xlnet-tass
This model is a fine-tuned version of xlnet/xlnet-large-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0457
- F1 Macro: 0.5708
- F1 Weighted: 0.5706
- Accuracy: 0.5734
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Weighted | Accuracy |
|---|---|---|---|---|---|---|
| 1.1137 | 1.0 | 241 | 1.0906 | 0.2136 | 0.2452 | 0.3933 |
| 1.1098 | 2.0 | 482 | 1.0671 | 0.2655 | 0.2900 | 0.4225 |
| 1.0103 | 3.0 | 723 | 0.9774 | 0.5043 | 0.5091 | 0.5297 |
| 0.9301 | 4.0 | 964 | 1.0256 | 0.4825 | 0.4864 | 0.5172 |
| 0.8909 | 5.0 | 1205 | 0.9376 | 0.5445 | 0.5467 | 0.5609 |
| 0.7939 | 6.0 | 1446 | 0.9314 | 0.5798 | 0.5809 | 0.5838 |
| 0.7485 | 7.0 | 1687 | 0.9856 | 0.5631 | 0.5663 | 0.5817 |
| 0.6591 | 8.0 | 1928 | 0.9335 | 0.5862 | 0.5866 | 0.5848 |
| 0.6165 | 9.0 | 2169 | 0.9862 | 0.5753 | 0.5771 | 0.5817 |
| 0.5153 | 10.0 | 2410 | 1.0457 | 0.5708 | 0.5706 | 0.5734 |
Framework versions
- Transformers 5.13.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2