distilbert-base-uncased_finetuned_ner
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0013
- Precision: 0.9420
- Recall: 0.9553
- F1: 0.9486
- Accuracy: 0.9997
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: 20
- eval_batch_size: 20
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 341 | 0.0032 | 0.8657 | 0.8682 | 0.8670 | 0.9993 |
0.0338 | 2.0 | 682 | 0.0017 | 0.9366 | 0.9372 | 0.9369 | 0.9997 |
0.0021 | 3.0 | 1023 | 0.0013 | 0.9420 | 0.9553 | 0.9486 | 0.9997 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 3