t5-base-squad-qag-c
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1841
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 15.4767 | 0.5714 | 1 | 18.0250 |
| 20.3032 | 1.5714 | 2 | 15.4582 |
| 18.4399 | 2.5714 | 3 | 13.1504 |
| 17.1036 | 3.5714 | 4 | 11.2818 |
| 15.6848 | 4.5714 | 5 | 9.9161 |
| 13.6358 | 5.5714 | 6 | 8.8008 |
| 11.9557 | 6.5714 | 7 | 7.8137 |
| 11.0088 | 7.5714 | 8 | 6.8813 |
| 9.0408 | 8.5714 | 9 | 6.0711 |
| 7.8859 | 9.5714 | 10 | 5.3071 |
| 6.9191 | 10.5714 | 11 | 4.8648 |
| 6.0631 | 11.5714 | 12 | 4.8851 |
| 4.7754 | 12.5714 | 13 | 4.9477 |
| 4.1728 | 13.5714 | 14 | 4.9322 |
| 3.5864 | 14.5714 | 15 | 4.5304 |
| 2.9632 | 15.5714 | 16 | 3.4513 |
| 2.7396 | 16.5714 | 17 | 2.1034 |
| 2.3785 | 17.5714 | 18 | 1.1440 |
| 2.193 | 18.5714 | 19 | 0.6816 |
| 2.1194 | 19.5714 | 20 | 0.5207 |
| 1.8983 | 20.5714 | 21 | 0.4698 |
| 1.8579 | 21.5714 | 22 | 0.4504 |
| 1.7537 | 22.5714 | 23 | 0.4418 |
| 1.6646 | 23.5714 | 24 | 0.4355 |
| 1.5684 | 24.5714 | 25 | 0.4285 |
| 1.5147 | 25.5714 | 26 | 0.4223 |
| 1.3791 | 26.5714 | 27 | 0.4167 |
| 1.2843 | 27.5714 | 28 | 0.4123 |
| 1.2089 | 28.5714 | 29 | 0.4094 |
| 1.1636 | 29.5714 | 30 | 0.4085 |
| 1.0997 | 30.5714 | 31 | 0.4075 |
| 1.0206 | 31.5714 | 32 | 0.4064 |
| 0.9747 | 32.5714 | 33 | 0.4038 |
| 0.9332 | 33.5714 | 34 | 0.4009 |
| 0.9319 | 34.5714 | 35 | 0.3970 |
| 0.8823 | 35.5714 | 36 | 0.3917 |
| 0.8401 | 36.5714 | 37 | 0.3856 |
| 0.8527 | 37.5714 | 38 | 0.3770 |
| 0.7512 | 38.5714 | 39 | 0.3655 |
| 0.797 | 39.5714 | 40 | 0.3536 |
| 0.765 | 40.5714 | 41 | 0.3407 |
| 0.7556 | 41.5714 | 42 | 0.3280 |
| 0.7198 | 42.5714 | 43 | 0.3157 |
| 0.7115 | 43.5714 | 44 | 0.3064 |
| 0.7074 | 44.5714 | 45 | 0.2981 |
| 0.639 | 45.5714 | 46 | 0.2905 |
| 0.6821 | 46.5714 | 47 | 0.2846 |
| 0.6098 | 47.5714 | 48 | 0.2789 |
| 0.6467 | 48.5714 | 49 | 0.2736 |
| 0.6593 | 49.5714 | 50 | 0.2677 |
| 0.5884 | 50.5714 | 51 | 0.2619 |
| 0.6107 | 51.5714 | 52 | 0.2562 |
| 0.6082 | 52.5714 | 53 | 0.2512 |
| 0.5592 | 53.5714 | 54 | 0.2470 |
| 0.6085 | 54.5714 | 55 | 0.2429 |
| 0.5684 | 55.5714 | 56 | 0.2396 |
| 0.5467 | 56.5714 | 57 | 0.2360 |
| 0.5505 | 57.5714 | 58 | 0.2335 |
| 0.5196 | 58.5714 | 59 | 0.2307 |
| 0.5306 | 59.5714 | 60 | 0.2280 |
| 0.5087 | 60.5714 | 61 | 0.2253 |
| 0.5083 | 61.5714 | 62 | 0.2229 |
| 0.5099 | 62.5714 | 63 | 0.2208 |
| 0.4928 | 63.5714 | 64 | 0.2186 |
| 0.4974 | 64.5714 | 65 | 0.2166 |
| 0.4766 | 65.5714 | 66 | 0.2144 |
| 0.4764 | 66.5714 | 67 | 0.2119 |
| 0.4599 | 67.5714 | 68 | 0.2091 |
| 0.496 | 68.5714 | 69 | 0.2066 |
| 0.3969 | 69.5714 | 70 | 0.2042 |
| 0.4769 | 70.5714 | 71 | 0.2018 |
| 0.4399 | 71.5714 | 72 | 0.1997 |
| 0.4417 | 72.5714 | 73 | 0.1977 |
| 0.4203 | 73.5714 | 74 | 0.1958 |
| 0.4459 | 74.5714 | 75 | 0.1942 |
| 0.3907 | 75.5714 | 76 | 0.1927 |
| 0.4548 | 76.5714 | 77 | 0.1917 |
| 0.3993 | 77.5714 | 78 | 0.1908 |
| 0.439 | 78.5714 | 79 | 0.1901 |
| 0.4249 | 79.5714 | 80 | 0.1893 |
| 0.4237 | 80.5714 | 81 | 0.1886 |
| 0.4178 | 81.5714 | 82 | 0.1881 |
| 0.4076 | 82.5714 | 83 | 0.1876 |
| 0.4216 | 83.5714 | 84 | 0.1870 |
| 0.3817 | 84.5714 | 85 | 0.1864 |
| 0.3956 | 85.5714 | 86 | 0.1861 |
| 0.4046 | 86.5714 | 87 | 0.1858 |
| 0.3896 | 87.5714 | 88 | 0.1855 |
| 0.3933 | 88.5714 | 89 | 0.1854 |
| 0.4152 | 89.5714 | 90 | 0.1852 |
| 0.3682 | 90.5714 | 91 | 0.1850 |
| 0.4242 | 91.5714 | 92 | 0.1848 |
| 0.3866 | 92.5714 | 93 | 0.1847 |
| 0.3844 | 93.5714 | 94 | 0.1846 |
| 0.3922 | 94.5714 | 95 | 0.1845 |
| 0.3621 | 95.5714 | 96 | 0.1844 |
| 0.3854 | 96.5714 | 97 | 0.1843 |
| 0.3991 | 97.5714 | 98 | 0.1842 |
| 0.3591 | 98.5714 | 99 | 0.1841 |
| 0.3664 | 99.5714 | 100 | 0.1841 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.0
- Tokenizers 0.21.0