---
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/bert_tiny_lda_20_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: bert_tiny_lda_20_v1_qqp
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE QQP
      type: glue
      args: qqp
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.8355181795696265
    - name: F1
      type: f1
      value: 0.7821386450006552
---

<!-- 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. -->

# bert_tiny_lda_20_v1_qqp

This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_20_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_20_v1) on the GLUE QQP dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3641
- Accuracy: 0.8355
- F1: 0.7821
- Combined Score: 0.8088

## 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: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     | Combined Score |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:|
| 0.4896        | 1.0   | 1422  | 0.4397          | 0.7902   | 0.6817 | 0.7359         |
| 0.3891        | 2.0   | 2844  | 0.3806          | 0.8247   | 0.7674 | 0.7960         |
| 0.3332        | 3.0   | 4266  | 0.3641          | 0.8355   | 0.7821 | 0.8088         |
| 0.29          | 4.0   | 5688  | 0.3666          | 0.8448   | 0.7868 | 0.8158         |
| 0.2535        | 5.0   | 7110  | 0.3724          | 0.8485   | 0.7977 | 0.8231         |
| 0.2212        | 6.0   | 8532  | 0.3716          | 0.8517   | 0.8042 | 0.8280         |
| 0.1947        | 7.0   | 9954  | 0.4039          | 0.8528   | 0.8050 | 0.8289         |
| 0.1711        | 8.0   | 11376 | 0.4276          | 0.8535   | 0.7964 | 0.8249         |


### Framework versions

- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3