metadata

license: apache-2.0
base_model: microsoft/resnet-50
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: resnet-50-finetuned-student_kaggle
    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: 1

resnet-50-finetuned-student_kaggle

This model is a fine-tuned version of microsoft/resnet-50 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.0012
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: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7142	1.0	47	0.6418	0.6101
0.3351	2.0	94	0.2597	0.8947
0.2574	3.0	141	0.1046	0.9780
0.1479	4.0	188	0.0616	0.9874
0.1284	5.0	235	0.0232	0.9953
0.077	6.0	282	0.0150	0.9953
0.103	7.0	329	0.0105	0.9984
0.0922	8.0	376	0.0094	0.9984
0.08	9.0	423	0.0056	1.0
0.0492	10.0	470	0.0045	1.0
0.0574	11.0	517	0.0043	1.0
0.0382	12.0	564	0.0023	1.0
0.0666	13.0	611	0.0022	1.0
0.0477	14.0	658	0.0022	1.0
0.0614	15.0	705	0.0023	1.0
0.0282	16.0	752	0.0014	1.0
0.0659	17.0	799	0.0016	1.0
0.0586	18.0	846	0.0010	1.0
0.0557	19.0	893	0.0013	1.0
0.07	20.0	940	0.0012	1.0

Framework versions

Transformers 4.40.1
Pytorch 2.2.1+cu121
Datasets 2.19.0
Tokenizers 0.19.1