Spaces:
Running
Running
File size: 1,907 Bytes
0b8359d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 |
# Lint as: python3
# Copyright 2020 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""Tests for official.nlp.tasks.masked_lm."""
import tensorflow as tf
from official.nlp.configs import bert
from official.nlp.configs import encoders
from official.nlp.tasks import masked_lm
class MLMTaskTest(tf.test.TestCase):
def test_task(self):
config = masked_lm.MaskedLMConfig(
network=bert.BertPretrainerConfig(
encoders.TransformerEncoderConfig(vocab_size=30522, num_layers=1),
num_masked_tokens=20,
cls_heads=[
bert.ClsHeadConfig(
inner_dim=10, num_classes=2, name="next_sentence")
]),
train_data=bert.BertPretrainDataConfig(
input_path="dummy",
max_predictions_per_seq=20,
seq_length=128,
global_batch_size=1))
task = masked_lm.MaskedLMTask(config)
model = task.build_model()
metrics = task.build_metrics()
dataset = task.build_inputs(config.train_data)
iterator = iter(dataset)
optimizer = tf.keras.optimizers.SGD(lr=0.1)
task.train_step(next(iterator), model, optimizer, metrics=metrics)
task.validation_step(next(iterator), model, metrics=metrics)
if __name__ == "__main__":
tf.test.main()
|