2025-02-10-08-48-20-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: 0.0276
- Precision: 0.9953
- Recall: 0.9951
- F1: 0.9951
- Accuracy: 0.9952
- Top1 Accuracy: 0.9951
- Error Rate: 0.0048
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: 32
- eval_batch_size: 32
- 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 |
|---|---|---|---|---|---|---|---|---|---|
| 1.1857 | 1.0 | 103 | 0.2269 | 0.9480 | 0.9390 | 0.9396 | 0.9449 | 0.9390 | 0.0551 |
| 0.2112 | 2.0 | 206 | 0.1580 | 0.9583 | 0.9561 | 0.9563 | 0.9554 | 0.9561 | 0.0446 |
| 0.1067 | 3.0 | 309 | 0.1165 | 0.9634 | 0.9610 | 0.9613 | 0.9571 | 0.9610 | 0.0429 |
| 0.0922 | 4.0 | 412 | 0.1750 | 0.9608 | 0.9537 | 0.9532 | 0.9549 | 0.9537 | 0.0451 |
| 0.0346 | 5.0 | 515 | 0.0920 | 0.9827 | 0.9805 | 0.9805 | 0.9845 | 0.9805 | 0.0155 |
| 0.018 | 6.0 | 618 | 0.0483 | 0.9881 | 0.9878 | 0.9877 | 0.9886 | 0.9878 | 0.0114 |
| 0.0114 | 7.0 | 721 | 0.0276 | 0.9953 | 0.9951 | 0.9951 | 0.9952 | 0.9951 | 0.0048 |
| 0.0067 | 8.0 | 824 | 0.0423 | 0.9906 | 0.9902 | 0.9903 | 0.9894 | 0.9902 | 0.0106 |
| 0.0014 | 9.0 | 927 | 0.0310 | 0.9953 | 0.9951 | 0.9951 | 0.9952 | 0.9951 | 0.0048 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.20.3