README.md

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: 0.49375

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: 1.3840
• Accuracy: 0.4938

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: 0.00012
• 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_ratio: 0.1
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	10	2.0302	0.2562
No log	2.0	20	1.8255	0.4188
No log	3.0	30	1.5799	0.3688
No log	4.0	40	1.4107	0.5062
No log	5.0	50	1.3364	0.5375
No log	6.0	60	1.3316	0.5125
No log	7.0	70	1.3021	0.5375
No log	8.0	80	1.2880	0.5375
No log	9.0	90	1.2682	0.5188
No log	10.0	100	1.2936	0.5125
No log	11.0	110	1.3376	0.5
No log	12.0	120	1.2905	0.5563
No log	13.0	130	1.2518	0.5062
No log	14.0	140	1.2633	0.5437
No log	15.0	150	1.4656	0.4313
No log	16.0	160	1.2513	0.575
No log	17.0	170	1.3498	0.4938
No log	18.0	180	1.3155	0.5062
No log	19.0	190	1.3673	0.5
No log	20.0	200	1.3840	0.4938

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.1