swin-tiny-patch4-window7-224-finetuned-plant-classification-finetuned-crops-classification

This model is a fine-tuned version of weightbot/swin-tiny-patch4-window7-224-finetuned-plant-classification on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.4259
• Accuracy: 0.8351

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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4225	1.0	183	0.3415	0.8703
0.4843	2.0	367	0.4024	0.8381
0.4679	3.0	550	0.4014	0.8385
0.4431	4.0	734	0.3986	0.8331
0.4263	5.0	917	0.4119	0.8351
0.3869	6.0	1101	0.4217	0.8278
0.3432	7.0	1284	0.4229	0.8305
0.3522	8.0	1468	0.4283	0.8347
0.3337	9.0	1651	0.4180	0.8301
0.2963	10.0	1835	0.4219	0.8366
0.3025	11.0	2018	0.4236	0.8335
0.2751	12.0	2202	0.4238	0.8366
0.271	13.0	2385	0.4314	0.8324
0.2416	14.0	2569	0.4229	0.8328
0.2507	14.96	2745	0.4259	0.8351

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1