Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Haitao999
/
Qwen2.5-7B-GRPO-NM-COT-20K
like
0
Text Generation
Transformers
TensorBoard
Safetensors
RLHFlow/numia_prompt_dpo1
qwen2
Generated from Trainer
open-r1
trl
grpo
conversational
text-generation-inference
arxiv:
2402.03300
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
dd76028
Qwen2.5-7B-GRPO-NM-COT-20K
/
all_results.json
Haitao999
Model save
48d3732
verified
about 2 months ago
raw
Copy download link
history
blame
Safe
185 Bytes
{
"total_flos"
:
0.0
,
"train_loss"
:
0.0
,
"train_runtime"
:
2.2646
,
"train_samples"
:
20000
,
"train_samples_per_second"
:
8831.586
,
"train_steps_per_second"
:
39.301
}