|
--- |
|
language: |
|
- en |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- glue |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: first_try |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: GLUE QQP |
|
type: glue |
|
config: qqp |
|
split: validation |
|
args: qqp |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9094978976007915 |
|
- name: F1 |
|
type: f1 |
|
value: 0.8781916841439461 |
|
--- |
|
|
|
<!-- 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 QQP dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2975 |
|
- Accuracy: 0.9095 |
|
- F1: 0.8782 |
|
- Combined Score: 0.8938 |
|
|
|
## 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 | F1 | Combined Score | | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:| |
|
| 0.3347 | 1.0 | 11371 | 0.2781 | 0.8986 | 0.8645 | 0.8816 | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 320, 1: 256, 2: 320, 3: 192, 4: 256, 5: 256, 6: 192, 7: 256, 8: 64, 9: 192, 10: 192, 11: 512, 12: 1675, 13: 1666, 14: 1787, 15: 1791, 16: 1772, 17: 1751, 18: 1709, 19: 1590, 20: 1320, 21: 762, 22: 348, 23: 115})]) | |
|
| 0.3347 | 1.0 | 11371 | 0.2633 | 0.9022 | 0.8709 | 0.8865 | 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})]) | |
|
| 0.1664 | 2.0 | 22742 | 0.2724 | 0.9048 | 0.8736 | 0.8892 | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 320, 1: 256, 2: 320, 3: 192, 4: 256, 5: 256, 6: 192, 7: 256, 8: 64, 9: 192, 10: 192, 11: 512, 12: 1675, 13: 1666, 14: 1787, 15: 1791, 16: 1772, 17: 1751, 18: 1709, 19: 1590, 20: 1320, 21: 762, 22: 348, 23: 115})]) | |
|
| 0.1664 | 2.0 | 22742 | 0.2665 | 0.9106 | 0.8809 | 0.8958 | 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})]) | |
|
| 0.092 | 3.0 | 34113 | 0.2872 | 0.9094 | 0.8786 | 0.8940 | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 320, 1: 256, 2: 320, 3: 192, 4: 256, 5: 256, 6: 192, 7: 256, 8: 64, 9: 192, 10: 192, 11: 512, 12: 1675, 13: 1666, 14: 1787, 15: 1791, 16: 1772, 17: 1751, 18: 1709, 19: 1590, 20: 1320, 21: 762, 22: 348, 23: 115})]) | |
|
| 0.092 | 3.0 | 34113 | 0.2708 | 0.9141 | 0.8846 | 0.8994 | 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})]) | |
|
| 0.0693 | 4.0 | 45484 | 0.2966 | 0.9088 | 0.8771 | 0.8930 | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 320, 1: 256, 2: 320, 3: 192, 4: 256, 5: 256, 6: 192, 7: 256, 8: 64, 9: 192, 10: 192, 11: 512, 12: 1675, 13: 1666, 14: 1787, 15: 1791, 16: 1772, 17: 1751, 18: 1709, 19: 1590, 20: 1320, 21: 762, 22: 348, 23: 115})]) | |
|
| 0.0693 | 4.0 | 45484 | 0.2779 | 0.9144 | 0.8846 | 0.8995 | 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 |
|
|
