Edit model card

my_awesome_mind_model

This model is a fine-tuned version of facebook/wav2vec2-base on the minds14 dataset. It achieves the following results on the evaluation set:

  • Loss: 2.6541
  • Accuracy: 0.0354

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: 3e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 0.8 3 2.6365 0.1062
No log 1.87 7 2.6370 0.1150
2.6359 2.93 11 2.6422 0.0708
2.6359 4.0 15 2.6449 0.0354
2.6359 4.8 18 2.6499 0.0354
2.6289 5.87 22 2.6580 0.0442
2.6289 6.93 26 2.6559 0.0354
2.6209 8.0 30 2.6541 0.0354

Framework versions

  • Transformers 4.28.1
  • Pytorch 2.0.0+cu118
  • Datasets 2.12.0
  • Tokenizers 0.13.3
Downloads last month
2