aleegis11 commited on
Commit
38dca7e
·
verified ·
1 Parent(s): 3065f78

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:bb7b5c3d0fc8ee31f6ead2f375018810cf66d5bccdee51a2d1242e3deced81d5
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43eb00ff5edd14f5c83cd0af6731028f73f14f37c669d3e12aea053a18c0368e
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2710de3c566ace186600822257fad89453f1ec8d7aad386cbdb2ed26e089bef6
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bf03cb8013bff5bb44fd71f7343137b610d145e564e7c95c538d7d8c989fb17
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db723ad080376a5fe261f88a2ea612fad38ad00d006b6453269186b96fd13de9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9597572bac40060135060090c19fc192155e990d2f5a0d90d087e8db6bf3bd65
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": 1.895154356956482,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.004653435398683078,
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": 13.722,
374
  "eval_steps_per_second": 3.431,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 6.7624822112256e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.7882341146469116,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.009306870797366156,
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": 13.722,
374
  "eval_steps_per_second": 3.431,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.004746504106656739,
379
+ "grad_norm": 2.5106000900268555,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.6629,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.004839572814630401,
386
+ "grad_norm": 1.8666657209396362,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.8131,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.004932641522604062,
393
+ "grad_norm": 1.975517749786377,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.8937,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.005025710230577724,
400
+ "grad_norm": 1.793887972831726,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.836,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.005118778938551386,
407
+ "grad_norm": 1.6891287565231323,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.9566,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.005211847646525047,
414
+ "grad_norm": 1.4570671319961548,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.5209,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.005304916354498709,
421
+ "grad_norm": 1.575348138809204,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.6971,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.00539798506247237,
428
+ "grad_norm": 1.690929889678955,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.7764,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.005491053770446032,
435
+ "grad_norm": 1.7088589668273926,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 2.0965,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.005584122478419693,
442
+ "grad_norm": 1.5418660640716553,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.7433,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.005677191186393355,
449
+ "grad_norm": 1.3604835271835327,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.6691,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.005770259894367017,
456
+ "grad_norm": 1.6632291078567505,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 2.0291,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.005863328602340678,
463
+ "grad_norm": 1.51374351978302,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.7343,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.00595639731031434,
470
+ "grad_norm": 1.6543316841125488,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 2.092,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.006049466018288001,
477
+ "grad_norm": 1.4366066455841064,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.6421,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.006142534726261663,
484
+ "grad_norm": 1.6704673767089844,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 2.1059,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.006235603434235324,
491
+ "grad_norm": 1.408278465270996,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.7576,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.0063286721422089855,
498
+ "grad_norm": 1.5189968347549438,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 2.1127,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.006421740850182647,
505
+ "grad_norm": 1.4850586652755737,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.6378,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.006514809558156309,
512
+ "grad_norm": 1.3093808889389038,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.4265,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.006607878266129971,
519
+ "grad_norm": 1.2844609022140503,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.7181,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.006700946974103632,
526
+ "grad_norm": 1.2631522417068481,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.6354,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.0067940156820772936,
533
+ "grad_norm": 1.588806390762329,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 2.1476,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.006887084390050955,
540
+ "grad_norm": 1.418257474899292,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.9464,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.006980153098024616,
547
+ "grad_norm": 1.4015493392944336,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.4929,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.007073221805998278,
554
+ "grad_norm": 1.4926618337631226,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.9594,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.00716629051397194,
561
+ "grad_norm": 1.4897574186325073,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.7255,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.007259359221945602,
568
+ "grad_norm": 1.4887974262237549,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 2.0148,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.007352427929919263,
575
+ "grad_norm": 1.9028290510177612,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.9502,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.0074454966378929245,
582
+ "grad_norm": 1.2643802165985107,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.6995,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.007538565345866586,
589
+ "grad_norm": 1.452819585800171,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.7471,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.007631634053840247,
596
+ "grad_norm": 1.3838050365447998,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.828,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.007724702761813909,
603
+ "grad_norm": 1.4136393070220947,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.8672,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.007817771469787571,
610
+ "grad_norm": 1.4885083436965942,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.8153,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.007910840177761232,
617
+ "grad_norm": 1.40280020236969,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.6192,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.008003908885734894,
624
+ "grad_norm": 1.5277206897735596,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.7702,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.008096977593708555,
631
+ "grad_norm": 1.5335403680801392,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 2.0259,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.008190046301682217,
638
+ "grad_norm": 1.6681487560272217,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.8646,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.00828311500965588,
645
+ "grad_norm": 1.5285978317260742,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.6269,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.00837618371762954,
652
+ "grad_norm": 1.6006323099136353,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 2.0429,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.008469252425603202,
659
+ "grad_norm": 1.5587456226348877,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.685,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.008562321133576863,
666
+ "grad_norm": 1.6037956476211548,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 1.5068,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.008655389841550525,
673
+ "grad_norm": 1.6179325580596924,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.8092,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.008748458549524185,
680
+ "grad_norm": 1.955496072769165,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.6188,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.008841527257497848,
687
+ "grad_norm": 1.6679211854934692,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.9612,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.00893459596547151,
694
+ "grad_norm": 1.6616119146347046,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.993,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.00902766467344517,
701
+ "grad_norm": 1.4882142543792725,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.6337,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.009120733381418833,
708
+ "grad_norm": 2.1910977363586426,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.7137,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.009213802089392494,
715
+ "grad_norm": 2.2215073108673096,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.6943,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.009306870797366156,
722
+ "grad_norm": 5.864289283752441,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 2.2214,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.009306870797366156,
729
+ "eval_loss": 1.7882341146469116,
730
+ "eval_runtime": 1318.1193,
731
+ "eval_samples_per_second": 13.729,
732
+ "eval_steps_per_second": 3.433,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.34913202323456e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null