metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- indonlu
metrics:
- accuracy
- f1
model-index:
- name: distilled-optimized-indobert-classification
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: indonlu
type: indonlu
args: smsa
metrics:
- name: Accuracy
type: accuracy
value: 0.8944444444444445
- name: F1
type: f1
value: 0.89395273315396
distilled-optimized-indobert-classification
This model is a fine-tuned version of distilbert-base-uncased on the indonlu dataset. It achieves the following results on the evaluation set:
- Loss: 0.7098
- Accuracy: 0.8944
- F1: 0.8940
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: 4.315104717136378e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 33
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 9
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.5386 | 1.0 | 688 | 1.0026 | 0.8325 | 0.8332 |
| 0.8165 | 2.0 | 1376 | 0.7364 | 0.8786 | 0.8782 |
| 0.4755 | 3.0 | 2064 | 0.8695 | 0.8794 | 0.8767 |
| 0.3011 | 4.0 | 2752 | 0.8100 | 0.8921 | 0.8899 |
| 0.1963 | 5.0 | 3440 | 0.8074 | 0.8960 | 0.8954 |
| 0.1312 | 6.0 | 4128 | 0.8235 | 0.8897 | 0.8906 |
| 0.0974 | 7.0 | 4816 | 0.7395 | 0.9063 | 0.9067 |
| 0.0716 | 8.0 | 5504 | 0.7185 | 0.8960 | 0.8953 |
| 0.0512 | 9.0 | 6192 | 0.7098 | 0.8944 | 0.8940 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.1.0
- Tokenizers 0.12.1