sumit7488/meet_brief

BART-model-fine_tuned

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: 0.5467
• Rouge1: 58.168
• Rouge2: 45.9825
• Rougel: 54.3562
• Rougelsum: 54.4552

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: 1e-05
• train_batch_size: 4
• eval_batch_size: 4
• gradient_accumulation_steps: 4
• weight_decay: 0.01
• 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: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
0.6587	1.0	563	0.6037	56.3206	44.2624	52.832	52.8704
0.6162	2.0	1126	0.5719	56.8789	44.8139	53.3803	53.4437
0.5815	3.0	1689	0.5560	57.6576	45.5559	53.943	54.0187
0.5663	4.0	2252	0.5491	57.9815	45.9701	54.2183	54.3077
0.546	5.0	2815	0.5467	58.168	45.9825	54.3562	54.4552

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0