metadata
license: apache-2.0
base_model: bert-base-cased
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 bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7641
- Precision: 0.0
- Recall: 0.0
- F1: 0.0
- Accuracy: 0.8610
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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 2 | 2.2048 | 0.0 | 0.0 | 0.0 | 0.7375 |
| No log | 2.0 | 4 | 1.7459 | 0.0 | 0.0 | 0.0 | 0.8533 |
| No log | 3.0 | 6 | 1.3333 | 0.0 | 0.0 | 0.0 | 0.8571 |
| No log | 4.0 | 8 | 1.0206 | 0.0 | 0.0 | 0.0 | 0.8610 |
| No log | 5.0 | 10 | 0.8468 | 0.0 | 0.0 | 0.0 | 0.8610 |
| No log | 6.0 | 12 | 0.7808 | 0.0 | 0.0 | 0.0 | 0.8610 |
| No log | 7.0 | 14 | 0.7649 | 0.0 | 0.0 | 0.0 | 0.8610 |
| No log | 8.0 | 16 | 0.7639 | 0.0 | 0.0 | 0.0 | 0.8610 |
| No log | 9.0 | 18 | 0.7644 | 0.0 | 0.0 | 0.0 | 0.8610 |
| No log | 10.0 | 20 | 0.7641 | 0.0 | 0.0 | 0.0 | 0.8610 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1