10-convnext-base-224-finetuned-spiderTraining100-100
This model is a fine-tuned version of facebook/convnext-base-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7028
- Accuracy: 0.805
- Precision: 0.8192
- Recall: 0.8070
- F1: 0.7991
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 2.9244 | 1.0 | 125 | 2.5311 | 0.379 | 0.4121 | 0.3838 | 0.3329 |
| 1.5583 | 2.0 | 250 | 1.4478 | 0.628 | 0.6814 | 0.6378 | 0.6201 |
| 1.0665 | 3.0 | 375 | 1.0350 | 0.704 | 0.7149 | 0.7139 | 0.6964 |
| 0.6867 | 4.0 | 500 | 0.8875 | 0.745 | 0.7643 | 0.7508 | 0.7350 |
| 0.5302 | 5.0 | 625 | 0.7989 | 0.762 | 0.7890 | 0.7697 | 0.7601 |
| 0.4267 | 6.0 | 750 | 0.7841 | 0.776 | 0.7897 | 0.7838 | 0.7697 |
| 0.3205 | 7.0 | 875 | 0.7701 | 0.792 | 0.8146 | 0.7935 | 0.7873 |
| 0.3248 | 8.0 | 1000 | 0.7391 | 0.811 | 0.8291 | 0.8148 | 0.8069 |
| 0.2753 | 9.0 | 1125 | 0.7146 | 0.81 | 0.8232 | 0.8130 | 0.8050 |
| 0.2053 | 10.0 | 1250 | 0.7028 | 0.805 | 0.8192 | 0.8070 | 0.7991 |
Framework versions
- Transformers 4.55.2
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.4