update model card README.md

README.md

@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0088
-- Pearson: 0.9821
-- Spearmanr: 0.9121
+- Loss: 0.0102
+- Pearson: 0.9770
+- Spearmanr: 0.9063
 
 ## Model description
 
@@ -38,29 +38,24 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 3e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 20
+- eval_batch_size: 20
 - seed: 25
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 8.0
-- num_epochs: 10
+- lr_scheduler_warmup_steps: 6.0
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|
-| 0.0321        | 1.0   | 131  | 0.0365          | 0.9196  | 0.8640    |
-| 0.0318        | 2.0   | 262  | 0.0347          | 0.9337  | 0.8884    |
-| 0.0044        | 3.0   | 393  | 0.0134          | 0.9667  | 0.9075    |
-| 0.0018        | 4.0   | 524  | 0.0140          | 0.9695  | 0.9089    |
-| 0.0043        | 5.0   | 655  | 0.0088          | 0.9807  | 0.9118    |
-| 0.0015        | 6.0   | 786  | 0.0103          | 0.9780  | 0.9118    |
-| 0.0004        | 7.0   | 917  | 0.0119          | 0.9809  | 0.9121    |
-| 0.0055        | 8.0   | 1048 | 0.0096          | 0.9820  | 0.9121    |
-| 0.0077        | 9.0   | 1179 | 0.0086          | 0.9823  | 0.9121    |
-| 0.0           | 10.0  | 1310 | 0.0088          | 0.9821  | 0.9121    |
+| 0.0241        | 1.0   | 105  | 0.0276          | 0.9385  | 0.8944    |
+| 0.011         | 2.0   | 210  | 0.0130          | 0.9693  | 0.9099    |
+| 0.0027        | 3.0   | 315  | 0.0113          | 0.9725  | 0.9052    |
+| 0.0031        | 4.0   | 420  | 0.0101          | 0.9759  | 0.9053    |
+| 0.0014        | 5.0   | 525  | 0.0102          | 0.9770  | 0.9063    |
 
 
 ### Framework versions