[SE3Transformer/DGLPyT] Move results to workdir

DGLPyTorch/DrugDiscovery/SE3Transformer/README.md

@@ -285,7 +285,7 @@ To train your model using mixed or TF32 precision with Tensor Cores or FP32, per
 3.  Start an interactive session in the NGC container to run training/inference.
     ```
     mkdir -p results
-    docker run -it --runtime=nvidia --shm-size=8g --ulimit memlock=-1 --ulimit stack=67108864 --rm -v ${PWD}/results:/results se3-transformer:latest
+    docker run -it --runtime=nvidia --shm-size=8g --ulimit memlock=-1 --ulimit stack=67108864 --rm -v ${PWD}/results:/workspace/se3-transformer/results se3-transformer:latest
     ```
 
 4. Start training.

DGLPyTorch/DrugDiscovery/SE3Transformer/se3_transformer/runtime/arguments.py

@@ -33,7 +33,7 @@ PARSER = argparse.ArgumentParser(description='SE(3)-Transformer')
 paths = PARSER.add_argument_group('Paths')
 paths.add_argument('--data_dir', type=pathlib.Path, default=pathlib.Path('./data'),
                    help='Directory where the data is located or should be downloaded')
-paths.add_argument('--log_dir', type=pathlib.Path, default=pathlib.Path('/results'),
+paths.add_argument('--log_dir', type=pathlib.Path, default=pathlib.Path('./results'),
                    help='Directory where the results logs should be saved')
 paths.add_argument('--dllogger_name', type=str, default='dllogger_results.json',
                    help='Name for the resulting DLLogger JSON file')