nttx commited on
Commit
ec0e35b
·
verified ·
1 Parent(s): e8fad7e

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 sha256:645f2f000f8085a2521f4f540fe088348c7d731a61b2c28b1ee6b9238dc365f9
3
  size 73911112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef1515e2fe323f93810fe5e65c1098394f87adaf330229a7f6bf8b5509a60bf2
3
  size 73911112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31d527191c0bc4a42290e28363a1b4293c0ef289691f34ad182d2a8da867d60a
3
  size 148047722
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aacaeede04feff0ceadff7da1ee176b7664752c9094b07f04ed7d41cc87dcf20
3
  size 148047722
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d09e38721d1e2ac59e33b625fbb39b8d7d3fd89629b06614e6812d3f8d92ace
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93b088441cb556b99f30ae391673c7dd1085860e8bdfedbda1a31ca734707f3b
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": 9.646056175231934,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.16003200640128026,
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": 36.143,
374
  "eval_steps_per_second": 4.533,
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": 5.22507534729216e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 8.918850898742676,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.3200640128025605,
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": 36.143,
374
  "eval_steps_per_second": 4.533,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.16323264652930586,
379
+ "grad_norm": 9.98580265045166,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 10.9351,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.16643328665733145,
386
+ "grad_norm": 9.032503128051758,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 10.4349,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.16963392678535708,
393
+ "grad_norm": 9.19552230834961,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 10.3482,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.17283456691338267,
400
+ "grad_norm": 8.802451133728027,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 10.199,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.1760352070414083,
407
+ "grad_norm": 8.750884056091309,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 10.1422,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.1792358471694339,
414
+ "grad_norm": 8.889410018920898,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 9.8411,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.18243648729745948,
421
+ "grad_norm": 8.85236930847168,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 9.7556,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.1856371274254851,
428
+ "grad_norm": 8.6629638671875,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 9.4654,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.1888377675535107,
435
+ "grad_norm": 8.871862411499023,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 9.7944,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.1920384076815363,
442
+ "grad_norm": 8.809235572814941,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 9.357,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.19523904780956192,
449
+ "grad_norm": 8.64078140258789,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 9.2908,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.1984396879375875,
456
+ "grad_norm": 8.398662567138672,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 9.2111,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.20164032806561313,
463
+ "grad_norm": 8.646689414978027,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 9.2725,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.20484096819363873,
470
+ "grad_norm": 8.852496147155762,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 9.2046,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.20804160832166432,
477
+ "grad_norm": 8.716590881347656,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 9.2535,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.21124224844968995,
484
+ "grad_norm": 8.654803276062012,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 8.919,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.21444288857771554,
491
+ "grad_norm": 8.683820724487305,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 9.0051,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.21764352870574113,
498
+ "grad_norm": 8.809885025024414,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 8.903,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.22084416883376676,
505
+ "grad_norm": 9.03306770324707,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 9.0358,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.22404480896179235,
512
+ "grad_norm": 8.856549263000488,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 8.8794,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.22724544908981797,
519
+ "grad_norm": 8.979342460632324,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 8.8219,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.23044608921784357,
526
+ "grad_norm": 9.096173286437988,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 8.5252,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.23364672934586916,
533
+ "grad_norm": 9.02049732208252,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 8.6853,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.2368473694738948,
540
+ "grad_norm": 8.875118255615234,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 8.8005,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.24004800960192038,
547
+ "grad_norm": 9.007421493530273,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 8.9351,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.24324864972994598,
554
+ "grad_norm": 9.179397583007812,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 8.3519,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.2464492898579716,
561
+ "grad_norm": 9.02707576751709,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 8.6803,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.2496499299859972,
568
+ "grad_norm": 9.033645629882812,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 8.8293,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.2528505701140228,
575
+ "grad_norm": 9.013845443725586,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 8.7671,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.2560512102420484,
582
+ "grad_norm": 9.009531021118164,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 8.5498,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.25925185037007403,
589
+ "grad_norm": 9.453420639038086,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 8.694,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.2624524904980996,
596
+ "grad_norm": 9.14536190032959,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 8.7665,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.2656531306261252,
603
+ "grad_norm": 9.32065200805664,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 8.8257,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.26885377075415084,
610
+ "grad_norm": 9.271746635437012,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 8.5479,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.2720544108821764,
617
+ "grad_norm": 9.394197463989258,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 8.7656,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.27525505101020203,
624
+ "grad_norm": 9.346041679382324,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 8.6702,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.27845569113822766,
631
+ "grad_norm": 9.438603401184082,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 8.3737,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.2816563312662532,
638
+ "grad_norm": 9.419256210327148,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 8.6043,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.28485697139427885,
645
+ "grad_norm": 9.320596694946289,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 8.5247,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.28805761152230447,
652
+ "grad_norm": 9.374907493591309,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 8.7696,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.2912582516503301,
659
+ "grad_norm": 9.681441307067871,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 8.6677,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.29445889177835566,
666
+ "grad_norm": 9.734357833862305,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 8.8343,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.2976595319063813,
673
+ "grad_norm": 9.929716110229492,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 8.6465,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.3008601720344069,
680
+ "grad_norm": 10.133479118347168,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 8.9382,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.30406081216243247,
687
+ "grad_norm": 10.50210189819336,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 8.9628,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.3072614522904581,
694
+ "grad_norm": 10.430581092834473,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 8.9042,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.3104620924184837,
701
+ "grad_norm": 10.7635498046875,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 9.0293,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.3136627325465093,
708
+ "grad_norm": 11.791208267211914,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 8.988,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.3168633726745349,
715
+ "grad_norm": 12.532336235046387,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 9.2857,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.3200640128025605,
722
+ "grad_norm": 13.276676177978516,
723
+ "learning_rate": 0.0,
724
+ "loss": 9.6307,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.3200640128025605,
729
+ "eval_loss": 8.918850898742676,
730
+ "eval_runtime": 58.2379,
731
+ "eval_samples_per_second": 36.145,
732
+ "eval_steps_per_second": 4.533,
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": 1.045015069458432e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null