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

dataset: femnist
dataset_dir: ../data/femnist/
output_dir: output/fedavg_cnn-2022-07-14_19:17:44/
model: cnn
num_rounds: 100
eval_every: 10
ServerType: <class 'rayleaf.entities.server.Server'>
client_types: [(<class 'rayleaf.entities.client.Client'>, 200)]
clients_per_round: 40
client_lr: 0.06
batch_size: 64
seed: 0
use_val_set: False
num_epochs: 10
gpus_per_client_cluster: 1
num_client_clusters: 7
save_model: False

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

Spawning 7 ClientClusters using cuda device (this may take a while)
200 total clients: 200 Clients

>>> Training Accuracy: Round 0 <<<
+------------+------------+-------------------+-------------------+
|    average |     median |   10th percentile |   90th percentile |
|------------+------------+-------------------+-------------------|
| 0.00251956 | 0.00292398 |                 0 |        0.00377645 |
+------------+------------+-------------------+-------------------+
>>> Test Accuracy: Round 0 <<<
+------------+----------+-------------------+-------------------+
|    average |   median |   10th percentile |   90th percentile |
|------------+----------+-------------------+-------------------|
| 0.00291545 |        0 |                 0 |        0.00238095 |
+------------+----------+-------------------+-------------------+
--- Round 1 of 100: Training 40 clients: 40 Clients ---
