nttx commited on
Commit
1cbe8d7
·
verified ·
1 Parent(s): 5970be9

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 sha256:57830f4f5467021f0c7bf3a695c19e99295d2c14e9cdccc6930b0a46c7ebc114
3
  size 338298
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc66ea8ac465eff3a5d80e46b09db4cf7cbba8d68fc9dcc41c56627b2a9b3505
3
  size 338298
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:190c80a17423a82513c4f3e7f85c8781db91fefac8ead9f5f5507a6c5dc72a7e
3
  size 424022
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be0d2429a1614caef962d48332ab19705faaca43189283c70ef7c6f18751fb50
3
  size 424022
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23316afa85ea472bab1f65d219dea875bb368af2c10ca76f59c20a921c69c010
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4e98090d3a3800c6de11b63fe8981755c269d5eb6a94c68fc233c74d21ccfca
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d689b2d605789fff660b4cfbb1ce6889a5251953118f474a71b33d74e2d19be7
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c4a11c3ec7ace2e963dc6e2b0b5b6372cc0250cefb36d5f7289475908638cb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 6.920870304107666,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.4424778761061947,
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": 876.858,
374
  "eval_steps_per_second": 110.761,
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": 1071657762816.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 6.912210941314697,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.8849557522123894,
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": 876.858,
374
  "eval_steps_per_second": 110.761,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.45132743362831856,
379
+ "grad_norm": 1.3638014793395996,
380
+ "learning_rate": 3.969463130731183e-06,
381
+ "loss": 6.9396,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.46017699115044247,
386
+ "grad_norm": 1.3456850051879883,
387
+ "learning_rate": 3.8772424536302565e-06,
388
+ "loss": 6.9365,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.4690265486725664,
393
+ "grad_norm": 1.2937833070755005,
394
+ "learning_rate": 3.782248193514766e-06,
395
+ "loss": 6.9452,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.4778761061946903,
400
+ "grad_norm": 1.2829818725585938,
401
+ "learning_rate": 3.684671656182497e-06,
402
+ "loss": 6.9442,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.48672566371681414,
407
+ "grad_norm": 1.3496243953704834,
408
+ "learning_rate": 3.5847093477938955e-06,
409
+ "loss": 6.9485,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.49557522123893805,
414
+ "grad_norm": 1.2824629545211792,
415
+ "learning_rate": 3.4825625791348093e-06,
416
+ "loss": 6.9387,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.504424778761062,
421
+ "grad_norm": 2.067007064819336,
422
+ "learning_rate": 3.3784370602033572e-06,
423
+ "loss": 6.9001,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.5132743362831859,
428
+ "grad_norm": 1.5888131856918335,
429
+ "learning_rate": 3.272542485937369e-06,
430
+ "loss": 6.9051,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.5221238938053098,
435
+ "grad_norm": 1.592550277709961,
436
+ "learning_rate": 3.165092113916688e-06,
437
+ "loss": 6.9145,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.5309734513274337,
442
+ "grad_norm": 1.7932591438293457,
443
+ "learning_rate": 3.056302334890786e-06,
444
+ "loss": 6.9171,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.5398230088495575,
449
+ "grad_norm": 1.763204574584961,
450
+ "learning_rate": 2.946392236996592e-06,
451
+ "loss": 6.9177,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.5486725663716814,
456
+ "grad_norm": 1.8218412399291992,
457
+ "learning_rate": 2.835583164544139e-06,
458
+ "loss": 6.9144,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.5575221238938053,
463
+ "grad_norm": 1.7646056413650513,
464
+ "learning_rate": 2.724098272258584e-06,
465
+ "loss": 6.9161,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.5663716814159292,
470
+ "grad_norm": 1.877703070640564,
471
+ "learning_rate": 2.6121620758762877e-06,
472
+ "loss": 6.9103,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.5752212389380531,
477
+ "grad_norm": 1.6913516521453857,
478
+ "learning_rate": 2.5e-06,
479
+ "loss": 6.913,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.584070796460177,
484
+ "grad_norm": 1.7488752603530884,
485
+ "learning_rate": 2.3878379241237136e-06,
486
+ "loss": 6.912,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.5929203539823009,
491
+ "grad_norm": 1.8251107931137085,
492
+ "learning_rate": 2.2759017277414165e-06,
493
+ "loss": 6.9121,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.6017699115044248,
498
+ "grad_norm": 1.877405047416687,
499
+ "learning_rate": 2.1644168354558623e-06,
500
+ "loss": 6.9093,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.6106194690265486,
505
+ "grad_norm": 1.677901268005371,
506
+ "learning_rate": 2.053607763003409e-06,
507
+ "loss": 6.9088,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.6194690265486725,
512
+ "grad_norm": 1.7203891277313232,
513
+ "learning_rate": 1.9436976651092143e-06,
514
+ "loss": 6.9131,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.6283185840707964,
519
+ "grad_norm": 1.7265475988388062,
520
+ "learning_rate": 1.8349078860833125e-06,
521
+ "loss": 6.9143,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.6371681415929203,
526
+ "grad_norm": 1.7067102193832397,
527
+ "learning_rate": 1.7274575140626318e-06,
528
+ "loss": 6.9094,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.6460176991150443,
533
+ "grad_norm": 1.6857355833053589,
534
+ "learning_rate": 1.6215629397966432e-06,
535
+ "loss": 6.9075,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.6548672566371682,
540
+ "grad_norm": 1.7189222574234009,
541
+ "learning_rate": 1.5174374208651913e-06,
542
+ "loss": 6.9025,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.6637168141592921,
547
+ "grad_norm": 1.7505325078964233,
548
+ "learning_rate": 1.415290652206105e-06,
549
+ "loss": 6.9037,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.672566371681416,
554
+ "grad_norm": 1.4659026861190796,
555
+ "learning_rate": 1.3153283438175036e-06,
556
+ "loss": 6.9195,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.6814159292035398,
561
+ "grad_norm": 1.3051509857177734,
562
+ "learning_rate": 1.217751806485235e-06,
563
+ "loss": 6.9336,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.6902654867256637,
568
+ "grad_norm": 1.3540781736373901,
569
+ "learning_rate": 1.122757546369744e-06,
570
+ "loss": 6.9316,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.6991150442477876,
575
+ "grad_norm": 1.2698006629943848,
576
+ "learning_rate": 1.0305368692688175e-06,
577
+ "loss": 6.9343,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.7079646017699115,
582
+ "grad_norm": 1.3174868822097778,
583
+ "learning_rate": 9.412754953531664e-07,
584
+ "loss": 6.9406,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.7168141592920354,
589
+ "grad_norm": 1.301322340965271,
590
+ "learning_rate": 8.551531851507186e-07,
591
+ "loss": 6.9307,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.7256637168141593,
596
+ "grad_norm": 1.3249800205230713,
597
+ "learning_rate": 7.723433775328385e-07,
598
+ "loss": 6.9336,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.7345132743362832,
603
+ "grad_norm": 1.4825643301010132,
604
+ "learning_rate": 6.930128404315214e-07,
605
+ "loss": 6.9442,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.7433628318584071,
610
+ "grad_norm": 1.2965272665023804,
611
+ "learning_rate": 6.17321334990973e-07,
612
+ "loss": 6.9319,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.7522123893805309,
617
+ "grad_norm": 2.0646309852600098,
618
+ "learning_rate": 5.454212938299256e-07,
619
+ "loss": 6.895,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.7610619469026548,
624
+ "grad_norm": 1.8665640354156494,
625
+ "learning_rate": 4.774575140626317e-07,
626
+ "loss": 6.8932,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.7699115044247787,
631
+ "grad_norm": 2.3491158485412598,
632
+ "learning_rate": 4.1356686569674344e-07,
633
+ "loss": 6.91,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.7787610619469026,
638
+ "grad_norm": 1.695754051208496,
639
+ "learning_rate": 3.538780159953348e-07,
640
+ "loss": 6.9096,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.7876106194690266,
645
+ "grad_norm": 1.8144688606262207,
646
+ "learning_rate": 2.98511170358155e-07,
647
+ "loss": 6.9101,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.7964601769911505,
652
+ "grad_norm": 1.8781906366348267,
653
+ "learning_rate": 2.4757783024395244e-07,
654
+ "loss": 6.9077,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.8053097345132744,
659
+ "grad_norm": 1.745964765548706,
660
+ "learning_rate": 2.0118056862137358e-07,
661
+ "loss": 6.9109,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.8141592920353983,
666
+ "grad_norm": 1.7597346305847168,
667
+ "learning_rate": 1.59412823400657e-07,
668
+ "loss": 6.9089,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.8230088495575221,
673
+ "grad_norm": 1.7316840887069702,
674
+ "learning_rate": 1.223587092621162e-07,
675
+ "loss": 6.9089,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.831858407079646,
680
+ "grad_norm": 1.678239345550537,
681
+ "learning_rate": 9.00928482603669e-08,
682
+ "loss": 6.9084,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.8407079646017699,
687
+ "grad_norm": 1.6864920854568481,
688
+ "learning_rate": 6.268021954544095e-08,
689
+ "loss": 6.9037,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.8495575221238938,
694
+ "grad_norm": 1.7664175033569336,
695
+ "learning_rate": 4.017602850342584e-08,
696
+ "loss": 6.9083,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.8584070796460177,
701
+ "grad_norm": 1.7239421606063843,
702
+ "learning_rate": 2.262559558016325e-08,
703
+ "loss": 6.9048,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.8672566371681416,
708
+ "grad_norm": 1.68112051486969,
709
+ "learning_rate": 1.006426501190233e-08,
710
+ "loss": 6.9039,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.8761061946902655,
715
+ "grad_norm": 1.8294252157211304,
716
+ "learning_rate": 2.5173336467135266e-09,
717
+ "loss": 6.9062,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.8849557522123894,
722
+ "grad_norm": 1.7845550775527954,
723
+ "learning_rate": 0.0,
724
+ "loss": 6.9032,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.8849557522123894,
729
+ "eval_loss": 6.912210941314697,
730
+ "eval_runtime": 0.2167,
731
+ "eval_samples_per_second": 876.675,
732
+ "eval_steps_per_second": 110.738,
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": 2148121165824.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null