ehottl/roberta-base-klue-ynat-classification

README.md

@@ -17,8 +17,8 @@ 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: 0.4633
-- Accuracy: 0.853
+- Loss: 0.4798
+- Accuracy: 0.848
 
 ## Model description
 
@@ -49,7 +49,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.4189        | 1.0   | 4460 | 0.4998          | 0.855    |
+| 0.4104        | 1.0   | 4460 | 0.4820          | 0.846    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52534a4e5d38d777b22802991c7aab0f1e86d99d8d1b07d937763af90d127c30
+oid sha256:b24e0d1fc94555e8cecb7f7d699a85db137e8a0a4c1ad749ad5cf391bccdddf0
 size 442518124

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe2515aaeee0c5a37b65275f372c2cad63324918defeaddf0a24e2df0a7e22b9
+oid sha256:aea02112cf098e1413fb94e5f4d499077cae5184bf789aaab240a0f4355ea33b
 size 5304