prxy5608 commited on
Commit
7b0bebc
·
verified ·
1 Parent(s): 585906a

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 sha256:9263f905aee60f5759727e73b8a4f1449317e9c3cbfb5f1a027c8cb228a76697
3
  size 191968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:864af0cc3ce39c8ddf96fb0943cfcb694123fc73c223b009c56e1b9516c05d24
3
  size 191968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de9c0b52465edb1e47d58a5efee60d8db8e44de76c7050429250f7b06bb90a1f
3
  size 253144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5843e9c3965b9c400f8cdff7a29eca288c1f3812e31f7cc55b243d75d4295414
3
  size 253144
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0522fdefe11b361029646c2d3b81b12e6d0744445d30d32a48866528cb2e36aa
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3fd520aa016ab6b2b4fb3d5f77690bcead8650f76330a74ec630e62e2557831
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c6c50c60a9a1ef382203c28d1d15b60f1719ddd22e6d4ee28a34e0e02c2e4cc
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:058219947ff711529dad66039b98666e7f25c784536319d0c623dbf17121adfa
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 10.310466766357422,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.9569377990430622,
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": 428.635,
374
  "eval_steps_per_second": 107.159,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 5577533030400.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.300241470336914,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.9138755980861244,
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": 428.635,
374
  "eval_steps_per_second": 107.159,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.9760765550239234,
379
+ "grad_norm": 0.08856772631406784,
380
+ "learning_rate": 8.200274834669675e-05,
381
+ "loss": 10.3106,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.9952153110047847,
386
+ "grad_norm": 0.09694826602935791,
387
+ "learning_rate": 8.117449009293668e-05,
388
+ "loss": 10.3171,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 1.014354066985646,
393
+ "grad_norm": 0.15517449378967285,
394
+ "learning_rate": 8.033199387471277e-05,
395
+ "loss": 18.3693,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 1.0334928229665072,
400
+ "grad_norm": 0.0667949989438057,
401
+ "learning_rate": 7.9475644475583e-05,
402
+ "loss": 10.0332,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 1.0526315789473684,
407
+ "grad_norm": 0.0705876350402832,
408
+ "learning_rate": 7.860583300610849e-05,
409
+ "loss": 10.3075,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 1.0717703349282297,
414
+ "grad_norm": 0.08071315288543701,
415
+ "learning_rate": 7.772295672522615e-05,
416
+ "loss": 10.3503,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 1.0909090909090908,
421
+ "grad_norm": 0.060574401170015335,
422
+ "learning_rate": 7.682741885881315e-05,
423
+ "loss": 10.2436,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 1.1100478468899522,
428
+ "grad_norm": 0.06491580605506897,
429
+ "learning_rate": 7.591962841552627e-05,
430
+ "loss": 10.377,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 1.1291866028708135,
435
+ "grad_norm": 0.08106613159179688,
436
+ "learning_rate": 7.500000000000001e-05,
437
+ "loss": 10.2996,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 1.1483253588516746,
442
+ "grad_norm": 0.08917899429798126,
443
+ "learning_rate": 7.406895362348916e-05,
444
+ "loss": 10.2626,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 1.167464114832536,
449
+ "grad_norm": 0.10297100991010666,
450
+ "learning_rate": 7.312691451204178e-05,
451
+ "loss": 10.3349,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 1.186602870813397,
456
+ "grad_norm": 0.07042112201452255,
457
+ "learning_rate": 7.217431291229067e-05,
458
+ "loss": 10.3964,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 1.2057416267942584,
463
+ "grad_norm": 0.07486451417207718,
464
+ "learning_rate": 7.121158389495186e-05,
465
+ "loss": 10.1931,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 1.2248803827751196,
470
+ "grad_norm": 0.09859184175729752,
471
+ "learning_rate": 7.023916715611969e-05,
472
+ "loss": 10.3828,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 1.244019138755981,
477
+ "grad_norm": 0.07667276263237,
478
+ "learning_rate": 6.925750681644953e-05,
479
+ "loss": 10.7305,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 1.263157894736842,
484
+ "grad_norm": 0.07506383955478668,
485
+ "learning_rate": 6.826705121831976e-05,
486
+ "loss": 10.1215,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 1.2822966507177034,
491
+ "grad_norm": 0.06321374326944351,
492
+ "learning_rate": 6.726825272106538e-05,
493
+ "loss": 10.0464,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 1.3014354066985647,
498
+ "grad_norm": 0.07606147229671478,
499
+ "learning_rate": 6.626156749437736e-05,
500
+ "loss": 10.3409,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 1.3205741626794258,
505
+ "grad_norm": 0.08716686069965363,
506
+ "learning_rate": 6.524745530996137e-05,
507
+ "loss": 10.3083,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 1.339712918660287,
512
+ "grad_norm": 0.07832231372594833,
513
+ "learning_rate": 6.422637933155162e-05,
514
+ "loss": 10.2791,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 1.3588516746411483,
519
+ "grad_norm": 0.09248408675193787,
520
+ "learning_rate": 6.319880590337549e-05,
521
+ "loss": 10.3614,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 1.3779904306220097,
526
+ "grad_norm": 0.08951514214277267,
527
+ "learning_rate": 6.216520433716545e-05,
528
+ "loss": 10.2633,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 1.3971291866028708,
533
+ "grad_norm": 0.08380934596061707,
534
+ "learning_rate": 6.112604669781572e-05,
535
+ "loss": 10.2203,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 1.4162679425837321,
540
+ "grad_norm": 0.08385058492422104,
541
+ "learning_rate": 6.008180758778167e-05,
542
+ "loss": 10.4143,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 1.4354066985645932,
547
+ "grad_norm": 0.07687491178512573,
548
+ "learning_rate": 5.903296393031995e-05,
549
+ "loss": 10.2941,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 1.4545454545454546,
554
+ "grad_norm": 0.07478059083223343,
555
+ "learning_rate": 5.7979994751668964e-05,
556
+ "loss": 10.2666,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 1.4736842105263157,
561
+ "grad_norm": 0.10892575234174728,
562
+ "learning_rate": 5.69233809622687e-05,
563
+ "loss": 10.3199,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 1.492822966507177,
568
+ "grad_norm": 0.09505303204059601,
569
+ "learning_rate": 5.58636051371201e-05,
570
+ "loss": 10.6274,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 1.5119617224880382,
575
+ "grad_norm": 0.09463223069906235,
576
+ "learning_rate": 5.480115129538409e-05,
577
+ "loss": 10.2876,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 1.5311004784688995,
582
+ "grad_norm": 0.08493571728467941,
583
+ "learning_rate": 5.373650467932122e-05,
584
+ "loss": 9.994,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 1.5502392344497609,
589
+ "grad_norm": 0.093894362449646,
590
+ "learning_rate": 5.267015153267245e-05,
591
+ "loss": 10.3278,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 1.569377990430622,
596
+ "grad_norm": 0.10776396840810776,
597
+ "learning_rate": 5.1602578878582776e-05,
598
+ "loss": 10.2704,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 1.588516746411483,
603
+ "grad_norm": 0.10382504016160965,
604
+ "learning_rate": 5.053427429716867e-05,
605
+ "loss": 10.2904,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 1.6076555023923444,
610
+ "grad_norm": 0.1062113493680954,
611
+ "learning_rate": 4.9465725702831346e-05,
612
+ "loss": 10.3657,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 1.6267942583732058,
617
+ "grad_norm": 0.12500600516796112,
618
+ "learning_rate": 4.839742112141724e-05,
619
+ "loss": 10.323,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 1.6459330143540671,
624
+ "grad_norm": 0.12947624921798706,
625
+ "learning_rate": 4.732984846732755e-05,
626
+ "loss": 10.2952,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 1.6650717703349283,
631
+ "grad_norm": 0.10035474598407745,
632
+ "learning_rate": 4.626349532067879e-05,
633
+ "loss": 10.2569,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 1.6842105263157894,
638
+ "grad_norm": 0.10493069142103195,
639
+ "learning_rate": 4.5198848704615914e-05,
640
+ "loss": 10.3804,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 1.7033492822966507,
645
+ "grad_norm": 0.09970294684171677,
646
+ "learning_rate": 4.4136394862879914e-05,
647
+ "loss": 10.2641,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 1.722488038277512,
652
+ "grad_norm": 0.1537674069404602,
653
+ "learning_rate": 4.307661903773129e-05,
654
+ "loss": 10.3269,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 1.7416267942583732,
659
+ "grad_norm": 0.1353168934583664,
660
+ "learning_rate": 4.2020005248331054e-05,
661
+ "loss": 10.7181,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 1.7607655502392343,
666
+ "grad_norm": 0.10454723984003067,
667
+ "learning_rate": 4.096703606968006e-05,
668
+ "loss": 10.1224,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.7799043062200957,
673
+ "grad_norm": 0.10816597938537598,
674
+ "learning_rate": 3.991819241221835e-05,
675
+ "loss": 10.0276,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.799043062200957,
680
+ "grad_norm": 0.12994703650474548,
681
+ "learning_rate": 3.887395330218429e-05,
682
+ "loss": 10.3349,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.8181818181818183,
687
+ "grad_norm": 0.1489221602678299,
688
+ "learning_rate": 3.783479566283457e-05,
689
+ "loss": 10.2663,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.8373205741626795,
694
+ "grad_norm": 0.11641079187393188,
695
+ "learning_rate": 3.680119409662452e-05,
696
+ "loss": 10.2685,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.8564593301435406,
701
+ "grad_norm": 0.13673876225948334,
702
+ "learning_rate": 3.5773620668448384e-05,
703
+ "loss": 10.3558,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.875598086124402,
708
+ "grad_norm": 0.1347990185022354,
709
+ "learning_rate": 3.4752544690038647e-05,
710
+ "loss": 10.2981,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.8947368421052633,
715
+ "grad_norm": 0.11974027007818222,
716
+ "learning_rate": 3.373843250562265e-05,
717
+ "loss": 10.2657,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.9138755980861244,
722
+ "grad_norm": 0.11552689224481583,
723
+ "learning_rate": 3.273174727893463e-05,
724
+ "loss": 10.3134,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.9138755980861244,
729
+ "eval_loss": 10.300241470336914,
730
+ "eval_runtime": 0.2059,
731
+ "eval_samples_per_second": 427.459,
732
+ "eval_steps_per_second": 106.865,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 11155066060800.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null