prxy5608 commited on
Commit
9047549
·
verified ·
1 Parent(s): 765e9fa

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:b9b31e4fb3a122c087751c2d41ec401cf63bebfb28360e1e6f8916af1b373cd9
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38d02d1ee0d4f11502c3709af77d01ebcb0b93981eea36f960ad037196c13e1b
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9589d24dfa450f4715896980ddf42faacc1b06e3860f69306a0eae2bea0a18e
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31a2fcd5bde721a716e5268bd51c98e46681afece65262bbf3049f14526b54a7
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51b016398685d2942cf46587387636aabc243004562c8b3cdfabb207d6ba3ef0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af2e58bb47b2e4e0001041dc3a8d1b12ebef229d5783d4a18e98a6b321b056d5
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": 1.5430727005004883,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.016874789065136685,
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": 33.926,
374
  "eval_steps_per_second": 8.485,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.367527271694336e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.5353269577026367,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.03374957813027337,
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": 33.926,
374
  "eval_steps_per_second": 8.485,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.01721228484643942,
379
+ "grad_norm": 1.4228336811065674,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.6601,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.017549780627742154,
386
+ "grad_norm": 1.322295069694519,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.2419,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.017887276409044885,
393
+ "grad_norm": 1.445678472518921,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.6227,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.01822477219034762,
400
+ "grad_norm": 1.3230798244476318,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.4315,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.018562267971650354,
407
+ "grad_norm": 1.3651715517044067,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.5568,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.01889976375295309,
414
+ "grad_norm": 1.269474983215332,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.5887,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.019237259534255823,
421
+ "grad_norm": 1.4516477584838867,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.4599,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.019574755315558554,
428
+ "grad_norm": 1.282692313194275,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.4515,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.01991225109686129,
435
+ "grad_norm": 1.5570868253707886,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.5617,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.020249746878164023,
442
+ "grad_norm": 1.2447081804275513,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.368,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.020587242659466758,
449
+ "grad_norm": 1.3168991804122925,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.4655,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.020924738440769492,
456
+ "grad_norm": 1.3223047256469727,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.5246,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.021262234222072223,
463
+ "grad_norm": 1.4290637969970703,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.6008,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.021599730003374958,
470
+ "grad_norm": 1.4363245964050293,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.5222,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.021937225784677692,
477
+ "grad_norm": 1.4145311117172241,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.3268,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.022274721565980427,
484
+ "grad_norm": 1.368954062461853,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.3751,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.022612217347283158,
491
+ "grad_norm": 1.4794690608978271,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.604,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.022949713128585892,
498
+ "grad_norm": 1.5086948871612549,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.4682,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.023287208909888626,
505
+ "grad_norm": 1.3436882495880127,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.5351,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.02362470469119136,
512
+ "grad_norm": 1.5566866397857666,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.6446,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.023962200472494095,
519
+ "grad_norm": 1.3160170316696167,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.3528,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.024299696253796826,
526
+ "grad_norm": 1.5016075372695923,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.4308,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.02463719203509956,
533
+ "grad_norm": 1.5386384725570679,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.5839,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.024974687816402295,
540
+ "grad_norm": 1.502233624458313,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.6412,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.02531218359770503,
547
+ "grad_norm": 1.5245769023895264,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.4053,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.02564967937900776,
554
+ "grad_norm": 1.3348147869110107,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.279,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.025987175160310495,
561
+ "grad_norm": 1.5596102476119995,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.6353,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.02632467094161323,
568
+ "grad_norm": 1.695809245109558,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.5378,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.026662166722915964,
575
+ "grad_norm": 1.4951751232147217,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.7345,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.0269996625042187,
582
+ "grad_norm": 1.2774806022644043,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.3024,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.02733715828552143,
589
+ "grad_norm": 1.4456425905227661,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.5536,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.027674654066824164,
596
+ "grad_norm": 1.423951506614685,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.5473,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.0280121498481269,
603
+ "grad_norm": 1.4260379076004028,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.5229,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.028349645629429633,
610
+ "grad_norm": 1.3661842346191406,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.4443,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.028687141410732364,
617
+ "grad_norm": 1.4436497688293457,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.5462,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.0290246371920351,
624
+ "grad_norm": 1.3736367225646973,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.4586,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.029362132973337833,
631
+ "grad_norm": 1.6109968423843384,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.6427,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.029699628754640568,
638
+ "grad_norm": 1.4181476831436157,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.4003,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.030037124535943302,
645
+ "grad_norm": 1.3104472160339355,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.4153,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.030374620317246033,
652
+ "grad_norm": 1.6174646615982056,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 1.5468,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.030712116098548767,
659
+ "grad_norm": 1.6859798431396484,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.5389,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.031049611879851502,
666
+ "grad_norm": 1.3607832193374634,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 1.2407,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.03138710766115423,
673
+ "grad_norm": 1.3353404998779297,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.3828,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.03172460344245697,
680
+ "grad_norm": 1.4945926666259766,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.5571,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.0320620992237597,
687
+ "grad_norm": 1.5455503463745117,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.5421,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.03239959500506244,
694
+ "grad_norm": 1.3872216939926147,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.5206,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.03273709078636517,
701
+ "grad_norm": 1.7368088960647583,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.7135,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.0330745865676679,
708
+ "grad_norm": 1.4623812437057495,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.437,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.03341208234897064,
715
+ "grad_norm": 1.4175429344177246,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.2106,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.03374957813027337,
722
+ "grad_norm": 2.094141960144043,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.578,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.03374957813027337,
729
+ "eval_loss": 1.5353269577026367,
730
+ "eval_runtime": 147.1368,
731
+ "eval_samples_per_second": 33.914,
732
+ "eval_steps_per_second": 8.482,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.728250925121536e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null