metadata
license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: smids_5x_deit_tiny_rms_00001_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: 0.8768718801996672
smids_5x_deit_tiny_rms_00001_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: 1.2381
- Accuracy: 0.8769
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- 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: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3659 | 1.0 | 375 | 0.3296 | 0.8686 |
| 0.2195 | 2.0 | 750 | 0.3046 | 0.8802 |
| 0.1328 | 3.0 | 1125 | 0.3414 | 0.8752 |
| 0.0957 | 4.0 | 1500 | 0.3842 | 0.8802 |
| 0.0592 | 5.0 | 1875 | 0.4781 | 0.8885 |
| 0.0554 | 6.0 | 2250 | 0.5329 | 0.8902 |
| 0.0561 | 7.0 | 2625 | 0.7030 | 0.8735 |
| 0.0111 | 8.0 | 3000 | 0.7077 | 0.8785 |
| 0.0138 | 9.0 | 3375 | 0.8845 | 0.8852 |
| 0.0035 | 10.0 | 3750 | 0.8403 | 0.8819 |
| 0.0539 | 11.0 | 4125 | 0.9586 | 0.8702 |
| 0.009 | 12.0 | 4500 | 0.9960 | 0.8802 |
| 0.0001 | 13.0 | 4875 | 1.0306 | 0.8719 |
| 0.0001 | 14.0 | 5250 | 1.0127 | 0.8835 |
| 0.0171 | 15.0 | 5625 | 1.0184 | 0.8885 |
| 0.0071 | 16.0 | 6000 | 0.9932 | 0.8869 |
| 0.0241 | 17.0 | 6375 | 1.0882 | 0.8752 |
| 0.0005 | 18.0 | 6750 | 1.0661 | 0.8902 |
| 0.0877 | 19.0 | 7125 | 1.0148 | 0.8785 |
| 0.0001 | 20.0 | 7500 | 1.0786 | 0.8735 |
| 0.0 | 21.0 | 7875 | 1.0833 | 0.8852 |
| 0.0 | 22.0 | 8250 | 1.1111 | 0.8785 |
| 0.0001 | 23.0 | 8625 | 1.2212 | 0.8752 |
| 0.0 | 24.0 | 9000 | 1.0341 | 0.8752 |
| 0.0 | 25.0 | 9375 | 1.1693 | 0.8752 |
| 0.0 | 26.0 | 9750 | 1.1184 | 0.8819 |
| 0.0 | 27.0 | 10125 | 1.0601 | 0.8785 |
| 0.0009 | 28.0 | 10500 | 1.1933 | 0.8702 |
| 0.0 | 29.0 | 10875 | 1.2058 | 0.8785 |
| 0.0 | 30.0 | 11250 | 1.1743 | 0.8735 |
| 0.0039 | 31.0 | 11625 | 1.2100 | 0.8785 |
| 0.0108 | 32.0 | 12000 | 1.2237 | 0.8769 |
| 0.0031 | 33.0 | 12375 | 1.2193 | 0.8735 |
| 0.0 | 34.0 | 12750 | 1.2009 | 0.8769 |
| 0.0 | 35.0 | 13125 | 1.1695 | 0.8802 |
| 0.0 | 36.0 | 13500 | 1.1623 | 0.8819 |
| 0.0 | 37.0 | 13875 | 1.2497 | 0.8702 |
| 0.0 | 38.0 | 14250 | 1.2770 | 0.8769 |
| 0.0 | 39.0 | 14625 | 1.2424 | 0.8769 |
| 0.0042 | 40.0 | 15000 | 1.2342 | 0.8819 |
| 0.0 | 41.0 | 15375 | 1.2571 | 0.8785 |
| 0.0026 | 42.0 | 15750 | 1.2422 | 0.8702 |
| 0.0032 | 43.0 | 16125 | 1.2321 | 0.8835 |
| 0.0033 | 44.0 | 16500 | 1.2366 | 0.8852 |
| 0.0026 | 45.0 | 16875 | 1.2353 | 0.8802 |
| 0.0 | 46.0 | 17250 | 1.2327 | 0.8785 |
| 0.0046 | 47.0 | 17625 | 1.2346 | 0.8785 |
| 0.0 | 48.0 | 18000 | 1.2359 | 0.8769 |
| 0.0024 | 49.0 | 18375 | 1.2368 | 0.8769 |
| 0.0026 | 50.0 | 18750 | 1.2381 | 0.8769 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.1+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2