End of training

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9610619087637641
+      value: 0.9825882454474842
     - name: Recall
       type: recall
-      value: 0.927775004160426
+      value: 0.9473498086204027
     - name: F1
       type: f1
-      value: 0.9441251495041227
+      value: 0.9646473204829485
     - name: Accuracy
       type: accuracy
-      value: 0.9654874318393404
+      value: 0.9779358957308153
 ---
 
 <!-- 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-uncased](https://huggingface.co/bert-base-uncased) on the ner dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0821
-- Precision: 0.9611
-- Recall: 0.9278
-- F1: 0.9441
-- Accuracy: 0.9655
+- Loss: 0.0525
+- Precision: 0.9826
+- Recall: 0.9473
+- F1: 0.9646
+- Accuracy: 0.9779
 
 ## Model description
 
@@ -67,20 +67,23 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 5e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0979        | 1.0   | 875  | 0.0852          | 0.9602    | 0.9262 | 0.9429 | 0.9648   |
-| 0.0549        | 2.0   | 1750 | 0.0821          | 0.9611    | 0.9278 | 0.9441 | 0.9655   |
+| 0.0568        | 1.0   | 875  | 0.0813          | 0.9641    | 0.9244 | 0.9438 | 0.9655   |
+| 0.0524        | 2.0   | 1750 | 0.0784          | 0.9619    | 0.9283 | 0.9448 | 0.9660   |
+| 0.0481        | 3.0   | 2625 | 0.0719          | 0.9684    | 0.9301 | 0.9489 | 0.9685   |
+| 0.0449        | 4.0   | 3500 | 0.0621          | 0.9736    | 0.9428 | 0.9579 | 0.9738   |
+| 0.0384        | 5.0   | 4375 | 0.0525          | 0.9826    | 0.9473 | 0.9646 | 0.9779   |
 
 
 ### Framework versions