metadata
license: mit
base_model: roberta-large
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: results
results: []
results
This model is a fine-tuned version of roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0605
- F1: 0.9264
- Roc Auc: 0.9583
- Accuracy: 0.9364
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: 0.003
- 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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| No log | 1.0 | 289 | 0.1752 | 0.7926 | 0.8617 | 0.8295 |
| 0.1506 | 2.0 | 578 | 0.0964 | 0.8924 | 0.9262 | 0.9102 |
| 0.1506 | 3.0 | 867 | 0.0782 | 0.9116 | 0.9517 | 0.9233 |
| 0.0518 | 4.0 | 1156 | 0.0695 | 0.9132 | 0.9309 | 0.9284 |
| 0.0518 | 5.0 | 1445 | 0.0626 | 0.9320 | 0.9628 | 0.9395 |
| 0.0284 | 6.0 | 1734 | 0.0595 | 0.9270 | 0.9621 | 0.9364 |
| 0.0109 | 7.0 | 2023 | 0.0605 | 0.9264 | 0.9583 | 0.9364 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2