update model card README.md

README.md

@@ -1,6 +1,5 @@
 ---
 license: mit
-base_model: kisti/korscideberta
 tags:
 - generated_from_trainer
 metrics:
@@ -17,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [kisti/korscideberta](https://huggingface.co/kisti/korscideberta) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6488
-- Accuracy: 0.7860
+- Loss: 0.7228
+- Accuracy: 0.7370
 
 ## Model description
 
@@ -38,26 +37,25 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1.5e-05
-- train_batch_size: 16
-- eval_batch_size: 8
+- train_batch_size: 32
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
 - num_epochs: 4
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.9289        | 1.32  | 500  | 0.9097          | 0.6835   |
-| 0.5205        | 2.64  | 1000 | 0.7150          | 0.7593   |
-| 0.3888        | 3.96  | 1500 | 0.6488          | 0.7860   |
+| 0.8395        | 2.63  | 500  | 0.7228          | 0.7370   |
 
 
 ### Framework versions
 
-- Transformers 4.31.0
-- Pytorch 2.0.1+cu118
-- Datasets 2.14.4
-- Tokenizers 0.13.3
+- Transformers 4.12.5
+- Pytorch 1.10.1+cu102
+- Datasets 2.14.6
+- Tokenizers 0.10.3