nttx commited on
Commit
380c3dc
·
verified ·
1 Parent(s): bd31e5b

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 sha256:7522b33e24c4baea039875a4fa0b3c3c99ecd3eadf5bdc3a0f33b9ba74f0f562
3
  size 73911112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8ac79c170b0e36c38c6a9510ce2b7f9ec7772c24a827ed3b1ba4a5fba37d9d2
3
  size 73911112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c62e2c9281d5881e02916a02a2547596ca23915e6052d5839f789a57e1873b7f
3
  size 148047722
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:998bd3cf90ff1d7cac381bb3a8c60e605fba1b29dca91b48fab71826b1a722be
3
  size 148047722
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae0c0ce9d7049fa5eb6fc0caed13040b077be88cffc623534ae5c682fe50676a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc652ac7dc2b1d597c62959c0402ecaf32b366b7f6510cc207fbaa8498634713
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": 4.233282089233398,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.14711290915777858,
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": 34.585,
374
  "eval_steps_per_second": 8.692,
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": 1.30626883682304e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 3.747371196746826,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.29422581831555716,
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": 34.585,
374
  "eval_steps_per_second": 8.692,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.15005516734093416,
379
+ "grad_norm": 0.8179550766944885,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 0.9759,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.15299742552408974,
386
+ "grad_norm": 1.5007497072219849,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 1.5544,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.1559396837072453,
393
+ "grad_norm": 1.9838329553604126,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 2.0934,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.1588819418904009,
400
+ "grad_norm": 2.2728323936462402,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 2.3952,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.16182420007355647,
407
+ "grad_norm": 2.803129196166992,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 2.7325,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.16476645825671202,
414
+ "grad_norm": 3.5593273639678955,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 2.9887,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.1677087164398676,
421
+ "grad_norm": 4.2021965980529785,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 3.6987,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.17065097462302317,
428
+ "grad_norm": 5.474735736846924,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 4.2206,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.17359323280617875,
435
+ "grad_norm": 4.47970724105835,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 3.8084,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.17653549098933433,
442
+ "grad_norm": 4.760900974273682,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 4.1375,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.17947774917248988,
449
+ "grad_norm": 5.88174295425415,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 4.1737,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.18242000735564545,
456
+ "grad_norm": 4.647493839263916,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 3.805,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.18536226553880103,
463
+ "grad_norm": 5.65695333480835,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 4.2409,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.1883045237219566,
470
+ "grad_norm": 4.901169300079346,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 3.9132,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.19124678190511218,
477
+ "grad_norm": 5.273778915405273,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 4.2319,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.19418904008826773,
484
+ "grad_norm": 4.926815986633301,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 3.9443,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.1971312982714233,
491
+ "grad_norm": 5.62088680267334,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 4.4193,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.2000735564545789,
498
+ "grad_norm": 5.968881130218506,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 4.2879,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.20301581463773447,
505
+ "grad_norm": 5.996151447296143,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 4.2618,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.20595807282089004,
512
+ "grad_norm": 5.866414546966553,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 4.3836,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.2089003310040456,
519
+ "grad_norm": 6.295736789703369,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 4.175,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.21184258918720117,
526
+ "grad_norm": 6.209023475646973,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 3.9133,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.21478484737035675,
533
+ "grad_norm": 5.8113226890563965,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 4.14,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.21772710555351232,
540
+ "grad_norm": 5.273384094238281,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 4.0519,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.2206693637366679,
547
+ "grad_norm": 5.25897216796875,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 4.0274,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.22361162191982348,
554
+ "grad_norm": 5.948103904724121,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 3.9088,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.22655388010297903,
561
+ "grad_norm": 5.906592845916748,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 3.8533,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.2294961382861346,
568
+ "grad_norm": 6.509231090545654,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 4.0038,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.23243839646929018,
575
+ "grad_norm": 6.27969217300415,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 4.0702,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.23538065465244576,
582
+ "grad_norm": 6.864594459533691,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 4.1275,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.23832291283560134,
589
+ "grad_norm": 6.287829399108887,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 4.1588,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.24126517101875689,
596
+ "grad_norm": 7.001311302185059,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 3.9487,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.24420742920191246,
603
+ "grad_norm": 7.293318271636963,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 4.0771,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.24714968738506804,
610
+ "grad_norm": 7.087822914123535,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 3.7547,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.2500919455682236,
617
+ "grad_norm": 6.749867916107178,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 4.134,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.2530342037513792,
624
+ "grad_norm": 7.396295547485352,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 3.7365,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.25597646193453477,
631
+ "grad_norm": 7.216960906982422,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 3.8599,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.25891872011769035,
638
+ "grad_norm": 6.818838119506836,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 3.7601,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.2618609783008459,
645
+ "grad_norm": 7.164091110229492,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 4.2241,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.26480323648400145,
652
+ "grad_norm": 7.2876200675964355,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 3.7849,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.267745494667157,
659
+ "grad_norm": 7.654216766357422,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 3.6541,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.2706877528503126,
666
+ "grad_norm": 8.395753860473633,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 4.0189,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.2736300110334682,
673
+ "grad_norm": 7.765085697174072,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 4.0054,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.27657226921662376,
680
+ "grad_norm": 7.680928707122803,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 4.5154,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.27951452739977933,
687
+ "grad_norm": 8.729131698608398,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 4.079,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.2824567855829349,
694
+ "grad_norm": 8.016386985778809,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 4.1921,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.2853990437660905,
701
+ "grad_norm": 7.682516574859619,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 3.7764,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.28834130194924606,
708
+ "grad_norm": 7.8229899406433105,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 4.1933,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.29128356013240164,
715
+ "grad_norm": 7.692922115325928,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 4.2323,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.29422581831555716,
722
+ "grad_norm": 7.556560039520264,
723
+ "learning_rate": 0.0,
724
+ "loss": 4.0707,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.29422581831555716,
729
+ "eval_loss": 3.747371196746826,
730
+ "eval_runtime": 16.5652,
731
+ "eval_samples_per_second": 34.591,
732
+ "eval_steps_per_second": 8.693,
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": 2.61253767364608e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null