metadata
license: apache-2.0
base_model: microsoft/beit-large-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: Boya3_3Class_Adamax_1e4_20Epoch_Beit-large-224_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: 0.8326095538886695
Boya3_3Class_Adamax_1e4_20Epoch_Beit-large-224_fold2
This model is a fine-tuned version of microsoft/beit-large-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.7149
- Accuracy: 0.8326
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: 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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.4839 | 1.0 | 631 | 0.4443 | 0.8220 |
0.3941 | 2.0 | 1262 | 0.4179 | 0.8298 |
0.1956 | 3.0 | 1893 | 0.4992 | 0.8314 |
0.198 | 4.0 | 2524 | 0.8608 | 0.8231 |
0.1306 | 5.0 | 3155 | 1.1049 | 0.8223 |
0.0083 | 6.0 | 3786 | 1.5038 | 0.8239 |
0.0374 | 7.0 | 4417 | 1.6141 | 0.8326 |
0.0 | 8.0 | 5048 | 1.6544 | 0.8259 |
0.0 | 9.0 | 5679 | 1.7031 | 0.8338 |
0.0001 | 10.0 | 6310 | 1.7149 | 0.8326 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.2