Skip to content

Actions: volcengine/verl

model_rmpad

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
61 workflow runs
61 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[misc][Long Context] feat: support ulysses for long context training
model_rmpad #36: Pull request #109 synchronize by PeterSH6
January 17, 2025 09:54 1m 3s PeterSH6:gm/uly
January 17, 2025 09:54 1m 3s
[misc][Long Context] feat: support ulysses for long context training
model_rmpad #35: Pull request #109 synchronize by PeterSH6
January 17, 2025 07:42 15m 35s PeterSH6:gm/uly
January 17, 2025 07:42 15m 35s
[misc][Long Context] feat: support ulysses for long context training
model_rmpad #34: Pull request #109 synchronize by PeterSH6
January 17, 2025 06:22 1m 4s PeterSH6:gm/uly
January 17, 2025 06:22 1m 4s
[misc][Long Context] feat: support ulysses for long context training
model_rmpad #33: Pull request #109 synchronize by PeterSH6
January 17, 2025 06:14 2m 34s PeterSH6:gm/uly
January 17, 2025 06:14 2m 34s
[misc][Long Context] feat: support ulysses for long context training
model_rmpad #32: Pull request #109 synchronize by PeterSH6
January 17, 2025 05:32 10m 49s PeterSH6:gm/uly
January 17, 2025 05:32 10m 49s
[misc][Long Context] feat: support ulysses for long context training
model_rmpad #31: Pull request #109 synchronize by PeterSH6
January 17, 2025 05:27 15m 13s PeterSH6:gm/uly
January 17, 2025 05:27 15m 13s
[misc] fix: fix license (#110)
model_rmpad #30: Commit a33a3ba pushed by PeterSH6
January 16, 2025 16:03 1m 10s main
January 16, 2025 16:03 1m 10s
[misc] fix: fix license
model_rmpad #29: Pull request #110 opened by vermouth1992
January 16, 2025 14:22 1m 8s chi/fix/license
January 16, 2025 14:22 1m 8s
[misc][Long Context] feat: support ulysses for long context training
model_rmpad #28: Pull request #109 synchronize by PeterSH6
January 16, 2025 13:34 1m 25s PeterSH6:gm/uly
January 16, 2025 13:34 1m 25s
[misc][Long Context] feat: support ulysses for long context training
model_rmpad #27: Pull request #109 opened by PeterSH6
January 16, 2025 13:21 1m 12s PeterSH6:gm/uly
January 16, 2025 13:21 1m 12s
refact: hybrid_engine dir to sharding_manager for more general repres…
model_rmpad #26: Commit 6a9f6e1 pushed by vermouth1992
January 14, 2025 08:19 1m 4s main
January 14, 2025 08:19 1m 4s
Fix loss value for gradient accumulation > 1 (#102)
model_rmpad #24: Commit e230de8 pushed by vermouth1992
January 14, 2025 01:51 1m 3s main
January 14, 2025 01:51 1m 3s
Fix the displayed loss in the sft trainer for gradient accumulation > 1
model_rmpad #23: Pull request #102 opened by hiyouga
January 13, 2025 18:25 1m 7s hiyouga:patch-1
January 13, 2025 18:25 1m 7s
[misc] feat: support different flash_attn versions with variable num …
model_rmpad #22: Commit 1facb9d pushed by PeterSH6
January 13, 2025 08:38 15m 50s main
January 13, 2025 08:38 15m 50s
[misc] feat: support different flash_attn versions with variable num returns
model_rmpad #21: Pull request #100 synchronize by PeterSH6
January 13, 2025 07:55 15m 13s gm/unpad
January 13, 2025 07:55 15m 13s
[misc] fix reward model issue with TokenClassification model and supp…
model_rmpad #20: Commit a0e8ed2 pushed by vermouth1992
January 13, 2025 07:49 14m 49s main
January 13, 2025 07:49 14m 49s
[misc] feat: support different flash_attn versions with variable num returns
model_rmpad #17: Pull request #100 opened by PeterSH6
January 12, 2025 16:05 9m 6s gm/unpad
January 12, 2025 16:05 9m 6s
[misc] feat: spport rmpad/data-packing in FSDP with transformers (#91)
model_rmpad #15: Commit 569210e pushed by vermouth1992
January 11, 2025 08:50 49s main
January 11, 2025 08:50 49s
[misc] feat: spport rmpad/data-packing in FSDP with transformers
model_rmpad #14: Pull request #91 synchronize by PeterSH6
January 11, 2025 08:12 5m 27s PeterSH6:gm/rmpad
January 11, 2025 08:12 5m 27s
[misc] feat: spport rmpad/data-packing in FSDP with transformers
model_rmpad #13: Pull request #91 synchronize by PeterSH6
January 11, 2025 07:50 5m 27s PeterSH6:gm/rmpad
January 11, 2025 07:50 5m 27s
[misc] feat: spport rmpad/data-packing in FSDP with transformers
model_rmpad #12: Pull request #91 synchronize by PeterSH6
January 11, 2025 07:33 1m 14s PeterSH6:gm/rmpad
January 11, 2025 07:33 1m 14s