distilbert-base-multilingual-cased-language_detection-LG
This model is a fine-tuned version of distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1102
- Accuracy: 0.9883
- Weighted f1: 0.9884
- Micro f1: 0.9883
- Macro f1: 0.9882
- Weighted recall: 0.9883
- Micro recall: 0.9883
- Macro recall: 0.9879
- Weighted precision: 0.9888
- Micro precision: 0.9883
- Macro precision: 0.9887
Model description
This is a classification model of 20 different languages.
For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Language%20Detection/Language%20Detection-20k%20Samples/language_detection-20k.ipynb
Intended uses & limitations
This model is intended to demonstrate my ability to solve a complex problem using technology.
Training and evaluation data
Dataset Source: https://www.kaggle.com/datasets/basilb2s/language-detection
Input Word Length:
Input Word Length By Class:
Class Distribution:
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Weighted f1 | Micro f1 | Macro f1 | Weighted recall | Micro recall | Macro recall | Weighted precision | Micro precision | Macro precision |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0.7343 | 1.0 | 246 | 0.1102 | 0.9883 | 0.9884 | 0.9883 | 0.9882 | 0.9883 | 0.9883 | 0.9879 | 0.9888 | 0.9883 | 0.9887 |
0.0939 | 2.0 | 492 | 0.0802 | 0.9883 | 0.9884 | 0.9883 | 0.9882 | 0.9883 | 0.9883 | 0.9879 | 0.9888 | 0.9883 | 0.9887 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1
- Datasets 2.9.0
- Tokenizers 0.12.1