End of training

README.md

@@ -17,8 +17,9 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3641
-- Accuracy: 0.6525
+- Loss: 0.6063
+- Accuracy: 0.69
+- Mcc: 0.2901
 
 ## Model description
 
@@ -43,22 +44,17 @@ 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: 10
+- num_epochs: 5
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 51   | 0.6307          | 0.6575   |
-| No log        | 2.0   | 102  | 0.6292          | 0.66     |
-| No log        | 3.0   | 153  | 0.6172          | 0.6725   |
-| No log        | 4.0   | 204  | 0.6778          | 0.64     |
-| No log        | 5.0   | 255  | 0.7877          | 0.6475   |
-| No log        | 6.0   | 306  | 0.8919          | 0.6425   |
-| No log        | 7.0   | 357  | 1.0539          | 0.65     |
-| No log        | 8.0   | 408  | 1.2609          | 0.6475   |
-| No log        | 9.0   | 459  | 1.3215          | 0.65     |
-| 0.3163        | 10.0  | 510  | 1.3641          | 0.6525   |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Mcc    |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| No log        | 1.0   | 51   | 0.6793          | 0.635    | 0.0    |
+| No log        | 2.0   | 102  | 0.6683          | 0.5925   | 0.2198 |
+| No log        | 3.0   | 153  | 0.6685          | 0.6525   | 0.1651 |
+| No log        | 4.0   | 204  | 0.6108          | 0.675    | 0.2395 |
+| No log        | 5.0   | 255  | 0.6063          | 0.69     | 0.2901 |
 
 
 ### Framework versions