sonjy/news-classifier

README.md

@@ -28,11 +28,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [monologg/koelectra-base-v3-discriminator](https://huggingface.co/monologg/koelectra-base-v3-discriminator) on the klue-ynat dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4202
-- Accuracy: 0.8594
-- Precision: 0.8507
-- Recall: 0.8706
-- F1: 0.8601
+- Loss: 0.4040
+- Accuracy: 0.8616
+- Precision: 0.8525
+- Recall: 0.8750
+- F1: 0.8632
 
 ## Model description
 
@@ -63,9 +63,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| 0.3906        | 1.0   | 714  | 0.4470          | 0.8435   | 0.8290    | 0.8656 | 0.8456 |
-| 0.2989        | 2.0   | 1428 | 0.4003          | 0.8545   | 0.8460    | 0.8650 | 0.8546 |
-| 0.2266        | 3.0   | 2142 | 0.4202          | 0.8594   | 0.8507    | 0.8706 | 0.8601 |
+| 0.3922        | 1.0   | 714  | 0.4190          | 0.8598   | 0.8472    | 0.8694 | 0.8574 |
+| 0.2973        | 2.0   | 1428 | 0.4020          | 0.8538   | 0.8448    | 0.8725 | 0.8568 |
+| 0.2244        | 3.0   | 2142 | 0.4040          | 0.8616   | 0.8525    | 0.8750 | 0.8632 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa028f456b48175925c42836b45b67d7fe8086f9063f4a790e1fcf5f1fbd6bae
+oid sha256:278cb2830113e87a108eece8213e18396b7f95806b8a8092b99e083223cfe511
 size 451731052

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c673010f057c006eb2437e13a321b8463051a5475368a50d867362284e6dfa7
+oid sha256:e7efd2cf27d93274500aa3a2510fdc36a9aad0db7bead12be9afd7f5ea87c08b
 size 5841