Edit model card

Model Trained Using AutoTrain

  • Problem type: Text Classification
  • Task: Legal Document Sequence Classification w/ bert-base-multilingual-cased
  • id2label: [0: 'Caption', 1: 'Footnote', 2: 'Formula', 3: 'List-item', 4: 'Page-footer', 5: 'Page-header', 6: 'Picture', 7: 'Section-header', 8: 'Table', 9: 'Text', 10: 'Title']
  • sample usage notebook here

Validation Metrics

loss: 0.5102838277816772

f1_macro: 0.605011586308457

f1_micro: 0.8910038281582305

f1_weighted: 0.8870714364293508

precision_macro: 0.6869883411452264

precision_micro: 0.8910038281582305

precision_weighted: 0.8858066104824025

recall_macro: 0.5550753643871188

recall_micro: 0.8910038281582305

recall_weighted: 0.8910038281582305

accuracy: 0.8910038281582305

Downloads last month
9
Safetensors
Model size
178M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train pruhtopia/bert-toc-classification-95k