finetuned-base_small_db
This model is a fine-tuned version of google/bert_uncased_L-4_H-512_A-8 on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.2838
- Accuracy: 0.9351
- F1: 0.9665
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: 3e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 200
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.2743 | 2.55 | 500 | 0.1548 | 0.9408 | 0.9695 |
| 0.1227 | 5.1 | 1000 | 0.2545 | 0.9206 | 0.9586 |
| 0.0569 | 7.65 | 1500 | 0.4467 | 0.8902 | 0.9419 |
| 0.0316 | 10.2 | 2000 | 0.2838 | 0.9351 | 0.9665 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2