|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: bert-base-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: ner-model |
|
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. --> |
|
|
|
# ner-model |
|
|
|
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1297 |
|
- Precision: 0.8229 |
|
- Recall: 0.8866 |
|
- F1: 0.8535 |
|
- Accuracy: 0.9667 |
|
|
|
## 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: 1e-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: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.1752 | 1.0 | 2489 | 0.1261 | 0.7649 | 0.8137 | 0.7885 | 0.9549 | |
|
| 0.1076 | 2.0 | 4978 | 0.1184 | 0.7881 | 0.8592 | 0.8221 | 0.9611 | |
|
| 0.074 | 3.0 | 7467 | 0.1137 | 0.7985 | 0.8802 | 0.8374 | 0.9634 | |
|
| 0.0634 | 4.0 | 9956 | 0.1239 | 0.8125 | 0.8927 | 0.8507 | 0.9651 | |
|
| 0.0387 | 5.0 | 12445 | 0.1297 | 0.8229 | 0.8866 | 0.8535 | 0.9667 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 3.0.0 |
|
- Tokenizers 0.19.1 |
|
|
