Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
convnext-tiny-224-finetuned-eurosat – AI Model by koray6 | AlphaNeural AI
You can deploy this model and start earning money today!
koray6
/
convnext-tiny-224-finetuned-eurosat
like
0
transformers
tensorboard
safetensors
convnext
image-classification
generated_from_trainer
facebook/convnext-tiny-224
finetune
apache-2.0
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
convnext-tiny-224-finetuned-eurosat
This model is a fine-tuned version of
facebook/convnext-tiny-224
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.3390
Accuracy: 0.9414
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: 64
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 256
optimizer: Use 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: 3
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
1.2852
1.0
57
0.9943
0.8728
0.5203
2.0
114
0.4478
0.9327
0.3931
3.0
171
0.3390
0.9414
Framework versions
Transformers 4.48.3
Pytorch 2.4.1+cu121
Datasets 2.14.5
Tokenizers 0.21.0
