nttx commited on
Commit
228ceae
·
verified ·
1 Parent(s): 8456f81

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:b2cf527965c5700108de657de9a2d4d811c6c07a77c9f374f0d08997120103a3
3
  size 119801528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e797d841c8af5302345cf23552f6bf68e50a6afdf2f4c19a7da0694023962ec6
3
  size 119801528
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30e9d79899d78efec2d7e9342f97a27df96143b7668d95578651b7fe052901ab
3
  size 239892858
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3f8a93e5247c7759d4fb61c27c8cb7e66a9e452d57581c24952c0f1d68f53ab
3
  size 239892858
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc14ad15a68691f146dbb8a903e21f7d3b050e9c7014636f73aa5c1ad8c31bc5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97fdc81fd14efede2f87b6b723b5eb246fb1670f8c9de4d4c51df47867f2d47f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1900bd8021f13c38b942ed30aea6e2cea1b47664e4ce28d0276b142334732307
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c4a11c3ec7ace2e963dc6e2b0b5b6372cc0250cefb36d5f7289475908638cb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.1045054197311401,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.4366812227074236,
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": 22.054,
374
  "eval_steps_per_second": 2.771,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -396,12 +754,12 @@
396
  "should_evaluate": false,
397
  "should_log": false,
398
  "should_save": true,
399
- "should_training_stop": false
400
  },
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.102855796686848e+17,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5521083474159241,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.8733624454148472,
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": 22.054,
374
  "eval_steps_per_second": 2.771,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.44541484716157204,
379
+ "grad_norm": 10.8828763961792,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 1.1097,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.45414847161572053,
386
+ "grad_norm": 9.804144859313965,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 1.0797,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.462882096069869,
393
+ "grad_norm": 9.358445167541504,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 0.9913,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.47161572052401746,
400
+ "grad_norm": 7.983417987823486,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 1.0035,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.48034934497816595,
407
+ "grad_norm": 6.968960285186768,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 0.9252,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.4890829694323144,
414
+ "grad_norm": 7.956702709197998,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 0.9374,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.4978165938864629,
421
+ "grad_norm": 7.5981316566467285,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 0.8405,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.5065502183406113,
428
+ "grad_norm": 6.980844020843506,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 0.8122,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.5152838427947598,
435
+ "grad_norm": 6.394181251525879,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 0.8213,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.5240174672489083,
442
+ "grad_norm": 6.020379543304443,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 0.7706,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.5327510917030568,
449
+ "grad_norm": 5.604485511779785,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 0.7309,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.5414847161572053,
456
+ "grad_norm": 5.216635704040527,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 0.6901,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.5502183406113537,
463
+ "grad_norm": 5.138515949249268,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 0.6371,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.5589519650655022,
470
+ "grad_norm": 4.725054740905762,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 0.7029,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.5676855895196506,
477
+ "grad_norm": 4.277512073516846,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 0.7045,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.5764192139737991,
484
+ "grad_norm": 4.2250895500183105,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 0.6796,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.5851528384279476,
491
+ "grad_norm": 4.00165319442749,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 0.6453,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.5938864628820961,
498
+ "grad_norm": 3.9128329753875732,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 0.6531,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.6026200873362445,
505
+ "grad_norm": 3.793243408203125,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 0.6271,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.611353711790393,
512
+ "grad_norm": 3.42594575881958,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 0.6708,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.6200873362445415,
519
+ "grad_norm": 3.490238666534424,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 0.6311,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.62882096069869,
526
+ "grad_norm": 3.291855812072754,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 0.606,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.6375545851528385,
533
+ "grad_norm": 3.161311149597168,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 0.584,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.6462882096069869,
540
+ "grad_norm": 3.532050848007202,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 0.594,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.6550218340611353,
547
+ "grad_norm": 2.6630725860595703,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 0.6057,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.6637554585152838,
554
+ "grad_norm": 2.9496963024139404,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 0.6237,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.6724890829694323,
561
+ "grad_norm": 3.1060798168182373,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 0.5885,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.6812227074235808,
568
+ "grad_norm": 3.2678000926971436,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 0.5962,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.6899563318777293,
575
+ "grad_norm": 3.410039186477661,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 0.5793,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.6986899563318777,
582
+ "grad_norm": 2.220125198364258,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 0.6232,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.7074235807860262,
589
+ "grad_norm": 2.8471932411193848,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 0.6665,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.7161572052401747,
596
+ "grad_norm": 2.7855539321899414,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 0.6758,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.7248908296943232,
603
+ "grad_norm": 2.605518341064453,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 0.6586,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.7336244541484717,
610
+ "grad_norm": 3.320639133453369,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 0.7289,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.74235807860262,
617
+ "grad_norm": 2.517763614654541,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 0.5632,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.7510917030567685,
624
+ "grad_norm": 2.858311176300049,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 0.5354,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.759825327510917,
631
+ "grad_norm": 2.437044620513916,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 0.6251,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.7685589519650655,
638
+ "grad_norm": 2.965240240097046,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 0.5035,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.777292576419214,
645
+ "grad_norm": 3.2179172039031982,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 0.5187,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.7860262008733624,
652
+ "grad_norm": 2.7170817852020264,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 0.5827,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.7947598253275109,
659
+ "grad_norm": 2.352201461791992,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 0.5898,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.8034934497816594,
666
+ "grad_norm": 2.2373578548431396,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 0.5585,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.8122270742358079,
673
+ "grad_norm": 2.281876564025879,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 0.5549,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.8209606986899564,
680
+ "grad_norm": 2.087616443634033,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 0.5942,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.8296943231441049,
687
+ "grad_norm": 2.5654754638671875,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 0.6034,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.8384279475982532,
694
+ "grad_norm": 2.958101987838745,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 0.5104,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.8471615720524017,
701
+ "grad_norm": 2.605172872543335,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 0.5872,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.8558951965065502,
708
+ "grad_norm": 2.4058775901794434,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 0.5573,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.8646288209606987,
715
+ "grad_norm": 2.566800594329834,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 0.5109,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.8733624454148472,
722
+ "grad_norm": 2.673686981201172,
723
+ "learning_rate": 0.0,
724
+ "loss": 0.5929,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.8733624454148472,
729
+ "eval_loss": 0.5521083474159241,
730
+ "eval_runtime": 35.0363,
731
+ "eval_samples_per_second": 22.034,
732
+ "eval_steps_per_second": 2.769,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
754
  "should_evaluate": false,
755
  "should_log": false,
756
  "should_save": true,
757
+ "should_training_stop": true
758
  },
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.205711593373696e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null