Hal_DSC_xlm-roberta-large-xnli_finetuned_finetuned_2
This model is a fine-tuned version of nhatha2004/DSC_xlm-roberta-large-xnli_finetuned on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3826
- Accuracy: 0.7793
- F1 Macro: 0.7800
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-06
- train_batch_size: 32
- eval_batch_size: 32
- 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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|---|---|---|---|---|---|
| No log | 1.0 | 175 | 0.8523 | 0.7779 | 0.7786 |
| No log | 2.0 | 350 | 0.9593 | 0.7757 | 0.7759 |
| 0.1691 | 3.0 | 525 | 1.2136 | 0.7686 | 0.7683 |
| 0.1691 | 4.0 | 700 | 1.3826 | 0.7793 | 0.7800 |
| 0.1691 | 5.0 | 875 | 1.5193 | 0.7664 | 0.7670 |
| 0.0628 | 6.0 | 1050 | 1.6440 | 0.7614 | 0.7604 |
| 0.0628 | 7.0 | 1225 | 1.7151 | 0.7707 | 0.7716 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.2