metadata
license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: smids_1x_beit_base_sgd_001_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: 0.84
smids_1x_beit_base_sgd_001_fold3
This model is a fine-tuned version of microsoft/beit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.3943
- Accuracy: 0.84
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: 0.001
- 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 |
---|---|---|---|---|
1.0814 | 1.0 | 75 | 1.0547 | 0.4367 |
0.8585 | 2.0 | 150 | 0.8397 | 0.63 |
0.7866 | 3.0 | 225 | 0.7414 | 0.6717 |
0.7611 | 4.0 | 300 | 0.6885 | 0.71 |
0.6598 | 5.0 | 375 | 0.6453 | 0.7433 |
0.6441 | 6.0 | 450 | 0.6118 | 0.7433 |
0.6302 | 7.0 | 525 | 0.5846 | 0.7667 |
0.58 | 8.0 | 600 | 0.5727 | 0.7717 |
0.6043 | 9.0 | 675 | 0.5453 | 0.7783 |
0.5566 | 10.0 | 750 | 0.5288 | 0.7917 |
0.5653 | 11.0 | 825 | 0.5189 | 0.795 |
0.5734 | 12.0 | 900 | 0.5084 | 0.8 |
0.526 | 13.0 | 975 | 0.4978 | 0.8067 |
0.5307 | 14.0 | 1050 | 0.4908 | 0.805 |
0.441 | 15.0 | 1125 | 0.4849 | 0.8167 |
0.4731 | 16.0 | 1200 | 0.4739 | 0.8183 |
0.4795 | 17.0 | 1275 | 0.4707 | 0.82 |
0.4461 | 18.0 | 1350 | 0.4612 | 0.8267 |
0.4796 | 19.0 | 1425 | 0.4551 | 0.82 |
0.4848 | 20.0 | 1500 | 0.4529 | 0.8217 |
0.4879 | 21.0 | 1575 | 0.4473 | 0.8217 |
0.424 | 22.0 | 1650 | 0.4423 | 0.8217 |
0.4384 | 23.0 | 1725 | 0.4358 | 0.8233 |
0.4332 | 24.0 | 1800 | 0.4326 | 0.83 |
0.4502 | 25.0 | 1875 | 0.4313 | 0.83 |
0.4747 | 26.0 | 1950 | 0.4225 | 0.83 |
0.4021 | 27.0 | 2025 | 0.4213 | 0.8367 |
0.3712 | 28.0 | 2100 | 0.4180 | 0.83 |
0.4664 | 29.0 | 2175 | 0.4162 | 0.835 |
0.4161 | 30.0 | 2250 | 0.4131 | 0.8317 |
0.3674 | 31.0 | 2325 | 0.4116 | 0.8383 |
0.3951 | 32.0 | 2400 | 0.4117 | 0.8317 |
0.4114 | 33.0 | 2475 | 0.4085 | 0.8333 |
0.3877 | 34.0 | 2550 | 0.4062 | 0.84 |
0.4073 | 35.0 | 2625 | 0.4053 | 0.8383 |
0.4212 | 36.0 | 2700 | 0.4054 | 0.8367 |
0.3625 | 37.0 | 2775 | 0.4024 | 0.8417 |
0.4369 | 38.0 | 2850 | 0.4016 | 0.8383 |
0.393 | 39.0 | 2925 | 0.3994 | 0.8417 |
0.3655 | 40.0 | 3000 | 0.3982 | 0.84 |
0.3762 | 41.0 | 3075 | 0.3980 | 0.84 |
0.3881 | 42.0 | 3150 | 0.3976 | 0.8417 |
0.4602 | 43.0 | 3225 | 0.3971 | 0.845 |
0.3865 | 44.0 | 3300 | 0.3963 | 0.845 |
0.4135 | 45.0 | 3375 | 0.3957 | 0.8433 |
0.3962 | 46.0 | 3450 | 0.3950 | 0.8467 |
0.3933 | 47.0 | 3525 | 0.3951 | 0.8433 |
0.3744 | 48.0 | 3600 | 0.3945 | 0.84 |
0.4098 | 49.0 | 3675 | 0.3944 | 0.84 |
0.3625 | 50.0 | 3750 | 0.3943 | 0.84 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0