t5-small-finetuned-doind
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0839
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- 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 |
|---|---|---|---|
| No log | 1.0 | 2 | 8.2131 |
| No log | 2.0 | 4 | 5.2570 |
| No log | 3.0 | 6 | 2.7250 |
| No log | 4.0 | 8 | 1.0910 |
| 4.9874 | 5.0 | 10 | 0.4884 |
| 4.9874 | 6.0 | 12 | 0.3084 |
| 4.9874 | 7.0 | 14 | 0.2764 |
| 4.9874 | 8.0 | 16 | 0.2767 |
| 4.9874 | 9.0 | 18 | 0.2745 |
| 1.2651 | 10.0 | 20 | 0.2684 |
| 1.2651 | 11.0 | 22 | 0.2581 |
| 1.2651 | 12.0 | 24 | 0.2461 |
| 1.2651 | 13.0 | 26 | 0.2330 |
| 1.2651 | 14.0 | 28 | 0.2229 |
| 0.7353 | 15.0 | 30 | 0.2206 |
| 0.7353 | 16.0 | 32 | 0.2220 |
| 0.7353 | 17.0 | 34 | 0.2234 |
| 0.7353 | 18.0 | 36 | 0.2205 |
| 0.7353 | 19.0 | 38 | 0.2149 |
| 0.5372 | 20.0 | 40 | 0.2098 |
| 0.5372 | 21.0 | 42 | 0.2040 |
| 0.5372 | 22.0 | 44 | 0.1989 |
| 0.5372 | 23.0 | 46 | 0.1925 |
| 0.5372 | 24.0 | 48 | 0.1849 |
| 0.4776 | 25.0 | 50 | 0.1804 |
| 0.4776 | 26.0 | 52 | 0.1733 |
| 0.4776 | 27.0 | 54 | 0.1683 |
| 0.4776 | 28.0 | 56 | 0.1646 |
| 0.4776 | 29.0 | 58 | 0.1637 |
| 0.4325 | 30.0 | 60 | 0.1645 |
| 0.4325 | 31.0 | 62 | 0.1645 |
| 0.4325 | 32.0 | 64 | 0.1614 |
| 0.4325 | 33.0 | 66 | 0.1556 |
| 0.4325 | 34.0 | 68 | 0.1467 |
| 0.3829 | 35.0 | 70 | 0.1384 |
| 0.3829 | 36.0 | 72 | 0.1322 |
| 0.3829 | 37.0 | 74 | 0.1304 |
| 0.3829 | 38.0 | 76 | 0.1316 |
| 0.3829 | 39.0 | 78 | 0.1321 |
| 0.3464 | 40.0 | 80 | 0.1338 |
| 0.3464 | 41.0 | 82 | 0.1364 |
| 0.3464 | 42.0 | 84 | 0.1378 |
| 0.3464 | 43.0 | 86 | 0.1365 |
| 0.3464 | 44.0 | 88 | 0.1341 |
| 0.325 | 45.0 | 90 | 0.1306 |
| 0.325 | 46.0 | 92 | 0.1265 |
| 0.325 | 47.0 | 94 | 0.1226 |
| 0.325 | 48.0 | 96 | 0.1207 |
| 0.325 | 49.0 | 98 | 0.1192 |
| 0.3044 | 50.0 | 100 | 0.1184 |
| 0.3044 | 51.0 | 102 | 0.1175 |
| 0.3044 | 52.0 | 104 | 0.1163 |
| 0.3044 | 53.0 | 106 | 0.1140 |
| 0.3044 | 54.0 | 108 | 0.1126 |
| 0.2875 | 55.0 | 110 | 0.1112 |
| 0.2875 | 56.0 | 112 | 0.1092 |
| 0.2875 | 57.0 | 114 | 0.1063 |
| 0.2875 | 58.0 | 116 | 0.1033 |
| 0.2875 | 59.0 | 118 | 0.1010 |
| 0.2666 | 60.0 | 120 | 0.1001 |
| 0.2666 | 61.0 | 122 | 0.0992 |
| 0.2666 | 62.0 | 124 | 0.0976 |
| 0.2666 | 63.0 | 126 | 0.0963 |
| 0.2666 | 64.0 | 128 | 0.0955 |
| 0.263 | 65.0 | 130 | 0.0955 |
| 0.263 | 66.0 | 132 | 0.0953 |
| 0.263 | 67.0 | 134 | 0.0944 |
| 0.263 | 68.0 | 136 | 0.0938 |
| 0.263 | 69.0 | 138 | 0.0933 |
| 0.2496 | 70.0 | 140 | 0.0926 |
| 0.2496 | 71.0 | 142 | 0.0929 |
| 0.2496 | 72.0 | 144 | 0.0934 |
| 0.2496 | 73.0 | 146 | 0.0936 |
| 0.2496 | 74.0 | 148 | 0.0939 |
| 0.2497 | 75.0 | 150 | 0.0941 |
| 0.2497 | 76.0 | 152 | 0.0944 |
| 0.2497 | 77.0 | 154 | 0.0937 |
| 0.2497 | 78.0 | 156 | 0.0931 |
| 0.2497 | 79.0 | 158 | 0.0929 |
| 0.2409 | 80.0 | 160 | 0.0923 |
| 0.2409 | 81.0 | 162 | 0.0915 |
| 0.2409 | 82.0 | 164 | 0.0912 |
| 0.2409 | 83.0 | 166 | 0.0900 |
| 0.2409 | 84.0 | 168 | 0.0894 |
| 0.2365 | 85.0 | 170 | 0.0887 |
| 0.2365 | 86.0 | 172 | 0.0878 |
| 0.2365 | 87.0 | 174 | 0.0870 |
| 0.2365 | 88.0 | 176 | 0.0859 |
| 0.2365 | 89.0 | 178 | 0.0851 |
| 0.2251 | 90.0 | 180 | 0.0846 |
| 0.2251 | 91.0 | 182 | 0.0841 |
| 0.2251 | 92.0 | 184 | 0.0838 |
| 0.2251 | 93.0 | 186 | 0.0837 |
| 0.2251 | 94.0 | 188 | 0.0838 |
| 0.2269 | 95.0 | 190 | 0.0836 |
| 0.2269 | 96.0 | 192 | 0.0836 |
| 0.2269 | 97.0 | 194 | 0.0836 |
| 0.2269 | 98.0 | 196 | 0.0838 |
| 0.2269 | 99.0 | 198 | 0.0838 |
| 0.2227 | 100.0 | 200 | 0.0839 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cxx11.abi
- Datasets 3.2.0
- Tokenizers 0.21.0