ghndrx/kubeflow-pipelines
1
0
Fork 0
mirror of https://github.com/ghndrx/kubeflow-pipelines.git synced 2026-02-10 06:45:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix Python/transformers version compatibility

Browse Source
This commit is contained in:
Greg Hendrickson
2026-02-03 01:11:20 +00:00
parent 297a75da4d
commit b086239c52
4 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
components/runpod_trainer/Dockerfile
View File

@@ -1,4 +1,4 @@
FROM runpod/pytorch:2.1.0-py3.10-cuda11.8.0-devel-ubuntu22.04
FROM runpod/pytorch:2.4.0-py3.11-cuda12.4.1-devel-ubuntu22.04
WORKDIR /app

7
components/runpod_trainer/requirements.txt
View File

@@ -1,9 +1,8 @@
runpod>=1.6.0
transformers>=4.36.0
runpod>=1.7.0
transformers==4.44.0
datasets>=2.16.0
accelerate>=0.25.0
accelerate>=0.30.0
boto3>=1.34.0
scikit-learn>=1.3.0
scipy>=1.11.0
torch>=2.1.0
safetensors>=0.4.0

1
pipelines/ddi_data_prep.py
View File

@@ -178,6 +178,7 @@ def ddi_data_prep_pipeline(
model_name: str = "emilyalsentzer/Bio_ClinicalBERT",
epochs: int = 3,
learning_rate: float = 2e-5,
# NOTE: Using internal endpoint. For Tailscale, add ACL: tag:k8s → tagged-devices:*
minio_endpoint: str = "http://minio.minio.svc.cluster.local:9000",
):
"""

4
pipelines/ddi_training_runpod.py
View File

@@ -198,8 +198,8 @@ def ddi_training_pipeline(
learning_rate: float = 2e-5,
model_version: str = "v1",
# MinIO settings - use Tailscale endpoint
minio_endpoint: str = "https://minio.walleye-frog.ts.net",
# MinIO settings - internal for now. For Tailscale, add ACL: tag:k8s → tagged-devices:*
minio_endpoint: str = "http://minio.minio.svc.cluster.local:9000",
):
"""
Full DDI training pipeline: