Hugging Face's logo

leonMW
/
DeepSeek-R1-Distill-Qwen-14B-GSPO-Basic-Easy

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
trl
grpo
conversational
text-generation-inference
Model card Files
xet
Community
leonMW commited on
Commit
bfb88c7
·
verified ·
1 Parent(s): dd35a3a

Model save

Browse files
Files changed (4) hide show
  1. all_results.json +4 -4
  2. generation_config.json +1 -3
  3. train_results.json +4 -4
  4. 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": 2.7042,
5
  "train_samples": 5000,
6
- "train_samples_per_second": 1848.955,
7
- "train_steps_per_second": 230.75
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
+ "train_loss": 0.0006463412022966599,
4
+ "train_runtime": 115411.6286,
5
  "train_samples": 5000,
6
+ "train_samples_per_second": 0.087,
7
+ "train_steps_per_second": 0.011
8
  }
generation_config.json CHANGED
@@ -2,9 +2,7 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 151646,
4
  "do_sample": true,
5
- "eos_token_id": [
6
- 151643
7
- ],
8
  "pad_token_id": 151643,
9
  "temperature": 0.6,
10
  "top_p": 0.95,
 
2
  "_from_model_config": true,
3
  "bos_token_id": 151646,
4
  "do_sample": true,
5
+ "eos_token_id": 151643,
 
 
6
  "pad_token_id": 151643,
7
  "temperature": 0.6,
8
  "top_p": 0.95,
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
- "train_loss": 0.0,
4
- "train_runtime": 2.7042,
5
  "train_samples": 5000,
6
- "train_samples_per_second": 1848.955,
7
- "train_steps_per_second": 230.75
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
+ "train_loss": 0.0006463412022966599,
4
+ "train_runtime": 115411.6286,
5
  "train_samples": 5000,
6
+ "train_samples_per_second": 0.087,
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