Skip to content

Actions: volcengine/verl

e2e_sft

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
196 workflow runs
196 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[misc]: fix ci and add warning to make sure wandb is used when loggin…
e2e_sft #237: Commit 3d566ad pushed by PeterSH6
February 9, 2025 16:21 34m 22s main
February 9, 2025 16:21 34m 22s
delete redundant append_to_dict (#236)
e2e_sft #236: Commit 6427f50 pushed by vermouth1992
February 9, 2025 14:45 1h 34m 49s main
February 9, 2025 14:45 1h 34m 49s
Add option to log validation generations to wandb (#177)
e2e_sft #233: Commit d0725a6 pushed by PeterSH6
February 9, 2025 13:42 1h 4m 33s main
February 9, 2025 13:42 1h 4m 33s
delete redundant append_to_dict
e2e_sft #232: Pull request #236 opened by Cppowboy
February 9, 2025 13:24 46m 38s Cppowboy:main
February 9, 2025 13:24 46m 38s
Add stronger reward verification sandbox
e2e_sft #231: Pull request #233 synchronize by ZefanW
February 9, 2025 13:05 1h 2m 22s ZefanW:sandbox
February 9, 2025 13:05 1h 2m 22s
Feature/add remax support
e2e_sft #230: Pull request #234 opened by liziniu
February 9, 2025 12:56 Action required liziniu:feature/add-remax-support
February 9, 2025 12:56 Action required
Add stronger reward verification sandbox
e2e_sft #229: Pull request #233 synchronize by ZefanW
February 9, 2025 12:41 54m 2s ZefanW:sandbox
February 9, 2025 12:41 54m 2s
Add stronger reward verification sandbox
e2e_sft #228: Pull request #233 opened by ZefanW
February 9, 2025 12:11 51m 0s ZefanW:sandbox
February 9, 2025 12:11 51m 0s
add requirements (#231)
e2e_sft #227: Commit 577a341 pushed by vermouth1992
February 9, 2025 11:41 21m 11s main
February 9, 2025 11:41 21m 11s
docs: add programming model guide (#230)
e2e_sft #226: Commit e842b73 pushed by eric-haibin-lin
February 9, 2025 11:10 31m 51s main
February 9, 2025 11:10 31m 51s
add requirements
e2e_sft #225: Pull request #231 opened by ZefanW
February 9, 2025 10:03 1h 6m 47s ZefanW:dummy
February 9, 2025 10:03 1h 6m 47s
implement REINFORCE++ algorithm (#228)
e2e_sft #222: Commit bdb50ac pushed by vermouth1992
February 9, 2025 09:37 36m 28s main
February 9, 2025 09:37 36m 28s
implement REINFORCE++ algorithm
e2e_sft #221: Pull request #228 synchronize by 4332001876
February 9, 2025 09:28 3m 24s 4332001876:feat_reinforce_plus_plus
February 9, 2025 09:28 3m 24s
implement REINFORCE++ algorithm
e2e_sft #220: Pull request #228 synchronize by 4332001876
February 9, 2025 08:32 30m 30s 4332001876:feat_reinforce_plus_plus
February 9, 2025 08:32 30m 30s
implement REINFORCE++ algorithm
e2e_sft #219: Pull request #228 synchronize by 4332001876
February 9, 2025 07:47 3m 26s 4332001876:feat_reinforce_plus_plus
February 9, 2025 07:47 3m 26s
Add push to hub functionality
e2e_sft #218: Pull request #196 synchronize by NielsRogge
February 8, 2025 17:17 Action required NielsRogge:add_push_to_hub
February 8, 2025 17:17 Action required
Add push to hub functionality
e2e_sft #217: Pull request #196 synchronize by NielsRogge
February 8, 2025 17:15 Action required NielsRogge:add_push_to_hub
February 8, 2025 17:15 Action required
Add push to hub functionality
e2e_sft #216: Pull request #196 synchronize by NielsRogge
February 8, 2025 17:15 Action required NielsRogge:add_push_to_hub
February 8, 2025 17:15 Action required
[ckpt] feat: integrate checkpoint resume in RL ray trainer (#222)
e2e_sft #214: Commit 5a400bf pushed by PeterSH6
February 8, 2025 13:35 29m 59s main
February 8, 2025 13:35 29m 59s
[ckpt] feat: integrate checkpoint resume in RL ray trainer
e2e_sft #213: Pull request #222 synchronize by PeterSH6
February 8, 2025 12:38 45m 1s gm/ckpt_integrate
February 8, 2025 12:38 45m 1s
[ckpt] feat: integrate checkpoint resume in RL ray trainer
e2e_sft #212: Pull request #222 synchronize by PeterSH6
February 8, 2025 12:25 3m 27s gm/ckpt_integrate
February 8, 2025 12:25 3m 27s
[ckpt] feat: integrate checkpoint resume in RL ray trainer
e2e_sft #211: Pull request #222 synchronize by PeterSH6
February 8, 2025 11:45 3m 20s gm/ckpt_integrate
February 8, 2025 11:45 3m 20s