TachyHealthResearch commited on
Commit
7af94ee
1 Parent(s): 0f57aaf

Training in progress, step 80, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98f4c3613d0942e1149efb5ec951f878e656ab8598ea1d74c4e1cc2f71b54b60
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f09498cd1630b3ad9557dd24672f3389a80d74d8c134ca2935f6eb023d4dd61a
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2ee711433e187c4c3ef92ebe11a92651d96a20e76be34859e3f9387f5d9e8a5
3
  size 42545748
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21d5094423c444e0b60c0d1f752350e8c383a4892b97fe7b562b23d640ae4f1e
3
  size 42545748
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:557e474a226d303e26d6758a2eb18bb0bbe3b1a451146f9953c40e79b727f273
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eb5c56ad7f28c08ba6a65f011db11d829b6a7b17048bf037654e46884108234
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1723a4b1c943236de3935bcf77e35b80aec5d8ffd41a734f2052202a2aabea88
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f33415f176b8a48691d03ed7dab3f1b327d681c8c56b2a0baf4a0c917f18d582
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": 0.028,
5
  "eval_steps": 1000,
6
- "global_step": 70,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -427,13 +427,73 @@
427
  "learning_rate": 6.31578947368421e-05,
428
  "loss": 1.7412,
429
  "step": 70
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
430
  }
431
  ],
432
  "logging_steps": 1,
433
  "max_steps": 100,
434
  "num_train_epochs": 1,
435
  "save_steps": 10,
436
- "total_flos": 4233108315045888.0,
437
  "trial_name": null,
438
  "trial_params": null
439
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.032,
5
  "eval_steps": 1000,
6
+ "global_step": 80,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
427
  "learning_rate": 6.31578947368421e-05,
428
  "loss": 1.7412,
429
  "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.03,
433
+ "learning_rate": 6.105263157894737e-05,
434
+ "loss": 2.3269,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.03,
439
+ "learning_rate": 5.894736842105263e-05,
440
+ "loss": 2.0108,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.03,
445
+ "learning_rate": 5.68421052631579e-05,
446
+ "loss": 1.4624,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.03,
451
+ "learning_rate": 5.4736842105263165e-05,
452
+ "loss": 1.4359,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.03,
457
+ "learning_rate": 5.2631578947368424e-05,
458
+ "loss": 1.5008,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.03,
463
+ "learning_rate": 5.052631578947369e-05,
464
+ "loss": 2.0177,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.03,
469
+ "learning_rate": 4.842105263157895e-05,
470
+ "loss": 1.829,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.03,
475
+ "learning_rate": 4.6315789473684214e-05,
476
+ "loss": 1.488,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.03,
481
+ "learning_rate": 4.421052631578947e-05,
482
+ "loss": 1.5957,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.03,
487
+ "learning_rate": 4.210526315789474e-05,
488
+ "loss": 1.7028,
489
+ "step": 80
490
  }
491
  ],
492
  "logging_steps": 1,
493
  "max_steps": 100,
494
  "num_train_epochs": 1,
495
  "save_steps": 10,
496
+ "total_flos": 4814878295752704.0,
497
  "trial_name": null,
498
  "trial_params": null
499
  }