Hugging Face's logo

lesso04
/
43add8cb-08d4-4521-abc0-1167226993fa

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso04 commited on
Commit
1f72912
•
1 Parent(s): b3217d3

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 sha256:4bbb77b7c972617d75a7ce25fa0d8ff5c92ed34162b2dc4f3f4ca2737fbd9480
3
  size 13587864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e5b99b8812279ae6e92ba2624b4c3b73cbcc988be58e28436ba4ce19a2f3c55
3
  size 13587864
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:232e5e54e51e7973329847fa30ae7958daa3c537a32d706f03ee75f7bf6fe76d
3
  size 27273018
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da00d1a61426ffb822cb82515acd5c32e54793e907f09714d0775f0f0c2b3b8e
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:f61491213d0f71c0e54a4d1cf06238749d8c8aeeb6a636e081ccade0a42c3757
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e74327a670fdb4f6d8981c7b37bfa0e3757d975977955213b3e2b0de12f48481
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": 0.09699321047526673,
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": 0.575,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 1298131429883904.0,
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": 0.1454898157129001,
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": 0.575,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.09893307468477207,
411
+ "grad_norm": 1.4063315391540527,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 0.5396,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.1008729388942774,
418
+ "grad_norm": 1.2367199659347534,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 0.4351,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.10281280310378274,
425
+ "grad_norm": 1.320259928703308,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 0.4758,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.10475266731328807,
432
+ "grad_norm": 1.6481106281280518,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 0.5796,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.10475266731328807,
439
+ "eval_loss": 0.4402259886264801,
440
+ "eval_runtime": 7.7586,
441
+ "eval_samples_per_second": 55.938,
442
+ "eval_steps_per_second": 7.089,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.1066925315227934,
447
+ "grad_norm": 1.4706881046295166,
448
+ "learning_rate": 5e-05,
449
+ "loss": 0.5325,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.10863239573229874,
454
+ "grad_norm": 1.681864619255066,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 0.5644,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.11057225994180407,
461
+ "grad_norm": 1.4026848077774048,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 0.3279,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.11251212415130941,
468
+ "grad_norm": 1.2170274257659912,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 0.3805,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.11445198836081474,
475
+ "grad_norm": 1.9468257427215576,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 0.5186,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.11639185257032007,
482
+ "grad_norm": 1.2916088104248047,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 0.2757,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.11833171677982542,
489
+ "grad_norm": 1.548339605331421,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 0.3923,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.12027158098933075,
496
+ "grad_norm": 2.265233039855957,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 0.6105,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.12221144519883609,
503
+ "grad_norm": 1.4970910549163818,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 0.4189,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.12221144519883609,
510
+ "eval_loss": 0.3442797064781189,
511
+ "eval_runtime": 7.745,
512
+ "eval_samples_per_second": 56.036,
513
+ "eval_steps_per_second": 7.101,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.12415130940834142,
518
+ "grad_norm": 1.1539958715438843,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 0.2965,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.12609117361784675,
525
+ "grad_norm": 1.2717357873916626,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 0.3565,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.1280310378273521,
532
+ "grad_norm": 1.1463826894760132,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 0.3243,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.12997090203685743,
539
+ "grad_norm": 2.083845615386963,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 0.4723,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.13191076624636275,
546
+ "grad_norm": 1.220322608947754,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 0.3566,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.1338506304558681,
553
+ "grad_norm": 1.4377970695495605,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 0.384,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.13579049466537343,
560
+ "grad_norm": 1.6574350595474243,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 0.3038,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.13773035887487875,
567
+ "grad_norm": 1.2186497449874878,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 0.2762,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.1396702230843841,
574
+ "grad_norm": 1.6001431941986084,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 0.25,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.1396702230843841,
581
+ "eval_loss": 0.3006916642189026,
582
+ "eval_runtime": 7.7498,
583
+ "eval_samples_per_second": 56.001,
584
+ "eval_steps_per_second": 7.097,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.14161008729388944,
589
+ "grad_norm": 1.6216119527816772,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 0.391,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.14354995150339475,
596
+ "grad_norm": 2.5727713108062744,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 0.5055,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.1454898157129001,
603
+ "grad_norm": 1.4488884210586548,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 0.3118,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 1936784325869568.0,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null