umn-cyber/indobert-hoax-detection

README.md

@@ -1,70 +1,71 @@
----
-library_name: transformers
-license: mit
-base_model: indolem/indobert-base-uncased
-tags:
-- generated_from_trainer
-metrics:
-- accuracy
-- f1
-- precision
-- recall
-model-index:
-- name: results
-  results: []
----
-
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
-# results
-
-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: 0.0526
-- Accuracy: 0.9888
-- F1: 0.9883
-- Precision: 0.9858
-- Recall: 0.9908
-
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
-
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 16
-- eval_batch_size: 16
-- seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- num_epochs: 3
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.0781        | 1.0   | 1478 | 0.0675          | 0.9858   | 0.9851 | 0.9810    | 0.9893 |
-| 0.037         | 2.0   | 2956 | 0.0560          | 0.9851   | 0.9843 | 0.9857    | 0.9829 |
-| 0.0333        | 3.0   | 4434 | 0.0526          | 0.9888   | 0.9883 | 0.9858    | 0.9908 |
-
-
-### Framework versions
-
-- Transformers 4.44.2
-- Pytorch 2.4.1+cu121
-- Datasets 3.0.1
-- Tokenizers 0.19.1
+---
+library_name: transformers
+license: mit
+base_model: indolem/indobert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: results
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# results
+
+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
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 10
+
+### 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 |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.4.1
+- Datasets 2.19.2
+- Tokenizers 0.20.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78b74ebd3abe16c161895a62bf2742aa43550093bc27c0efbf175089d0d2fd53
+oid sha256:213fb0637f4af46b86c17fcc9c0a4574f78f70ac6b34d2fc1aa0524533d11fbb
 size 442262520