metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: BERT_token_classification_18_techs
results: []
BERT_token_classification_18_techs
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0228
- Precision: 0.8769
- Recall: 0.9215
- F1: 0.8987
- Accuracy: 0.9927
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 |
|---|---|---|---|---|---|---|---|
| 0.6 | 1.0 | 1907 | 0.4260 | 0.3545 | 0.1303 | 0.1906 | 0.8856 |
| 0.4035 | 2.0 | 3814 | 0.2568 | 0.4196 | 0.2961 | 0.3472 | 0.9224 |
| 0.2808 | 3.0 | 5721 | 0.1464 | 0.5921 | 0.5058 | 0.5456 | 0.9568 |
| 0.1648 | 4.0 | 7628 | 0.0952 | 0.6679 | 0.6614 | 0.6646 | 0.9717 |
| 0.1138 | 5.0 | 9535 | 0.0708 | 0.7138 | 0.7422 | 0.7277 | 0.9781 |
| 0.0899 | 6.0 | 11442 | 0.0516 | 0.7779 | 0.7950 | 0.7863 | 0.9840 |
| 0.0609 | 7.0 | 13349 | 0.0357 | 0.8352 | 0.8496 | 0.8423 | 0.9888 |
| 0.0503 | 8.0 | 15256 | 0.0269 | 0.8677 | 0.9010 | 0.8841 | 0.9915 |
| 0.0376 | 9.0 | 17163 | 0.0248 | 0.8700 | 0.9155 | 0.8921 | 0.9920 |
| 0.0331 | 10.0 | 19070 | 0.0228 | 0.8769 | 0.9215 | 0.8987 | 0.9927 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.13.3