single_label_N_max_long_training
This model is a fine-tuned version of distilbert-base-uncased on the squad dataset. It achieves the following results on the evaluation set:
- Loss: 2.8288
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.0568 | 1.0 | 674 | 1.9993 |
| 1.6024 | 2.0 | 1348 | 1.8497 |
| 1.0196 | 3.0 | 2022 | 1.9178 |
| 0.7622 | 4.0 | 2696 | 2.0412 |
| 0.6066 | 5.0 | 3370 | 2.2523 |
| 0.4136 | 6.0 | 4044 | 2.3845 |
| 0.3113 | 7.0 | 4718 | 2.5712 |
| 0.2777 | 8.0 | 5392 | 2.6790 |
| 0.208 | 9.0 | 6066 | 2.7464 |
| 0.1749 | 10.0 | 6740 | 2.8288 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.2.1
- Tokenizers 0.12.1