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

dataset: speech_commands
dataset_dir: /home/huberkeley/rayleaf/data/speech_commands/
output_dir: output/speech_commands/fedavg/10clients-5cpr-0.05lr-25epochs-100rounds-2022-09-18_16:12:44
model: m5
num_rounds: 100
eval_every: 10
ServerType: <class 'rayleaf.entities.server.Server'>
client_types: [(<class 'rayleaf.entities.client.Client'>, 10)]
clients_per_round: 5
client_lr: 0.05
batch_size: 64
seed: 0
use_val_set: False
num_epochs: 25
gpus_per_client_cluster: 1
num_client_clusters: 6
save_model: False

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

Spawning 6 ClientClusters using cuda device (this may take a while)
10 total clients: 10 Clients

>>> Training Accuracy: Round 0 <<<
+-----------+-----------+-------------------+-------------------+
|   average |    median |   10th percentile |   90th percentile |
|-----------+-----------+-------------------+-------------------|
| 0.0353006 | 0.0371496 |          0.022366 |         0.0473295 |
+-----------+-----------+-------------------+-------------------+
>>> Test Accuracy: Round 0 <<<
+-----------+-----------+-------------------+-------------------+
|   average |    median |   10th percentile |   90th percentile |
|-----------+-----------+-------------------+-------------------|
| 0.0479303 | 0.0364583 |          0.025571 |         0.0778537 |
+-----------+-----------+-------------------+-------------------+
--- Round 1 of 100: Training 5 clients: 5 Clients ---
--- Round 2 of 100: Training 5 clients: 5 Clients ---
--- Round 3 of 100: Training 5 clients: 5 Clients ---
--- Round 4 of 100: Training 5 clients: 5 Clients ---
--- Round 5 of 100: Training 5 clients: 5 Clients ---
