---
language:
- en
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: hBERTv2_qqp
  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: 0.8651001731387583
    - name: F1
      type: f1
      value: 0.8160291438979962
---

<!-- 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. -->

# hBERTv2_qqp

This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2](https://huggingface.co/gokuls/bert_12_layer_model_v2) on the GLUE QQP dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3129
- Accuracy: 0.8651
- F1: 0.8160
- Combined Score: 0.8406

## 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: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     | Combined Score |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:|
| 0.4179        | 1.0   | 1422  | 0.3830          | 0.8252   | 0.7916 | 0.8084         |
| 0.2978        | 2.0   | 2844  | 0.3507          | 0.8357   | 0.7906 | 0.8131         |
| 0.2318        | 3.0   | 4266  | 0.3129          | 0.8651   | 0.8160 | 0.8406         |
| 0.1765        | 4.0   | 5688  | 0.3540          | 0.8700   | 0.8328 | 0.8514         |
| 0.1305        | 5.0   | 7110  | 0.4276          | 0.8734   | 0.8267 | 0.8500         |
| 0.1003        | 6.0   | 8532  | 0.4078          | 0.8748   | 0.8292 | 0.8520         |
| 0.0788        | 7.0   | 9954  | 0.4069          | 0.8767   | 0.8345 | 0.8556         |
| 0.0625        | 8.0   | 11376 | 0.4723          | 0.8760   | 0.8322 | 0.8541         |


### Framework versions

- Transformers 4.26.1
- Pytorch 1.14.0a0+410ce96
- Datasets 2.10.1
- Tokenizers 0.13.2