my-distilBERT-finetune-ner
This model is a fine-tuned version of distilbert-base-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0563
- Precision: 0.9377
- Recall: 0.9398
- F1: 0.9387
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: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|---|---|---|---|---|---|---|
| No log | 1.0 | 439 | 0.0547 | 0.9251 | 0.9291 | 0.9271 |
| 0.1451 | 2.0 | 878 | 0.0531 | 0.9315 | 0.9386 | 0.9350 |
| 0.0326 | 3.0 | 1317 | 0.0563 | 0.9377 | 0.9398 | 0.9387 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2