cimol commited on
Commit
2abcea2
·
verified ·
1 Parent(s): d7f2345

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 sha256:28c308b4a008b78dc36ec73a66a1c07110f9afc950a42f7ef1080557faa3a481
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9378d75810abf450abcc091bbe23663f53b94976717b4fa71ed929c9ba62a8ca
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8864c37a65b87b10cccad367e2a149ecd9bfc2ab0659598df5098c3295943cee
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a1712a8c9dd8ab372e655cdf3753005620287f226c490cfd4bcbf1da185e360
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4add6ac482975805e8b41fdc498d42bf3e63b6e1066b64d5075e36802e136008
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf3928560a0fac89e8dc1f8d64c9624302321953123449d57a1d66545f916a5e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:947b4b7e8b578cfa0f90060cb87e8d28c0e6be86b5cadcb00b9f65c8cbebcbb8
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d94dee72c7d02de6c69d9fa4cc2d9dd3225f09ac52c6adcb59ec7bae1df8f10
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.3040165901184082,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.09519276534983341,
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": 13.519,
374
  "eval_steps_per_second": 3.391,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.15499809800192e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.1414027214050293,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.19038553069966682,
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": 13.519,
374
  "eval_steps_per_second": 3.391,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.09709662065683008,
379
+ "grad_norm": 15.806927680969238,
380
+ "learning_rate": 6.226070475667393e-05,
381
+ "loss": 5.6676,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.09900047596382675,
386
+ "grad_norm": 11.198895454406738,
387
+ "learning_rate": 6.189403887999006e-05,
388
+ "loss": 5.4295,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.10090433127082342,
393
+ "grad_norm": 8.934762001037598,
394
+ "learning_rate": 6.152002044161171e-05,
395
+ "loss": 5.408,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.10280818657782008,
400
+ "grad_norm": 7.409307479858398,
401
+ "learning_rate": 6.113875169444539e-05,
402
+ "loss": 5.2086,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.10471204188481675,
407
+ "grad_norm": 8.708901405334473,
408
+ "learning_rate": 6.0750336873559605e-05,
409
+ "loss": 5.4806,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.10661589719181343,
414
+ "grad_norm": 8.244229316711426,
415
+ "learning_rate": 6.035488216768811e-05,
416
+ "loss": 5.1627,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.10851975249881009,
421
+ "grad_norm": 7.6382060050964355,
422
+ "learning_rate": 5.9952495690198894e-05,
423
+ "loss": 4.7832,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.11042360780580676,
428
+ "grad_norm": 7.794398784637451,
429
+ "learning_rate": 5.954328744953709e-05,
430
+ "loss": 4.759,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.11232746311280342,
435
+ "grad_norm": 8.159358978271484,
436
+ "learning_rate": 5.91273693191498e-05,
437
+ "loss": 4.8963,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.1142313184198001,
442
+ "grad_norm": 8.03155517578125,
443
+ "learning_rate": 5.870485500690094e-05,
444
+ "loss": 5.1858,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.11613517372679677,
449
+ "grad_norm": 9.014118194580078,
450
+ "learning_rate": 5.827586002398468e-05,
451
+ "loss": 5.2089,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.11803902903379343,
456
+ "grad_norm": 8.561113357543945,
457
+ "learning_rate": 5.784050165334589e-05,
458
+ "loss": 4.8377,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.1199428843407901,
463
+ "grad_norm": 9.359479904174805,
464
+ "learning_rate": 5.739889891761608e-05,
465
+ "loss": 4.8591,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.12184673964778676,
470
+ "grad_norm": 8.884666442871094,
471
+ "learning_rate": 5.6951172546573794e-05,
472
+ "loss": 4.8723,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.12375059495478344,
477
+ "grad_norm": 8.695745468139648,
478
+ "learning_rate": 5.6497444944138376e-05,
479
+ "loss": 5.0063,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.1256544502617801,
484
+ "grad_norm": 7.5747456550598145,
485
+ "learning_rate": 5.603784015490587e-05,
486
+ "loss": 4.7092,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.1275583055687768,
491
+ "grad_norm": 7.801674842834473,
492
+ "learning_rate": 5.557248383023655e-05,
493
+ "loss": 4.7957,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.12946216087577345,
498
+ "grad_norm": 8.105006217956543,
499
+ "learning_rate": 5.510150319390302e-05,
500
+ "loss": 4.4399,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.1313660161827701,
505
+ "grad_norm": 8.557613372802734,
506
+ "learning_rate": 5.4625027007308546e-05,
507
+ "loss": 4.885,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.13326987148976677,
512
+ "grad_norm": 11.274003028869629,
513
+ "learning_rate": 5.414318553428494e-05,
514
+ "loss": 4.8082,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.13517372679676345,
519
+ "grad_norm": 11.312886238098145,
520
+ "learning_rate": 5.3656110505479776e-05,
521
+ "loss": 4.7281,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.13707758210376011,
526
+ "grad_norm": 8.340498924255371,
527
+ "learning_rate": 5.316393508234253e-05,
528
+ "loss": 4.7314,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.13898143741075678,
533
+ "grad_norm": 8.157063484191895,
534
+ "learning_rate": 5.266679382071953e-05,
535
+ "loss": 4.9252,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.14088529271775346,
540
+ "grad_norm": 8.306255340576172,
541
+ "learning_rate": 5.216482263406778e-05,
542
+ "loss": 4.6616,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.14278914802475012,
547
+ "grad_norm": 8.908082962036133,
548
+ "learning_rate": 5.1658158756297576e-05,
549
+ "loss": 4.8742,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.14469300333174678,
554
+ "grad_norm": 7.921310901641846,
555
+ "learning_rate": 5.114694070425407e-05,
556
+ "loss": 4.4142,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.14659685863874344,
561
+ "grad_norm": 7.845428466796875,
562
+ "learning_rate": 5.063130823984823e-05,
563
+ "loss": 4.4547,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.14850071394574013,
568
+ "grad_norm": 8.892997741699219,
569
+ "learning_rate": 5.011140233184724e-05,
570
+ "loss": 5.108,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.1504045692527368,
575
+ "grad_norm": 9.606233596801758,
576
+ "learning_rate": 4.958736511733516e-05,
577
+ "loss": 4.6994,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.15230842455973345,
582
+ "grad_norm": 8.047012329101562,
583
+ "learning_rate": 4.905933986285393e-05,
584
+ "loss": 4.6938,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.15421227986673014,
589
+ "grad_norm": 9.193869590759277,
590
+ "learning_rate": 4.8527470925235824e-05,
591
+ "loss": 4.8014,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.1561161351737268,
596
+ "grad_norm": 7.83010196685791,
597
+ "learning_rate": 4.799190371213772e-05,
598
+ "loss": 4.6519,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.15801999048072346,
603
+ "grad_norm": 7.466574668884277,
604
+ "learning_rate": 4.745278464228808e-05,
605
+ "loss": 4.4398,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.15992384578772012,
610
+ "grad_norm": 8.107156753540039,
611
+ "learning_rate": 4.69102611054575e-05,
612
+ "loss": 4.6071,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.1618277010947168,
617
+ "grad_norm": 8.724653244018555,
618
+ "learning_rate": 4.6364481422163926e-05,
619
+ "loss": 4.9037,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.16373155640171347,
624
+ "grad_norm": 7.404033660888672,
625
+ "learning_rate": 4.581559480312316e-05,
626
+ "loss": 4.3696,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.16563541170871013,
631
+ "grad_norm": 8.051767349243164,
632
+ "learning_rate": 4.526375130845627e-05,
633
+ "loss": 4.5589,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.16753926701570682,
638
+ "grad_norm": 9.341611862182617,
639
+ "learning_rate": 4.4709101806664554e-05,
640
+ "loss": 4.7734,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.16944312232270348,
645
+ "grad_norm": 8.678064346313477,
646
+ "learning_rate": 4.4151797933383685e-05,
647
+ "loss": 4.6396,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.17134697762970014,
652
+ "grad_norm": 8.946483612060547,
653
+ "learning_rate": 4.359199204992797e-05,
654
+ "loss": 4.7698,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.17325083293669682,
659
+ "grad_norm": 8.687679290771484,
660
+ "learning_rate": 4.30298372016363e-05,
661
+ "loss": 4.7269,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.17515468824369348,
666
+ "grad_norm": 10.165061950683594,
667
+ "learning_rate": 4.246548707603114e-05,
668
+ "loss": 4.9481,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.17705854355069015,
673
+ "grad_norm": 8.327232360839844,
674
+ "learning_rate": 4.1899095960801805e-05,
675
+ "loss": 4.6007,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.1789623988576868,
680
+ "grad_norm": 8.452240943908691,
681
+ "learning_rate": 4.133081870162385e-05,
682
+ "loss": 4.6878,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.1808662541646835,
687
+ "grad_norm": 8.48222827911377,
688
+ "learning_rate": 4.076081065982569e-05,
689
+ "loss": 4.4604,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.18277010947168015,
694
+ "grad_norm": 9.326024055480957,
695
+ "learning_rate": 4.018922766991447e-05,
696
+ "loss": 4.7372,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.1846739647786768,
701
+ "grad_norm": 9.113911628723145,
702
+ "learning_rate": 3.961622599697241e-05,
703
+ "loss": 4.4883,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.1865778200856735,
708
+ "grad_norm": 8.056068420410156,
709
+ "learning_rate": 3.9041962293935516e-05,
710
+ "loss": 4.8074,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.18848167539267016,
715
+ "grad_norm": 8.778728485107422,
716
+ "learning_rate": 3.84665935587662e-05,
717
+ "loss": 4.4564,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.19038553069966682,
722
+ "grad_norm": 8.800410270690918,
723
+ "learning_rate": 3.7890277091531636e-05,
724
+ "loss": 4.6041,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.19038553069966682,
729
+ "eval_loss": 1.1414027214050293,
730
+ "eval_runtime": 65.4902,
731
+ "eval_samples_per_second": 13.513,
732
+ "eval_steps_per_second": 3.39,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.430999619600384e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null