metadata
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 SST2
type: glue
config: sst2
split: validation
args: sst2
metrics:
- name: Accuracy
type: accuracy
value: 0.9151376146788991
first_try
This model is a fine-tuned version of bert-base-uncased on the GLUE SST2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3079
- Accuracy: 0.9151
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 | |
|---|---|---|---|---|---|
| 0.1786 | 1.0 | 2105 | 0.3156 | 0.9151 | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 320, 1: 256, 2: 256, 3: 192, 4: 256, 5: 192, 6: 128, 7: 320, 8: 256, 9: 192, 10: 128, 11: 64, 12: 1585, 13: 1570, 14: 1775, 15: 1717, 16: 1679, 17: 1580, 18: 1621, 19: 1406, 20: 1188, 21: 930, 22: 828, 23: 654})]) |
| 0.1786 | 1.0 | 2105 | 0.2938 | 0.9220 | 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})]) |
| 0.0868 | 2.0 | 4210 | 0.3035 | 0.9197 | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 320, 1: 256, 2: 256, 3: 192, 4: 256, 5: 192, 6: 128, 7: 320, 8: 256, 9: 192, 10: 128, 11: 64, 12: 1585, 13: 1570, 14: 1775, 15: 1717, 16: 1679, 17: 1580, 18: 1621, 19: 1406, 20: 1188, 21: 930, 22: 828, 23: 654})]) |
| 0.0868 | 2.0 | 4210 | 0.3008 | 0.9232 | 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})]) |
| 0.0371 | 3.0 | 6315 | 0.3073 | 0.9151 | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 320, 1: 256, 2: 256, 3: 192, 4: 256, 5: 192, 6: 128, 7: 320, 8: 256, 9: 192, 10: 128, 11: 64, 12: 1585, 13: 1570, 14: 1775, 15: 1717, 16: 1679, 17: 1580, 18: 1621, 19: 1406, 20: 1188, 21: 930, 22: 828, 23: 654})]) |
| 0.0371 | 3.0 | 6315 | 0.2674 | 0.9289 | 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})]) |
| 0.0249 | 4.0 | 8420 | 0.3040 | 0.9140 | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 320, 1: 256, 2: 256, 3: 192, 4: 256, 5: 192, 6: 128, 7: 320, 8: 256, 9: 192, 10: 128, 11: 64, 12: 1585, 13: 1570, 14: 1775, 15: 1717, 16: 1679, 17: 1580, 18: 1621, 19: 1406, 20: 1188, 21: 930, 22: 828, 23: 654})]) |
| 0.0249 | 4.0 | 8420 | 0.2658 | 0.9312 | 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