metadata
license: mit
tags:
- generated_from_trainer
datasets:
- autextification2023
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: ia-detection-bert-tiny
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: autextification2023
type: autextification2023
config: detection_en
split: train
args: detection_en
metrics:
- name: Accuracy
type: accuracy
value: 0.699019787467937
- name: F1
type: f1
value: 0.7522153927372828
- name: Precision
type: precision
value: 0.6506621436492922
- name: Recall
type: recall
value: 0.891331546023235
ia-detection-bert-tiny
This model is a fine-tuned version of prajjwal1/bert-tiny on the autextification2023 dataset. It achieves the following results on the evaluation set:
- Loss: 0.9775
- Accuracy: 0.6990
- F1: 0.7522
- Precision: 0.6507
- Recall: 0.8913
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: 0.0001
- 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
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
0.3606 | 1.0 | 3808 | 0.4135 | 0.8068 | 0.8126 | 0.7795 | 0.8486 |
0.39 | 2.0 | 7616 | 0.4197 | 0.8213 | 0.8147 | 0.8344 | 0.7959 |
0.386 | 3.0 | 11424 | 0.5145 | 0.8210 | 0.8249 | 0.7977 | 0.8540 |
0.277 | 4.0 | 15232 | 0.7962 | 0.8080 | 0.7887 | 0.8633 | 0.7259 |
0.1913 | 5.0 | 19040 | 0.8833 | 0.8115 | 0.8001 | 0.8396 | 0.7642 |
0.2053 | 6.0 | 22848 | 0.9313 | 0.8180 | 0.8070 | 0.8468 | 0.7708 |
Framework versions
- Transformers 4.26.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.13.3