metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
datasets:
- ag_news
model-index:
- name: roberta-base_ag_news
results: []
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: 0.1897
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: 32
- eval_batch_size: 32
- 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 |
|---|---|---|---|
| 0.1879 | 1.0 | 3750 | 0.2106 |
| 0.1556 | 2.0 | 7500 | 0.1951 |
| 0.126 | 3.0 | 11250 | 0.1897 |
| 0.0576 | 4.0 | 15000 | 0.1921 |
| 0.0386 | 5.0 | 18750 | 0.2283 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.1+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2