umn-cyber/indobert-hoax-detection

README.md

@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [indobenchmark/indobert-base-p1](https://huggingface.co/indobenchmark/indobert-base-p1) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0543
-- Accuracy: 0.9848
-- F1: 0.9840
-- Precision: 0.9857
-- Recall: 0.9822
+- Loss: 0.0480
+- Accuracy: 0.9885
+- F1: 0.9879
+- Precision: 0.9879
+- Recall: 0.9879
 
 ## Model description
 
@@ -50,17 +50,15 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.0898        | 1.0   | 739  | 0.0585          | 0.9875   | 0.9869 | 0.9858    | 0.9879 |
-| 0.0464        | 2.0   | 1478 | 0.0493          | 0.9861   | 0.9854 | 0.9858    | 0.9851 |
-| 0.0247        | 3.0   | 2217 | 0.0629          | 0.9868   | 0.9862 | 0.9830    | 0.9893 |
-| 0.0097        | 4.0   | 2956 | 0.0773          | 0.9871   | 0.9865 | 0.9858    | 0.9872 |
-| 0.0031        | 5.0   | 3695 | 0.0862          | 0.9854   | 0.9847 | 0.9851    | 0.9844 |
+| 0.0797        | 1.0   | 739  | 0.0485          | 0.9882   | 0.9876 | 0.9858    | 0.9893 |
+| 0.0428        | 2.0   | 1478 | 0.0436          | 0.9868   | 0.9862 | 0.9817    | 0.9908 |
+| 0.0221        | 3.0   | 2217 | 0.0480          | 0.9885   | 0.9879 | 0.9879    | 0.9879 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80f35639246a1dab46fcf44850dfa6a974de0195f363e5a260839836b83ad96e
+oid sha256:029695a7a031ea0be3afa3f88ba0ec69f2fc066939c64305db1febd7a54a56d4
 size 497795072