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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4715
-- Matthews Correlation: 0.5234
+- Loss: 0.6130
+- Matthews Correlation: 0.5524
 
 ## Model description
 
@@ -37,23 +37,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 16
+- learning_rate: 5.3050141475538535e-05
+- train_batch_size: 32
 - eval_batch_size: 16
-- seed: 42
+- seed: 34
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| 0.5183        | 1.0   | 535  | 0.4565          | 0.4351               |
-| 0.3408        | 2.0   | 1070 | 0.4715          | 0.5234               |
-| 0.231         | 3.0   | 1605 | 0.6641          | 0.5179               |
-| 0.1725        | 4.0   | 2140 | 0.8203          | 0.5184               |
-| 0.1274        | 5.0   | 2675 | 0.8536          | 0.5212               |
+| No log        | 1.0   | 268  | 0.4489          | 0.5150               |
+| 0.4172        | 2.0   | 536  | 0.4673          | 0.5203               |
+| 0.4172        | 3.0   | 804  | 0.6130          | 0.5524               |
 
 
 ### Framework versions