metadata
library_name: transformers
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: dummy-dept
results: []
dummy-dept
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0113
- Accuracy: 0.965
- F1 Macro: 0.9646
- F1 Weighted: 0.9649
- Precision Macro: 0.9651
- Recall Macro: 0.9643
- Precision Weighted: 0.9649
- Recall Weighted: 0.965
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: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Weighted | Precision Macro | Recall Macro | Precision Weighted | Recall Weighted |
|---|---|---|---|---|---|---|---|---|---|---|
| 0.1519 | 0.1667 | 50 | 0.0597 | 0.8167 | 0.7852 | 0.8020 | 0.8365 | 0.8058 | 0.8487 | 0.8167 |
| 0.0488 | 0.3333 | 100 | 0.0173 | 0.9617 | 0.9614 | 0.9618 | 0.9627 | 0.9607 | 0.9624 | 0.9617 |
| 0.0223 | 0.5 | 150 | 0.0236 | 0.945 | 0.9460 | 0.9454 | 0.9427 | 0.9513 | 0.9478 | 0.945 |
| 0.0129 | 0.6667 | 200 | 0.0161 | 0.965 | 0.9655 | 0.9649 | 0.9652 | 0.9659 | 0.9649 | 0.965 |
| 0.0153 | 0.8333 | 250 | 0.0135 | 0.9667 | 0.9665 | 0.9665 | 0.9694 | 0.9639 | 0.9668 | 0.9667 |
| 0.0136 | 1.0 | 300 | 0.0113 | 0.965 | 0.9646 | 0.9649 | 0.9651 | 0.9643 | 0.9649 | 0.965 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1