mirror of
https://github.com/microsoft/autogen.git
synced 2025-08-02 13:52:39 +00:00
47 lines
1.1 KiB
Python
47 lines
1.1 KiB
Python
|
def test_regression():
|
||
|
|
try:
|
||
|
|
import ray
|
||
|
|
except ImportError:
|
||
|
|
return
|
||
|
|
from flaml import AutoML
|
||
|
|
|
||
|
|
from datasets import load_dataset
|
||
|
|
|
||
|
|
train_dataset = (
|
||
|
|
load_dataset("glue", "stsb", split="train[:1%]").to_pandas().iloc[0:4]
|
||
|
|
)
|
||
|
|
dev_dataset = (
|
||
|
|
load_dataset("glue", "stsb", split="train[1%:2%]").to_pandas().iloc[0:4]
|
||
|
|
)
|
||
|
|
|
||
|
|
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": 3,
|
||
|
|
"time_budget": 20,
|
||
|
|
"task": "seq-regression",
|
||
|
|
"metric": "rmse",
|
||
|
|
"model_history": True,
|
||
|
|
}
|
||
|
|
|
||
|
|
automl_settings["custom_hpo_args"] = {
|
||
|
|
"model_path": "google/electra-small-discriminator",
|
||
|
|
"output_dir": "data/output/",
|
||
|
|
"ckpt_per_epoch": 5,
|
||
|
|
"fp16": False,
|
||
|
|
}
|
||
|
|
|
||
|
|
automl.fit(
|
||
|
|
X_train=X_train, y_train=y_train, X_val=X_val, y_val=y_val, **automl_settings
|
||
|
|
)
|