metadata
license: mit
base_model: csarron/bert-base-uncased-squad-v1
tags:
- generated_from_trainer
model-index:
- name: bert-base-uncased-finetuned-squad-finetuned-nq
results: []
bert-base-uncased-finetuned-squad-finetuned-nq
This model is a fine-tuned version of csarron/bert-base-uncased-squad-v1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8659
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
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9034 | 1.0 | 9257 | 0.7792 |
| 0.6824 | 2.0 | 18514 | 0.7696 |
| 0.5353 | 3.0 | 27771 | 0.8659 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1