metadata

base_model: openai/clip-vit-base-patch32
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: ktp-kk-crop
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.945054945054945

ktp-kk-crop

This model is a fine-tuned version of openai/clip-vit-base-patch32 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.2528
Accuracy: 0.9451

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
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.9655	7	0.5985	0.6154
No log	1.9310	14	0.1681	0.9341
0.4711	2.8966	21	0.2271	0.9011
0.4711	4.0	29	0.8009	0.7473
0.3768	4.9655	36	0.1365	0.9560
0.3768	5.9310	43	0.1176	0.9780
0.069	6.8966	50	0.0880	0.9890
0.069	8.0	58	0.6839	0.9011
0.0212	8.9655	65	0.3376	0.9451
0.0212	9.9310	72	0.2240	0.9670
0.0201	10.8966	79	0.5612	0.9341
0.0201	12.0	87	0.2688	0.9560
0.0039	12.9655	94	0.1710	0.9780
0.0039	13.9310	101	0.3437	0.9560
0.0293	14.8966	108	0.2446	0.9670
0.0293	16.0	116	0.1507	0.9780
0.0009	16.9655	123	0.2032	0.9670
0.0009	17.9310	130	0.2481	0.9451
0.0	18.8966	137	0.2608	0.9451
0.0	20.0	145	0.2611	0.9451
0.0	20.9655	152	0.2579	0.9451
0.0	21.9310	159	0.2554	0.9451
0.0	22.8966	166	0.2536	0.9451
0.0	24.0	174	0.2528	0.9451
0.0	24.1379	175	0.2528	0.9451

Framework versions

Transformers 4.41.2
Pytorch 2.1.2
Datasets 2.19.2
Tokenizers 0.19.1