Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
zodi1121
/
zephyr-7b-dpo-full
like
0
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
trl
dpo
Generated from Trainer
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
main
zephyr-7b-dpo-full
/
runs
/
Aug19_07-43-13_simpo-8-0-0
Ctrl+K
Ctrl+K
1 contributor
History:
6 commits
zodi1121
End of training
dcc6994
verified
9 months ago
events.out.tfevents.1724079187.simpo-8-0-0.82974.0
Safe
42.3 kB
LFS
Training in progress, step 478
9 months ago
events.out.tfevents.1724086983.simpo-8-0-0.82974.1
Safe
828 Bytes
LFS
End of training
9 months ago