metadata
license: apache-2.0
base_model: microsoft/swinv2-large-patch4-window12-192-22k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swinv2-large-patch4-window12-192-22k-augmented
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8723404255319149
swinv2-large-patch4-window12-192-22k-augmented
This model is a fine-tuned version of microsoft/swinv2-large-patch4-window12-192-22k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.3067
- Accuracy: 0.8723
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: 48
- eval_batch_size: 48
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 384
- 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 | 0.89 | 3 | 1.4847 | 0.5816 |
| No log | 1.78 | 6 | 0.9256 | 0.6950 |
| 1.2457 | 2.96 | 10 | 0.6017 | 0.7589 |
| 1.2457 | 3.85 | 13 | 0.3806 | 0.8723 |
| 1.2457 | 4.74 | 16 | 0.3866 | 0.8440 |
| 0.3656 | 5.93 | 20 | 0.3358 | 0.8794 |
| 0.3656 | 6.81 | 23 | 0.2803 | 0.8865 |
| 0.3656 | 8.0 | 27 | 0.3079 | 0.8723 |
| 0.2205 | 8.89 | 30 | 0.3067 | 0.8723 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.1+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1