|
--- |
|
license: mit |
|
base_model: indobenchmark/indobert-base-p2 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: performa_model |
|
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. --> |
|
|
|
# performa_model |
|
|
|
This model is a fine-tuned version of [indobenchmark/indobert-base-p2](https://huggingface.co/indobenchmark/indobert-base-p2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5465 |
|
- Accuracy: 0.8122 |
|
- F1: 0.8102 |
|
- Precision: 0.8105 |
|
- Recall: 0.8100 |
|
|
|
## 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: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| No log | 0.14 | 50 | 0.4595 | 0.7946 | 0.7926 | 0.7926 | 0.7926 | |
|
| No log | 0.27 | 100 | 0.4523 | 0.7946 | 0.7946 | 0.7995 | 0.8009 | |
|
| No log | 0.41 | 150 | 0.4501 | 0.8122 | 0.8098 | 0.8110 | 0.8089 | |
|
| No log | 0.54 | 200 | 0.4676 | 0.7811 | 0.7709 | 0.7965 | 0.7678 | |
|
| No log | 0.68 | 250 | 0.4551 | 0.8135 | 0.8099 | 0.8149 | 0.8077 | |
|
| No log | 0.81 | 300 | 0.4422 | 0.8162 | 0.8152 | 0.8146 | 0.8168 | |
|
| No log | 0.95 | 350 | 0.4336 | 0.8162 | 0.8137 | 0.8154 | 0.8126 | |
|
| No log | 1.08 | 400 | 0.4645 | 0.8189 | 0.8164 | 0.8182 | 0.8153 | |
|
| No log | 1.22 | 450 | 0.4805 | 0.8243 | 0.8236 | 0.8231 | 0.8258 | |
|
| 0.4139 | 1.35 | 500 | 0.4984 | 0.8068 | 0.8053 | 0.8048 | 0.8061 | |
|
| 0.4139 | 1.49 | 550 | 0.4506 | 0.8149 | 0.8137 | 0.8131 | 0.8148 | |
|
| 0.4139 | 1.62 | 600 | 0.4364 | 0.8216 | 0.8201 | 0.8198 | 0.8204 | |
|
| 0.4139 | 1.76 | 650 | 0.4889 | 0.7892 | 0.7892 | 0.7992 | 0.7978 | |
|
| 0.4139 | 1.89 | 700 | 0.4348 | 0.8108 | 0.8105 | 0.8114 | 0.8143 | |
|
| 0.4139 | 2.03 | 750 | 0.4537 | 0.8068 | 0.8056 | 0.8050 | 0.8069 | |
|
| 0.4139 | 2.16 | 800 | 0.5296 | 0.7905 | 0.7905 | 0.7947 | 0.7964 | |
|
| 0.4139 | 2.3 | 850 | 0.5819 | 0.7946 | 0.7943 | 0.7955 | 0.7982 | |
|
| 0.4139 | 2.43 | 900 | 0.5868 | 0.8122 | 0.8110 | 0.8104 | 0.8124 | |
|
| 0.4139 | 2.57 | 950 | 0.5613 | 0.8081 | 0.8050 | 0.8081 | 0.8034 | |
|
| 0.2978 | 2.7 | 1000 | 0.5465 | 0.8122 | 0.8102 | 0.8105 | 0.8100 | |
|
| 0.2978 | 2.84 | 1050 | 0.5665 | 0.8041 | 0.8022 | 0.8022 | 0.8023 | |
|
| 0.2978 | 2.97 | 1100 | 0.5876 | 0.7932 | 0.7924 | 0.7921 | 0.7946 | |
|
| 0.2978 | 3.11 | 1150 | 0.7388 | 0.8014 | 0.8000 | 0.7994 | 0.8009 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|