beit-large-patch16-384-limb-person-crop-8_1e-5_5e-3_0.05
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: 0.8094
- Accuracy: 0.7164
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: 1e-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: 0.05
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.4037 | 1.0 | 214 | 1.3978 | 0.2728 |
1.2478 | 2.0 | 428 | 1.1724 | 0.4942 |
1.131 | 3.0 | 642 | 0.9780 | 0.5937 |
1.0611 | 4.0 | 856 | 1.0211 | 0.5937 |
1.0258 | 5.0 | 1070 | 0.9024 | 0.6559 |
0.9634 | 6.0 | 1284 | 0.8424 | 0.6857 |
0.8849 | 7.0 | 1498 | 0.8479 | 0.6907 |
0.8849 | 8.0 | 1712 | 0.8114 | 0.7123 |
0.8663 | 9.0 | 1926 | 0.8094 | 0.7164 |
0.8473 | 10.0 | 2140 | 0.8130 | 0.7098 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 1