prxy5606 commited on
Commit
365bb70
·
verified ·
1 Parent(s): cbc429e

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 sha256:35a66ffb102bdb2e85c336a4bc15001f2ad31abc4df64b05936254cf01fc269e
3
  size 134235712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48a76cc5bd6972cfab52bdd45db1f9e79080e999e4e7d03d8762e1985891a2c9
3
  size 134235712
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ab64a2e0982d1bf799548c77b066358c5a589a6906c75c46eed5fe989670aea
3
  size 268543610
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29104c6edc1219e971129d84e872f606a4ff9fc00950a5e3c6970743eb12d029
3
  size 268543610
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1894c8f7415479b6de062560fe0a0b24b2842fd36cdefaed8a22e126bd0b625f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd3d43fb645818d100589c8df8645f08b624ad45553476b28fdf12e86a74e257
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ece3236edcb393fe9fe067fb4c27aaaf2d1a125595517cb84b2456d9b62475c0
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.9772149920463562,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.06870491240123669,
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": 50.923,
374
  "eval_steps_per_second": 25.462,
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": 1.1393881576833024e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8876156806945801,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.13740982480247338,
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": 50.923,
374
  "eval_steps_per_second": 25.462,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.07007901064926142,
379
+ "grad_norm": 4.790940761566162,
380
+ "learning_rate": 7.938926261462366e-05,
381
+ "loss": 3.5343,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.07145310889728615,
386
+ "grad_norm": 4.0827860832214355,
387
+ "learning_rate": 7.754484907260513e-05,
388
+ "loss": 3.5173,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0728272071453109,
393
+ "grad_norm": 2.454427480697632,
394
+ "learning_rate": 7.564496387029532e-05,
395
+ "loss": 2.9402,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.07420130539333562,
400
+ "grad_norm": 1.7591845989227295,
401
+ "learning_rate": 7.369343312364993e-05,
402
+ "loss": 2.8061,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.07557540364136035,
407
+ "grad_norm": 1.4820759296417236,
408
+ "learning_rate": 7.169418695587791e-05,
409
+ "loss": 2.6238,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.0769495018893851,
414
+ "grad_norm": 1.361936092376709,
415
+ "learning_rate": 6.965125158269619e-05,
416
+ "loss": 2.8171,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.07832360013740983,
421
+ "grad_norm": 1.1161038875579834,
422
+ "learning_rate": 6.756874120406714e-05,
423
+ "loss": 2.6354,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.07969769838543456,
428
+ "grad_norm": 1.0470097064971924,
429
+ "learning_rate": 6.545084971874738e-05,
430
+ "loss": 2.7784,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.08107179663345929,
435
+ "grad_norm": 1.0488992929458618,
436
+ "learning_rate": 6.330184227833376e-05,
437
+ "loss": 2.8162,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.08244589488148403,
442
+ "grad_norm": 1.0387022495269775,
443
+ "learning_rate": 6.112604669781572e-05,
444
+ "loss": 2.8907,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.08381999312950876,
449
+ "grad_norm": 1.0147078037261963,
450
+ "learning_rate": 5.8927844739931834e-05,
451
+ "loss": 2.8147,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.08519409137753349,
456
+ "grad_norm": 1.0787792205810547,
457
+ "learning_rate": 5.6711663290882776e-05,
458
+ "loss": 3.0599,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.08656818962555823,
463
+ "grad_norm": 0.9972174167633057,
464
+ "learning_rate": 5.448196544517168e-05,
465
+ "loss": 3.0402,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.08794228787358296,
470
+ "grad_norm": 1.05092453956604,
471
+ "learning_rate": 5.2243241517525754e-05,
472
+ "loss": 3.1217,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.0893163861216077,
477
+ "grad_norm": 0.9785769581794739,
478
+ "learning_rate": 5e-05,
479
+ "loss": 2.9106,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.09069048436963242,
484
+ "grad_norm": 1.1027038097381592,
485
+ "learning_rate": 4.775675848247427e-05,
486
+ "loss": 3.1218,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.09206458261765717,
491
+ "grad_norm": 1.075793743133545,
492
+ "learning_rate": 4.551803455482833e-05,
493
+ "loss": 3.4223,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.0934386808656819,
498
+ "grad_norm": 1.0721230506896973,
499
+ "learning_rate": 4.328833670911724e-05,
500
+ "loss": 3.2137,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.09481277911370663,
505
+ "grad_norm": 1.0705825090408325,
506
+ "learning_rate": 4.107215526006817e-05,
507
+ "loss": 3.2946,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.09618687736173136,
512
+ "grad_norm": 1.1933683156967163,
513
+ "learning_rate": 3.887395330218429e-05,
514
+ "loss": 3.5703,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.0975609756097561,
519
+ "grad_norm": 1.1190630197525024,
520
+ "learning_rate": 3.6698157721666246e-05,
521
+ "loss": 3.3662,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.09893507385778083,
526
+ "grad_norm": 1.2145003080368042,
527
+ "learning_rate": 3.4549150281252636e-05,
528
+ "loss": 3.4709,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.10030917210580556,
533
+ "grad_norm": 1.1540323495864868,
534
+ "learning_rate": 3.243125879593286e-05,
535
+ "loss": 3.2167,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.1016832703538303,
540
+ "grad_norm": 1.1874574422836304,
541
+ "learning_rate": 3.0348748417303823e-05,
542
+ "loss": 3.4655,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.10305736860185503,
547
+ "grad_norm": 1.1657719612121582,
548
+ "learning_rate": 2.8305813044122097e-05,
549
+ "loss": 3.4028,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.10443146684987976,
554
+ "grad_norm": 1.2047468423843384,
555
+ "learning_rate": 2.630656687635007e-05,
556
+ "loss": 3.4156,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.1058055650979045,
561
+ "grad_norm": 1.2500311136245728,
562
+ "learning_rate": 2.43550361297047e-05,
563
+ "loss": 3.6538,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.10717966334592924,
568
+ "grad_norm": 1.23727548122406,
569
+ "learning_rate": 2.245515092739488e-05,
570
+ "loss": 3.7062,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.10855376159395397,
575
+ "grad_norm": 1.327557921409607,
576
+ "learning_rate": 2.061073738537635e-05,
577
+ "loss": 3.6038,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.1099278598419787,
582
+ "grad_norm": 1.3304165601730347,
583
+ "learning_rate": 1.8825509907063327e-05,
584
+ "loss": 3.8635,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.11130195809000344,
589
+ "grad_norm": 1.351146936416626,
590
+ "learning_rate": 1.7103063703014372e-05,
591
+ "loss": 3.7362,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.11267605633802817,
596
+ "grad_norm": 1.374627709388733,
597
+ "learning_rate": 1.544686755065677e-05,
598
+ "loss": 3.7078,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.1140501545860529,
603
+ "grad_norm": 1.3466027975082397,
604
+ "learning_rate": 1.3860256808630428e-05,
605
+ "loss": 3.7743,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.11542425283407763,
610
+ "grad_norm": 1.4703048467636108,
611
+ "learning_rate": 1.2346426699819458e-05,
612
+ "loss": 4.009,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.11679835108210238,
617
+ "grad_norm": 1.402172565460205,
618
+ "learning_rate": 1.090842587659851e-05,
619
+ "loss": 3.8147,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.1181724493301271,
624
+ "grad_norm": 1.5001634359359741,
625
+ "learning_rate": 9.549150281252633e-06,
626
+ "loss": 3.9168,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.11954654757815183,
631
+ "grad_norm": 1.468559980392456,
632
+ "learning_rate": 8.271337313934869e-06,
633
+ "loss": 4.349,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.12092064582617656,
638
+ "grad_norm": 1.5293834209442139,
639
+ "learning_rate": 7.077560319906695e-06,
640
+ "loss": 3.8892,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.12229474407420131,
645
+ "grad_norm": 1.5736913681030273,
646
+ "learning_rate": 5.9702234071631e-06,
647
+ "loss": 4.2034,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.12366884232222604,
652
+ "grad_norm": 1.5629932880401611,
653
+ "learning_rate": 4.951556604879048e-06,
654
+ "loss": 4.0794,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.12504294057025078,
659
+ "grad_norm": 1.7163255214691162,
660
+ "learning_rate": 4.023611372427471e-06,
661
+ "loss": 4.5224,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.1264170388182755,
666
+ "grad_norm": 1.7329245805740356,
667
+ "learning_rate": 3.18825646801314e-06,
668
+ "loss": 4.1498,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.12779113706630024,
673
+ "grad_norm": 1.832844853401184,
674
+ "learning_rate": 2.4471741852423237e-06,
675
+ "loss": 4.4573,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.12916523531432497,
680
+ "grad_norm": 1.913427710533142,
681
+ "learning_rate": 1.8018569652073381e-06,
682
+ "loss": 4.5025,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.1305393335623497,
687
+ "grad_norm": 1.9010084867477417,
688
+ "learning_rate": 1.2536043909088191e-06,
689
+ "loss": 4.4059,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.13191343181037443,
694
+ "grad_norm": 2.1113531589508057,
695
+ "learning_rate": 8.035205700685167e-07,
696
+ "loss": 4.5278,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.13328753005839916,
701
+ "grad_norm": 2.1245055198669434,
702
+ "learning_rate": 4.52511911603265e-07,
703
+ "loss": 4.6188,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.13466162830642392,
708
+ "grad_norm": 2.3013916015625,
709
+ "learning_rate": 2.012853002380466e-07,
710
+ "loss": 4.3355,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.13603572655444865,
715
+ "grad_norm": 2.819425106048584,
716
+ "learning_rate": 5.0346672934270534e-08,
717
+ "loss": 4.9912,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.13740982480247338,
722
+ "grad_norm": 3.633572816848755,
723
+ "learning_rate": 0.0,
724
+ "loss": 5.0884,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.13740982480247338,
729
+ "eval_loss": 0.8876156806945801,
730
+ "eval_runtime": 24.0584,
731
+ "eval_samples_per_second": 50.959,
732
+ "eval_steps_per_second": 25.48,
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": 2.2973029520769024e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null