nci-ner-v2-stage-b-staging
This model is a fine-tuned version of synapti/nci-ner-v2-staging on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4872
- Precision: 0.8799
- Recall: 0.9043
- F1: 0.8920
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-06
- train_batch_size: 16
- 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: cosine
- lr_scheduler_warmup_steps: 0.05
- num_epochs: 3
- label_smoothing_factor: 0.05
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|---|---|---|---|---|---|---|
| 0.6844 | 0.0346 | 100 | 0.4945 | 0.8598 | 0.8908 | 0.8751 |
| 0.5311 | 0.0692 | 200 | 0.4718 | 0.8566 | 0.8406 | 0.8485 |
| 0.4949 | 0.1038 | 300 | 0.4805 | 0.7719 | 0.7614 | 0.7666 |
Framework versions
- Transformers 5.15.1
- Pytorch 2.13.0+cu130
- Datasets 4.8.5
- Tokenizers 0.22.2