Skip to content

Actions: huggingface/trl

Secret Leaks

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
2,046 workflow runs
2,046 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Note on future release
Secret Leaks #2046: Commit 28af8af pushed by qgallouedec
January 16, 2025 17:26 17s vllm-onlinedpo
January 16, 2025 17:26 17s
fix grad computation
Secret Leaks #2045: Commit 071c19a pushed by qgallouedec
January 16, 2025 16:12 18s grpo
January 16, 2025 16:12 18s
fix token_level_kl
Secret Leaks #2044: Commit 475a157 pushed by kashif
January 16, 2025 14:04 18s fix-token-kl
January 16, 2025 14:04 18s
Update vllm dependency to exclude Windows platform
Secret Leaks #2043: Commit 4cc94d6 pushed by qgallouedec
January 16, 2025 09:49 40s vllm-onlinedpo
January 16, 2025 09:49 40s
no, an id
Secret Leaks #2042: Commit ed2fd05 pushed by qgallouedec
January 15, 2025 19:07 15s vllm-onlinedpo
January 15, 2025 19:07 15s
Add hfoption sections to speeding_up_training.md
Secret Leaks #2041: Commit aeed6c5 pushed by qgallouedec
January 15, 2025 19:02 17s vllm-onlinedpo
January 15, 2025 19:02 17s
January 15, 2025 18:56 20s
Merge branch 'main' into vllm-onlinedpo
Secret Leaks #2039: Commit ac5e31f pushed by qgallouedec
January 15, 2025 18:45 20s vllm-onlinedpo
January 15, 2025 18:45 20s
proper require_torch_accelerator
Secret Leaks #2038: Commit b39f54a pushed by qgallouedec
January 15, 2025 18:37 18s vllm-onlinedpo
January 15, 2025 18:37 18s
log reward std
Secret Leaks #2037: Commit c597c62 pushed by qgallouedec
January 15, 2025 17:37 16s grpo
January 15, 2025 17:37 16s
support any reward model
Secret Leaks #2036: Commit defa22d pushed by qgallouedec
January 15, 2025 16:59 17s grpo
January 15, 2025 16:59 17s
fix peft training
Secret Leaks #2035: Commit cc2b7b9 pushed by kashif
January 15, 2025 14:22 19s liger-dpo
January 15, 2025 14:22 19s
fix comment
Secret Leaks #2034: Commit 8ae06b1 pushed by kashif
January 15, 2025 11:19 21s liger-dpo
January 15, 2025 11:19 21s
Merge branch 'main' into liger-dpo
Secret Leaks #2033: Commit 50d341e pushed by kashif
January 15, 2025 11:11 21s liger-dpo
January 15, 2025 11:11 21s
fix config merge conflict
Secret Leaks #2032: Commit 2d82b39 pushed by kashif
January 15, 2025 11:10 20s liger-dpo
January 15, 2025 11:10 20s
fix outputs
Secret Leaks #2031: Commit e3eebd3 pushed by kashif
January 15, 2025 11:05 18s liger-dpo
January 15, 2025 11:05 18s
fix reward calculation
Secret Leaks #2030: Commit 106d271 pushed by qgallouedec
January 14, 2025 22:19 17s grpo
January 14, 2025 22:19 17s
test peft
Secret Leaks #2029: Commit 7223a21 pushed by qgallouedec
January 14, 2025 18:04 19s grpo
January 14, 2025 18:04 19s
initial liger support
Secret Leaks #2028: Commit f50e74d pushed by kashif
January 14, 2025 13:09 21s liger-dpo
January 14, 2025 13:09 21s
proper reward model for testing
Secret Leaks #2027: Commit 7a5cb32 pushed by qgallouedec
January 14, 2025 12:05 20s grpo
January 14, 2025 12:05 20s
allow model to be str and processing_class to be none; fix loss compu…
Secret Leaks #2026: Commit ab29a79 pushed by qgallouedec
January 14, 2025 10:51 21s grpo
January 14, 2025 10:51 21s
revert grpo config doc trial (didn't work)
Secret Leaks #2025: Commit 3ccf20a pushed by qgallouedec
January 14, 2025 10:49 18s grpo
January 14, 2025 10:49 18s
Compat with distrib training
Secret Leaks #2024: Commit 14ac49f pushed by qgallouedec
January 14, 2025 08:29 16s grpo
January 14, 2025 08:29 16s
unwrap_model_for_generation for distributed setting
Secret Leaks #2023: Commit af704ce pushed by qgallouedec
January 13, 2025 18:02 18s grpo
January 13, 2025 18:02 18s
weird doc trial
Secret Leaks #2022: Commit 5f1f8c1 pushed by qgallouedec
January 13, 2025 17:38 15s grpo
January 13, 2025 17:38 15s