IMDB_XLNET_5E
This model is a fine-tuned version of xlnet-base-cased on the imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.3195
- Accuracy: 0.94
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3192 | 0.63 | 50 | 0.2033 | 0.94 |
| 0.196 | 1.27 | 100 | 0.2036 | 0.9467 |
| 0.1651 | 1.9 | 150 | 0.2106 | 0.9267 |
| 0.0628 | 2.53 | 200 | 0.3531 | 0.92 |
| 0.0865 | 3.16 | 250 | 0.2186 | 0.9533 |
| 0.0436 | 3.8 | 300 | 0.2718 | 0.9533 |
| 0.0254 | 4.43 | 350 | 0.3195 | 0.94 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.0
- Datasets 2.6.1
- Tokenizers 0.13.1