metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- image-classification
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: Action_model
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: action_class
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8576449912126538
Action_model
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the action_class dataset. It achieves the following results on the evaluation set:
- Loss: 0.4589
- Accuracy: 0.8576
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.2754 | 0.37 | 100 | 1.1163 | 0.7329 |
0.9345 | 0.75 | 200 | 0.8296 | 0.7996 |
0.8816 | 1.12 | 300 | 0.7156 | 0.8102 |
0.7425 | 1.49 | 400 | 0.6529 | 0.8067 |
0.6883 | 1.87 | 500 | 0.6079 | 0.8243 |
0.5454 | 2.24 | 600 | 0.5605 | 0.8348 |
0.5383 | 2.61 | 700 | 0.5571 | 0.8295 |
0.5442 | 2.99 | 800 | 0.5864 | 0.8190 |
0.3986 | 3.36 | 900 | 0.5632 | 0.8313 |
0.3438 | 3.73 | 1000 | 0.5606 | 0.8366 |
0.4345 | 4.1 | 1100 | 0.5354 | 0.8366 |
0.4523 | 4.48 | 1200 | 0.4988 | 0.8576 |
0.3162 | 4.85 | 1300 | 0.5099 | 0.8541 |
0.3793 | 5.22 | 1400 | 0.5190 | 0.8436 |
0.3228 | 5.6 | 1500 | 0.4589 | 0.8576 |
0.1795 | 5.97 | 1600 | 0.5096 | 0.8489 |
0.2626 | 6.34 | 1700 | 0.5403 | 0.8489 |
0.3041 | 6.72 | 1800 | 0.4908 | 0.8489 |
0.1831 | 7.09 | 1900 | 0.5721 | 0.8383 |
0.2275 | 7.46 | 2000 | 0.5349 | 0.8313 |
0.1762 | 7.84 | 2100 | 0.5204 | 0.8541 |
0.2112 | 8.21 | 2200 | 0.5189 | 0.8629 |
0.1242 | 8.58 | 2300 | 0.5377 | 0.8471 |
0.1207 | 8.96 | 2400 | 0.5325 | 0.8559 |
0.1806 | 9.33 | 2500 | 0.5150 | 0.8647 |
0.1793 | 9.7 | 2600 | 0.5153 | 0.8664 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2