Skip to content

Actions: volcengine/verl

model_rmpad

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
323 workflow runs
323 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

add requirements
model_rmpad #345: Pull request #231 opened by ZefanW
February 9, 2025 10:03 1h 32m 19s ZefanW:dummy
February 9, 2025 10:03 1h 32m 19s
docs: add programming model guide
model_rmpad #344: Pull request #230 opened by eric-haibin-lin
February 9, 2025 10:02 36m 57s eric-haibin-lin:hlin/program-model
February 9, 2025 10:02 36m 57s
implement REINFORCE++ algorithm (#228)
model_rmpad #342: Commit bdb50ac pushed by vermouth1992
February 9, 2025 09:37 31m 26s main
February 9, 2025 09:37 31m 26s
implement REINFORCE++ algorithm
model_rmpad #341: Pull request #228 synchronize by 4332001876
February 9, 2025 09:28 30m 35s 4332001876:feat_reinforce_plus_plus
February 9, 2025 09:28 30m 35s
implement REINFORCE++ algorithm
model_rmpad #340: Pull request #228 synchronize by 4332001876
February 9, 2025 08:32 27m 14s 4332001876:feat_reinforce_plus_plus
February 9, 2025 08:32 27m 14s
implement REINFORCE++ algorithm
model_rmpad #339: Pull request #228 synchronize by 4332001876
February 9, 2025 07:47 30m 50s 4332001876:feat_reinforce_plus_plus
February 9, 2025 07:47 30m 50s
Add push to hub functionality
model_rmpad #338: 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
model_rmpad #337: 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
model_rmpad #336: 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)
model_rmpad #334: Commit 5a400bf pushed by PeterSH6
February 8, 2025 13:35 31m 39s main
February 8, 2025 13:35 31m 39s
[ckpt] feat: integrate checkpoint resume in RL ray trainer
model_rmpad #333: Pull request #222 synchronize by PeterSH6
February 8, 2025 12:38 46m 40s gm/ckpt_integrate
February 8, 2025 12:38 46m 40s
[ckpt] feat: integrate checkpoint resume in RL ray trainer
model_rmpad #332: Pull request #222 synchronize by PeterSH6
February 8, 2025 12:25 6m 47s gm/ckpt_integrate
February 8, 2025 12:25 6m 47s
[ckpt] feat: integrate checkpoint resume in RL ray trainer
model_rmpad #331: Pull request #222 synchronize by PeterSH6
February 8, 2025 11:45 8m 25s gm/ckpt_integrate
February 8, 2025 11:45 8m 25s
Add stronger reward verification sandbox
model_rmpad #330: Pull request #207 synchronize by ZefanW
February 8, 2025 10:45 3m 17s ZefanW:sandbox
February 8, 2025 10:45 3m 17s
[ckpt] feat: support saving and loading FSDP full state dict in ckpt manager
model_rmpad #328: Pull request #225 synchronize by PeterSH6
February 8, 2025 10:39 3m 0s gm/full_ckpt
February 8, 2025 10:39 3m 0s
[ckpt] feat: support saving and loading FSDP full state dict in ckpt manager
model_rmpad #327: Pull request #225 synchronize by PeterSH6
February 8, 2025 09:55 35m 4s gm/full_ckpt
February 8, 2025 09:55 35m 4s
[ckpt] feat: integrate checkpoint resume in RL ray trainer
model_rmpad #326: Pull request #222 synchronize by PeterSH6
February 8, 2025 09:33 20m 1s gm/ckpt_integrate
February 8, 2025 09:33 20m 1s
[Hardware] Add support for Huawei Ascend NPU
model_rmpad #325: Pull request #198 synchronize by Chendong98
February 8, 2025 09:22 Action required Chendong98:support-npu
February 8, 2025 09:22 Action required
[ckpt] feat: support saving and loading FSDP full state dict in ckpt manager
model_rmpad #324: Pull request #225 synchronize by PeterSH6
February 8, 2025 09:18 31m 22s gm/full_ckpt
February 8, 2025 09:18 31m 22s
[ckpt] feat: support saving and loading FSDP full state dict in ckpt manager
model_rmpad #323: Pull request #225 opened by PeterSH6
February 8, 2025 09:15 4m 33s gm/full_ckpt
February 8, 2025 09:15 4m 33s
[ckpt] feat: integrate checkpoint resume in RL ray trainer
model_rmpad #322: Pull request #222 synchronize by PeterSH6
February 8, 2025 08:03 8m 32s gm/ckpt_integrate
February 8, 2025 08:03 8m 32s
Memory efficiency improvement to logprobs_from_logits_v2 (#220)
model_rmpad #320: Commit 4b51624 pushed by vermouth1992
February 8, 2025 05:41 30m 37s main
February 8, 2025 05:41 30m 37s
Add stronger reward verification sandbox
model_rmpad #319: Pull request #207 synchronize by ZefanW
February 8, 2025 05:31 8m 15s ZefanW:sandbox
February 8, 2025 05:31 8m 15s
[ckpt] feat: integrate checkpoint resume in RL ray trainer
model_rmpad #318: Pull request #222 synchronize by PeterSH6
February 8, 2025 05:03 6m 43s gm/ckpt_integrate
February 8, 2025 05:03 6m 43s
[ckpt] feat: integrate checkpoint resume in RL ray trainer
model_rmpad #317: Pull request #222 synchronize by PeterSH6
February 8, 2025 04:15 32m 10s gm/ckpt_integrate
February 8, 2025 04:15 32m 10s