prxy5605 commited on
Commit
250beb0
·
verified ·
1 Parent(s): 27ca41e

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 sha256:6b0c6cf4df405b61401b637d7c44736f67f2ceed0aa0e6372dd1d9b0735bb3e0
3
  size 138995824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca67dcc71a8cc24119ee0cda991a3e522aa95ca973e2d16a37ebf23bdcc8980f
3
  size 138995824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a702a8a1d810bc267ab66129254b1195d69a8693c9e2fb7f9b02f2f4a2718726
3
  size 71077780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfcc86efab9d216591dd409ef208bb7e78d0c4aa57468d2e6dd77ad0c0d6b992
3
  size 71077780
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86f3666ee7877b4119a6d36c0ca47077d060e2b76902544b1577e61196cd9a73
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e95afd3891d0bb087e6903fbe81842fadb0e83c67c5ca069227affa0180e6994
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": 3.6407744884490967,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.12048192771084337,
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": 60.146,
374
  "eval_steps_per_second": 15.058,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3451611968962560.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 3.3175594806671143,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.24096385542168675,
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": 60.146,
374
  "eval_steps_per_second": 15.058,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.12289156626506025,
379
+ "grad_norm": 2.0507376194000244,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 3.0997,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.12530120481927712,
386
+ "grad_norm": 2.6045119762420654,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 3.3431,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.12771084337349398,
393
+ "grad_norm": 2.14469838142395,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 2.8362,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.13012048192771083,
400
+ "grad_norm": 2.6682627201080322,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 3.4038,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.13253012048192772,
407
+ "grad_norm": 2.431370496749878,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 3.4529,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.13493975903614458,
414
+ "grad_norm": 2.4101388454437256,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 3.906,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.13734939759036144,
421
+ "grad_norm": 1.765518069267273,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 3.543,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.13975903614457832,
428
+ "grad_norm": 1.5656791925430298,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 3.7954,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.14216867469879518,
435
+ "grad_norm": 1.2936886548995972,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 3.4387,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.14457831325301204,
442
+ "grad_norm": 0.97733473777771,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 3.537,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.14698795180722893,
449
+ "grad_norm": 0.7809424996376038,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 3.4851,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.1493975903614458,
456
+ "grad_norm": 0.869732141494751,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 3.6852,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.15180722891566265,
463
+ "grad_norm": 0.6646137833595276,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 3.1534,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.15421686746987953,
470
+ "grad_norm": 0.6337130665779114,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 3.5985,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.1566265060240964,
477
+ "grad_norm": 0.5813305377960205,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 3.4279,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.15903614457831325,
484
+ "grad_norm": 0.8562886118888855,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 3.4785,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.1614457831325301,
491
+ "grad_norm": 0.7590737342834473,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 3.5843,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.163855421686747,
498
+ "grad_norm": 0.7741421461105347,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 3.6298,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.16626506024096385,
505
+ "grad_norm": 0.6825758218765259,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 3.4934,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.1686746987951807,
512
+ "grad_norm": 0.6117427945137024,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 3.1839,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.1710843373493976,
519
+ "grad_norm": 0.5825290083885193,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 3.5409,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.17349397590361446,
526
+ "grad_norm": 0.6651800870895386,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 3.4238,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.17590361445783131,
533
+ "grad_norm": 0.8381586074829102,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 3.2639,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.1783132530120482,
540
+ "grad_norm": 0.7422766089439392,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 3.2455,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.18072289156626506,
547
+ "grad_norm": 0.6565409898757935,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 3.2713,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.18313253012048192,
554
+ "grad_norm": 0.7281730771064758,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 3.3428,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.1855421686746988,
561
+ "grad_norm": 0.7918378710746765,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 3.1877,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.18795180722891566,
568
+ "grad_norm": 0.7220017313957214,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 3.342,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.19036144578313252,
575
+ "grad_norm": 0.6950394511222839,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 3.7129,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.1927710843373494,
582
+ "grad_norm": 0.7593180537223816,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 2.9156,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.19518072289156627,
589
+ "grad_norm": 0.8869415521621704,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 3.2975,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.19759036144578312,
596
+ "grad_norm": 0.777900218963623,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 3.6063,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.2,
603
+ "grad_norm": 0.7878391146659851,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 3.2553,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.20240963855421687,
610
+ "grad_norm": 0.7920843958854675,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 3.7305,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.20481927710843373,
617
+ "grad_norm": 0.7009216547012329,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 3.4659,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.20722891566265061,
624
+ "grad_norm": 0.8619423508644104,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 3.7053,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.20963855421686747,
631
+ "grad_norm": 0.7608540058135986,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 3.6463,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.21204819277108433,
638
+ "grad_norm": 0.8320346474647522,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 3.5518,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.21445783132530122,
645
+ "grad_norm": 0.9128895401954651,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 3.5532,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.21686746987951808,
652
+ "grad_norm": 0.8454603552818298,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 3.5297,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.21927710843373494,
659
+ "grad_norm": 0.8832200765609741,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 3.7787,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.2216867469879518,
666
+ "grad_norm": 0.9075934886932373,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 3.4028,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.22409638554216868,
673
+ "grad_norm": 0.9533520340919495,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 2.9965,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.22650602409638554,
680
+ "grad_norm": 0.9323415160179138,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 3.7702,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.2289156626506024,
687
+ "grad_norm": 1.1381555795669556,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 3.3106,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.23132530120481928,
694
+ "grad_norm": 1.051990032196045,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 3.3298,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.23373493975903614,
701
+ "grad_norm": 1.1901023387908936,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 3.2697,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.236144578313253,
708
+ "grad_norm": 1.1955888271331787,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 3.2914,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.2385542168674699,
715
+ "grad_norm": 1.7270820140838623,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 4.2431,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.24096385542168675,
722
+ "grad_norm": 2.0670971870422363,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 3.4487,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.24096385542168675,
729
+ "eval_loss": 3.3175594806671143,
730
+ "eval_runtime": 11.6362,
731
+ "eval_samples_per_second": 60.071,
732
+ "eval_steps_per_second": 15.039,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 6886051739074560.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null