File size: 1,327 Bytes
42cc6ec |
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 |
# train.py
import numpy as np
from transformers import Trainer, TrainingArguments, AutoModelForSequenceClassification, AutoTokenizer
from datasets import load_dataset
# Constants
MODEL_NAME = 'distilbert-base-uncased'
OUTPUT_DIR = './model_output'
EPOCHS = 3
BATCH_SIZE = 16
LEARNING_RATE = 5e-5
# Load dataset (example: IMDb sentiment analysis dataset)
dataset = load_dataset('imdb')
# Load tokenizer
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
# Preprocess data
def preprocess_function(examples):
return tokenizer(examples['text'], truncation=True)
tokenized_datasets = dataset.map(preprocess_function, batched=True)
# Load model
model = AutoModelForSequenceClassification.from_pretrained(MODEL_NAME, num_labels=2)
# Define training arguments
training_args = TrainingArguments(
output_dir=OUTPUT_DIR,
evaluation_strategy="epoch",
learning_rate=LEARNING_RATE,
per_device_train_batch_size=BATCH_SIZE,
per_device_eval_batch_size=BATCH_SIZE,
num_train_epochs=EPOCHS,
weight_decay=0.01,
)
# Create Trainer
trainer = Trainer(
model=model,
args=training_args,
train_dataset=tokenized_datasets['train'],
eval_dataset=tokenized_datasets['test'],
)
# Train the model
trainer.train()
# Save the model
trainer.save_model(OUTPUT_DIR)
print("Model trained and saved!")
|