Skip to content

Actions: huggingface/trl

Build documentation

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
781 workflow runs
781 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

🎀 New default: beta=0.0 for GRPO (#3516)
Build documentation #1365: Commit 7359ddc pushed by qgallouedec
May 30, 2025 16:51 3m 18s main
May 30, 2025 16:51 3m 18s
🧭 Patch release guide (#3512)
Build documentation #1364: Commit 0844936 pushed by qgallouedec
May 30, 2025 16:50 3m 24s main
May 30, 2025 16:50 3m 24s
Release: 0.18.1
Build documentation #1363: Commit 2c49300 pushed by qgallouedec
May 29, 2025 19:02 3m 31s v0.18-release
May 29, 2025 19:02 3m 31s
📚 Fix doc building by removing vLLM from dev dependencies in `setup.c…
Build documentation #1362: Commit e530486 pushed by qgallouedec
May 29, 2025 18:50 3m 32s v0.18-release
May 29, 2025 18:50 3m 32s
📚 Fix doc building by removing vLLM from dev dependencies in `setup.c…
Build documentation #1361: Commit 897c87f pushed by qgallouedec
May 29, 2025 18:39 3m 15s main
May 29, 2025 18:39 3m 15s
📎 Fix clip ratio logging (#3506)
Build documentation #1360: Commit c13de6f pushed by qgallouedec
May 28, 2025 15:46 3m 39s main
May 28, 2025 15:46 3m 39s
⬆️ Bump dev version (#3505)
Build documentation #1359: Commit 722847a pushed by qgallouedec
May 28, 2025 02:04 3m 35s main
May 28, 2025 02:04 3m 35s
Release: v0.18 (#3504)
Build documentation #1358: Commit ef4b0b2 pushed by qgallouedec
May 28, 2025 01:46 3m 32s v0.18-release
May 28, 2025 01:46 3m 32s
Release: v0.18 (#3504)
Build documentation #1357: Commit ef4b0b2 pushed by qgallouedec
May 28, 2025 01:44 3m 42s main
May 28, 2025 01:44 3m 42s
✂️ [DPO] Fix truncation keep_end leading to zero'd out samples (#3398)
Build documentation #1356: Commit 8e8e62b pushed by qgallouedec
May 27, 2025 23:36 3m 52s main
May 27, 2025 23:36 3m 52s
🏰 [vllm] Support base_url parameter for vLLM client initialization …
Build documentation #1355: Commit 824100c pushed by qgallouedec
May 27, 2025 23:05 3m 46s main
May 27, 2025 23:05 3m 46s
🤧 LD-DPO support (#3458)
Build documentation #1354: Commit 4e7f0a5 pushed by qgallouedec
May 27, 2025 23:05 3m 33s main
May 27, 2025 23:05 3m 33s
📏 Completion length logging fix + remainder logging fix (#3482)
Build documentation #1353: Commit 17a9069 pushed by qgallouedec
May 27, 2025 21:31 3m 47s main
May 27, 2025 21:31 3m 47s
Forgotten commit from #3502
Build documentation #1352: Commit cb07c44 pushed by qgallouedec
May 27, 2025 20:02 3m 50s main
May 27, 2025 20:02 3m 50s
🔭 [GRPO] Log advantages and fraction of samples with an std of zero (…
Build documentation #1351: Commit 0b6a187 pushed by qgallouedec
May 27, 2025 19:58 3m 38s main
May 27, 2025 19:58 3m 38s
🐌 Clean two-sided clipping (#3499)
Build documentation #1350: Commit ac18c9d pushed by qgallouedec
May 27, 2025 16:39 3m 43s main
May 27, 2025 16:39 3m 43s
🛠️ Initialize reward_kwargs to prevent UnboundLocalError in GRPOTrain…
Build documentation #1349: Commit d1174ad pushed by qgallouedec
May 27, 2025 01:28 3m 44s main
May 27, 2025 01:28 3m 44s
👇 Update grpo.py to fix bugs for cli grpo --reward_funcs my_lib.my_re…
Build documentation #1348: Commit cd83841 pushed by qgallouedec
May 27, 2025 01:00 3m 37s main
May 27, 2025 01:00 3m 37s
[GKD] fix the gkd script (#3497)
Build documentation #1347: Commit c7e3f09 pushed by kashif
May 26, 2025 18:22 3m 34s main
May 26, 2025 18:22 3m 34s
[GRPO] disabling top_k sampling default (#3494)
Build documentation #1346: Commit 5c08897 pushed by kashif
May 26, 2025 09:32 3m 46s main
May 26, 2025 09:32 3m 46s
[Docs] sync logging doc to current metrics (#3478)
Build documentation #1345: Commit 3ef9faf pushed by kashif
May 25, 2025 15:46 3m 31s main
May 25, 2025 15:46 3m 31s
Fix mis-aligned prompts and completions in colocate mode (#3491)
Build documentation #1344: Commit 9ac614f pushed by qgallouedec
May 24, 2025 22:50 3m 34s main
May 24, 2025 22:50 3m 34s
[Doc][SFT] Update sft_trainer.md. link prompt-completion dataset exam…
Build documentation #1343: Commit 29401e7 pushed by kashif
May 24, 2025 17:13 3m 35s main
May 24, 2025 17:13 3m 35s
Fix typo (#3489)
Build documentation #1342: Commit 31bf3f9 pushed by kashif
May 24, 2025 11:24 3m 44s main
May 24, 2025 11:24 3m 44s
[CI] fix sampler api to make the CI green (#3488)
Build documentation #1341: Commit 7f32792 pushed by kashif
May 23, 2025 15:32 4m 1s main
May 23, 2025 15:32 4m 1s