|
--- |
|
base_model: MBZUAI/swiftformer-xs |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: swiftformer-xs-dmae-va-U-80 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# swiftformer-xs-dmae-va-U-80 |
|
|
|
This model is a fine-tuned version of [MBZUAI/swiftformer-xs](https://huggingface.co./MBZUAI/swiftformer-xs) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6494 |
|
- Accuracy: 0.8165 |
|
|
|
## 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 | 1.3781 | 0.3486 | |
|
| 1.3901 | 1.94 | 15 | 1.3538 | 0.3303 | |
|
| 1.3561 | 2.97 | 23 | 1.3091 | 0.3761 | |
|
| 1.2933 | 4.0 | 31 | 1.2623 | 0.4220 | |
|
| 1.2933 | 4.9 | 38 | 1.2065 | 0.5138 | |
|
| 1.2274 | 5.94 | 46 | 1.1353 | 0.5413 | |
|
| 1.1686 | 6.97 | 54 | 1.0854 | 0.6147 | |
|
| 1.097 | 8.0 | 62 | 1.0489 | 0.6330 | |
|
| 1.097 | 8.9 | 69 | 1.0185 | 0.6606 | |
|
| 1.0349 | 9.94 | 77 | 0.9682 | 0.6422 | |
|
| 1.0161 | 10.97 | 85 | 0.9511 | 0.6055 | |
|
| 0.9633 | 12.0 | 93 | 0.9009 | 0.6606 | |
|
| 0.939 | 12.9 | 100 | 0.9055 | 0.6514 | |
|
| 0.939 | 13.94 | 108 | 0.8781 | 0.6697 | |
|
| 0.9036 | 14.97 | 116 | 0.8494 | 0.7248 | |
|
| 0.8687 | 16.0 | 124 | 0.8503 | 0.6789 | |
|
| 0.8535 | 16.9 | 131 | 0.8164 | 0.7248 | |
|
| 0.8535 | 17.94 | 139 | 0.7883 | 0.7615 | |
|
| 0.8306 | 18.97 | 147 | 0.7667 | 0.7615 | |
|
| 0.8047 | 20.0 | 155 | 0.7600 | 0.7523 | |
|
| 0.7735 | 20.9 | 162 | 0.7331 | 0.7615 | |
|
| 0.784 | 21.94 | 170 | 0.7295 | 0.7523 | |
|
| 0.784 | 22.97 | 178 | 0.7281 | 0.7431 | |
|
| 0.7596 | 24.0 | 186 | 0.7045 | 0.7615 | |
|
| 0.7609 | 24.9 | 193 | 0.6915 | 0.7706 | |
|
| 0.7307 | 25.94 | 201 | 0.6970 | 0.8073 | |
|
| 0.7307 | 26.97 | 209 | 0.6796 | 0.7615 | |
|
| 0.7263 | 28.0 | 217 | 0.6615 | 0.7706 | |
|
| 0.6933 | 28.9 | 224 | 0.6628 | 0.7798 | |
|
| 0.6914 | 29.94 | 232 | 0.6596 | 0.8073 | |
|
| 0.7192 | 30.97 | 240 | 0.6453 | 0.7982 | |
|
| 0.7192 | 32.0 | 248 | 0.6569 | 0.7798 | |
|
| 0.6956 | 32.9 | 255 | 0.6494 | 0.8165 | |
|
| 0.7037 | 33.94 | 263 | 0.6478 | 0.8073 | |
|
| 0.669 | 34.97 | 271 | 0.6415 | 0.7798 | |
|
| 0.669 | 36.0 | 279 | 0.6441 | 0.7890 | |
|
| 0.6715 | 36.13 | 280 | 0.6445 | 0.7798 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
|
|
