fine-tune-bert-stock-thai-SABINA

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6786
-- Accuracy: 0.5914
+- Loss: 1.1118
+- Accuracy: 0.3859
 
 ## Model description
 
@@ -49,10 +49,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.7           | 1.0   | 553  | 0.6840          | 0.6010   |
-| 0.686         | 2.0   | 1106 | 0.6743          | 0.6010   |
-| 0.6853        | 3.0   | 1659 | 0.6757          | 0.6010   |
-| 0.6817        | 4.0   | 2212 | 0.6786          | 0.5914   |
+| 1.0824        | 1.0   | 553  | 1.0977          | 0.3990   |
+| 1.0801        | 2.0   | 1106 | 1.0912          | 0.3984   |
+| 1.0743        | 3.0   | 1659 | 1.0991          | 0.3966   |
+| 1.0676        | 4.0   | 2212 | 1.1118          | 0.3859   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15d34c2ed755fce02a5e1c3a6552c06e0192bfda87e48501452b2d3e4516bb4e
+oid sha256:b9364c97bb71198aaa6ed938e9d1b3e7bb6804f973822a3b9f166826f1aac56b
 size 711446532