Update README.md

README.md

@@ -7,21 +7,36 @@ tags:
 language:
 - ru
 metrics:
-- name: accuracy
-  type: accuracy
-  value: 66.78
-- name: f1
-  type: f1
-  value: 66.67
-- name: precision
-  type: precision
-  value: 66.67
-- name: recall
-  type: recall
-  value: 66.67
+- accuracy
+- f1
+- precision
+- recall
 base_model:
 - cointegrated/rubert-tiny2
 pipeline_tag: text-classification
+model-index:
+- name: rubert-tiny-nli-terra-v0
+  results:
+  - task:
+      type: text-classification
+      name: Text Classification
+    dataset:
+      name: TERRA
+      type: NLI
+      split: validation
+    metrics:
+    - type: accuracy
+      value: 0.6677524429967426
+      name: Accuracy
+    - type: macro f1
+      value: 0.6666666666666666
+      name: Macro F1
+    - type: macro precision
+      value: 0.6666666666666666
+      name: Macro Precision
+    - type: macro recall
+      value: 0.6666666666666666
+      name: Macro Recall
 ---
 
 **⚠️ Disclaimer: This model is in the early stages of development and may produce low-quality predictions. For better results, consider using the recommended Russian natural language inference models available [here](https://huggingface.co/cointegrated).**
@@ -72,15 +87,15 @@ print({v: p[k] for k, v in model.config.id2label.items()})
 
 The following metrics summarize the performance of the model on the test dataset:
 
-| Metric                     | Value                     |
-|----------------------------|---------------------------|
-| **Test Loss**              | 0.6261                    |
-| **Test Accuracy**          | 66.78%                    |
-| **Test F1 Score**          | 66.67%                    |
-| **Test Precision**         | 66.67%                    |
-| **Test Recall**            | 66.67%                    |
-| **Test Runtime***          | 0.7043 seconds            |
-| **Samples per Second***    | 435.88                    |
-| **Steps per Second***      | 14.20                     |
+| Metric                           | Value                     |
+|----------------------------------|---------------------------|
+| **Validation Loss**              | 0.6261                    |
+| **Validation Accuracy**          | 66.78%                    |
+| **Validation F1 Score**          | 66.67%                    |
+| **Validation Precision**         | 66.67%                    |
+| **Validation Recall**            | 66.67%                    |
+| **Validation Runtime***          | 0.7043 seconds            |
+| **Samples per Second***          | 435.88                    |
+| **Steps per Second***            | 14.20                     |
 
 *Using T4 GPU with Google Colab