beit-large-patch16-384-limb-person-crop-8_1e-4_1e-4_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: 0.8736
- 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: 0.15
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.3768 | 1.0 | 214 | 1.4562 | 0.2769 |
1.2626 | 2.0 | 428 | 1.1360 | 0.5589 |
1.2374 | 3.0 | 642 | 1.0635 | 0.6169 |
1.159 | 4.0 | 856 | 1.0249 | 0.6451 |
1.1232 | 5.0 | 1070 | 0.9774 | 0.6808 |
1.0871 | 6.0 | 1284 | 0.9632 | 0.7032 |
1.0233 | 7.0 | 1498 | 0.9026 | 0.7479 |
0.9934 | 8.0 | 1712 | 0.9091 | 0.7239 |
0.9313 | 9.0 | 1926 | 0.8778 | 0.7687 |
0.9193 | 10.0 | 2140 | 0.8736 | 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