metadata
license: mit
base_model: w11wo/indo-roberta-small
tags:
- generated_from_trainer
datasets:
- indonlu
metrics:
- accuracy
model-index:
- name: indo-roberta-small-finetuned-indonlu-smsa
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: indonlu
type: indonlu
config: smsa
split: validation
args: smsa
metrics:
- name: Accuracy
type: accuracy
value: 0.8809523809523809
indo-roberta-small-finetuned-indonlu-smsa
This model is a fine-tuned version of w11wo/indo-roberta-small on the indonlu dataset. It achieves the following results on the evaluation set:
- Loss: 0.4075
- Accuracy: 0.8810
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: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2000
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 1.0 | 344 | 0.6672 | 0.7103 |
0.7802 | 2.0 | 688 | 0.4828 | 0.8111 |
0.4817 | 3.0 | 1032 | 0.4378 | 0.8278 |
0.4817 | 4.0 | 1376 | 0.3920 | 0.8540 |
0.3703 | 5.0 | 1720 | 0.4251 | 0.8524 |
0.2826 | 6.0 | 2064 | 0.3883 | 0.8659 |
0.2826 | 7.0 | 2408 | 0.3782 | 0.8698 |
0.2024 | 8.0 | 2752 | 0.3932 | 0.8698 |
0.1429 | 9.0 | 3096 | 0.4075 | 0.8810 |
0.1429 | 10.0 | 3440 | 0.4257 | 0.8738 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2