zephyr-7b-dpo-full-prometheus-reward-scale-05 / model-00001-of-00003.safetensors

Commit History

Training in progress, step 437
64f09a9
verified

sfulay commited on

Training in progress, step 400
2ebd77f
verified

sfulay commited on

Training in progress, step 300
4d6028b
verified

sfulay commited on

Training in progress, step 200
56b9724
verified

sfulay commited on

Training in progress, step 100
1641d38
verified

sfulay commited on