arabert_cross_relevance_task4_fold5
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: 0.1959
- Qwk: 0.3973
- Mse: 0.1959
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 | 0.1176 | 2 | 0.2829 | 0.2281 | 0.2825 |
No log | 0.2353 | 4 | 0.3384 | 0.3607 | 0.3377 |
No log | 0.3529 | 6 | 0.2361 | 0.3469 | 0.2356 |
No log | 0.4706 | 8 | 0.2565 | 0.3434 | 0.2564 |
No log | 0.5882 | 10 | 0.2109 | 0.3531 | 0.2109 |
No log | 0.7059 | 12 | 0.1920 | 0.3266 | 0.1917 |
No log | 0.8235 | 14 | 0.1946 | 0.3334 | 0.1943 |
No log | 0.9412 | 16 | 0.1757 | 0.4574 | 0.1756 |
No log | 1.0588 | 18 | 0.1726 | 0.5071 | 0.1727 |
No log | 1.1765 | 20 | 0.1653 | 0.4079 | 0.1653 |
No log | 1.2941 | 22 | 0.1708 | 0.3931 | 0.1707 |
No log | 1.4118 | 24 | 0.1783 | 0.3512 | 0.1781 |
No log | 1.5294 | 26 | 0.1810 | 0.3512 | 0.1809 |
No log | 1.6471 | 28 | 0.1836 | 0.3467 | 0.1835 |
No log | 1.7647 | 30 | 0.1863 | 0.3686 | 0.1862 |
No log | 1.8824 | 32 | 0.1946 | 0.3724 | 0.1944 |
No log | 2.0 | 34 | 0.1957 | 0.3890 | 0.1956 |
No log | 2.1176 | 36 | 0.1833 | 0.3976 | 0.1833 |
No log | 2.2353 | 38 | 0.1883 | 0.3683 | 0.1884 |
No log | 2.3529 | 40 | 0.1889 | 0.3608 | 0.1889 |
No log | 2.4706 | 42 | 0.1805 | 0.3872 | 0.1805 |
No log | 2.5882 | 44 | 0.1951 | 0.4399 | 0.1949 |
No log | 2.7059 | 46 | 0.2076 | 0.4132 | 0.2074 |
No log | 2.8235 | 48 | 0.1906 | 0.4472 | 0.1904 |
No log | 2.9412 | 50 | 0.1805 | 0.4286 | 0.1806 |
No log | 3.0588 | 52 | 0.1962 | 0.3808 | 0.1964 |
No log | 3.1765 | 54 | 0.1906 | 0.3696 | 0.1907 |
No log | 3.2941 | 56 | 0.1903 | 0.3562 | 0.1903 |
No log | 3.4118 | 58 | 0.1893 | 0.3519 | 0.1893 |
No log | 3.5294 | 60 | 0.1793 | 0.3754 | 0.1793 |
No log | 3.6471 | 62 | 0.1725 | 0.3761 | 0.1726 |
No log | 3.7647 | 64 | 0.1732 | 0.3867 | 0.1732 |
No log | 3.8824 | 66 | 0.1756 | 0.3728 | 0.1757 |
No log | 4.0 | 68 | 0.1756 | 0.3768 | 0.1756 |
No log | 4.1176 | 70 | 0.1760 | 0.3788 | 0.1760 |
No log | 4.2353 | 72 | 0.1762 | 0.3724 | 0.1762 |
No log | 4.3529 | 74 | 0.1718 | 0.3623 | 0.1717 |
No log | 4.4706 | 76 | 0.1679 | 0.3667 | 0.1679 |
No log | 4.5882 | 78 | 0.1666 | 0.3816 | 0.1667 |
No log | 4.7059 | 80 | 0.1776 | 0.3966 | 0.1778 |
No log | 4.8235 | 82 | 0.1888 | 0.3969 | 0.1890 |
No log | 4.9412 | 84 | 0.1893 | 0.3969 | 0.1895 |
No log | 5.0588 | 86 | 0.1782 | 0.3768 | 0.1783 |
No log | 5.1765 | 88 | 0.1774 | 0.3683 | 0.1774 |
No log | 5.2941 | 90 | 0.1798 | 0.3744 | 0.1797 |
No log | 5.4118 | 92 | 0.1823 | 0.3684 | 0.1822 |
No log | 5.5294 | 94 | 0.1828 | 0.3752 | 0.1827 |
No log | 5.6471 | 96 | 0.1843 | 0.3774 | 0.1843 |
No log | 5.7647 | 98 | 0.1901 | 0.3698 | 0.1901 |
No log | 5.8824 | 100 | 0.1920 | 0.3735 | 0.1921 |
No log | 6.0 | 102 | 0.1844 | 0.3821 | 0.1845 |
No log | 6.1176 | 104 | 0.1765 | 0.4146 | 0.1766 |
No log | 6.2353 | 106 | 0.1765 | 0.4100 | 0.1765 |
No log | 6.3529 | 108 | 0.1783 | 0.4054 | 0.1783 |
No log | 6.4706 | 110 | 0.1769 | 0.3909 | 0.1769 |
No log | 6.5882 | 112 | 0.1761 | 0.3945 | 0.1762 |
No log | 6.7059 | 114 | 0.1788 | 0.3862 | 0.1789 |
No log | 6.8235 | 116 | 0.1789 | 0.3906 | 0.1789 |
No log | 6.9412 | 118 | 0.1803 | 0.4054 | 0.1804 |
No log | 7.0588 | 120 | 0.1833 | 0.3980 | 0.1834 |
No log | 7.1765 | 122 | 0.1902 | 0.4017 | 0.1903 |
No log | 7.2941 | 124 | 0.1979 | 0.4022 | 0.1981 |
No log | 7.4118 | 126 | 0.1996 | 0.3880 | 0.1998 |
No log | 7.5294 | 128 | 0.1940 | 0.3978 | 0.1941 |
No log | 7.6471 | 130 | 0.1917 | 0.4072 | 0.1918 |
No log | 7.7647 | 132 | 0.1940 | 0.3980 | 0.1940 |
No log | 7.8824 | 134 | 0.2019 | 0.3978 | 0.2020 |
No log | 8.0 | 136 | 0.2093 | 0.4067 | 0.2094 |
No log | 8.1176 | 138 | 0.2156 | 0.3976 | 0.2157 |
No log | 8.2353 | 140 | 0.2077 | 0.4067 | 0.2078 |
No log | 8.3529 | 142 | 0.1994 | 0.4031 | 0.1995 |
No log | 8.4706 | 144 | 0.1959 | 0.4118 | 0.1960 |
No log | 8.5882 | 146 | 0.1952 | 0.4068 | 0.1953 |
No log | 8.7059 | 148 | 0.1954 | 0.4021 | 0.1955 |
No log | 8.8235 | 150 | 0.1949 | 0.3954 | 0.1950 |
No log | 8.9412 | 152 | 0.1945 | 0.3906 | 0.1945 |
No log | 9.0588 | 154 | 0.1941 | 0.3852 | 0.1941 |
No log | 9.1765 | 156 | 0.1942 | 0.3755 | 0.1942 |
No log | 9.2941 | 158 | 0.1931 | 0.3852 | 0.1931 |
No log | 9.4118 | 160 | 0.1927 | 0.3852 | 0.1927 |
No log | 9.5294 | 162 | 0.1933 | 0.3941 | 0.1933 |
No log | 9.6471 | 164 | 0.1939 | 0.3941 | 0.1940 |
No log | 9.7647 | 166 | 0.1946 | 0.3957 | 0.1947 |
No log | 9.8824 | 168 | 0.1954 | 0.3973 | 0.1955 |
No log | 10.0 | 170 | 0.1959 | 0.3973 | 0.1959 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 0
Model tree for salbatarni/arabert_cross_relevance_task4_fold5
Base model
aubmindlab/bert-base-arabertv02