bbytxt commited on
Commit
3b43440
·
verified ·
1 Parent(s): 5b7abaa

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 sha256:2da46fd6be809701d61a26b03f142f3e968594ec44439edcdf354146968c1ca9
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:947cda0132d035abc630e030496e980676772d09eea30b13178ddb4234e7a8c1
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a701fa24aec6c02e28c8f4b5ccb3180395ce0f08f091b7723ae3d76864d5ee2
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc89178be38def250b612fc354c12ac5092e186d6d18d4c1a5eeb26a48560005
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08c4b7149ec358aeb5cd85c0812d9aaffc08ee8f26fdd7ada6bba3e4d8b854d9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fe416ab31f7fb740718cb7b6fb195baea1c90e6d1111d0e5ccc89106252052d
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": 1.9359604120254517,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.004724223455769458,
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": 30.698,
374
  "eval_steps_per_second": 7.675,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.483188782235648e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.7917085886001587,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.009448446911538916,
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": 30.698,
374
  "eval_steps_per_second": 7.675,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.004818707924884847,
379
+ "grad_norm": 3.9928219318389893,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 2.2698,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.004913192394000236,
386
+ "grad_norm": 2.3402740955352783,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 2.4355,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.005007676863115625,
393
+ "grad_norm": 1.7540591955184937,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 2.273,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.005102161332231014,
400
+ "grad_norm": 2.258511543273926,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 2.4268,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.005196645801346404,
407
+ "grad_norm": 1.5056934356689453,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.938,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.0052911302704617925,
414
+ "grad_norm": 1.229217290878296,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.7706,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.005385614739577182,
421
+ "grad_norm": 1.0093824863433838,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.7142,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.0054800992086925715,
428
+ "grad_norm": 1.0942527055740356,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.7846,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.00557458367780796,
435
+ "grad_norm": 0.9831579923629761,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.7108,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.0056690681469233496,
442
+ "grad_norm": 1.0122381448745728,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.8403,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.005763552616038739,
449
+ "grad_norm": 0.9493637084960938,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.7662,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.005858037085154128,
456
+ "grad_norm": 0.9440594911575317,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.6777,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.005952521554269517,
463
+ "grad_norm": 0.9995548129081726,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.7533,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.006047006023384906,
470
+ "grad_norm": 0.9642996191978455,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.7805,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.006141490492500295,
477
+ "grad_norm": 1.0062496662139893,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.7519,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.006235974961615685,
484
+ "grad_norm": 1.0581656694412231,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.7327,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.006330459430731073,
491
+ "grad_norm": 1.083849549293518,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.7668,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.006424943899846463,
498
+ "grad_norm": 0.9820895195007324,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.6484,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.006519428368961852,
505
+ "grad_norm": 1.1138657331466675,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.8989,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.006613912838077241,
512
+ "grad_norm": 1.0786190032958984,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.6859,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.00670839730719263,
519
+ "grad_norm": 1.0377622842788696,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.7283,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.006802881776308019,
526
+ "grad_norm": 1.203137755393982,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.8213,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.006897366245423408,
533
+ "grad_norm": 1.078721523284912,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.7945,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.006991850714538798,
540
+ "grad_norm": 1.117542028427124,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.7302,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.0070863351836541865,
547
+ "grad_norm": 1.2751412391662598,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.8452,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.007180819652769576,
554
+ "grad_norm": 1.122659683227539,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.7035,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.0072753041218849655,
561
+ "grad_norm": 1.195285677909851,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.7232,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.007369788591000354,
568
+ "grad_norm": 1.2533471584320068,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.7606,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.0074642730601157435,
575
+ "grad_norm": 1.1980570554733276,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.7599,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.007558757529231133,
582
+ "grad_norm": 1.2624444961547852,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.8498,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.007653241998346522,
589
+ "grad_norm": 1.2369712591171265,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.8208,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.007747726467461911,
596
+ "grad_norm": 1.256296992301941,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.7432,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.0078422109365773,
603
+ "grad_norm": 1.2641733884811401,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.6733,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.00793669540569269,
610
+ "grad_norm": 1.5003657341003418,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.7468,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.008031179874808078,
617
+ "grad_norm": 1.4441968202590942,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.9026,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.008125664343923467,
624
+ "grad_norm": 1.3647269010543823,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.7824,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.008220148813038857,
631
+ "grad_norm": 1.4593603610992432,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.7798,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.008314633282154246,
638
+ "grad_norm": 1.6032061576843262,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.8624,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.008409117751269636,
645
+ "grad_norm": 1.4728277921676636,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.7756,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.008503602220385023,
652
+ "grad_norm": 1.5030272006988525,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 1.9159,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.008598086689500413,
659
+ "grad_norm": 1.6059142351150513,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.836,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.008692571158615802,
666
+ "grad_norm": 1.453993320465088,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 1.7456,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.008787055627731192,
673
+ "grad_norm": 1.4265638589859009,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.8045,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.008881540096846581,
680
+ "grad_norm": 1.5469270944595337,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.9141,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.00897602456596197,
687
+ "grad_norm": 1.7251414060592651,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.7264,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.009070509035077359,
694
+ "grad_norm": 1.5912647247314453,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.8451,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.009164993504192748,
701
+ "grad_norm": 1.6220170259475708,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.9897,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.009259477973308138,
708
+ "grad_norm": 1.5250394344329834,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.836,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.009353962442423527,
715
+ "grad_norm": 1.9486126899719238,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.8885,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.009448446911538916,
722
+ "grad_norm": 1.716341495513916,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.9319,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.009448446911538916,
729
+ "eval_loss": 1.7917085886001587,
730
+ "eval_runtime": 580.1092,
731
+ "eval_samples_per_second": 30.729,
732
+ "eval_steps_per_second": 7.683,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.986788419272704e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null