Hugging Face's logo

BKM1804
/
pythia-410m-deduped-b44e92ca-edc7-4226-ba0d-bcfffc1a92e3-DPO

Transformers
Safetensors
Generated from Trainer
trl
dpo
Model card Files
xet
 Community
BKM1804 commited on
Commit
1894ceb
·
verified ·
1 Parent(s): 44ef68f

Training in progress, step 1000

Browse files
Files changed (4) hide show
  1. README.md +2 -2
  2. adapter_config.json +3 -3
  3. adapter_model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -4,8 +4,8 @@ library_name: transformers
4
  model_name: pythia-410m-deduped-b44e92ca-edc7-4226-ba0d-bcfffc1a92e3-DPO
5
  tags:
6
  - generated_from_trainer
7
- - dpo
8
  - trl
 
9
  licence: license
10
  ---
11
 
@@ -27,7 +27,7 @@ print(output["generated_text"])
27
 
28
  ## Training procedure
29
 
30
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/buikhacminh1804/sn56-dpo-train/runs/3qbbia2u)
31
 
32
 
33
  This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
 
4
  model_name: pythia-410m-deduped-b44e92ca-edc7-4226-ba0d-bcfffc1a92e3-DPO
5
  tags:
6
  - generated_from_trainer
 
7
  - trl
8
+ - dpo
9
  licence: license
10
  ---
11
 
 
27
 
28
  ## Training procedure
29
 
30
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/buikhacminh1804/sn56-dpo-train/runs/95uwl4lf)
31
 
32
 
33
  This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
adapter_config.json CHANGED
@@ -28,10 +28,10 @@
28
  "rank_pattern": {},
29
  "revision": null,
30
  "target_modules": [
31
- "dense",
32
- "dense_4h_to_h",
33
  "dense_h_to_4h",
34
- "query_key_value"
 
 
35
  ],
36
  "target_parameters": null,
37
  "task_type": null,
 
28
  "rank_pattern": {},
29
  "revision": null,
30
  "target_modules": [
 
 
31
  "dense_h_to_4h",
32
+ "dense",
33
+ "query_key_value",
34
+ "dense_4h_to_h"
35
  ],
36
  "target_parameters": null,
37
  "task_type": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af0e372b241d3f2885597dbc4d2837beb5f0ede9696be612a0ef942e303fb2b9
3
  size 201353888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b25edcdc121437e11db4ac6c5f6925fa4c72ebb265a3e0aa663f2da46526b4b5
3
  size 201353888
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:498b5565d355dc06d6c48c75fde5316d87b416f99479035aa90766334e5449b5
3
  size 7121
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdab29c4d49e411c4ec5654c4d4762ecc558a628eb8cd86bced200a21352fbd2
3
  size 7121