|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- ingredients_yes_no |
|
|
metrics: |
|
|
- precision |
|
|
- recall |
|
|
- f1 |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: distilbert-base-uncased-finetuned-ingredients |
|
|
results: |
|
|
- task: |
|
|
name: Token Classification |
|
|
type: token-classification |
|
|
dataset: |
|
|
name: ingredients_yes_no |
|
|
type: ingredients_yes_no |
|
|
args: IngredientsYesNo |
|
|
metrics: |
|
|
- name: Precision |
|
|
type: precision |
|
|
value: 0.9847619047619047 |
|
|
- name: Recall |
|
|
type: recall |
|
|
value: 0.988527724665392 |
|
|
- name: F1 |
|
|
type: f1 |
|
|
value: 0.9866412213740458 |
|
|
- name: Accuracy |
|
|
type: accuracy |
|
|
value: 0.9974453590689754 |
|
|
--- |
|
|
|
|
|
<!-- 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. --> |
|
|
|
|
|
# distilbert-base-uncased-finetuned-ingredients |
|
|
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the ingredients_yes_no dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0138 |
|
|
- Precision: 0.9848 |
|
|
- Recall: 0.9885 |
|
|
- F1: 0.9866 |
|
|
- Accuracy: 0.9974 |
|
|
|
|
|
## 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 | 1.0 | 83 | 0.1004 | 0.8978 | 0.9235 | 0.9105 | 0.9807 | |
|
|
| No log | 2.0 | 166 | 0.0237 | 0.9714 | 0.9751 | 0.9733 | 0.9940 | |
|
|
| No log | 3.0 | 249 | 0.0204 | 0.9715 | 0.9771 | 0.9743 | 0.9929 | |
|
|
| No log | 4.0 | 332 | 0.0138 | 0.9773 | 0.9866 | 0.9819 | 0.9969 | |
|
|
| No log | 5.0 | 415 | 0.0137 | 0.9829 | 0.9866 | 0.9847 | 0.9969 | |
|
|
| No log | 6.0 | 498 | 0.0134 | 0.9847 | 0.9866 | 0.9857 | 0.9972 | |
|
|
| 0.0923 | 7.0 | 581 | 0.0160 | 0.9866 | 0.9885 | 0.9876 | 0.9972 | |
|
|
| 0.0923 | 8.0 | 664 | 0.0147 | 0.9848 | 0.9885 | 0.9866 | 0.9974 | |
|
|
| 0.0923 | 9.0 | 747 | 0.0139 | 0.9848 | 0.9885 | 0.9866 | 0.9974 | |
|
|
| 0.0923 | 10.0 | 830 | 0.0138 | 0.9848 | 0.9885 | 0.9866 | 0.9974 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.10.0 |
|
|
- Pytorch 1.9.0+cu102 |
|
|
- Datasets 1.11.0 |
|
|
- Tokenizers 0.10.3 |
|
|
|
