aleegis09 commited on
Commit
6cfa40d
·
verified ·
1 Parent(s): 28b5e0a

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 sha256:38069e1ab3f08b64df0f137ce7e346bac1bbcc0cacc787b8a2324472224e69c8
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8217bd90ad64530b63e45e58d9a5be753fa5c034aba2961dd9eb8dcc634ffef7
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8d3afae8712a052582f82b48dfd974c3e3c4347afa8065f80a29f67ff5c5b39
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c050325b4fb179afba81060401aae2d9731faeb3832a8d17119861195e42f395
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:082f179c2e6b89921fe6a15182ba6488dea00ce6eb55735bd4287ec2227b26af
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27c71f7cc4e993e1000accc0cdc8c0b2d908df022408ffb802177bf3a05a23f1
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": 0.434339702129364,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.5586592178770949,
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": 20.004,
374
  "eval_steps_per_second": 5.034,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 2.422088103100416e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.35996368527412415,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.1173184357541899,
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": 20.004,
374
  "eval_steps_per_second": 5.034,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.5698324022346368,
379
+ "grad_norm": 0.6984612345695496,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.5736,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.5810055865921788,
386
+ "grad_norm": 0.76580810546875,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.4749,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.5921787709497207,
393
+ "grad_norm": 0.9494268894195557,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.6063,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.6033519553072626,
400
+ "grad_norm": 0.6763572692871094,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.3317,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.6145251396648045,
407
+ "grad_norm": 0.6486566662788391,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.3562,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.6256983240223464,
414
+ "grad_norm": 0.7950789928436279,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.2263,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.6368715083798883,
421
+ "grad_norm": 0.6552952527999878,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.3347,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.6480446927374302,
428
+ "grad_norm": 0.6345714926719666,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.2841,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.659217877094972,
435
+ "grad_norm": 0.6420994997024536,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.3026,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.6703910614525139,
442
+ "grad_norm": 0.7764968276023865,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.1627,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.6815642458100558,
449
+ "grad_norm": 0.5726867318153381,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.2436,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.6927374301675978,
456
+ "grad_norm": 0.5297699570655823,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.2084,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.7039106145251397,
463
+ "grad_norm": 0.4522324800491333,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.2346,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.7150837988826816,
470
+ "grad_norm": 0.5540947318077087,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.1747,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.7262569832402235,
477
+ "grad_norm": 0.48012828826904297,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.1713,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.7374301675977654,
484
+ "grad_norm": 0.5377119779586792,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.2226,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.7486033519553073,
491
+ "grad_norm": 2.5457634925842285,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.9298,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.7597765363128491,
498
+ "grad_norm": 0.6084294319152832,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.5864,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.770949720670391,
505
+ "grad_norm": 0.60562664270401,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.6605,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.7821229050279329,
512
+ "grad_norm": 0.5156601071357727,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.458,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.7932960893854749,
519
+ "grad_norm": 0.6329552531242371,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.5411,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.8044692737430168,
526
+ "grad_norm": 0.6346179246902466,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.5311,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.8156424581005587,
533
+ "grad_norm": 0.6511710286140442,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.6218,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.8268156424581006,
540
+ "grad_norm": 0.4940270781517029,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.4921,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.8379888268156425,
547
+ "grad_norm": 0.6882925033569336,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.6295,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.8491620111731844,
554
+ "grad_norm": 0.6235405802726746,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.457,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.8603351955307262,
561
+ "grad_norm": 0.6313698291778564,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.2338,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.8715083798882681,
568
+ "grad_norm": 0.7784355878829956,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.4064,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.88268156424581,
575
+ "grad_norm": 0.7756523489952087,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.2674,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.8938547486033519,
582
+ "grad_norm": 0.7363424897193909,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.4045,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.9050279329608939,
589
+ "grad_norm": 0.650582492351532,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.2804,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.9162011173184358,
596
+ "grad_norm": 0.7414998412132263,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.2908,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.9273743016759777,
603
+ "grad_norm": 0.5577226877212524,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.1618,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.9385474860335196,
610
+ "grad_norm": 0.43591392040252686,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.1398,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.9497206703910615,
617
+ "grad_norm": 0.3598768413066864,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.1208,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.9608938547486033,
624
+ "grad_norm": 0.39774054288864136,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.1733,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.9720670391061452,
631
+ "grad_norm": 0.4294886887073517,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.1291,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.9832402234636871,
638
+ "grad_norm": 0.43344977498054504,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.159,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.994413407821229,
645
+ "grad_norm": 0.5479728579521179,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.586,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 1.005586592178771,
652
+ "grad_norm": 1.402073860168457,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.8381,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 1.0167597765363128,
659
+ "grad_norm": 0.38112547993659973,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.517,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 1.0279329608938548,
666
+ "grad_norm": 0.47864004969596863,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.516,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.0391061452513966,
673
+ "grad_norm": 0.4763987958431244,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.4618,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.0502793296089385,
680
+ "grad_norm": 0.38241147994995117,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.3306,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.0614525139664805,
687
+ "grad_norm": 0.43910539150238037,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.3816,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.0726256983240223,
694
+ "grad_norm": 0.5805469751358032,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.4254,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.0837988826815643,
701
+ "grad_norm": 0.4538100063800812,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.3432,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.094972067039106,
708
+ "grad_norm": 0.44317829608917236,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.3423,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.106145251396648,
715
+ "grad_norm": 0.5460543036460876,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.3158,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.1173184357541899,
722
+ "grad_norm": 0.4699908196926117,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.335,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.1173184357541899,
729
+ "eval_loss": 0.35996368527412415,
730
+ "eval_runtime": 7.6399,
731
+ "eval_samples_per_second": 19.765,
732
+ "eval_steps_per_second": 4.974,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 4.82206444683264e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null