README.md

metadata

base_model: ''
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: wav2GPT2MusiSD3200
    results: []

wav2GPT2MusiSD3200

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

• Loss: 0.8962
• Rouge1: 28.7212
• Rouge2: 7.4616
• Rougel: 21.8892
• Rougelsum: 21.8832
• Gen Len: 46.0

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: 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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.0361	1.0	1361	0.9081	28.7212	7.4616	21.8892	21.8832	46.0
1.0015	2.0	2722	0.9021	28.1788	7.304	21.4695	21.4607	50.0
1.0003	3.0	4083	0.8976	27.7311	6.574	21.4759	21.4402	57.0
0.9761	4.0	5444	0.8914	27.7311	6.574	21.4759	21.4402	57.0
0.9928	5.0	6805	0.8884	27.7311	6.574	21.4759	21.4402	57.0
1.013	6.0	8166	0.8858	27.7311	6.574	21.4759	21.4402	57.0
1.0476	7.0	9527	0.8852	27.7311	6.574	21.4759	21.4402	57.0
1.0649	8.0	10888	0.8847	27.7311	6.574	21.4759	21.4402	57.0
1.1224	9.0	12249	0.8888	29.7298	7.2318	22.3598	22.3739	56.0
1.1818	10.0	13610	0.8949	29.7298	7.2318	22.3598	22.3739	56.0
1.1832	11.0	14971	0.8981	30.1982	7.2766	22.0853	22.118	59.0
1.1878	12.0	16332	0.8987	29.7298	7.2318	22.3598	22.3739	56.0
1.1833	13.0	17693	0.8983	29.7298	7.2318	22.3598	22.3739	56.0
1.1772	14.0	19054	0.8980	29.7298	7.2318	22.3598	22.3739	56.0
1.1723	15.0	20415	0.8974	28.7212	7.4616	21.8892	21.8832	46.0
1.1778	16.0	21776	0.8972	28.7212	7.4616	21.8892	21.8832	46.0
1.1707	17.0	23137	0.8968	28.7212	7.4616	21.8892	21.8832	46.0
1.1767	18.0	24498	0.8964	28.7212	7.4616	21.8892	21.8832	46.0
1.17	19.0	25859	0.8962	28.7212	7.4616	21.8892	21.8832	46.0
1.1737	20.0	27220	0.8962	28.7212	7.4616	21.8892	21.8832	46.0

Framework versions

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