End of training

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9991846071958415
+      value: 0.9986185030007927
     - name: Recall
       type: recall
-      value: 0.9994449353179727
+      value: 0.9989804934411745
     - name: F1
       type: f1
-      value: 0.9993147543026067
+      value: 0.998799465422339
     - name: Accuracy
       type: accuracy
-      value: 0.9996441930208012
+      value: 0.9994169549500524
 ---
 
 <!-- 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: 0.0011
-- Precision: 0.9992
-- Recall: 0.9994
-- F1: 0.9993
-- Accuracy: 0.9996
+- Loss: 0.0020
+- Precision: 0.9986
+- Recall: 0.9990
+- F1: 0.9988
+- Accuracy: 0.9994
 
 ## Model description
 
@@ -67,7 +67,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 5e-05
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
@@ -79,9 +79,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 486  | 0.0021          | 0.9985    | 0.9984 | 0.9985 | 0.9992   |
-| 0.0018        | 2.0   | 972  | 0.0013          | 0.9989    | 0.9993 | 0.9991 | 0.9995   |
-| 0.0018        | 3.0   | 1458 | 0.0011          | 0.9992    | 0.9994 | 0.9993 | 0.9996   |
+| 0.0068        | 1.03  | 500  | 0.0054          | 0.9976    | 0.9944 | 0.9960 | 0.9980   |
+| 0.0076        | 2.06  | 1000 | 0.0020          | 0.9986    | 0.9990 | 0.9988 | 0.9994   |
 
 
 ### Framework versions