T5Model_for_Ecommerce

This model is a fine-tuned version of Praveen76/FinetunedT5Model on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8721
• Rouge1: 0.0621
• Rouge2: 0.0389
• Rougel: 0.0557
• Rougelsum: 0.0558
• Gen Len: 3.5185

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	27	4.3352	0.2549	0.137	0.219	0.219	19.0
No log	2.0	54	1.1426	0.021	0.0122	0.0179	0.0179	1.4074
No log	3.0	81	1.0385	0.0	0.0	0.0	0.0	0.0
No log	4.0	108	1.0166	0.0	0.0	0.0	0.0	0.0
No log	5.0	135	0.9971	0.0	0.0	0.0	0.0	0.0
No log	6.0	162	0.9746	0.0	0.0	0.0	0.0	0.0
No log	7.0	189	0.9508	0.0	0.0	0.0	0.0	0.0
No log	8.0	216	0.9301	0.0	0.0	0.0	0.0	0.0
No log	9.0	243	0.9135	0.0	0.0	0.0	0.0	0.0
No log	10.0	270	0.8984	0.0379	0.0256	0.0336	0.0339	1.9352
No log	11.0	297	0.8892	0.0437	0.0294	0.0393	0.0391	2.287
No log	12.0	324	0.8821	0.0491	0.0319	0.0441	0.0443	2.6389
No log	13.0	351	0.8764	0.0537	0.0331	0.0479	0.048	2.9907
No log	14.0	378	0.8730	0.0621	0.0389	0.0557	0.0558	3.5185
No log	15.0	405	0.8721	0.0621	0.0389	0.0557	0.0558	3.5185

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3