10-convnextv2-base-22k-384-finetuned-spiderTraining20-500
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: 0.1779
- Accuracy: 0.9489
- Precision: 0.9485
- Recall: 0.9477
- F1: 0.9476
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: 25
- eval_batch_size: 25
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 4
- total_train_batch_size: 100
- 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 |
|---|---|---|---|---|---|---|---|
| 0.7479 | 1.0 | 80 | 0.5460 | 0.8238 | 0.8427 | 0.8154 | 0.8203 |
| 0.6232 | 2.0 | 160 | 0.4423 | 0.8619 | 0.8735 | 0.8584 | 0.8573 |
| 0.5591 | 3.0 | 240 | 0.4042 | 0.8769 | 0.8862 | 0.8662 | 0.8702 |
| 0.4503 | 4.0 | 320 | 0.3648 | 0.8839 | 0.8937 | 0.8811 | 0.8807 |
| 0.3479 | 5.0 | 400 | 0.3523 | 0.8989 | 0.8996 | 0.8956 | 0.8945 |
| 0.3144 | 6.0 | 480 | 0.2513 | 0.9189 | 0.9175 | 0.9164 | 0.9142 |
| 0.2779 | 7.0 | 560 | 0.2274 | 0.9289 | 0.9304 | 0.9234 | 0.9252 |
| 0.1958 | 8.0 | 640 | 0.2443 | 0.9289 | 0.9267 | 0.9285 | 0.9268 |
| 0.1479 | 9.0 | 720 | 0.2054 | 0.9399 | 0.9378 | 0.9383 | 0.9371 |
| 0.1533 | 10.0 | 800 | 0.1779 | 0.9489 | 0.9485 | 0.9477 | 0.9476 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3