Metrics
- loss: 0.6542
- accuracy: 0.8397
- precision: 0.8389
- recall: 0.8397
- precision_macro: 0.7972
- recall_macro: 0.7630
- macro_fpr: 0.0140
- weighted_fpr: 0.0135
- weighted_specificity: 0.9785
- macro_specificity: 0.9879
- weighted_sensitivity: 0.8397
- macro_sensitivity: 0.7630
- f1_micro: 0.8397
- f1_macro: 0.7711
- f1_weighted: 0.8376
- runtime: 23.8413
- samples_per_second: 54.1500
- steps_per_second: 6.7950
UNTRAINED-InLegal-InLegal-legal-merge-ties-d-053-w-050
UNTRAINED-InLegal-InLegal-legal-merge-ties-d-053-w-050 is a merge of the following models using mergekit:
🧩 Configuration
models:
- model: xshubhamx/InLegalBERT
parameters:
density: 0.53
weight: 0.5
- model: xshubhamx/legal-bert-base-uncased
parameters:
density: 0.53
weight: 0.5
merge_method: ties
base_model: xshubhamx/REAL-InLegalBERT
parameters:
normalize: true
int8_mask: true
dtype: float16
- Downloads last month
- 5
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.