jialicheng/unlearn_cifar10_resnet-50_random_label_8_42

42

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: 0.2196
• Accuracy: 0.9397
• Dt Accuracy: 0.9397
• Df Accuracy: 0.215
• Unlearn Overall Accuracy: 0.9266
• 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: 42
• 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	0.2832	0.9417	0.2719	0.2719	None
0.7897	2.0	782	0.2481	0.955	0.2524	0.2524	None
0.6942	3.0	1173	0.2265	0.9547	0.2530	0.2530	None
0.6517	4.0	1564	0.2299	0.9655	0.2367	0.2367	None
0.6517	5.0	1955	0.1980	0.9655	0.2369	0.2369	None
0.6068	6.0	2346	0.2085	0.9573	0.2494	0.2494	None
0.5709	7.0	2737	0.2066	0.9513	0.2588	0.2588	None
0.5487	8.0	3128	0.2078	0.9387	0.2773	0.2773	None
0.5276	9.0	3519	0.2003	0.9245	0.2983	0.2983	None
0.5276	10.0	3910	0.1973	0.8858	0.3524	0.3524	None
0.4966	11.0	4301	0.2045	0.7837	0.4788	0.4788	None
0.474	12.0	4692	0.2115	0.7365	0.5311	0.5311	None
0.4413	13.0	5083	0.2146	0.6245	0.6401	0.6401	None
0.4413	14.0	5474	0.2238	0.5218	0.7257	0.7257	None
0.4188	15.0	5865	0.2254	0.433	0.7903	0.7903	None
0.3852	16.0	6256	0.2238	0.3718	0.8325	0.8325	None
0.3574	17.0	6647	0.2213	0.3207	0.8646	0.8646	None
0.3372	18.0	7038	0.2134	0.2675	0.8982	0.8982	None
0.3372	19.0	7429	0.2149	0.2445	0.9113	0.9113	None
0.3145	20.0	7820	0.2196	0.215	0.9266	0.9266	None

Framework versions

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