Spaces:
Running
Running
File size: 4,664 Bytes
2852136 |
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 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 |
# Copyright 2024 HuggingFace Inc. and the LlamaFactory team.
#
# This code is inspired by the HuggingFace's transformers library.
# https://github.com/huggingface/transformers/blob/v4.40.0/examples/pytorch/language-modeling/run_clm.py
#
# 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 Literal, Optional
@dataclass
class DataArguments:
r"""
Arguments pertaining to what data we are going to input our model for training and evaluation.
"""
template: Optional[str] = field(
default=None,
metadata={"help": "Which template to use for constructing prompts in training and inference."},
)
dataset: Optional[str] = field(
default=None,
metadata={"help": "The name of provided dataset(s) to use. Use commas to separate multiple datasets."},
)
dataset_dir: str = field(
default="data",
metadata={"help": "Path to the folder containing the datasets."},
)
split: str = field(
default="train",
metadata={"help": "Which dataset split to use for training and evaluation."},
)
cutoff_len: int = field(
default=1024,
metadata={"help": "The cutoff length of the tokenized inputs in the dataset."},
)
reserved_label_len: int = field(
default=1,
metadata={"help": "The minimum cutoff length reserved for the tokenized labels in the dataset."},
)
train_on_prompt: bool = field(
default=False,
metadata={"help": "Whether to disable the mask on the prompt or not."},
)
streaming: bool = field(
default=False,
metadata={"help": "Enable dataset streaming."},
)
buffer_size: int = field(
default=16384,
metadata={"help": "Size of the buffer to randomly sample examples from in dataset streaming."},
)
mix_strategy: Literal["concat", "interleave_under", "interleave_over"] = field(
default="concat",
metadata={"help": "Strategy to use in dataset mixing (concat/interleave) (undersampling/oversampling)."},
)
interleave_probs: Optional[str] = field(
default=None,
metadata={"help": "Probabilities to sample data from datasets. Use commas to separate multiple datasets."},
)
overwrite_cache: bool = field(
default=False,
metadata={"help": "Overwrite the cached training and evaluation sets."},
)
preprocessing_num_workers: Optional[int] = field(
default=None,
metadata={"help": "The number of processes to use for the pre-processing."},
)
max_samples: Optional[int] = field(
default=None,
metadata={"help": "For debugging purposes, truncate the number of examples for each dataset."},
)
eval_num_beams: Optional[int] = field(
default=None,
metadata={"help": "Number of beams to use for evaluation. This argument will be passed to `model.generate`"},
)
ignore_pad_token_for_loss: bool = field(
default=True,
metadata={
"help": "Whether or not to ignore the tokens corresponding to padded labels in the loss computation."
},
)
val_size: float = field(
default=0.0,
metadata={"help": "Size of the development set, should be an integer or a float in range `[0,1)`."},
)
packing: Optional[bool] = field(
default=None,
metadata={
"help": "Whether or not to pack the sequences in training. Will automatically enable in pre-training."
},
)
tokenized_path: Optional[str] = field(
default=None,
metadata={"help": "Path to save or load the tokenized datasets."},
)
def __post_init__(self):
if self.reserved_label_len >= self.cutoff_len:
raise ValueError("`reserved_label_len` must be smaller than `cutoff_len`.")
if self.streaming and self.val_size > 1e-6 and self.val_size < 1:
raise ValueError("Streaming mode should have an integer val size.")
if self.streaming and self.max_samples is not None:
raise ValueError("`max_samples` is incompatible with `streaming`.")
|