Hugging Face
Models
Datasets
Spaces
Community
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
xet
Community
Deploy
Use this model
main
debug
/
train_results.json
sohyunan
Model save
2163a44
verified
11 months ago
raw
Copy download link
history
blame
contribute
delete
Safe
178 Bytes
{
"total_flos"
:
0.0
,
"train_loss"
:
0.0
,
"train_runtime"
:
27.9508
,
"train_samples"
:
2
,
"train_samples_per_second"
:
0.072
,
"train_steps_per_second"
:
0.036
}