|
--- |
|
license: mit |
|
base_model: indolem/indobert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- indonlu_nergrit |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: belajarner |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: indonlu_nergrit |
|
type: indonlu_nergrit |
|
config: indonlu_nergrit_source |
|
split: validation |
|
args: indonlu_nergrit_source |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.8400335008375209 |
|
- name: Recall |
|
type: recall |
|
value: 0.8631669535283993 |
|
- name: F1 |
|
type: f1 |
|
value: 0.8514431239388794 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.949652118912081 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# belajarner |
|
|
|
This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on the indonlu_nergrit dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2914 |
|
- Precision: 0.8400 |
|
- Recall: 0.8632 |
|
- F1: 0.8514 |
|
- Accuracy: 0.9497 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 8 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 209 | 0.2655 | 0.8163 | 0.8718 | 0.8431 | 0.9424 | |
|
| No log | 2.0 | 418 | 0.2315 | 0.8146 | 0.8546 | 0.8341 | 0.9486 | |
|
| 0.04 | 3.0 | 627 | 0.2466 | 0.8291 | 0.8640 | 0.8462 | 0.9470 | |
|
| 0.04 | 4.0 | 836 | 0.2412 | 0.8322 | 0.8623 | 0.8470 | 0.9503 | |
|
| 0.03 | 5.0 | 1045 | 0.2636 | 0.8386 | 0.8898 | 0.8635 | 0.9521 | |
|
| 0.03 | 6.0 | 1254 | 0.2830 | 0.8399 | 0.8623 | 0.8510 | 0.9497 | |
|
| 0.03 | 7.0 | 1463 | 0.2848 | 0.8376 | 0.8657 | 0.8515 | 0.9500 | |
|
| 0.013 | 8.0 | 1672 | 0.2914 | 0.8400 | 0.8632 | 0.8514 | 0.9497 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.2 |
|
|
