# Describes which dataset to load. 
dataset:
    # The name of the dataset to use. This is used as a key inside an if-else branch to determine which method to call.
    name: cifar10
    # These are custom settings for the above dataset. The keys differ based on the implementation.
    average_setting: micro
    num_classes: 10

# Battery configuration. This field holds the energy consumption of a device based on various metrics. 
battery:
    # The base consumption per second.
    deduction_per_second: 0
    # The consumption per megaflop of data processed.
    deduction_per_mflop: 0.001
    # The consumption per megabyte of data recieived over the network.
    deduction_per_mbyte_received: 0.001
    #  The consumption per megabyte of data sent over the network.
    deduction_per_mbyte_sent: 0.01

# Points to the loss function to use during backpropagation. This can be a builtin pytorch loss function or a custom one.
loss_fn:
    # `_target_` points to the class to instantiate.
    _target_: torch.nn.CrossEntropyLoss

# The `experiment` section contains experiment-specific parameters.
experiment:
    # The name of the experiment. Used in `wandb` as the project name, too.
    project: inda-ml-comparisons
    name: cifar100-effectiveness-adaptive-threshold-mechanism-none
    # The type of experiment. Only used for logging/wandb.
    job: train

    # Training parameters.
    batch_size: 64
    max_epochs: 1
    max_rounds: 200
    metrics: [ accuracy ]

    # Checkpoint saving and early stopping.
    save_weights: True
    server_model_save_path: "edml/models/weights/"
    client_model_save_path: "edml/models/weights/"

    # When enabled, early stopping uses the metric specified to check the model improvement rate after each
    # training round. If the rate is too small, training is stopped completely. 
    early_stopping: True
    early_stopping_patience: 200
    early_stopping_metric: accuracy

    # Dataset partitioning. If true, the dataset is split and each device gets their own data.
    partition: True
    # An optional lits of fractions used to determine the ratio of the data split. Numbers have to be between 0 and 1.
    # The numbers should add up to 1. The length should be equal to the number of devices participating in the 
    # experiment.
    fractions: !!null
    # An optional list of numbers describing a simulated latency of a device. The length should be equal to the number of devices participating in the 
    # experiment.
    latency: !!null

    # Useful for dubugging purposes. Only loads a single batch from the dataset.
    load_single_batch_for_debugging: False


# The model provider is responsible for providing a client and server model. The class can be extended for custom implementations.
# This config field has to be point to an implementation of `edml.models.provider.base.ModelProvider`.
model_provider:
    _target_: edml.models.provider.base.ModelProvider
    # Custom keys based on the model provider you use. In the case for `edml.models.provider.base.ModelProvider`, you can specify
    # the client and server model by ponting to two classes that inherit from `torch.nn.Module`.
    client:
        _target_: edml.models.mnist_models.ClientNet
    server:
        _target_: edml.models.mnist_models.ServerNet

# The optimizer to use during backpropagation.
optimizer: !!null

# The optional schduler to use for the learning rate. 
scheduler: !!null

# An optional initial seed. If not set, the seed is initialized randomly.
seed: default

# The device/network topology. Contains A list of devices, each with their unique ID, their IP address and their initial battery capacity.
topology:
    # A list of device definitions.
    devices: [
        # A device definition. All fields are mandatory.
        {
            device_id: "d0",
            address: "localhost:50051",
            battery_capacity: 45000,
        },
        {
            device_id: "d1",
            address: "localhost:50052",
            battery_capacity: 45000,
        },
        {
            device_id: "d2",
            address: "localhost:50053",
            battery_capacity: 45000,
        },
        {
        device_id: "d3",
        address: "localhost:50054",
        battery_capacity: 45000,
        },
        {
        device_id: "d4",
        address: "localhost:50055",
        battery_capacity: 45000,
        }
    ]

# The first n devices to use for the experiment. Defaults to the same number of devices declared above.
# Sometimes it is useful to shrink the count for debugging purposes.
num_devices: ${len:${topology.devices}}

# The device's unique ID. This is set inside the code and does not have to be set manually. It just exists here so that `hydra` 
# knows about the field and we can manipulate it during runtime.
own_device_id: "d0"

# The GRPC configuration. if not configured explicitly, sane default values will be used.
grpc: default

# The wandb configuration section.
wandb:
    # If true, the experiments get logged to wandb.
    enabled: true
    # The org or user to log the experiment run to.
    entity: <your-wandb-username-or-organisation-name>
    # The filename from which the API key is read from.
    wandb_key: wandb_key.txt

# If False, controllers will run devices in parallel. If True, they will run sequentially and their runtime is corrected
# to account for the parallelism in post-processing.
# Important Note: In a limited energy setting, the runtime will not be accounted for correctly (i.e. wall time) if parallelism is only simulated.
simulate_parallelism: False

# The key is used to group experiments together. Useful for grouping experiments of sweeps together in `wandb`.
# You define config key paths.
group_by:
  # The grouping takes the `controller.name`, `controller.scheduler.name` and `controller.adaptive_threshold_fn.name` properties into account.
  - controller: [ name, scheduler: name, adaptive_threshold_fn: name ]
  # Additionally, the `model_provider.decoder.path` property is taken into account.
  - model_provider: [ decoder: path ]

# `group_name` is a custom resolver for the configuration that takes a value and formats it in a special way for later usage.
# The term `${group_name:${group_by}}` means: use the value `group_by` to setup and configure the grouping. Normally, you'd 
# only change the `group_by` configuration value.
group: ${group_name:${group_by}}

name: cifar10
average_setting: micro
num_classes: 10

dataset: cifar10