convnextv2-base-22k-224-finetuned-hand_class
This model is a fine-tuned version of facebook/convnextv2-base-22k-224 on the image_folder dataset. It achieves the following results on the evaluation set:
- Loss: 0.5846
- Accuracy: 0.7337
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6258 | 1.0 | 14 | 0.5879 | 0.7136 |
| 0.5574 | 2.0 | 28 | 0.5707 | 0.7286 |
| 0.5062 | 3.0 | 42 | 0.5633 | 0.7186 |
| 0.4812 | 4.0 | 56 | 0.5761 | 0.7136 |
| 0.4418 | 5.0 | 70 | 0.5644 | 0.7312 |
| 0.4167 | 6.0 | 84 | 0.5756 | 0.7236 |
| 0.4091 | 7.0 | 98 | 0.5751 | 0.7337 |
| 0.379 | 8.0 | 112 | 0.5727 | 0.7312 |
| 0.3717 | 9.0 | 126 | 0.5877 | 0.7387 |
| 0.346 | 10.0 | 140 | 0.5846 | 0.7337 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3