---
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: 0.9013761467889908
---

<!-- 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 [google/bert_uncased_L-8_H-512_A-8](https://huggingface.co/google/bert_uncased_L-8_H-512_A-8) on the GLUE SST2 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3631
- Accuracy: 0.9014

## 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 |                                                                                                                                                                                                 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
| 0.3066        | 1.0   | 2105  | 0.3816          | 0.8807   | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 192, 1: 128, 2: 128, 3: 256, 4: 192, 5: 64, 6: 192, 7: 128, 8: 1656, 9: 1319, 10: 1194, 11: 1545, 12: 1531, 13: 1382, 14: 1248, 15: 1027})])  |
| 0.3066        | 1.0   | 2105  | 0.3869          | 0.8888   | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 512, 2: 512, 3: 512, 4: 512, 5: 512, 6: 512, 7: 512, 8: 2048, 9: 2048, 10: 2048, 11: 2048, 12: 2048, 13: 2048, 14: 2048, 15: 2048})]) |
| 0.1629        | 2.0   | 4210  | 0.3857          | 0.8899   | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 192, 1: 128, 2: 128, 3: 256, 4: 192, 5: 64, 6: 192, 7: 128, 8: 1656, 9: 1319, 10: 1194, 11: 1545, 12: 1531, 13: 1382, 14: 1248, 15: 1027})])  |
| 0.1629        | 2.0   | 4210  | 0.3559          | 0.9083   | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 512, 2: 512, 3: 512, 4: 512, 5: 512, 6: 512, 7: 512, 8: 2048, 9: 2048, 10: 2048, 11: 2048, 12: 2048, 13: 2048, 14: 2048, 15: 2048})]) |
| 0.0923        | 3.0   | 6315  | 0.4101          | 0.8968   | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 192, 1: 128, 2: 128, 3: 256, 4: 192, 5: 64, 6: 192, 7: 128, 8: 1656, 9: 1319, 10: 1194, 11: 1545, 12: 1531, 13: 1382, 14: 1248, 15: 1027})])  |
| 0.0923        | 3.0   | 6315  | 0.3862          | 0.9014   | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 512, 2: 512, 3: 512, 4: 512, 5: 512, 6: 512, 7: 512, 8: 2048, 9: 2048, 10: 2048, 11: 2048, 12: 2048, 13: 2048, 14: 2048, 15: 2048})]) |
| 0.0644        | 4.0   | 8420  | 0.3818          | 0.9048   | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 192, 1: 128, 2: 128, 3: 256, 4: 192, 5: 64, 6: 192, 7: 128, 8: 1656, 9: 1319, 10: 1194, 11: 1545, 12: 1531, 13: 1382, 14: 1248, 15: 1027})])  |
| 0.0644        | 4.0   | 8420  | 0.3599          | 0.9037   | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 512, 2: 512, 3: 512, 4: 512, 5: 512, 6: 512, 7: 512, 8: 2048, 9: 2048, 10: 2048, 11: 2048, 12: 2048, 13: 2048, 14: 2048, 15: 2048})]) |
| 0.0424        | 5.0   | 10525 | 0.4138          | 0.8968   | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 192, 1: 128, 2: 128, 3: 256, 4: 192, 5: 64, 6: 192, 7: 128, 8: 1656, 9: 1319, 10: 1194, 11: 1545, 12: 1531, 13: 1382, 14: 1248, 15: 1027})])  |
| 0.0424        | 5.0   | 10525 | 0.3742          | 0.9094   | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 512, 2: 512, 3: 512, 4: 512, 5: 512, 6: 512, 7: 512, 8: 2048, 9: 2048, 10: 2048, 11: 2048, 12: 2048, 13: 2048, 14: 2048, 15: 2048})]) |
| 0.0318        | 6.0   | 12630 | 0.3925          | 0.8956   | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 192, 1: 128, 2: 128, 3: 256, 4: 192, 5: 64, 6: 192, 7: 128, 8: 1656, 9: 1319, 10: 1194, 11: 1545, 12: 1531, 13: 1382, 14: 1248, 15: 1027})])  |
| 0.0318        | 6.0   | 12630 | 0.3637          | 0.9060   | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 512, 2: 512, 3: 512, 4: 512, 5: 512, 6: 512, 7: 512, 8: 2048, 9: 2048, 10: 2048, 11: 2048, 12: 2048, 13: 2048, 14: 2048, 15: 2048})]) |
| 0.0254        | 7.0   | 14735 | 0.3914          | 0.8945   | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 192, 1: 128, 2: 128, 3: 256, 4: 192, 5: 64, 6: 192, 7: 128, 8: 1656, 9: 1319, 10: 1194, 11: 1545, 12: 1531, 13: 1382, 14: 1248, 15: 1027})])  |
| 0.0254        | 7.0   | 14735 | 0.3670          | 0.9025   | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 512, 2: 512, 3: 512, 4: 512, 5: 512, 6: 512, 7: 512, 8: 2048, 9: 2048, 10: 2048, 11: 2048, 12: 2048, 13: 2048, 14: 2048, 15: 2048})]) |
| 0.0246        | 8.0   | 16840 | 0.3886          | 0.8956   | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 192, 1: 128, 2: 128, 3: 256, 4: 192, 5: 64, 6: 192, 7: 128, 8: 1656, 9: 1319, 10: 1194, 11: 1545, 12: 1531, 13: 1382, 14: 1248, 15: 1027})])  |
| 0.0246        | 8.0   | 16840 | 0.3631          | 0.9014   | OrderedDict([(<ElasticityDim.WIDTH: 'width'>, {0: 512, 1: 512, 2: 512, 3: 512, 4: 512, 5: 512, 6: 512, 7: 512, 8: 2048, 9: 2048, 10: 2048, 11: 2048, 12: 2048, 13: 2048, 14: 2048, 15: 2048})]) |


### Framework versions

- Transformers 4.29.1
- Pytorch 1.12.1
- Datasets 2.13.1
- Tokenizers 0.13.3