Update README.md

README.md

@@ -22,27 +22,27 @@ This repository contains a model trained to predict Common European Framework of
 - Model architecture: BERT (base model: `bert-base-...`)
 - Task: CEFR level prediction for text classification
 - Training dataset: CEFR dataset
-- Fine-tuning: Epochs, Loss, Accuracy, etc.
+- Fine-tuning: Epochs, Loss, etc.
 
 ## Performance
 
 The model's performance during training is summarized below:
 
 
-| Epoch | Training Loss | Validation Loss 
-|-------|---------------|-----------------
-| 1     | 0.350600      | 0.400248        
-| 2     | 0.300800      | 0.449286        
-| 3     | 0.218800      | 0.510898        
-| 4     | 0.150300      | 0.599973        
-| 5     | 0.099000      | 0.678500 
+| Epoch | Training Loss | Validation Loss |
+|-------|---------------|-----------------|
+| 1     | 0.412300      | 0.396337        |
+| 2     | 0.369600      | 0.388866        |
+| 3     | 0.298200      | 0.419018        |
+| 4     | 0.214500      | 0.481886        |
+| 5     | 0.148300      | 0.557343        |
 
-Additional metrics:
+--Additional metrics:
 
-- Training Loss: 0.22364403076171874
-- Training Runtime: 5274.6105 seconds
-- Training Samples per Second: 1.303
-- Total Floating Point Operations: 1.4498992298262528e+16
+--Training Loss: 0.2900624789151278
+--Training Runtime: 5168.3962 seconds
+--Training Samples per Second: 10.642
+--Total Floating Point Operations: 1.447162776576e+16
 
 ## Usage