onizukal's picture
End of training
980befd verified
---
license: apache-2.0
base_model: microsoft/beit-base-patch16-224-pt22k-ft22k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: Boya1_RMSProp_1-e5_20Epoch_09Momentum_Beit-base-patch16_fold3
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: 0.6555735930735931
---
<!-- 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. -->
# Boya1_RMSProp_1-e5_20Epoch_09Momentum_Beit-base-patch16_fold3
This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 3.0039
- Accuracy: 0.6556
## 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: 16
- 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: 20
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 1.1079 | 1.0 | 923 | 1.1521 | 0.6025 |
| 0.921 | 2.0 | 1846 | 1.0560 | 0.6326 |
| 0.6516 | 3.0 | 2769 | 1.0430 | 0.6442 |
| 0.3542 | 4.0 | 3692 | 1.2268 | 0.6399 |
| 0.2629 | 5.0 | 4615 | 1.3655 | 0.6496 |
| 0.2053 | 6.0 | 5538 | 1.6123 | 0.6415 |
| 0.0506 | 7.0 | 6461 | 1.9244 | 0.6383 |
| 0.0801 | 8.0 | 7384 | 2.1949 | 0.6334 |
| 0.079 | 9.0 | 8307 | 2.3005 | 0.6437 |
| 0.0549 | 10.0 | 9230 | 2.5668 | 0.6442 |
| 0.0012 | 11.0 | 10153 | 2.6623 | 0.6445 |
| 0.0562 | 12.0 | 11076 | 2.7298 | 0.6496 |
| 0.0187 | 13.0 | 11999 | 2.7730 | 0.6537 |
| 0.0405 | 14.0 | 12922 | 2.8958 | 0.6483 |
| 0.0037 | 15.0 | 13845 | 2.9177 | 0.6564 |
| 0.0009 | 16.0 | 14768 | 2.9650 | 0.6572 |
| 0.0001 | 17.0 | 15691 | 3.0071 | 0.6548 |
| 0.0009 | 18.0 | 16614 | 2.9743 | 0.6585 |
| 0.0024 | 19.0 | 17537 | 2.9839 | 0.6572 |
| 0.0003 | 20.0 | 18460 | 3.0039 | 0.6556 |
### Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1