lzxdjb commited on
Commit
9c9794c
·
verified ·
1 Parent(s): 398927d

Training in progress, step 1000

Browse files
Files changed (4) hide show
  1. README.md +2 -3
  2. model.safetensors +1 -1
  3. tokenizer.json +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,6 +1,5 @@
1
  ---
2
  base_model: Qwen/Qwen2-0.5B-Instruct
3
- datasets: trl-lib/chatbot_arena_completions
4
  library_name: transformers
5
  model_name: gkd-model
6
  tags:
@@ -12,7 +11,7 @@ licence: license
12
 
13
  # Model Card for gkd-model
14
 
15
- This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on the [trl-lib/chatbot_arena_completions](https://huggingface.co/datasets/trl-lib/chatbot_arena_completions) dataset.
16
  It has been trained using [TRL](https://github.com/huggingface/trl).
17
 
18
  ## Quick start
@@ -28,7 +27,7 @@ print(output["generated_text"])
28
 
29
  ## Training procedure
30
 
31
- [<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/zhengxinglei539-easynet/huggingface/runs/ofw10qv9)
32
 
33
 
34
  This model was trained with GKD, a method introduced in [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://huggingface.co/papers/2306.13649).
 
1
  ---
2
  base_model: Qwen/Qwen2-0.5B-Instruct
 
3
  library_name: transformers
4
  model_name: gkd-model
5
  tags:
 
11
 
12
  # Model Card for gkd-model
13
 
14
+ This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct).
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
  ## Quick start
 
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/zhengxinglei539-easynet/huggingface/runs/7qr4qjt7)
31
 
32
 
33
  This model was trained with GKD, a method introduced in [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://huggingface.co/papers/2306.13649).
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69055387925347584f8f7f6e6ff5a63fa2784aae4e2b5347db750d45984c72fb
3
  size 1260367448
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fccb3c9c027e5949aefc1fe49faae21c627defa14218b270faa3c9ad58260ce9
3
  size 1260367448
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
3
- size 11418266
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec56aaf49a46b5504d9900a27b1bb10f9b5f080ee7ce692d7d9f5fcb96d781ad
3
+ size 11418364
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:260046ee6800d1c809df4da8014435d23b9af3eee03c31e2f513f56f55175b6a
3
  size 7544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9732732b5e04123df43c2ef1df208703548a21e3ea48e38a8ed55e8bd2d965e
3
  size 7544