metadata

library_name: transformers
license: apache-2.0
base_model: WinKawaks/vit-tiny-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: mozilla_dataset_processed_mel_spec_vit_1
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.94

mozilla_dataset_processed_mel_spec_vit_1

This model is a fine-tuned version of WinKawaks/vit-tiny-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.4348
Accuracy: 0.94

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: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7532	1.0	11	0.6034	0.6367
0.4888	2.0	22	0.2861	0.9033
0.2919	3.0	33	0.2482	0.92
0.1771	4.0	44	0.2018	0.9233
0.1011	5.0	55	0.2074	0.9233
0.0563	6.0	66	0.2219	0.9367
0.0251	7.0	77	0.2835	0.9333
0.0041	8.0	88	0.3132	0.9367
0.001	9.0	99	0.4014	0.94
0.0	10.0	110	0.4260	0.9433
0.0	11.0	121	0.4316	0.94
0.0	12.0	132	0.4329	0.94
0.0	13.0	143	0.4327	0.9433
0.0	14.0	154	0.4334	0.94
0.0	15.0	165	0.4339	0.94
0.0	16.0	176	0.4340	0.94
0.0	17.0	187	0.4344	0.94
0.0	18.0	198	0.4346	0.94
0.0	19.0	209	0.4347	0.94
0.0	20.0	220	0.4348	0.94

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0