fc-binary-unfrozen

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: 0.2216
-- Accuracy: 0.9219
+- Loss: 0.3796
+- Accuracy: 0.9258
 
 ## Model description
 
@@ -44,15 +44,18 @@ The following hyperparameters were used during training:
 - distributed_type: tpu
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 6
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 306  | 0.2533          | 0.9199   |
-| 0.2874        | 2.0   | 612  | 0.2208          | 0.9297   |
-| 0.2874        | 3.0   | 918  | 0.2216          | 0.9219   |
+| No log        | 1.0   | 306  | 0.2649          | 0.9160   |
+| 0.2942        | 2.0   | 612  | 0.2373          | 0.9082   |
+| 0.2942        | 3.0   | 918  | 0.2091          | 0.9219   |
+| 0.1394        | 4.0   | 1224 | 0.2558          | 0.9355   |
+| 0.0607        | 5.0   | 1530 | 0.2584          | 0.9238   |
+| 0.0607        | 6.0   | 1836 | 0.3796          | 0.9258   |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4685f044615a1348e9369b0b3ea0b494cd52682b6555ebad32a2fa394371eb7
+oid sha256:a547ac897f73c99c959400ecbb2cbba7c086be09e492c4b9fb473a578d0eb3f6
 size 274758317