Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
maxkordn
/
Qwen2.5-Coder-7B-Instruct-Solver-RFT
like
0
Text Generation
Transformers
Safetensors
flattened_successful_trajectories/v1
qwen2
Generated from Trainer
cogzero
trl
sft
kordn
conversational
text-generation-inference
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
e27b690
Qwen2.5-Coder-7B-Instruct-Solver-RFT
/
eval_results.json
maxkordn
End of training
c15d218
verified
8 months ago
raw
Copy download link
history
blame
Safe
170 Bytes
{
"eval_loss"
:
0.10813906788825989
,
"eval_runtime"
:
52.8222
,
"eval_samples"
:
2505
,
"eval_samples_per_second"
:
47.423
,
"eval_steps_per_second"
:
5.944
}