fc-binary-prompt-unfrozen-model

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [line-corporation/line-distilbert-base-japanese](https://huggingface.co/line-corporation/line-distilbert-base-japanese) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3299
-- Accuracy: 0.9180
+- Loss: 0.2808
+- Accuracy: 0.9238
 
 ## Model description
 
@@ -50,12 +50,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 306  | 0.3487          | 0.8594   |
-| 0.3656        | 2.0   | 612  | 0.2860          | 0.8652   |
-| 0.3656        | 3.0   | 918  | 0.2392          | 0.9023   |
-| 0.2242        | 4.0   | 1224 | 0.2734          | 0.9004   |
-| 0.1212        | 5.0   | 1530 | 0.2840          | 0.9199   |
-| 0.1212        | 6.0   | 1836 | 0.3299          | 0.9180   |
+| No log        | 1.0   | 306  | 0.3327          | 0.875    |
+| 0.3288        | 2.0   | 612  | 0.2602          | 0.8926   |
+| 0.3288        | 3.0   | 918  | 0.2110          | 0.9160   |
+| 0.1925        | 4.0   | 1224 | 0.2477          | 0.9180   |
+| 0.1036        | 5.0   | 1530 | 0.2706          | 0.9199   |
+| 0.1036        | 6.0   | 1836 | 0.2808          | 0.9238   |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6482d51ef663690fdf2f47909e6d78dee92a8072a9e0c3e3965d19ce865e7f7f
+oid sha256:a42dcb0cee1a7907b1caa46e61cb5421c6689428e265af4106673a135946b9e2
 size 274755245