prxy5607 commited on
Commit
b53cd71
·
verified ·
1 Parent(s): a936a0f

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:ea4c30124aea260158ebfb06e0c21f701ef47cf027b64bcd19d24a14e829983a
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1181d08f8115690694c91f32ad4083c5239a9bfdf0f08d1cbd90da892f33b926
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f445c31672e5465ee3625a7523f88f77d2172cc3cdf209ac03cc12ce8a4f7f85
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b4dac30a0d04f79fabb5dabbd9e7003fb24e1d7b678ab34594314c46e0f630b
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7947e5ea1d2a340405f9aba323e6e5f7edf40d9a1bc912cd3c0a012e69ca554
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5113902aee1acd2e5defbc3b351bede371a538c497f17d095b7ae67be91c5644
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": 0.8254091143608093,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.005550159567087554,
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": 13.244,
374
  "eval_steps_per_second": 3.312,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.580280733197926e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8000498414039612,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.011100319134175108,
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": 13.244,
374
  "eval_steps_per_second": 3.312,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.005661162758429305,
379
+ "grad_norm": 1.0036686658859253,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.953,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.005772165949771056,
386
+ "grad_norm": 1.0603018999099731,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.8554,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.005883169141112807,
393
+ "grad_norm": 0.8736121654510498,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.8861,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.005994172332454558,
400
+ "grad_norm": 0.9409048557281494,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.8456,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.006105175523796309,
407
+ "grad_norm": 0.9477500915527344,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.8381,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.00621617871513806,
414
+ "grad_norm": 1.1850745677947998,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.8929,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.006327181906479812,
421
+ "grad_norm": 1.0310847759246826,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.8982,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.006438185097821562,
428
+ "grad_norm": 1.0277560949325562,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.8895,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.006549188289163313,
435
+ "grad_norm": 0.8867915868759155,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.7826,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.006660191480505065,
442
+ "grad_norm": 1.078498125076294,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.8777,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.0067711946718468155,
449
+ "grad_norm": 0.9189152717590332,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.7924,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.006882197863188566,
456
+ "grad_norm": 1.011573314666748,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.9122,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.006993201054530318,
463
+ "grad_norm": 1.0407687425613403,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.8104,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.007104204245872069,
470
+ "grad_norm": 1.0033093690872192,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.9252,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.00721520743721382,
477
+ "grad_norm": 0.919106662273407,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.7244,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.007326210628555571,
484
+ "grad_norm": 0.9753147959709167,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.7824,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.007437213819897322,
491
+ "grad_norm": 0.9869587421417236,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.7801,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.007548217011239073,
498
+ "grad_norm": 1.0366357564926147,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.821,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.007659220202580824,
505
+ "grad_norm": 1.1145334243774414,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.8619,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.007770223393922576,
512
+ "grad_norm": 1.2978206872940063,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.9037,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.007881226585264326,
519
+ "grad_norm": 1.1509613990783691,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.7544,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.007992229776606078,
526
+ "grad_norm": 1.0371291637420654,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.7826,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.008103232967947828,
533
+ "grad_norm": 1.0573813915252686,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.7808,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.00821423615928958,
540
+ "grad_norm": 1.2486634254455566,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.6838,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.008325239350631331,
547
+ "grad_norm": 1.2400583028793335,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.8826,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.008436242541973081,
554
+ "grad_norm": 1.0707412958145142,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.7261,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.008547245733314833,
561
+ "grad_norm": 1.325318455696106,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.9285,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.008658248924656584,
568
+ "grad_norm": 1.3431965112686157,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.9954,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.008769252115998334,
575
+ "grad_norm": 1.395011305809021,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.8256,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.008880255307340086,
582
+ "grad_norm": 1.2236677408218384,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.8649,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.008991258498681837,
589
+ "grad_norm": 1.3813550472259521,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.7499,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.009102261690023589,
596
+ "grad_norm": 1.1952629089355469,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.7567,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.009213264881365339,
603
+ "grad_norm": 1.1774139404296875,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.5969,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.00932426807270709,
610
+ "grad_norm": 1.3768928050994873,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.7333,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.009435271264048842,
617
+ "grad_norm": 1.5121829509735107,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.8053,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.009546274455390592,
624
+ "grad_norm": 1.3658143281936646,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.8026,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.009657277646732344,
631
+ "grad_norm": 1.400071620941162,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.6916,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.009768280838074095,
638
+ "grad_norm": 1.3228888511657715,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.7051,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.009879284029415845,
645
+ "grad_norm": 1.5070359706878662,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.8033,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.009990287220757597,
652
+ "grad_norm": 1.335098147392273,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.7683,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.010101290412099348,
659
+ "grad_norm": 1.4469175338745117,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.5573,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.010212293603441098,
666
+ "grad_norm": 1.5435446500778198,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.7527,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.01032329679478285,
673
+ "grad_norm": 1.571133017539978,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.797,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.010434299986124601,
680
+ "grad_norm": 1.4781806468963623,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.7084,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.010545303177466351,
687
+ "grad_norm": 1.586531162261963,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.7317,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.010656306368808103,
694
+ "grad_norm": 1.778027892112732,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.6611,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.010767309560149855,
701
+ "grad_norm": 1.9934014081954956,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.0245,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.010878312751491606,
708
+ "grad_norm": 2.2396204471588135,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.8315,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.010989315942833356,
715
+ "grad_norm": 2.139233350753784,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.6726,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.011100319134175108,
722
+ "grad_norm": 2.108496904373169,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.6403,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.011100319134175108,
729
+ "eval_loss": 0.8000498414039612,
730
+ "eval_runtime": 1145.8791,
731
+ "eval_samples_per_second": 13.241,
732
+ "eval_steps_per_second": 3.311,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.5122848626927206e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null