---
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: tiny-mlm-glue-mrpc-from-scratch-custom-tokenizer-target-glue-qqp
  results: []
---

<!-- 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. -->

# tiny-mlm-glue-mrpc-from-scratch-custom-tokenizer-target-glue-qqp

This model is a fine-tuned version of [muhtasham/tiny-mlm-glue-mrpc-from-scratch-custom-tokenizer](https://huggingface.co/muhtasham/tiny-mlm-glue-mrpc-from-scratch-custom-tokenizer) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5311
- Accuracy: 0.7402
- F1: 0.5973

## 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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- training_steps: 5000

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.6429        | 0.04  | 500  | 0.6232          | 0.6395   | 0.3481 |
| 0.6149        | 0.09  | 1000 | 0.6025          | 0.6619   | 0.4427 |
| 0.5929        | 0.13  | 1500 | 0.5800          | 0.6870   | 0.5779 |
| 0.5688        | 0.18  | 2000 | 0.5620          | 0.7075   | 0.5454 |
| 0.5597        | 0.22  | 2500 | 0.5503          | 0.7218   | 0.5681 |
| 0.5477        | 0.26  | 3000 | 0.5432          | 0.7283   | 0.5902 |
| 0.5467        | 0.31  | 3500 | 0.5388          | 0.7322   | 0.5946 |
| 0.541         | 0.35  | 4000 | 0.5357          | 0.7350   | 0.6098 |
| 0.543         | 0.4   | 4500 | 0.5331          | 0.7348   | 0.6141 |
| 0.5377        | 0.44  | 5000 | 0.5311          | 0.7402   | 0.5973 |


### Framework versions

- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2