mini-mlm-imdb-target-imdb
This model is a fine-tuned version of muhtasham/mini-mlm-imdb on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.1353
- Accuracy: 0.9502
- F1: 0.9744
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: 32
- eval_batch_size: 32
- 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 |
|---|---|---|---|---|---|
| 0.3856 | 0.64 | 500 | 0.1902 | 0.9298 | 0.9636 |
| 0.2794 | 1.28 | 1000 | 0.2200 | 0.9127 | 0.9544 |
| 0.2369 | 1.92 | 1500 | 0.1269 | 0.9539 | 0.9764 |
| 0.1963 | 2.56 | 2000 | 0.2422 | 0.9079 | 0.9517 |
| 0.1765 | 3.2 | 2500 | 0.3789 | 0.8644 | 0.9273 |
| 0.1486 | 3.84 | 3000 | 0.1353 | 0.9502 | 0.9744 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1
- Datasets 2.7.1
- Tokenizers 0.13.2