metadata

library_name: transformers
license: apache-2.0
base_model: microsoft/resnet-50
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: cat_dog_classifier_with_small_datasest
    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: 0.8571428571428571

cat_dog_classifier_with_small_datasest

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: 0.5540
Accuracy: 0.8571

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: 4
eval_batch_size: 8
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	140	0.5149	0.8143
No log	2.0	280	0.2519	0.9214
No log	3.0	420	0.3596	0.85
0.3145	4.0	560	0.2661	0.9214
0.3145	5.0	700	0.2600	0.8929
0.3145	6.0	840	0.1840	0.9286
0.3145	7.0	980	0.3145	0.9071
0.27	8.0	1120	0.2121	0.9214
0.27	9.0	1260	0.3926	0.8571
0.27	10.0	1400	0.3488	0.8786
0.2426	11.0	1540	0.2437	0.9071
0.2426	12.0	1680	0.2497	0.9
0.2426	13.0	1820	0.1663	0.9214
0.2426	14.0	1960	0.2132	0.9357
0.2556	15.0	2100	0.3464	0.8714
0.2556	16.0	2240	0.3063	0.9071
0.2556	17.0	2380	0.2992	0.9071
0.261	18.0	2520	0.3765	0.8857
0.261	19.0	2660	0.1396	0.9286
0.261	20.0	2800	0.5540	0.8571

Framework versions

Transformers 4.47.1
Pytorch 2.4.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0