vit-SUPER02 / README.md
GGital's picture
Model save
835d007 verified
---
license: apache-2.0
base_model: google/vit-large-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- f1
model-index:
- name: vit-SUPER02
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: F1
type: f1
value: 1.0
---
<!-- 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. -->
# vit-SUPER02
This model is a fine-tuned version of [google/vit-large-patch16-224](https://huggingface.co/google/vit-large-patch16-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0000
- F1: 1.0
## 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: 0.0002
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.0798 | 0.16 | 50 | 0.0393 | 0.9904 |
| 0.0161 | 0.31 | 100 | 0.0176 | 0.9936 |
| 0.0017 | 0.47 | 150 | 0.0020 | 0.9984 |
| 0.0012 | 0.62 | 200 | 0.0026 | 0.9985 |
| 0.0001 | 0.78 | 250 | 0.0001 | 1.0 |
| 0.0001 | 0.93 | 300 | 0.0001 | 1.0 |
| 0.0001 | 1.09 | 350 | 0.0001 | 1.0 |
| 0.0 | 1.24 | 400 | 0.0000 | 1.0 |
| 0.0 | 1.4 | 450 | 0.0000 | 1.0 |
| 0.0 | 1.55 | 500 | 0.0000 | 1.0 |
| 0.0 | 1.71 | 550 | 0.0000 | 1.0 |
| 0.0 | 1.86 | 600 | 0.0000 | 1.0 |
| 0.0 | 2.02 | 650 | 0.0000 | 1.0 |
| 0.0 | 2.17 | 700 | 0.0000 | 1.0 |
| 0.0 | 2.33 | 750 | 0.0000 | 1.0 |
| 0.0 | 2.48 | 800 | 0.0000 | 1.0 |
| 0.0 | 2.64 | 850 | 0.0000 | 1.0 |
| 0.0 | 2.8 | 900 | 0.0000 | 1.0 |
| 0.0 | 2.95 | 950 | 0.0000 | 1.0 |
| 0.0 | 3.11 | 1000 | 0.0000 | 1.0 |
| 0.0 | 3.26 | 1050 | 0.0000 | 1.0 |
| 0.0 | 3.42 | 1100 | 0.0000 | 1.0 |
| 0.0 | 3.57 | 1150 | 0.0000 | 1.0 |
| 0.0 | 3.73 | 1200 | 0.0000 | 1.0 |
| 0.0 | 3.88 | 1250 | 0.0000 | 1.0 |
| 0.0 | 4.04 | 1300 | 0.0000 | 1.0 |
| 0.0 | 4.19 | 1350 | 0.0000 | 1.0 |
| 0.0 | 4.35 | 1400 | 0.0000 | 1.0 |
| 0.0 | 4.5 | 1450 | 0.0000 | 1.0 |
| 0.0 | 4.66 | 1500 | 0.0000 | 1.0 |
| 0.0 | 4.81 | 1550 | 0.0000 | 1.0 |
| 0.0 | 4.97 | 1600 | 0.0000 | 1.0 |
| 0.0 | 5.12 | 1650 | 0.0000 | 1.0 |
| 0.0 | 5.28 | 1700 | 0.0000 | 1.0 |
| 0.0 | 5.43 | 1750 | 0.0000 | 1.0 |
| 0.0 | 5.59 | 1800 | 0.0000 | 1.0 |
| 0.0 | 5.75 | 1850 | 0.0000 | 1.0 |
| 0.0 | 5.9 | 1900 | 0.0000 | 1.0 |
| 0.0 | 6.06 | 1950 | 0.0000 | 1.0 |
| 0.0 | 6.21 | 2000 | 0.0000 | 1.0 |
| 0.0 | 6.37 | 2050 | 0.0000 | 1.0 |
| 0.0 | 6.52 | 2100 | 0.0000 | 1.0 |
| 0.0 | 6.68 | 2150 | 0.0000 | 1.0 |
| 0.0 | 6.83 | 2200 | 0.0000 | 1.0 |
| 0.0 | 6.99 | 2250 | 0.0000 | 1.0 |
| 0.0 | 7.14 | 2300 | 0.0000 | 1.0 |
| 0.0 | 7.3 | 2350 | 0.0000 | 1.0 |
| 0.0 | 7.45 | 2400 | 0.0000 | 1.0 |
| 0.0 | 7.61 | 2450 | 0.0000 | 1.0 |
| 0.0 | 7.76 | 2500 | 0.0000 | 1.0 |
| 0.0 | 7.92 | 2550 | 0.0000 | 1.0 |
| 0.0 | 8.07 | 2600 | 0.0000 | 1.0 |
| 0.0 | 8.23 | 2650 | 0.0000 | 1.0 |
| 0.0 | 8.39 | 2700 | 0.0000 | 1.0 |
| 0.0 | 8.54 | 2750 | 0.0000 | 1.0 |
| 0.0 | 8.7 | 2800 | 0.0000 | 1.0 |
| 0.0 | 8.85 | 2850 | 0.0000 | 1.0 |
| 0.0 | 9.01 | 2900 | 0.0000 | 1.0 |
| 0.0 | 9.16 | 2950 | 0.0000 | 1.0 |
| 0.0 | 9.32 | 3000 | 0.0000 | 1.0 |
| 0.0 | 9.47 | 3050 | 0.0000 | 1.0 |
| 0.0 | 9.63 | 3100 | 0.0000 | 1.0 |
| 0.0 | 9.78 | 3150 | 0.0000 | 1.0 |
| 0.0 | 9.94 | 3200 | 0.0000 | 1.0 |
### Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1