neginr commited on
Commit
464d2af
·
verified ·
1 Parent(s): e9dc8db

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 sha256:88a806b9c6b4bb91e6c6fd1343f95d9fce851cfbc70265cb7b8db93b29b31e65
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7b5b95e7fb569b790d30ee0fa82ac136d3137cc718659ad6778b5ffb54a9920
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d8703505b3192eab700975add904383401c6bb1d89d3a04908a5a1436bab9ba
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37c5c276a1510ff0e40175df1fb77b0046cfd82b80ff616ea27a9f1da608db6b
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4648f940b2ec9aa7140aca85d7d21cc4f1f41a611f00cc07d136dd3c70b55fd4
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1101e6f394f5d96ed7db940b26ea55d9c4127c4bfa4222307b73321df453f72
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:fda2665bae05e9e29729ab7c9041c8f9f8d2f47785c8b71da560fc16909a2696
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d52ffbabefbbc639a373d8eb9fc50661f03f83a9e33555ccaab3d6ad2b657dd
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -504,3 +504,251 @@
504
  {"current_steps": 504, "total_steps": 1235, "loss": 0.3781, "lr": 2.9522874311100684e-05, "epoch": 2.0404858299595143, "percentage": 40.81, "elapsed_time": "2:12:15", "remaining_time": "3:11:49"}
505
  {"current_steps": 505, "total_steps": 1235, "loss": 0.3529, "lr": 2.9473104272467526e-05, "epoch": 2.0445344129554655, "percentage": 40.89, "elapsed_time": "2:12:26", "remaining_time": "3:11:27"}
506
  {"current_steps": 506, "total_steps": 1235, "loss": 0.349, "lr": 2.942325848714505e-05, "epoch": 2.048582995951417, "percentage": 40.97, "elapsed_time": "2:12:44", "remaining_time": "3:11:14"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
504
  {"current_steps": 504, "total_steps": 1235, "loss": 0.3781, "lr": 2.9522874311100684e-05, "epoch": 2.0404858299595143, "percentage": 40.81, "elapsed_time": "2:12:15", "remaining_time": "3:11:49"}
505
  {"current_steps": 505, "total_steps": 1235, "loss": 0.3529, "lr": 2.9473104272467526e-05, "epoch": 2.0445344129554655, "percentage": 40.89, "elapsed_time": "2:12:26", "remaining_time": "3:11:27"}
506
  {"current_steps": 506, "total_steps": 1235, "loss": 0.349, "lr": 2.942325848714505e-05, "epoch": 2.048582995951417, "percentage": 40.97, "elapsed_time": "2:12:44", "remaining_time": "3:11:14"}
507
+ {"current_steps": 507, "total_steps": 1235, "loss": 0.3558, "lr": 2.9373337353698804e-05, "epoch": 2.0526315789473686, "percentage": 41.05, "elapsed_time": "2:12:57", "remaining_time": "3:10:54"}
508
+ {"current_steps": 508, "total_steps": 1235, "loss": 0.3511, "lr": 2.932334127129686e-05, "epoch": 2.0566801619433197, "percentage": 41.13, "elapsed_time": "2:13:10", "remaining_time": "3:10:34"}
509
+ {"current_steps": 509, "total_steps": 1235, "loss": 0.3477, "lr": 2.9273270639706547e-05, "epoch": 2.0607287449392713, "percentage": 41.21, "elapsed_time": "2:13:22", "remaining_time": "3:10:14"}
510
+ {"current_steps": 510, "total_steps": 1235, "loss": 0.3537, "lr": 2.922312585929131e-05, "epoch": 2.064777327935223, "percentage": 41.3, "elapsed_time": "2:13:41", "remaining_time": "3:10:03"}
511
+ {"current_steps": 511, "total_steps": 1235, "loss": 0.3676, "lr": 2.9172907331007478e-05, "epoch": 2.068825910931174, "percentage": 41.38, "elapsed_time": "2:14:00", "remaining_time": "3:09:52"}
512
+ {"current_steps": 512, "total_steps": 1235, "loss": 0.3575, "lr": 2.9122615456401053e-05, "epoch": 2.0728744939271255, "percentage": 41.46, "elapsed_time": "2:14:13", "remaining_time": "3:09:31"}
513
+ {"current_steps": 513, "total_steps": 1235, "loss": 0.3764, "lr": 2.9072250637604535e-05, "epoch": 2.076923076923077, "percentage": 41.54, "elapsed_time": "2:14:27", "remaining_time": "3:09:13"}
514
+ {"current_steps": 514, "total_steps": 1235, "loss": 0.3574, "lr": 2.9021813277333667e-05, "epoch": 2.080971659919028, "percentage": 41.62, "elapsed_time": "2:14:40", "remaining_time": "3:08:54"}
515
+ {"current_steps": 515, "total_steps": 1235, "loss": 0.3648, "lr": 2.8971303778884244e-05, "epoch": 2.08502024291498, "percentage": 41.7, "elapsed_time": "2:14:56", "remaining_time": "3:08:39"}
516
+ {"current_steps": 516, "total_steps": 1235, "loss": 0.3326, "lr": 2.8920722546128863e-05, "epoch": 2.0890688259109313, "percentage": 41.78, "elapsed_time": "2:15:10", "remaining_time": "3:08:21"}
517
+ {"current_steps": 517, "total_steps": 1235, "loss": 0.3643, "lr": 2.887006998351372e-05, "epoch": 2.0931174089068825, "percentage": 41.86, "elapsed_time": "2:15:27", "remaining_time": "3:08:07"}
518
+ {"current_steps": 518, "total_steps": 1235, "loss": 0.373, "lr": 2.881934649605535e-05, "epoch": 2.097165991902834, "percentage": 41.94, "elapsed_time": "2:15:40", "remaining_time": "3:07:48"}
519
+ {"current_steps": 519, "total_steps": 1235, "loss": 0.3331, "lr": 2.8768552489337408e-05, "epoch": 2.1012145748987856, "percentage": 42.02, "elapsed_time": "2:15:52", "remaining_time": "3:07:27"}
520
+ {"current_steps": 520, "total_steps": 1235, "loss": 0.3364, "lr": 2.8717688369507425e-05, "epoch": 2.1052631578947367, "percentage": 42.11, "elapsed_time": "2:16:07", "remaining_time": "3:07:10"}
521
+ {"current_steps": 521, "total_steps": 1235, "loss": 0.3599, "lr": 2.8666754543273535e-05, "epoch": 2.1093117408906883, "percentage": 42.19, "elapsed_time": "2:16:19", "remaining_time": "3:06:49"}
522
+ {"current_steps": 522, "total_steps": 1235, "loss": 0.3524, "lr": 2.8615751417901273e-05, "epoch": 2.11336032388664, "percentage": 42.27, "elapsed_time": "2:16:38", "remaining_time": "3:06:38"}
523
+ {"current_steps": 523, "total_steps": 1235, "loss": 0.3539, "lr": 2.856467940121025e-05, "epoch": 2.117408906882591, "percentage": 42.35, "elapsed_time": "2:16:55", "remaining_time": "3:06:24"}
524
+ {"current_steps": 524, "total_steps": 1235, "loss": 0.3529, "lr": 2.8513538901570964e-05, "epoch": 2.1214574898785425, "percentage": 42.43, "elapsed_time": "2:17:08", "remaining_time": "3:06:04"}
525
+ {"current_steps": 525, "total_steps": 1235, "loss": 0.3461, "lr": 2.846233032790149e-05, "epoch": 2.125506072874494, "percentage": 42.51, "elapsed_time": "2:17:22", "remaining_time": "3:05:46"}
526
+ {"current_steps": 526, "total_steps": 1235, "loss": 0.3496, "lr": 2.84110540896642e-05, "epoch": 2.1295546558704452, "percentage": 42.59, "elapsed_time": "2:17:38", "remaining_time": "3:05:31"}
527
+ {"current_steps": 527, "total_steps": 1235, "loss": 0.3504, "lr": 2.8359710596862555e-05, "epoch": 2.133603238866397, "percentage": 42.67, "elapsed_time": "2:17:51", "remaining_time": "3:05:12"}
528
+ {"current_steps": 528, "total_steps": 1235, "loss": 0.342, "lr": 2.8308300260037734e-05, "epoch": 2.1376518218623484, "percentage": 42.75, "elapsed_time": "2:18:09", "remaining_time": "3:05:00"}
529
+ {"current_steps": 529, "total_steps": 1235, "loss": 0.3554, "lr": 2.8256823490265424e-05, "epoch": 2.1417004048582995, "percentage": 42.83, "elapsed_time": "2:18:20", "remaining_time": "3:04:38"}
530
+ {"current_steps": 530, "total_steps": 1235, "loss": 0.3332, "lr": 2.8205280699152515e-05, "epoch": 2.145748987854251, "percentage": 42.91, "elapsed_time": "2:18:34", "remaining_time": "3:04:19"}
531
+ {"current_steps": 531, "total_steps": 1235, "loss": 0.3492, "lr": 2.8153672298833777e-05, "epoch": 2.1497975708502026, "percentage": 43.0, "elapsed_time": "2:18:51", "remaining_time": "3:04:05"}
532
+ {"current_steps": 532, "total_steps": 1235, "loss": 0.3433, "lr": 2.8101998701968615e-05, "epoch": 2.1538461538461537, "percentage": 43.08, "elapsed_time": "2:19:08", "remaining_time": "3:03:52"}
533
+ {"current_steps": 533, "total_steps": 1235, "loss": 0.3666, "lr": 2.805026032173773e-05, "epoch": 2.1578947368421053, "percentage": 43.16, "elapsed_time": "2:19:25", "remaining_time": "3:03:38"}
534
+ {"current_steps": 534, "total_steps": 1235, "loss": 0.3551, "lr": 2.7998457571839832e-05, "epoch": 2.161943319838057, "percentage": 43.24, "elapsed_time": "2:19:40", "remaining_time": "3:03:20"}
535
+ {"current_steps": 535, "total_steps": 1235, "loss": 0.3785, "lr": 2.7946590866488322e-05, "epoch": 2.165991902834008, "percentage": 43.32, "elapsed_time": "2:19:56", "remaining_time": "3:03:05"}
536
+ {"current_steps": 536, "total_steps": 1235, "loss": 0.3515, "lr": 2.7894660620408e-05, "epoch": 2.1700404858299596, "percentage": 43.4, "elapsed_time": "2:20:13", "remaining_time": "3:02:51"}
537
+ {"current_steps": 537, "total_steps": 1235, "loss": 0.3672, "lr": 2.784266724883173e-05, "epoch": 2.174089068825911, "percentage": 43.48, "elapsed_time": "2:20:26", "remaining_time": "3:02:32"}
538
+ {"current_steps": 538, "total_steps": 1235, "loss": 0.3551, "lr": 2.7790611167497128e-05, "epoch": 2.1781376518218623, "percentage": 43.56, "elapsed_time": "2:20:38", "remaining_time": "3:02:12"}
539
+ {"current_steps": 539, "total_steps": 1235, "loss": 0.3803, "lr": 2.7738492792643224e-05, "epoch": 2.182186234817814, "percentage": 43.64, "elapsed_time": "2:20:54", "remaining_time": "3:01:56"}
540
+ {"current_steps": 540, "total_steps": 1235, "loss": 0.3677, "lr": 2.768631254100716e-05, "epoch": 2.1862348178137654, "percentage": 43.72, "elapsed_time": "2:21:12", "remaining_time": "3:01:44"}
541
+ {"current_steps": 541, "total_steps": 1235, "loss": 0.3192, "lr": 2.7634070829820836e-05, "epoch": 2.1902834008097165, "percentage": 43.81, "elapsed_time": "2:21:27", "remaining_time": "3:01:27"}
542
+ {"current_steps": 542, "total_steps": 1235, "loss": 0.3692, "lr": 2.7581768076807592e-05, "epoch": 2.194331983805668, "percentage": 43.89, "elapsed_time": "2:21:41", "remaining_time": "3:01:09"}
543
+ {"current_steps": 543, "total_steps": 1235, "loss": 0.3424, "lr": 2.7529404700178832e-05, "epoch": 2.1983805668016196, "percentage": 43.97, "elapsed_time": "2:21:58", "remaining_time": "3:00:56"}
544
+ {"current_steps": 544, "total_steps": 1235, "loss": 0.3657, "lr": 2.7476981118630735e-05, "epoch": 2.2024291497975708, "percentage": 44.05, "elapsed_time": "2:22:12", "remaining_time": "3:00:38"}
545
+ {"current_steps": 545, "total_steps": 1235, "loss": 0.3461, "lr": 2.742449775134085e-05, "epoch": 2.2064777327935223, "percentage": 44.13, "elapsed_time": "2:22:27", "remaining_time": "3:00:21"}
546
+ {"current_steps": 546, "total_steps": 1235, "loss": 0.363, "lr": 2.7371955017964788e-05, "epoch": 2.2105263157894735, "percentage": 44.21, "elapsed_time": "2:22:42", "remaining_time": "3:00:05"}
547
+ {"current_steps": 547, "total_steps": 1235, "loss": 0.3419, "lr": 2.7319353338632845e-05, "epoch": 2.214574898785425, "percentage": 44.29, "elapsed_time": "2:22:56", "remaining_time": "2:59:47"}
548
+ {"current_steps": 548, "total_steps": 1235, "loss": 0.3408, "lr": 2.7266693133946645e-05, "epoch": 2.2186234817813766, "percentage": 44.37, "elapsed_time": "2:23:08", "remaining_time": "2:59:27"}
549
+ {"current_steps": 549, "total_steps": 1235, "loss": 0.347, "lr": 2.7213974824975785e-05, "epoch": 2.2226720647773277, "percentage": 44.45, "elapsed_time": "2:23:23", "remaining_time": "2:59:10"}
550
+ {"current_steps": 550, "total_steps": 1235, "loss": 0.3399, "lr": 2.7161198833254464e-05, "epoch": 2.2267206477732793, "percentage": 44.53, "elapsed_time": "2:23:38", "remaining_time": "2:58:53"}
551
+ {"current_steps": 551, "total_steps": 1235, "loss": 0.3616, "lr": 2.7108365580778095e-05, "epoch": 2.230769230769231, "percentage": 44.62, "elapsed_time": "2:23:52", "remaining_time": "2:58:35"}
552
+ {"current_steps": 552, "total_steps": 1235, "loss": 0.3931, "lr": 2.705547548999996e-05, "epoch": 2.234817813765182, "percentage": 44.7, "elapsed_time": "2:24:08", "remaining_time": "2:58:21"}
553
+ {"current_steps": 553, "total_steps": 1235, "loss": 0.3507, "lr": 2.7002528983827817e-05, "epoch": 2.2388663967611335, "percentage": 44.78, "elapsed_time": "2:24:24", "remaining_time": "2:58:05"}
554
+ {"current_steps": 554, "total_steps": 1235, "loss": 0.3536, "lr": 2.6949526485620517e-05, "epoch": 2.242914979757085, "percentage": 44.86, "elapsed_time": "2:24:37", "remaining_time": "2:57:46"}
555
+ {"current_steps": 555, "total_steps": 1235, "loss": 0.3624, "lr": 2.6896468419184623e-05, "epoch": 2.246963562753036, "percentage": 44.94, "elapsed_time": "2:24:47", "remaining_time": "2:57:24"}
556
+ {"current_steps": 556, "total_steps": 1235, "loss": 0.3676, "lr": 2.6843355208771024e-05, "epoch": 2.251012145748988, "percentage": 45.02, "elapsed_time": "2:25:04", "remaining_time": "2:57:10"}
557
+ {"current_steps": 557, "total_steps": 1235, "loss": 0.3599, "lr": 2.6790187279071536e-05, "epoch": 2.2550607287449393, "percentage": 45.1, "elapsed_time": "2:25:20", "remaining_time": "2:56:55"}
558
+ {"current_steps": 558, "total_steps": 1235, "loss": 0.3398, "lr": 2.67369650552155e-05, "epoch": 2.2591093117408905, "percentage": 45.18, "elapsed_time": "2:25:33", "remaining_time": "2:56:35"}
559
+ {"current_steps": 559, "total_steps": 1235, "loss": 0.3467, "lr": 2.6683688962766407e-05, "epoch": 2.263157894736842, "percentage": 45.26, "elapsed_time": "2:25:50", "remaining_time": "2:56:22"}
560
+ {"current_steps": 560, "total_steps": 1235, "loss": 0.3586, "lr": 2.6630359427718468e-05, "epoch": 2.2672064777327936, "percentage": 45.34, "elapsed_time": "2:26:03", "remaining_time": "2:56:03"}
561
+ {"current_steps": 561, "total_steps": 1235, "loss": 0.3432, "lr": 2.6576976876493225e-05, "epoch": 2.2712550607287447, "percentage": 45.43, "elapsed_time": "2:26:20", "remaining_time": "2:55:49"}
562
+ {"current_steps": 562, "total_steps": 1235, "loss": 0.3522, "lr": 2.652354173593614e-05, "epoch": 2.2753036437246963, "percentage": 45.51, "elapsed_time": "2:26:36", "remaining_time": "2:55:33"}
563
+ {"current_steps": 563, "total_steps": 1235, "loss": 0.3662, "lr": 2.647005443331317e-05, "epoch": 2.279352226720648, "percentage": 45.59, "elapsed_time": "2:26:50", "remaining_time": "2:55:15"}
564
+ {"current_steps": 564, "total_steps": 1235, "loss": 0.3458, "lr": 2.6416515396307354e-05, "epoch": 2.283400809716599, "percentage": 45.67, "elapsed_time": "2:27:02", "remaining_time": "2:54:56"}
565
+ {"current_steps": 565, "total_steps": 1235, "loss": 0.3495, "lr": 2.636292505301542e-05, "epoch": 2.2874493927125505, "percentage": 45.75, "elapsed_time": "2:27:19", "remaining_time": "2:54:41"}
566
+ {"current_steps": 566, "total_steps": 1235, "loss": 0.3508, "lr": 2.630928383194431e-05, "epoch": 2.291497975708502, "percentage": 45.83, "elapsed_time": "2:27:35", "remaining_time": "2:54:26"}
567
+ {"current_steps": 567, "total_steps": 1235, "loss": 0.3666, "lr": 2.625559216200781e-05, "epoch": 2.2955465587044532, "percentage": 45.91, "elapsed_time": "2:27:54", "remaining_time": "2:54:15"}
568
+ {"current_steps": 568, "total_steps": 1235, "loss": 0.369, "lr": 2.620185047252308e-05, "epoch": 2.299595141700405, "percentage": 45.99, "elapsed_time": "2:28:07", "remaining_time": "2:53:56"}
569
+ {"current_steps": 569, "total_steps": 1235, "loss": 0.3727, "lr": 2.614805919320723e-05, "epoch": 2.3036437246963564, "percentage": 46.07, "elapsed_time": "2:28:25", "remaining_time": "2:53:43"}
570
+ {"current_steps": 570, "total_steps": 1235, "loss": 0.3593, "lr": 2.6094218754173895e-05, "epoch": 2.3076923076923075, "percentage": 46.15, "elapsed_time": "2:28:40", "remaining_time": "2:53:26"}
571
+ {"current_steps": 571, "total_steps": 1235, "loss": 0.3435, "lr": 2.60403295859298e-05, "epoch": 2.311740890688259, "percentage": 46.23, "elapsed_time": "2:28:55", "remaining_time": "2:53:11"}
572
+ {"current_steps": 572, "total_steps": 1235, "loss": 0.3483, "lr": 2.5986392119371297e-05, "epoch": 2.3157894736842106, "percentage": 46.32, "elapsed_time": "2:29:10", "remaining_time": "2:52:53"}
573
+ {"current_steps": 573, "total_steps": 1235, "loss": 0.3579, "lr": 2.5932406785780928e-05, "epoch": 2.3198380566801617, "percentage": 46.4, "elapsed_time": "2:29:28", "remaining_time": "2:52:41"}
574
+ {"current_steps": 574, "total_steps": 1235, "loss": 0.3438, "lr": 2.5878374016823987e-05, "epoch": 2.3238866396761133, "percentage": 46.48, "elapsed_time": "2:29:48", "remaining_time": "2:52:30"}
575
+ {"current_steps": 575, "total_steps": 1235, "loss": 0.353, "lr": 2.5824294244545045e-05, "epoch": 2.327935222672065, "percentage": 46.56, "elapsed_time": "2:30:02", "remaining_time": "2:52:13"}
576
+ {"current_steps": 576, "total_steps": 1235, "loss": 0.3706, "lr": 2.577016790136453e-05, "epoch": 2.331983805668016, "percentage": 46.64, "elapsed_time": "2:30:18", "remaining_time": "2:51:58"}
577
+ {"current_steps": 577, "total_steps": 1235, "loss": 0.352, "lr": 2.5715995420075225e-05, "epoch": 2.3360323886639676, "percentage": 46.72, "elapsed_time": "2:30:30", "remaining_time": "2:51:37"}
578
+ {"current_steps": 578, "total_steps": 1235, "loss": 0.3596, "lr": 2.5661777233838864e-05, "epoch": 2.340080971659919, "percentage": 46.8, "elapsed_time": "2:30:43", "remaining_time": "2:51:19"}
579
+ {"current_steps": 579, "total_steps": 1235, "loss": 0.3336, "lr": 2.5607513776182616e-05, "epoch": 2.3441295546558703, "percentage": 46.88, "elapsed_time": "2:30:56", "remaining_time": "2:51:00"}
580
+ {"current_steps": 580, "total_steps": 1235, "loss": 0.3484, "lr": 2.5553205480995633e-05, "epoch": 2.348178137651822, "percentage": 46.96, "elapsed_time": "2:31:05", "remaining_time": "2:50:37"}
581
+ {"current_steps": 581, "total_steps": 1235, "loss": 0.3764, "lr": 2.5498852782525604e-05, "epoch": 2.3522267206477734, "percentage": 47.04, "elapsed_time": "2:31:22", "remaining_time": "2:50:23"}
582
+ {"current_steps": 582, "total_steps": 1235, "loss": 0.3612, "lr": 2.5444456115375252e-05, "epoch": 2.3562753036437245, "percentage": 47.13, "elapsed_time": "2:31:37", "remaining_time": "2:50:07"}
583
+ {"current_steps": 583, "total_steps": 1235, "loss": 0.376, "lr": 2.539001591449889e-05, "epoch": 2.360323886639676, "percentage": 47.21, "elapsed_time": "2:31:51", "remaining_time": "2:49:49"}
584
+ {"current_steps": 584, "total_steps": 1235, "loss": 0.3524, "lr": 2.53355326151989e-05, "epoch": 2.3643724696356276, "percentage": 47.29, "elapsed_time": "2:32:06", "remaining_time": "2:49:33"}
585
+ {"current_steps": 585, "total_steps": 1235, "loss": 0.3431, "lr": 2.5281006653122288e-05, "epoch": 2.3684210526315788, "percentage": 47.37, "elapsed_time": "2:32:18", "remaining_time": "2:49:13"}
586
+ {"current_steps": 586, "total_steps": 1235, "loss": 0.3864, "lr": 2.5226438464257217e-05, "epoch": 2.3724696356275303, "percentage": 47.45, "elapsed_time": "2:32:35", "remaining_time": "2:48:59"}
587
+ {"current_steps": 587, "total_steps": 1235, "loss": 0.3498, "lr": 2.5171828484929447e-05, "epoch": 2.376518218623482, "percentage": 47.53, "elapsed_time": "2:32:55", "remaining_time": "2:48:48"}
588
+ {"current_steps": 588, "total_steps": 1235, "loss": 0.356, "lr": 2.5117177151798934e-05, "epoch": 2.380566801619433, "percentage": 47.61, "elapsed_time": "2:33:10", "remaining_time": "2:48:32"}
589
+ {"current_steps": 589, "total_steps": 1235, "loss": 0.3523, "lr": 2.506248490185627e-05, "epoch": 2.3846153846153846, "percentage": 47.69, "elapsed_time": "2:33:22", "remaining_time": "2:48:13"}
590
+ {"current_steps": 590, "total_steps": 1235, "loss": 0.3809, "lr": 2.500775217241923e-05, "epoch": 2.388663967611336, "percentage": 47.77, "elapsed_time": "2:33:39", "remaining_time": "2:47:59"}
591
+ {"current_steps": 591, "total_steps": 1235, "loss": 0.3711, "lr": 2.4952979401129266e-05, "epoch": 2.3927125506072873, "percentage": 47.85, "elapsed_time": "2:33:52", "remaining_time": "2:47:40"}
592
+ {"current_steps": 592, "total_steps": 1235, "loss": 0.3478, "lr": 2.4898167025948e-05, "epoch": 2.396761133603239, "percentage": 47.94, "elapsed_time": "2:34:07", "remaining_time": "2:47:24"}
593
+ {"current_steps": 593, "total_steps": 1235, "loss": 0.3684, "lr": 2.4843315485153703e-05, "epoch": 2.4008097165991904, "percentage": 48.02, "elapsed_time": "2:34:22", "remaining_time": "2:47:08"}
594
+ {"current_steps": 594, "total_steps": 1235, "loss": 0.3695, "lr": 2.4788425217337856e-05, "epoch": 2.4048582995951415, "percentage": 48.1, "elapsed_time": "2:34:36", "remaining_time": "2:46:50"}
595
+ {"current_steps": 595, "total_steps": 1235, "loss": 0.364, "lr": 2.4733496661401572e-05, "epoch": 2.408906882591093, "percentage": 48.18, "elapsed_time": "2:34:52", "remaining_time": "2:46:34"}
596
+ {"current_steps": 596, "total_steps": 1235, "loss": 0.3956, "lr": 2.4678530256552114e-05, "epoch": 2.4129554655870447, "percentage": 48.26, "elapsed_time": "2:35:07", "remaining_time": "2:46:19"}
597
+ {"current_steps": 597, "total_steps": 1235, "loss": 0.3563, "lr": 2.46235264422994e-05, "epoch": 2.417004048582996, "percentage": 48.34, "elapsed_time": "2:35:26", "remaining_time": "2:46:07"}
598
+ {"current_steps": 598, "total_steps": 1235, "loss": 0.3498, "lr": 2.4568485658452452e-05, "epoch": 2.4210526315789473, "percentage": 48.42, "elapsed_time": "2:35:40", "remaining_time": "2:45:50"}
599
+ {"current_steps": 599, "total_steps": 1235, "loss": 0.3629, "lr": 2.451340834511592e-05, "epoch": 2.425101214574899, "percentage": 48.5, "elapsed_time": "2:36:01", "remaining_time": "2:45:39"}
600
+ {"current_steps": 600, "total_steps": 1235, "loss": 0.351, "lr": 2.4458294942686528e-05, "epoch": 2.42914979757085, "percentage": 48.58, "elapsed_time": "2:36:17", "remaining_time": "2:45:24"}
601
+ {"current_steps": 601, "total_steps": 1235, "loss": 0.3587, "lr": 2.440314589184958e-05, "epoch": 2.4331983805668016, "percentage": 48.66, "elapsed_time": "2:36:29", "remaining_time": "2:45:05"}
602
+ {"current_steps": 602, "total_steps": 1235, "loss": 0.377, "lr": 2.434796163357541e-05, "epoch": 2.437246963562753, "percentage": 48.74, "elapsed_time": "2:36:43", "remaining_time": "2:44:47"}
603
+ {"current_steps": 603, "total_steps": 1235, "loss": 0.3391, "lr": 2.429274260911588e-05, "epoch": 2.4412955465587043, "percentage": 48.83, "elapsed_time": "2:36:58", "remaining_time": "2:44:30"}
604
+ {"current_steps": 604, "total_steps": 1235, "loss": 0.3695, "lr": 2.423748926000084e-05, "epoch": 2.445344129554656, "percentage": 48.91, "elapsed_time": "2:37:13", "remaining_time": "2:44:14"}
605
+ {"current_steps": 605, "total_steps": 1235, "loss": 0.3691, "lr": 2.418220202803459e-05, "epoch": 2.4493927125506074, "percentage": 48.99, "elapsed_time": "2:37:30", "remaining_time": "2:44:00"}
606
+ {"current_steps": 606, "total_steps": 1235, "loss": 0.3602, "lr": 2.412688135529237e-05, "epoch": 2.4534412955465585, "percentage": 49.07, "elapsed_time": "2:37:44", "remaining_time": "2:43:44"}
607
+ {"current_steps": 607, "total_steps": 1235, "loss": 0.3659, "lr": 2.4071527684116807e-05, "epoch": 2.45748987854251, "percentage": 49.15, "elapsed_time": "2:38:04", "remaining_time": "2:43:32"}
608
+ {"current_steps": 608, "total_steps": 1235, "loss": 0.3613, "lr": 2.4016141457114372e-05, "epoch": 2.4615384615384617, "percentage": 49.23, "elapsed_time": "2:38:20", "remaining_time": "2:43:17"}
609
+ {"current_steps": 609, "total_steps": 1235, "loss": 0.3841, "lr": 2.396072311715187e-05, "epoch": 2.465587044534413, "percentage": 49.31, "elapsed_time": "2:38:37", "remaining_time": "2:43:03"}
610
+ {"current_steps": 610, "total_steps": 1235, "loss": 0.3486, "lr": 2.3905273107352863e-05, "epoch": 2.4696356275303644, "percentage": 49.39, "elapsed_time": "2:38:54", "remaining_time": "2:42:49"}
611
+ {"current_steps": 611, "total_steps": 1235, "loss": 0.3613, "lr": 2.3849791871094157e-05, "epoch": 2.473684210526316, "percentage": 49.47, "elapsed_time": "2:39:10", "remaining_time": "2:42:34"}
612
+ {"current_steps": 612, "total_steps": 1235, "loss": 0.3488, "lr": 2.379427985200223e-05, "epoch": 2.477732793522267, "percentage": 49.55, "elapsed_time": "2:39:21", "remaining_time": "2:42:13"}
613
+ {"current_steps": 613, "total_steps": 1235, "loss": 0.3523, "lr": 2.373873749394972e-05, "epoch": 2.4817813765182186, "percentage": 49.64, "elapsed_time": "2:39:38", "remaining_time": "2:41:58"}
614
+ {"current_steps": 614, "total_steps": 1235, "loss": 0.3589, "lr": 2.3683165241051836e-05, "epoch": 2.48582995951417, "percentage": 49.72, "elapsed_time": "2:39:54", "remaining_time": "2:41:43"}
615
+ {"current_steps": 615, "total_steps": 1235, "loss": 0.3387, "lr": 2.3627563537662823e-05, "epoch": 2.4898785425101213, "percentage": 49.8, "elapsed_time": "2:40:10", "remaining_time": "2:41:28"}
616
+ {"current_steps": 616, "total_steps": 1235, "loss": 0.3838, "lr": 2.3571932828372433e-05, "epoch": 2.493927125506073, "percentage": 49.88, "elapsed_time": "2:40:23", "remaining_time": "2:41:10"}
617
+ {"current_steps": 617, "total_steps": 1235, "loss": 0.3422, "lr": 2.351627355800233e-05, "epoch": 2.4979757085020244, "percentage": 49.96, "elapsed_time": "2:40:37", "remaining_time": "2:40:53"}
618
+ {"current_steps": 618, "total_steps": 1235, "loss": 0.3405, "lr": 2.346058617160256e-05, "epoch": 2.5020242914979756, "percentage": 50.04, "elapsed_time": "2:40:53", "remaining_time": "2:40:37"}
619
+ {"current_steps": 619, "total_steps": 1235, "loss": 0.3621, "lr": 2.3404871114447976e-05, "epoch": 2.506072874493927, "percentage": 50.12, "elapsed_time": "2:41:10", "remaining_time": "2:40:23"}
620
+ {"current_steps": 620, "total_steps": 1235, "loss": 0.3379, "lr": 2.334912883203469e-05, "epoch": 2.5101214574898787, "percentage": 50.2, "elapsed_time": "2:41:26", "remaining_time": "2:40:08"}
621
+ {"current_steps": 621, "total_steps": 1235, "loss": 0.3731, "lr": 2.3293359770076505e-05, "epoch": 2.51417004048583, "percentage": 50.28, "elapsed_time": "2:41:39", "remaining_time": "2:39:50"}
622
+ {"current_steps": 622, "total_steps": 1235, "loss": 0.3739, "lr": 2.323756437450136e-05, "epoch": 2.5182186234817814, "percentage": 50.36, "elapsed_time": "2:41:53", "remaining_time": "2:39:32"}
623
+ {"current_steps": 623, "total_steps": 1235, "loss": 0.3651, "lr": 2.3181743091447754e-05, "epoch": 2.522267206477733, "percentage": 50.45, "elapsed_time": "2:42:06", "remaining_time": "2:39:14"}
624
+ {"current_steps": 624, "total_steps": 1235, "loss": 0.3746, "lr": 2.3125896367261164e-05, "epoch": 2.526315789473684, "percentage": 50.53, "elapsed_time": "2:42:21", "remaining_time": "2:38:58"}
625
+ {"current_steps": 625, "total_steps": 1235, "loss": 0.368, "lr": 2.307002464849052e-05, "epoch": 2.5303643724696356, "percentage": 50.61, "elapsed_time": "2:42:35", "remaining_time": "2:38:41"}
626
+ {"current_steps": 626, "total_steps": 1235, "loss": 0.3627, "lr": 2.30141283818846e-05, "epoch": 2.534412955465587, "percentage": 50.69, "elapsed_time": "2:42:47", "remaining_time": "2:38:22"}
627
+ {"current_steps": 627, "total_steps": 1235, "loss": 0.3539, "lr": 2.2958208014388462e-05, "epoch": 2.5384615384615383, "percentage": 50.77, "elapsed_time": "2:43:04", "remaining_time": "2:38:07"}
628
+ {"current_steps": 628, "total_steps": 1235, "loss": 0.3477, "lr": 2.2902263993139857e-05, "epoch": 2.54251012145749, "percentage": 50.85, "elapsed_time": "2:43:18", "remaining_time": "2:37:50"}
629
+ {"current_steps": 629, "total_steps": 1235, "loss": 0.3689, "lr": 2.2846296765465708e-05, "epoch": 2.5465587044534415, "percentage": 50.93, "elapsed_time": "2:43:33", "remaining_time": "2:37:35"}
630
+ {"current_steps": 630, "total_steps": 1235, "loss": 0.3641, "lr": 2.2790306778878465e-05, "epoch": 2.5506072874493926, "percentage": 51.01, "elapsed_time": "2:43:49", "remaining_time": "2:37:19"}
631
+ {"current_steps": 631, "total_steps": 1235, "loss": 0.3402, "lr": 2.273429448107257e-05, "epoch": 2.554655870445344, "percentage": 51.09, "elapsed_time": "2:44:07", "remaining_time": "2:37:06"}
632
+ {"current_steps": 632, "total_steps": 1235, "loss": 0.3587, "lr": 2.2678260319920868e-05, "epoch": 2.5587044534412957, "percentage": 51.17, "elapsed_time": "2:44:24", "remaining_time": "2:36:51"}
633
+ {"current_steps": 633, "total_steps": 1235, "loss": 0.3582, "lr": 2.262220474347102e-05, "epoch": 2.562753036437247, "percentage": 51.26, "elapsed_time": "2:44:41", "remaining_time": "2:36:37"}
634
+ {"current_steps": 634, "total_steps": 1235, "loss": 0.3541, "lr": 2.2566128199941918e-05, "epoch": 2.5668016194331984, "percentage": 51.34, "elapsed_time": "2:44:56", "remaining_time": "2:36:21"}
635
+ {"current_steps": 635, "total_steps": 1235, "loss": 0.3639, "lr": 2.2510031137720104e-05, "epoch": 2.57085020242915, "percentage": 51.42, "elapsed_time": "2:45:14", "remaining_time": "2:36:07"}
636
+ {"current_steps": 636, "total_steps": 1235, "loss": 0.3491, "lr": 2.2453914005356206e-05, "epoch": 2.574898785425101, "percentage": 51.5, "elapsed_time": "2:45:30", "remaining_time": "2:35:53"}
637
+ {"current_steps": 637, "total_steps": 1235, "loss": 0.3752, "lr": 2.2397777251561302e-05, "epoch": 2.5789473684210527, "percentage": 51.58, "elapsed_time": "2:45:49", "remaining_time": "2:35:40"}
638
+ {"current_steps": 638, "total_steps": 1235, "loss": 0.3762, "lr": 2.2341621325203393e-05, "epoch": 2.582995951417004, "percentage": 51.66, "elapsed_time": "2:46:04", "remaining_time": "2:35:23"}
639
+ {"current_steps": 639, "total_steps": 1235, "loss": 0.3612, "lr": 2.2285446675303764e-05, "epoch": 2.5870445344129553, "percentage": 51.74, "elapsed_time": "2:46:17", "remaining_time": "2:35:05"}
640
+ {"current_steps": 640, "total_steps": 1235, "loss": 0.3494, "lr": 2.2229253751033423e-05, "epoch": 2.591093117408907, "percentage": 51.82, "elapsed_time": "2:46:30", "remaining_time": "2:34:47"}
641
+ {"current_steps": 641, "total_steps": 1235, "loss": 0.3707, "lr": 2.2173043001709492e-05, "epoch": 2.5951417004048585, "percentage": 51.9, "elapsed_time": "2:46:46", "remaining_time": "2:34:32"}
642
+ {"current_steps": 642, "total_steps": 1235, "loss": 0.3622, "lr": 2.2116814876791627e-05, "epoch": 2.5991902834008096, "percentage": 51.98, "elapsed_time": "2:47:00", "remaining_time": "2:34:15"}
643
+ {"current_steps": 643, "total_steps": 1235, "loss": 0.3725, "lr": 2.2060569825878413e-05, "epoch": 2.603238866396761, "percentage": 52.06, "elapsed_time": "2:47:19", "remaining_time": "2:34:03"}
644
+ {"current_steps": 644, "total_steps": 1235, "loss": 0.3681, "lr": 2.2004308298703777e-05, "epoch": 2.6072874493927127, "percentage": 52.15, "elapsed_time": "2:47:38", "remaining_time": "2:33:50"}
645
+ {"current_steps": 645, "total_steps": 1235, "loss": 0.3755, "lr": 2.1948030745133396e-05, "epoch": 2.611336032388664, "percentage": 52.23, "elapsed_time": "2:47:53", "remaining_time": "2:33:34"}
646
+ {"current_steps": 646, "total_steps": 1235, "loss": 0.3637, "lr": 2.1891737615161083e-05, "epoch": 2.6153846153846154, "percentage": 52.31, "elapsed_time": "2:48:07", "remaining_time": "2:33:17"}
647
+ {"current_steps": 647, "total_steps": 1235, "loss": 0.3502, "lr": 2.1835429358905218e-05, "epoch": 2.619433198380567, "percentage": 52.39, "elapsed_time": "2:48:21", "remaining_time": "2:33:00"}
648
+ {"current_steps": 648, "total_steps": 1235, "loss": 0.3572, "lr": 2.17791064266051e-05, "epoch": 2.623481781376518, "percentage": 52.47, "elapsed_time": "2:48:35", "remaining_time": "2:32:43"}
649
+ {"current_steps": 649, "total_steps": 1235, "loss": 0.3267, "lr": 2.172276926861741e-05, "epoch": 2.6275303643724697, "percentage": 52.55, "elapsed_time": "2:48:49", "remaining_time": "2:32:26"}
650
+ {"current_steps": 650, "total_steps": 1235, "loss": 0.3486, "lr": 2.166641833541255e-05, "epoch": 2.6315789473684212, "percentage": 52.63, "elapsed_time": "2:49:02", "remaining_time": "2:32:08"}
651
+ {"current_steps": 651, "total_steps": 1235, "loss": 0.376, "lr": 2.161005407757109e-05, "epoch": 2.6356275303643724, "percentage": 52.71, "elapsed_time": "2:49:20", "remaining_time": "2:31:54"}
652
+ {"current_steps": 652, "total_steps": 1235, "loss": 0.3387, "lr": 2.155367694578013e-05, "epoch": 2.639676113360324, "percentage": 52.79, "elapsed_time": "2:49:31", "remaining_time": "2:31:35"}
653
+ {"current_steps": 653, "total_steps": 1235, "loss": 0.3474, "lr": 2.1497287390829712e-05, "epoch": 2.6437246963562755, "percentage": 52.87, "elapsed_time": "2:49:48", "remaining_time": "2:31:20"}
654
+ {"current_steps": 654, "total_steps": 1235, "loss": 0.3644, "lr": 2.1440885863609208e-05, "epoch": 2.6477732793522266, "percentage": 52.96, "elapsed_time": "2:50:05", "remaining_time": "2:31:06"}
655
+ {"current_steps": 655, "total_steps": 1235, "loss": 0.3543, "lr": 2.1384472815103737e-05, "epoch": 2.651821862348178, "percentage": 53.04, "elapsed_time": "2:50:22", "remaining_time": "2:30:51"}
656
+ {"current_steps": 656, "total_steps": 1235, "loss": 0.36, "lr": 2.1328048696390534e-05, "epoch": 2.6558704453441297, "percentage": 53.12, "elapsed_time": "2:50:39", "remaining_time": "2:30:37"}
657
+ {"current_steps": 657, "total_steps": 1235, "loss": 0.3721, "lr": 2.1271613958635342e-05, "epoch": 2.659919028340081, "percentage": 53.2, "elapsed_time": "2:50:58", "remaining_time": "2:30:24"}
658
+ {"current_steps": 658, "total_steps": 1235, "loss": 0.3396, "lr": 2.1215169053088825e-05, "epoch": 2.6639676113360324, "percentage": 53.28, "elapsed_time": "2:51:12", "remaining_time": "2:30:08"}
659
+ {"current_steps": 659, "total_steps": 1235, "loss": 0.3655, "lr": 2.1158714431082937e-05, "epoch": 2.668016194331984, "percentage": 53.36, "elapsed_time": "2:51:30", "remaining_time": "2:29:54"}
660
+ {"current_steps": 660, "total_steps": 1235, "loss": 0.3415, "lr": 2.110225054402733e-05, "epoch": 2.672064777327935, "percentage": 53.44, "elapsed_time": "2:51:45", "remaining_time": "2:29:38"}
661
+ {"current_steps": 661, "total_steps": 1235, "loss": 0.3729, "lr": 2.1045777843405747e-05, "epoch": 2.6761133603238867, "percentage": 53.52, "elapsed_time": "2:51:59", "remaining_time": "2:29:21"}
662
+ {"current_steps": 662, "total_steps": 1235, "loss": 0.3461, "lr": 2.09892967807724e-05, "epoch": 2.6801619433198383, "percentage": 53.6, "elapsed_time": "2:52:16", "remaining_time": "2:29:06"}
663
+ {"current_steps": 663, "total_steps": 1235, "loss": 0.3409, "lr": 2.093280780774835e-05, "epoch": 2.6842105263157894, "percentage": 53.68, "elapsed_time": "2:52:29", "remaining_time": "2:28:48"}
664
+ {"current_steps": 664, "total_steps": 1235, "loss": 0.3535, "lr": 2.087631137601793e-05, "epoch": 2.688259109311741, "percentage": 53.77, "elapsed_time": "2:52:45", "remaining_time": "2:28:33"}
665
+ {"current_steps": 665, "total_steps": 1235, "loss": 0.3857, "lr": 2.0819807937325104e-05, "epoch": 2.6923076923076925, "percentage": 53.85, "elapsed_time": "2:53:03", "remaining_time": "2:28:19"}
666
+ {"current_steps": 666, "total_steps": 1235, "loss": 0.3508, "lr": 2.0763297943469847e-05, "epoch": 2.6963562753036436, "percentage": 53.93, "elapsed_time": "2:53:17", "remaining_time": "2:28:02"}
667
+ {"current_steps": 667, "total_steps": 1235, "loss": 0.3565, "lr": 2.070678184630458e-05, "epoch": 2.700404858299595, "percentage": 54.01, "elapsed_time": "2:53:35", "remaining_time": "2:27:49"}
668
+ {"current_steps": 668, "total_steps": 1235, "loss": 0.3387, "lr": 2.06502600977305e-05, "epoch": 2.7044534412955468, "percentage": 54.09, "elapsed_time": "2:53:50", "remaining_time": "2:27:33"}
669
+ {"current_steps": 669, "total_steps": 1235, "loss": 0.3735, "lr": 2.0593733149694008e-05, "epoch": 2.708502024291498, "percentage": 54.17, "elapsed_time": "2:54:06", "remaining_time": "2:27:17"}
670
+ {"current_steps": 670, "total_steps": 1235, "loss": 0.3569, "lr": 2.0537201454183074e-05, "epoch": 2.7125506072874495, "percentage": 54.25, "elapsed_time": "2:54:22", "remaining_time": "2:27:03"}
671
+ {"current_steps": 671, "total_steps": 1235, "loss": 0.3578, "lr": 2.0480665463223626e-05, "epoch": 2.716599190283401, "percentage": 54.33, "elapsed_time": "2:54:36", "remaining_time": "2:26:45"}
672
+ {"current_steps": 672, "total_steps": 1235, "loss": 0.3515, "lr": 2.042412562887594e-05, "epoch": 2.720647773279352, "percentage": 54.41, "elapsed_time": "2:54:46", "remaining_time": "2:26:25"}
673
+ {"current_steps": 673, "total_steps": 1235, "loss": 0.3863, "lr": 2.0367582403231033e-05, "epoch": 2.7246963562753037, "percentage": 54.49, "elapsed_time": "2:55:05", "remaining_time": "2:26:12"}
674
+ {"current_steps": 674, "total_steps": 1235, "loss": 0.3806, "lr": 2.0311036238407023e-05, "epoch": 2.7287449392712553, "percentage": 54.57, "elapsed_time": "2:55:21", "remaining_time": "2:25:57"}
675
+ {"current_steps": 675, "total_steps": 1235, "loss": 0.3468, "lr": 2.0254487586545534e-05, "epoch": 2.7327935222672064, "percentage": 54.66, "elapsed_time": "2:55:36", "remaining_time": "2:25:41"}
676
+ {"current_steps": 676, "total_steps": 1235, "loss": 0.3609, "lr": 2.0197936899808088e-05, "epoch": 2.736842105263158, "percentage": 54.74, "elapsed_time": "2:55:51", "remaining_time": "2:25:25"}
677
+ {"current_steps": 677, "total_steps": 1235, "loss": 0.3502, "lr": 2.0141384630372466e-05, "epoch": 2.7408906882591095, "percentage": 54.82, "elapsed_time": "2:56:07", "remaining_time": "2:25:10"}
678
+ {"current_steps": 678, "total_steps": 1235, "loss": 0.37, "lr": 2.0084831230429106e-05, "epoch": 2.7449392712550607, "percentage": 54.9, "elapsed_time": "2:56:25", "remaining_time": "2:24:56"}
679
+ {"current_steps": 679, "total_steps": 1235, "loss": 0.3468, "lr": 2.0028277152177492e-05, "epoch": 2.748987854251012, "percentage": 54.98, "elapsed_time": "2:56:39", "remaining_time": "2:24:39"}
680
+ {"current_steps": 680, "total_steps": 1235, "loss": 0.3553, "lr": 1.9971722847822518e-05, "epoch": 2.753036437246964, "percentage": 55.06, "elapsed_time": "2:56:51", "remaining_time": "2:24:20"}
681
+ {"current_steps": 681, "total_steps": 1235, "loss": 0.348, "lr": 1.99151687695709e-05, "epoch": 2.757085020242915, "percentage": 55.14, "elapsed_time": "2:57:06", "remaining_time": "2:24:04"}
682
+ {"current_steps": 682, "total_steps": 1235, "loss": 0.3621, "lr": 1.9858615369627537e-05, "epoch": 2.7611336032388665, "percentage": 55.22, "elapsed_time": "2:57:22", "remaining_time": "2:23:49"}
683
+ {"current_steps": 683, "total_steps": 1235, "loss": 0.3759, "lr": 1.9802063100191916e-05, "epoch": 2.765182186234818, "percentage": 55.3, "elapsed_time": "2:57:38", "remaining_time": "2:23:34"}
684
+ {"current_steps": 684, "total_steps": 1235, "loss": 0.3522, "lr": 1.974551241345447e-05, "epoch": 2.769230769230769, "percentage": 55.38, "elapsed_time": "2:57:49", "remaining_time": "2:23:14"}
685
+ {"current_steps": 685, "total_steps": 1235, "loss": 0.3704, "lr": 1.9688963761592984e-05, "epoch": 2.7732793522267207, "percentage": 55.47, "elapsed_time": "2:58:08", "remaining_time": "2:23:01"}
686
+ {"current_steps": 686, "total_steps": 1235, "loss": 0.3533, "lr": 1.963241759676897e-05, "epoch": 2.7773279352226723, "percentage": 55.55, "elapsed_time": "2:58:22", "remaining_time": "2:22:45"}
687
+ {"current_steps": 687, "total_steps": 1235, "loss": 0.3645, "lr": 1.9575874371124066e-05, "epoch": 2.7813765182186234, "percentage": 55.63, "elapsed_time": "2:58:36", "remaining_time": "2:22:28"}
688
+ {"current_steps": 688, "total_steps": 1235, "loss": 0.3428, "lr": 1.951933453677638e-05, "epoch": 2.785425101214575, "percentage": 55.71, "elapsed_time": "2:58:50", "remaining_time": "2:22:11"}
689
+ {"current_steps": 689, "total_steps": 1235, "loss": 0.3537, "lr": 1.9462798545816932e-05, "epoch": 2.7894736842105265, "percentage": 55.79, "elapsed_time": "2:59:02", "remaining_time": "2:21:53"}
690
+ {"current_steps": 690, "total_steps": 1235, "loss": 0.3602, "lr": 1.9406266850305996e-05, "epoch": 2.7935222672064777, "percentage": 55.87, "elapsed_time": "2:59:16", "remaining_time": "2:21:36"}
691
+ {"current_steps": 691, "total_steps": 1235, "loss": 0.3584, "lr": 1.9349739902269503e-05, "epoch": 2.7975708502024292, "percentage": 55.95, "elapsed_time": "2:59:32", "remaining_time": "2:21:21"}
692
+ {"current_steps": 692, "total_steps": 1235, "loss": 0.3624, "lr": 1.9293218153695425e-05, "epoch": 2.801619433198381, "percentage": 56.03, "elapsed_time": "2:59:49", "remaining_time": "2:21:06"}
693
+ {"current_steps": 693, "total_steps": 1235, "loss": 0.362, "lr": 1.9236702056530153e-05, "epoch": 2.805668016194332, "percentage": 56.11, "elapsed_time": "3:00:07", "remaining_time": "2:20:52"}
694
+ {"current_steps": 694, "total_steps": 1235, "loss": 0.3303, "lr": 1.9180192062674907e-05, "epoch": 2.8097165991902835, "percentage": 56.19, "elapsed_time": "3:00:20", "remaining_time": "2:20:34"}
695
+ {"current_steps": 695, "total_steps": 1235, "loss": 0.3679, "lr": 1.9123688623982076e-05, "epoch": 2.813765182186235, "percentage": 56.28, "elapsed_time": "3:00:35", "remaining_time": "2:20:19"}
696
+ {"current_steps": 696, "total_steps": 1235, "loss": 0.3566, "lr": 1.906719219225165e-05, "epoch": 2.817813765182186, "percentage": 56.36, "elapsed_time": "3:00:50", "remaining_time": "2:20:03"}
697
+ {"current_steps": 697, "total_steps": 1235, "loss": 0.3789, "lr": 1.9010703219227603e-05, "epoch": 2.8218623481781377, "percentage": 56.44, "elapsed_time": "3:01:09", "remaining_time": "2:19:49"}
698
+ {"current_steps": 698, "total_steps": 1235, "loss": 0.3498, "lr": 1.8954222156594256e-05, "epoch": 2.8259109311740893, "percentage": 56.52, "elapsed_time": "3:01:25", "remaining_time": "2:19:34"}
699
+ {"current_steps": 699, "total_steps": 1235, "loss": 0.3441, "lr": 1.8897749455972673e-05, "epoch": 2.8299595141700404, "percentage": 56.6, "elapsed_time": "3:01:38", "remaining_time": "2:19:16"}
700
+ {"current_steps": 700, "total_steps": 1235, "loss": 0.3455, "lr": 1.884128556891707e-05, "epoch": 2.834008097165992, "percentage": 56.68, "elapsed_time": "3:01:53", "remaining_time": "2:19:01"}
701
+ {"current_steps": 701, "total_steps": 1235, "loss": 0.3384, "lr": 1.878483094691119e-05, "epoch": 2.8380566801619436, "percentage": 56.76, "elapsed_time": "3:02:13", "remaining_time": "2:18:48"}
702
+ {"current_steps": 702, "total_steps": 1235, "loss": 0.3269, "lr": 1.8728386041364664e-05, "epoch": 2.8421052631578947, "percentage": 56.84, "elapsed_time": "3:02:27", "remaining_time": "2:18:32"}
703
+ {"current_steps": 703, "total_steps": 1235, "loss": 0.3662, "lr": 1.867195130360947e-05, "epoch": 2.8461538461538463, "percentage": 56.92, "elapsed_time": "3:02:40", "remaining_time": "2:18:14"}
704
+ {"current_steps": 704, "total_steps": 1235, "loss": 0.3341, "lr": 1.8615527184896263e-05, "epoch": 2.850202429149798, "percentage": 57.0, "elapsed_time": "3:02:54", "remaining_time": "2:17:57"}
705
+ {"current_steps": 705, "total_steps": 1235, "loss": 0.3455, "lr": 1.8559114136390795e-05, "epoch": 2.854251012145749, "percentage": 57.09, "elapsed_time": "3:03:05", "remaining_time": "2:17:38"}
706
+ {"current_steps": 706, "total_steps": 1235, "loss": 0.3576, "lr": 1.8502712609170298e-05, "epoch": 2.8582995951417005, "percentage": 57.17, "elapsed_time": "3:03:20", "remaining_time": "2:17:22"}
707
+ {"current_steps": 707, "total_steps": 1235, "loss": 0.3504, "lr": 1.8446323054219876e-05, "epoch": 2.862348178137652, "percentage": 57.25, "elapsed_time": "3:03:34", "remaining_time": "2:17:05"}
708
+ {"current_steps": 708, "total_steps": 1235, "loss": 0.369, "lr": 1.838994592242891e-05, "epoch": 2.866396761133603, "percentage": 57.33, "elapsed_time": "3:03:50", "remaining_time": "2:16:50"}
709
+ {"current_steps": 709, "total_steps": 1235, "loss": 0.3691, "lr": 1.8333581664587453e-05, "epoch": 2.8704453441295548, "percentage": 57.41, "elapsed_time": "3:04:06", "remaining_time": "2:16:35"}
710
+ {"current_steps": 710, "total_steps": 1235, "loss": 0.3578, "lr": 1.8277230731382593e-05, "epoch": 2.8744939271255063, "percentage": 57.49, "elapsed_time": "3:04:18", "remaining_time": "2:16:17"}
711
+ {"current_steps": 711, "total_steps": 1235, "loss": 0.3508, "lr": 1.82208935733949e-05, "epoch": 2.8785425101214575, "percentage": 57.57, "elapsed_time": "3:04:36", "remaining_time": "2:16:02"}
712
+ {"current_steps": 712, "total_steps": 1235, "loss": 0.3578, "lr": 1.8164570641094793e-05, "epoch": 2.882591093117409, "percentage": 57.65, "elapsed_time": "3:04:46", "remaining_time": "2:15:43"}
713
+ {"current_steps": 713, "total_steps": 1235, "loss": 0.3607, "lr": 1.810826238483892e-05, "epoch": 2.8866396761133606, "percentage": 57.73, "elapsed_time": "3:05:03", "remaining_time": "2:15:28"}
714
+ {"current_steps": 714, "total_steps": 1235, "loss": 0.3412, "lr": 1.8051969254866608e-05, "epoch": 2.8906882591093117, "percentage": 57.81, "elapsed_time": "3:05:18", "remaining_time": "2:15:12"}
715
+ {"current_steps": 715, "total_steps": 1235, "loss": 0.3394, "lr": 1.7995691701296226e-05, "epoch": 2.8947368421052633, "percentage": 57.89, "elapsed_time": "3:05:34", "remaining_time": "2:14:58"}
716
+ {"current_steps": 716, "total_steps": 1235, "loss": 0.3911, "lr": 1.7939430174121593e-05, "epoch": 2.898785425101215, "percentage": 57.98, "elapsed_time": "3:05:46", "remaining_time": "2:14:39"}
717
+ {"current_steps": 717, "total_steps": 1235, "loss": 0.365, "lr": 1.788318512320838e-05, "epoch": 2.902834008097166, "percentage": 58.06, "elapsed_time": "3:05:59", "remaining_time": "2:14:22"}
718
+ {"current_steps": 718, "total_steps": 1235, "loss": 0.3654, "lr": 1.782695699829051e-05, "epoch": 2.9068825910931175, "percentage": 58.14, "elapsed_time": "3:06:15", "remaining_time": "2:14:07"}
719
+ {"current_steps": 719, "total_steps": 1235, "loss": 0.3452, "lr": 1.7770746248966587e-05, "epoch": 2.910931174089069, "percentage": 58.22, "elapsed_time": "3:06:30", "remaining_time": "2:13:50"}
720
+ {"current_steps": 720, "total_steps": 1235, "loss": 0.384, "lr": 1.7714553324696243e-05, "epoch": 2.91497975708502, "percentage": 58.3, "elapsed_time": "3:06:50", "remaining_time": "2:13:38"}
721
+ {"current_steps": 721, "total_steps": 1235, "loss": 0.3512, "lr": 1.7658378674796614e-05, "epoch": 2.919028340080972, "percentage": 58.38, "elapsed_time": "3:07:08", "remaining_time": "2:13:24"}
722
+ {"current_steps": 722, "total_steps": 1235, "loss": 0.3686, "lr": 1.76022227484387e-05, "epoch": 2.9230769230769234, "percentage": 58.46, "elapsed_time": "3:07:24", "remaining_time": "2:13:09"}
723
+ {"current_steps": 723, "total_steps": 1235, "loss": 0.3509, "lr": 1.7546085994643807e-05, "epoch": 2.9271255060728745, "percentage": 58.54, "elapsed_time": "3:07:37", "remaining_time": "2:12:51"}
724
+ {"current_steps": 724, "total_steps": 1235, "loss": 0.3714, "lr": 1.7489968862279902e-05, "epoch": 2.931174089068826, "percentage": 58.62, "elapsed_time": "3:07:53", "remaining_time": "2:12:36"}
725
+ {"current_steps": 725, "total_steps": 1235, "loss": 0.3306, "lr": 1.743387180005809e-05, "epoch": 2.9352226720647776, "percentage": 58.7, "elapsed_time": "3:08:04", "remaining_time": "2:12:17"}
726
+ {"current_steps": 726, "total_steps": 1235, "loss": 0.3625, "lr": 1.737779525652899e-05, "epoch": 2.9392712550607287, "percentage": 58.79, "elapsed_time": "3:08:20", "remaining_time": "2:12:02"}
727
+ {"current_steps": 727, "total_steps": 1235, "loss": 0.3458, "lr": 1.732173968007914e-05, "epoch": 2.9433198380566803, "percentage": 58.87, "elapsed_time": "3:08:34", "remaining_time": "2:11:46"}
728
+ {"current_steps": 728, "total_steps": 1235, "loss": 0.3368, "lr": 1.7265705518927437e-05, "epoch": 2.9473684210526314, "percentage": 58.95, "elapsed_time": "3:08:51", "remaining_time": "2:11:31"}
729
+ {"current_steps": 729, "total_steps": 1235, "loss": 0.3442, "lr": 1.7209693221121542e-05, "epoch": 2.951417004048583, "percentage": 59.03, "elapsed_time": "3:09:08", "remaining_time": "2:11:16"}
730
+ {"current_steps": 730, "total_steps": 1235, "loss": 0.354, "lr": 1.7153703234534302e-05, "epoch": 2.9554655870445345, "percentage": 59.11, "elapsed_time": "3:09:25", "remaining_time": "2:11:02"}
731
+ {"current_steps": 731, "total_steps": 1235, "loss": 0.3254, "lr": 1.709773600686015e-05, "epoch": 2.9595141700404857, "percentage": 59.19, "elapsed_time": "3:09:40", "remaining_time": "2:10:46"}
732
+ {"current_steps": 732, "total_steps": 1235, "loss": 0.3764, "lr": 1.7041791985611548e-05, "epoch": 2.9635627530364372, "percentage": 59.27, "elapsed_time": "3:09:57", "remaining_time": "2:10:31"}
733
+ {"current_steps": 733, "total_steps": 1235, "loss": 0.3487, "lr": 1.69858716181154e-05, "epoch": 2.967611336032389, "percentage": 59.35, "elapsed_time": "3:10:11", "remaining_time": "2:10:15"}
734
+ {"current_steps": 734, "total_steps": 1235, "loss": 0.3744, "lr": 1.692997535150948e-05, "epoch": 2.97165991902834, "percentage": 59.43, "elapsed_time": "3:10:30", "remaining_time": "2:10:01"}
735
+ {"current_steps": 735, "total_steps": 1235, "loss": 0.3583, "lr": 1.687410363273884e-05, "epoch": 2.9757085020242915, "percentage": 59.51, "elapsed_time": "3:10:43", "remaining_time": "2:09:44"}
736
+ {"current_steps": 736, "total_steps": 1235, "loss": 0.3676, "lr": 1.6818256908552257e-05, "epoch": 2.979757085020243, "percentage": 59.6, "elapsed_time": "3:11:01", "remaining_time": "2:09:30"}
737
+ {"current_steps": 737, "total_steps": 1235, "loss": 0.376, "lr": 1.6762435625498646e-05, "epoch": 2.983805668016194, "percentage": 59.68, "elapsed_time": "3:11:18", "remaining_time": "2:09:16"}
738
+ {"current_steps": 738, "total_steps": 1235, "loss": 0.3549, "lr": 1.67066402299235e-05, "epoch": 2.9878542510121457, "percentage": 59.76, "elapsed_time": "3:11:37", "remaining_time": "2:09:03"}
739
+ {"current_steps": 739, "total_steps": 1235, "loss": 0.3517, "lr": 1.6650871167965313e-05, "epoch": 2.9919028340080973, "percentage": 59.84, "elapsed_time": "3:11:53", "remaining_time": "2:08:47"}
740
+ {"current_steps": 740, "total_steps": 1235, "loss": 0.3414, "lr": 1.6595128885552028e-05, "epoch": 2.9959514170040484, "percentage": 59.92, "elapsed_time": "3:12:05", "remaining_time": "2:08:29"}
741
+ {"current_steps": 741, "total_steps": 1235, "loss": 0.3571, "lr": 1.653941382839745e-05, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "3:12:20", "remaining_time": "2:08:13"}
742
+ {"current_steps": 742, "total_steps": 1235, "loss": 0.2311, "lr": 1.6483726441997673e-05, "epoch": 3.0040485829959516, "percentage": 60.08, "elapsed_time": "3:14:24", "remaining_time": "2:09:10"}
743
+ {"current_steps": 743, "total_steps": 1235, "loss": 0.2359, "lr": 1.642806717162757e-05, "epoch": 3.0080971659919027, "percentage": 60.16, "elapsed_time": "3:14:39", "remaining_time": "2:08:54"}
744
+ {"current_steps": 744, "total_steps": 1235, "loss": 0.2186, "lr": 1.637243646233718e-05, "epoch": 3.0121457489878543, "percentage": 60.24, "elapsed_time": "3:14:52", "remaining_time": "2:08:36"}
745
+ {"current_steps": 745, "total_steps": 1235, "loss": 0.2491, "lr": 1.6316834758948174e-05, "epoch": 3.016194331983806, "percentage": 60.32, "elapsed_time": "3:15:09", "remaining_time": "2:08:21"}
746
+ {"current_steps": 746, "total_steps": 1235, "loss": 0.2163, "lr": 1.6261262506050282e-05, "epoch": 3.020242914979757, "percentage": 60.4, "elapsed_time": "3:15:22", "remaining_time": "2:08:03"}
747
+ {"current_steps": 747, "total_steps": 1235, "loss": 0.2391, "lr": 1.620572014799777e-05, "epoch": 3.0242914979757085, "percentage": 60.49, "elapsed_time": "3:15:39", "remaining_time": "2:07:49"}
748
+ {"current_steps": 748, "total_steps": 1235, "loss": 0.236, "lr": 1.6150208128905857e-05, "epoch": 3.02834008097166, "percentage": 60.57, "elapsed_time": "3:15:49", "remaining_time": "2:07:29"}
749
+ {"current_steps": 749, "total_steps": 1235, "loss": 0.2399, "lr": 1.6094726892647147e-05, "epoch": 3.032388663967611, "percentage": 60.65, "elapsed_time": "3:16:00", "remaining_time": "2:07:11"}
750
+ {"current_steps": 750, "total_steps": 1235, "loss": 0.2403, "lr": 1.6039276882848135e-05, "epoch": 3.0364372469635628, "percentage": 60.73, "elapsed_time": "3:16:19", "remaining_time": "2:06:57"}
751
+ {"current_steps": 751, "total_steps": 1235, "loss": 0.2439, "lr": 1.5983858542885635e-05, "epoch": 3.0404858299595143, "percentage": 60.81, "elapsed_time": "3:16:32", "remaining_time": "2:06:39"}
752
+ {"current_steps": 752, "total_steps": 1235, "loss": 0.227, "lr": 1.5928472315883203e-05, "epoch": 3.0445344129554655, "percentage": 60.89, "elapsed_time": "3:16:47", "remaining_time": "2:06:24"}
753
+ {"current_steps": 753, "total_steps": 1235, "loss": 0.245, "lr": 1.5873118644707633e-05, "epoch": 3.048582995951417, "percentage": 60.97, "elapsed_time": "3:17:03", "remaining_time": "2:06:08"}
754
+ {"current_steps": 754, "total_steps": 1235, "loss": 0.199, "lr": 1.5817797971965413e-05, "epoch": 3.0526315789473686, "percentage": 61.05, "elapsed_time": "3:17:19", "remaining_time": "2:05:52"}