Rewriting structure, added to TODO
This commit is contained in:
10
TODO.md
10
TODO.md
@@ -8,9 +8,19 @@
|
||||
- Maybe more dataset configurations
|
||||
|
||||
|
||||
## Qualify
|
||||
|
||||
- Print stats for a dataset
|
||||
|
||||
## Fine-tune
|
||||
|
||||
- https://www.sbert.net/docs/sentence_transformer/loss_overview.html#loss-table
|
||||
- Use (anchor, positive) pairs to train a new model
|
||||
- Use (sentence) + class labels to train a new model
|
||||
- Implement BatchAllTripletLoss
|
||||
- Implement a two-phase training regime
|
||||
- 1. Train with anchored definitions then...
|
||||
- 2. Train with class labels
|
||||
|
||||
|
||||
## Evaluate
|
||||
|
||||
Reference in New Issue
Block a user