10-convnextv2-femto-1k-224-finetuned-spiderTraining20-500
This model is a fine-tuned version of facebook/convnextv2-femto-1k-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4856
- Accuracy: 0.8388
- Precision: 0.8342
- Recall: 0.8349
- F1: 0.8332
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: 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 |
|---|---|---|---|---|---|---|---|
| 1.9569 | 1.0 | 80 | 1.7758 | 0.5065 | 0.5330 | 0.5075 | 0.4959 |
| 1.05 | 2.0 | 160 | 0.9583 | 0.7207 | 0.7400 | 0.7158 | 0.7102 |
| 0.8342 | 3.0 | 240 | 0.7517 | 0.7568 | 0.7747 | 0.7420 | 0.7409 |
| 0.7 | 4.0 | 320 | 0.6801 | 0.7928 | 0.7921 | 0.7890 | 0.7826 |
| 0.5956 | 5.0 | 400 | 0.5913 | 0.8128 | 0.8130 | 0.8082 | 0.8061 |
| 0.572 | 6.0 | 480 | 0.5533 | 0.8278 | 0.8259 | 0.8223 | 0.8217 |
| 0.4786 | 7.0 | 560 | 0.5108 | 0.8348 | 0.8319 | 0.8308 | 0.8302 |
| 0.4201 | 8.0 | 640 | 0.5064 | 0.8318 | 0.8286 | 0.8248 | 0.8252 |
| 0.4486 | 9.0 | 720 | 0.4951 | 0.8408 | 0.8364 | 0.8363 | 0.8350 |
| 0.4382 | 10.0 | 800 | 0.4856 | 0.8388 | 0.8342 | 0.8349 | 0.8332 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3