blood34 commited on
Commit
f8e0025
·
verified ·
1 Parent(s): 44bcf32

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:c87373b07695848d5136e5ff462e8ffa23913ddf9265ed1b4a6c5ff6f75e037e
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef05a3cacb9e140de1d62aa62c89a289736ce8a73a5e034c40f9f97e9e7b5836
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32228a39a9c0afaeeb192dc6d8ab1176437288f83a08ab050e0001fc633aa9db
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c63b4340f3c0d6bc13fdd18111c2170dbcef0e9e7ce0c5bbd36b6cb28ab43c8
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:c1ff3499e4fc238800935123859e0ff0c6a8653a62dd220ca670c68ac12c5257
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e7bd38afa90c7b2ff704302889dc7bebc024d0c576b2234ebd6066017d891b5
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d359eb5d29e75fb2bbe5b7026981da69b95b8ad1fea469302d13cde104f7e8a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.271299362182617,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.01365280906546522,
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": 8.832,
374
  "eval_steps_per_second": 2.208,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.15499004493824e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.1340065002441406,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.02730561813093044,
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": 8.832,
374
  "eval_steps_per_second": 2.208,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.013925865246774524,
379
+ "grad_norm": 24.909616470336914,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 7.0786,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.014198921428083829,
386
+ "grad_norm": 24.512235641479492,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 8.499,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.014471977609393132,
393
+ "grad_norm": 20.238571166992188,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 8.7019,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.014745033790702437,
400
+ "grad_norm": 20.472135543823242,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 7.191,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.015018089972011742,
407
+ "grad_norm": 18.48778533935547,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 8.5567,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.015291146153321045,
414
+ "grad_norm": 17.57303810119629,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 8.4159,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.01556420233463035,
421
+ "grad_norm": 17.54515266418457,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 8.3224,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.015837258515939655,
428
+ "grad_norm": 18.000179290771484,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 9.0583,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.01611031469724896,
435
+ "grad_norm": 22.772430419921875,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 8.5008,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.016383370878558262,
442
+ "grad_norm": 16.104167938232422,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 7.918,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.016656427059867567,
449
+ "grad_norm": 15.550981521606445,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 7.9553,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.016929483241176872,
456
+ "grad_norm": 17.316165924072266,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 7.9485,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.017202539422486177,
463
+ "grad_norm": 17.424301147460938,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 7.3209,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.017475595603795482,
470
+ "grad_norm": 16.4025936126709,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 8.1016,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.017748651785104784,
477
+ "grad_norm": 18.199373245239258,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 8.2282,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.01802170796641409,
484
+ "grad_norm": 18.115741729736328,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 8.0613,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.018294764147723394,
491
+ "grad_norm": 18.224075317382812,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 8.5954,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.0185678203290327,
498
+ "grad_norm": 17.102075576782227,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 8.2442,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.018840876510342004,
505
+ "grad_norm": 23.462993621826172,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 9.5302,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.019113932691651306,
512
+ "grad_norm": 19.042011260986328,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 8.4879,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.01938698887296061,
519
+ "grad_norm": 16.553205490112305,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 6.8034,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.019660045054269916,
526
+ "grad_norm": 21.598339080810547,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 7.9676,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.01993310123557922,
533
+ "grad_norm": 18.137998580932617,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 7.6405,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.020206157416888526,
540
+ "grad_norm": 18.159276962280273,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 8.6501,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.020479213598197828,
547
+ "grad_norm": 15.387510299682617,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 7.4218,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.020752269779507133,
554
+ "grad_norm": 23.088130950927734,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 8.0995,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.021025325960816438,
561
+ "grad_norm": 17.979206085205078,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 8.097,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.021298382142125743,
568
+ "grad_norm": 20.9732723236084,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 9.4713,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.021571438323435048,
575
+ "grad_norm": 20.32724952697754,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 7.8127,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.02184449450474435,
582
+ "grad_norm": 20.800214767456055,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 8.0962,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.022117550686053655,
589
+ "grad_norm": 19.788745880126953,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 9.1246,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.02239060686736296,
596
+ "grad_norm": 20.843629837036133,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 8.05,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.022663663048672265,
603
+ "grad_norm": 16.206398010253906,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 7.2646,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.02293671922998157,
610
+ "grad_norm": 18.066072463989258,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 7.4305,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.023209775411290875,
617
+ "grad_norm": 20.16105079650879,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 8.6175,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.023482831592600176,
624
+ "grad_norm": 23.420856475830078,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 8.8125,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.02375588777390948,
631
+ "grad_norm": 23.20645523071289,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 7.9372,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.024028943955218787,
638
+ "grad_norm": 18.95828628540039,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 8.2753,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.02430200013652809,
645
+ "grad_norm": 20.9344482421875,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 8.9119,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.024575056317837397,
652
+ "grad_norm": 22.957317352294922,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 8.6468,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.024848112499146698,
659
+ "grad_norm": 20.31450653076172,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 7.4481,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.025121168680456003,
666
+ "grad_norm": 25.291793823242188,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 7.6528,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.02539422486176531,
673
+ "grad_norm": 23.33091926574707,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 8.0942,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.025667281043074613,
680
+ "grad_norm": 26.418405532836914,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 7.4102,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.02594033722438392,
687
+ "grad_norm": 25.400789260864258,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 8.5998,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.02621339340569322,
694
+ "grad_norm": 32.99055480957031,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 7.8845,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.026486449587002525,
701
+ "grad_norm": 25.209062576293945,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 6.6911,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.02675950576831183,
708
+ "grad_norm": 26.858041763305664,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 7.1683,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.027032561949621135,
715
+ "grad_norm": 28.698999404907227,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 7.3205,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.02730561813093044,
722
+ "grad_norm": 51.56425094604492,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 11.4165,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.02730561813093044,
729
+ "eval_loss": 2.1340065002441406,
730
+ "eval_runtime": 697.8133,
731
+ "eval_samples_per_second": 8.839,
732
+ "eval_steps_per_second": 2.21,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.430998008987648e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null