nttx commited on
Commit
7004214
·
verified ·
1 Parent(s): c2bea46

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 sha256:4ce414ddee18ea2ff8268914e587fa6d2815504d8486d1025eb97f9bd84d1270
3
  size 619632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3554b096598d4ffe4d6c6ab0fcd222e947ea0d773632e3166b47c90e404670f5
3
  size 619632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8836edf04604e89bc6da23b1b6ab3f81f9081ba6fd8b076849da1e070f6ab52
3
  size 1389562
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71fc2235a4435ff746559d8b6cd6f59a3a1257c2e7c18349931da4ee292afc98
3
  size 1389562
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb761900590c87c2c76cee8e5fee76eb0209f8b8f4c75269e304391b47f4c3ab
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16c0d3884c4171cb35b30e45733c8aceec60d607d1c8e91b302b35e908a4751a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ad2841b888ce0ae948634757c3fcacf0119c249e0fec8f3ca61ea266369ef92
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5d2a6c6aafc669cea03b9634666f204de949a3d45ce2f48a07e7e3eaf18c715
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 11.842723846435547,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.30257186081694404,
5
  "eval_steps": 25,
6
- "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -381,6 +381,372 @@
381
  "eval_samples_per_second": 71.924,
382
  "eval_steps_per_second": 10.069,
383
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
384
  }
385
  ],
386
  "logging_steps": 1,
@@ -409,7 +775,7 @@
409
  "attributes": {}
410
  }
411
  },
412
- "total_flos": 74996515012608.0,
413
  "train_batch_size": 8,
414
  "trial_name": null,
415
  "trial_params": null
 
1
  {
2
+ "best_metric": 11.836865425109863,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.6051437216338881,
5
  "eval_steps": 25,
6
+ "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
381
  "eval_samples_per_second": 71.924,
382
  "eval_steps_per_second": 10.069,
383
  "step": 50
384
+ },
385
+ {
386
+ "epoch": 0.3086232980332829,
387
+ "grad_norm": 0.08492244780063629,
388
+ "learning_rate": 0.0002668315918143169,
389
+ "loss": 11.8407,
390
+ "step": 51
391
+ },
392
+ {
393
+ "epoch": 0.3146747352496218,
394
+ "grad_norm": 0.062073949724435806,
395
+ "learning_rate": 0.00026526016662852886,
396
+ "loss": 11.8387,
397
+ "step": 52
398
+ },
399
+ {
400
+ "epoch": 0.3207261724659607,
401
+ "grad_norm": 0.05150603875517845,
402
+ "learning_rate": 0.00026365723046405023,
403
+ "loss": 11.8453,
404
+ "step": 53
405
+ },
406
+ {
407
+ "epoch": 0.3267776096822995,
408
+ "grad_norm": 0.05246227607131004,
409
+ "learning_rate": 0.0002620232215476231,
410
+ "loss": 11.8417,
411
+ "step": 54
412
+ },
413
+ {
414
+ "epoch": 0.3328290468986384,
415
+ "grad_norm": 0.052143048495054245,
416
+ "learning_rate": 0.0002603585866009697,
417
+ "loss": 11.8406,
418
+ "step": 55
419
+ },
420
+ {
421
+ "epoch": 0.3388804841149773,
422
+ "grad_norm": 0.05662680044770241,
423
+ "learning_rate": 0.00025866378071866334,
424
+ "loss": 11.8421,
425
+ "step": 56
426
+ },
427
+ {
428
+ "epoch": 0.34493192133131617,
429
+ "grad_norm": 0.09383895993232727,
430
+ "learning_rate": 0.00025693926724370956,
431
+ "loss": 11.8537,
432
+ "step": 57
433
+ },
434
+ {
435
+ "epoch": 0.35098335854765506,
436
+ "grad_norm": 0.060755398124456406,
437
+ "learning_rate": 0.00025518551764087326,
438
+ "loss": 11.8472,
439
+ "step": 58
440
+ },
441
+ {
442
+ "epoch": 0.35703479576399394,
443
+ "grad_norm": 0.050716038793325424,
444
+ "learning_rate": 0.00025340301136778483,
445
+ "loss": 11.8475,
446
+ "step": 59
447
+ },
448
+ {
449
+ "epoch": 0.3630862329803328,
450
+ "grad_norm": 0.10456804931163788,
451
+ "learning_rate": 0.00025159223574386114,
452
+ "loss": 11.8432,
453
+ "step": 60
454
+ },
455
+ {
456
+ "epoch": 0.3691376701966717,
457
+ "grad_norm": 0.06408683210611343,
458
+ "learning_rate": 0.0002497536858170772,
459
+ "loss": 11.8433,
460
+ "step": 61
461
+ },
462
+ {
463
+ "epoch": 0.3751891074130106,
464
+ "grad_norm": 0.07426877319812775,
465
+ "learning_rate": 0.00024788786422862526,
466
+ "loss": 11.8505,
467
+ "step": 62
468
+ },
469
+ {
470
+ "epoch": 0.3812405446293495,
471
+ "grad_norm": 0.050904687494039536,
472
+ "learning_rate": 0.00024599528107549745,
473
+ "loss": 11.8488,
474
+ "step": 63
475
+ },
476
+ {
477
+ "epoch": 0.38729198184568836,
478
+ "grad_norm": 0.06546781957149506,
479
+ "learning_rate": 0.00024407645377103054,
480
+ "loss": 11.8482,
481
+ "step": 64
482
+ },
483
+ {
484
+ "epoch": 0.39334341906202724,
485
+ "grad_norm": 0.050825174897909164,
486
+ "learning_rate": 0.00024213190690345018,
487
+ "loss": 11.8497,
488
+ "step": 65
489
+ },
490
+ {
491
+ "epoch": 0.39939485627836613,
492
+ "grad_norm": 0.05852922797203064,
493
+ "learning_rate": 0.00024016217209245374,
494
+ "loss": 11.8466,
495
+ "step": 66
496
+ },
497
+ {
498
+ "epoch": 0.405446293494705,
499
+ "grad_norm": 0.05514448508620262,
500
+ "learning_rate": 0.00023816778784387094,
501
+ "loss": 11.8445,
502
+ "step": 67
503
+ },
504
+ {
505
+ "epoch": 0.4114977307110439,
506
+ "grad_norm": 0.051131296902894974,
507
+ "learning_rate": 0.0002361492994024415,
508
+ "loss": 11.8466,
509
+ "step": 68
510
+ },
511
+ {
512
+ "epoch": 0.4175491679273828,
513
+ "grad_norm": 0.05901065096259117,
514
+ "learning_rate": 0.0002341072586027509,
515
+ "loss": 11.8469,
516
+ "step": 69
517
+ },
518
+ {
519
+ "epoch": 0.4236006051437216,
520
+ "grad_norm": 0.04616164416074753,
521
+ "learning_rate": 0.00023204222371836405,
522
+ "loss": 11.8433,
523
+ "step": 70
524
+ },
525
+ {
526
+ "epoch": 0.4296520423600605,
527
+ "grad_norm": 0.0439113974571228,
528
+ "learning_rate": 0.00022995475930919905,
529
+ "loss": 11.8429,
530
+ "step": 71
531
+ },
532
+ {
533
+ "epoch": 0.4357034795763994,
534
+ "grad_norm": 0.04801691696047783,
535
+ "learning_rate": 0.00022784543606718227,
536
+ "loss": 11.842,
537
+ "step": 72
538
+ },
539
+ {
540
+ "epoch": 0.44175491679273826,
541
+ "grad_norm": 0.048914726823568344,
542
+ "learning_rate": 0.00022571483066022657,
543
+ "loss": 11.8437,
544
+ "step": 73
545
+ },
546
+ {
547
+ "epoch": 0.44780635400907715,
548
+ "grad_norm": 0.04584801197052002,
549
+ "learning_rate": 0.0002235635255745762,
550
+ "loss": 11.8497,
551
+ "step": 74
552
+ },
553
+ {
554
+ "epoch": 0.45385779122541603,
555
+ "grad_norm": 0.046303898096084595,
556
+ "learning_rate": 0.00022139210895556104,
557
+ "loss": 11.8464,
558
+ "step": 75
559
+ },
560
+ {
561
+ "epoch": 0.45385779122541603,
562
+ "eval_loss": 11.841269493103027,
563
+ "eval_runtime": 1.0076,
564
+ "eval_samples_per_second": 49.625,
565
+ "eval_steps_per_second": 6.947,
566
+ "step": 75
567
+ },
568
+ {
569
+ "epoch": 0.4599092284417549,
570
+ "grad_norm": 0.05089502036571503,
571
+ "learning_rate": 0.00021920117444680317,
572
+ "loss": 11.8473,
573
+ "step": 76
574
+ },
575
+ {
576
+ "epoch": 0.4659606656580938,
577
+ "grad_norm": 0.05392273887991905,
578
+ "learning_rate": 0.00021699132102792097,
579
+ "loss": 11.8459,
580
+ "step": 77
581
+ },
582
+ {
583
+ "epoch": 0.4720121028744327,
584
+ "grad_norm": 0.053485482931137085,
585
+ "learning_rate": 0.0002147631528507739,
586
+ "loss": 11.8461,
587
+ "step": 78
588
+ },
589
+ {
590
+ "epoch": 0.47806354009077157,
591
+ "grad_norm": 0.046315018087625504,
592
+ "learning_rate": 0.00021251727907429355,
593
+ "loss": 11.8464,
594
+ "step": 79
595
+ },
596
+ {
597
+ "epoch": 0.48411497730711045,
598
+ "grad_norm": 0.05351250618696213,
599
+ "learning_rate": 0.0002102543136979454,
600
+ "loss": 11.8432,
601
+ "step": 80
602
+ },
603
+ {
604
+ "epoch": 0.49016641452344933,
605
+ "grad_norm": 0.047626495361328125,
606
+ "learning_rate": 0.0002079748753938678,
607
+ "loss": 11.8485,
608
+ "step": 81
609
+ },
610
+ {
611
+ "epoch": 0.4962178517397882,
612
+ "grad_norm": 0.08041282743215561,
613
+ "learning_rate": 0.0002056795873377331,
614
+ "loss": 11.8392,
615
+ "step": 82
616
+ },
617
+ {
618
+ "epoch": 0.5022692889561271,
619
+ "grad_norm": 0.10707160830497742,
620
+ "learning_rate": 0.00020336907703837748,
621
+ "loss": 11.8455,
622
+ "step": 83
623
+ },
624
+ {
625
+ "epoch": 0.5083207261724659,
626
+ "grad_norm": 0.06469403952360153,
627
+ "learning_rate": 0.00020104397616624645,
628
+ "loss": 11.8393,
629
+ "step": 84
630
+ },
631
+ {
632
+ "epoch": 0.5143721633888049,
633
+ "grad_norm": 0.05042410269379616,
634
+ "learning_rate": 0.00019870492038070252,
635
+ "loss": 11.8404,
636
+ "step": 85
637
+ },
638
+ {
639
+ "epoch": 0.5204236006051437,
640
+ "grad_norm": 0.050363682210445404,
641
+ "learning_rate": 0.0001963525491562421,
642
+ "loss": 11.8452,
643
+ "step": 86
644
+ },
645
+ {
646
+ "epoch": 0.5264750378214826,
647
+ "grad_norm": 0.0731741338968277,
648
+ "learning_rate": 0.0001939875056076697,
649
+ "loss": 11.8439,
650
+ "step": 87
651
+ },
652
+ {
653
+ "epoch": 0.5325264750378215,
654
+ "grad_norm": 0.053346894681453705,
655
+ "learning_rate": 0.00019161043631427666,
656
+ "loss": 11.8358,
657
+ "step": 88
658
+ },
659
+ {
660
+ "epoch": 0.5385779122541604,
661
+ "grad_norm": 0.07865788042545319,
662
+ "learning_rate": 0.00018922199114307294,
663
+ "loss": 11.8366,
664
+ "step": 89
665
+ },
666
+ {
667
+ "epoch": 0.5446293494704992,
668
+ "grad_norm": 0.05362819880247116,
669
+ "learning_rate": 0.00018682282307111987,
670
+ "loss": 11.8367,
671
+ "step": 90
672
+ },
673
+ {
674
+ "epoch": 0.5506807866868382,
675
+ "grad_norm": 0.05961053818464279,
676
+ "learning_rate": 0.00018441358800701273,
677
+ "loss": 11.8391,
678
+ "step": 91
679
+ },
680
+ {
681
+ "epoch": 0.556732223903177,
682
+ "grad_norm": 0.0769873559474945,
683
+ "learning_rate": 0.00018199494461156203,
684
+ "loss": 11.8361,
685
+ "step": 92
686
+ },
687
+ {
688
+ "epoch": 0.5627836611195158,
689
+ "grad_norm": 0.0490158312022686,
690
+ "learning_rate": 0.000179567554117722,
691
+ "loss": 11.8411,
692
+ "step": 93
693
+ },
694
+ {
695
+ "epoch": 0.5688350983358548,
696
+ "grad_norm": 0.055971693247556686,
697
+ "learning_rate": 0.00017713208014981648,
698
+ "loss": 11.8376,
699
+ "step": 94
700
+ },
701
+ {
702
+ "epoch": 0.5748865355521936,
703
+ "grad_norm": 0.06011113151907921,
704
+ "learning_rate": 0.00017468918854211007,
705
+ "loss": 11.8386,
706
+ "step": 95
707
+ },
708
+ {
709
+ "epoch": 0.5809379727685325,
710
+ "grad_norm": 0.04350106790661812,
711
+ "learning_rate": 0.00017223954715677627,
712
+ "loss": 11.842,
713
+ "step": 96
714
+ },
715
+ {
716
+ "epoch": 0.5869894099848714,
717
+ "grad_norm": 0.04748297482728958,
718
+ "learning_rate": 0.00016978382570131034,
719
+ "loss": 11.8418,
720
+ "step": 97
721
+ },
722
+ {
723
+ "epoch": 0.5930408472012103,
724
+ "grad_norm": 0.06736046820878983,
725
+ "learning_rate": 0.00016732269554543794,
726
+ "loss": 11.8372,
727
+ "step": 98
728
+ },
729
+ {
730
+ "epoch": 0.5990922844175491,
731
+ "grad_norm": 0.07441910356283188,
732
+ "learning_rate": 0.00016485682953756942,
733
+ "loss": 11.8341,
734
+ "step": 99
735
+ },
736
+ {
737
+ "epoch": 0.6051437216338881,
738
+ "grad_norm": 0.06404472142457962,
739
+ "learning_rate": 0.00016238690182084986,
740
+ "loss": 11.8413,
741
+ "step": 100
742
+ },
743
+ {
744
+ "epoch": 0.6051437216338881,
745
+ "eval_loss": 11.836865425109863,
746
+ "eval_runtime": 0.5877,
747
+ "eval_samples_per_second": 85.085,
748
+ "eval_steps_per_second": 11.912,
749
+ "step": 100
750
  }
751
  ],
752
  "logging_steps": 1,
 
775
  "attributes": {}
776
  }
777
  },
778
+ "total_flos": 140551022739456.0,
779
  "train_batch_size": 8,
780
  "trial_name": null,
781
  "trial_params": null