bart-summarizer

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

• Loss: 2.3295
• Rouge1: 0.33
• Rouge2: 0.0688
• Rougel: 0.205
• Rougelsum: 0.2847
• Gen Len: 129.5045

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.4379	0.9992	622	2.3295	0.33	0.0688	0.205	0.2847	129.5045

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1