Hugging Face's logo

DUAL-GPO
/
phi-2-gpo-20k-40k-60k-lora512-i2

PEFT
TensorBoard
Safetensors
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
Model card Files Metrics Community
phi-2-gpo-20k-40k-60k-lora512-i2 / runs /May18_15-22-02_ip-10-192-12-250 /events.out.tfevents.1716045809.ip-10-192-12-250.4686.0

Commit History

Training in progress, step 100
4f91141
verified

BraylonDash commited on