0x1202 commited on
Commit
7dcd4cb
·
verified ·
1 Parent(s): 156cbb4

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 sha256:083de0e17bec98e47e272e249c16fa5dde71b8dba3310558a507bbd46523f5ee
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc6679f17a4eba4cb719d3c1c23ad9fd8766b595f7ee0a020f248abc707f4393
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e1a86ff754ffb0b8734d24659c4fc524a00407ec4b0ba3d9561f5ff76b34885
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c6e65581068362858715e14bb97798f8e03fabfa411d17280c733ec3d9bc66a
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:217395e233075be7599fd8d7436e9b9723665b45d2d6269731631964b1bd72ef
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:535fdf4c0a3f71d25281edce97d7d5cb1c2b4e518dff96eeb9a6e9efb0fe9ed7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d359eb5d29e75fb2bbe5b7026981da69b95b8ad1fea469302d13cde104f7e8a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.5392982959747314,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.0942951438000943,
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": 56.303,
374
  "eval_steps_per_second": 14.123,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3883562421977088.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.4839268922805786,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.1885902876001886,
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": 56.303,
374
  "eval_steps_per_second": 14.123,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.09618104667609619,
379
+ "grad_norm": 1.2728794813156128,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.3532,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.09806694955209806,
386
+ "grad_norm": 1.2738091945648193,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.3604,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.09995285242809995,
393
+ "grad_norm": 1.0199331045150757,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.3546,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.10183875530410184,
400
+ "grad_norm": 0.8882190585136414,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.1719,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.10372465818010372,
407
+ "grad_norm": 0.8215413093566895,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.3678,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.10561056105610561,
414
+ "grad_norm": 0.7815274000167847,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.3791,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.1074964639321075,
421
+ "grad_norm": 0.7754129767417908,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.3071,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.10938236680810938,
428
+ "grad_norm": 0.8610193729400635,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.4257,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.11126826968411127,
435
+ "grad_norm": 0.7398249506950378,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.3307,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.11315417256011315,
442
+ "grad_norm": 0.8163387179374695,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.2897,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.11504007543611504,
449
+ "grad_norm": 0.8740779161453247,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.2508,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.11692597831211693,
456
+ "grad_norm": 0.818240225315094,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.2878,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.1188118811881188,
463
+ "grad_norm": 0.8404731154441833,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.3849,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.1206977840641207,
470
+ "grad_norm": 0.896458625793457,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.4535,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.12258368694012259,
477
+ "grad_norm": 0.8432134389877319,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.4789,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.12446958981612447,
484
+ "grad_norm": 0.8519056439399719,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.5264,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.12635549269212634,
491
+ "grad_norm": 0.7978764772415161,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.3318,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.12824139556812825,
498
+ "grad_norm": 0.8735756278038025,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.355,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.13012729844413012,
505
+ "grad_norm": 0.8317325711250305,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.3436,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.132013201320132,
512
+ "grad_norm": 0.9063963294029236,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.5033,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.1338991041961339,
519
+ "grad_norm": 0.8298577070236206,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.4334,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.13578500707213578,
526
+ "grad_norm": 0.821303129196167,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.4554,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.13767090994813766,
533
+ "grad_norm": 0.8228156566619873,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.3866,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.13955681282413956,
540
+ "grad_norm": 0.8506703972816467,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.473,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.14144271570014144,
547
+ "grad_norm": 0.8994743824005127,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.6536,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.14332861857614332,
554
+ "grad_norm": 0.9050391912460327,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.3966,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.14521452145214522,
561
+ "grad_norm": 0.9391245245933533,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.7276,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.1471004243281471,
568
+ "grad_norm": 0.8455343842506409,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.4665,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.14898632720414898,
575
+ "grad_norm": 0.9894546866416931,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.5861,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.15087223008015088,
582
+ "grad_norm": 0.883921205997467,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.4461,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.15275813295615276,
589
+ "grad_norm": 0.9232316613197327,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.7158,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.15464403583215464,
596
+ "grad_norm": 0.9596819877624512,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.7722,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.15652993870815654,
603
+ "grad_norm": 0.920516848564148,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.4213,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.15841584158415842,
610
+ "grad_norm": 0.9526838660240173,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.6793,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.1603017444601603,
617
+ "grad_norm": 0.9615785479545593,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.5577,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.1621876473361622,
624
+ "grad_norm": 0.891538679599762,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.4552,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.16407355021216408,
631
+ "grad_norm": 0.9908190369606018,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.4512,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.16595945308816595,
638
+ "grad_norm": 0.9302291870117188,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.6369,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.16784535596416786,
645
+ "grad_norm": 1.0175998210906982,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.5077,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.16973125884016974,
652
+ "grad_norm": 0.9874126315116882,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 1.733,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.1716171617161716,
659
+ "grad_norm": 0.9775768518447876,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.5483,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.1735030645921735,
666
+ "grad_norm": 1.0082566738128662,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 1.5691,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.1753889674681754,
673
+ "grad_norm": 1.0059901475906372,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.4483,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.17727487034417727,
680
+ "grad_norm": 0.9890210628509521,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.5623,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.17916077322017915,
687
+ "grad_norm": 1.0527801513671875,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.6086,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.18104667609618105,
694
+ "grad_norm": 1.0493412017822266,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.6354,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.18293257897218293,
701
+ "grad_norm": 1.129049301147461,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.4702,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.1848184818481848,
708
+ "grad_norm": 1.0613797903060913,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.5875,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.1867043847241867,
715
+ "grad_norm": 1.1796647310256958,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.6639,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.1885902876001886,
722
+ "grad_norm": 1.1907509565353394,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.5667,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.1885902876001886,
729
+ "eval_loss": 1.4839268922805786,
730
+ "eval_runtime": 15.8643,
731
+ "eval_samples_per_second": 56.29,
732
+ "eval_steps_per_second": 14.12,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 7767124843954176.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null