aleegis10 commited on
Commit
d4d5ec9
·
verified ·
1 Parent(s): 9d2884e

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 sha256:6a7be31186993279d7eb132568d67a97b4ec1a01a89a3b384f22d576c888a1a3
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a851b410fbb26fe2615278f0a240358be50b6862f7c6581124043d3c032036e6
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:890eb5641df94bbf8c5984b6cbb629ef206749bf622e3bcb205cc62093ef177f
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d890535e039823dca83b2a875f12de3e629ccda90a589cf97b594b66b2fdf444
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:ac905c132c7937cd7249cbe7d7511363923f3c21270712fcdfd69389a456464e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16e62860a68a4de3b2e2c00acb50be056c99f1797f74f228ae112b779d0c6fc8
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": 0.6620756983757019,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.7299270072992701,
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": 13.739,
374
  "eval_steps_per_second": 3.465,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 6.72883802112e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.44356289505958557,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.4635036496350364,
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": 13.739,
374
  "eval_steps_per_second": 3.465,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.7445255474452555,
379
+ "grad_norm": 0.6144942045211792,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.6887,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.7591240875912408,
386
+ "grad_norm": 0.44584447145462036,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.6056,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.7737226277372263,
393
+ "grad_norm": 0.5202380418777466,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.6939,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.7883211678832117,
400
+ "grad_norm": 0.3601526618003845,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.6728,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.8029197080291971,
407
+ "grad_norm": 0.42665866017341614,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.6846,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.8175182481751825,
414
+ "grad_norm": 0.630306601524353,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.6996,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.8321167883211679,
421
+ "grad_norm": 0.48954012989997864,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.6804,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.8467153284671532,
428
+ "grad_norm": 0.797709047794342,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.6244,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.8613138686131386,
435
+ "grad_norm": 0.470983624458313,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.6413,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.8759124087591241,
442
+ "grad_norm": 0.5941108465194702,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.6347,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.8905109489051095,
449
+ "grad_norm": 0.32307079434394836,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.6821,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.9051094890510949,
456
+ "grad_norm": 0.4610147178173065,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.6431,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.9197080291970803,
463
+ "grad_norm": 0.6533463597297668,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.6458,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.9343065693430657,
470
+ "grad_norm": 0.2629701495170593,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.6384,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.948905109489051,
477
+ "grad_norm": 0.3607243597507477,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.6496,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.9635036496350365,
484
+ "grad_norm": 0.24368129670619965,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.6429,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.9781021897810219,
491
+ "grad_norm": 1.090360403060913,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.7193,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.9927007299270073,
498
+ "grad_norm": 0.4807930588722229,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.6403,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 1.010948905109489,
505
+ "grad_norm": 1.2754051685333252,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.2307,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 1.0255474452554745,
512
+ "grad_norm": 0.6335033178329468,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.6324,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 1.0401459854014599,
519
+ "grad_norm": 0.8098115921020508,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.5842,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 1.0547445255474452,
526
+ "grad_norm": 0.47459185123443604,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.6183,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 1.0693430656934306,
533
+ "grad_norm": 0.9818742275238037,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.6439,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 1.083941605839416,
540
+ "grad_norm": 0.9477861523628235,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.5405,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 1.0985401459854014,
547
+ "grad_norm": 1.8204628229141235,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.5607,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 1.1131386861313868,
554
+ "grad_norm": 2.8951661586761475,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.7007,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 1.1277372262773722,
561
+ "grad_norm": 1.75932776927948,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.5977,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 1.1423357664233578,
568
+ "grad_norm": 1.4874998331069946,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.8672,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 1.1569343065693432,
575
+ "grad_norm": 1.1275254487991333,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.6145,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 1.1715328467153285,
582
+ "grad_norm": 0.588616132736206,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.5931,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 1.186131386861314,
589
+ "grad_norm": 0.5191588997840881,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.6296,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 1.2007299270072993,
596
+ "grad_norm": 0.776644229888916,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.5831,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 1.2153284671532847,
603
+ "grad_norm": 0.8567450642585754,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.6257,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 1.22992700729927,
610
+ "grad_norm": 0.9636512398719788,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.5479,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 1.2445255474452555,
617
+ "grad_norm": 1.2442514896392822,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.5543,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 1.2591240875912408,
624
+ "grad_norm": 2.7604684829711914,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.6211,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 1.2737226277372262,
631
+ "grad_norm": 2.9896342754364014,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.4459,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 1.2883211678832116,
638
+ "grad_norm": 2.8760337829589844,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.6636,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 1.3029197080291972,
645
+ "grad_norm": 3.1063735485076904,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.5903,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 1.3175182481751824,
652
+ "grad_norm": 2.3436295986175537,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.5067,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 1.332116788321168,
659
+ "grad_norm": 1.832503318786621,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.5966,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 1.3467153284671534,
666
+ "grad_norm": 1.6309736967086792,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.4747,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.3613138686131387,
673
+ "grad_norm": 1.4411300420761108,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.5607,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.3759124087591241,
680
+ "grad_norm": 1.1576124429702759,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.4929,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.3905109489051095,
687
+ "grad_norm": 1.752060055732727,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.601,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.405109489051095,
694
+ "grad_norm": 1.2885116338729858,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.5715,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.4197080291970803,
701
+ "grad_norm": 1.4122116565704346,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.4723,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.4343065693430657,
708
+ "grad_norm": 2.1593947410583496,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.5248,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.448905109489051,
715
+ "grad_norm": 1.843381643295288,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.5961,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.4635036496350364,
722
+ "grad_norm": 1.5842969417572021,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.5352,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.4635036496350364,
729
+ "eval_loss": 0.44356289505958557,
730
+ "eval_runtime": 8.3718,
731
+ "eval_samples_per_second": 13.737,
732
+ "eval_steps_per_second": 3.464,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.345767604224e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null