Hugging Face's logo

Beanpow
/
zephyr-7b-dpo-full

Text Generation
Transformers
TensorBoard
Safetensors
mistral
alignment-handbook
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
Beanpow commited on
Commit
b31d5dd
·
verified ·
1 Parent(s): 7eeb82d

Training in progress, step 800

Browse files
Files changed (1) hide show
  1. runs/Apr26_11-09-33_dsw-3393-565b8f59b6-l5p7k/events.out.tfevents.1714130237.dsw-3393-565b8f59b6-l5p7k.90785.0 +2 -2
runs/Apr26_11-09-33_dsw-3393-565b8f59b6-l5p7k/events.out.tfevents.1714130237.dsw-3393-565b8f59b6-l5p7k.90785.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b535873256fe26f3edf6e898491644346077e5e5e5473b361326da741ccc1e16
3
- size 55860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfeef706351dcff667a03ee94aefc1f362a2b0b96557ef34896372bc7e0d0d32
3
+ size 63193