update model card README.md

README.md

@@ -19,7 +19,7 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: 0.7291704844896334
+      value: 0.7148501877297316
 ---
 
 <!-- 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: 0.5961
-- F1: 0.7292
+- Loss: 1.1243
+- F1: 0.7149
 
 ## Model description
 
@@ -49,10 +49,10 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5.1956060024552943e-05
-- train_batch_size: 64
-- eval_batch_size: 64
-- seed: 0
+- learning_rate: 5.18796906442746e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 31415
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 4
@@ -61,10 +61,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.7439        | 1.0   | 51   | 0.6396          | 0.6592 |
-| 0.4792        | 2.0   | 102  | 0.5564          | 0.7408 |
-| 0.2576        | 3.0   | 153  | 0.5768          | 0.7355 |
-| 0.2065        | 4.0   | 204  | 0.5961          | 0.7292 |
+| 0.73          | 1.0   | 408  | 0.8206          | 0.6491 |
+| 0.3868        | 2.0   | 816  | 0.7733          | 0.7230 |
+| 0.0639        | 3.0   | 1224 | 0.9962          | 0.7101 |
+| 0.0507        | 4.0   | 1632 | 1.1243          | 0.7149 |
 
 
 ### Framework versions