metadata
license: mit
base_model: w11wo/indonesian-roberta-base-sentiment-classifier
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: train-reward-training
results: []
train-reward-training
This model is a fine-tuned version of w11wo/indonesian-roberta-base-sentiment-classifier on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3383
- Accuracy: 0.8673
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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.711 | 0.54 | 50 | 0.6858 | 0.8061 |
| 0.6942 | 1.08 | 100 | 0.6390 | 0.8469 |
| 0.586 | 1.61 | 150 | 0.4498 | 0.8673 |
| 0.4693 | 2.15 | 200 | 0.3464 | 0.8571 |
| 0.3404 | 2.69 | 250 | 0.3004 | 0.8673 |
| 0.3255 | 3.23 | 300 | 0.3514 | 0.8776 |
| 0.2332 | 3.76 | 350 | 0.3435 | 0.8776 |
| 0.1865 | 4.3 | 400 | 0.3013 | 0.8673 |
| 0.1552 | 4.84 | 450 | 0.2979 | 0.8878 |
| 0.1214 | 5.38 | 500 | 0.3166 | 0.8878 |
| 0.1284 | 5.91 | 550 | 0.3407 | 0.8673 |
| 0.0971 | 6.45 | 600 | 0.3490 | 0.8776 |
| 0.0953 | 6.99 | 650 | 0.3269 | 0.8673 |
| 0.0728 | 7.53 | 700 | 0.3388 | 0.8673 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.15.2