---
language:
- en
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: hBERTv1_new_pretrain_w_init_48_sst2
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE SST2
      type: glue
      config: sst2
      split: validation
      args: sst2
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.8176605504587156
---

<!-- 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. -->

# hBERTv1_new_pretrain_w_init_48_sst2

This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48) on the GLUE SST2 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4260
- Accuracy: 0.8177

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.5336        | 1.0   | 527  | 0.4260          | 0.8177   |
| 0.2532        | 2.0   | 1054 | 0.5554          | 0.8211   |
| 0.1845        | 3.0   | 1581 | 0.5318          | 0.8108   |
| 0.1484        | 4.0   | 2108 | 0.6237          | 0.8108   |
| 0.1195        | 5.0   | 2635 | 0.5310          | 0.8096   |
| 0.1           | 6.0   | 3162 | 0.7588          | 0.8028   |


### Framework versions

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