Skip to content

Actions: huggingface/trl

Actions

Build documentation

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
build_documentation.yml
1,191 workflow runs
1,191 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Add test for training with compute_metrics in RewardTrainer (#4958) Build documentation #2190: Commit e4995b2 pushed by qgallouedec
2m 4s main
main
2m 4s
Add test for tool call data in RewardTrainer (#4959) Build documentation #2189: Commit cb5a73b pushed by qgallouedec
2m 4s main
main
2m 4s
NeMo-Gym Integration (#4848) Build documentation #2188: Commit 90b875c pushed by sergiopaniego
3m 0s main
main
3m 0s
Release: 0.27.2 Build documentation #2187: Commit 1101f8f pushed by qgallouedec
2m 26s v0.27-release
v0.27-release
2m 26s
Remove access to warnings_issued (#4960) Build documentation #2186: Commit 5cb7eee pushed by qgallouedec
2m 21s main
main
2m 21s
Add test for training with compute_metrics in SFTTrainer (#4950) Build documentation #2185: Commit 2a55ed7 pushed by qgallouedec
2m 25s main
main
2m 25s
Minor fix docs style (#4953) Build documentation #2184: Commit 7b54e72 pushed by albertvillanova
2m 28s main
main
2m 28s
Fix PPO run_name parameter not taking effect (#4945) Build documentation #2183: Commit 2a9fb3f pushed by albertvillanova
2m 19s main
main
2m 19s
Update wordle.py example with masking of env tokens (#4895) Build documentation #2182: Commit a03c2fc pushed by sergiopaniego
4m 25s main
main
4m 25s
Remove ref_model_init_kwargs from experimental BCO (#4946) Build documentation #2181: Commit 68bc377 pushed by albertvillanova
2m 27s main
main
2m 27s
Fix SFTTrainer init logic: remove TrainingArguments.push_to_hub_token… Build documentation #2180: Commit 239c74d pushed by albertvillanova
2m 44s main
main
2m 44s
[GRPO] Add parquet logging for completions with individual rewards (#… Build documentation #2179: Commit 035c3ff pushed by qgallouedec
2m 35s main
main
2m 35s
Set default top_k to 0 in VLLMClient (#4927) Build documentation #2178: Commit 414e60f pushed by albertvillanova
2m 26s main
main
2m 26s
Fix import statement for import_utils in vllm_client.py (#4932) Build documentation #2177: Commit df332dc pushed by qgallouedec
1m 57s main
main
1m 57s
Fix profiling of VLLMGeneration.sync_weights (#4931) Build documentation #2176: Commit 27998e9 pushed by albertvillanova
1m 5s main
main
1m 5s
Set model dtype to float32 in experimental tests of trainers (#4925) Build documentation #2175: Commit 43fb8d3 pushed by albertvillanova
1m 8s main
main
1m 8s
Move VLLMClient to generation module (#4928) Build documentation #2174: Commit 5a7481e pushed by albertvillanova
1m 8s main
main
1m 8s
Require transformers<5 with PairRMJudge (#4926) Build documentation #2173: Commit 21a0d70 pushed by albertvillanova
2m 3s main
main
2m 3s
Set model dtype to float32 in tests of trainers (#4924) Build documentation #2172: Commit 4348375 pushed by albertvillanova
1m 56s main
main
1m 56s
Support tool call data in is_conversational (#4923) Build documentation #2171: Commit a6cbf27 pushed by qgallouedec
1m 58s main
main
1m 58s
Add validation for sync_ref_model in GRPOTrainer and `RLOOTrainer… Build documentation #2170: Commit ad91c6f pushed by qgallouedec
2m 2s main
main
2m 2s
Update learning rate comments and add assertions for reference model … Build documentation #2169: Commit 04717ff pushed by qgallouedec
2m 2s main
main
2m 2s
Remove chat template setup in dpo_vlm.py (#4906) Build documentation #2168: Commit b322d9b pushed by qgallouedec
2m 12s main
main
2m 12s
Fix extra EOS appended in DPO preprocessing for conversational data (… Build documentation #2167: Commit a70b4e0 pushed by qgallouedec
4m 26s main
main
4m 26s
Fix CI ValueError for 0 temperature (#4916) Build documentation #2166: Commit 8464b0e pushed by albertvillanova
2m 4s main
main
2m 4s