unpin datasets; update pre-commit (#3316)

* update pre-commit

* unpin datasets

.pre-commit-config.yaml

@@ -2,18 +2,18 @@
 exclude: ^tests/testdata/
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v5.0.0
+    rev: v6.0.0
     hooks:
       - id: check-added-large-files
       - id: check-ast
-      - id: check-byte-order-marker
+      - id: fix-byte-order-marker
       - id: check-case-conflict
       - id: check-json
       - id: check-merge-conflict
-        args: [--assume-in-merge]
+        args: [ --assume-in-merge ]
       - id: check-symlinks
       - id: check-yaml
-        args: ["--unsafe"]
+        args: [ "--unsafe" ]
       - id: destroyed-symlinks
       - id: detect-private-key
       - id: end-of-file-fixer
@@ -21,20 +21,17 @@ repos:
         always_run: false
       - id: requirements-txt-fixer
       - id: trailing-whitespace
-        args: [--markdown-linebreak-ext=md]
+        args: [ --markdown-linebreak-ext=md ]
       - id: fix-byte-order-marker
         exclude: docs/CNAME
-      - id: fix-encoding-pragma
-        args: [--remove]
       - id: mixed-line-ending
-        args: [--fix=lf]
+        args: [ --fix=lf ]
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.12.2
+    rev: v0.13.2
     hooks:
       # Run the linter.
-      - id: ruff
-        args:
-          - --fix
+      - id: ruff-check
+        args: [ --fix ]
       # Run the formatter.
       - id: ruff-format
   - repo: https://github.com/codespell-project/codespell
@@ -47,10 +44,10 @@ repos:
               .*\.json|ignore.txt|lm_eval/tasks/.*|.*yaml|.*\.ipynb
           )$
 
-        args: [--check-filenames, --check-hidden, --ignore-words=ignore.txt]
+        args: [ --check-filenames, --check-hidden, --ignore-words=ignore.txt ]
   - repo: https://github.com/jackdewinter/pymarkdown
-    rev: v0.9.30
+    rev: v0.9.32
     hooks:
       - id: pymarkdown
         exclude: ^(lm_eval/tasks/.*|docs/footguns\.md)$
-        args: [fix, -r]
+        args: [ fix, -r ]

lm_eval/__main__.py

@@ -437,6 +437,10 @@ def cli_evaluate(args: Union[argparse.Namespace, None] = None) -> None:
 
         if vparse(datasets.__version__) < vparse("4.0.0"):
             datasets.config.HF_DATASETS_TRUST_REMOTE_CODE = True
+        else:
+            eval_logger.warning(
+                "trust_remote_code and datasets scripts are no longer supported on datasets>=4.0.0. Skipping. If your task still requires this, please downgrade to datasets==3.6.0 or earlier."
+            )
 
         if isinstance(args.model_args, dict):
             args.model_args["trust_remote_code"] = True

pyproject.toml

@@ -6,7 +6,7 @@ build-backend = "setuptools.build_meta"
 name = "lm_eval"
 version = "0.4.9.1"
 authors = [
-    {name="EleutherAI", email="contact@eleuther.ai"}
+    { name = "EleutherAI", email = "contact@eleuther.ai" }
 ]
 description = "A framework for evaluating language models"
 readme = "README.md"
@@ -21,7 +21,7 @@ license = { "text" = "MIT" }
 dependencies = [
     "accelerate>=0.26.0",
     "evaluate",
-    "datasets>=2.16.0,<4.0",
+    "datasets>=2.16.0",
     "evaluate>=0.4.0",
     "jsonlines",
     "numexpr",
@@ -68,8 +68,8 @@ ibm_watsonx_ai = ["ibm_watsonx_ai>=1.1.22", "python-dotenv"]
 ifeval = ["langdetect", "immutabledict", "nltk>=3.9.1"]
 ipex = ["optimum"]
 japanese_leaderboard = ["emoji==2.14.0", "neologdn==0.5.3", "fugashi[unidic-lite]", "rouge_score>=0.1.2"]
-longbench=["jieba", "fuzzywuzzy", "rouge"]
-libra=["pymorphy2"]
+longbench = ["jieba", "fuzzywuzzy", "rouge"]
+libra = ["pymorphy2"]
 mamba = ["mamba_ssm", "causal-conv1d==1.0.2", "torch"]
 math = ["sympy>=1.12", "antlr4-python3-runtime==4.11", "math_verify[antlr4_11_0]"]
 multilingual = ["nagisa>=0.2.7", "jieba>=0.42.1", "pycountry"]
@@ -115,10 +115,10 @@ lines-after-imports = 2
 known-first-party = ["lm_eval"]
 
 [tool.ruff.lint.extend-per-file-ignores]
-"__init__.py" = ["F401","F402","F403"]
+"__init__.py" = ["F401", "F402", "F403"]
 "utils.py" = ["F401"]
 
 [dependency-groups]
 dev = [
-  "api","dev","sentencepiece"
+    "api", "dev", "sentencepiece"
 ]