metadata

tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: clip-vit-large-patch14-finetuned-fruits-360_vitlarge
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: fruits-360-original-size
          split: validation
          args: fruits-360-original-size
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9845857418111753

clip-vit-large-patch14-finetuned-fruits-360_vitlarge

This model is a fine-tuned version of openai/clip-vit-large-patch14 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.0743
Accuracy: 0.9846

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: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.0674	0.98	48	0.6958	0.7476
0.5475	1.99	97	0.4484	0.8542
0.4065	2.99	146	0.2249	0.9274
0.2386	4.0	195	0.1154	0.9724
0.197	4.92	240	0.0743	0.9846

Framework versions

Transformers 4.27.3
Pytorch 1.13.1+cu116
Datasets 2.10.1
Tokenizers 0.13.2