metadata

license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: emotion_classification_v1.1
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train[:5000]
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.575
          - name: Precision
            type: precision
            value: 0.6064414347689876
          - name: Recall
            type: recall
            value: 0.575
          - name: F1
            type: f1
            value: 0.5730570699748332

emotion_classification_v1.1

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: 1.2449
Accuracy: 0.575
Precision: 0.6064
Recall: 0.575
F1: 0.5731

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: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	40	1.8287	0.325	0.2995	0.325	0.2695
No log	2.0	80	1.5621	0.475	0.4171	0.475	0.4104
No log	3.0	120	1.4485	0.4188	0.3786	0.4188	0.3710
No log	4.0	160	1.4040	0.4313	0.5179	0.4313	0.3963
No log	5.0	200	1.3333	0.4938	0.5016	0.4938	0.4654
No log	6.0	240	1.3076	0.4688	0.4698	0.4688	0.4437
No log	7.0	280	1.3531	0.4813	0.5289	0.4813	0.4834
No log	8.0	320	1.3118	0.4688	0.4606	0.4688	0.4619
No log	9.0	360	1.3326	0.4938	0.5629	0.4938	0.4744
No log	10.0	400	1.2693	0.4938	0.4825	0.4938	0.4777
No log	11.0	440	1.2310	0.55	0.5747	0.55	0.5441
No log	12.0	480	1.2673	0.5375	0.5418	0.5375	0.5316
1.0804	13.0	520	1.3161	0.5125	0.5321	0.5125	0.5048
1.0804	14.0	560	1.2517	0.55	0.5550	0.55	0.5430
1.0804	15.0	600	1.3344	0.5	0.5023	0.5	0.4848

Framework versions

Transformers 4.41.2
Pytorch 2.3.0
Datasets 2.19.1
Tokenizers 0.19.1