arabert_baseline_development_task3_fold1
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: 0.2282
- Qwk: 0.0
- Mse: 0.2300
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
Training results
| Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
|---|---|---|---|---|---|
| No log | 0.6667 | 2 | 2.8377 | 0.0075 | 2.8075 |
| No log | 1.3333 | 4 | 0.7850 | -0.0722 | 0.7741 |
| No log | 2.0 | 6 | 0.2436 | 0.0 | 0.2359 |
| No log | 2.6667 | 8 | 0.2726 | -0.3562 | 0.2744 |
| No log | 3.3333 | 10 | 0.2421 | 0.0 | 0.2449 |
| No log | 4.0 | 12 | 0.2542 | 0.0 | 0.2555 |
| No log | 4.6667 | 14 | 0.2669 | 0.0 | 0.2677 |
| No log | 5.3333 | 16 | 0.2579 | 0.0 | 0.2592 |
| No log | 6.0 | 18 | 0.2389 | 0.0 | 0.2407 |
| No log | 6.6667 | 20 | 0.2143 | 0.0 | 0.2176 |
| No log | 7.3333 | 22 | 0.2121 | 0.0 | 0.2162 |
| No log | 8.0 | 24 | 0.2173 | 0.0 | 0.2199 |
| No log | 8.6667 | 26 | 0.2240 | 0.0 | 0.2258 |
| No log | 9.3333 | 28 | 0.2288 | 0.0 | 0.2304 |
| No log | 10.0 | 30 | 0.2282 | 0.0 | 0.2300 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 11
Model tree for salbatarni/arabert_baseline_development_task3_fold1
Base model
aubmindlab/bert-base-arabertv02
Finetuned
this model