aleegis10 commited on
Commit
c590cc2
·
verified ·
1 Parent(s): ddb1f1d

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:a7de79720fec510344a8adc48968a1621f010d4989048d4e08a17acbc78ce826
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dc4e17a91f20c94446595346fb4432ca8b424fd117f4728327d8058784b561b
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:04420d66376a5b9437c3439d0ee9827baf4fde781edaf1e4f0165dfa88f8e9a8
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cfda97d5176677b6cd58b1a00d3b9ebb91e6515ab39f3f53a6e5857a067d221
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5390b4c40eb61751b3c929d485c766a4fa005fac02d9fb0a4fdc3cd9b4d88ad5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0372a767b1e9eb3858edd1a414bd1df06b0bad95b855bd2bf5be8f2cabd5f36
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": 1.5928395986557007,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.03240440699935191,
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": 7.06,
374
  "eval_steps_per_second": 1.766,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.3606865912148787e+17,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.419034719467163,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.06480881399870382,
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": 7.06,
374
  "eval_steps_per_second": 1.766,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.03305249513933895,
379
+ "grad_norm": 6.980609893798828,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 6.867,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.033700583279325985,
386
+ "grad_norm": 6.9170098304748535,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 6.5762,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.034348671419313026,
393
+ "grad_norm": 6.112064361572266,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 6.7365,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.03499675955930007,
400
+ "grad_norm": 6.1971635818481445,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 6.3913,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.0356448476992871,
407
+ "grad_norm": 6.6786017417907715,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 6.6206,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.03629293583927414,
414
+ "grad_norm": 6.822116374969482,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 6.2955,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.03694102397926118,
421
+ "grad_norm": 6.868690013885498,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 6.1542,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.037589112119248216,
428
+ "grad_norm": 7.442452907562256,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 6.2679,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.03823720025923526,
435
+ "grad_norm": 7.3351006507873535,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 5.8176,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.03888528839922229,
442
+ "grad_norm": 7.827886581420898,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 5.9771,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.03953337653920933,
449
+ "grad_norm": 7.912171363830566,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 5.7801,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.04018146467919637,
456
+ "grad_norm": 7.832915782928467,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 5.5801,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.04082955281918341,
463
+ "grad_norm": 8.083939552307129,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 6.0501,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.04147764095917045,
470
+ "grad_norm": 7.929896831512451,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 5.9395,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.04212572909915749,
477
+ "grad_norm": 7.770750045776367,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 5.2696,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.04277381723914452,
484
+ "grad_norm": 8.002516746520996,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 5.3783,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.04342190537913156,
491
+ "grad_norm": 8.261298179626465,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 5.5322,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.0440699935191186,
498
+ "grad_norm": 8.621538162231445,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 6.0108,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.04471808165910564,
505
+ "grad_norm": 8.629108428955078,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 5.5071,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.04536616979909268,
512
+ "grad_norm": 8.700213432312012,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 5.6949,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.04601425793907971,
519
+ "grad_norm": 8.888072967529297,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 5.2336,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.046662346079066754,
526
+ "grad_norm": 9.403554916381836,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 5.8668,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.047310434219053794,
533
+ "grad_norm": 9.120081901550293,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 6.0044,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.04795852235904083,
540
+ "grad_norm": 9.56356143951416,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 5.7729,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.04860661049902787,
547
+ "grad_norm": 9.18362045288086,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 5.7522,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.0492546986390149,
554
+ "grad_norm": 9.9910249710083,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 5.6483,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.049902786779001944,
561
+ "grad_norm": 11.102643966674805,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 5.4694,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.050550874918988985,
568
+ "grad_norm": 9.472458839416504,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 5.0966,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.05119896305897602,
575
+ "grad_norm": 9.36568832397461,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 5.2008,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.05184705119896306,
582
+ "grad_norm": 10.136297225952148,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 5.381,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.0524951393389501,
589
+ "grad_norm": 9.870697021484375,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 5.6316,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.053143227478937134,
596
+ "grad_norm": 8.686858177185059,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 5.0702,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.053791315618924175,
603
+ "grad_norm": 11.320849418640137,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 6.1287,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.05443940375891121,
610
+ "grad_norm": 10.530974388122559,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 5.5568,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.05508749189889825,
617
+ "grad_norm": 9.906576156616211,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 5.4907,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.05573558003888529,
624
+ "grad_norm": 11.5390625,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 5.6662,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.056383668178872325,
631
+ "grad_norm": 11.390203475952148,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 5.6948,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.057031756318859365,
638
+ "grad_norm": 14.094040870666504,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 6.0756,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.057679844458846406,
645
+ "grad_norm": 12.248970031738281,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 5.9675,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.05832793259883344,
652
+ "grad_norm": 11.868046760559082,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 5.9813,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.05897602073882048,
659
+ "grad_norm": 12.603425025939941,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 5.7393,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.059624108878807515,
666
+ "grad_norm": 13.412906646728516,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 6.1246,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.060272197018794556,
673
+ "grad_norm": 16.6093807220459,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 6.923,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.0609202851587816,
680
+ "grad_norm": 17.576526641845703,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 5.9134,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.06156837329876863,
687
+ "grad_norm": 11.265088081359863,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 4.6002,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.06221646143875567,
694
+ "grad_norm": 10.883245468139648,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 4.139,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.06286454957874271,
701
+ "grad_norm": 9.871200561523438,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 4.9324,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.06351263771872975,
708
+ "grad_norm": 7.893340110778809,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 4.3389,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.06416072585871678,
715
+ "grad_norm": 9.363809585571289,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 4.5932,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.06480881399870382,
722
+ "grad_norm": 9.364603042602539,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 4.3352,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.06480881399870382,
729
+ "eval_loss": 1.419034719467163,
730
+ "eval_runtime": 367.8135,
731
+ "eval_samples_per_second": 7.066,
732
+ "eval_steps_per_second": 1.767,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.717763934177198e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null