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: 1.3980
• Rouge1: 0.002
• Rouge2: 0.0002
• Rougel: 0.0019
• Rougelsum: 0.0019
• Gen Len: 18.6364

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: 32
• eval_batch_size: 32
• 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	4.9361	0.0004	0.0001	0.0004	0.0004	17.933
No log	2.0	54	3.9155	0.0006	0.0001	0.0006	0.0006	18.1435
No log	3.0	81	3.2005	0.0004	0.0001	0.0004	0.0004	17.1292
No log	4.0	108	2.6800	0.0005	0.0001	0.0005	0.0005	17.9474
No log	5.0	135	2.3165	0.0018	0.0001	0.0018	0.0018	18.1627
No log	6.0	162	2.0678	0.0021	0.0001	0.0021	0.0021	18.4354
No log	7.0	189	1.8971	0.0016	0.0	0.0016	0.0016	18.7512
No log	8.0	216	1.7619	0.0017	0.0	0.0017	0.0017	18.8086
No log	9.0	243	1.6513	0.0015	0.0	0.0015	0.0015	18.7416
No log	10.0	270	1.5641	0.001	0.0	0.0011	0.001	18.8182
No log	11.0	297	1.4990	0.0011	0.0	0.0011	0.0011	18.7081
No log	12.0	324	1.4543	0.0018	0.0001	0.0017	0.0016	18.6507
No log	13.0	351	1.4226	0.0014	0.0	0.0015	0.0015	18.6316
No log	14.0	378	1.4043	0.0019	0.0002	0.0018	0.0018	18.6411
No log	15.0	405	1.3980	0.002	0.0002	0.0019	0.0019	18.6364

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1