Hugging Face's logo

lesso06
/
a358aca3-dd6a-48d2-8db4-2aeff72ecba3

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso06 commited on
Commit
fe3e76c
•
1 Parent(s): facbf7e

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:d1095df55485e28fe8bae34151699b2f3c4cc5e7715422d3816aea806e6c762e
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42a514cdeb120aed303b662a0bff1bc37714c1a3e8e4bf959710348c79303228
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07e1d52623dd72226079bfa03cb9efc8b3b678cb5c3fae3d4ddec31f33f9788e
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90579d74ab72c7f1650e62c917414eead63bba958fa246f22c20aa4d2687c83e
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": 0.0025842464337399213,
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": 0.0498,
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": 0.003876369650609882,
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": 0.0498,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.00263593136241472,
411
+ "grad_norm": 1.597001314163208,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 0.1898,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.0026876162910895183,
418
+ "grad_norm": 1.0472426414489746,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 0.0887,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.0027393012197643165,
425
+ "grad_norm": 1.2370333671569824,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 0.1294,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.0027909861484391152,
432
+ "grad_norm": 0.623787522315979,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 0.0634,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.0027909861484391152,
439
+ "eval_loss": 0.0726623609662056,
440
+ "eval_runtime": 2001.9362,
441
+ "eval_samples_per_second": 8.139,
442
+ "eval_steps_per_second": 1.018,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.0028426710771139135,
447
+ "grad_norm": 0.5839661359786987,
448
+ "learning_rate": 5e-05,
449
+ "loss": 0.0676,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.002894356005788712,
454
+ "grad_norm": 0.7963717579841614,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 0.0728,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.0029460409344635105,
461
+ "grad_norm": 0.5084842443466187,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 0.0732,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.002997725863138309,
468
+ "grad_norm": 0.5992403030395508,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 0.0716,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.0030494107918131075,
475
+ "grad_norm": 0.4697546064853668,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 0.0616,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.0031010957204879058,
482
+ "grad_norm": 0.6336478590965271,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 0.0646,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.003152780649162704,
489
+ "grad_norm": 0.6779618859291077,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 0.0735,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.0032044655778375028,
496
+ "grad_norm": 0.4873669147491455,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 0.0753,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.003256150506512301,
503
+ "grad_norm": 0.5097606182098389,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 0.0668,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.003256150506512301,
510
+ "eval_loss": 0.06682123243808746,
511
+ "eval_runtime": 2001.2998,
512
+ "eval_samples_per_second": 8.141,
513
+ "eval_steps_per_second": 1.018,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.0033078354351870993,
518
+ "grad_norm": 0.5775445699691772,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 0.053,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.003359520363861898,
525
+ "grad_norm": 0.6833822727203369,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 0.0524,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.0034112052925366963,
532
+ "grad_norm": 0.43024009466171265,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 0.0691,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.0034628902212114946,
539
+ "grad_norm": 0.43755966424942017,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 0.0623,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.0035145751498862933,
546
+ "grad_norm": 0.5165156126022339,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 0.0588,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.0035662600785610916,
553
+ "grad_norm": 0.43913787603378296,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 0.0672,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.00361794500723589,
560
+ "grad_norm": 0.5426086187362671,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 0.0544,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.0036696299359106886,
567
+ "grad_norm": 0.7457218766212463,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 0.0689,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.003721314864585487,
574
+ "grad_norm": 0.5793647766113281,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 0.0476,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.003721314864585487,
581
+ "eval_loss": 0.06450506299734116,
582
+ "eval_runtime": 2001.6572,
583
+ "eval_samples_per_second": 8.14,
584
+ "eval_steps_per_second": 1.018,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.003772999793260285,
589
+ "grad_norm": 0.3593558967113495,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 0.0443,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.003824684721935084,
596
+ "grad_norm": 0.4152470827102661,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 0.0503,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.003876369650609882,
603
+ "grad_norm": 0.6307422518730164,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 0.0658,
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