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 becasv2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 5.9173
+- Loss: 4.7546
 
 ## Model description
 
@@ -35,9 +35,9 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 2e-05
+- train_batch_size: 10
+- eval_batch_size: 10
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -47,16 +47,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 5    | 5.0022          |
-| No log        | 2.0   | 10   | 4.4653          |
-| No log        | 3.0   | 15   | 3.7818          |
-| No log        | 4.0   | 20   | 4.4116          |
-| No log        | 5.0   | 25   | 4.6704          |
-| No log        | 6.0   | 30   | 5.1893          |
-| No log        | 7.0   | 35   | 5.6040          |
-| No log        | 8.0   | 40   | 5.8588          |
-| No log        | 9.0   | 45   | 5.8949          |
-| No log        | 10.0  | 50   | 5.9173          |
+| No log        | 1.0   | 8    | 5.1392          |
+| No log        | 2.0   | 16   | 4.4811          |
+| No log        | 3.0   | 24   | 4.0169          |
+| No log        | 4.0   | 32   | 3.8533          |
+| No log        | 5.0   | 40   | 3.7860          |
+| No log        | 6.0   | 48   | 4.0378          |
+| No log        | 7.0   | 56   | 4.3794          |
+| No log        | 8.0   | 64   | 4.4559          |
+| No log        | 9.0   | 72   | 4.7100          |
+| No log        | 10.0  | 80   | 4.7546          |
 
 
 ### Framework versions