hilmansw's picture
Update README.md
e54fd87
|
raw
history blame
2.13 kB
metadata
license: mit
base_model: indobenchmark/indobert-base-p1
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: indobert-finetuned-aspect-happiness-index
    results: []
pipeline_tag: text-classification
language:
  - id
widget:
  - text: Aku senang kuliah di Undip
    example_title: Aspect Detection

indobert-finetuned-aspect-happiness-index

This model is a fine-tuned version of indobenchmark/indobert-base-p1 on an own private dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1476
  • Accuracy: 0.9732

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: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 270 0.1291 0.9648
0.301 2.0 540 0.1708 0.9593
0.301 3.0 810 0.1350 0.9685
0.0655 4.0 1080 0.1734 0.9648
0.0655 5.0 1350 0.1323 0.9713
0.023 6.0 1620 0.1551 0.9676
0.023 7.0 1890 0.1558 0.9704
0.0137 8.0 2160 0.1531 0.9732
0.0137 9.0 2430 0.1493 0.9722
0.0056 10.0 2700 0.1476 0.9732

Framework versions

  • Transformers 4.33.1
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3