You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 

112 lines
3.3 KiB

import subprocess
import sys
from random import sample, seed
import numpy as np # noqa: F401
from lightning_sdk import Machine, Studio # noqa: F401
# consistency of randomly sampled experiments.
seed(19920921)
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-3]
# learning_rate_values = [5e-4]
# alpha_values = [0, .25, 0.5, 0.75, 1] # alpha = 0 is unsupervised. alpha = 1 is supervised.
alpha_values = [0]
# widths = [2**k for k in range(4, 13)]
# depths = [1, 2, 4, 8, 16]
widths, depths = [512], [4]
batch_size_values = [256]
max_epochs_values = [100]
seeds = list(range(21, 1992))
optimizers = [
# "Adagrad",
"Adam",
# "SGD",
# "AdamW",
# "LBFGS",
# "RAdam",
# "RMSprop",
# "Adadelta",
]
# Generate all possible combinations of hyperparameters
all_params = [
(alpha, lr, bs, me, s, w, d, opt)
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
for d in depths
for opt in optimizers
]
# perform random search with a limit
search_params = sample(all_params, min(NUM_JOBS, len(all_params)))
# --trainer.callbacks+ lightning.pytorch.callbacks.EarlyStopping \
# --trainer.callbacks.init_args.monitor hp_metric \
for idx, params in enumerate(search_params):
a, lr, bs, me, s, w, d, opt = params
# cmd = f"cd ~/colors && python main.py --alpha {a} --lr {lr} --bs {bs} --max_epochs {me} --seed {s} --width {w}"
cmd = f"""
python newmain.py fit \
--seed_everything {s} \
--data.batch_size {bs} \
--data.train_size 0 \
--data.val_size 10000 \
--model.alpha {a} \
--model.width {w} \
--model.depth {d} \
--model.bias true \
--model.transform tanh \
--trainer.min_epochs 10 \
--trainer.max_epochs {me} \
--trainer.log_every_n_steps 3 \
--trainer.check_val_every_n_epoch 1 \
--trainer.limit_val_batches 50 \
--trainer.callbacks callbacks.SaveImageCallback \
--trainer.callbacks.init_args.final_dir out \
--trainer.callbacks.init_args.save_interval 0 \
--optimizer torch.optim.{opt} \
--optimizer.init_args.lr {lr} \
--trainer.callbacks+ lightning.pytorch.callbacks.LearningRateFinder
# --lr_scheduler lightning.pytorch.cli.ReduceLROnPlateau \
# --lr_scheduler.init_args.monitor hp_metric \
# --lr_scheduler.init_args.factor 0.05 \
# --lr_scheduler.init_args.patience 5 \
# --lr_scheduler.init_args.cooldown 10 \
# --lr_scheduler.init_args.verbose true
"""
# 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(test_cmd, shell=True, check=True)
subprocess.run(cmd, shell=True, check=True)
except KeyboardInterrupt:
print("Interrupted by user")
sys.exit(1)
# except subprocess.CalledProcessError:
# pass