pii-dual-nym-mmbert-base-v3
This model is a fine-tuned version of jhu-clsp/mmBERT-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0022
- Precision: 0.9968
- Recall: 0.9979
- F1: 0.9973
- Accuracy: 0.9994
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-05
- train_batch_size: 16
- eval_batch_size: 32
- 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: cosine_with_restarts
- lr_scheduler_warmup_steps: 200
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0158 | 0.8935 | 2000 | 0.0065 | 0.9923 | 0.9958 | 0.9940 | 0.9982 |
| 0.0046 | 1.7867 | 4000 | 0.0029 | 0.9959 | 0.9978 | 0.9969 | 0.9993 |
| 0.0002 | 2.6799 | 6000 | 0.0028 | 0.9968 | 0.9976 | 0.9972 | 0.9993 |
| 0.0001 | 3.5732 | 8000 | 0.0022 | 0.9969 | 0.9979 | 0.9974 | 0.9994 |
| 0.0006 | 4.0 | 8956 | 0.0022 | 0.9968 | 0.9979 | 0.9973 | 0.9994 |
Framework versions
- Transformers 5.18.0
- Pytorch 2.14.1+cu130
- Datasets 5.0.1
- Tokenizers 0.23.2