update model card README.md

README.md

@@ -19,7 +19,7 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: 0.6610606215436072
+      value: 0.6978724526113207
 ---
 
 <!-- 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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the tweet_eval dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3749
-- F1: 0.6611
+- Loss: 1.5092
+- F1: 0.6979
 
 ## Model description
 
@@ -49,9 +49,9 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 9.623266809785401e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 1.9499220651719123e-05
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 0
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -61,10 +61,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.5456        | 1.0   | 179  | 0.6118          | 0.6654 |
-| 0.4           | 2.0   | 358  | 0.6933          | 0.6453 |
-| 0.0957        | 3.0   | 537  | 0.9969          | 0.6299 |
-| 0.0483        | 4.0   | 716  | 1.3749          | 0.6611 |
+| 0.4779        | 1.0   | 716  | 0.5890          | 0.6852 |
+| 0.4553        | 2.0   | 1432 | 0.9082          | 0.6635 |
+| 1.268         | 3.0   | 2148 | 1.3061          | 0.6818 |
+| 0.0035        | 4.0   | 2864 | 1.5092          | 0.6979 |
 
 
 ### Framework versions