resnet-50-finetuned-eurosat

This model is a fine-tuned version of MF21377197/resnet-50-finetuned-eurosat on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 21.6578
• Accuracy: 0.5284

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: 1e-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: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
19.4471	1.0	351	25.2381	0.4514
14.378	2.0	703	24.5923	0.4594
20.7257	3.0	1055	24.3360	0.4706
23.0579	4.0	1407	17.9277	0.479
16.7616	5.0	1758	24.0013	0.4808
13.2407	6.0	2110	16.8144	0.4888
12.5439	7.0	2462	10.8161	0.496
10.301	8.0	2814	14.1573	0.5066
18.2068	9.0	3165	15.7831	0.5054
5.7088	10.0	3517	14.3309	0.512
18.9725	11.0	3869	21.6578	0.5284
16.9049	11.97	4212	12.9670	0.5204

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2