metadata
license: apache-2.0
base_model: distilbert-base-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: ner-classifier-distil-bert
results: []
ner-classifier-distil-bert
This model is a fine-tuned version of distilbert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0484
- Precision: 0.9237
- Recall: 0.9388
- F1: 0.9312
- Accuracy: 0.9929
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0319 | 1.0 | 3546 | 0.0326 | 0.8726 | 0.9023 | 0.8872 | 0.9882 |
| 0.0206 | 2.0 | 7092 | 0.0285 | 0.8967 | 0.9273 | 0.9117 | 0.9910 |
| 0.0133 | 3.0 | 10638 | 0.0295 | 0.9072 | 0.9307 | 0.9188 | 0.9916 |
| 0.0081 | 4.0 | 14184 | 0.0327 | 0.9127 | 0.9274 | 0.9200 | 0.9918 |
| 0.0038 | 5.0 | 17730 | 0.0346 | 0.9205 | 0.9297 | 0.9251 | 0.9922 |
| 0.0044 | 6.0 | 21276 | 0.0376 | 0.9258 | 0.9299 | 0.9278 | 0.9925 |
| 0.0017 | 7.0 | 24822 | 0.0427 | 0.9277 | 0.9256 | 0.9266 | 0.9923 |
| 0.0038 | 8.0 | 28368 | 0.0460 | 0.9170 | 0.9399 | 0.9283 | 0.9926 |
| 0.0008 | 9.0 | 31914 | 0.0473 | 0.9266 | 0.9344 | 0.9305 | 0.9928 |
| 0.0026 | 10.0 | 35460 | 0.0484 | 0.9237 | 0.9388 | 0.9312 | 0.9929 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2