andreaceto
/

schedulebot-nlu-engine

Generated from Trainer

Model card Files Files and versions

Metrics Training metrics Community

andreaceto commited on Jul 17, 2025

Commit

2909bed

·

verified ·

1 Parent(s): 2db8f9e

Update README.md

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -172,9 +172,9 @@ The model was evaluated on a held-out test set, and its performance was measured
 |    reschedule | 0.8571    | 0.8675 | 0.8623   | 83       |
 |      schedule | 0.8506    | 0.9250 | 0.8862   | 80       |
 | ---           | ---       | ---    | ---      | ----     |
-| **Accuracy**     |               |            | **0.8884**   | 439      |
-| **Macro Avg**    |    **0.8992** | **0.8837** | **0.8887**   | 439      |
-| **Weighted Avg** |    **0.8923** | **0.8884** | **0.8887**   | 439      |
 ### NER (Token Classification) Performance
@@ -185,9 +185,9 @@ The model was evaluated on a held-out test set, and its performance was measured
 | B-practitioner_name | 0.9540    | 0.9210 | 0.9372   | 405      |
 | O                   | 0.9775    | 0.9908 | 0.9841   | 3813     |
 | ---                 | ---       | ---    | ---      | ----     |
-| **Accuracy**        |           |        | 0.9711   | 4771     |
-| **Macro Avg**       | 0.9500    | 0.9147 | 0.9315   | 4771     |
-| **Weighted Avg**    | 0.9703    | 0.9711 | 0.9705   | 4771     |
 The model achieves near-perfect results on the NER task and excellent results on the intent classification task for this specific dataset.

 |    reschedule | 0.8571    | 0.8675 | 0.8623   | 83       |
 |      schedule | 0.8506    | 0.9250 | 0.8862   | 80       |
 | ---           | ---       | ---    | ---      | ----     |
+| **Accuracy**     |               |            | **0.8884**   | 439 |
+| **Macro Avg**    |    **0.8992** | **0.8837** | **0.8887**   | 439 |
+| **Weighted Avg** |    **0.8923** | **0.8884** | **0.8887**   | 439 |
 ### NER (Token Classification) Performance
 | B-practitioner_name | 0.9540    | 0.9210 | 0.9372   | 405      |
 | O                   | 0.9775    | 0.9908 | 0.9841   | 3813     |
 | ---                 | ---       | ---    | ---      | ----     |
+| **Accuracy**        |            |            | **0.9711** | 4771 |
+| **Macro Avg**       | **0.9500** | **0.9147** | **0.9315** | 4771 |
+| **Weighted Avg**    | **0.9703** | **0.9711** | **0.9705** | 4771 |
 The model achieves near-perfect results on the NER task and excellent results on the intent classification task for this specific dataset.