chore(deps): upgrade trl (foundation-model-stack#537)

* deps: upgrade trl

Signed-off-by: Will Johnson <mwjohnson728@gmail.com>

* docs: offline data preprocessing note

Signed-off-by: Will Johnson <mwjohnson728@gmail.com>

---------

Signed-off-by: Will Johnson <mwjohnson728@gmail.com>
Co-authored-by: Dushyant Behl <dushyantbehl@users.noreply.github.com>

Author: willmj

docs/offline-data-preprocessing.md

@@ -37,6 +37,8 @@ python scripts/offline_data_processing.py \
 
 Additionally, once the offline data processing is complete, users can leverage the shards stored in `output_dir` for tuning by passing it through the `--training_data_path` flag or passing it via `data_paths` argument in data config yaml, provided they find the sharded datasets beneficial for training.
 
+**NOTE**: The offline data preprocessing script is not compatible with processing image datasets for vision models. 
+
 ## Example Usage
 ### Applying Chat Template
 

pyproject.toml

@@ -34,7 +34,7 @@ dependencies = [
 "sentencepiece>=0.1.99,<0.3",
 "tokenizers>=0.13.3,<1.0",
 "tqdm>=4.66.2,<5.0",
-"trl>=0.13,<0.17",
+"trl>=0.13,<0.18",
 "peft>=0.8.0,<0.14",
 "protobuf>=5.28.0,<6.0.0",
 "datasets>=2.15.0,<4.0",