---
language:
- en
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: hBERTv2_new_pretrain_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: 0.7902547613158546
    - name: F1
      type: f1
      value: 0.7136682874122096
---

<!-- 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_new_pretrain_qqp

This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2_complete_training_new](https://huggingface.co/gokuls/bert_12_layer_model_v2_complete_training_new) on the GLUE QQP dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4399
- Accuracy: 0.7903
- F1: 0.7137
- Combined Score: 0.7520

## 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: 4e-05
- train_batch_size: 128
- eval_batch_size: 128
- 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

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     | Combined Score |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:|
| 0.5303        | 1.0   | 2843  | 0.4893          | 0.7608   | 0.6250 | 0.6929         |
| 0.4677        | 2.0   | 5686  | 0.4781          | 0.7773   | 0.6831 | 0.7302         |
| 0.4229        | 3.0   | 8529  | 0.4399          | 0.7903   | 0.7137 | 0.7520         |
| 0.3712        | 4.0   | 11372 | 0.4426          | 0.8018   | 0.7163 | 0.7590         |
| 0.3268        | 5.0   | 14215 | 0.4515          | 0.8107   | 0.7348 | 0.7728         |
| 0.2925        | 6.0   | 17058 | 0.5221          | 0.8119   | 0.7227 | 0.7673         |
| 0.2614        | 7.0   | 19901 | 0.4518          | 0.8058   | 0.7527 | 0.7792         |
| 0.2389        | 8.0   | 22744 | 0.5231          | 0.8134   | 0.7601 | 0.7868         |


### Framework versions

- Transformers 4.29.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3