resnet-50-limb-person-crop
This model is a fine-tuned version of microsoft/resnet-50 on the c14kevincardenas/beta_caller_284_person_crop dataset. It achieves the following results on the evaluation set:
- Loss: 1.2914
- Accuracy: 0.3416
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: 64
- eval_batch_size: 64
- 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 |
---|---|---|---|---|
1.3842 | 1.0 | 107 | 1.3839 | 0.2769 |
1.3832 | 2.0 | 214 | 1.3805 | 0.2745 |
1.3792 | 3.0 | 321 | 1.3748 | 0.2745 |
1.3694 | 4.0 | 428 | 1.3627 | 0.2910 |
1.3583 | 5.0 | 535 | 1.3431 | 0.3093 |
1.3451 | 6.0 | 642 | 1.3235 | 0.3159 |
1.3285 | 7.0 | 749 | 1.3172 | 0.3234 |
1.3068 | 8.0 | 856 | 1.2976 | 0.3408 |
1.3083 | 9.0 | 963 | 1.2914 | 0.3416 |
1.3114 | 10.0 | 1070 | 1.2949 | 0.3441 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 0