# Load model directly
from transformers import AutoTokenizer, AutoModelForQuestionAnswering
tokenizer = AutoTokenizer.from_pretrained("hung200504/bert-covidqa")
model = AutoModelForQuestionAnswering.from_pretrained("hung200504/bert-covidqa")Quick Links
bert-covidqa
This model is a fine-tuned version of phiyodr/bert-base-finetuned-squad2 on the covid_qa_deepset dataset. It achieves the following results on the evaluation set:
- Loss: 0.6451
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: 3e-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: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5829 | 0.04 | 5 | 1.0001 |
| 0.7899 | 0.09 | 10 | 0.7849 |
| 0.5929 | 0.13 | 15 | 0.7851 |
| 0.691 | 0.18 | 20 | 0.7549 |
| 0.6383 | 0.22 | 25 | 0.7199 |
| 0.3216 | 0.26 | 30 | 0.7625 |
| 0.3273 | 0.31 | 35 | 0.8644 |
| 0.5909 | 0.35 | 40 | 0.7117 |
| 0.2556 | 0.39 | 45 | 0.6681 |
| 0.6896 | 0.44 | 50 | 0.7138 |
| 0.6066 | 0.48 | 55 | 0.6614 |
| 0.2602 | 0.53 | 60 | 0.6791 |
| 0.4034 | 0.57 | 65 | 0.7168 |
| 0.5511 | 0.61 | 70 | 0.7783 |
| 0.6313 | 0.66 | 75 | 0.7269 |
| 0.261 | 0.7 | 80 | 0.7106 |
| 0.4904 | 0.75 | 85 | 0.6735 |
| 0.4706 | 0.79 | 90 | 0.6370 |
| 0.4174 | 0.83 | 95 | 0.6355 |
| 0.3762 | 0.88 | 100 | 0.6356 |
| 0.5128 | 0.92 | 105 | 0.6429 |
| 0.553 | 0.96 | 110 | 0.6451 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
- Downloads last month
- 11
Model tree for hung200504/bert-covidqa
Base model
phiyodr/bert-base-finetuned-squad2
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="hung200504/bert-covidqa")