Hugging Face's logo

lesso04
/
31eaffad-8c4e-4305-bc53-720338fd1aad

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
lesso04 commited on
Commit
286a0d3
•
1 Parent(s): 94a7576

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 sha256:772633cd29659f5c9cf32803e150c7f641ea7e6cc65547caf8bb75904f936b71
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a99ea3fdd078c3802dcdb8eb557864a51de709c43dfee49ee7215e36457e279a
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6d369ff5c65ce12b205c5783709b3475b14746f107488594246c7b2925323ef
3
  size 501168482
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc3d83d747e9ffdad1de3aa3c3e6a2cafee874565cd784e7fcf585eb0e2f2bf6
3
  size 501168482
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c08c9f2db3519491f65c896dc5570f0688363fea4110372251c117212111fc45
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ee9440c38b11df1bad9c246eb1b0880c612c59b45e12b698debf583c3696051
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": 0.1763668430335097,
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": 0.2969,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 6.347789697024e+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": 0.26455026455026454,
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": 0.2969,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.17989417989417988,
411
+ "grad_norm": 9.53512191772461,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 0.6029,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.18342151675485008,
418
+ "grad_norm": 3.098203182220459,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 0.1674,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.18694885361552027,
425
+ "grad_norm": 5.761476993560791,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 0.3695,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.19047619047619047,
432
+ "grad_norm": 3.4099481105804443,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 0.5525,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.19047619047619047,
439
+ "eval_loss": 0.10475945472717285,
440
+ "eval_runtime": 37.7225,
441
+ "eval_samples_per_second": 6.336,
442
+ "eval_steps_per_second": 0.795,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.19400352733686066,
447
+ "grad_norm": 3.259533643722534,
448
+ "learning_rate": 5e-05,
449
+ "loss": 0.2256,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.19753086419753085,
454
+ "grad_norm": 3.9592463970184326,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 0.5181,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.20105820105820105,
461
+ "grad_norm": 3.4747936725616455,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 0.4554,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.20458553791887124,
468
+ "grad_norm": 1.4295612573623657,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 0.1801,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.20811287477954143,
475
+ "grad_norm": 2.1647229194641113,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 0.1908,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.21164021164021163,
482
+ "grad_norm": 3.4215903282165527,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 0.3586,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.21516754850088182,
489
+ "grad_norm": 2.3255903720855713,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 0.2312,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.21869488536155202,
496
+ "grad_norm": 3.3858463764190674,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 0.294,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.2222222222222222,
503
+ "grad_norm": 4.583118438720703,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 0.469,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.2222222222222222,
510
+ "eval_loss": 0.11342418938875198,
511
+ "eval_runtime": 37.6648,
512
+ "eval_samples_per_second": 6.345,
513
+ "eval_steps_per_second": 0.797,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.2257495590828924,
518
+ "grad_norm": 2.167945384979248,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 0.2766,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.2292768959435626,
525
+ "grad_norm": 4.23003625869751,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 0.4786,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.2328042328042328,
532
+ "grad_norm": 2.1028635501861572,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 0.1599,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.23633156966490299,
539
+ "grad_norm": 2.2224302291870117,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 0.2536,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.23985890652557318,
546
+ "grad_norm": 1.0066758394241333,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 0.0962,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.24338624338624337,
553
+ "grad_norm": 2.389492988586426,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 0.3528,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.24691358024691357,
560
+ "grad_norm": 0.8155355453491211,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 0.0832,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.25044091710758376,
567
+ "grad_norm": 2.6937882900238037,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 0.1585,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.25396825396825395,
574
+ "grad_norm": 2.682079315185547,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 0.2465,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.25396825396825395,
581
+ "eval_loss": 0.11077579855918884,
582
+ "eval_runtime": 37.6536,
583
+ "eval_samples_per_second": 6.347,
584
+ "eval_steps_per_second": 0.797,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.25749559082892415,
589
+ "grad_norm": 2.9206907749176025,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 0.243,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.26102292768959434,
596
+ "grad_norm": 3.7066774368286133,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 0.1554,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.26455026455026454,
603
+ "grad_norm": 2.460815191268921,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 0.1775,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 9.521684545536e+16,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null