Hugging Face's logo

leonMW
/
DeepSeek-R1-Distill-Qwen-7B-GSPO-Basic

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
grpo
open-r1
trl
conversational
text-generation-inference
Model card Files Community
leonMW commited on
Commit
38be7aa
·
verified ·
1 Parent(s): 4766b53

Model save

Browse files
Files changed (3) hide show
  1. all_results.json +4 -4
  2. train_results.json +4 -4
  3. trainer_state.json +0 -0
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
- "train_loss": 0.0,
4
- "train_runtime": 1.3342,
5
  "train_samples": 3053,
6
- "train_samples_per_second": 2288.34,
7
- "train_steps_per_second": 65.959
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
+ "train_loss": 0.12009330927817659,
4
+ "train_runtime": 7974.5852,
5
  "train_samples": 3053,
6
+ "train_samples_per_second": 0.383,
7
+ "train_steps_per_second": 0.011
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
- "train_loss": 0.0,
4
- "train_runtime": 1.3342,
5
  "train_samples": 3053,
6
- "train_samples_per_second": 2288.34,
7
- "train_steps_per_second": 65.959
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
+ "train_loss": 0.12009330927817659,
4
+ "train_runtime": 7974.5852,
5
  "train_samples": 3053,
6
+ "train_samples_per_second": 0.383,
7
+ "train_steps_per_second": 0.011
8
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff