<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
t5-small-finetuned-xsum
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1681
- Rouge1: 60.7249
- Rouge2: 36.0768
- Rougel: 57.6761
- Rougelsum: 57.8618
- Gen Len: 17.9
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 2 | 2.7817 | 13.2305 | 4.2105 | 11.0476 | 11.2063 | 13.0 |
| No log | 2.0 | 4 | 2.7249 | 13.2305 | 4.2105 | 11.0476 | 11.2063 | 12.8 |
| No log | 3.0 | 6 | 2.6053 | 13.1273 | 4.2105 | 10.9075 | 11.1008 | 13.1 |
| No log | 4.0 | 8 | 2.4840 | 16.6829 | 6.2105 | 14.1984 | 14.6508 | 14.8 |
| No log | 5.0 | 10 | 2.3791 | 16.6829 | 6.2105 | 14.1984 | 14.6508 | 14.8 |
| No log | 6.0 | 12 | 2.2628 | 20.7742 | 9.5439 | 18.6218 | 18.9274 | 16.1 |
| No log | 7.0 | 14 | 2.1714 | 20.7742 | 9.5439 | 18.6218 | 18.9274 | 16.1 |
| No log | 8.0 | 16 | 2.0929 | 20.7742 | 9.5439 | 18.6218 | 18.9274 | 16.0 |
| No log | 9.0 | 18 | 2.0069 | 20.7742 | 9.5439 | 18.6218 | 18.9274 | 16.0 |
| No log | 10.0 | 20 | 1.9248 | 20.7742 | 8.4912 | 18.6218 | 18.9274 | 16.0 |
| No log | 11.0 | 22 | 1.8535 | 20.7742 | 8.4912 | 18.6218 | 18.9274 | 16.0 |
| No log | 12.0 | 24 | 1.7843 | 22.5821 | 10.8889 | 20.4396 | 20.9928 | 16.0 |
| No log | 13.0 | 26 | 1.7115 | 22.5821 | 10.8889 | 20.4396 | 20.9928 | 16.0 |
| No log | 14.0 | 28 | 1.6379 | 22.5821 | 10.8889 | 20.4396 | 20.9928 | 16.0 |
| No log | 15.0 | 30 | 1.5689 | 22.5821 | 10.8889 | 20.4396 | 20.9928 | 16.0 |
| No log | 16.0 | 32 | 1.5067 | 35.1364 | 17.6608 | 31.8254 | 31.8521 | 15.9 |
| No log | 17.0 | 34 | 1.4543 | 41.7696 | 20.2005 | 38.8803 | 39.3886 | 16.9 |
| No log | 18.0 | 36 | 1.4118 | 41.7696 | 20.2005 | 38.8803 | 39.3886 | 16.9 |
| No log | 19.0 | 38 | 1.3789 | 41.5843 | 20.2005 | 38.6571 | 39.219 | 16.9 |
| No log | 20.0 | 40 | 1.3543 | 41.5843 | 20.2005 | 38.6571 | 39.219 | 16.9 |
| No log | 21.0 | 42 | 1.3332 | 42.6832 | 20.2005 | 39.7017 | 40.5046 | 16.9 |
| No log | 22.0 | 44 | 1.3156 | 46.5429 | 22.7005 | 41.9156 | 42.7222 | 16.9 |
| No log | 23.0 | 46 | 1.2999 | 49.5478 | 25.0555 | 44.8352 | 45.4884 | 16.9 |
| No log | 24.0 | 48 | 1.2878 | 49.5478 | 25.0555 | 44.8352 | 45.4884 | 16.9 |
| No log | 25.0 | 50 | 1.2777 | 49.5478 | 25.0555 | 44.8352 | 45.4884 | 16.9 |
| No log | 26.0 | 52 | 1.2681 | 54.8046 | 28.7238 | 49.4767 | 49.699 | 17.4 |
| No log | 27.0 | 54 | 1.2596 | 54.8046 | 28.7238 | 49.4767 | 49.699 | 17.4 |
| No log | 28.0 | 56 | 1.2514 | 58.1449 | 30.5444 | 52.7235 | 53.4075 | 18.9 |
| No log | 29.0 | 58 | 1.2450 | 58.1449 | 30.5444 | 52.7235 | 53.4075 | 18.9 |
| No log | 30.0 | 60 | 1.2395 | 58.1449 | 30.5444 | 52.7235 | 53.4075 | 18.9 |
| No log | 31.0 | 62 | 1.2340 | 58.1449 | 30.5444 | 52.7235 | 53.4075 | 18.9 |
| No log | 32.0 | 64 | 1.2287 | 58.1449 | 30.5444 | 52.7235 | 53.4075 | 18.9 |
| No log | 33.0 | 66 | 1.2233 | 58.1449 | 30.5444 | 52.7235 | 53.4075 | 18.9 |
| No log | 34.0 | 68 | 1.2182 | 58.1449 | 30.5444 | 52.7235 | 53.4075 | 18.9 |
| No log | 35.0 | 70 | 1.2127 | 58.1449 | 30.5444 | 52.7235 | 53.4075 | 18.9 |
| No log | 36.0 | 72 | 1.2079 | 58.1449 | 30.5444 | 52.7235 | 53.4075 | 18.9 |
| No log | 37.0 | 74 | 1.2035 | 58.1449 | 30.5444 | 52.7235 | 53.4075 | 18.9 |
| No log | 38.0 | 76 | 1.1996 | 58.9759 | 30.5444 | 53.6606 | 54.2436 | 18.6 |
| No log | 39.0 | 78 | 1.1962 | 58.9759 | 30.5444 | 53.6606 | 54.2436 | 18.6 |
| No log | 40.0 | 80 | 1.1936 | 58.9759 | 30.5444 | 53.6606 | 54.2436 | 18.6 |
| No log | 41.0 | 82 | 1.1912 | 58.9759 | 30.5444 | 53.6606 | 54.2436 | 18.6 |
| No log | 42.0 | 84 | 1.1890 | 58.2807 | 30.5444 | 52.872 | 53.5594 | 18.5 |
| No log | 43.0 | 86 | 1.1874 | 58.2807 | 30.5444 | 52.872 | 53.5594 | 18.5 |
| No log | 44.0 | 88 | 1.1859 | 58.2807 | 30.5444 | 52.872 | 53.5594 | 18.5 |
| No log | 45.0 | 90 | 1.1844 | 58.2807 | 30.5444 | 52.872 | 53.5594 | 18.5 |
| No log | 46.0 | 92 | 1.1834 | 58.3968 | 30.5444 | 53.0602 | 53.7089 | 18.8 |
| No log | 47.0 | 94 | 1.1822 | 58.3968 | 30.5444 | 53.0602 | 53.7089 | 18.8 |
| No log | 48.0 | 96 | 1.1806 | 58.3968 | 30.5444 | 53.0602 | 53.7089 | 18.8 |
| No log | 49.0 | 98 | 1.1786 | 58.3968 | 30.5444 | 53.0602 | 53.7089 | 18.8 |
| No log | 50.0 | 100 | 1.1768 | 58.4517 | 31.303 | 54.18 | 54.6898 | 18.4 |
| No log | 51.0 | 102 | 1.1761 | 58.4517 | 31.303 | 54.18 | 54.6898 | 18.4 |
| No log | 52.0 | 104 | 1.1748 | 58.4517 | 31.303 | 54.18 | 54.6898 | 18.4 |
| No log | 53.0 | 106 | 1.1743 | 58.4517 | 33.9839 | 55.5054 | 55.8799 | 18.4 |
| No log | 54.0 | 108 | 1.1735 | 58.4517 | 33.9839 | 55.5054 | 55.8799 | 18.4 |
| No log | 55.0 | 110 | 1.1731 | 58.4517 | 33.9839 | 55.5054 | 55.8799 | 18.4 |
| No log | 56.0 | 112 | 1.1722 | 58.4517 | 33.9839 | 55.5054 | 55.8799 | 18.4 |
| No log | 57.0 | 114 | 1.1714 | 58.4517 | 33.9839 | 55.5054 | 55.8799 | 18.4 |
| No log | 58.0 | 116 | 1.1710 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 59.0 | 118 | 1.1702 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 60.0 | 120 | 1.1688 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 61.0 | 122 | 1.1682 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 62.0 | 124 | 1.1671 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 63.0 | 126 | 1.1669 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 64.0 | 128 | 1.1669 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 65.0 | 130 | 1.1668 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 66.0 | 132 | 1.1663 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 67.0 | 134 | 1.1665 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 68.0 | 136 | 1.1662 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 69.0 | 138 | 1.1663 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 70.0 | 140 | 1.1665 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 71.0 | 142 | 1.1664 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 72.0 | 144 | 1.1664 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 73.0 | 146 | 1.1662 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 74.0 | 148 | 1.1665 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 75.0 | 150 | 1.1662 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 76.0 | 152 | 1.1669 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 77.0 | 154 | 1.1668 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 78.0 | 156 | 1.1671 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 79.0 | 158 | 1.1674 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 80.0 | 160 | 1.1670 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 81.0 | 162 | 1.1671 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 82.0 | 164 | 1.1672 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 83.0 | 166 | 1.1675 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 84.0 | 168 | 1.1677 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 85.0 | 170 | 1.1677 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 86.0 | 172 | 1.1673 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 87.0 | 174 | 1.1673 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 88.0 | 176 | 1.1673 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 89.0 | 178 | 1.1673 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 90.0 | 180 | 1.1675 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 91.0 | 182 | 1.1675 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 92.0 | 184 | 1.1680 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 93.0 | 186 | 1.1680 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 94.0 | 188 | 1.1679 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 95.0 | 190 | 1.1679 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 96.0 | 192 | 1.1682 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 97.0 | 194 | 1.1681 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 98.0 | 196 | 1.1683 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 99.0 | 198 | 1.1683 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
| No log | 100.0 | 200 | 1.1681 | 60.7249 | 36.0768 | 57.6761 | 57.8618 | 17.9 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Tokenizers 0.13.2
