di35117/msmefinal
Clean up Blog.MD formatting and tags
Merge pull request #4 from di35117/mrinmoy
fixed readme
Fixed readme
Revise Blog.MD for improved clarity and structure
Update blog content on training small LLMs
some changes done
Revise Blog.MD for improved clarity and structure
collab notebook done
Merge pull request #3 from di35117/mrinmoy
Final changes
Merge branch 'main' of https://github.com/di35117/msme_env into mrinmoy
updated fixes
Merge branch 'main' of https://github.com/di35117/msme_env into mrinmoy
Changed the tone of readme
ui added
Merge branch 'main' of https://github.com/di35117/msme_env
index.html deleted
Merge pull request #2 from di35117/mrinmoy
Updated readme
changes done
changes
Merge branch 'main' of https://github.com/di35117/msme_env
some changes made
Merge branch 'main' of https://github.com/di35117/msme_env
constant error solved
Revise blog content on training small LLMs for language decoding
changes made
updates
some changes made
submission readme update
k
some chages made in train and score checkpoints
sime changes donbe
training and rewards fixed
several fixes fixed
.
some bug fixed
changes done in training loop to prevent aggresive changes
changes done
reward function fixed
Plot upgrade: business-outcome curves, annotated before/after, MSME/startup split, action-shift, KPI scorecard
some changes amde
Tune GRPO: lower entropy bonus, decay LR, amplify episode reward
several changes made
some changes done
some changes doen in train file
some changes done
reward fixed
some changes done