0x1202 commited on
Commit
3096acc
·
verified ·
1 Parent(s): 6495462

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 sha256:4d977a339dee2660bf84014b5b3fc6e94bdf3728eadd50bfd472886dbdc53751
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31669a547c7a941de29559d277c00367d200f8a02b4c662253f3571061ae4f45
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0978912d1bd881210781f1eab7c2dea9029a8106a833f6996ba6eb807282b9af
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd92d37d67dbba7bb054a2c7a5990fe8534d3b2c82cbbb1eedf6c6a49898ae87
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7027686a4f26db0452e23690e3dafd86ade7303e3fdeac7a2742ace60d4b0be
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a2a5ea1701faa7475cce244ca0fdad63dc772d46d394d62ce1592a1afb6849e
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": 0.6091567277908325,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.007406035919274209,
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": 57.152,
374
  "eval_steps_per_second": 14.289,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3883562421977088.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5101078748703003,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.014812071838548418,
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": 57.152,
374
  "eval_steps_per_second": 14.289,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.007554156637659693,
379
+ "grad_norm": 1.5589680671691895,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.1799,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.007702277356045176,
386
+ "grad_norm": 0.3515014052391052,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.0933,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.007850398074430661,
393
+ "grad_norm": 0.45875218510627747,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.1784,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.007998518792816146,
400
+ "grad_norm": 0.6269052624702454,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.2778,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.008146639511201629,
407
+ "grad_norm": 1.1689852476119995,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.4904,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.008294760229587113,
414
+ "grad_norm": 0.8358094692230225,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.3861,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.008442880947972598,
421
+ "grad_norm": 0.7253592014312744,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.3949,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.008591001666358082,
428
+ "grad_norm": 0.5812123417854309,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.3646,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.008739122384743565,
435
+ "grad_norm": 0.4843596816062927,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.2807,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.00888724310312905,
442
+ "grad_norm": 0.740838348865509,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.33,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.009035363821514535,
449
+ "grad_norm": 0.6797621846199036,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.3849,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.00918348453990002,
456
+ "grad_norm": 0.8141345977783203,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.5828,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.009331605258285502,
463
+ "grad_norm": 0.8279635310173035,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.4488,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.009479725976670987,
470
+ "grad_norm": 0.7811763882637024,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.5753,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.009627846695056471,
477
+ "grad_norm": 0.8266785144805908,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.5867,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.009775967413441956,
484
+ "grad_norm": 0.9202486276626587,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.6306,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.009924088131827439,
491
+ "grad_norm": 0.8798254728317261,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.5484,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.010072208850212924,
498
+ "grad_norm": 0.9810667634010315,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.629,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.010220329568598408,
505
+ "grad_norm": 0.9303103685379028,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.6537,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.010368450286983891,
512
+ "grad_norm": 1.0939483642578125,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.6746,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.010516571005369376,
519
+ "grad_norm": 1.0398846864700317,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.6258,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.01066469172375486,
526
+ "grad_norm": 1.010213851928711,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.5371,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.010812812442140345,
533
+ "grad_norm": 0.9675101041793823,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.5268,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.010960933160525828,
540
+ "grad_norm": 1.2306679487228394,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.7031,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.011109053878911312,
547
+ "grad_norm": 1.0080821514129639,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.5835,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.011257174597296797,
554
+ "grad_norm": 0.9551141262054443,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.5755,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.011405295315682282,
561
+ "grad_norm": 0.9900866746902466,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.5303,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.011553416034067765,
568
+ "grad_norm": 1.0662058591842651,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.5197,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.01170153675245325,
575
+ "grad_norm": 0.9889392852783203,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.499,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.011849657470838734,
582
+ "grad_norm": 1.0202381610870361,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.5596,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.011997778189224219,
589
+ "grad_norm": 1.0612425804138184,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.5745,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.012145898907609701,
596
+ "grad_norm": 0.996573805809021,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.4494,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.012294019625995186,
603
+ "grad_norm": 1.028623342514038,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.5359,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.01244214034438067,
610
+ "grad_norm": 0.9804308414459229,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.4899,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.012590261062766155,
617
+ "grad_norm": 1.0140541791915894,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.4538,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.012738381781151638,
624
+ "grad_norm": 1.1482181549072266,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.4932,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.012886502499537123,
631
+ "grad_norm": 1.0970213413238525,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.5062,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.013034623217922607,
638
+ "grad_norm": 1.2930101156234741,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.5562,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.01318274393630809,
645
+ "grad_norm": 1.2993074655532837,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.6827,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.013330864654693575,
652
+ "grad_norm": 1.2092087268829346,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.5543,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.01347898537307906,
659
+ "grad_norm": 1.3151931762695312,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.6098,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.013627106091464544,
666
+ "grad_norm": 1.3638769388198853,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.5903,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.013775226809850027,
673
+ "grad_norm": 1.42976975440979,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.5858,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.013923347528235512,
680
+ "grad_norm": 1.5196677446365356,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.5238,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.014071468246620996,
687
+ "grad_norm": 1.5567885637283325,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.5884,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.014219588965006481,
694
+ "grad_norm": 1.482249140739441,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.5593,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.014367709683391964,
701
+ "grad_norm": 1.4134503602981567,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.4576,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.014515830401777449,
708
+ "grad_norm": 1.6437745094299316,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.5049,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.014663951120162933,
715
+ "grad_norm": 2.009922981262207,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.5317,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.014812071838548418,
722
+ "grad_norm": 2.5810420513153076,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.6961,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.014812071838548418,
729
+ "eval_loss": 0.5101078748703003,
730
+ "eval_runtime": 199.0632,
731
+ "eval_samples_per_second": 57.123,
732
+ "eval_steps_per_second": 14.282,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 7747803637874688.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null