Skip to content

Actions: huggingface/trl

Build documentation

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
67 workflow run results
67 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

fix gradient checkpointing when using PEFT (#1118)
Build documentation #413: Commit 830cadf pushed by younesbelkada
December 20, 2023 12:35 3m 34s main
December 20, 2023 12:35 3m 34s
Make prepending of bos token configurable. (#1114)
Build documentation #412: Commit f2acd82 pushed by younesbelkada
December 20, 2023 10:28 3m 20s main
December 20, 2023 10:28 3m 20s
peft_module_casting_to_bf16 util method, append_concat_token flag…
Build documentation #411: Commit f100ca3 pushed by younesbelkada
December 19, 2023 16:43 3m 45s main
December 19, 2023 16:43 3m 45s
[Feature] Add Ascend NPU accelerator support (#1096)
Build documentation #410: Commit d708ec2 pushed by younesbelkada
December 15, 2023 14:34 3m 20s main
December 15, 2023 14:34 3m 20s
Updated documentation for docs/source/reward_trainer.mdx to import th…
Build documentation #409: Commit 8140129 pushed by younesbelkada
December 15, 2023 10:24 3m 21s main
December 15, 2023 10:24 3m 21s
[DPO] use ref model logprobs if it exists in the data (#885)
Build documentation #408: Commit 48b3ef0 pushed by kashif
December 12, 2023 16:16 3m 27s main
December 12, 2023 16:16 3m 27s
consistency on log (#1084)
Build documentation #407: Commit c0ce52a pushed by younesbelkada
December 12, 2023 09:58 3m 35s main
December 12, 2023 09:58 3m 35s
Removing tyro in sft_llama2.py (#1081)
Build documentation #406: Commit 393dbf6 pushed by vwxyzjn
December 11, 2023 17:28 5m 11s main
December 11, 2023 17:28 5m 11s
Make CI happy (#1080)
Build documentation #405: Commit 94fa4b0 pushed by younesbelkada
December 11, 2023 15:52 3m 46s main
December 11, 2023 15:52 3m 46s
add local folder support as input for rl_training. (#1078)
Build documentation #404: Commit cb7819e pushed by younesbelkada
December 11, 2023 15:37 3m 37s main
December 11, 2023 15:37 3m 37s
Add args to SFT example (#1079)
Build documentation #403: Commit 8f0fc4c pushed by younesbelkada
December 11, 2023 15:16 3m 34s main
December 11, 2023 15:16 3m 34s
[DPO] add KTO loss (#1075)
Build documentation #402: Commit d275cb4 pushed by kashif
December 11, 2023 10:41 3m 37s main
December 11, 2023 10:41 3m 37s
Add missing loss_type in ValueError message (#1067)
Build documentation #401: Commit 7d0a8ee pushed by younesbelkada
December 7, 2023 07:40 3m 26s main
December 7, 2023 07:40 3m 26s
enable multiple eval datasets (#1052)
Build documentation #400: Commit 5a23354 pushed by younesbelkada
December 6, 2023 19:26 3m 32s main
December 6, 2023 19:26 3m 32s
[SFTTrainer] Fix Trainer when args is None (#1064)
Build documentation #399: Commit 9fb00cf pushed by younesbelkada
December 6, 2023 18:02 3m 41s main
December 6, 2023 18:02 3m 41s
[core] Fix failing tests on main (#1065)
Build documentation #398: Commit ee44946 pushed by younesbelkada
December 6, 2023 17:31 3m 35s main
December 6, 2023 17:31 3m 35s
update doc for the computer_metrics argument of SFTTrainer (#1062)
Build documentation #397: Commit 7f2401b pushed by younesbelkada
December 6, 2023 16:46 3m 29s main
December 6, 2023 16:46 3m 29s
Improve PreTrainedModelWrapper._get_current_device (#1048)
Build documentation #396: Commit 23bf9d4 pushed by lvwerra
December 5, 2023 16:47 3m 47s main
December 5, 2023 16:47 3m 47s
Update doc CI (#1060)
Build documentation #395: Commit 501c347 pushed by younesbelkada
December 5, 2023 12:31 3m 28s main
December 5, 2023 12:31 3m 28s
[SFT Trainer] precompute packed iterable into a dataset (#979)
Build documentation #394: Commit f06f357 pushed by younesbelkada
December 4, 2023 12:13 3m 29s main
December 4, 2023 12:13 3m 29s
Fixing accelerator version function call. (#1056)
Build documentation #393: Commit 4cdc03a pushed by younesbelkada
December 4, 2023 11:40 3m 27s main
December 4, 2023 11:40 3m 27s
Update dpo_trainer.py (#1049)
Build documentation #392: Commit a60ceef pushed by lvwerra
December 1, 2023 16:03 3m 37s main
December 1, 2023 16:03 3m 37s
Revert "[DPO] Refactor eval logging of dpo trainer (#954)" (#1047)
Build documentation #391: Commit baa8f09 pushed by lvwerra
December 1, 2023 09:33 3m 40s main
December 1, 2023 09:33 3m 40s
remove spurious optimize_cuda_cache deprecation warning on init (#1045)
Build documentation #390: Commit c859f5f pushed by lvwerra
December 1, 2023 09:26 3m 39s main
December 1, 2023 09:26 3m 39s
Fixes reward and text gathering in distributed training (#850)
Build documentation #389: Commit 481ef96 pushed by vwxyzjn
November 30, 2023 15:32 3m 37s main
November 30, 2023 15:32 3m 37s