Hugging Face's logo

Dongwei
/
DeepSeek-R1-Distill-Qwen-7B-GRPO

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
open-r1
trl
grpo
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
Dongwei commited on
Commit
385d039
·
verified ·
1 Parent(s): 521ec25

Model save

Browse files
Files changed (5) hide show
  1. README.md +1 -1
  2. all_results.json +3 -3
  3. train_results.json +3 -3
  4. trainer_state.json +3 -3
  5. training_args.bin +1 -1
README.md CHANGED
@@ -27,7 +27,7 @@ print(output["generated_text"])
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/dongwei_jiang/huggingface/runs/tydougqd)
31
 
32
 
33
  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).
 
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/dongwei_jiang/huggingface/runs/slsgpc8k)
31
 
32
 
33
  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": 0.0,
4
- "train_runtime": 15.0247,
5
  "train_samples": 7,
6
- "train_samples_per_second": 0.466,
7
- "train_steps_per_second": 0.067
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
  "train_loss": 0.0,
4
+ "train_runtime": 15.3029,
5
  "train_samples": 7,
6
+ "train_samples_per_second": 0.457,
7
+ "train_steps_per_second": 0.065
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
  "train_loss": 0.0,
4
- "train_runtime": 15.0247,
5
  "train_samples": 7,
6
- "train_samples_per_second": 0.466,
7
- "train_steps_per_second": 0.067
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
  "train_loss": 0.0,
4
+ "train_runtime": 15.3029,
5
  "train_samples": 7,
6
+ "train_samples_per_second": 0.457,
7
+ "train_steps_per_second": 0.065
8
  }
trainer_state.json CHANGED
@@ -19,9 +19,9 @@
19
  "step": 1,
20
  "total_flos": 0.0,
21
  "train_loss": 0.0,
22
- "train_runtime": 15.0247,
23
- "train_samples_per_second": 0.466,
24
- "train_steps_per_second": 0.067
25
  }
26
  ],
27
  "logging_steps": 10,
 
19
  "step": 1,
20
  "total_flos": 0.0,
21
  "train_loss": 0.0,
22
+ "train_runtime": 15.3029,
23
+ "train_samples_per_second": 0.457,
24
+ "train_steps_per_second": 0.065
25
  }
26
  ],
27
  "logging_steps": 10,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63e920eb20fd9a47847c1936f4cdfeb92754f51d824c1538067eb254c1bb131b
3
  size 7032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94be28e893b0b61d63e40be03410c41e65bd380989730b1c09cbc7ff6f49c83d
3
  size 7032