pytorch/examples
在 GitHub 查看Is the loss of the first word covered during the language model evaluation?
Open
#453 创建于 2018年11月26日
good first issuenlp
仓库指标
- Star
- (21,634 star)
- PR 合并指标
- (30 天内没有已合并 PR)
描述
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. https://github.com/pytorch/examples/blob/537f6971872b839b36983ff40dafe688276fe6c3/word_language_model/main.py#L136 https://github.com/pytorch/examples/blob/537f6971872b839b36983ff40dafe688276fe6c3/word_language_model/main.py#L121-L125
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? https://github.com/pytorch/examples/blob/537f6971872b839b36983ff40dafe688276fe6c3/word_language_model/main.py#L85-L88