I am trying to do multiclass classification. I am following the HuggingFace sentiment analysis blog from Federico Pascual. When it came to define the metric function I just copied the code from the blog:
import numpy as np
from datasets import load_metric
def compute_metrics(eval_pred):
load_accuracy = load_metric(“accuracy”)
load_f1 = load_metric(“f1”)
logits, labels = eval_pred
predictions = np.argmax(logits, axis=-1)
accuracy = load_accuracy.compute(predictions=predictions, references=labels)[“accuracy”]
f1 = load_f1.compute(predictions=predictions, references=labels)[“f1”]
return {“accuracy”: accuracy, “f1”: f1}
When I run trainer.evaluate() I get this error:
ValueError: Target is multiclass but average=‘binary’. Please choose another average setting, one of [None, ‘micro’, ‘macro’, ‘weighted’].
Then I added the ‘average’ parameter to load_accuracy.compute() and load_f1.compute() and set it to first ‘None’ then ‘weighted’ and both led to same error:
TypeError: _compute() got an unexpected keyword argument ‘average’
You guys have any idea what’s wrong? Thanks in advance