bart-base-finetuned-xsum

steveabecassis/bart-base-finetuned-xsum

bart-base-finetuned-xsum is a machine learning model from steveabecassis. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

5% of all-time downloads

All-time downloads

151

Public

Repo size

1.1 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.json2.9 MB · 86%

At a glance

Library: transformers
License: apache-2.0
Model type: bart
Access: Public
Created: Jan 4, 2023
Updated: May 4, 2023
SHA: 138aa98d

Model card

From the Hugging Face model README

bart-base-finetuned-xsum

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: 0.5585
Rouge1: 0.8859
Rouge2: 0.8467
Rougel: 0.8883
Rougelsum: 0.8879

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: 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: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
No log	1.0	41	0.4596	0.8845	0.849	0.8874	0.8865
No log	2.0	82	0.4047	0.8839	0.8466	0.8852	0.8836
No log	3.0	123	0.4587	0.8765	0.836	0.8783	0.8755
No log	4.0	164	0.4488	0.8785	0.8389	0.8811	0.8784
No log	5.0	205	0.4443	0.8564	0.8084	0.855	0.8543
No log	6.0	246	0.4643	0.8965	0.8614	0.8981	0.8965
No log	7.0	287	0.4782	0.8831	0.8468	0.885	0.8836
No log	8.0	328	0.4870	0.853	0.8051	0.8554	0.8541
No log	9.0	369	0.4766	0.9029	0.8659	0.9052	0.9027
No log	10.0	410	0.5023	0.8924	0.8528	0.895	0.8926
No log	11.0	451	0.5254	0.8689	0.8234	0.8699	0.8692
No log	12.0	492	0.4996	0.8833	0.8424	0.8851	0.8843
0.1489	13.0	533	0.5095	0.8747	0.8345	0.8762	0.8749
0.1489	14.0	574	0.5034	0.868	0.8226	0.8699	0.8689
0.1489	15.0	615	0.4976	0.8609	0.8112	0.8632	0.8617
0.1489	16.0	656	0.5122	0.9055	0.8722	0.9068	0.9069
0.1489	17.0	697	0.5204	0.845	0.7954	0.8482	0.8461
0.1489	18.0	738	0.5363	0.8911	0.8528	0.8934	0.8919
0.1489	19.0	779	0.5572	0.8943	0.8594	0.8963	0.8956
0.1489	20.0	820	0.5469	0.9031	0.8688	0.9047	0.9047
0.1489	21.0	861	0.5508	0.8848	0.8472	0.887	0.8869
0.1489	22.0	902	0.5579	0.8724	0.8306	0.8747	0.8737
0.1489	23.0	943	0.5508	0.8772	0.8397	0.8808	0.8803
0.1489	24.0	984	0.5658	0.8627	0.8153	0.8645	0.8637
0.0336	25.0	1025	0.5539	0.904	0.8702	0.9052	0.9058
0.0336	26.0	1066	0.5605	0.9004	0.8659	0.9026	0.9017
0.0336	27.0	1107	0.5589	0.899	0.8644	0.9012	0.9005
0.0336	28.0	1148	0.5558	0.8872	0.8488	0.8894	0.889
0.0336	29.0	1189	0.5570	0.8859	0.8467	0.8883	0.8879
0.0336	30.0	1230	0.5585	0.8859	0.8467	0.8883	0.8879

Framework versions

Transformers 4.26.0.dev0
Pytorch 1.13.0
Datasets 2.8.0
Tokenizers 0.13.2

Library: transformers
Type: bart
License: apache-2.0
Created: Jan 4, 2023
Updated: May 4, 2023