t5_recommendation_sports_equipment_english

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

• Loss: 0.3614
• Rouge1: 63.8331
• Rouge2: 0.0
• Rougel: 63.8135
• Rougelsum: 63.8922
• Gen Len: 3.0177

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	0.96	6	7.0341	41.3666	0.0	41.2761	41.3863	3.4923
No log	1.96	12	2.9883	40.7910	0.0	40.6533	40.7615	3.0248
No log	2.96	18	0.7740	40.7320	0.0	40.6139	40.7320	3.0094
No log	3.96	24	0.6257	59.8583	0.0	59.8583	59.8583	3.0
No log	4.96	30	0.6243	59.8583	0.0	59.8583	59.8583	3.0
No log	5.96	36	0.4635	60.0945	0.0	59.9764	60.0945	3.0035
No log	6.96	42	0.3732	58.2841	0.0	58.1267	58.3038	3.1606
No log	7.96	48	0.3615	60.6749	0.0	60.5667	60.6848	3.0767
No log	8.96	54	0.3673	61.3144	0.0	61.1177	61.2948	3.0260
No log	9.96	60	0.3614	63.8331	0.0	63.8135	63.8922	3.0177

Framework versions

• Transformers 4.26.0
• Pytorch 2.1.0+cu121
• Datasets 2.8.0
• Tokenizers 0.13.3