metadata
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: fine_tuned_mix50k_arabert_similarity
results: []
fine_tuned_mix50k_arabert_similarity
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: 0.5527
- Accuracy: 0.8802
- Precision: 0.9022
- Recall: 0.8227
- F1: 0.8606
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 |
|---|---|---|---|---|---|---|---|
| 0.3452 | 1.0 | 9862 | 0.3132 | 0.8737 | 0.8774 | 0.8358 | 0.8561 |
| 0.2496 | 2.0 | 19724 | 0.2931 | 0.8778 | 0.8678 | 0.8589 | 0.8633 |
| 0.1939 | 3.0 | 29586 | 0.3597 | 0.8774 | 0.9047 | 0.8128 | 0.8563 |
| 0.1553 | 4.0 | 39448 | 0.4949 | 0.8788 | 0.8843 | 0.8402 | 0.8617 |
| 0.1219 | 5.0 | 49310 | 0.5527 | 0.8802 | 0.9022 | 0.8227 | 0.8606 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1