|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: Action_model |
|
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: 0.7676190476190476 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# Action_model |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7365 |
|
- Accuracy: 0.7676 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 2 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.3489 | 0.16 | 100 | 1.2612 | 0.7 | |
|
| 1.0112 | 0.32 | 200 | 0.9050 | 0.7590 | |
|
| 0.7962 | 0.48 | 300 | 0.8522 | 0.7505 | |
|
| 0.6383 | 0.64 | 400 | 0.8676 | 0.7219 | |
|
| 0.6485 | 0.8 | 500 | 0.8052 | 0.7324 | |
|
| 0.5452 | 0.96 | 600 | 0.7120 | 0.7848 | |
|
| 0.4882 | 1.11 | 700 | 0.7478 | 0.7714 | |
|
| 0.3409 | 1.27 | 800 | 0.7311 | 0.7743 | |
|
| 0.4105 | 1.43 | 900 | 0.7353 | 0.7810 | |
|
| 0.4011 | 1.59 | 1000 | 0.8154 | 0.7457 | |
|
| 0.3493 | 1.75 | 1100 | 0.7398 | 0.7752 | |
|
| 0.3389 | 1.91 | 1200 | 0.7365 | 0.7676 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
