aleegis12 commited on
Commit
166cae6
·
verified ·
1 Parent(s): 2c3f631

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 sha256:17ed84326376e1be67adfd3eb2632a3840fbb0d99f21de26861b090570fc0a59
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c4a5c1521d39d34635ae30db4e560764e8e058f479d4c754579093eba81f527
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:932029294123b3b6412eca962b61c85b3602f0e22f5c7e46175ca0ae56a151a6
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2faad991f6674dadfd8d59d53a1574dd0569810754c7999007efad25bbd821a9
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d766aff8c762b0c90032fe4374d1ff300031a06960df55bd89fab5a46b18ff0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45c67205e9cf0d2da4f99674c5f23dc96e5e32a1cbbce1e9acf0a594b546ed8d
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": 0.7910234928131104,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.07222824124232576,
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": 8.843,
374
  "eval_steps_per_second": 2.215,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.1090247051902976e+17,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6084063053131104,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.1444564824846515,
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": 8.843,
374
  "eval_steps_per_second": 2.215,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.07367280606717226,
379
+ "grad_norm": 10.92339038848877,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 2.896,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.07511737089201878,
386
+ "grad_norm": 4.852169990539551,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 2.614,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0765619357168653,
393
+ "grad_norm": 3.439312219619751,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 2.4682,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.0780065005417118,
400
+ "grad_norm": 2.424557685852051,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 2.6748,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.07945106536655833,
407
+ "grad_norm": 2.1135504245758057,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 2.0125,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.08089563019140483,
414
+ "grad_norm": 2.3444604873657227,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 2.3545,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.08234019501625135,
421
+ "grad_norm": 2.220395088195801,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 2.3434,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.08378475984109787,
428
+ "grad_norm": 2.29278564453125,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 2.0731,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.08522932466594438,
435
+ "grad_norm": 2.278346061706543,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 2.4211,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.0866738894907909,
442
+ "grad_norm": 2.0982675552368164,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.7617,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.08811845431563742,
449
+ "grad_norm": 2.262214183807373,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 2.022,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.08956301914048392,
456
+ "grad_norm": 2.122612714767456,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 2.0926,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.09100758396533044,
463
+ "grad_norm": 2.29144287109375,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 2.093,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.09245214879017696,
470
+ "grad_norm": 2.253896474838257,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.9666,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.09389671361502347,
477
+ "grad_norm": 2.204949140548706,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 2.2943,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.09534127843986999,
484
+ "grad_norm": 2.1490232944488525,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.9285,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.09678584326471651,
491
+ "grad_norm": 2.109954833984375,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 2.161,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.09823040808956301,
498
+ "grad_norm": 2.0772545337677,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.787,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.09967497291440953,
505
+ "grad_norm": 2.3547136783599854,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 2.0184,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.10111953773925605,
512
+ "grad_norm": 2.1117351055145264,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.9861,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.10256410256410256,
519
+ "grad_norm": 2.4485626220703125,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 2.2225,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.10400866738894908,
526
+ "grad_norm": 2.093348503112793,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 2.0359,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.1054532322137956,
533
+ "grad_norm": 2.024015188217163,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.7762,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.1068977970386421,
540
+ "grad_norm": 2.1689019203186035,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.6212,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.10834236186348863,
547
+ "grad_norm": 2.0198400020599365,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.8681,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.10978692668833515,
554
+ "grad_norm": 2.089298725128174,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 2.1604,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.11123149151318165,
561
+ "grad_norm": 2.336698532104492,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 2.1222,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.11267605633802817,
568
+ "grad_norm": 2.329235076904297,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 2.0341,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.11412062116287468,
575
+ "grad_norm": 2.9682834148406982,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 2.196,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.1155651859877212,
582
+ "grad_norm": 2.6919736862182617,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 2.1352,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.11700975081256772,
589
+ "grad_norm": 2.4734435081481934,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.8077,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.11845431563741422,
596
+ "grad_norm": 2.6794533729553223,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 2.2776,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.11989888046226074,
603
+ "grad_norm": 2.8582587242126465,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 2.1036,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.12134344528710726,
610
+ "grad_norm": 3.296032190322876,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 2.4848,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.12278801011195377,
617
+ "grad_norm": 3.1677138805389404,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 2.4112,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.12423257493680029,
624
+ "grad_norm": 3.2526278495788574,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 2.4407,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.1256771397616468,
631
+ "grad_norm": 3.802973508834839,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 2.5273,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.12712170458649333,
638
+ "grad_norm": 3.6186423301696777,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 2.1346,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.12856626941133983,
645
+ "grad_norm": 4.2363200187683105,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 2.6065,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.13001083423618634,
652
+ "grad_norm": 4.081016540527344,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 2.6405,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.13145539906103287,
659
+ "grad_norm": 5.950720310211182,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 2.1082,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.13289996388587938,
666
+ "grad_norm": 4.650112152099609,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 2.6436,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.13434452871072589,
673
+ "grad_norm": 4.918834686279297,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 2.8926,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.13578909353557242,
680
+ "grad_norm": 5.376173973083496,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 2.0728,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.13723365836041893,
687
+ "grad_norm": 6.745965480804443,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 3.4414,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.13867822318526543,
694
+ "grad_norm": 10.788195610046387,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 2.6239,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.14012278801011196,
701
+ "grad_norm": 10.470982551574707,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 2.8976,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.14156735283495847,
708
+ "grad_norm": 10.752097129821777,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 2.6363,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.14301191765980498,
715
+ "grad_norm": 12.399551391601562,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 4.3399,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.1444564824846515,
722
+ "grad_norm": 20.386749267578125,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 6.0517,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.1444564824846515,
729
+ "eval_loss": 0.6084063053131104,
730
+ "eval_runtime": 131.5687,
731
+ "eval_samples_per_second": 8.862,
732
+ "eval_steps_per_second": 2.219,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.2001619151355904e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null