metadata
license: mit
tags:
- generated_from_trainer
datasets:
- indonlu
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: sentiment_model
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: indonlu
type: indonlu
config: emot
split: validation
args: emot
metrics:
- name: Accuracy
type: accuracy
value: 0.7363636363636363
- name: Precision
type: precision
value: 0.7397155596092384
- name: Recall
type: recall
value: 0.7459489407651173
- name: F1
type: f1
value: 0.741920437379511
sentiment_model
This model is a fine-tuned version of indolem/indobert-base-uncased on the indonlu dataset. It achieves the following results on the evaluation set:
- Loss: 0.7788
- Accuracy: 0.7364
- Precision: 0.7397
- Recall: 0.7459
- F1: 0.7419
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 1.1939 | 1.0 | 221 | 0.8261 | 0.6932 | 0.7203 | 0.7034 | 0.7056 |
| 0.6866 | 2.0 | 442 | 0.7925 | 0.725 | 0.7378 | 0.7377 | 0.7346 |
| 0.4791 | 3.0 | 663 | 0.7788 | 0.7364 | 0.7397 | 0.7459 | 0.7419 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3