Add multi-class, multi-label and regression to transformers (#11012)

* add to  bert

* review comments

* Update src/transformers/configuration_utils.py

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

* Update src/transformers/configuration_utils.py

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

* self.config.problem_type

* fix style

* fix

* fin

* fix

* update doc

* fix

* test

* Test more problem types

* Update src/transformers/configuration_utils.py

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

* fix

* remove

* fix

* quality

* make fix-copies

* remove test

Co-authored-by: abhishek thakur <abhishekkrthakur@users.noreply.github.com>
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
Co-authored-by: Lysandre <lysandre.debut@reseau.eseo.fr>

tests/test_modeling_big_bird.py

@@ -433,6 +433,7 @@ class BigBirdModelTest(ModelTesterMixin, unittest.TestCase):
     # head masking & pruning is currently not supported for big bird
     test_head_masking = False
     test_pruning = False
+    test_sequence_classification_problem_types = True
 
     # torchscript should be possible, but takes prohibitively long to test.
     # Also torchscript is not an important feature to have in the beginning.