t5_finetuned_paraphrase

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

• Loss: 0.8386
• Rouge1: 67.2398
• Rouge2: 47.8969
• Rougel: 63.7914
• Rougelsum: 63.7998
• Gen Len: 18.039

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.9806	1.0	6250	0.8724	66.8051	47.0687	63.2656	63.2786	18.078
0.957	2.0	12500	0.8446	67.1024	47.6199	63.5856	63.6021	18.0458
0.9293	3.0	18750	0.8386	67.2398	47.8969	63.7914	63.7998	18.039

Framework versions

• Transformers 4.27.3
• Pytorch 1.7.1+cu101
• Datasets 2.13.2
• Tokenizers 0.13.2