metadata
library_name: transformers
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: roberta-base_LOGIC_Native
results: []
roberta-base_LOGIC_Native
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.1872
- Accuracy: 0.6367
- Macro Precision: 0.6085
- Macro F1: 0.5927
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro Precision | Macro F1 |
|---|---|---|---|---|---|---|
| No log | 1.0 | 116 | 2.2572 | 0.3633 | 0.3744 | 0.3280 |
| No log | 2.0 | 232 | 1.6881 | 0.4933 | 0.4444 | 0.4351 |
| No log | 3.0 | 348 | 1.5136 | 0.5767 | 0.5515 | 0.5475 |
| No log | 4.0 | 464 | 1.5064 | 0.6033 | 0.5808 | 0.5616 |
| 1.4911 | 5.0 | 580 | 1.5690 | 0.5967 | 0.5912 | 0.5609 |
| 1.4911 | 6.0 | 696 | 1.5927 | 0.6267 | 0.6002 | 0.5907 |
| 1.4911 | 7.0 | 812 | 1.6903 | 0.6267 | 0.5964 | 0.5876 |
| 1.4911 | 8.0 | 928 | 1.8527 | 0.6167 | 0.5924 | 0.5848 |
| 0.2082 | 9.0 | 1044 | 2.0450 | 0.6267 | 0.6208 | 0.5933 |
| 0.2082 | 10.0 | 1160 | 2.0799 | 0.63 | 0.5922 | 0.5852 |
| 0.2082 | 11.0 | 1276 | 2.1676 | 0.6333 | 0.6069 | 0.5889 |
| 0.2082 | 12.0 | 1392 | 2.1872 | 0.6367 | 0.6085 | 0.5927 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2