metadata
base_model: aubmindlab/bert-base-arabertv02
tags:
- generated_from_trainer
model-index:
- name: arabert_cross_relevance_task6_fold6
results: []
arabert_cross_relevance_task6_fold6
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: 0.2708
- Qwk: 0.2181
- Mse: 0.2714
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: 1
Training results
Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
---|---|---|---|---|---|
No log | 0.0308 | 2 | 0.3997 | 0.1409 | 0.4004 |
No log | 0.0615 | 4 | 0.3224 | 0.1635 | 0.3230 |
No log | 0.0923 | 6 | 0.3114 | 0.1336 | 0.3118 |
No log | 0.1231 | 8 | 0.2792 | 0.1434 | 0.2797 |
No log | 0.1538 | 10 | 0.5126 | 0.1528 | 0.5116 |
No log | 0.1846 | 12 | 0.5725 | 0.1322 | 0.5710 |
No log | 0.2154 | 14 | 0.3291 | 0.2313 | 0.3295 |
No log | 0.2462 | 16 | 0.2709 | 0.2220 | 0.2712 |
No log | 0.2769 | 18 | 0.2704 | 0.1746 | 0.2703 |
No log | 0.3077 | 20 | 0.2714 | 0.1858 | 0.2712 |
No log | 0.3385 | 22 | 0.2684 | 0.2083 | 0.2682 |
No log | 0.3692 | 24 | 0.2725 | 0.2135 | 0.2725 |
No log | 0.4 | 26 | 0.2759 | 0.2135 | 0.2760 |
No log | 0.4308 | 28 | 0.2785 | 0.2173 | 0.2789 |
No log | 0.4615 | 30 | 0.2798 | 0.1719 | 0.2803 |
No log | 0.4923 | 32 | 0.2835 | 0.1711 | 0.2841 |
No log | 0.5231 | 34 | 0.2859 | 0.1750 | 0.2866 |
No log | 0.5538 | 36 | 0.2843 | 0.1681 | 0.2850 |
No log | 0.5846 | 38 | 0.2824 | 0.1738 | 0.2833 |
No log | 0.6154 | 40 | 0.2828 | 0.2186 | 0.2837 |
No log | 0.6462 | 42 | 0.2811 | 0.2161 | 0.2821 |
No log | 0.6769 | 44 | 0.2826 | 0.2239 | 0.2836 |
No log | 0.7077 | 46 | 0.2875 | 0.2181 | 0.2884 |
No log | 0.7385 | 48 | 0.2931 | 0.2181 | 0.2940 |
No log | 0.7692 | 50 | 0.2938 | 0.2181 | 0.2947 |
No log | 0.8 | 52 | 0.2942 | 0.2266 | 0.2950 |
No log | 0.8308 | 54 | 0.2868 | 0.2266 | 0.2876 |
No log | 0.8615 | 56 | 0.2800 | 0.2224 | 0.2808 |
No log | 0.8923 | 58 | 0.2751 | 0.2181 | 0.2758 |
No log | 0.9231 | 60 | 0.2725 | 0.2181 | 0.2732 |
No log | 0.9538 | 62 | 0.2712 | 0.2181 | 0.2718 |
No log | 0.9846 | 64 | 0.2708 | 0.2181 | 0.2714 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1