update model card README.md

README.md

@@ -16,14 +16,14 @@ model-index:
     dataset:
       name: emotion
       type: emotion
-      args: default
+      args: split
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9245
+      value: 0.9355
     - name: F1
       type: f1
-      value: 0.9247712048482103
+      value: 0.9356480877541032
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,9 +33,9 @@ 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 emotion dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2179
-- Accuracy: 0.9245
-- F1: 0.9248
+- Loss: 0.1424
+- Accuracy: 0.9355
+- F1: 0.9356
 
 ## Model description
 
@@ -54,25 +54,26 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 5e-05
 - train_batch_size: 64
 - eval_batch_size: 64
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 3.0
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.8178        | 1.0   | 250  | 0.3219          | 0.9035   | 0.8996 |
-| 0.2526        | 2.0   | 500  | 0.2179          | 0.9245   | 0.9248 |
+| 0.5311        | 1.0   | 250  | 0.1817          | 0.932    | 0.9317 |
+| 0.14          | 2.0   | 500  | 0.1483          | 0.9365   | 0.9368 |
+| 0.0915        | 3.0   | 750  | 0.1424          | 0.9355   | 0.9356 |
 
 
 ### Framework versions
 
 - Transformers 4.13.0
-- Pytorch 1.12.1+cu113
-- Datasets 1.16.1
+- Pytorch 1.10.2+cu102
+- Datasets 2.8.0
 - Tokenizers 0.10.3