ryanmarten commited on
Commit
80c682e
·
verified ·
1 Parent(s): d517317

Training in progress, epoch 4

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:813e141444b3adbcddacbd5a0c9a43e5007ac0922bbd15d85f47216ab3e1f342
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bfd47b8b42782908601ad5b4d521325ca520e5d0d1ab33f465595bbb24e441d
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:b12e1b493bfe2fa72ec24f6dc498b7e5d44a29a1d15a63e4f6777909cae20ec0
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5ec0fc144fed3782694c80fea16bc8f89a816a5544c129df87babc835ffdd0a
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94493130bf78a0825b5e2288b4a594017c1cadc497eeeb729755d94d4a9b74ea
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beb5487f2eeb1079199edff35e924b551e768903c1629e70b426910d31ac884c
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a8bd49002c50a0aed27a0976dd085c84e1be1b980ff952e7174f89c7e35b73d
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6499a254e9857103cb63976ea78a0914cf27885f57d100d5035480b5af2e4e47
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -467,3 +467,158 @@
467
  {"current_steps": 467, "total_steps": 775, "loss": 0.3891, "lr": 1.636932454945297e-05, "epoch": 3.0032154340836015, "percentage": 60.26, "elapsed_time": "5:39:59", "remaining_time": "3:44:14"}
468
  {"current_steps": 468, "total_steps": 775, "loss": 0.3477, "lr": 1.6280713402979784e-05, "epoch": 3.009646302250804, "percentage": 60.39, "elapsed_time": "5:40:46", "remaining_time": "3:43:32"}
469
  {"current_steps": 469, "total_steps": 775, "loss": 0.3435, "lr": 1.619217781670663e-05, "epoch": 3.0160771704180065, "percentage": 60.52, "elapsed_time": "5:41:31", "remaining_time": "3:42:49"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
467
  {"current_steps": 467, "total_steps": 775, "loss": 0.3891, "lr": 1.636932454945297e-05, "epoch": 3.0032154340836015, "percentage": 60.26, "elapsed_time": "5:39:59", "remaining_time": "3:44:14"}
468
  {"current_steps": 468, "total_steps": 775, "loss": 0.3477, "lr": 1.6280713402979784e-05, "epoch": 3.009646302250804, "percentage": 60.39, "elapsed_time": "5:40:46", "remaining_time": "3:43:32"}
469
  {"current_steps": 469, "total_steps": 775, "loss": 0.3435, "lr": 1.619217781670663e-05, "epoch": 3.0160771704180065, "percentage": 60.52, "elapsed_time": "5:41:31", "remaining_time": "3:42:49"}
470
+ {"current_steps": 470, "total_steps": 775, "loss": 0.3488, "lr": 1.6103719589302826e-05, "epoch": 3.022508038585209, "percentage": 60.65, "elapsed_time": "5:42:16", "remaining_time": "3:42:06"}
471
+ {"current_steps": 471, "total_steps": 775, "loss": 0.3503, "lr": 1.601534051786604e-05, "epoch": 3.0289389067524115, "percentage": 60.77, "elapsed_time": "5:42:54", "remaining_time": "3:41:19"}
472
+ {"current_steps": 472, "total_steps": 775, "loss": 0.3481, "lr": 1.592704239788586e-05, "epoch": 3.035369774919614, "percentage": 60.9, "elapsed_time": "5:43:36", "remaining_time": "3:40:35"}
473
+ {"current_steps": 473, "total_steps": 775, "loss": 0.3466, "lr": 1.583882702320727e-05, "epoch": 3.0418006430868165, "percentage": 61.03, "elapsed_time": "5:44:19", "remaining_time": "3:39:50"}
474
+ {"current_steps": 474, "total_steps": 775, "loss": 0.3348, "lr": 1.5750696185994226e-05, "epoch": 3.0482315112540195, "percentage": 61.16, "elapsed_time": "5:44:56", "remaining_time": "3:39:02"}
475
+ {"current_steps": 475, "total_steps": 775, "loss": 0.3188, "lr": 1.5662651676693213e-05, "epoch": 3.054662379421222, "percentage": 61.29, "elapsed_time": "5:45:33", "remaining_time": "3:38:14"}
476
+ {"current_steps": 476, "total_steps": 775, "loss": 0.3215, "lr": 1.5574695283996942e-05, "epoch": 3.0610932475884245, "percentage": 61.42, "elapsed_time": "5:46:17", "remaining_time": "3:37:31"}
477
+ {"current_steps": 477, "total_steps": 775, "loss": 0.3421, "lr": 1.5486828794807923e-05, "epoch": 3.067524115755627, "percentage": 61.55, "elapsed_time": "5:46:54", "remaining_time": "3:36:43"}
478
+ {"current_steps": 478, "total_steps": 775, "loss": 0.3361, "lr": 1.5399053994202243e-05, "epoch": 3.0739549839228295, "percentage": 61.68, "elapsed_time": "5:47:40", "remaining_time": "3:36:01"}
479
+ {"current_steps": 479, "total_steps": 775, "loss": 0.3308, "lr": 1.531137266539323e-05, "epoch": 3.080385852090032, "percentage": 61.81, "elapsed_time": "5:48:25", "remaining_time": "3:35:18"}
480
+ {"current_steps": 480, "total_steps": 775, "loss": 0.3425, "lr": 1.5223786589695281e-05, "epoch": 3.0868167202572345, "percentage": 61.94, "elapsed_time": "5:49:09", "remaining_time": "3:34:34"}
481
+ {"current_steps": 481, "total_steps": 775, "loss": 0.3743, "lr": 1.5136297546487658e-05, "epoch": 3.0932475884244375, "percentage": 62.06, "elapsed_time": "5:49:57", "remaining_time": "3:33:54"}
482
+ {"current_steps": 482, "total_steps": 775, "loss": 0.3308, "lr": 1.5048907313178313e-05, "epoch": 3.09967845659164, "percentage": 62.19, "elapsed_time": "5:50:42", "remaining_time": "3:33:11"}
483
+ {"current_steps": 483, "total_steps": 775, "loss": 0.3153, "lr": 1.49616176651678e-05, "epoch": 3.1061093247588425, "percentage": 62.32, "elapsed_time": "5:51:28", "remaining_time": "3:32:29"}
484
+ {"current_steps": 484, "total_steps": 775, "loss": 0.3415, "lr": 1.4874430375813223e-05, "epoch": 3.112540192926045, "percentage": 62.45, "elapsed_time": "5:52:09", "remaining_time": "3:31:44"}
485
+ {"current_steps": 485, "total_steps": 775, "loss": 0.3294, "lr": 1.4787347216392171e-05, "epoch": 3.1189710610932475, "percentage": 62.58, "elapsed_time": "5:52:53", "remaining_time": "3:31:00"}
486
+ {"current_steps": 486, "total_steps": 775, "loss": 0.3294, "lr": 1.4700369956066771e-05, "epoch": 3.12540192926045, "percentage": 62.71, "elapsed_time": "5:53:39", "remaining_time": "3:30:18"}
487
+ {"current_steps": 487, "total_steps": 775, "loss": 0.3286, "lr": 1.4613500361847703e-05, "epoch": 3.1318327974276525, "percentage": 62.84, "elapsed_time": "5:54:23", "remaining_time": "3:29:34"}
488
+ {"current_steps": 488, "total_steps": 775, "loss": 0.3415, "lr": 1.4526740198558345e-05, "epoch": 3.1382636655948555, "percentage": 62.97, "elapsed_time": "5:55:05", "remaining_time": "3:28:50"}
489
+ {"current_steps": 489, "total_steps": 775, "loss": 0.3258, "lr": 1.4440091228798896e-05, "epoch": 3.144694533762058, "percentage": 63.1, "elapsed_time": "5:55:50", "remaining_time": "3:28:06"}
490
+ {"current_steps": 490, "total_steps": 775, "loss": 0.3522, "lr": 1.4353555212910577e-05, "epoch": 3.1511254019292605, "percentage": 63.23, "elapsed_time": "5:56:33", "remaining_time": "3:27:23"}
491
+ {"current_steps": 491, "total_steps": 775, "loss": 0.3421, "lr": 1.4267133908939842e-05, "epoch": 3.157556270096463, "percentage": 63.35, "elapsed_time": "5:57:25", "remaining_time": "3:26:44"}
492
+ {"current_steps": 492, "total_steps": 775, "loss": 0.335, "lr": 1.4180829072602715e-05, "epoch": 3.1639871382636655, "percentage": 63.48, "elapsed_time": "5:58:10", "remaining_time": "3:26:01"}
493
+ {"current_steps": 493, "total_steps": 775, "loss": 0.3659, "lr": 1.4094642457249063e-05, "epoch": 3.170418006430868, "percentage": 63.61, "elapsed_time": "5:58:56", "remaining_time": "3:25:18"}
494
+ {"current_steps": 494, "total_steps": 775, "loss": 0.3466, "lr": 1.4008575813827023e-05, "epoch": 3.176848874598071, "percentage": 63.74, "elapsed_time": "5:59:44", "remaining_time": "3:24:37"}
495
+ {"current_steps": 495, "total_steps": 775, "loss": 0.3505, "lr": 1.3922630890847387e-05, "epoch": 3.1832797427652735, "percentage": 63.87, "elapsed_time": "6:00:34", "remaining_time": "3:23:57"}
496
+ {"current_steps": 496, "total_steps": 775, "loss": 0.3455, "lr": 1.3836809434348108e-05, "epoch": 3.189710610932476, "percentage": 64.0, "elapsed_time": "6:01:16", "remaining_time": "3:23:12"}
497
+ {"current_steps": 497, "total_steps": 775, "loss": 0.3183, "lr": 1.375111318785884e-05, "epoch": 3.1961414790996785, "percentage": 64.13, "elapsed_time": "6:01:54", "remaining_time": "3:22:26"}
498
+ {"current_steps": 498, "total_steps": 775, "loss": 0.3393, "lr": 1.3665543892365482e-05, "epoch": 3.202572347266881, "percentage": 64.26, "elapsed_time": "6:02:34", "remaining_time": "3:21:40"}
499
+ {"current_steps": 499, "total_steps": 775, "loss": 0.3643, "lr": 1.3580103286274816e-05, "epoch": 3.2090032154340835, "percentage": 64.39, "elapsed_time": "6:03:19", "remaining_time": "3:20:57"}
500
+ {"current_steps": 500, "total_steps": 775, "loss": 0.3222, "lr": 1.3494793105379217e-05, "epoch": 3.215434083601286, "percentage": 64.52, "elapsed_time": "6:03:59", "remaining_time": "3:20:11"}
501
+ {"current_steps": 501, "total_steps": 775, "loss": 0.3288, "lr": 1.340961508282136e-05, "epoch": 3.221864951768489, "percentage": 64.65, "elapsed_time": "6:04:51", "remaining_time": "3:19:32"}
502
+ {"current_steps": 502, "total_steps": 775, "loss": 0.3453, "lr": 1.3324570949059035e-05, "epoch": 3.2282958199356915, "percentage": 64.77, "elapsed_time": "6:05:36", "remaining_time": "3:18:49"}
503
+ {"current_steps": 503, "total_steps": 775, "loss": 0.3716, "lr": 1.3239662431829949e-05, "epoch": 3.234726688102894, "percentage": 64.9, "elapsed_time": "6:06:19", "remaining_time": "3:18:05"}
504
+ {"current_steps": 504, "total_steps": 775, "loss": 0.3422, "lr": 1.3154891256116677e-05, "epoch": 3.2411575562700965, "percentage": 65.03, "elapsed_time": "6:07:03", "remaining_time": "3:17:22"}
505
+ {"current_steps": 505, "total_steps": 775, "loss": 0.3444, "lr": 1.3070259144111592e-05, "epoch": 3.247588424437299, "percentage": 65.16, "elapsed_time": "6:07:47", "remaining_time": "3:16:38"}
506
+ {"current_steps": 506, "total_steps": 775, "loss": 0.3181, "lr": 1.2985767815181878e-05, "epoch": 3.2540192926045015, "percentage": 65.29, "elapsed_time": "6:08:32", "remaining_time": "3:15:55"}
507
+ {"current_steps": 507, "total_steps": 775, "loss": 0.3298, "lr": 1.2901418985834582e-05, "epoch": 3.260450160771704, "percentage": 65.42, "elapsed_time": "6:09:16", "remaining_time": "3:15:11"}
508
+ {"current_steps": 508, "total_steps": 775, "loss": 0.342, "lr": 1.2817214369681794e-05, "epoch": 3.266881028938907, "percentage": 65.55, "elapsed_time": "6:09:57", "remaining_time": "3:14:26"}
509
+ {"current_steps": 509, "total_steps": 775, "loss": 0.3587, "lr": 1.2733155677405776e-05, "epoch": 3.2733118971061095, "percentage": 65.68, "elapsed_time": "6:10:47", "remaining_time": "3:13:46"}
510
+ {"current_steps": 510, "total_steps": 775, "loss": 0.329, "lr": 1.2649244616724253e-05, "epoch": 3.279742765273312, "percentage": 65.81, "elapsed_time": "6:11:32", "remaining_time": "3:13:03"}
511
+ {"current_steps": 511, "total_steps": 775, "loss": 0.3457, "lr": 1.2565482892355674e-05, "epoch": 3.2861736334405145, "percentage": 65.94, "elapsed_time": "6:12:13", "remaining_time": "3:12:18"}
512
+ {"current_steps": 512, "total_steps": 775, "loss": 0.3493, "lr": 1.248187220598462e-05, "epoch": 3.292604501607717, "percentage": 66.06, "elapsed_time": "6:13:00", "remaining_time": "3:11:36"}
513
+ {"current_steps": 513, "total_steps": 775, "loss": 0.3465, "lr": 1.2398414256227227e-05, "epoch": 3.2990353697749195, "percentage": 66.19, "elapsed_time": "6:13:46", "remaining_time": "3:10:53"}
514
+ {"current_steps": 514, "total_steps": 775, "loss": 0.3263, "lr": 1.2315110738596654e-05, "epoch": 3.305466237942122, "percentage": 66.32, "elapsed_time": "6:14:29", "remaining_time": "3:10:09"}
515
+ {"current_steps": 515, "total_steps": 775, "loss": 0.3383, "lr": 1.223196334546864e-05, "epoch": 3.311897106109325, "percentage": 66.45, "elapsed_time": "6:15:13", "remaining_time": "3:09:26"}
516
+ {"current_steps": 516, "total_steps": 775, "loss": 0.3151, "lr": 1.2148973766047164e-05, "epoch": 3.3183279742765275, "percentage": 66.58, "elapsed_time": "6:15:56", "remaining_time": "3:08:41"}
517
+ {"current_steps": 517, "total_steps": 775, "loss": 0.3177, "lr": 1.2066143686330069e-05, "epoch": 3.32475884244373, "percentage": 66.71, "elapsed_time": "6:16:37", "remaining_time": "3:07:56"}
518
+ {"current_steps": 518, "total_steps": 775, "loss": 0.3255, "lr": 1.1983474789074867e-05, "epoch": 3.3311897106109325, "percentage": 66.84, "elapsed_time": "6:17:19", "remaining_time": "3:07:12"}
519
+ {"current_steps": 519, "total_steps": 775, "loss": 0.3159, "lr": 1.1900968753764483e-05, "epoch": 3.337620578778135, "percentage": 66.97, "elapsed_time": "6:18:01", "remaining_time": "3:06:27"}
520
+ {"current_steps": 520, "total_steps": 775, "loss": 0.3417, "lr": 1.1818627256573203e-05, "epoch": 3.3440514469453375, "percentage": 67.1, "elapsed_time": "6:18:43", "remaining_time": "3:05:43"}
521
+ {"current_steps": 521, "total_steps": 775, "loss": 0.3359, "lr": 1.1736451970332594e-05, "epoch": 3.35048231511254, "percentage": 67.23, "elapsed_time": "6:19:27", "remaining_time": "3:04:59"}
522
+ {"current_steps": 522, "total_steps": 775, "loss": 0.3328, "lr": 1.1654444564497507e-05, "epoch": 3.356913183279743, "percentage": 67.35, "elapsed_time": "6:20:11", "remaining_time": "3:04:16"}
523
+ {"current_steps": 523, "total_steps": 775, "loss": 0.3188, "lr": 1.1572606705112177e-05, "epoch": 3.3633440514469455, "percentage": 67.48, "elapsed_time": "6:20:51", "remaining_time": "3:03:30"}
524
+ {"current_steps": 524, "total_steps": 775, "loss": 0.3489, "lr": 1.1490940054776365e-05, "epoch": 3.369774919614148, "percentage": 67.61, "elapsed_time": "6:21:36", "remaining_time": "3:02:47"}
525
+ {"current_steps": 525, "total_steps": 775, "loss": 0.337, "lr": 1.1409446272611591e-05, "epoch": 3.3762057877813505, "percentage": 67.74, "elapsed_time": "6:22:23", "remaining_time": "3:02:05"}
526
+ {"current_steps": 526, "total_steps": 775, "loss": 0.337, "lr": 1.132812701422744e-05, "epoch": 3.382636655948553, "percentage": 67.87, "elapsed_time": "6:23:06", "remaining_time": "3:01:21"}
527
+ {"current_steps": 527, "total_steps": 775, "loss": 0.3383, "lr": 1.1246983931687874e-05, "epoch": 3.3890675241157555, "percentage": 68.0, "elapsed_time": "6:23:50", "remaining_time": "3:00:38"}
528
+ {"current_steps": 528, "total_steps": 775, "loss": 0.3328, "lr": 1.1166018673477748e-05, "epoch": 3.395498392282958, "percentage": 68.13, "elapsed_time": "6:24:26", "remaining_time": "2:59:50"}
529
+ {"current_steps": 529, "total_steps": 775, "loss": 0.351, "lr": 1.1085232884469236e-05, "epoch": 3.401929260450161, "percentage": 68.26, "elapsed_time": "6:25:10", "remaining_time": "2:59:06"}
530
+ {"current_steps": 530, "total_steps": 775, "loss": 0.334, "lr": 1.1004628205888496e-05, "epoch": 3.4083601286173635, "percentage": 68.39, "elapsed_time": "6:25:54", "remaining_time": "2:58:23"}
531
+ {"current_steps": 531, "total_steps": 775, "loss": 0.3493, "lr": 1.0924206275282248e-05, "epoch": 3.414790996784566, "percentage": 68.52, "elapsed_time": "6:26:38", "remaining_time": "2:57:39"}
532
+ {"current_steps": 532, "total_steps": 775, "loss": 0.3181, "lr": 1.084396872648457e-05, "epoch": 3.4212218649517685, "percentage": 68.65, "elapsed_time": "6:27:14", "remaining_time": "2:56:52"}
533
+ {"current_steps": 533, "total_steps": 775, "loss": 0.3488, "lr": 1.0763917189583685e-05, "epoch": 3.427652733118971, "percentage": 68.77, "elapsed_time": "6:27:55", "remaining_time": "2:56:07"}
534
+ {"current_steps": 534, "total_steps": 775, "loss": 0.3241, "lr": 1.0684053290888824e-05, "epoch": 3.4340836012861735, "percentage": 68.9, "elapsed_time": "6:28:36", "remaining_time": "2:55:22"}
535
+ {"current_steps": 535, "total_steps": 775, "loss": 0.3303, "lr": 1.060437865289719e-05, "epoch": 3.440514469453376, "percentage": 69.03, "elapsed_time": "6:29:21", "remaining_time": "2:54:40"}
536
+ {"current_steps": 536, "total_steps": 775, "loss": 0.3109, "lr": 1.0524894894261035e-05, "epoch": 3.446945337620579, "percentage": 69.16, "elapsed_time": "6:30:01", "remaining_time": "2:53:54"}
537
+ {"current_steps": 537, "total_steps": 775, "loss": 0.3187, "lr": 1.044560362975474e-05, "epoch": 3.4533762057877815, "percentage": 69.29, "elapsed_time": "6:30:47", "remaining_time": "2:53:12"}
538
+ {"current_steps": 538, "total_steps": 775, "loss": 0.336, "lr": 1.0366506470242019e-05, "epoch": 3.459807073954984, "percentage": 69.42, "elapsed_time": "6:31:29", "remaining_time": "2:52:27"}
539
+ {"current_steps": 539, "total_steps": 775, "loss": 0.3243, "lr": 1.0287605022643183e-05, "epoch": 3.4662379421221865, "percentage": 69.55, "elapsed_time": "6:32:11", "remaining_time": "2:51:43"}
540
+ {"current_steps": 540, "total_steps": 775, "loss": 0.3602, "lr": 1.0208900889902504e-05, "epoch": 3.472668810289389, "percentage": 69.68, "elapsed_time": "6:32:57", "remaining_time": "2:51:00"}
541
+ {"current_steps": 541, "total_steps": 775, "loss": 0.323, "lr": 1.0130395670955655e-05, "epoch": 3.4790996784565915, "percentage": 69.81, "elapsed_time": "6:33:41", "remaining_time": "2:50:16"}
542
+ {"current_steps": 542, "total_steps": 775, "loss": 0.3368, "lr": 1.0052090960697231e-05, "epoch": 3.485530546623794, "percentage": 69.94, "elapsed_time": "6:34:21", "remaining_time": "2:49:31"}
543
+ {"current_steps": 543, "total_steps": 775, "loss": 0.2997, "lr": 9.97398834994831e-06, "epoch": 3.491961414790997, "percentage": 70.06, "elapsed_time": "6:35:00", "remaining_time": "2:48:46"}
544
+ {"current_steps": 544, "total_steps": 775, "loss": 0.3431, "lr": 9.896089425424188e-06, "epoch": 3.4983922829581995, "percentage": 70.19, "elapsed_time": "6:35:44", "remaining_time": "2:48:02"}
545
+ {"current_steps": 545, "total_steps": 775, "loss": 0.338, "lr": 9.818395769702099e-06, "epoch": 3.504823151125402, "percentage": 70.32, "elapsed_time": "6:36:25", "remaining_time": "2:47:18"}
546
+ {"current_steps": 546, "total_steps": 775, "loss": 0.343, "lr": 9.740908961189089e-06, "epoch": 3.5112540192926045, "percentage": 70.45, "elapsed_time": "6:37:05", "remaining_time": "2:46:32"}
547
+ {"current_steps": 547, "total_steps": 775, "loss": 0.3577, "lr": 9.663630574089948e-06, "epoch": 3.517684887459807, "percentage": 70.58, "elapsed_time": "6:37:48", "remaining_time": "2:45:48"}
548
+ {"current_steps": 548, "total_steps": 775, "loss": 0.3469, "lr": 9.586562178375206e-06, "epoch": 3.5241157556270095, "percentage": 70.71, "elapsed_time": "6:38:28", "remaining_time": "2:45:03"}
549
+ {"current_steps": 549, "total_steps": 775, "loss": 0.336, "lr": 9.509705339749277e-06, "epoch": 3.530546623794212, "percentage": 70.84, "elapsed_time": "6:39:08", "remaining_time": "2:44:18"}
550
+ {"current_steps": 550, "total_steps": 775, "loss": 0.3414, "lr": 9.433061619618604e-06, "epoch": 3.536977491961415, "percentage": 70.97, "elapsed_time": "6:39:58", "remaining_time": "2:43:37"}
551
+ {"current_steps": 551, "total_steps": 775, "loss": 0.3386, "lr": 9.356632575059986e-06, "epoch": 3.5434083601286175, "percentage": 71.1, "elapsed_time": "6:40:44", "remaining_time": "2:42:55"}
552
+ {"current_steps": 552, "total_steps": 775, "loss": 0.3486, "lr": 9.280419758788894e-06, "epoch": 3.54983922829582, "percentage": 71.23, "elapsed_time": "6:41:28", "remaining_time": "2:42:11"}
553
+ {"current_steps": 553, "total_steps": 775, "loss": 0.3613, "lr": 9.204424719127976e-06, "epoch": 3.5562700964630225, "percentage": 71.35, "elapsed_time": "6:42:11", "remaining_time": "2:41:27"}
554
+ {"current_steps": 554, "total_steps": 775, "loss": 0.3073, "lr": 9.12864899997558e-06, "epoch": 3.562700964630225, "percentage": 71.48, "elapsed_time": "6:42:45", "remaining_time": "2:40:39"}
555
+ {"current_steps": 555, "total_steps": 775, "loss": 0.3567, "lr": 9.053094140774367e-06, "epoch": 3.5691318327974275, "percentage": 71.61, "elapsed_time": "6:43:30", "remaining_time": "2:39:56"}
556
+ {"current_steps": 556, "total_steps": 775, "loss": 0.3269, "lr": 8.977761676480065e-06, "epoch": 3.57556270096463, "percentage": 71.74, "elapsed_time": "6:44:07", "remaining_time": "2:39:10"}
557
+ {"current_steps": 557, "total_steps": 775, "loss": 0.3276, "lr": 8.902653137530283e-06, "epoch": 3.581993569131833, "percentage": 71.87, "elapsed_time": "6:44:46", "remaining_time": "2:38:25"}
558
+ {"current_steps": 558, "total_steps": 775, "loss": 0.3221, "lr": 8.82777004981341e-06, "epoch": 3.5884244372990355, "percentage": 72.0, "elapsed_time": "6:45:26", "remaining_time": "2:37:40"}
559
+ {"current_steps": 559, "total_steps": 775, "loss": 0.3602, "lr": 8.753113934637621e-06, "epoch": 3.594855305466238, "percentage": 72.13, "elapsed_time": "6:46:14", "remaining_time": "2:36:58"}
560
+ {"current_steps": 560, "total_steps": 775, "loss": 0.3445, "lr": 8.678686308699957e-06, "epoch": 3.6012861736334405, "percentage": 72.26, "elapsed_time": "6:46:58", "remaining_time": "2:36:14"}
561
+ {"current_steps": 561, "total_steps": 775, "loss": 0.316, "lr": 8.60448868405552e-06, "epoch": 3.607717041800643, "percentage": 72.39, "elapsed_time": "6:47:46", "remaining_time": "2:35:33"}
562
+ {"current_steps": 562, "total_steps": 775, "loss": 0.32, "lr": 8.530522568086777e-06, "epoch": 3.6141479099678455, "percentage": 72.52, "elapsed_time": "6:48:32", "remaining_time": "2:34:50"}
563
+ {"current_steps": 563, "total_steps": 775, "loss": 0.3186, "lr": 8.456789463472902e-06, "epoch": 3.620578778135048, "percentage": 72.65, "elapsed_time": "6:49:17", "remaining_time": "2:34:07"}
564
+ {"current_steps": 564, "total_steps": 775, "loss": 0.341, "lr": 8.383290868159256e-06, "epoch": 3.627009646302251, "percentage": 72.77, "elapsed_time": "6:50:02", "remaining_time": "2:33:24"}
565
+ {"current_steps": 565, "total_steps": 775, "loss": 0.3329, "lr": 8.31002827532698e-06, "epoch": 3.6334405144694535, "percentage": 72.9, "elapsed_time": "6:50:48", "remaining_time": "2:32:41"}
566
+ {"current_steps": 566, "total_steps": 775, "loss": 0.3374, "lr": 8.23700317336262e-06, "epoch": 3.639871382636656, "percentage": 73.03, "elapsed_time": "6:51:33", "remaining_time": "2:31:58"}
567
+ {"current_steps": 567, "total_steps": 775, "loss": 0.3458, "lr": 8.164217045827934e-06, "epoch": 3.6463022508038585, "percentage": 73.16, "elapsed_time": "6:52:20", "remaining_time": "2:31:15"}
568
+ {"current_steps": 568, "total_steps": 775, "loss": 0.3405, "lr": 8.091671371429697e-06, "epoch": 3.652733118971061, "percentage": 73.29, "elapsed_time": "6:53:09", "remaining_time": "2:30:34"}
569
+ {"current_steps": 569, "total_steps": 775, "loss": 0.3483, "lr": 8.01936762398972e-06, "epoch": 3.6591639871382635, "percentage": 73.42, "elapsed_time": "6:53:54", "remaining_time": "2:29:50"}
570
+ {"current_steps": 570, "total_steps": 775, "loss": 0.3243, "lr": 7.947307272414874e-06, "epoch": 3.665594855305466, "percentage": 73.55, "elapsed_time": "6:54:38", "remaining_time": "2:29:07"}
571
+ {"current_steps": 571, "total_steps": 775, "loss": 0.3198, "lr": 7.875491780667246e-06, "epoch": 3.672025723472669, "percentage": 73.68, "elapsed_time": "6:55:21", "remaining_time": "2:28:23"}
572
+ {"current_steps": 572, "total_steps": 775, "loss": 0.3226, "lr": 7.803922607734398e-06, "epoch": 3.6784565916398715, "percentage": 73.81, "elapsed_time": "6:56:06", "remaining_time": "2:27:40"}
573
+ {"current_steps": 573, "total_steps": 775, "loss": 0.3269, "lr": 7.732601207599753e-06, "epoch": 3.684887459807074, "percentage": 73.94, "elapsed_time": "6:56:47", "remaining_time": "2:26:55"}
574
+ {"current_steps": 574, "total_steps": 775, "loss": 0.3467, "lr": 7.661529029213023e-06, "epoch": 3.6913183279742765, "percentage": 74.06, "elapsed_time": "6:57:34", "remaining_time": "2:26:13"}
575
+ {"current_steps": 575, "total_steps": 775, "loss": 0.3323, "lr": 7.590707516460807e-06, "epoch": 3.697749196141479, "percentage": 74.19, "elapsed_time": "6:58:25", "remaining_time": "2:25:32"}
576
+ {"current_steps": 576, "total_steps": 775, "loss": 0.342, "lr": 7.520138108137205e-06, "epoch": 3.7041800643086815, "percentage": 74.32, "elapsed_time": "6:59:13", "remaining_time": "2:24:50"}
577
+ {"current_steps": 577, "total_steps": 775, "loss": 0.3607, "lr": 7.44982223791463e-06, "epoch": 3.710610932475884, "percentage": 74.45, "elapsed_time": "7:00:02", "remaining_time": "2:24:08"}
578
+ {"current_steps": 578, "total_steps": 775, "loss": 0.3448, "lr": 7.379761334314688e-06, "epoch": 3.717041800643087, "percentage": 74.58, "elapsed_time": "7:00:51", "remaining_time": "2:23:26"}
579
+ {"current_steps": 579, "total_steps": 775, "loss": 0.3288, "lr": 7.3099568206791315e-06, "epoch": 3.7234726688102895, "percentage": 74.71, "elapsed_time": "7:01:36", "remaining_time": "2:22:43"}
580
+ {"current_steps": 580, "total_steps": 775, "loss": 0.3466, "lr": 7.240410115140934e-06, "epoch": 3.729903536977492, "percentage": 74.84, "elapsed_time": "7:02:27", "remaining_time": "2:22:01"}
581
+ {"current_steps": 581, "total_steps": 775, "loss": 0.3202, "lr": 7.171122630595526e-06, "epoch": 3.7363344051446945, "percentage": 74.97, "elapsed_time": "7:03:07", "remaining_time": "2:21:17"}
582
+ {"current_steps": 582, "total_steps": 775, "loss": 0.3502, "lr": 7.102095774672035e-06, "epoch": 3.742765273311897, "percentage": 75.1, "elapsed_time": "7:03:49", "remaining_time": "2:20:32"}
583
+ {"current_steps": 583, "total_steps": 775, "loss": 0.3203, "lr": 7.033330949704738e-06, "epoch": 3.7491961414790995, "percentage": 75.23, "elapsed_time": "7:04:29", "remaining_time": "2:19:47"}
584
+ {"current_steps": 584, "total_steps": 775, "loss": 0.3465, "lr": 6.964829552704526e-06, "epoch": 3.755627009646302, "percentage": 75.35, "elapsed_time": "7:05:09", "remaining_time": "2:19:03"}
585
+ {"current_steps": 585, "total_steps": 775, "loss": 0.3431, "lr": 6.89659297533057e-06, "epoch": 3.762057877813505, "percentage": 75.48, "elapsed_time": "7:05:52", "remaining_time": "2:18:19"}
586
+ {"current_steps": 586, "total_steps": 775, "loss": 0.3531, "lr": 6.828622603862012e-06, "epoch": 3.7684887459807075, "percentage": 75.61, "elapsed_time": "7:06:41", "remaining_time": "2:17:37"}
587
+ {"current_steps": 587, "total_steps": 775, "loss": 0.3644, "lr": 6.760919819169813e-06, "epoch": 3.77491961414791, "percentage": 75.74, "elapsed_time": "7:07:24", "remaining_time": "2:16:53"}
588
+ {"current_steps": 588, "total_steps": 775, "loss": 0.3183, "lr": 6.693485996688695e-06, "epoch": 3.7813504823151125, "percentage": 75.87, "elapsed_time": "7:08:10", "remaining_time": "2:16:10"}
589
+ {"current_steps": 589, "total_steps": 775, "loss": 0.3296, "lr": 6.62632250638922e-06, "epoch": 3.787781350482315, "percentage": 76.0, "elapsed_time": "7:08:53", "remaining_time": "2:15:26"}
590
+ {"current_steps": 590, "total_steps": 775, "loss": 0.3485, "lr": 6.559430712749928e-06, "epoch": 3.7942122186495175, "percentage": 76.13, "elapsed_time": "7:09:36", "remaining_time": "2:14:42"}
591
+ {"current_steps": 591, "total_steps": 775, "loss": 0.3105, "lr": 6.492811974729645e-06, "epoch": 3.80064308681672, "percentage": 76.26, "elapsed_time": "7:10:22", "remaining_time": "2:13:59"}
592
+ {"current_steps": 592, "total_steps": 775, "loss": 0.3473, "lr": 6.42646764573984e-06, "epoch": 3.807073954983923, "percentage": 76.39, "elapsed_time": "7:11:08", "remaining_time": "2:13:16"}
593
+ {"current_steps": 593, "total_steps": 775, "loss": 0.3421, "lr": 6.360399073617152e-06, "epoch": 3.8135048231511255, "percentage": 76.52, "elapsed_time": "7:11:55", "remaining_time": "2:12:33"}
594
+ {"current_steps": 594, "total_steps": 775, "loss": 0.3257, "lr": 6.2946076005960184e-06, "epoch": 3.819935691318328, "percentage": 76.65, "elapsed_time": "7:12:37", "remaining_time": "2:11:49"}
595
+ {"current_steps": 595, "total_steps": 775, "loss": 0.3398, "lr": 6.229094563281393e-06, "epoch": 3.8263665594855305, "percentage": 76.77, "elapsed_time": "7:13:16", "remaining_time": "2:11:04"}
596
+ {"current_steps": 596, "total_steps": 775, "loss": 0.3422, "lr": 6.163861292621569e-06, "epoch": 3.832797427652733, "percentage": 76.9, "elapsed_time": "7:14:00", "remaining_time": "2:10:20"}
597
+ {"current_steps": 597, "total_steps": 775, "loss": 0.3415, "lr": 6.098909113881193e-06, "epoch": 3.839228295819936, "percentage": 77.03, "elapsed_time": "7:14:37", "remaining_time": "2:09:35"}
598
+ {"current_steps": 598, "total_steps": 775, "loss": 0.3501, "lr": 6.034239346614281e-06, "epoch": 3.845659163987138, "percentage": 77.16, "elapsed_time": "7:15:18", "remaining_time": "2:08:50"}
599
+ {"current_steps": 599, "total_steps": 775, "loss": 0.347, "lr": 5.969853304637467e-06, "epoch": 3.852090032154341, "percentage": 77.29, "elapsed_time": "7:16:05", "remaining_time": "2:08:08"}
600
+ {"current_steps": 600, "total_steps": 775, "loss": 0.3621, "lr": 5.90575229600326e-06, "epoch": 3.8585209003215435, "percentage": 77.42, "elapsed_time": "7:16:47", "remaining_time": "2:07:23"}
601
+ {"current_steps": 601, "total_steps": 775, "loss": 0.3273, "lr": 5.841937622973515e-06, "epoch": 3.864951768488746, "percentage": 77.55, "elapsed_time": "7:17:32", "remaining_time": "2:06:40"}
602
+ {"current_steps": 602, "total_steps": 775, "loss": 0.3232, "lr": 5.778410581992953e-06, "epoch": 3.8713826366559485, "percentage": 77.68, "elapsed_time": "7:18:15", "remaining_time": "2:05:56"}
603
+ {"current_steps": 603, "total_steps": 775, "loss": 0.3482, "lr": 5.715172463662817e-06, "epoch": 3.877813504823151, "percentage": 77.81, "elapsed_time": "7:19:02", "remaining_time": "2:05:14"}
604
+ {"current_steps": 604, "total_steps": 775, "loss": 0.3357, "lr": 5.65222455271466e-06, "epoch": 3.884244372990354, "percentage": 77.94, "elapsed_time": "7:19:47", "remaining_time": "2:04:30"}
605
+ {"current_steps": 605, "total_steps": 775, "loss": 0.3377, "lr": 5.5895681279842615e-06, "epoch": 3.890675241157556, "percentage": 78.06, "elapsed_time": "7:20:32", "remaining_time": "2:03:47"}
606
+ {"current_steps": 606, "total_steps": 775, "loss": 0.3297, "lr": 5.52720446238562e-06, "epoch": 3.897106109324759, "percentage": 78.19, "elapsed_time": "7:21:14", "remaining_time": "2:03:03"}
607
+ {"current_steps": 607, "total_steps": 775, "loss": 0.3125, "lr": 5.465134822885119e-06, "epoch": 3.9035369774919615, "percentage": 78.32, "elapsed_time": "7:21:54", "remaining_time": "2:02:18"}
608
+ {"current_steps": 608, "total_steps": 775, "loss": 0.2965, "lr": 5.403360470475751e-06, "epoch": 3.909967845659164, "percentage": 78.45, "elapsed_time": "7:22:34", "remaining_time": "2:01:33"}
609
+ {"current_steps": 609, "total_steps": 775, "loss": 0.336, "lr": 5.341882660151527e-06, "epoch": 3.9163987138263665, "percentage": 78.58, "elapsed_time": "7:23:23", "remaining_time": "2:00:51"}
610
+ {"current_steps": 610, "total_steps": 775, "loss": 0.3316, "lr": 5.280702640881992e-06, "epoch": 3.922829581993569, "percentage": 78.71, "elapsed_time": "7:24:02", "remaining_time": "2:00:06"}
611
+ {"current_steps": 611, "total_steps": 775, "loss": 0.3225, "lr": 5.219821655586821e-06, "epoch": 3.929260450160772, "percentage": 78.84, "elapsed_time": "7:24:50", "remaining_time": "1:59:24"}
612
+ {"current_steps": 612, "total_steps": 775, "loss": 0.3206, "lr": 5.1592409411105775e-06, "epoch": 3.935691318327974, "percentage": 78.97, "elapsed_time": "7:25:30", "remaining_time": "1:58:39"}
613
+ {"current_steps": 613, "total_steps": 775, "loss": 0.3289, "lr": 5.0989617281976e-06, "epoch": 3.942122186495177, "percentage": 79.1, "elapsed_time": "7:26:13", "remaining_time": "1:57:55"}
614
+ {"current_steps": 614, "total_steps": 775, "loss": 0.3262, "lr": 5.038985241466978e-06, "epoch": 3.9485530546623795, "percentage": 79.23, "elapsed_time": "7:26:57", "remaining_time": "1:57:12"}
615
+ {"current_steps": 615, "total_steps": 775, "loss": 0.3297, "lr": 4.979312699387699e-06, "epoch": 3.954983922829582, "percentage": 79.35, "elapsed_time": "7:27:44", "remaining_time": "1:56:29"}
616
+ {"current_steps": 616, "total_steps": 775, "loss": 0.3294, "lr": 4.919945314253853e-06, "epoch": 3.9614147909967845, "percentage": 79.48, "elapsed_time": "7:28:26", "remaining_time": "1:55:45"}
617
+ {"current_steps": 617, "total_steps": 775, "loss": 0.3427, "lr": 4.860884292160053e-06, "epoch": 3.967845659163987, "percentage": 79.61, "elapsed_time": "7:29:10", "remaining_time": "1:55:01"}
618
+ {"current_steps": 618, "total_steps": 775, "loss": 0.3387, "lr": 4.802130832976905e-06, "epoch": 3.97427652733119, "percentage": 79.74, "elapsed_time": "7:29:54", "remaining_time": "1:54:17"}
619
+ {"current_steps": 619, "total_steps": 775, "loss": 0.337, "lr": 4.7436861303266255e-06, "epoch": 3.980707395498392, "percentage": 79.87, "elapsed_time": "7:30:37", "remaining_time": "1:53:34"}
620
+ {"current_steps": 620, "total_steps": 775, "loss": 0.3495, "lr": 4.685551371558798e-06, "epoch": 3.987138263665595, "percentage": 80.0, "elapsed_time": "7:31:20", "remaining_time": "1:52:50"}
621
+ {"current_steps": 621, "total_steps": 775, "loss": 0.3278, "lr": 4.6277277377262705e-06, "epoch": 3.9935691318327975, "percentage": 80.13, "elapsed_time": "7:32:01", "remaining_time": "1:52:05"}
622
+ {"current_steps": 622, "total_steps": 775, "loss": 0.3295, "lr": 4.570216403561141e-06, "epoch": 4.0, "percentage": 80.26, "elapsed_time": "7:32:42", "remaining_time": "1:51:21"}
623
+ {"current_steps": 623, "total_steps": 775, "loss": 0.2947, "lr": 4.513018537450897e-06, "epoch": 4.006430868167203, "percentage": 80.39, "elapsed_time": "7:34:10", "remaining_time": "1:50:48"}
624
+ {"current_steps": 624, "total_steps": 775, "loss": 0.2952, "lr": 4.456135301414672e-06, "epoch": 4.012861736334405, "percentage": 80.52, "elapsed_time": "7:34:52", "remaining_time": "1:50:04"}