fats-fme commited on
Commit
7f6bc79
·
verified ·
1 Parent(s): 51ef581

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:af075af66d9c05de9b723bd49e34ce2a00bc801a999330275ae69b7bef59a366
3
  size 377528296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba47d1b425b87fa2db354d6c654ec2a174c8e0e652235c6d6274caeb49771dc2
3
  size 377528296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b89acbfb70ff3472eab3476474ad07b129f63fcc2e2b8a502fd0645924dec53a
3
  size 192031828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c640bc1adc5898b240f2413363b5bb91f451c87fd34d4b6fa531c82712a39a9f
3
  size 192031828
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e85ad68fef0ed3b10b464b35783033c03d851402b340406e223746bd65b409d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c47e458b38df10d1d8b7e9c349c490c3b33f28e4a2ca9916f2935970dc7d851
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca2ad0660f4430a149f84300447ae0a59e68e8b51799a2e3848afe158aff8281
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:673ccf272a6ac969319297986ad3a484281eb54814eca9e7ffb558668525c080
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 4.233332633972168,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.08431703204047218,
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": 5.378,
374
  "eval_steps_per_second": 2.689,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -396,12 +754,12 @@
396
  "should_evaluate": false,
397
  "should_log": false,
398
  "should_save": true,
399
- "should_training_stop": false
400
  },
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.1480799903744e+17,
405
  "train_batch_size": 2,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.7002086639404297,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.16863406408094436,
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": 5.378,
374
  "eval_steps_per_second": 2.689,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.08600337268128162,
379
+ "grad_norm": 5.613102912902832,
380
+ "learning_rate": 2.5500000000000003e-05,
381
+ "loss": 32.7626,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.08768971332209106,
386
+ "grad_norm": 4.790407180786133,
387
+ "learning_rate": 2.6000000000000002e-05,
388
+ "loss": 32.4263,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0893760539629005,
393
+ "grad_norm": 5.307969570159912,
394
+ "learning_rate": 2.6500000000000004e-05,
395
+ "loss": 32.846,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.09106239460370995,
400
+ "grad_norm": 5.651579856872559,
401
+ "learning_rate": 2.7000000000000002e-05,
402
+ "loss": 34.7874,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.09274873524451939,
407
+ "grad_norm": 6.0560712814331055,
408
+ "learning_rate": 2.7500000000000004e-05,
409
+ "loss": 33.6984,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.09443507588532883,
414
+ "grad_norm": 6.183261394500732,
415
+ "learning_rate": 2.8000000000000003e-05,
416
+ "loss": 33.8316,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.09612141652613827,
421
+ "grad_norm": 6.355773448944092,
422
+ "learning_rate": 2.8499999999999998e-05,
423
+ "loss": 31.6443,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.09780775716694773,
428
+ "grad_norm": 6.424299240112305,
429
+ "learning_rate": 2.9e-05,
430
+ "loss": 32.2212,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.09949409780775717,
435
+ "grad_norm": 6.542140007019043,
436
+ "learning_rate": 2.95e-05,
437
+ "loss": 29.3199,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.10118043844856661,
442
+ "grad_norm": 6.4503254890441895,
443
+ "learning_rate": 3e-05,
444
+ "loss": 31.3944,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.10286677908937605,
449
+ "grad_norm": 7.207476615905762,
450
+ "learning_rate": 3.05e-05,
451
+ "loss": 30.4606,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.1045531197301855,
456
+ "grad_norm": 5.752547740936279,
457
+ "learning_rate": 3.1e-05,
458
+ "loss": 30.86,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.10623946037099494,
463
+ "grad_norm": 5.698461532592773,
464
+ "learning_rate": 3.15e-05,
465
+ "loss": 31.3354,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.10792580101180438,
470
+ "grad_norm": 5.86702823638916,
471
+ "learning_rate": 3.2000000000000005e-05,
472
+ "loss": 31.1521,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.10961214165261383,
477
+ "grad_norm": 7.257821559906006,
478
+ "learning_rate": 3.2500000000000004e-05,
479
+ "loss": 31.254,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.11129848229342328,
484
+ "grad_norm": 6.626792907714844,
485
+ "learning_rate": 3.3e-05,
486
+ "loss": 31.617,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.11298482293423272,
491
+ "grad_norm": 6.023996829986572,
492
+ "learning_rate": 3.35e-05,
493
+ "loss": 31.7345,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.11467116357504216,
498
+ "grad_norm": 6.6789960861206055,
499
+ "learning_rate": 3.4000000000000007e-05,
500
+ "loss": 30.4151,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.1163575042158516,
505
+ "grad_norm": 5.8820672035217285,
506
+ "learning_rate": 3.45e-05,
507
+ "loss": 28.6688,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.11804384485666104,
512
+ "grad_norm": 5.648659706115723,
513
+ "learning_rate": 3.5e-05,
514
+ "loss": 28.8623,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.11973018549747048,
519
+ "grad_norm": 6.760491371154785,
520
+ "learning_rate": 3.55e-05,
521
+ "loss": 28.7719,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.12141652613827993,
526
+ "grad_norm": 6.76365852355957,
527
+ "learning_rate": 3.6e-05,
528
+ "loss": 29.3167,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.12310286677908938,
533
+ "grad_norm": 6.645838737487793,
534
+ "learning_rate": 3.65e-05,
535
+ "loss": 29.4143,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.12478920741989882,
540
+ "grad_norm": 6.838345527648926,
541
+ "learning_rate": 3.7e-05,
542
+ "loss": 29.2239,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.12647554806070826,
547
+ "grad_norm": 6.978768348693848,
548
+ "learning_rate": 3.7500000000000003e-05,
549
+ "loss": 26.9242,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.1281618887015177,
554
+ "grad_norm": 6.758506774902344,
555
+ "learning_rate": 3.8e-05,
556
+ "loss": 27.8301,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.12984822934232715,
561
+ "grad_norm": 6.434322357177734,
562
+ "learning_rate": 3.85e-05,
563
+ "loss": 27.4472,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.1315345699831366,
568
+ "grad_norm": 6.526978015899658,
569
+ "learning_rate": 3.9000000000000006e-05,
570
+ "loss": 27.8921,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.13322091062394603,
575
+ "grad_norm": 5.958317756652832,
576
+ "learning_rate": 3.9500000000000005e-05,
577
+ "loss": 26.9556,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.13490725126475547,
582
+ "grad_norm": 6.362218379974365,
583
+ "learning_rate": 4e-05,
584
+ "loss": 27.881,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.13659359190556492,
589
+ "grad_norm": 6.112777233123779,
590
+ "learning_rate": 4.05e-05,
591
+ "loss": 26.8001,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.13827993254637436,
596
+ "grad_norm": 6.845430374145508,
597
+ "learning_rate": 4.1e-05,
598
+ "loss": 27.3685,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.1399662731871838,
603
+ "grad_norm": 6.485461711883545,
604
+ "learning_rate": 4.15e-05,
605
+ "loss": 25.8873,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.14165261382799327,
610
+ "grad_norm": 7.727623462677002,
611
+ "learning_rate": 4.2e-05,
612
+ "loss": 25.7141,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.1433389544688027,
617
+ "grad_norm": 6.628414154052734,
618
+ "learning_rate": 4.25e-05,
619
+ "loss": 25.4368,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.14502529510961215,
624
+ "grad_norm": 6.609959125518799,
625
+ "learning_rate": 4.3e-05,
626
+ "loss": 25.2724,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.1467116357504216,
631
+ "grad_norm": 7.340668201446533,
632
+ "learning_rate": 4.35e-05,
633
+ "loss": 25.7889,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.14839797639123103,
638
+ "grad_norm": 7.036075115203857,
639
+ "learning_rate": 4.4000000000000006e-05,
640
+ "loss": 25.5257,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.15008431703204048,
645
+ "grad_norm": 6.736301422119141,
646
+ "learning_rate": 4.4500000000000004e-05,
647
+ "loss": 24.4746,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.15177065767284992,
652
+ "grad_norm": 6.801417350769043,
653
+ "learning_rate": 4.5e-05,
654
+ "loss": 24.0649,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.15345699831365936,
659
+ "grad_norm": 6.542447566986084,
660
+ "learning_rate": 4.55e-05,
661
+ "loss": 23.5914,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.1551433389544688,
666
+ "grad_norm": 6.91330099105835,
667
+ "learning_rate": 4.600000000000001e-05,
668
+ "loss": 22.7971,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.15682967959527824,
673
+ "grad_norm": 7.042500019073486,
674
+ "learning_rate": 4.6500000000000005e-05,
675
+ "loss": 23.5959,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.15851602023608768,
680
+ "grad_norm": 6.547644138336182,
681
+ "learning_rate": 4.7e-05,
682
+ "loss": 22.68,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.16020236087689713,
687
+ "grad_norm": 6.529291152954102,
688
+ "learning_rate": 4.75e-05,
689
+ "loss": 23.6584,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.16188870151770657,
694
+ "grad_norm": 6.695392608642578,
695
+ "learning_rate": 4.8e-05,
696
+ "loss": 23.3885,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.163575042158516,
701
+ "grad_norm": 6.273005962371826,
702
+ "learning_rate": 4.85e-05,
703
+ "loss": 22.406,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.16526138279932545,
708
+ "grad_norm": 7.034113883972168,
709
+ "learning_rate": 4.9e-05,
710
+ "loss": 22.681,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.16694772344013492,
715
+ "grad_norm": 6.774496078491211,
716
+ "learning_rate": 4.9500000000000004e-05,
717
+ "loss": 22.1968,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.16863406408094436,
722
+ "grad_norm": 6.834523677825928,
723
+ "learning_rate": 5e-05,
724
+ "loss": 22.2685,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.16863406408094436,
729
+ "eval_loss": 2.7002086639404297,
730
+ "eval_runtime": 224.4614,
731
+ "eval_samples_per_second": 5.382,
732
+ "eval_steps_per_second": 2.691,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
754
  "should_evaluate": false,
755
  "should_log": false,
756
  "should_save": true,
757
+ "should_training_stop": true
758
  },
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.2961599807488e+17,
763
  "train_batch_size": 2,
764
  "trial_name": null,
765
  "trial_params": null