|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: electra-base-ner-food-recipe-v2 |
|
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. --> |
|
|
|
# electra-base-ner-food-recipe-v2 |
|
|
|
This model was trained from scratch on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1709 |
|
- Precision: 0.8007 |
|
- Recall: 0.8867 |
|
- F1: 0.8415 |
|
- Accuracy: 0.9669 |
|
|
|
## 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: 5e-06 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 0.5 | 400 | 0.1420 | 0.7862 | 0.8871 | 0.8336 | 0.9655 | |
|
| 0.101 | 1.01 | 800 | 0.1580 | 0.8317 | 0.8817 | 0.8559 | 0.9716 | |
|
| 0.0966 | 1.51 | 1200 | 0.1467 | 0.8105 | 0.8917 | 0.8492 | 0.9693 | |
|
| 0.0849 | 2.01 | 1600 | 0.1408 | 0.7966 | 0.8771 | 0.8349 | 0.9669 | |
|
| 0.085 | 2.51 | 2000 | 0.1487 | 0.7941 | 0.8880 | 0.8384 | 0.9662 | |
|
| 0.085 | 3.02 | 2400 | 0.1477 | 0.7773 | 0.8867 | 0.8284 | 0.9635 | |
|
| 0.0766 | 3.52 | 2800 | 0.1852 | 0.8298 | 0.8807 | 0.8545 | 0.9710 | |
|
| 0.0725 | 4.02 | 3200 | 0.1674 | 0.8073 | 0.8830 | 0.8435 | 0.9679 | |
|
| 0.069 | 4.52 | 3600 | 0.1709 | 0.8007 | 0.8867 | 0.8415 | 0.9669 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.4 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.3 |
|
|