MeowFR
/

mistral-7b-humanization-grpo

Reinforcement Learning

Model card Files Files and versions

mistral-7b-humanization-grpo

Commit History

Upload téléchargement.png

073458c
verified

MeowFR commited on Jan 31

Step 900 MA=0.629

d5a82e9
verified

MeowFR commited on Jan 31

Step 800 MA=0.724

dc4c59e
verified

MeowFR commited on Jan 31

Step 700 MA=0.636

1944152
verified

MeowFR commited on Jan 31

Step 600 MA=0.683

e1f8006
verified

MeowFR commited on Jan 31

Step 500 MA=0.682

9a440ee
verified

MeowFR commited on Jan 31

Step 400 MA=0.702

4df378a
verified

MeowFR commited on Jan 31

Step 300 MA=0.611

ad12b91
verified

MeowFR commited on Jan 31

Step 200 MA=0.699

79590d1
verified

MeowFR commited on Jan 30

Step 100 MA=0.712

ecec553
verified

MeowFR commited on Jan 30

initial commit

c219e4d
verified

MeowFR commited on Jan 28