---
language:
- en
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: hBERTv2_new_pretrain_w_init_48_mrpc
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE MRPC
      type: glue
      config: mrpc
      split: validation
      args: mrpc
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.696078431372549
    - name: F1
      type: f1
      value: 0.7912457912457912
---

<!-- 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_w_init_48_mrpc

This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48](https://huggingface.co/gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48) on the GLUE MRPC dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5938
- Accuracy: 0.6961
- F1: 0.7912
- Combined Score: 0.7437

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
| 0.6532        | 1.0   | 29   | 0.6271          | 0.6838   | 0.8072 | 0.7455         |
| 0.6168        | 2.0   | 58   | 0.5971          | 0.6814   | 0.8060 | 0.7437         |
| 0.5766        | 3.0   | 87   | 0.5938          | 0.6961   | 0.7912 | 0.7437         |
| 0.5304        | 4.0   | 116  | 0.6174          | 0.7059   | 0.8039 | 0.7549         |
| 0.4622        | 5.0   | 145  | 0.6873          | 0.6789   | 0.7753 | 0.7271         |
| 0.3228        | 6.0   | 174  | 0.7267          | 0.6887   | 0.7894 | 0.7391         |
| 0.2028        | 7.0   | 203  | 0.9771          | 0.7010   | 0.7875 | 0.7442         |
| 0.1406        | 8.0   | 232  | 1.1768          | 0.6789   | 0.7714 | 0.7252         |


### Framework versions

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