resnet-50-finetuned-resnet50_0831

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

• Loss: 0.0862
• Accuracy: 0.9764

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
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.9066	1.0	223	0.8770	0.6659
0.5407	2.0	446	0.4251	0.7867
0.3614	3.0	669	0.2009	0.9390
0.3016	4.0	892	0.1362	0.9582
0.2358	5.0	1115	0.1139	0.9676
0.247	6.0	1338	0.1081	0.9698
0.2135	7.0	1561	0.1027	0.9720
0.2043	8.0	1784	0.1026	0.9695
0.2165	9.0	2007	0.0957	0.9733
0.1983	10.0	2230	0.0936	0.9736
0.2116	11.0	2453	0.0949	0.9736
0.2341	12.0	2676	0.0905	0.9755
0.2004	13.0	2899	0.0901	0.9739
0.1956	14.0	3122	0.0877	0.9755
0.1668	15.0	3345	0.0847	0.9764
0.1855	16.0	3568	0.0850	0.9755
0.18	17.0	3791	0.0897	0.9745
0.1772	18.0	4014	0.0852	0.9755
0.1881	19.0	4237	0.0845	0.9764
0.2145	20.0	4460	0.0862	0.9764

Framework versions

• Transformers 4.21.1
• Pytorch 1.12.1
• Datasets 2.4.0
• Tokenizers 0.12.1