update model card README.md

README.md

@@ -16,7 +16,7 @@ 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 squad dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1577
+- Loss: 2.1904
 
 ## Model description
 
@@ -35,21 +35,24 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 0.0002
+- train_batch_size: 128
+- eval_batch_size: 128
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 6
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss |
-|:-------------:|:-----:|:-----:|:---------------:|
-| 1.2173        | 1.0   | 5533  | 1.1588          |
-| 0.9579        | 2.0   | 11066 | 1.1229          |
-| 0.7547        | 3.0   | 16599 | 1.1577          |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.6224        | 1.0   | 692  | 1.1812          |
+| 1.0216        | 2.0   | 1384 | 1.2495          |
+| 0.5638        | 3.0   | 2076 | 1.3098          |
+| 0.3679        | 4.0   | 2768 | 1.6784          |
+| 0.2703        | 5.0   | 3460 | 1.8842          |
+| 0.1057        | 6.0   | 4152 | 2.1904          |
 
 
 ### Framework versions