mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-04 13:20:12 +06:00
fc38d4c86f
* improving generation * finalized special token behaviour for no_beam_search generation * solved modeling_utils merge conflict * solve merge conflicts in modeling_utils.py * add run_generation improvements from PR #2749 * adapted language generation to not use hardcoded -1 if no padding token is available * remove the -1 removal as hard coded -1`s are not necessary anymore * add lightweight language generation testing for randomely initialized models - just checking whether no errors are thrown * add slow language generation tests for pretrained models using hardcoded output with pytorch seed * delete ipdb * check that all generated tokens are valid * renaming * renaming Generation -> Generate * make style * updated so that generate_beam_search has same token behavior than generate_no_beam_search * consistent return format for run_generation.py * deleted pretrain lm generate tests -> will be added in another PR * cleaning of unused if statements and renaming * run_generate will always return an iterable * make style * consistent renaming * improve naming, make sure generate function always returns the same tensor, add docstring * add slow tests for all lmhead models * make style and improve example comments modeling_utils * better naming and refactoring in modeling_utils * improving generation * finalized special token behaviour for no_beam_search generation * solved modeling_utils merge conflict * solve merge conflicts in modeling_utils.py * add run_generation improvements from PR #2749 * adapted language generation to not use hardcoded -1 if no padding token is available * remove the -1 removal as hard coded -1`s are not necessary anymore * add lightweight language generation testing for randomely initialized models - just checking whether no errors are thrown * add slow language generation tests for pretrained models using hardcoded output with pytorch seed * delete ipdb * check that all generated tokens are valid * renaming * renaming Generation -> Generate * make style * updated so that generate_beam_search has same token behavior than generate_no_beam_search * consistent return format for run_generation.py * deleted pretrain lm generate tests -> will be added in another PR * cleaning of unused if statements and renaming * run_generate will always return an iterable * make style * consistent renaming * improve naming, make sure generate function always returns the same tensor, add docstring * add slow tests for all lmhead models * make style and improve example comments modeling_utils * better naming and refactoring in modeling_utils * changed fast random lm generation testing design to more general one * delete in old testing design in gpt2 * correct old variable name * temporary fix for encoder_decoder lm generation tests - has to be updated when t5 is fixed * adapted all fast random generate tests to new design * better warning description in modeling_utils * better comment * better comment and error message Co-authored-by: Thomas Wolf <thomwolf@users.noreply.github.com>
101 lines
3.4 KiB
Python
101 lines
3.4 KiB
Python
# coding=utf-8
|
|
# Copyright 2018 HuggingFace Inc..
|
|
#
|
|
# 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.
|
|
|
|
|
|
import argparse
|
|
import logging
|
|
import sys
|
|
import unittest
|
|
from unittest.mock import patch
|
|
|
|
import run_generation
|
|
import run_glue
|
|
import run_squad
|
|
|
|
|
|
logging.basicConfig(level=logging.DEBUG)
|
|
|
|
logger = logging.getLogger()
|
|
|
|
|
|
def get_setup_file():
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument("-f")
|
|
args = parser.parse_args()
|
|
return args.f
|
|
|
|
|
|
class ExamplesTests(unittest.TestCase):
|
|
def test_run_glue(self):
|
|
stream_handler = logging.StreamHandler(sys.stdout)
|
|
logger.addHandler(stream_handler)
|
|
|
|
testargs = [
|
|
"run_glue.py",
|
|
"--data_dir=./examples/tests_samples/MRPC/",
|
|
"--task_name=mrpc",
|
|
"--do_train",
|
|
"--do_eval",
|
|
"--output_dir=./examples/tests_samples/temp_dir",
|
|
"--per_gpu_train_batch_size=2",
|
|
"--per_gpu_eval_batch_size=1",
|
|
"--learning_rate=1e-4",
|
|
"--max_steps=10",
|
|
"--warmup_steps=2",
|
|
"--overwrite_output_dir",
|
|
"--seed=42",
|
|
]
|
|
model_type, model_name = ("--model_type=bert", "--model_name_or_path=bert-base-uncased")
|
|
with patch.object(sys, "argv", testargs + [model_type, model_name]):
|
|
result = run_glue.main()
|
|
for value in result.values():
|
|
self.assertGreaterEqual(value, 0.75)
|
|
|
|
def test_run_squad(self):
|
|
stream_handler = logging.StreamHandler(sys.stdout)
|
|
logger.addHandler(stream_handler)
|
|
|
|
testargs = [
|
|
"run_squad.py",
|
|
"--data_dir=./examples/tests_samples/SQUAD",
|
|
"--model_name=bert-base-uncased",
|
|
"--output_dir=./examples/tests_samples/temp_dir",
|
|
"--max_steps=10",
|
|
"--warmup_steps=2",
|
|
"--do_train",
|
|
"--do_eval",
|
|
"--version_2_with_negative",
|
|
"--learning_rate=2e-4",
|
|
"--per_gpu_train_batch_size=2",
|
|
"--per_gpu_eval_batch_size=1",
|
|
"--overwrite_output_dir",
|
|
"--seed=42",
|
|
]
|
|
model_type, model_name = ("--model_type=bert", "--model_name_or_path=bert-base-uncased")
|
|
with patch.object(sys, "argv", testargs + [model_type, model_name]):
|
|
result = run_squad.main()
|
|
self.assertGreaterEqual(result["f1"], 30)
|
|
self.assertGreaterEqual(result["exact"], 30)
|
|
|
|
def test_generation(self):
|
|
stream_handler = logging.StreamHandler(sys.stdout)
|
|
logger.addHandler(stream_handler)
|
|
|
|
testargs = ["run_generation.py", "--prompt=Hello", "--length=10", "--seed=42"]
|
|
model_type, model_name = ("--model_type=openai-gpt", "--model_name_or_path=openai-gpt")
|
|
with patch.object(sys, "argv", testargs + [model_type, model_name]):
|
|
result = run_generation.main()
|
|
self.assertGreaterEqual(len(result[0]), 10)
|