Skip to content

Actions: huggingface/trl

Build documentation

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
665 workflow runs
665 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Fix _process_tokens for empty prompts in KTOTrainer (#2093)
Build documentation #836: Commit 44d998b pushed by kashif
September 21, 2024 10:49 3m 26s main
September 21, 2024 10:49 3m 26s
fix: device could be in meta, transformers#33154 (#2089)
Build documentation #835: Commit 9b80f3d pushed by kashif
September 21, 2024 07:11 3m 18s main
September 21, 2024 07:11 3m 18s
Fix typo in orpo example. (#2092)
Build documentation #834: Commit 2038e52 pushed by kashif
September 21, 2024 07:11 3m 34s main
September 21, 2024 07:11 3m 34s
training_args for all TrainingArguments (#2082)
Build documentation #833: Commit 10c2f63 pushed by qgallouedec
September 19, 2024 13:03 3m 53s main
September 19, 2024 13:03 3m 53s
[SFT] fix neftune_noise_alpha in SFTTrainer (#1841)
Build documentation #832: Commit 9fb871f pushed by kashif
September 19, 2024 09:57 3m 10s main
September 19, 2024 09:57 3m 10s
Bump dev version
Build documentation #831: Commit 3cec013 pushed by lewtun
September 19, 2024 08:47 3m 29s main
September 19, 2024 08:47 3m 29s
Release v0.11.0
Build documentation #830: Commit e4935e1 pushed by lewtun
September 19, 2024 07:50 3m 16s v0.11-release
September 19, 2024 07:50 3m 16s
Fix DeepSpeed for PPOv2Trainer.save (#2080)
Build documentation #829: Commit cc80ac6 pushed by lewtun
September 19, 2024 07:46 3m 23s v0.11-release
September 19, 2024 07:46 3m 23s
Fix DeepSpeed for PPOv2Trainer.save (#2080)
Build documentation #828: Commit cc80ac6 pushed by qgallouedec
September 19, 2024 07:30 3m 26s main
September 19, 2024 07:30 3m 26s
Standardize dataset naming (#2081)
Build documentation #827: Commit 4c0c98d pushed by qgallouedec
September 19, 2024 06:59 3m 33s main
September 19, 2024 06:59 3m 33s
[WIP] Fix logits/chosen and logits/rejected metrics in `KTOTraine…
Build documentation #826: Commit 0d2bee5 pushed by qgallouedec
September 18, 2024 19:09 4m 35s main
September 18, 2024 19:09 4m 35s
Conversational dataset support for Online DPO (#2075)
Build documentation #825: Commit 6920c2d pushed by qgallouedec
September 18, 2024 12:10 3m 23s main
September 18, 2024 12:10 3m 23s
Use wrapped model for reference completions in WinRateCallback and …
Build documentation #824: Commit 4d82676 pushed by lewtun
September 18, 2024 11:55 3m 24s main
September 18, 2024 11:55 3m 24s
processor(prompt, images=image) to `processor(images=image, text=pr…
Build documentation #823: Commit c314383 pushed by qgallouedec
September 17, 2024 10:09 3m 32s main
September 17, 2024 10:09 3m 32s
Added error when ref_model and model have same id (#2057)
Build documentation #822: Commit e74dbf2 pushed by qgallouedec
September 17, 2024 08:48 2m 50s main
September 17, 2024 08:48 2m 50s
Minor doc fixes and comments (#2073)
Build documentation #821: Commit 41fe228 pushed by qgallouedec
September 16, 2024 14:42 3m 42s main
September 16, 2024 14:42 3m 42s
Use transformers utilities when possible (#2064)
Build documentation #820: Commit 07f0e68 pushed by qgallouedec
September 16, 2024 13:56 3m 55s main
September 16, 2024 13:56 3m 55s
Nash md (#1853)
Build documentation #819: Commit dc2bd07 pushed by kashif
September 16, 2024 11:46 8m 57s main
September 16, 2024 11:46 8m 57s
[KTO] Overrides default learning_rate in KTOConfig (#2070)
Build documentation #818: Commit cdafc93 pushed by qgallouedec
September 16, 2024 10:24 8m 49s main
September 16, 2024 10:24 8m 49s
Standardizing datasets for testing (#2065)
Build documentation #817: Commit 40f0522 pushed by qgallouedec
September 14, 2024 20:34 3m 32s main
September 14, 2024 20:34 3m 32s
remove min_new_tokens=args.max_new_tokens (#2069)
Build documentation #816: Commit f6c6643 pushed by kashif
September 14, 2024 17:37 3m 40s main
September 14, 2024 17:37 3m 40s
Fix dataset in GKD script (#2067)
Build documentation #815: Commit 08ba866 pushed by kashif
September 14, 2024 10:29 3m 14s main
September 14, 2024 10:29 3m 14s
PEFT support for Online DPO (#2041)
Build documentation #814: Commit ebc85b2 pushed by qgallouedec
September 13, 2024 17:15 3m 54s main
September 13, 2024 17:15 3m 54s
Standardise API for WinRateCallback and LogCompletionsCallback (#…
Build documentation #813: Commit 88bede6 pushed by lewtun
September 13, 2024 15:38 4m 12s main
September 13, 2024 15:38 4m 12s
Shuffle examples before they are packed (#2037)
Build documentation #812: Commit 7a2bbe3 pushed by lewtun
September 13, 2024 12:23 3m 43s main
September 13, 2024 12:23 3m 43s