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: 0.2870
- Precision: 0.6543
- Recall: 0.6256
- F1: 0.6397
- Accuracy: 0.9433
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 | 0.3862 | 0.4247 | 0.2901 | 0.3447 | 0.9041 |
| 0.4179 | 2.0 | 564 | 0.3053 | 0.5411 | 0.4216 | 0.4739 | 0.9228 |
| 0.4179 | 3.0 | 846 | 0.2923 | 0.6195 | 0.5025 | 0.5549 | 0.9315 |
| 0.2108 | 4.0 | 1128 | 0.2770 | 0.5641 | 0.5346 | 0.5489 | 0.9322 |
| 0.2108 | 5.0 | 1410 | 0.2789 | 0.6104 | 0.5548 | 0.5813 | 0.9369 |
| 0.1279 | 6.0 | 1692 | 0.2793 | 0.6171 | 0.5953 | 0.6060 | 0.9382 |
| 0.1279 | 7.0 | 1974 | 0.2790 | 0.6348 | 0.6037 | 0.6188 | 0.9417 |
| 0.0881 | 8.0 | 2256 | 0.2864 | 0.6490 | 0.6206 | 0.6345 | 0.9419 |
| 0.0615 | 9.0 | 2538 | 0.2874 | 0.6414 | 0.6003 | 0.6202 | 0.9417 |
| 0.0615 | 10.0 | 2820 | 0.2870 | 0.6543 | 0.6256 | 0.6397 | 0.9433 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1