metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: my_isl_model
    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: 0.7283950617283951

my_isl_model

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: 1.9092
Accuracy: 0.7284

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.1292	0.96	11	3.0256	0.2593
2.9426	2.0	23	2.7796	0.2716
2.706	2.96	34	2.5462	0.4321
2.5389	4.0	46	2.4454	0.4568
2.3638	4.96	57	2.2169	0.6914
2.1862	6.0	69	2.1349	0.6296
2.0459	6.96	80	2.1135	0.6049
1.9912	8.0	92	1.9757	0.7531
1.9504	8.96	103	1.9073	0.7407
1.942	9.57	110	1.9092	0.7284

Framework versions

Transformers 4.27.4
Pytorch 2.0.0+cu118
Datasets 2.11.0
Tokenizers 0.13.3