gsmyrnis commited on
Commit
6b74401
·
verified ·
1 Parent(s): 89049aa

Training in progress, epoch 3

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bfaf4723d4e1c2ed979c007b255fdc6149d2ccbb756f0de145204cfcbb1ea05
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61c501cc79e5ac14965f4ce643d6e9fdccdfb066c04875a9b3219a1dbccd36ff
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:b341160beb7a2f638f04695102ef464525feb8ae55aeb3e1787a0fe7e8929b21
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bfdce1342609240892426be1b5c8fa04208768816b982e13e034214255e96ba
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0668592770d4704f0fb75bf222963ec92b6e9886062eef40812ca5a3405d4f4d
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:579c295ed980a0e135ca6d925650564931b248a29575132c7bad0b5a9215e9d6
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cbae243b541cf5c1d1ec5a5ec7d164947a7436e25349d240207f24189b978b8
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e9f39f054883097036dec3c75d13ca6361bf1660b7271a00ed50cb062ae216b
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -500,3 +500,250 @@
500
  {"current_steps": 500, "total_steps": 1235, "loss": 0.2726, "lr": 2.972118904869376e-05, "epoch": 2.0242914979757085, "percentage": 40.49, "elapsed_time": "2:44:35", "remaining_time": "4:01:57"}
501
  {"current_steps": 501, "total_steps": 1235, "loss": 0.268, "lr": 2.9671725970312563e-05, "epoch": 2.02834008097166, "percentage": 40.57, "elapsed_time": "2:44:54", "remaining_time": "4:01:36"}
502
  {"current_steps": 502, "total_steps": 1235, "loss": 0.2925, "lr": 2.9622185557068238e-05, "epoch": 2.032388663967611, "percentage": 40.65, "elapsed_time": "2:45:13", "remaining_time": "4:01:15"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
500
  {"current_steps": 500, "total_steps": 1235, "loss": 0.2726, "lr": 2.972118904869376e-05, "epoch": 2.0242914979757085, "percentage": 40.49, "elapsed_time": "2:44:35", "remaining_time": "4:01:57"}
501
  {"current_steps": 501, "total_steps": 1235, "loss": 0.268, "lr": 2.9671725970312563e-05, "epoch": 2.02834008097166, "percentage": 40.57, "elapsed_time": "2:44:54", "remaining_time": "4:01:36"}
502
  {"current_steps": 502, "total_steps": 1235, "loss": 0.2925, "lr": 2.9622185557068238e-05, "epoch": 2.032388663967611, "percentage": 40.65, "elapsed_time": "2:45:13", "remaining_time": "4:01:15"}
503
+ {"current_steps": 503, "total_steps": 1235, "loss": 0.2716, "lr": 2.95725682050846e-05, "epoch": 2.0364372469635628, "percentage": 40.73, "elapsed_time": "2:45:33", "remaining_time": "4:00:55"}
504
+ {"current_steps": 504, "total_steps": 1235, "loss": 0.2812, "lr": 2.9522874311100684e-05, "epoch": 2.0404858299595143, "percentage": 40.81, "elapsed_time": "2:45:54", "remaining_time": "4:00:37"}
505
+ {"current_steps": 505, "total_steps": 1235, "loss": 0.2811, "lr": 2.9473104272467526e-05, "epoch": 2.0445344129554655, "percentage": 40.89, "elapsed_time": "2:46:14", "remaining_time": "4:00:18"}
506
+ {"current_steps": 506, "total_steps": 1235, "loss": 0.2711, "lr": 2.942325848714505e-05, "epoch": 2.048582995951417, "percentage": 40.97, "elapsed_time": "2:46:32", "remaining_time": "3:59:56"}
507
+ {"current_steps": 507, "total_steps": 1235, "loss": 0.2869, "lr": 2.9373337353698804e-05, "epoch": 2.0526315789473686, "percentage": 41.05, "elapsed_time": "2:46:51", "remaining_time": "3:59:35"}
508
+ {"current_steps": 508, "total_steps": 1235, "loss": 0.2958, "lr": 2.932334127129686e-05, "epoch": 2.0566801619433197, "percentage": 41.13, "elapsed_time": "2:47:13", "remaining_time": "3:59:18"}
509
+ {"current_steps": 509, "total_steps": 1235, "loss": 0.2884, "lr": 2.9273270639706547e-05, "epoch": 2.0607287449392713, "percentage": 41.21, "elapsed_time": "2:47:34", "remaining_time": "3:59:01"}
510
+ {"current_steps": 510, "total_steps": 1235, "loss": 0.2823, "lr": 2.922312585929131e-05, "epoch": 2.064777327935223, "percentage": 41.3, "elapsed_time": "2:47:51", "remaining_time": "3:58:37"}
511
+ {"current_steps": 511, "total_steps": 1235, "loss": 0.3129, "lr": 2.9172907331007478e-05, "epoch": 2.068825910931174, "percentage": 41.38, "elapsed_time": "2:48:12", "remaining_time": "3:58:19"}
512
+ {"current_steps": 512, "total_steps": 1235, "loss": 0.2842, "lr": 2.9122615456401053e-05, "epoch": 2.0728744939271255, "percentage": 41.46, "elapsed_time": "2:48:29", "remaining_time": "3:57:55"}
513
+ {"current_steps": 513, "total_steps": 1235, "loss": 0.2734, "lr": 2.9072250637604535e-05, "epoch": 2.076923076923077, "percentage": 41.54, "elapsed_time": "2:48:53", "remaining_time": "3:57:41"}
514
+ {"current_steps": 514, "total_steps": 1235, "loss": 0.2795, "lr": 2.9021813277333667e-05, "epoch": 2.080971659919028, "percentage": 41.62, "elapsed_time": "2:49:11", "remaining_time": "3:57:19"}
515
+ {"current_steps": 515, "total_steps": 1235, "loss": 0.2686, "lr": 2.8971303778884244e-05, "epoch": 2.08502024291498, "percentage": 41.7, "elapsed_time": "2:49:32", "remaining_time": "3:57:02"}
516
+ {"current_steps": 516, "total_steps": 1235, "loss": 0.3021, "lr": 2.8920722546128863e-05, "epoch": 2.0890688259109313, "percentage": 41.78, "elapsed_time": "2:49:51", "remaining_time": "3:56:40"}
517
+ {"current_steps": 517, "total_steps": 1235, "loss": 0.2668, "lr": 2.887006998351372e-05, "epoch": 2.0931174089068825, "percentage": 41.86, "elapsed_time": "2:50:11", "remaining_time": "3:56:21"}
518
+ {"current_steps": 518, "total_steps": 1235, "loss": 0.2845, "lr": 2.881934649605535e-05, "epoch": 2.097165991902834, "percentage": 41.94, "elapsed_time": "2:50:29", "remaining_time": "3:55:59"}
519
+ {"current_steps": 519, "total_steps": 1235, "loss": 0.2836, "lr": 2.8768552489337408e-05, "epoch": 2.1012145748987856, "percentage": 42.02, "elapsed_time": "2:50:48", "remaining_time": "3:55:38"}
520
+ {"current_steps": 520, "total_steps": 1235, "loss": 0.2683, "lr": 2.8717688369507425e-05, "epoch": 2.1052631578947367, "percentage": 42.11, "elapsed_time": "2:51:06", "remaining_time": "3:55:16"}
521
+ {"current_steps": 521, "total_steps": 1235, "loss": 0.2561, "lr": 2.8666754543273535e-05, "epoch": 2.1093117408906883, "percentage": 42.19, "elapsed_time": "2:51:20", "remaining_time": "3:54:48"}
522
+ {"current_steps": 522, "total_steps": 1235, "loss": 0.2833, "lr": 2.8615751417901273e-05, "epoch": 2.11336032388664, "percentage": 42.27, "elapsed_time": "2:51:38", "remaining_time": "3:54:26"}
523
+ {"current_steps": 523, "total_steps": 1235, "loss": 0.2903, "lr": 2.856467940121025e-05, "epoch": 2.117408906882591, "percentage": 42.35, "elapsed_time": "2:52:01", "remaining_time": "3:54:11"}
524
+ {"current_steps": 524, "total_steps": 1235, "loss": 0.2719, "lr": 2.8513538901570964e-05, "epoch": 2.1214574898785425, "percentage": 42.43, "elapsed_time": "2:52:22", "remaining_time": "3:53:53"}
525
+ {"current_steps": 525, "total_steps": 1235, "loss": 0.2924, "lr": 2.846233032790149e-05, "epoch": 2.125506072874494, "percentage": 42.51, "elapsed_time": "2:52:43", "remaining_time": "3:53:34"}
526
+ {"current_steps": 526, "total_steps": 1235, "loss": 0.2832, "lr": 2.84110540896642e-05, "epoch": 2.1295546558704452, "percentage": 42.59, "elapsed_time": "2:53:02", "remaining_time": "3:53:14"}
527
+ {"current_steps": 527, "total_steps": 1235, "loss": 0.29, "lr": 2.8359710596862555e-05, "epoch": 2.133603238866397, "percentage": 42.67, "elapsed_time": "2:53:21", "remaining_time": "3:52:53"}
528
+ {"current_steps": 528, "total_steps": 1235, "loss": 0.2868, "lr": 2.8308300260037734e-05, "epoch": 2.1376518218623484, "percentage": 42.75, "elapsed_time": "2:53:43", "remaining_time": "3:52:37"}
529
+ {"current_steps": 529, "total_steps": 1235, "loss": 0.288, "lr": 2.8256823490265424e-05, "epoch": 2.1417004048582995, "percentage": 42.83, "elapsed_time": "2:54:01", "remaining_time": "3:52:15"}
530
+ {"current_steps": 530, "total_steps": 1235, "loss": 0.279, "lr": 2.8205280699152515e-05, "epoch": 2.145748987854251, "percentage": 42.91, "elapsed_time": "2:54:19", "remaining_time": "3:51:53"}
531
+ {"current_steps": 531, "total_steps": 1235, "loss": 0.2806, "lr": 2.8153672298833777e-05, "epoch": 2.1497975708502026, "percentage": 43.0, "elapsed_time": "2:54:37", "remaining_time": "3:51:31"}
532
+ {"current_steps": 532, "total_steps": 1235, "loss": 0.2652, "lr": 2.8101998701968615e-05, "epoch": 2.1538461538461537, "percentage": 43.08, "elapsed_time": "2:54:57", "remaining_time": "3:51:11"}
533
+ {"current_steps": 533, "total_steps": 1235, "loss": 0.2834, "lr": 2.805026032173773e-05, "epoch": 2.1578947368421053, "percentage": 43.16, "elapsed_time": "2:55:19", "remaining_time": "3:50:54"}
534
+ {"current_steps": 534, "total_steps": 1235, "loss": 0.2689, "lr": 2.7998457571839832e-05, "epoch": 2.161943319838057, "percentage": 43.24, "elapsed_time": "2:55:36", "remaining_time": "3:50:31"}
535
+ {"current_steps": 535, "total_steps": 1235, "loss": 0.2982, "lr": 2.7946590866488322e-05, "epoch": 2.165991902834008, "percentage": 43.32, "elapsed_time": "2:55:55", "remaining_time": "3:50:11"}
536
+ {"current_steps": 536, "total_steps": 1235, "loss": 0.2932, "lr": 2.7894660620408e-05, "epoch": 2.1700404858299596, "percentage": 43.4, "elapsed_time": "2:56:13", "remaining_time": "3:49:49"}
537
+ {"current_steps": 537, "total_steps": 1235, "loss": 0.2667, "lr": 2.784266724883173e-05, "epoch": 2.174089068825911, "percentage": 43.48, "elapsed_time": "2:56:32", "remaining_time": "3:49:28"}
538
+ {"current_steps": 538, "total_steps": 1235, "loss": 0.2838, "lr": 2.7790611167497128e-05, "epoch": 2.1781376518218623, "percentage": 43.56, "elapsed_time": "2:56:50", "remaining_time": "3:49:06"}
539
+ {"current_steps": 539, "total_steps": 1235, "loss": 0.2878, "lr": 2.7738492792643224e-05, "epoch": 2.182186234817814, "percentage": 43.64, "elapsed_time": "2:57:11", "remaining_time": "3:48:47"}
540
+ {"current_steps": 540, "total_steps": 1235, "loss": 0.2928, "lr": 2.768631254100716e-05, "epoch": 2.1862348178137654, "percentage": 43.72, "elapsed_time": "2:57:32", "remaining_time": "3:48:30"}
541
+ {"current_steps": 541, "total_steps": 1235, "loss": 0.2861, "lr": 2.7634070829820836e-05, "epoch": 2.1902834008097165, "percentage": 43.81, "elapsed_time": "2:57:52", "remaining_time": "3:48:10"}
542
+ {"current_steps": 542, "total_steps": 1235, "loss": 0.2711, "lr": 2.7581768076807592e-05, "epoch": 2.194331983805668, "percentage": 43.89, "elapsed_time": "2:58:08", "remaining_time": "3:47:46"}
543
+ {"current_steps": 543, "total_steps": 1235, "loss": 0.2959, "lr": 2.7529404700178832e-05, "epoch": 2.1983805668016196, "percentage": 43.97, "elapsed_time": "2:58:29", "remaining_time": "3:47:27"}
544
+ {"current_steps": 544, "total_steps": 1235, "loss": 0.3121, "lr": 2.7476981118630735e-05, "epoch": 2.2024291497975708, "percentage": 44.05, "elapsed_time": "2:58:53", "remaining_time": "3:47:13"}
545
+ {"current_steps": 545, "total_steps": 1235, "loss": 0.2863, "lr": 2.742449775134085e-05, "epoch": 2.2064777327935223, "percentage": 44.13, "elapsed_time": "2:59:13", "remaining_time": "3:46:54"}
546
+ {"current_steps": 546, "total_steps": 1235, "loss": 0.3079, "lr": 2.7371955017964788e-05, "epoch": 2.2105263157894735, "percentage": 44.21, "elapsed_time": "2:59:32", "remaining_time": "3:46:33"}
547
+ {"current_steps": 547, "total_steps": 1235, "loss": 0.2841, "lr": 2.7319353338632845e-05, "epoch": 2.214574898785425, "percentage": 44.29, "elapsed_time": "2:59:51", "remaining_time": "3:46:13"}
548
+ {"current_steps": 548, "total_steps": 1235, "loss": 0.2789, "lr": 2.7266693133946645e-05, "epoch": 2.2186234817813766, "percentage": 44.37, "elapsed_time": "3:00:08", "remaining_time": "3:45:49"}
549
+ {"current_steps": 549, "total_steps": 1235, "loss": 0.272, "lr": 2.7213974824975785e-05, "epoch": 2.2226720647773277, "percentage": 44.45, "elapsed_time": "3:00:29", "remaining_time": "3:45:32"}
550
+ {"current_steps": 550, "total_steps": 1235, "loss": 0.2898, "lr": 2.7161198833254464e-05, "epoch": 2.2267206477732793, "percentage": 44.53, "elapsed_time": "3:00:49", "remaining_time": "3:45:12"}
551
+ {"current_steps": 551, "total_steps": 1235, "loss": 0.2819, "lr": 2.7108365580778095e-05, "epoch": 2.230769230769231, "percentage": 44.62, "elapsed_time": "3:01:10", "remaining_time": "3:44:54"}
552
+ {"current_steps": 552, "total_steps": 1235, "loss": 0.2777, "lr": 2.705547548999996e-05, "epoch": 2.234817813765182, "percentage": 44.7, "elapsed_time": "3:01:27", "remaining_time": "3:44:31"}
553
+ {"current_steps": 553, "total_steps": 1235, "loss": 0.2669, "lr": 2.7002528983827817e-05, "epoch": 2.2388663967611335, "percentage": 44.78, "elapsed_time": "3:01:43", "remaining_time": "3:44:07"}
554
+ {"current_steps": 554, "total_steps": 1235, "loss": 0.2856, "lr": 2.6949526485620517e-05, "epoch": 2.242914979757085, "percentage": 44.86, "elapsed_time": "3:02:03", "remaining_time": "3:43:47"}
555
+ {"current_steps": 555, "total_steps": 1235, "loss": 0.2897, "lr": 2.6896468419184623e-05, "epoch": 2.246963562753036, "percentage": 44.94, "elapsed_time": "3:02:23", "remaining_time": "3:43:27"}
556
+ {"current_steps": 556, "total_steps": 1235, "loss": 0.2894, "lr": 2.6843355208771024e-05, "epoch": 2.251012145748988, "percentage": 45.02, "elapsed_time": "3:02:45", "remaining_time": "3:43:11"}
557
+ {"current_steps": 557, "total_steps": 1235, "loss": 0.2996, "lr": 2.6790187279071536e-05, "epoch": 2.2550607287449393, "percentage": 45.1, "elapsed_time": "3:03:05", "remaining_time": "3:42:52"}
558
+ {"current_steps": 558, "total_steps": 1235, "loss": 0.2784, "lr": 2.67369650552155e-05, "epoch": 2.2591093117408905, "percentage": 45.18, "elapsed_time": "3:03:27", "remaining_time": "3:42:34"}
559
+ {"current_steps": 559, "total_steps": 1235, "loss": 0.2928, "lr": 2.6683688962766407e-05, "epoch": 2.263157894736842, "percentage": 45.26, "elapsed_time": "3:03:47", "remaining_time": "3:42:14"}
560
+ {"current_steps": 560, "total_steps": 1235, "loss": 0.2739, "lr": 2.6630359427718468e-05, "epoch": 2.2672064777327936, "percentage": 45.34, "elapsed_time": "3:04:04", "remaining_time": "3:41:52"}
561
+ {"current_steps": 561, "total_steps": 1235, "loss": 0.2722, "lr": 2.6576976876493225e-05, "epoch": 2.2712550607287447, "percentage": 45.43, "elapsed_time": "3:04:17", "remaining_time": "3:41:24"}
562
+ {"current_steps": 562, "total_steps": 1235, "loss": 0.2871, "lr": 2.652354173593614e-05, "epoch": 2.2753036437246963, "percentage": 45.51, "elapsed_time": "3:04:36", "remaining_time": "3:41:04"}
563
+ {"current_steps": 563, "total_steps": 1235, "loss": 0.2869, "lr": 2.647005443331317e-05, "epoch": 2.279352226720648, "percentage": 45.59, "elapsed_time": "3:04:56", "remaining_time": "3:40:45"}
564
+ {"current_steps": 564, "total_steps": 1235, "loss": 0.2794, "lr": 2.6416515396307354e-05, "epoch": 2.283400809716599, "percentage": 45.67, "elapsed_time": "3:05:14", "remaining_time": "3:40:23"}
565
+ {"current_steps": 565, "total_steps": 1235, "loss": 0.2956, "lr": 2.636292505301542e-05, "epoch": 2.2874493927125505, "percentage": 45.75, "elapsed_time": "3:05:34", "remaining_time": "3:40:03"}
566
+ {"current_steps": 566, "total_steps": 1235, "loss": 0.2819, "lr": 2.630928383194431e-05, "epoch": 2.291497975708502, "percentage": 45.83, "elapsed_time": "3:05:55", "remaining_time": "3:39:46"}
567
+ {"current_steps": 567, "total_steps": 1235, "loss": 0.2997, "lr": 2.625559216200781e-05, "epoch": 2.2955465587044532, "percentage": 45.91, "elapsed_time": "3:06:13", "remaining_time": "3:39:24"}
568
+ {"current_steps": 568, "total_steps": 1235, "loss": 0.2879, "lr": 2.620185047252308e-05, "epoch": 2.299595141700405, "percentage": 45.99, "elapsed_time": "3:06:29", "remaining_time": "3:38:59"}
569
+ {"current_steps": 569, "total_steps": 1235, "loss": 0.2867, "lr": 2.614805919320723e-05, "epoch": 2.3036437246963564, "percentage": 46.07, "elapsed_time": "3:06:45", "remaining_time": "3:38:36"}
570
+ {"current_steps": 570, "total_steps": 1235, "loss": 0.2844, "lr": 2.6094218754173895e-05, "epoch": 2.3076923076923075, "percentage": 46.15, "elapsed_time": "3:07:04", "remaining_time": "3:38:15"}
571
+ {"current_steps": 571, "total_steps": 1235, "loss": 0.2864, "lr": 2.60403295859298e-05, "epoch": 2.311740890688259, "percentage": 46.23, "elapsed_time": "3:07:25", "remaining_time": "3:37:57"}
572
+ {"current_steps": 572, "total_steps": 1235, "loss": 0.3025, "lr": 2.5986392119371297e-05, "epoch": 2.3157894736842106, "percentage": 46.32, "elapsed_time": "3:07:44", "remaining_time": "3:37:36"}
573
+ {"current_steps": 573, "total_steps": 1235, "loss": 0.2921, "lr": 2.5932406785780928e-05, "epoch": 2.3198380566801617, "percentage": 46.4, "elapsed_time": "3:08:05", "remaining_time": "3:37:18"}
574
+ {"current_steps": 574, "total_steps": 1235, "loss": 0.2807, "lr": 2.5878374016823987e-05, "epoch": 2.3238866396761133, "percentage": 46.48, "elapsed_time": "3:08:25", "remaining_time": "3:36:59"}
575
+ {"current_steps": 575, "total_steps": 1235, "loss": 0.2823, "lr": 2.5824294244545045e-05, "epoch": 2.327935222672065, "percentage": 46.56, "elapsed_time": "3:08:45", "remaining_time": "3:36:40"}
576
+ {"current_steps": 576, "total_steps": 1235, "loss": 0.2693, "lr": 2.577016790136453e-05, "epoch": 2.331983805668016, "percentage": 46.64, "elapsed_time": "3:09:07", "remaining_time": "3:36:23"}
577
+ {"current_steps": 577, "total_steps": 1235, "loss": 0.2822, "lr": 2.5715995420075225e-05, "epoch": 2.3360323886639676, "percentage": 46.72, "elapsed_time": "3:09:26", "remaining_time": "3:36:02"}
578
+ {"current_steps": 578, "total_steps": 1235, "loss": 0.2934, "lr": 2.5661777233838864e-05, "epoch": 2.340080971659919, "percentage": 46.8, "elapsed_time": "3:09:47", "remaining_time": "3:35:44"}
579
+ {"current_steps": 579, "total_steps": 1235, "loss": 0.2708, "lr": 2.5607513776182616e-05, "epoch": 2.3441295546558703, "percentage": 46.88, "elapsed_time": "3:10:02", "remaining_time": "3:35:19"}
580
+ {"current_steps": 580, "total_steps": 1235, "loss": 0.2897, "lr": 2.5553205480995633e-05, "epoch": 2.348178137651822, "percentage": 46.96, "elapsed_time": "3:10:22", "remaining_time": "3:35:00"}
581
+ {"current_steps": 581, "total_steps": 1235, "loss": 0.3007, "lr": 2.5498852782525604e-05, "epoch": 2.3522267206477734, "percentage": 47.04, "elapsed_time": "3:10:43", "remaining_time": "3:34:41"}
582
+ {"current_steps": 582, "total_steps": 1235, "loss": 0.2998, "lr": 2.5444456115375252e-05, "epoch": 2.3562753036437245, "percentage": 47.13, "elapsed_time": "3:11:03", "remaining_time": "3:34:21"}
583
+ {"current_steps": 583, "total_steps": 1235, "loss": 0.2987, "lr": 2.539001591449889e-05, "epoch": 2.360323886639676, "percentage": 47.21, "elapsed_time": "3:11:26", "remaining_time": "3:34:05"}
584
+ {"current_steps": 584, "total_steps": 1235, "loss": 0.2771, "lr": 2.53355326151989e-05, "epoch": 2.3643724696356276, "percentage": 47.29, "elapsed_time": "3:11:45", "remaining_time": "3:33:45"}
585
+ {"current_steps": 585, "total_steps": 1235, "loss": 0.2681, "lr": 2.5281006653122288e-05, "epoch": 2.3684210526315788, "percentage": 47.37, "elapsed_time": "3:12:07", "remaining_time": "3:33:27"}
586
+ {"current_steps": 586, "total_steps": 1235, "loss": 0.2928, "lr": 2.5226438464257217e-05, "epoch": 2.3724696356275303, "percentage": 47.45, "elapsed_time": "3:12:25", "remaining_time": "3:33:06"}
587
+ {"current_steps": 587, "total_steps": 1235, "loss": 0.2883, "lr": 2.5171828484929447e-05, "epoch": 2.376518218623482, "percentage": 47.53, "elapsed_time": "3:12:43", "remaining_time": "3:32:45"}
588
+ {"current_steps": 588, "total_steps": 1235, "loss": 0.2719, "lr": 2.5117177151798934e-05, "epoch": 2.380566801619433, "percentage": 47.61, "elapsed_time": "3:13:07", "remaining_time": "3:32:29"}
589
+ {"current_steps": 589, "total_steps": 1235, "loss": 0.2766, "lr": 2.506248490185627e-05, "epoch": 2.3846153846153846, "percentage": 47.69, "elapsed_time": "3:13:24", "remaining_time": "3:32:07"}
590
+ {"current_steps": 590, "total_steps": 1235, "loss": 0.2771, "lr": 2.500775217241923e-05, "epoch": 2.388663967611336, "percentage": 47.77, "elapsed_time": "3:13:42", "remaining_time": "3:31:45"}
591
+ {"current_steps": 591, "total_steps": 1235, "loss": 0.2905, "lr": 2.4952979401129266e-05, "epoch": 2.3927125506072873, "percentage": 47.85, "elapsed_time": "3:14:03", "remaining_time": "3:31:27"}
592
+ {"current_steps": 592, "total_steps": 1235, "loss": 0.2812, "lr": 2.4898167025948e-05, "epoch": 2.396761133603239, "percentage": 47.94, "elapsed_time": "3:14:19", "remaining_time": "3:31:04"}
593
+ {"current_steps": 593, "total_steps": 1235, "loss": 0.2839, "lr": 2.4843315485153703e-05, "epoch": 2.4008097165991904, "percentage": 48.02, "elapsed_time": "3:14:34", "remaining_time": "3:30:38"}
594
+ {"current_steps": 594, "total_steps": 1235, "loss": 0.277, "lr": 2.4788425217337856e-05, "epoch": 2.4048582995951415, "percentage": 48.1, "elapsed_time": "3:14:52", "remaining_time": "3:30:17"}
595
+ {"current_steps": 595, "total_steps": 1235, "loss": 0.271, "lr": 2.4733496661401572e-05, "epoch": 2.408906882591093, "percentage": 48.18, "elapsed_time": "3:15:10", "remaining_time": "3:29:56"}
596
+ {"current_steps": 596, "total_steps": 1235, "loss": 0.2931, "lr": 2.4678530256552114e-05, "epoch": 2.4129554655870447, "percentage": 48.26, "elapsed_time": "3:15:31", "remaining_time": "3:29:37"}
597
+ {"current_steps": 597, "total_steps": 1235, "loss": 0.2851, "lr": 2.46235264422994e-05, "epoch": 2.417004048582996, "percentage": 48.34, "elapsed_time": "3:15:51", "remaining_time": "3:29:18"}
598
+ {"current_steps": 598, "total_steps": 1235, "loss": 0.2938, "lr": 2.4568485658452452e-05, "epoch": 2.4210526315789473, "percentage": 48.42, "elapsed_time": "3:16:13", "remaining_time": "3:29:01"}
599
+ {"current_steps": 599, "total_steps": 1235, "loss": 0.2943, "lr": 2.451340834511592e-05, "epoch": 2.425101214574899, "percentage": 48.5, "elapsed_time": "3:16:33", "remaining_time": "3:28:41"}
600
+ {"current_steps": 600, "total_steps": 1235, "loss": 0.3047, "lr": 2.4458294942686528e-05, "epoch": 2.42914979757085, "percentage": 48.58, "elapsed_time": "3:16:54", "remaining_time": "3:28:24"}
601
+ {"current_steps": 601, "total_steps": 1235, "loss": 0.28, "lr": 2.440314589184958e-05, "epoch": 2.4331983805668016, "percentage": 48.66, "elapsed_time": "3:17:13", "remaining_time": "3:28:03"}
602
+ {"current_steps": 602, "total_steps": 1235, "loss": 0.2673, "lr": 2.434796163357541e-05, "epoch": 2.437246963562753, "percentage": 48.74, "elapsed_time": "3:17:34", "remaining_time": "3:27:44"}
603
+ {"current_steps": 603, "total_steps": 1235, "loss": 0.291, "lr": 2.429274260911588e-05, "epoch": 2.4412955465587043, "percentage": 48.83, "elapsed_time": "3:17:52", "remaining_time": "3:27:23"}
604
+ {"current_steps": 604, "total_steps": 1235, "loss": 0.2778, "lr": 2.423748926000084e-05, "epoch": 2.445344129554656, "percentage": 48.91, "elapsed_time": "3:18:11", "remaining_time": "3:27:03"}
605
+ {"current_steps": 605, "total_steps": 1235, "loss": 0.2829, "lr": 2.418220202803459e-05, "epoch": 2.4493927125506074, "percentage": 48.99, "elapsed_time": "3:18:31", "remaining_time": "3:26:44"}
606
+ {"current_steps": 606, "total_steps": 1235, "loss": 0.2737, "lr": 2.412688135529237e-05, "epoch": 2.4534412955465585, "percentage": 49.07, "elapsed_time": "3:18:49", "remaining_time": "3:26:22"}
607
+ {"current_steps": 607, "total_steps": 1235, "loss": 0.2771, "lr": 2.4071527684116807e-05, "epoch": 2.45748987854251, "percentage": 49.15, "elapsed_time": "3:19:09", "remaining_time": "3:26:03"}
608
+ {"current_steps": 608, "total_steps": 1235, "loss": 0.2879, "lr": 2.4016141457114372e-05, "epoch": 2.4615384615384617, "percentage": 49.23, "elapsed_time": "3:19:29", "remaining_time": "3:25:43"}
609
+ {"current_steps": 609, "total_steps": 1235, "loss": 0.2776, "lr": 2.396072311715187e-05, "epoch": 2.465587044534413, "percentage": 49.31, "elapsed_time": "3:19:48", "remaining_time": "3:25:22"}
610
+ {"current_steps": 610, "total_steps": 1235, "loss": 0.2742, "lr": 2.3905273107352863e-05, "epoch": 2.4696356275303644, "percentage": 49.39, "elapsed_time": "3:20:07", "remaining_time": "3:25:02"}
611
+ {"current_steps": 611, "total_steps": 1235, "loss": 0.3132, "lr": 2.3849791871094157e-05, "epoch": 2.473684210526316, "percentage": 49.47, "elapsed_time": "3:20:29", "remaining_time": "3:24:45"}
612
+ {"current_steps": 612, "total_steps": 1235, "loss": 0.2757, "lr": 2.379427985200223e-05, "epoch": 2.477732793522267, "percentage": 49.55, "elapsed_time": "3:20:49", "remaining_time": "3:24:26"}
613
+ {"current_steps": 613, "total_steps": 1235, "loss": 0.2889, "lr": 2.373873749394972e-05, "epoch": 2.4817813765182186, "percentage": 49.64, "elapsed_time": "3:21:12", "remaining_time": "3:24:09"}
614
+ {"current_steps": 614, "total_steps": 1235, "loss": 0.2971, "lr": 2.3683165241051836e-05, "epoch": 2.48582995951417, "percentage": 49.72, "elapsed_time": "3:21:33", "remaining_time": "3:23:51"}
615
+ {"current_steps": 615, "total_steps": 1235, "loss": 0.2825, "lr": 2.3627563537662823e-05, "epoch": 2.4898785425101213, "percentage": 49.8, "elapsed_time": "3:21:46", "remaining_time": "3:23:24"}
616
+ {"current_steps": 616, "total_steps": 1235, "loss": 0.3069, "lr": 2.3571932828372433e-05, "epoch": 2.493927125506073, "percentage": 49.88, "elapsed_time": "3:22:04", "remaining_time": "3:23:03"}
617
+ {"current_steps": 617, "total_steps": 1235, "loss": 0.2858, "lr": 2.351627355800233e-05, "epoch": 2.4979757085020244, "percentage": 49.96, "elapsed_time": "3:22:24", "remaining_time": "3:22:44"}
618
+ {"current_steps": 618, "total_steps": 1235, "loss": 0.2954, "lr": 2.346058617160256e-05, "epoch": 2.5020242914979756, "percentage": 50.04, "elapsed_time": "3:22:41", "remaining_time": "3:22:21"}
619
+ {"current_steps": 619, "total_steps": 1235, "loss": 0.283, "lr": 2.3404871114447976e-05, "epoch": 2.506072874493927, "percentage": 50.12, "elapsed_time": "3:23:04", "remaining_time": "3:22:05"}
620
+ {"current_steps": 620, "total_steps": 1235, "loss": 0.2797, "lr": 2.334912883203469e-05, "epoch": 2.5101214574898787, "percentage": 50.2, "elapsed_time": "3:23:21", "remaining_time": "3:21:43"}
621
+ {"current_steps": 621, "total_steps": 1235, "loss": 0.2886, "lr": 2.3293359770076505e-05, "epoch": 2.51417004048583, "percentage": 50.28, "elapsed_time": "3:23:39", "remaining_time": "3:21:21"}
622
+ {"current_steps": 622, "total_steps": 1235, "loss": 0.2909, "lr": 2.323756437450136e-05, "epoch": 2.5182186234817814, "percentage": 50.36, "elapsed_time": "3:23:56", "remaining_time": "3:20:59"}
623
+ {"current_steps": 623, "total_steps": 1235, "loss": 0.2763, "lr": 2.3181743091447754e-05, "epoch": 2.522267206477733, "percentage": 50.45, "elapsed_time": "3:24:14", "remaining_time": "3:20:38"}
624
+ {"current_steps": 624, "total_steps": 1235, "loss": 0.2746, "lr": 2.3125896367261164e-05, "epoch": 2.526315789473684, "percentage": 50.53, "elapsed_time": "3:24:31", "remaining_time": "3:20:15"}
625
+ {"current_steps": 625, "total_steps": 1235, "loss": 0.2633, "lr": 2.307002464849052e-05, "epoch": 2.5303643724696356, "percentage": 50.61, "elapsed_time": "3:24:47", "remaining_time": "3:19:52"}
626
+ {"current_steps": 626, "total_steps": 1235, "loss": 0.2926, "lr": 2.30141283818846e-05, "epoch": 2.534412955465587, "percentage": 50.69, "elapsed_time": "3:25:04", "remaining_time": "3:19:29"}
627
+ {"current_steps": 627, "total_steps": 1235, "loss": 0.2851, "lr": 2.2958208014388462e-05, "epoch": 2.5384615384615383, "percentage": 50.77, "elapsed_time": "3:25:23", "remaining_time": "3:19:10"}
628
+ {"current_steps": 628, "total_steps": 1235, "loss": 0.2933, "lr": 2.2902263993139857e-05, "epoch": 2.54251012145749, "percentage": 50.85, "elapsed_time": "3:25:42", "remaining_time": "3:18:50"}
629
+ {"current_steps": 629, "total_steps": 1235, "loss": 0.2804, "lr": 2.2846296765465708e-05, "epoch": 2.5465587044534415, "percentage": 50.93, "elapsed_time": "3:26:01", "remaining_time": "3:18:29"}
630
+ {"current_steps": 630, "total_steps": 1235, "loss": 0.2855, "lr": 2.2790306778878465e-05, "epoch": 2.5506072874493926, "percentage": 51.01, "elapsed_time": "3:26:18", "remaining_time": "3:18:07"}
631
+ {"current_steps": 631, "total_steps": 1235, "loss": 0.3015, "lr": 2.273429448107257e-05, "epoch": 2.554655870445344, "percentage": 51.09, "elapsed_time": "3:26:38", "remaining_time": "3:17:47"}
632
+ {"current_steps": 632, "total_steps": 1235, "loss": 0.2858, "lr": 2.2678260319920868e-05, "epoch": 2.5587044534412957, "percentage": 51.17, "elapsed_time": "3:27:00", "remaining_time": "3:17:30"}
633
+ {"current_steps": 633, "total_steps": 1235, "loss": 0.2848, "lr": 2.262220474347102e-05, "epoch": 2.562753036437247, "percentage": 51.26, "elapsed_time": "3:27:19", "remaining_time": "3:17:09"}
634
+ {"current_steps": 634, "total_steps": 1235, "loss": 0.2728, "lr": 2.2566128199941918e-05, "epoch": 2.5668016194331984, "percentage": 51.34, "elapsed_time": "3:27:38", "remaining_time": "3:16:49"}
635
+ {"current_steps": 635, "total_steps": 1235, "loss": 0.2854, "lr": 2.2510031137720104e-05, "epoch": 2.57085020242915, "percentage": 51.42, "elapsed_time": "3:27:57", "remaining_time": "3:16:29"}
636
+ {"current_steps": 636, "total_steps": 1235, "loss": 0.2833, "lr": 2.2453914005356206e-05, "epoch": 2.574898785425101, "percentage": 51.5, "elapsed_time": "3:28:17", "remaining_time": "3:16:10"}
637
+ {"current_steps": 637, "total_steps": 1235, "loss": 0.2877, "lr": 2.2397777251561302e-05, "epoch": 2.5789473684210527, "percentage": 51.58, "elapsed_time": "3:28:36", "remaining_time": "3:15:50"}
638
+ {"current_steps": 638, "total_steps": 1235, "loss": 0.3121, "lr": 2.2341621325203393e-05, "epoch": 2.582995951417004, "percentage": 51.66, "elapsed_time": "3:28:59", "remaining_time": "3:15:33"}
639
+ {"current_steps": 639, "total_steps": 1235, "loss": 0.2869, "lr": 2.2285446675303764e-05, "epoch": 2.5870445344129553, "percentage": 51.74, "elapsed_time": "3:29:17", "remaining_time": "3:15:12"}
640
+ {"current_steps": 640, "total_steps": 1235, "loss": 0.2656, "lr": 2.2229253751033423e-05, "epoch": 2.591093117408907, "percentage": 51.82, "elapsed_time": "3:29:37", "remaining_time": "3:14:53"}
641
+ {"current_steps": 641, "total_steps": 1235, "loss": 0.2824, "lr": 2.2173043001709492e-05, "epoch": 2.5951417004048585, "percentage": 51.9, "elapsed_time": "3:29:53", "remaining_time": "3:14:29"}
642
+ {"current_steps": 642, "total_steps": 1235, "loss": 0.2938, "lr": 2.2116814876791627e-05, "epoch": 2.5991902834008096, "percentage": 51.98, "elapsed_time": "3:30:16", "remaining_time": "3:14:13"}
643
+ {"current_steps": 643, "total_steps": 1235, "loss": 0.2887, "lr": 2.2060569825878413e-05, "epoch": 2.603238866396761, "percentage": 52.06, "elapsed_time": "3:30:38", "remaining_time": "3:13:56"}
644
+ {"current_steps": 644, "total_steps": 1235, "loss": 0.3005, "lr": 2.2004308298703777e-05, "epoch": 2.6072874493927127, "percentage": 52.15, "elapsed_time": "3:31:01", "remaining_time": "3:13:39"}
645
+ {"current_steps": 645, "total_steps": 1235, "loss": 0.2873, "lr": 2.1948030745133396e-05, "epoch": 2.611336032388664, "percentage": 52.23, "elapsed_time": "3:31:17", "remaining_time": "3:13:16"}
646
+ {"current_steps": 646, "total_steps": 1235, "loss": 0.2749, "lr": 2.1891737615161083e-05, "epoch": 2.6153846153846154, "percentage": 52.31, "elapsed_time": "3:31:37", "remaining_time": "3:12:57"}
647
+ {"current_steps": 647, "total_steps": 1235, "loss": 0.2834, "lr": 2.1835429358905218e-05, "epoch": 2.619433198380567, "percentage": 52.39, "elapsed_time": "3:31:57", "remaining_time": "3:12:37"}
648
+ {"current_steps": 648, "total_steps": 1235, "loss": 0.2794, "lr": 2.17791064266051e-05, "epoch": 2.623481781376518, "percentage": 52.47, "elapsed_time": "3:32:17", "remaining_time": "3:12:18"}
649
+ {"current_steps": 649, "total_steps": 1235, "loss": 0.29, "lr": 2.172276926861741e-05, "epoch": 2.6275303643724697, "percentage": 52.55, "elapsed_time": "3:32:39", "remaining_time": "3:12:01"}
650
+ {"current_steps": 650, "total_steps": 1235, "loss": 0.2943, "lr": 2.166641833541255e-05, "epoch": 2.6315789473684212, "percentage": 52.63, "elapsed_time": "3:33:00", "remaining_time": "3:11:42"}
651
+ {"current_steps": 651, "total_steps": 1235, "loss": 0.2654, "lr": 2.161005407757109e-05, "epoch": 2.6356275303643724, "percentage": 52.71, "elapsed_time": "3:33:22", "remaining_time": "3:11:24"}
652
+ {"current_steps": 652, "total_steps": 1235, "loss": 0.3065, "lr": 2.155367694578013e-05, "epoch": 2.639676113360324, "percentage": 52.79, "elapsed_time": "3:33:41", "remaining_time": "3:11:04"}
653
+ {"current_steps": 653, "total_steps": 1235, "loss": 0.2994, "lr": 2.1497287390829712e-05, "epoch": 2.6437246963562755, "percentage": 52.87, "elapsed_time": "3:34:03", "remaining_time": "3:10:47"}
654
+ {"current_steps": 654, "total_steps": 1235, "loss": 0.2656, "lr": 2.1440885863609208e-05, "epoch": 2.6477732793522266, "percentage": 52.96, "elapsed_time": "3:34:23", "remaining_time": "3:10:27"}
655
+ {"current_steps": 655, "total_steps": 1235, "loss": 0.3018, "lr": 2.1384472815103737e-05, "epoch": 2.651821862348178, "percentage": 53.04, "elapsed_time": "3:34:44", "remaining_time": "3:10:09"}
656
+ {"current_steps": 656, "total_steps": 1235, "loss": 0.2878, "lr": 2.1328048696390534e-05, "epoch": 2.6558704453441297, "percentage": 53.12, "elapsed_time": "3:35:08", "remaining_time": "3:09:53"}
657
+ {"current_steps": 657, "total_steps": 1235, "loss": 0.2942, "lr": 2.1271613958635342e-05, "epoch": 2.659919028340081, "percentage": 53.2, "elapsed_time": "3:35:28", "remaining_time": "3:09:33"}
658
+ {"current_steps": 658, "total_steps": 1235, "loss": 0.2682, "lr": 2.1215169053088825e-05, "epoch": 2.6639676113360324, "percentage": 53.28, "elapsed_time": "3:35:45", "remaining_time": "3:09:11"}
659
+ {"current_steps": 659, "total_steps": 1235, "loss": 0.3041, "lr": 2.1158714431082937e-05, "epoch": 2.668016194331984, "percentage": 53.36, "elapsed_time": "3:36:06", "remaining_time": "3:08:53"}
660
+ {"current_steps": 660, "total_steps": 1235, "loss": 0.2906, "lr": 2.110225054402733e-05, "epoch": 2.672064777327935, "percentage": 53.44, "elapsed_time": "3:36:24", "remaining_time": "3:08:31"}
661
+ {"current_steps": 661, "total_steps": 1235, "loss": 0.2656, "lr": 2.1045777843405747e-05, "epoch": 2.6761133603238867, "percentage": 53.52, "elapsed_time": "3:36:39", "remaining_time": "3:08:08"}
662
+ {"current_steps": 662, "total_steps": 1235, "loss": 0.2989, "lr": 2.09892967807724e-05, "epoch": 2.6801619433198383, "percentage": 53.6, "elapsed_time": "3:36:57", "remaining_time": "3:07:47"}
663
+ {"current_steps": 663, "total_steps": 1235, "loss": 0.2752, "lr": 2.093280780774835e-05, "epoch": 2.6842105263157894, "percentage": 53.68, "elapsed_time": "3:37:18", "remaining_time": "3:07:29"}
664
+ {"current_steps": 664, "total_steps": 1235, "loss": 0.2934, "lr": 2.087631137601793e-05, "epoch": 2.688259109311741, "percentage": 53.77, "elapsed_time": "3:37:41", "remaining_time": "3:07:12"}
665
+ {"current_steps": 665, "total_steps": 1235, "loss": 0.264, "lr": 2.0819807937325104e-05, "epoch": 2.6923076923076925, "percentage": 53.85, "elapsed_time": "3:37:57", "remaining_time": "3:06:49"}
666
+ {"current_steps": 666, "total_steps": 1235, "loss": 0.2648, "lr": 2.0763297943469847e-05, "epoch": 2.6963562753036436, "percentage": 53.93, "elapsed_time": "3:38:18", "remaining_time": "3:06:31"}
667
+ {"current_steps": 667, "total_steps": 1235, "loss": 0.2865, "lr": 2.070678184630458e-05, "epoch": 2.700404858299595, "percentage": 54.01, "elapsed_time": "3:38:41", "remaining_time": "3:06:13"}
668
+ {"current_steps": 668, "total_steps": 1235, "loss": 0.2991, "lr": 2.06502600977305e-05, "epoch": 2.7044534412955468, "percentage": 54.09, "elapsed_time": "3:39:02", "remaining_time": "3:05:55"}
669
+ {"current_steps": 669, "total_steps": 1235, "loss": 0.2768, "lr": 2.0593733149694008e-05, "epoch": 2.708502024291498, "percentage": 54.17, "elapsed_time": "3:39:23", "remaining_time": "3:05:36"}
670
+ {"current_steps": 670, "total_steps": 1235, "loss": 0.2873, "lr": 2.0537201454183074e-05, "epoch": 2.7125506072874495, "percentage": 54.25, "elapsed_time": "3:39:42", "remaining_time": "3:05:16"}
671
+ {"current_steps": 671, "total_steps": 1235, "loss": 0.303, "lr": 2.0480665463223626e-05, "epoch": 2.716599190283401, "percentage": 54.33, "elapsed_time": "3:40:01", "remaining_time": "3:04:56"}
672
+ {"current_steps": 672, "total_steps": 1235, "loss": 0.2758, "lr": 2.042412562887594e-05, "epoch": 2.720647773279352, "percentage": 54.41, "elapsed_time": "3:40:20", "remaining_time": "3:04:36"}
673
+ {"current_steps": 673, "total_steps": 1235, "loss": 0.2969, "lr": 2.0367582403231033e-05, "epoch": 2.7246963562753037, "percentage": 54.49, "elapsed_time": "3:40:40", "remaining_time": "3:04:17"}
674
+ {"current_steps": 674, "total_steps": 1235, "loss": 0.3135, "lr": 2.0311036238407023e-05, "epoch": 2.7287449392712553, "percentage": 54.57, "elapsed_time": "3:41:00", "remaining_time": "3:03:56"}
675
+ {"current_steps": 675, "total_steps": 1235, "loss": 0.2823, "lr": 2.0254487586545534e-05, "epoch": 2.7327935222672064, "percentage": 54.66, "elapsed_time": "3:41:19", "remaining_time": "3:03:36"}
676
+ {"current_steps": 676, "total_steps": 1235, "loss": 0.2814, "lr": 2.0197936899808088e-05, "epoch": 2.736842105263158, "percentage": 54.74, "elapsed_time": "3:41:35", "remaining_time": "3:03:14"}
677
+ {"current_steps": 677, "total_steps": 1235, "loss": 0.2831, "lr": 2.0141384630372466e-05, "epoch": 2.7408906882591095, "percentage": 54.82, "elapsed_time": "3:41:52", "remaining_time": "3:02:52"}
678
+ {"current_steps": 678, "total_steps": 1235, "loss": 0.2777, "lr": 2.0084831230429106e-05, "epoch": 2.7449392712550607, "percentage": 54.9, "elapsed_time": "3:42:09", "remaining_time": "3:02:30"}
679
+ {"current_steps": 679, "total_steps": 1235, "loss": 0.2825, "lr": 2.0028277152177492e-05, "epoch": 2.748987854251012, "percentage": 54.98, "elapsed_time": "3:42:29", "remaining_time": "3:02:10"}
680
+ {"current_steps": 680, "total_steps": 1235, "loss": 0.2812, "lr": 1.9971722847822518e-05, "epoch": 2.753036437246964, "percentage": 55.06, "elapsed_time": "3:42:44", "remaining_time": "3:01:47"}
681
+ {"current_steps": 681, "total_steps": 1235, "loss": 0.263, "lr": 1.99151687695709e-05, "epoch": 2.757085020242915, "percentage": 55.14, "elapsed_time": "3:43:02", "remaining_time": "3:01:26"}
682
+ {"current_steps": 682, "total_steps": 1235, "loss": 0.2782, "lr": 1.9858615369627537e-05, "epoch": 2.7611336032388665, "percentage": 55.22, "elapsed_time": "3:43:21", "remaining_time": "3:01:06"}
683
+ {"current_steps": 683, "total_steps": 1235, "loss": 0.2796, "lr": 1.9802063100191916e-05, "epoch": 2.765182186234818, "percentage": 55.3, "elapsed_time": "3:43:41", "remaining_time": "3:00:47"}
684
+ {"current_steps": 684, "total_steps": 1235, "loss": 0.3007, "lr": 1.974551241345447e-05, "epoch": 2.769230769230769, "percentage": 55.38, "elapsed_time": "3:44:03", "remaining_time": "3:00:29"}
685
+ {"current_steps": 685, "total_steps": 1235, "loss": 0.2808, "lr": 1.9688963761592984e-05, "epoch": 2.7732793522267207, "percentage": 55.47, "elapsed_time": "3:44:22", "remaining_time": "3:00:09"}
686
+ {"current_steps": 686, "total_steps": 1235, "loss": 0.2899, "lr": 1.963241759676897e-05, "epoch": 2.7773279352226723, "percentage": 55.55, "elapsed_time": "3:44:42", "remaining_time": "2:59:49"}
687
+ {"current_steps": 687, "total_steps": 1235, "loss": 0.2811, "lr": 1.9575874371124066e-05, "epoch": 2.7813765182186234, "percentage": 55.63, "elapsed_time": "3:44:59", "remaining_time": "2:59:27"}
688
+ {"current_steps": 688, "total_steps": 1235, "loss": 0.2878, "lr": 1.951933453677638e-05, "epoch": 2.785425101214575, "percentage": 55.71, "elapsed_time": "3:45:17", "remaining_time": "2:59:07"}
689
+ {"current_steps": 689, "total_steps": 1235, "loss": 0.2845, "lr": 1.9462798545816932e-05, "epoch": 2.7894736842105265, "percentage": 55.79, "elapsed_time": "3:45:34", "remaining_time": "2:58:45"}
690
+ {"current_steps": 690, "total_steps": 1235, "loss": 0.2982, "lr": 1.9406266850305996e-05, "epoch": 2.7935222672064777, "percentage": 55.87, "elapsed_time": "3:45:54", "remaining_time": "2:58:26"}
691
+ {"current_steps": 691, "total_steps": 1235, "loss": 0.2882, "lr": 1.9349739902269503e-05, "epoch": 2.7975708502024292, "percentage": 55.95, "elapsed_time": "3:46:15", "remaining_time": "2:58:07"}
692
+ {"current_steps": 692, "total_steps": 1235, "loss": 0.2619, "lr": 1.9293218153695425e-05, "epoch": 2.801619433198381, "percentage": 56.03, "elapsed_time": "3:46:31", "remaining_time": "2:57:45"}
693
+ {"current_steps": 693, "total_steps": 1235, "loss": 0.2728, "lr": 1.9236702056530153e-05, "epoch": 2.805668016194332, "percentage": 56.11, "elapsed_time": "3:46:50", "remaining_time": "2:57:25"}
694
+ {"current_steps": 694, "total_steps": 1235, "loss": 0.2756, "lr": 1.9180192062674907e-05, "epoch": 2.8097165991902835, "percentage": 56.19, "elapsed_time": "3:47:09", "remaining_time": "2:57:04"}
695
+ {"current_steps": 695, "total_steps": 1235, "loss": 0.2925, "lr": 1.9123688623982076e-05, "epoch": 2.813765182186235, "percentage": 56.28, "elapsed_time": "3:47:24", "remaining_time": "2:56:41"}
696
+ {"current_steps": 696, "total_steps": 1235, "loss": 0.2852, "lr": 1.906719219225165e-05, "epoch": 2.817813765182186, "percentage": 56.36, "elapsed_time": "3:47:45", "remaining_time": "2:56:22"}
697
+ {"current_steps": 697, "total_steps": 1235, "loss": 0.2832, "lr": 1.9010703219227603e-05, "epoch": 2.8218623481781377, "percentage": 56.44, "elapsed_time": "3:48:04", "remaining_time": "2:56:02"}
698
+ {"current_steps": 698, "total_steps": 1235, "loss": 0.2881, "lr": 1.8954222156594256e-05, "epoch": 2.8259109311740893, "percentage": 56.52, "elapsed_time": "3:48:22", "remaining_time": "2:55:41"}
699
+ {"current_steps": 699, "total_steps": 1235, "loss": 0.2836, "lr": 1.8897749455972673e-05, "epoch": 2.8299595141700404, "percentage": 56.6, "elapsed_time": "3:48:38", "remaining_time": "2:55:19"}
700
+ {"current_steps": 700, "total_steps": 1235, "loss": 0.2945, "lr": 1.884128556891707e-05, "epoch": 2.834008097165992, "percentage": 56.68, "elapsed_time": "3:48:58", "remaining_time": "2:55:00"}
701
+ {"current_steps": 701, "total_steps": 1235, "loss": 0.275, "lr": 1.878483094691119e-05, "epoch": 2.8380566801619436, "percentage": 56.76, "elapsed_time": "3:49:20", "remaining_time": "2:54:42"}
702
+ {"current_steps": 702, "total_steps": 1235, "loss": 0.2943, "lr": 1.8728386041364664e-05, "epoch": 2.8421052631578947, "percentage": 56.84, "elapsed_time": "3:49:42", "remaining_time": "2:54:24"}
703
+ {"current_steps": 703, "total_steps": 1235, "loss": 0.3062, "lr": 1.867195130360947e-05, "epoch": 2.8461538461538463, "percentage": 56.92, "elapsed_time": "3:50:01", "remaining_time": "2:54:04"}
704
+ {"current_steps": 704, "total_steps": 1235, "loss": 0.3046, "lr": 1.8615527184896263e-05, "epoch": 2.850202429149798, "percentage": 57.0, "elapsed_time": "3:50:21", "remaining_time": "2:53:45"}
705
+ {"current_steps": 705, "total_steps": 1235, "loss": 0.2575, "lr": 1.8559114136390795e-05, "epoch": 2.854251012145749, "percentage": 57.09, "elapsed_time": "3:50:37", "remaining_time": "2:53:22"}
706
+ {"current_steps": 706, "total_steps": 1235, "loss": 0.2732, "lr": 1.8502712609170298e-05, "epoch": 2.8582995951417005, "percentage": 57.17, "elapsed_time": "3:50:57", "remaining_time": "2:53:03"}
707
+ {"current_steps": 707, "total_steps": 1235, "loss": 0.2749, "lr": 1.8446323054219876e-05, "epoch": 2.862348178137652, "percentage": 57.25, "elapsed_time": "3:51:14", "remaining_time": "2:52:42"}
708
+ {"current_steps": 708, "total_steps": 1235, "loss": 0.3104, "lr": 1.838994592242891e-05, "epoch": 2.866396761133603, "percentage": 57.33, "elapsed_time": "3:51:37", "remaining_time": "2:52:24"}
709
+ {"current_steps": 709, "total_steps": 1235, "loss": 0.2976, "lr": 1.8333581664587453e-05, "epoch": 2.8704453441295548, "percentage": 57.41, "elapsed_time": "3:51:57", "remaining_time": "2:52:05"}
710
+ {"current_steps": 710, "total_steps": 1235, "loss": 0.2931, "lr": 1.8277230731382593e-05, "epoch": 2.8744939271255063, "percentage": 57.49, "elapsed_time": "3:52:14", "remaining_time": "2:51:43"}
711
+ {"current_steps": 711, "total_steps": 1235, "loss": 0.2832, "lr": 1.82208935733949e-05, "epoch": 2.8785425101214575, "percentage": 57.57, "elapsed_time": "3:52:35", "remaining_time": "2:51:25"}
712
+ {"current_steps": 712, "total_steps": 1235, "loss": 0.2761, "lr": 1.8164570641094793e-05, "epoch": 2.882591093117409, "percentage": 57.65, "elapsed_time": "3:52:56", "remaining_time": "2:51:06"}
713
+ {"current_steps": 713, "total_steps": 1235, "loss": 0.2812, "lr": 1.810826238483892e-05, "epoch": 2.8866396761133606, "percentage": 57.73, "elapsed_time": "3:53:15", "remaining_time": "2:50:45"}
714
+ {"current_steps": 714, "total_steps": 1235, "loss": 0.299, "lr": 1.8051969254866608e-05, "epoch": 2.8906882591093117, "percentage": 57.81, "elapsed_time": "3:53:31", "remaining_time": "2:50:24"}
715
+ {"current_steps": 715, "total_steps": 1235, "loss": 0.2931, "lr": 1.7995691701296226e-05, "epoch": 2.8947368421052633, "percentage": 57.89, "elapsed_time": "3:53:54", "remaining_time": "2:50:06"}
716
+ {"current_steps": 716, "total_steps": 1235, "loss": 0.2865, "lr": 1.7939430174121593e-05, "epoch": 2.898785425101215, "percentage": 57.98, "elapsed_time": "3:54:13", "remaining_time": "2:49:46"}
717
+ {"current_steps": 717, "total_steps": 1235, "loss": 0.2762, "lr": 1.788318512320838e-05, "epoch": 2.902834008097166, "percentage": 58.06, "elapsed_time": "3:54:34", "remaining_time": "2:49:27"}
718
+ {"current_steps": 718, "total_steps": 1235, "loss": 0.274, "lr": 1.782695699829051e-05, "epoch": 2.9068825910931175, "percentage": 58.14, "elapsed_time": "3:54:50", "remaining_time": "2:49:06"}
719
+ {"current_steps": 719, "total_steps": 1235, "loss": 0.2528, "lr": 1.7770746248966587e-05, "epoch": 2.910931174089069, "percentage": 58.22, "elapsed_time": "3:55:09", "remaining_time": "2:48:45"}
720
+ {"current_steps": 720, "total_steps": 1235, "loss": 0.2752, "lr": 1.7714553324696243e-05, "epoch": 2.91497975708502, "percentage": 58.3, "elapsed_time": "3:55:26", "remaining_time": "2:48:24"}
721
+ {"current_steps": 721, "total_steps": 1235, "loss": 0.2707, "lr": 1.7658378674796614e-05, "epoch": 2.919028340080972, "percentage": 58.38, "elapsed_time": "3:55:47", "remaining_time": "2:48:05"}
722
+ {"current_steps": 722, "total_steps": 1235, "loss": 0.2833, "lr": 1.76022227484387e-05, "epoch": 2.9230769230769234, "percentage": 58.46, "elapsed_time": "3:56:08", "remaining_time": "2:47:46"}
723
+ {"current_steps": 723, "total_steps": 1235, "loss": 0.2774, "lr": 1.7546085994643807e-05, "epoch": 2.9271255060728745, "percentage": 58.54, "elapsed_time": "3:56:27", "remaining_time": "2:47:27"}
724
+ {"current_steps": 724, "total_steps": 1235, "loss": 0.2782, "lr": 1.7489968862279902e-05, "epoch": 2.931174089068826, "percentage": 58.62, "elapsed_time": "3:56:48", "remaining_time": "2:47:08"}
725
+ {"current_steps": 725, "total_steps": 1235, "loss": 0.2695, "lr": 1.743387180005809e-05, "epoch": 2.9352226720647776, "percentage": 58.7, "elapsed_time": "3:57:06", "remaining_time": "2:46:47"}
726
+ {"current_steps": 726, "total_steps": 1235, "loss": 0.288, "lr": 1.737779525652899e-05, "epoch": 2.9392712550607287, "percentage": 58.79, "elapsed_time": "3:57:24", "remaining_time": "2:46:26"}
727
+ {"current_steps": 727, "total_steps": 1235, "loss": 0.3083, "lr": 1.732173968007914e-05, "epoch": 2.9433198380566803, "percentage": 58.87, "elapsed_time": "3:57:42", "remaining_time": "2:46:06"}
728
+ {"current_steps": 728, "total_steps": 1235, "loss": 0.2665, "lr": 1.7265705518927437e-05, "epoch": 2.9473684210526314, "percentage": 58.95, "elapsed_time": "3:57:58", "remaining_time": "2:45:43"}
729
+ {"current_steps": 729, "total_steps": 1235, "loss": 0.2776, "lr": 1.7209693221121542e-05, "epoch": 2.951417004048583, "percentage": 59.03, "elapsed_time": "3:58:16", "remaining_time": "2:45:23"}
730
+ {"current_steps": 730, "total_steps": 1235, "loss": 0.2943, "lr": 1.7153703234534302e-05, "epoch": 2.9554655870445345, "percentage": 59.11, "elapsed_time": "3:58:36", "remaining_time": "2:45:03"}
731
+ {"current_steps": 731, "total_steps": 1235, "loss": 0.2913, "lr": 1.709773600686015e-05, "epoch": 2.9595141700404857, "percentage": 59.19, "elapsed_time": "3:58:55", "remaining_time": "2:44:43"}
732
+ {"current_steps": 732, "total_steps": 1235, "loss": 0.2993, "lr": 1.7041791985611548e-05, "epoch": 2.9635627530364372, "percentage": 59.27, "elapsed_time": "3:59:14", "remaining_time": "2:44:23"}
733
+ {"current_steps": 733, "total_steps": 1235, "loss": 0.2996, "lr": 1.69858716181154e-05, "epoch": 2.967611336032389, "percentage": 59.35, "elapsed_time": "3:59:35", "remaining_time": "2:44:04"}
734
+ {"current_steps": 734, "total_steps": 1235, "loss": 0.2713, "lr": 1.692997535150948e-05, "epoch": 2.97165991902834, "percentage": 59.43, "elapsed_time": "3:59:53", "remaining_time": "2:43:44"}
735
+ {"current_steps": 735, "total_steps": 1235, "loss": 0.3135, "lr": 1.687410363273884e-05, "epoch": 2.9757085020242915, "percentage": 59.51, "elapsed_time": "4:00:14", "remaining_time": "2:43:25"}
736
+ {"current_steps": 736, "total_steps": 1235, "loss": 0.2889, "lr": 1.6818256908552257e-05, "epoch": 2.979757085020243, "percentage": 59.6, "elapsed_time": "4:00:35", "remaining_time": "2:43:07"}
737
+ {"current_steps": 737, "total_steps": 1235, "loss": 0.2778, "lr": 1.6762435625498646e-05, "epoch": 2.983805668016194, "percentage": 59.68, "elapsed_time": "4:00:58", "remaining_time": "2:42:49"}
738
+ {"current_steps": 738, "total_steps": 1235, "loss": 0.2845, "lr": 1.67066402299235e-05, "epoch": 2.9878542510121457, "percentage": 59.76, "elapsed_time": "4:01:15", "remaining_time": "2:42:28"}
739
+ {"current_steps": 739, "total_steps": 1235, "loss": 0.2726, "lr": 1.6650871167965313e-05, "epoch": 2.9919028340080973, "percentage": 59.84, "elapsed_time": "4:01:31", "remaining_time": "2:42:06"}
740
+ {"current_steps": 740, "total_steps": 1235, "loss": 0.2957, "lr": 1.6595128885552028e-05, "epoch": 2.9959514170040484, "percentage": 59.92, "elapsed_time": "4:01:51", "remaining_time": "2:41:47"}
741
+ {"current_steps": 741, "total_steps": 1235, "loss": 0.2701, "lr": 1.653941382839745e-05, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "4:02:08", "remaining_time": "2:41:25"}
742
+ {"current_steps": 742, "total_steps": 1235, "loss": 0.2174, "lr": 1.6483726441997673e-05, "epoch": 3.0040485829959516, "percentage": 60.08, "elapsed_time": "4:04:59", "remaining_time": "2:42:46"}
743
+ {"current_steps": 743, "total_steps": 1235, "loss": 0.2053, "lr": 1.642806717162757e-05, "epoch": 3.0080971659919027, "percentage": 60.16, "elapsed_time": "4:05:22", "remaining_time": "2:42:28"}
744
+ {"current_steps": 744, "total_steps": 1235, "loss": 0.2191, "lr": 1.637243646233718e-05, "epoch": 3.0121457489878543, "percentage": 60.24, "elapsed_time": "4:05:43", "remaining_time": "2:42:09"}
745
+ {"current_steps": 745, "total_steps": 1235, "loss": 0.2032, "lr": 1.6316834758948174e-05, "epoch": 3.016194331983806, "percentage": 60.32, "elapsed_time": "4:05:59", "remaining_time": "2:41:47"}
746
+ {"current_steps": 746, "total_steps": 1235, "loss": 0.1966, "lr": 1.6261262506050282e-05, "epoch": 3.020242914979757, "percentage": 60.4, "elapsed_time": "4:06:19", "remaining_time": "2:41:28"}
747
+ {"current_steps": 747, "total_steps": 1235, "loss": 0.2168, "lr": 1.620572014799777e-05, "epoch": 3.0242914979757085, "percentage": 60.49, "elapsed_time": "4:06:40", "remaining_time": "2:41:09"}
748
+ {"current_steps": 748, "total_steps": 1235, "loss": 0.1822, "lr": 1.6150208128905857e-05, "epoch": 3.02834008097166, "percentage": 60.57, "elapsed_time": "4:07:03", "remaining_time": "2:40:50"}
749
+ {"current_steps": 749, "total_steps": 1235, "loss": 0.1962, "lr": 1.6094726892647147e-05, "epoch": 3.032388663967611, "percentage": 60.65, "elapsed_time": "4:07:22", "remaining_time": "2:40:30"}