metadata
library_name: transformers
license: apache-2.0
base_model: Jsevisal/ModernEMO-wheel-base-classweight
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: ModernEMO-psiconnea-wheel-base-classweight
results: []
ModernEMO-psiconnea-wheel-base-classweight
This model is a fine-tuned version of Jsevisal/ModernEMO-wheel-base-classweight on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4714
- F1: 0.7626
- Roc Auc: 0.8449
- Accuracy: 0.376
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: 8e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.98) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.4054 | 1.0 | 24 | 0.3117 | 0.6802 | 0.7748 | 0.24 |
| 0.2246 | 2.0 | 48 | 0.2869 | 0.7467 | 0.8271 | 0.328 |
| 0.1472 | 3.0 | 72 | 0.2870 | 0.7553 | 0.8281 | 0.368 |
| 0.093 | 4.0 | 96 | 0.4209 | 0.7536 | 0.8401 | 0.304 |
| 0.0575 | 5.0 | 120 | 0.4089 | 0.7589 | 0.8450 | 0.32 |
| 0.036 | 6.0 | 144 | 0.4369 | 0.7648 | 0.8467 | 0.4 |
| 0.026 | 7.0 | 168 | 0.4727 | 0.7579 | 0.8463 | 0.344 |
| 0.0187 | 8.0 | 192 | 0.4631 | 0.7701 | 0.8516 | 0.384 |
| 0.0162 | 9.0 | 216 | 0.4699 | 0.7612 | 0.8443 | 0.36 |
| 0.0141 | 10.0 | 240 | 0.4714 | 0.7626 | 0.8449 | 0.376 |
Framework versions
- Transformers 4.49.0.dev0
- Pytorch 2.3.1.post100
- Datasets 3.2.0
- Tokenizers 0.21.0