metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: training-1
results: []
training-1
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0448
- Accuracy: 0.9937
- Precision: 0.9912
- Recall: 0.9859
- F1: 0.9885
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: 1e-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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 0.5 | 302 | 0.0546 | 0.9870 | 0.9737 | 0.9789 | 0.9763 |
| No log | 1.0 | 604 | 0.0511 | 0.9913 | 0.9911 | 0.9771 | 0.9840 |
| 0.1032 | 1.5 | 906 | 0.0558 | 0.9899 | 0.9807 | 0.9824 | 0.9815 |
| 0.1032 | 2.0 | 1208 | 0.0467 | 0.9928 | 0.9982 | 0.9754 | 0.9866 |
| 0.0353 | 2.5 | 1510 | 0.0411 | 0.9937 | 0.9929 | 0.9842 | 0.9885 |
| 0.0353 | 3.0 | 1812 | 0.0460 | 0.9932 | 0.9911 | 0.9842 | 0.9876 |
| 0.0183 | 3.49 | 2114 | 0.0423 | 0.9937 | 0.9947 | 0.9824 | 0.9885 |
| 0.0183 | 3.99 | 2416 | 0.0476 | 0.9932 | 0.9911 | 0.9842 | 0.9876 |
| 0.013 | 4.49 | 2718 | 0.0463 | 0.9932 | 0.9911 | 0.9842 | 0.9876 |
| 0.013 | 4.99 | 3020 | 0.0448 | 0.9937 | 0.9912 | 0.9859 | 0.9885 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.2.0.dev20230913+cu121
- Datasets 2.14.5
- Tokenizers 0.13.3