End of training

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6611
-- Accuracy: 0.8062
+- Loss: 0.6888
+- Accuracy: 0.7907
 
 ## Model description
 
@@ -43,15 +43,19 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 7
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 64   | 0.7525          | 0.7907   |
-| No log        | 2.0   | 128  | 0.6659          | 0.8101   |
-| No log        | 3.0   | 192  | 0.6611          | 0.8062   |
+| No log        | 1.0   | 64   | 1.9924          | 0.3295   |
+| No log        | 2.0   | 128  | 1.4201          | 0.5698   |
+| No log        | 3.0   | 192  | 1.1120          | 0.6783   |
+| No log        | 4.0   | 256  | 0.8929          | 0.7403   |
+| No log        | 5.0   | 320  | 0.7634          | 0.7713   |
+| No log        | 6.0   | 384  | 0.7063          | 0.7713   |
+| No log        | 7.0   | 448  | 0.6888          | 0.7907   |
 
 
 ### Framework versions