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: 0.6621
-- Accuracy: 0.7461
+- Loss: 0.8124
+- Accuracy: 0.6777
 
 ## Model description
 
@@ -44,32 +44,17 @@ 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: 20
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 306  | 0.8904          | 0.5840   |
-| 0.9381        | 2.0   | 612  | 0.8377          | 0.6680   |
-| 0.9381        | 3.0   | 918  | 0.7989          | 0.6836   |
-| 0.8452        | 4.0   | 1224 | 0.7708          | 0.7051   |
-| 0.7968        | 5.0   | 1530 | 0.7486          | 0.7109   |
-| 0.7968        | 6.0   | 1836 | 0.7332          | 0.7129   |
-| 0.766         | 7.0   | 2142 | 0.7183          | 0.7188   |
-| 0.766         | 8.0   | 2448 | 0.7076          | 0.7246   |
-| 0.7466        | 9.0   | 2754 | 0.6985          | 0.7285   |
-| 0.7329        | 10.0  | 3060 | 0.6908          | 0.7305   |
-| 0.7329        | 11.0  | 3366 | 0.6848          | 0.7324   |
-| 0.7204        | 12.0  | 3672 | 0.6794          | 0.7344   |
-| 0.7204        | 13.0  | 3978 | 0.6750          | 0.7402   |
-| 0.7198        | 14.0  | 4284 | 0.6713          | 0.7422   |
-| 0.7133        | 15.0  | 4590 | 0.6684          | 0.7441   |
-| 0.7133        | 16.0  | 4896 | 0.6662          | 0.7422   |
-| 0.7041        | 17.0  | 5202 | 0.6644          | 0.7461   |
-| 0.7064        | 18.0  | 5508 | 0.6632          | 0.7422   |
-| 0.7064        | 19.0  | 5814 | 0.6624          | 0.7441   |
-| 0.7045        | 20.0  | 6120 | 0.6621          | 0.7461   |
+| No log        | 1.0   | 306  | 0.8936          | 0.5762   |
+| 0.9294        | 2.0   | 612  | 0.8541          | 0.6367   |
+| 0.9294        | 3.0   | 918  | 0.8295          | 0.6621   |
+| 0.8671        | 4.0   | 1224 | 0.8167          | 0.6777   |
+| 0.8414        | 5.0   | 1530 | 0.8124          | 0.6777   |
 
 
 ### Framework versions