--- license: apache-2.0 base_model: t5-small tags: - generated_from_trainer metrics: - rouge model-index: - name: news_model_6 results: [] --- # news_model_6 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: 2.6530 - Rouge1: 0.1504 - Rouge2: 0.0493 - Rougel: 0.1154 - Rougelsum: 0.1153 - Gen Len: 19.0 ## 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: 6 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| | 2.9574 | 1.0 | 2249 | 2.7282 | 0.1465 | 0.047 | 0.1125 | 0.1125 | 18.9979 | | 2.9013 | 2.0 | 4498 | 2.6873 | 0.1484 | 0.0481 | 0.1138 | 0.1138 | 18.9982 | | 2.8676 | 3.0 | 6747 | 2.6691 | 0.1492 | 0.0488 | 0.1144 | 0.1144 | 18.9982 | | 2.858 | 4.0 | 8996 | 2.6609 | 0.1499 | 0.0491 | 0.115 | 0.115 | 19.0 | | 2.8434 | 5.0 | 11245 | 2.6553 | 0.1501 | 0.0491 | 0.1151 | 0.1151 | 19.0 | | 2.8378 | 6.0 | 13494 | 2.6530 | 0.1504 | 0.0493 | 0.1154 | 0.1153 | 19.0 | ### Framework versions - Transformers 4.41.0.dev0 - Pytorch 2.2.1+cu121 - Datasets 2.19.1 - Tokenizers 0.19.1