aleegis10 commited on
Commit
a1b4cb2
·
verified ·
1 Parent(s): e70d37e

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 sha256:5584b3941b52ce65aad3227ff3f4b5d142a5dcd3a4a625916ca450026c6e2ee8
3
  size 226532664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a7ac5ea0cacf50e4f59790fe749c94368b6dda310c4fbfd7662ae2eb93529b6
3
  size 226532664
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9d2a530151c5194c3de3e6553dc5f047d227454001e5e8343308bf4ef855a31
3
  size 115354708
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0963c4f2027598301c342f293bef3e8541605fd3893850f5acf51c197d5e6667
3
  size 115354708
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5677218bf9c0085e3469e424e3e7c9aa7b19f0b1cb1da66708ff5d4123268d08
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ab5b556f12e4dbafbce2d20f407a5507ad76d5f76cec076b68db7b4b2d5375f
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": 1.592988133430481,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.016454134101192924,
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": 47.033,
374
  "eval_steps_per_second": 11.763,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.3432688996253696e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.4470807313919067,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.03290826820238585,
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": 47.033,
374
  "eval_steps_per_second": 11.763,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.016783216783216783,
379
+ "grad_norm": 14.585724830627441,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 6.0914,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.017112299465240642,
386
+ "grad_norm": 12.33920669555664,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 5.8927,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0174413821472645,
393
+ "grad_norm": 8.384288787841797,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 5.7106,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.01777046482928836,
400
+ "grad_norm": 5.3903937339782715,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 5.7199,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.01809954751131222,
407
+ "grad_norm": 3.546074628829956,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 5.2362,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.018428630193336074,
414
+ "grad_norm": 2.585486888885498,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 5.4502,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.018757712875359933,
421
+ "grad_norm": 2.2425572872161865,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 5.1769,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.019086795557383792,
428
+ "grad_norm": 1.9347532987594604,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 5.1616,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.01941587823940765,
435
+ "grad_norm": 1.8669167757034302,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 5.3023,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.01974496092143151,
442
+ "grad_norm": 1.8059626817703247,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 5.2465,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.02007404360345537,
449
+ "grad_norm": 1.601872205734253,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 5.3677,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.020403126285479228,
456
+ "grad_norm": 1.5859284400939941,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 5.4263,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.020732208967503087,
463
+ "grad_norm": 1.4872530698776245,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 5.0603,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.021061291649526942,
470
+ "grad_norm": 1.5247877836227417,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 5.5638,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.0213903743315508,
477
+ "grad_norm": 1.6158437728881836,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 5.4161,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.02171945701357466,
484
+ "grad_norm": 1.5754039287567139,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 5.4194,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.02204853969559852,
491
+ "grad_norm": 1.5747605562210083,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 5.1095,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.022377622377622378,
498
+ "grad_norm": 1.6026984453201294,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 5.4065,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.022706705059646237,
505
+ "grad_norm": 1.6130657196044922,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 5.4167,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.023035787741670095,
512
+ "grad_norm": 1.6912821531295776,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 5.6519,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.023364870423693954,
519
+ "grad_norm": 1.742060899734497,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 5.8117,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.023693953105717813,
526
+ "grad_norm": 1.6967644691467285,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 5.4258,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.02402303578774167,
533
+ "grad_norm": 1.7872289419174194,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 5.6749,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.024352118469765528,
540
+ "grad_norm": 1.8935869932174683,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 5.6662,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.024681201151789386,
547
+ "grad_norm": 1.9136574268341064,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 5.2773,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.025010283833813245,
554
+ "grad_norm": 2.138458728790283,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 5.712,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.025339366515837104,
561
+ "grad_norm": 2.2096593379974365,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 5.6899,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.025668449197860963,
568
+ "grad_norm": 2.2397191524505615,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 5.6085,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.025997531879884822,
575
+ "grad_norm": 2.2335917949676514,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 5.5117,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.02632661456190868,
582
+ "grad_norm": 2.3367552757263184,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 5.7426,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.026655697243932536,
589
+ "grad_norm": 2.4400556087493896,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 6.1936,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.026984779925956395,
596
+ "grad_norm": 2.3639447689056396,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 5.5684,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.027313862607980254,
603
+ "grad_norm": 2.6021528244018555,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 6.0803,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.027642945290004113,
610
+ "grad_norm": 2.728454351425171,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 6.0576,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.027972027972027972,
617
+ "grad_norm": 2.7983932495117188,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 5.929,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.02830111065405183,
624
+ "grad_norm": 2.7756054401397705,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 6.0336,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.02863019333607569,
631
+ "grad_norm": 2.88670015335083,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 5.9091,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.02895927601809955,
638
+ "grad_norm": 3.0520219802856445,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 6.4724,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.029288358700123408,
645
+ "grad_norm": 3.214491367340088,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 6.3031,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.029617441382147263,
652
+ "grad_norm": 3.2701969146728516,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 6.4869,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.029946524064171122,
659
+ "grad_norm": 3.7406764030456543,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 6.277,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.03027560674619498,
666
+ "grad_norm": 4.176053524017334,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 6.7109,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.03060468942821884,
673
+ "grad_norm": 4.0273637771606445,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 6.8581,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.0309337721102427,
680
+ "grad_norm": 5.2661566734313965,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 7.2504,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.03126285479226656,
687
+ "grad_norm": 4.821865558624268,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 6.854,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.03159193747429041,
694
+ "grad_norm": 5.117144584655762,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 6.8295,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.031921020156314275,
701
+ "grad_norm": 4.751927375793457,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 7.0724,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.03225010283833813,
708
+ "grad_norm": 5.606512069702148,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 7.2144,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.03257918552036199,
715
+ "grad_norm": 6.709188938140869,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 7.9249,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.03290826820238585,
722
+ "grad_norm": 8.786857604980469,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 7.9591,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.03290826820238585,
729
+ "eval_loss": 1.4470807313919067,
730
+ "eval_runtime": 108.7233,
731
+ "eval_samples_per_second": 47.074,
732
+ "eval_steps_per_second": 11.773,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.674100124254208e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null