# Header meta
spec_version = "0.1.0"

# These fields don't have any impact on the job to run, they contain
# merely informative data so the benchmark can be categorized when displayed
# in the dashboard.
[info]
description = """ MXNet training single-node {MXNet_version} CPU {py_version} resnet18v2 cifar10
"""
scheduling = 'single_run'

[info.labels]
# Labels and values must be 63 characters or less, beginning and ending with an alphanumeric character
# ([a-z0-9A-Z]) with dashes (-), underscores (_), dots (.), and alphanumerics between
task_name = "mx_train_single_node_cpu_{py_version}_resnet18v2_cifar10"

# 1. Hardware
[hardware]
instance_type = "c5.18xlarge"
strategy = "single_node"
aws_zone_id="use1-az2"

# 2. Environment
[env]
docker_image = "mxnet-training:{mxnet_version}-cpu-{py_version}"

[env.vars]
OMP_NUM_THREADS = "36"
KMP_AFFINITY='granularity=fine,verbose,compact,1,0'

# 3. Machine learning related settings:
 # dataset, benchmark code and parameters it takes
[ml]

benchmark_code = "python $(BAI_SCRIPTS_PATH)/deeplearning-benchmark/image_classification/image_classification.py"

args = "--model resnet18_v2 --dataset cifar10 --mode symbolic --gpus 0 --epochs 2 --log-interval 50 --kvstore local --dtype='float32' --batch-size=64"

# 5. Output
[output]
# [Opt] Custom metrics descriptions
# List all required metrics descriptions below.
# Make an entry in same format as the one below.
[[output.metrics]]
# Name of the metric that will appear in the dashboards.
name = "throughput"
# Metric unit (required)
units = "img/sec"
# Pattern for log parsing for this metric.
pattern = 'Speed: (\d+\.\d+|\d+) samples\/sec'