---
license: mit
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: newsdiscourse-model
  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. -->

# newsdiscourse-model

This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.7194
- F1: 0.5515

## 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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0

### Training results

| Training Loss | Epoch | Step | Validation Loss | F1     |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| No log        | 0.14  | 100  | 1.3632          | 0.3762 |
| No log        | 0.28  | 200  | 1.2278          | 0.4162 |
| No log        | 0.43  | 300  | 1.1802          | 0.4159 |
| No log        | 0.57  | 400  | 1.3237          | 0.4879 |
| 1.2           | 0.71  | 500  | 1.2971          | 0.4645 |
| 1.2           | 0.85  | 600  | 1.2550          | 0.5020 |
| 1.2           | 1.0   | 700  | 1.1854          | 0.4806 |
| 1.2           | 1.14  | 800  | 1.1788          | 0.5012 |
| 1.2           | 1.28  | 900  | 1.0935          | 0.4964 |
| 0.9189        | 1.42  | 1000 | 1.2862          | 0.4986 |
| 0.9189        | 1.57  | 1100 | 1.2223          | 0.4930 |
| 0.9189        | 1.71  | 1200 | 1.1197          | 0.4954 |
| 0.9189        | 1.85  | 1300 | 1.1257          | 0.5153 |
| 0.9189        | 1.99  | 1400 | 1.1729          | 0.5264 |
| 0.8143        | 2.14  | 1500 | 1.2722          | 0.5165 |
| 0.8143        | 2.28  | 1600 | 1.3218          | 0.5395 |
| 0.8143        | 2.42  | 1700 | 1.3383          | 0.5170 |
| 0.8143        | 2.56  | 1800 | 1.2503          | 0.5139 |
| 0.8143        | 2.71  | 1900 | 1.3630          | 0.5240 |
| 0.6175        | 2.85  | 2000 | 1.4028          | 0.5305 |
| 0.6175        | 2.99  | 2100 | 1.4017          | 0.5408 |
| 0.6175        | 3.13  | 2200 | 1.5930          | 0.5413 |
| 0.6175        | 3.28  | 2300 | 1.5373          | 0.5565 |
| 0.6175        | 3.42  | 2400 | 1.5013          | 0.5722 |
| 0.4726        | 3.56  | 2500 | 1.5704          | 0.5226 |
| 0.4726        | 3.7   | 2600 | 1.5891          | 0.5484 |
| 0.4726        | 3.85  | 2700 | 1.5236          | 0.5630 |
| 0.4726        | 3.99  | 2800 | 1.5233          | 0.5422 |
| 0.4726        | 4.13  | 2900 | 1.6105          | 0.5470 |
| 0.3745        | 4.27  | 3000 | 1.7136          | 0.5525 |
| 0.3745        | 4.42  | 3100 | 1.6561          | 0.5539 |
| 0.3745        | 4.56  | 3200 | 1.7664          | 0.5504 |
| 0.3745        | 4.7   | 3300 | 1.7505          | 0.5494 |
| 0.3745        | 4.84  | 3400 | 1.7313          | 0.5516 |
| 0.307         | 4.99  | 3500 | 1.7194          | 0.5515 |


### Framework versions

- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3