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_g
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train[:18]
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 1

urinary_carcinoma_classifier_g

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: 0.1879
Accuracy: 1.0

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	0.6847	0.5
No log	2.0	2	0.6741	0.75
No log	3.0	3	0.6468	0.75
No log	4.0	4	0.6268	0.75
No log	5.0	5	0.6053	0.75
No log	6.0	6	0.5515	0.75
No log	7.0	7	0.5259	1.0
No log	8.0	8	0.4513	1.0
No log	9.0	9	0.4493	1.0
0.1427	10.0	10	0.3979	1.0
0.1427	11.0	11	0.4203	1.0
0.1427	12.0	12	0.3690	1.0
0.1427	13.0	13	0.2793	1.0
0.1427	14.0	14	0.3143	1.0
0.1427	15.0	15	0.2536	1.0
0.1427	16.0	16	0.2509	1.0
0.1427	17.0	17	0.2619	1.0
0.1427	18.0	18	0.2187	1.0
0.1427	19.0	19	0.3027	1.0
0.055	20.0	20	0.2662	1.0
0.055	21.0	21	0.3630	0.75
0.055	22.0	22	0.4297	0.75
0.055	23.0	23	0.3473	0.75
0.055	24.0	24	0.4058	0.75
0.055	25.0	25	0.3959	0.75
0.055	26.0	26	0.2548	1.0
0.055	27.0	27	0.1835	1.0
0.055	28.0	28	0.1909	1.0
0.055	29.0	29	0.4000	0.75
0.029	30.0	30	0.1879	1.0

Framework versions

Transformers 4.42.4
Pytorch 2.3.1
Datasets 2.20.0
Tokenizers 0.19.1