jialicheng/cifar10_resnet-18

resnet-18

This model is a fine-tuned version of microsoft/resnet-18 on the cifar10 dataset. It achieves the following results on the evaluation set:

• Loss: nan
• Accuracy: 0.1

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: 1e-05
• 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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	333	nan	0.1
0.0	2.0	666	nan	0.1
0.0	3.0	999	nan	0.1
0.0	4.0	1332	nan	0.1
0.0	5.0	1665	nan	0.1
0.0	6.0	1998	nan	0.1
0.0	7.0	2331	nan	0.1
0.0	8.0	2664	nan	0.1
0.0	9.0	2997	nan	0.1
0.0	10.0	3330	nan	0.1
0.0	11.0	3663	nan	0.1
0.0	12.0	3996	nan	0.1
0.0	13.0	4329	nan	0.1
0.0	14.0	4662	nan	0.1
0.0	15.0	4995	nan	0.1
0.0	16.0	5328	nan	0.1
0.0	17.0	5661	nan	0.1
0.0	18.0	5994	nan	0.1
0.0	19.0	6327	nan	0.1
0.0	20.0	6660	nan	0.1
0.0	21.0	6993	nan	0.1
0.0	22.0	7326	nan	0.1
0.0	23.0	7659	nan	0.1
0.0	24.0	7992	nan	0.1
0.0	25.0	8325	nan	0.1
0.0	26.0	8658	nan	0.1
0.0	27.0	8991	nan	0.1
0.0	28.0	9324	nan	0.1
0.0	29.0	9657	nan	0.1
0.0	30.0	9990	nan	0.1
0.0	31.0	10323	nan	0.1
0.0	32.0	10656	nan	0.1
0.0	33.0	10989	nan	0.1
0.0	34.0	11322	nan	0.1
0.0	35.0	11655	nan	0.1
0.0	36.0	11988	nan	0.1
0.0	37.0	12321	nan	0.1
0.0	38.0	12654	nan	0.1
0.0	39.0	12987	nan	0.1
0.0	40.0	13320	nan	0.1
0.0	41.0	13653	nan	0.1
0.0	42.0	13986	nan	0.1
0.0	43.0	14319	nan	0.1
0.0	44.0	14652	nan	0.1
0.0	45.0	14985	nan	0.1
0.0	46.0	15318	nan	0.1
0.0	47.0	15651	nan	0.1
0.0	48.0	15984	nan	0.1
0.0	49.0	16317	nan	0.1
0.0	50.0	16650	nan	0.1
0.0	51.0	16983	nan	0.1
0.0	52.0	17316	nan	0.1
0.0	53.0	17649	nan	0.1
0.0	54.0	17982	nan	0.1
0.0	55.0	18315	nan	0.1
0.0	56.0	18648	nan	0.1
0.0	57.0	18981	nan	0.1
0.0	58.0	19314	nan	0.1
0.0	59.0	19647	nan	0.1
0.0	60.0	19980	nan	0.1
0.0	61.0	20313	nan	0.1
0.0	62.0	20646	nan	0.1
0.0	63.0	20979	nan	0.1
0.0	64.0	21312	nan	0.1
0.0	65.0	21645	nan	0.1
0.0	66.0	21978	nan	0.1
0.0	67.0	22311	nan	0.1
0.0	68.0	22644	nan	0.1
0.0	69.0	22977	nan	0.1
0.0	70.0	23310	nan	0.1
0.0	71.0	23643	nan	0.1
0.0	72.0	23976	nan	0.1
0.0	73.0	24309	nan	0.1
0.0	74.0	24642	nan	0.1
0.0	75.0	24975	nan	0.1
0.0	76.0	25308	nan	0.1
0.0	77.0	25641	nan	0.1
0.0	78.0	25974	nan	0.1
0.0	79.0	26307	nan	0.1
0.0	80.0	26640	nan	0.1
0.0	81.0	26973	nan	0.1
0.0	82.0	27306	nan	0.1
0.0	83.0	27639	nan	0.1
0.0	84.0	27972	nan	0.1
0.0	85.0	28305	nan	0.1
0.0	86.0	28638	nan	0.1
0.0	87.0	28971	nan	0.1
0.0	88.0	29304	nan	0.1
0.0	89.0	29637	nan	0.1
0.0	90.0	29970	nan	0.1
0.0	91.0	30303	nan	0.1
0.0	92.0	30636	nan	0.1
0.0	93.0	30969	nan	0.1
0.0	94.0	31302	nan	0.1
0.0	95.0	31635	nan	0.1
0.0	96.0	31968	nan	0.1
0.0	97.0	32301	nan	0.1
0.0	98.0	32634	nan	0.1
0.0	99.0	32967	nan	0.1
0.0	100.0	33300	nan	0.1

Framework versions

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