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

dataset: femnist
dataset_dir: ../data/femnist/
output_dir: output/fedavg_cnn-2022-07-16_23:58:41/
model: cnn
num_rounds: 10
eval_every: 1
ServerType: <class 'rayleaf.entities.server.Server'>
client_types: [(<class 'rayleaf.entities.client.Client'>, 10)]
clients_per_round: 5
client_lr: 0.06
batch_size: 64
seed: 0
use_val_set: False
num_epochs: 10
gpus_per_client_cluster: 1
num_client_clusters: 2
save_model: False

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

Spawning 2 ClientClusters using cuda device (this may take a while)
10 total clients: 10 Clients

>>> Training Accuracy: Round 0 <<<
+------------+------------+-------------------+-------------------+
|    average |     median |   10th percentile |   90th percentile |
|------------+------------+-------------------+-------------------|
| 0.00232897 | 0.00277027 |                 0 |        0.00299917 |
+------------+------------+-------------------+-------------------+
>>> Test Accuracy: Round 0 <<<
+-----------+----------+-------------------+-------------------+
|   average |   median |   10th percentile |   90th percentile |
|-----------+----------+-------------------+-------------------|
|         0 |        0 |                 0 |                 0 |
+-----------+----------+-------------------+-------------------+
--- Round 1 of 10: Training 5 clients: 5 Clients ---
