metadata
license: mit
tags:
- generated_from_trainer
datasets:
- kantinewinkel
model-index:
- name: kantinewinkel-repo
results: []
kantinewinkel-repo
This model is a fine-tuned version of SCUT-DLVCLab/lilt-roberta-en-base on the kantinewinkel dataset. It achieves the following results on the evaluation set:
- Loss: 0.0083
- Cash: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 5}
- Date: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 44}
- Subtotal: {'precision': 0.95, 'recall': 1.0, 'f1': 0.9743589743589743, 'number': 19}
- Total: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 19}
- Overall Precision: 0.9886
- Overall Recall: 1.0
- Overall F1: 0.9943
- Overall Accuracy: 0.9991
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cash | Date | Subtotal | Total | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.0476 | 8.7 | 200 | 0.0083 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 5} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 44} | {'precision': 0.95, 'recall': 1.0, 'f1': 0.9743589743589743, 'number': 19} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 19} | 0.9886 | 1.0 | 0.9943 | 0.9991 |
| 0.0003 | 17.39 | 400 | 0.0092 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 5} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 44} | {'precision': 0.95, 'recall': 1.0, 'f1': 0.9743589743589743, 'number': 19} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 19} | 0.9886 | 1.0 | 0.9943 | 0.9991 |
| 0.0005 | 26.09 | 600 | 0.0080 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 5} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 44} | {'precision': 0.95, 'recall': 1.0, 'f1': 0.9743589743589743, 'number': 19} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 19} | 0.9886 | 1.0 | 0.9943 | 0.9991 |
| 0.0 | 34.78 | 800 | 0.0082 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 5} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 44} | {'precision': 0.95, 'recall': 1.0, 'f1': 0.9743589743589743, 'number': 19} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 19} | 0.9886 | 1.0 | 0.9943 | 0.9991 |
| 0.0001 | 43.48 | 1000 | 0.0081 | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 5} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 44} | {'precision': 0.95, 'recall': 1.0, 'f1': 0.9743589743589743, 'number': 19} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 19} | 0.9886 | 1.0 | 0.9943 | 0.9991 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.13.1
- Datasets 2.12.0
- Tokenizers 0.13.2