BART_subjqa_model_v1
This model is a fine-tuned version of valhalla/bart-large-finetuned-squadv1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.6023
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: 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 410 | 2.3429 |
| 2.5714 | 2.0 | 820 | 2.5999 |
| 1.837 | 3.0 | 1230 | 2.9671 |
| 1.044 | 4.0 | 1640 | 3.8481 |
| 0.5292 | 5.0 | 2050 | 4.6023 |
Framework versions
- Transformers 4.28.0
- Pytorch 1.13.0a0+d321be6
- Datasets 2.12.0
- Tokenizers 0.13.3