absa_aspect_extractor
This model is a fine-tuned version of yangheng/deberta-v3-base-end2end-absa on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1436
- Precision: 0.5802
- Recall: 0.4227
- F1: 0.4891
- Accuracy: 0.9362
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 303 | 0.1357 | 0.5592 | 0.4069 | 0.4711 | 0.9403 |
| 0.1231 | 2.0 | 606 | 0.1390 | 0.5457 | 0.4224 | 0.4762 | 0.9378 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.2.0
- Tokenizers 0.22.1