End of training

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9805654698636115
+      value: 0.9814334577809573
     - name: Recall
       type: recall
-      value: 0.9645927116237604
+      value: 0.9663647269885645
     - name: F1
       type: f1
-      value: 0.9725135102144988
+      value: 0.9738408043522868
     - name: Accuracy
       type: accuracy
-      value: 0.9858187365837784
+      value: 0.9864516687615129
 ---
 
 <!-- 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-uncased](https://huggingface.co/distilbert-base-uncased) on the ner dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0454
-- Precision: 0.9806
-- Recall: 0.9646
-- F1: 0.9725
-- Accuracy: 0.9858
+- Loss: 0.0429
+- Precision: 0.9814
+- Recall: 0.9664
+- F1: 0.9738
+- Accuracy: 0.9865
 
 ## Model description
 
@@ -67,9 +67,9 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 32
-- eval_batch_size: 32
+- learning_rate: 4e-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
@@ -79,8 +79,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0831        | 1.17  | 500  | 0.0507          | 0.9756    | 0.9645 | 0.9700 | 0.9845   |
-| 0.0473        | 2.33  | 1000 | 0.0454          | 0.9806    | 0.9646 | 0.9725 | 0.9858   |
+| 0.0981        | 0.58  | 500  | 0.0546          | 0.9699    | 0.9642 | 0.9670 | 0.9829   |
+| 0.0528        | 1.17  | 1000 | 0.0487          | 0.9763    | 0.9649 | 0.9706 | 0.9848   |
+| 0.0485        | 1.75  | 1500 | 0.0462          | 0.9796    | 0.9643 | 0.9719 | 0.9855   |
+| 0.0439        | 2.33  | 2000 | 0.0447          | 0.9795    | 0.9662 | 0.9728 | 0.9859   |
+| 0.0426        | 2.91  | 2500 | 0.0429          | 0.9814    | 0.9664 | 0.9738 | 0.9865   |
 
 
 ### Framework versions