lesso commited on
Commit
9f38cd9
·
verified ·
1 Parent(s): 98f52c2

Training in progress, step 100, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4b314e8fb63daff55e83a017f04e3a851f9c9f6217e441c7a8d336cdc862b06
3
  size 1157746040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81828e3e61b4387228ad3c68a9ba9231d8672c73c1b05769197c2d6000a5a10c
3
  size 1157746040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b472b1de39010939a9bdae3f4c5b57c79fb54a3345f96a1e37cf963aa6f446d
3
  size 588699796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5303af86a139a579e4e2c61f6de3133b66ded50e50fd29e4c9abf77182aacbe0
3
  size 588699796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f98fbdd4d58209ef00d8f0a7f017e3042c6a22b25876059accf358aadf37a4c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d914f88fd473c9ee149cb520f3e290d828f1c3cc7e21304f6d037422c1b59399
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:748d9a23213f440465d56c8725191473b3687c4889dcbd09de987b3511dd9ea6
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac9085a964616f2d2af1a309022ca2f10b583138a852293c2266e9df64914089
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.6663289666175842,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.05042864346949067,
5
  "eval_steps": 50,
6
- "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -373,6 +373,364 @@
373
  "eval_samples_per_second": 8.843,
374
  "eval_steps_per_second": 2.221,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 4.357300236897485e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.635071337223053,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.10085728693898134,
5
  "eval_steps": 50,
6
+ "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
373
  "eval_samples_per_second": 8.843,
374
  "eval_steps_per_second": 2.221,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.05143721633888049,
379
+ "grad_norm": 0.8349344730377197,
380
+ "learning_rate": 7.856221052631579e-05,
381
+ "loss": 0.4587,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.052445789208270296,
386
+ "grad_norm": 0.6953268647193909,
387
+ "learning_rate": 7.803494736842106e-05,
388
+ "loss": 0.666,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.05345436207766011,
393
+ "grad_norm": 0.7224613428115845,
394
+ "learning_rate": 7.750768421052632e-05,
395
+ "loss": 0.7536,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.05446293494704992,
400
+ "grad_norm": 0.6757810115814209,
401
+ "learning_rate": 7.698042105263157e-05,
402
+ "loss": 0.6169,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.05547150781643974,
407
+ "grad_norm": 0.7635074257850647,
408
+ "learning_rate": 7.645315789473686e-05,
409
+ "loss": 0.6307,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.05648008068582955,
414
+ "grad_norm": 0.6975710988044739,
415
+ "learning_rate": 7.592589473684211e-05,
416
+ "loss": 0.6233,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.057488653555219364,
421
+ "grad_norm": 0.9252186417579651,
422
+ "learning_rate": 7.539863157894737e-05,
423
+ "loss": 0.6551,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.05849722642460918,
428
+ "grad_norm": 0.8248884677886963,
429
+ "learning_rate": 7.487136842105264e-05,
430
+ "loss": 0.5789,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.05950579929399899,
435
+ "grad_norm": 0.6074532866477966,
436
+ "learning_rate": 7.43441052631579e-05,
437
+ "loss": 0.5004,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.060514372163388806,
442
+ "grad_norm": 0.6752936244010925,
443
+ "learning_rate": 7.381684210526315e-05,
444
+ "loss": 0.4884,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.061522945032778616,
449
+ "grad_norm": 0.7720556259155273,
450
+ "learning_rate": 7.328957894736844e-05,
451
+ "loss": 0.7758,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.06253151790216843,
456
+ "grad_norm": 0.699116051197052,
457
+ "learning_rate": 7.276231578947369e-05,
458
+ "loss": 0.5716,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.06354009077155824,
463
+ "grad_norm": 0.7762227058410645,
464
+ "learning_rate": 7.223505263157895e-05,
465
+ "loss": 0.6935,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.06454866364094806,
470
+ "grad_norm": 0.6913344264030457,
471
+ "learning_rate": 7.170778947368422e-05,
472
+ "loss": 0.6068,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.06555723651033787,
477
+ "grad_norm": 0.7144531011581421,
478
+ "learning_rate": 7.118052631578947e-05,
479
+ "loss": 0.6431,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.06656580937972768,
484
+ "grad_norm": 0.6667282581329346,
485
+ "learning_rate": 7.065326315789474e-05,
486
+ "loss": 0.5421,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.06757438224911749,
491
+ "grad_norm": 0.6969847083091736,
492
+ "learning_rate": 7.0126e-05,
493
+ "loss": 0.6785,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.06858295511850732,
498
+ "grad_norm": 0.6973515748977661,
499
+ "learning_rate": 6.959873684210527e-05,
500
+ "loss": 0.5455,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.06959152798789713,
505
+ "grad_norm": 0.7713499069213867,
506
+ "learning_rate": 6.907147368421054e-05,
507
+ "loss": 0.7372,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.07060010085728693,
512
+ "grad_norm": 0.5957585573196411,
513
+ "learning_rate": 6.85442105263158e-05,
514
+ "loss": 0.4954,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.07160867372667676,
519
+ "grad_norm": 0.7025538086891174,
520
+ "learning_rate": 6.801694736842105e-05,
521
+ "loss": 0.5496,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.07261724659606657,
526
+ "grad_norm": 0.7217448353767395,
527
+ "learning_rate": 6.748968421052632e-05,
528
+ "loss": 0.5567,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.07362581946545638,
533
+ "grad_norm": 0.7021524906158447,
534
+ "learning_rate": 6.696242105263158e-05,
535
+ "loss": 0.5291,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.07463439233484619,
540
+ "grad_norm": 0.7426285743713379,
541
+ "learning_rate": 6.643515789473685e-05,
542
+ "loss": 0.6815,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.07564296520423601,
547
+ "grad_norm": 0.7391223311424255,
548
+ "learning_rate": 6.590789473684212e-05,
549
+ "loss": 0.6689,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.07665153807362582,
554
+ "grad_norm": 0.6848605871200562,
555
+ "learning_rate": 6.538063157894737e-05,
556
+ "loss": 0.5782,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.07766011094301563,
561
+ "grad_norm": 0.711951732635498,
562
+ "learning_rate": 6.485336842105264e-05,
563
+ "loss": 0.5801,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.07866868381240545,
568
+ "grad_norm": 0.5852221846580505,
569
+ "learning_rate": 6.43261052631579e-05,
570
+ "loss": 0.4995,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.07967725668179526,
575
+ "grad_norm": 0.9040377736091614,
576
+ "learning_rate": 6.379884210526315e-05,
577
+ "loss": 0.5318,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.08068582955118507,
582
+ "grad_norm": 0.756641149520874,
583
+ "learning_rate": 6.327157894736842e-05,
584
+ "loss": 0.6616,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.08169440242057488,
589
+ "grad_norm": 0.7158970832824707,
590
+ "learning_rate": 6.274431578947368e-05,
591
+ "loss": 0.6113,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.0827029752899647,
596
+ "grad_norm": 0.6931173205375671,
597
+ "learning_rate": 6.221705263157895e-05,
598
+ "loss": 0.5882,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.08371154815935451,
603
+ "grad_norm": 0.7512569427490234,
604
+ "learning_rate": 6.168978947368422e-05,
605
+ "loss": 0.6451,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.08472012102874432,
610
+ "grad_norm": 0.7793223261833191,
611
+ "learning_rate": 6.116252631578948e-05,
612
+ "loss": 0.6186,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.08572869389813415,
617
+ "grad_norm": 0.7280353307723999,
618
+ "learning_rate": 6.063526315789474e-05,
619
+ "loss": 0.6657,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.08673726676752395,
624
+ "grad_norm": 0.7213184833526611,
625
+ "learning_rate": 6.0108e-05,
626
+ "loss": 0.6312,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.08774583963691376,
631
+ "grad_norm": 0.7809893488883972,
632
+ "learning_rate": 5.9580736842105264e-05,
633
+ "loss": 0.6928,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.08875441250630359,
638
+ "grad_norm": 0.8184586763381958,
639
+ "learning_rate": 5.905347368421053e-05,
640
+ "loss": 0.6551,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.0897629853756934,
645
+ "grad_norm": 0.8529835939407349,
646
+ "learning_rate": 5.85262105263158e-05,
647
+ "loss": 0.7481,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.0907715582450832,
652
+ "grad_norm": 0.8931265473365784,
653
+ "learning_rate": 5.799894736842106e-05,
654
+ "loss": 0.7928,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.09178013111447302,
659
+ "grad_norm": 0.7958138585090637,
660
+ "learning_rate": 5.747168421052632e-05,
661
+ "loss": 0.6151,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.09278870398386284,
666
+ "grad_norm": 0.7931579351425171,
667
+ "learning_rate": 5.694442105263158e-05,
668
+ "loss": 0.7141,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.09379727685325265,
673
+ "grad_norm": 0.8281200528144836,
674
+ "learning_rate": 5.641715789473684e-05,
675
+ "loss": 0.6538,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.09480584972264246,
680
+ "grad_norm": 0.8042008280754089,
681
+ "learning_rate": 5.5889894736842104e-05,
682
+ "loss": 0.6661,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.09581442259203228,
687
+ "grad_norm": 0.8040047287940979,
688
+ "learning_rate": 5.5362631578947374e-05,
689
+ "loss": 0.5659,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.09682299546142209,
694
+ "grad_norm": 1.044537901878357,
695
+ "learning_rate": 5.483536842105264e-05,
696
+ "loss": 0.835,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.0978315683308119,
701
+ "grad_norm": 0.9413779377937317,
702
+ "learning_rate": 5.43081052631579e-05,
703
+ "loss": 0.7605,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.09884014120020171,
708
+ "grad_norm": 0.9656868577003479,
709
+ "learning_rate": 5.378084210526316e-05,
710
+ "loss": 0.7144,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.09984871406959153,
715
+ "grad_norm": 1.0694280862808228,
716
+ "learning_rate": 5.3253578947368426e-05,
717
+ "loss": 0.8615,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.10085728693898134,
722
+ "grad_norm": 1.2606571912765503,
723
+ "learning_rate": 5.272631578947368e-05,
724
+ "loss": 0.8549,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.10085728693898134,
729
+ "eval_loss": 0.635071337223053,
730
+ "eval_runtime": 47.0624,
731
+ "eval_samples_per_second": 8.882,
732
+ "eval_steps_per_second": 2.231,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 8.648580773235917e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null