metadata
license: apache-2.0
base_model: microsoft/beit-large-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_40x_beit_large_adamax_001_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: 0.7333333333333333
hushem_40x_beit_large_adamax_001_fold1
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: 3.2476
- Accuracy: 0.7333
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 |
|---|---|---|---|---|
| 0.3238 | 1.0 | 215 | 0.6915 | 0.7333 |
| 0.1477 | 2.0 | 430 | 1.2081 | 0.6444 |
| 0.0434 | 3.0 | 645 | 1.8202 | 0.6444 |
| 0.0459 | 4.0 | 860 | 1.9604 | 0.6222 |
| 0.0376 | 5.0 | 1075 | 0.7965 | 0.7778 |
| 0.0151 | 6.0 | 1290 | 1.6449 | 0.7111 |
| 0.0084 | 7.0 | 1505 | 2.7172 | 0.6222 |
| 0.0085 | 8.0 | 1720 | 2.4588 | 0.6667 |
| 0.0105 | 9.0 | 1935 | 3.0173 | 0.5333 |
| 0.0465 | 10.0 | 2150 | 1.5242 | 0.7778 |
| 0.0056 | 11.0 | 2365 | 2.2494 | 0.7333 |
| 0.0106 | 12.0 | 2580 | 2.3865 | 0.6889 |
| 0.0614 | 13.0 | 2795 | 1.3048 | 0.7778 |
| 0.0068 | 14.0 | 3010 | 2.7128 | 0.6889 |
| 0.0 | 15.0 | 3225 | 2.3042 | 0.7778 |
| 0.0001 | 16.0 | 3440 | 2.6333 | 0.7333 |
| 0.0483 | 17.0 | 3655 | 2.9792 | 0.7111 |
| 0.0 | 18.0 | 3870 | 2.6692 | 0.7111 |
| 0.0 | 19.0 | 4085 | 2.7990 | 0.7556 |
| 0.0 | 20.0 | 4300 | 2.7968 | 0.7333 |
| 0.0 | 21.0 | 4515 | 2.8289 | 0.7333 |
| 0.0 | 22.0 | 4730 | 2.8734 | 0.7333 |
| 0.0 | 23.0 | 4945 | 2.7220 | 0.7556 |
| 0.0742 | 24.0 | 5160 | 2.8716 | 0.7111 |
| 0.0011 | 25.0 | 5375 | 2.8927 | 0.7333 |
| 0.0 | 26.0 | 5590 | 2.8101 | 0.7333 |
| 0.0 | 27.0 | 5805 | 2.9619 | 0.7111 |
| 0.0 | 28.0 | 6020 | 3.0313 | 0.7111 |
| 0.0 | 29.0 | 6235 | 3.1395 | 0.7111 |
| 0.0 | 30.0 | 6450 | 3.4589 | 0.7111 |
| 0.0 | 31.0 | 6665 | 3.5502 | 0.6889 |
| 0.0 | 32.0 | 6880 | 3.7038 | 0.6667 |
| 0.0 | 33.0 | 7095 | 2.9949 | 0.7111 |
| 0.0 | 34.0 | 7310 | 3.0364 | 0.7111 |
| 0.0 | 35.0 | 7525 | 3.1096 | 0.7111 |
| 0.0 | 36.0 | 7740 | 3.1633 | 0.7333 |
| 0.0 | 37.0 | 7955 | 3.1868 | 0.7333 |
| 0.0 | 38.0 | 8170 | 3.2061 | 0.7333 |
| 0.0 | 39.0 | 8385 | 3.2444 | 0.7333 |
| 0.0 | 40.0 | 8600 | 3.2660 | 0.7333 |
| 0.0 | 41.0 | 8815 | 3.2861 | 0.7333 |
| 0.0 | 42.0 | 9030 | 3.3090 | 0.7333 |
| 0.0 | 43.0 | 9245 | 3.3340 | 0.7333 |
| 0.0 | 44.0 | 9460 | 3.3547 | 0.7333 |
| 0.0 | 45.0 | 9675 | 3.3742 | 0.7333 |
| 0.0 | 46.0 | 9890 | 3.3879 | 0.7333 |
| 0.0 | 47.0 | 10105 | 3.4047 | 0.7333 |
| 0.0 | 48.0 | 10320 | 3.2184 | 0.7333 |
| 0.0 | 49.0 | 10535 | 3.2219 | 0.7333 |
| 0.0 | 50.0 | 10750 | 3.2476 | 0.7333 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2