xlmr-sarcasmo-sentiment
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: 0.2949
- Accuracy: 0.9524
- F1: 0.9391
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: 32
- 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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.2855 | 1.0 | 72 | 1.1853 | 0.7669 | 0.7247 |
| 1.1417 | 2.0 | 144 | 0.8436 | 0.8110 | 0.7673 |
| 0.6883 | 3.0 | 216 | 0.8373 | 0.8337 | 0.7739 |
| 0.5870 | 4.0 | 288 | 0.8536 | 0.8420 | 0.7809 |
| 0.4991 | 5.0 | 360 | 0.8402 | 0.8477 | 0.8009 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.8.5
- Tokenizers 0.22.2