chrono-link-bert-topres19th-ner
This model is a fine-tuned version of emanuelaboros/chrono-link-bert-americanstories-1850-1890 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0690
- Precision: 0.7574
- Recall: 0.7970
- F1: 0.7767
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: 3e-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
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|---|---|---|---|---|---|---|
| 0.0555 | 1.0 | 368 | 0.0369 | 0.6835 | 0.8085 | 0.7407 |
| 0.0340 | 2.0 | 736 | 0.0377 | 0.7209 | 0.7915 | 0.7546 |
| 0.0189 | 3.0 | 1104 | 0.0402 | 0.7077 | 0.8553 | 0.7746 |
| 0.0093 | 4.0 | 1472 | 0.0481 | 0.7510 | 0.8340 | 0.7903 |
| 0.0043 | 5.0 | 1840 | 0.0495 | 0.7569 | 0.8213 | 0.7878 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.12.1+cu130
- Datasets 5.0.0
- Tokenizers 0.22.2