xlm-roberta-sarcasmo-bs32-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: 0.4162
- F1 Macro: 0.9318
- F1 Weighted: 0.9348
- Accuracy: 0.9346
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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 |
|---|---|---|---|---|---|---|
| 0.7488 | 1.0 | 478 | 0.2721 | 0.8905 | 0.8961 | 0.8966 |
| 0.4645 | 2.0 | 956 | 0.2086 | 0.9184 | 0.9225 | 0.9228 |
| 0.3753 | 3.0 | 1434 | 0.2213 | 0.9142 | 0.9186 | 0.9191 |
| 0.3079 | 4.0 | 1912 | 0.2329 | 0.9370 | 0.9401 | 0.9403 |
| 0.2744 | 5.0 | 2390 | 0.3248 | 0.9337 | 0.9372 | 0.9377 |
| 0.1634 | 6.0 | 2868 | 0.4056 | 0.9332 | 0.9368 | 0.9374 |
| 0.0987 | 7.0 | 3346 | 0.4162 | 0.9318 | 0.9348 | 0.9346 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2