metadata
library_name: transformers
license: mit
base_model: FacebookAI/xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: xlm_roberta_top20
results: []
xlm-roberta-csfd-20
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: 0.1968
- Accuracy: 0.9607
- F1: 0.9610
- Precision: 0.9627
- Recall: 0.9607
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: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 1.8509 | 1.0 | 584 | 0.6074 | 0.8533 | 0.8547 | 0.8792 | 0.8533 |
| 0.5597 | 2.0 | 1168 | 0.3286 | 0.9167 | 0.9176 | 0.9303 | 0.9167 |
| 0.2302 | 3.0 | 1752 | 0.2387 | 0.9413 | 0.9422 | 0.9491 | 0.9413 |
| 0.1052 | 4.0 | 2336 | 0.2314 | 0.9487 | 0.9494 | 0.9528 | 0.9487 |
| 0.0662 | 5.0 | 2920 | 0.1968 | 0.9607 | 0.9610 | 0.9627 | 0.9607 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.6.0+cu124
- Datasets 3.4.0
- Tokenizers 0.21.1