metadata
library_name: transformers
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: roberta-base-binary-classification
results: []
roberta-base-binary-classification
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8437
- Accuracy: 0.7197
- F1 Macro: 0.7136
- Precision Macro: 0.7122
- Recall Macro: 0.7180
- Auc: 0.7698
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Precision Macro | Recall Macro | Auc |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 79 | 0.6399 | 0.6720 | 0.6078 | 0.6827 | 0.6172 | 0.7059 |
| No log | 2.0 | 158 | 0.5915 | 0.7038 | 0.6997 | 0.7000 | 0.7071 | 0.7527 |
| No log | 3.0 | 237 | 0.6490 | 0.7420 | 0.7148 | 0.7461 | 0.7089 | 0.7592 |
| No log | 4.0 | 316 | 0.8437 | 0.7197 | 0.7136 | 0.7122 | 0.7180 | 0.7698 |
| No log | 5.0 | 395 | 1.2274 | 0.7070 | 0.6369 | 0.7682 | 0.6466 | 0.7648 |
| No log | 6.0 | 474 | 1.1953 | 0.7038 | 0.6992 | 0.6990 | 0.7059 | 0.7482 |
| 0.3882 | 7.0 | 553 | 1.2941 | 0.7357 | 0.7231 | 0.7257 | 0.7212 | 0.7580 |
| 0.3882 | 8.0 | 632 | 1.4526 | 0.7261 | 0.7150 | 0.7156 | 0.7145 | 0.7441 |
| 0.3882 | 9.0 | 711 | 1.6187 | 0.6975 | 0.6917 | 0.6908 | 0.6967 | 0.7349 |
| 0.3882 | 10.0 | 790 | 1.5593 | 0.7389 | 0.7275 | 0.7289 | 0.7264 | 0.7492 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1