beit-large-patch16-384-limb-person-crop-test
This model is a fine-tuned version of microsoft/beit-large-patch16-384 on the c14kevincardenas/beta_caller_284_person_crop dataset. It achieves the following results on the evaluation set:
- Loss: 0.8112
- Accuracy: 0.7587
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: 7.5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 2014
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10.0
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.1
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.3391 | 1.0 | 427 | 1.3012 | 0.3964 |
1.1728 | 2.0 | 854 | 1.0953 | 0.5614 |
1.1865 | 3.0 | 1281 | 0.9964 | 0.6244 |
1.1112 | 4.0 | 1708 | 0.9269 | 0.6808 |
1.0695 | 5.0 | 2135 | 0.8837 | 0.7007 |
1.0618 | 6.0 | 2562 | 0.8650 | 0.7305 |
0.978 | 7.0 | 2989 | 0.8299 | 0.7388 |
0.9225 | 8.0 | 3416 | 0.8514 | 0.7463 |
0.8603 | 9.0 | 3843 | 0.8112 | 0.7587 |
0.8756 | 10.0 | 4270 | 0.8204 | 0.7546 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 0