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: 0.4554
• Rouge1: 55.5556
• Rouge2: 47.6190
• Rougel: 55.9524
• Rougelsum: 55.5556
• Gen Len: 3.9048

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	6.7375	8.7145	0.9524	8.7598	8.5557	19.0
No log	1.96	12	2.8089	23.3333	9.5238	23.3333	23.3333	3.1429
No log	2.96	18	0.9394	9.5238	4.7619	9.5238	9.5238	3.1905
No log	3.96	24	0.6679	32.6190	14.2857	33.3333	32.0635	3.5714
No log	4.96	30	0.6736	25.2381	9.5238	25.3175	25.5556	4.2381
No log	5.96	36	0.6658	37.6190	23.8095	38.4127	37.9365	4.0476
No log	6.96	42	0.6460	45.5556	33.3333	46.6667	45.2381	3.8571
No log	7.96	48	0.5596	50.7937	42.8571	52.3810	50.7937	4.0
No log	8.96	54	0.5082	55.5556	47.6190	55.9524	55.5556	3.9524
No log	9.96	60	0.4554	55.5556	47.6190	55.9524	55.5556	3.9048

Framework versions

• Transformers 4.26.0
• Pytorch 1.13.0+cu117
• Datasets 2.8.0
• Tokenizers 0.13.3