We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
请教一个实验细节
新增参数在 Finetuning 训练中是完全随机初始化的吗?
The text was updated successfully, but these errors were encountered:
@nbcc 用 pytorch 的 nn.Linear 定义的参数,看源码使用 kaiming_uniform_ 做的参数初始化
另外感谢您的认可,期待你们的工作。。现在这个工作缺陷有点多,尤其是速度方面太慢了,整理代码后的实验现在都没跑完
Sorry, something went wrong.
@nbcc 用 pytorch 的 nn.Linear 定义的参数,看源码使用 kaiming_uniform_ 做的参数初始化 另外感谢您的认可,期待你们的工作。。现在这个工作缺陷有点多,尤其是速度方面太慢了,整理代码后的实验现在都没跑完
用 paddle 复现了一下 MWA 策略(基于开源的 ERNIE,在 lcqmc 数据集验证)。和 ERNIE 1.0 论文评估方式一致,采用 max(dev acc) 选取 checkpoint,得到 test acc;多次取平均后,test acc 指标 0.874,结果和 ERNIE 1.0 论文基线接近。。。
请问速度有多慢, 对比bert base
No branches or pull requests
请教一个实验细节
新增参数在 Finetuning 训练中是完全随机初始化的吗?
The text was updated successfully, but these errors were encountered: