metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: convnext-large-224-finetuned-eurosat
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: mio_Dataset2
split: validation
args: mio_Dataset2
metrics:
- name: Accuracy
type: accuracy
value: 0.7485380116959064
convnext-large-224-finetuned-eurosat
This model is a fine-tuned version of facebook/convnext-large-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.6440
- Accuracy: 0.7485
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 19 | 1.0763 | 0.4386 |
| No log | 2.0 | 38 | 0.9918 | 0.5322 |
| No log | 3.0 | 57 | 0.8919 | 0.6725 |
| No log | 4.0 | 76 | 0.8088 | 0.7135 |
| No log | 5.0 | 95 | 0.7502 | 0.7368 |
| No log | 6.0 | 114 | 0.7037 | 0.7310 |
| No log | 7.0 | 133 | 0.6792 | 0.7427 |
| No log | 8.0 | 152 | 0.6507 | 0.7368 |
| No log | 9.0 | 171 | 0.6440 | 0.7485 |
| No log | 10.0 | 190 | 0.6415 | 0.7485 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3