t5-small-samsum-ft

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

• eval_loss: 0.5409
• eval_rouge1: 0.4488
• eval_rouge2: 0.2254
• eval_rougeL: 0.3848
• eval_rougeLsum: 0.3848
• eval_gen_len: 16.6443
• eval_runtime: 58.6415
• eval_samples_per_second: 13.949
• eval_steps_per_second: 3.496
• epoch: 5.0
• step: 9210

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: 0.00027005552108591514
• train_batch_size: 8
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 341
• num_epochs: 6
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1