c-my/transformers
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

BIG Reorganize examples (#4213)

Browse Source 
* Created using Colaboratory

* [examples] reorganize files

* remove run_tpu_glue.py as superseded by TPU support in Trainer

* Bugfix: int, not tuple

* move files around
This commit is contained in:
Julien Chaumond authored and GitHub committed 2020-05-07 13:48:44 -04:00
1 parent cafa6a9e29
commit 0ae96ff8a7
65 files changed
+1355 -1308
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

examples/test_examples.py
+52 -41
View File
@@ -16,14 +16,24 @@
import argparse
import logging
import os
import sys
import unittest
from unittest.mock import patch
import run_generation
import run_glue
import run_language_modeling
import run_squad
SRC_DIRS = [
os.path.join(os.path.dirname(__file__), dirname)
for dirname in ["text-generation", "text-classification", "language-modeling", "question-answering"]
]
sys.path.extend(SRC_DIRS)
if SRC_DIRS is not None:
import run_generation
import run_glue
import run_language_modeling
import run_squad
logging.basicConfig(level=logging.DEBUG)
@@ -43,24 +53,24 @@ class ExamplesTests(unittest.TestCase):
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",
"--max_seq_length=128",
]
model_name = "--model_name_or_path=bert-base-uncased"
with patch.object(sys, "argv", testargs + [model_name]):
testargs = """
run_glue.py
--model_name_or_path bert-base-uncased
--data_dir ./tests/fixtures/tests_samples/MRPC/
--task_name mrpc
--do_train
--do_eval
--output_dir ./tests/fixtures/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
--max_seq_length=128
""".split()
with patch.object(sys, "argv", testargs):
result = run_glue.main()
del result["loss"]
for value in result.values():
@@ -78,7 +88,7 @@ class ExamplesTests(unittest.TestCase):
--line_by_line
--train_data_file ./tests/fixtures/sample_text.txt
--eval_data_file ./tests/fixtures/sample_text.txt
--output_dir ./tests/fixtures
--output_dir ./tests/fixtures/tests_samples/temp_dir
--overwrite_output_dir
--do_train
--do_eval
@@ -93,24 +103,25 @@ class ExamplesTests(unittest.TestCase):
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]):
testargs = """
run_squad.py
--model_type=bert
--model_name_or_path=bert-base-uncased
--data_dir=./tests/fixtures/tests_samples/SQUAD
--model_name=bert-base-uncased
--output_dir=./tests/fixtures/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
""".split()
with patch.object(sys, "argv", testargs):
result = run_squad.main()
self.assertGreaterEqual(result["f1"], 30)
self.assertGreaterEqual(result["exact"], 30)