test_trainer_XLNET_3ep_5e-5
This model is a fine-tuned version of xlnet-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5405
- Accuracy: 0.8773
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: 5e-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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7984 | 1.0 | 1125 | 0.6647 | 0.7923 |
| 0.5126 | 2.0 | 2250 | 0.4625 | 0.862 |
| 0.409 | 3.0 | 3375 | 0.5405 | 0.8773 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2