Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
pullpull
/
qwen-2.5-3b-r1-countdown
like
0
Text Generation
Transformers
TensorBoard
Safetensors
qwen2
Generated from Trainer
trl
grpo
conversational
text-generation-inference
arxiv:
2402.03300
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
9b8fb0b
qwen-2.5-3b-r1-countdown
/
all_results.json
pullpull
Model save
9b8fb0b
verified
about 2 months ago
raw
Copy download link
history
blame
Safe
203 Bytes
{
"total_flos"
:
0.0
,
"train_loss"
:
9.454646318052558e-05
,
"train_runtime"
:
16471.8629
,
"train_samples"
:
45000
,
"train_samples_per_second"
:
0.219
,
"train_steps_per_second"
:
0.027
}