sisl / astra-rl / 17291071111

Builds Branch Commit Type Ran Committer Via Coverage
17291071111 main Merge pull request #14 from sisl/copilot/fix-13 Add device consistency validation for logprobs to prevent cryptic runtime errors push web-flow github
47.44
17282073529 main Merge pull request #14 from sisl/copilot/fix-13 Add device consistency validation for logprobs to prevent cryptic runtime errors push web-flow github
47.44
17281286913 copilot/fix-13 Fix linting issues in device consistency tests Co-authored-by: Jemoka <28765741+Jemoka@users.noreply.github.com> Pull #14 Copilot github
47.44
17281618810 main push llama training example push Jemoka github
43.36
17280181140 feat/ppo bumping and adding accelerate dependency push Jemoka github
39.85
17262237829 main Merge pull request #12 from sisl/feat/ppo PPO push web-flow github
43.36
17233317758 main Merge pull request #12 from sisl/feat/ppo PPO push web-flow github
43.36
17204280202 main Merge pull request #12 from sisl/feat/ppo PPO push web-flow github
43.36
17186709736 main Merge pull request #12 from sisl/feat/ppo PPO push web-flow github
43.36
17173637546 main Merge pull request #12 from sisl/feat/ppo PPO push web-flow github
43.36
17150994463 main Merge pull request #12 from sisl/feat/ppo PPO push web-flow github
43.36
17122258069 main Merge pull request #12 from sisl/feat/ppo PPO push web-flow github
43.36
17093729270 main Merge pull request #12 from sisl/feat/ppo PPO push web-flow github
43.36
17084363507 main Merge pull request #12 from sisl/feat/ppo PPO push web-flow github
43.36
17084355398 feat/ppo add value calculation into hf extension, and fix typo push Jemoka github
43.36