neginr commited on
Commit
94d08e7
·
verified ·
1 Parent(s): 4a0366a

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 sha256:17d0d63fb96d14a07272680b4936e4c9c0815ff3586d5aa7c367045b225cde44
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5415e3960d6be43f840e6fd50574669205393c943075e8161c71c566da3a9f
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:f495033a27a9f0529efd7e652087d3546a08246ef2c505ec46f640d9a537e831
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:018778737a33d02a86df6a487aa7014c0a1123a59bd4472181c44a0bb6321b5f
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7755be26b5f9d0a71f6badbc240ca8f36e882398d5466d3ce21588760fc9972c
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0131aa59f8bb7272ae56d45f79ba66a42ced915dcd0bc18924a46a640b07fa95
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22533dc1f0861d4cd92f78329682a1e0ebe0dd421f2e393ab712e95011b4f206
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fa7f3141d3b127a383bb9457110a34f5d1f36f44ebb725bace414e4d458a8ba
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -502,3 +502,250 @@
502
  {"current_steps": 502, "total_steps": 1235, "loss": 0.2684, "lr": 2.9622185557068238e-05, "epoch": 2.032388663967611, "percentage": 40.65, "elapsed_time": "2:36:01", "remaining_time": "3:47:49"}
503
  {"current_steps": 503, "total_steps": 1235, "loss": 0.237, "lr": 2.95725682050846e-05, "epoch": 2.0364372469635628, "percentage": 40.73, "elapsed_time": "2:36:16", "remaining_time": "3:47:24"}
504
  {"current_steps": 504, "total_steps": 1235, "loss": 0.2431, "lr": 2.9522874311100684e-05, "epoch": 2.0404858299595143, "percentage": 40.81, "elapsed_time": "2:36:35", "remaining_time": "3:47:06"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
502
  {"current_steps": 502, "total_steps": 1235, "loss": 0.2684, "lr": 2.9622185557068238e-05, "epoch": 2.032388663967611, "percentage": 40.65, "elapsed_time": "2:36:01", "remaining_time": "3:47:49"}
503
  {"current_steps": 503, "total_steps": 1235, "loss": 0.237, "lr": 2.95725682050846e-05, "epoch": 2.0364372469635628, "percentage": 40.73, "elapsed_time": "2:36:16", "remaining_time": "3:47:24"}
504
  {"current_steps": 504, "total_steps": 1235, "loss": 0.2431, "lr": 2.9522874311100684e-05, "epoch": 2.0404858299595143, "percentage": 40.81, "elapsed_time": "2:36:35", "remaining_time": "3:47:06"}
505
+ {"current_steps": 505, "total_steps": 1235, "loss": 0.2538, "lr": 2.9473104272467526e-05, "epoch": 2.0445344129554655, "percentage": 40.89, "elapsed_time": "2:36:54", "remaining_time": "3:46:49"}
506
+ {"current_steps": 506, "total_steps": 1235, "loss": 0.2591, "lr": 2.942325848714505e-05, "epoch": 2.048582995951417, "percentage": 40.97, "elapsed_time": "2:37:15", "remaining_time": "3:46:34"}
507
+ {"current_steps": 507, "total_steps": 1235, "loss": 0.2217, "lr": 2.9373337353698804e-05, "epoch": 2.0526315789473686, "percentage": 41.05, "elapsed_time": "2:37:34", "remaining_time": "3:46:16"}
508
+ {"current_steps": 508, "total_steps": 1235, "loss": 0.2585, "lr": 2.932334127129686e-05, "epoch": 2.0566801619433197, "percentage": 41.13, "elapsed_time": "2:37:54", "remaining_time": "3:45:59"}
509
+ {"current_steps": 509, "total_steps": 1235, "loss": 0.2546, "lr": 2.9273270639706547e-05, "epoch": 2.0607287449392713, "percentage": 41.21, "elapsed_time": "2:38:12", "remaining_time": "3:45:39"}
510
+ {"current_steps": 510, "total_steps": 1235, "loss": 0.2496, "lr": 2.922312585929131e-05, "epoch": 2.064777327935223, "percentage": 41.3, "elapsed_time": "2:38:31", "remaining_time": "3:45:20"}
511
+ {"current_steps": 511, "total_steps": 1235, "loss": 0.235, "lr": 2.9172907331007478e-05, "epoch": 2.068825910931174, "percentage": 41.38, "elapsed_time": "2:38:47", "remaining_time": "3:44:58"}
512
+ {"current_steps": 512, "total_steps": 1235, "loss": 0.2479, "lr": 2.9122615456401053e-05, "epoch": 2.0728744939271255, "percentage": 41.46, "elapsed_time": "2:39:05", "remaining_time": "3:44:39"}
513
+ {"current_steps": 513, "total_steps": 1235, "loss": 0.2592, "lr": 2.9072250637604535e-05, "epoch": 2.076923076923077, "percentage": 41.54, "elapsed_time": "2:39:24", "remaining_time": "3:44:21"}
514
+ {"current_steps": 514, "total_steps": 1235, "loss": 0.2566, "lr": 2.9021813277333667e-05, "epoch": 2.080971659919028, "percentage": 41.62, "elapsed_time": "2:39:45", "remaining_time": "3:44:06"}
515
+ {"current_steps": 515, "total_steps": 1235, "loss": 0.2372, "lr": 2.8971303778884244e-05, "epoch": 2.08502024291498, "percentage": 41.7, "elapsed_time": "2:40:03", "remaining_time": "3:43:46"}
516
+ {"current_steps": 516, "total_steps": 1235, "loss": 0.2497, "lr": 2.8920722546128863e-05, "epoch": 2.0890688259109313, "percentage": 41.78, "elapsed_time": "2:40:19", "remaining_time": "3:43:24"}
517
+ {"current_steps": 517, "total_steps": 1235, "loss": 0.2514, "lr": 2.887006998351372e-05, "epoch": 2.0931174089068825, "percentage": 41.86, "elapsed_time": "2:40:38", "remaining_time": "3:43:06"}
518
+ {"current_steps": 518, "total_steps": 1235, "loss": 0.2497, "lr": 2.881934649605535e-05, "epoch": 2.097165991902834, "percentage": 41.94, "elapsed_time": "2:40:58", "remaining_time": "3:42:49"}
519
+ {"current_steps": 519, "total_steps": 1235, "loss": 0.257, "lr": 2.8768552489337408e-05, "epoch": 2.1012145748987856, "percentage": 42.02, "elapsed_time": "2:41:15", "remaining_time": "3:42:27"}
520
+ {"current_steps": 520, "total_steps": 1235, "loss": 0.2421, "lr": 2.8717688369507425e-05, "epoch": 2.1052631578947367, "percentage": 42.11, "elapsed_time": "2:41:33", "remaining_time": "3:42:09"}
521
+ {"current_steps": 521, "total_steps": 1235, "loss": 0.2423, "lr": 2.8666754543273535e-05, "epoch": 2.1093117408906883, "percentage": 42.19, "elapsed_time": "2:41:51", "remaining_time": "3:41:49"}
522
+ {"current_steps": 522, "total_steps": 1235, "loss": 0.2532, "lr": 2.8615751417901273e-05, "epoch": 2.11336032388664, "percentage": 42.27, "elapsed_time": "2:42:10", "remaining_time": "3:41:31"}
523
+ {"current_steps": 523, "total_steps": 1235, "loss": 0.2396, "lr": 2.856467940121025e-05, "epoch": 2.117408906882591, "percentage": 42.35, "elapsed_time": "2:42:31", "remaining_time": "3:41:15"}
524
+ {"current_steps": 524, "total_steps": 1235, "loss": 0.2338, "lr": 2.8513538901570964e-05, "epoch": 2.1214574898785425, "percentage": 42.43, "elapsed_time": "2:42:49", "remaining_time": "3:40:56"}
525
+ {"current_steps": 525, "total_steps": 1235, "loss": 0.2636, "lr": 2.846233032790149e-05, "epoch": 2.125506072874494, "percentage": 42.51, "elapsed_time": "2:43:06", "remaining_time": "3:40:34"}
526
+ {"current_steps": 526, "total_steps": 1235, "loss": 0.2385, "lr": 2.84110540896642e-05, "epoch": 2.1295546558704452, "percentage": 42.59, "elapsed_time": "2:43:22", "remaining_time": "3:40:12"}
527
+ {"current_steps": 527, "total_steps": 1235, "loss": 0.2494, "lr": 2.8359710596862555e-05, "epoch": 2.133603238866397, "percentage": 42.67, "elapsed_time": "2:43:40", "remaining_time": "3:39:52"}
528
+ {"current_steps": 528, "total_steps": 1235, "loss": 0.2448, "lr": 2.8308300260037734e-05, "epoch": 2.1376518218623484, "percentage": 42.75, "elapsed_time": "2:43:58", "remaining_time": "3:39:33"}
529
+ {"current_steps": 529, "total_steps": 1235, "loss": 0.255, "lr": 2.8256823490265424e-05, "epoch": 2.1417004048582995, "percentage": 42.83, "elapsed_time": "2:44:19", "remaining_time": "3:39:18"}
530
+ {"current_steps": 530, "total_steps": 1235, "loss": 0.2304, "lr": 2.8205280699152515e-05, "epoch": 2.145748987854251, "percentage": 42.91, "elapsed_time": "2:44:37", "remaining_time": "3:38:59"}
531
+ {"current_steps": 531, "total_steps": 1235, "loss": 0.2534, "lr": 2.8153672298833777e-05, "epoch": 2.1497975708502026, "percentage": 43.0, "elapsed_time": "2:44:59", "remaining_time": "3:38:45"}
532
+ {"current_steps": 532, "total_steps": 1235, "loss": 0.2353, "lr": 2.8101998701968615e-05, "epoch": 2.1538461538461537, "percentage": 43.08, "elapsed_time": "2:45:20", "remaining_time": "3:38:29"}
533
+ {"current_steps": 533, "total_steps": 1235, "loss": 0.2515, "lr": 2.805026032173773e-05, "epoch": 2.1578947368421053, "percentage": 43.16, "elapsed_time": "2:45:39", "remaining_time": "3:38:11"}
534
+ {"current_steps": 534, "total_steps": 1235, "loss": 0.2475, "lr": 2.7998457571839832e-05, "epoch": 2.161943319838057, "percentage": 43.24, "elapsed_time": "2:46:00", "remaining_time": "3:37:55"}
535
+ {"current_steps": 535, "total_steps": 1235, "loss": 0.2497, "lr": 2.7946590866488322e-05, "epoch": 2.165991902834008, "percentage": 43.32, "elapsed_time": "2:46:17", "remaining_time": "3:37:34"}
536
+ {"current_steps": 536, "total_steps": 1235, "loss": 0.2494, "lr": 2.7894660620408e-05, "epoch": 2.1700404858299596, "percentage": 43.4, "elapsed_time": "2:46:36", "remaining_time": "3:37:16"}
537
+ {"current_steps": 537, "total_steps": 1235, "loss": 0.2621, "lr": 2.784266724883173e-05, "epoch": 2.174089068825911, "percentage": 43.48, "elapsed_time": "2:46:53", "remaining_time": "3:36:55"}
538
+ {"current_steps": 538, "total_steps": 1235, "loss": 0.2451, "lr": 2.7790611167497128e-05, "epoch": 2.1781376518218623, "percentage": 43.56, "elapsed_time": "2:47:09", "remaining_time": "3:36:33"}
539
+ {"current_steps": 539, "total_steps": 1235, "loss": 0.2491, "lr": 2.7738492792643224e-05, "epoch": 2.182186234817814, "percentage": 43.64, "elapsed_time": "2:47:27", "remaining_time": "3:36:14"}
540
+ {"current_steps": 540, "total_steps": 1235, "loss": 0.241, "lr": 2.768631254100716e-05, "epoch": 2.1862348178137654, "percentage": 43.72, "elapsed_time": "2:47:44", "remaining_time": "3:35:53"}
541
+ {"current_steps": 541, "total_steps": 1235, "loss": 0.2462, "lr": 2.7634070829820836e-05, "epoch": 2.1902834008097165, "percentage": 43.81, "elapsed_time": "2:48:01", "remaining_time": "3:35:32"}
542
+ {"current_steps": 542, "total_steps": 1235, "loss": 0.2471, "lr": 2.7581768076807592e-05, "epoch": 2.194331983805668, "percentage": 43.89, "elapsed_time": "2:48:16", "remaining_time": "3:35:09"}
543
+ {"current_steps": 543, "total_steps": 1235, "loss": 0.257, "lr": 2.7529404700178832e-05, "epoch": 2.1983805668016196, "percentage": 43.97, "elapsed_time": "2:48:37", "remaining_time": "3:34:54"}
544
+ {"current_steps": 544, "total_steps": 1235, "loss": 0.2576, "lr": 2.7476981118630735e-05, "epoch": 2.2024291497975708, "percentage": 44.05, "elapsed_time": "2:48:55", "remaining_time": "3:34:34"}
545
+ {"current_steps": 545, "total_steps": 1235, "loss": 0.247, "lr": 2.742449775134085e-05, "epoch": 2.2064777327935223, "percentage": 44.13, "elapsed_time": "2:49:15", "remaining_time": "3:34:16"}
546
+ {"current_steps": 546, "total_steps": 1235, "loss": 0.2538, "lr": 2.7371955017964788e-05, "epoch": 2.2105263157894735, "percentage": 44.21, "elapsed_time": "2:49:33", "remaining_time": "3:33:58"}
547
+ {"current_steps": 547, "total_steps": 1235, "loss": 0.2476, "lr": 2.7319353338632845e-05, "epoch": 2.214574898785425, "percentage": 44.29, "elapsed_time": "2:49:47", "remaining_time": "3:33:33"}
548
+ {"current_steps": 548, "total_steps": 1235, "loss": 0.2446, "lr": 2.7266693133946645e-05, "epoch": 2.2186234817813766, "percentage": 44.37, "elapsed_time": "2:50:06", "remaining_time": "3:33:15"}
549
+ {"current_steps": 549, "total_steps": 1235, "loss": 0.2551, "lr": 2.7213974824975785e-05, "epoch": 2.2226720647773277, "percentage": 44.45, "elapsed_time": "2:50:25", "remaining_time": "3:32:56"}
550
+ {"current_steps": 550, "total_steps": 1235, "loss": 0.2489, "lr": 2.7161198833254464e-05, "epoch": 2.2267206477732793, "percentage": 44.53, "elapsed_time": "2:50:45", "remaining_time": "3:32:39"}
551
+ {"current_steps": 551, "total_steps": 1235, "loss": 0.2715, "lr": 2.7108365580778095e-05, "epoch": 2.230769230769231, "percentage": 44.62, "elapsed_time": "2:51:07", "remaining_time": "3:32:25"}
552
+ {"current_steps": 552, "total_steps": 1235, "loss": 0.2518, "lr": 2.705547548999996e-05, "epoch": 2.234817813765182, "percentage": 44.7, "elapsed_time": "2:51:24", "remaining_time": "3:32:05"}
553
+ {"current_steps": 553, "total_steps": 1235, "loss": 0.2475, "lr": 2.7002528983827817e-05, "epoch": 2.2388663967611335, "percentage": 44.78, "elapsed_time": "2:51:42", "remaining_time": "3:31:45"}
554
+ {"current_steps": 554, "total_steps": 1235, "loss": 0.2397, "lr": 2.6949526485620517e-05, "epoch": 2.242914979757085, "percentage": 44.86, "elapsed_time": "2:52:00", "remaining_time": "3:31:26"}
555
+ {"current_steps": 555, "total_steps": 1235, "loss": 0.2335, "lr": 2.6896468419184623e-05, "epoch": 2.246963562753036, "percentage": 44.94, "elapsed_time": "2:52:13", "remaining_time": "3:31:00"}
556
+ {"current_steps": 556, "total_steps": 1235, "loss": 0.2282, "lr": 2.6843355208771024e-05, "epoch": 2.251012145748988, "percentage": 45.02, "elapsed_time": "2:52:28", "remaining_time": "3:30:37"}
557
+ {"current_steps": 557, "total_steps": 1235, "loss": 0.2348, "lr": 2.6790187279071536e-05, "epoch": 2.2550607287449393, "percentage": 45.1, "elapsed_time": "2:52:43", "remaining_time": "3:30:14"}
558
+ {"current_steps": 558, "total_steps": 1235, "loss": 0.2476, "lr": 2.67369650552155e-05, "epoch": 2.2591093117408905, "percentage": 45.18, "elapsed_time": "2:53:00", "remaining_time": "3:29:53"}
559
+ {"current_steps": 559, "total_steps": 1235, "loss": 0.2264, "lr": 2.6683688962766407e-05, "epoch": 2.263157894736842, "percentage": 45.26, "elapsed_time": "2:53:16", "remaining_time": "3:29:32"}
560
+ {"current_steps": 560, "total_steps": 1235, "loss": 0.2695, "lr": 2.6630359427718468e-05, "epoch": 2.2672064777327936, "percentage": 45.34, "elapsed_time": "2:53:34", "remaining_time": "3:29:12"}
561
+ {"current_steps": 561, "total_steps": 1235, "loss": 0.2579, "lr": 2.6576976876493225e-05, "epoch": 2.2712550607287447, "percentage": 45.43, "elapsed_time": "2:53:51", "remaining_time": "3:28:53"}
562
+ {"current_steps": 562, "total_steps": 1235, "loss": 0.2329, "lr": 2.652354173593614e-05, "epoch": 2.2753036437246963, "percentage": 45.51, "elapsed_time": "2:54:11", "remaining_time": "3:28:35"}
563
+ {"current_steps": 563, "total_steps": 1235, "loss": 0.2376, "lr": 2.647005443331317e-05, "epoch": 2.279352226720648, "percentage": 45.59, "elapsed_time": "2:54:26", "remaining_time": "3:28:12"}
564
+ {"current_steps": 564, "total_steps": 1235, "loss": 0.2422, "lr": 2.6416515396307354e-05, "epoch": 2.283400809716599, "percentage": 45.67, "elapsed_time": "2:54:41", "remaining_time": "3:27:49"}
565
+ {"current_steps": 565, "total_steps": 1235, "loss": 0.2649, "lr": 2.636292505301542e-05, "epoch": 2.2874493927125505, "percentage": 45.75, "elapsed_time": "2:54:57", "remaining_time": "3:27:27"}
566
+ {"current_steps": 566, "total_steps": 1235, "loss": 0.2695, "lr": 2.630928383194431e-05, "epoch": 2.291497975708502, "percentage": 45.83, "elapsed_time": "2:55:15", "remaining_time": "3:27:09"}
567
+ {"current_steps": 567, "total_steps": 1235, "loss": 0.2689, "lr": 2.625559216200781e-05, "epoch": 2.2955465587044532, "percentage": 45.91, "elapsed_time": "2:55:36", "remaining_time": "3:26:52"}
568
+ {"current_steps": 568, "total_steps": 1235, "loss": 0.2601, "lr": 2.620185047252308e-05, "epoch": 2.299595141700405, "percentage": 45.99, "elapsed_time": "2:55:55", "remaining_time": "3:26:35"}
569
+ {"current_steps": 569, "total_steps": 1235, "loss": 0.237, "lr": 2.614805919320723e-05, "epoch": 2.3036437246963564, "percentage": 46.07, "elapsed_time": "2:56:13", "remaining_time": "3:26:15"}
570
+ {"current_steps": 570, "total_steps": 1235, "loss": 0.2429, "lr": 2.6094218754173895e-05, "epoch": 2.3076923076923075, "percentage": 46.15, "elapsed_time": "2:56:30", "remaining_time": "3:25:55"}
571
+ {"current_steps": 571, "total_steps": 1235, "loss": 0.2343, "lr": 2.60403295859298e-05, "epoch": 2.311740890688259, "percentage": 46.23, "elapsed_time": "2:56:49", "remaining_time": "3:25:37"}
572
+ {"current_steps": 572, "total_steps": 1235, "loss": 0.2415, "lr": 2.5986392119371297e-05, "epoch": 2.3157894736842106, "percentage": 46.32, "elapsed_time": "2:57:05", "remaining_time": "3:25:16"}
573
+ {"current_steps": 573, "total_steps": 1235, "loss": 0.2364, "lr": 2.5932406785780928e-05, "epoch": 2.3198380566801617, "percentage": 46.4, "elapsed_time": "2:57:24", "remaining_time": "3:24:57"}
574
+ {"current_steps": 574, "total_steps": 1235, "loss": 0.2804, "lr": 2.5878374016823987e-05, "epoch": 2.3238866396761133, "percentage": 46.48, "elapsed_time": "2:57:43", "remaining_time": "3:24:40"}
575
+ {"current_steps": 575, "total_steps": 1235, "loss": 0.2508, "lr": 2.5824294244545045e-05, "epoch": 2.327935222672065, "percentage": 46.56, "elapsed_time": "2:58:01", "remaining_time": "3:24:21"}
576
+ {"current_steps": 576, "total_steps": 1235, "loss": 0.2722, "lr": 2.577016790136453e-05, "epoch": 2.331983805668016, "percentage": 46.64, "elapsed_time": "2:58:22", "remaining_time": "3:24:04"}
577
+ {"current_steps": 577, "total_steps": 1235, "loss": 0.2529, "lr": 2.5715995420075225e-05, "epoch": 2.3360323886639676, "percentage": 46.72, "elapsed_time": "2:58:38", "remaining_time": "3:23:42"}
578
+ {"current_steps": 578, "total_steps": 1235, "loss": 0.255, "lr": 2.5661777233838864e-05, "epoch": 2.340080971659919, "percentage": 46.8, "elapsed_time": "2:58:57", "remaining_time": "3:23:25"}
579
+ {"current_steps": 579, "total_steps": 1235, "loss": 0.2291, "lr": 2.5607513776182616e-05, "epoch": 2.3441295546558703, "percentage": 46.88, "elapsed_time": "2:59:20", "remaining_time": "3:23:11"}
580
+ {"current_steps": 580, "total_steps": 1235, "loss": 0.2597, "lr": 2.5553205480995633e-05, "epoch": 2.348178137651822, "percentage": 46.96, "elapsed_time": "2:59:42", "remaining_time": "3:22:56"}
581
+ {"current_steps": 581, "total_steps": 1235, "loss": 0.2519, "lr": 2.5498852782525604e-05, "epoch": 2.3522267206477734, "percentage": 47.04, "elapsed_time": "3:00:03", "remaining_time": "3:22:40"}
582
+ {"current_steps": 582, "total_steps": 1235, "loss": 0.2437, "lr": 2.5444456115375252e-05, "epoch": 2.3562753036437245, "percentage": 47.13, "elapsed_time": "3:00:19", "remaining_time": "3:22:19"}
583
+ {"current_steps": 583, "total_steps": 1235, "loss": 0.2386, "lr": 2.539001591449889e-05, "epoch": 2.360323886639676, "percentage": 47.21, "elapsed_time": "3:00:37", "remaining_time": "3:22:00"}
584
+ {"current_steps": 584, "total_steps": 1235, "loss": 0.2471, "lr": 2.53355326151989e-05, "epoch": 2.3643724696356276, "percentage": 47.29, "elapsed_time": "3:00:54", "remaining_time": "3:21:39"}
585
+ {"current_steps": 585, "total_steps": 1235, "loss": 0.2363, "lr": 2.5281006653122288e-05, "epoch": 2.3684210526315788, "percentage": 47.37, "elapsed_time": "3:01:11", "remaining_time": "3:21:19"}
586
+ {"current_steps": 586, "total_steps": 1235, "loss": 0.2528, "lr": 2.5226438464257217e-05, "epoch": 2.3724696356275303, "percentage": 47.45, "elapsed_time": "3:01:28", "remaining_time": "3:20:59"}
587
+ {"current_steps": 587, "total_steps": 1235, "loss": 0.2683, "lr": 2.5171828484929447e-05, "epoch": 2.376518218623482, "percentage": 47.53, "elapsed_time": "3:01:42", "remaining_time": "3:20:35"}
588
+ {"current_steps": 588, "total_steps": 1235, "loss": 0.2621, "lr": 2.5117177151798934e-05, "epoch": 2.380566801619433, "percentage": 47.61, "elapsed_time": "3:02:00", "remaining_time": "3:20:16"}
589
+ {"current_steps": 589, "total_steps": 1235, "loss": 0.2554, "lr": 2.506248490185627e-05, "epoch": 2.3846153846153846, "percentage": 47.69, "elapsed_time": "3:02:21", "remaining_time": "3:20:00"}
590
+ {"current_steps": 590, "total_steps": 1235, "loss": 0.2485, "lr": 2.500775217241923e-05, "epoch": 2.388663967611336, "percentage": 47.77, "elapsed_time": "3:02:40", "remaining_time": "3:19:42"}
591
+ {"current_steps": 591, "total_steps": 1235, "loss": 0.2397, "lr": 2.4952979401129266e-05, "epoch": 2.3927125506072873, "percentage": 47.85, "elapsed_time": "3:02:59", "remaining_time": "3:19:24"}
592
+ {"current_steps": 592, "total_steps": 1235, "loss": 0.252, "lr": 2.4898167025948e-05, "epoch": 2.396761133603239, "percentage": 47.94, "elapsed_time": "3:03:19", "remaining_time": "3:19:07"}
593
+ {"current_steps": 593, "total_steps": 1235, "loss": 0.2639, "lr": 2.4843315485153703e-05, "epoch": 2.4008097165991904, "percentage": 48.02, "elapsed_time": "3:03:38", "remaining_time": "3:18:49"}
594
+ {"current_steps": 594, "total_steps": 1235, "loss": 0.2431, "lr": 2.4788425217337856e-05, "epoch": 2.4048582995951415, "percentage": 48.1, "elapsed_time": "3:03:59", "remaining_time": "3:18:32"}
595
+ {"current_steps": 595, "total_steps": 1235, "loss": 0.2333, "lr": 2.4733496661401572e-05, "epoch": 2.408906882591093, "percentage": 48.18, "elapsed_time": "3:04:14", "remaining_time": "3:18:10"}
596
+ {"current_steps": 596, "total_steps": 1235, "loss": 0.2597, "lr": 2.4678530256552114e-05, "epoch": 2.4129554655870447, "percentage": 48.26, "elapsed_time": "3:04:31", "remaining_time": "3:17:49"}
597
+ {"current_steps": 597, "total_steps": 1235, "loss": 0.2471, "lr": 2.46235264422994e-05, "epoch": 2.417004048582996, "percentage": 48.34, "elapsed_time": "3:04:50", "remaining_time": "3:17:31"}
598
+ {"current_steps": 598, "total_steps": 1235, "loss": 0.2271, "lr": 2.4568485658452452e-05, "epoch": 2.4210526315789473, "percentage": 48.42, "elapsed_time": "3:05:09", "remaining_time": "3:17:14"}
599
+ {"current_steps": 599, "total_steps": 1235, "loss": 0.2391, "lr": 2.451340834511592e-05, "epoch": 2.425101214574899, "percentage": 48.5, "elapsed_time": "3:05:25", "remaining_time": "3:16:52"}
600
+ {"current_steps": 600, "total_steps": 1235, "loss": 0.2469, "lr": 2.4458294942686528e-05, "epoch": 2.42914979757085, "percentage": 48.58, "elapsed_time": "3:05:41", "remaining_time": "3:16:31"}
601
+ {"current_steps": 601, "total_steps": 1235, "loss": 0.2353, "lr": 2.440314589184958e-05, "epoch": 2.4331983805668016, "percentage": 48.66, "elapsed_time": "3:05:58", "remaining_time": "3:16:11"}
602
+ {"current_steps": 602, "total_steps": 1235, "loss": 0.2405, "lr": 2.434796163357541e-05, "epoch": 2.437246963562753, "percentage": 48.74, "elapsed_time": "3:06:13", "remaining_time": "3:15:49"}
603
+ {"current_steps": 603, "total_steps": 1235, "loss": 0.2561, "lr": 2.429274260911588e-05, "epoch": 2.4412955465587043, "percentage": 48.83, "elapsed_time": "3:06:34", "remaining_time": "3:15:32"}
604
+ {"current_steps": 604, "total_steps": 1235, "loss": 0.2426, "lr": 2.423748926000084e-05, "epoch": 2.445344129554656, "percentage": 48.91, "elapsed_time": "3:06:52", "remaining_time": "3:15:13"}
605
+ {"current_steps": 605, "total_steps": 1235, "loss": 0.243, "lr": 2.418220202803459e-05, "epoch": 2.4493927125506074, "percentage": 48.99, "elapsed_time": "3:07:08", "remaining_time": "3:14:52"}
606
+ {"current_steps": 606, "total_steps": 1235, "loss": 0.2405, "lr": 2.412688135529237e-05, "epoch": 2.4534412955465585, "percentage": 49.07, "elapsed_time": "3:07:27", "remaining_time": "3:14:34"}
607
+ {"current_steps": 607, "total_steps": 1235, "loss": 0.2565, "lr": 2.4071527684116807e-05, "epoch": 2.45748987854251, "percentage": 49.15, "elapsed_time": "3:07:47", "remaining_time": "3:14:16"}
608
+ {"current_steps": 608, "total_steps": 1235, "loss": 0.2432, "lr": 2.4016141457114372e-05, "epoch": 2.4615384615384617, "percentage": 49.23, "elapsed_time": "3:08:06", "remaining_time": "3:13:59"}
609
+ {"current_steps": 609, "total_steps": 1235, "loss": 0.267, "lr": 2.396072311715187e-05, "epoch": 2.465587044534413, "percentage": 49.31, "elapsed_time": "3:08:22", "remaining_time": "3:13:38"}
610
+ {"current_steps": 610, "total_steps": 1235, "loss": 0.2366, "lr": 2.3905273107352863e-05, "epoch": 2.4696356275303644, "percentage": 49.39, "elapsed_time": "3:08:38", "remaining_time": "3:13:17"}
611
+ {"current_steps": 611, "total_steps": 1235, "loss": 0.2423, "lr": 2.3849791871094157e-05, "epoch": 2.473684210526316, "percentage": 49.47, "elapsed_time": "3:08:55", "remaining_time": "3:12:56"}
612
+ {"current_steps": 612, "total_steps": 1235, "loss": 0.2628, "lr": 2.379427985200223e-05, "epoch": 2.477732793522267, "percentage": 49.55, "elapsed_time": "3:09:15", "remaining_time": "3:12:39"}
613
+ {"current_steps": 613, "total_steps": 1235, "loss": 0.253, "lr": 2.373873749394972e-05, "epoch": 2.4817813765182186, "percentage": 49.64, "elapsed_time": "3:09:32", "remaining_time": "3:12:19"}
614
+ {"current_steps": 614, "total_steps": 1235, "loss": 0.2482, "lr": 2.3683165241051836e-05, "epoch": 2.48582995951417, "percentage": 49.72, "elapsed_time": "3:09:49", "remaining_time": "3:11:59"}
615
+ {"current_steps": 615, "total_steps": 1235, "loss": 0.2639, "lr": 2.3627563537662823e-05, "epoch": 2.4898785425101213, "percentage": 49.8, "elapsed_time": "3:10:08", "remaining_time": "3:11:40"}
616
+ {"current_steps": 616, "total_steps": 1235, "loss": 0.2531, "lr": 2.3571932828372433e-05, "epoch": 2.493927125506073, "percentage": 49.88, "elapsed_time": "3:10:28", "remaining_time": "3:11:24"}
617
+ {"current_steps": 617, "total_steps": 1235, "loss": 0.2388, "lr": 2.351627355800233e-05, "epoch": 2.4979757085020244, "percentage": 49.96, "elapsed_time": "3:10:47", "remaining_time": "3:11:06"}
618
+ {"current_steps": 618, "total_steps": 1235, "loss": 0.2359, "lr": 2.346058617160256e-05, "epoch": 2.5020242914979756, "percentage": 50.04, "elapsed_time": "3:11:01", "remaining_time": "3:10:42"}
619
+ {"current_steps": 619, "total_steps": 1235, "loss": 0.2432, "lr": 2.3404871114447976e-05, "epoch": 2.506072874493927, "percentage": 50.12, "elapsed_time": "3:11:23", "remaining_time": "3:10:27"}
620
+ {"current_steps": 620, "total_steps": 1235, "loss": 0.235, "lr": 2.334912883203469e-05, "epoch": 2.5101214574898787, "percentage": 50.2, "elapsed_time": "3:11:41", "remaining_time": "3:10:08"}
621
+ {"current_steps": 621, "total_steps": 1235, "loss": 0.2478, "lr": 2.3293359770076505e-05, "epoch": 2.51417004048583, "percentage": 50.28, "elapsed_time": "3:12:00", "remaining_time": "3:09:51"}
622
+ {"current_steps": 622, "total_steps": 1235, "loss": 0.2335, "lr": 2.323756437450136e-05, "epoch": 2.5182186234817814, "percentage": 50.36, "elapsed_time": "3:12:20", "remaining_time": "3:09:33"}
623
+ {"current_steps": 623, "total_steps": 1235, "loss": 0.2532, "lr": 2.3181743091447754e-05, "epoch": 2.522267206477733, "percentage": 50.45, "elapsed_time": "3:12:39", "remaining_time": "3:09:15"}
624
+ {"current_steps": 624, "total_steps": 1235, "loss": 0.2576, "lr": 2.3125896367261164e-05, "epoch": 2.526315789473684, "percentage": 50.53, "elapsed_time": "3:12:56", "remaining_time": "3:08:54"}
625
+ {"current_steps": 625, "total_steps": 1235, "loss": 0.2516, "lr": 2.307002464849052e-05, "epoch": 2.5303643724696356, "percentage": 50.61, "elapsed_time": "3:13:15", "remaining_time": "3:08:37"}
626
+ {"current_steps": 626, "total_steps": 1235, "loss": 0.2437, "lr": 2.30141283818846e-05, "epoch": 2.534412955465587, "percentage": 50.69, "elapsed_time": "3:13:32", "remaining_time": "3:08:17"}
627
+ {"current_steps": 627, "total_steps": 1235, "loss": 0.2384, "lr": 2.2958208014388462e-05, "epoch": 2.5384615384615383, "percentage": 50.77, "elapsed_time": "3:13:48", "remaining_time": "3:07:55"}
628
+ {"current_steps": 628, "total_steps": 1235, "loss": 0.2432, "lr": 2.2902263993139857e-05, "epoch": 2.54251012145749, "percentage": 50.85, "elapsed_time": "3:14:06", "remaining_time": "3:07:36"}
629
+ {"current_steps": 629, "total_steps": 1235, "loss": 0.248, "lr": 2.2846296765465708e-05, "epoch": 2.5465587044534415, "percentage": 50.93, "elapsed_time": "3:14:23", "remaining_time": "3:07:16"}
630
+ {"current_steps": 630, "total_steps": 1235, "loss": 0.2551, "lr": 2.2790306778878465e-05, "epoch": 2.5506072874493926, "percentage": 51.01, "elapsed_time": "3:14:41", "remaining_time": "3:06:58"}
631
+ {"current_steps": 631, "total_steps": 1235, "loss": 0.2494, "lr": 2.273429448107257e-05, "epoch": 2.554655870445344, "percentage": 51.09, "elapsed_time": "3:14:57", "remaining_time": "3:06:37"}
632
+ {"current_steps": 632, "total_steps": 1235, "loss": 0.2398, "lr": 2.2678260319920868e-05, "epoch": 2.5587044534412957, "percentage": 51.17, "elapsed_time": "3:15:14", "remaining_time": "3:06:16"}
633
+ {"current_steps": 633, "total_steps": 1235, "loss": 0.262, "lr": 2.262220474347102e-05, "epoch": 2.562753036437247, "percentage": 51.26, "elapsed_time": "3:15:33", "remaining_time": "3:05:59"}
634
+ {"current_steps": 634, "total_steps": 1235, "loss": 0.2576, "lr": 2.2566128199941918e-05, "epoch": 2.5668016194331984, "percentage": 51.34, "elapsed_time": "3:15:54", "remaining_time": "3:05:42"}
635
+ {"current_steps": 635, "total_steps": 1235, "loss": 0.2498, "lr": 2.2510031137720104e-05, "epoch": 2.57085020242915, "percentage": 51.42, "elapsed_time": "3:16:14", "remaining_time": "3:05:25"}
636
+ {"current_steps": 636, "total_steps": 1235, "loss": 0.2626, "lr": 2.2453914005356206e-05, "epoch": 2.574898785425101, "percentage": 51.5, "elapsed_time": "3:16:34", "remaining_time": "3:05:08"}
637
+ {"current_steps": 637, "total_steps": 1235, "loss": 0.2423, "lr": 2.2397777251561302e-05, "epoch": 2.5789473684210527, "percentage": 51.58, "elapsed_time": "3:16:49", "remaining_time": "3:04:46"}
638
+ {"current_steps": 638, "total_steps": 1235, "loss": 0.2582, "lr": 2.2341621325203393e-05, "epoch": 2.582995951417004, "percentage": 51.66, "elapsed_time": "3:17:07", "remaining_time": "3:04:27"}
639
+ {"current_steps": 639, "total_steps": 1235, "loss": 0.2608, "lr": 2.2285446675303764e-05, "epoch": 2.5870445344129553, "percentage": 51.74, "elapsed_time": "3:17:28", "remaining_time": "3:04:11"}
640
+ {"current_steps": 640, "total_steps": 1235, "loss": 0.2616, "lr": 2.2229253751033423e-05, "epoch": 2.591093117408907, "percentage": 51.82, "elapsed_time": "3:17:47", "remaining_time": "3:03:53"}
641
+ {"current_steps": 641, "total_steps": 1235, "loss": 0.2451, "lr": 2.2173043001709492e-05, "epoch": 2.5951417004048585, "percentage": 51.9, "elapsed_time": "3:18:06", "remaining_time": "3:03:35"}
642
+ {"current_steps": 642, "total_steps": 1235, "loss": 0.2386, "lr": 2.2116814876791627e-05, "epoch": 2.5991902834008096, "percentage": 51.98, "elapsed_time": "3:18:24", "remaining_time": "3:03:15"}
643
+ {"current_steps": 643, "total_steps": 1235, "loss": 0.2591, "lr": 2.2060569825878413e-05, "epoch": 2.603238866396761, "percentage": 52.06, "elapsed_time": "3:18:44", "remaining_time": "3:02:58"}
644
+ {"current_steps": 644, "total_steps": 1235, "loss": 0.2751, "lr": 2.2004308298703777e-05, "epoch": 2.6072874493927127, "percentage": 52.15, "elapsed_time": "3:19:03", "remaining_time": "3:02:40"}
645
+ {"current_steps": 645, "total_steps": 1235, "loss": 0.2317, "lr": 2.1948030745133396e-05, "epoch": 2.611336032388664, "percentage": 52.23, "elapsed_time": "3:19:17", "remaining_time": "3:02:17"}
646
+ {"current_steps": 646, "total_steps": 1235, "loss": 0.2364, "lr": 2.1891737615161083e-05, "epoch": 2.6153846153846154, "percentage": 52.31, "elapsed_time": "3:19:38", "remaining_time": "3:02:01"}
647
+ {"current_steps": 647, "total_steps": 1235, "loss": 0.2503, "lr": 2.1835429358905218e-05, "epoch": 2.619433198380567, "percentage": 52.39, "elapsed_time": "3:19:57", "remaining_time": "3:01:43"}
648
+ {"current_steps": 648, "total_steps": 1235, "loss": 0.2593, "lr": 2.17791064266051e-05, "epoch": 2.623481781376518, "percentage": 52.47, "elapsed_time": "3:20:14", "remaining_time": "3:01:23"}
649
+ {"current_steps": 649, "total_steps": 1235, "loss": 0.2562, "lr": 2.172276926861741e-05, "epoch": 2.6275303643724697, "percentage": 52.55, "elapsed_time": "3:20:32", "remaining_time": "3:01:04"}
650
+ {"current_steps": 650, "total_steps": 1235, "loss": 0.255, "lr": 2.166641833541255e-05, "epoch": 2.6315789473684212, "percentage": 52.63, "elapsed_time": "3:20:53", "remaining_time": "3:00:48"}
651
+ {"current_steps": 651, "total_steps": 1235, "loss": 0.253, "lr": 2.161005407757109e-05, "epoch": 2.6356275303643724, "percentage": 52.71, "elapsed_time": "3:21:13", "remaining_time": "3:00:30"}
652
+ {"current_steps": 652, "total_steps": 1235, "loss": 0.2549, "lr": 2.155367694578013e-05, "epoch": 2.639676113360324, "percentage": 52.79, "elapsed_time": "3:21:31", "remaining_time": "3:00:11"}
653
+ {"current_steps": 653, "total_steps": 1235, "loss": 0.2369, "lr": 2.1497287390829712e-05, "epoch": 2.6437246963562755, "percentage": 52.87, "elapsed_time": "3:21:46", "remaining_time": "2:59:50"}
654
+ {"current_steps": 654, "total_steps": 1235, "loss": 0.2303, "lr": 2.1440885863609208e-05, "epoch": 2.6477732793522266, "percentage": 52.96, "elapsed_time": "3:22:05", "remaining_time": "2:59:32"}
655
+ {"current_steps": 655, "total_steps": 1235, "loss": 0.2496, "lr": 2.1384472815103737e-05, "epoch": 2.651821862348178, "percentage": 53.04, "elapsed_time": "3:22:26", "remaining_time": "2:59:15"}
656
+ {"current_steps": 656, "total_steps": 1235, "loss": 0.2455, "lr": 2.1328048696390534e-05, "epoch": 2.6558704453441297, "percentage": 53.12, "elapsed_time": "3:22:43", "remaining_time": "2:58:55"}
657
+ {"current_steps": 657, "total_steps": 1235, "loss": 0.2506, "lr": 2.1271613958635342e-05, "epoch": 2.659919028340081, "percentage": 53.2, "elapsed_time": "3:23:02", "remaining_time": "2:58:37"}
658
+ {"current_steps": 658, "total_steps": 1235, "loss": 0.2459, "lr": 2.1215169053088825e-05, "epoch": 2.6639676113360324, "percentage": 53.28, "elapsed_time": "3:23:22", "remaining_time": "2:58:20"}
659
+ {"current_steps": 659, "total_steps": 1235, "loss": 0.2397, "lr": 2.1158714431082937e-05, "epoch": 2.668016194331984, "percentage": 53.36, "elapsed_time": "3:23:39", "remaining_time": "2:58:00"}
660
+ {"current_steps": 660, "total_steps": 1235, "loss": 0.2313, "lr": 2.110225054402733e-05, "epoch": 2.672064777327935, "percentage": 53.44, "elapsed_time": "3:23:55", "remaining_time": "2:57:39"}
661
+ {"current_steps": 661, "total_steps": 1235, "loss": 0.2899, "lr": 2.1045777843405747e-05, "epoch": 2.6761133603238867, "percentage": 53.52, "elapsed_time": "3:24:15", "remaining_time": "2:57:22"}
662
+ {"current_steps": 662, "total_steps": 1235, "loss": 0.2471, "lr": 2.09892967807724e-05, "epoch": 2.6801619433198383, "percentage": 53.6, "elapsed_time": "3:24:35", "remaining_time": "2:57:05"}
663
+ {"current_steps": 663, "total_steps": 1235, "loss": 0.2342, "lr": 2.093280780774835e-05, "epoch": 2.6842105263157894, "percentage": 53.68, "elapsed_time": "3:24:55", "remaining_time": "2:56:47"}
664
+ {"current_steps": 664, "total_steps": 1235, "loss": 0.2462, "lr": 2.087631137601793e-05, "epoch": 2.688259109311741, "percentage": 53.77, "elapsed_time": "3:25:10", "remaining_time": "2:56:26"}
665
+ {"current_steps": 665, "total_steps": 1235, "loss": 0.2507, "lr": 2.0819807937325104e-05, "epoch": 2.6923076923076925, "percentage": 53.85, "elapsed_time": "3:25:27", "remaining_time": "2:56:06"}
666
+ {"current_steps": 666, "total_steps": 1235, "loss": 0.2364, "lr": 2.0763297943469847e-05, "epoch": 2.6963562753036436, "percentage": 53.93, "elapsed_time": "3:25:47", "remaining_time": "2:55:49"}
667
+ {"current_steps": 667, "total_steps": 1235, "loss": 0.2646, "lr": 2.070678184630458e-05, "epoch": 2.700404858299595, "percentage": 54.01, "elapsed_time": "3:26:07", "remaining_time": "2:55:31"}
668
+ {"current_steps": 668, "total_steps": 1235, "loss": 0.2599, "lr": 2.06502600977305e-05, "epoch": 2.7044534412955468, "percentage": 54.09, "elapsed_time": "3:26:24", "remaining_time": "2:55:11"}
669
+ {"current_steps": 669, "total_steps": 1235, "loss": 0.2695, "lr": 2.0593733149694008e-05, "epoch": 2.708502024291498, "percentage": 54.17, "elapsed_time": "3:26:43", "remaining_time": "2:54:53"}
670
+ {"current_steps": 670, "total_steps": 1235, "loss": 0.2554, "lr": 2.0537201454183074e-05, "epoch": 2.7125506072874495, "percentage": 54.25, "elapsed_time": "3:27:01", "remaining_time": "2:54:34"}
671
+ {"current_steps": 671, "total_steps": 1235, "loss": 0.2407, "lr": 2.0480665463223626e-05, "epoch": 2.716599190283401, "percentage": 54.33, "elapsed_time": "3:27:21", "remaining_time": "2:54:17"}
672
+ {"current_steps": 672, "total_steps": 1235, "loss": 0.245, "lr": 2.042412562887594e-05, "epoch": 2.720647773279352, "percentage": 54.41, "elapsed_time": "3:27:36", "remaining_time": "2:53:56"}
673
+ {"current_steps": 673, "total_steps": 1235, "loss": 0.2447, "lr": 2.0367582403231033e-05, "epoch": 2.7246963562753037, "percentage": 54.49, "elapsed_time": "3:27:55", "remaining_time": "2:53:38"}
674
+ {"current_steps": 674, "total_steps": 1235, "loss": 0.2424, "lr": 2.0311036238407023e-05, "epoch": 2.7287449392712553, "percentage": 54.57, "elapsed_time": "3:28:12", "remaining_time": "2:53:18"}
675
+ {"current_steps": 675, "total_steps": 1235, "loss": 0.2628, "lr": 2.0254487586545534e-05, "epoch": 2.7327935222672064, "percentage": 54.66, "elapsed_time": "3:28:32", "remaining_time": "2:53:01"}
676
+ {"current_steps": 676, "total_steps": 1235, "loss": 0.2566, "lr": 2.0197936899808088e-05, "epoch": 2.736842105263158, "percentage": 54.74, "elapsed_time": "3:28:54", "remaining_time": "2:52:44"}
677
+ {"current_steps": 677, "total_steps": 1235, "loss": 0.2335, "lr": 2.0141384630372466e-05, "epoch": 2.7408906882591095, "percentage": 54.82, "elapsed_time": "3:29:15", "remaining_time": "2:52:28"}
678
+ {"current_steps": 678, "total_steps": 1235, "loss": 0.2397, "lr": 2.0084831230429106e-05, "epoch": 2.7449392712550607, "percentage": 54.9, "elapsed_time": "3:29:27", "remaining_time": "2:52:04"}
679
+ {"current_steps": 679, "total_steps": 1235, "loss": 0.249, "lr": 2.0028277152177492e-05, "epoch": 2.748987854251012, "percentage": 54.98, "elapsed_time": "3:29:45", "remaining_time": "2:51:45"}
680
+ {"current_steps": 680, "total_steps": 1235, "loss": 0.2429, "lr": 1.9971722847822518e-05, "epoch": 2.753036437246964, "percentage": 55.06, "elapsed_time": "3:29:59", "remaining_time": "2:51:23"}
681
+ {"current_steps": 681, "total_steps": 1235, "loss": 0.2605, "lr": 1.99151687695709e-05, "epoch": 2.757085020242915, "percentage": 55.14, "elapsed_time": "3:30:18", "remaining_time": "2:51:05"}
682
+ {"current_steps": 682, "total_steps": 1235, "loss": 0.2521, "lr": 1.9858615369627537e-05, "epoch": 2.7611336032388665, "percentage": 55.22, "elapsed_time": "3:30:34", "remaining_time": "2:50:44"}
683
+ {"current_steps": 683, "total_steps": 1235, "loss": 0.2511, "lr": 1.9802063100191916e-05, "epoch": 2.765182186234818, "percentage": 55.3, "elapsed_time": "3:30:52", "remaining_time": "2:50:25"}
684
+ {"current_steps": 684, "total_steps": 1235, "loss": 0.2793, "lr": 1.974551241345447e-05, "epoch": 2.769230769230769, "percentage": 55.38, "elapsed_time": "3:31:11", "remaining_time": "2:50:07"}
685
+ {"current_steps": 685, "total_steps": 1235, "loss": 0.2479, "lr": 1.9688963761592984e-05, "epoch": 2.7732793522267207, "percentage": 55.47, "elapsed_time": "3:31:31", "remaining_time": "2:49:50"}
686
+ {"current_steps": 686, "total_steps": 1235, "loss": 0.2461, "lr": 1.963241759676897e-05, "epoch": 2.7773279352226723, "percentage": 55.55, "elapsed_time": "3:31:47", "remaining_time": "2:49:29"}
687
+ {"current_steps": 687, "total_steps": 1235, "loss": 0.2522, "lr": 1.9575874371124066e-05, "epoch": 2.7813765182186234, "percentage": 55.63, "elapsed_time": "3:32:08", "remaining_time": "2:49:12"}
688
+ {"current_steps": 688, "total_steps": 1235, "loss": 0.249, "lr": 1.951933453677638e-05, "epoch": 2.785425101214575, "percentage": 55.71, "elapsed_time": "3:32:27", "remaining_time": "2:48:54"}
689
+ {"current_steps": 689, "total_steps": 1235, "loss": 0.2357, "lr": 1.9462798545816932e-05, "epoch": 2.7894736842105265, "percentage": 55.79, "elapsed_time": "3:32:48", "remaining_time": "2:48:38"}
690
+ {"current_steps": 690, "total_steps": 1235, "loss": 0.236, "lr": 1.9406266850305996e-05, "epoch": 2.7935222672064777, "percentage": 55.87, "elapsed_time": "3:33:07", "remaining_time": "2:48:20"}
691
+ {"current_steps": 691, "total_steps": 1235, "loss": 0.2373, "lr": 1.9349739902269503e-05, "epoch": 2.7975708502024292, "percentage": 55.95, "elapsed_time": "3:33:23", "remaining_time": "2:47:59"}
692
+ {"current_steps": 692, "total_steps": 1235, "loss": 0.2467, "lr": 1.9293218153695425e-05, "epoch": 2.801619433198381, "percentage": 56.03, "elapsed_time": "3:33:41", "remaining_time": "2:47:40"}
693
+ {"current_steps": 693, "total_steps": 1235, "loss": 0.2676, "lr": 1.9236702056530153e-05, "epoch": 2.805668016194332, "percentage": 56.11, "elapsed_time": "3:34:02", "remaining_time": "2:47:24"}
694
+ {"current_steps": 694, "total_steps": 1235, "loss": 0.2528, "lr": 1.9180192062674907e-05, "epoch": 2.8097165991902835, "percentage": 56.19, "elapsed_time": "3:34:22", "remaining_time": "2:47:06"}
695
+ {"current_steps": 695, "total_steps": 1235, "loss": 0.2595, "lr": 1.9123688623982076e-05, "epoch": 2.813765182186235, "percentage": 56.28, "elapsed_time": "3:34:38", "remaining_time": "2:46:46"}
696
+ {"current_steps": 696, "total_steps": 1235, "loss": 0.2482, "lr": 1.906719219225165e-05, "epoch": 2.817813765182186, "percentage": 56.36, "elapsed_time": "3:34:54", "remaining_time": "2:46:25"}
697
+ {"current_steps": 697, "total_steps": 1235, "loss": 0.2329, "lr": 1.9010703219227603e-05, "epoch": 2.8218623481781377, "percentage": 56.44, "elapsed_time": "3:35:09", "remaining_time": "2:46:04"}
698
+ {"current_steps": 698, "total_steps": 1235, "loss": 0.2556, "lr": 1.8954222156594256e-05, "epoch": 2.8259109311740893, "percentage": 56.52, "elapsed_time": "3:35:30", "remaining_time": "2:45:47"}
699
+ {"current_steps": 699, "total_steps": 1235, "loss": 0.262, "lr": 1.8897749455972673e-05, "epoch": 2.8299595141700404, "percentage": 56.6, "elapsed_time": "3:35:49", "remaining_time": "2:45:29"}
700
+ {"current_steps": 700, "total_steps": 1235, "loss": 0.2387, "lr": 1.884128556891707e-05, "epoch": 2.834008097165992, "percentage": 56.68, "elapsed_time": "3:36:09", "remaining_time": "2:45:12"}
701
+ {"current_steps": 701, "total_steps": 1235, "loss": 0.2323, "lr": 1.878483094691119e-05, "epoch": 2.8380566801619436, "percentage": 56.76, "elapsed_time": "3:36:31", "remaining_time": "2:44:56"}
702
+ {"current_steps": 702, "total_steps": 1235, "loss": 0.2664, "lr": 1.8728386041364664e-05, "epoch": 2.8421052631578947, "percentage": 56.84, "elapsed_time": "3:36:47", "remaining_time": "2:44:36"}
703
+ {"current_steps": 703, "total_steps": 1235, "loss": 0.2376, "lr": 1.867195130360947e-05, "epoch": 2.8461538461538463, "percentage": 56.92, "elapsed_time": "3:37:04", "remaining_time": "2:44:16"}
704
+ {"current_steps": 704, "total_steps": 1235, "loss": 0.2389, "lr": 1.8615527184896263e-05, "epoch": 2.850202429149798, "percentage": 57.0, "elapsed_time": "3:37:20", "remaining_time": "2:43:55"}
705
+ {"current_steps": 705, "total_steps": 1235, "loss": 0.2456, "lr": 1.8559114136390795e-05, "epoch": 2.854251012145749, "percentage": 57.09, "elapsed_time": "3:37:37", "remaining_time": "2:43:35"}
706
+ {"current_steps": 706, "total_steps": 1235, "loss": 0.247, "lr": 1.8502712609170298e-05, "epoch": 2.8582995951417005, "percentage": 57.17, "elapsed_time": "3:37:56", "remaining_time": "2:43:17"}
707
+ {"current_steps": 707, "total_steps": 1235, "loss": 0.2458, "lr": 1.8446323054219876e-05, "epoch": 2.862348178137652, "percentage": 57.25, "elapsed_time": "3:38:16", "remaining_time": "2:43:00"}
708
+ {"current_steps": 708, "total_steps": 1235, "loss": 0.2431, "lr": 1.838994592242891e-05, "epoch": 2.866396761133603, "percentage": 57.33, "elapsed_time": "3:38:31", "remaining_time": "2:42:39"}
709
+ {"current_steps": 709, "total_steps": 1235, "loss": 0.2309, "lr": 1.8333581664587453e-05, "epoch": 2.8704453441295548, "percentage": 57.41, "elapsed_time": "3:38:50", "remaining_time": "2:42:21"}
710
+ {"current_steps": 710, "total_steps": 1235, "loss": 0.2417, "lr": 1.8277230731382593e-05, "epoch": 2.8744939271255063, "percentage": 57.49, "elapsed_time": "3:39:05", "remaining_time": "2:42:00"}
711
+ {"current_steps": 711, "total_steps": 1235, "loss": 0.2542, "lr": 1.82208935733949e-05, "epoch": 2.8785425101214575, "percentage": 57.57, "elapsed_time": "3:39:22", "remaining_time": "2:41:40"}
712
+ {"current_steps": 712, "total_steps": 1235, "loss": 0.2374, "lr": 1.8164570641094793e-05, "epoch": 2.882591093117409, "percentage": 57.65, "elapsed_time": "3:39:41", "remaining_time": "2:41:22"}
713
+ {"current_steps": 713, "total_steps": 1235, "loss": 0.241, "lr": 1.810826238483892e-05, "epoch": 2.8866396761133606, "percentage": 57.73, "elapsed_time": "3:40:00", "remaining_time": "2:41:04"}
714
+ {"current_steps": 714, "total_steps": 1235, "loss": 0.263, "lr": 1.8051969254866608e-05, "epoch": 2.8906882591093117, "percentage": 57.81, "elapsed_time": "3:40:17", "remaining_time": "2:40:44"}
715
+ {"current_steps": 715, "total_steps": 1235, "loss": 0.2415, "lr": 1.7995691701296226e-05, "epoch": 2.8947368421052633, "percentage": 57.89, "elapsed_time": "3:40:37", "remaining_time": "2:40:27"}
716
+ {"current_steps": 716, "total_steps": 1235, "loss": 0.2437, "lr": 1.7939430174121593e-05, "epoch": 2.898785425101215, "percentage": 57.98, "elapsed_time": "3:40:54", "remaining_time": "2:40:07"}
717
+ {"current_steps": 717, "total_steps": 1235, "loss": 0.2298, "lr": 1.788318512320838e-05, "epoch": 2.902834008097166, "percentage": 58.06, "elapsed_time": "3:41:08", "remaining_time": "2:39:45"}
718
+ {"current_steps": 718, "total_steps": 1235, "loss": 0.2412, "lr": 1.782695699829051e-05, "epoch": 2.9068825910931175, "percentage": 58.14, "elapsed_time": "3:41:27", "remaining_time": "2:39:27"}
719
+ {"current_steps": 719, "total_steps": 1235, "loss": 0.2521, "lr": 1.7770746248966587e-05, "epoch": 2.910931174089069, "percentage": 58.22, "elapsed_time": "3:41:48", "remaining_time": "2:39:10"}
720
+ {"current_steps": 720, "total_steps": 1235, "loss": 0.2394, "lr": 1.7714553324696243e-05, "epoch": 2.91497975708502, "percentage": 58.3, "elapsed_time": "3:42:05", "remaining_time": "2:38:51"}
721
+ {"current_steps": 721, "total_steps": 1235, "loss": 0.2427, "lr": 1.7658378674796614e-05, "epoch": 2.919028340080972, "percentage": 58.38, "elapsed_time": "3:42:25", "remaining_time": "2:38:34"}
722
+ {"current_steps": 722, "total_steps": 1235, "loss": 0.2357, "lr": 1.76022227484387e-05, "epoch": 2.9230769230769234, "percentage": 58.46, "elapsed_time": "3:42:45", "remaining_time": "2:38:16"}
723
+ {"current_steps": 723, "total_steps": 1235, "loss": 0.2605, "lr": 1.7546085994643807e-05, "epoch": 2.9271255060728745, "percentage": 58.54, "elapsed_time": "3:43:01", "remaining_time": "2:37:56"}
724
+ {"current_steps": 724, "total_steps": 1235, "loss": 0.2439, "lr": 1.7489968862279902e-05, "epoch": 2.931174089068826, "percentage": 58.62, "elapsed_time": "3:43:21", "remaining_time": "2:37:38"}
725
+ {"current_steps": 725, "total_steps": 1235, "loss": 0.2433, "lr": 1.743387180005809e-05, "epoch": 2.9352226720647776, "percentage": 58.7, "elapsed_time": "3:43:37", "remaining_time": "2:37:18"}
726
+ {"current_steps": 726, "total_steps": 1235, "loss": 0.2393, "lr": 1.737779525652899e-05, "epoch": 2.9392712550607287, "percentage": 58.79, "elapsed_time": "3:43:56", "remaining_time": "2:37:00"}
727
+ {"current_steps": 727, "total_steps": 1235, "loss": 0.2555, "lr": 1.732173968007914e-05, "epoch": 2.9433198380566803, "percentage": 58.87, "elapsed_time": "3:44:15", "remaining_time": "2:36:41"}
728
+ {"current_steps": 728, "total_steps": 1235, "loss": 0.2346, "lr": 1.7265705518927437e-05, "epoch": 2.9473684210526314, "percentage": 58.95, "elapsed_time": "3:44:29", "remaining_time": "2:36:20"}
729
+ {"current_steps": 729, "total_steps": 1235, "loss": 0.2698, "lr": 1.7209693221121542e-05, "epoch": 2.951417004048583, "percentage": 59.03, "elapsed_time": "3:44:48", "remaining_time": "2:36:02"}
730
+ {"current_steps": 730, "total_steps": 1235, "loss": 0.2598, "lr": 1.7153703234534302e-05, "epoch": 2.9554655870445345, "percentage": 59.11, "elapsed_time": "3:45:06", "remaining_time": "2:35:43"}
731
+ {"current_steps": 731, "total_steps": 1235, "loss": 0.2478, "lr": 1.709773600686015e-05, "epoch": 2.9595141700404857, "percentage": 59.19, "elapsed_time": "3:45:25", "remaining_time": "2:35:25"}
732
+ {"current_steps": 732, "total_steps": 1235, "loss": 0.2532, "lr": 1.7041791985611548e-05, "epoch": 2.9635627530364372, "percentage": 59.27, "elapsed_time": "3:45:43", "remaining_time": "2:35:06"}
733
+ {"current_steps": 733, "total_steps": 1235, "loss": 0.2424, "lr": 1.69858716181154e-05, "epoch": 2.967611336032389, "percentage": 59.35, "elapsed_time": "3:46:02", "remaining_time": "2:34:48"}
734
+ {"current_steps": 734, "total_steps": 1235, "loss": 0.2581, "lr": 1.692997535150948e-05, "epoch": 2.97165991902834, "percentage": 59.43, "elapsed_time": "3:46:24", "remaining_time": "2:34:32"}
735
+ {"current_steps": 735, "total_steps": 1235, "loss": 0.2238, "lr": 1.687410363273884e-05, "epoch": 2.9757085020242915, "percentage": 59.51, "elapsed_time": "3:46:41", "remaining_time": "2:34:12"}
736
+ {"current_steps": 736, "total_steps": 1235, "loss": 0.2276, "lr": 1.6818256908552257e-05, "epoch": 2.979757085020243, "percentage": 59.6, "elapsed_time": "3:47:01", "remaining_time": "2:33:54"}
737
+ {"current_steps": 737, "total_steps": 1235, "loss": 0.2399, "lr": 1.6762435625498646e-05, "epoch": 2.983805668016194, "percentage": 59.68, "elapsed_time": "3:47:18", "remaining_time": "2:33:35"}
738
+ {"current_steps": 738, "total_steps": 1235, "loss": 0.2252, "lr": 1.67066402299235e-05, "epoch": 2.9878542510121457, "percentage": 59.76, "elapsed_time": "3:47:36", "remaining_time": "2:33:16"}
739
+ {"current_steps": 739, "total_steps": 1235, "loss": 0.2624, "lr": 1.6650871167965313e-05, "epoch": 2.9919028340080973, "percentage": 59.84, "elapsed_time": "3:47:56", "remaining_time": "2:32:59"}
740
+ {"current_steps": 740, "total_steps": 1235, "loss": 0.2363, "lr": 1.6595128885552028e-05, "epoch": 2.9959514170040484, "percentage": 59.92, "elapsed_time": "3:48:13", "remaining_time": "2:32:39"}
741
+ {"current_steps": 741, "total_steps": 1235, "loss": 0.2534, "lr": 1.653941382839745e-05, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "3:48:33", "remaining_time": "2:32:22"}
742
+ {"current_steps": 742, "total_steps": 1235, "loss": 0.1837, "lr": 1.6483726441997673e-05, "epoch": 3.0040485829959516, "percentage": 60.08, "elapsed_time": "3:50:42", "remaining_time": "2:33:16"}
743
+ {"current_steps": 743, "total_steps": 1235, "loss": 0.1723, "lr": 1.642806717162757e-05, "epoch": 3.0080971659919027, "percentage": 60.16, "elapsed_time": "3:51:00", "remaining_time": "2:32:58"}
744
+ {"current_steps": 744, "total_steps": 1235, "loss": 0.1763, "lr": 1.637243646233718e-05, "epoch": 3.0121457489878543, "percentage": 60.24, "elapsed_time": "3:51:17", "remaining_time": "2:32:38"}
745
+ {"current_steps": 745, "total_steps": 1235, "loss": 0.186, "lr": 1.6316834758948174e-05, "epoch": 3.016194331983806, "percentage": 60.32, "elapsed_time": "3:51:36", "remaining_time": "2:32:20"}
746
+ {"current_steps": 746, "total_steps": 1235, "loss": 0.1967, "lr": 1.6261262506050282e-05, "epoch": 3.020242914979757, "percentage": 60.4, "elapsed_time": "3:51:52", "remaining_time": "2:31:59"}
747
+ {"current_steps": 747, "total_steps": 1235, "loss": 0.1674, "lr": 1.620572014799777e-05, "epoch": 3.0242914979757085, "percentage": 60.49, "elapsed_time": "3:52:08", "remaining_time": "2:31:39"}
748
+ {"current_steps": 748, "total_steps": 1235, "loss": 0.1726, "lr": 1.6150208128905857e-05, "epoch": 3.02834008097166, "percentage": 60.57, "elapsed_time": "3:52:27", "remaining_time": "2:31:21"}
749
+ {"current_steps": 749, "total_steps": 1235, "loss": 0.1743, "lr": 1.6094726892647147e-05, "epoch": 3.032388663967611, "percentage": 60.65, "elapsed_time": "3:52:44", "remaining_time": "2:31:00"}
750
+ {"current_steps": 750, "total_steps": 1235, "loss": 0.1811, "lr": 1.6039276882848135e-05, "epoch": 3.0364372469635628, "percentage": 60.73, "elapsed_time": "3:53:04", "remaining_time": "2:30:43"}
751
+ {"current_steps": 751, "total_steps": 1235, "loss": 0.1487, "lr": 1.5983858542885635e-05, "epoch": 3.0404858299595143, "percentage": 60.81, "elapsed_time": "3:53:21", "remaining_time": "2:30:23"}