metadata
library_name: transformers
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: bert
results: []
bert
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: 0.1679
- Accuracy: 0.9669
- F1: 0.9667
- Precision: 0.9685
- Recall: 0.9669
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: 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: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 1.1054 | 1.0 | 38 | 1.0886 | 0.4106 | 0.2390 | 0.1686 | 0.4106 |
| 1.0709 | 2.0 | 76 | 0.9872 | 0.6490 | 0.5588 | 0.5174 | 0.6490 |
| 0.838 | 3.0 | 114 | 0.7455 | 0.6424 | 0.5447 | 0.4737 | 0.6424 |
| 0.2981 | 4.0 | 152 | 0.2033 | 0.9338 | 0.9340 | 0.9413 | 0.9338 |
| 0.1249 | 5.0 | 190 | 0.1285 | 0.9669 | 0.9668 | 0.9672 | 0.9669 |
| 0.1224 | 6.0 | 228 | 0.2481 | 0.9470 | 0.9476 | 0.9546 | 0.9470 |
| 0.0015 | 7.0 | 266 | 0.3061 | 0.9536 | 0.9535 | 0.9582 | 0.9536 |
| 0.0332 | 8.0 | 304 | 0.3735 | 0.9404 | 0.9406 | 0.9498 | 0.9404 |
| 0.1496 | 9.0 | 342 | 0.2024 | 0.9669 | 0.9670 | 0.9700 | 0.9669 |
| 0.0629 | 10.0 | 380 | 0.1679 | 0.9669 | 0.9667 | 0.9685 | 0.9669 |
Framework versions
- Transformers 4.50.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.4.1
- Tokenizers 0.21.0