The model did not return a loss from the inputs, only the following keys: logits. For reference, the inputs it received are input_values

Intermediate
2

Edit: fixed for me by changing BertModel to BertForSequenceClassification.

I’m getting the same error, also following the tutorials in the course, chapter 3: Fine-tuning a model with the Trainer API - Hugging Face Course.

My code:

import evaluate
import numpy as np
from datasets import load_dataset
from transformers import (
    BertModel,
    BertTokenizerFast,
    TrainingArguments,
    Trainer,
    EvalPrediction,
)

checkpoint = "bert-base-uncased"
model = BertModel.from_pretrained(checkpoint)
tokenizer = BertTokenizerFast.from_pretrained(checkpoint)
raw_ds = load_dataset("glue", "mrpc")
metric = evaluate.load("glue", "mrpc")

dataset = raw_ds.map(
    lambda x: tokenizer(x["sentence1"], x["sentence2"], truncation=True),
    batched=True,
)
dataset = dataset.remove_columns(["sentence1", "sentence2", "idx"])
dataset = dataset.rename_column("label", "labels")
dataset = dataset.with_format("torch")

trainer_args = TrainingArguments("test-trainer", evaluation_strategy="epoch")


def compute_metrics(eval_preds: EvalPrediction):
    x, y = eval_preds
    preds = np.argmax(x, -1)
    return metric.compute(predictions=preds, references=y)


trainer = Trainer(
    model=model,
    args=trainer_args,
    train_dataset=dataset["train"],
    eval_dataset=dataset["validation"],
    tokenizer=tokenizer,
    compute_metrics=compute_metrics,
)

trainer.train()
3 Likes