Hugging Face's logo

lesso06
/
469a38ab-62f1-4bec-a86f-f84336a58e49

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso06 commited on
Commit
1b5738c
•
1 Parent(s): 3d2f813

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 sha256:782d68c77b317b289b6d064726556dfc03f3a29ebd9c21d70aa692d258d8b94c
3
  size 45118424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6fdf6dd9d1f4d4b9cd88d1b93b4d823d7b339663307f6b0b46b5ada3ee3a91e
3
  size 45118424
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de90258827ac1c1224a803c0178e47d2d8107e47d789509d370e78f588aeaa3e
3
  size 90365754
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15b2dc95425d7b4589fcda2c3fb2c2dfe7735f6107df9fdfa3cd94066b198146
3
  size 90365754
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7da9f1139f61cc766662dec9be1a789e9af6ce81829e82037fdc4fc6fe2c5c18
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5ffb3bbcae13d3c8fcd45cf15a774d6b9dbb4edf8a95da70978b37d6d5b2b51
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": 0.05737234652897304,
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": 0.0247,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 8322414098251776.0,
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": 0.08605851979345955,
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": 0.0247,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.058519793459552494,
411
+ "grad_norm": 0.18079611659049988,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 0.0215,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.05966724039013196,
418
+ "grad_norm": 0.12951500713825226,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 0.0297,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.060814687320711415,
425
+ "grad_norm": 0.12222294509410858,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 0.0202,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.06196213425129088,
432
+ "grad_norm": 0.13354460895061493,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 0.0278,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.06196213425129088,
439
+ "eval_loss": 0.025066262111067772,
440
+ "eval_runtime": 41.5419,
441
+ "eval_samples_per_second": 17.669,
442
+ "eval_steps_per_second": 2.215,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.06310958118187034,
447
+ "grad_norm": 0.18413366377353668,
448
+ "learning_rate": 5e-05,
449
+ "loss": 0.0195,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.0642570281124498,
454
+ "grad_norm": 0.25024259090423584,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 0.0287,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.06540447504302926,
461
+ "grad_norm": 0.12252403795719147,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 0.0268,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.06655192197360872,
468
+ "grad_norm": 0.16308040916919708,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 0.0279,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.06769936890418818,
475
+ "grad_norm": 0.13704562187194824,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 0.0157,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.06884681583476764,
482
+ "grad_norm": 0.12924720346927643,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 0.0219,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.0699942627653471,
489
+ "grad_norm": 0.12658867239952087,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 0.02,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.07114170969592656,
496
+ "grad_norm": 0.22576895356178284,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 0.0258,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.07228915662650602,
503
+ "grad_norm": 0.15099763870239258,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 0.0212,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.07228915662650602,
510
+ "eval_loss": 0.024402011185884476,
511
+ "eval_runtime": 41.4179,
512
+ "eval_samples_per_second": 17.722,
513
+ "eval_steps_per_second": 2.221,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.07343660355708548,
518
+ "grad_norm": 0.1566763073205948,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 0.0128,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.07458405048766495,
525
+ "grad_norm": 0.1659335196018219,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 0.0175,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.0757314974182444,
532
+ "grad_norm": 0.210612952709198,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 0.0272,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.07687894434882386,
539
+ "grad_norm": 0.13868023455142975,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 0.0214,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.07802639127940333,
546
+ "grad_norm": 0.1765725314617157,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 0.0265,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.07917383820998279,
553
+ "grad_norm": 0.24902477860450745,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 0.0297,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.08032128514056225,
560
+ "grad_norm": 0.29836687445640564,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 0.0404,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.0814687320711417,
567
+ "grad_norm": 0.19871705770492554,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 0.026,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.08261617900172118,
574
+ "grad_norm": 0.19763556122779846,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 0.0242,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.08261617900172118,
581
+ "eval_loss": 0.023439526557922363,
582
+ "eval_runtime": 41.6199,
583
+ "eval_samples_per_second": 17.636,
584
+ "eval_steps_per_second": 2.21,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.08376362593230063,
589
+ "grad_norm": 0.19204814732074738,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 0.0244,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.08491107286288009,
596
+ "grad_norm": 0.09625480324029922,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 0.0158,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.08605851979345955,
603
+ "grad_norm": 0.2161574512720108,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 0.0282,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 1.2628779532812288e+16,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null