metadata
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: msi-swinv2-tiny
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: validation
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.6404109589041096
- name: F1
type: f1
value: 0.5016949152542373
- name: Precision
type: precision
value: 0.6290224650880388
- name: Recall
type: recall
value: 0.41723721304873135
msi-swinv2-tiny
This model was trained from scratch on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.7208
- Accuracy: 0.6404
- F1: 0.5017
- Precision: 0.6290
- Recall: 0.4172
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-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.4992 | 1.0 | 2015 | 0.7072 | 0.6189 | 0.4517 | 0.6009 | 0.3619 |
| 0.4581 | 2.0 | 4031 | 0.7145 | 0.6383 | 0.4787 | 0.6387 | 0.3828 |
| 0.4229 | 3.0 | 6047 | 0.7146 | 0.6434 | 0.5077 | 0.6329 | 0.4238 |
| 0.4096 | 4.0 | 8060 | 0.7208 | 0.6404 | 0.5017 | 0.6290 | 0.4172 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0