wehub-resource-sync
69 lines
2.8 KiB
Python
69 lines
2.8 KiB
Python
# Copyright 2020 The HuggingFace Team. All rights reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
from dataclasses import dataclass, field
|
|
from typing import Optional
|
|
|
|
from .training_args import TrainingArguments
|
|
from .utils import add_start_docstrings
|
|
|
|
__all__ = [
|
|
"Seq2SeqTrainingArguments",
|
|
]
|
|
|
|
|
|
@dataclass
|
|
@add_start_docstrings(TrainingArguments.__doc__)
|
|
class Seq2SeqTrainingArguments(TrainingArguments):
|
|
"""
|
|
Args:
|
|
sortish_sampler (`bool`, *optional*, defaults to `False`):
|
|
Whether to use a *sortish sampler* or not. Only possible if the underlying datasets are *Seq2SeqDataset*
|
|
for now but will become generally available in the near future.
|
|
|
|
It sorts the inputs according to lengths in order to minimize the padding size, with a bit of randomness
|
|
for the training set.
|
|
predict_with_generate (`bool`, *optional*, defaults to `False`):
|
|
Whether to use generate to calculate generative metrics (ROUGE, BLEU).
|
|
generation_max_length (`int`, *optional*):
|
|
The `max_length` to use on each evaluation loop when `predict_with_generate=True`. Will default to the
|
|
`max_length` value of the model configuration.
|
|
generation_num_beams (`int`, *optional*):
|
|
The `num_beams` to use on each evaluation loop when `predict_with_generate=True`. Will default to the
|
|
`num_beams` value of the model configuration.
|
|
"""
|
|
|
|
sortish_sampler: bool = field(default=False, metadata={"help": "Whether to use SortishSampler or not."})
|
|
predict_with_generate: bool = field(
|
|
default=False, metadata={"help": "Whether to use generate to calculate generative metrics (ROUGE, BLEU)."}
|
|
)
|
|
generation_max_length: Optional[int] = field(
|
|
default=None,
|
|
metadata={
|
|
"help": (
|
|
"The `max_length` to use on each evaluation loop when `predict_with_generate=True`. Will default "
|
|
"to the `max_length` value of the model configuration."
|
|
)
|
|
},
|
|
)
|
|
generation_num_beams: Optional[int] = field(
|
|
default=None,
|
|
metadata={
|
|
"help": (
|
|
"The `num_beams` to use on each evaluation loop when `predict_with_generate=True`. Will default "
|
|
"to the `num_beams` value of the model configuration."
|
|
)
|
|
},
|
|
)
|