update model card README.md

README.md

@@ -1,7 +1,6 @@
 ---
 license: apache-2.0
 tags:
-- text-classification
 - generated_from_trainer
 datasets:
 - glue
@@ -23,10 +22,10 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8578431372549019
+      value: 0.8553921568627451
     - name: F1
       type: f1
-      value: 0.8982456140350877
+      value: 0.897391304347826
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -34,11 +33,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # platzi-distilroberta-base-mrpc-glue-omar-espejel
 
-This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the glue and the mrpc datasets.
+This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the glue dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6574
-- Accuracy: 0.8578
-- F1: 0.8982
+- Loss: 0.6342
+- Accuracy: 0.8554
+- F1: 0.8974
 
 ## Model description
 
@@ -63,15 +62,14 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 4
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.5047        | 1.09  | 500  | 0.7064          | 0.8284   | 0.8768 |
-| 0.3665        | 2.18  | 1000 | 0.6574          | 0.8578   | 0.8982 |
-| 0.2025        | 3.27  | 1500 | 0.7720          | 0.8505   | 0.8932 |
+| 0.5004        | 1.09  | 500  | 0.6371          | 0.8113   | 0.8715 |
+| 0.33          | 2.18  | 1000 | 0.6342          | 0.8554   | 0.8974 |
 
 
 ### Framework versions