MichaelOnly's picture
Update README.md
f4a411a
|
raw
history blame
548 Bytes
---
datasets:
- neurae/dnd_style_intents
language:
- en
pipeline_tag: text-classification
license: apache-2.0
metrics:
- accuracy
- f1
---
This is distilbert base tuned with optimal lr, lr scheduler and weight decay on dnd-style-intents dataset.
| parametrs | value |
|---------------|----------|
| learning rate | 1,8e-4 |
| lr scheduler | linear |
| weight decay | 0 |
Model has next metrics on test data from dataset
| metric | value |
|----------|-------|
| accuracy | 0,985 |
| Macro F1 | 0,984 |
| Micro F1 | 0,985 |