch": 3.813765182186235, "percentage": 76.28, "elapsed_time": "4:52:33", "remaining_time": "1:30:59"}
943
+ {"current_steps": 943, "total_steps": 1235, "loss": 0.2854, "lr": 6.439046522302013e-06, "epoch": 3.817813765182186, "percentage": 76.36, "elapsed_time": "4:52:53", "remaining_time": "1:30:41"}
944
+ {"current_steps": 944, "total_steps": 1235, "loss": 0.2851, "lr": 6.397532352852191e-06, "epoch": 3.8218623481781377, "percentage": 76.44, "elapsed_time": "4:53:12", "remaining_time": "1:30:22"}
945
+ {"current_steps": 945, "total_steps": 1235, "loss": 0.2781, "lr": 6.356126948371202e-06, "epoch": 3.8259109311740893, "percentage": 76.52, "elapsed_time": "4:53:26", "remaining_time": "1:30:03"}
946
+ {"current_steps": 946, "total_steps": 1235, "loss": 0.282, "lr": 6.314830639935559e-06, "epoch": 3.8299595141700404, "percentage": 76.6, "elapsed_time": "4:53:43", "remaining_time": "1:29:44"}
947
+ {"current_steps": 947, "total_steps": 1235, "loss": 0.2904, "lr": 6.273643757749448e-06, "epoch": 3.834008097165992, "percentage": 76.68, "elapsed_time": "4:54:02", "remaining_time": "1:29:25"}
948
+ {"current_steps": 948, "total_steps": 1235, "loss": 0.2771, "lr": 6.2325666311420856e-06, "epoch": 3.8380566801619436, "percentage": 76.76, "elapsed_time": "4:54:19", "remaining_time": "1:29:06"}
949
+ {"current_steps": 949, "total_steps": 1235, "loss": 0.2883, "lr": 6.1915995885650675e-06, "epoch": 3.8421052631578947, "percentage": 76.84, "elapsed_time": "4:54:36", "remaining_time": "1:28:47"}
950
+ {"current_steps": 950, "total_steps": 1235, "loss": 0.2819, "lr": 6.150742957589784e-06, "epoch": 3.8461538461538463, "percentage": 76.92, "elapsed_time": "4:54:54", "remaining_time": "1:28:28"}
951
+ {"current_steps": 951, "total_steps": 1235, "loss": 0.2978, "lr": 6.109997064904774e-06, "epoch": 3.850202429149798, "percentage": 77.0, "elapsed_time": "4:55:09", "remaining_time": "1:28:08"}
952
+ {"current_steps": 952, "total_steps": 1235, "loss": 0.2896, "lr": 6.069362236313092e-06, "epoch": 3.854251012145749, "percentage": 77.09, "elapsed_time": "4:55:24", "remaining_time": "1:27:49"}
953
+ {"current_steps": 953, "total_steps": 1235, "loss": 0.2843, "lr": 6.0288387967297565e-06, "epoch": 3.8582995951417005, "percentage": 77.17, "elapsed_time": "4:55:41", "remaining_time": "1:27:29"}
954
+ {"current_steps": 954, "total_steps": 1235, "loss": 0.2973, "lr": 5.988427070179108e-06, "epoch": 3.862348178137652, "percentage": 77.25, "elapsed_time": "4:56:01", "remaining_time": "1:27:11"}
955
+ {"current_steps": 955, "total_steps": 1235, "loss": 0.2804, "lr": 5.948127379792234e-06, "epoch": 3.866396761133603, "percentage": 77.33, "elapsed_time": "4:56:22", "remaining_time": "1:26:53"}
956
+ {"current_steps": 956, "total_steps": 1235, "loss": 0.2906, "lr": 5.90794004780439e-06, "epoch": 3.8704453441295548, "percentage": 77.41, "elapsed_time": "4:56:42", "remaining_time": "1:26:35"}
957
+ {"current_steps": 957, "total_steps": 1235, "loss": 0.286, "lr": 5.867865395552405e-06, "epoch": 3.8744939271255063, "percentage": 77.49, "elapsed_time": "4:56:59", "remaining_time": "1:26:16"}
958
+ {"current_steps": 958, "total_steps": 1235, "loss": 0.2893, "lr": 5.8279037434721364e-06, "epoch": 3.8785425101214575, "percentage": 77.57, "elapsed_time": "4:57:18", "remaining_time": "1:25:57"}
959
+ {"current_steps": 959, "total_steps": 1235, "loss": 0.2814, "lr": 5.788055411095892e-06, "epoch": 3.882591093117409, "percentage": 77.65, "elapsed_time": "4:57:36", "remaining_time": "1:25:39"}
960
+ {"current_steps": 960, "total_steps": 1235, "loss": 0.2755, "lr": 5.7483207170498625e-06, "epoch": 3.8866396761133606, "percentage": 77.73, "elapsed_time": "4:57:54", "remaining_time": "1:25:20"}
961
+ {"current_steps": 961, "total_steps": 1235, "loss": 0.2967, "lr": 5.708699979051613e-06, "epoch": 3.8906882591093117, "percentage": 77.81, "elapsed_time": "4:58:13", "remaining_time": "1:25:01"}
962
+ {"current_steps": 962, "total_steps": 1235, "loss": 0.2716, "lr": 5.66919351390751e-06, "epoch": 3.8947368421052633, "percentage": 77.89, "elapsed_time": "4:58:31", "remaining_time": "1:24:42"}
963
+ {"current_steps": 963, "total_steps": 1235, "loss": 0.2907, "lr": 5.629801637510188e-06, "epoch": 3.898785425101215, "percentage": 77.98, "elapsed_time": "4:58:52", "remaining_time": "1:24:25"}
964
+ {"current_steps": 964, "total_steps": 1235, "loss": 0.2931, "lr": 5.590524664836043e-06, "epoch": 3.902834008097166, "percentage": 78.06, "elapsed_time": "4:59:11", "remaining_time": "1:24:06"}
965
+ {"current_steps": 965, "total_steps": 1235, "loss": 0.2918, "lr": 5.551362909942708e-06, "epoch": 3.9068825910931175, "percentage": 78.14, "elapsed_time": "4:59:30", "remaining_time": "1:23:48"}
966
+ {"current_steps": 966, "total_steps": 1235, "loss": 0.3026, "lr": 5.51231668596653e-06, "epoch": 3.910931174089069, "percentage": 78.22, "elapsed_time": "4:59:51", "remaining_time": "1:23:30"}
967
+ {"current_steps": 967, "total_steps": 1235, "loss": 0.2814, "lr": 5.47338630512007e-06, "epoch": 3.91497975708502, "percentage": 78.3, "elapsed_time": "5:00:07", "remaining_time": "1:23:10"}
968
+ {"current_steps": 968, "total_steps": 1235, "loss": 0.2812, "lr": 5.434572078689617e-06, "epoch": 3.919028340080972, "percentage": 78.38, "elapsed_time": "5:00:25", "remaining_time": "1:22:51"}
969
+ {"current_steps": 969, "total_steps": 1235, "loss": 0.2936, "lr": 5.395874317032694e-06, "epoch": 3.9230769230769234, "percentage": 78.46, "elapsed_time": "5:00:44", "remaining_time": "1:22:33"}
970
+ {"current_steps": 970, "total_steps": 1235, "loss": 0.2874, "lr": 5.357293329575573e-06, "epoch": 3.9271255060728745, "percentage": 78.54, "elapsed_time": "5:01:01", "remaining_time": "1:22:14"}
971
+ {"current_steps": 971, "total_steps": 1235, "loss": 0.2735, "lr": 5.318829424810797e-06, "epoch": 3.931174089068826, "percentage": 78.62, "elapsed_time": "5:01:18", "remaining_time": "1:21:55"}
972
+ {"current_steps": 972, "total_steps": 1235, "loss": 0.2827, "lr": 5.280482910294728e-06, "epoch": 3.9352226720647776, "percentage": 78.7, "elapsed_time": "5:01:35", "remaining_time": "1:21:36"}
973
+ {"current_steps": 973, "total_steps": 1235, "loss": 0.2739, "lr": 5.242254092645078e-06, "epoch": 3.9392712550607287, "percentage": 78.79, "elapsed_time": "5:01:53", "remaining_time": "1:21:17"}
974
+ {"current_steps": 974, "total_steps": 1235, "loss": 0.2917, "lr": 5.2041432775384445e-06, "epoch": 3.9433198380566803, "percentage": 78.87, "elapsed_time": "5:02:14", "remaining_time": "1:20:59"}
975
+ {"current_steps": 975, "total_steps": 1235, "loss": 0.2778, "lr": 5.166150769707892e-06, "epoch": 3.9473684210526314, "percentage": 78.95, "elapsed_time": "5:02:33", "remaining_time": "1:20:41"}
976
+ {"current_steps": 976, "total_steps": 1235, "loss": 0.2981, "lr": 5.128276872940503e-06, "epoch": 3.951417004048583, "percentage": 79.03, "elapsed_time": "5:02:51", "remaining_time": "1:20:22"}
977
+ {"current_steps": 977, "total_steps": 1235, "loss": 0.2851, "lr": 5.090521890074953e-06, "epoch": 3.9554655870445345, "percentage": 79.11, "elapsed_time": "5:03:10", "remaining_time": "1:20:03"}
978
+ {"current_steps": 978, "total_steps": 1235, "loss": 0.2908, "lr": 5.0528861229990675e-06, "epoch": 3.9595141700404857, "percentage": 79.19, "elapsed_time": "5:03:33", "remaining_time": "1:19:46"}
979
+ {"current_steps": 979, "total_steps": 1235, "loss": 0.2916, "lr": 5.015369872647442e-06, "epoch": 3.9635627530364372, "percentage": 79.27, "elapsed_time": "5:03:51", "remaining_time": "1:19:27"}
980
+ {"current_steps": 980, "total_steps": 1235, "loss": 0.2806, "lr": 4.9779734389990195e-06, "epoch": 3.967611336032389, "percentage": 79.35, "elapsed_time": "5:04:13", "remaining_time": "1:19:09"}
981
+ {"current_steps": 981, "total_steps": 1235, "loss": 0.2935, "lr": 4.940697121074675e-06, "epoch": 3.97165991902834, "percentage": 79.43, "elapsed_time": "5:04:29", "remaining_time": "1:18:50"}
982
+ {"current_steps": 982, "total_steps": 1235, "loss": 0.3071, "lr": 4.903541216934864e-06, "epoch": 3.9757085020242915, "percentage": 79.51, "elapsed_time": "5:04:50", "remaining_time": "1:18:32"}
983
+ {"current_steps": 983, "total_steps": 1235, "loss": 0.2754, "lr": 4.8665060236772e-06, "epoch": 3.979757085020243, "percentage": 79.6, "elapsed_time": "5:05:10", "remaining_time": "1:18:14"}
984
+ {"current_steps": 984, "total_steps": 1235, "loss": 0.2901, "lr": 4.829591837434102e-06, "epoch": 3.983805668016194, "percentage": 79.68, "elapsed_time": "5:05:27", "remaining_time": "1:17:55"}
985
+ {"current_steps": 985, "total_steps": 1235, "loss": 0.2824, "lr": 4.792798953370424e-06, "epoch": 3.9878542510121457, "percentage": 79.76, "elapsed_time": "5:05:46", "remaining_time": "1:17:36"}
986
+ {"current_steps": 986, "total_steps": 1235, "loss": 0.2846, "lr": 4.756127665681083e-06, "epoch": 3.9919028340080973, "percentage": 79.84, "elapsed_time": "5:06:04", "remaining_time": "1:17:17"}
987
+ {"current_steps": 987, "total_steps": 1235, "loss": 0.2747, "lr": 4.719578267588725e-06, "epoch": 3.9959514170040484, "percentage": 79.92, "elapsed_time": "5:06:20", "remaining_time": "1:16:58"}
988
+ {"current_steps": 988, "total_steps": 1235, "loss": 0.2762, "lr": 4.6831510513413525e-06, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "5:06:35", "remaining_time": "1:16:38"}
989
+ {"current_steps": 989, "total_steps": 1235, "loss": 0.231, "lr": 4.6468463082100176e-06, "epoch": 4.004048582995951, "percentage": 80.08, "elapsed_time": "5:08:07", "remaining_time": "1:16:38"}
990
+ {"current_steps": 990, "total_steps": 1235, "loss": 0.2279, "lr": 4.610664328486485e-06, "epoch": 4.008097165991903, "percentage": 80.16, "elapsed_time": "5:08:27", "remaining_time": "1:16:20"}
991
+ {"current_steps": 991, "total_steps": 1235, "loss": 0.2093, "lr": 4.5746054014809e-06, "epoch": 4.012145748987854, "percentage": 80.24, "elapsed_time": "5:08:46", "remaining_time": "1:16:01"}
992
+ {"current_steps": 992, "total_steps": 1235, "loss": 0.2128, "lr": 4.5386698155194766e-06, "epoch": 4.016194331983805, "percentage": 80.32, "elapsed_time": "5:09:06", "remaining_time": "1:15:43"}
993
+ {"current_steps": 993, "total_steps": 1235, "loss": 0.2106, "lr": 4.502857857942204e-06, "epoch": 4.020242914979757, "percentage": 80.4, "elapsed_time": "5:09:20", "remaining_time": "1:15:23"}
994
+ {"current_steps": 994, "total_steps": 1235, "loss": 0.209, "lr": 4.467169815100549e-06, "epoch": 4.0242914979757085, "percentage": 80.49, "elapsed_time": "5:09:36", "remaining_time": "1:15:04"}
995
+ {"current_steps": 995, "total_steps": 1235, "loss": 0.207, "lr": 4.431605972355137e-06, "epoch": 4.02834008097166, "percentage": 80.57, "elapsed_time": "5:09:56", "remaining_time": "1:14:45"}
996
+ {"current_steps": 996, "total_steps": 1235, "loss": 0.2248, "lr": 4.396166614073516e-06, "epoch": 4.032388663967612, "percentage": 80.65, "elapsed_time": "5:10:14", "remaining_time": "1:14:26"}