xlm-roberta-sarcasmo-bs16-ep10
This model is a fine-tuned version of xlm-roberta-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5980
- F1 Macro: 0.9330
- F1 Weighted: 0.9361
- Accuracy: 0.9361
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Weighted | Accuracy |
|---|---|---|---|---|---|---|
| 0.3332 | 1.0 | 955 | 0.2610 | 0.8953 | 0.9000 | 0.8997 |
| 0.2880 | 2.0 | 1910 | 0.2216 | 0.9147 | 0.9191 | 0.9196 |
| 0.2410 | 3.0 | 2865 | 0.2955 | 0.9197 | 0.9238 | 0.9243 |
| 0.1338 | 4.0 | 3820 | 0.3369 | 0.9324 | 0.9358 | 0.9361 |
| 0.0894 | 5.0 | 4775 | 0.3966 | 0.9322 | 0.9355 | 0.9356 |
| 0.0556 | 6.0 | 5730 | 0.4219 | 0.9353 | 0.9382 | 0.9382 |
| 0.0504 | 7.0 | 6685 | 0.4733 | 0.9304 | 0.9340 | 0.9343 |
| 0.0370 | 8.0 | 7640 | 0.5204 | 0.9316 | 0.9347 | 0.9346 |
| 0.0111 | 9.0 | 8595 | 0.5980 | 0.9330 | 0.9361 | 0.9361 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2