---
language:
- en
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: hBERTv2_new_pretrain_stsb
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE STSB
      type: glue
      config: stsb
      split: validation
      args: stsb
    metrics:
    - name: Spearmanr
      type: spearmanr
      value: 0.21439771990122156
---

<!-- 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_stsb

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 STSB dataset.
It achieves the following results on the evaluation set:
- Loss: 2.2332
- Pearson: 0.2243
- Spearmanr: 0.2144
- Combined Score: 0.2193

## 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 | Pearson | Spearmanr | Combined Score |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:|
| 2.399         | 1.0   | 45   | 2.6135          | 0.0824  | 0.0835    | 0.0830         |
| 1.9751        | 2.0   | 90   | 2.2332          | 0.2243  | 0.2144    | 0.2193         |
| 1.6719        | 3.0   | 135  | 2.3954          | 0.2796  | 0.2667    | 0.2732         |
| 1.3496        | 4.0   | 180  | 3.7160          | 0.3057  | 0.2958    | 0.3007         |
| 1.1653        | 5.0   | 225  | 2.7682          | 0.3327  | 0.3203    | 0.3265         |
| 0.8439        | 6.0   | 270  | 2.4277          | 0.3960  | 0.3888    | 0.3924         |
| 0.6687        | 7.0   | 315  | 2.3823          | 0.3995  | 0.3905    | 0.3950         |


### Framework versions

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