metadata
license: mit
base_model: ryantaw/bert-small-finetuned
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert-small-finetuned-finetuned
results: []
bert-small-finetuned-finetuned
This model is a fine-tuned version of ryantaw/bert-small-finetuned on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8577
- Accuracy: 0.6846
- F1 Score: 0.6854
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: 2e-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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Score |
|---|---|---|---|---|---|
| No log | 1.0 | 186 | 0.8402 | 0.6577 | 0.6553 |
| No log | 2.0 | 372 | 0.8577 | 0.6846 | 0.6854 |
| 0.7061 | 3.0 | 558 | 0.9049 | 0.6415 | 0.6367 |
| 0.7061 | 4.0 | 744 | 0.9252 | 0.6631 | 0.6625 |
| 0.7061 | 5.0 | 930 | 1.0010 | 0.6685 | 0.6670 |
| 0.3613 | 6.0 | 1116 | 1.1754 | 0.6199 | 0.6130 |
| 0.3613 | 7.0 | 1302 | 1.2138 | 0.6604 | 0.6592 |
| 0.3613 | 8.0 | 1488 | 1.3055 | 0.6604 | 0.6583 |
| 0.1426 | 9.0 | 1674 | 1.3710 | 0.6523 | 0.6495 |
| 0.1426 | 10.0 | 1860 | 1.3899 | 0.6550 | 0.6529 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1