
############################## Experiment details ##############################

dataset: speech_commands
dataset_dir: ../datasets/speech_commands/
output_dir: output/debug/signavg-speech_commands-2022-07-10_19:10:35/
model: mel
num_rounds: 100
eval_every: 10
ServerType: <class 'rayleaf.entities.server.Server'>
client_types: [(<class 'rayleaf.entities.client.Client'>, 5)]
clients_per_round: 1
client_lr: 0.01
batch_size: 64
seed: 0
use_val_set: False
num_epochs: 5
gpus_per_client_cluster: 0.1
num_client_clusters: 1
save_model: False

############################## Simulation ##############################

Spawning 1 ClientClusters using cuda device (this may take a while)
5 total clients: 5 Clients

>>> Training Accuracy: Round 0 <<<
+-----------+-----------+-------------------+-------------------+
|   average |    median |   10th percentile |   90th percentile |
|-----------+-----------+-------------------+-------------------|
| 0.0339806 | 0.0388889 |         0.0171935 |         0.0465714 |
+-----------+-----------+-------------------+-------------------+
>>> Test Accuracy: Round 0 <<<
+-----------+----------+-------------------+-------------------+
|   average |   median |   10th percentile |   90th percentile |
|-----------+----------+-------------------+-------------------|
| 0.0344828 |     0.02 |                 0 |         0.0743207 |
+-----------+----------+-------------------+-------------------+
--- Round 1 of 100: Training 1 clients: 1 Client ---
