10-convnextv2-base-22k-384-finetuned-spiderTraining50-200
This model is a fine-tuned version of facebook/convnextv2-base-22k-384 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2953
- Accuracy: 0.9179
- Precision: 0.9143
- Recall: 0.9169
- F1: 0.9135
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: 0.0005
- train_batch_size: 27
- eval_batch_size: 27
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 4
- total_train_batch_size: 108
- 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 | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 1.2896 | 1.0 | 74 | 0.9797 | 0.7057 | 0.7360 | 0.7011 | 0.6843 |
| 1.1398 | 1.99 | 148 | 0.9558 | 0.7227 | 0.7691 | 0.7254 | 0.7197 |
| 0.7899 | 2.99 | 222 | 0.6987 | 0.7948 | 0.8101 | 0.7890 | 0.7866 |
| 0.5357 | 4.0 | 297 | 0.6526 | 0.8148 | 0.8327 | 0.8161 | 0.8104 |
| 0.4807 | 5.0 | 371 | 0.5543 | 0.8398 | 0.8512 | 0.8407 | 0.8367 |
| 0.3575 | 5.99 | 445 | 0.4465 | 0.8789 | 0.8814 | 0.8790 | 0.8746 |
| 0.3728 | 6.99 | 519 | 0.4344 | 0.8819 | 0.8840 | 0.8794 | 0.8772 |
| 0.2892 | 8.0 | 594 | 0.3911 | 0.8859 | 0.8879 | 0.8839 | 0.8804 |
| 0.2082 | 9.0 | 668 | 0.3256 | 0.9079 | 0.9067 | 0.9091 | 0.9053 |
| 0.1737 | 9.97 | 740 | 0.2953 | 0.9179 | 0.9143 | 0.9169 | 0.9135 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3