convnextv2-tiny-22k-384-finetuned-spiderTraining20-500
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: 0.2472
- Accuracy: 0.9279
- Precision: 0.9271
- Recall: 0.9247
- F1: 0.9247
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: 16
- eval_batch_size: 16
- seed: 42
- 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 |
|---|---|---|---|---|---|---|---|
| 0.9602 | 1.0 | 125 | 0.7123 | 0.8148 | 0.8207 | 0.8080 | 0.8050 |
| 0.5216 | 2.0 | 250 | 0.3843 | 0.8909 | 0.8921 | 0.8893 | 0.8881 |
| 0.4456 | 3.0 | 375 | 0.2864 | 0.9179 | 0.9168 | 0.9099 | 0.9116 |
| 0.3673 | 4.0 | 500 | 0.2652 | 0.9229 | 0.9229 | 0.9200 | 0.9201 |
| 0.3069 | 5.0 | 625 | 0.2472 | 0.9279 | 0.9271 | 0.9247 | 0.9247 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3