FGVCBoeing737

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: 0.9134
• Accuracy: 0.8239

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• num_epochs: 20
• label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.2723	1.0	63	2.3126	0.2590
2.2044	2.0	126	2.2263	0.4819
2.0267	3.0	189	2.0182	0.5422
1.6565	4.0	252	1.6908	0.5904
1.3822	5.0	315	1.4238	0.6717
1.1317	6.0	378	1.2162	0.7169
1.0107	7.0	441	1.0833	0.7801
0.8907	8.0	504	1.0006	0.7982
0.7858	9.0	567	0.9280	0.8163
0.7806	10.0	630	0.9243	0.8373
0.6625	11.0	693	0.9156	0.8223
0.6463	12.0	756	0.8927	0.8404
0.7098	13.0	819	0.8751	0.8434
0.6272	14.0	882	0.8363	0.8464
0.6315	15.0	945	0.8752	0.8434
0.6549	16.0	1008	0.8558	0.8313
0.6195	17.0	1071	0.8487	0.8404
0.5881	18.0	1134	0.8336	0.8614
0.6305	19.0	1197	0.8696	0.8283
0.6076	20.0	1260	0.8685	0.8343

Framework versions

• Transformers 5.16.1
• Pytorch 2.11.0+cu128
• Datasets 4.8.5
• Tokenizers 0.23.1