# load metrics
accuracy = evaluate.load("accuracy")
auc_score = evaluate.load("roc_auc")

def compute_metrics(eval_pred):
    # get predictions
    predictions, labels = eval_pred

    # apply softmax to get probabilities
    probabilities = np.exp(predictions) / np.exp(predictions).sum(-1, 
                                                                 keepdims=True)
    # use probabilities of the positive class for ROC AUC
    positive_class_probs = probabilities[:, 1]
    # compute auc
    auc = np.round(auc_score.compute(prediction_scores=positive_class_probs, 
                                     references=labels)['roc_auc'],3)

    # predict most probable class
    predicted_classes = np.argmax(predictions, axis=1)
    # compute accuracy
    acc = np.round(accuracy.compute(predictions=predicted_classes, 
                                     references=labels)['accuracy'],3)

    return {"Accuracy": acc, "AUC": auc}