my_awesome_arxiv_model

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

• Loss: 2.5995
• Rouge1: 0.1783
• Rouge2: 0.0671
• Rougel: 0.1433
• Rougelsum: 0.1433
• 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: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.8985	1.0	1269	2.6663	0.1735	0.0651	0.1393	0.1393	19.0
2.7954	2.0	2538	2.6231	0.1759	0.0675	0.1417	0.1417	19.0
2.7799	3.0	3807	2.6054	0.1779	0.0674	0.1434	0.1435	19.0
2.7715	4.0	5076	2.5995	0.1783	0.0671	0.1433	0.1433	19.0

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0