bart-base-facebook – AI Model by sunsvrv | AlphaNeural AI

You can deploy this model and start earning money today!

sunsvrv/
bart-base-facebook

like

0

text2text-generation

generated_from_trainer

endpoints_compatible

Views

No views yet

bart-base-facebook

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

Loss: 2.1877
Rouge1: 0.7146
Rouge2: 0.3305
Rougel: 0.2988
Rougelsum: 0.6822

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: 10
eval_batch_size: 10
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
2.505	1.0	1359	2.1048	0.6788	0.3022	0.2843	0.6497
2.0216	2.0	2718	2.1010	0.7022	0.3182	0.2974	0.672
1.7088	3.0	4077	2.1228	0.7048	0.3214	0.2968	0.6722
1.4778	4.0	5436	2.1655	0.7117	0.325	0.2984	0.6786
1.3161	5.0	6795	2.1877	0.7146	0.3305	0.2988	0.6822

Framework versions

Transformers 4.22.2
Pytorch 1.12.1+cu113
Datasets 2.5.2
Tokenizers 0.12.1