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: 0.4968
• Rouge1: 69.8413
• Rouge2: 61.9048
• Rougel: 69.8413
• Rougelsum: 70.2381
• Gen Len: 4.2381

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	7.0208	13.5224	1.8519	13.7870	13.5032	18.7143
No log	1.92	12	1.8113	20.4762	14.2857	20.4762	20.9524	3.6667
No log	2.88	18	0.7760	23.8095	4.7619	23.3333	23.3333	4.1429
No log	4.0	25	0.5784	38.4127	23.8095	38.8889	39.9206	4.0476
No log	4.96	31	0.5181	54.1270	42.8571	54.8413	54.6825	3.9524
No log	5.92	37	0.4786	62.6984	52.3810	62.6984	62.6984	3.9048
No log	6.88	43	0.4605	64.2857	52.3810	64.6032	64.6032	4.2857
No log	8.0	50	0.6243	67.4603	57.1429	67.4603	67.4603	4.3810
No log	8.96	56	0.5484	64.2857	57.1429	65.0794	65.0794	4.1429
No log	9.6	60	0.4968	69.8413	61.9048	69.8413	70.2381	4.2381

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0