wav2GPT2MusiSD3100 / README.md
nacielo's picture
update model card README.md
f461833
metadata
base_model: ''
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: wav2GPT2MusiSD3100
    results: []

wav2GPT2MusiSD3100

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

  • Loss: 1.4092
  • Rouge1: 15.6142
  • Rouge2: 2.2075
  • Rougel: 14.8541
  • Rougelsum: 14.8888
  • Gen Len: 60.0

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-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: 10

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
1.9569 1.0 959 1.7932 19.6635 2.3177 17.8258 17.8164 57.0
1.7035 2.0 1918 1.6795 18.4799 2.3155 16.3977 16.4296 63.0
1.6267 3.0 2877 1.6036 21.2993 2.9167 19.1184 19.1044 61.0
1.5669 4.0 3836 1.5429 16.6273 2.141 15.4121 15.4484 60.0
1.5373 5.0 4795 1.4901 15.6142 2.2075 14.8541 14.8888 60.0
1.5333 6.0 5754 1.4583 14.3844 2.1564 13.524 13.5429 58.0
1.5303 7.0 6713 1.4323 15.6142 2.2075 14.8541 14.8888 60.0
1.5337 8.0 7672 1.4156 15.6142 2.2075 14.8541 14.8888 60.0
1.5518 9.0 8631 1.4099 15.6142 2.2075 14.8541 14.8888 60.0
1.5764 10.0 9590 1.4092 15.6142 2.2075 14.8541 14.8888 60.0

Framework versions

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