klasifikasiburung

This model is a fine-tuned version of RobertZ2011/resnet-18-birb on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.0186
• Accuracy: 0.7565
• Precision: 0.7631
• Recall: 0.7565
• F1: 0.7554

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
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
1.5955	1.0	188	1.4442	0.7235	0.7426	0.7235	0.7169
1.1224	2.0	376	1.2881	0.7458	0.7546	0.7458	0.7406
0.7778	3.0	564	1.1965	0.7501	0.7635	0.7501	0.7483
0.5573	4.0	752	1.1417	0.7565	0.7635	0.7565	0.7538
0.4231	5.0	940	1.1077	0.7584	0.7671	0.7584	0.7567
0.2878	6.0	1128	1.0893	0.7601	0.7716	0.7601	0.7597
0.2043	7.0	1316	1.0688	0.7591	0.7661	0.7591	0.7579
0.1326	8.0	1504	1.0687	0.7582	0.7653	0.7582	0.7565
0.0851	9.0	1692	1.0502	0.7598	0.7652	0.7598	0.7581
0.0807	10.0	1880	1.0318	0.7582	0.7644	0.7582	0.7569
0.0581	11.0	2068	1.0403	0.7572	0.7629	0.7572	0.7558
0.043	12.0	2256	1.0295	0.7565	0.7633	0.7565	0.7557
0.0379	13.0	2444	1.0271	0.7568	0.7636	0.7568	0.7557
0.0399	14.0	2632	1.0319	0.7558	0.7627	0.7558	0.7549
0.0447	15.0	2820	1.0186	0.7565	0.7631	0.7565	0.7554

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1