[Assignment 4 Wiki] Incorrect tokenizer output keyword

[vietanh125]

In the training loop code snippet,

loss_function = <create your loss function>
optimizer = <create your optimizer>

for epoch in range(NUM_EPOCHS):
	for batch in dataloader:
		inputs = batch["inputs"]
		gold_outputs = batch["labels"]
		
		predicted_logits = model(inputs)
		batch_loss = loss_function(predicted_logits, gold_outputs)
		
		optimizer.zero_grad()
		batch_loss.backward()
		optimizer.step()

I suppose the keyword for taking inputs from the batch should be input_ids instead of inputs.

[alexanderkoller]

Thank you, I fixed it.