Hugging Face's logo

qgallouedec
/
Qwen2-0.5B-Reward-Math-Sheperd

Token Classification
Transformers
Safetensors
qwen2
Generated from Trainer
trl
stepwise-reward-trainer
text-generation-inference
Model card Files
xet
 Community
qgallouedec HF Staff commited on
Commit
4dbd820
·
verified ·
1 Parent(s): ea9972d

Model save

Browse files
Files changed (2) hide show
  1. all_results.json +8 -0
  2. eval_results.json +8 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_accuracy": 0.9966289556146843,
4
+ "eval_loss": 0.007473934907466173,
5
+ "eval_runtime": 63.1801,
6
+ "eval_samples_per_second": 351.899,
7
+ "eval_steps_per_second": 5.508
8
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_accuracy": 0.9966289556146843,
4
+ "eval_loss": 0.007473934907466173,
5
+ "eval_runtime": 63.1801,
6
+ "eval_samples_per_second": 351.899,
7
+ "eval_steps_per_second": 5.508
8
+ }