Training completed!

README.md

@@ -26,7 +26,7 @@ model-index:
       value: 0.9275
     - name: F1
       type: f1
-      value: 0.9273639380542699
+      value: 0.9275296202470541
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -36,9 +36,9 @@ 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 emotion dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2153
+- Loss: 0.2122
 - Accuracy: 0.9275
-- F1: 0.9274
+- F1: 0.9275
 
 ## Model description
 
@@ -69,8 +69,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.8711        | 1.0   | 250  | 0.3211          | 0.905    | 0.9033 |
-| 0.2572        | 2.0   | 500  | 0.2153          | 0.9275   | 0.9274 |
+| 0.7877        | 1.0   | 250  | 0.2995          | 0.9125   | 0.9118 |
+| 0.2429        | 2.0   | 500  | 0.2122          | 0.9275   | 0.9275 |
 
 
 ### Framework versions