---
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: tiny-mlm-glue-qnli-from-scratch-custom-tokenizer-target-glue-qnli
  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-qnli-from-scratch-custom-tokenizer-target-glue-qnli

This model is a fine-tuned version of [muhtasham/tiny-mlm-glue-qnli-from-scratch-custom-tokenizer](https://huggingface.co/muhtasham/tiny-mlm-glue-qnli-from-scratch-custom-tokenizer) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6605
- Accuracy: 0.6096

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.6927        | 0.15  | 500  | 0.6897          | 0.5435   |
| 0.6834        | 0.31  | 1000 | 0.6687          | 0.5883   |
| 0.6709        | 0.46  | 1500 | 0.6631          | 0.6035   |
| 0.6647        | 0.61  | 2000 | 0.6655          | 0.5971   |
| 0.662         | 0.76  | 2500 | 0.6550          | 0.6081   |
| 0.6615        | 0.92  | 3000 | 0.6542          | 0.6150   |
| 0.6511        | 1.07  | 3500 | 0.6699          | 0.6000   |
| 0.6471        | 1.22  | 4000 | 0.6620          | 0.6066   |
| 0.6411        | 1.37  | 4500 | 0.6605          | 0.6096   |


### Framework versions

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