Skip to content

Actions: volcengine/verl

Actions

e2e_gsm8k

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
e2e_gsm8k.yml
217 workflow runs
217 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[misc][Long Context] feat: support ulysses for long context training e2e_gsm8k #17: Pull request #109 synchronize by PeterSH6
January 17, 2025 05:32 25m 3s PeterSH6:gm/uly
PeterSH6:gm/uly
January 17, 2025 05:32 25m 3s
[misc][Long Context] feat: support ulysses for long context training e2e_gsm8k #16: Pull request #109 synchronize by PeterSH6
January 17, 2025 05:27 14m 14s PeterSH6:gm/uly
PeterSH6:gm/uly
January 17, 2025 05:27 14m 14s
[misc] fix: fix license (#110) e2e_gsm8k #15: Commit a33a3ba pushed by PeterSH6
January 16, 2025 16:03 15m 35s main
main
January 16, 2025 16:03 15m 35s
[misc] fix: fix license e2e_gsm8k #14: Pull request #110 opened by vermouth1992
January 16, 2025 14:22 14m 31s chi/fix/license
chi/fix/license
January 16, 2025 14:22 14m 31s
[misc][Long Context] feat: support ulysses for long context training e2e_gsm8k #13: Pull request #109 synchronize by PeterSH6
January 16, 2025 13:34 15m 42s PeterSH6:gm/uly
PeterSH6:gm/uly
January 16, 2025 13:34 15m 42s
[misc][Long Context] feat: support ulysses for long context training e2e_gsm8k #12: Pull request #109 opened by PeterSH6
January 16, 2025 13:21 5m 28s PeterSH6:gm/uly
PeterSH6:gm/uly
January 16, 2025 13:21 5m 28s
refact: hybrid_engine dir to sharding_manager for more general repres… e2e_gsm8k #11: Commit 6a9f6e1 pushed by vermouth1992
January 14, 2025 08:19 14m 11s main
main
January 14, 2025 08:19 14m 11s
[BREAKING][refactor] feat: hybrid_engine dir to sharding_manager for more general repres… e2e_gsm8k #10: Pull request #103 opened by PeterSH6
January 14, 2025 07:55 14m 6s gm/sharding_refact
gm/sharding_refact
January 14, 2025 07:55 14m 6s
Fix loss value for gradient accumulation > 1 (#102) e2e_gsm8k #9: Commit e230de8 pushed by vermouth1992
January 14, 2025 01:51 15m 6s main
main
January 14, 2025 01:51 15m 6s
Fix the displayed loss in the sft trainer for gradient accumulation > 1 e2e_gsm8k #8: Pull request #102 opened by hiyouga
January 13, 2025 18:25 14m 5s hiyouga:patch-1
hiyouga:patch-1
January 13, 2025 18:25 14m 5s
[misc] feat: support different flash_attn versions with variable num … e2e_gsm8k #7: Commit 1facb9d pushed by PeterSH6
January 13, 2025 08:38 14m 51s main
main
January 13, 2025 08:38 14m 51s
[misc] feat: support different flash_attn versions with variable num returns e2e_gsm8k #6: Pull request #100 synchronize by PeterSH6
January 13, 2025 07:55 29m 14s gm/unpad
gm/unpad
January 13, 2025 07:55 29m 14s
[misc] fix reward model issue with TokenClassification model and supp… e2e_gsm8k #5: Commit a0e8ed2 pushed by vermouth1992
January 13, 2025 07:49 14m 5s main
main
January 13, 2025 07:49 14m 5s
[misc] fix reward model issue with TokenClassification model and support running particular steps instead of epochs e2e_gsm8k #4: Pull request #99 synchronize by PeterSH6
January 13, 2025 07:13 28m 49s PeterSH6:gm/ci_function
PeterSH6:gm/ci_function
January 13, 2025 07:13 28m 49s
[misc] fix reward model issue with TokenClassification model and support running particular steps instead of epochs e2e_gsm8k #3: Pull request #99 synchronize by PeterSH6
January 13, 2025 03:55 3h 19m 45s PeterSH6:gm/ci_function
PeterSH6:gm/ci_function
January 13, 2025 03:55 3h 19m 45s
[misc] feat: support different flash_attn versions with variable num returns e2e_gsm8k #2: Pull request #100 opened by PeterSH6
January 12, 2025 16:05 8m 16s gm/unpad
gm/unpad
January 12, 2025 16:05 8m 16s
[misc] fix reward model issue with TokenClassification model and support running particular steps instead of epochs e2e_gsm8k #1: Pull request #99 opened by PeterSH6
January 12, 2025 14:54 15m 11s PeterSH6:gm/ci_function
PeterSH6:gm/ci_function
January 12, 2025 14:54 15m 11s