factual-consistency-classification-ja

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: 0.9166
-- Accuracy: 0.4707
+- Loss: 0.8034
+- Accuracy: 0.6230
 
 ## Model description
 
@@ -44,22 +44,42 @@ 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: 10
+- num_epochs: 30
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 306  | 1.0543          | 0.2891   |
-| 1.0487        | 2.0   | 612  | 1.0134          | 0.3301   |
-| 1.0487        | 3.0   | 918  | 0.9846          | 0.3457   |
-| 0.9961        | 4.0   | 1224 | 0.9620          | 0.3965   |
-| 0.963         | 5.0   | 1530 | 0.9462          | 0.4258   |
-| 0.963         | 6.0   | 1836 | 0.9326          | 0.4688   |
-| 0.9401        | 7.0   | 2142 | 0.9254          | 0.4707   |
-| 0.9401        | 8.0   | 2448 | 0.9208          | 0.4688   |
-| 0.9295        | 9.0   | 2754 | 0.9176          | 0.4707   |
-| 0.9232        | 10.0  | 3060 | 0.9166          | 0.4707   |
+| No log        | 1.0   | 306  | 1.0539          | 0.2891   |
+| 1.0502        | 2.0   | 612  | 1.0074          | 0.3203   |
+| 1.0502        | 3.0   | 918  | 0.9738          | 0.3711   |
+| 0.9895        | 4.0   | 1224 | 0.9452          | 0.4453   |
+| 0.9483        | 5.0   | 1530 | 0.9245          | 0.4766   |
+| 0.9483        | 6.0   | 1836 | 0.9041          | 0.5566   |
+| 0.918         | 7.0   | 2142 | 0.8945          | 0.5117   |
+| 0.918         | 8.0   | 2448 | 0.8853          | 0.5      |
+| 0.9002        | 9.0   | 2754 | 0.8786          | 0.4922   |
+| 0.884         | 10.0  | 3060 | 0.8658          | 0.5352   |
+| 0.884         | 11.0  | 3366 | 0.8614          | 0.5176   |
+| 0.8697        | 12.0  | 3672 | 0.8467          | 0.5938   |
+| 0.8697        | 13.0  | 3978 | 0.8429          | 0.5801   |
+| 0.8648        | 14.0  | 4284 | 0.8386          | 0.5703   |
+| 0.8571        | 15.0  | 4590 | 0.8311          | 0.5996   |
+| 0.8571        | 16.0  | 4896 | 0.8289          | 0.5879   |
+| 0.8478        | 17.0  | 5202 | 0.8285          | 0.5762   |
+| 0.8468        | 18.0  | 5508 | 0.8193          | 0.6152   |
+| 0.8468        | 19.0  | 5814 | 0.8192          | 0.5957   |
+| 0.8439        | 20.0  | 6120 | 0.8165          | 0.5996   |
+| 0.8439        | 21.0  | 6426 | 0.8157          | 0.5918   |
+| 0.8396        | 22.0  | 6732 | 0.8120          | 0.6055   |
+| 0.8354        | 23.0  | 7038 | 0.8103          | 0.6055   |
+| 0.8354        | 24.0  | 7344 | 0.8091          | 0.6035   |
+| 0.8362        | 25.0  | 7650 | 0.8055          | 0.6152   |
+| 0.8362        | 26.0  | 7956 | 0.8055          | 0.6074   |
+| 0.8334        | 27.0  | 8262 | 0.8045          | 0.6211   |
+| 0.8325        | 28.0  | 8568 | 0.8037          | 0.6191   |
+| 0.8325        | 29.0  | 8874 | 0.8034          | 0.6230   |
+| 0.833         | 30.0  | 9180 | 0.8034          | 0.6230   |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd717c6204324760639f39260180a6740d996ae18f8d997b232b562aa3f30cab
+oid sha256:338f2d144537ab887447cb85ca42e66d70ca222e5a2a051570a756dcae72807e
 size 274758641