metadata
library_name: transformers
license: mit
base_model: joeddav/xlm-roberta-large-xnli
tags:
- generated_from_trainer
model-index:
- name: roberta_fine_simile
results: []
roberta_fine_simile
This model is a fine-tuned version of joeddav/xlm-roberta-large-xnli on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6860
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: 0.0005
- train_batch_size: 8
- eval_batch_size: 8
- 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
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7328 | 1.0 | 225 | 0.7291 |
| 0.7723 | 2.0 | 450 | 0.6914 |
| 0.7069 | 3.0 | 675 | 0.7188 |
| 0.6843 | 4.0 | 900 | 0.6874 |
| 0.699 | 5.0 | 1125 | 0.6860 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1