metadata

library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
  - generated_from_trainer
datasets:
  - minds14
metrics:
  - accuracy
model-index:
  - name: test_model_dir
    results:
      - task:
          name: Audio Classification
          type: audio-classification
        dataset:
          name: minds14
          type: minds14
          config: en-US
          split: train
          args: en-US
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.035398230088495575

test_model_dir

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: 2.7409
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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.8	3	2.6436	0.0619
No log	1.8667	7	2.6432	0.0619
2.6369	2.9333	11	2.6476	0.0442
2.6369	4.0	15	2.6537	0.0708
2.6369	4.8	18	2.6607	0.0708
2.6202	5.8667	22	2.6715	0.0708
2.6202	6.9333	26	2.6795	0.0531
2.6072	8.0	30	2.6857	0.0531
2.6072	8.8	33	2.6839	0.0531
2.6072	9.8667	37	2.6861	0.0619
2.5931	10.9333	41	2.6896	0.0531
2.5931	12.0	45	2.6916	0.0442
2.5931	12.8	48	2.6958	0.0531
2.5709	13.8667	52	2.7015	0.0531
2.5709	14.9333	56	2.7040	0.0442
2.5539	16.0	60	2.7116	0.0531
2.5539	16.8	63	2.7192	0.0354
2.5539	17.8667	67	2.7237	0.0265
2.5413	18.9333	71	2.7218	0.0354
2.5413	20.0	75	2.7317	0.0265
2.5413	20.8	78	2.7224	0.0354
2.516	21.8667	82	2.7218	0.0265
2.516	22.9333	86	2.7273	0.0265
2.5084	24.0	90	2.7202	0.0442
2.5084	24.8	93	2.7282	0.0265
2.5084	25.8667	97	2.7359	0.0265
2.4734	26.9333	101	2.7279	0.0265
2.4734	28.0	105	2.7302	0.0265
2.4734	28.8	108	2.7367	0.0442
2.4653	29.8667	112	2.7411	0.0265
2.4653	30.9333	116	2.7394	0.0354
2.4439	32.0	120	2.7451	0.0354
2.4439	32.8	123	2.7397	0.0265
2.4439	33.8667	127	2.7356	0.0265
2.4314	34.9333	131	2.7414	0.0354
2.4314	36.0	135	2.7484	0.0265
2.4314	36.8	138	2.7482	0.0265
2.4165	37.8667	142	2.7449	0.0354
2.4165	38.9333	146	2.7414	0.0354
2.4129	40.0	150	2.7409	0.0354

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1