t5-base-finetuned-scitldr

This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.0232
• Rouge1: 35.2134
• Rouge2: 16.8919
• Rougel: 30.8442
• Rougelsum: 30.9316
• Gen Len: 18.7981

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: 3e-06
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.0533	1.0	996	2.0285	34.9774	16.6163	30.6177	30.7038	18.7981
2.0994	2.0	1992	2.0232	35.2134	16.8919	30.8442	30.9316	18.7981

Framework versions

• Transformers 4.16.2
• Pytorch 1.10.0+cu111
• Datasets 1.18.3
• Tokenizers 0.11.0