Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
dadadar
/
Qwen2.5-3B-Open-R1-GRPO
like
0
Text Generation
Transformers
Safetensors
open-r1/OpenR1-Math-220k
qwen2
Generated from Trainer
open-r1
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
Qwen2.5-3B-Open-R1-GRPO
/
train_results.json
dadadar
Model save
1a8d880
verified
about 1 year ago
raw
Copy download link
history
blame
Safe
200 Bytes
{
"total_flos"
:
0.0
,
"train_loss"
:
162.96194878991443
,
"train_runtime"
:
154205.9094
,
"train_samples"
:
20000
,
"train_samples_per_second"
:
0.13
,
"train_steps_per_second"
:
0.016
}