---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- matthews_correlation
model-index:
- name: HW1
  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. -->

# HW1

This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1607
- Matthews Correlation: 0.5443

## 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: 1.4175716836316547e-05
- train_batch_size: 4
- eval_batch_size: 16
- seed: 20
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Matthews Correlation |
|:-------------:|:-----:|:-----:|:---------------:|:--------------------:|
| 0.5335        | 1.0   | 2138  | 0.5571          | 0.4299               |
| 0.4842        | 2.0   | 4276  | 0.9165          | 0.4857               |
| 0.3472        | 3.0   | 6414  | 1.0049          | 0.5239               |
| 0.2567        | 4.0   | 8552  | 0.9978          | 0.5604               |
| 0.1409        | 5.0   | 10690 | 1.1607          | 0.5443               |


### Framework versions

- Transformers 4.39.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2