Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
icemoon28
/
countdown_chinese
like
0
Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
trl
grpo
conversational
text-generation-inference
arxiv:
2402.03300
Model card
Files
Files and versions
xet
Community
1
Deploy
Use this model
refs/pr/1
countdown_chinese
/
all_results.json
icemoon28
Model save
3ab490d
verified
about 1 year ago
raw
Copy download link
history
blame
205 Bytes
{
"total_flos"
:
0.0
,
"train_loss"
:
0.00014642298419068685
,
"train_runtime"
:
10716.9446
,
"train_samples"
:
485460
,
"train_samples_per_second"
:
1.344
,
"train_steps_per_second"
:
0.056
}