metadata
library_name: transformers
license: apache-2.0
base_model: dima806/facial_emotions_image_detection
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: image_classification2
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: 0.66875
image_classification2
This model is a fine-tuned version of dima806/facial_emotions_image_detection on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.9519
- Accuracy: 0.6687
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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.8187 | 1.0 | 80 | 1.7527 | 0.4813 |
| 1.52 | 2.0 | 160 | 1.3596 | 0.6312 |
| 1.4072 | 3.0 | 240 | 1.2119 | 0.5875 |
| 1.0868 | 4.0 | 320 | 1.0981 | 0.625 |
| 0.9286 | 5.0 | 400 | 1.0133 | 0.6625 |
| 0.9353 | 6.0 | 480 | 0.9711 | 0.625 |
| 0.7437 | 7.0 | 560 | 0.9389 | 0.6562 |
| 0.6774 | 8.0 | 640 | 0.9519 | 0.6687 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1