beit-large-patch16-384-limb-person-crop-8_1e-4_5e-3_0.1
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: 0.8073
- Accuracy: 0.7695
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: 0.0001
- 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: 0.1
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.2871 | 1.0 | 214 | 1.3688 | 0.4071 |
1.1933 | 2.0 | 428 | 1.0977 | 0.5755 |
1.1594 | 3.0 | 642 | 1.0862 | 0.5597 |
1.1173 | 4.0 | 856 | 0.9833 | 0.6285 |
1.095 | 5.0 | 1070 | 0.8918 | 0.7081 |
1.0206 | 6.0 | 1284 | 0.8634 | 0.7197 |
0.9692 | 7.0 | 1498 | 0.8321 | 0.7504 |
0.9255 | 8.0 | 1712 | 0.8306 | 0.7471 |
0.8544 | 9.0 | 1926 | 0.8124 | 0.7703 |
0.8448 | 10.0 | 2140 | 0.8073 | 0.7695 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 0