metadata
license: mit
base_model: FacebookAI/xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: Vic_model2
results: []
Vic_model2
This model is a fine-tuned version of FacebookAI/xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2487
- Accuracy: 0.9657
- Precision: 0.9663
- Recall: 0.9657
- F1: 0.9654
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: 5e-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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.8139 | 1.0 | 1313 | 0.6269 | 0.83 | 0.8370 | 0.8300 | 0.8242 |
| 0.4671 | 2.0 | 2626 | 0.5028 | 0.8786 | 0.8837 | 0.8786 | 0.8757 |
| 0.343 | 3.0 | 3939 | 0.4058 | 0.8957 | 0.9038 | 0.8957 | 0.8965 |
| 0.222 | 4.0 | 5252 | 0.4109 | 0.9286 | 0.9295 | 0.9286 | 0.9274 |
| 0.1237 | 5.0 | 6565 | 0.3822 | 0.9357 | 0.9387 | 0.9357 | 0.9354 |
| 0.0629 | 6.0 | 7878 | 0.3639 | 0.9429 | 0.9459 | 0.9429 | 0.9433 |
| 0.0186 | 7.0 | 9191 | 0.2977 | 0.9557 | 0.9567 | 0.9557 | 0.9555 |
| 0.0104 | 8.0 | 10504 | 0.2487 | 0.9657 | 0.9663 | 0.9657 | 0.9654 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1