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_top10
results: []
xlm-roberta-csfd-10
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: 0.1591
- Accuracy: 0.9613
- F1: 0.9617
- Precision: 0.9630
- Recall: 0.9613
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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 292 | 0.5781 | 0.8427 | 0.8432 | 0.8710 | 0.8427 |
| 1.0772 | 2.0 | 584 | 0.2642 | 0.9213 | 0.9213 | 0.9327 | 0.9213 |
| 1.0772 | 3.0 | 876 | 0.2215 | 0.9413 | 0.9408 | 0.9484 | 0.9413 |
| 0.1222 | 4.0 | 1168 | 0.1546 | 0.96 | 0.9604 | 0.9618 | 0.9600 |
| 0.1222 | 5.0 | 1460 | 0.1591 | 0.9613 | 0.9617 | 0.9630 | 0.9613 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.6.0+cu124
- Datasets 3.4.0
- Tokenizers 0.21.1