metadata
license: apache-2.0
base_model: indolem/indobertweet-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: sentiment-tapera
results: []
sentiment-tapera
This model is a fine-tuned version of indolem/indobertweet-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6966
- Accuracy: 0.8455
- Precision: 0.7812
- Recall: 0.7567
- F1: 0.7675
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: 0.0001
- 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
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.6236 | 1.0 | 90 | 0.5920 | 0.8049 | 0.5358 | 0.5904 | 0.5575 |
| 0.363 | 2.0 | 180 | 0.4065 | 0.8374 | 0.7515 | 0.7181 | 0.7322 |
| 0.1506 | 3.0 | 270 | 0.4414 | 0.8537 | 0.8191 | 0.7303 | 0.7606 |
| 0.0619 | 4.0 | 360 | 0.6592 | 0.8496 | 0.8036 | 0.7151 | 0.7420 |
| 0.0261 | 5.0 | 450 | 0.6966 | 0.8455 | 0.7812 | 0.7567 | 0.7675 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1