metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: fine_tuned_boolq__XLMroberta
results: []
fine_tuned_boolq__XLMroberta
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.9741
- Accuracy: 0.6111
- F1: 0.6255
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 400
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.671 | 4.1667 | 50 | 0.5406 | 0.7778 | 0.6806 |
| 0.4838 | 8.3333 | 100 | 0.6437 | 0.6667 | 0.6667 |
| 0.2531 | 12.5 | 150 | 1.1091 | 0.6667 | 0.6667 |
| 0.0646 | 16.6667 | 200 | 1.5667 | 0.7222 | 0.7072 |
| 0.0016 | 20.8333 | 250 | 2.3289 | 0.6111 | 0.6255 |
| 0.001 | 25.0 | 300 | 2.6698 | 0.6111 | 0.6255 |
| 0.0005 | 29.1667 | 350 | 2.9762 | 0.6111 | 0.6255 |
| 0.0005 | 33.3333 | 400 | 2.9741 | 0.6111 | 0.6255 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1