metadata

license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: urinary_carcinoma_classifier_g001
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train[:23]
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.6

urinary_carcinoma_classifier_g001

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: 0.6827
Accuracy: 0.6

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: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	1	0.7147	0.4
No log	2.0	2	0.7114	0.4
No log	3.0	3	0.6968	0.2
No log	4.0	4	0.7055	0.4
No log	5.0	5	0.6741	0.4
No log	6.0	6	0.6580	0.6
No log	7.0	7	0.6092	0.6
No log	8.0	8	0.6200	0.6
No log	9.0	9	0.6139	0.6
0.3094	10.0	10	0.5969	0.6
0.3094	11.0	11	0.5677	0.6
0.3094	12.0	12	0.6021	0.6
0.3094	13.0	13	0.6189	0.6
0.3094	14.0	14	0.6054	0.6
0.3094	15.0	15	0.6240	0.6
0.3094	16.0	16	0.5388	0.6
0.3094	17.0	17	0.5320	0.6
0.3094	18.0	18	0.5973	0.6
0.3094	19.0	19	0.5981	0.8
0.1723	20.0	20	0.6531	0.6
0.1723	21.0	21	0.6246	0.6
0.1723	22.0	22	0.6718	0.6
0.1723	23.0	23	0.6692	0.6
0.1723	24.0	24	0.6537	0.6
0.1723	25.0	25	0.4650	0.6
0.1723	26.0	26	0.6873	0.6
0.1723	27.0	27	0.6461	0.6
0.1723	28.0	28	0.5876	0.8
0.1723	29.0	29	0.4898	0.6
0.1049	30.0	30	0.6827	0.6

Framework versions

Transformers 4.42.4
Pytorch 2.3.1
Datasets 2.20.0
Tokenizers 0.19.1