metadata
license: apache-2.0
base_model: indolem/indobertweet-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: indo_sentiment_indobertbdc
results: []
indo_sentiment_indobertbdc
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: 0.8227
- Accuracy: 0.8234
- Precision: 0.6493
- Recall: 0.5790
- F1: 0.6035
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 |
|---|---|---|---|---|---|---|---|
| 0.9616 | 1.0 | 110 | 0.6410 | 0.8084 | 0.5908 | 0.5401 | 0.5498 |
| 0.5537 | 2.0 | 220 | 0.6940 | 0.7994 | 0.5502 | 0.5731 | 0.5501 |
| 0.311 | 3.0 | 330 | 0.7103 | 0.8104 | 0.6113 | 0.5502 | 0.5690 |
| 0.1748 | 4.0 | 440 | 0.8169 | 0.8174 | 0.6415 | 0.5875 | 0.6008 |
| 0.0996 | 5.0 | 550 | 0.8227 | 0.8234 | 0.6493 | 0.5790 | 0.6035 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1