metadata
library_name: transformers
license: apache-2.0
base_model: google-bert/bert-base-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-cased-finetuned-ner-final
results: []
bert-base-cased-finetuned-ner-final
This model is a fine-tuned version of google-bert/bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7343
- Precision: 0.8366
- Recall: 0.8508
- F1: 0.8436
- Accuracy: 0.9652
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: 1.58775582613963e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.115325565287072
- num_epochs: 8
- label_smoothing_factor: 0.114373096835144
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.7514 | 1.0 | 4250 | 0.7540 | 0.8011 | 0.8113 | 0.8062 | 0.9580 |
| 0.7317 | 2.0 | 8500 | 0.7358 | 0.8277 | 0.8302 | 0.8289 | 0.9619 |
| 0.7212 | 3.0 | 12750 | 0.7329 | 0.8183 | 0.8442 | 0.8310 | 0.9635 |
| 0.7023 | 4.0 | 17000 | 0.7346 | 0.8192 | 0.8459 | 0.8324 | 0.9640 |
| 0.6935 | 5.0 | 21250 | 0.7343 | 0.8366 | 0.8508 | 0.8436 | 0.9652 |
| 0.6851 | 6.0 | 25500 | 0.7409 | 0.8319 | 0.8514 | 0.8415 | 0.9646 |
| 0.678 | 7.0 | 29750 | 0.7450 | 0.8299 | 0.8528 | 0.8412 | 0.9645 |
| 0.672 | 8.0 | 34000 | 0.7475 | 0.8349 | 0.8525 | 0.8436 | 0.9646 |
Framework versions
- Transformers 4.50.1
- Pytorch 2.5.1+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1