End of training

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.5721739130434783
+      value: 0.5975820379965457
     - name: Recall
       type: recall
-      value: 0.3049119555143652
+      value: 0.3206672845227062
     - name: F1
       type: f1
-      value: 0.39782345828295046
+      value: 0.4173703256936067
     - name: Accuracy
       type: accuracy
-      value: 0.9421999914497029
+      value: 0.9423709973921593
 ---
 
 <!-- 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 wnut_17 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2734
-- Precision: 0.5722
-- Recall: 0.3049
-- F1: 0.3978
-- Accuracy: 0.9422
+- Loss: 0.2763
+- Precision: 0.5976
+- Recall: 0.3207
+- F1: 0.4174
+- Accuracy: 0.9424
 
 ## Model description
 
@@ -79,8 +79,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 213  | 0.2771          | 0.5809    | 0.2530 | 0.3525 | 0.9393   |
-| No log        | 2.0   | 426  | 0.2734          | 0.5722    | 0.3049 | 0.3978 | 0.9422   |
+| No log        | 1.0   | 213  | 0.2865          | 0.6141    | 0.2419 | 0.3471 | 0.9389   |
+| No log        | 2.0   | 426  | 0.2763          | 0.5976    | 0.3207 | 0.4174 | 0.9424   |
 
 
 ### Framework versions