convnextv2-tiny-22k-384-finetuned-spiderTraining1000-1000
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: 0.5648
- Accuracy: 0.8509
- Precision: 0.8513
- Recall: 0.8405
- F1: 0.8436
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
- distributed_type: multi-GPU
- 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 |
|---|---|---|---|---|---|---|---|
| 1.8531 | 1.0 | 6858 | 1.3392 | 0.6713 | 0.6983 | 0.6342 | 0.6413 |
| 1.2682 | 2.0 | 13717 | 0.8656 | 0.7746 | 0.7827 | 0.7572 | 0.7591 |
| 1.0224 | 3.0 | 20576 | 0.6918 | 0.8165 | 0.8210 | 0.8029 | 0.8059 |
| 0.9031 | 4.0 | 27435 | 0.6062 | 0.8400 | 0.8426 | 0.8281 | 0.8318 |
| 0.8482 | 5.0 | 34290 | 0.5648 | 0.8509 | 0.8513 | 0.8405 | 0.8436 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3