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: 0.6201466196035841
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: 3.7539
- Accuracy: 0.6201
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.3484 | 1.0 | 924 | 1.3605 | 0.5327 |
| 1.1536 | 2.0 | 1848 | 1.2783 | 0.5515 |
| 1.1327 | 3.0 | 2772 | 1.1624 | 0.6071 |
| 0.7516 | 4.0 | 3696 | 1.2618 | 0.5952 |
| 0.5923 | 5.0 | 4620 | 1.4123 | 0.6022 |
| 0.5275 | 6.0 | 5544 | 1.5876 | 0.5927 |
| 0.3529 | 7.0 | 6468 | 1.7994 | 0.5887 |
| 0.2628 | 8.0 | 7392 | 1.9375 | 0.5984 |
| 0.2774 | 9.0 | 8316 | 2.3876 | 0.5889 |
| 0.1651 | 10.0 | 9240 | 2.6650 | 0.5873 |
| 0.1728 | 11.0 | 10164 | 2.8556 | 0.5867 |
| 0.028 | 12.0 | 11088 | 3.0398 | 0.6003 |
| 0.0023 | 13.0 | 12012 | 3.3114 | 0.6044 |
| 0.0042 | 14.0 | 12936 | 3.3149 | 0.6082 |
| 0.0192 | 15.0 | 13860 | 3.4661 | 0.6028 |
| 0.0004 | 16.0 | 14784 | 3.5853 | 0.6058 |
| 0.0363 | 17.0 | 15708 | 3.5853 | 0.6144 |
| 0.0 | 18.0 | 16632 | 3.7544 | 0.6123 |
| 0.002 | 19.0 | 17556 | 3.7503 | 0.6155 |
| 0.0 | 20.0 | 18480 | 3.7539 | 0.6201 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1