metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: emotion_classifier
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: 0.4125
emotion_classifier
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: 1.6092
- Accuracy: 0.4125
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 40 | 2.0750 | 0.15 |
| No log | 2.0 | 80 | 2.0046 | 0.1875 |
| No log | 3.0 | 120 | 1.8909 | 0.3063 |
| No log | 4.0 | 160 | 1.7726 | 0.3563 |
| No log | 5.0 | 200 | 1.6970 | 0.3438 |
| No log | 6.0 | 240 | 1.6562 | 0.3937 |
| No log | 7.0 | 280 | 1.6269 | 0.4062 |
| No log | 8.0 | 320 | 1.6092 | 0.4125 |
| No log | 9.0 | 360 | 1.6012 | 0.4125 |
| No log | 10.0 | 400 | 1.5955 | 0.4125 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.5.1+cpu
- Datasets 3.2.0
- Tokenizers 0.21.0