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: 0.1369
• Accuracy: 0.95

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: 4e-05
• train_batch_size: 8
• 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
• lr_scheduler_warmup_steps: 500
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	70	0.5422	0.8571
No log	2.0	140	0.5221	0.8786
No log	3.0	210	0.4977	0.8571
No log	4.0	280	0.4617	0.8786
No log	5.0	350	0.3932	0.9143
No log	6.0	420	0.3411	0.9143
No log	7.0	490	0.2884	0.9143
0.4971	8.0	560	0.2429	0.9286
0.4971	9.0	630	0.2151	0.9429
0.4971	10.0	700	0.1962	0.9286
0.4971	11.0	770	0.1727	0.9357
0.4971	12.0	840	0.1676	0.95
0.4971	13.0	910	0.1764	0.9286
0.4971	14.0	980	0.1565	0.9429
0.2878	15.0	1050	0.1578	0.9429
0.2878	16.0	1120	0.1577	0.9429
0.2878	17.0	1190	0.1393	0.9429
0.2878	18.0	1260	0.1472	0.9429
0.2878	19.0	1330	0.1315	0.95
0.2878	20.0	1400	0.1369	0.95

Framework versions

• Transformers 4.47.1
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0