prxy5608 commited on
Commit
54b6596
·
verified ·
1 Parent(s): be1889b

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 sha256:02cc92889a0d5b0b1bbb5d4b26d8304107251d22b8ac03babe44751c92dc8590
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ae7fb951efd40cadaa8d4e798d0cef3405d7a5673bfcb19a035d884c3dc6082
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6c93e26e1c3f091b0fdf4eba6be4735e0f86885c23b88f97be73666b13b0b0f
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77c3dde79ccc95908ca3a863b0d6964aa6670a111f700bc75a562beeb6714cce
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45e89011e8a7cc17c2d28dae9d6bc64de205f962706d84a3006b198d005046a9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3170e57bfd77a0c009b8af0846cfe2fcb3a26c6d685b057a397bd5371972bbfa
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": 1.8632498979568481,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.034638032559750606,
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": 13.171,
374
  "eval_steps_per_second": 3.294,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.54256789372928e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.6982988119125366,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.06927606511950121,
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": 13.171,
374
  "eval_steps_per_second": 3.294,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.03533079321094562,
379
+ "grad_norm": 1.2950654029846191,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.5298,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.03602355386214063,
386
+ "grad_norm": 1.2909640073776245,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.6083,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.036716314513335645,
393
+ "grad_norm": 0.9368382692337036,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.7538,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.03740907516453065,
400
+ "grad_norm": 0.7290942668914795,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.6392,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.03810183581572567,
407
+ "grad_norm": 0.6426312327384949,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.7225,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.038794596466920676,
414
+ "grad_norm": 0.5837317705154419,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.6282,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.03948735711811569,
421
+ "grad_norm": 0.5810585618019104,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.5666,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.0401801177693107,
428
+ "grad_norm": 0.5959537625312805,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.5718,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.040872878420505715,
435
+ "grad_norm": 0.6295363306999207,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.5756,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.04156563907170073,
442
+ "grad_norm": 0.6176732182502747,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.5888,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.04225839972289574,
449
+ "grad_norm": 0.5834788084030151,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.5,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.042951160374090754,
456
+ "grad_norm": 0.6111202239990234,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.4321,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.04364392102528576,
463
+ "grad_norm": 0.6033303737640381,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.4581,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.04433668167648078,
470
+ "grad_norm": 0.6345365643501282,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.4483,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.045029442327675785,
477
+ "grad_norm": 0.6359748244285583,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.5392,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.0457222029788708,
484
+ "grad_norm": 0.63890540599823,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.5423,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.046414963630065816,
491
+ "grad_norm": 0.6280885934829712,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.5097,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.047107724281260824,
498
+ "grad_norm": 0.6749413013458252,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.53,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.04780048493245584,
505
+ "grad_norm": 0.672849714756012,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.6531,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.04849324558365085,
512
+ "grad_norm": 0.655882716178894,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.4457,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.04918600623484586,
519
+ "grad_norm": 0.7098842859268188,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.5776,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.04987876688604087,
526
+ "grad_norm": 0.7302150726318359,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.6309,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.050571527537235886,
533
+ "grad_norm": 0.7837209105491638,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.6634,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.051264288188430894,
540
+ "grad_norm": 0.7368186712265015,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.5211,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.05195704883962591,
547
+ "grad_norm": 0.7818071246147156,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.4992,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.052649809490820924,
554
+ "grad_norm": 0.7995255589485168,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.6081,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.05334257014201593,
561
+ "grad_norm": 0.8555031418800354,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.5777,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.05403533079321095,
568
+ "grad_norm": 0.8953914046287537,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.6073,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.054728091444405956,
575
+ "grad_norm": 0.9667080640792847,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.7662,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.05542085209560097,
582
+ "grad_norm": 0.9754164814949036,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.7188,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.05611361274679598,
589
+ "grad_norm": 1.0194123983383179,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.6131,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.056806373397990995,
596
+ "grad_norm": 1.0185964107513428,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.6057,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.057499134049186,
603
+ "grad_norm": 1.0227956771850586,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.7111,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.05819189470038102,
610
+ "grad_norm": 1.1718602180480957,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.6701,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.05888465535157603,
617
+ "grad_norm": 1.2311724424362183,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.7365,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.05957741600277104,
624
+ "grad_norm": 1.255084753036499,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.7453,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.06027017665396606,
631
+ "grad_norm": 1.4649220705032349,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.7197,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.060962937305161065,
638
+ "grad_norm": 1.3487746715545654,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.687,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.06165569795635608,
645
+ "grad_norm": 1.438979148864746,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.7361,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.06234845860755109,
652
+ "grad_norm": 1.5143617391586304,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 1.7665,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.0630412192587461,
659
+ "grad_norm": 1.5927358865737915,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.8169,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.06373397990994112,
666
+ "grad_norm": 1.537095069885254,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 1.4944,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.06442674056113613,
673
+ "grad_norm": 1.8598449230194092,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.5148,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.06511950121233114,
680
+ "grad_norm": 2.0445775985717773,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.701,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.06581226186352615,
687
+ "grad_norm": 2.032562732696533,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.6913,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.06650502251472117,
694
+ "grad_norm": 2.152479648590088,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.8405,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.06719778316591618,
701
+ "grad_norm": 2.379943370819092,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.6487,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.06789054381711118,
708
+ "grad_norm": 2.6310393810272217,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.8972,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.0685833044683062,
715
+ "grad_norm": 2.870434522628784,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.8055,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.06927606511950121,
722
+ "grad_norm": 4.0857086181640625,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.7904,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.06927606511950121,
729
+ "eval_loss": 1.6982988119125366,
730
+ "eval_runtime": 184.5442,
731
+ "eval_samples_per_second": 13.173,
732
+ "eval_steps_per_second": 3.295,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.508513578745856e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null