metadata
license: mit
base_model: LazarusNLP/NusaBERT-base
tags:
- generated_from_trainer
datasets:
- indonlu
metrics:
- f1
model-index:
- name: NusaBERT-base-SmSA
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: indonlu
type: indonlu
config: smsa
split: validation
args: smsa
metrics:
- name: F1
type: f1
value: 0.8746
NusaBERT-base-SmSA
This model is a fine-tuned version of LazarusNLP/NusaBERT-base on the indonlu dataset. It achieves the following results on the evaluation set:
- Loss: 0.2992
- F1: 0.8746
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100
Training results
Training Loss | Epoch | Step | Validation Loss | F1 |
---|---|---|---|---|
No log | 1.0 | 344 | 0.2119 | 0.895 |
0.3517 | 2.0 | 688 | 0.1745 | 0.9193 |
0.1543 | 3.0 | 1032 | 0.1945 | 0.9135 |
0.1543 | 4.0 | 1376 | 0.1901 | 0.9149 |
0.1006 | 5.0 | 1720 | 0.2158 | 0.9172 |
0.0652 | 6.0 | 2064 | 0.2796 | 0.9151 |
0.0652 | 7.0 | 2408 | 0.3146 | 0.9164 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu118
- Datasets 2.17.1
- Tokenizers 0.15.1