squad_a_only_train5_redo
This model is a fine-tuned version of grakshit/squad_a_only_train5 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9986
- Accuracy: 0.7699
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: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.3698 | 1.0 | 1188 | 0.5654 | 0.728 |
0.293 | 2.0 | 2376 | 0.6748 | 0.7682 |
0.2379 | 3.0 | 3564 | 0.7829 | 0.7575 |
0.1946 | 4.0 | 4752 | 0.9986 | 0.7699 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
- Downloads last month
- 4