perform flakey patched tests in individual runner

.github/workflows/tests-nightly.yml

@@ -44,6 +44,11 @@ jobs:
           python-version: ${{ matrix.python_version }}
           cache: 'pip' # caching pip dependencies
 
+      - name: upgrade pip
+        run: |
+          pip3 install --upgrade pip
+          pip3 install --upgrade packaging setuptools wheel
+
       - name: Install PyTorch
         run: |
           pip3 install torch==${{ matrix.pytorch_version }} --index-url https://download.pytorch.org/whl/cpu

cicd/cicd.sh

@@ -8,3 +8,8 @@ pytest -v --durations=10 -n8 --ignore=tests/e2e/ --ignore=tests/patched/ /worksp
 pytest -v --durations=10 -n1 --dist loadfile /workspace/axolotl/tests/e2e/patched/
 pytest -v --durations=10 -n1 --dist loadfile /workspace/axolotl/tests/e2e/integrations/
 pytest -v --durations=10 --ignore=tests/e2e/patched/ --ignore=tests/e2e/multigpu/ --ignore=tests/e2e/integrations/ /workspace/axolotl/tests/e2e/
+
+tests=$(pytest --collect-only -q tests/e2e/each)
+for t in $tests; do
+    pytest $t
+done

requirements.txt

@@ -12,7 +12,7 @@ liger-kernel==0.4.2
 
 packaging==23.2
 peft==0.14.0
-transformers>=4.46.3
+transformers==4.47.0
 tokenizers>=0.20.1
 accelerate==1.2.0
 datasets==3.1.0

src/axolotl/utils/callbacks/__init__.py

@@ -66,10 +66,7 @@ class EvalFirstStepCallback(
         control: TrainerControl,
         **kwargs,
     ):
-        if (
-            args.evaluation_strategy == IntervalStrategy.STEPS
-            and state.global_step == 1
-        ):
+        if args.eval_strategy == IntervalStrategy.STEPS and state.global_step == 1:
             control.should_evaluate = True
         return control