Hugging Face's logo

hzy
/
Qwen2.5-1.5B-Knowledge-R1-GRPO

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
trl
grpo
conversational
text-generation-inference
Model card Files
xet
 Community
hzy commited on
Commit
26c526b
·
verified ·
1 Parent(s): 004d950

Model save

Browse files
Files changed (6) hide show
  1. README.md +1 -1
  2. all_results.json +4 -4
  3. model.safetensors +1 -1
  4. train_results.json +4 -4
  5. trainer_state.json +0 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -26,7 +26,7 @@ print(output["generated_text"])
26
 
27
  ## Training procedure
28
 
29
- [<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/hzy312/202502224_kr1_Qwen2.5-1.5B-Instruct_formal/runs/1740404119)
30
 
31
 
32
  This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
 
26
 
27
  ## Training procedure
28
 
29
+ [<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/hzy312/202502224_kr1_Qwen2.5-1.5B-Instruct_formal/runs/7259637705.65474-81ac6866-253c-43a1-b162-315e7caecbe7)
30
 
31
 
32
  This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
- "train_loss": 0.30994002032279966,
4
- "train_runtime": 35925.9642,
5
  "train_samples": 15000,
6
- "train_samples_per_second": 0.418,
7
- "train_steps_per_second": 0.052
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
+ "train_loss": 0.738647110915184,
4
+ "train_runtime": 47500.6212,
5
  "train_samples": 15000,
6
+ "train_samples_per_second": 0.316,
7
+ "train_steps_per_second": 0.039
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:414ca98478cc8857f2d5df7a55e260aa8e0e4cf4d3c2f7e7f110ef5b880fcc55
3
  size 3554214752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c3cd6c530a16e159b67b89474bb2465b33c417f6853b2dc02d486d5ecc8d4f8
3
  size 3554214752
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
- "train_loss": 0.30994002032279966,
4
- "train_runtime": 35925.9642,
5
  "train_samples": 15000,
6
- "train_samples_per_second": 0.418,
7
- "train_steps_per_second": 0.052
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
+ "train_loss": 0.738647110915184,
4
+ "train_runtime": 47500.6212,
5
  "train_samples": 15000,
6
+ "train_samples_per_second": 0.316,
7
+ "train_steps_per_second": 0.039
8
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:076e5027a3c5a3f04e5d5051d54676e79b3978b6ccfcdfb939977b15140d016d
3
  size 7800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:136b1882b22f2f736d20769827a43033940f9bb1c86dab9c614b962a90cf751a
3
  size 7800