arabert_cross_relevance_task6_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: 0.1940
- Qwk: 0.0307
- Mse: 0.1940
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 | 0.125 | 2 | 0.7363 | -0.0058 | 0.7363 |
No log | 0.25 | 4 | 0.1881 | 0.0012 | 0.1881 |
No log | 0.375 | 6 | 0.1606 | 0.0267 | 0.1606 |
No log | 0.5 | 8 | 0.4512 | 0.0043 | 0.4512 |
No log | 0.625 | 10 | 0.4525 | 0.0060 | 0.4525 |
No log | 0.75 | 12 | 0.2338 | 0.0094 | 0.2338 |
No log | 0.875 | 14 | 0.1664 | 0.0094 | 0.1664 |
No log | 1.0 | 16 | 0.1743 | 0.0185 | 0.1743 |
No log | 1.125 | 18 | 0.2334 | 0.0273 | 0.2334 |
No log | 1.25 | 20 | 0.2489 | 0.0319 | 0.2489 |
No log | 1.375 | 22 | 0.1857 | 0.0335 | 0.1857 |
No log | 1.5 | 24 | 0.1610 | 0.0301 | 0.1610 |
No log | 1.625 | 26 | 0.1692 | 0.0355 | 0.1692 |
No log | 1.75 | 28 | 0.1989 | 0.0300 | 0.1989 |
No log | 1.875 | 30 | 0.2050 | 0.0300 | 0.2050 |
No log | 2.0 | 32 | 0.1869 | 0.0319 | 0.1869 |
No log | 2.125 | 34 | 0.2181 | 0.0319 | 0.2181 |
No log | 2.25 | 36 | 0.2092 | 0.0319 | 0.2092 |
No log | 2.375 | 38 | 0.1582 | 0.0355 | 0.1582 |
No log | 2.5 | 40 | 0.1522 | 0.0425 | 0.1522 |
No log | 2.625 | 42 | 0.1547 | 0.0342 | 0.1547 |
No log | 2.75 | 44 | 0.1614 | 0.0273 | 0.1614 |
No log | 2.875 | 46 | 0.1863 | 0.0273 | 0.1863 |
No log | 3.0 | 48 | 0.2170 | 0.0273 | 0.2170 |
No log | 3.125 | 50 | 0.2013 | 0.0254 | 0.2013 |
No log | 3.25 | 52 | 0.1678 | 0.0254 | 0.1678 |
No log | 3.375 | 54 | 0.1689 | 0.0254 | 0.1689 |
No log | 3.5 | 56 | 0.1680 | 0.0254 | 0.1680 |
No log | 3.625 | 58 | 0.1692 | 0.0273 | 0.1692 |
No log | 3.75 | 60 | 0.1633 | 0.0307 | 0.1633 |
No log | 3.875 | 62 | 0.1712 | 0.0307 | 0.1712 |
No log | 4.0 | 64 | 0.1638 | 0.0324 | 0.1638 |
No log | 4.125 | 66 | 0.1666 | 0.0410 | 0.1666 |
No log | 4.25 | 68 | 0.1931 | 0.0316 | 0.1931 |
No log | 4.375 | 70 | 0.1935 | 0.0332 | 0.1935 |
No log | 4.5 | 72 | 0.1622 | 0.0407 | 0.1622 |
No log | 4.625 | 74 | 0.1528 | 0.0502 | 0.1528 |
No log | 4.75 | 76 | 0.1546 | 0.0427 | 0.1546 |
No log | 4.875 | 78 | 0.1610 | 0.0373 | 0.1610 |
No log | 5.0 | 80 | 0.1796 | 0.0324 | 0.1796 |
No log | 5.125 | 82 | 0.1905 | 0.0287 | 0.1905 |
No log | 5.25 | 84 | 0.1795 | 0.0355 | 0.1795 |
No log | 5.375 | 86 | 0.1867 | 0.0287 | 0.1867 |
No log | 5.5 | 88 | 0.2057 | 0.0372 | 0.2057 |
No log | 5.625 | 90 | 0.2005 | 0.0352 | 0.2005 |
No log | 5.75 | 92 | 0.1798 | 0.0304 | 0.1798 |
No log | 5.875 | 94 | 0.1808 | 0.0287 | 0.1808 |
No log | 6.0 | 96 | 0.1804 | 0.0307 | 0.1804 |
No log | 6.125 | 98 | 0.1740 | 0.0307 | 0.1740 |
No log | 6.25 | 100 | 0.1812 | 0.0307 | 0.1812 |
No log | 6.375 | 102 | 0.1920 | 0.0307 | 0.1920 |
No log | 6.5 | 104 | 0.1897 | 0.0287 | 0.1897 |
No log | 6.625 | 106 | 0.1990 | 0.0287 | 0.1990 |
No log | 6.75 | 108 | 0.2005 | 0.0287 | 0.2005 |
No log | 6.875 | 110 | 0.2110 | 0.0251 | 0.2110 |
No log | 7.0 | 112 | 0.2243 | 0.0251 | 0.2243 |
No log | 7.125 | 114 | 0.2176 | 0.0270 | 0.2176 |
No log | 7.25 | 116 | 0.2051 | 0.0307 | 0.2051 |
No log | 7.375 | 118 | 0.1875 | 0.0359 | 0.1875 |
No log | 7.5 | 120 | 0.1841 | 0.0359 | 0.1841 |
No log | 7.625 | 122 | 0.1903 | 0.0307 | 0.1903 |
No log | 7.75 | 124 | 0.2160 | 0.0290 | 0.2160 |
No log | 7.875 | 126 | 0.2336 | 0.0290 | 0.2336 |
No log | 8.0 | 128 | 0.2472 | 0.0290 | 0.2472 |
No log | 8.125 | 130 | 0.2417 | 0.0290 | 0.2417 |
No log | 8.25 | 132 | 0.2168 | 0.0290 | 0.2168 |
No log | 8.375 | 134 | 0.1854 | 0.0342 | 0.1854 |
No log | 8.5 | 136 | 0.1717 | 0.0377 | 0.1717 |
No log | 8.625 | 138 | 0.1718 | 0.0377 | 0.1718 |
No log | 8.75 | 140 | 0.1803 | 0.0342 | 0.1803 |
No log | 8.875 | 142 | 0.1951 | 0.0307 | 0.1951 |
No log | 9.0 | 144 | 0.2030 | 0.0307 | 0.2030 |
No log | 9.125 | 146 | 0.2104 | 0.0270 | 0.2104 |
No log | 9.25 | 148 | 0.2101 | 0.0270 | 0.2101 |
No log | 9.375 | 150 | 0.2065 | 0.0287 | 0.2065 |
No log | 9.5 | 152 | 0.2028 | 0.0307 | 0.2028 |
No log | 9.625 | 154 | 0.1984 | 0.0307 | 0.1984 |
No log | 9.75 | 156 | 0.1954 | 0.0307 | 0.1954 |
No log | 9.875 | 158 | 0.1942 | 0.0307 | 0.1942 |
No log | 10.0 | 160 | 0.1940 | 0.0307 | 0.1940 |
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_task6_fold1
Base model
aubmindlab/bert-base-arabertv02