---
library_name: transformers
base_model: kartashoffv/news_topic_classification
tags:
- generated_from_trainer
metrics:
- precision
- recall
model-index:
- name: news-classification-transformer
  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. -->

# news-classification-transformer

This model is a fine-tuned version of [kartashoffv/news_topic_classification](https://huggingface.co/kartashoffv/news_topic_classification) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 9.4277
- Precision: 0.8168
- Recall: 0.5947
- Exact Match: 0.9989

## 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: 3.5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- 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: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Exact Match |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:-----------:|
| 8.4905        | 1.0   | 2139 | 10.5464         | 0.7943    | 0.5356 | 0.9988      |
| 7.7107        | 2.0   | 4278 | 9.5836          | 0.8179    | 0.5860 | 0.9989      |
| 7.2361        | 3.0   | 6417 | 9.4277          | 0.8168    | 0.5947 | 0.9989      |


### Framework versions

- Transformers 4.46.3
- Pytorch 2.4.0
- Datasets 3.1.0
- Tokenizers 0.20.3