beit-large-patch16-512-limb-person-crop
This model is a fine-tuned version of microsoft/beit-large-patch16-512 on the c14kevincardenas/beta_caller_284_person_crop dataset. It achieves the following results on the evaluation set:
- Loss: 0.6628
- Accuracy: 0.7438
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: 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: 0.005
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.3525 | 1.0 | 214 | 1.3037 | 0.4113 |
1.1151 | 2.0 | 428 | 1.0382 | 0.5672 |
1.0525 | 3.0 | 642 | 0.8376 | 0.6633 |
0.9856 | 4.0 | 856 | 0.7885 | 0.6741 |
0.9618 | 5.0 | 1070 | 0.7969 | 0.6741 |
0.8441 | 6.0 | 1284 | 0.6628 | 0.7438 |
0.8498 | 7.0 | 1498 | 0.7226 | 0.7231 |
0.7203 | 8.0 | 1712 | 0.6814 | 0.7488 |
0.6923 | 9.0 | 1926 | 0.6816 | 0.7653 |
0.6974 | 10.0 | 2140 | 0.6793 | 0.7629 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 0