bart-large-finetuned-summarization

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

• Loss: 1.1841
• Rouge1: 32.6763
• Rouge2: 23.1598
• Rougel: 31.2322
• Rougelsum: 32.278

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
1.7048	1.0	308	1.1916	32.0296	21.6931	30.2623	31.1959
1.1153	2.0	616	1.2054	30.7076	21.7771	29.3115	29.9377
0.78	3.0	924	1.1096	32.4164	22.494	31.0367	31.8135
0.5335	4.0	1232	1.1547	33.2561	23.6119	32.1371	32.591
0.361	5.0	1540	1.1841	32.6763	23.1598	31.2322	32.278

Framework versions

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