Hugging Face's logo

lesso11
/
fde22031-44ea-43f8-ac1d-6bebbfde5d49

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso11 commited on
Commit
d27acd5
·
verified ·
1 Parent(s): dac4edd

Training in progress, step 75, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +202 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83ba0a32fc5c864b61e84423197483a72737f7b84cfdb3f57f4d2b90b24d7c34
3
  size 50624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13946f5153cfffe605d7dada89e9524858029bfe128cea35d2992dad8954cf85
3
  size 50624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97970cef5619ce89b5b9a8bfce176e7827f6594bbc7fbd8365a86930e5552bfd
3
  size 118090
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32ba03b6f01f56bcce4c761c15a6d6bd51867f7176a001d8afc606ab93b9274c
3
  size 118090
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33752213e91e5d9daaf41b0e911b3b2623b16a8672150d6b365a88ada68018bd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4e42707bff3a01dd441022647b82d0d244a8f2409373d258e9184fc37cc91af
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.0831255195344971,
5
  "eval_steps": 9,
6
- "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -405,6 +405,205 @@
405
  "learning_rate": 5.868240888334653e-05,
406
  "loss": 11.754,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 10185002188800.0,
428
  "train_batch_size": 8,
429
  "trial_name": null,
430
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.12468827930174564,
5
  "eval_steps": 9,
6
+ "global_step": 75,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
405
  "learning_rate": 5.868240888334653e-05,
406
  "loss": 11.754,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.08478802992518704,
411
+ "grad_norm": 0.0709136351943016,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 11.756,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.08645054031587697,
418
+ "grad_norm": 0.05604271590709686,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 11.7583,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.08811305070656691,
425
+ "grad_norm": 0.06510225683450699,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 11.7568,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.08977556109725686,
432
+ "grad_norm": 0.06891396641731262,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 11.7463,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.08977556109725686,
439
+ "eval_loss": 11.756059646606445,
440
+ "eval_runtime": 10.8526,
441
+ "eval_samples_per_second": 46.717,
442
+ "eval_steps_per_second": 5.897,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.0914380714879468,
447
+ "grad_norm": 0.05632815137505531,
448
+ "learning_rate": 5e-05,
449
+ "loss": 11.7531,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.09310058187863675,
454
+ "grad_norm": 0.0708206370472908,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 11.7558,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.09476309226932668,
461
+ "grad_norm": 0.08333998173475266,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 11.7516,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.09642560266001662,
468
+ "grad_norm": 0.06372737884521484,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 11.7488,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.09808811305070657,
475
+ "grad_norm": 0.05615927651524544,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 11.7482,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.09975062344139651,
482
+ "grad_norm": 0.0624222457408905,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 11.7565,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.10141313383208644,
489
+ "grad_norm": 0.06704821437597275,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 11.7547,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.10307564422277639,
496
+ "grad_norm": 0.09131279587745667,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 11.7494,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.10473815461346633,
503
+ "grad_norm": 0.06280036270618439,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 11.7585,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.10473815461346633,
510
+ "eval_loss": 11.755424499511719,
511
+ "eval_runtime": 10.8532,
512
+ "eval_samples_per_second": 46.714,
513
+ "eval_steps_per_second": 5.897,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.10640066500415628,
518
+ "grad_norm": 0.07713477313518524,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 11.7581,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.10806317539484622,
525
+ "grad_norm": 0.080855593085289,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 11.7548,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.10972568578553615,
532
+ "grad_norm": 0.06689275801181793,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 11.7557,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.1113881961762261,
539
+ "grad_norm": 0.0768292099237442,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 11.7577,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.11305070656691604,
546
+ "grad_norm": 0.052165545523166656,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 11.7578,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.11471321695760599,
553
+ "grad_norm": 0.07575516402721405,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 11.7549,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.11637572734829593,
560
+ "grad_norm": 0.05817292258143425,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 11.7565,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.11803823773898586,
567
+ "grad_norm": 0.07991883158683777,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 11.7516,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.11970074812967581,
574
+ "grad_norm": 0.06573547422885895,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 11.7566,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.11970074812967581,
581
+ "eval_loss": 11.754947662353516,
582
+ "eval_runtime": 10.8431,
583
+ "eval_samples_per_second": 46.758,
584
+ "eval_steps_per_second": 5.902,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.12136325852036575,
589
+ "grad_norm": 0.07040063291788101,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 11.7524,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.1230257689110557,
596
+ "grad_norm": 0.05799221619963646,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 11.7536,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.12468827930174564,
603
+ "grad_norm": 0.06470559537410736,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 11.7533,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 15277503283200.0,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null