Getting the following error when running trainer.train()
ValueError: You have to specify either input_ids or inputs_embeds
Here is my trainer
trainer = Trainer(
model=model,
args=training_args,
train_dataset=train_test_valid_dataset[“train”],
eval_dataset=train_test_valid_dataset[“test”],
compute_metrics=compute_metrics
)
Using the AutoTkenizer
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(“distilbert-base-uncased”)
def tokenize_function(examples):
return tokenizer(examples[“title”], padding=“max_length”, truncation=True)
tokenized_datasets = train_test_valid_dataset.map(tokenize_function, batched=True)
Can someone help out here ?