metadata
library_name: transformers
license: mit
base_model: FacebookAI/xlm-roberta-large
tags:
- generated_from_trainer
model-index:
- name: entex_pre
results: []
entex_pre
This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2082
- F1 Macro: 0.8500
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
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Macro |
|---|---|---|---|---|
| 1.0679 | 1.0 | 26 | 0.5775 | 0.2761 |
| 0.3311 | 2.0 | 52 | 0.2341 | 0.7785 |
| 0.186 | 3.0 | 78 | 0.2036 | 0.8220 |
| 0.1366 | 4.0 | 104 | 0.1852 | 0.8459 |
| 0.1003 | 5.0 | 130 | 0.1907 | 0.8516 |
| 0.0793 | 6.0 | 156 | 0.2027 | 0.8486 |
| 0.0668 | 7.0 | 182 | 0.2082 | 0.8500 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1