|
|
|
import subprocess
|
|
|
|
import sys
|
|
|
|
from random import sample
|
|
|
|
|
|
|
|
import numpy as np # noqa: F401
|
|
|
|
from lightning_sdk import Machine, Studio # noqa: F401
|
|
|
|
|
|
|
|
NUM_JOBS = 100
|
|
|
|
|
|
|
|
# reference to the current studio
|
|
|
|
# if you run outside of Lightning, you can pass the Studio name
|
|
|
|
# studio = Studio()
|
|
|
|
|
|
|
|
# use the jobs plugin
|
|
|
|
# studio.install_plugin("jobs")
|
|
|
|
# job_plugin = studio.installed_plugins["jobs"]
|
|
|
|
|
|
|
|
# do a sweep over learning rates
|
|
|
|
|
|
|
|
# Define the ranges or sets of values for each hyperparameter
|
|
|
|
# alpha_values = list(np.round(np.linspace(2, 4, 21), 4))
|
|
|
|
# learning_rate_values = list(np.round(np.logspace(-5, -3, 21), 5))
|
|
|
|
learning_rate_values = [1e-2]
|
|
|
|
alpha_values = [0, 1, 2]
|
|
|
|
widths = [2**k for k in range(4, 15)]
|
|
|
|
# learning_rate_values = [5e-4]
|
|
|
|
batch_size_values = [256]
|
|
|
|
max_epochs_values = [100]
|
|
|
|
seeds = list(range(21, 1992))
|
|
|
|
|
|
|
|
# Generate all possible combinations of hyperparameters
|
|
|
|
all_params = [
|
|
|
|
(alpha, lr, bs, me, s, w)
|
|
|
|
for alpha in alpha_values
|
|
|
|
for lr in learning_rate_values
|
|
|
|
for bs in batch_size_values
|
|
|
|
for me in max_epochs_values
|
|
|
|
for s in seeds
|
|
|
|
for w in widths
|
|
|
|
]
|
|
|
|
|
|
|
|
|
|
|
|
# perform random search with a limit
|
|
|
|
search_params = sample(all_params, min(NUM_JOBS, len(all_params)))
|
|
|
|
|
|
|
|
for idx, params in enumerate(search_params):
|
|
|
|
a, lr, bs, me, s, w = params
|
|
|
|
cmd = f"cd ~/colors && python main.py --alpha {a} --lr {lr} --bs {bs} --max_epochs {me} --seed {s} --width {w}"
|
|
|
|
# job_name = f"color2_{bs}_{a}_{lr:2.2e}"
|
|
|
|
# job_plugin.run(cmd, machine=Machine.T4, name=job_name)
|
|
|
|
print(f"Running {params}: {cmd}")
|
|
|
|
try:
|
|
|
|
# Run the command and wait for it to complete
|
|
|
|
subprocess.run(cmd, shell=True, check=True)
|
|
|
|
except KeyboardInterrupt:
|
|
|
|
print("Interrupted by user")
|
|
|
|
sys.exit(1)
|