metadata
license: cc-by-nc-sa-4.0
tags:
- simplification
- generated_from_trainer
metrics:
- rouge
model-index:
- name: mt5-simplification-spanish-clara-med
results: []
mt5-simplification-spanish-clara-med
This model is a fine-tuned version of oskrmiguel/mt5-simplification-spanish on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9829
- Rouge1: 33.5827
- Rouge2: 19.3568
- Rougel: 30.9427
- Rougelsum: 30.922
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: 5.6e-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: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 190 | 2.6879 | 31.8425 | 17.5967 | 29.0762 | 29.1474 |
| No log | 2.0 | 380 | 2.4770 | 32.6054 | 18.6606 | 30.0148 | 30.0565 |
| 3.3044 | 3.0 | 570 | 2.3618 | 32.873 | 18.9033 | 30.2114 | 30.2842 |
| 3.3044 | 4.0 | 760 | 2.2842 | 33.0173 | 18.9165 | 30.2803 | 30.3708 |
| 2.7475 | 5.0 | 950 | 2.2176 | 32.769 | 18.6209 | 30.1211 | 30.1858 |
| 2.7475 | 6.0 | 1140 | 2.1974 | 32.8461 | 18.7023 | 30.1932 | 30.2432 |
| 2.7475 | 7.0 | 1330 | 2.1625 | 32.8013 | 18.7017 | 30.1099 | 30.1752 |
| 2.5234 | 8.0 | 1520 | 2.1315 | 33.0317 | 18.8095 | 30.3504 | 30.394 |
| 2.5234 | 9.0 | 1710 | 2.1086 | 33.2546 | 18.9599 | 30.5465 | 30.5782 |
| 2.3775 | 10.0 | 1900 | 2.0830 | 33.2349 | 18.8346 | 30.4815 | 30.524 |
| 2.3775 | 11.0 | 2090 | 2.0655 | 33.1573 | 18.9358 | 30.4626 | 30.4931 |
| 2.3775 | 12.0 | 2280 | 2.0599 | 33.2281 | 19.0066 | 30.5592 | 30.5896 |
| 2.2837 | 13.0 | 2470 | 2.0464 | 33.2839 | 19.1136 | 30.7237 | 30.7471 |
| 2.2837 | 14.0 | 2660 | 2.0343 | 33.4208 | 19.0347 | 30.6897 | 30.7073 |
| 2.2132 | 15.0 | 2850 | 2.0351 | 33.4278 | 19.0579 | 30.7056 | 30.7218 |
| 2.2132 | 16.0 | 3040 | 2.0276 | 33.541 | 19.1772 | 30.8324 | 30.8551 |
| 2.2132 | 17.0 | 3230 | 2.0122 | 33.455 | 19.1121 | 30.79 | 30.8033 |
| 2.1561 | 18.0 | 3420 | 2.0124 | 33.3712 | 19.1315 | 30.7892 | 30.8023 |
| 2.1561 | 19.0 | 3610 | 2.0098 | 33.5589 | 19.2569 | 30.86 | 30.8629 |
| 2.1136 | 20.0 | 3800 | 2.0018 | 33.4333 | 19.124 | 30.7894 | 30.8035 |
| 2.1136 | 21.0 | 3990 | 1.9954 | 33.5845 | 19.2881 | 30.9155 | 30.9167 |
| 2.1136 | 22.0 | 4180 | 1.9947 | 33.6133 | 19.3605 | 30.9736 | 30.9831 |
| 2.0851 | 23.0 | 4370 | 1.9924 | 33.6015 | 19.3226 | 30.9673 | 30.9695 |
| 2.0851 | 24.0 | 4560 | 1.9861 | 33.7693 | 19.3866 | 31.0921 | 31.0837 |
| 2.0569 | 25.0 | 4750 | 1.9851 | 33.7423 | 19.431 | 31.0085 | 31.0119 |
| 2.0569 | 26.0 | 4940 | 1.9865 | 33.6365 | 19.3494 | 30.9259 | 30.9263 |
| 2.0569 | 27.0 | 5130 | 1.9864 | 33.6976 | 19.3426 | 30.9851 | 30.9756 |
| 2.0421 | 28.0 | 5320 | 1.9843 | 33.6246 | 19.3228 | 30.9379 | 30.9345 |
| 2.0421 | 29.0 | 5510 | 1.9835 | 33.5947 | 19.3477 | 30.912 | 30.9164 |
| 2.0319 | 30.0 | 5700 | 1.9829 | 33.5827 | 19.3568 | 30.9427 | 30.922 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0
- Datasets 2.8.0
- Tokenizers 0.12.1