nttx commited on
Commit
6b8a1b2
·
verified ·
1 Parent(s): ffc157c

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 sha256:91e93374e34d8cd402fc43eefc9d8315d3e326a1e6359ff881ed4e8a2f56679f
3
  size 985240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dc6c59c18e5a47cc20ec2ea85928bf284768efb619cb36c39f4cb0a868e127e
3
  size 985240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:372642c09921d74911530af9e8482b2c3b94681771e265f2c6c4d4458a9b6e15
3
  size 1980078
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:406bba763add6afad7d556436aa96c23f1ec6356f36b2fe1cc81b8babf607483
3
  size 1980078
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd398caf88c081dda7d535a3978705439b653e4cceb23d0f66a9e47ebbe50f8c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d288bf14a6d0b4283aca957c6bd056390978747ba8dee8f69df2d2d377c117e
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": 11.050891876220703,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.04906771344455348,
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": 337.292,
374
  "eval_steps_per_second": 42.26,
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": 7703686545408.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 11.038614273071289,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.09813542688910697,
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": 337.292,
374
  "eval_steps_per_second": 42.26,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.050049067713444556,
379
+ "grad_norm": 4.3872294425964355,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 44.1583,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.05103042198233562,
386
+ "grad_norm": 4.958473205566406,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 44.1556,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.052011776251226695,
393
+ "grad_norm": 4.641199588775635,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 44.1518,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.05299313052011776,
400
+ "grad_norm": 4.831917762756348,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 44.1574,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.053974484789008834,
407
+ "grad_norm": 4.641740322113037,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 44.177,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.0549558390578999,
414
+ "grad_norm": 5.027724742889404,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 44.1403,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.05593719332679097,
421
+ "grad_norm": 4.93941068649292,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 44.1304,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.05691854759568204,
428
+ "grad_norm": 4.8098063468933105,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 44.1245,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.05789990186457311,
435
+ "grad_norm": 4.973179340362549,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 44.141,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.058881256133464184,
442
+ "grad_norm": 4.688238620758057,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 44.154,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.05986261040235525,
449
+ "grad_norm": 4.850657939910889,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 44.1483,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.06084396467124632,
456
+ "grad_norm": 4.537477016448975,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 44.1491,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.06182531894013739,
463
+ "grad_norm": 4.47567081451416,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 44.1562,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.06280667320902845,
470
+ "grad_norm": 4.615531921386719,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 44.1694,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.06378802747791953,
477
+ "grad_norm": 4.739807605743408,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 44.1339,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.0647693817468106,
484
+ "grad_norm": 4.978174686431885,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 44.1016,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.06575073601570167,
491
+ "grad_norm": 4.427630424499512,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 44.1453,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.06673209028459273,
498
+ "grad_norm": 4.460508823394775,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 44.1541,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.06771344455348381,
505
+ "grad_norm": 4.592861175537109,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 44.1361,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.06869479882237488,
512
+ "grad_norm": 4.343865394592285,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 44.1732,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.06967615309126594,
519
+ "grad_norm": 4.420068264007568,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 44.1383,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.07065750736015702,
526
+ "grad_norm": 4.614556789398193,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 44.142,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.07163886162904809,
533
+ "grad_norm": 4.291627883911133,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 44.1535,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.07262021589793916,
540
+ "grad_norm": 4.367705345153809,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 44.1653,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.07360157016683022,
547
+ "grad_norm": 4.751893997192383,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 44.1325,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.0745829244357213,
554
+ "grad_norm": 4.403656959533691,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 44.1413,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.07556427870461237,
561
+ "grad_norm": 4.389298915863037,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 44.1718,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.07654563297350343,
568
+ "grad_norm": 4.401954174041748,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 44.1616,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.0775269872423945,
575
+ "grad_norm": 4.580694198608398,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 44.1418,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.07850834151128558,
582
+ "grad_norm": 4.462921619415283,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 44.1092,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.07948969578017664,
589
+ "grad_norm": 4.829708099365234,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 44.1295,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.08047105004906771,
596
+ "grad_norm": 4.394340991973877,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 44.1685,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.08145240431795878,
603
+ "grad_norm": 4.454510688781738,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 44.1542,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.08243375858684986,
610
+ "grad_norm": 4.497045040130615,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 44.1375,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.08341511285574092,
617
+ "grad_norm": 4.434609889984131,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 44.1345,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.08439646712463199,
624
+ "grad_norm": 4.5244035720825195,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 44.1467,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.08537782139352307,
631
+ "grad_norm": 4.269883632659912,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 44.1526,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.08635917566241413,
638
+ "grad_norm": 4.184451103210449,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 44.1822,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.0873405299313052,
645
+ "grad_norm": 4.249412536621094,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 44.1716,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.08832188420019627,
652
+ "grad_norm": 3.827402114868164,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 44.1924,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.08930323846908735,
659
+ "grad_norm": 4.114834785461426,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 44.2127,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.09028459273797841,
666
+ "grad_norm": 3.819640636444092,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 44.2051,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.09126594700686948,
673
+ "grad_norm": 4.212294578552246,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 44.1976,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.09224730127576054,
680
+ "grad_norm": 3.624086618423462,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 44.2229,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.09322865554465162,
687
+ "grad_norm": 3.4577605724334717,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 44.2466,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.09421000981354269,
694
+ "grad_norm": 3.643979072570801,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 44.3109,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.09519136408243375,
701
+ "grad_norm": 4.863288879394531,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 44.1834,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.09617271835132483,
708
+ "grad_norm": 3.8488268852233887,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 44.2992,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.0971540726202159,
715
+ "grad_norm": 4.9372148513793945,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 44.3093,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.09813542688910697,
722
+ "grad_norm": 5.151540756225586,
723
+ "learning_rate": 0.0,
724
+ "loss": 44.4666,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.09813542688910697,
729
+ "eval_loss": 11.038614273071289,
730
+ "eval_runtime": 5.0993,
731
+ "eval_samples_per_second": 336.516,
732
+ "eval_steps_per_second": 42.163,
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": 15407373090816.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null