Runqi Yang

F1 和AUC只能用于二分类任务

@zy614582280 亲，我们暂不提供开源数据集之外的技术支持哦~

A single V100(32G) can run this experiment. For a 16GB GPU, in my previous runs setting the batch size to 488 leads to similar results. Decreasing batch size to 64...

Sorry for the late reply....

Something like `sum(p.numel() for p in model.parameters() if p.requires_grad)`

What's your tensorflow version?

It seems like some APIs are not working. A way to temporarily solve this is to specify the checkpoint by the exact step, like "./models/quora/benchmark-4/checkpoint-37500". You can find your best...

感谢反馈🙏

谢谢你的建议

You should set "eval_file" to "test" (like what "main.json5" does), which evaluates the test set directly in each evaluation during training. This is not what we should do in production,...