Hugging Face's logo

bbytxt
/
bb8e4082-d946-444b-b70b-4bd3c25926dc

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
bbytxt commited on
Commit
8383018
·
verified ·
1 Parent(s): 69a9eef

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 +179 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:faef6ff2f6fb88da685ba921f6b7d0e1238e1fcbc27dfcbfa3fe1b59744e2fb2
3
  size 3029024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:503c5de0d2fd77b308e228dd9783543e10f9cec68c79a5e1865d6891c7a5650d
3
  size 3029024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1589e3d0ab10b51ccd3d5cc7a1fc7da05313c1a2e86770ec2e3e6b3cef466e5f
3
  size 1663290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08b13c6a3b0a5d79cf181ee3404941d3515c26f76725da8baaa02095de9f14d8
3
  size 1663290
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef8ab9fc50710a10dd0b647d381bc93c7fbacd0e194ec6c4b6c13784ed8220c1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4226d955c69fcc95a9cd533c5f83c0cdfe523489574405ce6fe8a74ad7dfca4f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83c409614fe7c4294c30c517ac4a1097721f51ec5d3456b5de1ee4e4e2aed9ba
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 2.1023528575897217,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.019788265558523796,
5
  "eval_steps": 50,
6
- "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -373,6 +373,181 @@
373
  "eval_samples_per_second": 51.232,
374
  "eval_steps_per_second": 12.81,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -396,12 +571,12 @@
396
  "should_evaluate": false,
397
  "should_log": false,
398
  "should_save": true,
399
- "should_training_stop": false
400
  },
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 130824536064000.0,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
  "best_metric": 2.1023528575897217,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.029682398337785694,
5
  "eval_steps": 50,
6
+ "global_step": 75,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
373
  "eval_samples_per_second": 51.232,
374
  "eval_steps_per_second": 12.81,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.02018403086969427,
379
+ "grad_norm": 2.083672046661377,
380
+ "learning_rate": 4.007047666771274e-05,
381
+ "loss": 2.1264,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.020579796180864748,
386
+ "grad_norm": 2.1195905208587646,
387
+ "learning_rate": 3.728908329032567e-05,
388
+ "loss": 2.0814,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.020975561492035222,
393
+ "grad_norm": 2.336852550506592,
394
+ "learning_rate": 3.4549150281252636e-05,
395
+ "loss": 2.0431,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.0213713268032057,
400
+ "grad_norm": 2.270529270172119,
401
+ "learning_rate": 3.1859614732467954e-05,
402
+ "loss": 2.0404,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.021767092114376174,
407
+ "grad_norm": 1.912915587425232,
408
+ "learning_rate": 2.9229249349905684e-05,
409
+ "loss": 2.0207,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.02216285742554665,
414
+ "grad_norm": 2.281681537628174,
415
+ "learning_rate": 2.6666633838716314e-05,
416
+ "loss": 2.067,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.022558622736717125,
421
+ "grad_norm": 1.9110603332519531,
422
+ "learning_rate": 2.418012691805191e-05,
423
+ "loss": 1.9778,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.022954388047887603,
428
+ "grad_norm": 1.8000211715698242,
429
+ "learning_rate": 2.1777839056661554e-05,
430
+ "loss": 1.9394,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.023350153359058077,
435
+ "grad_norm": 1.7174650430679321,
436
+ "learning_rate": 1.946760601822809e-05,
437
+ "loss": 1.9967,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.023745918670228554,
442
+ "grad_norm": 2.0586373805999756,
443
+ "learning_rate": 1.725696330273575e-05,
444
+ "loss": 1.9891,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.024141683981399032,
449
+ "grad_norm": 2.5579705238342285,
450
+ "learning_rate": 1.5153121567235335e-05,
451
+ "loss": 1.9442,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.024537449292569506,
456
+ "grad_norm": 1.8055744171142578,
457
+ "learning_rate": 1.3162943106179749e-05,
458
+ "loss": 1.9219,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.024933214603739984,
463
+ "grad_norm": 1.803011417388916,
464
+ "learning_rate": 1.1292919468045877e-05,
465
+ "loss": 2.0183,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.025328979914910458,
470
+ "grad_norm": 1.7811270952224731,
471
+ "learning_rate": 9.549150281252633e-06,
472
+ "loss": 1.8916,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.025724745226080935,
477
+ "grad_norm": 1.733910322189331,
478
+ "learning_rate": 7.937323358440935e-06,
479
+ "loss": 1.9905,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.02612051053725141,
484
+ "grad_norm": 1.70806086063385,
485
+ "learning_rate": 6.462696144011149e-06,
486
+ "loss": 1.8904,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.026516275848421887,
491
+ "grad_norm": 1.6646728515625,
492
+ "learning_rate": 5.13007856543209e-06,
493
+ "loss": 1.9227,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.02691204115959236,
498
+ "grad_norm": 1.7067934274673462,
499
+ "learning_rate": 3.9438173442575e-06,
500
+ "loss": 1.9334,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.02730780647076284,
505
+ "grad_norm": 1.6381385326385498,
506
+ "learning_rate": 2.9077818180237693e-06,
507
+ "loss": 1.9143,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.027703571781933313,
512
+ "grad_norm": 1.9795570373535156,
513
+ "learning_rate": 2.0253513192751373e-06,
514
+ "loss": 1.9075,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.02809933709310379,
519
+ "grad_norm": 1.563312292098999,
520
+ "learning_rate": 1.2994041528833266e-06,
521
+ "loss": 1.907,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.028495102404274265,
526
+ "grad_norm": 1.734750747680664,
527
+ "learning_rate": 7.323082076153509e-07,
528
+ "loss": 1.8587,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.028890867715444742,
533
+ "grad_norm": 1.636612892150879,
534
+ "learning_rate": 3.2591323257248893e-07,
535
+ "loss": 1.9035,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.029286633026615216,
540
+ "grad_norm": 2.093644380569458,
541
+ "learning_rate": 8.15448036932176e-08,
542
+ "loss": 1.9695,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.029682398337785694,
547
+ "grad_norm": 1.7379897832870483,
548
+ "learning_rate": 0.0,
549
+ "loss": 1.8646,
550
+ "step": 75
551
  }
552
  ],
553
  "logging_steps": 1,
 
571
  "should_evaluate": false,
572
  "should_log": false,
573
  "should_save": true,
574
+ "should_training_stop": true
575
  },
576
  "attributes": {}
577
  }
578
  },
579
+ "total_flos": 196236804096000.0,
580
  "train_batch_size": 4,
581
  "trial_name": null,
582
  "trial_params": null