Skip to content

Actions: huggingface/trl

Tests

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
278 workflow run results
278 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[DPO] use ref model logprobs if it exists in the data
Tests #2075: Pull request #885 synchronize by kashif
November 3, 2023 19:27 10m 12s kashif:reference-logprobs
November 3, 2023 19:27 10m 12s
Re-add summarize example
Tests #2074: Pull request #888 synchronize by vwxyzjn
November 3, 2023 17:50 45s vwxyzjn:summarize-again
November 3, 2023 17:50 45s
[DPO] use ref model logprobs if it exists in the data
Tests #2073: Pull request #885 synchronize by kashif
November 3, 2023 14:39 9m 11s kashif:reference-logprobs
November 3, 2023 14:39 9m 11s
Adds model kwargs to SFT and DPO trainers
Tests #2072: Pull request #951 synchronize by edbeeching
November 3, 2023 13:20 10m 2s model-kwargs-argument
November 3, 2023 13:20 10m 2s
Adds model kwargs to SFT and DPO trainers
Tests #2071: Pull request #951 synchronize by edbeeching
November 3, 2023 12:58 10m 23s model-kwargs-argument
November 3, 2023 12:58 10m 23s
Adds model kwargs to SFT and DPO trainers
Tests #2070: Pull request #951 synchronize by edbeeching
November 3, 2023 12:54 11m 31s model-kwargs-argument
November 3, 2023 12:54 11m 31s
[DPO] use ref model logprobs if it exists in the data
Tests #2069: Pull request #885 synchronize by kashif
November 3, 2023 11:58 11m 0s kashif:reference-logprobs
November 3, 2023 11:58 11m 0s
[DPO] use ref model logprobs if it exists in the data
Tests #2068: Pull request #885 synchronize by kashif
November 3, 2023 11:56 5m 55s kashif:reference-logprobs
November 3, 2023 11:56 5m 55s
[DPO] use ref model logprobs if it exists in the data
Tests #2067: Pull request #885 synchronize by kashif
November 3, 2023 11:42 10m 43s kashif:reference-logprobs
November 3, 2023 11:42 10m 43s
[DPO] use ref model logprobs if it exists in the data
Tests #2066: Pull request #885 synchronize by kashif
November 3, 2023 11:42 11m 56s kashif:reference-logprobs
November 3, 2023 11:42 11m 56s
[DPO] use ref model logprobs if it exists in the data
Tests #2065: Pull request #885 synchronize by kashif
November 3, 2023 11:42 11m 10s kashif:reference-logprobs
November 3, 2023 11:42 11m 10s
Adds model kwargs to SFT and DPO trainers
Tests #2064: Pull request #951 opened by edbeeching
November 3, 2023 11:03 10m 0s model-kwargs-argument
November 3, 2023 11:03 10m 0s
[DPO] use ref model logprobs if it exists in the data
Tests #2063: Pull request #885 synchronize by kashif
November 3, 2023 09:41 11m 39s kashif:reference-logprobs
November 3, 2023 09:41 11m 39s
[CI] Fix CI with new transformers release (#946)
Tests #2061: Commit 951ca18 pushed by younesbelkada
November 3, 2023 09:39 11m 7s main
November 3, 2023 09:39 11m 7s
[DPO] use ref model logprobs if it exists in the data
Tests #2060: Pull request #885 synchronize by kashif
November 3, 2023 09:17 5m 27s kashif:reference-logprobs
November 3, 2023 09:17 5m 27s
Fix unwrapping peft models
Tests #2059: Pull request #948 opened by kkteru
November 2, 2023 21:48 7m 35s kkteru:fix-unwrapping-peft-models
November 2, 2023 21:48 7m 35s
[CI] Fix CI with new transformers release
Tests #2058: Pull request #946 synchronize by younesbelkada
November 2, 2023 19:24 11m 1s fix-ci-new-release
November 2, 2023 19:24 11m 1s
[DPO] use ref model logprobs if it exists in the data
Tests #2057: Pull request #885 synchronize by kashif
November 2, 2023 19:18 7m 58s kashif:reference-logprobs
November 2, 2023 19:18 7m 58s
[CI] Fix CI with new transformers release
Tests #2056: Pull request #946 opened by younesbelkada
November 2, 2023 19:08 5m 46s fix-ci-new-release
November 2, 2023 19:08 5m 46s
Introducing the Iterative Trainer (#737)
Tests #2054: Commit cc1de98 pushed by younesbelkada
November 2, 2023 16:37 11m 50s main
November 2, 2023 16:37 11m 50s
Update dpo_trainer.py (#941)
Tests #2053: Commit a64a522 pushed by younesbelkada
November 2, 2023 10:27 12m 3s main
November 2, 2023 10:27 12m 3s
Upcast log probs in fp32 to avoid NaN reward
Tests #2052: Pull request #942 opened by younesbelkada
November 2, 2023 09:04 12m 4s dpo-upcast-logits-fp32
November 2, 2023 09:04 12m 4s
Introducing the Iterative Trainer
Tests #2051: Pull request #737 synchronize by gaetanlop
November 2, 2023 02:27 11m 43s gaetanlop:iterativetrainer
November 2, 2023 02:27 11m 43s