neginr commited on
Commit
639a481
·
verified ·
1 Parent(s): cf020ba

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 sha256:57ff037f49a280febfc4e94bea5ca9597e0a76e208966094389e594659585c34
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e51450912e4f57866594d8e87f1dae342fd21ee7dc8106a1c839015b49211df
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e67dc991592113902f1103dc278e503fcf2b5dc4683055e8d03e5dd54474529
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80847921bd657cc984f9feb449141d68c39f99d66bf5d5f23ba58b6932d9b3f5
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2aa5663aaa316379ce50409773452fc3d57879264a99b7d3415b1222cc6e72a7
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd2025b890787d1aa25d5c65d63acb722b0c22e18d8867cd212b96ecfab45e5c
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:f0921afa8e2b9dcea5be23ecdd94473be7b33d9150590bce8d1a78ef619764ad
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5634e24a0011fdf0c70649a914934c4766cf552db4043a2969cc721d9339153
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -747,3 +747,250 @@
747
  {"current_steps": 747, "total_steps": 1235, "loss": 0.2625, "lr": 1.620572014799777e-05, "epoch": 3.0242914979757085, "percentage": 60.49, "elapsed_time": "4:13:12", "remaining_time": "2:45:24"}
748
  {"current_steps": 748, "total_steps": 1235, "loss": 0.2561, "lr": 1.6150208128905857e-05, "epoch": 3.02834008097166, "percentage": 60.57, "elapsed_time": "4:13:32", "remaining_time": "2:45:04"}
749
  {"current_steps": 749, "total_steps": 1235, "loss": 0.2649, "lr": 1.6094726892647147e-05, "epoch": 3.032388663967611, "percentage": 60.65, "elapsed_time": "4:13:53", "remaining_time": "2:44:44"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
747
  {"current_steps": 747, "total_steps": 1235, "loss": 0.2625, "lr": 1.620572014799777e-05, "epoch": 3.0242914979757085, "percentage": 60.49, "elapsed_time": "4:13:12", "remaining_time": "2:45:24"}
748
  {"current_steps": 748, "total_steps": 1235, "loss": 0.2561, "lr": 1.6150208128905857e-05, "epoch": 3.02834008097166, "percentage": 60.57, "elapsed_time": "4:13:32", "remaining_time": "2:45:04"}
749
  {"current_steps": 749, "total_steps": 1235, "loss": 0.2649, "lr": 1.6094726892647147e-05, "epoch": 3.032388663967611, "percentage": 60.65, "elapsed_time": "4:13:53", "remaining_time": "2:44:44"}
750
+ {"current_steps": 750, "total_steps": 1235, "loss": 0.2592, "lr": 1.6039276882848135e-05, "epoch": 3.0364372469635628, "percentage": 60.73, "elapsed_time": "4:14:13", "remaining_time": "2:44:24"}
751
+ {"current_steps": 751, "total_steps": 1235, "loss": 0.2383, "lr": 1.5983858542885635e-05, "epoch": 3.0404858299595143, "percentage": 60.81, "elapsed_time": "4:14:33", "remaining_time": "2:44:03"}
752
+ {"current_steps": 752, "total_steps": 1235, "loss": 0.2429, "lr": 1.5928472315883203e-05, "epoch": 3.0445344129554655, "percentage": 60.89, "elapsed_time": "4:14:51", "remaining_time": "2:43:41"}
753
+ {"current_steps": 753, "total_steps": 1235, "loss": 0.2596, "lr": 1.5873118644707633e-05, "epoch": 3.048582995951417, "percentage": 60.97, "elapsed_time": "4:15:12", "remaining_time": "2:43:21"}
754
+ {"current_steps": 754, "total_steps": 1235, "loss": 0.2495, "lr": 1.5817797971965413e-05, "epoch": 3.0526315789473686, "percentage": 61.05, "elapsed_time": "4:15:34", "remaining_time": "2:43:02"}
755
+ {"current_steps": 755, "total_steps": 1235, "loss": 0.2562, "lr": 1.576251073999917e-05, "epoch": 3.0566801619433197, "percentage": 61.13, "elapsed_time": "4:15:53", "remaining_time": "2:42:41"}
756
+ {"current_steps": 756, "total_steps": 1235, "loss": 0.2532, "lr": 1.5707257390884126e-05, "epoch": 3.0607287449392713, "percentage": 61.21, "elapsed_time": "4:16:14", "remaining_time": "2:42:21"}
757
+ {"current_steps": 757, "total_steps": 1235, "loss": 0.2548, "lr": 1.5652038366424595e-05, "epoch": 3.064777327935223, "percentage": 61.3, "elapsed_time": "4:16:36", "remaining_time": "2:42:02"}
758
+ {"current_steps": 758, "total_steps": 1235, "loss": 0.265, "lr": 1.5596854108150424e-05, "epoch": 3.068825910931174, "percentage": 61.38, "elapsed_time": "4:16:58", "remaining_time": "2:41:42"}
759
+ {"current_steps": 759, "total_steps": 1235, "loss": 0.2492, "lr": 1.5541705057313476e-05, "epoch": 3.0728744939271255, "percentage": 61.46, "elapsed_time": "4:17:17", "remaining_time": "2:41:21"}
760
+ {"current_steps": 760, "total_steps": 1235, "loss": 0.2536, "lr": 1.5486591654884086e-05, "epoch": 3.076923076923077, "percentage": 61.54, "elapsed_time": "4:17:37", "remaining_time": "2:41:00"}
761
+ {"current_steps": 761, "total_steps": 1235, "loss": 0.2337, "lr": 1.543151434154755e-05, "epoch": 3.080971659919028, "percentage": 61.62, "elapsed_time": "4:17:56", "remaining_time": "2:40:39"}
762
+ {"current_steps": 762, "total_steps": 1235, "loss": 0.2597, "lr": 1.5376473557700615e-05, "epoch": 3.08502024291498, "percentage": 61.7, "elapsed_time": "4:18:15", "remaining_time": "2:40:18"}
763
+ {"current_steps": 763, "total_steps": 1235, "loss": 0.2597, "lr": 1.5321469743447893e-05, "epoch": 3.0890688259109313, "percentage": 61.78, "elapsed_time": "4:18:34", "remaining_time": "2:39:57"}
764
+ {"current_steps": 764, "total_steps": 1235, "loss": 0.2484, "lr": 1.5266503338598434e-05, "epoch": 3.0931174089068825, "percentage": 61.86, "elapsed_time": "4:18:54", "remaining_time": "2:39:36"}
765
+ {"current_steps": 765, "total_steps": 1235, "loss": 0.2655, "lr": 1.5211574782662149e-05, "epoch": 3.097165991902834, "percentage": 61.94, "elapsed_time": "4:19:15", "remaining_time": "2:39:17"}
766
+ {"current_steps": 766, "total_steps": 1235, "loss": 0.2623, "lr": 1.5156684514846307e-05, "epoch": 3.1012145748987856, "percentage": 62.02, "elapsed_time": "4:19:37", "remaining_time": "2:38:57"}
767
+ {"current_steps": 767, "total_steps": 1235, "loss": 0.2617, "lr": 1.5101832974052012e-05, "epoch": 3.1052631578947367, "percentage": 62.11, "elapsed_time": "4:19:57", "remaining_time": "2:38:37"}
768
+ {"current_steps": 768, "total_steps": 1235, "loss": 0.2596, "lr": 1.5047020598870737e-05, "epoch": 3.1093117408906883, "percentage": 62.19, "elapsed_time": "4:20:17", "remaining_time": "2:38:16"}
769
+ {"current_steps": 769, "total_steps": 1235, "loss": 0.2529, "lr": 1.4992247827580778e-05, "epoch": 3.11336032388664, "percentage": 62.27, "elapsed_time": "4:20:40", "remaining_time": "2:37:58"}
770
+ {"current_steps": 770, "total_steps": 1235, "loss": 0.2559, "lr": 1.493751509814374e-05, "epoch": 3.117408906882591, "percentage": 62.35, "elapsed_time": "4:20:58", "remaining_time": "2:37:35"}
771
+ {"current_steps": 771, "total_steps": 1235, "loss": 0.2381, "lr": 1.4882822848201073e-05, "epoch": 3.1214574898785425, "percentage": 62.43, "elapsed_time": "4:21:17", "remaining_time": "2:37:14"}
772
+ {"current_steps": 772, "total_steps": 1235, "loss": 0.2528, "lr": 1.4828171515070553e-05, "epoch": 3.125506072874494, "percentage": 62.51, "elapsed_time": "4:21:37", "remaining_time": "2:36:54"}
773
+ {"current_steps": 773, "total_steps": 1235, "loss": 0.2515, "lr": 1.4773561535742793e-05, "epoch": 3.1295546558704452, "percentage": 62.59, "elapsed_time": "4:21:56", "remaining_time": "2:36:33"}
774
+ {"current_steps": 774, "total_steps": 1235, "loss": 0.2596, "lr": 1.4718993346877715e-05, "epoch": 3.133603238866397, "percentage": 62.67, "elapsed_time": "4:22:18", "remaining_time": "2:36:13"}
775
+ {"current_steps": 775, "total_steps": 1235, "loss": 0.2536, "lr": 1.466446738480111e-05, "epoch": 3.1376518218623484, "percentage": 62.75, "elapsed_time": "4:22:37", "remaining_time": "2:35:52"}
776
+ {"current_steps": 776, "total_steps": 1235, "loss": 0.271, "lr": 1.460998408550112e-05, "epoch": 3.1417004048582995, "percentage": 62.83, "elapsed_time": "4:22:55", "remaining_time": "2:35:31"}
777
+ {"current_steps": 777, "total_steps": 1235, "loss": 0.257, "lr": 1.4555543884624751e-05, "epoch": 3.145748987854251, "percentage": 62.91, "elapsed_time": "4:23:17", "remaining_time": "2:35:11"}
778
+ {"current_steps": 778, "total_steps": 1235, "loss": 0.2653, "lr": 1.4501147217474402e-05, "epoch": 3.1497975708502026, "percentage": 63.0, "elapsed_time": "4:23:36", "remaining_time": "2:34:50"}
779
+ {"current_steps": 779, "total_steps": 1235, "loss": 0.2667, "lr": 1.444679451900437e-05, "epoch": 3.1538461538461537, "percentage": 63.08, "elapsed_time": "4:23:57", "remaining_time": "2:34:30"}
780
+ {"current_steps": 780, "total_steps": 1235, "loss": 0.2688, "lr": 1.4392486223817397e-05, "epoch": 3.1578947368421053, "percentage": 63.16, "elapsed_time": "4:24:15", "remaining_time": "2:34:08"}
781
+ {"current_steps": 781, "total_steps": 1235, "loss": 0.2675, "lr": 1.4338222766161143e-05, "epoch": 3.161943319838057, "percentage": 63.24, "elapsed_time": "4:24:36", "remaining_time": "2:33:48"}
782
+ {"current_steps": 782, "total_steps": 1235, "loss": 0.2532, "lr": 1.4284004579924777e-05, "epoch": 3.165991902834008, "percentage": 63.32, "elapsed_time": "4:24:57", "remaining_time": "2:33:29"}
783
+ {"current_steps": 783, "total_steps": 1235, "loss": 0.2544, "lr": 1.4229832098635479e-05, "epoch": 3.1700404858299596, "percentage": 63.4, "elapsed_time": "4:25:17", "remaining_time": "2:33:08"}
784
+ {"current_steps": 784, "total_steps": 1235, "loss": 0.2591, "lr": 1.4175705755454963e-05, "epoch": 3.174089068825911, "percentage": 63.48, "elapsed_time": "4:25:37", "remaining_time": "2:32:47"}
785
+ {"current_steps": 785, "total_steps": 1235, "loss": 0.2567, "lr": 1.412162598317602e-05, "epoch": 3.1781376518218623, "percentage": 63.56, "elapsed_time": "4:25:58", "remaining_time": "2:32:27"}
786
+ {"current_steps": 786, "total_steps": 1235, "loss": 0.2618, "lr": 1.406759321421907e-05, "epoch": 3.182186234817814, "percentage": 63.64, "elapsed_time": "4:26:18", "remaining_time": "2:32:07"}
787
+ {"current_steps": 787, "total_steps": 1235, "loss": 0.2563, "lr": 1.401360788062871e-05, "epoch": 3.1862348178137654, "percentage": 63.72, "elapsed_time": "4:26:39", "remaining_time": "2:31:47"}
788
+ {"current_steps": 788, "total_steps": 1235, "loss": 0.2559, "lr": 1.3959670414070204e-05, "epoch": 3.1902834008097165, "percentage": 63.81, "elapsed_time": "4:26:59", "remaining_time": "2:31:27"}
789
+ {"current_steps": 789, "total_steps": 1235, "loss": 0.2409, "lr": 1.3905781245826108e-05, "epoch": 3.194331983805668, "percentage": 63.89, "elapsed_time": "4:27:16", "remaining_time": "2:31:05"}
790
+ {"current_steps": 790, "total_steps": 1235, "loss": 0.2295, "lr": 1.3851940806792778e-05, "epoch": 3.1983805668016196, "percentage": 63.97, "elapsed_time": "4:27:36", "remaining_time": "2:30:44"}
791
+ {"current_steps": 791, "total_steps": 1235, "loss": 0.2517, "lr": 1.379814952747693e-05, "epoch": 3.2024291497975708, "percentage": 64.05, "elapsed_time": "4:27:56", "remaining_time": "2:30:23"}
792
+ {"current_steps": 792, "total_steps": 1235, "loss": 0.2583, "lr": 1.3744407837992193e-05, "epoch": 3.2064777327935223, "percentage": 64.13, "elapsed_time": "4:28:14", "remaining_time": "2:30:02"}
793
+ {"current_steps": 793, "total_steps": 1235, "loss": 0.2604, "lr": 1.3690716168055692e-05, "epoch": 3.2105263157894735, "percentage": 64.21, "elapsed_time": "4:28:31", "remaining_time": "2:29:40"}
794
+ {"current_steps": 794, "total_steps": 1235, "loss": 0.2477, "lr": 1.363707494698459e-05, "epoch": 3.214574898785425, "percentage": 64.29, "elapsed_time": "4:28:51", "remaining_time": "2:29:19"}
795
+ {"current_steps": 795, "total_steps": 1235, "loss": 0.2578, "lr": 1.358348460369265e-05, "epoch": 3.2186234817813766, "percentage": 64.37, "elapsed_time": "4:29:12", "remaining_time": "2:28:59"}
796
+ {"current_steps": 796, "total_steps": 1235, "loss": 0.2475, "lr": 1.352994556668684e-05, "epoch": 3.2226720647773277, "percentage": 64.45, "elapsed_time": "4:29:33", "remaining_time": "2:28:39"}
797
+ {"current_steps": 797, "total_steps": 1235, "loss": 0.2479, "lr": 1.3476458264063865e-05, "epoch": 3.2267206477732793, "percentage": 64.53, "elapsed_time": "4:29:53", "remaining_time": "2:28:19"}
798
+ {"current_steps": 798, "total_steps": 1235, "loss": 0.2673, "lr": 1.342302312350678e-05, "epoch": 3.230769230769231, "percentage": 64.62, "elapsed_time": "4:30:13", "remaining_time": "2:27:58"}
799
+ {"current_steps": 799, "total_steps": 1235, "loss": 0.2549, "lr": 1.3369640572281537e-05, "epoch": 3.234817813765182, "percentage": 64.7, "elapsed_time": "4:30:35", "remaining_time": "2:27:39"}
800
+ {"current_steps": 800, "total_steps": 1235, "loss": 0.2688, "lr": 1.3316311037233596e-05, "epoch": 3.2388663967611335, "percentage": 64.78, "elapsed_time": "4:30:55", "remaining_time": "2:27:18"}
801
+ {"current_steps": 801, "total_steps": 1235, "loss": 0.2615, "lr": 1.326303494478451e-05, "epoch": 3.242914979757085, "percentage": 64.86, "elapsed_time": "4:31:12", "remaining_time": "2:26:57"}
802
+ {"current_steps": 802, "total_steps": 1235, "loss": 0.2736, "lr": 1.3209812720928472e-05, "epoch": 3.246963562753036, "percentage": 64.94, "elapsed_time": "4:31:31", "remaining_time": "2:26:35"}
803
+ {"current_steps": 803, "total_steps": 1235, "loss": 0.2486, "lr": 1.315664479122898e-05, "epoch": 3.251012145748988, "percentage": 65.02, "elapsed_time": "4:31:49", "remaining_time": "2:26:14"}
804
+ {"current_steps": 804, "total_steps": 1235, "loss": 0.2539, "lr": 1.3103531580815378e-05, "epoch": 3.2550607287449393, "percentage": 65.1, "elapsed_time": "4:32:07", "remaining_time": "2:25:52"}
805
+ {"current_steps": 805, "total_steps": 1235, "loss": 0.2505, "lr": 1.3050473514379488e-05, "epoch": 3.2591093117408905, "percentage": 65.18, "elapsed_time": "4:32:28", "remaining_time": "2:25:32"}
806
+ {"current_steps": 806, "total_steps": 1235, "loss": 0.248, "lr": 1.2997471016172188e-05, "epoch": 3.263157894736842, "percentage": 65.26, "elapsed_time": "4:32:47", "remaining_time": "2:25:11"}
807
+ {"current_steps": 807, "total_steps": 1235, "loss": 0.2531, "lr": 1.2944524510000042e-05, "epoch": 3.2672064777327936, "percentage": 65.34, "elapsed_time": "4:33:06", "remaining_time": "2:24:50"}
808
+ {"current_steps": 808, "total_steps": 1235, "loss": 0.2547, "lr": 1.2891634419221908e-05, "epoch": 3.2712550607287447, "percentage": 65.43, "elapsed_time": "4:33:28", "remaining_time": "2:24:31"}
809
+ {"current_steps": 809, "total_steps": 1235, "loss": 0.2506, "lr": 1.2838801166745545e-05, "epoch": 3.2753036437246963, "percentage": 65.51, "elapsed_time": "4:33:51", "remaining_time": "2:24:12"}
810
+ {"current_steps": 810, "total_steps": 1235, "loss": 0.2454, "lr": 1.2786025175024216e-05, "epoch": 3.279352226720648, "percentage": 65.59, "elapsed_time": "4:34:11", "remaining_time": "2:23:52"}
811
+ {"current_steps": 811, "total_steps": 1235, "loss": 0.2626, "lr": 1.2733306866053357e-05, "epoch": 3.283400809716599, "percentage": 65.67, "elapsed_time": "4:34:34", "remaining_time": "2:23:33"}
812
+ {"current_steps": 812, "total_steps": 1235, "loss": 0.2669, "lr": 1.2680646661367163e-05, "epoch": 3.2874493927125505, "percentage": 65.75, "elapsed_time": "4:34:56", "remaining_time": "2:23:13"}
813
+ {"current_steps": 813, "total_steps": 1235, "loss": 0.2482, "lr": 1.2628044982035219e-05, "epoch": 3.291497975708502, "percentage": 65.83, "elapsed_time": "4:35:16", "remaining_time": "2:22:53"}
814
+ {"current_steps": 814, "total_steps": 1235, "loss": 0.2546, "lr": 1.2575502248659155e-05, "epoch": 3.2955465587044532, "percentage": 65.91, "elapsed_time": "4:35:36", "remaining_time": "2:22:32"}
815
+ {"current_steps": 815, "total_steps": 1235, "loss": 0.2459, "lr": 1.2523018881369269e-05, "epoch": 3.299595141700405, "percentage": 65.99, "elapsed_time": "4:35:58", "remaining_time": "2:22:13"}
816
+ {"current_steps": 816, "total_steps": 1235, "loss": 0.263, "lr": 1.2470595299821176e-05, "epoch": 3.3036437246963564, "percentage": 66.07, "elapsed_time": "4:36:20", "remaining_time": "2:21:53"}
817
+ {"current_steps": 817, "total_steps": 1235, "loss": 0.261, "lr": 1.2418231923192416e-05, "epoch": 3.3076923076923075, "percentage": 66.15, "elapsed_time": "4:36:40", "remaining_time": "2:21:33"}
818
+ {"current_steps": 818, "total_steps": 1235, "loss": 0.2711, "lr": 1.2365929170179165e-05, "epoch": 3.311740890688259, "percentage": 66.23, "elapsed_time": "4:36:58", "remaining_time": "2:21:11"}
819
+ {"current_steps": 819, "total_steps": 1235, "loss": 0.2515, "lr": 1.2313687458992848e-05, "epoch": 3.3157894736842106, "percentage": 66.32, "elapsed_time": "4:37:19", "remaining_time": "2:20:51"}
820
+ {"current_steps": 820, "total_steps": 1235, "loss": 0.2532, "lr": 1.2261507207356785e-05, "epoch": 3.3198380566801617, "percentage": 66.4, "elapsed_time": "4:37:36", "remaining_time": "2:20:29"}
821
+ {"current_steps": 821, "total_steps": 1235, "loss": 0.2611, "lr": 1.220938883250288e-05, "epoch": 3.3238866396761133, "percentage": 66.48, "elapsed_time": "4:37:56", "remaining_time": "2:20:09"}
822
+ {"current_steps": 822, "total_steps": 1235, "loss": 0.2483, "lr": 1.215733275116827e-05, "epoch": 3.327935222672065, "percentage": 66.56, "elapsed_time": "4:38:11", "remaining_time": "2:19:46"}
823
+ {"current_steps": 823, "total_steps": 1235, "loss": 0.2368, "lr": 1.2105339379592005e-05, "epoch": 3.331983805668016, "percentage": 66.64, "elapsed_time": "4:38:27", "remaining_time": "2:19:23"}
824
+ {"current_steps": 824, "total_steps": 1235, "loss": 0.2481, "lr": 1.2053409133511681e-05, "epoch": 3.3360323886639676, "percentage": 66.72, "elapsed_time": "4:38:49", "remaining_time": "2:19:04"}
825
+ {"current_steps": 825, "total_steps": 1235, "loss": 0.2449, "lr": 1.2001542428160173e-05, "epoch": 3.340080971659919, "percentage": 66.8, "elapsed_time": "4:39:10", "remaining_time": "2:18:44"}
826
+ {"current_steps": 826, "total_steps": 1235, "loss": 0.239, "lr": 1.1949739678262278e-05, "epoch": 3.3441295546558703, "percentage": 66.88, "elapsed_time": "4:39:26", "remaining_time": "2:18:22"}
827
+ {"current_steps": 827, "total_steps": 1235, "loss": 0.2541, "lr": 1.189800129803139e-05, "epoch": 3.348178137651822, "percentage": 66.96, "elapsed_time": "4:39:47", "remaining_time": "2:18:01"}
828
+ {"current_steps": 828, "total_steps": 1235, "loss": 0.2624, "lr": 1.1846327701166228e-05, "epoch": 3.3522267206477734, "percentage": 67.04, "elapsed_time": "4:40:07", "remaining_time": "2:17:41"}
829
+ {"current_steps": 829, "total_steps": 1235, "loss": 0.2613, "lr": 1.1794719300847493e-05, "epoch": 3.3562753036437245, "percentage": 67.13, "elapsed_time": "4:40:28", "remaining_time": "2:17:21"}
830
+ {"current_steps": 830, "total_steps": 1235, "loss": 0.2667, "lr": 1.1743176509734582e-05, "epoch": 3.360323886639676, "percentage": 67.21, "elapsed_time": "4:40:49", "remaining_time": "2:17:01"}
831
+ {"current_steps": 831, "total_steps": 1235, "loss": 0.2514, "lr": 1.1691699739962275e-05, "epoch": 3.3643724696356276, "percentage": 67.29, "elapsed_time": "4:41:08", "remaining_time": "2:16:40"}
832
+ {"current_steps": 832, "total_steps": 1235, "loss": 0.2676, "lr": 1.1640289403137456e-05, "epoch": 3.3684210526315788, "percentage": 67.37, "elapsed_time": "4:41:27", "remaining_time": "2:16:19"}
833
+ {"current_steps": 833, "total_steps": 1235, "loss": 0.2533, "lr": 1.1588945910335802e-05, "epoch": 3.3724696356275303, "percentage": 67.45, "elapsed_time": "4:41:47", "remaining_time": "2:15:59"}
834
+ {"current_steps": 834, "total_steps": 1235, "loss": 0.252, "lr": 1.1537669672098517e-05, "epoch": 3.376518218623482, "percentage": 67.53, "elapsed_time": "4:42:06", "remaining_time": "2:15:38"}
835
+ {"current_steps": 835, "total_steps": 1235, "loss": 0.2441, "lr": 1.1486461098429036e-05, "epoch": 3.380566801619433, "percentage": 67.61, "elapsed_time": "4:42:27", "remaining_time": "2:15:18"}
836
+ {"current_steps": 836, "total_steps": 1235, "loss": 0.246, "lr": 1.1435320598789747e-05, "epoch": 3.3846153846153846, "percentage": 67.69, "elapsed_time": "4:42:48", "remaining_time": "2:14:58"}
837
+ {"current_steps": 837, "total_steps": 1235, "loss": 0.244, "lr": 1.1384248582098736e-05, "epoch": 3.388663967611336, "percentage": 67.77, "elapsed_time": "4:43:08", "remaining_time": "2:14:38"}
838
+ {"current_steps": 838, "total_steps": 1235, "loss": 0.2378, "lr": 1.1333245456726467e-05, "epoch": 3.3927125506072873, "percentage": 67.85, "elapsed_time": "4:43:27", "remaining_time": "2:14:17"}
839
+ {"current_steps": 839, "total_steps": 1235, "loss": 0.2519, "lr": 1.128231163049258e-05, "epoch": 3.396761133603239, "percentage": 67.94, "elapsed_time": "4:43:48", "remaining_time": "2:13:57"}
840
+ {"current_steps": 840, "total_steps": 1235, "loss": 0.2474, "lr": 1.123144751066259e-05, "epoch": 3.4008097165991904, "percentage": 68.02, "elapsed_time": "4:44:08", "remaining_time": "2:13:36"}
841
+ {"current_steps": 841, "total_steps": 1235, "loss": 0.2574, "lr": 1.1180653503944657e-05, "epoch": 3.4048582995951415, "percentage": 68.1, "elapsed_time": "4:44:29", "remaining_time": "2:13:16"}
842
+ {"current_steps": 842, "total_steps": 1235, "loss": 0.2541, "lr": 1.1129930016486287e-05, "epoch": 3.408906882591093, "percentage": 68.18, "elapsed_time": "4:44:47", "remaining_time": "2:12:55"}
843
+ {"current_steps": 843, "total_steps": 1235, "loss": 0.2623, "lr": 1.107927745387114e-05, "epoch": 3.4129554655870447, "percentage": 68.26, "elapsed_time": "4:45:08", "remaining_time": "2:12:35"}
844
+ {"current_steps": 844, "total_steps": 1235, "loss": 0.2459, "lr": 1.1028696221115766e-05, "epoch": 3.417004048582996, "percentage": 68.34, "elapsed_time": "4:45:26", "remaining_time": "2:12:14"}
845
+ {"current_steps": 845, "total_steps": 1235, "loss": 0.2514, "lr": 1.0978186722666341e-05, "epoch": 3.4210526315789473, "percentage": 68.42, "elapsed_time": "4:45:46", "remaining_time": "2:11:53"}
846
+ {"current_steps": 846, "total_steps": 1235, "loss": 0.2545, "lr": 1.0927749362395475e-05, "epoch": 3.425101214574899, "percentage": 68.5, "elapsed_time": "4:46:05", "remaining_time": "2:11:33"}
847
+ {"current_steps": 847, "total_steps": 1235, "loss": 0.2456, "lr": 1.0877384543598954e-05, "epoch": 3.42914979757085, "percentage": 68.58, "elapsed_time": "4:46:23", "remaining_time": "2:11:11"}
848
+ {"current_steps": 848, "total_steps": 1235, "loss": 0.2673, "lr": 1.0827092668992529e-05, "epoch": 3.4331983805668016, "percentage": 68.66, "elapsed_time": "4:46:42", "remaining_time": "2:10:50"}
849
+ {"current_steps": 849, "total_steps": 1235, "loss": 0.234, "lr": 1.077687414070869e-05, "epoch": 3.437246963562753, "percentage": 68.74, "elapsed_time": "4:46:59", "remaining_time": "2:10:29"}
850
+ {"current_steps": 850, "total_steps": 1235, "loss": 0.2651, "lr": 1.0726729360293451e-05, "epoch": 3.4412955465587043, "percentage": 68.83, "elapsed_time": "4:47:20", "remaining_time": "2:10:08"}
851
+ {"current_steps": 851, "total_steps": 1235, "loss": 0.2553, "lr": 1.0676658728703147e-05, "epoch": 3.445344129554656, "percentage": 68.91, "elapsed_time": "4:47:41", "remaining_time": "2:09:48"}
852
+ {"current_steps": 852, "total_steps": 1235, "loss": 0.2526, "lr": 1.0626662646301198e-05, "epoch": 3.4493927125506074, "percentage": 68.99, "elapsed_time": "4:47:58", "remaining_time": "2:09:27"}
853
+ {"current_steps": 853, "total_steps": 1235, "loss": 0.2527, "lr": 1.0576741512854958e-05, "epoch": 3.4534412955465585, "percentage": 69.07, "elapsed_time": "4:48:19", "remaining_time": "2:09:07"}
854
+ {"current_steps": 854, "total_steps": 1235, "loss": 0.2578, "lr": 1.052689572753247e-05, "epoch": 3.45748987854251, "percentage": 69.15, "elapsed_time": "4:48:40", "remaining_time": "2:08:47"}
855
+ {"current_steps": 855, "total_steps": 1235, "loss": 0.2272, "lr": 1.0477125688899328e-05, "epoch": 3.4615384615384617, "percentage": 69.23, "elapsed_time": "4:48:56", "remaining_time": "2:08:25"}
856
+ {"current_steps": 856, "total_steps": 1235, "loss": 0.2737, "lr": 1.0427431794915406e-05, "epoch": 3.465587044534413, "percentage": 69.31, "elapsed_time": "4:49:16", "remaining_time": "2:08:04"}
857
+ {"current_steps": 857, "total_steps": 1235, "loss": 0.2536, "lr": 1.0377814442931769e-05, "epoch": 3.4696356275303644, "percentage": 69.39, "elapsed_time": "4:49:36", "remaining_time": "2:07:44"}
858
+ {"current_steps": 858, "total_steps": 1235, "loss": 0.2569, "lr": 1.0328274029687439e-05, "epoch": 3.473684210526316, "percentage": 69.47, "elapsed_time": "4:49:56", "remaining_time": "2:07:24"}
859
+ {"current_steps": 859, "total_steps": 1235, "loss": 0.2562, "lr": 1.0278810951306253e-05, "epoch": 3.477732793522267, "percentage": 69.55, "elapsed_time": "4:50:16", "remaining_time": "2:07:03"}
860
+ {"current_steps": 860, "total_steps": 1235, "loss": 0.2591, "lr": 1.0229425603293647e-05, "epoch": 3.4817813765182186, "percentage": 69.64, "elapsed_time": "4:50:38", "remaining_time": "2:06:43"}
861
+ {"current_steps": 861, "total_steps": 1235, "loss": 0.265, "lr": 1.0180118380533558e-05, "epoch": 3.48582995951417, "percentage": 69.72, "elapsed_time": "4:50:58", "remaining_time": "2:06:23"}
862
+ {"current_steps": 862, "total_steps": 1235, "loss": 0.2482, "lr": 1.0130889677285225e-05, "epoch": 3.4898785425101213, "percentage": 69.8, "elapsed_time": "4:51:18", "remaining_time": "2:06:03"}
863
+ {"current_steps": 863, "total_steps": 1235, "loss": 0.2583, "lr": 1.008173988718005e-05, "epoch": 3.493927125506073, "percentage": 69.88, "elapsed_time": "4:51:38", "remaining_time": "2:05:42"}
864
+ {"current_steps": 864, "total_steps": 1235, "loss": 0.2476, "lr": 1.0032669403218439e-05, "epoch": 3.4979757085020244, "percentage": 69.96, "elapsed_time": "4:51:57", "remaining_time": "2:05:21"}
865
+ {"current_steps": 865, "total_steps": 1235, "loss": 0.2489, "lr": 9.983678617766677e-06, "epoch": 3.5020242914979756, "percentage": 70.04, "elapsed_time": "4:52:18", "remaining_time": "2:05:02"}
866
+ {"current_steps": 866, "total_steps": 1235, "loss": 0.2538, "lr": 9.934767922553788e-06, "epoch": 3.506072874493927, "percentage": 70.12, "elapsed_time": "4:52:38", "remaining_time": "2:04:41"}
867
+ {"current_steps": 867, "total_steps": 1235, "loss": 0.2712, "lr": 9.885937708668371e-06, "epoch": 3.5101214574898787, "percentage": 70.2, "elapsed_time": "4:52:58", "remaining_time": "2:04:21"}
868
+ {"current_steps": 868, "total_steps": 1235, "loss": 0.2727, "lr": 9.837188366555524e-06, "epoch": 3.51417004048583, "percentage": 70.28, "elapsed_time": "4:53:16", "remaining_time": "2:04:00"}
869
+ {"current_steps": 869, "total_steps": 1235, "loss": 0.2613, "lr": 9.788520286013691e-06, "epoch": 3.5182186234817814, "percentage": 70.36, "elapsed_time": "4:53:36", "remaining_time": "2:03:39"}
870
+ {"current_steps": 870, "total_steps": 1235, "loss": 0.2475, "lr": 9.739933856191537e-06, "epoch": 3.522267206477733, "percentage": 70.45, "elapsed_time": "4:53:57", "remaining_time": "2:03:19"}
871
+ {"current_steps": 871, "total_steps": 1235, "loss": 0.2518, "lr": 9.691429465584866e-06, "epoch": 3.526315789473684, "percentage": 70.53, "elapsed_time": "4:54:18", "remaining_time": "2:02:59"}
872
+ {"current_steps": 872, "total_steps": 1235, "loss": 0.2534, "lr": 9.643007502033492e-06, "epoch": 3.5303643724696356, "percentage": 70.61, "elapsed_time": "4:54:36", "remaining_time": "2:02:38"}
873
+ {"current_steps": 873, "total_steps": 1235, "loss": 0.2641, "lr": 9.594668352718152e-06, "epoch": 3.534412955465587, "percentage": 70.69, "elapsed_time": "4:54:54", "remaining_time": "2:02:17"}
874
+ {"current_steps": 874, "total_steps": 1235, "loss": 0.2715, "lr": 9.546412404157383e-06, "epoch": 3.5384615384615383, "percentage": 70.77, "elapsed_time": "4:55:12", "remaining_time": "2:01:55"}
875
+ {"current_steps": 875, "total_steps": 1235, "loss": 0.2764, "lr": 9.498240042204471e-06, "epoch": 3.54251012145749, "percentage": 70.85, "elapsed_time": "4:55:31", "remaining_time": "2:01:35"}
876
+ {"current_steps": 876, "total_steps": 1235, "loss": 0.2667, "lr": 9.450151652044339e-06, "epoch": 3.5465587044534415, "percentage": 70.93, "elapsed_time": "4:55:52", "remaining_time": "2:01:15"}
877
+ {"current_steps": 877, "total_steps": 1235, "loss": 0.2692, "lr": 9.402147618190472e-06, "epoch": 3.5506072874493926, "percentage": 71.01, "elapsed_time": "4:56:14", "remaining_time": "2:00:55"}
878
+ {"current_steps": 878, "total_steps": 1235, "loss": 0.2443, "lr": 9.354228324481841e-06, "epoch": 3.554655870445344, "percentage": 71.09, "elapsed_time": "4:56:38", "remaining_time": "2:00:36"}
879
+ {"current_steps": 879, "total_steps": 1235, "loss": 0.2563, "lr": 9.306394154079852e-06, "epoch": 3.5587044534412957, "percentage": 71.17, "elapsed_time": "4:56:58", "remaining_time": "2:00:16"}
880
+ {"current_steps": 880, "total_steps": 1235, "loss": 0.2462, "lr": 9.258645489465254e-06, "epoch": 3.562753036437247, "percentage": 71.26, "elapsed_time": "4:57:20", "remaining_time": "1:59:56"}
881
+ {"current_steps": 881, "total_steps": 1235, "loss": 0.2616, "lr": 9.21098271243509e-06, "epoch": 3.5668016194331984, "percentage": 71.34, "elapsed_time": "4:57:39", "remaining_time": "1:59:36"}
882
+ {"current_steps": 882, "total_steps": 1235, "loss": 0.2609, "lr": 9.163406204099659e-06, "epoch": 3.57085020242915, "percentage": 71.42, "elapsed_time": "4:58:01", "remaining_time": "1:59:16"}
883
+ {"current_steps": 883, "total_steps": 1235, "loss": 0.2642, "lr": 9.115916344879452e-06, "epoch": 3.574898785425101, "percentage": 71.5, "elapsed_time": "4:58:19", "remaining_time": "1:58:55"}
884
+ {"current_steps": 884, "total_steps": 1235, "loss": 0.2449, "lr": 9.068513514502126e-06, "epoch": 3.5789473684210527, "percentage": 71.58, "elapsed_time": "4:58:40", "remaining_time": "1:58:35"}
885
+ {"current_steps": 885, "total_steps": 1235, "loss": 0.2644, "lr": 9.021198091999439e-06, "epoch": 3.582995951417004, "percentage": 71.66, "elapsed_time": "4:59:01", "remaining_time": "1:58:15"}
886
+ {"current_steps": 886, "total_steps": 1235, "loss": 0.2447, "lr": 8.973970455704251e-06, "epoch": 3.5870445344129553, "percentage": 71.74, "elapsed_time": "4:59:23", "remaining_time": "1:57:55"}
887
+ {"current_steps": 887, "total_steps": 1235, "loss": 0.2606, "lr": 8.926830983247495e-06, "epoch": 3.591093117408907, "percentage": 71.82, "elapsed_time": "4:59:42", "remaining_time": "1:57:35"}
888
+ {"current_steps": 888, "total_steps": 1235, "loss": 0.2522, "lr": 8.879780051555116e-06, "epoch": 3.5951417004048585, "percentage": 71.9, "elapsed_time": "5:00:00", "remaining_time": "1:57:14"}
889
+ {"current_steps": 889, "total_steps": 1235, "loss": 0.2505, "lr": 8.83281803684512e-06, "epoch": 3.5991902834008096, "percentage": 71.98, "elapsed_time": "5:00:22", "remaining_time": "1:56:54"}
890
+ {"current_steps": 890, "total_steps": 1235, "loss": 0.2548, "lr": 8.785945314624532e-06, "epoch": 3.603238866396761, "percentage": 72.06, "elapsed_time": "5:00:45", "remaining_time": "1:56:35"}
891
+ {"current_steps": 891, "total_steps": 1235, "loss": 0.2646, "lr": 8.739162259686385e-06, "epoch": 3.6072874493927127, "percentage": 72.15, "elapsed_time": "5:01:04", "remaining_time": "1:56:14"}
892
+ {"current_steps": 892, "total_steps": 1235, "loss": 0.2388, "lr": 8.692469246106734e-06, "epoch": 3.611336032388664, "percentage": 72.23, "elapsed_time": "5:01:22", "remaining_time": "1:55:53"}
893
+ {"current_steps": 893, "total_steps": 1235, "loss": 0.2562, "lr": 8.645866647241677e-06, "epoch": 3.6153846153846154, "percentage": 72.31, "elapsed_time": "5:01:42", "remaining_time": "1:55:32"}
894
+ {"current_steps": 894, "total_steps": 1235, "loss": 0.2545, "lr": 8.599354835724348e-06, "epoch": 3.619433198380567, "percentage": 72.39, "elapsed_time": "5:02:01", "remaining_time": "1:55:12"}
895
+ {"current_steps": 895, "total_steps": 1235, "loss": 0.2323, "lr": 8.552934183461958e-06, "epoch": 3.623481781376518, "percentage": 72.47, "elapsed_time": "5:02:21", "remaining_time": "1:54:51"}
896
+ {"current_steps": 896, "total_steps": 1235, "loss": 0.2737, "lr": 8.506605061632805e-06, "epoch": 3.6275303643724697, "percentage": 72.55, "elapsed_time": "5:02:43", "remaining_time": "1:54:32"}
897
+ {"current_steps": 897, "total_steps": 1235, "loss": 0.237, "lr": 8.460367840683308e-06, "epoch": 3.6315789473684212, "percentage": 72.63, "elapsed_time": "5:02:59", "remaining_time": "1:54:10"}
898
+ {"current_steps": 898, "total_steps": 1235, "loss": 0.2759, "lr": 8.414222890325065e-06, "epoch": 3.6356275303643724, "percentage": 72.71, "elapsed_time": "5:03:21", "remaining_time": "1:53:50"}
899
+ {"current_steps": 899, "total_steps": 1235, "loss": 0.2695, "lr": 8.368170579531855e-06, "epoch": 3.639676113360324, "percentage": 72.79, "elapsed_time": "5:03:42", "remaining_time": "1:53:30"}
900
+ {"current_steps": 900, "total_steps": 1235, "loss": 0.2565, "lr": 8.322211276536733e-06, "epoch": 3.6437246963562755, "percentage": 72.87, "elapsed_time": "5:04:01", "remaining_time": "1:53:09"}
901
+ {"current_steps": 901, "total_steps": 1235, "loss": 0.2524, "lr": 8.27634534882907e-06, "epoch": 3.6477732793522266, "percentage": 72.96, "elapsed_time": "5:04:21", "remaining_time": "1:52:49"}
902
+ {"current_steps": 902, "total_steps": 1235, "loss": 0.2557, "lr": 8.230573163151585e-06, "epoch": 3.651821862348178, "percentage": 73.04, "elapsed_time": "5:04:39", "remaining_time": "1:52:28"}
903
+ {"current_steps": 903, "total_steps": 1235, "loss": 0.2487, "lr": 8.184895085497466e-06, "epoch": 3.6558704453441297, "percentage": 73.12, "elapsed_time": "5:04:59", "remaining_time": "1:52:08"}
904
+ {"current_steps": 904, "total_steps": 1235, "loss": 0.2459, "lr": 8.139311481107401e-06, "epoch": 3.659919028340081, "percentage": 73.2, "elapsed_time": "5:05:17", "remaining_time": "1:51:46"}
905
+ {"current_steps": 905, "total_steps": 1235, "loss": 0.24, "lr": 8.093822714466686e-06, "epoch": 3.6639676113360324, "percentage": 73.28, "elapsed_time": "5:05:38", "remaining_time": "1:51:26"}
906
+ {"current_steps": 906, "total_steps": 1235, "loss": 0.2476, "lr": 8.048429149302271e-06, "epoch": 3.668016194331984, "percentage": 73.36, "elapsed_time": "5:05:56", "remaining_time": "1:51:05"}
907
+ {"current_steps": 907, "total_steps": 1235, "loss": 0.2518, "lr": 8.003131148579902e-06, "epoch": 3.672064777327935, "percentage": 73.44, "elapsed_time": "5:06:18", "remaining_time": "1:50:46"}
908
+ {"current_steps": 908, "total_steps": 1235, "loss": 0.2502, "lr": 7.957929074501182e-06, "epoch": 3.6761133603238867, "percentage": 73.52, "elapsed_time": "5:06:39", "remaining_time": "1:50:26"}
909
+ {"current_steps": 909, "total_steps": 1235, "loss": 0.2483, "lr": 7.912823288500695e-06, "epoch": 3.6801619433198383, "percentage": 73.6, "elapsed_time": "5:07:00", "remaining_time": "1:50:06"}
910
+ {"current_steps": 910, "total_steps": 1235, "loss": 0.2612, "lr": 7.867814151243102e-06, "epoch": 3.6842105263157894, "percentage": 73.68, "elapsed_time": "5:07:19", "remaining_time": "1:49:45"}
911
+ {"current_steps": 911, "total_steps": 1235, "loss": 0.2472, "lr": 7.822902022620267e-06, "epoch": 3.688259109311741, "percentage": 73.77, "elapsed_time": "5:07:40", "remaining_time": "1:49:25"}
912
+ {"current_steps": 912, "total_steps": 1235, "loss": 0.2696, "lr": 7.778087261748377e-06, "epoch": 3.6923076923076925, "percentage": 73.85, "elapsed_time": "5:07:57", "remaining_time": "1:49:04"}
913
+ {"current_steps": 913, "total_steps": 1235, "loss": 0.2646, "lr": 7.733370226965056e-06, "epoch": 3.6963562753036436, "percentage": 73.93, "elapsed_time": "5:08:18", "remaining_time": "1:48:44"}
914
+ {"current_steps": 914, "total_steps": 1235, "loss": 0.2424, "lr": 7.688751275826527e-06, "epoch": 3.700404858299595, "percentage": 74.01, "elapsed_time": "5:08:37", "remaining_time": "1:48:23"}
915
+ {"current_steps": 915, "total_steps": 1235, "loss": 0.2597, "lr": 7.644230765104735e-06, "epoch": 3.7044534412955468, "percentage": 74.09, "elapsed_time": "5:08:58", "remaining_time": "1:48:03"}
916
+ {"current_steps": 916, "total_steps": 1235, "loss": 0.2398, "lr": 7.599809050784502e-06, "epoch": 3.708502024291498, "percentage": 74.17, "elapsed_time": "5:09:17", "remaining_time": "1:47:42"}
917
+ {"current_steps": 917, "total_steps": 1235, "loss": 0.2334, "lr": 7.555486488060661e-06, "epoch": 3.7125506072874495, "percentage": 74.25, "elapsed_time": "5:09:35", "remaining_time": "1:47:21"}
918
+ {"current_steps": 918, "total_steps": 1235, "loss": 0.26, "lr": 7.511263431335249e-06, "epoch": 3.716599190283401, "percentage": 74.33, "elapsed_time": "5:09:54", "remaining_time": "1:47:00"}
919
+ {"current_steps": 919, "total_steps": 1235, "loss": 0.2529, "lr": 7.467140234214656e-06, "epoch": 3.720647773279352, "percentage": 74.41, "elapsed_time": "5:10:13", "remaining_time": "1:46:40"}
920
+ {"current_steps": 920, "total_steps": 1235, "loss": 0.2291, "lr": 7.423117249506777e-06, "epoch": 3.7246963562753037, "percentage": 74.49, "elapsed_time": "5:10:33", "remaining_time": "1:46:19"}
921
+ {"current_steps": 921, "total_steps": 1235, "loss": 0.2494, "lr": 7.379194829218231e-06, "epoch": 3.7287449392712553, "percentage": 74.57, "elapsed_time": "5:10:52", "remaining_time": "1:45:59"}
922
+ {"current_steps": 922, "total_steps": 1235, "loss": 0.2495, "lr": 7.335373324551518e-06, "epoch": 3.7327935222672064, "percentage": 74.66, "elapsed_time": "5:11:13", "remaining_time": "1:45:39"}
923
+ {"current_steps": 923, "total_steps": 1235, "loss": 0.2498, "lr": 7.291653085902224e-06, "epoch": 3.736842105263158, "percentage": 74.74, "elapsed_time": "5:11:32", "remaining_time": "1:45:18"}
924
+ {"current_steps": 924, "total_steps": 1235, "loss": 0.2565, "lr": 7.248034462856213e-06, "epoch": 3.7408906882591095, "percentage": 74.82, "elapsed_time": "5:11:52", "remaining_time": "1:44:58"}
925
+ {"current_steps": 925, "total_steps": 1235, "loss": 0.261, "lr": 7.20451780418683e-06, "epoch": 3.7449392712550607, "percentage": 74.9, "elapsed_time": "5:12:13", "remaining_time": "1:44:38"}
926
+ {"current_steps": 926, "total_steps": 1235, "loss": 0.2494, "lr": 7.161103457852128e-06, "epoch": 3.748987854251012, "percentage": 74.98, "elapsed_time": "5:12:32", "remaining_time": "1:44:17"}
927
+ {"current_steps": 927, "total_steps": 1235, "loss": 0.2586, "lr": 7.117791770992046e-06, "epoch": 3.753036437246964, "percentage": 75.06, "elapsed_time": "5:12:52", "remaining_time": "1:43:57"}
928
+ {"current_steps": 928, "total_steps": 1235, "loss": 0.2525, "lr": 7.074583089925688e-06, "epoch": 3.757085020242915, "percentage": 75.14, "elapsed_time": "5:13:13", "remaining_time": "1:43:37"}
929
+ {"current_steps": 929, "total_steps": 1235, "loss": 0.2433, "lr": 7.0314777601485155e-06, "epoch": 3.7611336032388665, "percentage": 75.22, "elapsed_time": "5:13:33", "remaining_time": "1:43:16"}
930
+ {"current_steps": 930, "total_steps": 1235, "loss": 0.2567, "lr": 6.988476126329604e-06, "epoch": 3.765182186234818, "percentage": 75.3, "elapsed_time": "5:13:53", "remaining_time": "1:42:56"}
931
+ {"current_steps": 931, "total_steps": 1235, "loss": 0.2609, "lr": 6.945578532308857e-06, "epoch": 3.769230769230769, "percentage": 75.38, "elapsed_time": "5:14:11", "remaining_time": "1:42:35"}
932
+ {"current_steps": 932, "total_steps": 1235, "loss": 0.2603, "lr": 6.902785321094301e-06, "epoch": 3.7732793522267207, "percentage": 75.47, "elapsed_time": "5:14:32", "remaining_time": "1:42:15"}
933
+ {"current_steps": 933, "total_steps": 1235, "loss": 0.251, "lr": 6.8600968348593115e-06, "epoch": 3.7773279352226723, "percentage": 75.55, "elapsed_time": "5:14:54", "remaining_time": "1:41:55"}
934
+ {"current_steps": 934, "total_steps": 1235, "loss": 0.2439, "lr": 6.817513414939892e-06, "epoch": 3.7813765182186234, "percentage": 75.63, "elapsed_time": "5:15:12", "remaining_time": "1:41:34"}
935
+ {"current_steps": 935, "total_steps": 1235, "loss": 0.2272, "lr": 6.775035401831924e-06, "epoch": 3.785425101214575, "percentage": 75.71, "elapsed_time": "5:15:31", "remaining_time": "1:41:14"}
936
+ {"current_steps": 936, "total_steps": 1235, "loss": 0.238, "lr": 6.732663135188473e-06, "epoch": 3.7894736842105265, "percentage": 75.79, "elapsed_time": "5:15:48", "remaining_time": "1:40:53"}
937
+ {"current_steps": 937, "total_steps": 1235, "loss": 0.2485, "lr": 6.690396953817055e-06, "epoch": 3.7935222672064777, "percentage": 75.87, "elapsed_time": "5:16:10", "remaining_time": "1:40:33"}
938
+ {"current_steps": 938, "total_steps": 1235, "loss": 0.2506, "lr": 6.648237195676927e-06, "epoch": 3.7975708502024292, "percentage": 75.95, "elapsed_time": "5:16:30", "remaining_time": "1:40:13"}
939
+ {"current_steps": 939, "total_steps": 1235, "loss": 0.2565, "lr": 6.606184197876395e-06, "epoch": 3.801619433198381, "percentage": 76.03, "elapsed_time": "5:16:49", "remaining_time": "1:39:52"}
940
+ {"current_steps": 940, "total_steps": 1235, "loss": 0.2462, "lr": 6.564238296670109e-06, "epoch": 3.805668016194332, "percentage": 76.11, "elapsed_time": "5:17:09", "remaining_time": "1:39:32"}
941
+ {"current_steps": 941, "total_steps": 1235, "loss": 0.2512, "lr": 6.52239982745638e-06, "epoch": 3.8097165991902835, "percentage": 76.19, "elapsed_time": "5:17:29", "remaining_time": "1:39:11"}
942
+ {"current_steps": 942, "total_steps": 1235, "loss": 0.2768, "lr": 6.480669124774484e-06, "epoch": 3.813765182186235, "percentage": 76.28, "elapsed_time": "5:17:51", "remaining_time": "1:38:52"}
943
+ {"current_steps": 943, "total_steps": 1235, "loss": 0.2445, "lr": 6.439046522302013e-06, "epoch": 3.817813765182186, "percentage": 76.36, "elapsed_time": "5:18:09", "remaining_time": "1:38:31"}
944
+ {"current_steps": 944, "total_steps": 1235, "loss": 0.2514, "lr": 6.397532352852191e-06, "epoch": 3.8218623481781377, "percentage": 76.44, "elapsed_time": "5:18:29", "remaining_time": "1:38:10"}
945
+ {"current_steps": 945, "total_steps": 1235, "loss": 0.243, "lr": 6.356126948371202e-06, "epoch": 3.8259109311740893, "percentage": 76.52, "elapsed_time": "5:18:46", "remaining_time": "1:37:49"}
946
+ {"current_steps": 946, "total_steps": 1235, "loss": 0.2592, "lr": 6.314830639935559e-06, "epoch": 3.8299595141700404, "percentage": 76.6, "elapsed_time": "5:19:04", "remaining_time": "1:37:28"}
947
+ {"current_steps": 947, "total_steps": 1235, "loss": 0.2441, "lr": 6.273643757749448e-06, "epoch": 3.834008097165992, "percentage": 76.68, "elapsed_time": "5:19:27", "remaining_time": "1:37:09"}
948
+ {"current_steps": 948, "total_steps": 1235, "loss": 0.2432, "lr": 6.2325666311420856e-06, "epoch": 3.8380566801619436, "percentage": 76.76, "elapsed_time": "5:19:46", "remaining_time": "1:36:48"}
949
+ {"current_steps": 949, "total_steps": 1235, "loss": 0.2456, "lr": 6.1915995885650675e-06, "epoch": 3.8421052631578947, "percentage": 76.84, "elapsed_time": "5:20:09", "remaining_time": "1:36:29"}
950
+ {"current_steps": 950, "total_steps": 1235, "loss": 0.2301, "lr": 6.150742957589784e-06, "epoch": 3.8461538461538463, "percentage": 76.92, "elapsed_time": "5:20:29", "remaining_time": "1:36:08"}
951
+ {"current_steps": 951, "total_steps": 1235, "loss": 0.267, "lr": 6.109997064904774e-06, "epoch": 3.850202429149798, "percentage": 77.0, "elapsed_time": "5:20:45", "remaining_time": "1:35:47"}
952
+ {"current_steps": 952, "total_steps": 1235, "loss": 0.2629, "lr": 6.069362236313092e-06, "epoch": 3.854251012145749, "percentage": 77.09, "elapsed_time": "5:21:05", "remaining_time": "1:35:27"}
953
+ {"current_steps": 953, "total_steps": 1235, "loss": 0.2507, "lr": 6.0288387967297565e-06, "epoch": 3.8582995951417005, "percentage": 77.17, "elapsed_time": "5:21:25", "remaining_time": "1:35:06"}
954
+ {"current_steps": 954, "total_steps": 1235, "loss": 0.2476, "lr": 5.988427070179108e-06, "epoch": 3.862348178137652, "percentage": 77.25, "elapsed_time": "5:21:46", "remaining_time": "1:34:46"}
955
+ {"current_steps": 955, "total_steps": 1235, "loss": 0.2443, "lr": 5.948127379792234e-06, "epoch": 3.866396761133603, "percentage": 77.33, "elapsed_time": "5:22:04", "remaining_time": "1:34:25"}
956
+ {"current_steps": 956, "total_steps": 1235, "loss": 0.261, "lr": 5.90794004780439e-06, "epoch": 3.8704453441295548, "percentage": 77.41, "elapsed_time": "5:22:25", "remaining_time": "1:34:05"}
957
+ {"current_steps": 957, "total_steps": 1235, "loss": 0.2547, "lr": 5.867865395552405e-06, "epoch": 3.8744939271255063, "percentage": 77.49, "elapsed_time": "5:22:46", "remaining_time": "1:33:45"}
958
+ {"current_steps": 958, "total_steps": 1235, "loss": 0.2475, "lr": 5.8279037434721364e-06, "epoch": 3.8785425101214575, "percentage": 77.57, "elapsed_time": "5:23:05", "remaining_time": "1:33:25"}
959
+ {"current_steps": 959, "total_steps": 1235, "loss": 0.2585, "lr": 5.788055411095892e-06, "epoch": 3.882591093117409, "percentage": 77.65, "elapsed_time": "5:23:24", "remaining_time": "1:33:04"}
960
+ {"current_steps": 960, "total_steps": 1235, "loss": 0.2498, "lr": 5.7483207170498625e-06, "epoch": 3.8866396761133606, "percentage": 77.73, "elapsed_time": "5:23:46", "remaining_time": "1:32:44"}
961
+ {"current_steps": 961, "total_steps": 1235, "loss": 0.2497, "lr": 5.708699979051613e-06, "epoch": 3.8906882591093117, "percentage": 77.81, "elapsed_time": "5:24:06", "remaining_time": "1:32:24"}
962
+ {"current_steps": 962, "total_steps": 1235, "loss": 0.2486, "lr": 5.66919351390751e-06, "epoch": 3.8947368421052633, "percentage": 77.89, "elapsed_time": "5:24:27", "remaining_time": "1:32:04"}
963
+ {"current_steps": 963, "total_steps": 1235, "loss": 0.2411, "lr": 5.629801637510188e-06, "epoch": 3.898785425101215, "percentage": 77.98, "elapsed_time": "5:24:47", "remaining_time": "1:31:44"}
964
+ {"current_steps": 964, "total_steps": 1235, "loss": 0.2408, "lr": 5.590524664836043e-06, "epoch": 3.902834008097166, "percentage": 78.06, "elapsed_time": "5:25:09", "remaining_time": "1:31:24"}
965
+ {"current_steps": 965, "total_steps": 1235, "loss": 0.2693, "lr": 5.551362909942708e-06, "epoch": 3.9068825910931175, "percentage": 78.14, "elapsed_time": "5:25:27", "remaining_time": "1:31:03"}
966
+ {"current_steps": 966, "total_steps": 1235, "loss": 0.2546, "lr": 5.51231668596653e-06, "epoch": 3.910931174089069, "percentage": 78.22, "elapsed_time": "5:25:48", "remaining_time": "1:30:43"}
967
+ {"current_steps": 967, "total_steps": 1235, "loss": 0.2618, "lr": 5.47338630512007e-06, "epoch": 3.91497975708502, "percentage": 78.3, "elapsed_time": "5:26:08", "remaining_time": "1:30:23"}
968
+ {"current_steps": 968, "total_steps": 1235, "loss": 0.2628, "lr": 5.434572078689617e-06, "epoch": 3.919028340080972, "percentage": 78.38, "elapsed_time": "5:26:29", "remaining_time": "1:30:03"}
969
+ {"current_steps": 969, "total_steps": 1235, "loss": 0.2465, "lr": 5.395874317032694e-06, "epoch": 3.9230769230769234, "percentage": 78.46, "elapsed_time": "5:26:46", "remaining_time": "1:29:42"}
970
+ {"current_steps": 970, "total_steps": 1235, "loss": 0.2442, "lr": 5.357293329575573e-06, "epoch": 3.9271255060728745, "percentage": 78.54, "elapsed_time": "5:27:04", "remaining_time": "1:29:21"}
971
+ {"current_steps": 971, "total_steps": 1235, "loss": 0.2457, "lr": 5.318829424810797e-06, "epoch": 3.931174089068826, "percentage": 78.62, "elapsed_time": "5:27:24", "remaining_time": "1:29:01"}
972
+ {"current_steps": 972, "total_steps": 1235, "loss": 0.2673, "lr": 5.280482910294728e-06, "epoch": 3.9352226720647776, "percentage": 78.7, "elapsed_time": "5:27:44", "remaining_time": "1:28:40"}
973
+ {"current_steps": 973, "total_steps": 1235, "loss": 0.2548, "lr": 5.242254092645078e-06, "epoch": 3.9392712550607287, "percentage": 78.79, "elapsed_time": "5:28:07", "remaining_time": "1:28:21"}
974
+ {"current_steps": 974, "total_steps": 1235, "loss": 0.2691, "lr": 5.2041432775384445e-06, "epoch": 3.9433198380566803, "percentage": 78.87, "elapsed_time": "5:28:29", "remaining_time": "1:28:01"}
975
+ {"current_steps": 975, "total_steps": 1235, "loss": 0.2505, "lr": 5.166150769707892e-06, "epoch": 3.9473684210526314, "percentage": 78.95, "elapsed_time": "5:28:49", "remaining_time": "1:27:41"}
976
+ {"current_steps": 976, "total_steps": 1235, "loss": 0.2588, "lr": 5.128276872940503e-06, "epoch": 3.951417004048583, "percentage": 79.03, "elapsed_time": "5:29:09", "remaining_time": "1:27:20"}
977
+ {"current_steps": 977, "total_steps": 1235, "loss": 0.2593, "lr": 5.090521890074953e-06, "epoch": 3.9554655870445345, "percentage": 79.11, "elapsed_time": "5:29:28", "remaining_time": "1:27:00"}
978
+ {"current_steps": 978, "total_steps": 1235, "loss": 0.2384, "lr": 5.0528861229990675e-06, "epoch": 3.9595141700404857, "percentage": 79.19, "elapsed_time": "5:29:49", "remaining_time": "1:26:40"}
979
+ {"current_steps": 979, "total_steps": 1235, "loss": 0.2647, "lr": 5.015369872647442e-06, "epoch": 3.9635627530364372, "percentage": 79.27, "elapsed_time": "5:30:08", "remaining_time": "1:26:19"}
980
+ {"current_steps": 980, "total_steps": 1235, "loss": 0.2541, "lr": 4.9779734389990195e-06, "epoch": 3.967611336032389, "percentage": 79.35, "elapsed_time": "5:30:29", "remaining_time": "1:25:59"}
981
+ {"current_steps": 981, "total_steps": 1235, "loss": 0.2391, "lr": 4.940697121074675e-06, "epoch": 3.97165991902834, "percentage": 79.43, "elapsed_time": "5:30:49", "remaining_time": "1:25:39"}
982
+ {"current_steps": 982, "total_steps": 1235, "loss": 0.2713, "lr": 4.903541216934864e-06, "epoch": 3.9757085020242915, "percentage": 79.51, "elapsed_time": "5:31:10", "remaining_time": "1:25:19"}
983
+ {"current_steps": 983, "total_steps": 1235, "loss": 0.2505, "lr": 4.8665060236772e-06, "epoch": 3.979757085020243, "percentage": 79.6, "elapsed_time": "5:31:30", "remaining_time": "1:24:59"}
984
+ {"current_steps": 984, "total_steps": 1235, "loss": 0.2491, "lr": 4.829591837434102e-06, "epoch": 3.983805668016194, "percentage": 79.68, "elapsed_time": "5:31:47", "remaining_time": "1:24:38"}
985
+ {"current_steps": 985, "total_steps": 1235, "loss": 0.2392, "lr": 4.792798953370424e-06, "epoch": 3.9878542510121457, "percentage": 79.76, "elapsed_time": "5:32:07", "remaining_time": "1:24:17"}
986
+ {"current_steps": 986, "total_steps": 1235, "loss": 0.2622, "lr": 4.756127665681083e-06, "epoch": 3.9919028340080973, "percentage": 79.84, "elapsed_time": "5:32:28", "remaining_time": "1:23:57"}
987
+ {"current_steps": 987, "total_steps": 1235, "loss": 0.2584, "lr": 4.719578267588725e-06, "epoch": 3.9959514170040484, "percentage": 79.92, "elapsed_time": "5:32:51", "remaining_time": "1:23:38"}
988
+ {"current_steps": 988, "total_steps": 1235, "loss": 0.2555, "lr": 4.6831510513413525e-06, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "5:33:09", "remaining_time": "1:23:17"}
989
+ {"current_steps": 989, "total_steps": 1235, "loss": 0.1892, "lr": 4.6468463082100176e-06, "epoch": 4.004048582995951, "percentage": 80.08, "elapsed_time": "5:35:13", "remaining_time": "1:23:23"}
990
+ {"current_steps": 990, "total_steps": 1235, "loss": 0.1995, "lr": 4.610664328486485e-06, "epoch": 4.008097165991903, "percentage": 80.16, "elapsed_time": "5:35:35", "remaining_time": "1:23:02"}
991
+ {"current_steps": 991, "total_steps": 1235, "loss": 0.1747, "lr": 4.5746054014809e-06, "epoch": 4.012145748987854, "percentage": 80.24, "elapsed_time": "5:35:52", "remaining_time": "1:22:41"}
992
+ {"current_steps": 992, "total_steps": 1235, "loss": 0.1948, "lr": 4.5386698155194766e-06, "epoch": 4.016194331983805, "percentage": 80.32, "elapsed_time": "5:36:13", "remaining_time": "1:22:21"}
993
+ {"current_steps": 993, "total_steps": 1235, "loss": 0.2028, "lr": 4.502857857942204e-06, "epoch": 4.020242914979757, "percentage": 80.4, "elapsed_time": "5:36:34", "remaining_time": "1:22:01"}
994
+ {"current_steps": 994, "total_steps": 1235, "loss": 0.1927, "lr": 4.467169815100549e-06, "epoch": 4.0242914979757085, "percentage": 80.49, "elapsed_time": "5:36:55", "remaining_time": "1:21:41"}
995
+ {"current_steps": 995, "total_steps": 1235, "loss": 0.2008, "lr": 4.431605972355137e-06, "epoch": 4.02834008097166, "percentage": 80.57, "elapsed_time": "5:37:16", "remaining_time": "1:21:21"}
996
+ {"current_steps": 996, "total_steps": 1235, "loss": 0.1939, "lr": 4.396166614073516e-06, "epoch": 4.032388663967612, "percentage": 80.65, "elapsed_time": "5:37:37", "remaining_time": "1:21:00"}