#### /print debug information to stdout
# Read the dataset
train_batch_size = 16
num_epochs = 4
model_save_path = 'output/training_stsbenchmark_roberta-' + datetime.now(
).strftime("%Y-%m-%d_%H-%M-%S")
sts_reader = STSDataReader('datasets/stsbenchmark', normalize_scores=True)
# Use XLNet for mapping tokens to embeddings
word_embedding_model = models.RoBERTa('roberta-base')
# Apply mean pooling to get one fixed sized sentence vector
pooling_model = models.Pooling(
word_embedding_model.get_word_embedding_dimension(),
pooling_mode_mean_tokens=True,
pooling_mode_cls_token=False,
pooling_mode_max_tokens=False)
model = SentenceTransformer(modules=[word_embedding_model, pooling_model])
# Convert the dataset to a DataLoader ready for training
logging.info("Read STSbenchmark train dataset")
train_data = SentencesDataset(sts_reader.get_examples('sts-train.csv'), model)
train_dataloader = DataLoader(train_data,
shuffle=True,
batch_size=train_batch_size)
train_loss = losses.CosineSimilarityLoss(model=model)
logging.info("Read STSbenchmark dev dataset")
dev_data = SentencesDataset(examples=sts_reader.get_examples('sts-dev.csv'),
level=logging.INFO,
handlers=[LoggingHandler()])
#### /print debug information to stdout
# Read the dataset
train_batch_size = 16
num_epochs = 4
model_save_path = 'output/training_stsbenchmark_bert-'+datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
sts_reader = STSDataReader('datasets/stsbenchmark', normalize_scores=True)
# Use BERT for mapping tokens to embeddings
word_embedding_model = models.BERT('bert-base-uncased')
# Apply mean pooling to get one fixed sized sentence vector
pooling_model = models.Pooling(word_embedding_model.get_word_embedding_dimension(),
pooling_mode_mean_tokens=False,
pooling_mode_first_k_token=False)
model = SentenceTransformer(modules=[word_embedding_model, pooling_model])
# Convert the dataset to a DataLoader ready for training
logging.info("Read STSbenchmark train dataset")
train_data = SentencesDataset(sts_reader.get_examples('sts-train.csv'), model)
train_dataloader = DataLoader(train_data, shuffle=True, batch_size=train_batch_size)
train_loss = losses.CosineSimilarityLoss(model=model)
logging.info("Read STSbenchmark dev dataset")
dev_data = SentencesDataset(examples=sts_reader.get_examples('sts-dev.csv'), model=model)
dev_dataloader = DataLoader(dev_data, shuffle=False, batch_size=train_batch_size)
evaluator = EmbeddingSimilarityEvaluator(dev_dataloader)