update model card README.md

README.md

@@ -17,15 +17,15 @@ model-index:
       name: tweet_eval
       type: tweet_eval
       config: emotion
-      split: train
+      split: validation
       args: emotion
     metrics:
     - name: Precision
       type: precision
-      value: 0.7311211804904578
+      value: 0.7505623807659564
     - name: Recall
       type: recall
-      value: 0.7298750848074663
+      value: 0.7243031825553111
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,10 +35,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the tweet_eval dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1658
-- Precision: 0.7311
-- Recall: 0.7299
-- Fscore: 0.7299
+- Loss: 1.1413
+- Precision: 0.7506
+- Recall: 0.7243
+- Fscore: 0.7340
 
 ## Model description
 
@@ -69,14 +69,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Fscore |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
-| 0.8562        | 1.0   | 815  | 0.7859          | 0.7527    | 0.6006 | 0.6173 |
-| 0.5352        | 2.0   | 1630 | 0.9248          | 0.7545    | 0.7188 | 0.7293 |
-| 0.2543        | 3.0   | 2445 | 1.1658          | 0.7311    | 0.7299 | 0.7299 |
+| 0.8556        | 1.0   | 815  | 0.7854          | 0.7461    | 0.5929 | 0.6088 |
+| 0.5369        | 2.0   | 1630 | 0.9014          | 0.7549    | 0.7278 | 0.7359 |
+| 0.2571        | 3.0   | 2445 | 1.1413          | 0.7506    | 0.7243 | 0.7340 |
 
 
 ### Framework versions
 
-- Transformers 4.24.0
-- Pytorch 1.12.1+cu113
-- Datasets 2.7.1
-- Tokenizers 0.13.2
+- Transformers 4.28.1
+- Pytorch 2.0.0+cu118
+- Datasets 2.11.0
+- Tokenizers 0.13.3