Training complete

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9337967560410461
+      value: 0.9327828241123038
     - name: Recall
       type: recall
-      value: 0.9495119488387749
+      value: 0.9505217098619994
     - name: F1
       type: f1
-      value: 0.941588785046729
+      value: 0.9415687255147119
     - name: Accuracy
       type: accuracy
-      value: 0.9864308000235474
+      value: 0.9863572143403779
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,9 +44,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0619
-- Precision: 0.9338
-- Recall: 0.9495
+- Loss: 0.0620
+- Precision: 0.9328
+- Recall: 0.9505
 - F1: 0.9416
 - Accuracy: 0.9864
 
@@ -79,9 +79,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0761        | 1.0   | 1756 | 0.0650          | 0.9078    | 0.9374 | 0.9223 | 0.9826   |
-| 0.0341        | 2.0   | 3512 | 0.0708          | 0.9317    | 0.9463 | 0.9390 | 0.9852   |
-| 0.0208        | 3.0   | 5268 | 0.0619          | 0.9338    | 0.9495 | 0.9416 | 0.9864   |
+| 0.0767        | 1.0   | 1756 | 0.0664          | 0.8984    | 0.9327 | 0.9152 | 0.9822   |
+| 0.036         | 2.0   | 3512 | 0.0679          | 0.9271    | 0.9456 | 0.9363 | 0.9845   |
+| 0.0228        | 3.0   | 5268 | 0.0620          | 0.9328    | 0.9505 | 0.9416 | 0.9864   |
 
 
 ### Framework versions