t5_finetuned_gentextSIM

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

• Loss: 0.7167
• Rouge1: 13.6594
• Rouge2: 6.8495
• Rougel: 11.9371
• Rougelsum: 11.9632
• Gen Len: 13.3918

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: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	25	1.1849	29.1345	15.5888	25.7823	25.7828	11.9897
No log	2.0	50	0.7564	12.1041	6.3228	9.8401	10.0182	13.5155
No log	3.0	75	0.7167	13.6594	6.8495	11.9371	11.9632	13.3918

Framework versions

• Transformers 4.26.0
• Pytorch 1.13.1+cu116
• Datasets 2.9.0
• Tokenizers 0.13.2