aleegis10 commited on
Commit
9ad7e19
·
verified ·
1 Parent(s): 92e0a56

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 sha256:2620f0257c8ba6bd735306b8f4bf96fc415fb5a418b5aa33fb6197ad19552bfb
3
  size 864368280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36534757536f5ecef86424bb1a26e55f3f2e4bf4b4c796b25c8abfeaa3ceb0cd
3
  size 864368280
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fdebd94ce55615792bcda5069df6109114b9970c04dcc3be235cdd8e7e668531
3
  size 439588164
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:021144fd720fe4017ac7b3dffa4e676ced19af39a247bb8e422e1ad61d64e9e5
3
  size 439588164
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40f1a933da7f4d0c39785b261cf5c6eb820ca5632684a2b77454c86582b61041
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9c14200ae77e712cd900e36e8c1d68a261b0de6b6d563c5a1f80604b2496bf2
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": 0.963438868522644,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.015601841017240034,
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": 9.367,
374
  "eval_steps_per_second": 2.343,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 8.39543112597504e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8465943932533264,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.031203682034480068,
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": 9.367,
374
  "eval_steps_per_second": 2.343,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.015913877837584835,
379
+ "grad_norm": 1.680629014968872,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.9826,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.016225914657929635,
386
+ "grad_norm": 1.1629451513290405,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.8711,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.016537951478274436,
393
+ "grad_norm": 0.999272346496582,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.9047,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.016849988298619237,
400
+ "grad_norm": 1.0136737823486328,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.7953,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.017162025118964037,
407
+ "grad_norm": 0.951803982257843,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.6757,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.017474061939308838,
414
+ "grad_norm": 1.0217398405075073,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.822,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.01778609875965364,
421
+ "grad_norm": 0.9405883550643921,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.7946,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.01809813557999844,
428
+ "grad_norm": 0.9246597290039062,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.7408,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.01841017240034324,
435
+ "grad_norm": 1.0739665031433105,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.8104,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.01872220922068804,
442
+ "grad_norm": 1.036548376083374,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.7561,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.01903424604103284,
449
+ "grad_norm": 0.9185912013053894,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.7367,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.019346282861377642,
456
+ "grad_norm": 0.9082395434379578,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.8553,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.019658319681722443,
463
+ "grad_norm": 0.9209671020507812,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.7051,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.019970356502067244,
470
+ "grad_norm": 0.8518406748771667,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.6811,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.020282393322412044,
477
+ "grad_norm": 0.8296268582344055,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.6696,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.020594430142756845,
484
+ "grad_norm": 0.8943758606910706,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.6595,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.020906466963101646,
491
+ "grad_norm": 0.9089400172233582,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.8329,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.021218503783446446,
498
+ "grad_norm": 0.9639408588409424,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.7802,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.021530540603791247,
505
+ "grad_norm": 0.9582761526107788,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.7514,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.021842577424136048,
512
+ "grad_norm": 0.8935718536376953,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.7832,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.02215461424448085,
519
+ "grad_norm": 0.8567960262298584,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.7493,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.02246665106482565,
526
+ "grad_norm": 0.9141445755958557,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.8103,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.02277868788517045,
533
+ "grad_norm": 0.8256440162658691,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.7201,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.02309072470551525,
540
+ "grad_norm": 0.9923111796379089,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.7621,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.02340276152586005,
547
+ "grad_norm": 0.8481928706169128,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.8073,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.02371479834620485,
554
+ "grad_norm": 0.882407546043396,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.7526,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.024026835166549652,
561
+ "grad_norm": 0.8140597939491272,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.6825,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.024338871986894453,
568
+ "grad_norm": 0.8657062649726868,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.7353,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.024650908807239254,
575
+ "grad_norm": 0.8869200944900513,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.7921,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.024962945627584054,
582
+ "grad_norm": 0.9941065311431885,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.8222,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.025274982447928855,
589
+ "grad_norm": 0.9149479269981384,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.7853,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.025587019268273656,
596
+ "grad_norm": 0.9197757244110107,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.7227,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.025899056088618456,
603
+ "grad_norm": 0.9976024031639099,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.8561,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.026211092908963257,
610
+ "grad_norm": 0.8757933974266052,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.7793,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.026523129729308058,
617
+ "grad_norm": 1.0709153413772583,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.8835,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.02683516654965286,
624
+ "grad_norm": 0.8737066388130188,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.8136,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.02714720336999766,
631
+ "grad_norm": 0.9159258604049683,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.9143,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.02745924019034246,
638
+ "grad_norm": 0.9400917887687683,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.8458,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.02777127701068726,
645
+ "grad_norm": 0.8912694454193115,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.7847,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.02808331383103206,
652
+ "grad_norm": 0.8344074487686157,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.7255,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.028395350651376862,
659
+ "grad_norm": 0.9551566243171692,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.7822,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.028707387471721663,
666
+ "grad_norm": 0.8455932140350342,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.7324,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.029019424292066463,
673
+ "grad_norm": 0.7846436500549316,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.7129,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.029331461112411264,
680
+ "grad_norm": 1.35532546043396,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.2972,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.029643497932756065,
687
+ "grad_norm": 1.1400768756866455,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.112,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.029955534753100865,
694
+ "grad_norm": 1.5415581464767456,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.441,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.030267571573445666,
701
+ "grad_norm": 1.1367700099945068,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.3925,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.030579608393790467,
708
+ "grad_norm": 0.9753825664520264,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.5174,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.030891645214135267,
715
+ "grad_norm": 0.905869722366333,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.334,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.031203682034480068,
722
+ "grad_norm": 0.930263876914978,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.4637,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.031203682034480068,
729
+ "eval_loss": 0.8465943932533264,
730
+ "eval_runtime": 576.3777,
731
+ "eval_samples_per_second": 9.365,
732
+ "eval_steps_per_second": 2.342,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.679086225195008e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null