nttx commited on
Commit
83d872d
·
verified ·
1 Parent(s): 7ca593d

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 sha256:92bbbb464618ef61eff30a74094c5b0187060467c33730d1eb9f682936b48aa0
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78e6ee315515d3f08e7fb84e031046ab3744dbe31c3ef3d56f9186e9d781218e
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86f5211c344017d151b3bacfbcc711c88927e7b026113cf9832355f1f79f806a
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f759dec904b10ef2126661c04ae68cfccd564f7ec72a1b7aa7cc3ab193d9b2aa
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:deea3f83111ad92bcef41b7dfdafdbf9003b0760ee945cdbc865ffc946983126
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f758d49082f29034e842a5b4a00c22b8664390bfaf712dac140f69dc1425f80
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d689b2d605789fff660b4cfbb1ce6889a5251953118f474a71b33d74e2d19be7
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c4a11c3ec7ace2e963dc6e2b0b5b6372cc0250cefb36d5f7289475908638cb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.34164541959762573,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.06424670735624799,
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": 12.43,
374
  "eval_steps_per_second": 1.555,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -396,12 +754,12 @@
396
  "should_evaluate": false,
397
  "should_log": false,
398
  "should_save": true,
399
- "should_training_stop": false
400
  },
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.65570641213522e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.32453402876853943,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.12849341471249598,
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": 12.43,
374
  "eval_steps_per_second": 1.555,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.06553164150337296,
379
+ "grad_norm": 0.26072192192077637,
380
+ "learning_rate": 3.969463130731183e-06,
381
+ "loss": 0.1646,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.06681657565049791,
386
+ "grad_norm": 0.3280903398990631,
387
+ "learning_rate": 3.8772424536302565e-06,
388
+ "loss": 0.2271,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.06810150979762288,
393
+ "grad_norm": 0.34677988290786743,
394
+ "learning_rate": 3.782248193514766e-06,
395
+ "loss": 0.2508,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.06938644394474783,
400
+ "grad_norm": 0.4058302044868469,
401
+ "learning_rate": 3.684671656182497e-06,
402
+ "loss": 0.2262,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.0706713780918728,
407
+ "grad_norm": 0.38339221477508545,
408
+ "learning_rate": 3.5847093477938955e-06,
409
+ "loss": 0.2467,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.07195631223899775,
414
+ "grad_norm": 0.4589427411556244,
415
+ "learning_rate": 3.4825625791348093e-06,
416
+ "loss": 0.2348,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.07324124638612271,
421
+ "grad_norm": 0.5955134034156799,
422
+ "learning_rate": 3.3784370602033572e-06,
423
+ "loss": 0.3195,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.07452618053324767,
428
+ "grad_norm": 0.492436021566391,
429
+ "learning_rate": 3.272542485937369e-06,
430
+ "loss": 0.2931,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.07581111468037263,
435
+ "grad_norm": 0.5189871191978455,
436
+ "learning_rate": 3.165092113916688e-06,
437
+ "loss": 0.273,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.07709604882749758,
442
+ "grad_norm": 0.5466316938400269,
443
+ "learning_rate": 3.056302334890786e-06,
444
+ "loss": 0.3282,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.07838098297462255,
449
+ "grad_norm": 0.6036167144775391,
450
+ "learning_rate": 2.946392236996592e-06,
451
+ "loss": 0.2782,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.0796659171217475,
456
+ "grad_norm": 0.600953221321106,
457
+ "learning_rate": 2.835583164544139e-06,
458
+ "loss": 0.2846,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.08095085126887247,
463
+ "grad_norm": 0.6118208765983582,
464
+ "learning_rate": 2.724098272258584e-06,
465
+ "loss": 0.298,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.08223578541599744,
470
+ "grad_norm": 0.5902886986732483,
471
+ "learning_rate": 2.6121620758762877e-06,
472
+ "loss": 0.3588,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.08352071956312239,
477
+ "grad_norm": 0.5028055906295776,
478
+ "learning_rate": 2.5e-06,
479
+ "loss": 0.2523,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.08480565371024736,
484
+ "grad_norm": 0.6613095998764038,
485
+ "learning_rate": 2.3878379241237136e-06,
486
+ "loss": 0.2476,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.08609058785737231,
491
+ "grad_norm": 0.5534865260124207,
492
+ "learning_rate": 2.2759017277414165e-06,
493
+ "loss": 0.2462,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.08737552200449727,
498
+ "grad_norm": 0.7256202697753906,
499
+ "learning_rate": 2.1644168354558623e-06,
500
+ "loss": 0.3748,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.08866045615162223,
505
+ "grad_norm": 0.7539519667625427,
506
+ "learning_rate": 2.053607763003409e-06,
507
+ "loss": 0.3342,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.0899453902987472,
512
+ "grad_norm": 0.6876543760299683,
513
+ "learning_rate": 1.9436976651092143e-06,
514
+ "loss": 0.2865,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.09123032444587215,
519
+ "grad_norm": 0.7085744738578796,
520
+ "learning_rate": 1.8349078860833125e-06,
521
+ "loss": 0.2928,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.09251525859299711,
526
+ "grad_norm": 0.6572118997573853,
527
+ "learning_rate": 1.7274575140626318e-06,
528
+ "loss": 0.2248,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.09380019274012207,
533
+ "grad_norm": 0.6709907054901123,
534
+ "learning_rate": 1.6215629397966432e-06,
535
+ "loss": 0.3372,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.09508512688724703,
540
+ "grad_norm": 0.7788072824478149,
541
+ "learning_rate": 1.5174374208651913e-06,
542
+ "loss": 0.3332,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.09637006103437198,
547
+ "grad_norm": 0.7085012793540955,
548
+ "learning_rate": 1.415290652206105e-06,
549
+ "loss": 0.2757,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.09765499518149695,
554
+ "grad_norm": 0.8017731308937073,
555
+ "learning_rate": 1.3153283438175036e-06,
556
+ "loss": 0.3319,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.0989399293286219,
561
+ "grad_norm": 0.7940526604652405,
562
+ "learning_rate": 1.217751806485235e-06,
563
+ "loss": 0.3149,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.10022486347574687,
568
+ "grad_norm": 0.8877953290939331,
569
+ "learning_rate": 1.122757546369744e-06,
570
+ "loss": 0.3214,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.10150979762287182,
575
+ "grad_norm": 0.9085245728492737,
576
+ "learning_rate": 1.0305368692688175e-06,
577
+ "loss": 0.3384,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.10279473176999679,
582
+ "grad_norm": 0.7721331715583801,
583
+ "learning_rate": 9.412754953531664e-07,
584
+ "loss": 0.263,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.10407966591712174,
589
+ "grad_norm": 1.0416125059127808,
590
+ "learning_rate": 8.551531851507186e-07,
591
+ "loss": 0.4007,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.10536460006424671,
596
+ "grad_norm": 0.8873374462127686,
597
+ "learning_rate": 7.723433775328385e-07,
598
+ "loss": 0.3045,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.10664953421137166,
603
+ "grad_norm": 0.8218931555747986,
604
+ "learning_rate": 6.930128404315214e-07,
605
+ "loss": 0.2967,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.10793446835849663,
610
+ "grad_norm": 0.9357181191444397,
611
+ "learning_rate": 6.17321334990973e-07,
612
+ "loss": 0.3382,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.1092194025056216,
617
+ "grad_norm": 1.129144549369812,
618
+ "learning_rate": 5.454212938299256e-07,
619
+ "loss": 0.3723,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.11050433665274655,
624
+ "grad_norm": 0.9294447302818298,
625
+ "learning_rate": 4.774575140626317e-07,
626
+ "loss": 0.3518,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.11178927079987151,
631
+ "grad_norm": 1.224295735359192,
632
+ "learning_rate": 4.1356686569674344e-07,
633
+ "loss": 0.4988,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.11307420494699646,
638
+ "grad_norm": 1.0254179239273071,
639
+ "learning_rate": 3.538780159953348e-07,
640
+ "loss": 0.3184,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.11435913909412143,
645
+ "grad_norm": 1.141256332397461,
646
+ "learning_rate": 2.98511170358155e-07,
647
+ "loss": 0.3678,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.11564407324124638,
652
+ "grad_norm": 1.2963924407958984,
653
+ "learning_rate": 2.4757783024395244e-07,
654
+ "loss": 0.432,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.11692900738837135,
659
+ "grad_norm": 1.0066637992858887,
660
+ "learning_rate": 2.0118056862137358e-07,
661
+ "loss": 0.3393,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.1182139415354963,
666
+ "grad_norm": 1.2111726999282837,
667
+ "learning_rate": 1.59412823400657e-07,
668
+ "loss": 0.4263,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.11949887568262127,
673
+ "grad_norm": 1.2096489667892456,
674
+ "learning_rate": 1.223587092621162e-07,
675
+ "loss": 0.3961,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.12078380982974622,
680
+ "grad_norm": 1.258070468902588,
681
+ "learning_rate": 9.00928482603669e-08,
682
+ "loss": 0.4429,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.12206874397687119,
687
+ "grad_norm": 1.3796954154968262,
688
+ "learning_rate": 6.268021954544095e-08,
689
+ "loss": 0.3849,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.12335367812399614,
694
+ "grad_norm": 1.115661382675171,
695
+ "learning_rate": 4.017602850342584e-08,
696
+ "loss": 0.2734,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.12463861227112111,
701
+ "grad_norm": 1.1489228010177612,
702
+ "learning_rate": 2.262559558016325e-08,
703
+ "loss": 0.3193,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.12592354641824607,
708
+ "grad_norm": 1.5417214632034302,
709
+ "learning_rate": 1.006426501190233e-08,
710
+ "loss": 0.4079,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.127208480565371,
715
+ "grad_norm": 1.401361346244812,
716
+ "learning_rate": 2.5173336467135266e-09,
717
+ "loss": 0.3922,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.12849341471249598,
722
+ "grad_norm": 2.738529920578003,
723
+ "learning_rate": 0.0,
724
+ "loss": 0.7924,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.12849341471249598,
729
+ "eval_loss": 0.32453402876853943,
730
+ "eval_runtime": 105.3757,
731
+ "eval_samples_per_second": 12.441,
732
+ "eval_steps_per_second": 1.556,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
754
  "should_evaluate": false,
755
  "should_log": false,
756
  "should_save": true,
757
+ "should_training_stop": true
758
  },
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.5273699984801792e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null