aleegis09 commited on
Commit
bfb4d39
·
verified ·
1 Parent(s): f318be0

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:f5fe747b88bd5829bc171475bccc10a0745ae5a94a2ea07f0ee9b11effd70d88
3
  size 138995824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2c832c7c338c089953b13edd4ec20f50223d6934fefe9d6c6edd2ab5fd24df2
3
  size 138995824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff0b3bfeea49c206a5ef77dfc78e7b513269e4520fde0812a4d2ed795338f2a9
3
  size 71077780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bb953eaf4f751e42cc97306c715a5ead14c96170e39faa3fb4b64eb2c7fcede
3
  size 71077780
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd1ec4d514d395f3d28a6b7982b16980d4417391ae620f9d643443999600eec1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1755d42c60e50ff7c04ecac5c6e1061394aa2f05c7189115068dc63454405dd5
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": 2.3451285362243652,
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": 59.487,
374
  "eval_steps_per_second": 14.874,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3451611968962560.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.2260937690734863,
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": 59.487,
374
  "eval_steps_per_second": 14.874,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.004746504106656739,
379
+ "grad_norm": 1.0793604850769043,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 2.0619,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.004839572814630401,
386
+ "grad_norm": 1.2041372060775757,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 2.2603,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.004932641522604062,
393
+ "grad_norm": 1.2433840036392212,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 2.4774,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.005025710230577724,
400
+ "grad_norm": 0.9980171322822571,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 2.4083,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.005118778938551386,
407
+ "grad_norm": 0.8141014575958252,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 2.3011,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.005211847646525047,
414
+ "grad_norm": 0.8396517038345337,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 2.0085,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.005304916354498709,
421
+ "grad_norm": 1.0535227060317993,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 2.5437,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.00539798506247237,
428
+ "grad_norm": 0.9660801291465759,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 2.2237,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.005491053770446032,
435
+ "grad_norm": 0.8122984766960144,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 2.3608,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.005584122478419693,
442
+ "grad_norm": 0.785032331943512,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.9222,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.005677191186393355,
449
+ "grad_norm": 0.808636486530304,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 2.5387,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.005770259894367017,
456
+ "grad_norm": 0.9330622553825378,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 2.2626,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.005863328602340678,
463
+ "grad_norm": 0.8387428522109985,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 2.6472,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.00595639731031434,
470
+ "grad_norm": 0.7978306412696838,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.8203,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.006049466018288001,
477
+ "grad_norm": 0.7352349162101746,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 2.1042,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.006142534726261663,
484
+ "grad_norm": 0.759606659412384,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 2.3022,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.006235603434235324,
491
+ "grad_norm": 0.8301123976707458,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 2.1345,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.0063286721422089855,
498
+ "grad_norm": 0.7451291680335999,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.8591,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.006421740850182647,
505
+ "grad_norm": 0.9728070497512817,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 2.7392,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.006514809558156309,
512
+ "grad_norm": 0.9151380658149719,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 2.3832,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.006607878266129971,
519
+ "grad_norm": 0.907772421836853,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 2.7511,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.006700946974103632,
526
+ "grad_norm": 0.9469855427742004,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 2.2524,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.0067940156820772936,
533
+ "grad_norm": 0.8078688979148865,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 2.6212,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.006887084390050955,
540
+ "grad_norm": 0.7528191804885864,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 2.3951,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.006980153098024616,
547
+ "grad_norm": 0.7665908336639404,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 2.1368,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.007073221805998278,
554
+ "grad_norm": 0.7805386185646057,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 2.2643,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.00716629051397194,
561
+ "grad_norm": 0.7518503665924072,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 2.3292,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.007259359221945602,
568
+ "grad_norm": 0.7999743819236755,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 2.1856,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.007352427929919263,
575
+ "grad_norm": 0.7561430931091309,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 2.2459,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.0074454966378929245,
582
+ "grad_norm": 0.7938767075538635,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 2.0714,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.007538565345866586,
589
+ "grad_norm": 0.8000980019569397,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 2.5162,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.007631634053840247,
596
+ "grad_norm": 0.7641688585281372,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 2.1551,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.007724702761813909,
603
+ "grad_norm": 0.8685629367828369,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 2.1017,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.007817771469787571,
610
+ "grad_norm": 0.9702941179275513,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 2.4495,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.007910840177761232,
617
+ "grad_norm": 0.8403957486152649,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.7543,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.008003908885734894,
624
+ "grad_norm": 1.0476443767547607,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 2.7362,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.008096977593708555,
631
+ "grad_norm": 0.8195080757141113,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 2.5326,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.008190046301682217,
638
+ "grad_norm": 0.9867530465126038,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 2.3212,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.00828311500965588,
645
+ "grad_norm": 0.873130202293396,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 2.2296,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.00837618371762954,
652
+ "grad_norm": 0.9660400748252869,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 2.312,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.008469252425603202,
659
+ "grad_norm": 0.8753485679626465,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 2.4439,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.008562321133576863,
666
+ "grad_norm": 0.8424671292304993,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 2.2858,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.008655389841550525,
673
+ "grad_norm": 0.9123796224594116,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 2.471,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.008748458549524185,
680
+ "grad_norm": 0.7733258008956909,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.9602,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.008841527257497848,
687
+ "grad_norm": 0.7955862283706665,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.9895,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.00893459596547151,
694
+ "grad_norm": 0.8176329135894775,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 2.4244,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.00902766467344517,
701
+ "grad_norm": 0.8636637330055237,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.9982,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.009120733381418833,
708
+ "grad_norm": 0.8942632079124451,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 2.4093,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.009213802089392494,
715
+ "grad_norm": 0.9849814176559448,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 2.1861,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.009306870797366156,
722
+ "grad_norm": 1.0841326713562012,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 2.4123,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.009306870797366156,
729
+ "eval_loss": 2.2260937690734863,
730
+ "eval_runtime": 304.6034,
731
+ "eval_samples_per_second": 59.412,
732
+ "eval_steps_per_second": 14.855,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 6886051739074560.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null