metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
datasets:
- ag_news
metrics:
- accuracy
model-index:
- name: roberta-base_ag_news
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: ag_news
type: ag_news
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.89
roberta-base_ag_news
This model is a fine-tuned version of roberta-base on the ag_news dataset. It achieves the following results on the evaluation set:
- Loss: 0.4016
- Accuracy: 0.89
- F1-score: 0.8903
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1-score |
|---|---|---|---|---|---|
| 0.5297 | 1.0 | 250 | 0.4016 | 0.89 | 0.8903 |
| 0.4108 | 2.0 | 500 | 0.4182 | 0.8863 | 0.8865 |
| 0.2583 | 3.0 | 750 | 0.5196 | 0.8958 | 0.8955 |
| 0.0053 | 4.0 | 1000 | 0.5965 | 0.8884 | 0.8884 |
| 0.0037 | 5.0 | 1250 | 0.5868 | 0.8911 | 0.8906 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1