Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
ZHIYII
/
Qwen2.5-7B-Reward
like
0
Text Classification
Transformers
TensorBoard
Safetensors
ZHIYII/Live_code_preference
qwen2
Generated from Trainer
trl
reward-trainer
text-generation-inference
Inference Endpoints
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
1ba6158
Qwen2.5-7B-Reward
/
all_results.json
ZHIYII
Model save
1ba6158
verified
about 1 month ago
raw
Copy download link
history
blame
Safe
191 Bytes
{
"epoch"
:
1.0
,
"eval_accuracy"
:
0.996
,
"eval_loss"
:
0.012167233042418957
,
"eval_runtime"
:
97.8596
,
"eval_samples_per_second"
:
51.094
,
"eval_steps_per_second"
:
0.807
}