---
library_name: transformers
language:
- en
base_model: Hartunka/bert_base_rand_10_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: bert_base_rand_10_v2_mrpc
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE MRPC
      type: glue
      args: mrpc
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.6985294117647058
    - name: F1
      type: f1
      value: 0.7875647668393783
---

<!-- 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_base_rand_10_v2_mrpc

This model is a fine-tuned version of [Hartunka/bert_base_rand_10_v2](https://huggingface.co/Hartunka/bert_base_rand_10_v2) on the GLUE MRPC dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5933
- Accuracy: 0.6985
- F1: 0.7876
- Combined Score: 0.7430

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
| 0.635         | 1.0   | 15   | 0.5951          | 0.7010   | 0.8051 | 0.7530         |
| 0.5764        | 2.0   | 30   | 0.5933          | 0.6985   | 0.7876 | 0.7430         |
| 0.4976        | 3.0   | 45   | 0.6354          | 0.6740   | 0.7532 | 0.7136         |
| 0.3711        | 4.0   | 60   | 0.6945          | 0.6789   | 0.7673 | 0.7231         |
| 0.24          | 5.0   | 75   | 1.0009          | 0.6569   | 0.7338 | 0.6954         |
| 0.1426        | 6.0   | 90   | 1.1919          | 0.6299   | 0.7113 | 0.6706         |
| 0.0893        | 7.0   | 105  | 1.2962          | 0.6618   | 0.7518 | 0.7068         |


### Framework versions

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