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: 0.9462
• Rouge1: 0.0406
• Rouge2: 0.0272
• Rougel: 0.0345
• Rougelsum: 0.0344
• Gen Len: 1.9352

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• 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	4.2817	0.2641	0.1401	0.2239	0.2236	19.0
No log	2.0	54	1.2657	0.0685	0.0411	0.0583	0.0589	4.0463
No log	3.0	81	1.1014	0.0	0.0	0.0	0.0	0.0
No log	4.0	108	1.0864	0.0	0.0	0.0	0.0	0.0
No log	5.0	135	1.0668	0.0	0.0	0.0	0.0	0.0
No log	6.0	162	1.0474	0.0	0.0	0.0	0.0	0.0
No log	7.0	189	1.0204	0.0	0.0	0.0	0.0	0.0
No log	8.0	216	1.0035	0.0	0.0	0.0	0.0	0.0
No log	9.0	243	0.9870	0.0	0.0	0.0	0.0	0.0
No log	10.0	270	0.9732	0.0	0.0	0.0	0.0	0.0
No log	11.0	297	0.9625	0.0098	0.0059	0.0094	0.0094	0.5278
No log	12.0	324	0.9563	0.0295	0.0194	0.0266	0.0264	1.4074
No log	13.0	351	0.9504	0.0325	0.0213	0.0291	0.029	1.5833
No log	14.0	378	0.9472	0.0406	0.0272	0.0345	0.0344	1.9352
No log	15.0	405	0.9462	0.0406	0.0272	0.0345	0.0344	1.9352

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0