metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: vit-base-aihub_model-v2
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: 0.8373493975903614
- name: Precision
type: precision
value: 0.8745971666076694
- name: Recall
type: recall
value: 0.7993336310123969
- name: F1
type: f1
value: 0.8036849674785987
vit-base-aihub_model-v2
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.1993
- Accuracy: 0.8373
- Precision: 0.8746
- Recall: 0.7993
- F1: 0.8037
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: 128
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 3 | 1.6294 | 0.6747 | 0.6434 | 0.6238 | 0.5944 |
| No log | 2.0 | 6 | 1.4495 | 0.7530 | 0.7776 | 0.7018 | 0.6875 |
| No log | 3.0 | 9 | 1.3163 | 0.8373 | 0.8563 | 0.7993 | 0.8022 |
| 1.5378 | 4.0 | 12 | 1.2327 | 0.8373 | 0.8736 | 0.7993 | 0.8035 |
| 1.5378 | 5.0 | 15 | 1.1993 | 0.8373 | 0.8746 | 0.7993 | 0.8037 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3