bart-convo-summarizer-peft

This model is a fine-tuned version of Advaith1612/bart_convo-summarizer on the samsum dataset. It achieves the following results on the evaluation set:

• Loss: 0.1007

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
2.2141	1.0	37	1.5593
1.0508	2.0	74	0.5395
0.3323	3.0	111	0.1873
0.1741	4.0	148	0.1134
0.1335	5.0	185	0.1007

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1