jialicheng/unlearn_cifar10_resnet-50_random_label_8_87

87

This model is a fine-tuned version of microsoft/resnet-50 on the cifar10 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2222
• Accuracy: 0.94
• Dt Accuracy: 0.94
• Df Accuracy: 0.231
• Unlearn Overall Accuracy: 0.9179
• Unlearn Time: None

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: 0.001
• train_batch_size: 128
• eval_batch_size: 256
• seed: 87
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Overall Accuracy	Unlearn Overall Accuracy	Time
No log	1.0	391	0.3013	0.9403	0.2739	0.2739	None
0.7897	2.0	782	0.2529	0.9553	0.2521	0.2521	None
0.6946	3.0	1173	0.2355	0.9543	0.2538	0.2538	None
0.6439	4.0	1564	0.1967	0.9647	0.2380	0.2380	None
0.6439	5.0	1955	0.2254	0.9555	0.2519	0.2519	None
0.6041	6.0	2346	0.2282	0.9623	0.2417	0.2417	None
0.5736	7.0	2737	0.2296	0.9497	0.2608	0.2608	None
0.5436	8.0	3128	0.2229	0.9287	0.2920	0.2920	None
0.5261	9.0	3519	0.2179	0.903	0.3287	0.3287	None
0.5261	10.0	3910	0.2276	0.8598	0.3862	0.3862	None
0.4971	11.0	4301	0.2203	0.7798	0.4832	0.4832	None
0.4664	12.0	4692	0.2195	0.7123	0.5562	0.5562	None
0.4386	13.0	5083	0.2225	0.6055	0.6572	0.6572	None
0.4386	14.0	5474	0.2057	0.5495	0.7056	0.7056	None
0.4116	15.0	5865	0.2111	0.4738	0.7637	0.7637	None
0.3831	16.0	6256	0.2276	0.3568	0.8421	0.8421	None
0.3574	17.0	6647	0.2316	0.305	0.8737	0.8737	None
0.3365	18.0	7038	0.2420	0.2435	0.9064	0.9064	None
0.3365	19.0	7429	0.2353	0.223	0.9203	0.9203	None
0.3182	20.0	7820	0.2222	0.231	0.9179	0.9179	None

Framework versions

• Transformers 4.37.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.0
• Tokenizers 0.15.2