metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: emotion_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: 0.5375
emotion_classification
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.3694
- Accuracy: 0.5375
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
- lr_scheduler_warmup_steps: 9
- num_epochs: 18
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 10 | 2.0629 | 0.1437 |
| No log | 2.0 | 20 | 2.0123 | 0.275 |
| No log | 3.0 | 30 | 1.9333 | 0.3312 |
| No log | 4.0 | 40 | 1.8060 | 0.3812 |
| No log | 5.0 | 50 | 1.7009 | 0.3563 |
| No log | 6.0 | 60 | 1.6149 | 0.4188 |
| No log | 7.0 | 70 | 1.5948 | 0.4437 |
| No log | 8.0 | 80 | 1.5391 | 0.5 |
| No log | 9.0 | 90 | 1.4770 | 0.4688 |
| No log | 10.0 | 100 | 1.5026 | 0.5 |
| No log | 11.0 | 110 | 1.4644 | 0.4437 |
| No log | 12.0 | 120 | 1.4115 | 0.5125 |
| No log | 13.0 | 130 | 1.4216 | 0.4813 |
| No log | 14.0 | 140 | 1.4086 | 0.5 |
| No log | 15.0 | 150 | 1.4093 | 0.5 |
| No log | 16.0 | 160 | 1.3891 | 0.4875 |
| No log | 17.0 | 170 | 1.3754 | 0.4938 |
| No log | 18.0 | 180 | 1.3779 | 0.5188 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1