update model card README.md

README.md

@@ -19,7 +19,7 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: 0.6978724526113207
+      value: 0.6753923142373446
 ---
 
 <!-- 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: 1.5092
-- F1: 0.6979
+- Loss: 0.9694
+- F1: 0.6754
 
 ## Model description
 
@@ -49,10 +49,10 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1.9499220651719123e-05
-- train_batch_size: 4
-- eval_batch_size: 4
-- seed: 0
+- learning_rate: 5.1637764704815665e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- 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     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.4779        | 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 |
+| 0.6601        | 1.0   | 90   | 0.6298          | 0.6230 |
+| 0.4887        | 2.0   | 180  | 0.6039          | 0.6816 |
+| 0.2543        | 3.0   | 270  | 0.7362          | 0.6803 |
+| 0.1472        | 4.0   | 360  | 0.9694          | 0.6754 |
 
 
 ### Framework versions