|
|
--- |
|
|
license: apache-2.0 |
|
|
base_model: mpalaval/bert-ner-3 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- precision |
|
|
- recall |
|
|
- f1 |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: bert-ner-4 |
|
|
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-ner-4 |
|
|
|
|
|
This model is a fine-tuned version of [mpalaval/bert-ner-3](https://huggingface.co/mpalaval/bert-ner-3) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.6352 |
|
|
- Precision: 0.2024 |
|
|
- Recall: 0.4674 |
|
|
- F1: 0.2825 |
|
|
- Accuracy: 0.8901 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
|
| No log | 1.0 | 258 | 0.4728 | 0.1508 | 0.4021 | 0.2193 | 0.8795 | |
|
|
| 0.0801 | 2.0 | 516 | 0.4265 | 0.1744 | 0.4124 | 0.2451 | 0.8906 | |
|
|
| 0.0801 | 3.0 | 774 | 0.5207 | 0.1564 | 0.4296 | 0.2294 | 0.8761 | |
|
|
| 0.0513 | 4.0 | 1032 | 0.4908 | 0.1718 | 0.4021 | 0.2407 | 0.8882 | |
|
|
| 0.0513 | 5.0 | 1290 | 0.5247 | 0.1967 | 0.4089 | 0.2656 | 0.8988 | |
|
|
| 0.0263 | 6.0 | 1548 | 0.5547 | 0.1902 | 0.4261 | 0.2630 | 0.8955 | |
|
|
| 0.0263 | 7.0 | 1806 | 0.6413 | 0.1849 | 0.4639 | 0.2644 | 0.8836 | |
|
|
| 0.0133 | 8.0 | 2064 | 0.6059 | 0.2035 | 0.4742 | 0.2848 | 0.8900 | |
|
|
| 0.0133 | 9.0 | 2322 | 0.6311 | 0.2041 | 0.4742 | 0.2854 | 0.8906 | |
|
|
| 0.0088 | 10.0 | 2580 | 0.6352 | 0.2024 | 0.4674 | 0.2825 | 0.8901 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.34.1 |
|
|
- Pytorch 2.1.0+cu118 |
|
|
- Datasets 2.14.6 |
|
|
- Tokenizers 0.14.1 |
|
|
|
