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_indobertweet
results: []
indo_sentiment_indobertweet
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: 0.1473
- Accuracy: 0.9655
- Precision: 0.9649
- Recall: 0.9603
- F1: 0.9625
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.1977 | 1.0 | 248 | 0.1372 | 0.9541 | 0.9570 | 0.9433 | 0.9495 |
| 0.0902 | 2.0 | 496 | 0.1201 | 0.9638 | 0.9645 | 0.9568 | 0.9604 |
| 0.036 | 3.0 | 744 | 0.1473 | 0.9655 | 0.9649 | 0.9603 | 0.9625 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1