---
language:
- en
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: hBERTv2_new_pretrain_mnli
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE MNLI
      type: glue
      config: mnli
      split: validation_matched
      args: mnli
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.318246541903987
---

<!-- 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_mnli

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 MNLI dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0992
- Accuracy: 0.3182

## 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

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 70.7498       | 1.0   | 3068  | 30.0481         | 0.3274   |
| 5.5287        | 2.0   | 6136  | 1.1252          | 0.3274   |
| 1.354         | 3.0   | 9204  | 1.0991          | 0.3182   |
| 3.0766        | 4.0   | 12272 | 1.2373          | 0.3182   |
| 4.2409        | 5.0   | 15340 | 1.1912          | 0.3274   |
| 5.4957        | 6.0   | 18408 | 1.1716          | 0.3545   |
| 3.0327        | 7.0   | 21476 | 1.3155          | 0.3274   |
| 1.571         | 8.0   | 24544 | 1.3787          | 0.3274   |


### Framework versions

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