update model card README.md

README.md

@@ -19,7 +19,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.5633802816901409
+      value: 0.5774647887323944
 ---
 
 <!-- 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-xlarge-v2](https://huggingface.co/albert-xlarge-v2) on the glue dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6968
-- Accuracy: 0.5634
+- Loss: 0.6986
+- Accuracy: 0.5775
 
 ## Model description
 
@@ -50,8 +50,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -61,16 +61,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 80   | 0.6968          | 0.5634   |
-| No log        | 2.0   | 160  | 0.6903          | 0.5634   |
-| No log        | 3.0   | 240  | 0.6852          | 0.5634   |
-| No log        | 4.0   | 320  | 0.7036          | 0.4366   |
-| No log        | 5.0   | 400  | 0.6924          | 0.5493   |
+| No log        | 1.0   | 40   | 0.6827          | 0.5634   |
+| No log        | 2.0   | 80   | 0.7022          | 0.5634   |
+| No log        | 3.0   | 120  | 0.6865          | 0.5493   |
+| No log        | 4.0   | 160  | 0.7093          | 0.5070   |
+| No log        | 5.0   | 200  | 0.6986          | 0.5775   |
 
 
 ### Framework versions
 
 - Transformers 4.15.0
-- Pytorch 1.9.0+cu102
+- Pytorch 1.10.0+cu111
 - Datasets 1.18.0
 - Tokenizers 0.10.3