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 [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2032
-- Accuracy: 0.9486
-- F1: 0.9440
-- Precision: 0.9801
-- Recall: 0.9104
+- Loss: 0.0994
+- Accuracy: 0.9858
+- F1: 0.9850
+- Precision: 0.9871
+- Recall: 0.9829
 
 ## Model description
 
@@ -44,9 +44,9 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 16
+- learning_rate: 3e-05
+- train_batch_size: 16
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -55,12 +55,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     | Precision | Recall |
-|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.0619        | 1.0   | 2955  | 0.0744          | 0.9865   | 0.9858 | 0.9823    | 0.9893 |
-| 0.1059        | 2.0   | 5910  | 0.0789          | 0.9865   | 0.9858 | 0.9844    | 0.9872 |
-| 0.235         | 3.0   | 8865  | 0.1177          | 0.9763   | 0.9755 | 0.9588    | 0.9929 |
-| 0.2333        | 4.0   | 11820 | 0.2032          | 0.9486   | 0.9440 | 0.9801    | 0.9104 |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 0.1153        | 1.0   | 1478 | 0.0675          | 0.9871   | 0.9865 | 0.9837    | 0.9893 |
+| 0.0632        | 2.0   | 2956 | 0.0508          | 0.9882   | 0.9876 | 0.9811    | 0.9943 |
+| 0.0397        | 3.0   | 4434 | 0.0546          | 0.9865   | 0.9858 | 0.9810    | 0.9908 |
+| 0.027         | 4.0   | 5912 | 0.0817          | 0.9875   | 0.9869 | 0.9858    | 0.9879 |
+| 0.0177        | 5.0   | 7390 | 0.0994          | 0.9858   | 0.9850 | 0.9871    | 0.9829 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:804c5b5ffec80bfdb8381c3378a8889731815bcf45d0c05b60a0b069d76c4c2c
+oid sha256:6d7b76c4e9ab7363440e20831f9c13c92e1f3fc4988bc62413d293da1e388bb1
 size 442262520