update model card README.md

README.md

@@ -19,7 +19,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.740072202166065
+      value: 0.7364620938628159
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,8 +29,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the glue dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9481
-- Accuracy: 0.7401
+- Loss: 0.9021
+- Accuracy: 0.7365
 
 ## Model description
 
@@ -50,8 +50,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- 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
@@ -61,11 +61,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 156  | 0.6756          | 0.5235   |
-| No log        | 2.0   | 312  | 0.6740          | 0.6679   |
-| No log        | 3.0   | 468  | 0.6451          | 0.6895   |
-| 0.4906        | 4.0   | 624  | 0.7788          | 0.6859   |
-| 0.4906        | 5.0   | 780  | 0.9481          | 0.7401   |
+| No log        | 1.0   | 249  | 0.6435          | 0.6390   |
+| No log        | 2.0   | 498  | 0.6611          | 0.6643   |
+| 0.6323        | 3.0   | 747  | 0.5905          | 0.7220   |
+| 0.6323        | 4.0   | 996  | 0.7265          | 0.7256   |
+| 0.3885        | 5.0   | 1245 | 0.9021          | 0.7365   |
 
 
 ### Framework versions