metadata
library_name: transformers
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: model
results: []
model
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2755
- Precision: 0.4545
- Recall: 0.0935
- F1: 0.1550
- Accuracy: 0.9109
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.3038 | 0.4292 | 100 | 0.2895 | 0.0 | 0.0 | 0.0 | 0.9125 |
| 0.2835 | 0.8584 | 200 | 0.2731 | 0.0 | 0.0 | 0.0 | 0.9125 |
| 0.2383 | 1.2876 | 300 | 0.2710 | 0.5606 | 0.0384 | 0.0719 | 0.9132 |
| 0.2385 | 1.7167 | 400 | 0.2685 | 0.6786 | 0.0197 | 0.0383 | 0.9134 |
| 0.2356 | 2.1459 | 500 | 0.2734 | 0.4466 | 0.0955 | 0.1574 | 0.9105 |
| 0.2067 | 2.5751 | 600 | 0.2719 | 0.4703 | 0.0987 | 0.1631 | 0.9114 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0