t5-small-finetuned-xsum

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

• eval_loss: 2.3668
• eval_rouge1: 30.1181
• eval_rouge2: 8.9201
• eval_rougeL: 23.7442
• eval_rougeLsum: 23.7362
• eval_gen_len: 19.6939
• eval_runtime: 710.2112
• eval_samples_per_second: 15.956
• eval_steps_per_second: 0.998
• epoch: 3.0
• step: 38259

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 4
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.3.1
• Tokenizers 0.21.0