Spaces:
Sleeping
Sleeping
File size: 1,409 Bytes
fb042ae |
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 |
# Import Hugging Face libraries and datasets
from transformers import Trainer, TrainingArguments, BertForSequenceClassification, BertTokenizer
from datasets import load_dataset
# Load dataset
dataset = load_dataset("imdb")
# Preprocess data: Tokenizer
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
def tokenize_function(examples):
return tokenizer(examples['text'], padding='max_length', truncation=True)
# Apply tokenization
tokenized_datasets = dataset.map(tokenize_function, batched=True)
# Load pre-trained model
model = BertForSequenceClassification.from_pretrained('bert-base-uncased', num_labels=2)
# Training Arguments
training_args = TrainingArguments(
output_dir='/results', # Save path in the Space environment
evaluation_strategy="epoch", # Eval after each epoch
learning_rate=2e-5, # Learning rate
per_device_train_batch_size=8, # Training batch size
per_device_eval_batch_size=8, # Eval batch size
num_train_epochs=3, # Number of epochs
weight_decay=0.01 # Weight decay for regularization
)
# Trainer setup
trainer = Trainer(
model=model,
args=training_args,
train_dataset=tokenized_datasets["train"],
eval_dataset=tokenized_datasets["test"]
)
# Train the model (this will run in the cloud, no need for local machine)
trainer.train()
|