product_recommendation

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

• Loss: 0.4953
• Rouge1: 73.0159
• Rouge2: 66.6667
• Rougel: 72.2222
• Rougelsum: 72.2222
• Gen Len: 4.1905

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	0.4314	60.3175	47.6190	59.8413	60.3175	4.1429
No log	1.96	12	0.4339	52.6984	38.0952	53.1746	52.3810	4.0952
No log	2.96	18	0.5350	65.0794	52.3810	64.2857	64.9206	4.4286
No log	3.96	24	0.3075	72.8571	61.9048	72.1429	72.1429	4.1905
No log	4.96	30	0.4016	74.6032	66.6667	74.6032	75.3968	4.3333
No log	5.96	36	0.4496	76.1905	71.4286	74.6032	74.6032	4.1905
No log	6.96	42	0.5539	60.3175	57.1429	61.9048	60.3175	4.0
No log	7.96	48	0.3816	80.9524	76.1905	79.3651	79.3651	4.1905
No log	8.96	54	0.4602	74.6032	71.4286	74.6032	74.6032	4.1429
No log	9.96	60	0.4953	73.0159	66.6667	72.2222	72.2222	4.1905

Framework versions

• Transformers 4.26.0
• Pytorch 2.0.1+cu118
• Datasets 2.8.0
• Tokenizers 0.13.3