<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
audio-class-minds14
This model is a fine-tuned version of juniorjukeko/audio-class-minds14 on the minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 2.6380
- Accuracy: 0.0885
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: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 143
- 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 | 2.6452 | 0.0796 |
No log | 1.87 | 7 | 2.6469 | 0.0796 |
2.643 | 2.93 | 11 | 2.6449 | 0.0708 |
2.643 | 4.0 | 15 | 2.6426 | 0.0708 |
2.643 | 4.8 | 18 | 2.6429 | 0.0708 |
2.649 | 5.87 | 22 | 2.6413 | 0.0885 |
2.649 | 6.93 | 26 | 2.6388 | 0.0885 |
2.6382 | 8.0 | 30 | 2.6380 | 0.0885 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3