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: 0.706714913887871
- name: F1
type: f1
value: 0.7557691574169433
- name: Precision
type: precision
value: 0.6592799627337459
- name: Recall
type: recall
value: 0.8853440571939232
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: 1.0749
- Accuracy: 0.7067
- F1: 0.7558
- Precision: 0.6593
- Recall: 0.8853
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 |
|---|---|---|---|---|---|---|---|
| 0.4176 | 1.0 | 3808 | 0.4391 | 0.7962 | 0.7629 | 0.8973 | 0.6635 |
| 0.2567 | 2.0 | 7616 | 0.4912 | 0.8233 | 0.8021 | 0.8984 | 0.7244 |
| 0.2342 | 3.0 | 11424 | 0.5477 | 0.8473 | 0.8355 | 0.8932 | 0.7848 |
| 0.2226 | 4.0 | 15232 | 0.7703 | 0.8059 | 0.7743 | 0.9103 | 0.6736 |
| 0.2706 | 5.0 | 19040 | 0.7108 | 0.8422 | 0.8311 | 0.8825 | 0.7854 |
| 0.1797 | 6.0 | 22848 | 0.8042 | 0.8381 | 0.8314 | 0.8567 | 0.8075 |
Framework versions
- Transformers 4.26.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.13.3