metadata
base_model: aubmindlab/bert-base-arabert
tags:
- generated_from_trainer
model-index:
- name: QA_FineTuned_Arabertr
results: []
QA_FineTuned_Arabertr
This model is a fine-tuned version of aubmindlab/bert-base-arabert on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.8357
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: 0.0002
- 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.518 | 0.13 | 10 | 4.3573 |
| 4.254 | 0.27 | 20 | 3.8054 |
| 3.9915 | 0.4 | 30 | 3.5788 |
| 3.836 | 0.53 | 40 | 3.4054 |
| 3.6733 | 0.67 | 50 | 3.2506 |
| 3.4425 | 0.8 | 60 | 3.0882 |
| 3.2917 | 0.93 | 70 | 2.9934 |
| 2.9622 | 1.07 | 80 | 3.0029 |
| 2.3228 | 1.2 | 90 | 3.1190 |
| 2.4004 | 1.33 | 100 | 2.8613 |
| 2.3946 | 1.47 | 110 | 2.8983 |
| 2.3108 | 1.6 | 120 | 2.7711 |
| 2.3778 | 1.73 | 130 | 2.7062 |
| 2.3335 | 1.87 | 140 | 2.9916 |
| 2.4273 | 2.0 | 150 | 2.6713 |
| 1.4165 | 2.13 | 160 | 2.8003 |
| 1.1488 | 2.27 | 170 | 2.7959 |
| 1.2044 | 2.4 | 180 | 3.1311 |
| 1.2715 | 2.53 | 190 | 2.8319 |
| 1.1309 | 2.67 | 200 | 2.8048 |
| 1.3421 | 2.8 | 210 | 2.8158 |
| 0.9567 | 2.93 | 220 | 2.8357 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2