nttx commited on
Commit
83a9ecf
·
verified ·
1 Parent(s): ed75adf

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:d9434ae7861922fd31fa47661e97b5d84a2360306d79d7b140907ecdec0be868
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:845ab66162e290bbc503ead1fc26378054da32e6780091212111a14890d22af2
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d42291ea6427c6a8d226683cce19d4465e95cd3ead81b676f4aa7b2c91b0176
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:999444773cb6037a39e0487aa548e8d4905f1c316af750b8a2aa560fe94ed3e5
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:db2c76246d2f8ebe039d89bd73e8004fc053327c1a4b5cbf6ef9e45b2df3dabd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:116bfafc53348ca05cab17424413b1375849e2553733eacad29d83866b3f7549
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": 1.732652187347412,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.02464268112370626,
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": 13.093,
374
  "eval_steps_per_second": 3.276,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.22654807898194e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.431005597114563,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.04928536224741252,
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": 13.093,
374
  "eval_steps_per_second": 3.276,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.025135534746180386,
379
+ "grad_norm": 35.06370544433594,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 7.3535,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.025628388368654508,
386
+ "grad_norm": 7.263309001922607,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 6.6987,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.026121241991128634,
393
+ "grad_norm": 4.144477844238281,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 5.9729,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.02661409561360276,
400
+ "grad_norm": 3.6691770553588867,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 6.0169,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.027106949236076885,
407
+ "grad_norm": 3.6410415172576904,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 5.9244,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.02759980285855101,
414
+ "grad_norm": 3.8702380657196045,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 6.2104,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.028092656481025137,
421
+ "grad_norm": 3.817110776901245,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 5.8548,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.02858551010349926,
428
+ "grad_norm": 7.407201290130615,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 5.5015,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.029078363725973385,
435
+ "grad_norm": 5.8004984855651855,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 5.5889,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.02957121734844751,
442
+ "grad_norm": 4.282701015472412,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 5.8837,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.030064070970921637,
449
+ "grad_norm": 4.238832950592041,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 5.9101,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.030556924593395762,
456
+ "grad_norm": 4.113567352294922,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 5.9194,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.031049778215869888,
463
+ "grad_norm": 4.071282386779785,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 5.705,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.031542631838344014,
470
+ "grad_norm": 3.9348578453063965,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 5.9225,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.032035485460818136,
477
+ "grad_norm": 6.435613632202148,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 5.9364,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.032528339083292265,
484
+ "grad_norm": 5.112850666046143,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 5.9065,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.03302119270576639,
491
+ "grad_norm": 4.052131175994873,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 5.6007,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.03351404632824051,
498
+ "grad_norm": 3.9013149738311768,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 5.6739,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.03400689995071464,
505
+ "grad_norm": 4.061436653137207,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 5.5508,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.03449975357318876,
512
+ "grad_norm": 4.149789333343506,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 5.8792,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.03499260719566289,
519
+ "grad_norm": 3.755802869796753,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 5.2883,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.03548546081813701,
526
+ "grad_norm": 3.9959685802459717,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 5.8289,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.035978314440611135,
533
+ "grad_norm": 4.5482072830200195,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 5.5595,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.036471168063085264,
540
+ "grad_norm": 4.273440361022949,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 5.7877,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.03696402168555939,
547
+ "grad_norm": 4.279988765716553,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 5.7015,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.037456875308033516,
554
+ "grad_norm": 3.8421711921691895,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 5.6129,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.03794972893050764,
561
+ "grad_norm": 4.161666393280029,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 5.6966,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.03844258255298177,
568
+ "grad_norm": 4.275053977966309,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 5.7704,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.03893543617545589,
575
+ "grad_norm": 4.343554496765137,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 5.9121,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.03942828979793001,
582
+ "grad_norm": 4.524814128875732,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 5.6133,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.03992114342040414,
589
+ "grad_norm": 4.053195953369141,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 5.8539,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.040413997042878264,
596
+ "grad_norm": 4.116884231567383,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 5.6884,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.04090685066535239,
603
+ "grad_norm": 4.242743492126465,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 5.6097,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.041399704287826515,
610
+ "grad_norm": 4.237097263336182,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 5.7156,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.04189255791030064,
617
+ "grad_norm": 4.75575590133667,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 5.6946,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.04238541153277477,
624
+ "grad_norm": 4.682205677032471,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 5.7993,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.04287826515524889,
631
+ "grad_norm": 4.896819591522217,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 6.1002,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.04337111877772302,
638
+ "grad_norm": 4.500687599182129,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 5.5547,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.04386397240019714,
645
+ "grad_norm": 4.486171722412109,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 5.5062,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.04435682602267127,
652
+ "grad_norm": 4.3436737060546875,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 5.5787,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.04484967964514539,
659
+ "grad_norm": 4.709849834442139,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 5.8669,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.045342533267619514,
666
+ "grad_norm": 4.942005634307861,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 5.7457,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.04583538689009364,
673
+ "grad_norm": 4.71359920501709,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 5.8917,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.046328240512567766,
680
+ "grad_norm": 4.906127452850342,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 6.1047,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.046821094135041895,
687
+ "grad_norm": 4.9009504318237305,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 5.6463,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.04731394775751602,
694
+ "grad_norm": 5.0316853523254395,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 5.982,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.04780680137999014,
701
+ "grad_norm": 5.0484299659729,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 5.7041,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.04829965500246427,
708
+ "grad_norm": 5.215059280395508,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 5.9011,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.04879250862493839,
715
+ "grad_norm": 5.8646955490112305,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 6.112,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.04928536224741252,
722
+ "grad_norm": 6.156351089477539,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 5.9004,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.04928536224741252,
729
+ "eval_loss": 1.431005597114563,
730
+ "eval_runtime": 261.684,
731
+ "eval_samples_per_second": 13.058,
732
+ "eval_steps_per_second": 3.267,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.441732116747387e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null