metadata
license: apache-2.0
base_model: microsoft/swinv2-tiny-patch4-window8-256
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: swinv2-tiny-patch4-window8-256-Kontur-competition-1.3K
results: []
swinv2-tiny-patch4-window8-256-Kontur-competition-1.3K
This model is a fine-tuned version of microsoft/swinv2-tiny-patch4-window8-256 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0416
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: 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 |
|---|---|---|---|
| No log | 0.84 | 4 | 0.6306 |
| No log | 1.89 | 9 | 0.4185 |
| 0.6216 | 2.95 | 14 | 0.2351 |
| 0.6216 | 4.0 | 19 | 0.1235 |
| 0.3128 | 4.84 | 23 | 0.0767 |
| 0.3128 | 5.89 | 28 | 0.0676 |
| 0.1492 | 6.95 | 33 | 0.0416 |
| 0.1492 | 8.0 | 38 | 0.0493 |
| 0.1011 | 8.42 | 40 | 0.0504 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2