Hugging Face's logo

lesso11
/
dcfbb7ff-4cba-4097-8c27-876925909644

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso11 commited on
Commit
526b742
·
verified ·
1 Parent(s): 6f2ed79

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 sha256:1aa35fb39b2e75c94fedc4fc74f5b1fc70bf16aefc66ead64c47cdf0e79b1e25
3
  size 13587864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee973b61fb6827b54356447d901e570efdcbca7180e20d6ae56614bde4b35533
3
  size 13587864
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12074d34bcce312ded1383decb51bc38e258ce3992f16b288cb27751eb930a43
3
  size 27273018
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2794508ae46cf73d24cd868783910af8465280cccf4dc02ce60d7a6608e2c8e3
3
  size 27273018
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05f8d8c64896b75aa08caf4a3a052d9d1d276898c69cfdf38186ab3c0d3fde81
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38b1a2d570362d5fe7bbb15687da3c63cd96031cb350ed30b48bd64ead1a0b67
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": 0.08340283569641367,
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": 2.5161,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 694187930419200.0,
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": 0.12510425354462051,
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": 2.5161,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.08507089241034195,
411
+ "grad_norm": 5.465274333953857,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 2.5525,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.08673894912427023,
418
+ "grad_norm": 3.293487787246704,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 2.0532,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.0884070058381985,
425
+ "grad_norm": 2.6559829711914062,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 1.8814,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.09007506255212677,
432
+ "grad_norm": 2.6199533939361572,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 1.838,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.09007506255212677,
439
+ "eval_loss": 1.9475644826889038,
440
+ "eval_runtime": 4.4657,
441
+ "eval_samples_per_second": 113.085,
442
+ "eval_steps_per_second": 14.332,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.09174311926605505,
447
+ "grad_norm": 3.225780963897705,
448
+ "learning_rate": 5e-05,
449
+ "loss": 1.9229,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.09341117597998332,
454
+ "grad_norm": 3.074723958969116,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 1.8347,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.0950792326939116,
461
+ "grad_norm": 3.197967290878296,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 1.7263,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.09674728940783987,
468
+ "grad_norm": 4.160449504852295,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 2.0481,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.09841534612176814,
475
+ "grad_norm": 3.7194972038269043,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 1.8318,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.10008340283569642,
482
+ "grad_norm": 2.449399709701538,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 1.5901,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.10175145954962468,
489
+ "grad_norm": 3.4351389408111572,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 1.5641,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.10341951626355296,
496
+ "grad_norm": 3.361947774887085,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 1.578,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.10508757297748124,
503
+ "grad_norm": 3.230473279953003,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 1.669,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.10508757297748124,
510
+ "eval_loss": 1.5358057022094727,
511
+ "eval_runtime": 4.3922,
512
+ "eval_samples_per_second": 114.977,
513
+ "eval_steps_per_second": 14.571,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.1067556296914095,
518
+ "grad_norm": 2.4203217029571533,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 1.4209,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.10842368640533778,
525
+ "grad_norm": 2.566002130508423,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 1.56,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.11009174311926606,
532
+ "grad_norm": 2.262228012084961,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 1.1765,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.11175979983319433,
539
+ "grad_norm": 3.0135338306427,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 1.4756,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.1134278565471226,
546
+ "grad_norm": 2.6408193111419678,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 1.5436,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.11509591326105087,
553
+ "grad_norm": 2.683082103729248,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 1.5177,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.11676396997497915,
560
+ "grad_norm": 3.316333293914795,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 1.5634,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.11843202668890743,
567
+ "grad_norm": 2.793429136276245,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 1.3015,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.12010008340283569,
574
+ "grad_norm": 2.920193910598755,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 1.1048,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.12010008340283569,
581
+ "eval_loss": 1.251120924949646,
582
+ "eval_runtime": 4.3942,
583
+ "eval_samples_per_second": 114.923,
584
+ "eval_steps_per_second": 14.565,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.12176814011676397,
589
+ "grad_norm": 4.115492343902588,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 1.2124,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.12343619683069225,
596
+ "grad_norm": 2.110515594482422,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 1.0832,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.12510425354462051,
603
+ "grad_norm": 2.922022819519043,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 1.0819,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 1041281895628800.0,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null