neginr commited on
Commit
22b7072
·
verified ·
1 Parent(s): 53dc119

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:d70e3faf7c035120018bde5decd4a031043316cc536f3c3d98a86b5432f13c48
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e1e019ff898fcdc4f1b2bbcec20aaa540747768493f45ff1dc432d7809e1be9
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:fb88fddbb312a90fa607e5322013f202d0c8b11e9b701c260ca0d07a55077a27
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cad8933095486aa0ff0aecc5518e285a9e0cecade0c5d4ca3f39d4a360864c07
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ef8b2f0026eae0260e00830fbd94bc20810de01d26caa9f944eae423d5aa404
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c85371997efee5e39240fa1ee2809808069ea6017357d3afb49eeeee35754543
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c58310239cd9091fb9c24c5728aa75b80ac96a8a752df4b54159fb1bc2b36c4
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a542ac268888f074d137523d4775ceae9beb3614e420d1e25a1607881b083596
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -559,3 +559,250 @@
559
  {"current_steps": 559, "total_steps": 1235, "loss": 0.0945, "lr": 2.6683688962766407e-05, "epoch": 2.263157894736842, "percentage": 45.26, "elapsed_time": "3:08:10", "remaining_time": "3:47:33"}
560
  {"current_steps": 560, "total_steps": 1235, "loss": 0.0915, "lr": 2.6630359427718468e-05, "epoch": 2.2672064777327936, "percentage": 45.34, "elapsed_time": "3:08:30", "remaining_time": "3:47:13"}
561
  {"current_steps": 561, "total_steps": 1235, "loss": 0.0809, "lr": 2.6576976876493225e-05, "epoch": 2.2712550607287447, "percentage": 45.43, "elapsed_time": "3:08:48", "remaining_time": "3:46:50"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
559
  {"current_steps": 559, "total_steps": 1235, "loss": 0.0945, "lr": 2.6683688962766407e-05, "epoch": 2.263157894736842, "percentage": 45.26, "elapsed_time": "3:08:10", "remaining_time": "3:47:33"}
560
  {"current_steps": 560, "total_steps": 1235, "loss": 0.0915, "lr": 2.6630359427718468e-05, "epoch": 2.2672064777327936, "percentage": 45.34, "elapsed_time": "3:08:30", "remaining_time": "3:47:13"}
561
  {"current_steps": 561, "total_steps": 1235, "loss": 0.0809, "lr": 2.6576976876493225e-05, "epoch": 2.2712550607287447, "percentage": 45.43, "elapsed_time": "3:08:48", "remaining_time": "3:46:50"}
562
+ {"current_steps": 562, "total_steps": 1235, "loss": 0.1024, "lr": 2.652354173593614e-05, "epoch": 2.2753036437246963, "percentage": 45.51, "elapsed_time": "3:09:09", "remaining_time": "3:46:30"}
563
+ {"current_steps": 563, "total_steps": 1235, "loss": 0.0919, "lr": 2.647005443331317e-05, "epoch": 2.279352226720648, "percentage": 45.59, "elapsed_time": "3:09:24", "remaining_time": "3:46:04"}
564
+ {"current_steps": 564, "total_steps": 1235, "loss": 0.0892, "lr": 2.6416515396307354e-05, "epoch": 2.283400809716599, "percentage": 45.67, "elapsed_time": "3:09:45", "remaining_time": "3:45:46"}
565
+ {"current_steps": 565, "total_steps": 1235, "loss": 0.095, "lr": 2.636292505301542e-05, "epoch": 2.2874493927125505, "percentage": 45.75, "elapsed_time": "3:10:05", "remaining_time": "3:45:24"}
566
+ {"current_steps": 566, "total_steps": 1235, "loss": 0.1032, "lr": 2.630928383194431e-05, "epoch": 2.291497975708502, "percentage": 45.83, "elapsed_time": "3:10:24", "remaining_time": "3:45:04"}
567
+ {"current_steps": 567, "total_steps": 1235, "loss": 0.0844, "lr": 2.625559216200781e-05, "epoch": 2.2955465587044532, "percentage": 45.91, "elapsed_time": "3:10:44", "remaining_time": "3:44:43"}
568
+ {"current_steps": 568, "total_steps": 1235, "loss": 0.0867, "lr": 2.620185047252308e-05, "epoch": 2.299595141700405, "percentage": 45.99, "elapsed_time": "3:11:04", "remaining_time": "3:44:22"}
569
+ {"current_steps": 569, "total_steps": 1235, "loss": 0.0969, "lr": 2.614805919320723e-05, "epoch": 2.3036437246963564, "percentage": 46.07, "elapsed_time": "3:11:26", "remaining_time": "3:44:04"}
570
+ {"current_steps": 570, "total_steps": 1235, "loss": 0.0857, "lr": 2.6094218754173895e-05, "epoch": 2.3076923076923075, "percentage": 46.15, "elapsed_time": "3:11:44", "remaining_time": "3:43:42"}
571
+ {"current_steps": 571, "total_steps": 1235, "loss": 0.0835, "lr": 2.60403295859298e-05, "epoch": 2.311740890688259, "percentage": 46.23, "elapsed_time": "3:12:04", "remaining_time": "3:43:20"}
572
+ {"current_steps": 572, "total_steps": 1235, "loss": 0.1098, "lr": 2.5986392119371297e-05, "epoch": 2.3157894736842106, "percentage": 46.32, "elapsed_time": "3:12:24", "remaining_time": "3:43:01"}
573
+ {"current_steps": 573, "total_steps": 1235, "loss": 0.0993, "lr": 2.5932406785780928e-05, "epoch": 2.3198380566801617, "percentage": 46.4, "elapsed_time": "3:12:45", "remaining_time": "3:42:41"}
574
+ {"current_steps": 574, "total_steps": 1235, "loss": 0.0877, "lr": 2.5878374016823987e-05, "epoch": 2.3238866396761133, "percentage": 46.48, "elapsed_time": "3:13:06", "remaining_time": "3:42:22"}
575
+ {"current_steps": 575, "total_steps": 1235, "loss": 0.087, "lr": 2.5824294244545045e-05, "epoch": 2.327935222672065, "percentage": 46.56, "elapsed_time": "3:13:27", "remaining_time": "3:42:03"}
576
+ {"current_steps": 576, "total_steps": 1235, "loss": 0.0786, "lr": 2.577016790136453e-05, "epoch": 2.331983805668016, "percentage": 46.64, "elapsed_time": "3:13:49", "remaining_time": "3:41:44"}
577
+ {"current_steps": 577, "total_steps": 1235, "loss": 0.0831, "lr": 2.5715995420075225e-05, "epoch": 2.3360323886639676, "percentage": 46.72, "elapsed_time": "3:14:07", "remaining_time": "3:41:22"}
578
+ {"current_steps": 578, "total_steps": 1235, "loss": 0.0916, "lr": 2.5661777233838864e-05, "epoch": 2.340080971659919, "percentage": 46.8, "elapsed_time": "3:14:28", "remaining_time": "3:41:02"}
579
+ {"current_steps": 579, "total_steps": 1235, "loss": 0.0779, "lr": 2.5607513776182616e-05, "epoch": 2.3441295546558703, "percentage": 46.88, "elapsed_time": "3:14:46", "remaining_time": "3:40:40"}
580
+ {"current_steps": 580, "total_steps": 1235, "loss": 0.0912, "lr": 2.5553205480995633e-05, "epoch": 2.348178137651822, "percentage": 46.96, "elapsed_time": "3:15:06", "remaining_time": "3:40:20"}
581
+ {"current_steps": 581, "total_steps": 1235, "loss": 0.0854, "lr": 2.5498852782525604e-05, "epoch": 2.3522267206477734, "percentage": 47.04, "elapsed_time": "3:15:25", "remaining_time": "3:39:59"}
582
+ {"current_steps": 582, "total_steps": 1235, "loss": 0.0892, "lr": 2.5444456115375252e-05, "epoch": 2.3562753036437245, "percentage": 47.13, "elapsed_time": "3:15:44", "remaining_time": "3:39:36"}
583
+ {"current_steps": 583, "total_steps": 1235, "loss": 0.0817, "lr": 2.539001591449889e-05, "epoch": 2.360323886639676, "percentage": 47.21, "elapsed_time": "3:16:04", "remaining_time": "3:39:16"}
584
+ {"current_steps": 584, "total_steps": 1235, "loss": 0.0701, "lr": 2.53355326151989e-05, "epoch": 2.3643724696356276, "percentage": 47.29, "elapsed_time": "3:16:22", "remaining_time": "3:38:53"}
585
+ {"current_steps": 585, "total_steps": 1235, "loss": 0.0924, "lr": 2.5281006653122288e-05, "epoch": 2.3684210526315788, "percentage": 47.37, "elapsed_time": "3:16:40", "remaining_time": "3:38:31"}
586
+ {"current_steps": 586, "total_steps": 1235, "loss": 0.0876, "lr": 2.5226438464257217e-05, "epoch": 2.3724696356275303, "percentage": 47.45, "elapsed_time": "3:17:00", "remaining_time": "3:38:11"}
587
+ {"current_steps": 587, "total_steps": 1235, "loss": 0.0893, "lr": 2.5171828484929447e-05, "epoch": 2.376518218623482, "percentage": 47.53, "elapsed_time": "3:17:21", "remaining_time": "3:37:52"}
588
+ {"current_steps": 588, "total_steps": 1235, "loss": 0.0869, "lr": 2.5117177151798934e-05, "epoch": 2.380566801619433, "percentage": 47.61, "elapsed_time": "3:17:41", "remaining_time": "3:37:31"}
589
+ {"current_steps": 589, "total_steps": 1235, "loss": 0.0789, "lr": 2.506248490185627e-05, "epoch": 2.3846153846153846, "percentage": 47.69, "elapsed_time": "3:18:02", "remaining_time": "3:37:12"}
590
+ {"current_steps": 590, "total_steps": 1235, "loss": 0.0931, "lr": 2.500775217241923e-05, "epoch": 2.388663967611336, "percentage": 47.77, "elapsed_time": "3:18:22", "remaining_time": "3:36:52"}
591
+ {"current_steps": 591, "total_steps": 1235, "loss": 0.0968, "lr": 2.4952979401129266e-05, "epoch": 2.3927125506072873, "percentage": 47.85, "elapsed_time": "3:18:42", "remaining_time": "3:36:32"}
592
+ {"current_steps": 592, "total_steps": 1235, "loss": 0.0895, "lr": 2.4898167025948e-05, "epoch": 2.396761133603239, "percentage": 47.94, "elapsed_time": "3:19:03", "remaining_time": "3:36:12"}
593
+ {"current_steps": 593, "total_steps": 1235, "loss": 0.0791, "lr": 2.4843315485153703e-05, "epoch": 2.4008097165991904, "percentage": 48.02, "elapsed_time": "3:19:22", "remaining_time": "3:35:51"}
594
+ {"current_steps": 594, "total_steps": 1235, "loss": 0.0839, "lr": 2.4788425217337856e-05, "epoch": 2.4048582995951415, "percentage": 48.1, "elapsed_time": "3:19:44", "remaining_time": "3:35:32"}
595
+ {"current_steps": 595, "total_steps": 1235, "loss": 0.0825, "lr": 2.4733496661401572e-05, "epoch": 2.408906882591093, "percentage": 48.18, "elapsed_time": "3:20:03", "remaining_time": "3:35:11"}
596
+ {"current_steps": 596, "total_steps": 1235, "loss": 0.0741, "lr": 2.4678530256552114e-05, "epoch": 2.4129554655870447, "percentage": 48.26, "elapsed_time": "3:20:21", "remaining_time": "3:34:49"}
597
+ {"current_steps": 597, "total_steps": 1235, "loss": 0.0713, "lr": 2.46235264422994e-05, "epoch": 2.417004048582996, "percentage": 48.34, "elapsed_time": "3:20:42", "remaining_time": "3:34:29"}
598
+ {"current_steps": 598, "total_steps": 1235, "loss": 0.0661, "lr": 2.4568485658452452e-05, "epoch": 2.4210526315789473, "percentage": 48.42, "elapsed_time": "3:21:02", "remaining_time": "3:34:09"}
599
+ {"current_steps": 599, "total_steps": 1235, "loss": 0.0824, "lr": 2.451340834511592e-05, "epoch": 2.425101214574899, "percentage": 48.5, "elapsed_time": "3:21:21", "remaining_time": "3:33:47"}
600
+ {"current_steps": 600, "total_steps": 1235, "loss": 0.0808, "lr": 2.4458294942686528e-05, "epoch": 2.42914979757085, "percentage": 48.58, "elapsed_time": "3:21:38", "remaining_time": "3:33:24"}
601
+ {"current_steps": 601, "total_steps": 1235, "loss": 0.0708, "lr": 2.440314589184958e-05, "epoch": 2.4331983805668016, "percentage": 48.66, "elapsed_time": "3:21:57", "remaining_time": "3:33:03"}
602
+ {"current_steps": 602, "total_steps": 1235, "loss": 0.0556, "lr": 2.434796163357541e-05, "epoch": 2.437246963562753, "percentage": 48.74, "elapsed_time": "3:22:14", "remaining_time": "3:32:39"}
603
+ {"current_steps": 603, "total_steps": 1235, "loss": 0.071, "lr": 2.429274260911588e-05, "epoch": 2.4412955465587043, "percentage": 48.83, "elapsed_time": "3:22:35", "remaining_time": "3:32:19"}
604
+ {"current_steps": 604, "total_steps": 1235, "loss": 0.07, "lr": 2.423748926000084e-05, "epoch": 2.445344129554656, "percentage": 48.91, "elapsed_time": "3:22:51", "remaining_time": "3:31:55"}
605
+ {"current_steps": 605, "total_steps": 1235, "loss": 0.0832, "lr": 2.418220202803459e-05, "epoch": 2.4493927125506074, "percentage": 48.99, "elapsed_time": "3:23:12", "remaining_time": "3:31:36"}
606
+ {"current_steps": 606, "total_steps": 1235, "loss": 0.0622, "lr": 2.412688135529237e-05, "epoch": 2.4534412955465585, "percentage": 49.07, "elapsed_time": "3:23:29", "remaining_time": "3:31:13"}
607
+ {"current_steps": 607, "total_steps": 1235, "loss": 0.0711, "lr": 2.4071527684116807e-05, "epoch": 2.45748987854251, "percentage": 49.15, "elapsed_time": "3:23:47", "remaining_time": "3:30:50"}
608
+ {"current_steps": 608, "total_steps": 1235, "loss": 0.0866, "lr": 2.4016141457114372e-05, "epoch": 2.4615384615384617, "percentage": 49.23, "elapsed_time": "3:24:08", "remaining_time": "3:30:30"}
609
+ {"current_steps": 609, "total_steps": 1235, "loss": 0.0681, "lr": 2.396072311715187e-05, "epoch": 2.465587044534413, "percentage": 49.31, "elapsed_time": "3:24:30", "remaining_time": "3:30:12"}
610
+ {"current_steps": 610, "total_steps": 1235, "loss": 0.0845, "lr": 2.3905273107352863e-05, "epoch": 2.4696356275303644, "percentage": 49.39, "elapsed_time": "3:24:49", "remaining_time": "3:29:51"}
611
+ {"current_steps": 611, "total_steps": 1235, "loss": 0.0686, "lr": 2.3849791871094157e-05, "epoch": 2.473684210526316, "percentage": 49.47, "elapsed_time": "3:25:10", "remaining_time": "3:29:32"}
612
+ {"current_steps": 612, "total_steps": 1235, "loss": 0.0655, "lr": 2.379427985200223e-05, "epoch": 2.477732793522267, "percentage": 49.55, "elapsed_time": "3:25:29", "remaining_time": "3:29:11"}
613
+ {"current_steps": 613, "total_steps": 1235, "loss": 0.0612, "lr": 2.373873749394972e-05, "epoch": 2.4817813765182186, "percentage": 49.64, "elapsed_time": "3:25:48", "remaining_time": "3:28:49"}
614
+ {"current_steps": 614, "total_steps": 1235, "loss": 0.082, "lr": 2.3683165241051836e-05, "epoch": 2.48582995951417, "percentage": 49.72, "elapsed_time": "3:26:09", "remaining_time": "3:28:30"}
615
+ {"current_steps": 615, "total_steps": 1235, "loss": 0.0718, "lr": 2.3627563537662823e-05, "epoch": 2.4898785425101213, "percentage": 49.8, "elapsed_time": "3:26:27", "remaining_time": "3:28:08"}
616
+ {"current_steps": 616, "total_steps": 1235, "loss": 0.0753, "lr": 2.3571932828372433e-05, "epoch": 2.493927125506073, "percentage": 49.88, "elapsed_time": "3:26:49", "remaining_time": "3:27:49"}
617
+ {"current_steps": 617, "total_steps": 1235, "loss": 0.0792, "lr": 2.351627355800233e-05, "epoch": 2.4979757085020244, "percentage": 49.96, "elapsed_time": "3:27:09", "remaining_time": "3:27:30"}
618
+ {"current_steps": 618, "total_steps": 1235, "loss": 0.0784, "lr": 2.346058617160256e-05, "epoch": 2.5020242914979756, "percentage": 50.04, "elapsed_time": "3:27:30", "remaining_time": "3:27:10"}
619
+ {"current_steps": 619, "total_steps": 1235, "loss": 0.071, "lr": 2.3404871114447976e-05, "epoch": 2.506072874493927, "percentage": 50.12, "elapsed_time": "3:27:52", "remaining_time": "3:26:51"}
620
+ {"current_steps": 620, "total_steps": 1235, "loss": 0.0656, "lr": 2.334912883203469e-05, "epoch": 2.5101214574898787, "percentage": 50.2, "elapsed_time": "3:28:10", "remaining_time": "3:26:29"}
621
+ {"current_steps": 621, "total_steps": 1235, "loss": 0.0698, "lr": 2.3293359770076505e-05, "epoch": 2.51417004048583, "percentage": 50.28, "elapsed_time": "3:28:30", "remaining_time": "3:26:09"}
622
+ {"current_steps": 622, "total_steps": 1235, "loss": 0.0708, "lr": 2.323756437450136e-05, "epoch": 2.5182186234817814, "percentage": 50.36, "elapsed_time": "3:28:50", "remaining_time": "3:25:48"}
623
+ {"current_steps": 623, "total_steps": 1235, "loss": 0.0609, "lr": 2.3181743091447754e-05, "epoch": 2.522267206477733, "percentage": 50.45, "elapsed_time": "3:29:08", "remaining_time": "3:25:26"}
624
+ {"current_steps": 624, "total_steps": 1235, "loss": 0.067, "lr": 2.3125896367261164e-05, "epoch": 2.526315789473684, "percentage": 50.53, "elapsed_time": "3:29:26", "remaining_time": "3:25:04"}
625
+ {"current_steps": 625, "total_steps": 1235, "loss": 0.0578, "lr": 2.307002464849052e-05, "epoch": 2.5303643724696356, "percentage": 50.61, "elapsed_time": "3:29:47", "remaining_time": "3:24:45"}
626
+ {"current_steps": 626, "total_steps": 1235, "loss": 0.0591, "lr": 2.30141283818846e-05, "epoch": 2.534412955465587, "percentage": 50.69, "elapsed_time": "3:30:07", "remaining_time": "3:24:25"}
627
+ {"current_steps": 627, "total_steps": 1235, "loss": 0.0721, "lr": 2.2958208014388462e-05, "epoch": 2.5384615384615383, "percentage": 50.77, "elapsed_time": "3:30:25", "remaining_time": "3:24:03"}
628
+ {"current_steps": 628, "total_steps": 1235, "loss": 0.0663, "lr": 2.2902263993139857e-05, "epoch": 2.54251012145749, "percentage": 50.85, "elapsed_time": "3:30:47", "remaining_time": "3:23:44"}
629
+ {"current_steps": 629, "total_steps": 1235, "loss": 0.0658, "lr": 2.2846296765465708e-05, "epoch": 2.5465587044534415, "percentage": 50.93, "elapsed_time": "3:31:06", "remaining_time": "3:23:23"}
630
+ {"current_steps": 630, "total_steps": 1235, "loss": 0.0704, "lr": 2.2790306778878465e-05, "epoch": 2.5506072874493926, "percentage": 51.01, "elapsed_time": "3:31:26", "remaining_time": "3:23:03"}
631
+ {"current_steps": 631, "total_steps": 1235, "loss": 0.0623, "lr": 2.273429448107257e-05, "epoch": 2.554655870445344, "percentage": 51.09, "elapsed_time": "3:31:46", "remaining_time": "3:22:42"}
632
+ {"current_steps": 632, "total_steps": 1235, "loss": 0.0589, "lr": 2.2678260319920868e-05, "epoch": 2.5587044534412957, "percentage": 51.17, "elapsed_time": "3:32:05", "remaining_time": "3:22:21"}
633
+ {"current_steps": 633, "total_steps": 1235, "loss": 0.0746, "lr": 2.262220474347102e-05, "epoch": 2.562753036437247, "percentage": 51.26, "elapsed_time": "3:32:25", "remaining_time": "3:22:01"}
634
+ {"current_steps": 634, "total_steps": 1235, "loss": 0.0639, "lr": 2.2566128199941918e-05, "epoch": 2.5668016194331984, "percentage": 51.34, "elapsed_time": "3:32:46", "remaining_time": "3:21:41"}
635
+ {"current_steps": 635, "total_steps": 1235, "loss": 0.0669, "lr": 2.2510031137720104e-05, "epoch": 2.57085020242915, "percentage": 51.42, "elapsed_time": "3:33:09", "remaining_time": "3:21:24"}
636
+ {"current_steps": 636, "total_steps": 1235, "loss": 0.0657, "lr": 2.2453914005356206e-05, "epoch": 2.574898785425101, "percentage": 51.5, "elapsed_time": "3:33:30", "remaining_time": "3:21:05"}
637
+ {"current_steps": 637, "total_steps": 1235, "loss": 0.0716, "lr": 2.2397777251561302e-05, "epoch": 2.5789473684210527, "percentage": 51.58, "elapsed_time": "3:33:49", "remaining_time": "3:20:43"}
638
+ {"current_steps": 638, "total_steps": 1235, "loss": 0.0662, "lr": 2.2341621325203393e-05, "epoch": 2.582995951417004, "percentage": 51.66, "elapsed_time": "3:34:09", "remaining_time": "3:20:23"}
639
+ {"current_steps": 639, "total_steps": 1235, "loss": 0.0646, "lr": 2.2285446675303764e-05, "epoch": 2.5870445344129553, "percentage": 51.74, "elapsed_time": "3:34:30", "remaining_time": "3:20:04"}
640
+ {"current_steps": 640, "total_steps": 1235, "loss": 0.0625, "lr": 2.2229253751033423e-05, "epoch": 2.591093117408907, "percentage": 51.82, "elapsed_time": "3:34:48", "remaining_time": "3:19:41"}
641
+ {"current_steps": 641, "total_steps": 1235, "loss": 0.0569, "lr": 2.2173043001709492e-05, "epoch": 2.5951417004048585, "percentage": 51.9, "elapsed_time": "3:35:06", "remaining_time": "3:19:20"}
642
+ {"current_steps": 642, "total_steps": 1235, "loss": 0.0633, "lr": 2.2116814876791627e-05, "epoch": 2.5991902834008096, "percentage": 51.98, "elapsed_time": "3:35:24", "remaining_time": "3:18:58"}
643
+ {"current_steps": 643, "total_steps": 1235, "loss": 0.0664, "lr": 2.2060569825878413e-05, "epoch": 2.603238866396761, "percentage": 52.06, "elapsed_time": "3:35:45", "remaining_time": "3:18:38"}
644
+ {"current_steps": 644, "total_steps": 1235, "loss": 0.0623, "lr": 2.2004308298703777e-05, "epoch": 2.6072874493927127, "percentage": 52.15, "elapsed_time": "3:36:07", "remaining_time": "3:18:19"}
645
+ {"current_steps": 645, "total_steps": 1235, "loss": 0.0666, "lr": 2.1948030745133396e-05, "epoch": 2.611336032388664, "percentage": 52.23, "elapsed_time": "3:36:25", "remaining_time": "3:17:58"}
646
+ {"current_steps": 646, "total_steps": 1235, "loss": 0.0643, "lr": 2.1891737615161083e-05, "epoch": 2.6153846153846154, "percentage": 52.31, "elapsed_time": "3:36:45", "remaining_time": "3:17:38"}
647
+ {"current_steps": 647, "total_steps": 1235, "loss": 0.0637, "lr": 2.1835429358905218e-05, "epoch": 2.619433198380567, "percentage": 52.39, "elapsed_time": "3:37:06", "remaining_time": "3:17:18"}
648
+ {"current_steps": 648, "total_steps": 1235, "loss": 0.0557, "lr": 2.17791064266051e-05, "epoch": 2.623481781376518, "percentage": 52.47, "elapsed_time": "3:37:27", "remaining_time": "3:16:59"}
649
+ {"current_steps": 649, "total_steps": 1235, "loss": 0.0603, "lr": 2.172276926861741e-05, "epoch": 2.6275303643724697, "percentage": 52.55, "elapsed_time": "3:37:46", "remaining_time": "3:16:37"}
650
+ {"current_steps": 650, "total_steps": 1235, "loss": 0.0561, "lr": 2.166641833541255e-05, "epoch": 2.6315789473684212, "percentage": 52.63, "elapsed_time": "3:38:04", "remaining_time": "3:16:16"}
651
+ {"current_steps": 651, "total_steps": 1235, "loss": 0.0711, "lr": 2.161005407757109e-05, "epoch": 2.6356275303643724, "percentage": 52.71, "elapsed_time": "3:38:24", "remaining_time": "3:15:55"}
652
+ {"current_steps": 652, "total_steps": 1235, "loss": 0.0597, "lr": 2.155367694578013e-05, "epoch": 2.639676113360324, "percentage": 52.79, "elapsed_time": "3:38:42", "remaining_time": "3:15:33"}
653
+ {"current_steps": 653, "total_steps": 1235, "loss": 0.0622, "lr": 2.1497287390829712e-05, "epoch": 2.6437246963562755, "percentage": 52.87, "elapsed_time": "3:39:01", "remaining_time": "3:15:12"}
654
+ {"current_steps": 654, "total_steps": 1235, "loss": 0.0492, "lr": 2.1440885863609208e-05, "epoch": 2.6477732793522266, "percentage": 52.96, "elapsed_time": "3:39:22", "remaining_time": "3:14:53"}
655
+ {"current_steps": 655, "total_steps": 1235, "loss": 0.0525, "lr": 2.1384472815103737e-05, "epoch": 2.651821862348178, "percentage": 53.04, "elapsed_time": "3:39:37", "remaining_time": "3:14:28"}
656
+ {"current_steps": 656, "total_steps": 1235, "loss": 0.0556, "lr": 2.1328048696390534e-05, "epoch": 2.6558704453441297, "percentage": 53.12, "elapsed_time": "3:39:59", "remaining_time": "3:14:10"}
657
+ {"current_steps": 657, "total_steps": 1235, "loss": 0.0561, "lr": 2.1271613958635342e-05, "epoch": 2.659919028340081, "percentage": 53.2, "elapsed_time": "3:40:21", "remaining_time": "3:13:51"}
658
+ {"current_steps": 658, "total_steps": 1235, "loss": 0.0549, "lr": 2.1215169053088825e-05, "epoch": 2.6639676113360324, "percentage": 53.28, "elapsed_time": "3:40:41", "remaining_time": "3:13:31"}
659
+ {"current_steps": 659, "total_steps": 1235, "loss": 0.0573, "lr": 2.1158714431082937e-05, "epoch": 2.668016194331984, "percentage": 53.36, "elapsed_time": "3:41:02", "remaining_time": "3:13:12"}
660
+ {"current_steps": 660, "total_steps": 1235, "loss": 0.0633, "lr": 2.110225054402733e-05, "epoch": 2.672064777327935, "percentage": 53.44, "elapsed_time": "3:41:18", "remaining_time": "3:12:48"}
661
+ {"current_steps": 661, "total_steps": 1235, "loss": 0.0512, "lr": 2.1045777843405747e-05, "epoch": 2.6761133603238867, "percentage": 53.52, "elapsed_time": "3:41:35", "remaining_time": "3:12:25"}
662
+ {"current_steps": 662, "total_steps": 1235, "loss": 0.0624, "lr": 2.09892967807724e-05, "epoch": 2.6801619433198383, "percentage": 53.6, "elapsed_time": "3:41:54", "remaining_time": "3:12:04"}
663
+ {"current_steps": 663, "total_steps": 1235, "loss": 0.0461, "lr": 2.093280780774835e-05, "epoch": 2.6842105263157894, "percentage": 53.68, "elapsed_time": "3:42:14", "remaining_time": "3:11:44"}
664
+ {"current_steps": 664, "total_steps": 1235, "loss": 0.05, "lr": 2.087631137601793e-05, "epoch": 2.688259109311741, "percentage": 53.77, "elapsed_time": "3:42:34", "remaining_time": "3:11:24"}
665
+ {"current_steps": 665, "total_steps": 1235, "loss": 0.0616, "lr": 2.0819807937325104e-05, "epoch": 2.6923076923076925, "percentage": 53.85, "elapsed_time": "3:42:52", "remaining_time": "3:11:02"}
666
+ {"current_steps": 666, "total_steps": 1235, "loss": 0.055, "lr": 2.0763297943469847e-05, "epoch": 2.6963562753036436, "percentage": 53.93, "elapsed_time": "3:43:12", "remaining_time": "3:10:42"}
667
+ {"current_steps": 667, "total_steps": 1235, "loss": 0.0557, "lr": 2.070678184630458e-05, "epoch": 2.700404858299595, "percentage": 54.01, "elapsed_time": "3:43:34", "remaining_time": "3:10:23"}
668
+ {"current_steps": 668, "total_steps": 1235, "loss": 0.0549, "lr": 2.06502600977305e-05, "epoch": 2.7044534412955468, "percentage": 54.09, "elapsed_time": "3:43:53", "remaining_time": "3:10:02"}
669
+ {"current_steps": 669, "total_steps": 1235, "loss": 0.06, "lr": 2.0593733149694008e-05, "epoch": 2.708502024291498, "percentage": 54.17, "elapsed_time": "3:44:13", "remaining_time": "3:09:42"}
670
+ {"current_steps": 670, "total_steps": 1235, "loss": 0.054, "lr": 2.0537201454183074e-05, "epoch": 2.7125506072874495, "percentage": 54.25, "elapsed_time": "3:44:32", "remaining_time": "3:09:21"}
671
+ {"current_steps": 671, "total_steps": 1235, "loss": 0.0509, "lr": 2.0480665463223626e-05, "epoch": 2.716599190283401, "percentage": 54.33, "elapsed_time": "3:44:53", "remaining_time": "3:09:01"}
672
+ {"current_steps": 672, "total_steps": 1235, "loss": 0.0519, "lr": 2.042412562887594e-05, "epoch": 2.720647773279352, "percentage": 54.41, "elapsed_time": "3:45:14", "remaining_time": "3:08:42"}
673
+ {"current_steps": 673, "total_steps": 1235, "loss": 0.0461, "lr": 2.0367582403231033e-05, "epoch": 2.7246963562753037, "percentage": 54.49, "elapsed_time": "3:45:36", "remaining_time": "3:08:24"}
674
+ {"current_steps": 674, "total_steps": 1235, "loss": 0.0692, "lr": 2.0311036238407023e-05, "epoch": 2.7287449392712553, "percentage": 54.57, "elapsed_time": "3:45:56", "remaining_time": "3:08:04"}
675
+ {"current_steps": 675, "total_steps": 1235, "loss": 0.0464, "lr": 2.0254487586545534e-05, "epoch": 2.7327935222672064, "percentage": 54.66, "elapsed_time": "3:46:16", "remaining_time": "3:07:43"}
676
+ {"current_steps": 676, "total_steps": 1235, "loss": 0.0566, "lr": 2.0197936899808088e-05, "epoch": 2.736842105263158, "percentage": 54.74, "elapsed_time": "3:46:34", "remaining_time": "3:07:21"}
677
+ {"current_steps": 677, "total_steps": 1235, "loss": 0.0464, "lr": 2.0141384630372466e-05, "epoch": 2.7408906882591095, "percentage": 54.82, "elapsed_time": "3:46:53", "remaining_time": "3:07:00"}
678
+ {"current_steps": 678, "total_steps": 1235, "loss": 0.0505, "lr": 2.0084831230429106e-05, "epoch": 2.7449392712550607, "percentage": 54.9, "elapsed_time": "3:47:12", "remaining_time": "3:06:39"}
679
+ {"current_steps": 679, "total_steps": 1235, "loss": 0.0634, "lr": 2.0028277152177492e-05, "epoch": 2.748987854251012, "percentage": 54.98, "elapsed_time": "3:47:34", "remaining_time": "3:06:20"}
680
+ {"current_steps": 680, "total_steps": 1235, "loss": 0.0547, "lr": 1.9971722847822518e-05, "epoch": 2.753036437246964, "percentage": 55.06, "elapsed_time": "3:47:52", "remaining_time": "3:05:59"}
681
+ {"current_steps": 681, "total_steps": 1235, "loss": 0.0576, "lr": 1.99151687695709e-05, "epoch": 2.757085020242915, "percentage": 55.14, "elapsed_time": "3:48:12", "remaining_time": "3:05:38"}
682
+ {"current_steps": 682, "total_steps": 1235, "loss": 0.0515, "lr": 1.9858615369627537e-05, "epoch": 2.7611336032388665, "percentage": 55.22, "elapsed_time": "3:48:30", "remaining_time": "3:05:17"}
683
+ {"current_steps": 683, "total_steps": 1235, "loss": 0.0455, "lr": 1.9802063100191916e-05, "epoch": 2.765182186234818, "percentage": 55.3, "elapsed_time": "3:48:48", "remaining_time": "3:04:55"}
684
+ {"current_steps": 684, "total_steps": 1235, "loss": 0.038, "lr": 1.974551241345447e-05, "epoch": 2.769230769230769, "percentage": 55.38, "elapsed_time": "3:49:09", "remaining_time": "3:04:35"}
685
+ {"current_steps": 685, "total_steps": 1235, "loss": 0.0531, "lr": 1.9688963761592984e-05, "epoch": 2.7732793522267207, "percentage": 55.47, "elapsed_time": "3:49:28", "remaining_time": "3:04:15"}
686
+ {"current_steps": 686, "total_steps": 1235, "loss": 0.0504, "lr": 1.963241759676897e-05, "epoch": 2.7773279352226723, "percentage": 55.55, "elapsed_time": "3:49:48", "remaining_time": "3:03:55"}
687
+ {"current_steps": 687, "total_steps": 1235, "loss": 0.0554, "lr": 1.9575874371124066e-05, "epoch": 2.7813765182186234, "percentage": 55.63, "elapsed_time": "3:50:08", "remaining_time": "3:03:34"}
688
+ {"current_steps": 688, "total_steps": 1235, "loss": 0.0527, "lr": 1.951933453677638e-05, "epoch": 2.785425101214575, "percentage": 55.71, "elapsed_time": "3:50:29", "remaining_time": "3:03:15"}
689
+ {"current_steps": 689, "total_steps": 1235, "loss": 0.048, "lr": 1.9462798545816932e-05, "epoch": 2.7894736842105265, "percentage": 55.79, "elapsed_time": "3:50:49", "remaining_time": "3:02:54"}
690
+ {"current_steps": 690, "total_steps": 1235, "loss": 0.0411, "lr": 1.9406266850305996e-05, "epoch": 2.7935222672064777, "percentage": 55.87, "elapsed_time": "3:51:08", "remaining_time": "3:02:34"}
691
+ {"current_steps": 691, "total_steps": 1235, "loss": 0.0446, "lr": 1.9349739902269503e-05, "epoch": 2.7975708502024292, "percentage": 55.95, "elapsed_time": "3:51:30", "remaining_time": "3:02:15"}
692
+ {"current_steps": 692, "total_steps": 1235, "loss": 0.0462, "lr": 1.9293218153695425e-05, "epoch": 2.801619433198381, "percentage": 56.03, "elapsed_time": "3:51:49", "remaining_time": "3:01:54"}
693
+ {"current_steps": 693, "total_steps": 1235, "loss": 0.045, "lr": 1.9236702056530153e-05, "epoch": 2.805668016194332, "percentage": 56.11, "elapsed_time": "3:52:08", "remaining_time": "3:01:33"}
694
+ {"current_steps": 694, "total_steps": 1235, "loss": 0.0506, "lr": 1.9180192062674907e-05, "epoch": 2.8097165991902835, "percentage": 56.19, "elapsed_time": "3:52:29", "remaining_time": "3:01:14"}
695
+ {"current_steps": 695, "total_steps": 1235, "loss": 0.0384, "lr": 1.9123688623982076e-05, "epoch": 2.813765182186235, "percentage": 56.28, "elapsed_time": "3:52:51", "remaining_time": "3:00:55"}
696
+ {"current_steps": 696, "total_steps": 1235, "loss": 0.0466, "lr": 1.906719219225165e-05, "epoch": 2.817813765182186, "percentage": 56.36, "elapsed_time": "3:53:11", "remaining_time": "3:00:35"}
697
+ {"current_steps": 697, "total_steps": 1235, "loss": 0.0451, "lr": 1.9010703219227603e-05, "epoch": 2.8218623481781377, "percentage": 56.44, "elapsed_time": "3:53:33", "remaining_time": "3:00:16"}
698
+ {"current_steps": 698, "total_steps": 1235, "loss": 0.0427, "lr": 1.8954222156594256e-05, "epoch": 2.8259109311740893, "percentage": 56.52, "elapsed_time": "3:53:53", "remaining_time": "2:59:56"}
699
+ {"current_steps": 699, "total_steps": 1235, "loss": 0.0411, "lr": 1.8897749455972673e-05, "epoch": 2.8299595141700404, "percentage": 56.6, "elapsed_time": "3:54:12", "remaining_time": "2:59:35"}
700
+ {"current_steps": 700, "total_steps": 1235, "loss": 0.0455, "lr": 1.884128556891707e-05, "epoch": 2.834008097165992, "percentage": 56.68, "elapsed_time": "3:54:35", "remaining_time": "2:59:17"}
701
+ {"current_steps": 701, "total_steps": 1235, "loss": 0.0396, "lr": 1.878483094691119e-05, "epoch": 2.8380566801619436, "percentage": 56.76, "elapsed_time": "3:54:52", "remaining_time": "2:58:55"}
702
+ {"current_steps": 702, "total_steps": 1235, "loss": 0.0481, "lr": 1.8728386041364664e-05, "epoch": 2.8421052631578947, "percentage": 56.84, "elapsed_time": "3:55:13", "remaining_time": "2:58:35"}
703
+ {"current_steps": 703, "total_steps": 1235, "loss": 0.0402, "lr": 1.867195130360947e-05, "epoch": 2.8461538461538463, "percentage": 56.92, "elapsed_time": "3:55:32", "remaining_time": "2:58:15"}
704
+ {"current_steps": 704, "total_steps": 1235, "loss": 0.0492, "lr": 1.8615527184896263e-05, "epoch": 2.850202429149798, "percentage": 57.0, "elapsed_time": "3:55:52", "remaining_time": "2:57:54"}
705
+ {"current_steps": 705, "total_steps": 1235, "loss": 0.0454, "lr": 1.8559114136390795e-05, "epoch": 2.854251012145749, "percentage": 57.09, "elapsed_time": "3:56:12", "remaining_time": "2:57:34"}
706
+ {"current_steps": 706, "total_steps": 1235, "loss": 0.0421, "lr": 1.8502712609170298e-05, "epoch": 2.8582995951417005, "percentage": 57.17, "elapsed_time": "3:56:31", "remaining_time": "2:57:13"}
707
+ {"current_steps": 707, "total_steps": 1235, "loss": 0.0487, "lr": 1.8446323054219876e-05, "epoch": 2.862348178137652, "percentage": 57.25, "elapsed_time": "3:56:50", "remaining_time": "2:56:52"}
708
+ {"current_steps": 708, "total_steps": 1235, "loss": 0.0466, "lr": 1.838994592242891e-05, "epoch": 2.866396761133603, "percentage": 57.33, "elapsed_time": "3:57:11", "remaining_time": "2:56:33"}
709
+ {"current_steps": 709, "total_steps": 1235, "loss": 0.0395, "lr": 1.8333581664587453e-05, "epoch": 2.8704453441295548, "percentage": 57.41, "elapsed_time": "3:57:29", "remaining_time": "2:56:11"}
710
+ {"current_steps": 710, "total_steps": 1235, "loss": 0.04, "lr": 1.8277230731382593e-05, "epoch": 2.8744939271255063, "percentage": 57.49, "elapsed_time": "3:57:48", "remaining_time": "2:55:50"}
711
+ {"current_steps": 711, "total_steps": 1235, "loss": 0.0451, "lr": 1.82208935733949e-05, "epoch": 2.8785425101214575, "percentage": 57.57, "elapsed_time": "3:58:05", "remaining_time": "2:55:28"}
712
+ {"current_steps": 712, "total_steps": 1235, "loss": 0.0339, "lr": 1.8164570641094793e-05, "epoch": 2.882591093117409, "percentage": 57.65, "elapsed_time": "3:58:23", "remaining_time": "2:55:06"}
713
+ {"current_steps": 713, "total_steps": 1235, "loss": 0.0403, "lr": 1.810826238483892e-05, "epoch": 2.8866396761133606, "percentage": 57.73, "elapsed_time": "3:58:44", "remaining_time": "2:54:46"}
714
+ {"current_steps": 714, "total_steps": 1235, "loss": 0.0456, "lr": 1.8051969254866608e-05, "epoch": 2.8906882591093117, "percentage": 57.81, "elapsed_time": "3:59:05", "remaining_time": "2:54:27"}
715
+ {"current_steps": 715, "total_steps": 1235, "loss": 0.0428, "lr": 1.7995691701296226e-05, "epoch": 2.8947368421052633, "percentage": 57.89, "elapsed_time": "3:59:24", "remaining_time": "2:54:07"}
716
+ {"current_steps": 716, "total_steps": 1235, "loss": 0.04, "lr": 1.7939430174121593e-05, "epoch": 2.898785425101215, "percentage": 57.98, "elapsed_time": "3:59:44", "remaining_time": "2:53:46"}
717
+ {"current_steps": 717, "total_steps": 1235, "loss": 0.0438, "lr": 1.788318512320838e-05, "epoch": 2.902834008097166, "percentage": 58.06, "elapsed_time": "4:00:04", "remaining_time": "2:53:26"}
718
+ {"current_steps": 718, "total_steps": 1235, "loss": 0.0386, "lr": 1.782695699829051e-05, "epoch": 2.9068825910931175, "percentage": 58.14, "elapsed_time": "4:00:25", "remaining_time": "2:53:07"}
719
+ {"current_steps": 719, "total_steps": 1235, "loss": 0.0414, "lr": 1.7770746248966587e-05, "epoch": 2.910931174089069, "percentage": 58.22, "elapsed_time": "4:00:46", "remaining_time": "2:52:47"}
720
+ {"current_steps": 720, "total_steps": 1235, "loss": 0.0388, "lr": 1.7714553324696243e-05, "epoch": 2.91497975708502, "percentage": 58.3, "elapsed_time": "4:01:07", "remaining_time": "2:52:28"}
721
+ {"current_steps": 721, "total_steps": 1235, "loss": 0.0356, "lr": 1.7658378674796614e-05, "epoch": 2.919028340080972, "percentage": 58.38, "elapsed_time": "4:01:28", "remaining_time": "2:52:09"}
722
+ {"current_steps": 722, "total_steps": 1235, "loss": 0.0388, "lr": 1.76022227484387e-05, "epoch": 2.9230769230769234, "percentage": 58.46, "elapsed_time": "4:01:49", "remaining_time": "2:51:49"}
723
+ {"current_steps": 723, "total_steps": 1235, "loss": 0.0352, "lr": 1.7546085994643807e-05, "epoch": 2.9271255060728745, "percentage": 58.54, "elapsed_time": "4:02:09", "remaining_time": "2:51:28"}
724
+ {"current_steps": 724, "total_steps": 1235, "loss": 0.038, "lr": 1.7489968862279902e-05, "epoch": 2.931174089068826, "percentage": 58.62, "elapsed_time": "4:02:28", "remaining_time": "2:51:08"}
725
+ {"current_steps": 725, "total_steps": 1235, "loss": 0.0363, "lr": 1.743387180005809e-05, "epoch": 2.9352226720647776, "percentage": 58.7, "elapsed_time": "4:02:48", "remaining_time": "2:50:48"}
726
+ {"current_steps": 726, "total_steps": 1235, "loss": 0.036, "lr": 1.737779525652899e-05, "epoch": 2.9392712550607287, "percentage": 58.79, "elapsed_time": "4:03:05", "remaining_time": "2:50:25"}
727
+ {"current_steps": 727, "total_steps": 1235, "loss": 0.0326, "lr": 1.732173968007914e-05, "epoch": 2.9433198380566803, "percentage": 58.87, "elapsed_time": "4:03:22", "remaining_time": "2:50:03"}
728
+ {"current_steps": 728, "total_steps": 1235, "loss": 0.0344, "lr": 1.7265705518927437e-05, "epoch": 2.9473684210526314, "percentage": 58.95, "elapsed_time": "4:03:39", "remaining_time": "2:49:41"}
729
+ {"current_steps": 729, "total_steps": 1235, "loss": 0.0377, "lr": 1.7209693221121542e-05, "epoch": 2.951417004048583, "percentage": 59.03, "elapsed_time": "4:04:01", "remaining_time": "2:49:22"}
730
+ {"current_steps": 730, "total_steps": 1235, "loss": 0.0344, "lr": 1.7153703234534302e-05, "epoch": 2.9554655870445345, "percentage": 59.11, "elapsed_time": "4:04:21", "remaining_time": "2:49:02"}
731
+ {"current_steps": 731, "total_steps": 1235, "loss": 0.036, "lr": 1.709773600686015e-05, "epoch": 2.9595141700404857, "percentage": 59.19, "elapsed_time": "4:04:41", "remaining_time": "2:48:42"}
732
+ {"current_steps": 732, "total_steps": 1235, "loss": 0.0343, "lr": 1.7041791985611548e-05, "epoch": 2.9635627530364372, "percentage": 59.27, "elapsed_time": "4:04:59", "remaining_time": "2:48:21"}
733
+ {"current_steps": 733, "total_steps": 1235, "loss": 0.0463, "lr": 1.69858716181154e-05, "epoch": 2.967611336032389, "percentage": 59.35, "elapsed_time": "4:05:20", "remaining_time": "2:48:01"}
734
+ {"current_steps": 734, "total_steps": 1235, "loss": 0.0322, "lr": 1.692997535150948e-05, "epoch": 2.97165991902834, "percentage": 59.43, "elapsed_time": "4:05:38", "remaining_time": "2:47:40"}
735
+ {"current_steps": 735, "total_steps": 1235, "loss": 0.0309, "lr": 1.687410363273884e-05, "epoch": 2.9757085020242915, "percentage": 59.51, "elapsed_time": "4:05:57", "remaining_time": "2:47:19"}
736
+ {"current_steps": 736, "total_steps": 1235, "loss": 0.0312, "lr": 1.6818256908552257e-05, "epoch": 2.979757085020243, "percentage": 59.6, "elapsed_time": "4:06:15", "remaining_time": "2:46:57"}
737
+ {"current_steps": 737, "total_steps": 1235, "loss": 0.0414, "lr": 1.6762435625498646e-05, "epoch": 2.983805668016194, "percentage": 59.68, "elapsed_time": "4:06:38", "remaining_time": "2:46:39"}
738
+ {"current_steps": 738, "total_steps": 1235, "loss": 0.0285, "lr": 1.67066402299235e-05, "epoch": 2.9878542510121457, "percentage": 59.76, "elapsed_time": "4:06:56", "remaining_time": "2:46:17"}
739
+ {"current_steps": 739, "total_steps": 1235, "loss": 0.0366, "lr": 1.6650871167965313e-05, "epoch": 2.9919028340080973, "percentage": 59.84, "elapsed_time": "4:07:17", "remaining_time": "2:45:58"}
740
+ {"current_steps": 740, "total_steps": 1235, "loss": 0.0344, "lr": 1.6595128885552028e-05, "epoch": 2.9959514170040484, "percentage": 59.92, "elapsed_time": "4:07:35", "remaining_time": "2:45:36"}
741
+ {"current_steps": 741, "total_steps": 1235, "loss": 0.0314, "lr": 1.653941382839745e-05, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "4:07:55", "remaining_time": "2:45:16"}
742
+ {"current_steps": 742, "total_steps": 1235, "loss": 0.0181, "lr": 1.6483726441997673e-05, "epoch": 3.0040485829959516, "percentage": 60.08, "elapsed_time": "4:09:55", "remaining_time": "2:46:03"}
743
+ {"current_steps": 743, "total_steps": 1235, "loss": 0.0204, "lr": 1.642806717162757e-05, "epoch": 3.0080971659919027, "percentage": 60.16, "elapsed_time": "4:10:15", "remaining_time": "2:45:43"}
744
+ {"current_steps": 744, "total_steps": 1235, "loss": 0.0153, "lr": 1.637243646233718e-05, "epoch": 3.0121457489878543, "percentage": 60.24, "elapsed_time": "4:10:35", "remaining_time": "2:45:22"}
745
+ {"current_steps": 745, "total_steps": 1235, "loss": 0.0201, "lr": 1.6316834758948174e-05, "epoch": 3.016194331983806, "percentage": 60.32, "elapsed_time": "4:10:52", "remaining_time": "2:45:00"}
746
+ {"current_steps": 746, "total_steps": 1235, "loss": 0.0166, "lr": 1.6261262506050282e-05, "epoch": 3.020242914979757, "percentage": 60.4, "elapsed_time": "4:11:09", "remaining_time": "2:44:38"}
747
+ {"current_steps": 747, "total_steps": 1235, "loss": 0.0205, "lr": 1.620572014799777e-05, "epoch": 3.0242914979757085, "percentage": 60.49, "elapsed_time": "4:11:30", "remaining_time": "2:44:18"}
748
+ {"current_steps": 748, "total_steps": 1235, "loss": 0.02, "lr": 1.6150208128905857e-05, "epoch": 3.02834008097166, "percentage": 60.57, "elapsed_time": "4:11:48", "remaining_time": "2:43:56"}
749
+ {"current_steps": 749, "total_steps": 1235, "loss": 0.0168, "lr": 1.6094726892647147e-05, "epoch": 3.032388663967611, "percentage": 60.65, "elapsed_time": "4:12:08", "remaining_time": "2:43:36"}
750
+ {"current_steps": 750, "total_steps": 1235, "loss": 0.0174, "lr": 1.6039276882848135e-05, "epoch": 3.0364372469635628, "percentage": 60.73, "elapsed_time": "4:12:27", "remaining_time": "2:43:15"}
751
+ {"current_steps": 751, "total_steps": 1235, "loss": 0.0222, "lr": 1.5983858542885635e-05, "epoch": 3.0404858299595143, "percentage": 60.81, "elapsed_time": "4:12:50", "remaining_time": "2:42:57"}
752
+ {"current_steps": 752, "total_steps": 1235, "loss": 0.0175, "lr": 1.5928472315883203e-05, "epoch": 3.0445344129554655, "percentage": 60.89, "elapsed_time": "4:13:11", "remaining_time": "2:42:37"}
753
+ {"current_steps": 753, "total_steps": 1235, "loss": 0.0206, "lr": 1.5873118644707633e-05, "epoch": 3.048582995951417, "percentage": 60.97, "elapsed_time": "4:13:31", "remaining_time": "2:42:17"}
754
+ {"current_steps": 754, "total_steps": 1235, "loss": 0.0165, "lr": 1.5817797971965413e-05, "epoch": 3.0526315789473686, "percentage": 61.05, "elapsed_time": "4:13:52", "remaining_time": "2:41:57"}
755
+ {"current_steps": 755, "total_steps": 1235, "loss": 0.0187, "lr": 1.576251073999917e-05, "epoch": 3.0566801619433197, "percentage": 61.13, "elapsed_time": "4:14:12", "remaining_time": "2:41:36"}
756
+ {"current_steps": 756, "total_steps": 1235, "loss": 0.0233, "lr": 1.5707257390884126e-05, "epoch": 3.0607287449392713, "percentage": 61.21, "elapsed_time": "4:14:33", "remaining_time": "2:41:17"}
757
+ {"current_steps": 757, "total_steps": 1235, "loss": 0.0171, "lr": 1.5652038366424595e-05, "epoch": 3.064777327935223, "percentage": 61.3, "elapsed_time": "4:14:53", "remaining_time": "2:40:56"}
758
+ {"current_steps": 758, "total_steps": 1235, "loss": 0.0181, "lr": 1.5596854108150424e-05, "epoch": 3.068825910931174, "percentage": 61.38, "elapsed_time": "4:15:15", "remaining_time": "2:40:37"}
759
+ {"current_steps": 759, "total_steps": 1235, "loss": 0.0126, "lr": 1.5541705057313476e-05, "epoch": 3.0728744939271255, "percentage": 61.46, "elapsed_time": "4:15:32", "remaining_time": "2:40:15"}
760
+ {"current_steps": 760, "total_steps": 1235, "loss": 0.0157, "lr": 1.5486591654884086e-05, "epoch": 3.076923076923077, "percentage": 61.54, "elapsed_time": "4:15:50", "remaining_time": "2:39:53"}
761
+ {"current_steps": 761, "total_steps": 1235, "loss": 0.0175, "lr": 1.543151434154755e-05, "epoch": 3.080971659919028, "percentage": 61.62, "elapsed_time": "4:16:10", "remaining_time": "2:39:33"}
762
+ {"current_steps": 762, "total_steps": 1235, "loss": 0.0203, "lr": 1.5376473557700615e-05, "epoch": 3.08502024291498, "percentage": 61.7, "elapsed_time": "4:16:31", "remaining_time": "2:39:14"}
763
+ {"current_steps": 763, "total_steps": 1235, "loss": 0.0154, "lr": 1.5321469743447893e-05, "epoch": 3.0890688259109313, "percentage": 61.78, "elapsed_time": "4:16:51", "remaining_time": "2:38:53"}
764
+ {"current_steps": 764, "total_steps": 1235, "loss": 0.0202, "lr": 1.5266503338598434e-05, "epoch": 3.0931174089068825, "percentage": 61.86, "elapsed_time": "4:17:10", "remaining_time": "2:38:32"}
765
+ {"current_steps": 765, "total_steps": 1235, "loss": 0.0196, "lr": 1.5211574782662149e-05, "epoch": 3.097165991902834, "percentage": 61.94, "elapsed_time": "4:17:30", "remaining_time": "2:38:12"}
766
+ {"current_steps": 766, "total_steps": 1235, "loss": 0.0126, "lr": 1.5156684514846307e-05, "epoch": 3.1012145748987856, "percentage": 62.02, "elapsed_time": "4:17:46", "remaining_time": "2:37:49"}
767
+ {"current_steps": 767, "total_steps": 1235, "loss": 0.0185, "lr": 1.5101832974052012e-05, "epoch": 3.1052631578947367, "percentage": 62.11, "elapsed_time": "4:18:07", "remaining_time": "2:37:29"}
768
+ {"current_steps": 768, "total_steps": 1235, "loss": 0.0143, "lr": 1.5047020598870737e-05, "epoch": 3.1093117408906883, "percentage": 62.19, "elapsed_time": "4:18:26", "remaining_time": "2:37:09"}
769
+ {"current_steps": 769, "total_steps": 1235, "loss": 0.0155, "lr": 1.4992247827580778e-05, "epoch": 3.11336032388664, "percentage": 62.27, "elapsed_time": "4:18:46", "remaining_time": "2:36:48"}
770
+ {"current_steps": 770, "total_steps": 1235, "loss": 0.0136, "lr": 1.493751509814374e-05, "epoch": 3.117408906882591, "percentage": 62.35, "elapsed_time": "4:19:05", "remaining_time": "2:36:27"}
771
+ {"current_steps": 771, "total_steps": 1235, "loss": 0.0167, "lr": 1.4882822848201073e-05, "epoch": 3.1214574898785425, "percentage": 62.43, "elapsed_time": "4:19:27", "remaining_time": "2:36:08"}
772
+ {"current_steps": 772, "total_steps": 1235, "loss": 0.0185, "lr": 1.4828171515070553e-05, "epoch": 3.125506072874494, "percentage": 62.51, "elapsed_time": "4:19:45", "remaining_time": "2:35:47"}
773
+ {"current_steps": 773, "total_steps": 1235, "loss": 0.0158, "lr": 1.4773561535742793e-05, "epoch": 3.1295546558704452, "percentage": 62.59, "elapsed_time": "4:20:03", "remaining_time": "2:35:25"}
774
+ {"current_steps": 774, "total_steps": 1235, "loss": 0.0153, "lr": 1.4718993346877715e-05, "epoch": 3.133603238866397, "percentage": 62.67, "elapsed_time": "4:20:25", "remaining_time": "2:35:06"}
775
+ {"current_steps": 775, "total_steps": 1235, "loss": 0.0204, "lr": 1.466446738480111e-05, "epoch": 3.1376518218623484, "percentage": 62.75, "elapsed_time": "4:20:44", "remaining_time": "2:34:45"}
776
+ {"current_steps": 776, "total_steps": 1235, "loss": 0.0124, "lr": 1.460998408550112e-05, "epoch": 3.1417004048582995, "percentage": 62.83, "elapsed_time": "4:21:05", "remaining_time": "2:34:26"}
777
+ {"current_steps": 777, "total_steps": 1235, "loss": 0.0118, "lr": 1.4555543884624751e-05, "epoch": 3.145748987854251, "percentage": 62.91, "elapsed_time": "4:21:25", "remaining_time": "2:34:06"}
778
+ {"current_steps": 778, "total_steps": 1235, "loss": 0.0138, "lr": 1.4501147217474402e-05, "epoch": 3.1497975708502026, "percentage": 63.0, "elapsed_time": "4:21:45", "remaining_time": "2:33:45"}
779
+ {"current_steps": 779, "total_steps": 1235, "loss": 0.0147, "lr": 1.444679451900437e-05, "epoch": 3.1538461538461537, "percentage": 63.08, "elapsed_time": "4:22:03", "remaining_time": "2:33:24"}
780
+ {"current_steps": 780, "total_steps": 1235, "loss": 0.0136, "lr": 1.4392486223817397e-05, "epoch": 3.1578947368421053, "percentage": 63.16, "elapsed_time": "4:22:23", "remaining_time": "2:33:03"}
781
+ {"current_steps": 781, "total_steps": 1235, "loss": 0.0148, "lr": 1.4338222766161143e-05, "epoch": 3.161943319838057, "percentage": 63.24, "elapsed_time": "4:22:43", "remaining_time": "2:32:43"}
782
+ {"current_steps": 782, "total_steps": 1235, "loss": 0.0155, "lr": 1.4284004579924777e-05, "epoch": 3.165991902834008, "percentage": 63.32, "elapsed_time": "4:23:01", "remaining_time": "2:32:21"}
783
+ {"current_steps": 783, "total_steps": 1235, "loss": 0.0191, "lr": 1.4229832098635479e-05, "epoch": 3.1700404858299596, "percentage": 63.4, "elapsed_time": "4:23:23", "remaining_time": "2:32:03"}
784
+ {"current_steps": 784, "total_steps": 1235, "loss": 0.0163, "lr": 1.4175705755454963e-05, "epoch": 3.174089068825911, "percentage": 63.48, "elapsed_time": "4:23:41", "remaining_time": "2:31:41"}
785
+ {"current_steps": 785, "total_steps": 1235, "loss": 0.0139, "lr": 1.412162598317602e-05, "epoch": 3.1781376518218623, "percentage": 63.56, "elapsed_time": "4:24:02", "remaining_time": "2:31:21"}
786
+ {"current_steps": 786, "total_steps": 1235, "loss": 0.0143, "lr": 1.406759321421907e-05, "epoch": 3.182186234817814, "percentage": 63.64, "elapsed_time": "4:24:21", "remaining_time": "2:31:00"}
787
+ {"current_steps": 787, "total_steps": 1235, "loss": 0.0114, "lr": 1.401360788062871e-05, "epoch": 3.1862348178137654, "percentage": 63.72, "elapsed_time": "4:24:39", "remaining_time": "2:30:39"}
788
+ {"current_steps": 788, "total_steps": 1235, "loss": 0.0131, "lr": 1.3959670414070204e-05, "epoch": 3.1902834008097165, "percentage": 63.81, "elapsed_time": "4:24:56", "remaining_time": "2:30:17"}
789
+ {"current_steps": 789, "total_steps": 1235, "loss": 0.0158, "lr": 1.3905781245826108e-05, "epoch": 3.194331983805668, "percentage": 63.89, "elapsed_time": "4:25:16", "remaining_time": "2:29:56"}
790
+ {"current_steps": 790, "total_steps": 1235, "loss": 0.0143, "lr": 1.3851940806792778e-05, "epoch": 3.1983805668016196, "percentage": 63.97, "elapsed_time": "4:25:35", "remaining_time": "2:29:36"}
791
+ {"current_steps": 791, "total_steps": 1235, "loss": 0.0127, "lr": 1.379814952747693e-05, "epoch": 3.2024291497975708, "percentage": 64.05, "elapsed_time": "4:25:53", "remaining_time": "2:29:14"}
792
+ {"current_steps": 792, "total_steps": 1235, "loss": 0.015, "lr": 1.3744407837992193e-05, "epoch": 3.2064777327935223, "percentage": 64.13, "elapsed_time": "4:26:13", "remaining_time": "2:28:54"}
793
+ {"current_steps": 793, "total_steps": 1235, "loss": 0.0139, "lr": 1.3690716168055692e-05, "epoch": 3.2105263157894735, "percentage": 64.21, "elapsed_time": "4:26:31", "remaining_time": "2:28:33"}
794
+ {"current_steps": 794, "total_steps": 1235, "loss": 0.0153, "lr": 1.363707494698459e-05, "epoch": 3.214574898785425, "percentage": 64.29, "elapsed_time": "4:26:50", "remaining_time": "2:28:12"}
795
+ {"current_steps": 795, "total_steps": 1235, "loss": 0.0123, "lr": 1.358348460369265e-05, "epoch": 3.2186234817813766, "percentage": 64.37, "elapsed_time": "4:27:09", "remaining_time": "2:27:51"}
796
+ {"current_steps": 796, "total_steps": 1235, "loss": 0.0161, "lr": 1.352994556668684e-05, "epoch": 3.2226720647773277, "percentage": 64.45, "elapsed_time": "4:27:29", "remaining_time": "2:27:31"}
797
+ {"current_steps": 797, "total_steps": 1235, "loss": 0.0177, "lr": 1.3476458264063865e-05, "epoch": 3.2267206477732793, "percentage": 64.53, "elapsed_time": "4:27:49", "remaining_time": "2:27:10"}
798
+ {"current_steps": 798, "total_steps": 1235, "loss": 0.0159, "lr": 1.342302312350678e-05, "epoch": 3.230769230769231, "percentage": 64.62, "elapsed_time": "4:28:11", "remaining_time": "2:26:51"}
799
+ {"current_steps": 799, "total_steps": 1235, "loss": 0.0119, "lr": 1.3369640572281537e-05, "epoch": 3.234817813765182, "percentage": 64.7, "elapsed_time": "4:28:34", "remaining_time": "2:26:33"}
800
+ {"current_steps": 800, "total_steps": 1235, "loss": 0.0128, "lr": 1.3316311037233596e-05, "epoch": 3.2388663967611335, "percentage": 64.78, "elapsed_time": "4:28:51", "remaining_time": "2:26:11"}
801
+ {"current_steps": 801, "total_steps": 1235, "loss": 0.0146, "lr": 1.326303494478451e-05, "epoch": 3.242914979757085, "percentage": 64.86, "elapsed_time": "4:29:11", "remaining_time": "2:25:51"}
802
+ {"current_steps": 802, "total_steps": 1235, "loss": 0.0142, "lr": 1.3209812720928472e-05, "epoch": 3.246963562753036, "percentage": 64.94, "elapsed_time": "4:29:31", "remaining_time": "2:25:31"}
803
+ {"current_steps": 803, "total_steps": 1235, "loss": 0.0147, "lr": 1.315664479122898e-05, "epoch": 3.251012145748988, "percentage": 65.02, "elapsed_time": "4:29:50", "remaining_time": "2:25:10"}
804
+ {"current_steps": 804, "total_steps": 1235, "loss": 0.0138, "lr": 1.3103531580815378e-05, "epoch": 3.2550607287449393, "percentage": 65.1, "elapsed_time": "4:30:10", "remaining_time": "2:24:50"}
805
+ {"current_steps": 805, "total_steps": 1235, "loss": 0.0149, "lr": 1.3050473514379488e-05, "epoch": 3.2591093117408905, "percentage": 65.18, "elapsed_time": "4:30:29", "remaining_time": "2:24:29"}
806
+ {"current_steps": 806, "total_steps": 1235, "loss": 0.0173, "lr": 1.2997471016172188e-05, "epoch": 3.263157894736842, "percentage": 65.26, "elapsed_time": "4:30:49", "remaining_time": "2:24:08"}
807
+ {"current_steps": 807, "total_steps": 1235, "loss": 0.0164, "lr": 1.2944524510000042e-05, "epoch": 3.2672064777327936, "percentage": 65.34, "elapsed_time": "4:31:12", "remaining_time": "2:23:50"}
808
+ {"current_steps": 808, "total_steps": 1235, "loss": 0.0145, "lr": 1.2891634419221908e-05, "epoch": 3.2712550607287447, "percentage": 65.43, "elapsed_time": "4:31:31", "remaining_time": "2:23:29"}