wav2GPT2Musicfreeze / README.md
nacielo's picture
update model card README.md
f96a3fc
|
raw
history blame
2.41 kB
metadata
base_model: ''
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: wav2GPT2Musicfreeze
    results: []

wav2GPT2Musicfreeze

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

  • Loss: 1.0685
  • Rouge1: 32.5473
  • Rouge2: 9.2754
  • Rougel: 23.52
  • Rougelsum: 23.5525
  • Gen Len: 74.0

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: 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
2.2767 1.0 1361 1.8699 31.5702 8.644 23.435 23.5065 54.0
1.9325 2.0 2722 1.6511 29.4728 8.9646 21.6881 21.6896 87.0
1.7731 3.0 4083 1.5085 29.7153 8.7535 21.8973 21.9541 85.0
1.638 4.0 5444 1.4016 32.9074 7.9981 23.745 23.7152 59.0
1.5524 5.0 6805 1.2975 32.8051 9.6371 23.658 23.6868 74.0
1.4795 6.0 8166 1.2239 27.9746 7.7738 20.7341 20.6989 50.0
1.4163 7.0 9527 1.1602 29.1471 7.3243 22.2569 22.253 57.0
1.3457 8.0 10888 1.1083 33.2668 9.4555 23.5864 23.6329 78.0
1.3106 9.0 12249 1.0809 32.5473 9.2754 23.52 23.5525 74.0
1.2819 10.0 13610 1.0685 32.5473 9.2754 23.52 23.5525 74.0

Framework versions

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