mirror of
https://github.com/microsoft/autogen.git
synced 2025-08-03 06:12:22 +00:00
569908fbe6
* console log handler * version update * doc * skippable steps * notebook update * constraint sign * doc for constraints * bug fix: define-by-run and unflatten_hierarchical * const * handle nested space in indexof() * test grid search * test suggestion * model test * >1 ckpts * always increase iter count * log total # iterations * security patch * make iter_per_learner consistent
61 lines
1.5 KiB
Python
61 lines
1.5 KiB
Python
import sys
|
|
import pytest
|
|
|
|
|
|
@pytest.mark.skipif(sys.platform == "darwin", reason="do not run on mac os")
|
|
def test_regression():
|
|
try:
|
|
import ray
|
|
except ImportError:
|
|
return
|
|
from flaml import AutoML
|
|
import requests
|
|
from datasets import load_dataset
|
|
|
|
try:
|
|
train_dataset = load_dataset("glue", "stsb", split="train[:2%]").to_pandas()
|
|
dev_dataset = (
|
|
load_dataset("glue", "stsb", split="train[2%:3%]").to_pandas().iloc[:32]
|
|
)
|
|
except requests.exceptions.ConnectionError:
|
|
return
|
|
|
|
custom_sent_keys = ["sentence1", "sentence2"]
|
|
label_key = "label"
|
|
|
|
X_train = train_dataset[custom_sent_keys]
|
|
y_train = train_dataset[label_key]
|
|
|
|
X_val = dev_dataset[custom_sent_keys]
|
|
y_val = dev_dataset[label_key]
|
|
|
|
automl = AutoML()
|
|
|
|
automl_settings = {
|
|
"gpu_per_trial": 0,
|
|
"max_iter": 2,
|
|
"time_budget": 5,
|
|
"task": "seq-regression",
|
|
"metric": "pearsonr",
|
|
"starting_points": {"transformer": {"num_train_epochs": 1}},
|
|
"use_ray": True,
|
|
}
|
|
|
|
automl_settings["custom_hpo_args"] = {
|
|
"model_path": "google/electra-small-discriminator",
|
|
"output_dir": "test/data/output/",
|
|
"ckpt_per_epoch": 5,
|
|
"fp16": False,
|
|
}
|
|
|
|
ray.shutdown()
|
|
ray.init()
|
|
automl.fit(
|
|
X_train=X_train, y_train=y_train, X_val=X_val, y_val=y_val, **automl_settings
|
|
)
|
|
automl.predict(X_val)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
test_regression()
|