metadata
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: M11
results: []
This model was trained on data without unique labels.
M11
This model is a fine-tuned version of aubmindlab/bert-base-arabertv2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0194
- Accuracy: 0.9974
- Precision: 0.9961
- Recall: 0.9987
- F1: 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.0269 | 1.0 | 21116 | 0.0205 | 0.9961 | 0.9941 | 0.9981 | 0.9961 |
| 0.012 | 2.0 | 42232 | 0.0179 | 0.9968 | 0.9963 | 0.9974 | 0.9968 |
| 0.0067 | 3.0 | 63348 | 0.0201 | 0.9972 | 0.9971 | 0.9972 | 0.9972 |
| 0.0042 | 4.0 | 84464 | 0.0180 | 0.9975 | 0.9962 | 0.9987 | 0.9975 |
| 0.0028 | 5.0 | 105580 | 0.0194 | 0.9974 | 0.9961 | 0.9987 | 0.9974 |
Framework versions
- Transformers 4.21.2
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1