fine-tune-wangchanberta-stock-thai-SABINA

README.md

@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [airesearch/wangchanberta-base-att-spm-uncased](https://huggingface.co/airesearch/wangchanberta-base-att-spm-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6935
-- Accuracy: 0.5032
+- Loss: 0.6753
+- Accuracy: 0.5998
 
 ## Model description
 
@@ -48,13 +48,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.7242        | 1.0   | 485  | 0.7214          | 0.5079   |
-| 0.7023        | 2.0   | 970  | 0.7894          | 0.5074   |
-| 0.6989        | 3.0   | 1455 | 0.6988          | 0.5069   |
-| 0.6951        | 4.0   | 1940 | 0.7020          | 0.5074   |
-| 0.6958        | 5.0   | 2425 | 0.7038          | 0.5074   |
-| 0.6953        | 6.0   | 2910 | 0.7026          | 0.5063   |
-| 0.6936        | 7.0   | 3395 | 0.6935          | 0.5032   |
+| 0.715         | 1.0   | 553  | 0.6922          | 0.5140   |
+| 0.6929        | 2.0   | 1106 | 0.6738          | 0.6019   |
+| 0.6898        | 3.0   | 1659 | 0.6753          | 0.6010   |
+| 0.6902        | 4.0   | 2212 | 0.6782          | 0.6010   |
+| 0.6879        | 5.0   | 2765 | 0.6734          | 0.6010   |
+| 0.6878        | 6.0   | 3318 | 0.6777          | 0.6003   |
+| 0.6876        | 7.0   | 3871 | 0.6753          | 0.5998   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c83b27c44c555aae9b6f66f0807f81f6dd99a0573e66c90ba24f6a4f7309f6aa
+oid sha256:cc89f5af539a0616e856fb6a3d7d163c0515407d40ac38da134079fdb9c775ca
 size 421011004