metadata
library_name: transformers
license: apache-2.0
base_model: indolem/indobertweet-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: nama_model_baru
results: []
nama_model_baru
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: 0.6555
- Accuracy: 0.8836
- Precision: 0.8930
- Recall: 0.8829
- F1: 0.8867
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 |
|---|---|---|---|---|---|---|---|
| 0.5761 | 1.0 | 107 | 0.3777 | 0.8425 | 0.8475 | 0.8425 | 0.8449 |
| 0.2084 | 2.0 | 214 | 0.5319 | 0.8562 | 0.8861 | 0.8419 | 0.8518 |
| 0.0812 | 3.0 | 321 | 0.5681 | 0.8699 | 0.8763 | 0.8802 | 0.8767 |
| 0.034 | 4.0 | 428 | 0.6506 | 0.8733 | 0.8796 | 0.8733 | 0.8743 |
| 0.013 | 5.0 | 535 | 0.6555 | 0.8836 | 0.8930 | 0.8829 | 0.8867 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1