metadata
base_model: aubmindlab/bert-base-arabertv02
tags:
- generated_from_trainer
model-index:
- name: arabert_cross_relevance_task1_fold0
results: []
arabert_cross_relevance_task1_fold0
This model is a fine-tuned version of aubmindlab/bert-base-arabertv02 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1791
- Qwk: 0.0281
- Mse: 0.1791
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
|---|---|---|---|---|---|
| No log | 0.0690 | 2 | 1.5191 | -0.0019 | 1.5191 |
| No log | 0.1379 | 4 | 0.3899 | 0.0231 | 0.3899 |
| No log | 0.2069 | 6 | 0.1889 | 0.0929 | 0.1889 |
| No log | 0.2759 | 8 | 0.2118 | 0.0239 | 0.2118 |
| No log | 0.3448 | 10 | 0.1816 | 0.0394 | 0.1816 |
| No log | 0.4138 | 12 | 0.1490 | 0.0571 | 0.1490 |
| No log | 0.4828 | 14 | 0.1823 | 0.0368 | 0.1823 |
| No log | 0.5517 | 16 | 0.2402 | 0.0300 | 0.2402 |
| No log | 0.6207 | 18 | 0.2832 | 0.0245 | 0.2832 |
| No log | 0.6897 | 20 | 0.2599 | 0.0245 | 0.2599 |
| No log | 0.7586 | 22 | 0.2442 | 0.0281 | 0.2442 |
| No log | 0.8276 | 24 | 0.2126 | 0.0335 | 0.2126 |
| No log | 0.8966 | 26 | 0.1901 | 0.0368 | 0.1901 |
| No log | 0.9655 | 28 | 0.1791 | 0.0281 | 0.1791 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1