metadata
base_model: Alexander-Learn/bert-finetuned-squad
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: bert-finetuned-squad-finetuned-DouRC_squad
results: []
bert-finetuned-squad-finetuned-DouRC_squad
This model is a fine-tuned version of Alexander-Learn/bert-finetuned-squad on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2794
- Exact Match: 0.725
- F1: 0.5962
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: 72
- eval_batch_size: 72
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Exact Match | F1 |
|---|---|---|---|---|---|
| 1.1781 | 1.0 | 828 | 1.1097 | 0.72 | 0.6202 |
| 0.9177 | 2.0 | 1656 | 1.1056 | 0.715 | 0.5938 |
| 0.7366 | 3.0 | 2484 | 1.1415 | 0.715 | 0.5756 |
| 0.6056 | 4.0 | 3312 | 1.2132 | 0.71 | 0.5830 |
| 0.5191 | 5.0 | 4140 | 1.2794 | 0.725 | 0.5962 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1