File size: 2,056 Bytes
109c4d7 |
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 56 57 58 59 60 61 62 63 64 65 |
# Install required packages before running:
# pip install torch transformers datasets evaluate safetensors
import torch
from datasets import load_dataset
from transformers import AutoTokenizer, AutoModelForSequenceClassification, TrainingArguments, Trainer
import evaluate
# 1️⃣ Load Dataset
dataset = load_dataset("imdb")
# 2️⃣ Tokenizer
model_name = "distilbert-base-uncased"
tokenizer = AutoTokenizer.from_pretrained(model_name)
def tokenize_fn(batch):
return tokenizer(batch["text"], truncation=True, padding="max_length", max_length=256)
tokenized_datasets = dataset.map(tokenize_fn, batched=True)
# 3️⃣ Load Model
model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=2)
# 4️⃣ Evaluation metric
accuracy = evaluate.load("accuracy")
def compute_metrics(eval_pred):
logits, labels = eval_pred
predictions = torch.argmax(torch.tensor(logits), dim=-1)
return accuracy.compute(predictions=predictions, references=labels)
# 5️⃣ Training Arguments
training_args = TrainingArguments(
output_dir="./results",
evaluation_strategy="epoch",
save_strategy="epoch",
logging_dir="./logs",
learning_rate=2e-5,
per_device_train_batch_size=8,
per_device_eval_batch_size=8,
num_train_epochs=1,
weight_decay=0.01,
push_to_hub=False,
save_safetensors=True # 🔹 Save model in safetensors format
)
# 6️⃣ Trainer
trainer = Trainer(
model=model,
args=training_args,
train_dataset=tokenized_datasets["train"].shuffle(seed=42).select(range(2000)), # small subset
eval_dataset=tokenized_datasets["test"].shuffle(seed=42).select(range(500)), # small subset
tokenizer=tokenizer,
compute_metrics=compute_metrics
)
# 7️⃣ Train Model
trainer.train()
# 8️⃣ Save final model in safetensors
trainer.save_model("./final_safetensors_model") # saves as model.safetensors
tokenizer.save_pretrained("./final_safetensors_model")
print("✅ Training complete. Model saved in safetensors format at './final_safetensors_model'")
|