Is the loss of the first word covered during the language model evaluation?

[khassanoff]

In the language model example, it seems that during the evaluation, the code starts from computing the loss of the second word. Thus, skipping the loss of the first word.

examples/word_language_model/main.py

Line 136 in 537f697

data, targets = get_batch(data_source, i)

examples/word_language_model/main.py

Lines 121 to 125 in 537f697

	def get_batch(source, i):
	seq_len = min(args.bptt, len(source) - 1 - i)
	data = source[i:i+seq_len]
	target = source[i+1:i+1+seq_len].view(-1)
	return data, target

Furthermore, the evaluation data is divided into 10 batches, hence, the losses of 10 words are skipped.
Am I right or I did miss something?

examples/word_language_model/main.py

Lines 85 to 88 in 537f697

	eval_batch_size = 10
	train_data = batchify(corpus.train, args.batch_size)
	val_data = batchify(corpus.valid, eval_batch_size)
	test_data = batchify(corpus.test, eval_batch_size)