File size: 12,933 Bytes
a0fb398 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 |
import random
import logging
from datasets import load_dataset, Dataset, DatasetDict
from sentence_transformers import (
SentenceTransformer,
SentenceTransformerTrainer,
SentenceTransformerTrainingArguments,
SentenceTransformerModelCardData,
)
from sentence_transformers.losses import MatryoshkaLoss, MultipleNegativesRankingLoss
from sentence_transformers.training_args import BatchSamplers, MultiDatasetBatchSamplers
from sentence_transformers.models.StaticEmbedding import StaticEmbedding
from transformers import AutoTokenizer
logging.basicConfig(
format="%(asctime)s - %(message)s", datefmt="%Y-%m-%d %H:%M:%S", level=logging.INFO
)
random.seed(12)
def main():
# 1. Load a model to finetune with 2. (Optional) model card data
static_embedding = StaticEmbedding(AutoTokenizer.from_pretrained("google-bert/bert-base-multilingual-uncased"), embedding_dim=1024)
model = SentenceTransformer(
modules=[static_embedding],
model_card_data=SentenceTransformerModelCardData(
license="apache-2.0",
model_name="Static Embeddings with BERT Multilingual uncased tokenizer finetuned on various datasets",
),
)
# 3. Set up training & evaluation datasets - each dataset is trained with MNRL (with MRL)
print("Loading wikititles dataset...")
wikititles_dataset = load_dataset("sentence-transformers/parallel-sentences-wikititles", split="train")
wikititles_dataset_dict = wikititles_dataset.train_test_split(test_size=10_000, seed=12)
wikititles_train_dataset: Dataset = wikititles_dataset_dict["train"]
wikititles_eval_dataset: Dataset = wikititles_dataset_dict["test"]
print("Loaded wikititles dataset.")
print("Loading tatoeba dataset...")
tatoeba_dataset = load_dataset("sentence-transformers/parallel-sentences-tatoeba", "all", split="train")
tatoeba_dataset_dict = tatoeba_dataset.train_test_split(test_size=10_000, seed=12)
tatoeba_train_dataset: Dataset = tatoeba_dataset_dict["train"]
tatoeba_eval_dataset: Dataset = tatoeba_dataset_dict["test"]
print("Loaded tatoeba dataset.")
print("Loading talks dataset...")
talks_dataset = load_dataset("sentence-transformers/parallel-sentences-talks", "all", split="train")
talks_dataset_dict = talks_dataset.train_test_split(test_size=10_000, seed=12)
talks_train_dataset: Dataset = talks_dataset_dict["train"]
talks_eval_dataset: Dataset = talks_dataset_dict["test"]
print("Loaded talks dataset.")
print("Loading europarl dataset...")
europarl_dataset = load_dataset("sentence-transformers/parallel-sentences-europarl", "all", split="train[:5000000]")
europarl_dataset_dict = europarl_dataset.train_test_split(test_size=10_000, seed=12)
europarl_train_dataset: Dataset = europarl_dataset_dict["train"]
europarl_eval_dataset: Dataset = europarl_dataset_dict["test"]
print("Loaded europarl dataset.")
print("Loading global voices dataset...")
global_voices_dataset = load_dataset("sentence-transformers/parallel-sentences-global-voices", "all", split="train")
global_voices_dataset_dict = global_voices_dataset.train_test_split(test_size=10_000, seed=12)
global_voices_train_dataset: Dataset = global_voices_dataset_dict["train"]
global_voices_eval_dataset: Dataset = global_voices_dataset_dict["test"]
print("Loaded global voices dataset.")
print("Loading jw300 dataset...")
jw300_dataset = load_dataset("sentence-transformers/parallel-sentences-jw300", "all", split="train")
jw300_dataset_dict = jw300_dataset.train_test_split(test_size=10_000, seed=12)
jw300_train_dataset: Dataset = jw300_dataset_dict["train"]
jw300_eval_dataset: Dataset = jw300_dataset_dict["test"]
print("Loaded jw300 dataset.")
print("Loading muse dataset...")
muse_dataset = load_dataset("sentence-transformers/parallel-sentences-muse", split="train")
muse_dataset_dict = muse_dataset.train_test_split(test_size=10_000, seed=12)
muse_train_dataset: Dataset = muse_dataset_dict["train"]
muse_eval_dataset: Dataset = muse_dataset_dict["test"]
print("Loaded muse dataset.")
print("Loading wikimatrix dataset...")
wikimatrix_dataset = load_dataset("sentence-transformers/parallel-sentences-wikimatrix", "all", split="train")
wikimatrix_dataset_dict = wikimatrix_dataset.train_test_split(test_size=10_000, seed=12)
wikimatrix_train_dataset: Dataset = wikimatrix_dataset_dict["train"]
wikimatrix_eval_dataset: Dataset = wikimatrix_dataset_dict["test"]
print("Loaded wikimatrix dataset.")
print("Loading opensubtitles dataset...")
opensubtitles_dataset = load_dataset("sentence-transformers/parallel-sentences-opensubtitles", "all", split="train[:5000000]")
opensubtitles_dataset_dict = opensubtitles_dataset.train_test_split(test_size=10_000, seed=12)
opensubtitles_train_dataset: Dataset = opensubtitles_dataset_dict["train"]
opensubtitles_eval_dataset: Dataset = opensubtitles_dataset_dict["test"]
print("Loaded opensubtitles dataset.")
print("Loading stackexchange dataset...")
stackexchange_dataset = load_dataset("sentence-transformers/stackexchange-duplicates", "post-post-pair", split="train")
stackexchange_dataset_dict = stackexchange_dataset.train_test_split(test_size=10_000, seed=12)
stackexchange_train_dataset: Dataset = stackexchange_dataset_dict["train"]
stackexchange_eval_dataset: Dataset = stackexchange_dataset_dict["test"]
print("Loaded stackexchange dataset.")
print("Loading quora dataset...")
quora_dataset = load_dataset("sentence-transformers/quora-duplicates", "triplet", split="train")
quora_dataset_dict = quora_dataset.train_test_split(test_size=10_000, seed=12)
quora_train_dataset: Dataset = quora_dataset_dict["train"]
quora_eval_dataset: Dataset = quora_dataset_dict["test"]
print("Loaded quora dataset.")
print("Loading wikianswers duplicates dataset...")
wikianswers_duplicates_dataset = load_dataset("sentence-transformers/wikianswers-duplicates", split="train[:10000000]")
wikianswers_duplicates_dict = wikianswers_duplicates_dataset.train_test_split(test_size=10_000, seed=12)
wikianswers_duplicates_train_dataset: Dataset = wikianswers_duplicates_dict["train"]
wikianswers_duplicates_eval_dataset: Dataset = wikianswers_duplicates_dict["test"]
print("Loaded wikianswers duplicates dataset.")
print("Loading all nli dataset...")
all_nli_train_dataset = load_dataset("sentence-transformers/all-nli", "triplet", split="train")
all_nli_eval_dataset = load_dataset("sentence-transformers/all-nli", "triplet", split="dev")
print("Loaded all nli dataset.")
print("Loading simple wiki dataset...")
simple_wiki_dataset = load_dataset("sentence-transformers/simple-wiki", split="train")
simple_wiki_dataset_dict = simple_wiki_dataset.train_test_split(test_size=10_000, seed=12)
simple_wiki_train_dataset: Dataset = simple_wiki_dataset_dict["train"]
simple_wiki_eval_dataset: Dataset = simple_wiki_dataset_dict["test"]
print("Loaded simple wiki dataset.")
print("Loading altlex dataset...")
altlex_dataset = load_dataset("sentence-transformers/altlex", split="train")
altlex_dataset_dict = altlex_dataset.train_test_split(test_size=10_000, seed=12)
altlex_train_dataset: Dataset = altlex_dataset_dict["train"]
altlex_eval_dataset: Dataset = altlex_dataset_dict["test"]
print("Loaded altlex dataset.")
print("Loading flickr30k captions dataset...")
flickr30k_captions_dataset = load_dataset("sentence-transformers/flickr30k-captions", split="train")
flickr30k_captions_dataset_dict = flickr30k_captions_dataset.train_test_split(test_size=10_000, seed=12)
flickr30k_captions_train_dataset: Dataset = flickr30k_captions_dataset_dict["train"]
flickr30k_captions_eval_dataset: Dataset = flickr30k_captions_dataset_dict["test"]
print("Loaded flickr30k captions dataset.")
print("Loading coco captions dataset...")
coco_captions_dataset = load_dataset("sentence-transformers/coco-captions", split="train")
coco_captions_dataset_dict = coco_captions_dataset.train_test_split(test_size=10_000, seed=12)
coco_captions_train_dataset: Dataset = coco_captions_dataset_dict["train"]
coco_captions_eval_dataset: Dataset = coco_captions_dataset_dict["test"]
print("Loaded coco captions dataset.")
print("Loading nli for simcse dataset...")
nli_for_simcse_dataset = load_dataset("sentence-transformers/nli-for-simcse", "triplet", split="train")
nli_for_simcse_dataset_dict = nli_for_simcse_dataset.train_test_split(test_size=10_000, seed=12)
nli_for_simcse_train_dataset: Dataset = nli_for_simcse_dataset_dict["train"]
nli_for_simcse_eval_dataset: Dataset = nli_for_simcse_dataset_dict["test"]
print("Loaded nli for simcse dataset.")
print("Loading negation dataset...")
negation_dataset = load_dataset("jinaai/negation-dataset", split="train")
negation_dataset_dict = negation_dataset.train_test_split(test_size=100, seed=12)
negation_train_dataset: Dataset = negation_dataset_dict["train"]
negation_eval_dataset: Dataset = negation_dataset_dict["test"]
print("Loaded negation dataset.")
train_dataset = DatasetDict({
"wikititles": wikititles_train_dataset,
"tatoeba": tatoeba_train_dataset,
"talks": talks_train_dataset,
"europarl": europarl_train_dataset,
"global_voices": global_voices_train_dataset,
"jw300": jw300_train_dataset,
"muse": muse_train_dataset,
"wikimatrix": wikimatrix_train_dataset,
"opensubtitles": opensubtitles_train_dataset,
"stackexchange": stackexchange_train_dataset,
"quora": quora_train_dataset,
"wikianswers_duplicates": wikianswers_duplicates_train_dataset,
"all_nli": all_nli_train_dataset,
"simple_wiki": simple_wiki_train_dataset,
"altlex": altlex_train_dataset,
"flickr30k_captions": flickr30k_captions_train_dataset,
"coco_captions": coco_captions_train_dataset,
"nli_for_simcse": nli_for_simcse_train_dataset,
"negation": negation_train_dataset,
})
eval_dataset = DatasetDict({
"wikititles": wikititles_eval_dataset,
"tatoeba": tatoeba_eval_dataset,
"talks": talks_eval_dataset,
"europarl": europarl_eval_dataset,
"global_voices": global_voices_eval_dataset,
"jw300": jw300_eval_dataset,
"muse": muse_eval_dataset,
"wikimatrix": wikimatrix_eval_dataset,
"opensubtitles": opensubtitles_eval_dataset,
"stackexchange": stackexchange_eval_dataset,
"quora": quora_eval_dataset,
"wikianswers_duplicates": wikianswers_duplicates_eval_dataset,
"all_nli": all_nli_eval_dataset,
"simple_wiki": simple_wiki_eval_dataset,
"altlex": altlex_eval_dataset,
"flickr30k_captions": flickr30k_captions_eval_dataset,
"coco_captions": coco_captions_eval_dataset,
"nli_for_simcse": nli_for_simcse_eval_dataset,
"negation": negation_eval_dataset,
})
print(train_dataset)
# 4. Define a loss function
loss = MultipleNegativesRankingLoss(model)
loss = MatryoshkaLoss(model, loss, matryoshka_dims=[32, 64, 128, 256, 512, 1024])
# 5. (Optional) Specify training arguments
run_name = "static-similarity-mrl-multilingual-v1"
args = SentenceTransformerTrainingArguments(
# Required parameter:
output_dir=f"models/{run_name}",
# Optional training parameters:
num_train_epochs=1,
per_device_train_batch_size=2048,
per_device_eval_batch_size=2048,
learning_rate=2e-1,
warmup_ratio=0.1,
fp16=False, # Set to False if you get an error that your GPU can't run on FP16
bf16=True, # Set to True if you have a GPU that supports BF16
batch_sampler=BatchSamplers.NO_DUPLICATES, # MultipleNegativesRankingLoss benefits from no duplicate samples in a batch
multi_dataset_batch_sampler=MultiDatasetBatchSamplers.PROPORTIONAL,
# Optional tracking/debugging parameters:
eval_strategy="steps",
eval_steps=1000,
save_strategy="steps",
save_steps=1000,
save_total_limit=2,
logging_steps=1000,
logging_first_step=True,
run_name=run_name, # Will be used in W&B if `wandb` is installed
)
# 6. Create a trainer & train
trainer = SentenceTransformerTrainer(
model=model,
args=args,
train_dataset=train_dataset,
eval_dataset=eval_dataset,
loss=loss,
)
trainer.train()
# 7. Save the trained model
model.save_pretrained(f"models/{run_name}/final")
# 8. (Optional) Push it to the Hugging Face Hub
model.push_to_hub(run_name, private=True)
if __name__ == "__main__":
main() |