resnet-50_rice-leaf-disease-augmented_tl_020125

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

• Loss: 0.7926
• Accuracy: 0.739

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.8935	1.0	250	1.5964	0.5395
1.4144	2.0	500	1.2223	0.6045
1.1814	3.0	750	1.0813	0.645
1.0714	4.0	1000	1.0132	0.6575
0.9906	5.0	1250	0.9498	0.6865
0.9428	6.0	1500	0.9129	0.7085
0.9026	7.0	1750	0.8716	0.722
0.8749	8.0	2000	0.8627	0.717
0.8501	9.0	2250	0.8443	0.726
0.828	10.0	2500	0.8177	0.737
0.8126	11.0	2750	0.8112	0.736
0.8036	12.0	3000	0.8031	0.744
0.79	13.0	3250	0.8043	0.735
0.7925	14.0	3500	0.7939	0.7385
0.7838	15.0	3750	0.7926	0.739

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0