neginr commited on
Commit
2b9fe6a
·
verified ·
1 Parent(s): 584b65d

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:bf81cab86821eca1e87a7ca640de428674e7dca9aacf03c3e1b09b4cac1c383a
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a54f1f3a54cf67c956ab127cbd48409c7924358ec50756699abfa417f980cf9
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8dadd027c93cd11fa8d2e13ffa0f1905c081600cc6034b0476cfd88ddc54d609
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2e4332c088756d6b3ca21dc869a4cfa8ae8942a2f3a0578f189cf67644758e1
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4919d244376d5cf1e5c8931e6bb95c1626cba29227ce1137fb069bd9fa8798b0
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ebdab4c564635fe8f5727a74be7c82c624bdd59397d7021caf46cdfb9417e5d
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fe6b3b90d8e8a4799d170d1e98d244246a166eaf77cb5780a50403ecdc372bb
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0234da0057abff1bbef696947d0c0fe3e5b6aba27ec674b1b588c7c8b84ff5ce
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -546,3 +546,250 @@
546
  {"current_steps": 499, "total_steps": 1235, "loss": 0.4359, "lr": 2.9770574396706364e-05, "epoch": 2.020242914979757, "percentage": 40.4, "elapsed_time": "2:53:55", "remaining_time": "4:16:31"}
547
  {"current_steps": 500, "total_steps": 1235, "loss": 0.4096, "lr": 2.972118904869376e-05, "epoch": 2.0242914979757085, "percentage": 40.49, "elapsed_time": "2:54:16", "remaining_time": "4:16:11"}
548
  {"current_steps": 501, "total_steps": 1235, "loss": 0.4799, "lr": 2.9671725970312563e-05, "epoch": 2.02834008097166, "percentage": 40.57, "elapsed_time": "2:54:37", "remaining_time": "4:15:50"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
546
  {"current_steps": 499, "total_steps": 1235, "loss": 0.4359, "lr": 2.9770574396706364e-05, "epoch": 2.020242914979757, "percentage": 40.4, "elapsed_time": "2:53:55", "remaining_time": "4:16:31"}
547
  {"current_steps": 500, "total_steps": 1235, "loss": 0.4096, "lr": 2.972118904869376e-05, "epoch": 2.0242914979757085, "percentage": 40.49, "elapsed_time": "2:54:16", "remaining_time": "4:16:11"}
548
  {"current_steps": 501, "total_steps": 1235, "loss": 0.4799, "lr": 2.9671725970312563e-05, "epoch": 2.02834008097166, "percentage": 40.57, "elapsed_time": "2:54:37", "remaining_time": "4:15:50"}
549
+ {"current_steps": 502, "total_steps": 1235, "loss": 0.3881, "lr": 2.9622185557068238e-05, "epoch": 2.032388663967611, "percentage": 40.65, "elapsed_time": "2:54:56", "remaining_time": "4:15:26"}
550
+ {"current_steps": 503, "total_steps": 1235, "loss": 0.4188, "lr": 2.95725682050846e-05, "epoch": 2.0364372469635628, "percentage": 40.73, "elapsed_time": "2:55:15", "remaining_time": "4:15:02"}
551
+ {"current_steps": 504, "total_steps": 1235, "loss": 0.4071, "lr": 2.9522874311100684e-05, "epoch": 2.0404858299595143, "percentage": 40.81, "elapsed_time": "2:55:36", "remaining_time": "4:14:41"}
552
+ {"current_steps": 505, "total_steps": 1235, "loss": 0.4421, "lr": 2.9473104272467526e-05, "epoch": 2.0445344129554655, "percentage": 40.89, "elapsed_time": "2:55:57", "remaining_time": "4:14:21"}
553
+ {"current_steps": 506, "total_steps": 1235, "loss": 0.403, "lr": 2.942325848714505e-05, "epoch": 2.048582995951417, "percentage": 40.97, "elapsed_time": "2:56:18", "remaining_time": "4:14:01"}
554
+ {"current_steps": 507, "total_steps": 1235, "loss": 0.4417, "lr": 2.9373337353698804e-05, "epoch": 2.0526315789473686, "percentage": 41.05, "elapsed_time": "2:56:41", "remaining_time": "4:13:42"}
555
+ {"current_steps": 508, "total_steps": 1235, "loss": 0.4294, "lr": 2.932334127129686e-05, "epoch": 2.0566801619433197, "percentage": 41.13, "elapsed_time": "2:57:02", "remaining_time": "4:13:21"}
556
+ {"current_steps": 509, "total_steps": 1235, "loss": 0.4277, "lr": 2.9273270639706547e-05, "epoch": 2.0607287449392713, "percentage": 41.21, "elapsed_time": "2:57:22", "remaining_time": "4:12:59"}
557
+ {"current_steps": 510, "total_steps": 1235, "loss": 0.4045, "lr": 2.922312585929131e-05, "epoch": 2.064777327935223, "percentage": 41.3, "elapsed_time": "2:57:43", "remaining_time": "4:12:39"}
558
+ {"current_steps": 511, "total_steps": 1235, "loss": 0.4156, "lr": 2.9172907331007478e-05, "epoch": 2.068825910931174, "percentage": 41.38, "elapsed_time": "2:58:04", "remaining_time": "4:12:17"}
559
+ {"current_steps": 512, "total_steps": 1235, "loss": 0.415, "lr": 2.9122615456401053e-05, "epoch": 2.0728744939271255, "percentage": 41.46, "elapsed_time": "2:58:24", "remaining_time": "4:11:56"}
560
+ {"current_steps": 513, "total_steps": 1235, "loss": 0.3965, "lr": 2.9072250637604535e-05, "epoch": 2.076923076923077, "percentage": 41.54, "elapsed_time": "2:58:47", "remaining_time": "4:11:37"}
561
+ {"current_steps": 514, "total_steps": 1235, "loss": 0.4048, "lr": 2.9021813277333667e-05, "epoch": 2.080971659919028, "percentage": 41.62, "elapsed_time": "2:59:07", "remaining_time": "4:11:16"}
562
+ {"current_steps": 515, "total_steps": 1235, "loss": 0.3877, "lr": 2.8971303778884244e-05, "epoch": 2.08502024291498, "percentage": 41.7, "elapsed_time": "2:59:30", "remaining_time": "4:10:57"}
563
+ {"current_steps": 516, "total_steps": 1235, "loss": 0.4315, "lr": 2.8920722546128863e-05, "epoch": 2.0890688259109313, "percentage": 41.78, "elapsed_time": "2:59:49", "remaining_time": "4:10:34"}
564
+ {"current_steps": 517, "total_steps": 1235, "loss": 0.4272, "lr": 2.887006998351372e-05, "epoch": 2.0931174089068825, "percentage": 41.86, "elapsed_time": "3:00:09", "remaining_time": "4:10:11"}
565
+ {"current_steps": 518, "total_steps": 1235, "loss": 0.4136, "lr": 2.881934649605535e-05, "epoch": 2.097165991902834, "percentage": 41.94, "elapsed_time": "3:00:29", "remaining_time": "4:09:50"}
566
+ {"current_steps": 519, "total_steps": 1235, "loss": 0.4155, "lr": 2.8768552489337408e-05, "epoch": 2.1012145748987856, "percentage": 42.02, "elapsed_time": "3:00:51", "remaining_time": "4:09:29"}
567
+ {"current_steps": 520, "total_steps": 1235, "loss": 0.4113, "lr": 2.8717688369507425e-05, "epoch": 2.1052631578947367, "percentage": 42.11, "elapsed_time": "3:01:11", "remaining_time": "4:09:08"}
568
+ {"current_steps": 521, "total_steps": 1235, "loss": 0.4058, "lr": 2.8666754543273535e-05, "epoch": 2.1093117408906883, "percentage": 42.19, "elapsed_time": "3:01:32", "remaining_time": "4:08:46"}
569
+ {"current_steps": 522, "total_steps": 1235, "loss": 0.4019, "lr": 2.8615751417901273e-05, "epoch": 2.11336032388664, "percentage": 42.27, "elapsed_time": "3:01:53", "remaining_time": "4:08:26"}
570
+ {"current_steps": 523, "total_steps": 1235, "loss": 0.3916, "lr": 2.856467940121025e-05, "epoch": 2.117408906882591, "percentage": 42.35, "elapsed_time": "3:02:11", "remaining_time": "4:08:02"}
571
+ {"current_steps": 524, "total_steps": 1235, "loss": 0.4396, "lr": 2.8513538901570964e-05, "epoch": 2.1214574898785425, "percentage": 42.43, "elapsed_time": "3:02:30", "remaining_time": "4:07:38"}
572
+ {"current_steps": 525, "total_steps": 1235, "loss": 0.4244, "lr": 2.846233032790149e-05, "epoch": 2.125506072874494, "percentage": 42.51, "elapsed_time": "3:02:49", "remaining_time": "4:07:14"}
573
+ {"current_steps": 526, "total_steps": 1235, "loss": 0.4349, "lr": 2.84110540896642e-05, "epoch": 2.1295546558704452, "percentage": 42.59, "elapsed_time": "3:03:09", "remaining_time": "4:06:52"}
574
+ {"current_steps": 527, "total_steps": 1235, "loss": 0.408, "lr": 2.8359710596862555e-05, "epoch": 2.133603238866397, "percentage": 42.67, "elapsed_time": "3:03:31", "remaining_time": "4:06:33"}
575
+ {"current_steps": 528, "total_steps": 1235, "loss": 0.436, "lr": 2.8308300260037734e-05, "epoch": 2.1376518218623484, "percentage": 42.75, "elapsed_time": "3:03:52", "remaining_time": "4:06:12"}
576
+ {"current_steps": 529, "total_steps": 1235, "loss": 0.4265, "lr": 2.8256823490265424e-05, "epoch": 2.1417004048582995, "percentage": 42.83, "elapsed_time": "3:04:13", "remaining_time": "4:05:51"}
577
+ {"current_steps": 530, "total_steps": 1235, "loss": 0.4229, "lr": 2.8205280699152515e-05, "epoch": 2.145748987854251, "percentage": 42.91, "elapsed_time": "3:04:34", "remaining_time": "4:05:30"}
578
+ {"current_steps": 531, "total_steps": 1235, "loss": 0.4325, "lr": 2.8153672298833777e-05, "epoch": 2.1497975708502026, "percentage": 43.0, "elapsed_time": "3:04:54", "remaining_time": "4:05:08"}
579
+ {"current_steps": 532, "total_steps": 1235, "loss": 0.3928, "lr": 2.8101998701968615e-05, "epoch": 2.1538461538461537, "percentage": 43.08, "elapsed_time": "3:05:14", "remaining_time": "4:04:46"}
580
+ {"current_steps": 533, "total_steps": 1235, "loss": 0.4244, "lr": 2.805026032173773e-05, "epoch": 2.1578947368421053, "percentage": 43.16, "elapsed_time": "3:05:30", "remaining_time": "4:04:20"}
581
+ {"current_steps": 534, "total_steps": 1235, "loss": 0.4137, "lr": 2.7998457571839832e-05, "epoch": 2.161943319838057, "percentage": 43.24, "elapsed_time": "3:05:50", "remaining_time": "4:03:57"}
582
+ {"current_steps": 535, "total_steps": 1235, "loss": 0.4348, "lr": 2.7946590866488322e-05, "epoch": 2.165991902834008, "percentage": 43.32, "elapsed_time": "3:06:12", "remaining_time": "4:03:38"}
583
+ {"current_steps": 536, "total_steps": 1235, "loss": 0.3951, "lr": 2.7894660620408e-05, "epoch": 2.1700404858299596, "percentage": 43.4, "elapsed_time": "3:06:31", "remaining_time": "4:03:15"}
584
+ {"current_steps": 537, "total_steps": 1235, "loss": 0.3983, "lr": 2.784266724883173e-05, "epoch": 2.174089068825911, "percentage": 43.48, "elapsed_time": "3:06:51", "remaining_time": "4:02:53"}
585
+ {"current_steps": 538, "total_steps": 1235, "loss": 0.4357, "lr": 2.7790611167497128e-05, "epoch": 2.1781376518218623, "percentage": 43.56, "elapsed_time": "3:07:15", "remaining_time": "4:02:35"}
586
+ {"current_steps": 539, "total_steps": 1235, "loss": 0.4227, "lr": 2.7738492792643224e-05, "epoch": 2.182186234817814, "percentage": 43.64, "elapsed_time": "3:07:35", "remaining_time": "4:02:14"}
587
+ {"current_steps": 540, "total_steps": 1235, "loss": 0.422, "lr": 2.768631254100716e-05, "epoch": 2.1862348178137654, "percentage": 43.72, "elapsed_time": "3:07:52", "remaining_time": "4:01:48"}
588
+ {"current_steps": 541, "total_steps": 1235, "loss": 0.4016, "lr": 2.7634070829820836e-05, "epoch": 2.1902834008097165, "percentage": 43.81, "elapsed_time": "3:08:13", "remaining_time": "4:01:28"}
589
+ {"current_steps": 542, "total_steps": 1235, "loss": 0.4274, "lr": 2.7581768076807592e-05, "epoch": 2.194331983805668, "percentage": 43.89, "elapsed_time": "3:08:35", "remaining_time": "4:01:08"}
590
+ {"current_steps": 543, "total_steps": 1235, "loss": 0.4013, "lr": 2.7529404700178832e-05, "epoch": 2.1983805668016196, "percentage": 43.97, "elapsed_time": "3:08:56", "remaining_time": "4:00:47"}
591
+ {"current_steps": 544, "total_steps": 1235, "loss": 0.4263, "lr": 2.7476981118630735e-05, "epoch": 2.2024291497975708, "percentage": 44.05, "elapsed_time": "3:09:17", "remaining_time": "4:00:25"}
592
+ {"current_steps": 545, "total_steps": 1235, "loss": 0.4252, "lr": 2.742449775134085e-05, "epoch": 2.2064777327935223, "percentage": 44.13, "elapsed_time": "3:09:37", "remaining_time": "4:00:04"}
593
+ {"current_steps": 546, "total_steps": 1235, "loss": 0.4024, "lr": 2.7371955017964788e-05, "epoch": 2.2105263157894735, "percentage": 44.21, "elapsed_time": "3:09:55", "remaining_time": "3:59:40"}
594
+ {"current_steps": 547, "total_steps": 1235, "loss": 0.4126, "lr": 2.7319353338632845e-05, "epoch": 2.214574898785425, "percentage": 44.29, "elapsed_time": "3:10:14", "remaining_time": "3:59:17"}
595
+ {"current_steps": 548, "total_steps": 1235, "loss": 0.42, "lr": 2.7266693133946645e-05, "epoch": 2.2186234817813766, "percentage": 44.37, "elapsed_time": "3:10:35", "remaining_time": "3:58:56"}
596
+ {"current_steps": 549, "total_steps": 1235, "loss": 0.4231, "lr": 2.7213974824975785e-05, "epoch": 2.2226720647773277, "percentage": 44.45, "elapsed_time": "3:10:57", "remaining_time": "3:58:36"}
597
+ {"current_steps": 550, "total_steps": 1235, "loss": 0.4303, "lr": 2.7161198833254464e-05, "epoch": 2.2267206477732793, "percentage": 44.53, "elapsed_time": "3:11:19", "remaining_time": "3:58:17"}
598
+ {"current_steps": 551, "total_steps": 1235, "loss": 0.4384, "lr": 2.7108365580778095e-05, "epoch": 2.230769230769231, "percentage": 44.62, "elapsed_time": "3:11:41", "remaining_time": "3:57:57"}
599
+ {"current_steps": 552, "total_steps": 1235, "loss": 0.3975, "lr": 2.705547548999996e-05, "epoch": 2.234817813765182, "percentage": 44.7, "elapsed_time": "3:11:58", "remaining_time": "3:57:32"}
600
+ {"current_steps": 553, "total_steps": 1235, "loss": 0.4175, "lr": 2.7002528983827817e-05, "epoch": 2.2388663967611335, "percentage": 44.78, "elapsed_time": "3:12:21", "remaining_time": "3:57:13"}
601
+ {"current_steps": 554, "total_steps": 1235, "loss": 0.4095, "lr": 2.6949526485620517e-05, "epoch": 2.242914979757085, "percentage": 44.86, "elapsed_time": "3:12:43", "remaining_time": "3:56:54"}
602
+ {"current_steps": 555, "total_steps": 1235, "loss": 0.4142, "lr": 2.6896468419184623e-05, "epoch": 2.246963562753036, "percentage": 44.94, "elapsed_time": "3:13:02", "remaining_time": "3:56:31"}
603
+ {"current_steps": 556, "total_steps": 1235, "loss": 0.4503, "lr": 2.6843355208771024e-05, "epoch": 2.251012145748988, "percentage": 45.02, "elapsed_time": "3:13:25", "remaining_time": "3:56:12"}
604
+ {"current_steps": 557, "total_steps": 1235, "loss": 0.4141, "lr": 2.6790187279071536e-05, "epoch": 2.2550607287449393, "percentage": 45.1, "elapsed_time": "3:13:45", "remaining_time": "3:55:51"}
605
+ {"current_steps": 558, "total_steps": 1235, "loss": 0.4178, "lr": 2.67369650552155e-05, "epoch": 2.2591093117408905, "percentage": 45.18, "elapsed_time": "3:14:06", "remaining_time": "3:55:30"}
606
+ {"current_steps": 559, "total_steps": 1235, "loss": 0.4088, "lr": 2.6683688962766407e-05, "epoch": 2.263157894736842, "percentage": 45.26, "elapsed_time": "3:14:27", "remaining_time": "3:55:09"}
607
+ {"current_steps": 560, "total_steps": 1235, "loss": 0.4224, "lr": 2.6630359427718468e-05, "epoch": 2.2672064777327936, "percentage": 45.34, "elapsed_time": "3:14:48", "remaining_time": "3:54:48"}
608
+ {"current_steps": 561, "total_steps": 1235, "loss": 0.4069, "lr": 2.6576976876493225e-05, "epoch": 2.2712550607287447, "percentage": 45.43, "elapsed_time": "3:15:09", "remaining_time": "3:54:28"}
609
+ {"current_steps": 562, "total_steps": 1235, "loss": 0.4129, "lr": 2.652354173593614e-05, "epoch": 2.2753036437246963, "percentage": 45.51, "elapsed_time": "3:15:30", "remaining_time": "3:54:07"}
610
+ {"current_steps": 563, "total_steps": 1235, "loss": 0.4428, "lr": 2.647005443331317e-05, "epoch": 2.279352226720648, "percentage": 45.59, "elapsed_time": "3:15:51", "remaining_time": "3:53:46"}
611
+ {"current_steps": 564, "total_steps": 1235, "loss": 0.4068, "lr": 2.6416515396307354e-05, "epoch": 2.283400809716599, "percentage": 45.67, "elapsed_time": "3:16:12", "remaining_time": "3:53:26"}
612
+ {"current_steps": 565, "total_steps": 1235, "loss": 0.4326, "lr": 2.636292505301542e-05, "epoch": 2.2874493927125505, "percentage": 45.75, "elapsed_time": "3:16:31", "remaining_time": "3:53:03"}
613
+ {"current_steps": 566, "total_steps": 1235, "loss": 0.3991, "lr": 2.630928383194431e-05, "epoch": 2.291497975708502, "percentage": 45.83, "elapsed_time": "3:16:53", "remaining_time": "3:52:43"}
614
+ {"current_steps": 567, "total_steps": 1235, "loss": 0.4129, "lr": 2.625559216200781e-05, "epoch": 2.2955465587044532, "percentage": 45.91, "elapsed_time": "3:17:12", "remaining_time": "3:52:20"}
615
+ {"current_steps": 568, "total_steps": 1235, "loss": 0.4389, "lr": 2.620185047252308e-05, "epoch": 2.299595141700405, "percentage": 45.99, "elapsed_time": "3:17:35", "remaining_time": "3:52:02"}
616
+ {"current_steps": 569, "total_steps": 1235, "loss": 0.3988, "lr": 2.614805919320723e-05, "epoch": 2.3036437246963564, "percentage": 46.07, "elapsed_time": "3:17:55", "remaining_time": "3:51:40"}
617
+ {"current_steps": 570, "total_steps": 1235, "loss": 0.4196, "lr": 2.6094218754173895e-05, "epoch": 2.3076923076923075, "percentage": 46.15, "elapsed_time": "3:18:16", "remaining_time": "3:51:19"}
618
+ {"current_steps": 571, "total_steps": 1235, "loss": 0.4097, "lr": 2.60403295859298e-05, "epoch": 2.311740890688259, "percentage": 46.23, "elapsed_time": "3:18:33", "remaining_time": "3:50:53"}
619
+ {"current_steps": 572, "total_steps": 1235, "loss": 0.4018, "lr": 2.5986392119371297e-05, "epoch": 2.3157894736842106, "percentage": 46.32, "elapsed_time": "3:18:56", "remaining_time": "3:50:34"}
620
+ {"current_steps": 573, "total_steps": 1235, "loss": 0.3885, "lr": 2.5932406785780928e-05, "epoch": 2.3198380566801617, "percentage": 46.4, "elapsed_time": "3:19:16", "remaining_time": "3:50:13"}
621
+ {"current_steps": 574, "total_steps": 1235, "loss": 0.398, "lr": 2.5878374016823987e-05, "epoch": 2.3238866396761133, "percentage": 46.48, "elapsed_time": "3:19:35", "remaining_time": "3:49:50"}
622
+ {"current_steps": 575, "total_steps": 1235, "loss": 0.4198, "lr": 2.5824294244545045e-05, "epoch": 2.327935222672065, "percentage": 46.56, "elapsed_time": "3:19:55", "remaining_time": "3:49:28"}
623
+ {"current_steps": 576, "total_steps": 1235, "loss": 0.4469, "lr": 2.577016790136453e-05, "epoch": 2.331983805668016, "percentage": 46.64, "elapsed_time": "3:20:13", "remaining_time": "3:49:04"}
624
+ {"current_steps": 577, "total_steps": 1235, "loss": 0.4215, "lr": 2.5715995420075225e-05, "epoch": 2.3360323886639676, "percentage": 46.72, "elapsed_time": "3:20:33", "remaining_time": "3:48:43"}
625
+ {"current_steps": 578, "total_steps": 1235, "loss": 0.4154, "lr": 2.5661777233838864e-05, "epoch": 2.340080971659919, "percentage": 46.8, "elapsed_time": "3:20:53", "remaining_time": "3:48:20"}
626
+ {"current_steps": 579, "total_steps": 1235, "loss": 0.4104, "lr": 2.5607513776182616e-05, "epoch": 2.3441295546558703, "percentage": 46.88, "elapsed_time": "3:21:12", "remaining_time": "3:47:57"}
627
+ {"current_steps": 580, "total_steps": 1235, "loss": 0.435, "lr": 2.5553205480995633e-05, "epoch": 2.348178137651822, "percentage": 46.96, "elapsed_time": "3:21:34", "remaining_time": "3:47:38"}
628
+ {"current_steps": 581, "total_steps": 1235, "loss": 0.3959, "lr": 2.5498852782525604e-05, "epoch": 2.3522267206477734, "percentage": 47.04, "elapsed_time": "3:21:53", "remaining_time": "3:47:15"}
629
+ {"current_steps": 582, "total_steps": 1235, "loss": 0.4268, "lr": 2.5444456115375252e-05, "epoch": 2.3562753036437245, "percentage": 47.13, "elapsed_time": "3:22:15", "remaining_time": "3:46:55"}
630
+ {"current_steps": 583, "total_steps": 1235, "loss": 0.4083, "lr": 2.539001591449889e-05, "epoch": 2.360323886639676, "percentage": 47.21, "elapsed_time": "3:22:35", "remaining_time": "3:46:34"}
631
+ {"current_steps": 584, "total_steps": 1235, "loss": 0.3885, "lr": 2.53355326151989e-05, "epoch": 2.3643724696356276, "percentage": 47.29, "elapsed_time": "3:22:56", "remaining_time": "3:46:13"}
632
+ {"current_steps": 585, "total_steps": 1235, "loss": 0.3883, "lr": 2.5281006653122288e-05, "epoch": 2.3684210526315788, "percentage": 47.37, "elapsed_time": "3:23:17", "remaining_time": "3:45:53"}
633
+ {"current_steps": 586, "total_steps": 1235, "loss": 0.3796, "lr": 2.5226438464257217e-05, "epoch": 2.3724696356275303, "percentage": 47.45, "elapsed_time": "3:23:38", "remaining_time": "3:45:31"}
634
+ {"current_steps": 587, "total_steps": 1235, "loss": 0.3907, "lr": 2.5171828484929447e-05, "epoch": 2.376518218623482, "percentage": 47.53, "elapsed_time": "3:23:57", "remaining_time": "3:45:09"}
635
+ {"current_steps": 588, "total_steps": 1235, "loss": 0.401, "lr": 2.5117177151798934e-05, "epoch": 2.380566801619433, "percentage": 47.61, "elapsed_time": "3:24:16", "remaining_time": "3:44:46"}
636
+ {"current_steps": 589, "total_steps": 1235, "loss": 0.4104, "lr": 2.506248490185627e-05, "epoch": 2.3846153846153846, "percentage": 47.69, "elapsed_time": "3:24:36", "remaining_time": "3:44:24"}
637
+ {"current_steps": 590, "total_steps": 1235, "loss": 0.4413, "lr": 2.500775217241923e-05, "epoch": 2.388663967611336, "percentage": 47.77, "elapsed_time": "3:24:58", "remaining_time": "3:44:04"}
638
+ {"current_steps": 591, "total_steps": 1235, "loss": 0.415, "lr": 2.4952979401129266e-05, "epoch": 2.3927125506072873, "percentage": 47.85, "elapsed_time": "3:25:16", "remaining_time": "3:43:40"}
639
+ {"current_steps": 592, "total_steps": 1235, "loss": 0.4117, "lr": 2.4898167025948e-05, "epoch": 2.396761133603239, "percentage": 47.94, "elapsed_time": "3:25:36", "remaining_time": "3:43:19"}
640
+ {"current_steps": 593, "total_steps": 1235, "loss": 0.4058, "lr": 2.4843315485153703e-05, "epoch": 2.4008097165991904, "percentage": 48.02, "elapsed_time": "3:25:57", "remaining_time": "3:42:58"}
641
+ {"current_steps": 594, "total_steps": 1235, "loss": 0.4115, "lr": 2.4788425217337856e-05, "epoch": 2.4048582995951415, "percentage": 48.1, "elapsed_time": "3:26:18", "remaining_time": "3:42:37"}
642
+ {"current_steps": 595, "total_steps": 1235, "loss": 0.4168, "lr": 2.4733496661401572e-05, "epoch": 2.408906882591093, "percentage": 48.18, "elapsed_time": "3:26:39", "remaining_time": "3:42:17"}
643
+ {"current_steps": 596, "total_steps": 1235, "loss": 0.4109, "lr": 2.4678530256552114e-05, "epoch": 2.4129554655870447, "percentage": 48.26, "elapsed_time": "3:27:02", "remaining_time": "3:41:59"}
644
+ {"current_steps": 597, "total_steps": 1235, "loss": 0.411, "lr": 2.46235264422994e-05, "epoch": 2.417004048582996, "percentage": 48.34, "elapsed_time": "3:27:24", "remaining_time": "3:41:39"}
645
+ {"current_steps": 598, "total_steps": 1235, "loss": 0.4197, "lr": 2.4568485658452452e-05, "epoch": 2.4210526315789473, "percentage": 48.42, "elapsed_time": "3:27:46", "remaining_time": "3:41:19"}
646
+ {"current_steps": 599, "total_steps": 1235, "loss": 0.428, "lr": 2.451340834511592e-05, "epoch": 2.425101214574899, "percentage": 48.5, "elapsed_time": "3:28:09", "remaining_time": "3:41:01"}
647
+ {"current_steps": 600, "total_steps": 1235, "loss": 0.4232, "lr": 2.4458294942686528e-05, "epoch": 2.42914979757085, "percentage": 48.58, "elapsed_time": "3:28:29", "remaining_time": "3:40:38"}
648
+ {"current_steps": 601, "total_steps": 1235, "loss": 0.4232, "lr": 2.440314589184958e-05, "epoch": 2.4331983805668016, "percentage": 48.66, "elapsed_time": "3:28:49", "remaining_time": "3:40:17"}
649
+ {"current_steps": 602, "total_steps": 1235, "loss": 0.4005, "lr": 2.434796163357541e-05, "epoch": 2.437246963562753, "percentage": 48.74, "elapsed_time": "3:29:08", "remaining_time": "3:39:54"}
650
+ {"current_steps": 603, "total_steps": 1235, "loss": 0.4072, "lr": 2.429274260911588e-05, "epoch": 2.4412955465587043, "percentage": 48.83, "elapsed_time": "3:29:28", "remaining_time": "3:39:33"}
651
+ {"current_steps": 604, "total_steps": 1235, "loss": 0.3976, "lr": 2.423748926000084e-05, "epoch": 2.445344129554656, "percentage": 48.91, "elapsed_time": "3:29:50", "remaining_time": "3:39:13"}
652
+ {"current_steps": 605, "total_steps": 1235, "loss": 0.3948, "lr": 2.418220202803459e-05, "epoch": 2.4493927125506074, "percentage": 48.99, "elapsed_time": "3:30:09", "remaining_time": "3:38:50"}
653
+ {"current_steps": 606, "total_steps": 1235, "loss": 0.3869, "lr": 2.412688135529237e-05, "epoch": 2.4534412955465585, "percentage": 49.07, "elapsed_time": "3:30:29", "remaining_time": "3:38:28"}
654
+ {"current_steps": 607, "total_steps": 1235, "loss": 0.4346, "lr": 2.4071527684116807e-05, "epoch": 2.45748987854251, "percentage": 49.15, "elapsed_time": "3:30:47", "remaining_time": "3:38:05"}
655
+ {"current_steps": 608, "total_steps": 1235, "loss": 0.4481, "lr": 2.4016141457114372e-05, "epoch": 2.4615384615384617, "percentage": 49.23, "elapsed_time": "3:31:06", "remaining_time": "3:37:42"}
656
+ {"current_steps": 609, "total_steps": 1235, "loss": 0.4182, "lr": 2.396072311715187e-05, "epoch": 2.465587044534413, "percentage": 49.31, "elapsed_time": "3:31:25", "remaining_time": "3:37:19"}
657
+ {"current_steps": 610, "total_steps": 1235, "loss": 0.4298, "lr": 2.3905273107352863e-05, "epoch": 2.4696356275303644, "percentage": 49.39, "elapsed_time": "3:31:44", "remaining_time": "3:36:56"}
658
+ {"current_steps": 611, "total_steps": 1235, "loss": 0.4181, "lr": 2.3849791871094157e-05, "epoch": 2.473684210526316, "percentage": 49.47, "elapsed_time": "3:32:03", "remaining_time": "3:36:34"}
659
+ {"current_steps": 612, "total_steps": 1235, "loss": 0.417, "lr": 2.379427985200223e-05, "epoch": 2.477732793522267, "percentage": 49.55, "elapsed_time": "3:32:25", "remaining_time": "3:36:14"}
660
+ {"current_steps": 613, "total_steps": 1235, "loss": 0.3992, "lr": 2.373873749394972e-05, "epoch": 2.4817813765182186, "percentage": 49.64, "elapsed_time": "3:32:46", "remaining_time": "3:35:53"}
661
+ {"current_steps": 614, "total_steps": 1235, "loss": 0.4223, "lr": 2.3683165241051836e-05, "epoch": 2.48582995951417, "percentage": 49.72, "elapsed_time": "3:33:04", "remaining_time": "3:35:30"}
662
+ {"current_steps": 615, "total_steps": 1235, "loss": 0.4421, "lr": 2.3627563537662823e-05, "epoch": 2.4898785425101213, "percentage": 49.8, "elapsed_time": "3:33:26", "remaining_time": "3:35:10"}
663
+ {"current_steps": 616, "total_steps": 1235, "loss": 0.3953, "lr": 2.3571932828372433e-05, "epoch": 2.493927125506073, "percentage": 49.88, "elapsed_time": "3:33:43", "remaining_time": "3:34:45"}
664
+ {"current_steps": 617, "total_steps": 1235, "loss": 0.4082, "lr": 2.351627355800233e-05, "epoch": 2.4979757085020244, "percentage": 49.96, "elapsed_time": "3:34:02", "remaining_time": "3:34:23"}
665
+ {"current_steps": 618, "total_steps": 1235, "loss": 0.3918, "lr": 2.346058617160256e-05, "epoch": 2.5020242914979756, "percentage": 50.04, "elapsed_time": "3:34:24", "remaining_time": "3:34:03"}
666
+ {"current_steps": 619, "total_steps": 1235, "loss": 0.4531, "lr": 2.3404871114447976e-05, "epoch": 2.506072874493927, "percentage": 50.12, "elapsed_time": "3:34:46", "remaining_time": "3:33:43"}
667
+ {"current_steps": 620, "total_steps": 1235, "loss": 0.4107, "lr": 2.334912883203469e-05, "epoch": 2.5101214574898787, "percentage": 50.2, "elapsed_time": "3:35:04", "remaining_time": "3:33:20"}
668
+ {"current_steps": 621, "total_steps": 1235, "loss": 0.4309, "lr": 2.3293359770076505e-05, "epoch": 2.51417004048583, "percentage": 50.28, "elapsed_time": "3:35:27", "remaining_time": "3:33:01"}
669
+ {"current_steps": 622, "total_steps": 1235, "loss": 0.3762, "lr": 2.323756437450136e-05, "epoch": 2.5182186234817814, "percentage": 50.36, "elapsed_time": "3:35:47", "remaining_time": "3:32:40"}
670
+ {"current_steps": 623, "total_steps": 1235, "loss": 0.4241, "lr": 2.3181743091447754e-05, "epoch": 2.522267206477733, "percentage": 50.45, "elapsed_time": "3:36:10", "remaining_time": "3:32:21"}
671
+ {"current_steps": 624, "total_steps": 1235, "loss": 0.4173, "lr": 2.3125896367261164e-05, "epoch": 2.526315789473684, "percentage": 50.53, "elapsed_time": "3:36:32", "remaining_time": "3:32:01"}
672
+ {"current_steps": 625, "total_steps": 1235, "loss": 0.43, "lr": 2.307002464849052e-05, "epoch": 2.5303643724696356, "percentage": 50.61, "elapsed_time": "3:36:51", "remaining_time": "3:31:39"}
673
+ {"current_steps": 626, "total_steps": 1235, "loss": 0.4342, "lr": 2.30141283818846e-05, "epoch": 2.534412955465587, "percentage": 50.69, "elapsed_time": "3:37:10", "remaining_time": "3:31:16"}
674
+ {"current_steps": 627, "total_steps": 1235, "loss": 0.4176, "lr": 2.2958208014388462e-05, "epoch": 2.5384615384615383, "percentage": 50.77, "elapsed_time": "3:37:32", "remaining_time": "3:30:57"}
675
+ {"current_steps": 628, "total_steps": 1235, "loss": 0.4293, "lr": 2.2902263993139857e-05, "epoch": 2.54251012145749, "percentage": 50.85, "elapsed_time": "3:37:53", "remaining_time": "3:30:35"}
676
+ {"current_steps": 629, "total_steps": 1235, "loss": 0.4191, "lr": 2.2846296765465708e-05, "epoch": 2.5465587044534415, "percentage": 50.93, "elapsed_time": "3:38:15", "remaining_time": "3:30:17"}
677
+ {"current_steps": 630, "total_steps": 1235, "loss": 0.4199, "lr": 2.2790306778878465e-05, "epoch": 2.5506072874493926, "percentage": 51.01, "elapsed_time": "3:38:38", "remaining_time": "3:29:57"}
678
+ {"current_steps": 631, "total_steps": 1235, "loss": 0.4003, "lr": 2.273429448107257e-05, "epoch": 2.554655870445344, "percentage": 51.09, "elapsed_time": "3:39:00", "remaining_time": "3:29:38"}
679
+ {"current_steps": 632, "total_steps": 1235, "loss": 0.4092, "lr": 2.2678260319920868e-05, "epoch": 2.5587044534412957, "percentage": 51.17, "elapsed_time": "3:39:21", "remaining_time": "3:29:17"}
680
+ {"current_steps": 633, "total_steps": 1235, "loss": 0.4088, "lr": 2.262220474347102e-05, "epoch": 2.562753036437247, "percentage": 51.26, "elapsed_time": "3:39:42", "remaining_time": "3:28:57"}
681
+ {"current_steps": 634, "total_steps": 1235, "loss": 0.4376, "lr": 2.2566128199941918e-05, "epoch": 2.5668016194331984, "percentage": 51.34, "elapsed_time": "3:40:03", "remaining_time": "3:28:35"}
682
+ {"current_steps": 635, "total_steps": 1235, "loss": 0.4313, "lr": 2.2510031137720104e-05, "epoch": 2.57085020242915, "percentage": 51.42, "elapsed_time": "3:40:22", "remaining_time": "3:28:13"}
683
+ {"current_steps": 636, "total_steps": 1235, "loss": 0.4181, "lr": 2.2453914005356206e-05, "epoch": 2.574898785425101, "percentage": 51.5, "elapsed_time": "3:40:42", "remaining_time": "3:27:51"}
684
+ {"current_steps": 637, "total_steps": 1235, "loss": 0.4028, "lr": 2.2397777251561302e-05, "epoch": 2.5789473684210527, "percentage": 51.58, "elapsed_time": "3:41:01", "remaining_time": "3:27:29"}
685
+ {"current_steps": 638, "total_steps": 1235, "loss": 0.411, "lr": 2.2341621325203393e-05, "epoch": 2.582995951417004, "percentage": 51.66, "elapsed_time": "3:41:21", "remaining_time": "3:27:07"}
686
+ {"current_steps": 639, "total_steps": 1235, "loss": 0.4288, "lr": 2.2285446675303764e-05, "epoch": 2.5870445344129553, "percentage": 51.74, "elapsed_time": "3:41:44", "remaining_time": "3:26:48"}
687
+ {"current_steps": 640, "total_steps": 1235, "loss": 0.4139, "lr": 2.2229253751033423e-05, "epoch": 2.591093117408907, "percentage": 51.82, "elapsed_time": "3:42:05", "remaining_time": "3:26:28"}
688
+ {"current_steps": 641, "total_steps": 1235, "loss": 0.4206, "lr": 2.2173043001709492e-05, "epoch": 2.5951417004048585, "percentage": 51.9, "elapsed_time": "3:42:27", "remaining_time": "3:26:09"}
689
+ {"current_steps": 642, "total_steps": 1235, "loss": 0.427, "lr": 2.2116814876791627e-05, "epoch": 2.5991902834008096, "percentage": 51.98, "elapsed_time": "3:42:50", "remaining_time": "3:25:49"}
690
+ {"current_steps": 643, "total_steps": 1235, "loss": 0.4144, "lr": 2.2060569825878413e-05, "epoch": 2.603238866396761, "percentage": 52.06, "elapsed_time": "3:43:10", "remaining_time": "3:25:28"}
691
+ {"current_steps": 644, "total_steps": 1235, "loss": 0.4078, "lr": 2.2004308298703777e-05, "epoch": 2.6072874493927127, "percentage": 52.15, "elapsed_time": "3:43:31", "remaining_time": "3:25:07"}
692
+ {"current_steps": 645, "total_steps": 1235, "loss": 0.4266, "lr": 2.1948030745133396e-05, "epoch": 2.611336032388664, "percentage": 52.23, "elapsed_time": "3:43:54", "remaining_time": "3:24:48"}
693
+ {"current_steps": 646, "total_steps": 1235, "loss": 0.4195, "lr": 2.1891737615161083e-05, "epoch": 2.6153846153846154, "percentage": 52.31, "elapsed_time": "3:44:15", "remaining_time": "3:24:28"}
694
+ {"current_steps": 647, "total_steps": 1235, "loss": 0.4243, "lr": 2.1835429358905218e-05, "epoch": 2.619433198380567, "percentage": 52.39, "elapsed_time": "3:44:36", "remaining_time": "3:24:07"}
695
+ {"current_steps": 648, "total_steps": 1235, "loss": 0.4057, "lr": 2.17791064266051e-05, "epoch": 2.623481781376518, "percentage": 52.47, "elapsed_time": "3:44:57", "remaining_time": "3:23:46"}
696
+ {"current_steps": 649, "total_steps": 1235, "loss": 0.4, "lr": 2.172276926861741e-05, "epoch": 2.6275303643724697, "percentage": 52.55, "elapsed_time": "3:45:15", "remaining_time": "3:23:23"}
697
+ {"current_steps": 650, "total_steps": 1235, "loss": 0.4091, "lr": 2.166641833541255e-05, "epoch": 2.6315789473684212, "percentage": 52.63, "elapsed_time": "3:45:38", "remaining_time": "3:23:04"}
698
+ {"current_steps": 651, "total_steps": 1235, "loss": 0.3851, "lr": 2.161005407757109e-05, "epoch": 2.6356275303643724, "percentage": 52.71, "elapsed_time": "3:45:58", "remaining_time": "3:22:43"}
699
+ {"current_steps": 652, "total_steps": 1235, "loss": 0.42, "lr": 2.155367694578013e-05, "epoch": 2.639676113360324, "percentage": 52.79, "elapsed_time": "3:46:19", "remaining_time": "3:22:22"}
700
+ {"current_steps": 653, "total_steps": 1235, "loss": 0.4124, "lr": 2.1497287390829712e-05, "epoch": 2.6437246963562755, "percentage": 52.87, "elapsed_time": "3:46:41", "remaining_time": "3:22:02"}
701
+ {"current_steps": 654, "total_steps": 1235, "loss": 0.4288, "lr": 2.1440885863609208e-05, "epoch": 2.6477732793522266, "percentage": 52.96, "elapsed_time": "3:47:02", "remaining_time": "3:21:42"}
702
+ {"current_steps": 655, "total_steps": 1235, "loss": 0.3994, "lr": 2.1384472815103737e-05, "epoch": 2.651821862348178, "percentage": 53.04, "elapsed_time": "3:47:24", "remaining_time": "3:21:21"}
703
+ {"current_steps": 656, "total_steps": 1235, "loss": 0.414, "lr": 2.1328048696390534e-05, "epoch": 2.6558704453441297, "percentage": 53.12, "elapsed_time": "3:47:44", "remaining_time": "3:21:00"}
704
+ {"current_steps": 657, "total_steps": 1235, "loss": 0.418, "lr": 2.1271613958635342e-05, "epoch": 2.659919028340081, "percentage": 53.2, "elapsed_time": "3:48:05", "remaining_time": "3:20:40"}
705
+ {"current_steps": 658, "total_steps": 1235, "loss": 0.3932, "lr": 2.1215169053088825e-05, "epoch": 2.6639676113360324, "percentage": 53.28, "elapsed_time": "3:48:26", "remaining_time": "3:20:19"}
706
+ {"current_steps": 659, "total_steps": 1235, "loss": 0.4029, "lr": 2.1158714431082937e-05, "epoch": 2.668016194331984, "percentage": 53.36, "elapsed_time": "3:48:46", "remaining_time": "3:19:57"}
707
+ {"current_steps": 660, "total_steps": 1235, "loss": 0.4197, "lr": 2.110225054402733e-05, "epoch": 2.672064777327935, "percentage": 53.44, "elapsed_time": "3:49:07", "remaining_time": "3:19:36"}
708
+ {"current_steps": 661, "total_steps": 1235, "loss": 0.4078, "lr": 2.1045777843405747e-05, "epoch": 2.6761133603238867, "percentage": 53.52, "elapsed_time": "3:49:28", "remaining_time": "3:19:16"}
709
+ {"current_steps": 662, "total_steps": 1235, "loss": 0.426, "lr": 2.09892967807724e-05, "epoch": 2.6801619433198383, "percentage": 53.6, "elapsed_time": "3:49:48", "remaining_time": "3:18:55"}
710
+ {"current_steps": 663, "total_steps": 1235, "loss": 0.4225, "lr": 2.093280780774835e-05, "epoch": 2.6842105263157894, "percentage": 53.68, "elapsed_time": "3:50:09", "remaining_time": "3:18:33"}
711
+ {"current_steps": 664, "total_steps": 1235, "loss": 0.4049, "lr": 2.087631137601793e-05, "epoch": 2.688259109311741, "percentage": 53.77, "elapsed_time": "3:50:32", "remaining_time": "3:18:14"}
712
+ {"current_steps": 665, "total_steps": 1235, "loss": 0.3945, "lr": 2.0819807937325104e-05, "epoch": 2.6923076923076925, "percentage": 53.85, "elapsed_time": "3:50:52", "remaining_time": "3:17:53"}
713
+ {"current_steps": 666, "total_steps": 1235, "loss": 0.4289, "lr": 2.0763297943469847e-05, "epoch": 2.6963562753036436, "percentage": 53.93, "elapsed_time": "3:51:12", "remaining_time": "3:17:32"}
714
+ {"current_steps": 667, "total_steps": 1235, "loss": 0.3884, "lr": 2.070678184630458e-05, "epoch": 2.700404858299595, "percentage": 54.01, "elapsed_time": "3:51:32", "remaining_time": "3:17:10"}
715
+ {"current_steps": 668, "total_steps": 1235, "loss": 0.4158, "lr": 2.06502600977305e-05, "epoch": 2.7044534412955468, "percentage": 54.09, "elapsed_time": "3:51:53", "remaining_time": "3:16:49"}
716
+ {"current_steps": 669, "total_steps": 1235, "loss": 0.4178, "lr": 2.0593733149694008e-05, "epoch": 2.708502024291498, "percentage": 54.17, "elapsed_time": "3:52:15", "remaining_time": "3:16:29"}
717
+ {"current_steps": 670, "total_steps": 1235, "loss": 0.412, "lr": 2.0537201454183074e-05, "epoch": 2.7125506072874495, "percentage": 54.25, "elapsed_time": "3:52:36", "remaining_time": "3:16:09"}
718
+ {"current_steps": 671, "total_steps": 1235, "loss": 0.422, "lr": 2.0480665463223626e-05, "epoch": 2.716599190283401, "percentage": 54.33, "elapsed_time": "3:52:58", "remaining_time": "3:15:49"}
719
+ {"current_steps": 672, "total_steps": 1235, "loss": 0.4191, "lr": 2.042412562887594e-05, "epoch": 2.720647773279352, "percentage": 54.41, "elapsed_time": "3:53:17", "remaining_time": "3:15:27"}
720
+ {"current_steps": 673, "total_steps": 1235, "loss": 0.4162, "lr": 2.0367582403231033e-05, "epoch": 2.7246963562753037, "percentage": 54.49, "elapsed_time": "3:53:37", "remaining_time": "3:15:05"}
721
+ {"current_steps": 674, "total_steps": 1235, "loss": 0.3689, "lr": 2.0311036238407023e-05, "epoch": 2.7287449392712553, "percentage": 54.57, "elapsed_time": "3:53:56", "remaining_time": "3:14:42"}
722
+ {"current_steps": 675, "total_steps": 1235, "loss": 0.4076, "lr": 2.0254487586545534e-05, "epoch": 2.7327935222672064, "percentage": 54.66, "elapsed_time": "3:54:16", "remaining_time": "3:14:21"}
723
+ {"current_steps": 676, "total_steps": 1235, "loss": 0.4135, "lr": 2.0197936899808088e-05, "epoch": 2.736842105263158, "percentage": 54.74, "elapsed_time": "3:54:36", "remaining_time": "3:14:00"}
724
+ {"current_steps": 677, "total_steps": 1235, "loss": 0.4187, "lr": 2.0141384630372466e-05, "epoch": 2.7408906882591095, "percentage": 54.82, "elapsed_time": "3:54:57", "remaining_time": "3:13:39"}
725
+ {"current_steps": 678, "total_steps": 1235, "loss": 0.4161, "lr": 2.0084831230429106e-05, "epoch": 2.7449392712550607, "percentage": 54.9, "elapsed_time": "3:55:18", "remaining_time": "3:13:18"}
726
+ {"current_steps": 679, "total_steps": 1235, "loss": 0.4081, "lr": 2.0028277152177492e-05, "epoch": 2.748987854251012, "percentage": 54.98, "elapsed_time": "3:55:39", "remaining_time": "3:12:57"}
727
+ {"current_steps": 680, "total_steps": 1235, "loss": 0.4293, "lr": 1.9971722847822518e-05, "epoch": 2.753036437246964, "percentage": 55.06, "elapsed_time": "3:55:56", "remaining_time": "3:12:34"}
728
+ {"current_steps": 681, "total_steps": 1235, "loss": 0.4139, "lr": 1.99151687695709e-05, "epoch": 2.757085020242915, "percentage": 55.14, "elapsed_time": "3:56:18", "remaining_time": "3:12:14"}
729
+ {"current_steps": 682, "total_steps": 1235, "loss": 0.4302, "lr": 1.9858615369627537e-05, "epoch": 2.7611336032388665, "percentage": 55.22, "elapsed_time": "3:56:38", "remaining_time": "3:11:52"}
730
+ {"current_steps": 683, "total_steps": 1235, "loss": 0.4326, "lr": 1.9802063100191916e-05, "epoch": 2.765182186234818, "percentage": 55.3, "elapsed_time": "3:56:58", "remaining_time": "3:11:31"}
731
+ {"current_steps": 684, "total_steps": 1235, "loss": 0.3997, "lr": 1.974551241345447e-05, "epoch": 2.769230769230769, "percentage": 55.38, "elapsed_time": "3:57:18", "remaining_time": "3:11:10"}
732
+ {"current_steps": 685, "total_steps": 1235, "loss": 0.4236, "lr": 1.9688963761592984e-05, "epoch": 2.7732793522267207, "percentage": 55.47, "elapsed_time": "3:57:39", "remaining_time": "3:10:48"}
733
+ {"current_steps": 686, "total_steps": 1235, "loss": 0.4079, "lr": 1.963241759676897e-05, "epoch": 2.7773279352226723, "percentage": 55.55, "elapsed_time": "3:57:59", "remaining_time": "3:10:28"}
734
+ {"current_steps": 687, "total_steps": 1235, "loss": 0.4201, "lr": 1.9575874371124066e-05, "epoch": 2.7813765182186234, "percentage": 55.63, "elapsed_time": "3:58:19", "remaining_time": "3:10:06"}
735
+ {"current_steps": 688, "total_steps": 1235, "loss": 0.4131, "lr": 1.951933453677638e-05, "epoch": 2.785425101214575, "percentage": 55.71, "elapsed_time": "3:58:40", "remaining_time": "3:09:45"}
736
+ {"current_steps": 689, "total_steps": 1235, "loss": 0.4143, "lr": 1.9462798545816932e-05, "epoch": 2.7894736842105265, "percentage": 55.79, "elapsed_time": "3:59:00", "remaining_time": "3:09:24"}
737
+ {"current_steps": 690, "total_steps": 1235, "loss": 0.4036, "lr": 1.9406266850305996e-05, "epoch": 2.7935222672064777, "percentage": 55.87, "elapsed_time": "3:59:21", "remaining_time": "3:09:03"}
738
+ {"current_steps": 691, "total_steps": 1235, "loss": 0.4005, "lr": 1.9349739902269503e-05, "epoch": 2.7975708502024292, "percentage": 55.95, "elapsed_time": "3:59:37", "remaining_time": "3:08:39"}
739
+ {"current_steps": 692, "total_steps": 1235, "loss": 0.4152, "lr": 1.9293218153695425e-05, "epoch": 2.801619433198381, "percentage": 56.03, "elapsed_time": "3:59:56", "remaining_time": "3:08:16"}
740
+ {"current_steps": 693, "total_steps": 1235, "loss": 0.4049, "lr": 1.9236702056530153e-05, "epoch": 2.805668016194332, "percentage": 56.11, "elapsed_time": "4:00:17", "remaining_time": "3:07:56"}
741
+ {"current_steps": 694, "total_steps": 1235, "loss": 0.3971, "lr": 1.9180192062674907e-05, "epoch": 2.8097165991902835, "percentage": 56.19, "elapsed_time": "4:00:35", "remaining_time": "3:07:33"}
742
+ {"current_steps": 695, "total_steps": 1235, "loss": 0.4218, "lr": 1.9123688623982076e-05, "epoch": 2.813765182186235, "percentage": 56.28, "elapsed_time": "4:00:56", "remaining_time": "3:07:12"}
743
+ {"current_steps": 696, "total_steps": 1235, "loss": 0.4337, "lr": 1.906719219225165e-05, "epoch": 2.817813765182186, "percentage": 56.36, "elapsed_time": "4:01:18", "remaining_time": "3:06:52"}
744
+ {"current_steps": 697, "total_steps": 1235, "loss": 0.4107, "lr": 1.9010703219227603e-05, "epoch": 2.8218623481781377, "percentage": 56.44, "elapsed_time": "4:01:38", "remaining_time": "3:06:30"}
745
+ {"current_steps": 698, "total_steps": 1235, "loss": 0.3906, "lr": 1.8954222156594256e-05, "epoch": 2.8259109311740893, "percentage": 56.52, "elapsed_time": "4:01:58", "remaining_time": "3:06:09"}
746
+ {"current_steps": 699, "total_steps": 1235, "loss": 0.423, "lr": 1.8897749455972673e-05, "epoch": 2.8299595141700404, "percentage": 56.6, "elapsed_time": "4:02:17", "remaining_time": "3:05:47"}
747
+ {"current_steps": 700, "total_steps": 1235, "loss": 0.3979, "lr": 1.884128556891707e-05, "epoch": 2.834008097165992, "percentage": 56.68, "elapsed_time": "4:02:39", "remaining_time": "3:05:27"}
748
+ {"current_steps": 701, "total_steps": 1235, "loss": 0.4124, "lr": 1.878483094691119e-05, "epoch": 2.8380566801619436, "percentage": 56.76, "elapsed_time": "4:03:01", "remaining_time": "3:05:07"}
749
+ {"current_steps": 702, "total_steps": 1235, "loss": 0.4344, "lr": 1.8728386041364664e-05, "epoch": 2.8421052631578947, "percentage": 56.84, "elapsed_time": "4:03:23", "remaining_time": "3:04:48"}
750
+ {"current_steps": 703, "total_steps": 1235, "loss": 0.4147, "lr": 1.867195130360947e-05, "epoch": 2.8461538461538463, "percentage": 56.92, "elapsed_time": "4:03:43", "remaining_time": "3:04:26"}
751
+ {"current_steps": 704, "total_steps": 1235, "loss": 0.4338, "lr": 1.8615527184896263e-05, "epoch": 2.850202429149798, "percentage": 57.0, "elapsed_time": "4:04:04", "remaining_time": "3:04:05"}
752
+ {"current_steps": 705, "total_steps": 1235, "loss": 0.4277, "lr": 1.8559114136390795e-05, "epoch": 2.854251012145749, "percentage": 57.09, "elapsed_time": "4:04:27", "remaining_time": "3:03:46"}
753
+ {"current_steps": 706, "total_steps": 1235, "loss": 0.4176, "lr": 1.8502712609170298e-05, "epoch": 2.8582995951417005, "percentage": 57.17, "elapsed_time": "4:04:46", "remaining_time": "3:03:24"}
754
+ {"current_steps": 707, "total_steps": 1235, "loss": 0.4151, "lr": 1.8446323054219876e-05, "epoch": 2.862348178137652, "percentage": 57.25, "elapsed_time": "4:05:07", "remaining_time": "3:03:04"}
755
+ {"current_steps": 708, "total_steps": 1235, "loss": 0.4299, "lr": 1.838994592242891e-05, "epoch": 2.866396761133603, "percentage": 57.33, "elapsed_time": "4:05:27", "remaining_time": "3:02:42"}
756
+ {"current_steps": 709, "total_steps": 1235, "loss": 0.4353, "lr": 1.8333581664587453e-05, "epoch": 2.8704453441295548, "percentage": 57.41, "elapsed_time": "4:05:48", "remaining_time": "3:02:21"}
757
+ {"current_steps": 710, "total_steps": 1235, "loss": 0.3972, "lr": 1.8277230731382593e-05, "epoch": 2.8744939271255063, "percentage": 57.49, "elapsed_time": "4:06:06", "remaining_time": "3:01:59"}
758
+ {"current_steps": 711, "total_steps": 1235, "loss": 0.4188, "lr": 1.82208935733949e-05, "epoch": 2.8785425101214575, "percentage": 57.57, "elapsed_time": "4:06:27", "remaining_time": "3:01:38"}
759
+ {"current_steps": 712, "total_steps": 1235, "loss": 0.4184, "lr": 1.8164570641094793e-05, "epoch": 2.882591093117409, "percentage": 57.65, "elapsed_time": "4:06:48", "remaining_time": "3:01:17"}
760
+ {"current_steps": 713, "total_steps": 1235, "loss": 0.4049, "lr": 1.810826238483892e-05, "epoch": 2.8866396761133606, "percentage": 57.73, "elapsed_time": "4:07:06", "remaining_time": "3:00:54"}
761
+ {"current_steps": 714, "total_steps": 1235, "loss": 0.4138, "lr": 1.8051969254866608e-05, "epoch": 2.8906882591093117, "percentage": 57.81, "elapsed_time": "4:07:26", "remaining_time": "3:00:33"}
762
+ {"current_steps": 715, "total_steps": 1235, "loss": 0.4341, "lr": 1.7995691701296226e-05, "epoch": 2.8947368421052633, "percentage": 57.89, "elapsed_time": "4:07:49", "remaining_time": "3:00:13"}
763
+ {"current_steps": 716, "total_steps": 1235, "loss": 0.4188, "lr": 1.7939430174121593e-05, "epoch": 2.898785425101215, "percentage": 57.98, "elapsed_time": "4:08:09", "remaining_time": "2:59:53"}
764
+ {"current_steps": 717, "total_steps": 1235, "loss": 0.4485, "lr": 1.788318512320838e-05, "epoch": 2.902834008097166, "percentage": 58.06, "elapsed_time": "4:08:31", "remaining_time": "2:59:32"}
765
+ {"current_steps": 718, "total_steps": 1235, "loss": 0.4051, "lr": 1.782695699829051e-05, "epoch": 2.9068825910931175, "percentage": 58.14, "elapsed_time": "4:08:50", "remaining_time": "2:59:10"}
766
+ {"current_steps": 719, "total_steps": 1235, "loss": 0.4133, "lr": 1.7770746248966587e-05, "epoch": 2.910931174089069, "percentage": 58.22, "elapsed_time": "4:09:10", "remaining_time": "2:58:49"}
767
+ {"current_steps": 720, "total_steps": 1235, "loss": 0.4115, "lr": 1.7714553324696243e-05, "epoch": 2.91497975708502, "percentage": 58.3, "elapsed_time": "4:09:30", "remaining_time": "2:58:28"}
768
+ {"current_steps": 721, "total_steps": 1235, "loss": 0.4162, "lr": 1.7658378674796614e-05, "epoch": 2.919028340080972, "percentage": 58.38, "elapsed_time": "4:09:52", "remaining_time": "2:58:08"}
769
+ {"current_steps": 722, "total_steps": 1235, "loss": 0.4171, "lr": 1.76022227484387e-05, "epoch": 2.9230769230769234, "percentage": 58.46, "elapsed_time": "4:10:11", "remaining_time": "2:57:45"}
770
+ {"current_steps": 723, "total_steps": 1235, "loss": 0.4064, "lr": 1.7546085994643807e-05, "epoch": 2.9271255060728745, "percentage": 58.54, "elapsed_time": "4:10:31", "remaining_time": "2:57:24"}
771
+ {"current_steps": 724, "total_steps": 1235, "loss": 0.4097, "lr": 1.7489968862279902e-05, "epoch": 2.931174089068826, "percentage": 58.62, "elapsed_time": "4:10:54", "remaining_time": "2:57:05"}
772
+ {"current_steps": 725, "total_steps": 1235, "loss": 0.3974, "lr": 1.743387180005809e-05, "epoch": 2.9352226720647776, "percentage": 58.7, "elapsed_time": "4:11:15", "remaining_time": "2:56:44"}
773
+ {"current_steps": 726, "total_steps": 1235, "loss": 0.4199, "lr": 1.737779525652899e-05, "epoch": 2.9392712550607287, "percentage": 58.79, "elapsed_time": "4:11:36", "remaining_time": "2:56:24"}
774
+ {"current_steps": 727, "total_steps": 1235, "loss": 0.3969, "lr": 1.732173968007914e-05, "epoch": 2.9433198380566803, "percentage": 58.87, "elapsed_time": "4:11:55", "remaining_time": "2:56:01"}
775
+ {"current_steps": 728, "total_steps": 1235, "loss": 0.4294, "lr": 1.7265705518927437e-05, "epoch": 2.9473684210526314, "percentage": 58.95, "elapsed_time": "4:12:14", "remaining_time": "2:55:40"}
776
+ {"current_steps": 729, "total_steps": 1235, "loss": 0.4126, "lr": 1.7209693221121542e-05, "epoch": 2.951417004048583, "percentage": 59.03, "elapsed_time": "4:12:32", "remaining_time": "2:55:17"}
777
+ {"current_steps": 730, "total_steps": 1235, "loss": 0.4069, "lr": 1.7153703234534302e-05, "epoch": 2.9554655870445345, "percentage": 59.11, "elapsed_time": "4:12:55", "remaining_time": "2:54:58"}
778
+ {"current_steps": 731, "total_steps": 1235, "loss": 0.4101, "lr": 1.709773600686015e-05, "epoch": 2.9595141700404857, "percentage": 59.19, "elapsed_time": "4:13:17", "remaining_time": "2:54:37"}
779
+ {"current_steps": 732, "total_steps": 1235, "loss": 0.4257, "lr": 1.7041791985611548e-05, "epoch": 2.9635627530364372, "percentage": 59.27, "elapsed_time": "4:13:35", "remaining_time": "2:54:15"}
780
+ {"current_steps": 733, "total_steps": 1235, "loss": 0.4087, "lr": 1.69858716181154e-05, "epoch": 2.967611336032389, "percentage": 59.35, "elapsed_time": "4:13:56", "remaining_time": "2:53:54"}
781
+ {"current_steps": 734, "total_steps": 1235, "loss": 0.4199, "lr": 1.692997535150948e-05, "epoch": 2.97165991902834, "percentage": 59.43, "elapsed_time": "4:14:19", "remaining_time": "2:53:35"}
782
+ {"current_steps": 735, "total_steps": 1235, "loss": 0.4164, "lr": 1.687410363273884e-05, "epoch": 2.9757085020242915, "percentage": 59.51, "elapsed_time": "4:14:40", "remaining_time": "2:53:14"}
783
+ {"current_steps": 736, "total_steps": 1235, "loss": 0.4127, "lr": 1.6818256908552257e-05, "epoch": 2.979757085020243, "percentage": 59.6, "elapsed_time": "4:15:00", "remaining_time": "2:52:53"}
784
+ {"current_steps": 737, "total_steps": 1235, "loss": 0.4016, "lr": 1.6762435625498646e-05, "epoch": 2.983805668016194, "percentage": 59.68, "elapsed_time": "4:15:19", "remaining_time": "2:52:31"}
785
+ {"current_steps": 738, "total_steps": 1235, "loss": 0.4114, "lr": 1.67066402299235e-05, "epoch": 2.9878542510121457, "percentage": 59.76, "elapsed_time": "4:15:41", "remaining_time": "2:52:11"}
786
+ {"current_steps": 739, "total_steps": 1235, "loss": 0.4149, "lr": 1.6650871167965313e-05, "epoch": 2.9919028340080973, "percentage": 59.84, "elapsed_time": "4:15:59", "remaining_time": "2:51:49"}
787
+ {"current_steps": 740, "total_steps": 1235, "loss": 0.4255, "lr": 1.6595128885552028e-05, "epoch": 2.9959514170040484, "percentage": 59.92, "elapsed_time": "4:16:20", "remaining_time": "2:51:28"}
788
+ {"current_steps": 741, "total_steps": 1235, "loss": 0.4182, "lr": 1.653941382839745e-05, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "4:16:38", "remaining_time": "2:51:05"}
789
+ {"current_steps": 742, "total_steps": 1235, "loss": 0.3037, "lr": 1.6483726441997673e-05, "epoch": 3.0040485829959516, "percentage": 60.08, "elapsed_time": "4:18:45", "remaining_time": "2:51:55"}
790
+ {"current_steps": 743, "total_steps": 1235, "loss": 0.3098, "lr": 1.642806717162757e-05, "epoch": 3.0080971659919027, "percentage": 60.16, "elapsed_time": "4:19:07", "remaining_time": "2:51:35"}
791
+ {"current_steps": 744, "total_steps": 1235, "loss": 0.3237, "lr": 1.637243646233718e-05, "epoch": 3.0121457489878543, "percentage": 60.24, "elapsed_time": "4:19:28", "remaining_time": "2:51:14"}
792
+ {"current_steps": 745, "total_steps": 1235, "loss": 0.3087, "lr": 1.6316834758948174e-05, "epoch": 3.016194331983806, "percentage": 60.32, "elapsed_time": "4:19:50", "remaining_time": "2:50:54"}
793
+ {"current_steps": 746, "total_steps": 1235, "loss": 0.3245, "lr": 1.6261262506050282e-05, "epoch": 3.020242914979757, "percentage": 60.4, "elapsed_time": "4:20:10", "remaining_time": "2:50:32"}
794
+ {"current_steps": 747, "total_steps": 1235, "loss": 0.3237, "lr": 1.620572014799777e-05, "epoch": 3.0242914979757085, "percentage": 60.49, "elapsed_time": "4:20:30", "remaining_time": "2:50:11"}
795
+ {"current_steps": 748, "total_steps": 1235, "loss": 0.3496, "lr": 1.6150208128905857e-05, "epoch": 3.02834008097166, "percentage": 60.57, "elapsed_time": "4:20:53", "remaining_time": "2:49:51"}