metadata

library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: finetuned-arsenic
    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: 0.9986902423051736

finetuned-arsenic

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: 0.0039
Accuracy: 0.9987

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: 0.0002
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 4
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3535	0.1848	100	0.2896	0.8762
0.1869	0.3697	200	0.1380	0.9574
0.1594	0.5545	300	0.1052	0.9679
0.117	0.7394	400	0.0502	0.9836
0.0796	0.9242	500	0.0881	0.9673
0.0795	1.1091	600	0.0698	0.9751
0.0644	1.2939	700	0.0342	0.9895
0.054	1.4787	800	0.0344	0.9882
0.0776	1.6636	900	0.0292	0.9915
0.0143	1.8484	1000	0.0242	0.9928
0.0597	2.0333	1100	0.0132	0.9954
0.0285	2.2181	1200	0.0263	0.9928
0.0349	2.4030	1300	0.0070	0.9980
0.0164	2.5878	1400	0.0067	0.9987
0.0058	2.7726	1500	0.0119	0.9954
0.0013	2.9575	1600	0.0066	0.9987
0.0028	3.1423	1700	0.0052	0.9987
0.0028	3.3272	1800	0.0052	0.9987
0.0244	3.5120	1900	0.0264	0.9928
0.002	3.6969	2000	0.0025	0.9993
0.0054	3.8817	2100	0.0039	0.9987

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.19.1