bart-finetuned-loaf-256-lyrictoplan – AI Model by adamjweintraut | AlphaNeural AI

You can deploy this model and start earning money today!

adamjweintraut/
bart-finetuned-loaf-256-lyrictoplan

like

0

text2text-generation

generated_from_trainer

facebook/bart-large

endpoints_compatible

Views

No views yet

bart-finetuned-loaf-256-lyrictoplan

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: 0.6919
Rouge1: 0.4711
Rouge2: 0.2369
Rougel: 0.3533
Rougelsum: 0.3554
Gen Len: 255.0

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: 5e-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
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.5494	0.89	500	0.9278	0.4886	0.2428	0.3683	0.3694	255.0
0.9078	1.78	1000	0.8602	0.5238	0.2865	0.3859	0.3845	255.0
0.7613	2.67	1500	0.7383	0.4688	0.2288	0.3621	0.3645	255.0
0.6693	3.56	2000	0.7123	0.5007	0.2624	0.3711	0.3727	255.0
0.6079	4.45	2500	0.6919	0.4711	0.2369	0.3533	0.3554	255.0

Framework versions

Transformers 4.39.3
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2