Hugging Face's logo

ikerm11
/
gemma1b_humanizer_lora

Reinforcement Learning
Transformers
PyTorch
Safetensors
trl
ppo
Model card Files
xet
 Community
ikerm11 commited on
Commit
d9be180
·
verified ·
1 Parent(s): cec8d1b

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. adapter_model.safetensors +1 -1
  2. config.json +2 -2
  3. pytorch_model.bin +1 -1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69a7a49e07a7f27550a52a68f6df578e40cf63b3676a9954c02b99aba595ffda
3
  size 2995512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2bdcbf1584f1951843c42396c9c5b892b8e3aa2289e4f596f99f76f8a7313c0
3
  size 2995512
config.json CHANGED
@@ -19,14 +19,14 @@
19
  "is_peft_model": true,
20
  "kl_penalty": "kl",
21
  "lam": 0.95,
22
- "learning_rate": 5e-06,
23
  "log_with": null,
24
  "max_grad_norm": null,
25
  "mini_batch_size": 1,
26
  "model_name": "gpt2",
27
  "optimize_cuda_cache": null,
28
  "optimize_device_cache": false,
29
- "ppo_epochs": 2,
30
  "project_kwargs": {},
31
  "push_to_hub_if_best_kwargs": {},
32
  "query_dataset": "imdb",
 
19
  "is_peft_model": true,
20
  "kl_penalty": "kl",
21
  "lam": 0.95,
22
+ "learning_rate": 5e-07,
23
  "log_with": null,
24
  "max_grad_norm": null,
25
  "mini_batch_size": 1,
26
  "model_name": "gpt2",
27
  "optimize_cuda_cache": null,
28
  "optimize_device_cache": false,
29
+ "ppo_epochs": 1,
30
  "project_kwargs": {},
31
  "push_to_hub_if_best_kwargs": {},
32
  "query_dataset": "imdb",
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb45ef2d3a1788c5b252220141901333aa5c2fa21188a453b6122c9b0da13fca
3
  size 6140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79ee882c91a51deb97b681adeb73e2fdbad5a9fc353158fe54cbb2ccdfb12103
3
  size 6140