10-convnextv2-large-22k-384-finetuned-spiderTraining20-500
This model is a fine-tuned version of facebook/convnextv2-large-22k-384 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0881
- Accuracy: 0.9740
- Precision: 0.9749
- Recall: 0.9729
- F1: 0.9733
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: 15
- eval_batch_size: 15
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 4
- total_train_batch_size: 60
- 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 |
|---|---|---|---|---|---|---|---|
| 0.5835 | 1.0 | 133 | 0.4317 | 0.8659 | 0.8765 | 0.8664 | 0.8594 |
| 0.3813 | 2.0 | 266 | 0.2008 | 0.9499 | 0.9533 | 0.9464 | 0.9488 |
| 0.3476 | 2.99 | 399 | 0.1535 | 0.9580 | 0.9591 | 0.9563 | 0.9570 |
| 0.1858 | 4.0 | 533 | 0.1591 | 0.9540 | 0.9542 | 0.9535 | 0.9532 |
| 0.1962 | 5.0 | 666 | 0.1356 | 0.9570 | 0.9565 | 0.9566 | 0.9556 |
| 0.1674 | 6.0 | 799 | 0.1290 | 0.9610 | 0.9612 | 0.9597 | 0.9599 |
| 0.1673 | 6.99 | 932 | 0.1138 | 0.9660 | 0.9669 | 0.9643 | 0.9651 |
| 0.1793 | 8.0 | 1066 | 0.0919 | 0.9720 | 0.9714 | 0.9707 | 0.9706 |
| 0.1369 | 9.0 | 1199 | 0.0936 | 0.9690 | 0.9690 | 0.9676 | 0.9677 |
| 0.1256 | 9.98 | 1330 | 0.0881 | 0.9740 | 0.9749 | 0.9729 | 0.9733 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3