cilooor commited on
Commit
2318f0b
·
verified ·
1 Parent(s): 48357a6

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:e106118a2f9b6a7edc717aa3f220280869f964af76b03e0058d330106dd03aea
3
  size 100966336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08eddf5d2e1789ff2f97c75af72290ccecf51a8a5190d83f884a919bd7797fbc
3
  size 100966336
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb6194ae8b4a56b4cb5b3330b5c7b119d6a7aeb39e2a8a540d46dcd3022fe695
3
  size 51613348
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9be178ef563b2fda0549454bcba7c6bac8dc41ee555d989efeef6bbcd010fb4d
3
  size 51613348
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0737c65cfb863a83c7789853d624689484fa6d0da1b7397792a75b91ed0ea9de
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a27e81cefaa8529725105e912d37767f2af2ad487c8790d604cb2445088ea2b0
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e07c26f7a41136ba9f3d3869ea72572828daa7f34e9c88ec270e56c2618f851
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b7af7cbef1883982510fef2007cf89af07627ee7ec1378e98375ea74556514a
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.9474524855613708,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.02733360666940003,
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": 32.478,
374
  "eval_steps_per_second": 8.127,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.43243442388992e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8693193197250366,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.05466721333880006,
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": 32.478,
374
  "eval_steps_per_second": 8.127,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.02788027880278803,
379
+ "grad_norm": 0.9167900681495667,
380
+ "learning_rate": 6.739731809235446e-05,
381
+ "loss": 0.7292,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.02842695093617603,
386
+ "grad_norm": 1.0346499681472778,
387
+ "learning_rate": 6.71470445011073e-05,
388
+ "loss": 0.7878,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.02897362306956403,
393
+ "grad_norm": 0.9062778949737549,
394
+ "learning_rate": 6.688579272361309e-05,
395
+ "loss": 0.8643,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.02952029520295203,
400
+ "grad_norm": 0.6097351908683777,
401
+ "learning_rate": 6.66136519771145e-05,
402
+ "loss": 0.8222,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.03006696733634003,
407
+ "grad_norm": 0.5191702246665955,
408
+ "learning_rate": 6.633071519742718e-05,
409
+ "loss": 0.9669,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.030613639469728032,
414
+ "grad_norm": 0.37056273221969604,
415
+ "learning_rate": 6.603707900720217e-05,
416
+ "loss": 0.8109,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.031160311603116032,
421
+ "grad_norm": 0.3645178973674774,
422
+ "learning_rate": 6.573284368292943e-05,
423
+ "loss": 0.921,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.03170698373650403,
428
+ "grad_norm": 0.35407713055610657,
429
+ "learning_rate": 6.541811312069348e-05,
430
+ "loss": 0.8393,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.03225365586989203,
435
+ "grad_norm": 0.30585721135139465,
436
+ "learning_rate": 6.509299480069303e-05,
437
+ "loss": 0.8196,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.03280032800328003,
442
+ "grad_norm": 0.31569743156433105,
443
+ "learning_rate": 6.47575997505365e-05,
444
+ "loss": 0.9089,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.03334700013666803,
449
+ "grad_norm": 0.31442388892173767,
450
+ "learning_rate": 6.441204250732624e-05,
451
+ "loss": 0.7743,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.03389367227005603,
456
+ "grad_norm": 0.3461879789829254,
457
+ "learning_rate": 6.405644107854427e-05,
458
+ "loss": 0.8485,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.03444034440344403,
463
+ "grad_norm": 0.346314400434494,
464
+ "learning_rate": 6.369091690175273e-05,
465
+ "loss": 0.7661,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.03498701653683203,
470
+ "grad_norm": 0.3185812532901764,
471
+ "learning_rate": 6.331559480312315e-05,
472
+ "loss": 0.8583,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.03553368867022003,
477
+ "grad_norm": 0.3503943979740143,
478
+ "learning_rate": 6.293060295480838e-05,
479
+ "loss": 0.8725,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.03608036080360803,
484
+ "grad_norm": 0.3459616005420685,
485
+ "learning_rate": 6.25360728311719e-05,
486
+ "loss": 0.8382,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.03662703293699603,
491
+ "grad_norm": 0.38812822103500366,
492
+ "learning_rate": 6.213213916388954e-05,
493
+ "loss": 0.9174,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.03717370507038404,
498
+ "grad_norm": 0.37094104290008545,
499
+ "learning_rate": 6.171893989593859e-05,
500
+ "loss": 0.881,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.03772037720377204,
505
+ "grad_norm": 0.5786832571029663,
506
+ "learning_rate": 6.129661613449057e-05,
507
+ "loss": 0.9016,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.03826704933716004,
512
+ "grad_norm": 0.6645287871360779,
513
+ "learning_rate": 6.086531210272306e-05,
514
+ "loss": 0.965,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.03881372147054804,
519
+ "grad_norm": 0.43764594197273254,
520
+ "learning_rate": 6.042517509056784e-05,
521
+ "loss": 0.9049,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.03936039360393604,
526
+ "grad_norm": 0.34731465578079224,
527
+ "learning_rate": 5.997635540441133e-05,
528
+ "loss": 0.8948,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.03990706573732404,
533
+ "grad_norm": 0.40091952681541443,
534
+ "learning_rate": 5.9519006315765176e-05,
535
+ "loss": 0.8426,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.04045373787071204,
540
+ "grad_norm": 0.3977827727794647,
541
+ "learning_rate": 5.9053284008924185e-05,
542
+ "loss": 0.8352,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.04100041000410004,
547
+ "grad_norm": 0.4238167107105255,
548
+ "learning_rate": 5.85793475276295e-05,
549
+ "loss": 0.8615,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.04154708213748804,
554
+ "grad_norm": 0.46092405915260315,
555
+ "learning_rate": 5.809735872075529e-05,
556
+ "loss": 0.8255,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.04209375427087604,
561
+ "grad_norm": 0.4420395791530609,
562
+ "learning_rate": 5.760748218703755e-05,
563
+ "loss": 0.7647,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.04264042640426404,
568
+ "grad_norm": 0.4960534870624542,
569
+ "learning_rate": 5.710988521886378e-05,
570
+ "loss": 0.909,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.04318709853765204,
575
+ "grad_norm": 0.49868643283843994,
576
+ "learning_rate": 5.660473774514275e-05,
577
+ "loss": 0.7568,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.04373377067104004,
582
+ "grad_norm": 0.5315876603126526,
583
+ "learning_rate": 5.6092212273273975e-05,
584
+ "loss": 0.8924,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.04428044280442804,
589
+ "grad_norm": 0.5740758776664734,
590
+ "learning_rate": 5.557248383023655e-05,
591
+ "loss": 0.8379,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.04482711493781605,
596
+ "grad_norm": 0.613091766834259,
597
+ "learning_rate": 5.5045729902817676e-05,
598
+ "loss": 0.9659,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.04537378707120405,
603
+ "grad_norm": 0.6900278329849243,
604
+ "learning_rate": 5.4512130377000987e-05,
605
+ "loss": 0.9506,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.04592045920459205,
610
+ "grad_norm": 0.6675617694854736,
611
+ "learning_rate": 5.397186747653573e-05,
612
+ "loss": 0.9986,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.04646713133798005,
617
+ "grad_norm": 0.6233535408973694,
618
+ "learning_rate": 5.342512570070745e-05,
619
+ "loss": 0.9033,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.04701380347136805,
624
+ "grad_norm": 0.659621000289917,
625
+ "learning_rate": 5.287209176133174e-05,
626
+ "loss": 0.9068,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.04756047560475605,
631
+ "grad_norm": 0.759048342704773,
632
+ "learning_rate": 5.231295451899226e-05,
633
+ "loss": 0.9384,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.04810714773814405,
638
+ "grad_norm": 0.8321371078491211,
639
+ "learning_rate": 5.174790491854502e-05,
640
+ "loss": 1.0077,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.04865381987153205,
645
+ "grad_norm": 0.7181084156036377,
646
+ "learning_rate": 5.117713592391096e-05,
647
+ "loss": 1.0386,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.04920049200492005,
652
+ "grad_norm": 0.8390389084815979,
653
+ "learning_rate": 5.060084245217884e-05,
654
+ "loss": 1.0526,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.04974716413830805,
659
+ "grad_norm": 0.7568452954292297,
660
+ "learning_rate": 5.0019221307041306e-05,
661
+ "loss": 0.9571,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.05029383627169605,
666
+ "grad_norm": 1.033366322517395,
667
+ "learning_rate": 4.943247111158662e-05,
668
+ "loss": 0.9084,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.05084050840508405,
673
+ "grad_norm": 0.9008201360702515,
674
+ "learning_rate": 4.884079224046898e-05,
675
+ "loss": 0.8388,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.05138718053847205,
680
+ "grad_norm": 0.8567910194396973,
681
+ "learning_rate": 4.824438675148086e-05,
682
+ "loss": 0.9807,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.05193385267186005,
687
+ "grad_norm": 1.0424281358718872,
688
+ "learning_rate": 4.764345831655036e-05,
689
+ "loss": 1.0143,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.05248052480524805,
694
+ "grad_norm": 1.1355541944503784,
695
+ "learning_rate": 4.703821215218748e-05,
696
+ "loss": 0.9176,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.053027196938636056,
701
+ "grad_norm": 1.2170919179916382,
702
+ "learning_rate": 4.642885494940291e-05,
703
+ "loss": 0.8303,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.053573869072024057,
708
+ "grad_norm": 1.626427173614502,
709
+ "learning_rate": 4.581559480312316e-05,
710
+ "loss": 0.8297,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.05412054120541206,
715
+ "grad_norm": 1.3740547895431519,
716
+ "learning_rate": 4.519864114112636e-05,
717
+ "loss": 0.7661,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.05466721333880006,
722
+ "grad_norm": 2.6349620819091797,
723
+ "learning_rate": 4.45782046525229e-05,
724
+ "loss": 1.0357,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.05466721333880006,
729
+ "eval_loss": 0.8693193197250366,
730
+ "eval_runtime": 94.6807,
731
+ "eval_samples_per_second": 32.541,
732
+ "eval_steps_per_second": 8.143,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.896121962482893e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null