jialicheng/unlearn_cifar10_resnet-34_random_label_8_42

42

This model is a fine-tuned version of microsoft/resnet-34 on the cifar10 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2863
• Accuracy: 0.9317
• Dt Accuracy: 0.9317
• Df Accuracy: 0.9103
• Unlearn Overall Accuracy: 0.3171
• 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: 32
• 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
1.4072	1.0	1563	1.0172	0.664	0	0	None
1.2027	2.0	3126	0.7016	0.779	0.4594	0.4594	None
1.0832	3.0	4689	0.6236	0.8005	0.4402	0.4402	None
0.9889	4.0	6252	0.5985	0.8193	0.4227	0.4227	None
0.9204	5.0	7815	0.4907	0.861	0.3769	0.3769	None
0.8778	6.0	9378	0.4286	0.8828	0.3510	0.3510	None
0.8325	7.0	10941	0.4126	0.894	0.3365	0.3365	None
0.7979	8.0	12504	0.3926	0.8902	0.3417	0.3417	None
0.7779	9.0	14067	0.3737	0.9058	0.3216	0.3216	None
0.7473	10.0	15630	0.3414	0.9123	0.3130	0.3130	None
0.7116	11.0	17193	0.3312	0.9185	0.3045	0.3045	None
0.6857	12.0	18756	0.3128	0.9217	0.3002	0.3002	None
0.6821	13.0	20319	0.3064	0.9185	0.3050	0.3050	None
0.6513	14.0	21882	0.3067	0.9255	0.2950	0.2950	None
0.6267	15.0	23445	0.3125	0.9087	0.3186	0.3186	None
0.6004	16.0	25008	0.3138	0.918	0.3058	0.3058	None
0.5819	17.0	26571	0.2932	0.9215	0.3012	0.3012	None
0.5722	18.0	28134	0.2899	0.9195	0.3040	0.3040	None
0.5395	19.0	29697	0.2762	0.9197	0.3038	0.3038	None
0.5441	20.0	31260	0.2863	0.9103	0.3171	0.3171	None

Framework versions

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