RickyIG's picture
End of training
7aa2af4
---
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: emotion_face_image_classification
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.55
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# emotion_face_image_classification
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2110
- Accuracy: 0.55
## 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: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.0717 | 1.0 | 10 | 2.0593 | 0.2062 |
| 2.005 | 2.0 | 20 | 1.9999 | 0.2625 |
| 1.9169 | 3.0 | 30 | 1.8931 | 0.35 |
| 1.7635 | 4.0 | 40 | 1.7616 | 0.4062 |
| 1.6614 | 5.0 | 50 | 1.6452 | 0.4562 |
| 1.6182 | 6.0 | 60 | 1.5661 | 0.4125 |
| 1.5434 | 7.0 | 70 | 1.5183 | 0.4125 |
| 1.46 | 8.0 | 80 | 1.4781 | 0.4875 |
| 1.4564 | 9.0 | 90 | 1.3939 | 0.5125 |
| 1.2966 | 10.0 | 100 | 1.3800 | 0.4562 |
| 1.3732 | 11.0 | 110 | 1.3557 | 0.475 |
| 1.2907 | 12.0 | 120 | 1.3473 | 0.5 |
| 1.2875 | 13.0 | 130 | 1.3416 | 0.5312 |
| 1.2743 | 14.0 | 140 | 1.2964 | 0.4875 |
| 1.1249 | 15.0 | 150 | 1.2385 | 0.525 |
| 1.0963 | 16.0 | 160 | 1.2775 | 0.5062 |
| 1.0261 | 17.0 | 170 | 1.2751 | 0.5125 |
| 0.9298 | 18.0 | 180 | 1.2318 | 0.525 |
| 1.0668 | 19.0 | 190 | 1.2520 | 0.5437 |
| 0.9933 | 20.0 | 200 | 1.2512 | 0.525 |
| 1.1069 | 21.0 | 210 | 1.3016 | 0.5 |
| 1.0279 | 22.0 | 220 | 1.3279 | 0.475 |
| 0.967 | 23.0 | 230 | 1.2481 | 0.5 |
| 0.8115 | 24.0 | 240 | 1.1791 | 0.5563 |
| 0.7912 | 25.0 | 250 | 1.2336 | 0.55 |
| 0.9294 | 26.0 | 260 | 1.1759 | 0.5813 |
| 0.8936 | 27.0 | 270 | 1.1685 | 0.6 |
| 0.7706 | 28.0 | 280 | 1.2403 | 0.5312 |
| 0.7694 | 29.0 | 290 | 1.2479 | 0.5687 |
| 0.7265 | 30.0 | 300 | 1.2000 | 0.5625 |
| 0.6781 | 31.0 | 310 | 1.1856 | 0.55 |
| 0.6676 | 32.0 | 320 | 1.2661 | 0.5437 |
| 0.7254 | 33.0 | 330 | 1.1986 | 0.5437 |
| 0.7396 | 34.0 | 340 | 1.1497 | 0.575 |
| 0.5532 | 35.0 | 350 | 1.2796 | 0.5062 |
| 0.622 | 36.0 | 360 | 1.2749 | 0.5125 |
| 0.6958 | 37.0 | 370 | 1.2034 | 0.5687 |
| 0.6102 | 38.0 | 380 | 1.2576 | 0.5188 |
| 0.6161 | 39.0 | 390 | 1.2635 | 0.5062 |
| 0.6927 | 40.0 | 400 | 1.1535 | 0.5437 |
| 0.549 | 41.0 | 410 | 1.1405 | 0.6 |
| 0.6668 | 42.0 | 420 | 1.2683 | 0.5312 |
| 0.5144 | 43.0 | 430 | 1.2249 | 0.6 |
| 0.6703 | 44.0 | 440 | 1.2297 | 0.5687 |
| 0.6383 | 45.0 | 450 | 1.1507 | 0.6062 |
| 0.5211 | 46.0 | 460 | 1.2914 | 0.4813 |
| 0.4743 | 47.0 | 470 | 1.2782 | 0.5125 |
| 0.553 | 48.0 | 480 | 1.2256 | 0.5375 |
| 0.6407 | 49.0 | 490 | 1.2149 | 0.5687 |
| 0.4195 | 50.0 | 500 | 1.2024 | 0.5625 |
### Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3