update model card README.md

README.md

@@ -1,6 +1,4 @@
 ---
-language:
-- en
 tags:
 - generated_from_trainer
 datasets:
@@ -14,7 +12,7 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: GLUE WNLI
+      name: glue
       type: glue
       config: wnli
       split: validation
@@ -22,7 +20,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.5633802816901409
+      value: 0.43661971830985913
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +28,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hBERTv1_new_pretrain_w_init__wnli
 
-This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_wt_init](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_wt_init) on the GLUE WNLI dataset.
+This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_wt_init](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_wt_init) on the glue dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6855
-- Accuracy: 0.5634
+- Loss: 0.7182
+- Accuracy: 0.4366
 
 ## Model description
 
@@ -52,7 +50,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0005
+- learning_rate: 4e-05
 - train_batch_size: 128
 - eval_batch_size: 128
 - seed: 10
@@ -65,20 +63,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 12.3688       | 1.0   | 5    | 6.2236          | 0.5634   |
-| 3.5093        | 2.0   | 10   | 0.7491          | 0.4366   |
-| 1.9112        | 3.0   | 15   | 2.5146          | 0.5634   |
-| 1.4995        | 4.0   | 20   | 1.8104          | 0.4366   |
-| 1.3047        | 5.0   | 25   | 0.6936          | 0.5634   |
-| 1.4685        | 6.0   | 30   | 0.7440          | 0.5634   |
-| 0.924         | 7.0   | 35   | 1.1066          | 0.4366   |
-| 0.8423        | 8.0   | 40   | 0.8221          | 0.4366   |
-| 0.8166        | 9.0   | 45   | 0.6855          | 0.5634   |
-| 0.7552        | 10.0  | 50   | 0.7181          | 0.5634   |
-| 0.7515        | 11.0  | 55   | 0.6951          | 0.5634   |
-| 0.7127        | 12.0  | 60   | 0.7140          | 0.4366   |
-| 0.7112        | 13.0  | 65   | 0.6901          | 0.5634   |
-| 0.6976        | 14.0  | 70   | 0.7009          | 0.4366   |
+| 0.9261        | 1.0   | 5    | 0.6915          | 0.5352   |
+| 0.7312        | 2.0   | 10   | 0.6844          | 0.5634   |
+| 0.7289        | 3.0   | 15   | 0.7337          | 0.5634   |
+| 0.7656        | 4.0   | 20   | 0.7585          | 0.4366   |
+| 0.7189        | 5.0   | 25   | 0.6906          | 0.5634   |
+| 0.7167        | 6.0   | 30   | 0.6911          | 0.5634   |
+| 0.7089        | 7.0   | 35   | 0.7182          | 0.4366   |
 
 
 ### Framework versions