ramdhanfirdaus commited on
Commit
90a5ead
1 Parent(s): 3df757f

Training in progress, step 2800, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44860346aace7a1112857b41617cfacbd95eec8eda80b8fdb3a10160a4d26cb1
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f51e0d641399fb1c1612ff0ca1212a0fe51c9a7914c915ccb237f942e0826d4
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbd92190aab7a6459aa4ca4f86bb23daa36849ded0d6fab45fee6f5afb372d29
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e73c1893194c55a3ebee151cafbfaeda5a0485140090e102a9db74fa434df8ab
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:d0e1dc4e8513a0bba3d4b52d1e66539d1d92aa1df08b8a7f141be24c582260ed
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9d6bd701fca6e19968b0e9d9d7fe0c31a82f71b8340d6006477f972d51d1483
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d747a341abc7681ba1384e20b96e3fad64e2a0f72aee64e5047f8f5bba229c8f
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79c08a7148c570c3d4c87a735e3acef3af52d256eb019f3a3f3feeab8a656949
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.3734662532806396,
3
- "best_model_checkpoint": "./outputs/checkpoint-2700",
4
- "epoch": 1.9672131147540983,
5
  "eval_steps": 100,
6
- "global_step": 2700,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -385,13 +385,27 @@
385
  "eval_samples_per_second": 43.702,
386
  "eval_steps_per_second": 5.468,
387
  "step": 2700
 
 
 
 
 
 
 
 
 
 
 
 
 
 
388
  }
389
  ],
390
  "logging_steps": 100,
391
  "max_steps": 4116,
392
  "num_train_epochs": 3,
393
  "save_steps": 100,
394
- "total_flos": 1.6093831259072102e+17,
395
  "trial_name": null,
396
  "trial_params": null
397
  }
 
1
  {
2
+ "best_metric": 1.3625913858413696,
3
+ "best_model_checkpoint": "./outputs/checkpoint-2800",
4
+ "epoch": 2.040072859744991,
5
  "eval_steps": 100,
6
+ "global_step": 2800,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
385
  "eval_samples_per_second": 43.702,
386
  "eval_steps_per_second": 5.468,
387
  "step": 2700
388
+ },
389
+ {
390
+ "epoch": 2.04,
391
+ "learning_rate": 0.0002,
392
+ "loss": 1.341,
393
+ "step": 2800
394
+ },
395
+ {
396
+ "epoch": 2.04,
397
+ "eval_loss": 1.3625913858413696,
398
+ "eval_runtime": 150.8911,
399
+ "eval_samples_per_second": 41.58,
400
+ "eval_steps_per_second": 5.202,
401
+ "step": 2800
402
  }
403
  ],
404
  "logging_steps": 100,
405
  "max_steps": 4116,
406
  "num_train_epochs": 3,
407
  "save_steps": 100,
408
+ "total_flos": 1.6689897048172954e+17,
409
  "trial_name": null,
410
  "trial_params": null
411
  }