End of training

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.963972882815022
+      value: 0.9779481031086752
     - name: Recall
       type: recall
-      value: 0.9317482110168082
+      value: 0.950199700449326
     - name: F1
       type: f1
-      value: 0.9475866591916392
+      value: 0.96387423507069
     - name: Accuracy
       type: accuracy
-      value: 0.9675355765394335
+      value: 0.977337411889879
 ---
 
 <!-- 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 [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the ner dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0729
-- Precision: 0.9640
-- Recall: 0.9317
-- F1: 0.9476
-- Accuracy: 0.9675
+- Loss: 0.0518
+- Precision: 0.9779
+- Recall: 0.9502
+- F1: 0.9639
+- Accuracy: 0.9773
 
 ## Model description
 
@@ -67,21 +67,23 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 6e-05
+- learning_rate: 1e-05
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 438  | 0.0865          | 0.9568    | 0.9243 | 0.9403 | 0.9632   |
-| 0.0768        | 2.0   | 876  | 0.0794          | 0.9635    | 0.9277 | 0.9452 | 0.9662   |
-| 0.0515        | 3.0   | 1314 | 0.0729          | 0.9640    | 0.9317 | 0.9476 | 0.9675   |
+| No log        | 1.0   | 438  | 0.0725          | 0.9691    | 0.9325 | 0.9505 | 0.9693   |
+| 0.0435        | 2.0   | 876  | 0.0635          | 0.9687    | 0.9392 | 0.9537 | 0.9711   |
+| 0.039         | 3.0   | 1314 | 0.0569          | 0.9790    | 0.9416 | 0.9599 | 0.9751   |
+| 0.0392        | 4.0   | 1752 | 0.0542          | 0.9744    | 0.9490 | 0.9615 | 0.9758   |
+| 0.0378        | 5.0   | 2190 | 0.0518          | 0.9779    | 0.9502 | 0.9639 | 0.9773   |
 
 
 ### Framework versions