---
language:
- en
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: hBERTv2_new_pretrain_w_init__wnli
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE WNLI
      type: glue
      config: wnli
      split: validation
      args: wnli
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.5633802816901409
---

<!-- 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__wnli

This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2_complete_training_new_wt_init](https://huggingface.co/gokuls/bert_12_layer_model_v2_complete_training_new_wt_init) on the GLUE WNLI dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6990
- Accuracy: 0.5634

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.9111        | 1.0   | 5    | 0.7288          | 0.5493   |
| 0.7278        | 2.0   | 10   | 0.7028          | 0.5634   |
| 0.707         | 3.0   | 15   | 0.6990          | 0.5634   |
| 0.7068        | 4.0   | 20   | 0.7351          | 0.4366   |
| 0.7424        | 5.0   | 25   | 0.7129          | 0.5634   |
| 0.7298        | 6.0   | 30   | 0.7102          | 0.4366   |
| 0.7043        | 7.0   | 35   | 0.7217          | 0.4366   |
| 0.7081        | 8.0   | 40   | 0.7003          | 0.5634   |


### Framework versions

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