metadata
license: apache-2.0
base_model: facebook/deit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_40x_deit_base_n_f5
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8536585365853658
hushem_40x_deit_base_n_f5
This model is a fine-tuned version of facebook/deit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.4453
- Accuracy: 0.8537
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: 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0209 | 1.0 | 110 | 0.5124 | 0.8049 |
| 0.0043 | 2.0 | 220 | 0.6220 | 0.8049 |
| 0.0003 | 3.0 | 330 | 0.5631 | 0.8293 |
| 0.0001 | 4.0 | 440 | 0.6476 | 0.8049 |
| 0.0001 | 5.0 | 550 | 0.4557 | 0.8293 |
| 0.0001 | 6.0 | 660 | 0.5177 | 0.8780 |
| 0.0001 | 7.0 | 770 | 0.4360 | 0.8780 |
| 0.0 | 8.0 | 880 | 0.4399 | 0.8780 |
| 0.0 | 9.0 | 990 | 0.4439 | 0.8537 |
| 0.0 | 10.0 | 1100 | 0.4453 | 0.8537 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1