Skip to content

Actions: huggingface/trl

Build PR Documentation

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
265 workflow run results
265 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Update utils.py
Build PR Documentation #1793: Pull request #1012 synchronize by ZihanWang314
November 28, 2023 18:36 3m 34s ZihanWang314:patch-1
November 28, 2023 18:36 3m 34s
Fixes reward and text gathering in distributed training
Build PR Documentation #1792: Pull request #850 synchronize by vwxyzjn
November 27, 2023 15:26 3m 33s fix-reward-gather
November 27, 2023 15:26 3m 33s
Fixes reward and text gathering in distributed training
Build PR Documentation #1791: Pull request #850 synchronize by vwxyzjn
November 27, 2023 15:17 3m 5s fix-reward-gather
November 27, 2023 15:17 3m 5s
Fixes reward and text gathering in distributed training
Build PR Documentation #1790: Pull request #850 synchronize by vwxyzjn
November 27, 2023 14:55 3m 40s fix-reward-gather
November 27, 2023 14:55 3m 40s
[DPO] cDPO loss
Build PR Documentation #1789: Pull request #1035 synchronize by kashif
November 26, 2023 10:27 3m 38s kashif:cDPO
November 26, 2023 10:27 3m 38s
[DPO] cDPO loss
Build PR Documentation #1788: Pull request #1035 opened by kashif
November 26, 2023 10:26 55s kashif:cDPO
November 26, 2023 10:26 55s
[SFT Trainer] precompute packed iterable into a dataset
Build PR Documentation #1787: Pull request #979 synchronize by lvwerra
November 24, 2023 17:05 3m 34s precompute-packing
November 24, 2023 17:05 3m 34s
[SFT Trainer] precompute packed iterable into a dataset
Build PR Documentation #1786: Pull request #979 synchronize by lvwerra
November 24, 2023 16:16 3m 34s precompute-packing
November 24, 2023 16:16 3m 34s
[DPO] use ref model logprobs if it exists in the data
Build PR Documentation #1785: Pull request #885 synchronize by kashif
November 24, 2023 15:36 3m 45s kashif:reference-logprobs
November 24, 2023 15:36 3m 45s
[DPO] use ref model logprobs if it exists in the data
Build PR Documentation #1784: Pull request #885 synchronize by kashif
November 24, 2023 15:00 3m 27s kashif:reference-logprobs
November 24, 2023 15:00 3m 27s
[DPO] IPO Training loss
Build PR Documentation #1782: Pull request #1022 synchronize by kashif
November 23, 2023 11:43 3m 30s kashif:ipo
November 23, 2023 11:43 3m 30s
[DPO] IPO Training loss
Build PR Documentation #1781: Pull request #1022 synchronize by kashif
November 23, 2023 11:40 2m 45s kashif:ipo
November 23, 2023 11:40 2m 45s
[DPO] IPO Training loss
Build PR Documentation #1780: Pull request #1022 synchronize by kashif
November 23, 2023 11:30 3m 21s kashif:ipo
November 23, 2023 11:30 3m 21s
[Document] Minor fixes of sft_trainer document
Build PR Documentation #1779: Pull request #1029 opened by mutichung
November 23, 2023 11:28 3m 18s clarify_sfttrainer_doc
November 23, 2023 11:28 3m 18s
[DPO] IPO Training loss
Build PR Documentation #1775: Pull request #1022 synchronize by kashif
November 22, 2023 15:15 3m 35s kashif:ipo
November 22, 2023 15:15 3m 35s
[DPO] IPO Training loss
Build PR Documentation #1774: Pull request #1022 synchronize by kashif
November 22, 2023 15:13 2m 21s kashif:ipo
November 22, 2023 15:13 2m 21s
[DPO] IPO Training loss
Build PR Documentation #1773: Pull request #1022 synchronize by kashif
November 22, 2023 14:07 3m 27s kashif:ipo
November 22, 2023 14:07 3m 27s
[DPO] IPO Training loss
Build PR Documentation #1772: Pull request #1022 synchronize by kashif
November 22, 2023 13:25 3m 22s kashif:ipo
November 22, 2023 13:25 3m 22s
[DPO] IPO Training loss
Build PR Documentation #1771: Pull request #1022 opened by kashif
November 22, 2023 13:12 3m 27s kashif:ipo
November 22, 2023 13:12 3m 27s
Fixes reward and text gathering in distributed training
Build PR Documentation #1770: Pull request #850 synchronize by vwxyzjn
November 22, 2023 04:57 3m 43s fix-reward-gather
November 22, 2023 04:57 3m 43s
Fixes reward and text gathering in distributed training
Build PR Documentation #1769: Pull request #850 synchronize by vwxyzjn
November 22, 2023 04:56 1m 3s fix-reward-gather
November 22, 2023 04:56 1m 3s