Commits

Commit history

1. Commits on Feb 5, 2025

   • Update grpo.py (#171)

     Some-random

     authored
     736b59fView commit details

     Copy full SHA for 736b59f

     Browse repository at this point

   • fix uv env path + details (#188)

     Show description for 3fd56dc
     

     edbeeching

     and

     lewtun

     authored
     3fd56dcView commit details

     Copy full SHA for 3fd56dc

     Browse repository at this point

   • chore(setup.py): bump vllm>=0.7.1 (#181)

     Show description for 138df0c
     ctjlewis

     authored
     138df0cView commit details

     Copy full SHA for 138df0c

     Browse repository at this point

   • GRPO training args fixes (#177)

     Show description for 5aff57c
     

     edbeeching

     and

     kashif

     authored
     5aff57cView commit details

     Copy full SHA for 5aff57c

     Browse repository at this point
2. Commits on Feb 4, 2025

   • Fix code quality after adding puzzles (#178)

     Rocketknight1

     authored
     1fc8d42View commit details

     Copy full SHA for 1fc8d42

     Browse repository at this point

   • Fix quality after adding puzzles

     Rocketknight1

     committed
     b24ce90View commit details

     Copy full SHA for b24ce90

     Browse repository at this point

   • Add puzzles

     Rocketknight1

     committed
     9ca4ed5View commit details

     Copy full SHA for 9ca4ed5

     Browse repository at this point

   • Add puzzles

     Rocketknight1

     committed
     b2d7ba2View commit details

     Copy full SHA for b2d7ba2

     Browse repository at this point
3. Commits on Jan 31, 2025

   • use ruff (#137)

     Show description for a0d61cc
     

     kashif

     and

     qgallouedec

     authored
     a0d61ccView commit details

     Copy full SHA for a0d61cc

     Browse repository at this point

   • Recipes for optimzing training scripts (#120)

     Show description for e450a6f
     

     3 peopleauthored
     e450a6fView commit details

     Copy full SHA for e450a6f

     Browse repository at this point

   • Update README.md (#132)

     Some-random

     authored
     22512e6View commit details

     Copy full SHA for 22512e6

     Browse repository at this point

   • Adds async model push to PushToHubRevisionCallback (#124)

     Show description for 99d1083
     edbeeching

     authored
     99d1083View commit details

     Copy full SHA for 99d1083

     Browse repository at this point
4. Commits on Jan 30, 2025

   • Fix message removal in GRPO script (#131)

     qgallouedec

     authored
     6820d39View commit details

     Copy full SHA for 6820d39

     Browse repository at this point

   • Add Table of Contents to README for easier navigation (#125)

     Show description for 356f6a5
     sam-schorb

     authored
     356f6a5View commit details

     Copy full SHA for 356f6a5

     Browse repository at this point

   • Grpo slurm scripts (#112)

     Show description for c0b53fa
     

     kashif

     and

     lewtun

     authored
     c0b53faView commit details

     Copy full SHA for c0b53fa

     Browse repository at this point

   • Adds auto eval callbacks (#115)

     Show description for 972e47e
     edbeeching

     authored
     972e47eView commit details

     Copy full SHA for 972e47e

     Browse repository at this point

   • Fix help text for --retries to match actual default value (#103)

     Show description for f7b8e52
     ATaylorAerospace

     authored
     f7b8e52View commit details

     Copy full SHA for f7b8e52

     Browse repository at this point

   • docs(README): note about CUDA 12.1 (#121)

     Show description for fb1b4c4
     ctjlewis

     authored
     fb1b4c4View commit details

     Copy full SHA for fb1b4c4

     Browse repository at this point
5. Commits on Jan 29, 2025

   • Update README.md (#93)

     edbeeching

     authored
     bd0e15bView commit details

     Copy full SHA for bd0e15b

     Browse repository at this point

   • Corrected Typos in README.md (#110)

     Mayur-Pagote

     authored
     7a7682bView commit details

     Copy full SHA for 7a7682b

     Browse repository at this point

   • Modified: pip install --upgrade pip (#99)

     isthatdebbiej

     authored
     971294bView commit details

     Copy full SHA for 971294b

     Browse repository at this point

   • fix typos (#40)

     Show description for 401a219
     

     mariagrandury

     and

     qgallouedec

     authored
     401a219View commit details

     Copy full SHA for 401a219

     Browse repository at this point

   • Improve repoduction of r1 reported score (#92)

     Show description for e2235cf
     

     hynky1999

     and

     Hynek Kydlicek

     authored
     e2235cfView commit details

     Copy full SHA for e2235cf

     Browse repository at this point
6. Commits on Jan 28, 2025

   • Change conda for uv (#91)

     Show description for c4fdb69
     andimarafioti

     authored
     c4fdb69View commit details

     Copy full SHA for c4fdb69

     Browse repository at this point

   • Add `--timeout`, `--retries`, `--prompt-template` and TP and PP by slurm variables (#94)

     Show description for c5941ed
     gabrielmbmb

     authored
     c5941edView commit details

     Copy full SHA for c5941ed

     Browse repository at this point
7. Commits on Jan 27, 2025

   • Bump actions/setup-python from 2 to 5 (#75)

     Show description for e2e403d
     dependabot[bot]

     authored
     e2e403dView commit details

     Copy full SHA for e2e403d

     Browse repository at this point

   • Bump actions/checkout from 2 to 4 (#76)

     Show description for 29015d7
     dependabot[bot]

     authored
     29015d7View commit details

     Copy full SHA for 29015d7

     Browse repository at this point

   • Added dependabot integration (#70)

     ygdrax

     authored
     9ab30a1View commit details

     Copy full SHA for 9ab30a1

     Browse repository at this point

   • Add `--input-batch-size`, `--client-replicas` args and download Ray logs (#71)

     Show description for b03480d
     

     gabrielmbmb

     and

     qgallouedec

     authored
     b03480dView commit details

     Copy full SHA for b03480d

     Browse repository at this point

   • Update README.md (#72)

     qgallouedec

     authored
     67764bcView commit details

     Copy full SHA for 67764bc

     Browse repository at this point

   • Implement make evaluate command (#41)

     Show description for d6f1a17
     mariagrandury

     authored
     d6f1a17View commit details

     Copy full SHA for d6f1a17

     Browse repository at this point

   • docs: fix grammar and phrasing issues (1, 2, 3) (#62)

     Show description for 8d37c5c
     CharlesCNorton

     authored
     8d37c5cView commit details

     Copy full SHA for 8d37c5c

     Browse repository at this point

   • Update evaluate.slurm

     Show description for feb59d2
     edbeeching

     authored
     feb59d2View commit details

     Copy full SHA for feb59d2

     Browse repository at this point
8. Commits on Jan 26, 2025

   • docs: update README.md (#54)

     Show description for 7c01b59
     

     eltociear

     and

     qgallouedec

     authored
     7c01b59View commit details

     Copy full SHA for 7c01b59

     Browse repository at this point

   • Reward verification and evaluation fixes (#55)

     Show description for 90b0947
     

     3 peopleauthored
     90b0947View commit details

     Copy full SHA for 90b0947

     Browse repository at this point