Hugging Face's logo

lesso02
/
0cb37a5c-21bc-42ad-b4cd-d96b07f7bff3

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso02 commited on
Commit
2a5b082
·
verified ·
1 Parent(s): 3be9edd

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 sha256:3b3e6beb222c15f1dc321f9db2d9c46ce05901c265f102d04df2051917cfd310
3
  size 45118424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:189fbc9395719e60d6550327269a856cc15c1e29099ab00bfd701c4f21e2e011
3
  size 45118424
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4306a29be05a683d7fb5bd18f166b4f18749635a0ab2c91be88a3d236bd6b33
3
  size 90365754
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfc1c02530bd4e977feb06ab96497a9aba172d34eb315aebe466d3b2f9312616
3
  size 90365754
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:026030288cd601691b26a9dd3addc963d8372e0cdb3ae5ae397bb1e558a3e4d2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4a797e4556a00e672702ff04c6ecce740fabaca58e7ff5b6ddf14351f843364
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": 0.17667844522968199,
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": 2.7125,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 4838612847820800.0,
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": 0.26501766784452296,
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": 2.7125,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.18021201413427562,
411
+ "grad_norm": 3.0649173259735107,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 2.8662,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.18374558303886926,
418
+ "grad_norm": 3.1530253887176514,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 2.6954,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.1872791519434629,
425
+ "grad_norm": 3.109790802001953,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 2.9053,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.19081272084805653,
432
+ "grad_norm": 3.0539212226867676,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 2.7137,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.19081272084805653,
439
+ "eval_loss": 2.8013288974761963,
440
+ "eval_runtime": 7.2778,
441
+ "eval_samples_per_second": 32.84,
442
+ "eval_steps_per_second": 4.122,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.19434628975265017,
447
+ "grad_norm": 3.252530574798584,
448
+ "learning_rate": 5e-05,
449
+ "loss": 2.8904,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.1978798586572438,
454
+ "grad_norm": 3.2859199047088623,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 2.8972,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.20141342756183744,
461
+ "grad_norm": 3.0715034008026123,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 2.6976,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.2049469964664311,
468
+ "grad_norm": 3.305929660797119,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 3.0879,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.20848056537102475,
475
+ "grad_norm": 2.9862401485443115,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 2.7462,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.21201413427561838,
482
+ "grad_norm": 3.282827138900757,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 2.9555,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.21554770318021202,
489
+ "grad_norm": 3.254582405090332,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 2.7325,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.21908127208480566,
496
+ "grad_norm": 3.2542083263397217,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 2.9844,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.2226148409893993,
503
+ "grad_norm": 3.1028382778167725,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 3.0317,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.2226148409893993,
510
+ "eval_loss": 2.7716846466064453,
511
+ "eval_runtime": 7.2764,
512
+ "eval_samples_per_second": 32.846,
513
+ "eval_steps_per_second": 4.123,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.22614840989399293,
518
+ "grad_norm": 2.934584617614746,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 2.6931,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.22968197879858657,
525
+ "grad_norm": 2.996783971786499,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 2.6433,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.2332155477031802,
532
+ "grad_norm": 3.002028465270996,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 2.8005,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.23674911660777384,
539
+ "grad_norm": 3.1908152103424072,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 2.568,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.24028268551236748,
546
+ "grad_norm": 3.1398322582244873,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 2.8163,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.24381625441696114,
553
+ "grad_norm": 3.36586332321167,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 2.7572,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.24734982332155478,
560
+ "grad_norm": 3.007260799407959,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 2.9016,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.2508833922261484,
567
+ "grad_norm": 3.0115766525268555,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 2.766,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.254416961130742,
574
+ "grad_norm": 3.172506809234619,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 2.9897,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.254416961130742,
581
+ "eval_loss": 2.7495005130767822,
582
+ "eval_runtime": 7.2746,
583
+ "eval_samples_per_second": 32.854,
584
+ "eval_steps_per_second": 4.124,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.2579505300353357,
589
+ "grad_norm": 3.1129682064056396,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 2.82,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.26148409893992935,
596
+ "grad_norm": 3.208728551864624,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 2.8844,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.26501766784452296,
603
+ "grad_norm": 3.0997607707977295,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 2.7786,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 7257919271731200.0,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null