update model card README.md

README.md

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.915483870967742
+      value: 0.9509677419354838
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ 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 clinc_oos dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7690
-- Accuracy: 0.9155
+- Loss: 0.2354
+- Accuracy: 0.9510
 
 ## Model description
 
@@ -52,8 +52,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 48
-- eval_batch_size: 48
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -63,11 +63,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 318  | 3.2756          | 0.7426   |
-| 3.7796        | 2.0   | 636  | 1.8550          | 0.8377   |
-| 3.7796        | 3.0   | 954  | 1.1476          | 0.8945   |
-| 1.6746        | 4.0   | 1272 | 0.8513          | 0.9119   |
-| 0.8936        | 5.0   | 1590 | 0.7690          | 0.9155   |
+| 2.0114        | 1.0   | 1907 | 0.9483          | 0.8577   |
+| 0.2978        | 2.0   | 3814 | 0.2961          | 0.9368   |
+| 0.097         | 3.0   | 5721 | 0.2422          | 0.9474   |
+| 0.0393        | 4.0   | 7628 | 0.2349          | 0.9519   |
+| 0.023         | 5.0   | 9535 | 0.2354          | 0.9510   |
 
 
 ### Framework versions