---
library_name: transformers
license: apache-2.0
base_model: microsoft/swinv2-base-patch4-window8-256
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: swinv2-base-patch4-window8-256-dmae-humeda-DAV15
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# swinv2-base-patch4-window8-256-dmae-humeda-DAV15

This model is a fine-tuned version of [microsoft/swinv2-base-patch4-window8-256](https://huggingface.co/microsoft/swinv2-base-patch4-window8-256) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8423
- Accuracy: 0.75

## 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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 42

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Accuracy |
|:-------------:|:-------:|:----:|:---------------:|:--------:|
| No log        | 0.8696  | 5    | 1.5972          | 0.3077   |
| 6.7562        | 1.8696  | 10   | 1.5357          | 0.3077   |
| 6.7562        | 2.8696  | 15   | 1.4954          | 0.4038   |
| 6.2842        | 3.8696  | 20   | 1.4612          | 0.3462   |
| 6.2842        | 4.8696  | 25   | 1.3875          | 0.3269   |
| 4.9858        | 5.8696  | 30   | 1.3370          | 0.3462   |
| 4.9858        | 6.8696  | 35   | 1.2739          | 0.4423   |
| 3.5596        | 7.8696  | 40   | 1.1774          | 0.4808   |
| 3.5596        | 8.8696  | 45   | 1.1214          | 0.4808   |
| 2.6814        | 9.8696  | 50   | 1.0999          | 0.5192   |
| 2.6814        | 10.8696 | 55   | 1.1773          | 0.4615   |
| 2.3236        | 11.8696 | 60   | 0.9874          | 0.5192   |
| 2.3236        | 12.8696 | 65   | 1.1124          | 0.5      |
| 1.8037        | 13.8696 | 70   | 0.8936          | 0.6538   |
| 1.8037        | 14.8696 | 75   | 1.2064          | 0.4423   |
| 1.6474        | 15.8696 | 80   | 0.8423          | 0.75     |
| 1.6474        | 16.8696 | 85   | 1.0134          | 0.6346   |
| 1.5505        | 17.8696 | 90   | 0.8965          | 0.6923   |
| 1.5505        | 18.8696 | 95   | 0.9215          | 0.6538   |
| 1.2697        | 19.8696 | 100  | 1.0155          | 0.6154   |
| 1.2697        | 20.8696 | 105  | 0.8500          | 0.7115   |
| 1.1783        | 21.8696 | 110  | 0.9573          | 0.6538   |
| 1.1783        | 22.8696 | 115  | 0.8915          | 0.6923   |
| 1.0235        | 23.8696 | 120  | 0.9831          | 0.6538   |
| 1.0235        | 24.8696 | 125  | 0.9464          | 0.6538   |
| 0.9706        | 25.8696 | 130  | 0.9413          | 0.6923   |
| 0.9706        | 26.8696 | 135  | 1.0249          | 0.6346   |
| 0.9409        | 27.8696 | 140  | 0.9754          | 0.6538   |
| 0.9409        | 28.8696 | 145  | 0.9530          | 0.7115   |
| 0.9447        | 29.8696 | 150  | 1.0266          | 0.6538   |
| 0.9447        | 30.8696 | 155  | 1.0819          | 0.6538   |
| 0.8352        | 31.8696 | 160  | 0.9922          | 0.6923   |
| 0.8352        | 32.8696 | 165  | 0.9755          | 0.6923   |
| 0.8055        | 33.8696 | 170  | 0.9768          | 0.7115   |
| 0.8055        | 34.8696 | 175  | 0.9950          | 0.6923   |
| 0.7481        | 35.8696 | 180  | 1.0135          | 0.6923   |
| 0.7481        | 36.8696 | 185  | 1.0168          | 0.6923   |
| 0.7483        | 37.8696 | 190  | 1.0091          | 0.6923   |
| 0.7483        | 38.8696 | 195  | 1.0055          | 0.6923   |
| 0.8145        | 39.8696 | 200  | 1.0040          | 0.6923   |
| 0.8145        | 40.8696 | 205  | 1.0039          | 0.6923   |
| 0.7501        | 41.8696 | 210  | 1.0038          | 0.6923   |


### Framework versions

- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0