From 4f8833e3e01f22ea635c530b53d9b06003d24151 Mon Sep 17 00:00:00 2001 From: hariharandev1 Date: Mon, 29 Jul 2024 03:56:32 -0700 Subject: [PATCH] Reducing debug level for Apps. --- .github/workflows/ci.yml | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index c4128f8a..719f3a51 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -198,6 +198,7 @@ jobs: run: | source ${VENV_PATH}/bin/activate rm -rf output data checkpoints + export DFTRACER_LOG_LEVEL=INFO mpirun -np 2 ${DLIO_EXEC} workload=resnet50_tf ++workload.dataset.num_files_train=64 ++workload.workflow.train=False ++workload.workflow.generate_data=True ++workload.dataset.num_files_train=4 ++workload.dataset.num_samples_per_file=16 mpirun -np 2 ${DLIO_EXEC} workload=resnet50_tf ++workload.dataset.num_files_train=64 ++workload.workflow.train=True ++workload.workflow.generate_data=False ++workload.dataset.num_files_train=4 ++workload.dataset.num_samples_per_file=16 ++workload.train.computation_time=0.01 ++workload.train.epochs=1 rm -rf data @@ -205,6 +206,7 @@ jobs: run: | source ${VENV_PATH}/bin/activate rm -rf output data checkpoints + export DFTRACER_LOG_LEVEL=INFO mpirun -np 2 ${DLIO_EXEC} workload=unet3d_a100 ++workload.train.computation_time=0.05 ++workload.evaluation.eval_time=0.01 ++workload.workflow.train=False ++workload.workflow.generate_data=True ++workload.dataset.num_files_train=8 ++workload.dataset.num_files_eval=8 ++workload.reader.read_threads=2 ++workload.dataset.record_length=4096 ++workload.dataset.record_length_stdev=0 mpirun -np 2 ${DLIO_EXEC} workload=unet3d_a100 ++workload.train.computation_time=0.05 ++workload.evaluation.eval_time=0.01 ++workload.train.epochs=1 ++workload.workflow.train=True ++workload.workflow.generate_data=False ++workload.dataset.num_files_train=8 ++workload.dataset.num_files_eval=8 ++workload.reader.read_threads=0 ++workload.dataset.record_length=4096 ++workload.dataset.record_length_stdev=0 rm -rf data @@ -212,6 +214,7 @@ jobs: run: | source ${VENV_PATH}/bin/activate rm -rf output data checkpoints + export DFTRACER_LOG_LEVEL=INFO mpirun -np 2 ${DLIO_EXEC} workload=unet3d_a100 ++workload.framework=tensorflow ++workload.data_reader.data_loader=tensorflow ++workload.train.computation_time=0.05 ++workload.evaluation.eval_time=0.01 ++workload.train.epochs=2 ++workload.workflow.train=False ++workload.workflow.generate_data=True ++workload.dataset.num_files_train=16 ++workload.dataset.num_files_eval=16 ++workload.reader.read_threads=2 ++workload.dataset.record_length=4096 ++workload.dataset.record_length_stdev=0 mpirun -np 2 ${DLIO_EXEC} workload=unet3d_a100 ++workload.framework=tensorflow ++workload.data_reader.data_loader=tensorflow ++workload.train.computation_time=0.05 ++workload.evaluation.eval_time=0.01 ++workload.train.epochs=2 ++workload.workflow.train=True ++workload.workflow.generate_data=False ++workload.dataset.num_files_train=16 ++workload.dataset.num_files_eval=16 ++workload.reader.read_threads=2 ++workload.dataset.record_length=4096 ++workload.dataset.record_length_stdev=0 rm -rf data @@ -219,6 +222,7 @@ jobs: run: | source ${VENV_PATH}/bin/activate rm -rf output data checkpoints + export DFTRACER_LOG_LEVEL=INFO mpirun -np 2 ${DLIO_EXEC} workload=unet3d_a100 ++workload.workflow.generate_data=True ++workload.dataset.num_files_train=42 mpirun -np 2 ${DLIO_EXEC} workload=unet3d_h100 ++workload.workflow.generate_data=True ++workload.dataset.num_files_train=42 mpirun -np 2 ${DLIO_EXEC} workload=unet3d_h100 ++workload.workflow.generate_data=True ++workload.dataset.num_files_train=42 ++workload.dataset.format=synthetic @@ -227,6 +231,7 @@ jobs: run: | source ${VENV_PATH}/bin/activate rm -rf output data checkpoints + export DFTRACER_LOG_LEVEL=INFO mpirun -np 2 ${DLIO_EXEC} workload=resnet50_a100 ++workload.workflow.generate_data=True ++workload.dataset.num_files_train=4 mpirun -np 2 ${DLIO_EXEC} workload=resnet50_h100 ++workload.workflow.generate_data=True ++workload.dataset.num_files_train=4 mpirun -np 2 ${DLIO_EXEC} workload=resnet50_h100 ++workload.workflow.generate_data=True ++workload.dataset.num_files_train=4 ++workload.dataset.format=synthetic @@ -235,6 +240,7 @@ jobs: run: | source ${VENV_PATH}/bin/activate rm -rf output data checkpoints + export DFTRACER_LOG_LEVEL=INFO mpirun -np 2 ${DLIO_EXEC} workload=cosmoflow_a100 ++workload.workflow.generate_data=True ++workload.dataset.num_files_train=16 mpirun -np 2 ${DLIO_EXEC} workload=cosmoflow_h100 ++workload.workflow.generate_data=True ++workload.dataset.num_files_train=16 mpirun -np 2 ${DLIO_EXEC} workload=cosmoflow_h100 ++workload.workflow.generate_data=True ++workload.dataset.num_files_train=16 ++workload.dataset.format=synthetic