aleegis11 commited on
Commit
447e1c1
·
verified ·
1 Parent(s): 4ae7a4c

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:dda8208b1cd0ba44b9fdf867af501c1bd06142a9f834e685ba6435b4625fb295
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7bed5bf6e403571cd4b2c52593e152f4e8a5d742b792e28bbacf835a35b61e2
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cbc32dc14f4cbb600f6ce1a7b620c31b16731a9b4db97c7a7d90aa72e1ca9d7
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdaa1eb075669105165ecff759347bd28db820270f008c4fdafba25a4463644d
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a53bffa166e1c766256324a84ed685c220d1afee191bcf64d759d9ae0762bef
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e29024cee0e32918d804c461b1559b02a369606d17096809c8f0b30b8f84677b
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": 1.1050190925598145,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.02520478890989288,
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": 47.71,
374
  "eval_steps_per_second": 11.938,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 4772337901633536.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.0116993188858032,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.05040957781978576,
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": 47.71,
374
  "eval_steps_per_second": 11.938,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.02570888468809074,
379
+ "grad_norm": 1.292781949043274,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.9901,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.026212980466288595,
386
+ "grad_norm": 1.1206916570663452,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.0152,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.02671707624448645,
393
+ "grad_norm": 0.8595021367073059,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.9863,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.02722117202268431,
400
+ "grad_norm": 0.6013736724853516,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.0146,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.027725267800882167,
407
+ "grad_norm": 0.5559196472167969,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.9531,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.028229363579080024,
414
+ "grad_norm": 0.5038899779319763,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.9519,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.028733459357277884,
421
+ "grad_norm": 0.44719502329826355,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.9766,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.02923755513547574,
428
+ "grad_norm": 0.4539150297641754,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.9853,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.029741650913673597,
435
+ "grad_norm": 0.45345962047576904,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.9229,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.030245746691871456,
442
+ "grad_norm": 0.4743633568286896,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.9564,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.030749842470069313,
449
+ "grad_norm": 0.484157532453537,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.9582,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.03125393824826717,
456
+ "grad_norm": 0.44355064630508423,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.9991,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.03175803402646503,
463
+ "grad_norm": 0.40092796087265015,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.915,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.032262129804662885,
470
+ "grad_norm": 0.3976602554321289,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.891,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.03276622558286074,
477
+ "grad_norm": 0.41375917196273804,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.9286,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.0332703213610586,
484
+ "grad_norm": 0.4368148148059845,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.9392,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.03377441713925646,
491
+ "grad_norm": 0.4674438536167145,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.9399,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.03427851291745432,
498
+ "grad_norm": 0.4300023913383484,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.9015,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.034782608695652174,
505
+ "grad_norm": 0.44563958048820496,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.9133,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.03528670447385003,
512
+ "grad_norm": 0.4508240222930908,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.9124,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.03579080025204789,
519
+ "grad_norm": 0.48746979236602783,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.9495,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.036294896030245744,
526
+ "grad_norm": 0.5286091566085815,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.9482,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.03679899180844361,
533
+ "grad_norm": 0.5450381636619568,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.9255,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.03730308758664146,
540
+ "grad_norm": 0.5480132102966309,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.9612,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.03780718336483932,
547
+ "grad_norm": 0.5725929737091064,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.0166,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.038311279143037176,
554
+ "grad_norm": 0.5540945529937744,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.9842,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.03881537492123503,
561
+ "grad_norm": 0.593117356300354,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.9666,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.03931947069943289,
568
+ "grad_norm": 0.7941222190856934,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.9603,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.03982356647763075,
575
+ "grad_norm": 0.6581109166145325,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.9778,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.04032766225582861,
582
+ "grad_norm": 0.707141101360321,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.0769,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.040831758034026465,
589
+ "grad_norm": 0.7098904252052307,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.0253,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.04133585381222432,
596
+ "grad_norm": 0.725770115852356,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.9254,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.04183994959042218,
603
+ "grad_norm": 0.8920672535896301,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.9655,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.04234404536862004,
610
+ "grad_norm": 0.8527565002441406,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.924,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.0428481411468179,
617
+ "grad_norm": 0.9886060357093811,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.8559,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.043352236925015754,
624
+ "grad_norm": 0.9404958486557007,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.7445,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.04385633270321361,
631
+ "grad_norm": 1.1955063343048096,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.0882,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.04436042848141147,
638
+ "grad_norm": 1.2329496145248413,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.8986,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.04486452425960932,
645
+ "grad_norm": 1.3696224689483643,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.0774,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.045368620037807186,
652
+ "grad_norm": 1.3210687637329102,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.8344,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.04587271581600504,
659
+ "grad_norm": 1.2450342178344727,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.9926,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.0463768115942029,
666
+ "grad_norm": 1.536271572113037,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.9797,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.046880907372400756,
673
+ "grad_norm": 1.8610961437225342,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.1009,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.04738500315059861,
680
+ "grad_norm": 1.8540403842926025,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.1389,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.04788909892879647,
687
+ "grad_norm": 2.1709673404693604,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.9783,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.04839319470699433,
694
+ "grad_norm": 2.641937494277954,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.1573,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.04889729048519219,
701
+ "grad_norm": 2.51130747795105,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.1294,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.049401386263390044,
708
+ "grad_norm": 2.792402505874634,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.3566,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.0499054820415879,
715
+ "grad_norm": 3.161710023880005,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.4144,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.05040957781978576,
722
+ "grad_norm": 6.212632656097412,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.7334,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.05040957781978576,
729
+ "eval_loss": 1.0116993188858032,
730
+ "eval_runtime": 70.2364,
731
+ "eval_samples_per_second": 47.568,
732
+ "eval_steps_per_second": 11.903,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 9486712185028608.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null