Crop_Disease_model

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.4412
• Accuracy: 0.6533

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
2.9809	0.9787	23	2.9338	0.144
2.7916	2.0	47	2.6349	0.4693
2.3529	2.9787	70	2.3237	0.4973
2.0897	4.0	94	2.0598	0.532
1.8713	4.9787	117	1.8989	0.5453
1.6276	6.0	141	1.7701	0.584
1.5641	6.9787	164	1.6756	0.612
1.4144	8.0	188	1.6190	0.62
1.3294	8.9787	211	1.5457	0.6373
1.2586	10.0	235	1.4913	0.644
1.2052	10.9787	258	1.4816	0.6227
1.1644	12.0	282	1.4547	0.6387
1.1158	12.9787	305	1.4392	0.6453
1.0931	14.0	329	1.4277	0.6507
1.0969	14.6809	345	1.4412	0.6533

Framework versions

• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.19.2
• Tokenizers 0.19.1