File size: 960 Bytes
feb9889 |
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 |
from datasets import load_dataset
from transformers import AutoTokenizer
from transformers import AutoModelForSequenceClassification, TrainingArguments, Trainer
dataset = load_dataset("emotion")
tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased")
def tokenize_function(examples):
return tokenizer(examples["text"], padding="max_length", truncation=True, max_length=128)
tokenized_datasets = dataset.map(tokenize_function, batched=True)
model = AutoModelForSequenceClassification.from_pretrained("distilbert-base-uncased", num_labels=6)
training_args = TrainingArguments(
output_dir="./results",
num_train_epochs=1, # Reduce epochs for faster training
per_device_train_batch_size=8, # Smaller batch size to fit CPU
logging_dir="./logs",
)
trainer = Trainer(
model=model,
args=training_args,
train_dataset=tokenized_datasets["train"],
eval_dataset=tokenized_datasets["validation"]
)
trainer.train()
|