ramdhanfirdaus commited on
Commit
c034a78
1 Parent(s): 9581293

Training in progress, step 3000, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:916e90696b24d9882c92abf3092c0ed82bd4cedbeeef4caeb480cc8a219d698c
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69b33d3eec283021369b55393cb287c152e4fe9ade2d47cd9f563fedc8f2ff55
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ed9e5dbe38cd1f5e0b104e32f16bccee4a9fdf026b0460715c08ebb1b8f1039
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d11af7f5a5f826609b73511dd39c85415c456adf1f7f7a2e964a7f84f8f73411
3
  size 100693001
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c203d7bb1a91e0292a965d8ca5fb218ce38bc4a460a20de85094975b0d59d26
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9eb493e8a5e1ded45f7ff787c88732b7edf2f372416a05f1233e6e453f81d56
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f8ff9625f3ca0a3b7f45b0a306f91dd9b6f1df22bd03f7af912988d7d454a46
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee5232fa4eb8d1b9b87542cf20cfe22809b071cb5309d4e2a9f60e7d3ad7ddc7
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.4502085447311401,
3
- "best_model_checkpoint": "./outputs/checkpoint-2900",
4
- "epoch": 2.1129326047358834,
5
  "eval_steps": 100,
6
- "global_step": 2900,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -413,13 +413,27 @@
413
  "eval_samples_per_second": 43.719,
414
  "eval_steps_per_second": 5.47,
415
  "step": 2900
 
 
 
 
 
 
 
 
 
 
 
 
 
 
416
  }
417
  ],
418
  "logging_steps": 100,
419
  "max_steps": 4116,
420
  "num_train_epochs": 3,
421
  "save_steps": 100,
422
- "total_flos": 1.7266613396692992e+17,
423
  "trial_name": null,
424
  "trial_params": null
425
  }
 
1
  {
2
+ "best_metric": 1.4365726709365845,
3
+ "best_model_checkpoint": "./outputs/checkpoint-3000",
4
+ "epoch": 2.185792349726776,
5
  "eval_steps": 100,
6
+ "global_step": 3000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
413
  "eval_samples_per_second": 43.719,
414
  "eval_steps_per_second": 5.47,
415
  "step": 2900
416
+ },
417
+ {
418
+ "epoch": 2.19,
419
+ "learning_rate": 0.0002,
420
+ "loss": 1.4147,
421
+ "step": 3000
422
+ },
423
+ {
424
+ "epoch": 2.19,
425
+ "eval_loss": 1.4365726709365845,
426
+ "eval_runtime": 143.5627,
427
+ "eval_samples_per_second": 43.702,
428
+ "eval_steps_per_second": 5.468,
429
+ "step": 3000
430
  }
431
  ],
432
  "logging_steps": 100,
433
  "max_steps": 4116,
434
  "num_train_epochs": 3,
435
  "save_steps": 100,
436
+ "total_flos": 1.7864118963540787e+17,
437
  "trial_name": null,
438
  "trial_params": null
439
  }