Steeljin/roberta-base-klue-ynat-classification

README.md

@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [klue/roberta-base](https://huggingface.co/klue/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4750
-- Accuracy: 0.853
+- Loss: 0.4702
+- Accuracy: 0.849
 
 ## Model description
 
@@ -48,7 +48,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.5413        | 1.0   | 1250 | 0.5173          | 0.841    |
+| 0.5393        | 1.0   | 1250 | 0.5263          | 0.832    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2826c18ba9ddbe3191ee0b95546ae0222600b14c60f730f595318e2d1e24e4fc
+oid sha256:e0d2719a8422d761128cfc8b972c695e5a044bcc42b36d8d7a5512ccc800fe97
 size 442518124

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e5ab43a05b3306c5cfb0d0335ecd235cd335a98b327a4d554b924cfd7be3ef2
+oid sha256:fa46abf289d54cd64d6a60ecc01ff217278a285f0e98da3fc56ceddcbcba80e3
 size 4984