metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-large-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: image_emotion_classification_project_4
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: 0.51875
image_emotion_classification_project_4
This model is a fine-tuned version of google/vit-large-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.9052
- Accuracy: 0.5188
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: reduce_lr_on_plateau
- lr_scheduler_warmup_steps: 50
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6977 | 1.0 | 640 | 1.5713 | 0.325 |
| 1.7006 | 2.0 | 1280 | 1.4543 | 0.4562 |
| 1.6725 | 3.0 | 1920 | 1.6124 | 0.4625 |
| 1.2312 | 4.0 | 2560 | 1.6711 | 0.5 |
| 0.6097 | 5.0 | 3200 | 1.8838 | 0.5312 |
| 1.264 | 6.0 | 3840 | 2.0933 | 0.4875 |
| 2.4064 | 7.0 | 4480 | 2.0628 | 0.5188 |
| 2.0741 | 8.0 | 5120 | 2.6505 | 0.4625 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3