---
library_name: transformers
language:
- en
base_model: Hartunka/tiny_bert_rand_5_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: tiny_bert_rand_5_v1_mrpc
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE MRPC
      type: glue
      args: mrpc
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.7058823529411765
    - name: F1
      type: f1
      value: 0.8119122257053292
---

<!-- 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_bert_rand_5_v1_mrpc

This model is a fine-tuned version of [Hartunka/tiny_bert_rand_5_v1](https://huggingface.co/Hartunka/tiny_bert_rand_5_v1) on the GLUE MRPC dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5841
- Accuracy: 0.7059
- F1: 0.8119
- Combined Score: 0.7589

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
| 0.6249        | 1.0   | 15   | 0.5955          | 0.7059   | 0.8154 | 0.7606         |
| 0.585         | 2.0   | 30   | 0.5841          | 0.7059   | 0.8119 | 0.7589         |
| 0.547         | 3.0   | 45   | 0.5992          | 0.7059   | 0.8154 | 0.7606         |
| 0.5109        | 4.0   | 60   | 0.6076          | 0.6961   | 0.7794 | 0.7377         |
| 0.4274        | 5.0   | 75   | 0.6408          | 0.7010   | 0.7875 | 0.7442         |
| 0.33          | 6.0   | 90   | 0.7433          | 0.6642   | 0.7540 | 0.7091         |
| 0.2371        | 7.0   | 105  | 0.8375          | 0.7108   | 0.7966 | 0.7537         |


### Framework versions

- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1