metadata
license: apache-2.0
base_model: facebook/deit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_40x_deit_base_sgd_0001_fold1
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: 0.37777777777777777
hushem_40x_deit_base_sgd_0001_fold1
This model is a fine-tuned version of facebook/deit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.2920
- Accuracy: 0.3778
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: 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 |
|---|---|---|---|---|
| 1.3635 | 1.0 | 215 | 1.4586 | 0.2889 |
| 1.3564 | 2.0 | 430 | 1.4485 | 0.2889 |
| 1.3735 | 3.0 | 645 | 1.4395 | 0.2889 |
| 1.3415 | 4.0 | 860 | 1.4312 | 0.2889 |
| 1.3033 | 5.0 | 1075 | 1.4236 | 0.2889 |
| 1.3111 | 6.0 | 1290 | 1.4165 | 0.2667 |
| 1.2796 | 7.0 | 1505 | 1.4098 | 0.2667 |
| 1.265 | 8.0 | 1720 | 1.4035 | 0.2667 |
| 1.2454 | 9.0 | 1935 | 1.3975 | 0.2667 |
| 1.2437 | 10.0 | 2150 | 1.3919 | 0.2667 |
| 1.2689 | 11.0 | 2365 | 1.3867 | 0.2667 |
| 1.212 | 12.0 | 2580 | 1.3818 | 0.2667 |
| 1.2193 | 13.0 | 2795 | 1.3771 | 0.2667 |
| 1.2167 | 14.0 | 3010 | 1.3726 | 0.2667 |
| 1.205 | 15.0 | 3225 | 1.3683 | 0.2667 |
| 1.2084 | 16.0 | 3440 | 1.3641 | 0.2889 |
| 1.1861 | 17.0 | 3655 | 1.3601 | 0.3333 |
| 1.1898 | 18.0 | 3870 | 1.3563 | 0.3556 |
| 1.1745 | 19.0 | 4085 | 1.3526 | 0.3556 |
| 1.1602 | 20.0 | 4300 | 1.3489 | 0.3556 |
| 1.1523 | 21.0 | 4515 | 1.3454 | 0.3556 |
| 1.1329 | 22.0 | 4730 | 1.3420 | 0.3556 |
| 1.1475 | 23.0 | 4945 | 1.3387 | 0.3556 |
| 1.1333 | 24.0 | 5160 | 1.3354 | 0.3556 |
| 1.1285 | 25.0 | 5375 | 1.3322 | 0.3333 |
| 1.0938 | 26.0 | 5590 | 1.3292 | 0.3333 |
| 1.0832 | 27.0 | 5805 | 1.3262 | 0.3333 |
| 1.0889 | 28.0 | 6020 | 1.3234 | 0.3333 |
| 1.0886 | 29.0 | 6235 | 1.3206 | 0.3333 |
| 1.0684 | 30.0 | 6450 | 1.3180 | 0.3333 |
| 1.0707 | 31.0 | 6665 | 1.3154 | 0.3333 |
| 1.068 | 32.0 | 6880 | 1.3130 | 0.3333 |
| 1.0647 | 33.0 | 7095 | 1.3107 | 0.3556 |
| 1.0516 | 34.0 | 7310 | 1.3085 | 0.3556 |
| 1.0515 | 35.0 | 7525 | 1.3064 | 0.3556 |
| 1.0477 | 36.0 | 7740 | 1.3045 | 0.3556 |
| 1.0685 | 37.0 | 7955 | 1.3027 | 0.3556 |
| 1.0459 | 38.0 | 8170 | 1.3010 | 0.3556 |
| 1.0276 | 39.0 | 8385 | 1.2995 | 0.3556 |
| 1.016 | 40.0 | 8600 | 1.2981 | 0.3556 |
| 1.044 | 41.0 | 8815 | 1.2969 | 0.3556 |
| 1.0849 | 42.0 | 9030 | 1.2957 | 0.3556 |
| 1.0504 | 43.0 | 9245 | 1.2948 | 0.3778 |
| 1.0115 | 44.0 | 9460 | 1.2940 | 0.3778 |
| 1.0336 | 45.0 | 9675 | 1.2933 | 0.3778 |
| 1.0415 | 46.0 | 9890 | 1.2928 | 0.3778 |
| 1.013 | 47.0 | 10105 | 1.2924 | 0.3778 |
| 1.0207 | 48.0 | 10320 | 1.2921 | 0.3778 |
| 1.054 | 49.0 | 10535 | 1.2920 | 0.3778 |
| 1.0317 | 50.0 | 10750 | 1.2920 | 0.3778 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2