prxy5605 commited on
Commit
d1453ef
·
verified ·
1 Parent(s): 25b9d30

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:c817f04884e03a5a36445c1ad47d03c4aa5aa117672a86bf8d5265294375b0cf
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00eaadf807d93761ef5e07139c8dddbb275e835a415337718c887545d74e7ba7
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bddefb71fe53ef66816f53a3f93d907066beb57833ffcba5aceb82ebb9c013b
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59c49c3f7d0592475f5a3b291ddc60e64ea767a49fdbecfaa24782fe4b88e25b
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4719350c0e52f581766e15785f00fc4c5f905e43d1dc77913784d58829c61ee1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49e687ee3597cc2458951fb9af2b7ff6d3ff128adb033f60830e063504287484
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5335737b4b4d079cdec612fe6ee661ed4d29f9e0e55eb4eada44a9677240228
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e0244c146d76bf610ae39789eea36d0bff336b81d211db008e020e66921060c
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.475726842880249,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.01536216299254935,
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": 12.357,
374
  "eval_steps_per_second": 6.178,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.19077308849193e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.2480071783065796,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.0307243259850987,
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": 12.357,
374
  "eval_steps_per_second": 6.178,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.015669406252400337,
379
+ "grad_norm": 17.104642868041992,
380
+ "learning_rate": 9.285836503510562e-05,
381
+ "loss": 6.866,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.015976649512251324,
386
+ "grad_norm": 12.813888549804688,
387
+ "learning_rate": 9.24024048078213e-05,
388
+ "loss": 6.4915,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.01628389277210231,
393
+ "grad_norm": 8.647307395935059,
394
+ "learning_rate": 9.193352839727121e-05,
395
+ "loss": 4.6191,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.0165911360319533,
400
+ "grad_norm": 8.637353897094727,
401
+ "learning_rate": 9.145187862775209e-05,
402
+ "loss": 5.2535,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.016898379291804287,
407
+ "grad_norm": 8.05450439453125,
408
+ "learning_rate": 9.09576022144496e-05,
409
+ "loss": 4.8999,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.017205622551655274,
414
+ "grad_norm": 8.113150596618652,
415
+ "learning_rate": 9.045084971874738e-05,
416
+ "loss": 4.5401,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.01751286581150626,
421
+ "grad_norm": 9.034808158874512,
422
+ "learning_rate": 8.993177550236464e-05,
423
+ "loss": 5.2058,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.017820109071357247,
428
+ "grad_norm": 9.577351570129395,
429
+ "learning_rate": 8.940053768033609e-05,
430
+ "loss": 4.8838,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.018127352331208234,
435
+ "grad_norm": 8.906129837036133,
436
+ "learning_rate": 8.885729807284856e-05,
437
+ "loss": 4.4069,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.01843459559105922,
442
+ "grad_norm": 8.663689613342285,
443
+ "learning_rate": 8.83022221559489e-05,
444
+ "loss": 4.3744,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.018741838850910207,
449
+ "grad_norm": 8.294697761535645,
450
+ "learning_rate": 8.773547901113862e-05,
451
+ "loss": 4.1245,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.019049082110761194,
456
+ "grad_norm": 8.371333122253418,
457
+ "learning_rate": 8.715724127386972e-05,
458
+ "loss": 4.5234,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.019356325370612184,
463
+ "grad_norm": 8.438100814819336,
464
+ "learning_rate": 8.656768508095853e-05,
465
+ "loss": 4.2958,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.01966356863046317,
470
+ "grad_norm": 8.364363670349121,
471
+ "learning_rate": 8.596699001693255e-05,
472
+ "loss": 3.934,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.019970811890314157,
477
+ "grad_norm": 7.366670608520508,
478
+ "learning_rate": 8.535533905932738e-05,
479
+ "loss": 3.5163,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.020278055150165144,
484
+ "grad_norm": 7.6314921379089355,
485
+ "learning_rate": 8.473291852294987e-05,
486
+ "loss": 3.7853,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.02058529841001613,
491
+ "grad_norm": 7.76265811920166,
492
+ "learning_rate": 8.409991800312493e-05,
493
+ "loss": 3.8884,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.020892541669867117,
498
+ "grad_norm": 8.086345672607422,
499
+ "learning_rate": 8.345653031794292e-05,
500
+ "loss": 3.5251,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.021199784929718104,
505
+ "grad_norm": 6.946031093597412,
506
+ "learning_rate": 8.280295144952536e-05,
507
+ "loss": 3.593,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.02150702818956909,
512
+ "grad_norm": 7.788767337799072,
513
+ "learning_rate": 8.213938048432697e-05,
514
+ "loss": 4.1621,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.021814271449420077,
519
+ "grad_norm": 8.629899978637695,
520
+ "learning_rate": 8.146601955249188e-05,
521
+ "loss": 3.7884,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.022121514709271064,
526
+ "grad_norm": 6.985069274902344,
527
+ "learning_rate": 8.07830737662829e-05,
528
+ "loss": 3.9133,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.022428757969122054,
533
+ "grad_norm": 6.972623825073242,
534
+ "learning_rate": 8.009075115760243e-05,
535
+ "loss": 3.205,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.02273600122897304,
540
+ "grad_norm": 7.396304130554199,
541
+ "learning_rate": 7.938926261462366e-05,
542
+ "loss": 3.4196,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.023043244488824027,
547
+ "grad_norm": 7.159494876861572,
548
+ "learning_rate": 7.86788218175523e-05,
549
+ "loss": 3.5241,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.023350487748675014,
554
+ "grad_norm": 7.689444541931152,
555
+ "learning_rate": 7.795964517353735e-05,
556
+ "loss": 4.3798,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.023657731008526,
561
+ "grad_norm": 8.844693183898926,
562
+ "learning_rate": 7.723195175075136e-05,
563
+ "loss": 4.4668,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.023964974268376987,
568
+ "grad_norm": 8.752437591552734,
569
+ "learning_rate": 7.649596321166024e-05,
570
+ "loss": 4.4342,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.024272217528227974,
575
+ "grad_norm": 8.479850769042969,
576
+ "learning_rate": 7.575190374550272e-05,
577
+ "loss": 4.2627,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.02457946078807896,
582
+ "grad_norm": 8.894695281982422,
583
+ "learning_rate": 7.500000000000001e-05,
584
+ "loss": 4.7375,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.024886704047929947,
589
+ "grad_norm": 9.680545806884766,
590
+ "learning_rate": 7.424048101231686e-05,
591
+ "loss": 5.2633,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.025193947307780934,
596
+ "grad_norm": 9.162818908691406,
597
+ "learning_rate": 7.347357813929454e-05,
598
+ "loss": 4.553,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.025501190567631924,
603
+ "grad_norm": 9.10145378112793,
604
+ "learning_rate": 7.269952498697734e-05,
605
+ "loss": 4.7129,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.02580843382748291,
610
+ "grad_norm": 9.074843406677246,
611
+ "learning_rate": 7.191855733945387e-05,
612
+ "loss": 4.0724,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.026115677087333897,
617
+ "grad_norm": 9.07311725616455,
618
+ "learning_rate": 7.113091308703498e-05,
619
+ "loss": 4.7301,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.026422920347184884,
624
+ "grad_norm": 11.810867309570312,
625
+ "learning_rate": 7.033683215379002e-05,
626
+ "loss": 5.2496,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.02673016360703587,
631
+ "grad_norm": 10.740492820739746,
632
+ "learning_rate": 6.953655642446368e-05,
633
+ "loss": 5.3248,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.027037406866886857,
638
+ "grad_norm": 10.580676078796387,
639
+ "learning_rate": 6.873032967079561e-05,
640
+ "loss": 4.8344,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.027344650126737844,
645
+ "grad_norm": 11.064846992492676,
646
+ "learning_rate": 6.7918397477265e-05,
647
+ "loss": 4.8108,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.02765189338658883,
652
+ "grad_norm": 11.720850944519043,
653
+ "learning_rate": 6.710100716628344e-05,
654
+ "loss": 4.8933,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.027959136646439817,
659
+ "grad_norm": 9.551570892333984,
660
+ "learning_rate": 6.627840772285784e-05,
661
+ "loss": 4.714,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.028266379906290804,
666
+ "grad_norm": 11.187040328979492,
667
+ "learning_rate": 6.545084971874738e-05,
668
+ "loss": 4.073,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.028573623166141794,
673
+ "grad_norm": 9.788082122802734,
674
+ "learning_rate": 6.461858523613684e-05,
675
+ "loss": 4.7062,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.02888086642599278,
680
+ "grad_norm": 10.513997077941895,
681
+ "learning_rate": 6.378186779084995e-05,
682
+ "loss": 4.612,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.029188109685843767,
687
+ "grad_norm": 12.733663558959961,
688
+ "learning_rate": 6.294095225512603e-05,
689
+ "loss": 5.4784,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.029495352945694754,
694
+ "grad_norm": 13.620742797851562,
695
+ "learning_rate": 6.209609477998338e-05,
696
+ "loss": 5.3613,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.02980259620554574,
701
+ "grad_norm": 13.19336986541748,
702
+ "learning_rate": 6.124755271719325e-05,
703
+ "loss": 5.6018,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.030109839465396727,
708
+ "grad_norm": 13.040425300598145,
709
+ "learning_rate": 6.0395584540887963e-05,
710
+ "loss": 5.054,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.030417082725247714,
715
+ "grad_norm": 14.068294525146484,
716
+ "learning_rate": 5.9540449768827246e-05,
717
+ "loss": 5.6559,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.0307243259850987,
722
+ "grad_norm": 14.678174018859863,
723
+ "learning_rate": 5.868240888334653e-05,
724
+ "loss": 5.2266,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.0307243259850987,
729
+ "eval_loss": 1.2480071783065796,
730
+ "eval_runtime": 443.7094,
731
+ "eval_samples_per_second": 12.355,
732
+ "eval_steps_per_second": 6.177,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.434577118649385e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null