cf-longformer-finetuned_v
This model is a fine-tuned version of allenai/longformer-base-4096 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5359
- F1: 0.6086
- Roc Auc: 0.7423
- Accuracy: 0.2768
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 500
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.6629 | 1.0 | 434 | 0.6679 | 0.4736 | 0.6372 | 0.0751 |
| 0.5338 | 2.0 | 868 | 0.5600 | 0.5979 | 0.7311 | 0.2390 |
| 0.4899 | 3.0 | 1302 | 0.5366 | 0.6158 | 0.7445 | 0.2702 |
| 0.4291 | 4.0 | 1736 | 0.5252 | 0.6293 | 0.7556 | 0.2898 |
| 0.4442 | 5.0 | 2170 | 0.5304 | 0.6273 | 0.7551 | 0.2979 |
| 0.301 | 6.0 | 2604 | 0.5593 | 0.6255 | 0.7522 | 0.2968 |
| 0.2634 | 7.0 | 3038 | 0.5765 | 0.6269 | 0.7537 | 0.3048 |
| 0.248 | 8.0 | 3472 | 0.5779 | 0.6277 | 0.7544 | 0.3037 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1