nttx commited on
Commit
3dd0d69
·
verified ·
1 Parent(s): d5c83ef

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:dd7b351ff484834d95f653fcbeda55e8c58b25240ade7e79679c0d4d75165599
3
  size 119801528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6612d24f31d6ae4c422e9082b9a147773ab314c5487f85c0dd86e161d997cd00
3
  size 119801528
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5e5d2e00296e7ffa59e1cc250c00e63d524eaf511f7e38f82910270f4f3ffa4
3
  size 239892858
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb6892b1d259c2f538d73d3c2f8533217eb84cc2c26295497436d2db5cf21a46
3
  size 239892858
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a70667c0261d9dd881186af1fe36352fad1d26904194d0859aaf99822b56366
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71178bf9183a1fa3d216dd322fd63afa95e8fefdc059298eb60a2bb296e1bfb5
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1900bd8021f13c38b942ed30aea6e2cea1b47664e4ce28d0276b142334732307
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": 6.598214626312256,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.6650041562759768,
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": 21.06,
374
  "eval_steps_per_second": 2.658,
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": 1.1235343428747264e+17,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 6.341156959533691,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.3300083125519535,
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": 21.06,
374
  "eval_steps_per_second": 2.658,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.6783042394014963,
379
+ "grad_norm": 4.251577377319336,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 6.2798,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.6916043225270158,
386
+ "grad_norm": 4.440990924835205,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 6.411,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.7049044056525353,
393
+ "grad_norm": 4.534366130828857,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 6.3749,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.7182044887780549,
400
+ "grad_norm": 4.792974948883057,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 6.5882,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.7315045719035744,
407
+ "grad_norm": 4.119089603424072,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 7.0134,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.744804655029094,
414
+ "grad_norm": 5.824765205383301,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 7.1678,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.7581047381546134,
421
+ "grad_norm": 5.396547794342041,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 6.8397,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.771404821280133,
428
+ "grad_norm": 4.455073356628418,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 6.9153,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.7847049044056525,
435
+ "grad_norm": 4.221690654754639,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 6.4359,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.7980049875311721,
442
+ "grad_norm": 4.620625019073486,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 6.4225,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.8113050706566916,
449
+ "grad_norm": 4.270419120788574,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 6.4349,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.8246051537822111,
456
+ "grad_norm": 4.561497211456299,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 6.3981,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.8379052369077307,
463
+ "grad_norm": 4.116311073303223,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 6.3619,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.8512053200332502,
470
+ "grad_norm": 4.2598042488098145,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 6.2785,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.8645054031587698,
477
+ "grad_norm": 4.3235182762146,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 6.4626,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.8778054862842892,
484
+ "grad_norm": 4.136751174926758,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 6.1445,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.8911055694098088,
491
+ "grad_norm": 4.677116394042969,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 6.1271,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.9044056525353283,
498
+ "grad_norm": 4.643939018249512,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 6.122,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.9177057356608479,
505
+ "grad_norm": 4.568877696990967,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 6.1806,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.9310058187863675,
512
+ "grad_norm": 4.61746072769165,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 6.0616,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.9443059019118869,
519
+ "grad_norm": 4.636501789093018,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 6.3057,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.9576059850374065,
526
+ "grad_norm": 5.082956790924072,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 6.4644,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.970906068162926,
533
+ "grad_norm": 4.843846321105957,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 6.6131,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.9842061512884456,
540
+ "grad_norm": 4.2939300537109375,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 6.2079,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.9975062344139651,
547
+ "grad_norm": 4.610700607299805,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 6.3489,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 1.0108063175394846,
554
+ "grad_norm": 7.985718250274658,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 12.4597,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 1.0241064006650042,
561
+ "grad_norm": 5.7571563720703125,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 6.8142,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 1.0374064837905237,
568
+ "grad_norm": 6.237396240234375,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 6.7316,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 1.0507065669160431,
575
+ "grad_norm": 5.167440414428711,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 6.7593,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 1.0640066500415628,
582
+ "grad_norm": 4.465665340423584,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 6.2203,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 1.0773067331670823,
589
+ "grad_norm": 4.801064968109131,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 6.2462,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 1.090606816292602,
596
+ "grad_norm": 4.532647132873535,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 6.4136,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 1.1039068994181214,
603
+ "grad_norm": 4.427244186401367,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 6.1425,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 1.1172069825436408,
610
+ "grad_norm": 4.380748748779297,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 6.0886,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 1.1305070656691605,
617
+ "grad_norm": 4.316006660461426,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 6.2332,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 1.14380714879468,
624
+ "grad_norm": 4.423862457275391,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 6.1998,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 1.1571072319201996,
631
+ "grad_norm": 4.6291399002075195,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 6.1195,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 1.170407315045719,
638
+ "grad_norm": 4.459833145141602,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 6.1848,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 1.1837073981712385,
645
+ "grad_norm": 4.596796035766602,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 6.1726,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 1.1970074812967582,
652
+ "grad_norm": 4.879339218139648,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 6.1748,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 1.2103075644222776,
659
+ "grad_norm": 4.79614782333374,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 6.2828,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 1.223607647547797,
666
+ "grad_norm": 5.011311054229736,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 6.0512,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.2369077306733167,
673
+ "grad_norm": 4.9499640464782715,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 6.3872,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.2502078137988362,
680
+ "grad_norm": 3.838749885559082,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 6.8677,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.2635078969243558,
687
+ "grad_norm": 5.61954927444458,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 6.9986,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.2768079800498753,
694
+ "grad_norm": 5.3152923583984375,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 6.606,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.2901080631753947,
701
+ "grad_norm": 5.0369439125061035,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 6.5901,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.3034081463009144,
708
+ "grad_norm": 4.628929138183594,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 6.4785,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.3167082294264338,
715
+ "grad_norm": 4.957996368408203,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 6.1472,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.3300083125519535,
722
+ "grad_norm": 4.551487445831299,
723
+ "learning_rate": 0.0,
724
+ "loss": 6.3276,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.3300083125519535,
729
+ "eval_loss": 6.341156959533691,
730
+ "eval_runtime": 24.0556,
731
+ "eval_samples_per_second": 21.076,
732
+ "eval_steps_per_second": 2.66,
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": 2.2443115462577357e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null