File size: 1,113 Bytes
87d2a20 cfa4fa0 87d2a20 cfa4fa0 87d2a20 |
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 |
from datasets import load_dataset
from transformers import BertForSequenceClassification, Trainer, TrainingArguments
from transformers import BertTokenizer
# Load the dataset
dataset = load_dataset('csv', data_files='dataset.csv')
# Load the tokenizer
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
# Tokenize the dataset
def tokenize_function(examples):
return tokenizer(examples['question'], padding="max_length", truncation=True)
tokenized_datasets = dataset.map(tokenize_function, batched=True)
# Load the model
model = BertForSequenceClassification.from_pretrained('bert-base-uncased', num_labels=1)
# Define training arguments
training_args = TrainingArguments(
output_dir="./results",
evaluation_strategy="epoch",
learning_rate=2e-3,
per_device_train_batch_size=8,
per_device_eval_batch_size=8,
num_train_epochs=10,
weight_decay=0.01,
)
# Create Trainer instance
trainer = Trainer(
model=model,
args=training_args,
train_dataset=tokenized_datasets['train'],
eval_dataset=tokenized_datasets['test']
)
# Train the model
trainer.train()
|