update model card README.md

README.md

@@ -1,5 +1,4 @@
 ---
-license: mit
 tags:
 - generated_from_trainer
 metrics:
@@ -14,10 +13,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Contract-new-tokenizer-mDeBERTa-v3-kor-further
 
-This model is a fine-tuned version of [lighthouse/mdeberta-v3-base-kor-further](https://huggingface.co/lighthouse/mdeberta-v3-base-kor-further) on the None dataset.
+This model is a fine-tuned version of [skang187/before](https://huggingface.co/skang187/before) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0957
-- Accuracy: 0.9718
+- Loss: 0.0605
+- Accuracy: 0.9879
 
 ## Model description
 
@@ -51,9 +50,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 249  | 0.1601          | 0.9386   |
-| No log        | 2.0   | 498  | 0.1140          | 0.9618   |
-| No log        | 3.0   | 747  | 0.0957          | 0.9718   |
+| No log        | 1.0   | 249  | 0.0780          | 0.9779   |
+| No log        | 2.0   | 498  | 0.0563          | 0.9879   |
+| No log        | 3.0   | 747  | 0.0605          | 0.9879   |
 
 
 ### Framework versions