phi0108/audio_classification

1---2license: apache-2.03tags:4- generated_from_trainer5datasets:6- minds147metrics:8- accuracy9model-index:10- name: audio_classification11  results: []12---13 14<!-- This model card has been generated automatically according to the information the Trainer had access to. You15should probably proofread and complete it, then remove this comment. -->16 17# audio_classification18 19This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the minds14 dataset.20It achieves the following results on the evaluation set:21- Loss: 2.638522- Accuracy: 0.070823 24## Model description25 26More information needed27 28## Intended uses & limitations29 30More information needed31 32## Training and evaluation data33 34More information needed35 36## Training procedure37 38### Training hyperparameters39 40The following hyperparameters were used during training:41- learning_rate: 3e-0542- train_batch_size: 3243- eval_batch_size: 3244- seed: 4245- gradient_accumulation_steps: 446- total_train_batch_size: 12847- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0848- lr_scheduler_type: linear49- lr_scheduler_warmup_ratio: 0.150- num_epochs: 1051 52### Training results53 54| Training Loss | Epoch | Step | Validation Loss | Accuracy |55|:-------------:|:-----:|:----:|:---------------:|:--------:|56| No log        | 0.8   | 3    | 2.6440          | 0.0442   |57| No log        | 1.87  | 7    | 2.6566          | 0.0531   |58| 2.6406        | 2.93  | 11   | 2.6527          | 0.0354   |59| 2.6406        | 4.0   | 15   | 2.6533          | 0.0619   |60| 2.6406        | 4.8   | 18   | 2.6503          | 0.0796   |61| 2.6412        | 5.87  | 22   | 2.6402          | 0.0885   |62| 2.6412        | 6.93  | 26   | 2.6394          | 0.0619   |63| 2.6389        | 8.0   | 30   | 2.6385          | 0.0708   |64 65 66### Framework versions67 68- Transformers 4.27.469- Pytorch 2.0.070- Datasets 2.11.071- Tokenizers 0.13.372