update model card README.md

README.md

@@ -16,7 +16,7 @@ model-index:
       name: glue
       type: glue
       config: sst2
-      split: train
+      split: validation
       args: sst2
     metrics:
     - name: Accuracy
@@ -31,7 +31,7 @@ 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 glue dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2817
+- Loss: 0.2805
 - Accuracy: 0.9025
 
 ## Model description
@@ -63,16 +63,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 132  | 0.2534          | 0.8956   |
-| No log        | 2.0   | 264  | 0.2679          | 0.9002   |
-| No log        | 3.0   | 396  | 0.2817          | 0.9025   |
-| 0.1896        | 4.0   | 528  | 0.2933          | 0.9002   |
-| 0.1896        | 5.0   | 660  | 0.3008          | 0.9002   |
+| No log        | 1.0   | 132  | 0.2592          | 0.8888   |
+| No log        | 2.0   | 264  | 0.2770          | 0.8979   |
+| No log        | 3.0   | 396  | 0.2805          | 0.9025   |
+| 0.1914        | 4.0   | 528  | 0.2975          | 0.9014   |
+| 0.1914        | 5.0   | 660  | 0.3026          | 0.9002   |
 
 
 ### Framework versions
 
-- Transformers 4.23.1
-- Pytorch 1.12.1+cu116
-- Datasets 2.6.1
-- Tokenizers 0.13.1
+- Transformers 4.29.1
+- Pytorch 2.0.1+cu117
+- Datasets 2.12.0
+- Tokenizers 0.13.3