convnextv2-tiny-22k-384-0.001-finetuned-spiderTraining50-200
This model is a fine-tuned version of facebook/convnextv2-tiny-22k-384 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5655
- Accuracy: 0.8318
- Precision: 0.8330
- Recall: 0.8327
- F1: 0.8298
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: 0.001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 2.009 | 1.0 | 125 | 1.8101 | 0.4835 | 0.5749 | 0.4868 | 0.4647 |
| 1.4548 | 2.0 | 250 | 1.3139 | 0.6156 | 0.6797 | 0.6129 | 0.6074 |
| 1.0483 | 3.0 | 375 | 0.8844 | 0.7407 | 0.7514 | 0.7369 | 0.7285 |
| 0.7144 | 4.0 | 500 | 0.6839 | 0.7888 | 0.8000 | 0.7890 | 0.7840 |
| 0.4368 | 5.0 | 625 | 0.5655 | 0.8318 | 0.8330 | 0.8327 | 0.8298 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3