metadata
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: fine-tuned-arabert-arabGloss-ds
results: []
fine-tuned-arabert-arabGloss-ds
This model is a fine-tuned version of aubmindlab/bert-base-arabertv02 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7052
- Accuracy: 0.8295
- Precision: 0.8016
- Recall: 0.6175
- F1: 0.6976
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 |
|---|---|---|---|---|---|---|---|
| 0.4109 | 1.0 | 9494 | 0.4561 | 0.8065 | 0.6987 | 0.6900 | 0.6943 |
| 0.297 | 2.0 | 18988 | 0.4803 | 0.8213 | 0.7353 | 0.6855 | 0.7095 |
| 0.2316 | 3.0 | 28482 | 0.5530 | 0.8278 | 0.7438 | 0.7007 | 0.7216 |
| 0.1885 | 4.0 | 37976 | 0.7052 | 0.8295 | 0.8016 | 0.6175 | 0.6976 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.1
- Tokenizers 0.12.1