Hugging Face's logo

lesso02
/
0ea11aa7-80f1-4ede-aefe-8252d0840afc

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso02 commited on
Commit
8c6b166
·
verified ·
1 Parent(s): 3aebd54

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 sha256:81a0d27178da9a66836da6f11cea143dfdcc2650eaffa54509fdf22d6fc88ffd
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79e6e1f47a7c01ef37762658f2562a130b4969acfdc6cdaeae0892faccf6e306
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d03b2e42dda809adfa2a10f7f5c16f86511073646850c8e3668f98c6f5f612f8
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af035ac60441adec8aaf248768c8462992cd4faa60bcfff3cfd45ad8a1bb7ca0
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:510f9e5b7272ae4aba6beb222480f0e50fec01ede841c869e490ed27fbca1e1a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d02cb420ffbe4bfa74ec929339f92e110525992fececf073c0ca01e03bfa1c21
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": 0.3787878787878788,
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": 0.9869,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 6.565702459509965e+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": 0.5681818181818182,
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": 0.9869,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.38636363636363635,
411
+ "grad_norm": 0.5107312798500061,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 1.1914,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.3939393939393939,
418
+ "grad_norm": 0.9764262437820435,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 1.3385,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.4015151515151515,
425
+ "grad_norm": 0.8512474894523621,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 0.8658,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.4090909090909091,
432
+ "grad_norm": 0.7570309638977051,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 1.8693,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.4090909090909091,
439
+ "eval_loss": 1.3887274265289307,
440
+ "eval_runtime": 19.3267,
441
+ "eval_samples_per_second": 5.743,
442
+ "eval_steps_per_second": 0.724,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.4166666666666667,
447
+ "grad_norm": 0.48338302969932556,
448
+ "learning_rate": 5e-05,
449
+ "loss": 1.1701,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.42424242424242425,
454
+ "grad_norm": 4.494511127471924,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 1.3139,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.4318181818181818,
461
+ "grad_norm": 0.8095260858535767,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 1.2047,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.4393939393939394,
468
+ "grad_norm": 1.4627423286437988,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 1.2054,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.44696969696969696,
475
+ "grad_norm": 1.4437791109085083,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 1.3913,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.45454545454545453,
482
+ "grad_norm": 0.6056512594223022,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 1.1049,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.4621212121212121,
489
+ "grad_norm": 1.0000839233398438,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 0.7936,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.4696969696969697,
496
+ "grad_norm": 0.6748735308647156,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 1.2368,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.4772727272727273,
503
+ "grad_norm": 0.5631169080734253,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 0.996,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.4772727272727273,
510
+ "eval_loss": 1.3775228261947632,
511
+ "eval_runtime": 19.3436,
512
+ "eval_samples_per_second": 5.738,
513
+ "eval_steps_per_second": 0.724,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.48484848484848486,
518
+ "grad_norm": 0.7982277274131775,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 0.9235,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.49242424242424243,
525
+ "grad_norm": 0.6029773354530334,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 1.176,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.5,
532
+ "grad_norm": 0.6423137784004211,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 1.2562,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.5075757575757576,
539
+ "grad_norm": 0.9672674536705017,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 2.1069,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.5151515151515151,
546
+ "grad_norm": 0.7522253394126892,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 1.7731,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.5227272727272727,
553
+ "grad_norm": 0.8013143539428711,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 1.9471,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.5303030303030303,
560
+ "grad_norm": 1.507096767425537,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 1.9572,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.5378787878787878,
567
+ "grad_norm": 1.2770590782165527,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 1.3016,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.5454545454545454,
574
+ "grad_norm": 0.7512741684913635,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 0.9932,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.5454545454545454,
581
+ "eval_loss": 1.3720847368240356,
582
+ "eval_runtime": 19.3385,
583
+ "eval_samples_per_second": 5.74,
584
+ "eval_steps_per_second": 0.724,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.553030303030303,
589
+ "grad_norm": 1.2508105039596558,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 1.5886,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.5606060606060606,
596
+ "grad_norm": 1.4357924461364746,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 1.2307,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.5681818181818182,
603
+ "grad_norm": 1.215354084968567,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 2.2534,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 9.90419523553198e+16,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null