| | --- |
| | license: mit |
| | base_model: hung200504/bert-squadv2 |
| | tags: |
| | - generated_from_trainer |
| | model-index: |
| | - name: bert-covid-21 |
| | results: [] |
| | --- |
| | |
| | <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| | should probably proofread and complete it, then remove this comment. --> |
| |
|
| | # bert-covid-21 |
| |
|
| | This model is a fine-tuned version of [hung200504/bert-squadv2](https://huggingface.co/hung200504/bert-squadv2) on an unknown dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 0.6103 |
| |
|
| | ## 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: 8 |
| | - eval_batch_size: 8 |
| | - 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 | |
| | |:-------------:|:-----:|:----:|:---------------:| |
| | | 4.2561 | 0.03 | 5 | 1.1801 | |
| | | 1.1175 | 0.06 | 10 | 0.9406 | |
| | | 1.2258 | 0.08 | 15 | 0.7456 | |
| | | 0.8306 | 0.11 | 20 | 0.5948 | |
| | | 0.5743 | 0.14 | 25 | 0.5835 | |
| | | 0.4958 | 0.17 | 30 | 0.7125 | |
| | | 0.4448 | 0.2 | 35 | 0.6664 | |
| | | 0.8538 | 0.22 | 40 | 0.7098 | |
| | | 0.8115 | 0.25 | 45 | 0.6869 | |
| | | 0.9364 | 0.28 | 50 | 0.5814 | |
| | | 1.0413 | 0.31 | 55 | 0.5434 | |
| | | 0.7219 | 0.34 | 60 | 0.5274 | |
| | | 0.6852 | 0.37 | 65 | 0.5764 | |
| | | 0.4603 | 0.39 | 70 | 0.6586 | |
| | | 0.8428 | 0.42 | 75 | 0.7742 | |
| | | 0.3679 | 0.45 | 80 | 0.7430 | |
| | | 1.0074 | 0.48 | 85 | 0.6630 | |
| | | 0.8531 | 0.51 | 90 | 0.5403 | |
| | | 0.4513 | 0.53 | 95 | 0.5452 | |
| | | 0.3039 | 0.56 | 100 | 0.6193 | |
| | | 1.7221 | 0.59 | 105 | 0.6734 | |
| | | 0.8286 | 0.62 | 110 | 0.5892 | |
| | | 0.6836 | 0.65 | 115 | 0.5413 | |
| | | 0.2059 | 0.67 | 120 | 0.5407 | |
| | | 0.8272 | 0.7 | 125 | 0.5446 | |
| | | 0.3456 | 0.73 | 130 | 0.5652 | |
| | | 1.1423 | 0.76 | 135 | 0.5697 | |
| | | 0.2456 | 0.79 | 140 | 0.5737 | |
| | | 0.7639 | 0.81 | 145 | 0.5767 | |
| | | 0.5946 | 0.84 | 150 | 0.5565 | |
| | | 0.0976 | 0.87 | 155 | 0.5857 | |
| | | 0.3246 | 0.9 | 160 | 0.6162 | |
| | | 1.039 | 0.93 | 165 | 0.6297 | |
| | | 0.6297 | 0.96 | 170 | 0.6217 | |
| | | 1.1724 | 0.98 | 175 | 0.6103 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.34.1 |
| | - Pytorch 2.1.0+cu118 |
| | - Datasets 2.14.6 |
| | - Tokenizers 0.14.1 |
| |
|
