---
language:
- en
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: add_BERT_no_pretrain_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: 0.6838235294117647
    - name: F1
      type: f1
      value: 0.8122270742358079
---

<!-- 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. -->

# add_BERT_no_pretrain_mrpc

This model is a fine-tuned version of [](https://huggingface.co/) on the GLUE MRPC dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6240
- Accuracy: 0.6838
- F1: 0.8122
- Combined Score: 0.7480

## 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: 0.0005
- 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
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Combined Score |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
| 1.154         | 1.0   | 29   | 0.6856          | 0.6838   | 0.8122 | 0.7480         |
| 0.6781        | 2.0   | 58   | 0.6609          | 0.6838   | 0.8122 | 0.7480         |
| 0.6458        | 3.0   | 87   | 0.6348          | 0.6838   | 0.8122 | 0.7480         |
| 0.6395        | 4.0   | 116  | 19.6354         | 0.3186   | 0.0071 | 0.1629         |
| 1.1486        | 5.0   | 145  | 0.6657          | 0.6838   | 0.8122 | 0.7480         |
| 0.6446        | 6.0   | 174  | 0.6277          | 0.6838   | 0.8122 | 0.7480         |
| 0.644         | 7.0   | 203  | 0.6242          | 0.6838   | 0.8122 | 0.7480         |
| 0.6337        | 8.0   | 232  | 0.6242          | 0.6838   | 0.8122 | 0.7480         |
| 0.6388        | 9.0   | 261  | 0.6253          | 0.6838   | 0.8122 | 0.7480         |
| 0.634         | 10.0  | 290  | 0.6242          | 0.6838   | 0.8122 | 0.7480         |
| 0.6346        | 11.0  | 319  | 0.6264          | 0.6838   | 0.8122 | 0.7480         |
| 0.6338        | 12.0  | 348  | 0.6273          | 0.6838   | 0.8122 | 0.7480         |
| 0.6343        | 13.0  | 377  | 0.6262          | 0.6838   | 0.8122 | 0.7480         |
| 0.6339        | 14.0  | 406  | 0.6240          | 0.6838   | 0.8122 | 0.7480         |
| 0.635         | 15.0  | 435  | 0.6244          | 0.6838   | 0.8122 | 0.7480         |
| 0.6331        | 16.0  | 464  | 0.6240          | 0.6838   | 0.8122 | 0.7480         |
| 0.6328        | 17.0  | 493  | 0.6267          | 0.6838   | 0.8122 | 0.7480         |
| 0.6338        | 18.0  | 522  | 0.6257          | 0.6838   | 0.8122 | 0.7480         |
| 0.6321        | 19.0  | 551  | 0.6240          | 0.6838   | 0.8122 | 0.7480         |


### Framework versions

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