Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
sohyunan
/
debug
like
0
Text Generation
Transformers
Safetensors
maze_5x5
gemma2
Generated from Trainer
controller-grpo
trl
grpo
conversational
text-generation-inference
arxiv:
2402.03300
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
main
debug
/
eval_results.json
sohyunan
Model save
2163a44
verified
about 2 months ago
raw
Copy download link
history
blame
contribute
delete
Safe
168 Bytes
{
"eval_loss"
:
1.4901161193847656e-08
,
"eval_runtime"
:
6.7089
,
"eval_samples"
:
2
,
"eval_samples_per_second"
:
0.298
,
"eval_steps_per_second"
:
0.149
}