sfulay
/

zephyr-7b-dpo-full-magpi-reward-scale-05

Generated from Trainer

Model card Files Files and versions Community

zephyr-7b-dpo-full-magpi-reward-scale-05 / model-00003-of-00003.safetensors

Commit History

Training in progress, step 352

eadcf5e
verified

sfulay commited on Aug 16, 2024

Training in progress, step 300

09d3f98
verified

sfulay commited on Aug 16, 2024

Training in progress, step 200

0c83b00
verified

sfulay commited on Aug 16, 2024

Training in progress, step 100

6aa0753
verified

sfulay commited on Aug 16, 2024

Training in progress, step 100

acbae14
verified

sfulay commited on Aug 15, 2024