ejercicio3_tickets_adrian_perez

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

• Loss: 0.2471
• Rougel: 0.4917

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: 0.0003
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.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: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rougel
0.3383	0.4794	500	0.3009	0.4760
0.2944	0.9588	1000	0.2729	0.4841
0.2653	1.4382	1500	0.2637	0.4851
0.2459	1.9175	2000	0.2533	0.4912
0.2221	2.3969	2500	0.2508	0.4905
0.2225	2.8763	3000	0.2471	0.4917

Framework versions

• Transformers 4.51.1
• Pytorch 2.5.1+cu124
• Datasets 3.5.0
• Tokenizers 0.21.0