metadata

tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
  - f1
model-index:
  - name: dit-base-finetuned-brs
    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: 0.8235294117647058
          - name: F1
            type: f1
            value: 0.8421052631578948

dit-base-finetuned-brs

This model is a fine-tuned version of microsoft/dit-base on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 1.2679
Accuracy: 0.8235
F1: 0.8421
Precision (ppv): 0.8889
Recall (sensitivity): 0.8
Specificity: 0.8571
Npv: 0.75
Auc: 0.8286

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: 1e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision (ppv)	Recall (sensitivity)	Specificity	Npv	Auc
0.6951	6.25	100	0.7100	0.4706	0.4	0.6	0.3	0.7143	0.4167	0.5071
0.5094	12.49	200	0.6511	0.5294	0.6	0.6	0.6	0.4286	0.4286	0.5143
0.5338	18.74	300	0.6113	0.6471	0.6667	0.75	0.6	0.7143	0.5556	0.6571
0.444	24.98	400	0.7057	0.6471	0.625	0.8333	0.5	0.8571	0.5455	0.6786
0.3877	31.25	500	0.7836	0.7059	0.7368	0.7778	0.7	0.7143	0.625	0.7071
0.6238	37.49	600	0.8340	0.7059	0.6667	1.0	0.5	1.0	0.5833	0.75
0.6856	43.74	700	1.0278	0.7647	0.8000	0.8	0.8	0.7143	0.7143	0.7571
0.487	49.98	800	1.0279	0.7647	0.7778	0.875	0.7	0.8571	0.6667	0.7786
0.4039	56.25	900	0.9028	0.7647	0.7778	0.875	0.7	0.8571	0.6667	0.7786
0.2214	62.49	1000	0.6894	0.8235	0.8235	1.0	0.7	1.0	0.7	0.85
0.7441	68.74	1100	1.1261	0.8235	0.8421	0.8889	0.8	0.8571	0.75	0.8286
0.5714	74.98	1200	0.8956	0.8235	0.8235	1.0	0.7	1.0	0.7	0.85
0.3093	81.25	1300	1.2498	0.7059	0.7059	0.8571	0.6	0.8571	0.6	0.7286
0.6528	87.49	1400	1.6744	0.7647	0.7778	0.875	0.7	0.8571	0.6667	0.7786
0.3314	93.74	1500	1.8034	0.7059	0.7059	0.8571	0.6	0.8571	0.6	0.7286
0.3617	99.98	1600	1.2679	0.8235	0.8421	0.8889	0.8	0.8571	0.75	0.8286

Framework versions

Transformers 4.23.1
Pytorch 1.12.1+cu113
Datasets 2.6.1
Tokenizers 0.13.1