metadata
library_name: transformers
license: mit
base_model: FacebookAI/roberta-base
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: fold_4_model_roberta
results: []
fold_4_model_roberta
This model is a fine-tuned version of FacebookAI/roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6094
- F1: 0.7390
- Roc Auc: 0.8019
- Accuracy: 0.4144
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 adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.0424 | 1.0 | 111 | 0.6255 | 0.7252 | 0.7940 | 0.3784 |
| 0.0322 | 2.0 | 222 | 0.6856 | 0.7102 | 0.7831 | 0.3514 |
| 0.0205 | 3.0 | 333 | 0.6094 | 0.7390 | 0.8019 | 0.4144 |
| 0.0169 | 4.0 | 444 | 0.6782 | 0.7135 | 0.7842 | 0.3694 |
| 0.0149 | 5.0 | 555 | 0.6594 | 0.7262 | 0.7939 | 0.3784 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0