Hugging Face's logo

lesso11
/
650f6b00-aa88-4851-8c12-6af3c6d61932

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso11 commited on
Commit
45d4f01
•
1 Parent(s): ca6bdd3

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 sha256:710ccb049fdaffaf8fce1380862bdac948ded73a52ed5ed9054c95634fde3e3a
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9ecb935822deefa465591ce47b7057fe71ccd90a32293e3b0275d3517110f64
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f171b131291604025ad57072b26d135af815ce58bbb9f25a807601e0e928a7d
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9887b56fbfafc91c0755c86a8c4decf8cff31d3d6504b0da4ebccc2d1bfe5ca
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:828a7e6e11ce6fb1a2356180954a5b20df0e28e99bfb6b79a96217eb20a3be28
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeda752780d4d1e2c8cc72596036685baf31024a594da9ff5aea8a1a54a0f80c
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": 0.24213075060532688,
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": 3.1599,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 3.70943641780224e+16,
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": 0.36319612590799033,
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": 3.1599,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.2469733656174334,
411
+ "grad_norm": 1.263146996498108,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 2.975,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.25181598062953997,
418
+ "grad_norm": 3.4207539558410645,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 3.4015,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.2566585956416465,
425
+ "grad_norm": 1.5546566247940063,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 2.9378,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.26150121065375304,
432
+ "grad_norm": 2.120374917984009,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 2.9896,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.26150121065375304,
439
+ "eval_loss": 3.084446668624878,
440
+ "eval_runtime": 18.926,
441
+ "eval_samples_per_second": 9.194,
442
+ "eval_steps_per_second": 1.162,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.26634382566585957,
447
+ "grad_norm": 1.9824186563491821,
448
+ "learning_rate": 5e-05,
449
+ "loss": 3.0358,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.2711864406779661,
454
+ "grad_norm": 1.7688870429992676,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 3.1711,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.27602905569007263,
461
+ "grad_norm": 2.102198839187622,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 3.4714,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.28087167070217917,
468
+ "grad_norm": 1.664321780204773,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 3.0841,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.2857142857142857,
475
+ "grad_norm": 2.4341115951538086,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 3.2948,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.29055690072639223,
482
+ "grad_norm": 0.9612340927124023,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 2.9165,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.29539951573849876,
489
+ "grad_norm": 1.2795825004577637,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 3.1389,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.30024213075060535,
496
+ "grad_norm": 0.9679549932479858,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 2.9197,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.3050847457627119,
503
+ "grad_norm": 1.515199899673462,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 3.0526,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.3050847457627119,
510
+ "eval_loss": 3.055881977081299,
511
+ "eval_runtime": 18.9316,
512
+ "eval_samples_per_second": 9.191,
513
+ "eval_steps_per_second": 1.162,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.3099273607748184,
518
+ "grad_norm": 1.8831665515899658,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 3.1823,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.31476997578692495,
525
+ "grad_norm": 1.6448265314102173,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 2.922,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.3196125907990315,
532
+ "grad_norm": 1.7221674919128418,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 3.2304,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.324455205811138,
539
+ "grad_norm": 1.9639180898666382,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 3.296,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.32929782082324455,
546
+ "grad_norm": 1.215235710144043,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 2.6854,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.3341404358353511,
553
+ "grad_norm": 2.490431785583496,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 3.0375,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.3389830508474576,
560
+ "grad_norm": 1.9049839973449707,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 3.2666,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.34382566585956414,
567
+ "grad_norm": 1.5522865056991577,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 2.8866,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.3486682808716707,
574
+ "grad_norm": 1.4543166160583496,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 3.0314,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.3486682808716707,
581
+ "eval_loss": 3.0360867977142334,
582
+ "eval_runtime": 18.9447,
583
+ "eval_samples_per_second": 9.185,
584
+ "eval_steps_per_second": 1.161,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.35351089588377727,
589
+ "grad_norm": 3.4857094287872314,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 3.3805,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.3583535108958838,
596
+ "grad_norm": 1.6463013887405396,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 3.0626,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.36319612590799033,
603
+ "grad_norm": 1.6041393280029297,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 2.9819,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 5.56415462670336e+16,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null