metadata
license: gpl-3.0
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: test2
results: []
pipeline_tag: text-classification
test2
This model is a fine-tuned version of jcblaise/bert-tagalog-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4185
- Accuracy: 0.8669
- Precision: 0.8249
- Recall: 0.8612
- F1: 0.8426
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: 1e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 172 | 0.3674 | 0.8444 | 0.8014 | 0.8295 | 0.8152 |
| No log | 2.0 | 344 | 0.3508 | 0.8542 | 0.8235 | 0.8243 | 0.8239 |
| 0.2992 | 3.0 | 516 | 0.3643 | 0.8564 | 0.8596 | 0.7803 | 0.8181 |
| 0.2992 | 4.0 | 688 | 0.3639 | 0.8622 | 0.8155 | 0.8620 | 0.8381 |
| 0.2992 | 5.0 | 860 | 0.3803 | 0.864 | 0.8316 | 0.8418 | 0.8367 |
| 0.1733 | 6.0 | 1032 | 0.3969 | 0.8702 | 0.8352 | 0.8550 | 0.8450 |
| 0.1733 | 7.0 | 1204 | 0.4185 | 0.8669 | 0.8249 | 0.8612 | 0.8426 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Tokenizers 0.13.2