|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: bert-base-greek-uncased-v1-finetuned-ner |
|
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-base-greek-uncased-v1-finetuned-ner |
|
|
|
This model is a fine-tuned version of [nlpaueb/bert-base-greek-uncased-v1](https://huggingface.co/nlpaueb/bert-base-greek-uncased-v1) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1052 |
|
- Precision: 0.8440 |
|
- Recall: 0.8566 |
|
- F1: 0.8503 |
|
- Accuracy: 0.9768 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- 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 | 0.64 | 250 | 0.0913 | 0.7814 | 0.8208 | 0.8073 | 0.9728 | |
|
| 0.1144 | 1.29 | 500 | 0.0823 | 0.7940 | 0.8448 | 0.8342 | 0.9755 | |
|
| 0.1144 | 1.93 | 750 | 0.0812 | 0.8057 | 0.8212 | 0.8328 | 0.9751 | |
|
| 0.0570 | 2.58 | 1000 | 0.0855 | 0.8244 | 0.8514 | 0.8292 | 0.9744 | |
|
| 0.0570 | 3.22 | 1250 | 0.0926 | 0.8329 | 0.8441 | 0.8397 | 0.9760 | |
|
| 0.0393 | 3.87 | 1500 | 0.0869 | 0.8256 | 0.8633 | 0.8440 | 0.9774 | |
|
| 0.0393 | 4.51 | 1750 | 0.1049 | 0.8290 | 0.8636 | 0.8459 | 0.9766 | |
|
| 0.026 | 5.15 | 2000 | 0.1093 | 0.8440 | 0.8566 | 0.8503 | 0.9768 | |
|
| 0.026 | 5.8 | 2250 | 0.1172 | 0.8301 | 0.8514 | 0.8406 | 0.9760 | |
|
| 0.0189 | 6.44 | 2500 | 0.1273 | 0.8238 | 0.8688 | 0.8457 | 0.9766 | |
|
| 0.0189 | 7.09 | 2750 | 0.1246 | 0.8350 | 0.8539 | 0.8443 | 0.9764 | |
|
| 0.0148 | 7.73 | 3000 | 0.1262 | 0.8333 | 0.8608 | 0.8468 | 0.9764 | |
|
| 0.0148 | 8.38 | 3250 | 0.1347 | 0.8319 | 0.8591 | 0.8453 | 0.9762 | |
|
| 0.0010 | 9.02 | 3500 | 0.1325 | 0.8376 | 0.8504 | 0.8439 | 0.9766 | |
|
| 0.0010 | 9.66 | 3750 | 0.1362 | 0.8371 | 0.8563 | 0.8466 | 0.9765 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.22.0 |
|
- Pytorch 1.12.1+cu113 |
|
- Datasets 2.4.0 |
|
- Tokenizers 0.12.1 |
|
|