script/train.py

import pandas as pd
from datasets import Dataset
from transformers import (
    AutoTokenizer,
    AutoModelForSequenceClassification,
    TrainingArguments,
    Trainer
)
import torch
import numpy as np
from sklearn.metrics import accuracy_score, f1_score

# Load CSV
df = pd.read_csv("./../data/text.csv")
dataset = Dataset.from_pandas(df)

#Tokenizer & model (DistilBERT architecture)
model_name = "distilbert-base-uncased"
tokenizer = AutoTokenizer.from_pretrained(model_name)

def tokenize(batch):
    return tokenizer(batch["text"], padding=True, truncation=True)

dataset = dataset.map(tokenize, batched=True)
dataset = dataset.rename_column("label", "labels")
dataset.set_format("torch", columns=["input_ids", "attention_mask", "labels"])
train_test = dataset.train_test_split(test_size=0.2)

#Model
model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=2)

#Metrics
def compute_metrics(eval_pred):
    logits, labels = eval_pred
    preds = np.argmax(logits, axis=-1)
    return {
        "accuracy": accuracy_score(labels, preds),
        "f1": f1_score(labels, preds),
    }

#TrainingArguments
training_args = TrainingArguments(
    output_dir="./results",
    num_train_epochs=3,
    per_device_train_batch_size=16,
    per_device_eval_batch_size=16,
    evaluation_strategy="epoch",
    logging_dir="./logs",
    save_strategy="epoch",
)

#Trainer
trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=train_test["train"],
    eval_dataset=train_test["test"],
    compute_metrics=compute_metrics,
    tokenizer=tokenizer,
)

#Train
trainer.train()

#Save
model.save_pretrained("PigeonAIModel1")
tokenizer.save_pretrained("PigeonAIModel1")