brixeus commited on
Commit
0c5dc11
·
verified ·
1 Parent(s): 1cb0016

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 sha256:3a7414f1717e763fd1d1bc0ff1443bc226d38715dd3e84929ccf125f81229575
3
  size 389074464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a1b26be33253ad0a66ee5d25b8f9a2d25786b2b02e44283b3f4858c74918498
3
  size 389074464
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f0354fcbdc7c02ba64c683e6f035eb2dc2a1c44a6fb808c1334ca6f3d81e6d2
3
  size 198011252
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34b6e58541ad0d0a61f2edc7efde332154dc6f3545e03394635737552df4fecb
3
  size 198011252
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed0956d47007a2a867730c82ef5b0cd441e0ef3721f94e37bb72572e8a5f5044
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a8366215dffbd63174077be1231ee70e87f021ffca8910618e93d26b5e4c45c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed340328d62f63f2d9d00f6904395875dd09851f050e03ae91b4b798d852ce41
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99ca67f9a35cd1c50df3d93bedf5a6642db2c7847c021a0a8d3f44c1bf4993d3
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.2765874862670898,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.06791171477079797,
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": 16.335,
374
  "eval_steps_per_second": 4.084,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 4.041831845619302e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.2262212038040161,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.13582342954159593,
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": 16.335,
374
  "eval_steps_per_second": 4.084,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.06926994906621392,
379
+ "grad_norm": 0.7125508189201355,
380
+ "learning_rate": 9.729774092143627e-05,
381
+ "loss": 1.3574,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.07062818336162988,
386
+ "grad_norm": 0.5578199028968811,
387
+ "learning_rate": 9.716559066288715e-05,
388
+ "loss": 1.2801,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.07198641765704585,
393
+ "grad_norm": 0.4072265923023224,
394
+ "learning_rate": 9.703037989675087e-05,
395
+ "loss": 1.1512,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.0733446519524618,
400
+ "grad_norm": 0.2695824205875397,
401
+ "learning_rate": 9.689211739666023e-05,
402
+ "loss": 1.2332,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.07470288624787776,
407
+ "grad_norm": 0.2340139001607895,
408
+ "learning_rate": 9.675081213427076e-05,
409
+ "loss": 1.1724,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.07606112054329371,
414
+ "grad_norm": 0.23189423978328705,
415
+ "learning_rate": 9.66064732786784e-05,
416
+ "loss": 1.1846,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.07741935483870968,
421
+ "grad_norm": 0.2402050495147705,
422
+ "learning_rate": 9.645911019582467e-05,
423
+ "loss": 1.207,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.07877758913412564,
428
+ "grad_norm": 0.25576063990592957,
429
+ "learning_rate": 9.630873244788883e-05,
430
+ "loss": 1.2574,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.08013582342954159,
435
+ "grad_norm": 0.25986823439598083,
436
+ "learning_rate": 9.615534979266745e-05,
437
+ "loss": 1.2114,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.08149405772495756,
442
+ "grad_norm": 0.250826358795166,
443
+ "learning_rate": 9.599897218294122e-05,
444
+ "loss": 1.1968,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.08285229202037352,
449
+ "grad_norm": 0.25176748633384705,
450
+ "learning_rate": 9.583960976582913e-05,
451
+ "loss": 1.1929,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.08421052631578947,
456
+ "grad_norm": 0.2325923889875412,
457
+ "learning_rate": 9.567727288213005e-05,
458
+ "loss": 1.2047,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.08556876061120543,
463
+ "grad_norm": 0.22908318042755127,
464
+ "learning_rate": 9.551197206565173e-05,
465
+ "loss": 1.1473,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.0869269949066214,
470
+ "grad_norm": 0.21206900477409363,
471
+ "learning_rate": 9.534371804252728e-05,
472
+ "loss": 1.1855,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.08828522920203735,
477
+ "grad_norm": 0.22555455565452576,
478
+ "learning_rate": 9.517252173051911e-05,
479
+ "loss": 1.1698,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.08964346349745331,
484
+ "grad_norm": 0.23330341279506683,
485
+ "learning_rate": 9.49983942383106e-05,
486
+ "loss": 1.1946,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.09100169779286928,
491
+ "grad_norm": 0.24638806283473969,
492
+ "learning_rate": 9.482134686478519e-05,
493
+ "loss": 1.209,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.09235993208828523,
498
+ "grad_norm": 0.2484908103942871,
499
+ "learning_rate": 9.464139109829321e-05,
500
+ "loss": 1.1865,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.09371816638370119,
505
+ "grad_norm": 0.23545753955841064,
506
+ "learning_rate": 9.445853861590647e-05,
507
+ "loss": 1.2447,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.09507640067911714,
512
+ "grad_norm": 0.22677823901176453,
513
+ "learning_rate": 9.42728012826605e-05,
514
+ "loss": 1.1572,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.09643463497453311,
519
+ "grad_norm": 0.22840863466262817,
520
+ "learning_rate": 9.408419115078471e-05,
521
+ "loss": 1.2223,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.09779286926994907,
526
+ "grad_norm": 0.23291656374931335,
527
+ "learning_rate": 9.389272045892024e-05,
528
+ "loss": 1.2053,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.09915110356536502,
533
+ "grad_norm": 0.24530543386936188,
534
+ "learning_rate": 9.36984016313259e-05,
535
+ "loss": 1.2103,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.10050933786078098,
540
+ "grad_norm": 0.24790343642234802,
541
+ "learning_rate": 9.350124727707197e-05,
542
+ "loss": 1.1125,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.10186757215619695,
547
+ "grad_norm": 0.23026898503303528,
548
+ "learning_rate": 9.330127018922194e-05,
549
+ "loss": 1.2442,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.1032258064516129,
554
+ "grad_norm": 0.24416302144527435,
555
+ "learning_rate": 9.309848334400246e-05,
556
+ "loss": 1.1953,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.10458404074702886,
561
+ "grad_norm": 0.22965535521507263,
562
+ "learning_rate": 9.289289989996133e-05,
563
+ "loss": 1.2232,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.10594227504244483,
568
+ "grad_norm": 0.2312672883272171,
569
+ "learning_rate": 9.268453319711363e-05,
570
+ "loss": 1.1542,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.10730050933786078,
575
+ "grad_norm": 0.2299879491329193,
576
+ "learning_rate": 9.247339675607605e-05,
577
+ "loss": 1.209,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.10865874363327674,
582
+ "grad_norm": 0.23572081327438354,
583
+ "learning_rate": 9.225950427718975e-05,
584
+ "loss": 1.2257,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.1100169779286927,
589
+ "grad_norm": 0.23509450256824493,
590
+ "learning_rate": 9.204286963963111e-05,
591
+ "loss": 1.1656,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.11137521222410866,
596
+ "grad_norm": 0.2482880800962448,
597
+ "learning_rate": 9.182350690051133e-05,
598
+ "loss": 1.1448,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.11273344651952462,
603
+ "grad_norm": 0.24817270040512085,
604
+ "learning_rate": 9.160143029396422e-05,
605
+ "loss": 1.2322,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.11409168081494057,
610
+ "grad_norm": 0.24748308956623077,
611
+ "learning_rate": 9.13766542302225e-05,
612
+ "loss": 1.1227,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.11544991511035653,
617
+ "grad_norm": 0.25305241346359253,
618
+ "learning_rate": 9.114919329468282e-05,
619
+ "loss": 1.1337,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.1168081494057725,
624
+ "grad_norm": 0.24612681567668915,
625
+ "learning_rate": 9.091906224695935e-05,
626
+ "loss": 1.114,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.11816638370118845,
631
+ "grad_norm": 0.28515782952308655,
632
+ "learning_rate": 9.068627601992598e-05,
633
+ "loss": 1.1734,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.11952461799660441,
638
+ "grad_norm": 0.2633991539478302,
639
+ "learning_rate": 9.045084971874738e-05,
640
+ "loss": 1.1993,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.12088285229202038,
645
+ "grad_norm": 0.26582807302474976,
646
+ "learning_rate": 9.021279861989885e-05,
647
+ "loss": 1.1467,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.12224108658743633,
652
+ "grad_norm": 0.26425063610076904,
653
+ "learning_rate": 8.997213817017507e-05,
654
+ "loss": 1.2081,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.12359932088285229,
659
+ "grad_norm": 0.26553940773010254,
660
+ "learning_rate": 8.972888398568772e-05,
661
+ "loss": 1.1629,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.12495755517826825,
666
+ "grad_norm": 0.2655147910118103,
667
+ "learning_rate": 8.948305185085225e-05,
668
+ "loss": 1.1801,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.12631578947368421,
673
+ "grad_norm": 0.2920195162296295,
674
+ "learning_rate": 8.92346577173636e-05,
675
+ "loss": 1.1947,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.12767402376910017,
680
+ "grad_norm": 0.2780720591545105,
681
+ "learning_rate": 8.898371770316111e-05,
682
+ "loss": 1.209,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.12903225806451613,
687
+ "grad_norm": 0.27526527643203735,
688
+ "learning_rate": 8.873024809138272e-05,
689
+ "loss": 1.173,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.13039049235993208,
694
+ "grad_norm": 0.29257383942604065,
695
+ "learning_rate": 8.847426532930831e-05,
696
+ "loss": 1.2088,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.13174872665534804,
701
+ "grad_norm": 0.29788464307785034,
702
+ "learning_rate": 8.821578602729242e-05,
703
+ "loss": 1.135,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.13310696095076402,
708
+ "grad_norm": 0.31753095984458923,
709
+ "learning_rate": 8.795482695768658e-05,
710
+ "loss": 1.1596,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.13446519524617997,
715
+ "grad_norm": 0.37438032031059265,
716
+ "learning_rate": 8.769140505375085e-05,
717
+ "loss": 1.1788,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.13582342954159593,
722
+ "grad_norm": 0.4673005938529968,
723
+ "learning_rate": 8.742553740855506e-05,
724
+ "loss": 1.2225,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.13582342954159593,
729
+ "eval_loss": 1.2262212038040161,
730
+ "eval_runtime": 75.8474,
731
+ "eval_samples_per_second": 16.349,
732
+ "eval_steps_per_second": 4.087,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 8.054998217156198e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null