metadata
license: apache-2.0
base_model: Omartificial-Intelligence-Space/SA-BERT-V1
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: Mohammed_Saudi_Classifier_SABERT
results: []
Mohammed_Saudi_Classifier_SABERT
This model is a fine-tuned version of Omartificial-Intelligence-Space/SA-BERT-V1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0890
- Accuracy: 0.6355
- F1: 0.6159
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: 3e-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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 60 | 3.7608 | 0.0093 | 0.0002 |
| No log | 2.0 | 120 | 3.6178 | 0.2243 | 0.2016 |
| No log | 3.0 | 180 | 3.1702 | 0.4486 | 0.3837 |
| No log | 4.0 | 240 | 2.8401 | 0.4860 | 0.4399 |
| No log | 5.0 | 300 | 2.5739 | 0.5514 | 0.5257 |
| No log | 6.0 | 360 | 2.4024 | 0.5981 | 0.5784 |
| No log | 7.0 | 420 | 2.2519 | 0.5794 | 0.5480 |
| No log | 8.0 | 480 | 2.1640 | 0.5981 | 0.5746 |
| 2.693 | 9.0 | 540 | 2.1130 | 0.6075 | 0.5796 |
| 2.693 | 10.0 | 600 | 2.0890 | 0.6355 | 0.6159 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.7.1+cu126
- Datasets 3.6.0
- Tokenizers 0.19.1