update model card README.md

README.md

@@ -22,10 +22,10 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.926
+      value: 0.9385
     - name: F1
       type: f1
-      value: 0.9260625630192153
+      value: 0.9382234767195092
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,9 +35,9 @@ 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: 0.2295
-- Accuracy: 0.926
-- F1: 0.9261
+- Loss: 0.2716
+- Accuracy: 0.9385
+- F1: 0.9382
 
 ## Model description
 
@@ -57,8 +57,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 64
-- eval_batch_size: 64
+- train_batch_size: 1
+- eval_batch_size: 1
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -66,15 +66,15 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.8332        | 1.0   | 250  | 0.3398          | 0.8935   | 0.8875 |
-| 0.2614        | 2.0   | 500  | 0.2295          | 0.926    | 0.9261 |
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
+| 0.5485        | 1.0   | 16000 | 0.3088          | 0.933    | 0.9322 |
+| 0.2384        | 2.0   | 32000 | 0.2716          | 0.9385   | 0.9382 |
 
 
 ### Framework versions
 
 - Transformers 4.21.1
 - Pytorch 1.11.0
-- Datasets 2.3.0
+- Datasets 2.4.0
 - Tokenizers 0.12.1