metadata
license: apache-2.0
base_model: indolem/indobertweet-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: digidawfinal1
results: []
digidawfinal1
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: 0.7436
- Accuracy: 0.7997
- Precision: 0.6770
- Recall: 0.5562
- F1: 0.5692
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 |
|---|---|---|---|---|---|---|---|
| 0.9382 | 1.0 | 110 | 0.7230 | 0.7797 | 0.5441 | 0.4990 | 0.5122 |
| 0.5261 | 2.0 | 220 | 0.7172 | 0.7850 | 0.5485 | 0.5116 | 0.5248 |
| 0.2929 | 3.0 | 330 | 0.7436 | 0.7997 | 0.6770 | 0.5562 | 0.5692 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1