metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- recall
model-index:
- name: vca
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Recall
type: recall
value: 0.7818181818181819
vca
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: 0.3844
- Recall: 0.7818
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: cosine_with_restarts
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Recall |
|---|---|---|---|---|
| No log | 1.0 | 11 | 0.4763 | 0.6987 |
| No log | 2.0 | 22 | 0.4438 | 0.6390 |
| No log | 3.0 | 33 | 0.4511 | 0.5870 |
| No log | 4.0 | 44 | 0.4084 | 0.7610 |
| No log | 5.0 | 55 | 0.3562 | 0.8078 |
| No log | 6.0 | 66 | 0.3844 | 0.7818 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.11.0
- Tokenizers 0.13.3