End of training

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9269461077844311
+      value: 0.9994683935820607
     - name: Recall
       type: recall
-      value: 0.9381818181818182
+      value: 0.999371798588963
     - name: F1
       type: f1
-      value: 0.9325301204819277
+      value: 0.9994200937515101
     - name: Accuracy
       type: accuracy
-      value: 0.9986404599129894
+      value: 0.9998144414067816
 ---
 
 <!-- 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: 0.0067
-- Precision: 0.9269
-- Recall: 0.9382
-- F1: 0.9325
-- Accuracy: 0.9986
+- Loss: 0.0018
+- Precision: 0.9995
+- Recall: 0.9994
+- F1: 0.9994
+- Accuracy: 0.9998
 
 ## Model description
 
@@ -79,11 +79,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 63   | 0.0500          | 0.8048    | 0.4097 | 0.5430 | 0.9883   |
-| No log        | 2.0   | 126  | 0.0305          | 0.8104    | 0.7564 | 0.7824 | 0.9936   |
-| No log        | 3.0   | 189  | 0.0136          | 0.8643    | 0.8412 | 0.8526 | 0.9965   |
-| No log        | 4.0   | 252  | 0.0089          | 0.8571    | 0.9164 | 0.8858 | 0.9976   |
-| No log        | 5.0   | 315  | 0.0067          | 0.9269    | 0.9382 | 0.9325 | 0.9986   |
+| 0.1459        | 1.0   | 533  | 0.0584          | 0.9602    | 0.9620 | 0.9611 | 0.9876   |
+| 0.0546        | 2.0   | 1066 | 0.0237          | 0.9866    | 0.9866 | 0.9866 | 0.9957   |
+| 0.025         | 3.0   | 1599 | 0.0080          | 0.9967    | 0.9945 | 0.9956 | 0.9985   |
+| 0.0116        | 4.0   | 2132 | 0.0040          | 0.9980    | 0.9979 | 0.9980 | 0.9994   |
+| 0.0058        | 5.0   | 2665 | 0.0018          | 0.9995    | 0.9994 | 0.9994 | 0.9998   |
 
 
 ### Framework versions