End of training

README.md

@@ -26,16 +26,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9298884840454896
+      value: 0.9398762157382847
     - name: Recall
       type: recall
-      value: 0.9421635529701309
+      value: 0.9513368385725472
     - name: F1
       type: f1
-      value: 0.9359857746165815
+      value: 0.9455718018568967
     - name: Accuracy
       type: accuracy
-      value: 0.985035029469236
+      value: 0.9865442356267972
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -45,11 +45,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the conll2003 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0574
-- Precision: 0.9299
-- Recall: 0.9422
-- F1: 0.9360
-- Accuracy: 0.9850
+- Loss: 0.0727
+- Precision: 0.9399
+- Recall: 0.9513
+- F1: 0.9456
+- Accuracy: 0.9865
 
 ## Model description
 
@@ -74,15 +74,22 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 439  | 0.0743          | 0.8911    | 0.9132 | 0.9020 | 0.9793   |
-| 0.1936        | 2.0   | 878  | 0.0598          | 0.9231    | 0.9367 | 0.9298 | 0.9841   |
-| 0.0507        | 3.0   | 1317 | 0.0574          | 0.9299    | 0.9422 | 0.9360 | 0.9850   |
+| No log        | 1.0   | 439  | 0.0697          | 0.8960    | 0.9187 | 0.9072 | 0.9799   |
+| 0.185         | 2.0   | 878  | 0.0607          | 0.9227    | 0.9384 | 0.9304 | 0.9837   |
+| 0.0471        | 3.0   | 1317 | 0.0560          | 0.9341    | 0.9433 | 0.9387 | 0.9858   |
+| 0.0263        | 4.0   | 1756 | 0.0610          | 0.9300    | 0.9447 | 0.9373 | 0.9853   |
+| 0.0161        | 5.0   | 2195 | 0.0629          | 0.9361    | 0.9516 | 0.9437 | 0.9859   |
+| 0.0112        | 6.0   | 2634 | 0.0676          | 0.9372    | 0.9490 | 0.9431 | 0.9860   |
+| 0.0076        | 7.0   | 3073 | 0.0697          | 0.9348    | 0.9487 | 0.9417 | 0.9859   |
+| 0.0056        | 8.0   | 3512 | 0.0706          | 0.9364    | 0.9497 | 0.9430 | 0.9862   |
+| 0.0056        | 9.0   | 3951 | 0.0719          | 0.9381    | 0.9497 | 0.9439 | 0.9864   |
+| 0.0038        | 10.0  | 4390 | 0.0727          | 0.9399    | 0.9513 | 0.9456 | 0.9865   |
 
 
 ### Framework versions