metadata
license: apache-2.0
base_model: indolem/indobertweet-base-uncased
tags:
- generated_from_trainer
model-index:
- name: buburayam2024_indobtwt_7_overunder
results: []
buburayam2024_indobtwt_7_overunder
This model is a fine-tuned version of indolem/indobertweet-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0210
- F1 macro: 0.3275
- Weighted: 0.4492
- Balanced accuracy: 0.4916
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 | F1 macro | Weighted | Balanced accuracy |
|---|---|---|---|---|---|---|
| 1.9685 | 1.0 | 43 | 1.7035 | 0.1920 | 0.4257 | 0.2649 |
| 1.4692 | 2.0 | 86 | 1.5573 | 0.2713 | 0.4184 | 0.4311 |
| 0.8033 | 3.0 | 129 | 1.4403 | 0.3597 | 0.5636 | 0.5084 |
| 0.3962 | 4.0 | 172 | 1.6567 | 0.3514 | 0.4921 | 0.5171 |
| 0.1335 | 5.0 | 215 | 1.9523 | 0.3306 | 0.4306 | 0.5034 |
| 0.0797 | 6.0 | 258 | 2.1614 | 0.3126 | 0.4075 | 0.4914 |
| 0.0392 | 7.0 | 301 | 2.0210 | 0.3275 | 0.4492 | 0.4916 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1