Skip to content

Commit

Permalink
Merge pull request #448 from wangzhen38/wz38-stuff
Browse files Browse the repository at this point in the history
update readme
  • Loading branch information
frankwhzhang authored May 19, 2021
2 parents 7bcd9ec + 84c8887 commit bf62d6d
Show file tree
Hide file tree
Showing 2 changed files with 2 additions and 2 deletions.
2 changes: 1 addition & 1 deletion models/multitask/esmm/readme.md
Original file line number Diff line number Diff line change
Expand Up @@ -78,7 +78,7 @@ ESMM是发表在 SIGIR’2018 的论文[《Entire Space Multi-Task Model: An E
### 效果复现
为了方便使用者能够快速的跑通每一个模型,我们在每个模型下都提供了样例数据。如果需要复现readme中的效果,请按如下步骤依次操作即可。
在全量数据下模型的训练指标如下:
| 模型 | auc_ctcvr | batch_size | epoch_num | Time of each epoch |
| 模型 | auc_ctr | batch_size | epoch_num | Time of each epoch |
| :------| :------ | :------ | :------| :------ |
| ESMM | 0.82 | 1024 | 10 | 约3分钟 |

Expand Down
2 changes: 1 addition & 1 deletion models/rank/logistic_regression/readme.md
Original file line number Diff line number Diff line change
Expand Up @@ -100,7 +100,7 @@ logistic_regression模型的组网比较直观,本质是一个二分类任务

| 模型 | auc | batch_size | epoch_num| Time of each epoch |
| :------| :------ | :------ | :------| :------ |
| LR | 0.67 | 1024 | 2 | 约30分钟 |
| LR | 0.77+ | 1024 | 2 | 约30分钟 |

1. 确认您当前所在目录为PaddleRec/models/rank/logistic_regression
2. 进入paddlerec/datasets/criteo_lr目录下,执行该脚本,会从国内源的服务器上下载我们预处理完成的criteo全量数据集,并解压到指定文件夹。
Expand Down

0 comments on commit bf62d6d

Please sign in to comment.