Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
tanliboy
/
zephyr-gemma-2-9b-dpo-4k
like
0
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
gemma2
alignment-handbook
trl
dpo
Generated from Trainer
Model card
Files
Files and versions
xet
Metrics
Training metrics
Community
main
zephyr-gemma-2-9b-dpo-4k
/
runs
/
Aug11_15-24-00_action-graph-trainer
43.4 kB
1 contributor
History:
2 commits
tanliboy
End of training
aebef63
verified
about 1 year ago
events.out.tfevents.1723390427.action-graph-trainer.2255898.0
Safe
42.6 kB
xet
Model save
about 1 year ago
events.out.tfevents.1723408324.action-graph-trainer.2255898.1
Safe
828 Bytes
xet
End of training
about 1 year ago