riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-31 02:02:21 +06:00
Code Issues Actions 23 Packages Projects Releases Wiki Activity

Fix skip of test_training_gradient_checkpointing (#34723)

Browse Source 
19d58d31f has introduced a context manager to manage subtests of
test_training_gradient_checkpointing. However, test body was not
moved under "with" statement. Thus, while tests are correctly
marked as skipped, test bodies were still executed. In some cases,
as with llama this caused attribute errors.

Fixes: #34722
Fixes: 19d58d31f ("Add MLLama (#33703)")

Signed-off-by: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com>
This commit is contained in:
Dmitry Rogozhkin 2024-11-18 06:45:40 -08:00 committed by GitHub
parent c772d4d91e
commit 1c471fc307
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 18 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
tests/test_modeling_common.py
View File

@ -849,29 +849,29 @@ class ModelTesterMixin:
):
self.skipTest(reason=f"`supports_gradient_checkpointing` is False for {model_class.__name__}.")
config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common()
config.use_cache = False
config.return_dict = True
model = model_class(config)
config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common()
config.use_cache = False
config.return_dict = True
model = model_class(config)
model.to(torch_device)
model.gradient_checkpointing_enable(gradient_checkpointing_kwargs=gradient_checkpointing_kwargs)
model.train()
model.to(torch_device)
model.gradient_checkpointing_enable(gradient_checkpointing_kwargs=gradient_checkpointing_kwargs)
model.train()
# unfreeze additional layers
for p in model.parameters():
p.requires_grad_(True)
# unfreeze additional layers
for p in model.parameters():
p.requires_grad_(True)
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
inputs = self._prepare_for_class(inputs_dict, model_class, return_labels=True)
loss = model(**inputs).loss
loss.backward()
optimizer.step()
inputs = self._prepare_for_class(inputs_dict, model_class, return_labels=True)
loss = model(**inputs).loss
loss.backward()
optimizer.step()
for k, v in model.named_parameters():
if v.requires_grad:
self.assertTrue(v.grad is not None, f"{k} in {model_class.__name__} has no gradient!")
for k, v in model.named_parameters():
if v.requires_grad:
self.assertTrue(v.grad is not None, f"{k} in {model_class.__name__} has no gradient!")
def test_training(self):
if not self.model_tester.is_training: