arabert_cross_relevance_task7_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: 0.2739
- Qwk: 0.1498
- Mse: 0.2741
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: 64
- eval_batch_size: 64
- 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 | 0.1333 | 2 | 0.6915 | 0.0152 | 0.6916 |
No log | 0.2667 | 4 | 0.3007 | 0.0046 | 0.3008 |
No log | 0.4 | 6 | 0.2606 | 0.0103 | 0.2607 |
No log | 0.5333 | 8 | 0.2472 | -0.0037 | 0.2473 |
No log | 0.6667 | 10 | 0.2753 | 0.0398 | 0.2754 |
No log | 0.8 | 12 | 0.3087 | 0.0531 | 0.3087 |
No log | 0.9333 | 14 | 0.2871 | 0.0584 | 0.2872 |
No log | 1.0667 | 16 | 0.2862 | 0.0547 | 0.2864 |
No log | 1.2 | 18 | 0.2778 | 0.0673 | 0.2780 |
No log | 1.3333 | 20 | 0.2869 | 0.1208 | 0.2871 |
No log | 1.4667 | 22 | 0.2743 | 0.0873 | 0.2746 |
No log | 1.6 | 24 | 0.2612 | 0.0650 | 0.2614 |
No log | 1.7333 | 26 | 0.2604 | 0.0715 | 0.2606 |
No log | 1.8667 | 28 | 0.2749 | 0.0788 | 0.2752 |
No log | 2.0 | 30 | 0.3010 | 0.1611 | 0.3013 |
No log | 2.1333 | 32 | 0.2981 | 0.1189 | 0.2984 |
No log | 2.2667 | 34 | 0.2813 | 0.1170 | 0.2815 |
No log | 2.4 | 36 | 0.2636 | 0.0868 | 0.2638 |
No log | 2.5333 | 38 | 0.2577 | 0.0986 | 0.2579 |
No log | 2.6667 | 40 | 0.2578 | 0.0676 | 0.2580 |
No log | 2.8 | 42 | 0.2611 | 0.0743 | 0.2612 |
No log | 2.9333 | 44 | 0.2605 | 0.0949 | 0.2607 |
No log | 3.0667 | 46 | 0.2576 | 0.0837 | 0.2578 |
No log | 3.2 | 48 | 0.2526 | 0.0883 | 0.2528 |
No log | 3.3333 | 50 | 0.2493 | 0.0796 | 0.2494 |
No log | 3.4667 | 52 | 0.2494 | 0.0762 | 0.2495 |
No log | 3.6 | 54 | 0.2509 | 0.0762 | 0.2511 |
No log | 3.7333 | 56 | 0.2599 | 0.1102 | 0.2601 |
No log | 3.8667 | 58 | 0.2617 | 0.1201 | 0.2619 |
No log | 4.0 | 60 | 0.2569 | 0.1201 | 0.2571 |
No log | 4.1333 | 62 | 0.2518 | 0.1245 | 0.2520 |
No log | 4.2667 | 64 | 0.2475 | 0.1331 | 0.2476 |
No log | 4.4 | 66 | 0.2458 | 0.1627 | 0.2459 |
No log | 4.5333 | 68 | 0.2466 | 0.1664 | 0.2467 |
No log | 4.6667 | 70 | 0.2489 | 0.1701 | 0.2490 |
No log | 4.8 | 72 | 0.2533 | 0.1802 | 0.2534 |
No log | 4.9333 | 74 | 0.2587 | 0.1795 | 0.2588 |
No log | 5.0667 | 76 | 0.2679 | 0.1591 | 0.2681 |
No log | 5.2 | 78 | 0.2741 | 0.1432 | 0.2743 |
No log | 5.3333 | 80 | 0.2711 | 0.1317 | 0.2714 |
No log | 5.4667 | 82 | 0.2652 | 0.1368 | 0.2654 |
No log | 5.6 | 84 | 0.2681 | 0.1474 | 0.2683 |
No log | 5.7333 | 86 | 0.2684 | 0.1626 | 0.2686 |
No log | 5.8667 | 88 | 0.2645 | 0.1797 | 0.2647 |
No log | 6.0 | 90 | 0.2589 | 0.1859 | 0.2590 |
No log | 6.1333 | 92 | 0.2593 | 0.1154 | 0.2594 |
No log | 6.2667 | 94 | 0.2625 | 0.1365 | 0.2626 |
No log | 6.4 | 96 | 0.2688 | 0.1779 | 0.2690 |
No log | 6.5333 | 98 | 0.2740 | 0.2609 | 0.2742 |
No log | 6.6667 | 100 | 0.2759 | 0.2576 | 0.2760 |
No log | 6.8 | 102 | 0.2726 | 0.2039 | 0.2728 |
No log | 6.9333 | 104 | 0.2690 | 0.1750 | 0.2692 |
No log | 7.0667 | 106 | 0.2676 | 0.1430 | 0.2678 |
No log | 7.2 | 108 | 0.2660 | 0.1277 | 0.2662 |
No log | 7.3333 | 110 | 0.2660 | 0.1610 | 0.2661 |
No log | 7.4667 | 112 | 0.2678 | 0.1840 | 0.2679 |
No log | 7.6 | 114 | 0.2687 | 0.1801 | 0.2688 |
No log | 7.7333 | 116 | 0.2685 | 0.1647 | 0.2686 |
No log | 7.8667 | 118 | 0.2673 | 0.1609 | 0.2675 |
No log | 8.0 | 120 | 0.2674 | 0.1352 | 0.2676 |
No log | 8.1333 | 122 | 0.2685 | 0.1172 | 0.2687 |
No log | 8.2667 | 124 | 0.2696 | 0.1172 | 0.2697 |
No log | 8.4 | 126 | 0.2705 | 0.1304 | 0.2707 |
No log | 8.5333 | 128 | 0.2717 | 0.1481 | 0.2719 |
No log | 8.6667 | 130 | 0.2734 | 0.1645 | 0.2736 |
No log | 8.8 | 132 | 0.2747 | 0.1828 | 0.2748 |
No log | 8.9333 | 134 | 0.2744 | 0.1903 | 0.2746 |
No log | 9.0667 | 136 | 0.2741 | 0.1738 | 0.2742 |
No log | 9.2 | 138 | 0.2734 | 0.1664 | 0.2736 |
No log | 9.3333 | 140 | 0.2736 | 0.1700 | 0.2738 |
No log | 9.4667 | 142 | 0.2738 | 0.1700 | 0.2739 |
No log | 9.6 | 144 | 0.2739 | 0.1572 | 0.2741 |
No log | 9.7333 | 146 | 0.2738 | 0.1498 | 0.2740 |
No log | 9.8667 | 148 | 0.2739 | 0.1498 | 0.2741 |
No log | 10.0 | 150 | 0.2739 | 0.1498 | 0.2741 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 1
Model tree for salbatarni/arabert_cross_relevance_task7_fold0
Base model
aubmindlab/bert-base-arabertv02