aleegis10 commited on
Commit
1b88a67
·
verified ·
1 Parent(s): 835acfc

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 sha256:89c4b78b9d54899d6d668c0b6322851102cb54478fad81686fe7468813b7870a
3
  size 289452128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92da10b2aab8bce8f3dba5614a9aaf9a059162afd16230051c0b6ba978fbf657
3
  size 289452128
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc64dc41b14e569c6fae0a3572a8ec14843fdaa73a09cb9d04cab02922131d0b
3
  size 147359892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c06df4650860d3efd1685de2c458c5cd4ddcb16a8f2c38d47b62a0cacc8132b7
3
  size 147359892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54b068227a1b5549b05592bf6a72e16aed8f4a6f26a63c93afc352437f9d8176
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fda109e1319443dedd2496afda05a126f3531d30415fddf50ca9d30c7a06356
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": 0.37262478470802307,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.7518796992481203,
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": 26.809,
374
  "eval_steps_per_second": 6.702,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.9936966632013824e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.33665910363197327,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.5037593984962405,
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": 26.809,
374
  "eval_steps_per_second": 6.702,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.7669172932330827,
379
+ "grad_norm": 0.06599943339824677,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.2615,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.7819548872180451,
386
+ "grad_norm": 0.09893481433391571,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.3557,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.7969924812030075,
393
+ "grad_norm": 0.09345290064811707,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.3434,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.8120300751879699,
400
+ "grad_norm": 0.08674218505620956,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.3158,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.8270676691729323,
407
+ "grad_norm": 0.08880195766687393,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.3337,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.8421052631578947,
414
+ "grad_norm": 0.09427762776613235,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.2699,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.8571428571428571,
421
+ "grad_norm": 0.13124015927314758,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.3954,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.8721804511278195,
428
+ "grad_norm": 0.0997491180896759,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.3735,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.8872180451127819,
435
+ "grad_norm": 0.10970690846443176,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.3586,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.9022556390977443,
442
+ "grad_norm": 0.11503557860851288,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.3521,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.9172932330827067,
449
+ "grad_norm": 0.11184751987457275,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.341,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.9323308270676691,
456
+ "grad_norm": 0.1396840214729309,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.3936,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.9473684210526315,
463
+ "grad_norm": 0.13676707446575165,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.4158,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.9624060150375939,
470
+ "grad_norm": 0.22201699018478394,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.5111,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.9774436090225563,
477
+ "grad_norm": 0.08992062509059906,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.2262,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.9924812030075187,
484
+ "grad_norm": 0.10290435701608658,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.33,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 1.0075187969924813,
491
+ "grad_norm": 0.18397407233715057,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.4702,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 1.0225563909774436,
498
+ "grad_norm": 0.07360022515058517,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.2287,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 1.037593984962406,
505
+ "grad_norm": 0.07548756897449493,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.2616,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 1.0526315789473684,
512
+ "grad_norm": 0.07878497987985611,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.2625,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 1.0676691729323309,
519
+ "grad_norm": 0.09046885371208191,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.3015,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 1.0827067669172932,
526
+ "grad_norm": 0.11554723978042603,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.3655,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 1.0977443609022557,
533
+ "grad_norm": 0.12574858963489532,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.4256,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 1.112781954887218,
540
+ "grad_norm": 0.09299656748771667,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.2958,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 1.1278195488721805,
547
+ "grad_norm": 0.08710354566574097,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.2783,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 1.1428571428571428,
554
+ "grad_norm": 0.12041075527667999,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.3115,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 1.1578947368421053,
561
+ "grad_norm": 0.09662258625030518,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.2791,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 1.1729323308270676,
568
+ "grad_norm": 0.12336187064647675,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.3641,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 1.1879699248120301,
575
+ "grad_norm": 0.12569434940814972,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.3622,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 1.2030075187969924,
582
+ "grad_norm": 0.12593090534210205,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.3494,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 1.218045112781955,
589
+ "grad_norm": 0.14964139461517334,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.3904,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 1.2330827067669172,
596
+ "grad_norm": 0.14055132865905762,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.3165,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 1.2481203007518797,
603
+ "grad_norm": 0.12390806525945663,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.3155,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 1.263157894736842,
610
+ "grad_norm": 0.06820280849933624,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.2357,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 1.2781954887218046,
617
+ "grad_norm": 0.10265903174877167,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.279,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 1.2932330827067668,
624
+ "grad_norm": 0.09636881947517395,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.2502,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 1.3082706766917294,
631
+ "grad_norm": 0.08445224165916443,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.2709,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 1.3233082706766917,
638
+ "grad_norm": 0.09228705614805222,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.2645,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 1.3383458646616542,
645
+ "grad_norm": 0.11085734516382217,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.2749,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 1.3533834586466165,
652
+ "grad_norm": 0.12179312109947205,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.2668,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 1.368421052631579,
659
+ "grad_norm": 0.11226280778646469,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.3082,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 1.3834586466165413,
666
+ "grad_norm": 0.1071193665266037,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.2984,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.3984962406015038,
673
+ "grad_norm": 0.10544191300868988,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.29,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.413533834586466,
680
+ "grad_norm": 0.1404181867837906,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.3858,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.4285714285714286,
687
+ "grad_norm": 0.12208665907382965,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.283,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.443609022556391,
694
+ "grad_norm": 0.12611155211925507,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.3017,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.4586466165413534,
701
+ "grad_norm": 0.1585017889738083,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.3501,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.4736842105263157,
708
+ "grad_norm": 0.1821914166212082,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.3796,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.4887218045112782,
715
+ "grad_norm": 0.15494661033153534,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.335,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.5037593984962405,
722
+ "grad_norm": 0.08711566030979156,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.2393,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.5037593984962405,
729
+ "eval_loss": 0.33665910363197327,
730
+ "eval_runtime": 4.2837,
731
+ "eval_samples_per_second": 26.146,
732
+ "eval_steps_per_second": 6.536,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 3.912939924042547e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null