Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
kangdawei
/
DAPO
like
0
Text Generation
Transformers
Safetensors
knoveleng/open-rs
qwen2
Generated from Trainer
open-r1
dapo
trl
conversational
text-generation-inference
arxiv:
2503.14476
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
DAPO
/
all_results.json
kangdawei
Model save
3939526
verified
about 2 months ago
raw
Copy download link
history
blame
contribute
delete
200 Bytes
{
"total_flos"
:
0.0
,
"train_loss"
:
0.02940896774176508
,
"train_runtime"
:
83918.4654
,
"train_samples"
:
7000
,
"train_samples_per_second"
:
0.114
,
"train_steps_per_second"
:
0.002
}