Hugging Face's logo

lesso04
/
20cfda91-55bd-48fb-8be0-a2c68d1d33d8

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso04 commited on
Commit
15bed22
·
verified ·
1 Parent(s): 84a91c4

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 sha256:05f5749d350049ec9b5a63a1a8775eb8ce8bff49a225f809f56ebe1bbc66ed7e
3
  size 13587864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f32b21467a29485c7b2128b4a71b1d47284c09cde5d76664b7ae4b6ee1daaaa4
3
  size 13587864
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:585161e71fe20c2f2c44d16e0523cd55fc7a79468697cd65434b8f863b671533
3
  size 27273018
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ceb14edd1c39d45d959f38ce4377987ac6cd4755d0603854e0ed8f9605f3711
3
  size 27273018
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:870ade4a4e3d55877d26589aaae85a5d2c1b1111fc0b69288c21885a3e103062
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:509f56cf0ca61682fbd67e154f38de895f0045bcf99ce0b8c283801f600a9995
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": 0.0032938076416337285,
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": 1.68,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 1055165654237184.0,
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": 0.004940711462450593,
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": 1.68,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.0033596837944664033,
411
+ "grad_norm": 3.5803892612457275,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 1.7835,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.0034255599472990776,
418
+ "grad_norm": 3.1176340579986572,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 1.5672,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.0034914361001317524,
425
+ "grad_norm": 2.987795114517212,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 1.4914,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.0035573122529644267,
432
+ "grad_norm": 6.246347427368164,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 1.5927,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.0035573122529644267,
439
+ "eval_loss": 1.4257876873016357,
440
+ "eval_runtime": 184.4229,
441
+ "eval_samples_per_second": 69.319,
442
+ "eval_steps_per_second": 8.665,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.0036231884057971015,
447
+ "grad_norm": 3.4647183418273926,
448
+ "learning_rate": 5e-05,
449
+ "loss": 1.4436,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.003689064558629776,
454
+ "grad_norm": 3.349560499191284,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 1.3829,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.0037549407114624506,
461
+ "grad_norm": 3.176090955734253,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 1.2451,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.0038208168642951254,
468
+ "grad_norm": 3.0225908756256104,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 1.3579,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.0038866930171277997,
475
+ "grad_norm": 2.4458398818969727,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 1.101,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.003952569169960474,
482
+ "grad_norm": 3.876741886138916,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 1.3687,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.004018445322793149,
489
+ "grad_norm": 3.945711374282837,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 1.1523,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.004084321475625824,
496
+ "grad_norm": 3.1722943782806396,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 0.9701,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.004150197628458498,
503
+ "grad_norm": 4.902099609375,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 0.9159,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.004150197628458498,
510
+ "eval_loss": 1.0228184461593628,
511
+ "eval_runtime": 184.3336,
512
+ "eval_samples_per_second": 69.353,
513
+ "eval_steps_per_second": 8.669,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.004216073781291172,
518
+ "grad_norm": 2.736250400543213,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 0.9313,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.004281949934123847,
525
+ "grad_norm": 2.595193862915039,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 0.9,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.004347826086956522,
532
+ "grad_norm": 1.9990233182907104,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 0.8328,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.0044137022397891966,
539
+ "grad_norm": 4.0702223777771,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 1.0872,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.0044795783926218705,
546
+ "grad_norm": 1.7851134538650513,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 0.8029,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.004545454545454545,
553
+ "grad_norm": 2.5434176921844482,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 0.835,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.00461133069828722,
560
+ "grad_norm": 3.252372980117798,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 0.8726,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.004677206851119895,
567
+ "grad_norm": 1.7027548551559448,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 0.7541,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.0047430830039525695,
574
+ "grad_norm": 2.5379581451416016,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 0.8231,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.0047430830039525695,
581
+ "eval_loss": 0.8483124375343323,
582
+ "eval_runtime": 184.3066,
583
+ "eval_samples_per_second": 69.363,
584
+ "eval_steps_per_second": 8.67,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.0048089591567852434,
589
+ "grad_norm": 1.877734899520874,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 0.7158,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.004874835309617918,
596
+ "grad_norm": 1.7974519729614258,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 0.7645,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.004940711462450593,
603
+ "grad_norm": 4.693776607513428,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 1.0939,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 1548039084834816.0,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null