t5-small-finetuned-amazon-en-es

This model is a fine-tuned version of google-t5/t5-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.1338
• Rouge1: 15.288
• Rouge2: 5.9122
• Rougel: 15.0016
• Rougelsum: 15.025

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: 5.6e-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: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
3.4582	1.0	565	3.2280	15.5752	6.4445	15.0167	15.1207
3.1756	2.0	1130	3.1846	15.4189	7.2436	14.9347	15.0646
3.0769	3.0	1695	3.1641	14.7754	6.4923	14.4351	14.5265
3.0117	4.0	2260	3.1495	14.7305	6.6849	14.4567	14.5639
2.9806	5.0	2825	3.1389	15.4222	6.8815	15.0067	15.1059
2.9389	6.0	3390	3.1381	15.8264	6.5277	15.3998	15.4669
2.9173	7.0	3955	3.1358	15.2775	5.9122	14.9794	14.9913
2.9034	8.0	4520	3.1338	15.288	5.9122	15.0016	15.025

Framework versions

• Transformers 4.41.1
• Pytorch 2.2.2+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1