Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
trl-lib
/
Qwen2-0.5B-Reward-Math-Sheperd
like
0
Follow
TRL
99
Token Classification
Transformers
TensorBoard
Safetensors
trl-lib/math_shepherd
qwen2
Generated from Trainer
trl
stepwise-reward-trainer
text-generation-inference
arxiv:
2211.14275
Model card
Files
Files and versions
Metrics
Training metrics
Community
1
Train
Deploy
Use this model
main
Qwen2-0.5B-Reward-Math-Sheperd
/
runs
/
Dec09_19-51-10_ip-26-0-171-21
Ctrl+K
Ctrl+K
1 contributor
History:
15 commits
qgallouedec
HF Staff
Model save
2b8acab
verified
5 months ago
events.out.tfevents.1733773892.ip-26-0-171-21.2852281.0
Safe
104 kB
LFS
Training in progress, step 6601
5 months ago
events.out.tfevents.1733785797.ip-26-0-171-21.2852281.1
Safe
411 Bytes
LFS
Model save
5 months ago