metadata
license: apache-2.0
base_model: indolem/indobertweet-base-uncased
tags:
- generated_from_trainer
model-index:
- name: topic-classification-tweet-12
results: []
topic-classification-tweet-12
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: 1.3923
- Balanced Accuracy: 0.5496
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Balanced Accuracy |
|---|---|---|---|---|
| 0.909 | 1.0 | 502 | 0.7448 | 0.5030 |
| 0.5271 | 2.0 | 1004 | 0.8620 | 0.4808 |
| 0.3275 | 3.0 | 1506 | 1.0028 | 0.5423 |
| 0.1935 | 4.0 | 2008 | 1.2544 | 0.5398 |
| 0.121 | 5.0 | 2510 | 1.3225 | 0.5354 |
| 0.0871 | 6.0 | 3012 | 1.3923 | 0.5496 |
| 0.0635 | 7.0 | 3514 | 1.4081 | 0.5376 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1