Hugging Face's logo

lesso01
/
fee883ac-1b9e-4499-b8db-0908baaca52e

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso01 commited on
Commit
900a71d
•
1 Parent(s): a8be1e4

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 sha256:08d64a4bb43242d4c403d27ddb407d4e18311c02495986c7ac9b34fa990b4e52
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf5313c9de80553f97d62783c0e1495835981f083ae701770d222e18a973973d
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2eee7058997c4fe9b77bdb64b6dc93eec5a74e984b24ccc1ab51ddd3339f2099
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:458be46e7ac05a18391ea4dd140c46a5561fe6e1a242fde3488e581a747ed8ec
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4253dace03c2bbc93981228fd26ac6c0cd235e555b7edb4597567f488ad8806f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecbf52846b0950d1b0204ef5064ad518cb02596007e36540f5b060f1237792f0
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": 0.06765899864682003,
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": 0.0058,
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": 0.10148849797023005,
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": 0.0058,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.06901217861975643,
411
+ "grad_norm": 0.0919797345995903,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 0.0045,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.07036535859269283,
418
+ "grad_norm": 0.05789254978299141,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 0.0048,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.07171853856562922,
425
+ "grad_norm": 0.18244007229804993,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 0.0155,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.07307171853856563,
432
+ "grad_norm": 0.6028981804847717,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 0.1107,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.07307171853856563,
439
+ "eval_loss": 0.018029918894171715,
440
+ "eval_runtime": 32.6237,
441
+ "eval_samples_per_second": 19.097,
442
+ "eval_steps_per_second": 2.391,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.07442489851150202,
447
+ "grad_norm": 0.5009127855300903,
448
+ "learning_rate": 5e-05,
449
+ "loss": 0.0893,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.07577807848443843,
454
+ "grad_norm": 0.04764901474118233,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 0.0064,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.07713125845737483,
461
+ "grad_norm": 0.8551574945449829,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 0.1503,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.07848443843031123,
468
+ "grad_norm": 0.0777273029088974,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 0.005,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.07983761840324763,
475
+ "grad_norm": 0.6547033786773682,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 0.1104,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.08119079837618404,
482
+ "grad_norm": 0.15890103578567505,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 0.0155,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.08254397834912043,
489
+ "grad_norm": 1.0533157587051392,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 0.1344,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.08389715832205684,
496
+ "grad_norm": 0.13047480583190918,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 0.0116,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.08525033829499323,
503
+ "grad_norm": 0.14830543100833893,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 0.0111,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.08525033829499323,
510
+ "eval_loss": 0.01703736186027527,
511
+ "eval_runtime": 32.5933,
512
+ "eval_samples_per_second": 19.114,
513
+ "eval_steps_per_second": 2.393,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.08660351826792964,
518
+ "grad_norm": 0.10914517939090729,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 0.008,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.08795669824086604,
525
+ "grad_norm": 0.13250844180583954,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 0.0078,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.08930987821380243,
532
+ "grad_norm": 0.14327938854694366,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 0.0085,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.09066305818673884,
539
+ "grad_norm": 0.14970730245113373,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 0.0042,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.09201623815967523,
546
+ "grad_norm": 0.08402867615222931,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 0.0104,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.09336941813261164,
553
+ "grad_norm": 0.08050940930843353,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 0.005,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.09472259810554803,
560
+ "grad_norm": 0.5739089250564575,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 0.0547,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.09607577807848444,
567
+ "grad_norm": 0.11337218433618546,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 0.0091,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.09742895805142084,
574
+ "grad_norm": 0.06483836472034454,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 0.0072,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.09742895805142084,
581
+ "eval_loss": 0.015148372389376163,
582
+ "eval_runtime": 32.5938,
583
+ "eval_samples_per_second": 19.114,
584
+ "eval_steps_per_second": 2.393,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.09878213802435724,
589
+ "grad_norm": 0.12975576519966125,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 0.0114,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.10013531799729364,
596
+ "grad_norm": 0.08989189565181732,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 0.0041,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.10148849797023005,
603
+ "grad_norm": 0.6734408140182495,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 0.0926,
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