metadata
license: mit
tags:
- generated_from_trainer
model-index:
- name: new_model
results: []
new_model
This model is a fine-tuned version of SCUT-DLVCLab/lilt-roberta-en-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0582
- Answer: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8}
- Header: {'precision': 0.05263157894736842, 'recall': 0.07692307692307693, 'f1': 0.0625, 'number': 13}
- Question: {'precision': 0.1, 'recall': 0.15384615384615385, 'f1': 0.12121212121212123, 'number': 13}
- Overall Precision: 0.0682
- Overall Recall: 0.0882
- Overall F1: 0.0769
- Overall Accuracy: 0.6434
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 2500
Training results
| Training Loss | Epoch | Step | Validation Loss | Answer | Header | Question | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|---|---|---|---|---|---|---|---|---|---|---|
| 0.1677 | 3.08 | 200 | 0.0239 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 13} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 13} | 0.0 | 0.0 | 0.0 | 0.7295 |
| 0.0578 | 6.15 | 400 | 0.0251 | {'precision': 0.4, 'recall': 0.25, 'f1': 0.3076923076923077, 'number': 8} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 13} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 13} | 0.1333 | 0.0588 | 0.0816 | 0.7295 |
| 0.0275 | 9.23 | 600 | 0.0291 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | {'precision': 0.05555555555555555, 'recall': 0.07692307692307693, 'f1': 0.06451612903225808, 'number': 13} | {'precision': 0.05263157894736842, 'recall': 0.07692307692307693, 'f1': 0.0625, 'number': 13} | 0.0526 | 0.0588 | 0.0556 | 0.7008 |
| 0.0124 | 12.31 | 800 | 0.0401 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 13} | {'precision': 0.0625, 'recall': 0.07692307692307693, 'f1': 0.06896551724137931, 'number': 13} | 0.0303 | 0.0294 | 0.0299 | 0.6352 |
| 0.0086 | 15.38 | 1000 | 0.0416 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | {'precision': 0.05263157894736842, 'recall': 0.07692307692307693, 'f1': 0.0625, 'number': 13} | {'precision': 0.05263157894736842, 'recall': 0.07692307692307693, 'f1': 0.0625, 'number': 13} | 0.0513 | 0.0588 | 0.0548 | 0.6311 |
| 0.0045 | 18.46 | 1200 | 0.0447 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 13} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 13} | 0.0 | 0.0 | 0.0 | 0.6639 |
| 0.0027 | 21.54 | 1400 | 0.0467 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | {'precision': 0.05, 'recall': 0.07692307692307693, 'f1': 0.060606060606060615, 'number': 13} | {'precision': 0.09523809523809523, 'recall': 0.15384615384615385, 'f1': 0.11764705882352941, 'number': 13} | 0.0667 | 0.0882 | 0.0759 | 0.6639 |
| 0.0013 | 24.62 | 1600 | 0.0494 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | {'precision': 0.045454545454545456, 'recall': 0.07692307692307693, 'f1': 0.05714285714285715, 'number': 13} | {'precision': 0.08695652173913043, 'recall': 0.15384615384615385, 'f1': 0.1111111111111111, 'number': 13} | 0.0612 | 0.0882 | 0.0723 | 0.6434 |
| 0.0009 | 27.69 | 1800 | 0.0559 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | {'precision': 0.045454545454545456, 'recall': 0.07692307692307693, 'f1': 0.05714285714285715, 'number': 13} | {'precision': 0.08695652173913043, 'recall': 0.15384615384615385, 'f1': 0.1111111111111111, 'number': 13} | 0.06 | 0.0882 | 0.0714 | 0.6475 |
| 0.0006 | 30.77 | 2000 | 0.0522 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | {'precision': 0.0625, 'recall': 0.07692307692307693, 'f1': 0.06896551724137931, 'number': 13} | {'precision': 0.05555555555555555, 'recall': 0.07692307692307693, 'f1': 0.06451612903225808, 'number': 13} | 0.0526 | 0.0588 | 0.0556 | 0.6393 |
| 0.0004 | 33.85 | 2200 | 0.0557 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | {'precision': 0.05263157894736842, 'recall': 0.07692307692307693, 'f1': 0.0625, 'number': 13} | {'precision': 0.1, 'recall': 0.15384615384615385, 'f1': 0.12121212121212123, 'number': 13} | 0.0682 | 0.0882 | 0.0769 | 0.6516 |
| 0.0005 | 36.92 | 2400 | 0.0582 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | {'precision': 0.05263157894736842, 'recall': 0.07692307692307693, 'f1': 0.0625, 'number': 13} | {'precision': 0.1, 'recall': 0.15384615384615385, 'f1': 0.12121212121212123, 'number': 13} | 0.0682 | 0.0882 | 0.0769 | 0.6434 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.1.0.dev20230810
- Datasets 2.14.4
- Tokenizers 0.11.0