convnextv2-tiny-22k-384-1e-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: 2.2312
- Accuracy: 0.5025
- Precision: 0.5189
- Recall: 0.5032
- F1: 0.4858
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: 1e-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 |
|---|---|---|---|---|---|---|---|
| 3.6298 | 1.0 | 125 | 3.4996 | 0.1481 | 0.1491 | 0.1491 | 0.1288 |
| 2.9856 | 2.0 | 250 | 2.8859 | 0.3263 | 0.3797 | 0.3289 | 0.3014 |
| 2.5878 | 3.0 | 375 | 2.5019 | 0.4404 | 0.4744 | 0.4397 | 0.4201 |
| 2.3898 | 4.0 | 500 | 2.2965 | 0.4905 | 0.5187 | 0.4896 | 0.4703 |
| 2.3254 | 5.0 | 625 | 2.2312 | 0.5025 | 0.5189 | 0.5032 | 0.4858 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3