bbytxt commited on
Commit
75a0aa8
·
verified ·
1 Parent(s): 0bf3bb8

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:d0ded7a2b25cf6762b8bf5de0579a37457257949d9042ae415b94deafd57b653
3
  size 13587864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c368789bd1e2e440cd6aa0b3282bf5b100731b81da18b7966ca480c8a7e2bf7a
3
  size 13587864
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16a4b550fa6011fad18f3dbc0abe9283b30c43ab8de68e5192669cc4dec666b0
3
  size 27273018
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff8c5c4a26e3175ae8beb4187c980a2789466eba69a59ba24c1aafac8a08a9bd
3
  size 27273018
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:811777fbef37769d718e649bfa2b3e59a22d4e4de258b40c2324730c1e4c638c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ac3e88c4fbed7e72298e252b4a356d7b0bd4ef5ac2d275faba331f0e7470585
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": 4.4730048179626465,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.014263300527742119,
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": 159.464,
374
  "eval_steps_per_second": 39.866,
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": 1391846800490496.0,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 4.398462772369385,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.028526601055484237,
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": 159.464,
374
  "eval_steps_per_second": 39.866,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.014548566538296961,
379
+ "grad_norm": 1.7294424772262573,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 3.1736,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.014833832548851804,
386
+ "grad_norm": 1.8418482542037964,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 3.4268,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.015119098559406647,
393
+ "grad_norm": 2.02036190032959,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 3.7533,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.01540436456996149,
400
+ "grad_norm": 1.7710672616958618,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 3.4441,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.015689630580516332,
407
+ "grad_norm": 1.7376676797866821,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 3.3789,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.015974896591071173,
414
+ "grad_norm": 1.8672767877578735,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 3.7761,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.016260162601626018,
421
+ "grad_norm": 1.9220268726348877,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 3.7599,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.01654542861218086,
428
+ "grad_norm": 1.7978780269622803,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 3.542,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.0168306946227357,
435
+ "grad_norm": 1.8631057739257812,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 3.89,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.017115960633290545,
442
+ "grad_norm": 1.9112904071807861,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 3.9064,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.017401226643845386,
449
+ "grad_norm": 1.8794102668762207,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 3.7488,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.017686492654400227,
456
+ "grad_norm": 1.7349375486373901,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 3.9465,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.01797175866495507,
463
+ "grad_norm": 1.9494880437850952,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 3.9429,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.018257024675509912,
470
+ "grad_norm": 1.9176416397094727,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 4.0286,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.018542290686064757,
477
+ "grad_norm": 1.9241676330566406,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 4.0452,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.018827556696619598,
484
+ "grad_norm": 1.9808131456375122,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 4.0911,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.01911282270717444,
491
+ "grad_norm": 2.1437771320343018,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 4.3343,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.019398088717729283,
498
+ "grad_norm": 2.098871946334839,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 4.1912,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.019683354728284124,
505
+ "grad_norm": 1.9121192693710327,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 3.9316,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.01996862073883897,
512
+ "grad_norm": 2.1575756072998047,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 4.2355,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.02025388674939381,
519
+ "grad_norm": 2.0468432903289795,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 4.2079,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.02053915275994865,
526
+ "grad_norm": 2.1697824001312256,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 4.3365,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.020824418770503495,
533
+ "grad_norm": 2.1824512481689453,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 4.2945,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.021109684781058336,
540
+ "grad_norm": 2.1010141372680664,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 4.3266,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.02139495079161318,
547
+ "grad_norm": 2.166463851928711,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 4.2321,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.02168021680216802,
554
+ "grad_norm": 2.4518635272979736,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 4.4078,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.021965482812722863,
561
+ "grad_norm": 2.344184398651123,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 4.5186,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.022250748823277707,
568
+ "grad_norm": 2.274261713027954,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 4.3573,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.022536014833832548,
575
+ "grad_norm": 2.2358288764953613,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 4.5504,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.022821280844387393,
582
+ "grad_norm": 2.2493133544921875,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 4.584,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.023106546854942234,
589
+ "grad_norm": 2.253169059753418,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 4.5174,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.023391812865497075,
596
+ "grad_norm": 2.337402582168579,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 4.506,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.02367707887605192,
603
+ "grad_norm": 2.3492746353149414,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 4.5267,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.02396234488660676,
610
+ "grad_norm": 2.207144260406494,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 4.6889,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.024247610897161605,
617
+ "grad_norm": 2.466681480407715,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 4.7795,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.024532876907716446,
624
+ "grad_norm": 2.5349717140197754,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 4.6551,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.024818142918271287,
631
+ "grad_norm": 2.4833574295043945,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 4.7014,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.02510340892882613,
638
+ "grad_norm": 2.309326410293579,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 4.4093,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.025388674939380972,
645
+ "grad_norm": 2.554025173187256,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 4.8266,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.025673940949935817,
652
+ "grad_norm": 2.5444960594177246,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 4.8623,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.025959206960490658,
659
+ "grad_norm": 2.548241138458252,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 4.7327,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.0262444729710455,
666
+ "grad_norm": 2.4548227787017822,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 4.793,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.026529738981600343,
673
+ "grad_norm": 2.6474790573120117,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 4.7439,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.026815004992155184,
680
+ "grad_norm": 2.674259901046753,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 4.9857,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.02710027100271003,
687
+ "grad_norm": 2.7254526615142822,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 5.0972,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.02738553701326487,
694
+ "grad_norm": 2.9822192192077637,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 5.3265,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.02767080302381971,
701
+ "grad_norm": 2.92980694770813,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 5.0558,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.027956069034374555,
708
+ "grad_norm": 2.8623178005218506,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 5.2151,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.028241335044929396,
715
+ "grad_norm": 3.296135663986206,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 5.4848,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.028526601055484237,
722
+ "grad_norm": 3.891191005706787,
723
+ "learning_rate": 0.0,
724
+ "loss": 5.632,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.028526601055484237,
729
+ "eval_loss": 4.398462772369385,
730
+ "eval_runtime": 37.0281,
731
+ "eval_samples_per_second": 159.446,
732
+ "eval_steps_per_second": 39.862,
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": 2783693600980992.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null