distilroberta-base-finetuned-leftarticles-mlm
This model is a fine-tuned version of distilroberta-base on a dataset of left wing news articles, happybusinessperson/leftarticles, adapted from https://www.kaggle.com/datasets/mhoali/right-and-left-wing-news-articles-with-nlp. It achieves the following results on the evaluation set:
- Loss: 1.7207
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.9373 | 1.0 | 2239 | 1.7868 |
1.8676 | 2.0 | 4478 | 1.7572 |
1.8194 | 3.0 | 6717 | 1.7297 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 2
Model tree for happybusinessperson/distilroberta-base-finetuned-leftarticles-mlm
Base model
distilbert/distilroberta-base
Finetuned
this model