BERT, or Bidirectional Encoder Representations from Transformers, improves upon standard Transformers by removing the unidirectionality constraint by using a masked language model (MLM) pre-training objective. The masked language model randomly masks some of the tokens from the input, and the objective is to predict the original vocabulary id of the masked word based only on its context. Unlike left-to-right language model pre-training, the MLM objective enables the representation to fuse the left and the right context, which allows us to pre-train a deep bidirectional Transformer. In addition to the masked language model, BERT uses a next sentence prediction task that jointly pre-trains text-pair representations.
bash init_tf.sh
This Google Drive location contains the following.
You need to download tf1_ckpt folde , vocab.txt and bert_config.json into one file named bert_pretrain_ckpt_tf
bert_pretrain_ckpt_tf: contains checkpoint files
model.ckpt-28252.data-00000-of-00001
model.ckpt-28252.index
model.ckpt-28252.meta
vocab.txt
bert_config.json
Download and preprocess datasets You need to make a file named bert_pretrain_tf_records and store the results above. tips: you can git clone this repo in other place ,we need the bert_pretrain_tf_records results here.
bash run_1card_FPS.sh
bash run_multi_card_FPS.sh
acc | fps | |
---|---|---|
multi_card | 0.424126 | 0.267241 |
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。