GilbertKrantz/Scientific-Paper-Summarization

1---2library_name: transformers3license: apache-2.04base_model: google-t5/t5-small5tags:6- generated_from_trainer7metrics:8- rouge9model-index:10- name: Scientific-Paper-Summarization11  results: []12---13 14<!-- This model card has been generated automatically according to the information the Trainer had access to. You15should probably proofread and complete it, then remove this comment. -->16 17# Scientific-Paper-Summarization18 19This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset.20It achieves the following results on the evaluation set:21- Loss: 3.793622- Rouge1: 0.149923- Rouge2: 0.027624- Rougel: 0.115925- Rougelsum: 0.115526- Gen Len: 18.96527 28## Model description29 30More information needed31 32## Intended uses & limitations33 34More information needed35 36## Training and evaluation data37 38More information needed39 40## Training procedure41 42### Training hyperparameters43 44The following hyperparameters were used during training:45- learning_rate: 2e-0546- train_batch_size: 3247- eval_batch_size: 3248- seed: 4249- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0850- lr_scheduler_type: linear51- num_epochs: 452- mixed_precision_training: Native AMP53 54### Training results55 56| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |57|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|58| No log        | 1.0   | 63   | 3.9012          | 0.1389 | 0.0232 | 0.1061 | 0.1058    | 19.0    |59| No log        | 2.0   | 126  | 3.8223          | 0.1479 | 0.0257 | 0.1149 | 0.1146    | 18.965  |60| No log        | 3.0   | 189  | 3.7987          | 0.1492 | 0.0274 | 0.1159 | 0.1155    | 18.965  |61| No log        | 4.0   | 252  | 3.7936          | 0.1499 | 0.0276 | 0.1159 | 0.1155    | 18.965  |62 63 64### Framework versions65 66- Transformers 4.45.167- Pytorch 2.4.068- Datasets 3.0.169- Tokenizers 0.20.070