metadata
license: mit
base_model: indobenchmark/indobart-v2
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: bdc2024-indobartv2
results: []
bdc2024-indobartv2
This model is a fine-tuned version of indobenchmark/indobart-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3023
- Accuracy: 0.7162
- Balanced Accuracy: 0.4029
- Precision: 0.7027
- Recall: 0.7162
- F1: 0.6930
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: 2e-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
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Balanced Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 242 | 0.9849 | 0.7271 | 0.3492 | 0.6729 | 0.7271 | 0.6848 |
| No log | 2.0 | 484 | 0.9894 | 0.7293 | 0.3458 | 0.6597 | 0.7293 | 0.6824 |
| 0.7769 | 3.0 | 726 | 1.0067 | 0.7205 | 0.3858 | 0.6719 | 0.7205 | 0.6898 |
| 0.7769 | 4.0 | 968 | 1.1637 | 0.7314 | 0.3937 | 0.7281 | 0.7314 | 0.7006 |
| 0.3534 | 5.0 | 1210 | 1.3002 | 0.7358 | 0.3892 | 0.7103 | 0.7358 | 0.6999 |
| 0.3534 | 6.0 | 1452 | 1.3023 | 0.7162 | 0.4029 | 0.7027 | 0.7162 | 0.6930 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.13.3