auxyus commited on
Commit
a8c7ad0
·
verified ·
1 Parent(s): 2d3dc8e

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:c88362cfe50973d14e9c9cf971dba4d9f238bd2c8d4d4f48cd5917c81b19f673
3
  size 912336848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5ce9388ff5c0d016e84e5463befac62b67968957fff89127716a439a91513cd
3
  size 912336848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97a26c84d45812d78efe031ffabe77785f437ad0fe565afd9812d0af27f5825a
3
  size 463916180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:125c09852ff0efdf055c0b05d8491ab176667896b227314f13bcf828c1716814
3
  size 463916180
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de688329c46c6b609a55be32c0d60fda95d166295363c68e32bec4af3b0f287a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73802fadfe7a3f3281ac6f7349f29b843350a9fb51f5dee1bb39ff24037f453b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed340328d62f63f2d9d00f6904395875dd09851f050e03ae91b4b798d852ce41
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99ca67f9a35cd1c50df3d93bedf5a6642db2c7847c021a0a8d3f44c1bf4993d3
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.8847057223320007,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.03170577045022194,
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": 8.924,
374
  "eval_steps_per_second": 2.231,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.1662573078315008e+17,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8155827522277832,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.06341154090044387,
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": 8.924,
374
  "eval_steps_per_second": 2.231,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.032339885859226376,
379
+ "grad_norm": 3.129869222640991,
380
+ "learning_rate": 9.729774092143627e-05,
381
+ "loss": 3.7664,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.032974001268230815,
386
+ "grad_norm": 2.0350043773651123,
387
+ "learning_rate": 9.716559066288715e-05,
388
+ "loss": 3.6251,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.033608116677235254,
393
+ "grad_norm": 1.3122864961624146,
394
+ "learning_rate": 9.703037989675087e-05,
395
+ "loss": 3.5988,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.03424223208623969,
400
+ "grad_norm": 1.3547205924987793,
401
+ "learning_rate": 9.689211739666023e-05,
402
+ "loss": 3.4852,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.03487634749524413,
407
+ "grad_norm": 1.131834864616394,
408
+ "learning_rate": 9.675081213427076e-05,
409
+ "loss": 3.4682,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.03551046290424857,
414
+ "grad_norm": 1.118656039237976,
415
+ "learning_rate": 9.66064732786784e-05,
416
+ "loss": 3.4695,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.03614457831325301,
421
+ "grad_norm": 1.095979928970337,
422
+ "learning_rate": 9.645911019582467e-05,
423
+ "loss": 3.3906,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.03677869372225745,
428
+ "grad_norm": 1.330224633216858,
429
+ "learning_rate": 9.630873244788883e-05,
430
+ "loss": 3.5858,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.03741280913126189,
435
+ "grad_norm": 1.1612094640731812,
436
+ "learning_rate": 9.615534979266745e-05,
437
+ "loss": 3.5082,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.03804692454026633,
442
+ "grad_norm": 1.1439632177352905,
443
+ "learning_rate": 9.599897218294122e-05,
444
+ "loss": 3.4478,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.03868103994927077,
449
+ "grad_norm": 1.480470895767212,
450
+ "learning_rate": 9.583960976582913e-05,
451
+ "loss": 3.3747,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.039315155358275206,
456
+ "grad_norm": 1.1436293125152588,
457
+ "learning_rate": 9.567727288213005e-05,
458
+ "loss": 3.3507,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.039949270767279645,
463
+ "grad_norm": 1.1501903533935547,
464
+ "learning_rate": 9.551197206565173e-05,
465
+ "loss": 3.3903,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.040583386176284084,
470
+ "grad_norm": 1.1135419607162476,
471
+ "learning_rate": 9.534371804252728e-05,
472
+ "loss": 3.2974,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.04121750158528852,
477
+ "grad_norm": 1.1008535623550415,
478
+ "learning_rate": 9.517252173051911e-05,
479
+ "loss": 3.3343,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.04185161699429296,
484
+ "grad_norm": 1.1229270696640015,
485
+ "learning_rate": 9.49983942383106e-05,
486
+ "loss": 3.3202,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.0424857324032974,
491
+ "grad_norm": 1.129658579826355,
492
+ "learning_rate": 9.482134686478519e-05,
493
+ "loss": 3.4031,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.04311984781230184,
498
+ "grad_norm": 1.1309914588928223,
499
+ "learning_rate": 9.464139109829321e-05,
500
+ "loss": 3.3727,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.04375396322130628,
505
+ "grad_norm": 1.1195210218429565,
506
+ "learning_rate": 9.445853861590647e-05,
507
+ "loss": 3.3391,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.04438807863031072,
512
+ "grad_norm": 1.14125657081604,
513
+ "learning_rate": 9.42728012826605e-05,
514
+ "loss": 3.2907,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.04502219403931516,
519
+ "grad_norm": 1.1160163879394531,
520
+ "learning_rate": 9.408419115078471e-05,
521
+ "loss": 3.2616,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.045656309448319596,
526
+ "grad_norm": 1.1449788808822632,
527
+ "learning_rate": 9.389272045892024e-05,
528
+ "loss": 3.3349,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.046290424857324035,
533
+ "grad_norm": 1.096792221069336,
534
+ "learning_rate": 9.36984016313259e-05,
535
+ "loss": 3.2215,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.046924540266328474,
540
+ "grad_norm": 1.1410120725631714,
541
+ "learning_rate": 9.350124727707197e-05,
542
+ "loss": 3.3399,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.04755865567533291,
547
+ "grad_norm": 1.1690126657485962,
548
+ "learning_rate": 9.330127018922194e-05,
549
+ "loss": 3.354,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.04819277108433735,
554
+ "grad_norm": 1.2746645212173462,
555
+ "learning_rate": 9.309848334400246e-05,
556
+ "loss": 3.3572,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.04882688649334179,
561
+ "grad_norm": 1.1271394491195679,
562
+ "learning_rate": 9.289289989996133e-05,
563
+ "loss": 3.3658,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.04946100190234623,
568
+ "grad_norm": 1.2954553365707397,
569
+ "learning_rate": 9.268453319711363e-05,
570
+ "loss": 3.2274,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.05009511731135067,
575
+ "grad_norm": 1.1216834783554077,
576
+ "learning_rate": 9.247339675607605e-05,
577
+ "loss": 3.267,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.05072923272035511,
582
+ "grad_norm": 1.1674860715866089,
583
+ "learning_rate": 9.225950427718975e-05,
584
+ "loss": 3.3223,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.05136334812935954,
589
+ "grad_norm": 1.0981123447418213,
590
+ "learning_rate": 9.204286963963111e-05,
591
+ "loss": 3.1553,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.05199746353836398,
596
+ "grad_norm": 1.2098571062088013,
597
+ "learning_rate": 9.182350690051133e-05,
598
+ "loss": 3.287,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.05263157894736842,
603
+ "grad_norm": 1.128381371498108,
604
+ "learning_rate": 9.160143029396422e-05,
605
+ "loss": 3.26,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.05326569435637286,
610
+ "grad_norm": 1.2328784465789795,
611
+ "learning_rate": 9.13766542302225e-05,
612
+ "loss": 3.3351,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.053899809765377296,
617
+ "grad_norm": 1.1560747623443604,
618
+ "learning_rate": 9.114919329468282e-05,
619
+ "loss": 3.268,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.054533925174381735,
624
+ "grad_norm": 1.191244125366211,
625
+ "learning_rate": 9.091906224695935e-05,
626
+ "loss": 3.1744,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.055168040583386174,
631
+ "grad_norm": 1.1172856092453003,
632
+ "learning_rate": 9.068627601992598e-05,
633
+ "loss": 3.1647,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.05580215599239061,
638
+ "grad_norm": 1.1811506748199463,
639
+ "learning_rate": 9.045084971874738e-05,
640
+ "loss": 3.1507,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.05643627140139505,
645
+ "grad_norm": 1.2562776803970337,
646
+ "learning_rate": 9.021279861989885e-05,
647
+ "loss": 3.1243,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.05707038681039949,
652
+ "grad_norm": 1.2073371410369873,
653
+ "learning_rate": 8.997213817017507e-05,
654
+ "loss": 3.2071,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.05770450221940393,
659
+ "grad_norm": 1.179689884185791,
660
+ "learning_rate": 8.972888398568772e-05,
661
+ "loss": 3.1118,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.05833861762840837,
666
+ "grad_norm": 1.1589559316635132,
667
+ "learning_rate": 8.948305185085225e-05,
668
+ "loss": 3.0971,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.05897273303741281,
673
+ "grad_norm": 1.5334442853927612,
674
+ "learning_rate": 8.92346577173636e-05,
675
+ "loss": 2.9583,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.05960684844641725,
680
+ "grad_norm": 1.1919718980789185,
681
+ "learning_rate": 8.898371770316111e-05,
682
+ "loss": 2.9499,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.060240963855421686,
687
+ "grad_norm": 1.2710996866226196,
688
+ "learning_rate": 8.873024809138272e-05,
689
+ "loss": 3.0539,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.060875079264426125,
694
+ "grad_norm": 1.2094289064407349,
695
+ "learning_rate": 8.847426532930831e-05,
696
+ "loss": 2.9798,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.061509194673430564,
701
+ "grad_norm": 1.2845017910003662,
702
+ "learning_rate": 8.821578602729242e-05,
703
+ "loss": 2.7427,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.062143310082435003,
708
+ "grad_norm": 1.26568603515625,
709
+ "learning_rate": 8.795482695768658e-05,
710
+ "loss": 2.7497,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.06277742549143944,
715
+ "grad_norm": 1.4030022621154785,
716
+ "learning_rate": 8.769140505375085e-05,
717
+ "loss": 2.6945,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.06341154090044387,
722
+ "grad_norm": 1.5023269653320312,
723
+ "learning_rate": 8.742553740855506e-05,
724
+ "loss": 2.8778,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.06341154090044387,
729
+ "eval_loss": 0.8155827522277832,
730
+ "eval_runtime": 297.7632,
731
+ "eval_samples_per_second": 8.92,
732
+ "eval_steps_per_second": 2.23,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.3383168908263424e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null