Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
HuggingFaceH4
/
Qwen2.5-Math-1.5B-Instruct-PRM-0.2
like
0
Follow
Hugging Face H4
1.09k
Token Classification
Transformers
Safetensors
HuggingFaceH4/prm800k-trl-dedup
qwen2
Generated from Trainer
trl
prm
text-generation-inference
arxiv:
2211.14275
Model card
Files
Files and versions
xet
Community
Train
Deploy
Use this model
bc44d4a
Qwen2.5-Math-1.5B-Instruct-PRM-0.2
/
all_results.json
plaguss
Model save
ca50afa
verified
6 months ago
raw
Copy download link
history
blame
Safe
203 Bytes
{
"epoch"
:
1.0
,
"eval_accuracy"
:
0.9162550061554284
,
"eval_loss"
:
0.2708306312561035
,
"eval_runtime"
:
29.6687
,
"eval_samples_per_second"
:
345.347
,
"eval_steps_per_second"
:
5.427
}