metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- rock-glacier-dataset
metrics:
- accuracy
model-index:
- name: skynet
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: rock-glacier-dataset
type: rock-glacier-dataset
config: image-classification
split: train
args: image-classification
metrics:
- name: Accuracy
type: accuracy
value: 0.9688888888888889
skynet
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the rock-glacier-dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.1080
- Accuracy: 0.9689
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4521 | 0.3 | 75 | 0.4436 | 0.824 |
| 0.3561 | 0.61 | 150 | 0.2802 | 0.9244 |
| 0.2306 | 0.91 | 225 | 0.2124 | 0.9307 |
| 0.1621 | 1.21 | 300 | 0.1695 | 0.9458 |
| 0.1396 | 1.52 | 375 | 0.1589 | 0.9476 |
| 0.1157 | 1.82 | 450 | 0.1342 | 0.9547 |
| 0.0707 | 2.13 | 525 | 0.1342 | 0.96 |
| 0.0578 | 2.43 | 600 | 0.1294 | 0.9591 |
| 0.0687 | 2.73 | 675 | 0.1285 | 0.9609 |
| 0.0431 | 3.04 | 750 | 0.1066 | 0.9671 |
| 0.0249 | 3.34 | 825 | 0.1069 | 0.968 |
| 0.0614 | 3.64 | 900 | 0.1073 | 0.968 |
| 0.0469 | 3.95 | 975 | 0.1080 | 0.9689 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2