Yudsky's picture
End of training
7e89ce8 verified
metadata
library_name: transformers
license: apache-2.0
base_model: dennisjooo/emotion_classification
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: image_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: 0.6375

image_classification

This model is a fine-tuned version of dennisjooo/emotion_classification on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0965
  • Accuracy: 0.6375

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: 0.0001
  • train_batch_size: 32
  • eval_batch_size: 32
  • 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: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.1559 1.0 20 1.2425 0.5437
1.1243 2.0 40 1.1168 0.6312
1.0982 3.0 60 1.1411 0.6312
1.1412 4.0 80 1.1407 0.6625
1.1165 5.0 100 1.1910 0.6188
1.0722 6.0 120 1.1595 0.6125
1.1606 7.0 140 1.1311 0.6562
1.0792 8.0 160 1.1579 0.5938
1.0923 9.0 180 1.2815 0.5563
1.1298 10.0 200 1.0916 0.675

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1