Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
JayHyeon
/
Qwen2-0.5B-Reward_5e-4
like
0
Text Classification
Transformers
TensorBoard
Safetensors
trl-lib/ultrafeedback_binarized
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
ebb08c6
Qwen2-0.5B-Reward_5e-4
/
all_results.json
JayHyeon
Model save
7dedb33
verified
about 1 month ago
raw
Copy download link
history
blame
Safe
189 Bytes
{
"epoch"
:
1.0
,
"eval_accuracy"
:
0.654
,
"eval_loss"
:
0.6072803735733032
,
"eval_runtime"
:
35.2702
,
"eval_samples_per_second"
:
28.353
,
"eval_steps_per_second"
:
0.907
}