Spaces:
Sleeping
Sleeping
File size: 1,350 Bytes
68ecee6 |
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 |
import torch
print(torch.cuda.is_available())
from transformers import AutoModelForSequenceClassification, AutoTokenizer, Trainer, TrainingArguments
from datasets import load_dataset
# Load the IMDb dataset
dataset = load_dataset('imdb')
# Initialize the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained('distilbert-base-uncased')
model = AutoModelForSequenceClassification.from_pretrained('distilbert-base-uncased', num_labels=2)
# Tokenize the dataset
def tokenize_function(examples):
return tokenizer(examples['text'], padding="max_length", truncation=True)
tokenized_datasets = dataset.map(tokenize_function, batched=True)
# Set up training arguments
training_args = TrainingArguments(
output_dir="./results",
evaluation_strategy="epoch",
learning_rate=2e-5,
per_device_train_batch_size=16,
per_device_eval_batch_size=16,
num_train_epochs=1, # Start with fewer epochs for quicker runs
weight_decay=0.01,
)
# Initialize the Trainer
trainer = Trainer(
model=model,
args=training_args,
train_dataset=tokenized_datasets["train"].shuffle(seed=42).select(range(1000)), # Use a subset for quicker runs
eval_dataset=tokenized_datasets["test"].shuffle(seed=42).select(range(1000)),
)
# Train the model
trainer.train()
# Evaluate the model
results = trainer.evaluate()
print(results)
|