metadata
license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: Boya1_SGD_1-e3_20Epoch_Deit-tiny-patch16_fold2
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.4181081081081081
Boya1_SGD_1-e3_20Epoch_Deit-tiny-patch16_fold2
This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.7360
- Accuracy: 0.4181
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: 0.001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
2.448 | 1.0 | 923 | 2.4582 | 0.2016 |
2.3582 | 2.0 | 1846 | 2.3021 | 0.2376 |
2.2617 | 3.0 | 2769 | 2.1666 | 0.2897 |
2.0757 | 4.0 | 3692 | 2.0662 | 0.3235 |
2.008 | 5.0 | 4615 | 1.9944 | 0.3449 |
2.0395 | 6.0 | 5538 | 1.9375 | 0.3595 |
1.9087 | 7.0 | 6461 | 1.8952 | 0.3749 |
1.9463 | 8.0 | 7384 | 1.8644 | 0.3805 |
1.8879 | 9.0 | 8307 | 1.8376 | 0.3908 |
1.7446 | 10.0 | 9230 | 1.8140 | 0.3938 |
1.7618 | 11.0 | 10153 | 1.7964 | 0.3965 |
1.7616 | 12.0 | 11076 | 1.7817 | 0.4051 |
1.7296 | 13.0 | 11999 | 1.7702 | 0.4057 |
1.8498 | 14.0 | 12922 | 1.7608 | 0.4124 |
1.7605 | 15.0 | 13845 | 1.7532 | 0.4111 |
1.7119 | 16.0 | 14768 | 1.7468 | 0.4154 |
1.7061 | 17.0 | 15691 | 1.7421 | 0.4157 |
1.6731 | 18.0 | 16614 | 1.7387 | 0.4178 |
1.5776 | 19.0 | 17537 | 1.7366 | 0.4189 |
1.5522 | 20.0 | 18460 | 1.7360 | 0.4181 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.1.0
- Datasets 2.19.0
- Tokenizers 0.19.1