metadata
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned-ner-harem
results: []
distilbert-base-uncased-finetuned-ner-harem
This model is a fine-tuned version of distilbert/distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2794
- Precision: 0.6556
- Recall: 0.6324
- F1: 0.6438
- Accuracy: 0.9448
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: 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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 282 | 0.3860 | 0.3575 | 0.2411 | 0.2880 | 0.9035 |
| 0.4189 | 2.0 | 564 | 0.3048 | 0.5051 | 0.4165 | 0.4566 | 0.9227 |
| 0.4189 | 3.0 | 846 | 0.2893 | 0.5924 | 0.5025 | 0.5438 | 0.9303 |
| 0.209 | 4.0 | 1128 | 0.2752 | 0.5640 | 0.5649 | 0.5644 | 0.9335 |
| 0.209 | 5.0 | 1410 | 0.2880 | 0.6466 | 0.5616 | 0.6011 | 0.9409 |
| 0.1252 | 6.0 | 1692 | 0.2656 | 0.6404 | 0.5885 | 0.6134 | 0.9426 |
| 0.1252 | 7.0 | 1974 | 0.2662 | 0.6367 | 0.6324 | 0.6345 | 0.9419 |
| 0.0859 | 8.0 | 2256 | 0.2717 | 0.6584 | 0.6273 | 0.6425 | 0.9444 |
| 0.0593 | 9.0 | 2538 | 0.2774 | 0.6590 | 0.6290 | 0.6437 | 0.9440 |
| 0.0593 | 10.0 | 2820 | 0.2794 | 0.6556 | 0.6324 | 0.6438 | 0.9448 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1