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

README.md

@@ -1,6 +1,7 @@
 ---
 library_name: transformers
-base_model: textattack/bert-base-uncased-yelp-polarity
+license: apache-2.0
+base_model: beomi/kcbert-base
 tags:
 - generated_from_trainer
 metrics:
@@ -15,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # DLthon_BERT
 
-This model is a fine-tuned version of [textattack/bert-base-uncased-yelp-polarity](https://huggingface.co/textattack/bert-base-uncased-yelp-polarity) on an unknown dataset.
+This model is a fine-tuned version of [beomi/kcbert-base](https://huggingface.co/beomi/kcbert-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4843
-- F1: 0.0651
+- Loss: 0.0353
+- F1: 0.9925
 
 ## Model description
 
@@ -37,20 +38,23 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.01
+- learning_rate: 0.0001
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| No log        | 1.0   | 109  | 1.5636          | 0.0651 |
-| No log        | 2.0   | 218  | 1.4843          | 0.0651 |
+| No log        | 1.0   | 224  | 0.2364          | 0.9215 |
+| No log        | 2.0   | 448  | 0.1404          | 0.9546 |
+| 0.326         | 3.0   | 672  | 0.0788          | 0.9799 |
+| 0.326         | 4.0   | 896  | 0.0563          | 0.9862 |
+| 0.0935        | 5.0   | 1120 | 0.0353          | 0.9925 |
 
 
 ### Framework versions