neginr commited on
Commit
a70afeb
·
verified ·
1 Parent(s): 01c6013

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:b4aa61ab6a44fe73c399640cebfea00362e29546cb19975e35913578e5f5e085
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e644927c722a3579a45da0e2d6da2443061822607c690f7260a6c52202da063a
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86a996ed860120a0f14f4108f9eba73a8b42c966fdd5324f8d25abc1eee6f929
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ece6b58ff49a0bd4a32209d731dc18d7b059d1783e795da2e192d0fe949e93ff
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:efd24a70310a4743204b1b7ccf0337cb49854e056fc81d08224c92c50e321a58
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60f1c43f40d65da231c12800816126fe33001cce95a087e6f2144936824e33bf
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22d904a065b6cae2aae693d0febfc23279009d5ff290596cc9450fdb5b547bec
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba6905da278e9861b66aae1e8b4a73ab5898fe2e8428883bd36a183d606ca046
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -502,3 +502,249 @@
502
  {"current_steps": 502, "total_steps": 1235, "loss": 0.2266, "lr": 2.9622185557068238e-05, "epoch": 2.032388663967611, "percentage": 40.65, "elapsed_time": "2:19:39", "remaining_time": "3:23:55"}
503
  {"current_steps": 503, "total_steps": 1235, "loss": 0.2181, "lr": 2.95725682050846e-05, "epoch": 2.0364372469635628, "percentage": 40.73, "elapsed_time": "2:19:54", "remaining_time": "3:23:36"}
504
  {"current_steps": 504, "total_steps": 1235, "loss": 0.2281, "lr": 2.9522874311100684e-05, "epoch": 2.0404858299595143, "percentage": 40.81, "elapsed_time": "2:20:12", "remaining_time": "3:23:21"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
502
  {"current_steps": 502, "total_steps": 1235, "loss": 0.2266, "lr": 2.9622185557068238e-05, "epoch": 2.032388663967611, "percentage": 40.65, "elapsed_time": "2:19:39", "remaining_time": "3:23:55"}
503
  {"current_steps": 503, "total_steps": 1235, "loss": 0.2181, "lr": 2.95725682050846e-05, "epoch": 2.0364372469635628, "percentage": 40.73, "elapsed_time": "2:19:54", "remaining_time": "3:23:36"}
504
  {"current_steps": 504, "total_steps": 1235, "loss": 0.2281, "lr": 2.9522874311100684e-05, "epoch": 2.0404858299595143, "percentage": 40.81, "elapsed_time": "2:20:12", "remaining_time": "3:23:21"}
505
+ {"current_steps": 505, "total_steps": 1235, "loss": 0.2136, "lr": 2.9473104272467526e-05, "epoch": 2.0445344129554655, "percentage": 40.89, "elapsed_time": "2:20:32", "remaining_time": "3:23:08"}
506
+ {"current_steps": 506, "total_steps": 1235, "loss": 0.208, "lr": 2.942325848714505e-05, "epoch": 2.048582995951417, "percentage": 40.97, "elapsed_time": "2:20:47", "remaining_time": "3:22:49"}
507
+ {"current_steps": 507, "total_steps": 1235, "loss": 0.2075, "lr": 2.9373337353698804e-05, "epoch": 2.0526315789473686, "percentage": 41.05, "elapsed_time": "2:21:02", "remaining_time": "3:22:31"}
508
+ {"current_steps": 508, "total_steps": 1235, "loss": 0.2234, "lr": 2.932334127129686e-05, "epoch": 2.0566801619433197, "percentage": 41.13, "elapsed_time": "2:21:21", "remaining_time": "3:22:17"}
509
+ {"current_steps": 509, "total_steps": 1235, "loss": 0.2178, "lr": 2.9273270639706547e-05, "epoch": 2.0607287449392713, "percentage": 41.21, "elapsed_time": "2:21:37", "remaining_time": "3:22:00"}
510
+ {"current_steps": 510, "total_steps": 1235, "loss": 0.2135, "lr": 2.922312585929131e-05, "epoch": 2.064777327935223, "percentage": 41.3, "elapsed_time": "2:21:51", "remaining_time": "3:21:39"}
511
+ {"current_steps": 511, "total_steps": 1235, "loss": 0.2324, "lr": 2.9172907331007478e-05, "epoch": 2.068825910931174, "percentage": 41.38, "elapsed_time": "2:22:06", "remaining_time": "3:21:20"}
512
+ {"current_steps": 512, "total_steps": 1235, "loss": 0.2252, "lr": 2.9122615456401053e-05, "epoch": 2.0728744939271255, "percentage": 41.46, "elapsed_time": "2:22:23", "remaining_time": "3:21:04"}
513
+ {"current_steps": 513, "total_steps": 1235, "loss": 0.2269, "lr": 2.9072250637604535e-05, "epoch": 2.076923076923077, "percentage": 41.54, "elapsed_time": "2:22:39", "remaining_time": "3:20:46"}
514
+ {"current_steps": 514, "total_steps": 1235, "loss": 0.2106, "lr": 2.9021813277333667e-05, "epoch": 2.080971659919028, "percentage": 41.62, "elapsed_time": "2:22:55", "remaining_time": "3:20:29"}
515
+ {"current_steps": 515, "total_steps": 1235, "loss": 0.2115, "lr": 2.8971303778884244e-05, "epoch": 2.08502024291498, "percentage": 41.7, "elapsed_time": "2:23:09", "remaining_time": "3:20:08"}
516
+ {"current_steps": 516, "total_steps": 1235, "loss": 0.2327, "lr": 2.8920722546128863e-05, "epoch": 2.0890688259109313, "percentage": 41.78, "elapsed_time": "2:23:28", "remaining_time": "3:19:55"}
517
+ {"current_steps": 517, "total_steps": 1235, "loss": 0.2197, "lr": 2.887006998351372e-05, "epoch": 2.0931174089068825, "percentage": 41.86, "elapsed_time": "2:23:42", "remaining_time": "3:19:34"}
518
+ {"current_steps": 518, "total_steps": 1235, "loss": 0.2214, "lr": 2.881934649605535e-05, "epoch": 2.097165991902834, "percentage": 41.94, "elapsed_time": "2:23:59", "remaining_time": "3:19:19"}
519
+ {"current_steps": 519, "total_steps": 1235, "loss": 0.2091, "lr": 2.8768552489337408e-05, "epoch": 2.1012145748987856, "percentage": 42.02, "elapsed_time": "2:24:13", "remaining_time": "3:18:57"}
520
+ {"current_steps": 520, "total_steps": 1235, "loss": 0.2128, "lr": 2.8717688369507425e-05, "epoch": 2.1052631578947367, "percentage": 42.11, "elapsed_time": "2:24:26", "remaining_time": "3:18:35"}
521
+ {"current_steps": 521, "total_steps": 1235, "loss": 0.2215, "lr": 2.8666754543273535e-05, "epoch": 2.1093117408906883, "percentage": 42.19, "elapsed_time": "2:24:43", "remaining_time": "3:18:19"}
522
+ {"current_steps": 522, "total_steps": 1235, "loss": 0.2265, "lr": 2.8615751417901273e-05, "epoch": 2.11336032388664, "percentage": 42.27, "elapsed_time": "2:24:59", "remaining_time": "3:18:02"}
523
+ {"current_steps": 523, "total_steps": 1235, "loss": 0.2133, "lr": 2.856467940121025e-05, "epoch": 2.117408906882591, "percentage": 42.35, "elapsed_time": "2:25:17", "remaining_time": "3:17:47"}
524
+ {"current_steps": 524, "total_steps": 1235, "loss": 0.2192, "lr": 2.8513538901570964e-05, "epoch": 2.1214574898785425, "percentage": 42.43, "elapsed_time": "2:25:35", "remaining_time": "3:17:32"}
525
+ {"current_steps": 525, "total_steps": 1235, "loss": 0.2131, "lr": 2.846233032790149e-05, "epoch": 2.125506072874494, "percentage": 42.51, "elapsed_time": "2:25:50", "remaining_time": "3:17:13"}
526
+ {"current_steps": 526, "total_steps": 1235, "loss": 0.2151, "lr": 2.84110540896642e-05, "epoch": 2.1295546558704452, "percentage": 42.59, "elapsed_time": "2:26:07", "remaining_time": "3:16:57"}
527
+ {"current_steps": 527, "total_steps": 1235, "loss": 0.2106, "lr": 2.8359710596862555e-05, "epoch": 2.133603238866397, "percentage": 42.67, "elapsed_time": "2:26:22", "remaining_time": "3:16:39"}
528
+ {"current_steps": 528, "total_steps": 1235, "loss": 0.2191, "lr": 2.8308300260037734e-05, "epoch": 2.1376518218623484, "percentage": 42.75, "elapsed_time": "2:26:40", "remaining_time": "3:16:23"}
529
+ {"current_steps": 529, "total_steps": 1235, "loss": 0.2213, "lr": 2.8256823490265424e-05, "epoch": 2.1417004048582995, "percentage": 42.83, "elapsed_time": "2:26:57", "remaining_time": "3:16:07"}
530
+ {"current_steps": 530, "total_steps": 1235, "loss": 0.221, "lr": 2.8205280699152515e-05, "epoch": 2.145748987854251, "percentage": 42.91, "elapsed_time": "2:27:17", "remaining_time": "3:15:55"}
531
+ {"current_steps": 531, "total_steps": 1235, "loss": 0.2202, "lr": 2.8153672298833777e-05, "epoch": 2.1497975708502026, "percentage": 43.0, "elapsed_time": "2:27:33", "remaining_time": "3:15:38"}
532
+ {"current_steps": 532, "total_steps": 1235, "loss": 0.2138, "lr": 2.8101998701968615e-05, "epoch": 2.1538461538461537, "percentage": 43.08, "elapsed_time": "2:27:49", "remaining_time": "3:15:21"}
533
+ {"current_steps": 533, "total_steps": 1235, "loss": 0.2195, "lr": 2.805026032173773e-05, "epoch": 2.1578947368421053, "percentage": 43.16, "elapsed_time": "2:28:04", "remaining_time": "3:15:01"}
534
+ {"current_steps": 534, "total_steps": 1235, "loss": 0.2161, "lr": 2.7998457571839832e-05, "epoch": 2.161943319838057, "percentage": 43.24, "elapsed_time": "2:28:21", "remaining_time": "3:14:45"}
535
+ {"current_steps": 535, "total_steps": 1235, "loss": 0.2144, "lr": 2.7946590866488322e-05, "epoch": 2.165991902834008, "percentage": 43.32, "elapsed_time": "2:28:37", "remaining_time": "3:14:27"}
536
+ {"current_steps": 536, "total_steps": 1235, "loss": 0.2041, "lr": 2.7894660620408e-05, "epoch": 2.1700404858299596, "percentage": 43.4, "elapsed_time": "2:28:51", "remaining_time": "3:14:08"}
537
+ {"current_steps": 537, "total_steps": 1235, "loss": 0.2109, "lr": 2.784266724883173e-05, "epoch": 2.174089068825911, "percentage": 43.48, "elapsed_time": "2:29:08", "remaining_time": "3:13:50"}
538
+ {"current_steps": 538, "total_steps": 1235, "loss": 0.2308, "lr": 2.7790611167497128e-05, "epoch": 2.1781376518218623, "percentage": 43.56, "elapsed_time": "2:29:24", "remaining_time": "3:13:33"}
539
+ {"current_steps": 539, "total_steps": 1235, "loss": 0.2345, "lr": 2.7738492792643224e-05, "epoch": 2.182186234817814, "percentage": 43.64, "elapsed_time": "2:29:41", "remaining_time": "3:13:17"}
540
+ {"current_steps": 540, "total_steps": 1235, "loss": 0.2339, "lr": 2.768631254100716e-05, "epoch": 2.1862348178137654, "percentage": 43.72, "elapsed_time": "2:29:59", "remaining_time": "3:13:02"}
541
+ {"current_steps": 541, "total_steps": 1235, "loss": 0.2205, "lr": 2.7634070829820836e-05, "epoch": 2.1902834008097165, "percentage": 43.81, "elapsed_time": "2:30:14", "remaining_time": "3:12:44"}
542
+ {"current_steps": 542, "total_steps": 1235, "loss": 0.2167, "lr": 2.7581768076807592e-05, "epoch": 2.194331983805668, "percentage": 43.89, "elapsed_time": "2:30:27", "remaining_time": "3:12:22"}
543
+ {"current_steps": 543, "total_steps": 1235, "loss": 0.2083, "lr": 2.7529404700178832e-05, "epoch": 2.1983805668016196, "percentage": 43.97, "elapsed_time": "2:30:45", "remaining_time": "3:12:07"}
544
+ {"current_steps": 544, "total_steps": 1235, "loss": 0.2221, "lr": 2.7476981118630735e-05, "epoch": 2.2024291497975708, "percentage": 44.05, "elapsed_time": "2:31:04", "remaining_time": "3:11:53"}
545
+ {"current_steps": 545, "total_steps": 1235, "loss": 0.2257, "lr": 2.742449775134085e-05, "epoch": 2.2064777327935223, "percentage": 44.13, "elapsed_time": "2:31:22", "remaining_time": "3:11:39"}
546
+ {"current_steps": 546, "total_steps": 1235, "loss": 0.226, "lr": 2.7371955017964788e-05, "epoch": 2.2105263157894735, "percentage": 44.21, "elapsed_time": "2:31:42", "remaining_time": "3:11:25"}
547
+ {"current_steps": 547, "total_steps": 1235, "loss": 0.2227, "lr": 2.7319353338632845e-05, "epoch": 2.214574898785425, "percentage": 44.29, "elapsed_time": "2:31:58", "remaining_time": "3:11:08"}
548
+ {"current_steps": 548, "total_steps": 1235, "loss": 0.203, "lr": 2.7266693133946645e-05, "epoch": 2.2186234817813766, "percentage": 44.37, "elapsed_time": "2:32:14", "remaining_time": "3:10:51"}
549
+ {"current_steps": 549, "total_steps": 1235, "loss": 0.2161, "lr": 2.7213974824975785e-05, "epoch": 2.2226720647773277, "percentage": 44.45, "elapsed_time": "2:32:26", "remaining_time": "3:10:28"}
550
+ {"current_steps": 550, "total_steps": 1235, "loss": 0.2417, "lr": 2.7161198833254464e-05, "epoch": 2.2267206477732793, "percentage": 44.53, "elapsed_time": "2:32:46", "remaining_time": "3:10:16"}
551
+ {"current_steps": 551, "total_steps": 1235, "loss": 0.2344, "lr": 2.7108365580778095e-05, "epoch": 2.230769230769231, "percentage": 44.62, "elapsed_time": "2:33:03", "remaining_time": "3:10:00"}
552
+ {"current_steps": 552, "total_steps": 1235, "loss": 0.2279, "lr": 2.705547548999996e-05, "epoch": 2.234817813765182, "percentage": 44.7, "elapsed_time": "2:33:25", "remaining_time": "3:09:49"}
553
+ {"current_steps": 553, "total_steps": 1235, "loss": 0.2074, "lr": 2.7002528983827817e-05, "epoch": 2.2388663967611335, "percentage": 44.78, "elapsed_time": "2:33:45", "remaining_time": "3:09:37"}
554
+ {"current_steps": 554, "total_steps": 1235, "loss": 0.218, "lr": 2.6949526485620517e-05, "epoch": 2.242914979757085, "percentage": 44.86, "elapsed_time": "2:34:01", "remaining_time": "3:09:20"}
555
+ {"current_steps": 555, "total_steps": 1235, "loss": 0.2069, "lr": 2.6896468419184623e-05, "epoch": 2.246963562753036, "percentage": 44.94, "elapsed_time": "2:34:19", "remaining_time": "3:09:04"}
556
+ {"current_steps": 556, "total_steps": 1235, "loss": 0.2216, "lr": 2.6843355208771024e-05, "epoch": 2.251012145748988, "percentage": 45.02, "elapsed_time": "2:34:36", "remaining_time": "3:08:48"}
557
+ {"current_steps": 557, "total_steps": 1235, "loss": 0.2057, "lr": 2.6790187279071536e-05, "epoch": 2.2550607287449393, "percentage": 45.1, "elapsed_time": "2:34:52", "remaining_time": "3:08:30"}
558
+ {"current_steps": 558, "total_steps": 1235, "loss": 0.2281, "lr": 2.67369650552155e-05, "epoch": 2.2591093117408905, "percentage": 45.18, "elapsed_time": "2:35:10", "remaining_time": "3:08:15"}
559
+ {"current_steps": 559, "total_steps": 1235, "loss": 0.2201, "lr": 2.6683688962766407e-05, "epoch": 2.263157894736842, "percentage": 45.26, "elapsed_time": "2:35:26", "remaining_time": "3:07:58"}
560
+ {"current_steps": 560, "total_steps": 1235, "loss": 0.22, "lr": 2.6630359427718468e-05, "epoch": 2.2672064777327936, "percentage": 45.34, "elapsed_time": "2:35:44", "remaining_time": "3:07:43"}
561
+ {"current_steps": 561, "total_steps": 1235, "loss": 0.2184, "lr": 2.6576976876493225e-05, "epoch": 2.2712550607287447, "percentage": 45.43, "elapsed_time": "2:35:59", "remaining_time": "3:07:24"}
562
+ {"current_steps": 562, "total_steps": 1235, "loss": 0.2228, "lr": 2.652354173593614e-05, "epoch": 2.2753036437246963, "percentage": 45.51, "elapsed_time": "2:36:16", "remaining_time": "3:07:09"}
563
+ {"current_steps": 563, "total_steps": 1235, "loss": 0.2184, "lr": 2.647005443331317e-05, "epoch": 2.279352226720648, "percentage": 45.59, "elapsed_time": "2:36:33", "remaining_time": "3:06:51"}
564
+ {"current_steps": 564, "total_steps": 1235, "loss": 0.2248, "lr": 2.6416515396307354e-05, "epoch": 2.283400809716599, "percentage": 45.67, "elapsed_time": "2:36:46", "remaining_time": "3:06:31"}
565
+ {"current_steps": 565, "total_steps": 1235, "loss": 0.2275, "lr": 2.636292505301542e-05, "epoch": 2.2874493927125505, "percentage": 45.75, "elapsed_time": "2:37:02", "remaining_time": "3:06:13"}
566
+ {"current_steps": 566, "total_steps": 1235, "loss": 0.2205, "lr": 2.630928383194431e-05, "epoch": 2.291497975708502, "percentage": 45.83, "elapsed_time": "2:37:20", "remaining_time": "3:05:58"}
567
+ {"current_steps": 567, "total_steps": 1235, "loss": 0.2251, "lr": 2.625559216200781e-05, "epoch": 2.2955465587044532, "percentage": 45.91, "elapsed_time": "2:37:36", "remaining_time": "3:05:40"}
568
+ {"current_steps": 568, "total_steps": 1235, "loss": 0.2135, "lr": 2.620185047252308e-05, "epoch": 2.299595141700405, "percentage": 45.99, "elapsed_time": "2:37:50", "remaining_time": "3:05:21"}
569
+ {"current_steps": 569, "total_steps": 1235, "loss": 0.2395, "lr": 2.614805919320723e-05, "epoch": 2.3036437246963564, "percentage": 46.07, "elapsed_time": "2:38:04", "remaining_time": "3:05:00"}
570
+ {"current_steps": 570, "total_steps": 1235, "loss": 0.2172, "lr": 2.6094218754173895e-05, "epoch": 2.3076923076923075, "percentage": 46.15, "elapsed_time": "2:38:14", "remaining_time": "3:04:37"}
571
+ {"current_steps": 571, "total_steps": 1235, "loss": 0.2161, "lr": 2.60403295859298e-05, "epoch": 2.311740890688259, "percentage": 46.23, "elapsed_time": "2:38:32", "remaining_time": "3:04:21"}
572
+ {"current_steps": 572, "total_steps": 1235, "loss": 0.2269, "lr": 2.5986392119371297e-05, "epoch": 2.3157894736842106, "percentage": 46.32, "elapsed_time": "2:38:48", "remaining_time": "3:04:04"}
573
+ {"current_steps": 573, "total_steps": 1235, "loss": 0.2225, "lr": 2.5932406785780928e-05, "epoch": 2.3198380566801617, "percentage": 46.4, "elapsed_time": "2:39:04", "remaining_time": "3:03:46"}
574
+ {"current_steps": 574, "total_steps": 1235, "loss": 0.2347, "lr": 2.5878374016823987e-05, "epoch": 2.3238866396761133, "percentage": 46.48, "elapsed_time": "2:39:22", "remaining_time": "3:03:31"}
575
+ {"current_steps": 575, "total_steps": 1235, "loss": 0.215, "lr": 2.5824294244545045e-05, "epoch": 2.327935222672065, "percentage": 46.56, "elapsed_time": "2:39:37", "remaining_time": "3:03:12"}
576
+ {"current_steps": 576, "total_steps": 1235, "loss": 0.2331, "lr": 2.577016790136453e-05, "epoch": 2.331983805668016, "percentage": 46.64, "elapsed_time": "2:39:55", "remaining_time": "3:02:58"}
577
+ {"current_steps": 577, "total_steps": 1235, "loss": 0.2081, "lr": 2.5715995420075225e-05, "epoch": 2.3360323886639676, "percentage": 46.72, "elapsed_time": "2:40:09", "remaining_time": "3:02:38"}
578
+ {"current_steps": 578, "total_steps": 1235, "loss": 0.2214, "lr": 2.5661777233838864e-05, "epoch": 2.340080971659919, "percentage": 46.8, "elapsed_time": "2:40:27", "remaining_time": "3:02:23"}
579
+ {"current_steps": 579, "total_steps": 1235, "loss": 0.2312, "lr": 2.5607513776182616e-05, "epoch": 2.3441295546558703, "percentage": 46.88, "elapsed_time": "2:40:42", "remaining_time": "3:02:04"}
580
+ {"current_steps": 580, "total_steps": 1235, "loss": 0.2439, "lr": 2.5553205480995633e-05, "epoch": 2.348178137651822, "percentage": 46.96, "elapsed_time": "2:40:59", "remaining_time": "3:01:48"}
581
+ {"current_steps": 581, "total_steps": 1235, "loss": 0.2318, "lr": 2.5498852782525604e-05, "epoch": 2.3522267206477734, "percentage": 47.04, "elapsed_time": "2:41:11", "remaining_time": "3:01:26"}
582
+ {"current_steps": 582, "total_steps": 1235, "loss": 0.2164, "lr": 2.5444456115375252e-05, "epoch": 2.3562753036437245, "percentage": 47.13, "elapsed_time": "2:41:26", "remaining_time": "3:01:08"}
583
+ {"current_steps": 583, "total_steps": 1235, "loss": 0.2256, "lr": 2.539001591449889e-05, "epoch": 2.360323886639676, "percentage": 47.21, "elapsed_time": "2:41:46", "remaining_time": "3:00:55"}
584
+ {"current_steps": 584, "total_steps": 1235, "loss": 0.2212, "lr": 2.53355326151989e-05, "epoch": 2.3643724696356276, "percentage": 47.29, "elapsed_time": "2:42:04", "remaining_time": "3:00:39"}
585
+ {"current_steps": 585, "total_steps": 1235, "loss": 0.2354, "lr": 2.5281006653122288e-05, "epoch": 2.3684210526315788, "percentage": 47.37, "elapsed_time": "2:42:19", "remaining_time": "3:00:21"}
586
+ {"current_steps": 586, "total_steps": 1235, "loss": 0.2251, "lr": 2.5226438464257217e-05, "epoch": 2.3724696356275303, "percentage": 47.45, "elapsed_time": "2:42:33", "remaining_time": "3:00:01"}
587
+ {"current_steps": 587, "total_steps": 1235, "loss": 0.2196, "lr": 2.5171828484929447e-05, "epoch": 2.376518218623482, "percentage": 47.53, "elapsed_time": "2:42:48", "remaining_time": "2:59:43"}
588
+ {"current_steps": 588, "total_steps": 1235, "loss": 0.2102, "lr": 2.5117177151798934e-05, "epoch": 2.380566801619433, "percentage": 47.61, "elapsed_time": "2:43:03", "remaining_time": "2:59:25"}
589
+ {"current_steps": 589, "total_steps": 1235, "loss": 0.2059, "lr": 2.506248490185627e-05, "epoch": 2.3846153846153846, "percentage": 47.69, "elapsed_time": "2:43:18", "remaining_time": "2:59:06"}
590
+ {"current_steps": 590, "total_steps": 1235, "loss": 0.2215, "lr": 2.500775217241923e-05, "epoch": 2.388663967611336, "percentage": 47.77, "elapsed_time": "2:43:31", "remaining_time": "2:58:46"}
591
+ {"current_steps": 591, "total_steps": 1235, "loss": 0.2176, "lr": 2.4952979401129266e-05, "epoch": 2.3927125506072873, "percentage": 47.85, "elapsed_time": "2:43:46", "remaining_time": "2:58:28"}
592
+ {"current_steps": 592, "total_steps": 1235, "loss": 0.2096, "lr": 2.4898167025948e-05, "epoch": 2.396761133603239, "percentage": 47.94, "elapsed_time": "2:44:02", "remaining_time": "2:58:10"}
593
+ {"current_steps": 593, "total_steps": 1235, "loss": 0.2114, "lr": 2.4843315485153703e-05, "epoch": 2.4008097165991904, "percentage": 48.02, "elapsed_time": "2:44:17", "remaining_time": "2:57:52"}
594
+ {"current_steps": 594, "total_steps": 1235, "loss": 0.2152, "lr": 2.4788425217337856e-05, "epoch": 2.4048582995951415, "percentage": 48.1, "elapsed_time": "2:44:32", "remaining_time": "2:57:34"}
595
+ {"current_steps": 595, "total_steps": 1235, "loss": 0.2231, "lr": 2.4733496661401572e-05, "epoch": 2.408906882591093, "percentage": 48.18, "elapsed_time": "2:44:48", "remaining_time": "2:57:16"}
596
+ {"current_steps": 596, "total_steps": 1235, "loss": 0.223, "lr": 2.4678530256552114e-05, "epoch": 2.4129554655870447, "percentage": 48.26, "elapsed_time": "2:45:07", "remaining_time": "2:57:02"}
597
+ {"current_steps": 597, "total_steps": 1235, "loss": 0.2329, "lr": 2.46235264422994e-05, "epoch": 2.417004048582996, "percentage": 48.34, "elapsed_time": "2:45:24", "remaining_time": "2:56:46"}
598
+ {"current_steps": 598, "total_steps": 1235, "loss": 0.2355, "lr": 2.4568485658452452e-05, "epoch": 2.4210526315789473, "percentage": 48.42, "elapsed_time": "2:45:40", "remaining_time": "2:56:28"}
599
+ {"current_steps": 599, "total_steps": 1235, "loss": 0.2368, "lr": 2.451340834511592e-05, "epoch": 2.425101214574899, "percentage": 48.5, "elapsed_time": "2:45:57", "remaining_time": "2:56:12"}
600
+ {"current_steps": 600, "total_steps": 1235, "loss": 0.2153, "lr": 2.4458294942686528e-05, "epoch": 2.42914979757085, "percentage": 48.58, "elapsed_time": "2:46:13", "remaining_time": "2:55:54"}
601
+ {"current_steps": 601, "total_steps": 1235, "loss": 0.2186, "lr": 2.440314589184958e-05, "epoch": 2.4331983805668016, "percentage": 48.66, "elapsed_time": "2:46:29", "remaining_time": "2:55:38"}
602
+ {"current_steps": 602, "total_steps": 1235, "loss": 0.2515, "lr": 2.434796163357541e-05, "epoch": 2.437246963562753, "percentage": 48.74, "elapsed_time": "2:46:49", "remaining_time": "2:55:25"}
603
+ {"current_steps": 603, "total_steps": 1235, "loss": 0.2178, "lr": 2.429274260911588e-05, "epoch": 2.4412955465587043, "percentage": 48.83, "elapsed_time": "2:47:08", "remaining_time": "2:55:10"}
604
+ {"current_steps": 604, "total_steps": 1235, "loss": 0.2243, "lr": 2.423748926000084e-05, "epoch": 2.445344129554656, "percentage": 48.91, "elapsed_time": "2:47:23", "remaining_time": "2:54:52"}
605
+ {"current_steps": 605, "total_steps": 1235, "loss": 0.2139, "lr": 2.418220202803459e-05, "epoch": 2.4493927125506074, "percentage": 48.99, "elapsed_time": "2:47:41", "remaining_time": "2:54:37"}
606
+ {"current_steps": 606, "total_steps": 1235, "loss": 0.2459, "lr": 2.412688135529237e-05, "epoch": 2.4534412955465585, "percentage": 49.07, "elapsed_time": "2:48:01", "remaining_time": "2:54:23"}
607
+ {"current_steps": 607, "total_steps": 1235, "loss": 0.2294, "lr": 2.4071527684116807e-05, "epoch": 2.45748987854251, "percentage": 49.15, "elapsed_time": "2:48:18", "remaining_time": "2:54:08"}
608
+ {"current_steps": 608, "total_steps": 1235, "loss": 0.2231, "lr": 2.4016141457114372e-05, "epoch": 2.4615384615384617, "percentage": 49.23, "elapsed_time": "2:48:33", "remaining_time": "2:53:49"}
609
+ {"current_steps": 609, "total_steps": 1235, "loss": 0.2247, "lr": 2.396072311715187e-05, "epoch": 2.465587044534413, "percentage": 49.31, "elapsed_time": "2:48:50", "remaining_time": "2:53:32"}
610
+ {"current_steps": 610, "total_steps": 1235, "loss": 0.2164, "lr": 2.3905273107352863e-05, "epoch": 2.4696356275303644, "percentage": 49.39, "elapsed_time": "2:49:09", "remaining_time": "2:53:19"}
611
+ {"current_steps": 611, "total_steps": 1235, "loss": 0.2329, "lr": 2.3849791871094157e-05, "epoch": 2.473684210526316, "percentage": 49.47, "elapsed_time": "2:49:24", "remaining_time": "2:53:00"}
612
+ {"current_steps": 612, "total_steps": 1235, "loss": 0.222, "lr": 2.379427985200223e-05, "epoch": 2.477732793522267, "percentage": 49.55, "elapsed_time": "2:49:41", "remaining_time": "2:52:44"}
613
+ {"current_steps": 613, "total_steps": 1235, "loss": 0.2258, "lr": 2.373873749394972e-05, "epoch": 2.4817813765182186, "percentage": 49.64, "elapsed_time": "2:49:56", "remaining_time": "2:52:26"}
614
+ {"current_steps": 614, "total_steps": 1235, "loss": 0.2131, "lr": 2.3683165241051836e-05, "epoch": 2.48582995951417, "percentage": 49.72, "elapsed_time": "2:50:13", "remaining_time": "2:52:10"}
615
+ {"current_steps": 615, "total_steps": 1235, "loss": 0.2103, "lr": 2.3627563537662823e-05, "epoch": 2.4898785425101213, "percentage": 49.8, "elapsed_time": "2:50:32", "remaining_time": "2:51:56"}
616
+ {"current_steps": 616, "total_steps": 1235, "loss": 0.2227, "lr": 2.3571932828372433e-05, "epoch": 2.493927125506073, "percentage": 49.88, "elapsed_time": "2:50:49", "remaining_time": "2:51:39"}
617
+ {"current_steps": 617, "total_steps": 1235, "loss": 0.2292, "lr": 2.351627355800233e-05, "epoch": 2.4979757085020244, "percentage": 49.96, "elapsed_time": "2:51:03", "remaining_time": "2:51:20"}
618
+ {"current_steps": 618, "total_steps": 1235, "loss": 0.228, "lr": 2.346058617160256e-05, "epoch": 2.5020242914979756, "percentage": 50.04, "elapsed_time": "2:51:21", "remaining_time": "2:51:05"}
619
+ {"current_steps": 619, "total_steps": 1235, "loss": 0.2285, "lr": 2.3404871114447976e-05, "epoch": 2.506072874493927, "percentage": 50.12, "elapsed_time": "2:51:36", "remaining_time": "2:50:46"}
620
+ {"current_steps": 620, "total_steps": 1235, "loss": 0.2206, "lr": 2.334912883203469e-05, "epoch": 2.5101214574898787, "percentage": 50.2, "elapsed_time": "2:51:54", "remaining_time": "2:50:31"}
621
+ {"current_steps": 621, "total_steps": 1235, "loss": 0.2212, "lr": 2.3293359770076505e-05, "epoch": 2.51417004048583, "percentage": 50.28, "elapsed_time": "2:52:11", "remaining_time": "2:50:14"}
622
+ {"current_steps": 622, "total_steps": 1235, "loss": 0.2267, "lr": 2.323756437450136e-05, "epoch": 2.5182186234817814, "percentage": 50.36, "elapsed_time": "2:52:28", "remaining_time": "2:49:59"}
623
+ {"current_steps": 623, "total_steps": 1235, "loss": 0.2172, "lr": 2.3181743091447754e-05, "epoch": 2.522267206477733, "percentage": 50.45, "elapsed_time": "2:52:46", "remaining_time": "2:49:43"}
624
+ {"current_steps": 624, "total_steps": 1235, "loss": 0.2272, "lr": 2.3125896367261164e-05, "epoch": 2.526315789473684, "percentage": 50.53, "elapsed_time": "2:53:03", "remaining_time": "2:49:27"}
625
+ {"current_steps": 625, "total_steps": 1235, "loss": 0.2201, "lr": 2.307002464849052e-05, "epoch": 2.5303643724696356, "percentage": 50.61, "elapsed_time": "2:53:20", "remaining_time": "2:49:10"}
626
+ {"current_steps": 626, "total_steps": 1235, "loss": 0.2117, "lr": 2.30141283818846e-05, "epoch": 2.534412955465587, "percentage": 50.69, "elapsed_time": "2:53:33", "remaining_time": "2:48:50"}
627
+ {"current_steps": 627, "total_steps": 1235, "loss": 0.2205, "lr": 2.2958208014388462e-05, "epoch": 2.5384615384615383, "percentage": 50.77, "elapsed_time": "2:53:51", "remaining_time": "2:48:35"}
628
+ {"current_steps": 628, "total_steps": 1235, "loss": 0.2247, "lr": 2.2902263993139857e-05, "epoch": 2.54251012145749, "percentage": 50.85, "elapsed_time": "2:54:07", "remaining_time": "2:48:18"}
629
+ {"current_steps": 629, "total_steps": 1235, "loss": 0.2314, "lr": 2.2846296765465708e-05, "epoch": 2.5465587044534415, "percentage": 50.93, "elapsed_time": "2:54:23", "remaining_time": "2:48:00"}
630
+ {"current_steps": 630, "total_steps": 1235, "loss": 0.2059, "lr": 2.2790306778878465e-05, "epoch": 2.5506072874493926, "percentage": 51.01, "elapsed_time": "2:54:41", "remaining_time": "2:47:45"}
631
+ {"current_steps": 631, "total_steps": 1235, "loss": 0.2178, "lr": 2.273429448107257e-05, "epoch": 2.554655870445344, "percentage": 51.09, "elapsed_time": "2:54:56", "remaining_time": "2:47:27"}
632
+ {"current_steps": 632, "total_steps": 1235, "loss": 0.2217, "lr": 2.2678260319920868e-05, "epoch": 2.5587044534412957, "percentage": 51.17, "elapsed_time": "2:55:06", "remaining_time": "2:47:04"}
633
+ {"current_steps": 633, "total_steps": 1235, "loss": 0.2298, "lr": 2.262220474347102e-05, "epoch": 2.562753036437247, "percentage": 51.26, "elapsed_time": "2:55:22", "remaining_time": "2:46:47"}
634
+ {"current_steps": 634, "total_steps": 1235, "loss": 0.2103, "lr": 2.2566128199941918e-05, "epoch": 2.5668016194331984, "percentage": 51.34, "elapsed_time": "2:55:39", "remaining_time": "2:46:30"}
635
+ {"current_steps": 635, "total_steps": 1235, "loss": 0.2237, "lr": 2.2510031137720104e-05, "epoch": 2.57085020242915, "percentage": 51.42, "elapsed_time": "2:55:58", "remaining_time": "2:46:16"}
636
+ {"current_steps": 636, "total_steps": 1235, "loss": 0.2137, "lr": 2.2453914005356206e-05, "epoch": 2.574898785425101, "percentage": 51.5, "elapsed_time": "2:56:12", "remaining_time": "2:45:57"}
637
+ {"current_steps": 637, "total_steps": 1235, "loss": 0.2301, "lr": 2.2397777251561302e-05, "epoch": 2.5789473684210527, "percentage": 51.58, "elapsed_time": "2:56:29", "remaining_time": "2:45:41"}
638
+ {"current_steps": 638, "total_steps": 1235, "loss": 0.2278, "lr": 2.2341621325203393e-05, "epoch": 2.582995951417004, "percentage": 51.66, "elapsed_time": "2:56:45", "remaining_time": "2:45:23"}
639
+ {"current_steps": 639, "total_steps": 1235, "loss": 0.2181, "lr": 2.2285446675303764e-05, "epoch": 2.5870445344129553, "percentage": 51.74, "elapsed_time": "2:56:59", "remaining_time": "2:45:04"}
640
+ {"current_steps": 640, "total_steps": 1235, "loss": 0.2184, "lr": 2.2229253751033423e-05, "epoch": 2.591093117408907, "percentage": 51.82, "elapsed_time": "2:57:19", "remaining_time": "2:44:51"}
641
+ {"current_steps": 641, "total_steps": 1235, "loss": 0.2225, "lr": 2.2173043001709492e-05, "epoch": 2.5951417004048585, "percentage": 51.9, "elapsed_time": "2:57:36", "remaining_time": "2:44:34"}
642
+ {"current_steps": 642, "total_steps": 1235, "loss": 0.1966, "lr": 2.2116814876791627e-05, "epoch": 2.5991902834008096, "percentage": 51.98, "elapsed_time": "2:57:46", "remaining_time": "2:44:12"}
643
+ {"current_steps": 643, "total_steps": 1235, "loss": 0.2193, "lr": 2.2060569825878413e-05, "epoch": 2.603238866396761, "percentage": 52.06, "elapsed_time": "2:58:03", "remaining_time": "2:43:56"}
644
+ {"current_steps": 644, "total_steps": 1235, "loss": 0.2045, "lr": 2.2004308298703777e-05, "epoch": 2.6072874493927127, "percentage": 52.15, "elapsed_time": "2:58:20", "remaining_time": "2:43:39"}
645
+ {"current_steps": 645, "total_steps": 1235, "loss": 0.2426, "lr": 2.1948030745133396e-05, "epoch": 2.611336032388664, "percentage": 52.23, "elapsed_time": "2:58:39", "remaining_time": "2:43:24"}
646
+ {"current_steps": 646, "total_steps": 1235, "loss": 0.2181, "lr": 2.1891737615161083e-05, "epoch": 2.6153846153846154, "percentage": 52.31, "elapsed_time": "2:58:55", "remaining_time": "2:43:08"}
647
+ {"current_steps": 647, "total_steps": 1235, "loss": 0.2245, "lr": 2.1835429358905218e-05, "epoch": 2.619433198380567, "percentage": 52.39, "elapsed_time": "2:59:13", "remaining_time": "2:42:52"}
648
+ {"current_steps": 648, "total_steps": 1235, "loss": 0.2124, "lr": 2.17791064266051e-05, "epoch": 2.623481781376518, "percentage": 52.47, "elapsed_time": "2:59:27", "remaining_time": "2:42:33"}
649
+ {"current_steps": 649, "total_steps": 1235, "loss": 0.2375, "lr": 2.172276926861741e-05, "epoch": 2.6275303643724697, "percentage": 52.55, "elapsed_time": "2:59:39", "remaining_time": "2:42:13"}
650
+ {"current_steps": 650, "total_steps": 1235, "loss": 0.2116, "lr": 2.166641833541255e-05, "epoch": 2.6315789473684212, "percentage": 52.63, "elapsed_time": "2:59:56", "remaining_time": "2:41:56"}
651
+ {"current_steps": 651, "total_steps": 1235, "loss": 0.2399, "lr": 2.161005407757109e-05, "epoch": 2.6356275303643724, "percentage": 52.71, "elapsed_time": "3:00:10", "remaining_time": "2:41:37"}
652
+ {"current_steps": 652, "total_steps": 1235, "loss": 0.222, "lr": 2.155367694578013e-05, "epoch": 2.639676113360324, "percentage": 52.79, "elapsed_time": "3:00:25", "remaining_time": "2:41:19"}
653
+ {"current_steps": 653, "total_steps": 1235, "loss": 0.2199, "lr": 2.1497287390829712e-05, "epoch": 2.6437246963562755, "percentage": 52.87, "elapsed_time": "3:00:43", "remaining_time": "2:41:04"}
654
+ {"current_steps": 654, "total_steps": 1235, "loss": 0.2233, "lr": 2.1440885863609208e-05, "epoch": 2.6477732793522266, "percentage": 52.96, "elapsed_time": "3:01:00", "remaining_time": "2:40:48"}
655
+ {"current_steps": 655, "total_steps": 1235, "loss": 0.2196, "lr": 2.1384472815103737e-05, "epoch": 2.651821862348178, "percentage": 53.04, "elapsed_time": "3:01:17", "remaining_time": "2:40:32"}
656
+ {"current_steps": 656, "total_steps": 1235, "loss": 0.2243, "lr": 2.1328048696390534e-05, "epoch": 2.6558704453441297, "percentage": 53.12, "elapsed_time": "3:01:35", "remaining_time": "2:40:16"}
657
+ {"current_steps": 657, "total_steps": 1235, "loss": 0.2355, "lr": 2.1271613958635342e-05, "epoch": 2.659919028340081, "percentage": 53.2, "elapsed_time": "3:01:54", "remaining_time": "2:40:02"}
658
+ {"current_steps": 658, "total_steps": 1235, "loss": 0.2137, "lr": 2.1215169053088825e-05, "epoch": 2.6639676113360324, "percentage": 53.28, "elapsed_time": "3:02:14", "remaining_time": "2:39:48"}
659
+ {"current_steps": 659, "total_steps": 1235, "loss": 0.2062, "lr": 2.1158714431082937e-05, "epoch": 2.668016194331984, "percentage": 53.36, "elapsed_time": "3:02:30", "remaining_time": "2:39:31"}
660
+ {"current_steps": 660, "total_steps": 1235, "loss": 0.2153, "lr": 2.110225054402733e-05, "epoch": 2.672064777327935, "percentage": 53.44, "elapsed_time": "3:02:47", "remaining_time": "2:39:14"}
661
+ {"current_steps": 661, "total_steps": 1235, "loss": 0.2365, "lr": 2.1045777843405747e-05, "epoch": 2.6761133603238867, "percentage": 53.52, "elapsed_time": "3:03:05", "remaining_time": "2:38:59"}
662
+ {"current_steps": 662, "total_steps": 1235, "loss": 0.2306, "lr": 2.09892967807724e-05, "epoch": 2.6801619433198383, "percentage": 53.6, "elapsed_time": "3:03:21", "remaining_time": "2:38:42"}
663
+ {"current_steps": 663, "total_steps": 1235, "loss": 0.219, "lr": 2.093280780774835e-05, "epoch": 2.6842105263157894, "percentage": 53.68, "elapsed_time": "3:03:41", "remaining_time": "2:38:28"}
664
+ {"current_steps": 664, "total_steps": 1235, "loss": 0.226, "lr": 2.087631137601793e-05, "epoch": 2.688259109311741, "percentage": 53.77, "elapsed_time": "3:03:59", "remaining_time": "2:38:13"}
665
+ {"current_steps": 665, "total_steps": 1235, "loss": 0.222, "lr": 2.0819807937325104e-05, "epoch": 2.6923076923076925, "percentage": 53.85, "elapsed_time": "3:04:18", "remaining_time": "2:37:58"}
666
+ {"current_steps": 666, "total_steps": 1235, "loss": 0.2298, "lr": 2.0763297943469847e-05, "epoch": 2.6963562753036436, "percentage": 53.93, "elapsed_time": "3:04:33", "remaining_time": "2:37:40"}
667
+ {"current_steps": 667, "total_steps": 1235, "loss": 0.2164, "lr": 2.070678184630458e-05, "epoch": 2.700404858299595, "percentage": 54.01, "elapsed_time": "3:04:52", "remaining_time": "2:37:26"}
668
+ {"current_steps": 668, "total_steps": 1235, "loss": 0.233, "lr": 2.06502600977305e-05, "epoch": 2.7044534412955468, "percentage": 54.09, "elapsed_time": "3:05:07", "remaining_time": "2:37:07"}
669
+ {"current_steps": 669, "total_steps": 1235, "loss": 0.2388, "lr": 2.0593733149694008e-05, "epoch": 2.708502024291498, "percentage": 54.17, "elapsed_time": "3:05:27", "remaining_time": "2:36:54"}
670
+ {"current_steps": 670, "total_steps": 1235, "loss": 0.2151, "lr": 2.0537201454183074e-05, "epoch": 2.7125506072874495, "percentage": 54.25, "elapsed_time": "3:05:40", "remaining_time": "2:36:34"}
671
+ {"current_steps": 671, "total_steps": 1235, "loss": 0.2325, "lr": 2.0480665463223626e-05, "epoch": 2.716599190283401, "percentage": 54.33, "elapsed_time": "3:05:55", "remaining_time": "2:36:16"}
672
+ {"current_steps": 672, "total_steps": 1235, "loss": 0.2199, "lr": 2.042412562887594e-05, "epoch": 2.720647773279352, "percentage": 54.41, "elapsed_time": "3:06:10", "remaining_time": "2:35:58"}
673
+ {"current_steps": 673, "total_steps": 1235, "loss": 0.2211, "lr": 2.0367582403231033e-05, "epoch": 2.7246963562753037, "percentage": 54.49, "elapsed_time": "3:06:25", "remaining_time": "2:35:40"}
674
+ {"current_steps": 674, "total_steps": 1235, "loss": 0.2074, "lr": 2.0311036238407023e-05, "epoch": 2.7287449392712553, "percentage": 54.57, "elapsed_time": "3:06:36", "remaining_time": "2:35:19"}
675
+ {"current_steps": 675, "total_steps": 1235, "loss": 0.2126, "lr": 2.0254487586545534e-05, "epoch": 2.7327935222672064, "percentage": 54.66, "elapsed_time": "3:06:50", "remaining_time": "2:35:00"}
676
+ {"current_steps": 676, "total_steps": 1235, "loss": 0.2348, "lr": 2.0197936899808088e-05, "epoch": 2.736842105263158, "percentage": 54.74, "elapsed_time": "3:07:09", "remaining_time": "2:34:45"}
677
+ {"current_steps": 677, "total_steps": 1235, "loss": 0.2157, "lr": 2.0141384630372466e-05, "epoch": 2.7408906882591095, "percentage": 54.82, "elapsed_time": "3:07:26", "remaining_time": "2:34:30"}
678
+ {"current_steps": 678, "total_steps": 1235, "loss": 0.2244, "lr": 2.0084831230429106e-05, "epoch": 2.7449392712550607, "percentage": 54.9, "elapsed_time": "3:07:40", "remaining_time": "2:34:10"}
679
+ {"current_steps": 679, "total_steps": 1235, "loss": 0.2302, "lr": 2.0028277152177492e-05, "epoch": 2.748987854251012, "percentage": 54.98, "elapsed_time": "3:07:55", "remaining_time": "2:33:52"}
680
+ {"current_steps": 680, "total_steps": 1235, "loss": 0.2203, "lr": 1.9971722847822518e-05, "epoch": 2.753036437246964, "percentage": 55.06, "elapsed_time": "3:08:09", "remaining_time": "2:33:34"}
681
+ {"current_steps": 681, "total_steps": 1235, "loss": 0.2363, "lr": 1.99151687695709e-05, "epoch": 2.757085020242915, "percentage": 55.14, "elapsed_time": "3:08:29", "remaining_time": "2:33:20"}
682
+ {"current_steps": 682, "total_steps": 1235, "loss": 0.2313, "lr": 1.9858615369627537e-05, "epoch": 2.7611336032388665, "percentage": 55.22, "elapsed_time": "3:08:46", "remaining_time": "2:33:04"}
683
+ {"current_steps": 683, "total_steps": 1235, "loss": 0.2155, "lr": 1.9802063100191916e-05, "epoch": 2.765182186234818, "percentage": 55.3, "elapsed_time": "3:09:02", "remaining_time": "2:32:47"}
684
+ {"current_steps": 684, "total_steps": 1235, "loss": 0.2237, "lr": 1.974551241345447e-05, "epoch": 2.769230769230769, "percentage": 55.38, "elapsed_time": "3:09:20", "remaining_time": "2:32:31"}
685
+ {"current_steps": 685, "total_steps": 1235, "loss": 0.2286, "lr": 1.9688963761592984e-05, "epoch": 2.7732793522267207, "percentage": 55.47, "elapsed_time": "3:09:34", "remaining_time": "2:32:12"}
686
+ {"current_steps": 686, "total_steps": 1235, "loss": 0.2363, "lr": 1.963241759676897e-05, "epoch": 2.7773279352226723, "percentage": 55.55, "elapsed_time": "3:09:51", "remaining_time": "2:31:56"}
687
+ {"current_steps": 687, "total_steps": 1235, "loss": 0.2313, "lr": 1.9575874371124066e-05, "epoch": 2.7813765182186234, "percentage": 55.63, "elapsed_time": "3:10:09", "remaining_time": "2:31:40"}
688
+ {"current_steps": 688, "total_steps": 1235, "loss": 0.2104, "lr": 1.951933453677638e-05, "epoch": 2.785425101214575, "percentage": 55.71, "elapsed_time": "3:10:27", "remaining_time": "2:31:25"}
689
+ {"current_steps": 689, "total_steps": 1235, "loss": 0.2124, "lr": 1.9462798545816932e-05, "epoch": 2.7894736842105265, "percentage": 55.79, "elapsed_time": "3:10:43", "remaining_time": "2:31:08"}
690
+ {"current_steps": 690, "total_steps": 1235, "loss": 0.2136, "lr": 1.9406266850305996e-05, "epoch": 2.7935222672064777, "percentage": 55.87, "elapsed_time": "3:10:56", "remaining_time": "2:30:48"}
691
+ {"current_steps": 691, "total_steps": 1235, "loss": 0.2045, "lr": 1.9349739902269503e-05, "epoch": 2.7975708502024292, "percentage": 55.95, "elapsed_time": "3:11:08", "remaining_time": "2:30:28"}
692
+ {"current_steps": 692, "total_steps": 1235, "loss": 0.2168, "lr": 1.9293218153695425e-05, "epoch": 2.801619433198381, "percentage": 56.03, "elapsed_time": "3:11:23", "remaining_time": "2:30:10"}
693
+ {"current_steps": 693, "total_steps": 1235, "loss": 0.2188, "lr": 1.9236702056530153e-05, "epoch": 2.805668016194332, "percentage": 56.11, "elapsed_time": "3:11:44", "remaining_time": "2:29:57"}
694
+ {"current_steps": 694, "total_steps": 1235, "loss": 0.2187, "lr": 1.9180192062674907e-05, "epoch": 2.8097165991902835, "percentage": 56.19, "elapsed_time": "3:12:04", "remaining_time": "2:29:43"}
695
+ {"current_steps": 695, "total_steps": 1235, "loss": 0.2161, "lr": 1.9123688623982076e-05, "epoch": 2.813765182186235, "percentage": 56.28, "elapsed_time": "3:12:21", "remaining_time": "2:29:27"}
696
+ {"current_steps": 696, "total_steps": 1235, "loss": 0.2282, "lr": 1.906719219225165e-05, "epoch": 2.817813765182186, "percentage": 56.36, "elapsed_time": "3:12:35", "remaining_time": "2:29:08"}
697
+ {"current_steps": 697, "total_steps": 1235, "loss": 0.2203, "lr": 1.9010703219227603e-05, "epoch": 2.8218623481781377, "percentage": 56.44, "elapsed_time": "3:12:49", "remaining_time": "2:28:50"}
698
+ {"current_steps": 698, "total_steps": 1235, "loss": 0.2191, "lr": 1.8954222156594256e-05, "epoch": 2.8259109311740893, "percentage": 56.52, "elapsed_time": "3:13:06", "remaining_time": "2:28:34"}
699
+ {"current_steps": 699, "total_steps": 1235, "loss": 0.2351, "lr": 1.8897749455972673e-05, "epoch": 2.8299595141700404, "percentage": 56.6, "elapsed_time": "3:13:24", "remaining_time": "2:28:18"}
700
+ {"current_steps": 700, "total_steps": 1235, "loss": 0.2215, "lr": 1.884128556891707e-05, "epoch": 2.834008097165992, "percentage": 56.68, "elapsed_time": "3:13:42", "remaining_time": "2:28:02"}
701
+ {"current_steps": 701, "total_steps": 1235, "loss": 0.2197, "lr": 1.878483094691119e-05, "epoch": 2.8380566801619436, "percentage": 56.76, "elapsed_time": "3:13:58", "remaining_time": "2:27:45"}
702
+ {"current_steps": 702, "total_steps": 1235, "loss": 0.2337, "lr": 1.8728386041364664e-05, "epoch": 2.8421052631578947, "percentage": 56.84, "elapsed_time": "3:14:16", "remaining_time": "2:27:30"}
703
+ {"current_steps": 703, "total_steps": 1235, "loss": 0.2144, "lr": 1.867195130360947e-05, "epoch": 2.8461538461538463, "percentage": 56.92, "elapsed_time": "3:14:31", "remaining_time": "2:27:12"}
704
+ {"current_steps": 704, "total_steps": 1235, "loss": 0.228, "lr": 1.8615527184896263e-05, "epoch": 2.850202429149798, "percentage": 57.0, "elapsed_time": "3:14:45", "remaining_time": "2:26:54"}
705
+ {"current_steps": 705, "total_steps": 1235, "loss": 0.2262, "lr": 1.8559114136390795e-05, "epoch": 2.854251012145749, "percentage": 57.09, "elapsed_time": "3:15:01", "remaining_time": "2:26:36"}
706
+ {"current_steps": 706, "total_steps": 1235, "loss": 0.2073, "lr": 1.8502712609170298e-05, "epoch": 2.8582995951417005, "percentage": 57.17, "elapsed_time": "3:15:19", "remaining_time": "2:26:21"}
707
+ {"current_steps": 707, "total_steps": 1235, "loss": 0.2287, "lr": 1.8446323054219876e-05, "epoch": 2.862348178137652, "percentage": 57.25, "elapsed_time": "3:15:36", "remaining_time": "2:26:05"}
708
+ {"current_steps": 708, "total_steps": 1235, "loss": 0.2056, "lr": 1.838994592242891e-05, "epoch": 2.866396761133603, "percentage": 57.33, "elapsed_time": "3:15:50", "remaining_time": "2:25:46"}
709
+ {"current_steps": 709, "total_steps": 1235, "loss": 0.2199, "lr": 1.8333581664587453e-05, "epoch": 2.8704453441295548, "percentage": 57.41, "elapsed_time": "3:16:04", "remaining_time": "2:25:27"}
710
+ {"current_steps": 710, "total_steps": 1235, "loss": 0.2212, "lr": 1.8277230731382593e-05, "epoch": 2.8744939271255063, "percentage": 57.49, "elapsed_time": "3:16:23", "remaining_time": "2:25:13"}
711
+ {"current_steps": 711, "total_steps": 1235, "loss": 0.2139, "lr": 1.82208935733949e-05, "epoch": 2.8785425101214575, "percentage": 57.57, "elapsed_time": "3:16:39", "remaining_time": "2:24:56"}
712
+ {"current_steps": 712, "total_steps": 1235, "loss": 0.2112, "lr": 1.8164570641094793e-05, "epoch": 2.882591093117409, "percentage": 57.65, "elapsed_time": "3:16:51", "remaining_time": "2:24:36"}
713
+ {"current_steps": 713, "total_steps": 1235, "loss": 0.2175, "lr": 1.810826238483892e-05, "epoch": 2.8866396761133606, "percentage": 57.73, "elapsed_time": "3:17:08", "remaining_time": "2:24:20"}
714
+ {"current_steps": 714, "total_steps": 1235, "loss": 0.2217, "lr": 1.8051969254866608e-05, "epoch": 2.8906882591093117, "percentage": 57.81, "elapsed_time": "3:17:25", "remaining_time": "2:24:03"}
715
+ {"current_steps": 715, "total_steps": 1235, "loss": 0.2169, "lr": 1.7995691701296226e-05, "epoch": 2.8947368421052633, "percentage": 57.89, "elapsed_time": "3:17:39", "remaining_time": "2:23:45"}
716
+ {"current_steps": 716, "total_steps": 1235, "loss": 0.2137, "lr": 1.7939430174121593e-05, "epoch": 2.898785425101215, "percentage": 57.98, "elapsed_time": "3:17:54", "remaining_time": "2:23:27"}
717
+ {"current_steps": 717, "total_steps": 1235, "loss": 0.2148, "lr": 1.788318512320838e-05, "epoch": 2.902834008097166, "percentage": 58.06, "elapsed_time": "3:18:10", "remaining_time": "2:23:10"}
718
+ {"current_steps": 718, "total_steps": 1235, "loss": 0.2133, "lr": 1.782695699829051e-05, "epoch": 2.9068825910931175, "percentage": 58.14, "elapsed_time": "3:18:27", "remaining_time": "2:22:54"}
719
+ {"current_steps": 719, "total_steps": 1235, "loss": 0.2201, "lr": 1.7770746248966587e-05, "epoch": 2.910931174089069, "percentage": 58.22, "elapsed_time": "3:18:45", "remaining_time": "2:22:38"}
720
+ {"current_steps": 720, "total_steps": 1235, "loss": 0.2265, "lr": 1.7714553324696243e-05, "epoch": 2.91497975708502, "percentage": 58.3, "elapsed_time": "3:18:59", "remaining_time": "2:22:20"}
721
+ {"current_steps": 721, "total_steps": 1235, "loss": 0.225, "lr": 1.7658378674796614e-05, "epoch": 2.919028340080972, "percentage": 58.38, "elapsed_time": "3:19:17", "remaining_time": "2:22:04"}
722
+ {"current_steps": 722, "total_steps": 1235, "loss": 0.2115, "lr": 1.76022227484387e-05, "epoch": 2.9230769230769234, "percentage": 58.46, "elapsed_time": "3:19:30", "remaining_time": "2:21:45"}
723
+ {"current_steps": 723, "total_steps": 1235, "loss": 0.2079, "lr": 1.7546085994643807e-05, "epoch": 2.9271255060728745, "percentage": 58.54, "elapsed_time": "3:19:46", "remaining_time": "2:21:28"}
724
+ {"current_steps": 724, "total_steps": 1235, "loss": 0.2307, "lr": 1.7489968862279902e-05, "epoch": 2.931174089068826, "percentage": 58.62, "elapsed_time": "3:20:00", "remaining_time": "2:21:09"}
725
+ {"current_steps": 725, "total_steps": 1235, "loss": 0.2208, "lr": 1.743387180005809e-05, "epoch": 2.9352226720647776, "percentage": 58.7, "elapsed_time": "3:20:18", "remaining_time": "2:20:54"}
726
+ {"current_steps": 726, "total_steps": 1235, "loss": 0.2289, "lr": 1.737779525652899e-05, "epoch": 2.9392712550607287, "percentage": 58.79, "elapsed_time": "3:20:35", "remaining_time": "2:20:38"}
727
+ {"current_steps": 727, "total_steps": 1235, "loss": 0.2238, "lr": 1.732173968007914e-05, "epoch": 2.9433198380566803, "percentage": 58.87, "elapsed_time": "3:20:54", "remaining_time": "2:20:23"}
728
+ {"current_steps": 728, "total_steps": 1235, "loss": 0.2144, "lr": 1.7265705518927437e-05, "epoch": 2.9473684210526314, "percentage": 58.95, "elapsed_time": "3:21:11", "remaining_time": "2:20:06"}
729
+ {"current_steps": 729, "total_steps": 1235, "loss": 0.2079, "lr": 1.7209693221121542e-05, "epoch": 2.951417004048583, "percentage": 59.03, "elapsed_time": "3:21:24", "remaining_time": "2:19:48"}
730
+ {"current_steps": 730, "total_steps": 1235, "loss": 0.2221, "lr": 1.7153703234534302e-05, "epoch": 2.9554655870445345, "percentage": 59.11, "elapsed_time": "3:21:34", "remaining_time": "2:19:27"}
731
+ {"current_steps": 731, "total_steps": 1235, "loss": 0.2127, "lr": 1.709773600686015e-05, "epoch": 2.9595141700404857, "percentage": 59.19, "elapsed_time": "3:21:52", "remaining_time": "2:19:11"}
732
+ {"current_steps": 732, "total_steps": 1235, "loss": 0.2313, "lr": 1.7041791985611548e-05, "epoch": 2.9635627530364372, "percentage": 59.27, "elapsed_time": "3:22:11", "remaining_time": "2:18:56"}
733
+ {"current_steps": 733, "total_steps": 1235, "loss": 0.1997, "lr": 1.69858716181154e-05, "epoch": 2.967611336032389, "percentage": 59.35, "elapsed_time": "3:22:24", "remaining_time": "2:18:37"}
734
+ {"current_steps": 734, "total_steps": 1235, "loss": 0.2176, "lr": 1.692997535150948e-05, "epoch": 2.97165991902834, "percentage": 59.43, "elapsed_time": "3:22:40", "remaining_time": "2:18:20"}
735
+ {"current_steps": 735, "total_steps": 1235, "loss": 0.2188, "lr": 1.687410363273884e-05, "epoch": 2.9757085020242915, "percentage": 59.51, "elapsed_time": "3:22:56", "remaining_time": "2:18:03"}
736
+ {"current_steps": 736, "total_steps": 1235, "loss": 0.2238, "lr": 1.6818256908552257e-05, "epoch": 2.979757085020243, "percentage": 59.6, "elapsed_time": "3:23:17", "remaining_time": "2:17:49"}
737
+ {"current_steps": 737, "total_steps": 1235, "loss": 0.2148, "lr": 1.6762435625498646e-05, "epoch": 2.983805668016194, "percentage": 59.68, "elapsed_time": "3:23:34", "remaining_time": "2:17:33"}
738
+ {"current_steps": 738, "total_steps": 1235, "loss": 0.2113, "lr": 1.67066402299235e-05, "epoch": 2.9878542510121457, "percentage": 59.76, "elapsed_time": "3:23:50", "remaining_time": "2:17:16"}
739
+ {"current_steps": 739, "total_steps": 1235, "loss": 0.2234, "lr": 1.6650871167965313e-05, "epoch": 2.9919028340080973, "percentage": 59.84, "elapsed_time": "3:24:08", "remaining_time": "2:17:01"}
740
+ {"current_steps": 740, "total_steps": 1235, "loss": 0.2218, "lr": 1.6595128885552028e-05, "epoch": 2.9959514170040484, "percentage": 59.92, "elapsed_time": "3:24:19", "remaining_time": "2:16:40"}
741
+ {"current_steps": 741, "total_steps": 1235, "loss": 0.2082, "lr": 1.653941382839745e-05, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "3:24:34", "remaining_time": "2:16:23"}
742
+ {"current_steps": 742, "total_steps": 1235, "loss": 0.154, "lr": 1.6483726441997673e-05, "epoch": 3.0040485829959516, "percentage": 60.08, "elapsed_time": "3:26:27", "remaining_time": "2:17:10"}
743
+ {"current_steps": 743, "total_steps": 1235, "loss": 0.1621, "lr": 1.642806717162757e-05, "epoch": 3.0080971659919027, "percentage": 60.16, "elapsed_time": "3:26:47", "remaining_time": "2:16:56"}
744
+ {"current_steps": 744, "total_steps": 1235, "loss": 0.1581, "lr": 1.637243646233718e-05, "epoch": 3.0121457489878543, "percentage": 60.24, "elapsed_time": "3:27:06", "remaining_time": "2:16:40"}
745
+ {"current_steps": 745, "total_steps": 1235, "loss": 0.1551, "lr": 1.6316834758948174e-05, "epoch": 3.016194331983806, "percentage": 60.32, "elapsed_time": "3:27:20", "remaining_time": "2:16:22"}
746
+ {"current_steps": 746, "total_steps": 1235, "loss": 0.1557, "lr": 1.6261262506050282e-05, "epoch": 3.020242914979757, "percentage": 60.4, "elapsed_time": "3:27:39", "remaining_time": "2:16:07"}
747
+ {"current_steps": 747, "total_steps": 1235, "loss": 0.158, "lr": 1.620572014799777e-05, "epoch": 3.0242914979757085, "percentage": 60.49, "elapsed_time": "3:27:58", "remaining_time": "2:15:51"}
748
+ {"current_steps": 748, "total_steps": 1235, "loss": 0.1625, "lr": 1.6150208128905857e-05, "epoch": 3.02834008097166, "percentage": 60.57, "elapsed_time": "3:28:14", "remaining_time": "2:15:34"}
749
+ {"current_steps": 749, "total_steps": 1235, "loss": 0.1483, "lr": 1.6094726892647147e-05, "epoch": 3.032388663967611, "percentage": 60.65, "elapsed_time": "3:28:33", "remaining_time": "2:15:19"}
750
+ {"current_steps": 750, "total_steps": 1235, "loss": 0.1645, "lr": 1.6039276882848135e-05, "epoch": 3.0364372469635628, "percentage": 60.73, "elapsed_time": "3:28:51", "remaining_time": "2:15:03"}