File size: 7,242 Bytes
0499fd5 cac60d2 fa8d2eb 0499fd5 cac60d2 0499fd5 cac60d2 0499fd5 ecfe1a8 0499fd5 ecfe1a8 0499fd5 ecfe1a8 0499fd5 ecfe1a8 0499fd5 cac60d2 0499fd5 ecfe1a8 cac60d2 ecfe1a8 cac60d2 ecfe1a8 cac60d2 ecfe1a8 0499fd5 cac60d2 0499fd5 ecfe1a8 0499fd5 ecfe1a8 0499fd5 cac60d2 b9e4a28 0499fd5 9e537b8 e0e9a43 6c6dc97 e0e9a43 c1daee1 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 |
import functools
import seqio
import tensorflow as tf
import t5.data
from datasets import load_dataset
from t5.data import postprocessors
from t5.data import preprocessors
from t5.evaluation import metrics
from seqio import FunctionDataSource, utils
TaskRegistry = seqio.TaskRegistry
vocabulary = seqio.SentencePieceVocabulary('gs://t5-data/vocabs/mc4.250000.100extra/sentencepiece.model', extra_ids=0)
DEFAULT_OUTPUT_FEATURES = {
"inputs": seqio.Feature(
vocabulary=vocabulary, add_eos=True,
required=False),
"targets": seqio.Feature(
vocabulary=vocabulary, add_eos=True)
}
def gen_dataset(split, shuffle=False, seed=None, column="text", dataset_params=None):
dataset = load_dataset(**dataset_params)
if shuffle:
if seed:
dataset = dataset.shuffle(seed=seed)
else:
dataset = dataset.shuffle()
while True:
for item in dataset[str(split)]:
yield item[column]
def dataset_fn(split, shuffle_files, seed=None, dataset_params=None):
return tf.data.Dataset.from_generator(
functools.partial(gen_dataset, split, shuffle_files, seed, dataset_params=dataset_params),
output_signature=tf.TensorSpec(shape=(), dtype=tf.string, name=dataset_name)
)
@utils.map_over_dataset
def target_to_key(x, key_map, target_key):
"""Assign the value from the dataset to target_key in key_map"""
return {**key_map, target_key: x}
# Final pretraining task used in Raffel et al., 2019 adaptated to NCC
dataset_name = 'NbAiLab/NCC'
dataset_params = {"path": dataset_name}
dataset_shapes = {'train': 20830348, 'validation': 473079}
TaskRegistry.add(
"ncc_span_corruption",
source=seqio.FunctionDataSource(
dataset_fn=functools.partial(dataset_fn, dataset_params=dataset_params),
splits=("train", "validation"),
caching_permitted=False,
num_input_examples=dataset_shapes,
),
preprocessors=[
functools.partial(
target_to_key, key_map={
"inputs": None,
"targets": None,
}, target_key="targets"),
seqio.preprocessors.tokenize,
# seqio.CacheDatasetPlaceholder(),
preprocessors.span_corruption,
seqio.preprocessors.append_eos_after_trim,
],
output_features={"targets": DEFAULT_OUTPUT_FEATURES["targets"]},
metric_fns=[]
)
# Final pretraining task used in Raffel et al., 2019 adaptated to NCC
dataset_name = 'NbAiLab/NCC_small'
dataset_params = {"path": dataset_name}
dataset_shapes = {'train': 452845, 'validation': 473079}
TaskRegistry.add(
"ncc_small_span_corruption",
source=seqio.FunctionDataSource(
dataset_fn=functools.partial(dataset_fn, dataset_params=dataset_params),
splits=("train", "validation"),
caching_permitted=False,
num_input_examples=dataset_shapes,
),
preprocessors=[
functools.partial(
target_to_key, key_map={
"inputs": None,
"targets": None,
}, target_key="targets"),
seqio.preprocessors.tokenize,
# seqio.CacheDatasetPlaceholder(),
preprocessors.span_corruption,
seqio.preprocessors.append_eos_after_trim,
],
output_features={"targets": DEFAULT_OUTPUT_FEATURES["targets"]},
metric_fns=[]
)
# Final pretraining task used in Raffel et al., 2019 adaptated to NCC
dataset_name = 'NbAiLab/NCC'
dataset_params = {"path": dataset_name, "use_auth_token": True, "streaming": True}
dataset_shapes = None
TaskRegistry.add(
"ncc_span_corruption_stream",
source=seqio.FunctionDataSource(
dataset_fn=functools.partial(dataset_fn, dataset_params=dataset_params),
splits=("train", "validation"),
caching_permitted=False,
num_input_examples=dataset_shapes,
),
preprocessors=[
functools.partial(
target_to_key, key_map={
"inputs": None,
"targets": None,
}, target_key="targets"),
seqio.preprocessors.tokenize,
# seqio.CacheDatasetPlaceholder(),
preprocessors.span_corruption,
seqio.preprocessors.append_eos_after_trim,
],
output_features={"targets": DEFAULT_OUTPUT_FEATURES["targets"]},
metric_fns=[]
)
# Final pretraining task used in Raffel et al., 2019 adaptated to NCC
dataset_name = 'NbAiLab/NCC_plus_english'
dataset_params = {"path": dataset_name, "use_auth_token": True, "streaming": True}
dataset_shapes = None
TaskRegistry.add(
"ncc_english_span_corruption_stream",
source=seqio.FunctionDataSource(
dataset_fn=functools.partial(dataset_fn, dataset_params=dataset_params),
splits=("train", "validation"),
caching_permitted=False,
num_input_examples=dataset_shapes,
),
preprocessors=[
functools.partial(
target_to_key, key_map={
"inputs": None,
"targets": None,
}, target_key="targets"),
seqio.preprocessors.tokenize,
# seqio.CacheDatasetPlaceholder(),
preprocessors.span_corruption,
seqio.preprocessors.append_eos_after_trim,
],
output_features={"targets": DEFAULT_OUTPUT_FEATURES["targets"]},
metric_fns=[]
)
# Final pretraining task used in Raffel et al., 2019 adaptated to NCC
dataset_name = 'NbAiLab/scandinavian'
dataset_params = {"path": dataset_name, "use_auth_token": True, "streaming": True}
dataset_shapes = None
TaskRegistry.add(
"ncc_scandinavian_span_corruption_stream",
source=seqio.FunctionDataSource(
dataset_fn=functools.partial(dataset_fn, dataset_params=dataset_params),
splits=("train", "validation"),
caching_permitted=False,
num_input_examples=dataset_shapes,
),
preprocessors=[
functools.partial(
target_to_key, key_map={
"inputs": None,
"targets": None,
}, target_key="targets"),
seqio.preprocessors.tokenize,
# seqio.CacheDatasetPlaceholder(),
preprocessors.span_corruption,
seqio.preprocessors.append_eos_after_trim,
],
output_features={"targets": DEFAULT_OUTPUT_FEATURES["targets"]},
metric_fns=[]
)
# Final pretraining task used in Raffel et al., 2019 adaptated to NCC
dataset_name = 'NbAiLab/balanced_bokmaal_nynorsk'
dataset_params = {"path": dataset_name, "use_auth_token": True, "streaming": True}
dataset_shapes = None
TaskRegistry.add(
"balanced_bokmaal_nynorsk_span_corruption_stream",
source=seqio.FunctionDataSource(
dataset_fn=functools.partial(dataset_fn, dataset_params=dataset_params),
splits=("train", "validation"),
caching_permitted=False,
num_input_examples=dataset_shapes,
),
preprocessors=[
functools.partial(
target_to_key, key_map={
"inputs": None,
"targets": None,
}, target_key="targets"),
seqio.preprocessors.tokenize,
# seqio.CacheDatasetPlaceholder(),
preprocessors.span_corruption,
seqio.preprocessors.append_eos_after_trim,
],
output_features={"targets": DEFAULT_OUTPUT_FEATURES["targets"]},
metric_fns=[]
)
|