| --- |
| license: apache-2.0 |
| tags: |
| - generated_from_trainer |
| metrics: |
| - precision |
| - recall |
| - f1 |
| - accuracy |
| model-index: |
| - name: BERT_token_classification_14_techs |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # BERT_token_classification_14_techs |
|
|
| This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.0225 |
| - Precision: 0.8752 |
| - Recall: 0.9167 |
| - F1: 0.8955 |
| - 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 | |
| |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
| | 0.5777 | 1.0 | 1907 | 0.4271 | 0.3517 | 0.0988 | 0.1543 | 0.8843 | |
| | 0.3951 | 2.0 | 3814 | 0.2512 | 0.4325 | 0.3259 | 0.3717 | 0.9227 | |
| | 0.2678 | 3.0 | 5721 | 0.1405 | 0.5783 | 0.5598 | 0.5689 | 0.9580 | |
| | 0.153 | 4.0 | 7628 | 0.0924 | 0.6640 | 0.6804 | 0.6721 | 0.9725 | |
| | 0.1129 | 5.0 | 9535 | 0.0717 | 0.7014 | 0.7462 | 0.7231 | 0.9773 | |
| | 0.0798 | 6.0 | 11442 | 0.0598 | 0.7699 | 0.8102 | 0.7895 | 0.9832 | |
| | 0.0637 | 7.0 | 13349 | 0.0405 | 0.8221 | 0.8484 | 0.8351 | 0.9883 | |
| | 0.0483 | 8.0 | 15256 | 0.0307 | 0.8259 | 0.8818 | 0.8529 | 0.9893 | |
| | 0.0375 | 9.0 | 17163 | 0.0244 | 0.8674 | 0.9123 | 0.8893 | 0.9919 | |
| | 0.0315 | 10.0 | 19070 | 0.0225 | 0.8752 | 0.9167 | 0.8955 | 0.9927 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.30.2 |
| - Pytorch 2.3.1+cu121 |
| - Datasets 2.20.0 |
| - Tokenizers 0.13.3 |
|
|
