t5-large-finetuned-amazon-test_2

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

• Loss: 3.3001
• Rouge1: 15.7824
• Rouge2: 5.363
• Rougel: 15.6395
• Rougelsum: 15.4975

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: 8
• eval_batch_size: 8
• 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
1.7536	1.0	1314	2.6889	15.4715	7.1041	15.012	15.0539
1.9856	2.0	2628	2.5947	15.5517	7.607	15.2437	15.1322
1.7233	3.0	3942	2.7304	16.8701	7.3701	16.6526	16.4333
1.5162	4.0	5256	2.8605	16.278	6.2082	16.114	16.0542
1.3537	5.0	6570	2.9747	15.8483	5.8158	15.5124	15.4393
1.2302	6.0	7884	3.1345	15.6894	5.516	15.5049	15.2841
1.141	7.0	9198	3.2224	15.7304	6.131	15.7835	15.5706
1.0733	8.0	10512	3.3001	15.7824	5.363	15.6395	15.4975

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3