2025-01-21-15-21-31-convnextv2-tiny-1k-224
This model is a fine-tuned version of facebook/convnextv2-tiny-1k-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0591
- Precision: 0.9799
- Recall: 0.9778
- F1: 0.9776
- Accuracy: 0.976
- Top1 Accuracy: 0.9778
- Error Rate: 0.0240
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 3407
- 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 | Precision | Recall | F1 | Accuracy | Top1 Accuracy | Error Rate |
|---|---|---|---|---|---|---|---|---|---|
| 0.7126 | 1.0 | 135 | 1.3514 | 0.7672 | 0.6593 | 0.6371 | 0.6614 | 0.6593 | 0.3386 |
| 0.4328 | 2.0 | 270 | 0.2026 | 0.9348 | 0.9333 | 0.9330 | 0.9347 | 0.9333 | 0.0653 |
| 0.3438 | 3.0 | 405 | 0.0591 | 0.9799 | 0.9778 | 0.9776 | 0.976 | 0.9778 | 0.0240 |
| 0.2082 | 4.0 | 540 | 0.0919 | 0.9725 | 0.9704 | 0.9703 | 0.9719 | 0.9704 | 0.0281 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3