metadata
license: apache-2.0
base_model: microsoft/beit-large-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: Boya2_3Class_RMSprop_1e5_20Epoch_Beit-large-224_fold4
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: 0.8628524500410621
Boya2_3Class_RMSprop_1e5_20Epoch_Beit-large-224_fold4
This model is a fine-tuned version of microsoft/beit-large-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.5247
- Accuracy: 0.8629
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: 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3762 | 1.0 | 913 | 0.3808 | 0.8420 |
| 0.3285 | 2.0 | 1826 | 0.3567 | 0.8566 |
| 0.216 | 3.0 | 2739 | 0.4224 | 0.8494 |
| 0.2451 | 4.0 | 3652 | 0.6798 | 0.8598 |
| 0.0553 | 5.0 | 4565 | 1.0822 | 0.8483 |
| 0.0017 | 6.0 | 5478 | 1.2537 | 0.8503 |
| 0.0008 | 7.0 | 6391 | 1.3944 | 0.8552 |
| 0.0002 | 8.0 | 7304 | 1.4327 | 0.8585 |
| 0.0001 | 9.0 | 8217 | 1.5474 | 0.8661 |
| 0.0 | 10.0 | 9130 | 1.5247 | 0.8629 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.2