Spaces:
Sleeping
Sleeping
File size: 2,679 Bytes
455a40f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 |
# 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.
import logging
from dataclasses import dataclass, field
from typing import Optional
from seq2seq_trainer import arg_to_scheduler
from transformers import TrainingArguments
logger = logging.getLogger(__name__)
@dataclass
class Seq2SeqTrainingArguments(TrainingArguments):
"""
Parameters:
label_smoothing (:obj:`float`, `optional`, defaults to 0):
The label smoothing epsilon to apply (if not zero).
sortish_sampler (:obj:`bool`, `optional`, defaults to :obj:`False`):
Whether to SortishSamler or not. It sorts the inputs according to lenghts in-order to minimizing the padding size.
predict_with_generate (:obj:`bool`, `optional`, defaults to :obj:`False`):
Whether to use generate to calculate generative metrics (ROUGE, BLEU).
"""
label_smoothing: Optional[float] = field(
default=0.0, metadata={"help": "The label smoothing epsilon to apply (if not zero)."}
)
sortish_sampler: bool = field(default=False, metadata={"help": "Whether to SortishSamler or not."})
predict_with_generate: bool = field(
default=False, metadata={"help": "Whether to use generate to calculate generative metrics (ROUGE, BLEU)."}
)
adafactor: bool = field(default=False, metadata={"help": "whether to use adafactor"})
encoder_layerdrop: Optional[float] = field(
default=None, metadata={"help": "Encoder layer dropout probability. Goes into model.config."}
)
decoder_layerdrop: Optional[float] = field(
default=None, metadata={"help": "Decoder layer dropout probability. Goes into model.config."}
)
dropout: Optional[float] = field(default=None, metadata={"help": "Dropout probability. Goes into model.config."})
attention_dropout: Optional[float] = field(
default=None, metadata={"help": "Attention dropout probability. Goes into model.config."}
)
lr_scheduler: Optional[str] = field(
default="linear",
metadata={"help": f"Which lr scheduler to use. Selected in {sorted(arg_to_scheduler.keys())}"},
)
|