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: 0.4020
• Rouge1: 57.9365
• Rouge2: 47.6190
• Rougel: 57.9365
• Rougelsum: 57.9365
• Gen Len: 4.1429

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	7.7857	20.2721	10.3896	20.0454	20.9524	11.3810
No log	1.92	12	3.1922	20.0	4.7619	20.4762	20.4762	3.1905
No log	2.88	18	0.8028	5.5556	0.0	5.5556	5.5556	3.0
No log	4.0	25	0.7207	32.8571	19.0476	32.9365	34.0476	3.2381
No log	4.96	31	0.5217	50.3968	42.8571	50.0	50.7937	3.9524
No log	5.92	37	0.4420	57.9365	47.6190	57.9365	57.9365	4.0476
No log	6.88	43	0.4694	67.4603	61.9048	67.4603	67.4603	4.0
No log	8.0	50	0.4408	57.9365	47.6190	57.9365	57.9365	4.1429
No log	8.96	56	0.4269	57.9365	47.6190	57.9365	57.9365	4.1429
No log	9.6	60	0.4020	57.9365	47.6190	57.9365	57.9365	4.1429

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu118
• Datasets 2.8.0
• Tokenizers 0.13.3