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
98421e6
·
verified ·
1 Parent(s): 1a4a665

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 +2 -2
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/hzy312/20250213_r1_reproduction_Qwen2.5-7B-Instruct/runs/7260140985.63412-d3ebea55-1c2d-453c-ad42-f0417f673921)
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/hzy312/20250218_knowledge_r1_Qwen2.5-1.5B-Instruct/runs/7260138335.90879-c2e38c2a-119b-4bdb-a39e-ea5d90047159)
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": 5.353166522324368,
4
- "train_runtime": 7842.24,
5
  "train_samples": 15000,
6
- "train_samples_per_second": 1.913,
7
- "train_steps_per_second": 0.06
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
+ "train_loss": 0.0492804956890872,
4
+ "train_runtime": 5735.3452,
5
  "train_samples": 15000,
6
+ "train_samples_per_second": 5.231,
7
+ "train_steps_per_second": 0.374
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ceb357dd975e64492dee77cfb9f0f4b2351efa227fa3727c0d9de1c23c49f9e
3
  size 3554214752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0ecc6d92dada0cad8f4276dc9085e0f9730519e1c364ea6e61a2707f0f51e1a
3
  size 3554214752
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
- "train_loss": 5.353166522324368,
4
- "train_runtime": 7842.24,
5
  "train_samples": 15000,
6
- "train_samples_per_second": 1.913,
7
- "train_steps_per_second": 0.06
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
+ "train_loss": 0.0492804956890872,
4
+ "train_runtime": 5735.3452,
5
  "train_samples": 15000,
6
+ "train_samples_per_second": 5.231,
7
+ "train_steps_per_second": 0.374
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 sha256:0e44d60999224ad48d7078952f9d80a8dbfe63fe134329c74de5b663f87ebb7b
3
- size 7544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85e88a7cb4ca0e7b67f0a7dc72b9e03de20126bc8ad6cd52ec1f06c76878f217
3
+ size 7608