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: 0.4761
• Rouge1: 62.6984
• Rouge2: 52.3810
• Rougel: 62.6984
• Rougelsum: 62.2222
• Gen Len: 4.0952

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	6.6619	9.5321	2.0106	9.7341	9.6021	18.6190
No log	1.96	12	2.5944	21.4286	9.5238	21.4286	21.4286	3.1429
No log	2.96	18	0.8201	19.0476	9.5238	18.7302	18.5714	4.4762
No log	3.96	24	0.5805	41.5873	23.8095	41.2698	41.5873	3.5714
No log	4.96	30	0.5416	46.6667	38.0952	45.2381	45.5556	4.1429
No log	5.96	36	0.6763	55.8730	42.8571	55.5556	55.3175	4.0476
No log	6.96	42	0.7193	58.5714	47.6190	57.9365	57.4603	4.0476
No log	7.96	48	0.5980	58.5714	47.6190	57.9365	57.4603	4.0
No log	8.96	54	0.4943	62.6984	52.3810	62.6984	62.2222	4.0952
No log	9.96	60	0.4761	62.6984	52.3810	62.6984	62.2222	4.0952

Framework versions

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