bart-base-finetuned-summarization

This model is a fine-tuned version of facebook/bart-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.2885
• Rouge1: 31.8585
• Rouge2: 20.7559
• Rougel: 28.879
• Rougelsum: 29.6017

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: 5.6e-05
• train_batch_size: 1
• eval_batch_size: 1
• 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	Rouge1	Rouge2	Rougel	Rougelsum
1.8516	1.0	308	1.3028	29.4331	19.2619	27.1598	28.1099
1.2211	2.0	616	1.2506	30.2583	19.7126	28.1328	28.9654
0.911	3.0	924	1.2316	29.3854	18.6132	27.3488	28.2225
0.6824	4.0	1232	1.2583	32.0664	22.0751	29.521	30.5109
0.542	5.0	1540	1.2885	31.8585	20.7559	28.879	29.6017

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.0+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3