|
|
--- |
|
|
language: |
|
|
- en |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- glue |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: first_try |
|
|
results: |
|
|
- task: |
|
|
name: Text Classification |
|
|
type: text-classification |
|
|
dataset: |
|
|
name: GLUE QNLI |
|
|
type: glue |
|
|
config: qnli |
|
|
split: validation |
|
|
args: qnli |
|
|
metrics: |
|
|
- name: Accuracy |
|
|
type: accuracy |
|
|
value: 0.8973091707852828 |
|
|
--- |
|
|
|
|
|
<!-- 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. --> |
|
|
|
|
|
# first_try |
|
|
|
|
|
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE QNLI dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.5902 |
|
|
- Accuracy: 0.8973 |
|
|
|
|
|
## 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: 32 |
|
|
- eval_batch_size: 128 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 6 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:| |
|
|
| 0.8032 | 1.0 | 3274 | 0.3192 | 0.8891 | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 320, 2: 320, 3: 576, 4: 576, 5: 512, 6: 448, 7: 448, 8: 448, 9: 320, 10: 384, 11: 448, 12: 1104, 13: 1066, 14: 1126, 15: 1102, 16: 1067, 17: 1023, 18: 1048, 19: 1061, 20: 984, 21: 772, 22: 609, 23: 205})]) | |
|
|
| 0.8032 | 1.0 | 3274 | 0.2594 | 0.9059 | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})]) | |
|
|
| 0.5165 | 2.0 | 6548 | 0.3693 | 0.8925 | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 320, 2: 320, 3: 576, 4: 576, 5: 512, 6: 448, 7: 448, 8: 448, 9: 320, 10: 384, 11: 448, 12: 1104, 13: 1066, 14: 1126, 15: 1102, 16: 1067, 17: 1023, 18: 1048, 19: 1061, 20: 984, 21: 772, 22: 609, 23: 205})]) | |
|
|
| 0.5165 | 2.0 | 6548 | 0.2860 | 0.9200 | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})]) | |
|
|
| 0.2972 | 3.0 | 9822 | 0.4699 | 0.8949 | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 320, 2: 320, 3: 576, 4: 576, 5: 512, 6: 448, 7: 448, 8: 448, 9: 320, 10: 384, 11: 448, 12: 1104, 13: 1066, 14: 1126, 15: 1102, 16: 1067, 17: 1023, 18: 1048, 19: 1061, 20: 984, 21: 772, 22: 609, 23: 205})]) | |
|
|
| 0.2972 | 3.0 | 9822 | 0.3910 | 0.9162 | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})]) | |
|
|
| 0.1611 | 4.0 | 13096 | 0.5542 | 0.8964 | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 320, 2: 320, 3: 576, 4: 576, 5: 512, 6: 448, 7: 448, 8: 448, 9: 320, 10: 384, 11: 448, 12: 1104, 13: 1066, 14: 1126, 15: 1102, 16: 1067, 17: 1023, 18: 1048, 19: 1061, 20: 984, 21: 772, 22: 609, 23: 205})]) | |
|
|
| 0.1611 | 4.0 | 13096 | 0.4473 | 0.9160 | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})]) | |
|
|
| 0.1155 | 5.0 | 16370 | 0.5926 | 0.8969 | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 320, 2: 320, 3: 576, 4: 576, 5: 512, 6: 448, 7: 448, 8: 448, 9: 320, 10: 384, 11: 448, 12: 1104, 13: 1066, 14: 1126, 15: 1102, 16: 1067, 17: 1023, 18: 1048, 19: 1061, 20: 984, 21: 772, 22: 609, 23: 205})]) | |
|
|
| 0.1155 | 5.0 | 16370 | 0.4788 | 0.9180 | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})]) | |
|
|
| 0.0867 | 6.0 | 19644 | 0.6002 | 0.8958 | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 320, 2: 320, 3: 576, 4: 576, 5: 512, 6: 448, 7: 448, 8: 448, 9: 320, 10: 384, 11: 448, 12: 1104, 13: 1066, 14: 1126, 15: 1102, 16: 1067, 17: 1023, 18: 1048, 19: 1061, 20: 984, 21: 772, 22: 609, 23: 205})]) | |
|
|
| 0.0867 | 6.0 | 19644 | 0.4831 | 0.9176 | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 768, 1: 768, 2: 768, 3: 768, 4: 768, 5: 768, 6: 768, 7: 768, 8: 768, 9: 768, 10: 768, 11: 768, 12: 3072, 13: 3072, 14: 3072, 15: 3072, 16: 3072, 17: 3072, 18: 3072, 19: 3072, 20: 3072, 21: 3072, 22: 3072, 23: 3072})]) | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.29.1 |
|
|
- Pytorch 1.12.1 |
|
|
- Datasets 2.13.1 |
|
|
- Tokenizers 0.13.3 |
|
|
|
