2025-06-12 21:12:58 +00:00
|
|
|
#!/bin/bash
|
|
|
|
|
|
|
|
# Runs marker benchmark, measuring both olmOCR-bench performance and per document processing performance
|
|
|
|
# ./scripts/run_marker_benchmark.sh
|
|
|
|
# ./scripts/run_marker_benchmark.sh 1.7.5
|
|
|
|
|
|
|
|
set -e
|
|
|
|
|
|
|
|
# Parse command line arguments
|
|
|
|
MARKER_VERSION="${1:-1.7.5}"
|
|
|
|
echo "Using marker version: $MARKER_VERSION"
|
|
|
|
|
|
|
|
# Check for uncommitted changes
|
|
|
|
if ! git diff-index --quiet HEAD --; then
|
|
|
|
echo "Error: There are uncommitted changes in the repository."
|
|
|
|
echo "Please commit or stash your changes before running the benchmark."
|
|
|
|
echo ""
|
|
|
|
echo "Uncommitted changes:"
|
|
|
|
git status --short
|
|
|
|
exit 1
|
|
|
|
fi
|
|
|
|
|
|
|
|
# Use conda environment Python if available, otherwise use system Python
|
|
|
|
if [ -n "$CONDA_PREFIX" ]; then
|
|
|
|
PYTHON="$CONDA_PREFIX/bin/python"
|
|
|
|
echo "Using conda Python from: $CONDA_PREFIX"
|
|
|
|
else
|
|
|
|
PYTHON="python"
|
|
|
|
echo "Warning: No conda environment detected, using system Python"
|
|
|
|
fi
|
|
|
|
|
|
|
|
# Get version from version.py
|
|
|
|
VERSION=$($PYTHON -c 'import olmocr.version; print(olmocr.version.VERSION)')
|
|
|
|
echo "OlmOCR version: $VERSION"
|
|
|
|
|
|
|
|
# Get first 10 characters of git hash
|
|
|
|
GIT_HASH=$(git rev-parse HEAD | cut -c1-10)
|
|
|
|
echo "Git hash: $GIT_HASH"
|
|
|
|
|
|
|
|
# Get current git branch name
|
|
|
|
GIT_BRANCH=$(git rev-parse --abbrev-ref HEAD)
|
|
|
|
echo "Git branch: $GIT_BRANCH"
|
|
|
|
|
|
|
|
# Create full image tag
|
|
|
|
IMAGE_TAG="olmocr-benchmark-${VERSION}-${GIT_HASH}"
|
|
|
|
echo "Building Docker image with tag: $IMAGE_TAG"
|
|
|
|
|
|
|
|
# Build the Docker image
|
|
|
|
echo "Building Docker image..."
|
|
|
|
docker build --platform linux/amd64 -f ./Dockerfile -t $IMAGE_TAG .
|
|
|
|
|
|
|
|
# Get Beaker username
|
|
|
|
BEAKER_USER=$(beaker account whoami --format json | jq -r '.[0].name')
|
|
|
|
echo "Beaker user: $BEAKER_USER"
|
|
|
|
|
|
|
|
# Push image to beaker
|
|
|
|
echo "Trying to push image to Beaker..."
|
|
|
|
if ! beaker image create --workspace ai2/oe-data-pdf --name $IMAGE_TAG $IMAGE_TAG 2>/dev/null; then
|
|
|
|
echo "Warning: Beaker image with tag $IMAGE_TAG already exists. Using existing image."
|
|
|
|
fi
|
|
|
|
|
|
|
|
# Create Python script to run beaker experiment
|
|
|
|
cat << 'EOF' > /tmp/run_benchmark_experiment.py
|
|
|
|
import sys
|
|
|
|
from beaker import Beaker, ExperimentSpec, TaskSpec, TaskContext, ResultSpec, TaskResources, ImageSource, Priority, Constraints, EnvVar
|
|
|
|
|
|
|
|
# Get image tag, beaker user, git branch, git hash, and marker version from command line
|
|
|
|
image_tag = sys.argv[1]
|
|
|
|
beaker_user = sys.argv[2]
|
|
|
|
git_branch = sys.argv[3]
|
|
|
|
git_hash = sys.argv[4]
|
|
|
|
marker_version = sys.argv[5]
|
|
|
|
|
|
|
|
# Initialize Beaker client
|
|
|
|
b = Beaker.from_env(default_workspace="ai2/olmocr")
|
|
|
|
|
|
|
|
|
|
|
|
# Check if AWS credentials secret exists
|
|
|
|
aws_creds_secret = f"{beaker_user}-AWS_CREDENTIALS_FILE"
|
|
|
|
try:
|
|
|
|
# Try to get the secret to see if it exists
|
|
|
|
b.secret.get(aws_creds_secret, workspace="ai2/olmocr")
|
|
|
|
has_aws_creds = True
|
|
|
|
print(f"Found AWS credentials secret: {aws_creds_secret}")
|
|
|
|
except:
|
|
|
|
has_aws_creds = False
|
|
|
|
print(f"AWS credentials secret not found: {aws_creds_secret}")
|
|
|
|
|
|
|
|
# First experiment: Original benchmark job
|
|
|
|
commands = []
|
|
|
|
if has_aws_creds:
|
|
|
|
commands.extend([
|
|
|
|
"mkdir -p ~/.aws",
|
|
|
|
'echo "$AWS_CREDENTIALS_FILE" > ~/.aws/credentials'
|
|
|
|
])
|
|
|
|
commands.extend([
|
|
|
|
"git clone https://huggingface.co/datasets/allenai/olmOCR-bench",
|
|
|
|
"cd olmOCR-bench && git lfs pull && cd ..",
|
2025-06-12 21:18:58 +00:00
|
|
|
f"pip install marker-pdf=={marker_version}",
|
2025-06-12 21:23:53 +00:00
|
|
|
"pip install --upgrade torchvision",
|
2025-06-12 21:12:58 +00:00
|
|
|
"python -m olmocr.bench.convert marker --dir ./olmOCR-bench/bench_data",
|
|
|
|
"python -m olmocr.bench.benchmark --dir ./olmOCR-bench/bench_data"
|
|
|
|
])
|
|
|
|
|
|
|
|
# Build task spec with optional env vars
|
|
|
|
task_spec_args = {
|
|
|
|
"name": "marker-benchmark",
|
|
|
|
"image": ImageSource(beaker=f"{beaker_user}/{image_tag}"),
|
|
|
|
"command": [
|
|
|
|
"bash", "-c",
|
|
|
|
" && ".join(commands)
|
|
|
|
],
|
|
|
|
"context": TaskContext(
|
|
|
|
priority=Priority.normal,
|
|
|
|
preemptible=True,
|
|
|
|
),
|
|
|
|
"resources": TaskResources(gpu_count=1),
|
|
|
|
"constraints": Constraints(cluster=["ai2/ceres-cirrascale", "ai2/jupiter-cirrascale-2"]),
|
|
|
|
"result": ResultSpec(path="/noop-results"),
|
|
|
|
}
|
|
|
|
|
|
|
|
# Add env vars if AWS credentials exist
|
|
|
|
if has_aws_creds:
|
|
|
|
task_spec_args["env_vars"] = [
|
|
|
|
EnvVar(name="AWS_CREDENTIALS_FILE", secret=aws_creds_secret)
|
|
|
|
]
|
|
|
|
|
|
|
|
# Create first experiment spec
|
|
|
|
experiment_spec = ExperimentSpec(
|
|
|
|
description=f"Marker {marker_version} Benchmark Run - Branch: {git_branch}, Commit: {git_hash}",
|
|
|
|
budget="ai2/oe-data",
|
|
|
|
tasks=[TaskSpec(**task_spec_args)],
|
|
|
|
)
|
|
|
|
|
|
|
|
# Create the first experiment
|
|
|
|
experiment = b.experiment.create(spec=experiment_spec, workspace="ai2/olmocr")
|
|
|
|
print(f"Created benchmark experiment: {experiment.id}")
|
|
|
|
print(f"View at: https://beaker.org/ex/{experiment.id}")
|
|
|
|
print("-------")
|
|
|
|
print("")
|
|
|
|
|
|
|
|
|
|
|
|
perf_commands = []
|
|
|
|
if has_aws_creds:
|
|
|
|
perf_commands.extend([
|
|
|
|
"mkdir -p ~/.aws",
|
|
|
|
'echo "$AWS_CREDENTIALS_FILE" > ~/.aws/credentials'
|
|
|
|
])
|
|
|
|
perf_commands.extend([
|
2025-06-12 21:18:58 +00:00
|
|
|
f"pip install marker-pdf=={marker_version}",
|
2025-06-12 21:23:53 +00:00
|
|
|
"pip install --upgrade torchvision",
|
2025-06-12 21:38:28 +00:00
|
|
|
"pip install awscli",
|
2025-06-12 21:29:39 +00:00
|
|
|
"aws s3 cp --recursive s3://ai2-oe-data/jakep/olmocr/olmOCR-mix-0225/benchmark_set/ /root/olmOCR-mix-0225_benchmark_set/",
|
2025-06-12 22:35:08 +00:00
|
|
|
# Tried with workers 8, but it was taking a really huge amount of time
|
|
|
|
#"time marker --force_ocr /root/olmOCR-mix-0225_benchmark_set/ --output_dir /root/olmOCR-mix-0225_benchmark_set_marker --workers 8"
|
|
|
|
"time marker --force_ocr /root/olmOCR-mix-0225_benchmark_set/ --output_dir /root/olmOCR-mix-0225_benchmark_set_marker"
|
2025-06-12 21:12:58 +00:00
|
|
|
])
|
|
|
|
|
|
|
|
# Build performance task spec
|
|
|
|
perf_task_spec_args = {
|
|
|
|
"name": "marker-performance",
|
|
|
|
"image": ImageSource(beaker=f"{beaker_user}/{image_tag}"),
|
|
|
|
"command": [
|
|
|
|
"bash", "-c",
|
|
|
|
" && ".join(perf_commands)
|
|
|
|
],
|
|
|
|
"context": TaskContext(
|
|
|
|
priority=Priority.normal,
|
|
|
|
preemptible=True,
|
|
|
|
),
|
|
|
|
"resources": TaskResources(gpu_count=1),
|
|
|
|
"constraints": Constraints(cluster=["ai2/ceres-cirrascale", "ai2/jupiter-cirrascale-2"]),
|
|
|
|
"result": ResultSpec(path="/noop-results"),
|
|
|
|
}
|
|
|
|
|
|
|
|
# Add env vars if AWS credentials exist
|
|
|
|
if has_aws_creds:
|
|
|
|
perf_task_spec_args["env_vars"] = [
|
|
|
|
EnvVar(name="AWS_CREDENTIALS_FILE", secret=aws_creds_secret)
|
|
|
|
]
|
|
|
|
|
|
|
|
# Create performance experiment spec
|
|
|
|
perf_experiment_spec = ExperimentSpec(
|
|
|
|
description=f"Marker {marker_version} Performance Test - Branch: {git_branch}, Commit: {git_hash}",
|
|
|
|
budget="ai2/oe-data",
|
|
|
|
tasks=[TaskSpec(**perf_task_spec_args)],
|
|
|
|
)
|
|
|
|
|
|
|
|
# Create the performance experiment
|
|
|
|
perf_experiment = b.experiment.create(spec=perf_experiment_spec, workspace="ai2/olmocr")
|
|
|
|
print(f"Created performance experiment: {perf_experiment.id}")
|
|
|
|
print(f"View at: https://beaker.org/ex/{perf_experiment.id}")
|
|
|
|
EOF
|
|
|
|
|
|
|
|
# Run the Python script to create the experiments
|
|
|
|
echo "Creating Beaker experiments..."
|
|
|
|
$PYTHON /tmp/run_benchmark_experiment.py $IMAGE_TAG $BEAKER_USER $GIT_BRANCH $GIT_HASH $MARKER_VERSION
|
|
|
|
|
|
|
|
# Clean up temporary file
|
|
|
|
rm /tmp/run_benchmark_experiment.py
|
|
|
|
|
|
|
|
echo "Benchmark experiments submitted successfully!"
|