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 33 Packages Projects Releases Wiki Activity

[Trainer] Fix default data collator (#30142)

Browse Source 
* Fix data collator

* Support feature extractors as well
This commit is contained in:
NielsRogge 2024-04-09 12:52:50 +02:00 committed by GitHub
parent ec59a42192
commit ba1b24e07b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
src/transformers/trainer.py
View File

@ -58,6 +58,7 @@ from . import __version__
from .configuration_utils import PretrainedConfig
from .data.data_collator import DataCollator, DataCollatorWithPadding, default_data_collator
from .debug_utils import DebugOption, DebugUnderflowOverflow
from .feature_extraction_sequence_utils import SequenceFeatureExtractor
from .hyperparameter_search import ALL_HYPERPARAMETER_SEARCH_BACKENDS, default_hp_search_backend
from .image_processing_utils import BaseImageProcessor
from .integrations.deepspeed import deepspeed_init, deepspeed_load_checkpoint, is_deepspeed_available
@ -492,7 +493,11 @@ class Trainer:
):
self.place_model_on_device = False
default_collator = DataCollatorWithPadding(tokenizer) if tokenizer is not None else default_data_collator
default_collator = (
DataCollatorWithPadding(tokenizer)
if tokenizer is not None and isinstance(tokenizer, (PreTrainedTokenizerBase, SequenceFeatureExtractor))
else default_data_collator
)
self.data_collator = data_collator if data_collator is not None else default_collator
self.train_dataset = train_dataset
self.eval_dataset = eval_dataset