End of training

README.md

@@ -17,9 +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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5528
-- Pearson: 0.8700
-- Spearmanr: 0.8662
+- Loss: 0.5419
+- Pearson: 0.8721
+- Spearmanr: 0.8692
 
 ## Model description
 
@@ -38,10 +38,10 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 16
+- learning_rate: 7.503545930910804e-05
+- train_batch_size: 8
 - eval_batch_size: 16
-- seed: 42
+- seed: 19
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 5
@@ -50,11 +50,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|
-| No log        | 1.0   | 360  | 0.5742          | 0.8645  | 0.8618    |
-| 1.0066        | 2.0   | 720  | 0.5734          | 0.8691  | 0.8661    |
-| 0.394         | 3.0   | 1080 | 0.5896          | 0.8688  | 0.8662    |
-| 0.394         | 4.0   | 1440 | 0.5528          | 0.8700  | 0.8662    |
-| 0.2484        | 5.0   | 1800 | 0.5631          | 0.8691  | 0.8654    |
+| 1.1437        | 1.0   | 719  | 0.6564          | 0.8435  | 0.8459    |
+| 0.6029        | 2.0   | 1438 | 0.5862          | 0.8616  | 0.8575    |
+| 0.2677        | 3.0   | 2157 | 0.5680          | 0.8676  | 0.8648    |
+| 0.1959        | 4.0   | 2876 | 0.5500          | 0.8705  | 0.8686    |
+| 0.0985        | 5.0   | 3595 | 0.5419          | 0.8721  | 0.8692    |
 
 
 ### Framework versions