search

facebookresearch / dpr-scale

Scalable training for dense retrieval models.
262 stars 25 forks source link

Fix minor bugs #15

Closed jacklin64 closed 1 year ago

jacklin64 commented 1 year ago

This PR aims to fix two bugs:

  1. The gpu_1_host trainer used in the msmarco baseline training set max_step 500. @alexlimh pointed out it may cause error after training 500 steps. Maybe we should set it to null?
  2. As pointed out by @Freddavide in the #14, the root cause is that some titles in BEIR original dataset contains "\t" or "\n", which may cause error in the transformed format. So we want to remove "\t" or "\n" in the title.
facebook-github-bot commented 1 year ago

Hi @jacklin64!

Thank you for your pull request.

We require contributors to sign our Contributor License Agreement, and yours needs attention.

You currently have a record in our system, but the CLA is no longer valid, and will need to be resubmitted.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks!