beit-large-patch16-384-limb-person-crop-8_5e-5_1e-3_0.15
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: 1.3535
- Accuracy: 0.3483
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: 0.15
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.3404 | 1.0 | 214 | 1.4186 | 0.3980 |
1.3839 | 2.0 | 428 | 1.3841 | 0.2703 |
1.3931 | 3.0 | 642 | 1.3867 | 0.2745 |
1.3889 | 4.0 | 856 | 1.3884 | 0.2745 |
1.3864 | 5.0 | 1070 | 1.3842 | 0.2761 |
1.3892 | 6.0 | 1284 | 1.3802 | 0.2877 |
1.369 | 7.0 | 1498 | 1.3726 | 0.3143 |
1.3545 | 8.0 | 1712 | 1.3627 | 0.3275 |
1.3626 | 9.0 | 1926 | 1.3594 | 0.3391 |
1.3464 | 10.0 | 2140 | 1.3535 | 0.3483 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 0