aleegis11 commited on
Commit
dc6660d
·
verified ·
1 Parent(s): 2e95c4d

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:c9e80afd3bc4f0d76cfa50e80df9ae1cf4c90576bbb50955c453d150c563b243
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f36a5f76887904ba5ebd4d0b495ca38ff58ebfb13c47250a1f3eb528776a392
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9137b24f673be076e4460f54f008f13ba59ad758826a61246eeb5b29af1b2a1
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4f11bff183ac58462980156dcb7e5e743460bd80a022e659da8264d20231e49
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27885ce41e574820a94c96758f0783dc1e14943ca877157fa8668436a82d9ba2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38820ddfe9e4e2e009161dd58efecfd416fca410dac287608a38870013984c10
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": 1.1465318202972412,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.22857142857142856,
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": 8.993,
374
  "eval_steps_per_second": 2.267,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.0213137333406925e+17,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.0969529151916504,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.45714285714285713,
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": 8.993,
374
  "eval_steps_per_second": 2.267,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.23314285714285715,
379
+ "grad_norm": 0.14895500242710114,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.5121,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.2377142857142857,
386
+ "grad_norm": 0.16254602372646332,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.118,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.2422857142857143,
393
+ "grad_norm": 0.17265716195106506,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.3765,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.24685714285714286,
400
+ "grad_norm": 0.18003533780574799,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.2285,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.25142857142857145,
407
+ "grad_norm": 0.15403780341148376,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.2193,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.256,
414
+ "grad_norm": 0.141326904296875,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.2924,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.26057142857142856,
421
+ "grad_norm": 0.12267368286848068,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.2832,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.2651428571428571,
428
+ "grad_norm": 0.12160666286945343,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.3969,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.26971428571428574,
435
+ "grad_norm": 0.12419481575489044,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.4133,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.2742857142857143,
442
+ "grad_norm": 0.11516056209802628,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.3351,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.27885714285714286,
449
+ "grad_norm": 0.13372984528541565,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.3921,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.2834285714285714,
456
+ "grad_norm": 0.13296741247177124,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.3812,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.288,
463
+ "grad_norm": 0.14010053873062134,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.3304,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.2925714285714286,
470
+ "grad_norm": 0.1268775314092636,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.3265,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.29714285714285715,
477
+ "grad_norm": 0.12483099102973938,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.2259,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.3017142857142857,
484
+ "grad_norm": 0.13041441142559052,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.3675,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.3062857142857143,
491
+ "grad_norm": 0.12797042727470398,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.2383,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.31085714285714283,
498
+ "grad_norm": 0.13023968040943146,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.2535,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.31542857142857145,
505
+ "grad_norm": 0.12802593410015106,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.2855,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.32,
512
+ "grad_norm": 0.12662489712238312,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.1503,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.32457142857142857,
519
+ "grad_norm": 0.13285095989704132,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.2358,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.3291428571428571,
526
+ "grad_norm": 0.12332078069448471,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.1553,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.33371428571428574,
533
+ "grad_norm": 0.12388018518686295,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.1739,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.3382857142857143,
540
+ "grad_norm": 0.14020569622516632,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.1668,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.34285714285714286,
547
+ "grad_norm": 0.1221918910741806,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.1935,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.3474285714285714,
554
+ "grad_norm": 0.1297471970319748,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.1603,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.352,
561
+ "grad_norm": 0.11684367805719376,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.0564,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.3565714285714286,
568
+ "grad_norm": 0.11793461441993713,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.1733,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.36114285714285715,
575
+ "grad_norm": 0.12452173233032227,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.2412,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.3657142857142857,
582
+ "grad_norm": 0.12887261807918549,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.2228,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.3702857142857143,
589
+ "grad_norm": 0.11742619425058365,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.263,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.37485714285714283,
596
+ "grad_norm": 0.11659453809261322,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.1504,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.37942857142857145,
603
+ "grad_norm": 0.12475767731666565,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.2661,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.384,
610
+ "grad_norm": 0.1260615885257721,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.1136,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.38857142857142857,
617
+ "grad_norm": 0.13305872678756714,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.1865,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.3931428571428571,
624
+ "grad_norm": 0.1305752694606781,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.2529,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.3977142857142857,
631
+ "grad_norm": 0.12492652237415314,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.9044,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.4022857142857143,
638
+ "grad_norm": 0.12890726327896118,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.1121,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.40685714285714286,
645
+ "grad_norm": 0.12997473776340485,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.0347,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.4114285714285714,
652
+ "grad_norm": 0.12488750368356705,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.8619,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.416,
659
+ "grad_norm": 0.12945248186588287,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.9846,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.4205714285714286,
666
+ "grad_norm": 0.12920667231082916,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 1.0864,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.42514285714285716,
673
+ "grad_norm": 0.14830996096134186,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.0887,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.4297142857142857,
680
+ "grad_norm": 0.15009595453739166,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.7742,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.4342857142857143,
687
+ "grad_norm": 0.1972149759531021,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.7414,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.43885714285714283,
694
+ "grad_norm": 0.3312933146953583,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.6417,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.44342857142857145,
701
+ "grad_norm": 0.4016004502773285,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.4978,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.448,
708
+ "grad_norm": 0.6031044721603394,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.2744,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.45257142857142857,
715
+ "grad_norm": 0.7307276725769043,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.2363,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.45714285714285713,
722
+ "grad_norm": 0.6628548502922058,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.2283,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.45714285714285713,
729
+ "eval_loss": 1.0969529151916504,
730
+ "eval_runtime": 41.0178,
731
+ "eval_samples_per_second": 8.996,
732
+ "eval_steps_per_second": 2.267,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.059261240840028e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null