Hugging Face's logo

Yukang
/
Qwen2.5-3B-Open-R1-Code-GRPO

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
open-r1
trl
grpo
conversational
text-generation-inference
Model card Files Community
Yukang commited on
Commit
f2765ac
·
verified ·
1 Parent(s): a840137

Training in progress, step 510

Browse files
Files changed (8) hide show
  1. README.md +1 -1
  2. all_results.json +4 -4
  3. config.json +1 -1
  4. model-00001-of-00002.safetensors +1 -1
  5. model-00002-of-00002.safetensors +1 -1
  6. train_results.json +4 -4
  7. trainer_state.json +0 -0
  8. training_args.bin +1 -1
README.md CHANGED
@@ -29,7 +29,7 @@ print(output["generated_text"])
29
 
30
  ## Training procedure
31
 
32
- [<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/chenyukang2020-nvidia/huggingface/runs/87jsozpo)
33
 
34
 
35
  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).
 
29
 
30
  ## Training procedure
31
 
32
+ [<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/chenyukang2020-nvidia/huggingface/runs/3c0353cy)
33
 
34
 
35
  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": 7.054507823697492e-06,
4
- "train_runtime": 74.8551,
5
  "train_samples": 35735,
6
- "train_samples_per_second": 3419.94,
7
- "train_steps_per_second": 6.68
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
+ "train_loss": 9.052564064315237e-07,
4
+ "train_runtime": 75.296,
5
  "train_samples": 35735,
6
+ "train_samples_per_second": 3399.916,
7
+ "train_steps_per_second": 6.64
8
  }
config.json CHANGED
@@ -22,7 +22,7 @@
22
  "tie_word_embeddings": true,
23
  "torch_dtype": "bfloat16",
24
  "transformers_version": "4.52.3",
25
- "use_cache": true,
26
  "use_sliding_window": false,
27
  "vocab_size": 151936
28
  }
 
22
  "tie_word_embeddings": true,
23
  "torch_dtype": "bfloat16",
24
  "transformers_version": "4.52.3",
25
+ "use_cache": false,
26
  "use_sliding_window": false,
27
  "vocab_size": 151936
28
  }
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30a1c3e68897bce63060646578aae237a4e7fe4665fdbfe981a18e12955e3935
3
  size 4957560304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eb6df84914c787eed2bf2a200ef3c85bbe9d288a43a32a6b00caf7521fab0e1
3
  size 4957560304
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97164a9d2e2aabf03e747f6ad265ad18373f5e2ec138503538a81b4441e37b8f
3
  size 1214366696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:307cd5439b2d80cfe9a640f0053a40ea50ff56c6b5574102626f485412b8f5d1
3
  size 1214366696
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
- "train_loss": 7.054507823697492e-06,
4
- "train_runtime": 74.8551,
5
  "train_samples": 35735,
6
- "train_samples_per_second": 3419.94,
7
- "train_steps_per_second": 6.68
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
+ "train_loss": 9.052564064315237e-07,
4
+ "train_runtime": 75.296,
5
  "train_samples": 35735,
6
+ "train_samples_per_second": 3399.916,
7
+ "train_steps_per_second": 6.64
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 sha256:5da1eddcbb114c354e9593c8cba67202a1f2a74a6c5a77536d99af07d7db0751
3
  size 8504
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9846bdd09191086fb5e7169a23b49f5974ac89201b2747a86923aa998fb05bfd
3
  size 8504