metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: cat-sounds
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: 0.9461732548359967
- name: F1
type: f1
value: 0.9463827697148198
- name: Precision
type: precision
value: 0.9476585951632728
- name: Recall
type: recall
value: 0.9461732548359967
cat-sounds
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.2256
- Accuracy: 0.9462
- F1: 0.9464
- Precision: 0.9477
- Recall: 0.9462
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.2716 | 1.0 | 297 | 0.3630 | 0.8957 | 0.8961 | 0.9047 | 0.8957 |
| 0.098 | 2.0 | 594 | 0.2674 | 0.9344 | 0.9350 | 0.9372 | 0.9344 |
| 0.0487 | 3.0 | 891 | 0.2256 | 0.9462 | 0.9464 | 0.9477 | 0.9462 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1