[Almost all TF models] TF clean up: add missing CLM / MLM loss; fix T5 naming and keras compile (#5395)

* add first version of clm tf

* make style

* add more tests for bert

* update tf clm loss

* fix tests

* correct tf ner script

* add mlm loss

* delete bogus file

* clean tf auto model + add tests

* finish adding clm loss everywhere

* fix training in distilbert

* fix flake8

* save intermediate

* fix tf t5 naming

* remove prints

* finish up

* up

* fix tf gpt2

* fix new test utils import

* fix flake8

* keep backward compatibility

* Update src/transformers/modeling_tf_albert.py

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Update src/transformers/modeling_tf_auto.py

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Update src/transformers/modeling_tf_electra.py

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Update src/transformers/modeling_tf_roberta.py

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Update src/transformers/modeling_tf_mobilebert.py

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Update src/transformers/modeling_tf_auto.py

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Update src/transformers/modeling_tf_bert.py

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Update src/transformers/modeling_tf_distilbert.py

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* apply sylvains suggestions

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
This commit is contained in:
Patrick von Platen
2020-07-07 18:15:53 +02:00
committed by GitHub
parent 33e43edddc
commit 4dc65591b5
23 changed files with 1516 additions and 315 deletions

View File

@@ -17,7 +17,7 @@
import unittest
from transformers import is_torch_available
from transformers.testing_utils import require_torch, torch_device
from transformers.testing_utils import require_torch, slow, torch_device
from .test_configuration_common import ConfigTester
from .test_modeling_common import ModelTesterMixin, ids_tensor
@@ -32,6 +32,7 @@ if is_torch_available():
DistilBertForTokenClassification,
DistilBertForQuestionAnswering,
DistilBertForSequenceClassification,
DISTILBERT_PRETRAINED_MODEL_ARCHIVE_LIST,
)
class DistilBertModelTester(object):
@@ -276,8 +277,8 @@ class DistilBertModelTest(ModelTesterMixin, unittest.TestCase):
config_and_inputs = self.model_tester.prepare_config_and_inputs()
self.model_tester.create_and_check_distilbert_for_multiple_choice(*config_and_inputs)
# @slow
# def test_model_from_pretrained(self):
# for model_name in DISTILBERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]:
# model = DistilBertModel.from_pretrained(model_name)
# self.assertIsNotNone(model)
@slow
def test_model_from_pretrained(self):
for model_name in DISTILBERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]:
model = DistilBertModel.from_pretrained(model_name)
self.assertIsNotNone(model)