build(deps): Update trl requirement from <0.20.0,>=0.19.1 to >=0.19.1,<0.24.0

[dependabot]

Updates the requirements on trl to permit the latest version.

Release notes

Sourced from trl's releases.

v0.23.0

Major

🥓 Context Parallelism

SFT now supports Context Parallelism (CP) for training large language models on very large sequences. You can now train with an arbitrarily long sequence length.

by @​kashif in huggingface/trl#3994

🧨 Dynamic Fine-Tuning

Dynamic Fine-Tuning (DFT) is a nnow supported in TRL.

from trl import SFTConfig
training_args = SFTConfig(
loss_type="dft",
...
)

by @​qgallouedec in huggingface/trl#4042

🪵 Truncated Importance Sampling (TIS) to address rollout-training mismatch

Different implementations are used for rollout generation (vLLM) and model training. The implementation gap implicitly turns the on-policy RL to be off-policy. Truncated Importance Sampling (TIS) a simple yet effective importance sampling technique for handling such discrepancy. This is now implemented in GRPO.

from trl import GRPOConfig
training_args = GRPOConfig(
...
use_vllm=True,
vllm_importance_sampling_correction=True, # default True
vllm_importance_sampling_cap=2.0, # hyper-parameter C
)

by @​LeonEricsson in huggingface/trl#3867

🥣 [SFTTrainer]: Add Aux Loss for MoE models

Mixture of Experts (MoE) models require an auxiliary loss to ensure that the different experts are used evenly. This auxiliary loss is now supported in SFTTrainer.

... (truncated)

Commits

• 6adfd13 Release: 0.23 (#4053)
• a647e5a 🗜 Hotfix: avoid passing quantization_config=None (#4019)
• 816ac61 🪪 Update SFTTrainer to handle labels correctly and add configuration example ...
• 373a64a 💬 Remove setting chat template in sft script (#4037)
• 09e1924 ✨ Improve SFT doc (#4005)
• a228cb5 Add autodoc for BestOfNSampler and improve docstrings (#4034)
• 6c6f13b 🏂 Fix label shifting logic in SFTTrainer for compatibility with CP (#4038)
• b3f9f61 Update VLM arch check to AutoModelForImageTextToText for DPO and Online DPO...
• 659d2c1 🧨 DFT (#4042)
• 82b34e5 Update transformers minimum version to 4.56.1 (#4047)
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot merge will merge this PR after your CI passes on it
• @dependabot squash and merge will squash and merge this PR after your CI passes on it
• @dependabot cancel merge will cancel a previously requested merge and block automerging
• @dependabot reopen will reopen this PR if it is closed
• @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

[github-actions]

Thanks for making a pull request! 😃
One of the maintainers will review and advise on the next steps.

[dependabot]

Superseded by #619.