metadata
license: apache-2.0
base_model: microsoft/beit-large-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: smids_10x_beit_large_sgd_00001_fold2
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: 0.6472545757071547
smids_10x_beit_large_sgd_00001_fold2
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: 0.7989
- Accuracy: 0.6473
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: 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 |
---|---|---|---|---|
1.1712 | 1.0 | 750 | 1.2053 | 0.3594 |
1.1095 | 2.0 | 1500 | 1.1744 | 0.3677 |
1.079 | 3.0 | 2250 | 1.1476 | 0.3677 |
1.0868 | 4.0 | 3000 | 1.1238 | 0.3760 |
1.0188 | 5.0 | 3750 | 1.1026 | 0.4043 |
1.0313 | 6.0 | 4500 | 1.0830 | 0.4176 |
0.9867 | 7.0 | 5250 | 1.0650 | 0.4343 |
0.9922 | 8.0 | 6000 | 1.0482 | 0.4509 |
1.0089 | 9.0 | 6750 | 1.0324 | 0.4626 |
0.9248 | 10.0 | 7500 | 1.0176 | 0.4809 |
0.9924 | 11.0 | 8250 | 1.0037 | 0.4942 |
0.9341 | 12.0 | 9000 | 0.9905 | 0.5042 |
0.9032 | 13.0 | 9750 | 0.9777 | 0.5158 |
0.9223 | 14.0 | 10500 | 0.9658 | 0.5241 |
0.8875 | 15.0 | 11250 | 0.9546 | 0.5275 |
0.8812 | 16.0 | 12000 | 0.9440 | 0.5408 |
0.8383 | 17.0 | 12750 | 0.9339 | 0.5524 |
0.8368 | 18.0 | 13500 | 0.9242 | 0.5557 |
0.8681 | 19.0 | 14250 | 0.9150 | 0.5657 |
0.8552 | 20.0 | 15000 | 0.9065 | 0.5674 |
0.8564 | 21.0 | 15750 | 0.8983 | 0.5691 |
0.8254 | 22.0 | 16500 | 0.8905 | 0.5740 |
0.842 | 23.0 | 17250 | 0.8831 | 0.5807 |
0.802 | 24.0 | 18000 | 0.8761 | 0.5857 |
0.8617 | 25.0 | 18750 | 0.8694 | 0.5973 |
0.8384 | 26.0 | 19500 | 0.8631 | 0.6057 |
0.8257 | 27.0 | 20250 | 0.8572 | 0.6106 |
0.8327 | 28.0 | 21000 | 0.8516 | 0.6156 |
0.8111 | 29.0 | 21750 | 0.8464 | 0.6173 |
0.7892 | 30.0 | 22500 | 0.8414 | 0.6206 |
0.7974 | 31.0 | 23250 | 0.8368 | 0.6256 |
0.8791 | 32.0 | 24000 | 0.8325 | 0.6256 |
0.7583 | 33.0 | 24750 | 0.8285 | 0.6306 |
0.7714 | 34.0 | 25500 | 0.8248 | 0.6323 |
0.7891 | 35.0 | 26250 | 0.8214 | 0.6356 |
0.7659 | 36.0 | 27000 | 0.8182 | 0.6389 |
0.8096 | 37.0 | 27750 | 0.8154 | 0.6356 |
0.7644 | 38.0 | 28500 | 0.8128 | 0.6373 |
0.8029 | 39.0 | 29250 | 0.8104 | 0.6406 |
0.7912 | 40.0 | 30000 | 0.8082 | 0.6406 |
0.7766 | 41.0 | 30750 | 0.8063 | 0.6423 |
0.7693 | 42.0 | 31500 | 0.8047 | 0.6439 |
0.735 | 43.0 | 32250 | 0.8032 | 0.6456 |
0.7637 | 44.0 | 33000 | 0.8020 | 0.6456 |
0.7733 | 45.0 | 33750 | 0.8010 | 0.6473 |
0.7268 | 46.0 | 34500 | 0.8002 | 0.6473 |
0.8097 | 47.0 | 35250 | 0.7996 | 0.6473 |
0.7648 | 48.0 | 36000 | 0.7991 | 0.6473 |
0.7593 | 49.0 | 36750 | 0.7989 | 0.6473 |
0.7579 | 50.0 | 37500 | 0.7989 | 0.6473 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2