BARTModel_for_Ecommerce

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

• Loss: 0.6511
• Rouge1: 0.35
• Rouge2: 0.2527
• Rougel: 0.3229
• Rougelsum: 0.323
• Gen Len: 20.0

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	3.3125	0.2888	0.1482	0.2448	0.2454	20.0
No log	2.0	54	2.2699	0.2926	0.1667	0.2564	0.2574	20.0
No log	3.0	81	1.7686	0.3119	0.1908	0.2752	0.2753	20.0
No log	4.0	108	1.3882	0.324	0.2104	0.2937	0.2939	20.0
No log	5.0	135	1.1275	0.3151	0.2061	0.2871	0.2877	20.0
No log	6.0	162	0.9372	0.3293	0.2231	0.3017	0.3022	20.0
No log	7.0	189	0.8252	0.33	0.2182	0.2982	0.2988	20.0
No log	8.0	216	0.7575	0.3378	0.2317	0.3058	0.3065	20.0
No log	9.0	243	0.7102	0.3498	0.2418	0.3148	0.3149	20.0
No log	10.0	270	0.6890	0.3411	0.2374	0.3119	0.3126	20.0
No log	11.0	297	0.6760	0.3441	0.2394	0.3151	0.3155	20.0
No log	12.0	324	0.6640	0.3442	0.2417	0.3151	0.3152	20.0
No log	13.0	351	0.6520	0.3548	0.2506	0.3242	0.3246	20.0
No log	14.0	378	0.6519	0.3497	0.2506	0.3199	0.3201	20.0
No log	15.0	405	0.6511	0.35	0.2527	0.3229	0.323	20.0

Framework versions

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