metadata
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-large-patch16_fold1
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: 0.6581591094216671
Boya1_RMSProp_1-e5_20Epoch_09Momentum_Beit-large-patch16_fold1
This model is a fine-tuned version of microsoft/beit-base-patch16-224-pt22k-ft22k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.6175
- Accuracy: 0.6582
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 |
|---|---|---|---|---|
| 1.0967 | 1.0 | 924 | 1.1282 | 0.6305 |
| 0.9514 | 2.0 | 1848 | 1.0677 | 0.6335 |
| 0.8134 | 3.0 | 2772 | 0.9657 | 0.6761 |
| 0.5172 | 4.0 | 3696 | 1.0638 | 0.6641 |
| 0.4644 | 5.0 | 4620 | 1.1745 | 0.6655 |
| 0.3079 | 6.0 | 5544 | 1.2914 | 0.6601 |
| 0.1569 | 7.0 | 6468 | 1.4210 | 0.6636 |
| 0.1324 | 8.0 | 7392 | 1.5083 | 0.6603 |
| 0.0833 | 9.0 | 8316 | 1.5875 | 0.6644 |
| 0.1019 | 10.0 | 9240 | 1.6175 | 0.6582 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1