Spaces:
Sleeping
Sleeping
Commit History
-
Updated Loss Reward
Ankit623b83c -
Blog Added
Ankit4690767 -
added
Ankit4fa20ab -
Re-add oracle.jsonl using LFS
Ankitfc2ea9e -
Track jsonl with LFS
Ankit1fc05a8 -
Add LFS tracking
Ankit03fcaa7 -
fix: GRPO zero-gradient trap, DSL prompt seed, best_reward, teacher oracle
0b77231 -
training results
ede0718
-
track pngs with lfs
f199299 -
Remove artifacts from git tracking to fix HF push
c0b88d6 -
Merge pull request #7 from rohan-27p/rohan
Unverified signatureipynb81dcf17 -
ipynb
4416aad -
Merge pull request #6 from rohan-27p/rohan
Unverified signaturedockerfile for hf depe9af855 -
dockerfile for hf dep
d3b9f66 -
Merge pull request #5 from rohan-27p/rohan
Unverified signaturereadme0d4b374 -
readme
a34d4a2 -
Merge pull request #4 from rohan-27p/rohan
Unverified signaturediscovery plote1a1a44 -
discovery plot
1edadfb -
Merge pull request #3 from rohan-27p/rohan
Unverified signaturereward curvea6e5d36 -
reward curve
8c686ce -
Merge pull request #2 from rohan-27p/rohan
Unverified signatureimp DSL, reward structure, paradigm shift060e448 -
imp DSL, reward structure, paradigm shift
8270f31 -
Merge pull request #1 from rohan-27p/rohan
Unverified signatureRL8ebf5fc -
submodule access,timeout, gro checkpoints, mdl penalty
92e9724 -
V1
Ankitbe9f416 -
first commit
6759502