Training complete

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9339279814998348
+      value: 0.9317129629629629
     - name: Recall
       type: recall
-      value: 0.9515314708852238
+      value: 0.9483338943116796
     - name: F1
       type: f1
-      value: 0.9426475491830609
+      value: 0.9399499582985822
     - name: Accuracy
       type: accuracy
-      value: 0.9865191028433508
+      value: 0.9858126802849237
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,11 +44,11 @@ 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: 0.0580
-- Precision: 0.9339
-- Recall: 0.9515
-- F1: 0.9426
-- Accuracy: 0.9865
+- Loss: 0.0617
+- Precision: 0.9317
+- Recall: 0.9483
+- F1: 0.9399
+- Accuracy: 0.9858
 
 ## Model description
 
@@ -79,9 +79,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0788        | 1.0   | 1756 | 0.0760          | 0.9137    | 0.9354 | 0.9244 | 0.9801   |
-| 0.0408        | 2.0   | 3512 | 0.0560          | 0.9321    | 0.9497 | 0.9408 | 0.9862   |
-| 0.0261        | 3.0   | 5268 | 0.0580          | 0.9339    | 0.9515 | 0.9426 | 0.9865   |
+| 0.0789        | 1.0   | 1756 | 0.0745          | 0.9112    | 0.9366 | 0.9237 | 0.9802   |
+| 0.0406        | 2.0   | 3512 | 0.0604          | 0.9264    | 0.9487 | 0.9374 | 0.9852   |
+| 0.0256        | 3.0   | 5268 | 0.0617          | 0.9317    | 0.9483 | 0.9399 | 0.9858   |
 
 
 ### Framework versions