metadata
base_model: MBZUAI/swiftformer-xs
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: swiftformer-xs-dmae-va-U-40
results: []
swiftformer-xs-dmae-va-U-40
This model is a fine-tuned version of MBZUAI/swiftformer-xs on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7007
- Accuracy: 0.7523
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 40
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.9 | 7 | 1.3578 | 0.2936 |
| 1.3702 | 1.94 | 15 | 1.3703 | 0.2936 |
| 1.3497 | 2.97 | 23 | 1.3361 | 0.3394 |
| 1.3004 | 4.0 | 31 | 1.2852 | 0.3670 |
| 1.3004 | 4.9 | 38 | 1.2317 | 0.4312 |
| 1.2248 | 5.94 | 46 | 1.1786 | 0.4587 |
| 1.1485 | 6.97 | 54 | 1.1240 | 0.5046 |
| 1.0759 | 8.0 | 62 | 1.0727 | 0.5505 |
| 1.0759 | 8.9 | 69 | 1.0404 | 0.5596 |
| 1.0244 | 9.94 | 77 | 0.9742 | 0.6239 |
| 0.9782 | 10.97 | 85 | 0.9374 | 0.6422 |
| 0.9359 | 12.0 | 93 | 0.9197 | 0.6789 |
| 0.9051 | 12.9 | 100 | 0.8753 | 0.6881 |
| 0.9051 | 13.94 | 108 | 0.8679 | 0.6972 |
| 0.8652 | 14.97 | 116 | 0.8316 | 0.7156 |
| 0.8336 | 16.0 | 124 | 0.8222 | 0.6972 |
| 0.8177 | 16.9 | 131 | 0.8178 | 0.6972 |
| 0.8177 | 17.94 | 139 | 0.7818 | 0.7339 |
| 0.8077 | 18.97 | 147 | 0.7627 | 0.7339 |
| 0.7796 | 20.0 | 155 | 0.7478 | 0.7339 |
| 0.7673 | 20.9 | 162 | 0.7415 | 0.7431 |
| 0.7445 | 21.94 | 170 | 0.7414 | 0.7156 |
| 0.7445 | 22.97 | 178 | 0.7375 | 0.7156 |
| 0.7413 | 24.0 | 186 | 0.7354 | 0.7156 |
| 0.739 | 24.9 | 193 | 0.7110 | 0.7431 |
| 0.6992 | 25.94 | 201 | 0.7121 | 0.7339 |
| 0.6992 | 26.97 | 209 | 0.7044 | 0.7431 |
| 0.7111 | 28.0 | 217 | 0.6947 | 0.7339 |
| 0.7013 | 28.9 | 224 | 0.7007 | 0.7523 |
| 0.712 | 29.94 | 232 | 0.6793 | 0.7431 |
| 0.671 | 30.97 | 240 | 0.6808 | 0.7431 |
| 0.671 | 32.0 | 248 | 0.6821 | 0.7339 |
| 0.6862 | 32.9 | 255 | 0.6705 | 0.7339 |
| 0.6606 | 33.94 | 263 | 0.6784 | 0.7431 |
| 0.6667 | 34.97 | 271 | 0.6764 | 0.7523 |
| 0.6667 | 36.0 | 279 | 0.6717 | 0.7523 |
| 0.6687 | 36.13 | 280 | 0.6736 | 0.7523 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1