Hugging Face's logo

plaguss
/
Qwen2.5-0.5B-Math-Shepherd-PRM-token-0.1

Token Classification
Transformers
Safetensors
qwen2
Generated from Trainer
trl
stepwise-reward-trainer
text-generation-inference
Inference Endpoints
Model card Files Community
plaguss HF staff commited on
Commit
64f138a
•
1 Parent(s): 2f8b8fe

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": 0.9998485078018482,
3
+ "eval_accuracy": 0.9968007098503038,
4
+ "eval_loss": 0.0070624761283397675,
5
+ "eval_runtime": 106.6709,
6
+ "eval_samples_per_second": 208.417,
7
+ "eval_steps_per_second": 6.515
8
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9998485078018482,
3
+ "eval_accuracy": 0.9968007098503038,
4
+ "eval_loss": 0.0070624761283397675,
5
+ "eval_runtime": 106.6709,
6
+ "eval_samples_per_second": 208.417,
7
+ "eval_steps_per_second": 6.515
8
+ }