metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: BERTModelQA2
results: []
BERTModelQA2
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: 2.1894
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 |
|---|---|---|---|
| 2.7749 | 1.0 | 563 | 1.6499 |
| 1.3956 | 2.0 | 1126 | 1.4280 |
| 1.0094 | 3.0 | 1689 | 1.4128 |
| 0.7522 | 4.0 | 2252 | 1.5635 |
| 0.5826 | 5.0 | 2815 | 1.6302 |
| 0.4356 | 6.0 | 3378 | 1.7976 |
| 0.3399 | 7.0 | 3941 | 1.9001 |
| 0.2234 | 8.0 | 4504 | 2.0518 |
| 0.1806 | 9.0 | 5067 | 2.1244 |
| 0.1543 | 10.0 | 5630 | 2.1894 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.0
- Tokenizers 0.13.2