metadata
library_name: transformers
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert-ner-conll2003
results: []
distilbert-ner-conll2003
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0131
- Accuracy: 0.9965
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0825 | 1.0 | 878 | 0.0111 | 0.9968 |
| 0.0075 | 2.0 | 1756 | 0.0092 | 0.9973 |
| 0.0041 | 3.0 | 2634 | 0.0093 | 0.9975 |
| 0.0027 | 4.0 | 3512 | 0.0097 | 0.9975 |
| 0.0021 | 5.0 | 4390 | 0.0099 | 0.9975 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3