neginr commited on
Commit
b84f685
·
verified ·
1 Parent(s): 9fbd370

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 sha256:2bcb15949aa71b676d8389ec6aa5b209cc359744e782824a7862b4b3c4f18ecf
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a61d8b1532510792a8060e2ef458585b9f95984ed43afe420d0993e3d561c4d0
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:d0b326fee4a7d0fef9640880adca6dc576a9b5846a2417757215f30e0603b143
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d265f1c5acfce00f7cb4c9818c57026ac71dbefda80144cad78e1de6f3a90d9
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:bffdcaa42bf89d09fa1922eb6b64543d120c7beb04991219952bf38b5d1f43e9
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a59adb3a3ffac04d5ad5dd1d338cd3bb57d528aab6a176f5613311ee6375c0ef
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73072c48326e8b28f529cf373ee433d570c6110443be6ce18842903cf1375c7a
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39ee84b0e6d1b2346ad07875b618457dae9c76726dc1bcd31951038d5d1bd212
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -503,3 +503,249 @@
503
  {"current_steps": 503, "total_steps": 1235, "loss": 0.2486, "lr": 2.95725682050846e-05, "epoch": 2.0364372469635628, "percentage": 40.73, "elapsed_time": "2:25:54", "remaining_time": "3:32:20"}
504
  {"current_steps": 504, "total_steps": 1235, "loss": 0.2547, "lr": 2.9522874311100684e-05, "epoch": 2.0404858299595143, "percentage": 40.81, "elapsed_time": "2:26:12", "remaining_time": "3:32:02"}
505
  {"current_steps": 505, "total_steps": 1235, "loss": 0.2391, "lr": 2.9473104272467526e-05, "epoch": 2.0445344129554655, "percentage": 40.89, "elapsed_time": "2:26:30", "remaining_time": "3:31:47"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
503
  {"current_steps": 503, "total_steps": 1235, "loss": 0.2486, "lr": 2.95725682050846e-05, "epoch": 2.0364372469635628, "percentage": 40.73, "elapsed_time": "2:25:54", "remaining_time": "3:32:20"}
504
  {"current_steps": 504, "total_steps": 1235, "loss": 0.2547, "lr": 2.9522874311100684e-05, "epoch": 2.0404858299595143, "percentage": 40.81, "elapsed_time": "2:26:12", "remaining_time": "3:32:02"}
505
  {"current_steps": 505, "total_steps": 1235, "loss": 0.2391, "lr": 2.9473104272467526e-05, "epoch": 2.0445344129554655, "percentage": 40.89, "elapsed_time": "2:26:30", "remaining_time": "3:31:47"}
506
+ {"current_steps": 506, "total_steps": 1235, "loss": 0.2283, "lr": 2.942325848714505e-05, "epoch": 2.048582995951417, "percentage": 40.97, "elapsed_time": "2:26:46", "remaining_time": "3:31:27"}
507
+ {"current_steps": 507, "total_steps": 1235, "loss": 0.2537, "lr": 2.9373337353698804e-05, "epoch": 2.0526315789473686, "percentage": 41.05, "elapsed_time": "2:27:04", "remaining_time": "3:31:11"}
508
+ {"current_steps": 508, "total_steps": 1235, "loss": 0.2565, "lr": 2.932334127129686e-05, "epoch": 2.0566801619433197, "percentage": 41.13, "elapsed_time": "2:27:22", "remaining_time": "3:30:54"}
509
+ {"current_steps": 509, "total_steps": 1235, "loss": 0.2455, "lr": 2.9273270639706547e-05, "epoch": 2.0607287449392713, "percentage": 41.21, "elapsed_time": "2:27:37", "remaining_time": "3:30:33"}
510
+ {"current_steps": 510, "total_steps": 1235, "loss": 0.2702, "lr": 2.922312585929131e-05, "epoch": 2.064777327935223, "percentage": 41.3, "elapsed_time": "2:27:53", "remaining_time": "3:30:14"}
511
+ {"current_steps": 511, "total_steps": 1235, "loss": 0.2516, "lr": 2.9172907331007478e-05, "epoch": 2.068825910931174, "percentage": 41.38, "elapsed_time": "2:28:09", "remaining_time": "3:29:55"}
512
+ {"current_steps": 512, "total_steps": 1235, "loss": 0.2421, "lr": 2.9122615456401053e-05, "epoch": 2.0728744939271255, "percentage": 41.46, "elapsed_time": "2:28:27", "remaining_time": "3:29:37"}
513
+ {"current_steps": 513, "total_steps": 1235, "loss": 0.248, "lr": 2.9072250637604535e-05, "epoch": 2.076923076923077, "percentage": 41.54, "elapsed_time": "2:28:42", "remaining_time": "3:29:17"}
514
+ {"current_steps": 514, "total_steps": 1235, "loss": 0.2193, "lr": 2.9021813277333667e-05, "epoch": 2.080971659919028, "percentage": 41.62, "elapsed_time": "2:28:56", "remaining_time": "3:28:54"}
515
+ {"current_steps": 515, "total_steps": 1235, "loss": 0.2457, "lr": 2.8971303778884244e-05, "epoch": 2.08502024291498, "percentage": 41.7, "elapsed_time": "2:29:11", "remaining_time": "3:28:34"}
516
+ {"current_steps": 516, "total_steps": 1235, "loss": 0.261, "lr": 2.8920722546128863e-05, "epoch": 2.0890688259109313, "percentage": 41.78, "elapsed_time": "2:29:30", "remaining_time": "3:28:19"}
517
+ {"current_steps": 517, "total_steps": 1235, "loss": 0.2744, "lr": 2.887006998351372e-05, "epoch": 2.0931174089068825, "percentage": 41.86, "elapsed_time": "2:29:51", "remaining_time": "3:28:06"}
518
+ {"current_steps": 518, "total_steps": 1235, "loss": 0.2467, "lr": 2.881934649605535e-05, "epoch": 2.097165991902834, "percentage": 41.94, "elapsed_time": "2:30:05", "remaining_time": "3:27:44"}
519
+ {"current_steps": 519, "total_steps": 1235, "loss": 0.2699, "lr": 2.8768552489337408e-05, "epoch": 2.1012145748987856, "percentage": 42.02, "elapsed_time": "2:30:23", "remaining_time": "3:27:28"}
520
+ {"current_steps": 520, "total_steps": 1235, "loss": 0.2601, "lr": 2.8717688369507425e-05, "epoch": 2.1052631578947367, "percentage": 42.11, "elapsed_time": "2:30:44", "remaining_time": "3:27:15"}
521
+ {"current_steps": 521, "total_steps": 1235, "loss": 0.2513, "lr": 2.8666754543273535e-05, "epoch": 2.1093117408906883, "percentage": 42.19, "elapsed_time": "2:31:01", "remaining_time": "3:26:57"}
522
+ {"current_steps": 522, "total_steps": 1235, "loss": 0.2424, "lr": 2.8615751417901273e-05, "epoch": 2.11336032388664, "percentage": 42.27, "elapsed_time": "2:31:18", "remaining_time": "3:26:40"}
523
+ {"current_steps": 523, "total_steps": 1235, "loss": 0.2646, "lr": 2.856467940121025e-05, "epoch": 2.117408906882591, "percentage": 42.35, "elapsed_time": "2:31:33", "remaining_time": "3:26:20"}
524
+ {"current_steps": 524, "total_steps": 1235, "loss": 0.2477, "lr": 2.8513538901570964e-05, "epoch": 2.1214574898785425, "percentage": 42.43, "elapsed_time": "2:31:52", "remaining_time": "3:26:04"}
525
+ {"current_steps": 525, "total_steps": 1235, "loss": 0.2327, "lr": 2.846233032790149e-05, "epoch": 2.125506072874494, "percentage": 42.51, "elapsed_time": "2:32:09", "remaining_time": "3:25:46"}
526
+ {"current_steps": 526, "total_steps": 1235, "loss": 0.2478, "lr": 2.84110540896642e-05, "epoch": 2.1295546558704452, "percentage": 42.59, "elapsed_time": "2:32:24", "remaining_time": "3:25:26"}
527
+ {"current_steps": 527, "total_steps": 1235, "loss": 0.2367, "lr": 2.8359710596862555e-05, "epoch": 2.133603238866397, "percentage": 42.67, "elapsed_time": "2:32:39", "remaining_time": "3:25:05"}
528
+ {"current_steps": 528, "total_steps": 1235, "loss": 0.2305, "lr": 2.8308300260037734e-05, "epoch": 2.1376518218623484, "percentage": 42.75, "elapsed_time": "2:32:56", "remaining_time": "3:24:47"}
529
+ {"current_steps": 529, "total_steps": 1235, "loss": 0.237, "lr": 2.8256823490265424e-05, "epoch": 2.1417004048582995, "percentage": 42.83, "elapsed_time": "2:33:09", "remaining_time": "3:24:24"}
530
+ {"current_steps": 530, "total_steps": 1235, "loss": 0.2454, "lr": 2.8205280699152515e-05, "epoch": 2.145748987854251, "percentage": 42.91, "elapsed_time": "2:33:23", "remaining_time": "3:24:02"}
531
+ {"current_steps": 531, "total_steps": 1235, "loss": 0.2479, "lr": 2.8153672298833777e-05, "epoch": 2.1497975708502026, "percentage": 43.0, "elapsed_time": "2:33:40", "remaining_time": "3:23:43"}
532
+ {"current_steps": 532, "total_steps": 1235, "loss": 0.2525, "lr": 2.8101998701968615e-05, "epoch": 2.1538461538461537, "percentage": 43.08, "elapsed_time": "2:33:56", "remaining_time": "3:23:24"}
533
+ {"current_steps": 533, "total_steps": 1235, "loss": 0.2552, "lr": 2.805026032173773e-05, "epoch": 2.1578947368421053, "percentage": 43.16, "elapsed_time": "2:34:11", "remaining_time": "3:23:04"}
534
+ {"current_steps": 534, "total_steps": 1235, "loss": 0.2624, "lr": 2.7998457571839832e-05, "epoch": 2.161943319838057, "percentage": 43.24, "elapsed_time": "2:34:30", "remaining_time": "3:22:49"}
535
+ {"current_steps": 535, "total_steps": 1235, "loss": 0.2687, "lr": 2.7946590866488322e-05, "epoch": 2.165991902834008, "percentage": 43.32, "elapsed_time": "2:34:48", "remaining_time": "3:22:33"}
536
+ {"current_steps": 536, "total_steps": 1235, "loss": 0.2524, "lr": 2.7894660620408e-05, "epoch": 2.1700404858299596, "percentage": 43.4, "elapsed_time": "2:35:06", "remaining_time": "3:22:16"}
537
+ {"current_steps": 537, "total_steps": 1235, "loss": 0.273, "lr": 2.784266724883173e-05, "epoch": 2.174089068825911, "percentage": 43.48, "elapsed_time": "2:35:24", "remaining_time": "3:22:00"}
538
+ {"current_steps": 538, "total_steps": 1235, "loss": 0.2475, "lr": 2.7790611167497128e-05, "epoch": 2.1781376518218623, "percentage": 43.56, "elapsed_time": "2:35:38", "remaining_time": "3:21:38"}
539
+ {"current_steps": 539, "total_steps": 1235, "loss": 0.2568, "lr": 2.7738492792643224e-05, "epoch": 2.182186234817814, "percentage": 43.64, "elapsed_time": "2:35:57", "remaining_time": "3:21:23"}
540
+ {"current_steps": 540, "total_steps": 1235, "loss": 0.251, "lr": 2.768631254100716e-05, "epoch": 2.1862348178137654, "percentage": 43.72, "elapsed_time": "2:36:16", "remaining_time": "3:21:07"}
541
+ {"current_steps": 541, "total_steps": 1235, "loss": 0.251, "lr": 2.7634070829820836e-05, "epoch": 2.1902834008097165, "percentage": 43.81, "elapsed_time": "2:36:36", "remaining_time": "3:20:53"}
542
+ {"current_steps": 542, "total_steps": 1235, "loss": 0.2468, "lr": 2.7581768076807592e-05, "epoch": 2.194331983805668, "percentage": 43.89, "elapsed_time": "2:36:53", "remaining_time": "3:20:35"}
543
+ {"current_steps": 543, "total_steps": 1235, "loss": 0.2476, "lr": 2.7529404700178832e-05, "epoch": 2.1983805668016196, "percentage": 43.97, "elapsed_time": "2:37:10", "remaining_time": "3:20:17"}
544
+ {"current_steps": 544, "total_steps": 1235, "loss": 0.2412, "lr": 2.7476981118630735e-05, "epoch": 2.2024291497975708, "percentage": 44.05, "elapsed_time": "2:37:27", "remaining_time": "3:20:00"}
545
+ {"current_steps": 545, "total_steps": 1235, "loss": 0.2619, "lr": 2.742449775134085e-05, "epoch": 2.2064777327935223, "percentage": 44.13, "elapsed_time": "2:37:43", "remaining_time": "3:19:41"}
546
+ {"current_steps": 546, "total_steps": 1235, "loss": 0.2425, "lr": 2.7371955017964788e-05, "epoch": 2.2105263157894735, "percentage": 44.21, "elapsed_time": "2:37:58", "remaining_time": "3:19:20"}
547
+ {"current_steps": 547, "total_steps": 1235, "loss": 0.2541, "lr": 2.7319353338632845e-05, "epoch": 2.214574898785425, "percentage": 44.29, "elapsed_time": "2:38:12", "remaining_time": "3:18:59"}
548
+ {"current_steps": 548, "total_steps": 1235, "loss": 0.2404, "lr": 2.7266693133946645e-05, "epoch": 2.2186234817813766, "percentage": 44.37, "elapsed_time": "2:38:32", "remaining_time": "3:18:45"}
549
+ {"current_steps": 549, "total_steps": 1235, "loss": 0.2576, "lr": 2.7213974824975785e-05, "epoch": 2.2226720647773277, "percentage": 44.45, "elapsed_time": "2:38:48", "remaining_time": "3:18:25"}
550
+ {"current_steps": 550, "total_steps": 1235, "loss": 0.2524, "lr": 2.7161198833254464e-05, "epoch": 2.2267206477732793, "percentage": 44.53, "elapsed_time": "2:39:03", "remaining_time": "3:18:06"}
551
+ {"current_steps": 551, "total_steps": 1235, "loss": 0.2328, "lr": 2.7108365580778095e-05, "epoch": 2.230769230769231, "percentage": 44.62, "elapsed_time": "2:39:20", "remaining_time": "3:17:47"}
552
+ {"current_steps": 552, "total_steps": 1235, "loss": 0.2558, "lr": 2.705547548999996e-05, "epoch": 2.234817813765182, "percentage": 44.7, "elapsed_time": "2:39:39", "remaining_time": "3:17:32"}
553
+ {"current_steps": 553, "total_steps": 1235, "loss": 0.2547, "lr": 2.7002528983827817e-05, "epoch": 2.2388663967611335, "percentage": 44.78, "elapsed_time": "2:39:57", "remaining_time": "3:17:15"}
554
+ {"current_steps": 554, "total_steps": 1235, "loss": 0.2543, "lr": 2.6949526485620517e-05, "epoch": 2.242914979757085, "percentage": 44.86, "elapsed_time": "2:40:12", "remaining_time": "3:16:56"}
555
+ {"current_steps": 555, "total_steps": 1235, "loss": 0.2677, "lr": 2.6896468419184623e-05, "epoch": 2.246963562753036, "percentage": 44.94, "elapsed_time": "2:40:30", "remaining_time": "3:16:39"}
556
+ {"current_steps": 556, "total_steps": 1235, "loss": 0.2716, "lr": 2.6843355208771024e-05, "epoch": 2.251012145748988, "percentage": 45.02, "elapsed_time": "2:40:48", "remaining_time": "3:16:23"}
557
+ {"current_steps": 557, "total_steps": 1235, "loss": 0.253, "lr": 2.6790187279071536e-05, "epoch": 2.2550607287449393, "percentage": 45.1, "elapsed_time": "2:41:06", "remaining_time": "3:16:06"}
558
+ {"current_steps": 558, "total_steps": 1235, "loss": 0.2674, "lr": 2.67369650552155e-05, "epoch": 2.2591093117408905, "percentage": 45.18, "elapsed_time": "2:41:25", "remaining_time": "3:15:50"}
559
+ {"current_steps": 559, "total_steps": 1235, "loss": 0.2472, "lr": 2.6683688962766407e-05, "epoch": 2.263157894736842, "percentage": 45.26, "elapsed_time": "2:41:40", "remaining_time": "3:15:31"}
560
+ {"current_steps": 560, "total_steps": 1235, "loss": 0.266, "lr": 2.6630359427718468e-05, "epoch": 2.2672064777327936, "percentage": 45.34, "elapsed_time": "2:41:58", "remaining_time": "3:15:13"}
561
+ {"current_steps": 561, "total_steps": 1235, "loss": 0.2549, "lr": 2.6576976876493225e-05, "epoch": 2.2712550607287447, "percentage": 45.43, "elapsed_time": "2:42:17", "remaining_time": "3:14:58"}
562
+ {"current_steps": 562, "total_steps": 1235, "loss": 0.2413, "lr": 2.652354173593614e-05, "epoch": 2.2753036437246963, "percentage": 45.51, "elapsed_time": "2:42:33", "remaining_time": "3:14:39"}
563
+ {"current_steps": 563, "total_steps": 1235, "loss": 0.2586, "lr": 2.647005443331317e-05, "epoch": 2.279352226720648, "percentage": 45.59, "elapsed_time": "2:42:49", "remaining_time": "3:14:20"}
564
+ {"current_steps": 564, "total_steps": 1235, "loss": 0.2415, "lr": 2.6416515396307354e-05, "epoch": 2.283400809716599, "percentage": 45.67, "elapsed_time": "2:42:59", "remaining_time": "3:13:54"}
565
+ {"current_steps": 565, "total_steps": 1235, "loss": 0.2583, "lr": 2.636292505301542e-05, "epoch": 2.2874493927125505, "percentage": 45.75, "elapsed_time": "2:43:20", "remaining_time": "3:13:42"}
566
+ {"current_steps": 566, "total_steps": 1235, "loss": 0.2458, "lr": 2.630928383194431e-05, "epoch": 2.291497975708502, "percentage": 45.83, "elapsed_time": "2:43:36", "remaining_time": "3:13:22"}
567
+ {"current_steps": 567, "total_steps": 1235, "loss": 0.247, "lr": 2.625559216200781e-05, "epoch": 2.2955465587044532, "percentage": 45.91, "elapsed_time": "2:43:51", "remaining_time": "3:13:02"}
568
+ {"current_steps": 568, "total_steps": 1235, "loss": 0.2541, "lr": 2.620185047252308e-05, "epoch": 2.299595141700405, "percentage": 45.99, "elapsed_time": "2:44:09", "remaining_time": "3:12:45"}
569
+ {"current_steps": 569, "total_steps": 1235, "loss": 0.2595, "lr": 2.614805919320723e-05, "epoch": 2.3036437246963564, "percentage": 46.07, "elapsed_time": "2:44:27", "remaining_time": "3:12:30"}
570
+ {"current_steps": 570, "total_steps": 1235, "loss": 0.2606, "lr": 2.6094218754173895e-05, "epoch": 2.3076923076923075, "percentage": 46.15, "elapsed_time": "2:44:44", "remaining_time": "3:12:12"}
571
+ {"current_steps": 571, "total_steps": 1235, "loss": 0.2539, "lr": 2.60403295859298e-05, "epoch": 2.311740890688259, "percentage": 46.23, "elapsed_time": "2:45:00", "remaining_time": "3:11:52"}
572
+ {"current_steps": 572, "total_steps": 1235, "loss": 0.2744, "lr": 2.5986392119371297e-05, "epoch": 2.3157894736842106, "percentage": 46.32, "elapsed_time": "2:45:16", "remaining_time": "3:11:33"}
573
+ {"current_steps": 573, "total_steps": 1235, "loss": 0.2598, "lr": 2.5932406785780928e-05, "epoch": 2.3198380566801617, "percentage": 46.4, "elapsed_time": "2:45:33", "remaining_time": "3:11:16"}
574
+ {"current_steps": 574, "total_steps": 1235, "loss": 0.2641, "lr": 2.5878374016823987e-05, "epoch": 2.3238866396761133, "percentage": 46.48, "elapsed_time": "2:45:49", "remaining_time": "3:10:57"}
575
+ {"current_steps": 575, "total_steps": 1235, "loss": 0.2566, "lr": 2.5824294244545045e-05, "epoch": 2.327935222672065, "percentage": 46.56, "elapsed_time": "2:46:07", "remaining_time": "3:10:41"}
576
+ {"current_steps": 576, "total_steps": 1235, "loss": 0.2617, "lr": 2.577016790136453e-05, "epoch": 2.331983805668016, "percentage": 46.64, "elapsed_time": "2:46:23", "remaining_time": "3:10:21"}
577
+ {"current_steps": 577, "total_steps": 1235, "loss": 0.2438, "lr": 2.5715995420075225e-05, "epoch": 2.3360323886639676, "percentage": 46.72, "elapsed_time": "2:46:40", "remaining_time": "3:10:04"}
578
+ {"current_steps": 578, "total_steps": 1235, "loss": 0.2682, "lr": 2.5661777233838864e-05, "epoch": 2.340080971659919, "percentage": 46.8, "elapsed_time": "2:46:54", "remaining_time": "3:09:43"}
579
+ {"current_steps": 579, "total_steps": 1235, "loss": 0.2642, "lr": 2.5607513776182616e-05, "epoch": 2.3441295546558703, "percentage": 46.88, "elapsed_time": "2:47:10", "remaining_time": "3:09:24"}
580
+ {"current_steps": 580, "total_steps": 1235, "loss": 0.2833, "lr": 2.5553205480995633e-05, "epoch": 2.348178137651822, "percentage": 46.96, "elapsed_time": "2:47:29", "remaining_time": "3:09:08"}
581
+ {"current_steps": 581, "total_steps": 1235, "loss": 0.264, "lr": 2.5498852782525604e-05, "epoch": 2.3522267206477734, "percentage": 47.04, "elapsed_time": "2:47:44", "remaining_time": "3:08:49"}
582
+ {"current_steps": 582, "total_steps": 1235, "loss": 0.264, "lr": 2.5444456115375252e-05, "epoch": 2.3562753036437245, "percentage": 47.13, "elapsed_time": "2:48:02", "remaining_time": "3:08:32"}
583
+ {"current_steps": 583, "total_steps": 1235, "loss": 0.2391, "lr": 2.539001591449889e-05, "epoch": 2.360323886639676, "percentage": 47.21, "elapsed_time": "2:48:16", "remaining_time": "3:08:11"}
584
+ {"current_steps": 584, "total_steps": 1235, "loss": 0.2537, "lr": 2.53355326151989e-05, "epoch": 2.3643724696356276, "percentage": 47.29, "elapsed_time": "2:48:35", "remaining_time": "3:07:56"}
585
+ {"current_steps": 585, "total_steps": 1235, "loss": 0.235, "lr": 2.5281006653122288e-05, "epoch": 2.3684210526315788, "percentage": 47.37, "elapsed_time": "2:48:50", "remaining_time": "3:07:36"}
586
+ {"current_steps": 586, "total_steps": 1235, "loss": 0.2405, "lr": 2.5226438464257217e-05, "epoch": 2.3724696356275303, "percentage": 47.45, "elapsed_time": "2:49:09", "remaining_time": "3:07:20"}
587
+ {"current_steps": 587, "total_steps": 1235, "loss": 0.2851, "lr": 2.5171828484929447e-05, "epoch": 2.376518218623482, "percentage": 47.53, "elapsed_time": "2:49:20", "remaining_time": "3:06:56"}
588
+ {"current_steps": 588, "total_steps": 1235, "loss": 0.2605, "lr": 2.5117177151798934e-05, "epoch": 2.380566801619433, "percentage": 47.61, "elapsed_time": "2:49:38", "remaining_time": "3:06:40"}
589
+ {"current_steps": 589, "total_steps": 1235, "loss": 0.2466, "lr": 2.506248490185627e-05, "epoch": 2.3846153846153846, "percentage": 47.69, "elapsed_time": "2:49:54", "remaining_time": "3:06:20"}
590
+ {"current_steps": 590, "total_steps": 1235, "loss": 0.2465, "lr": 2.500775217241923e-05, "epoch": 2.388663967611336, "percentage": 47.77, "elapsed_time": "2:50:09", "remaining_time": "3:06:01"}
591
+ {"current_steps": 591, "total_steps": 1235, "loss": 0.2484, "lr": 2.4952979401129266e-05, "epoch": 2.3927125506072873, "percentage": 47.85, "elapsed_time": "2:50:25", "remaining_time": "3:05:42"}
592
+ {"current_steps": 592, "total_steps": 1235, "loss": 0.2833, "lr": 2.4898167025948e-05, "epoch": 2.396761133603239, "percentage": 47.94, "elapsed_time": "2:50:43", "remaining_time": "3:05:26"}
593
+ {"current_steps": 593, "total_steps": 1235, "loss": 0.2361, "lr": 2.4843315485153703e-05, "epoch": 2.4008097165991904, "percentage": 48.02, "elapsed_time": "2:51:05", "remaining_time": "3:05:14"}
594
+ {"current_steps": 594, "total_steps": 1235, "loss": 0.26, "lr": 2.4788425217337856e-05, "epoch": 2.4048582995951415, "percentage": 48.1, "elapsed_time": "2:51:22", "remaining_time": "3:04:56"}
595
+ {"current_steps": 595, "total_steps": 1235, "loss": 0.2331, "lr": 2.4733496661401572e-05, "epoch": 2.408906882591093, "percentage": 48.18, "elapsed_time": "2:51:40", "remaining_time": "3:04:39"}
596
+ {"current_steps": 596, "total_steps": 1235, "loss": 0.2635, "lr": 2.4678530256552114e-05, "epoch": 2.4129554655870447, "percentage": 48.26, "elapsed_time": "2:51:57", "remaining_time": "3:04:22"}
597
+ {"current_steps": 597, "total_steps": 1235, "loss": 0.2667, "lr": 2.46235264422994e-05, "epoch": 2.417004048582996, "percentage": 48.34, "elapsed_time": "2:52:15", "remaining_time": "3:04:05"}
598
+ {"current_steps": 598, "total_steps": 1235, "loss": 0.265, "lr": 2.4568485658452452e-05, "epoch": 2.4210526315789473, "percentage": 48.42, "elapsed_time": "2:52:31", "remaining_time": "3:03:46"}
599
+ {"current_steps": 599, "total_steps": 1235, "loss": 0.2837, "lr": 2.451340834511592e-05, "epoch": 2.425101214574899, "percentage": 48.5, "elapsed_time": "2:52:49", "remaining_time": "3:03:30"}
600
+ {"current_steps": 600, "total_steps": 1235, "loss": 0.2616, "lr": 2.4458294942686528e-05, "epoch": 2.42914979757085, "percentage": 48.58, "elapsed_time": "2:53:10", "remaining_time": "3:03:16"}
601
+ {"current_steps": 601, "total_steps": 1235, "loss": 0.266, "lr": 2.440314589184958e-05, "epoch": 2.4331983805668016, "percentage": 48.66, "elapsed_time": "2:53:29", "remaining_time": "3:03:01"}
602
+ {"current_steps": 602, "total_steps": 1235, "loss": 0.2564, "lr": 2.434796163357541e-05, "epoch": 2.437246963562753, "percentage": 48.74, "elapsed_time": "2:53:47", "remaining_time": "3:02:43"}
603
+ {"current_steps": 603, "total_steps": 1235, "loss": 0.2525, "lr": 2.429274260911588e-05, "epoch": 2.4412955465587043, "percentage": 48.83, "elapsed_time": "2:54:00", "remaining_time": "3:02:22"}
604
+ {"current_steps": 604, "total_steps": 1235, "loss": 0.2523, "lr": 2.423748926000084e-05, "epoch": 2.445344129554656, "percentage": 48.91, "elapsed_time": "2:54:19", "remaining_time": "3:02:07"}
605
+ {"current_steps": 605, "total_steps": 1235, "loss": 0.2572, "lr": 2.418220202803459e-05, "epoch": 2.4493927125506074, "percentage": 48.99, "elapsed_time": "2:54:36", "remaining_time": "3:01:49"}
606
+ {"current_steps": 606, "total_steps": 1235, "loss": 0.2579, "lr": 2.412688135529237e-05, "epoch": 2.4534412955465585, "percentage": 49.07, "elapsed_time": "2:54:55", "remaining_time": "3:01:34"}
607
+ {"current_steps": 607, "total_steps": 1235, "loss": 0.2787, "lr": 2.4071527684116807e-05, "epoch": 2.45748987854251, "percentage": 49.15, "elapsed_time": "2:55:16", "remaining_time": "3:01:20"}
608
+ {"current_steps": 608, "total_steps": 1235, "loss": 0.2755, "lr": 2.4016141457114372e-05, "epoch": 2.4615384615384617, "percentage": 49.23, "elapsed_time": "2:55:32", "remaining_time": "3:01:02"}
609
+ {"current_steps": 609, "total_steps": 1235, "loss": 0.2542, "lr": 2.396072311715187e-05, "epoch": 2.465587044534413, "percentage": 49.31, "elapsed_time": "2:55:47", "remaining_time": "3:00:42"}
610
+ {"current_steps": 610, "total_steps": 1235, "loss": 0.2485, "lr": 2.3905273107352863e-05, "epoch": 2.4696356275303644, "percentage": 49.39, "elapsed_time": "2:56:05", "remaining_time": "3:00:24"}
611
+ {"current_steps": 611, "total_steps": 1235, "loss": 0.2397, "lr": 2.3849791871094157e-05, "epoch": 2.473684210526316, "percentage": 49.47, "elapsed_time": "2:56:20", "remaining_time": "3:00:05"}
612
+ {"current_steps": 612, "total_steps": 1235, "loss": 0.2577, "lr": 2.379427985200223e-05, "epoch": 2.477732793522267, "percentage": 49.55, "elapsed_time": "2:56:40", "remaining_time": "2:59:50"}
613
+ {"current_steps": 613, "total_steps": 1235, "loss": 0.2568, "lr": 2.373873749394972e-05, "epoch": 2.4817813765182186, "percentage": 49.64, "elapsed_time": "2:56:57", "remaining_time": "2:59:33"}
614
+ {"current_steps": 614, "total_steps": 1235, "loss": 0.2518, "lr": 2.3683165241051836e-05, "epoch": 2.48582995951417, "percentage": 49.72, "elapsed_time": "2:57:11", "remaining_time": "2:59:12"}
615
+ {"current_steps": 615, "total_steps": 1235, "loss": 0.2545, "lr": 2.3627563537662823e-05, "epoch": 2.4898785425101213, "percentage": 49.8, "elapsed_time": "2:57:27", "remaining_time": "2:58:54"}
616
+ {"current_steps": 616, "total_steps": 1235, "loss": 0.2713, "lr": 2.3571932828372433e-05, "epoch": 2.493927125506073, "percentage": 49.88, "elapsed_time": "2:57:45", "remaining_time": "2:58:37"}
617
+ {"current_steps": 617, "total_steps": 1235, "loss": 0.2587, "lr": 2.351627355800233e-05, "epoch": 2.4979757085020244, "percentage": 49.96, "elapsed_time": "2:58:05", "remaining_time": "2:58:22"}
618
+ {"current_steps": 618, "total_steps": 1235, "loss": 0.2645, "lr": 2.346058617160256e-05, "epoch": 2.5020242914979756, "percentage": 50.04, "elapsed_time": "2:58:24", "remaining_time": "2:58:07"}
619
+ {"current_steps": 619, "total_steps": 1235, "loss": 0.2696, "lr": 2.3404871114447976e-05, "epoch": 2.506072874493927, "percentage": 50.12, "elapsed_time": "2:58:43", "remaining_time": "2:57:51"}
620
+ {"current_steps": 620, "total_steps": 1235, "loss": 0.2352, "lr": 2.334912883203469e-05, "epoch": 2.5101214574898787, "percentage": 50.2, "elapsed_time": "2:59:03", "remaining_time": "2:57:36"}
621
+ {"current_steps": 621, "total_steps": 1235, "loss": 0.252, "lr": 2.3293359770076505e-05, "epoch": 2.51417004048583, "percentage": 50.28, "elapsed_time": "2:59:24", "remaining_time": "2:57:22"}
622
+ {"current_steps": 622, "total_steps": 1235, "loss": 0.2373, "lr": 2.323756437450136e-05, "epoch": 2.5182186234817814, "percentage": 50.36, "elapsed_time": "2:59:40", "remaining_time": "2:57:04"}
623
+ {"current_steps": 623, "total_steps": 1235, "loss": 0.2432, "lr": 2.3181743091447754e-05, "epoch": 2.522267206477733, "percentage": 50.45, "elapsed_time": "2:59:53", "remaining_time": "2:56:42"}
624
+ {"current_steps": 624, "total_steps": 1235, "loss": 0.2596, "lr": 2.3125896367261164e-05, "epoch": 2.526315789473684, "percentage": 50.53, "elapsed_time": "3:00:12", "remaining_time": "2:56:26"}
625
+ {"current_steps": 625, "total_steps": 1235, "loss": 0.2626, "lr": 2.307002464849052e-05, "epoch": 2.5303643724696356, "percentage": 50.61, "elapsed_time": "3:00:30", "remaining_time": "2:56:10"}
626
+ {"current_steps": 626, "total_steps": 1235, "loss": 0.2555, "lr": 2.30141283818846e-05, "epoch": 2.534412955465587, "percentage": 50.69, "elapsed_time": "3:00:46", "remaining_time": "2:55:52"}
627
+ {"current_steps": 627, "total_steps": 1235, "loss": 0.2431, "lr": 2.2958208014388462e-05, "epoch": 2.5384615384615383, "percentage": 50.77, "elapsed_time": "3:01:03", "remaining_time": "2:55:34"}
628
+ {"current_steps": 628, "total_steps": 1235, "loss": 0.2408, "lr": 2.2902263993139857e-05, "epoch": 2.54251012145749, "percentage": 50.85, "elapsed_time": "3:01:19", "remaining_time": "2:55:15"}
629
+ {"current_steps": 629, "total_steps": 1235, "loss": 0.255, "lr": 2.2846296765465708e-05, "epoch": 2.5465587044534415, "percentage": 50.93, "elapsed_time": "3:01:36", "remaining_time": "2:54:57"}
630
+ {"current_steps": 630, "total_steps": 1235, "loss": 0.2601, "lr": 2.2790306778878465e-05, "epoch": 2.5506072874493926, "percentage": 51.01, "elapsed_time": "3:01:55", "remaining_time": "2:54:42"}
631
+ {"current_steps": 631, "total_steps": 1235, "loss": 0.2452, "lr": 2.273429448107257e-05, "epoch": 2.554655870445344, "percentage": 51.09, "elapsed_time": "3:02:13", "remaining_time": "2:54:25"}
632
+ {"current_steps": 632, "total_steps": 1235, "loss": 0.2557, "lr": 2.2678260319920868e-05, "epoch": 2.5587044534412957, "percentage": 51.17, "elapsed_time": "3:02:27", "remaining_time": "2:54:05"}
633
+ {"current_steps": 633, "total_steps": 1235, "loss": 0.2566, "lr": 2.262220474347102e-05, "epoch": 2.562753036437247, "percentage": 51.26, "elapsed_time": "3:02:45", "remaining_time": "2:53:48"}
634
+ {"current_steps": 634, "total_steps": 1235, "loss": 0.2508, "lr": 2.2566128199941918e-05, "epoch": 2.5668016194331984, "percentage": 51.34, "elapsed_time": "3:03:00", "remaining_time": "2:53:29"}
635
+ {"current_steps": 635, "total_steps": 1235, "loss": 0.2567, "lr": 2.2510031137720104e-05, "epoch": 2.57085020242915, "percentage": 51.42, "elapsed_time": "3:03:17", "remaining_time": "2:53:11"}
636
+ {"current_steps": 636, "total_steps": 1235, "loss": 0.263, "lr": 2.2453914005356206e-05, "epoch": 2.574898785425101, "percentage": 51.5, "elapsed_time": "3:03:32", "remaining_time": "2:52:51"}
637
+ {"current_steps": 637, "total_steps": 1235, "loss": 0.2688, "lr": 2.2397777251561302e-05, "epoch": 2.5789473684210527, "percentage": 51.58, "elapsed_time": "3:03:50", "remaining_time": "2:52:35"}
638
+ {"current_steps": 638, "total_steps": 1235, "loss": 0.2692, "lr": 2.2341621325203393e-05, "epoch": 2.582995951417004, "percentage": 51.66, "elapsed_time": "3:04:08", "remaining_time": "2:52:18"}
639
+ {"current_steps": 639, "total_steps": 1235, "loss": 0.2721, "lr": 2.2285446675303764e-05, "epoch": 2.5870445344129553, "percentage": 51.74, "elapsed_time": "3:04:24", "remaining_time": "2:51:59"}
640
+ {"current_steps": 640, "total_steps": 1235, "loss": 0.2514, "lr": 2.2229253751033423e-05, "epoch": 2.591093117408907, "percentage": 51.82, "elapsed_time": "3:04:44", "remaining_time": "2:51:45"}
641
+ {"current_steps": 641, "total_steps": 1235, "loss": 0.277, "lr": 2.2173043001709492e-05, "epoch": 2.5951417004048585, "percentage": 51.9, "elapsed_time": "3:04:59", "remaining_time": "2:51:25"}
642
+ {"current_steps": 642, "total_steps": 1235, "loss": 0.2704, "lr": 2.2116814876791627e-05, "epoch": 2.5991902834008096, "percentage": 51.98, "elapsed_time": "3:05:18", "remaining_time": "2:51:10"}
643
+ {"current_steps": 643, "total_steps": 1235, "loss": 0.2492, "lr": 2.2060569825878413e-05, "epoch": 2.603238866396761, "percentage": 52.06, "elapsed_time": "3:05:30", "remaining_time": "2:50:48"}
644
+ {"current_steps": 644, "total_steps": 1235, "loss": 0.2521, "lr": 2.2004308298703777e-05, "epoch": 2.6072874493927127, "percentage": 52.15, "elapsed_time": "3:05:51", "remaining_time": "2:50:33"}
645
+ {"current_steps": 645, "total_steps": 1235, "loss": 0.2743, "lr": 2.1948030745133396e-05, "epoch": 2.611336032388664, "percentage": 52.23, "elapsed_time": "3:06:10", "remaining_time": "2:50:17"}
646
+ {"current_steps": 646, "total_steps": 1235, "loss": 0.2661, "lr": 2.1891737615161083e-05, "epoch": 2.6153846153846154, "percentage": 52.31, "elapsed_time": "3:06:26", "remaining_time": "2:49:59"}
647
+ {"current_steps": 647, "total_steps": 1235, "loss": 0.2631, "lr": 2.1835429358905218e-05, "epoch": 2.619433198380567, "percentage": 52.39, "elapsed_time": "3:06:44", "remaining_time": "2:49:42"}
648
+ {"current_steps": 648, "total_steps": 1235, "loss": 0.2602, "lr": 2.17791064266051e-05, "epoch": 2.623481781376518, "percentage": 52.47, "elapsed_time": "3:06:59", "remaining_time": "2:49:23"}
649
+ {"current_steps": 649, "total_steps": 1235, "loss": 0.2236, "lr": 2.172276926861741e-05, "epoch": 2.6275303643724697, "percentage": 52.55, "elapsed_time": "3:07:17", "remaining_time": "2:49:06"}
650
+ {"current_steps": 650, "total_steps": 1235, "loss": 0.2533, "lr": 2.166641833541255e-05, "epoch": 2.6315789473684212, "percentage": 52.63, "elapsed_time": "3:07:37", "remaining_time": "2:48:51"}
651
+ {"current_steps": 651, "total_steps": 1235, "loss": 0.2411, "lr": 2.161005407757109e-05, "epoch": 2.6356275303643724, "percentage": 52.71, "elapsed_time": "3:07:56", "remaining_time": "2:48:35"}
652
+ {"current_steps": 652, "total_steps": 1235, "loss": 0.2825, "lr": 2.155367694578013e-05, "epoch": 2.639676113360324, "percentage": 52.79, "elapsed_time": "3:08:16", "remaining_time": "2:48:21"}
653
+ {"current_steps": 653, "total_steps": 1235, "loss": 0.2777, "lr": 2.1497287390829712e-05, "epoch": 2.6437246963562755, "percentage": 52.87, "elapsed_time": "3:08:34", "remaining_time": "2:48:04"}
654
+ {"current_steps": 654, "total_steps": 1235, "loss": 0.247, "lr": 2.1440885863609208e-05, "epoch": 2.6477732793522266, "percentage": 52.96, "elapsed_time": "3:08:51", "remaining_time": "2:47:46"}
655
+ {"current_steps": 655, "total_steps": 1235, "loss": 0.255, "lr": 2.1384472815103737e-05, "epoch": 2.651821862348178, "percentage": 53.04, "elapsed_time": "3:09:07", "remaining_time": "2:47:28"}
656
+ {"current_steps": 656, "total_steps": 1235, "loss": 0.2489, "lr": 2.1328048696390534e-05, "epoch": 2.6558704453441297, "percentage": 53.12, "elapsed_time": "3:09:22", "remaining_time": "2:47:08"}
657
+ {"current_steps": 657, "total_steps": 1235, "loss": 0.2377, "lr": 2.1271613958635342e-05, "epoch": 2.659919028340081, "percentage": 53.2, "elapsed_time": "3:09:38", "remaining_time": "2:46:49"}
658
+ {"current_steps": 658, "total_steps": 1235, "loss": 0.2613, "lr": 2.1215169053088825e-05, "epoch": 2.6639676113360324, "percentage": 53.28, "elapsed_time": "3:09:54", "remaining_time": "2:46:31"}
659
+ {"current_steps": 659, "total_steps": 1235, "loss": 0.2453, "lr": 2.1158714431082937e-05, "epoch": 2.668016194331984, "percentage": 53.36, "elapsed_time": "3:10:11", "remaining_time": "2:46:14"}
660
+ {"current_steps": 660, "total_steps": 1235, "loss": 0.2414, "lr": 2.110225054402733e-05, "epoch": 2.672064777327935, "percentage": 53.44, "elapsed_time": "3:10:22", "remaining_time": "2:45:51"}
661
+ {"current_steps": 661, "total_steps": 1235, "loss": 0.2445, "lr": 2.1045777843405747e-05, "epoch": 2.6761133603238867, "percentage": 53.52, "elapsed_time": "3:10:38", "remaining_time": "2:45:32"}
662
+ {"current_steps": 662, "total_steps": 1235, "loss": 0.2423, "lr": 2.09892967807724e-05, "epoch": 2.6801619433198383, "percentage": 53.6, "elapsed_time": "3:10:54", "remaining_time": "2:45:14"}
663
+ {"current_steps": 663, "total_steps": 1235, "loss": 0.2671, "lr": 2.093280780774835e-05, "epoch": 2.6842105263157894, "percentage": 53.68, "elapsed_time": "3:11:11", "remaining_time": "2:44:56"}
664
+ {"current_steps": 664, "total_steps": 1235, "loss": 0.2489, "lr": 2.087631137601793e-05, "epoch": 2.688259109311741, "percentage": 53.77, "elapsed_time": "3:11:28", "remaining_time": "2:44:39"}
665
+ {"current_steps": 665, "total_steps": 1235, "loss": 0.2557, "lr": 2.0819807937325104e-05, "epoch": 2.6923076923076925, "percentage": 53.85, "elapsed_time": "3:11:46", "remaining_time": "2:44:22"}
666
+ {"current_steps": 666, "total_steps": 1235, "loss": 0.2533, "lr": 2.0763297943469847e-05, "epoch": 2.6963562753036436, "percentage": 53.93, "elapsed_time": "3:12:03", "remaining_time": "2:44:05"}
667
+ {"current_steps": 667, "total_steps": 1235, "loss": 0.2729, "lr": 2.070678184630458e-05, "epoch": 2.700404858299595, "percentage": 54.01, "elapsed_time": "3:12:22", "remaining_time": "2:43:49"}
668
+ {"current_steps": 668, "total_steps": 1235, "loss": 0.2634, "lr": 2.06502600977305e-05, "epoch": 2.7044534412955468, "percentage": 54.09, "elapsed_time": "3:12:37", "remaining_time": "2:43:30"}
669
+ {"current_steps": 669, "total_steps": 1235, "loss": 0.2432, "lr": 2.0593733149694008e-05, "epoch": 2.708502024291498, "percentage": 54.17, "elapsed_time": "3:12:54", "remaining_time": "2:43:12"}
670
+ {"current_steps": 670, "total_steps": 1235, "loss": 0.2476, "lr": 2.0537201454183074e-05, "epoch": 2.7125506072874495, "percentage": 54.25, "elapsed_time": "3:13:11", "remaining_time": "2:42:55"}
671
+ {"current_steps": 671, "total_steps": 1235, "loss": 0.2893, "lr": 2.0480665463223626e-05, "epoch": 2.716599190283401, "percentage": 54.33, "elapsed_time": "3:13:25", "remaining_time": "2:42:34"}
672
+ {"current_steps": 672, "total_steps": 1235, "loss": 0.2442, "lr": 2.042412562887594e-05, "epoch": 2.720647773279352, "percentage": 54.41, "elapsed_time": "3:13:41", "remaining_time": "2:42:16"}
673
+ {"current_steps": 673, "total_steps": 1235, "loss": 0.2573, "lr": 2.0367582403231033e-05, "epoch": 2.7246963562753037, "percentage": 54.49, "elapsed_time": "3:13:58", "remaining_time": "2:41:59"}
674
+ {"current_steps": 674, "total_steps": 1235, "loss": 0.2483, "lr": 2.0311036238407023e-05, "epoch": 2.7287449392712553, "percentage": 54.57, "elapsed_time": "3:14:16", "remaining_time": "2:41:42"}
675
+ {"current_steps": 675, "total_steps": 1235, "loss": 0.2503, "lr": 2.0254487586545534e-05, "epoch": 2.7327935222672064, "percentage": 54.66, "elapsed_time": "3:14:34", "remaining_time": "2:41:25"}
676
+ {"current_steps": 676, "total_steps": 1235, "loss": 0.2413, "lr": 2.0197936899808088e-05, "epoch": 2.736842105263158, "percentage": 54.74, "elapsed_time": "3:14:54", "remaining_time": "2:41:10"}
677
+ {"current_steps": 677, "total_steps": 1235, "loss": 0.2443, "lr": 2.0141384630372466e-05, "epoch": 2.7408906882591095, "percentage": 54.82, "elapsed_time": "3:15:11", "remaining_time": "2:40:52"}
678
+ {"current_steps": 678, "total_steps": 1235, "loss": 0.2344, "lr": 2.0084831230429106e-05, "epoch": 2.7449392712550607, "percentage": 54.9, "elapsed_time": "3:15:24", "remaining_time": "2:40:31"}
679
+ {"current_steps": 679, "total_steps": 1235, "loss": 0.2337, "lr": 2.0028277152177492e-05, "epoch": 2.748987854251012, "percentage": 54.98, "elapsed_time": "3:15:39", "remaining_time": "2:40:12"}
680
+ {"current_steps": 680, "total_steps": 1235, "loss": 0.2541, "lr": 1.9971722847822518e-05, "epoch": 2.753036437246964, "percentage": 55.06, "elapsed_time": "3:15:55", "remaining_time": "2:39:54"}
681
+ {"current_steps": 681, "total_steps": 1235, "loss": 0.249, "lr": 1.99151687695709e-05, "epoch": 2.757085020242915, "percentage": 55.14, "elapsed_time": "3:16:14", "remaining_time": "2:39:38"}
682
+ {"current_steps": 682, "total_steps": 1235, "loss": 0.2688, "lr": 1.9858615369627537e-05, "epoch": 2.7611336032388665, "percentage": 55.22, "elapsed_time": "3:16:29", "remaining_time": "2:39:19"}
683
+ {"current_steps": 683, "total_steps": 1235, "loss": 0.2688, "lr": 1.9802063100191916e-05, "epoch": 2.765182186234818, "percentage": 55.3, "elapsed_time": "3:16:48", "remaining_time": "2:39:03"}
684
+ {"current_steps": 684, "total_steps": 1235, "loss": 0.2646, "lr": 1.974551241345447e-05, "epoch": 2.769230769230769, "percentage": 55.38, "elapsed_time": "3:17:03", "remaining_time": "2:38:44"}
685
+ {"current_steps": 685, "total_steps": 1235, "loss": 0.2631, "lr": 1.9688963761592984e-05, "epoch": 2.7732793522267207, "percentage": 55.47, "elapsed_time": "3:17:19", "remaining_time": "2:38:26"}
686
+ {"current_steps": 686, "total_steps": 1235, "loss": 0.2716, "lr": 1.963241759676897e-05, "epoch": 2.7773279352226723, "percentage": 55.55, "elapsed_time": "3:17:32", "remaining_time": "2:38:05"}
687
+ {"current_steps": 687, "total_steps": 1235, "loss": 0.2598, "lr": 1.9575874371124066e-05, "epoch": 2.7813765182186234, "percentage": 55.63, "elapsed_time": "3:17:50", "remaining_time": "2:37:48"}
688
+ {"current_steps": 688, "total_steps": 1235, "loss": 0.2471, "lr": 1.951933453677638e-05, "epoch": 2.785425101214575, "percentage": 55.71, "elapsed_time": "3:18:07", "remaining_time": "2:37:31"}
689
+ {"current_steps": 689, "total_steps": 1235, "loss": 0.2714, "lr": 1.9462798545816932e-05, "epoch": 2.7894736842105265, "percentage": 55.79, "elapsed_time": "3:18:30", "remaining_time": "2:37:18"}
690
+ {"current_steps": 690, "total_steps": 1235, "loss": 0.278, "lr": 1.9406266850305996e-05, "epoch": 2.7935222672064777, "percentage": 55.87, "elapsed_time": "3:18:45", "remaining_time": "2:36:59"}
691
+ {"current_steps": 691, "total_steps": 1235, "loss": 0.2592, "lr": 1.9349739902269503e-05, "epoch": 2.7975708502024292, "percentage": 55.95, "elapsed_time": "3:19:01", "remaining_time": "2:36:41"}
692
+ {"current_steps": 692, "total_steps": 1235, "loss": 0.2717, "lr": 1.9293218153695425e-05, "epoch": 2.801619433198381, "percentage": 56.03, "elapsed_time": "3:19:21", "remaining_time": "2:36:25"}
693
+ {"current_steps": 693, "total_steps": 1235, "loss": 0.2531, "lr": 1.9236702056530153e-05, "epoch": 2.805668016194332, "percentage": 56.11, "elapsed_time": "3:19:38", "remaining_time": "2:36:08"}
694
+ {"current_steps": 694, "total_steps": 1235, "loss": 0.2558, "lr": 1.9180192062674907e-05, "epoch": 2.8097165991902835, "percentage": 56.19, "elapsed_time": "3:19:59", "remaining_time": "2:35:54"}
695
+ {"current_steps": 695, "total_steps": 1235, "loss": 0.247, "lr": 1.9123688623982076e-05, "epoch": 2.813765182186235, "percentage": 56.28, "elapsed_time": "3:20:16", "remaining_time": "2:35:36"}
696
+ {"current_steps": 696, "total_steps": 1235, "loss": 0.2911, "lr": 1.906719219225165e-05, "epoch": 2.817813765182186, "percentage": 56.36, "elapsed_time": "3:20:32", "remaining_time": "2:35:18"}
697
+ {"current_steps": 697, "total_steps": 1235, "loss": 0.2528, "lr": 1.9010703219227603e-05, "epoch": 2.8218623481781377, "percentage": 56.44, "elapsed_time": "3:20:47", "remaining_time": "2:34:59"}
698
+ {"current_steps": 698, "total_steps": 1235, "loss": 0.2484, "lr": 1.8954222156594256e-05, "epoch": 2.8259109311740893, "percentage": 56.52, "elapsed_time": "3:21:06", "remaining_time": "2:34:43"}
699
+ {"current_steps": 699, "total_steps": 1235, "loss": 0.2348, "lr": 1.8897749455972673e-05, "epoch": 2.8299595141700404, "percentage": 56.6, "elapsed_time": "3:21:20", "remaining_time": "2:34:23"}
700
+ {"current_steps": 700, "total_steps": 1235, "loss": 0.2494, "lr": 1.884128556891707e-05, "epoch": 2.834008097165992, "percentage": 56.68, "elapsed_time": "3:21:39", "remaining_time": "2:34:07"}
701
+ {"current_steps": 701, "total_steps": 1235, "loss": 0.2383, "lr": 1.878483094691119e-05, "epoch": 2.8380566801619436, "percentage": 56.76, "elapsed_time": "3:21:53", "remaining_time": "2:33:47"}
702
+ {"current_steps": 702, "total_steps": 1235, "loss": 0.2402, "lr": 1.8728386041364664e-05, "epoch": 2.8421052631578947, "percentage": 56.84, "elapsed_time": "3:22:08", "remaining_time": "2:33:28"}
703
+ {"current_steps": 703, "total_steps": 1235, "loss": 0.2603, "lr": 1.867195130360947e-05, "epoch": 2.8461538461538463, "percentage": 56.92, "elapsed_time": "3:22:31", "remaining_time": "2:33:15"}
704
+ {"current_steps": 704, "total_steps": 1235, "loss": 0.2479, "lr": 1.8615527184896263e-05, "epoch": 2.850202429149798, "percentage": 57.0, "elapsed_time": "3:22:48", "remaining_time": "2:32:58"}
705
+ {"current_steps": 705, "total_steps": 1235, "loss": 0.2555, "lr": 1.8559114136390795e-05, "epoch": 2.854251012145749, "percentage": 57.09, "elapsed_time": "3:23:03", "remaining_time": "2:32:38"}
706
+ {"current_steps": 706, "total_steps": 1235, "loss": 0.2557, "lr": 1.8502712609170298e-05, "epoch": 2.8582995951417005, "percentage": 57.17, "elapsed_time": "3:23:22", "remaining_time": "2:32:23"}
707
+ {"current_steps": 707, "total_steps": 1235, "loss": 0.2576, "lr": 1.8446323054219876e-05, "epoch": 2.862348178137652, "percentage": 57.25, "elapsed_time": "3:23:37", "remaining_time": "2:32:03"}
708
+ {"current_steps": 708, "total_steps": 1235, "loss": 0.2796, "lr": 1.838994592242891e-05, "epoch": 2.866396761133603, "percentage": 57.33, "elapsed_time": "3:23:52", "remaining_time": "2:31:45"}
709
+ {"current_steps": 709, "total_steps": 1235, "loss": 0.2395, "lr": 1.8333581664587453e-05, "epoch": 2.8704453441295548, "percentage": 57.41, "elapsed_time": "3:24:12", "remaining_time": "2:31:29"}
710
+ {"current_steps": 710, "total_steps": 1235, "loss": 0.2426, "lr": 1.8277230731382593e-05, "epoch": 2.8744939271255063, "percentage": 57.49, "elapsed_time": "3:24:24", "remaining_time": "2:31:08"}
711
+ {"current_steps": 711, "total_steps": 1235, "loss": 0.2448, "lr": 1.82208935733949e-05, "epoch": 2.8785425101214575, "percentage": 57.57, "elapsed_time": "3:24:39", "remaining_time": "2:30:49"}
712
+ {"current_steps": 712, "total_steps": 1235, "loss": 0.2275, "lr": 1.8164570641094793e-05, "epoch": 2.882591093117409, "percentage": 57.65, "elapsed_time": "3:24:54", "remaining_time": "2:30:30"}
713
+ {"current_steps": 713, "total_steps": 1235, "loss": 0.249, "lr": 1.810826238483892e-05, "epoch": 2.8866396761133606, "percentage": 57.73, "elapsed_time": "3:25:12", "remaining_time": "2:30:14"}
714
+ {"current_steps": 714, "total_steps": 1235, "loss": 0.2443, "lr": 1.8051969254866608e-05, "epoch": 2.8906882591093117, "percentage": 57.81, "elapsed_time": "3:25:26", "remaining_time": "2:29:54"}
715
+ {"current_steps": 715, "total_steps": 1235, "loss": 0.2576, "lr": 1.7995691701296226e-05, "epoch": 2.8947368421052633, "percentage": 57.89, "elapsed_time": "3:25:41", "remaining_time": "2:29:35"}
716
+ {"current_steps": 716, "total_steps": 1235, "loss": 0.2896, "lr": 1.7939430174121593e-05, "epoch": 2.898785425101215, "percentage": 57.98, "elapsed_time": "3:26:01", "remaining_time": "2:29:20"}
717
+ {"current_steps": 717, "total_steps": 1235, "loss": 0.2467, "lr": 1.788318512320838e-05, "epoch": 2.902834008097166, "percentage": 58.06, "elapsed_time": "3:26:18", "remaining_time": "2:29:02"}
718
+ {"current_steps": 718, "total_steps": 1235, "loss": 0.2491, "lr": 1.782695699829051e-05, "epoch": 2.9068825910931175, "percentage": 58.14, "elapsed_time": "3:26:37", "remaining_time": "2:28:46"}
719
+ {"current_steps": 719, "total_steps": 1235, "loss": 0.2308, "lr": 1.7770746248966587e-05, "epoch": 2.910931174089069, "percentage": 58.22, "elapsed_time": "3:26:53", "remaining_time": "2:28:28"}
720
+ {"current_steps": 720, "total_steps": 1235, "loss": 0.2492, "lr": 1.7714553324696243e-05, "epoch": 2.91497975708502, "percentage": 58.3, "elapsed_time": "3:27:12", "remaining_time": "2:28:12"}
721
+ {"current_steps": 721, "total_steps": 1235, "loss": 0.258, "lr": 1.7658378674796614e-05, "epoch": 2.919028340080972, "percentage": 58.38, "elapsed_time": "3:27:27", "remaining_time": "2:27:53"}
722
+ {"current_steps": 722, "total_steps": 1235, "loss": 0.2431, "lr": 1.76022227484387e-05, "epoch": 2.9230769230769234, "percentage": 58.46, "elapsed_time": "3:27:45", "remaining_time": "2:27:37"}
723
+ {"current_steps": 723, "total_steps": 1235, "loss": 0.2615, "lr": 1.7546085994643807e-05, "epoch": 2.9271255060728745, "percentage": 58.54, "elapsed_time": "3:28:01", "remaining_time": "2:27:19"}
724
+ {"current_steps": 724, "total_steps": 1235, "loss": 0.214, "lr": 1.7489968862279902e-05, "epoch": 2.931174089068826, "percentage": 58.62, "elapsed_time": "3:28:19", "remaining_time": "2:27:01"}
725
+ {"current_steps": 725, "total_steps": 1235, "loss": 0.2727, "lr": 1.743387180005809e-05, "epoch": 2.9352226720647776, "percentage": 58.7, "elapsed_time": "3:28:33", "remaining_time": "2:26:42"}
726
+ {"current_steps": 726, "total_steps": 1235, "loss": 0.2776, "lr": 1.737779525652899e-05, "epoch": 2.9392712550607287, "percentage": 58.79, "elapsed_time": "3:28:50", "remaining_time": "2:26:25"}
727
+ {"current_steps": 727, "total_steps": 1235, "loss": 0.255, "lr": 1.732173968007914e-05, "epoch": 2.9433198380566803, "percentage": 58.87, "elapsed_time": "3:29:08", "remaining_time": "2:26:08"}
728
+ {"current_steps": 728, "total_steps": 1235, "loss": 0.2671, "lr": 1.7265705518927437e-05, "epoch": 2.9473684210526314, "percentage": 58.95, "elapsed_time": "3:29:25", "remaining_time": "2:25:51"}
729
+ {"current_steps": 729, "total_steps": 1235, "loss": 0.2349, "lr": 1.7209693221121542e-05, "epoch": 2.951417004048583, "percentage": 59.03, "elapsed_time": "3:29:39", "remaining_time": "2:25:31"}
730
+ {"current_steps": 730, "total_steps": 1235, "loss": 0.2477, "lr": 1.7153703234534302e-05, "epoch": 2.9554655870445345, "percentage": 59.11, "elapsed_time": "3:29:54", "remaining_time": "2:25:12"}
731
+ {"current_steps": 731, "total_steps": 1235, "loss": 0.2657, "lr": 1.709773600686015e-05, "epoch": 2.9595141700404857, "percentage": 59.19, "elapsed_time": "3:30:14", "remaining_time": "2:24:57"}
732
+ {"current_steps": 732, "total_steps": 1235, "loss": 0.2371, "lr": 1.7041791985611548e-05, "epoch": 2.9635627530364372, "percentage": 59.27, "elapsed_time": "3:30:34", "remaining_time": "2:24:41"}
733
+ {"current_steps": 733, "total_steps": 1235, "loss": 0.2453, "lr": 1.69858716181154e-05, "epoch": 2.967611336032389, "percentage": 59.35, "elapsed_time": "3:30:52", "remaining_time": "2:24:25"}
734
+ {"current_steps": 734, "total_steps": 1235, "loss": 0.2556, "lr": 1.692997535150948e-05, "epoch": 2.97165991902834, "percentage": 59.43, "elapsed_time": "3:31:09", "remaining_time": "2:24:07"}
735
+ {"current_steps": 735, "total_steps": 1235, "loss": 0.2487, "lr": 1.687410363273884e-05, "epoch": 2.9757085020242915, "percentage": 59.51, "elapsed_time": "3:31:28", "remaining_time": "2:23:51"}
736
+ {"current_steps": 736, "total_steps": 1235, "loss": 0.2571, "lr": 1.6818256908552257e-05, "epoch": 2.979757085020243, "percentage": 59.6, "elapsed_time": "3:31:45", "remaining_time": "2:23:34"}
737
+ {"current_steps": 737, "total_steps": 1235, "loss": 0.2461, "lr": 1.6762435625498646e-05, "epoch": 2.983805668016194, "percentage": 59.68, "elapsed_time": "3:32:00", "remaining_time": "2:23:15"}
738
+ {"current_steps": 738, "total_steps": 1235, "loss": 0.2803, "lr": 1.67066402299235e-05, "epoch": 2.9878542510121457, "percentage": 59.76, "elapsed_time": "3:32:16", "remaining_time": "2:22:57"}
739
+ {"current_steps": 739, "total_steps": 1235, "loss": 0.2485, "lr": 1.6650871167965313e-05, "epoch": 2.9919028340080973, "percentage": 59.84, "elapsed_time": "3:32:37", "remaining_time": "2:22:42"}
740
+ {"current_steps": 740, "total_steps": 1235, "loss": 0.2452, "lr": 1.6595128885552028e-05, "epoch": 2.9959514170040484, "percentage": 59.92, "elapsed_time": "3:32:52", "remaining_time": "2:22:23"}
741
+ {"current_steps": 741, "total_steps": 1235, "loss": 0.2557, "lr": 1.653941382839745e-05, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "3:33:12", "remaining_time": "2:22:08"}
742
+ {"current_steps": 742, "total_steps": 1235, "loss": 0.1615, "lr": 1.6483726441997673e-05, "epoch": 3.0040485829959516, "percentage": 60.08, "elapsed_time": "3:35:13", "remaining_time": "2:22:59"}
743
+ {"current_steps": 743, "total_steps": 1235, "loss": 0.1752, "lr": 1.642806717162757e-05, "epoch": 3.0080971659919027, "percentage": 60.16, "elapsed_time": "3:35:28", "remaining_time": "2:22:41"}
744
+ {"current_steps": 744, "total_steps": 1235, "loss": 0.1598, "lr": 1.637243646233718e-05, "epoch": 3.0121457489878543, "percentage": 60.24, "elapsed_time": "3:35:48", "remaining_time": "2:22:25"}
745
+ {"current_steps": 745, "total_steps": 1235, "loss": 0.1655, "lr": 1.6316834758948174e-05, "epoch": 3.016194331983806, "percentage": 60.32, "elapsed_time": "3:36:08", "remaining_time": "2:22:09"}
746
+ {"current_steps": 746, "total_steps": 1235, "loss": 0.2061, "lr": 1.6261262506050282e-05, "epoch": 3.020242914979757, "percentage": 60.4, "elapsed_time": "3:36:26", "remaining_time": "2:21:52"}
747
+ {"current_steps": 747, "total_steps": 1235, "loss": 0.1757, "lr": 1.620572014799777e-05, "epoch": 3.0242914979757085, "percentage": 60.49, "elapsed_time": "3:36:45", "remaining_time": "2:21:36"}
748
+ {"current_steps": 748, "total_steps": 1235, "loss": 0.1723, "lr": 1.6150208128905857e-05, "epoch": 3.02834008097166, "percentage": 60.57, "elapsed_time": "3:36:59", "remaining_time": "2:21:16"}
749
+ {"current_steps": 749, "total_steps": 1235, "loss": 0.1868, "lr": 1.6094726892647147e-05, "epoch": 3.032388663967611, "percentage": 60.65, "elapsed_time": "3:37:15", "remaining_time": "2:20:58"}
750
+ {"current_steps": 750, "total_steps": 1235, "loss": 0.151, "lr": 1.6039276882848135e-05, "epoch": 3.0364372469635628, "percentage": 60.73, "elapsed_time": "3:37:32", "remaining_time": "2:20:40"}
751
+ {"current_steps": 751, "total_steps": 1235, "loss": 0.1633, "lr": 1.5983858542885635e-05, "epoch": 3.0404858299595143, "percentage": 60.81, "elapsed_time": "3:37:46", "remaining_time": "2:20:21"}