--- tags: - simplification - generated_from_trainer metrics: - rouge model-index: - name: NASES-clara-med results: [] --- # NASES-clara-med This model is a fine-tuned version of [ELiRF/NASES](https://huggingface.co/ELiRF/NASES) on the None dataset. It achieves the following results on the evaluation set: - Loss: 3.2666 - Rouge1: 44.0787 - Rouge2: 26.1429 - Rougel: 38.4286 - Rougelsum: 38.5202 ## 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 | 2.1442 | 43.6265 | 25.4681 | 37.6224 | 37.8012 | | No log | 2.0 | 380 | 2.0839 | 44.0795 | 25.8075 | 37.9463 | 38.0445 | | 1.8145 | 3.0 | 570 | 2.1689 | 43.3863 | 25.7517 | 37.4822 | 37.7461 | | 1.8145 | 4.0 | 760 | 2.2569 | 43.9293 | 25.7951 | 37.9177 | 38.0658 | | 0.6803 | 5.0 | 950 | 2.3760 | 43.9972 | 26.1618 | 38.4315 | 38.5305 | | 0.6803 | 6.0 | 1140 | 2.4979 | 44.7986 | 27.0088 | 39.0031 | 39.1731 | | 0.6803 | 7.0 | 1330 | 2.5881 | 43.8723 | 25.9782 | 38.1705 | 38.3225 | | 0.2323 | 8.0 | 1520 | 2.6624 | 43.851 | 25.9263 | 38.2445 | 38.3659 | | 0.2323 | 9.0 | 1710 | 2.7113 | 43.5292 | 25.4795 | 37.6883 | 37.8992 | | 0.1464 | 10.0 | 1900 | 2.7451 | 44.6014 | 27.0125 | 38.9456 | 39.1796 | | 0.1464 | 11.0 | 2090 | 2.7932 | 43.9568 | 26.0931 | 38.3672 | 38.5118 | | 0.1464 | 12.0 | 2280 | 2.8651 | 43.8429 | 25.9007 | 38.0691 | 38.191 | | 0.0863 | 13.0 | 2470 | 2.8978 | 44.192 | 26.1818 | 38.4167 | 38.579 | | 0.0863 | 14.0 | 2660 | 2.9279 | 43.6745 | 25.6503 | 37.8948 | 38.0051 | | 0.0657 | 15.0 | 2850 | 2.9942 | 44.1633 | 25.7856 | 38.0295 | 38.1905 | | 0.0657 | 16.0 | 3040 | 2.9843 | 44.0347 | 25.9893 | 38.3486 | 38.5219 | | 0.0657 | 17.0 | 3230 | 3.0189 | 44.3013 | 26.1884 | 38.5594 | 38.7396 | | 0.0473 | 18.0 | 3420 | 3.0837 | 43.5877 | 25.6931 | 38.1147 | 38.2258 | | 0.0473 | 19.0 | 3610 | 3.1025 | 44.1191 | 25.9657 | 38.338 | 38.5039 | | 0.0302 | 20.0 | 3800 | 3.1395 | 44.393 | 26.3189 | 38.7891 | 38.8664 | | 0.0302 | 21.0 | 3990 | 3.1808 | 44.4783 | 26.3023 | 38.4714 | 38.6428 | | 0.0302 | 22.0 | 4180 | 3.1388 | 44.6364 | 26.7442 | 38.9591 | 39.1097 | | 0.0194 | 23.0 | 4370 | 3.1859 | 44.919 | 26.9807 | 39.2653 | 39.3442 | | 0.0194 | 24.0 | 4560 | 3.2126 | 44.4693 | 26.6534 | 38.8354 | 38.9278 | | 0.0159 | 25.0 | 4750 | 3.1988 | 44.5436 | 26.63 | 38.9413 | 39.0007 | | 0.0159 | 26.0 | 4940 | 3.2539 | 44.0378 | 26.0958 | 38.4445 | 38.5443 | | 0.0159 | 27.0 | 5130 | 3.2844 | 44.6057 | 26.476 | 38.6502 | 38.7949 | | 0.0117 | 28.0 | 5320 | 3.2755 | 44.1804 | 26.3747 | 38.6084 | 38.7027 | | 0.0117 | 29.0 | 5510 | 3.2731 | 44.0453 | 26.0298 | 38.3911 | 38.4826 | | 0.0102 | 30.0 | 5700 | 3.2666 | 44.0787 | 26.1429 | 38.4286 | 38.5202 | ### Framework versions - Transformers 4.25.1 - Pytorch 1.13.0 - Datasets 2.8.0 - Tokenizers 0.12.1