convnextv2-tiny-22k-384-0.05-finetuned-spiderTraining50-200
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: 3.9245
- Accuracy: 0.0130
- Precision: 0.0003
- Recall: 0.02
- F1: 0.0005
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: 0.05
- 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 |
|---|---|---|---|---|---|---|---|
| 4.0774 | 1.0 | 125 | 4.0954 | 0.0140 | 0.0003 | 0.02 | 0.0006 |
| 4.028 | 2.0 | 250 | 4.0415 | 0.0180 | 0.0004 | 0.02 | 0.0007 |
| 3.9495 | 3.0 | 375 | 3.9851 | 0.0140 | 0.0003 | 0.02 | 0.0006 |
| 3.9533 | 4.0 | 500 | 3.9242 | 0.0210 | 0.0004 | 0.02 | 0.0008 |
| 3.9196 | 5.0 | 625 | 3.9245 | 0.0130 | 0.0003 | 0.02 | 0.0005 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3