|
--- |
|
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 MNLI |
|
type: glue |
|
config: mnli |
|
split: validation_matched |
|
args: mnli |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.8417412530512612 |
|
--- |
|
|
|
<!-- 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 MNLI dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4506 |
|
- Accuracy: 0.8417 |
|
|
|
## 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 | | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:| |
|
| 0.3038 | 1.0 | 12272 | 0.4950 | 0.8238 | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 256, 1: 256, 2: 192, 3: 320, 4: 192, 5: 384, 6: 128, 7: 256, 8: 256, 9: 256, 10: 192, 11: 256, 12: 1542, 13: 1611, 14: 1891, 15: 1877, 16: 1825, 17: 1790, 18: 1678, 19: 1544, 20: 1223, 21: 628, 22: 345, 23: 213})]) | |
|
| 0.3038 | 1.0 | 12272 | 0.4592 | 0.8385 | 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})]) | |
|
| 0.1683 | 2.0 | 24544 | 0.4678 | 0.8326 | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 256, 1: 256, 2: 192, 3: 320, 4: 192, 5: 384, 6: 128, 7: 256, 8: 256, 9: 256, 10: 192, 11: 256, 12: 1542, 13: 1611, 14: 1891, 15: 1877, 16: 1825, 17: 1790, 18: 1678, 19: 1544, 20: 1223, 21: 628, 22: 345, 23: 213})]) | |
|
| 0.1683 | 2.0 | 24544 | 0.4285 | 0.8479 | 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})]) | |
|
| 0.1132 | 3.0 | 36816 | 0.4638 | 0.8381 | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 256, 1: 256, 2: 192, 3: 320, 4: 192, 5: 384, 6: 128, 7: 256, 8: 256, 9: 256, 10: 192, 11: 256, 12: 1542, 13: 1611, 14: 1891, 15: 1877, 16: 1825, 17: 1790, 18: 1678, 19: 1544, 20: 1223, 21: 628, 22: 345, 23: 213})]) | |
|
| 0.1132 | 3.0 | 36816 | 0.4231 | 0.8492 | 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})]) | |
|
| 0.0894 | 4.0 | 49088 | 0.4678 | 0.8383 | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 256, 1: 256, 2: 192, 3: 320, 4: 192, 5: 384, 6: 128, 7: 256, 8: 256, 9: 256, 10: 192, 11: 256, 12: 1542, 13: 1611, 14: 1891, 15: 1877, 16: 1825, 17: 1790, 18: 1678, 19: 1544, 20: 1223, 21: 628, 22: 345, 23: 213})]) | |
|
| 0.0894 | 4.0 | 49088 | 0.4261 | 0.8497 | 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 |
|
|
