update model card README.md

README.md

@@ -16,14 +16,16 @@ model-index:
     dataset:
       name: emotion
       type: emotion
+      config: default
+      split: train
       args: default
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9275
+      value: 0.923
     - name: F1
       type: f1
-      value: 0.9273204837245832
+      value: 0.9226309564543956
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,9 +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: 0.2178
-- Accuracy: 0.9275
-- F1: 0.9273
+- Loss: 0.2256
+- Accuracy: 0.923
+- F1: 0.9226
 
 ## Model description
 
@@ -66,13 +68,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.8381        | 1.0   | 250  | 0.3130          | 0.9075   | 0.9054 |
-| 0.2443        | 2.0   | 500  | 0.2178          | 0.9275   | 0.9273 |
+| 0.807         | 1.0   | 250  | 0.3202          | 0.8995   | 0.8968 |
+| 0.2491        | 2.0   | 500  | 0.2256          | 0.923    | 0.9226 |
 
 
 ### Framework versions
 
-- Transformers 4.13.0
-- Pytorch 1.12.0+cu113
-- Datasets 1.16.1
-- Tokenizers 0.10.3
+- Transformers 4.23.1
+- Pytorch 1.12.1+cu113
+- Datasets 2.6.1
+- Tokenizers 0.13.1