metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: BERT_token_classification_14PTC_aug800_fixed
results: []
BERT_token_classification_14PTC_aug800_fixed
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: 1.5869
- Precision: 0.0559
- Recall: 0.0728
- F1: 0.0633
- Accuracy: 0.7101
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 |
|---|---|---|---|---|---|---|---|
| 0.6525 | 1.0 | 1839 | 1.1412 | 0.0228 | 0.0133 | 0.0168 | 0.7311 |
| 0.3649 | 2.0 | 3678 | 1.1856 | 0.0351 | 0.0302 | 0.0325 | 0.7211 |
| 0.2838 | 3.0 | 5517 | 1.2173 | 0.0650 | 0.0631 | 0.0640 | 0.7328 |
| 0.2152 | 4.0 | 7356 | 1.3204 | 0.0578 | 0.0631 | 0.0603 | 0.7231 |
| 0.1864 | 5.0 | 9195 | 1.3214 | 0.0594 | 0.0613 | 0.0603 | 0.7312 |
| 0.1579 | 6.0 | 11034 | 1.4035 | 0.0616 | 0.0577 | 0.0596 | 0.7220 |
| 0.1427 | 7.0 | 12873 | 1.4422 | 0.0529 | 0.0657 | 0.0586 | 0.7068 |
| 0.1297 | 8.0 | 14712 | 1.5468 | 0.0623 | 0.0835 | 0.0713 | 0.7059 |
| 0.1161 | 9.0 | 16551 | 1.5283 | 0.0621 | 0.0790 | 0.0696 | 0.7140 |
| 0.0943 | 10.0 | 18390 | 1.5869 | 0.0559 | 0.0728 | 0.0633 | 0.7101 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.13.3