--- license: apache-2.0 tags: - generated_from_trainer metrics: - rouge model-index: - name: t5-small-SA results: [] pipeline_tag: summarization --- # t5-small-finetuned-xsum This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.2847 - Rouge1: 0.1422 - Rouge2: 0.0403 - Rougel: 0.1337 - Rougelsum: 0.1342 - Gen Len: 8.4248 ## 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: 1 - eval_batch_size: 1 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 12 ### Training results | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| | 2.7269 | 1.0 | 527 | 1.5826 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | | 1.5708 | 2.0 | 1054 | 1.4112 | 0.035 | 0.0105 | 0.0357 | 0.0349 | 1.7168 | | 1.4796 | 3.0 | 1581 | 1.3644 | 0.1012 | 0.0167 | 0.0948 | 0.0942 | 8.2212 | | 1.3451 | 4.0 | 2108 | 1.3399 | 0.126 | 0.0205 | 0.1183 | 0.1182 | 9.0088 | | 1.3491 | 5.0 | 2635 | 1.3247 | 0.1307 | 0.0266 | 0.1232 | 0.1236 | 8.0088 | | 1.3109 | 6.0 | 3162 | 1.3112 | 0.1428 | 0.0325 | 0.1332 | 0.1334 | 7.6549 | | 1.2462 | 7.0 | 3689 | 1.3046 | 0.1435 | 0.0319 | 0.1342 | 0.1349 | 7.885 | | 1.2353 | 8.0 | 4216 | 1.2937 | 0.1404 | 0.0313 | 0.1297 | 0.1303 | 9.1239 | | 1.2838 | 9.0 | 4743 | 1.2903 | 0.1434 | 0.0372 | 0.1338 | 0.1344 | 8.1062 | | 1.2317 | 10.0 | 5270 | 1.2870 | 0.1459 | 0.0421 | 0.1388 | 0.1389 | 8.4248 | | 1.2598 | 11.0 | 5797 | 1.2857 | 0.1421 | 0.0403 | 0.1346 | 0.1351 | 8.2389 | | 1.1579 | 12.0 | 6324 | 1.2847 | 0.1422 | 0.0403 | 0.1337 | 0.1342 | 8.4248 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1+cu116 - Datasets 2.10.0 - Tokenizers 0.13.2