convnextv2-tiny-22k-384-finetuned-spiderTraining100-100
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: 1.3480
- Accuracy: 0.708
- Precision: 0.7226
- Recall: 0.7142
- F1: 0.6994
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 |
|---|---|---|---|---|---|---|---|
| 3.5765 | 1.0 | 125 | 3.3326 | 0.293 | 0.3422 | 0.2932 | 0.2604 |
| 2.29 | 2.0 | 250 | 2.1112 | 0.539 | 0.5769 | 0.5460 | 0.5180 |
| 1.8212 | 3.0 | 375 | 1.6097 | 0.657 | 0.6790 | 0.6674 | 0.6465 |
| 1.4779 | 4.0 | 500 | 1.4234 | 0.688 | 0.7060 | 0.6974 | 0.6802 |
| 1.3378 | 5.0 | 625 | 1.3480 | 0.708 | 0.7226 | 0.7142 | 0.6994 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3