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

dataset: speech_commands
dataset_dir: ../data/speech_commands/
output_dir: output/fedavg-speech_commands-2022-08-13_21:46:07/
model: m5
num_rounds: 100
eval_every: 10
ServerType: <class 'rayleaf.entities.server.Server'>
client_types: [(<class 'rayleaf.entities.client.Client'>, 400)]
clients_per_round: 20
client_lr: 0.05
batch_size: 64
seed: 0
use_val_set: False
num_epochs: 10
gpus_per_client_cluster: 1
num_client_clusters: 1
save_model: False

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

Spawning 1 ClientClusters using cuda device (this may take a while)
400 total clients: 400 Clients

>>> Training Accuracy: Round 0 <<<
+-----------+-----------+-------------------+-------------------+
|   average |    median |   10th percentile |   90th percentile |
|-----------+-----------+-------------------+-------------------|
| 0.0420496 | 0.0410267 |         0.0215054 |         0.0641026 |
+-----------+-----------+-------------------+-------------------+
>>> Test Accuracy: Round 0 <<<
+-----------+----------+-------------------+-------------------+
|   average |   median |   10th percentile |   90th percentile |
|-----------+----------+-------------------+-------------------|
| 0.0390974 |     0.04 |                 0 |         0.0909091 |
+-----------+----------+-------------------+-------------------+
--- Round 1 of 100: Training 20 clients: 20 Clients ---
