nttx commited on
Commit
e24c0b1
·
verified ·
1 Parent(s): 5b039d6

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 sha256:24ba9d0c7023e5a4be341313ce199926fbb73f70a0c7bc9de26beac92c29ea52
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df3cd7dc4965d915883f5f0d6bf8b3d418955e42d6348c71a9459b6befc5e05c
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:accb2eacc9836527064847f1e3c32ef7d6ecc9eb8934f17a9c36c7a8cf93a9e7
3
  size 501168482
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4de003f7dc48169776691d8a49566c7fcb121c489ba741e668e27d3b089c9015
3
  size 501168482
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:910bfb5b36078d12007205b529a39064ef6a6c93a587f5ecb2d014314cf09f1e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48d6c5df0275f1308369bbed9002c4ca6d339429d8674f90dd685252441d1533
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": 0.7435109615325928,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.03252561392096276,
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": 6.639,
374
  "eval_steps_per_second": 1.662,
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": 1.6440879602466816e+17,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7389546632766724,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.06505122784192552,
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": 6.639,
374
  "eval_steps_per_second": 1.662,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.03317612619938201,
379
+ "grad_norm": 0.48402392864227295,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 4.2489,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.03382663847780127,
386
+ "grad_norm": 0.5398579835891724,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 4.166,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.03447715075622052,
393
+ "grad_norm": 0.5588984489440918,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 4.6712,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.03512766303463978,
400
+ "grad_norm": 0.5224852561950684,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 4.4866,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.03577817531305903,
407
+ "grad_norm": 0.5074653029441833,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 4.466,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.03642868759147829,
414
+ "grad_norm": 0.5670197606086731,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 4.3119,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.03707919986989754,
421
+ "grad_norm": 0.4569515287876129,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 4.5278,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.0377297121483168,
428
+ "grad_norm": 0.5136495232582092,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 4.5103,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.038380224426736054,
435
+ "grad_norm": 0.45289337635040283,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 4.5161,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.03903073670515531,
442
+ "grad_norm": 0.5101237297058105,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 4.3636,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.039681248983574564,
449
+ "grad_norm": 0.4960824251174927,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 4.6382,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.04033176126199382,
456
+ "grad_norm": 0.47291213274002075,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 4.7356,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.040982273540413075,
463
+ "grad_norm": 0.5523029565811157,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 4.6053,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.041632785818832334,
470
+ "grad_norm": 0.4428810775279999,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 4.5437,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.042283298097251586,
477
+ "grad_norm": 0.49818718433380127,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 4.8466,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.04293381037567084,
484
+ "grad_norm": 0.4763147234916687,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 4.5998,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.043584322654090096,
491
+ "grad_norm": 0.597857654094696,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 4.5964,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.04423483493250935,
498
+ "grad_norm": 0.5390750169754028,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 4.3763,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.04488534721092861,
505
+ "grad_norm": 0.49823203682899475,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 4.7298,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.04553585948934786,
512
+ "grad_norm": 0.5256410837173462,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 4.8487,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.04618637176776712,
519
+ "grad_norm": 0.5595061182975769,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 4.9873,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.04683688404618637,
526
+ "grad_norm": 0.6115620136260986,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 4.8716,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.04748739632460563,
533
+ "grad_norm": 0.601868212223053,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 4.8483,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.04813790860302488,
540
+ "grad_norm": 0.619591474533081,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 5.1136,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.04878842088144414,
547
+ "grad_norm": 0.7487257719039917,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 4.9936,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.04943893315986339,
554
+ "grad_norm": 0.6831351518630981,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 4.9526,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.05008944543828265,
561
+ "grad_norm": 0.7687312364578247,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 5.0725,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.0507399577167019,
568
+ "grad_norm": 0.7937861680984497,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 5.294,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.05139046999512116,
575
+ "grad_norm": 0.9356114268302917,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 5.6726,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.05204098227354041,
582
+ "grad_norm": 0.9393124580383301,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 5.3861,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.05269149455195967,
589
+ "grad_norm": 1.04855477809906,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 6.1938,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.05334200683037892,
596
+ "grad_norm": 1.0108082294464111,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 5.5263,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.05399251910879818,
603
+ "grad_norm": 0.9941501617431641,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 5.3024,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.05464303138721743,
610
+ "grad_norm": 1.0947118997573853,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 5.6406,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.05529354366563669,
617
+ "grad_norm": 1.3851187229156494,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 6.3249,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.055944055944055944,
624
+ "grad_norm": 1.4180490970611572,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 6.6054,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.056594568222475196,
631
+ "grad_norm": 1.4259532690048218,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 6.1053,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.057245080500894455,
638
+ "grad_norm": 1.4208811521530151,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 5.9681,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.057895592779313707,
645
+ "grad_norm": 1.4157319068908691,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 6.4869,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.058546105057732965,
652
+ "grad_norm": 1.6923154592514038,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 6.8299,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.05919661733615222,
659
+ "grad_norm": 1.7933100461959839,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 6.8221,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.059847129614571476,
666
+ "grad_norm": 1.8865070343017578,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 6.7431,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.06049764189299073,
673
+ "grad_norm": 2.5307703018188477,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 8.523,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.06114815417140999,
680
+ "grad_norm": 2.0570056438446045,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 7.3828,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.06179866644982924,
687
+ "grad_norm": 2.696568250656128,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 7.8743,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.0624491787282485,
694
+ "grad_norm": 4.576745510101318,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 10.2667,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.06309969100666775,
701
+ "grad_norm": 3.2011473178863525,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 9.303,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.063750203285087,
708
+ "grad_norm": 4.851830959320068,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 11.6186,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.06440071556350627,
715
+ "grad_norm": 5.677859783172607,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 14.1113,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.06505122784192552,
722
+ "grad_norm": 7.9092607498168945,
723
+ "learning_rate": 0.0,
724
+ "loss": 18.4214,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.06505122784192552,
729
+ "eval_loss": 0.7389546632766724,
730
+ "eval_runtime": 389.1253,
731
+ "eval_samples_per_second": 6.653,
732
+ "eval_steps_per_second": 1.665,
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": 3.304045495399219e+17,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null