Parlai: will you give the best scripts to train the typical model such as seq2seq or transformer on each task/dataset in the ParlAI?

[zhaoguangxiang]

In my view, this can facilitate the research of dialogue systems.

[stephenroller]

Hi @zhaoguangxiang. One goal we have in the next few weeks is to actively beef up our model zoo. These models will come with the hyperparameters used to train them.

[jaseweston]

Yes, the goal is to have in parlai/projects tracking of best efforts on
these tasks.
For convai2 for example we have this here:
https://github.com/facebookresearch/ParlAI/tree/master/projects/convai2
As Stephen says we do have things we are going to release into the model
zoo soon.
Note that this is also a community effort, where others can check in their
best models, as there are many tasks...

On Wed, Feb 20, 2019 at 9:24 AM Stephen Roller [e-mail]
wrote:

Hi @zhaoguangxiang https://github.com/zhaoguangxiang. One goal we have
in the next few weeks is to actively beef up our model zoo. These models
will come with the hyperparameters used to train them.

—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
https://github.com/facebookresearch/ParlAI/issues/1468#issuecomment-465596555,
or mute the thread
https://github.com/notifications/unsubscribe-auth/AKjk-L_3U6ADsUXVF15zUi4KihZ2yCKpks5vPVqxgaJpZM4bFHHC
.

[stephenroller]

Hi @zhaoguangxiang. While the zoo is never fully complete, there are some improvements from last week. Most of these have the training scripts available.

[stephenroller]

(Feel free to reopen for specific requests or additional questions)

[JohannesTK]

Have you thought of having different hyperparameters sets like Tensor2Tensor? I.e. transformer_base, transformer_tiny, etc. Feels like this would vastly speed up the experimentation and training on new datasets because it would take out a lot of the guessing game.