fixing load best model at the end (#389)

test/nlp/run_gpu.py

@@ -0,0 +1,82 @@
+import sys
+import pytest
+import pickle
+import shutil
+
+
+@pytest.mark.skipif(sys.platform == "darwin", reason="do not run on mac os")
+def _test_hf_data():
+    from flaml import AutoML
+    import requests
+    from datasets import load_dataset
+
+    try:
+        train_dataset = load_dataset("glue", "mrpc", split="train").to_pandas()
+        dev_dataset = load_dataset("glue", "mrpc", split="validation").to_pandas()
+        test_dataset = load_dataset("glue", "mrpc", split="test").to_pandas()
+    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]
+
+    X_test = test_dataset[custom_sent_keys]
+
+    automl = AutoML()
+
+    automl_settings = {
+        "gpu_per_trial": 1,
+        "max_iter": 5,
+        "time_budget": 5000,
+        "task": "seq-classification",
+        "metric": "accuracy",
+        "log_file_name": "seqclass.log",
+        "use_ray": True,
+    }
+
+    automl_settings["custom_hpo_args"] = {
+        "model_path": "facebook/muppet-roberta-base",
+        "output_dir": "test/data/output/",
+        "ckpt_per_epoch": 5,
+        "fp16": True,
+    }
+
+    automl.fit(
+        X_train=X_train, y_train=y_train, X_val=X_val, y_val=y_val, **automl_settings
+    )
+
+    automl = AutoML()
+    automl.retrain_from_log(
+        X_train=X_train,
+        y_train=y_train,
+        train_full=True,
+        record_id=0,
+        **automl_settings
+    )
+    with open("automl.pkl", "wb") as f:
+        pickle.dump(automl, f, pickle.HIGHEST_PROTOCOL)
+    with open("automl.pkl", "rb") as f:
+        automl = pickle.load(f)
+    shutil.rmtree("test/data/output/")
+    automl.predict(X_test)
+    automl.predict(["test test", "test test"])
+    automl.predict(
+        [
+            ["test test", "test test"],
+            ["test test", "test test"],
+            ["test test", "test test"],
+        ]
+    )
+
+    automl.predict_proba(X_test)
+    print(automl.classes_)
+
+
+if __name__ == "__main__":
+    _test_hf_data()