Hugging Face's logo

chenggong1995
/
Qwen2.5-3B-Instruct-grpo-E6-D100-L4096-lr5e7

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
trl
grpo
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
chenggong1995 commited on
Commit
427bd8f
·
verified ·
1 Parent(s): 84803ad

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/gongc1995-city-university-of-hong-kong/huggingface/runs/deifoffg)
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/gongc1995-city-university-of-hong-kong/huggingface/runs/q0wfn7mm)
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": 1.5862,
5
  "train_samples": 100,
6
- "train_samples_per_second": 189.126,
7
- "train_steps_per_second": 1.891
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
  "train_loss": 0.0,
4
+ "train_runtime": 1.4995,
5
  "train_samples": 100,
6
+ "train_samples_per_second": 200.061,
7
+ "train_steps_per_second": 2.001
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
  "train_loss": 0.0,
4
- "train_runtime": 1.5862,
5
  "train_samples": 100,
6
- "train_samples_per_second": 189.126,
7
- "train_steps_per_second": 1.891
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
  "train_loss": 0.0,
4
+ "train_runtime": 1.4995,
5
  "train_samples": 100,
6
+ "train_samples_per_second": 200.061,
7
+ "train_steps_per_second": 2.001
8
  }
trainer_state.json CHANGED
@@ -13,9 +13,9 @@
13
  "step": 3,
14
  "total_flos": 0.0,
15
  "train_loss": 0.0,
16
- "train_runtime": 1.5862,
17
- "train_samples_per_second": 189.126,
18
- "train_steps_per_second": 1.891
19
  }
20
  ],
21
  "logging_steps": 5,
 
13
  "step": 3,
14
  "total_flos": 0.0,
15
  "train_loss": 0.0,
16
+ "train_runtime": 1.4995,
17
+ "train_samples_per_second": 200.061,
18
+ "train_steps_per_second": 2.001
19
  }
20
  ],
21
  "logging_steps": 5,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c6fabe9eb8d1ab11f0f21a7483a3714e7116c3f52306c859275b51d682c5e1e
3
  size 8056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a5c3fe792e95ed8eb581278cf998f32881152767cde99981585c343b1788118
3
  size 8056