metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner
results: []
bert-finetuned-ner
This model is a fine-tuned version of distilbert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1622
- Precision: 0.7774
- Recall: 0.7937
- F1: 0.7854
- Accuracy: 0.9707
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: 8e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 131 | 0.1355 | 0.6880 | 0.7298 | 0.7083 | 0.9604 |
| No log | 2.0 | 262 | 0.1194 | 0.7564 | 0.7727 | 0.7645 | 0.9684 |
| No log | 3.0 | 393 | 0.1277 | 0.7731 | 0.7868 | 0.7799 | 0.9691 |
| 0.0433 | 4.0 | 524 | 0.1433 | 0.7553 | 0.7829 | 0.7688 | 0.9685 |
| 0.0433 | 5.0 | 655 | 0.1515 | 0.7734 | 0.7946 | 0.7839 | 0.9700 |
| 0.0433 | 6.0 | 786 | 0.1518 | 0.7819 | 0.8008 | 0.7912 | 0.9708 |
| 0.0433 | 7.0 | 917 | 0.1602 | 0.7752 | 0.7914 | 0.7832 | 0.9704 |
| 0.0094 | 8.0 | 1048 | 0.1622 | 0.7774 | 0.7937 | 0.7854 | 0.9707 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3