finetuned-self_mlm_small
This model is a fine-tuned version of muhtasham/bert-small-mlm-finetuned-imdb on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.3759
- Accuracy: 0.9372
- F1: 0.9676
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: 64
- eval_batch_size: 64
- 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 |
|---|---|---|---|---|---|
| 0.2834 | 1.28 | 500 | 0.2254 | 0.9150 | 0.9556 |
| 0.1683 | 2.56 | 1000 | 0.3738 | 0.8694 | 0.9301 |
| 0.1069 | 3.84 | 1500 | 0.2102 | 0.9354 | 0.9666 |
| 0.0651 | 5.12 | 2000 | 0.2278 | 0.9446 | 0.9715 |
| 0.0412 | 6.39 | 2500 | 0.4061 | 0.9156 | 0.9559 |
| 0.0316 | 7.67 | 3000 | 0.4371 | 0.9110 | 0.9534 |
| 0.0219 | 8.95 | 3500 | 0.3759 | 0.9372 | 0.9676 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2