update model card README.md

README.md

@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [klue/roberta-large](https://huggingface.co/klue/roberta-large) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0189
-- Precision: 0.9763
-- Recall: 0.9736
-- F1: 0.9749
-- Accuracy: 0.9964
+- Loss: 0.0290
+- Precision: 0.9626
+- Recall: 0.9588
+- F1: 0.9607
+- Accuracy: 0.9936
 
 ## Model description
 
@@ -43,8 +43,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 2
+- eval_batch_size: 2
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -54,14 +54,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 155  | 0.0265          | 0.9538    | 0.9599 | 0.9569 | 0.9943   |
-| No log        | 2.0   | 310  | 0.0194          | 0.9589    | 0.9772 | 0.9680 | 0.9951   |
-| No log        | 3.0   | 465  | 0.0189          | 0.9763    | 0.9736 | 0.9749 | 0.9964   |
+| 0.0682        | 1.0   | 1240 | 0.0561          | 0.9327    | 0.9392 | 0.9359 | 0.9898   |
+| 0.0359        | 2.0   | 2480 | 0.0408          | 0.9701    | 0.9539 | 0.9619 | 0.9939   |
+| 0.0157        | 3.0   | 3720 | 0.0290          | 0.9626    | 0.9588 | 0.9607 | 0.9936   |
 
 
 ### Framework versions
 
-- Transformers 4.37.2
-- Pytorch 2.1.0+cu121
-- Datasets 2.17.1
-- Tokenizers 0.15.2
+- Transformers 4.31.0.dev0
+- Pytorch 2.0.1+cu117
+- Datasets 2.13.2.dev0
+- Tokenizers 0.13.3