|
--- |
|
license: apache-2.0 |
|
base_model: microsoft/beit-large-patch16-224 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: smids_10x_beit_large_adamax_00001_fold2 |
|
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: 0.9151414309484193 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# smids_10x_beit_large_adamax_00001_fold2 |
|
|
|
This model is a fine-tuned version of [microsoft/beit-large-patch16-224](https://huggingface.co/microsoft/beit-large-patch16-224) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9196 |
|
- Accuracy: 0.9151 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 50 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
| 0.1587 | 1.0 | 750 | 0.2691 | 0.9101 | |
|
| 0.0471 | 2.0 | 1500 | 0.3138 | 0.9135 | |
|
| 0.0407 | 3.0 | 2250 | 0.4729 | 0.9118 | |
|
| 0.0287 | 4.0 | 3000 | 0.5798 | 0.9068 | |
|
| 0.012 | 5.0 | 3750 | 0.7233 | 0.9118 | |
|
| 0.0109 | 6.0 | 4500 | 0.7175 | 0.9168 | |
|
| 0.0017 | 7.0 | 5250 | 0.7940 | 0.9085 | |
|
| 0.0129 | 8.0 | 6000 | 0.7917 | 0.9068 | |
|
| 0.0001 | 9.0 | 6750 | 0.8466 | 0.9068 | |
|
| 0.0033 | 10.0 | 7500 | 0.8662 | 0.9002 | |
|
| 0.0001 | 11.0 | 8250 | 0.9262 | 0.9035 | |
|
| 0.0005 | 12.0 | 9000 | 0.8648 | 0.9035 | |
|
| 0.0001 | 13.0 | 9750 | 0.9176 | 0.9101 | |
|
| 0.0001 | 14.0 | 10500 | 0.9531 | 0.8985 | |
|
| 0.0002 | 15.0 | 11250 | 0.9250 | 0.9035 | |
|
| 0.0418 | 16.0 | 12000 | 0.9389 | 0.9085 | |
|
| 0.0 | 17.0 | 12750 | 0.9725 | 0.9035 | |
|
| 0.0001 | 18.0 | 13500 | 0.9072 | 0.9101 | |
|
| 0.0173 | 19.0 | 14250 | 0.9123 | 0.9151 | |
|
| 0.0042 | 20.0 | 15000 | 0.9275 | 0.9068 | |
|
| 0.0 | 21.0 | 15750 | 0.9111 | 0.9101 | |
|
| 0.0243 | 22.0 | 16500 | 0.9348 | 0.9101 | |
|
| 0.0002 | 23.0 | 17250 | 1.0125 | 0.9052 | |
|
| 0.0002 | 24.0 | 18000 | 0.8943 | 0.9101 | |
|
| 0.0 | 25.0 | 18750 | 1.0215 | 0.9035 | |
|
| 0.0001 | 26.0 | 19500 | 0.9907 | 0.9085 | |
|
| 0.0358 | 27.0 | 20250 | 0.9413 | 0.9101 | |
|
| 0.0003 | 28.0 | 21000 | 0.8860 | 0.9201 | |
|
| 0.0 | 29.0 | 21750 | 0.9273 | 0.9218 | |
|
| 0.0 | 30.0 | 22500 | 0.9583 | 0.9068 | |
|
| 0.0 | 31.0 | 23250 | 0.9280 | 0.9218 | |
|
| 0.0 | 32.0 | 24000 | 0.9420 | 0.9168 | |
|
| 0.0 | 33.0 | 24750 | 0.9244 | 0.9185 | |
|
| 0.0 | 34.0 | 25500 | 0.9598 | 0.9085 | |
|
| 0.0 | 35.0 | 26250 | 0.9576 | 0.9101 | |
|
| 0.0 | 36.0 | 27000 | 0.9574 | 0.9101 | |
|
| 0.0013 | 37.0 | 27750 | 0.9671 | 0.9101 | |
|
| 0.0 | 38.0 | 28500 | 0.9627 | 0.9101 | |
|
| 0.0 | 39.0 | 29250 | 0.9639 | 0.9118 | |
|
| 0.0001 | 40.0 | 30000 | 0.9418 | 0.9118 | |
|
| 0.0003 | 41.0 | 30750 | 0.9216 | 0.9135 | |
|
| 0.0 | 42.0 | 31500 | 0.9226 | 0.9185 | |
|
| 0.0 | 43.0 | 32250 | 0.9076 | 0.9218 | |
|
| 0.0 | 44.0 | 33000 | 0.9133 | 0.9151 | |
|
| 0.0006 | 45.0 | 33750 | 0.9164 | 0.9151 | |
|
| 0.0 | 46.0 | 34500 | 0.9118 | 0.9168 | |
|
| 0.0 | 47.0 | 35250 | 0.9173 | 0.9151 | |
|
| 0.0 | 48.0 | 36000 | 0.9178 | 0.9101 | |
|
| 0.0 | 49.0 | 36750 | 0.9196 | 0.9135 | |
|
| 0.0 | 50.0 | 37500 | 0.9196 | 0.9151 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.2 |
|
|
