SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

per_device instead of per_gpu/error thrown when argument unknown (#4618)

Browse Source 
* per_device instead of per_gpu/error thrown when argument unknown

* [docs] Restore examples.md symlink

* Correct absolute links so that symlink to the doc works correctly

* Update src/transformers/hf_argparser.py

Co-authored-by: Julien Chaumond <chaumond@gmail.com>

* Warning + reorder

* Docs

* Style

* not for squad

Co-authored-by: Julien Chaumond <chaumond@gmail.com>
This commit is contained in:
Lysandre Debut
2020-05-27 11:36:55 -04:00
committed by GitHub
parent 1381b6d01d
commit 6a17688021
10 changed files with 73 additions and 686 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
src/transformers/training_args.py
View File

@@ -58,8 +58,28 @@ class TrainingArguments:
default=False, metadata={"help": "Run evaluation during training at each logging step."},
)
per_gpu_train_batch_size: int = field(default=8, metadata={"help": "Batch size per GPU/CPU for training."})
per_gpu_eval_batch_size: int = field(default=8, metadata={"help": "Batch size per GPU/CPU for evaluation."})
per_device_train_batch_size: int = field(
default=8, metadata={"help": "Batch size per GPU/TPU core/CPU for training."}
)
per_device_eval_batch_size: int = field(
default=8, metadata={"help": "Batch size per GPU/TPU core/CPU for evaluation."}
)
per_gpu_train_batch_size: Optional[int] = field(
default=None,
metadata={
"help": "Deprecated, the use of `--per_device_train_batch_size` is preferred. "
"Batch size per GPU/TPU core/CPU for training."
},
)
per_gpu_eval_batch_size: Optional[int] = field(
default=None,
metadata={
"help": "Deprecated, the use of `--per_device_eval_batch_size` is preferred."
"Batch size per GPU/TPU core/CPU for evaluation."
},
)
gradient_accumulation_steps: int = field(
default=1,
metadata={"help": "Number of updates steps to accumulate before performing a backward/update pass."},
@@ -115,11 +135,23 @@ class TrainingArguments:
@property
def train_batch_size(self) -> int:
return self.per_gpu_train_batch_size * max(1, self.n_gpu)
if self.per_gpu_train_batch_size:
logger.warning(
"Using deprecated `--per_gpu_train_batch_size` argument which will be removed in a future "
"version. Using `--per_device_train_batch_size` is preferred."
)
per_device_batch_size = self.per_gpu_train_batch_size or self.per_device_train_batch_size
return per_device_batch_size * max(1, self.n_gpu)
@property
def eval_batch_size(self) -> int:
return self.per_gpu_eval_batch_size * max(1, self.n_gpu)
if self.per_gpu_eval_batch_size:
logger.warning(
"Using deprecated `--per_gpu_eval_batch_size` argument which will be removed in a future "
"version. Using `--per_device_eval_batch_size` is preferred."
)
per_device_batch_size = self.per_gpu_eval_batch_size or self.per_device_eval_batch_size
return per_device_batch_size * max(1, self.n_gpu)
@cached_property
@torch_required