beit-large-patch16-384-limb-person-crop-8_5e-5_5e-4_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: 0.7131
- Accuracy: 0.7678
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: 0.05
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.3649 | 1.0 | 214 | 1.5215 | 0.3640 |
1.1297 | 2.0 | 428 | 1.0014 | 0.6003 |
1.0881 | 3.0 | 642 | 0.9018 | 0.6559 |
1.0065 | 4.0 | 856 | 0.9688 | 0.5995 |
1.0028 | 5.0 | 1070 | 0.8240 | 0.7015 |
0.9225 | 6.0 | 1284 | 0.7355 | 0.7521 |
0.8522 | 7.0 | 1498 | 0.7693 | 0.7463 |
0.821 | 8.0 | 1712 | 0.7131 | 0.7678 |
0.735 | 9.0 | 1926 | 0.7316 | 0.7761 |
0.7123 | 10.0 | 2140 | 0.7301 | 0.7778 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 0