<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
distilbert-base-uncased-finetuned-squad-qa
This model is a fine-tuned version of EricPeter/distilbert-base-uncased-finetuned-squad on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.6656
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: 20
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
No log | 1.0 | 57 | 2.0140 |
No log | 2.0 | 114 | 2.0078 |
No log | 3.0 | 171 | 1.9940 |
No log | 4.0 | 228 | 2.2072 |
No log | 5.0 | 285 | 2.3538 |
No log | 6.0 | 342 | 2.3988 |
No log | 7.0 | 399 | 2.5309 |
No log | 8.0 | 456 | 2.7524 |
1.3301 | 9.0 | 513 | 2.9685 |
1.3301 | 10.0 | 570 | 3.1665 |
1.3301 | 11.0 | 627 | 3.1134 |
1.3301 | 12.0 | 684 | 3.3792 |
1.3301 | 13.0 | 741 | 3.2990 |
1.3301 | 14.0 | 798 | 3.4498 |
1.3301 | 15.0 | 855 | 3.4019 |
1.3301 | 16.0 | 912 | 3.4137 |
1.3301 | 17.0 | 969 | 3.6699 |
0.2401 | 18.0 | 1026 | 3.6200 |
0.2401 | 19.0 | 1083 | 3.5943 |
0.2401 | 20.0 | 1140 | 3.6656 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3