Document how to finetune pretrained model on downstream task

Clay-foundation / model

The Clay Foundation Model (in development)

https://clay-foundation.github.io/model/

Apache License 2.0

299 stars 38 forks source link

Document how to finetune pretrained model on downstream task #99

Closed weiji14 closed 8 months ago

weiji14 commented 8 months ago

Explaining how the pre-trained model can be finetuned after attaching a head to the network.

Opening this PR on behalf of @lillythomas who did the actual work and who wrote the original Jupyter notebook. The Jupyter Notebook has been converted to Markdown for easier visibilty on GitHub.

Screenshot:

Part of #90.

lillythomas commented 8 months ago

Oops I made one more typo:

"Here's a peak at the decoder layers:"

Peak should be peek

otherwise, feel free to merge when you're ready!

weiji14 commented 8 months ago

Was a few seconds away from clicking that merge button. Good catch!

weiji14 commented 8 months ago

Oops, there was typo in the PR title, oh well :laughing: