wav2BertMusic

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

• Loss: 2.1932
• Rouge1: 24.6783
• Rouge2: 7.4152
• Rougel: 18.5063
• Rougelsum: 18.4876
• Gen Len: 57.47

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: 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
3.9337	1.0	1361	3.0866	33.4529	9.1841	24.0245	24.0402	61.0
2.9007	2.0	2722	2.5830	21.3719	5.1164	17.9298	17.9543	22.0
2.618	3.0	4083	2.3494	28.6972	8.052	21.1856	21.2321	80.0
2.4682	4.0	5444	2.2407	25.5182	7.855	19.118	19.1135	53.54
2.421	5.0	6805	2.1932	24.6783	7.4152	18.5063	18.4876	57.47

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu117
• Datasets 2.14.2
• Tokenizers 0.13.3