Model save

README.md

@@ -17,7 +17,7 @@ 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 the squad dataset.
 It achieves the following results on the evaluation set:
-- Loss: 5.3101
+- Loss: 3.5143
 
 ## Model description
 
@@ -36,21 +36,28 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 5e-05
 - train_batch_size: 40
 - eval_batch_size: 40
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 100  | 5.5239          |
-| No log        | 2.0   | 200  | 5.3671          |
-| No log        | 3.0   | 300  | 5.3101          |
+| No log        | 1.0   | 100  | 4.7435          |
+| No log        | 2.0   | 200  | 4.3343          |
+| No log        | 3.0   | 300  | 4.0804          |
+| No log        | 4.0   | 400  | 3.8983          |
+| 4.3932        | 5.0   | 500  | 3.7642          |
+| 4.3932        | 6.0   | 600  | 3.6649          |
+| 4.3932        | 7.0   | 700  | 3.5978          |
+| 4.3932        | 8.0   | 800  | 3.5499          |
+| 4.3932        | 9.0   | 900  | 3.5216          |
+| 3.7318        | 10.0  | 1000 | 3.5143          |
 
 
 ### Framework versions