|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: new_model |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# new_model |
|
|
|
This model is a fine-tuned version of [SCUT-DLVCLab/lilt-roberta-en-base](https://huggingface.co/SCUT-DLVCLab/lilt-roberta-en-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0292 |
|
- Answer: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 10} |
|
- Header: {'precision': 0.07692307692307693, 'recall': 0.058823529411764705, 'f1': 0.06666666666666667, 'number': 17} |
|
- Question: {'precision': 0.0625, 'recall': 0.058823529411764705, 'f1': 0.06060606060606061, 'number': 17} |
|
- Overall Precision: 0.0556 |
|
- Overall Recall: 0.0455 |
|
- Overall F1: 0.0500 |
|
- Overall Accuracy: 0.6578 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:| |
|
| 0.1533 | 3.92 | 200 | 0.0173 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 10} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 17} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 17} | 0.0 | 0.0 | 0.0 | 0.5989 | |
|
| 0.0443 | 7.84 | 400 | 0.0137 | {'precision': 0.09090909090909091, 'recall': 0.1, 'f1': 0.09523809523809525, 'number': 10} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 17} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 17} | 0.0164 | 0.0227 | 0.0190 | 0.6203 | |
|
| 0.0194 | 11.76 | 600 | 0.0162 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 10} | {'precision': 0.2222222222222222, 'recall': 0.11764705882352941, 'f1': 0.15384615384615383, 'number': 17} | {'precision': 0.07142857142857142, 'recall': 0.058823529411764705, 'f1': 0.06451612903225808, 'number': 17} | 0.1154 | 0.0682 | 0.0857 | 0.6417 | |
|
| 0.0089 | 15.69 | 800 | 0.0186 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 10} | {'precision': 0.06666666666666667, 'recall': 0.058823529411764705, 'f1': 0.0625, 'number': 17} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 17} | 0.0278 | 0.0227 | 0.0250 | 0.6684 | |
|
| 0.0036 | 19.61 | 1000 | 0.0264 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 10} | {'precision': 0.07692307692307693, 'recall': 0.058823529411764705, 'f1': 0.06666666666666667, 'number': 17} | {'precision': 0.0625, 'recall': 0.058823529411764705, 'f1': 0.06060606060606061, 'number': 17} | 0.0556 | 0.0455 | 0.0500 | 0.6578 | |
|
| 0.0031 | 23.53 | 1200 | 0.0200 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 10} | {'precision': 0.1111111111111111, 'recall': 0.11764705882352941, 'f1': 0.11428571428571428, 'number': 17} | {'precision': 0.05263157894736842, 'recall': 0.058823529411764705, 'f1': 0.05555555555555555, 'number': 17} | 0.0732 | 0.0682 | 0.0706 | 0.6791 | |
|
| 0.0015 | 27.45 | 1400 | 0.0222 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 10} | {'precision': 0.05, 'recall': 0.058823529411764705, 'f1': 0.05405405405405405, 'number': 17} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 17} | 0.0196 | 0.0227 | 0.0211 | 0.6631 | |
|
| 0.0011 | 31.37 | 1600 | 0.0249 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 10} | {'precision': 0.05555555555555555, 'recall': 0.058823529411764705, 'f1': 0.05714285714285714, 'number': 17} | {'precision': 0.045454545454545456, 'recall': 0.058823529411764705, 'f1': 0.05128205128205128, 'number': 17} | 0.0408 | 0.0455 | 0.0430 | 0.6845 | |
|
| 0.0006 | 35.29 | 1800 | 0.0243 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 10} | {'precision': 0.05555555555555555, 'recall': 0.058823529411764705, 'f1': 0.05714285714285714, 'number': 17} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 17} | 0.0213 | 0.0227 | 0.0220 | 0.6952 | |
|
| 0.0004 | 39.22 | 2000 | 0.0290 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 10} | {'precision': 0.07142857142857142, 'recall': 0.058823529411764705, 'f1': 0.06451612903225808, 'number': 17} | {'precision': 0.05555555555555555, 'recall': 0.058823529411764705, 'f1': 0.05714285714285714, 'number': 17} | 0.0488 | 0.0455 | 0.0471 | 0.6578 | |
|
| 0.0002 | 43.14 | 2200 | 0.0288 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 10} | {'precision': 0.07142857142857142, 'recall': 0.058823529411764705, 'f1': 0.06451612903225808, 'number': 17} | {'precision': 0.05555555555555555, 'recall': 0.058823529411764705, 'f1': 0.05714285714285714, 'number': 17} | 0.0488 | 0.0455 | 0.0471 | 0.6578 | |
|
| 0.0002 | 47.06 | 2400 | 0.0292 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 10} | {'precision': 0.07692307692307693, 'recall': 0.058823529411764705, 'f1': 0.06666666666666667, 'number': 17} | {'precision': 0.0625, 'recall': 0.058823529411764705, 'f1': 0.06060606060606061, 'number': 17} | 0.0556 | 0.0455 | 0.0500 | 0.6578 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.1 |
|
- Pytorch 2.1.0.dev20230810 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.11.0 |
|
|
