hubert2BertMusicwithNewS10 – AI Model by nacielo | AlphaNeural AI

You can deploy this model and start earning money today!

nacielo/
hubert2BertMusicwithNewS10

like

0

speech-encoder-decoder

automatic-speech-recognition

generated_from_trainer

endpoints_compatible

Views

No views yet

hubert2BertMusicwithNewS10

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

Loss: 2.8649
Rouge1: 24.5018
Rouge2: 7.2557
Rougel: 18.535
Rougelsum: 18.4997
Gen Len: 50.24

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: 1e-06
train_batch_size: 4
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
3.2422	1.0	1361	2.9931	25.0594	6.9031	18.6171	18.5836	48.72
3.1189	2.0	2722	2.9560	24.0397	7.0297	18.3958	18.3901	48.51
3.1167	3.0	4083	2.9341	24.2991	7.1132	18.4583	18.4489	46.43
3.1044	4.0	5444	2.9114	24.6611	7.2594	18.633	18.6267	49.35
3.1629	5.0	6805	2.8981	24.1154	7.3257	18.5844	18.5767	46.03
3.1118	6.0	8166	2.8856	24.7206	7.2058	18.615	18.5836	51.1
3.1004	7.0	9527	2.8762	24.3086	7.2822	18.5582	18.4717	48.02
3.0851	8.0	10888	2.8702	24.3488	7.2356	18.4268	18.3977	49.38
3.0963	9.0	12249	2.8663	24.4728	7.2887	18.4689	18.4485	50.51
3.0999	10.0	13610	2.8649	24.5018	7.2557	18.535	18.4997	50.24

Framework versions

Transformers 4.31.0
Pytorch 2.0.1+cu117
Datasets 2.14.2
Tokenizers 0.13.3