mdeberta_v3_base_nli_classifier_mnli_anli_fevernli_xnli
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3806
- F1 Macro: 0.8528
- F1 Micro: 0.8692
- Accuracy Balanced: 0.8510
- Accuracy: 0.8692
- Precision Macro: 0.8548
- Recall Macro: 0.8510
- Precision Micro: 0.8692
- Recall Micro: 0.8692
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: 16
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Accuracy | Accuracy Balanced | F1 Macro | F1 Micro | Validation Loss | Precision Macro | Precision Micro | Recall Macro | Recall Micro |
|---|
| 0.2249 | 1.0 | 12340 | 0.8655 | 0.8474 | 0.8488 | 0.8655 | 0.3410 | 0.8503 | 0.8655 | 0.8474 | 0.8655 |
| 0.1734 | 2.0 | 24680 | 0.3806 | 0.8528 | 0.8692 | 0.8510 | 0.8692 | 0.8548 | 0.8510 | 0.8692 | 0.8692 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1
