|
--- |
|
base_model: microsoft/mdeberta-v3-base |
|
library_name: transformers |
|
license: mit |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: scenario-non-kd-pre-ner-full-mdeberta_data-univner_en44 |
|
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. --> |
|
|
|
# scenario-non-kd-pre-ner-full-mdeberta_data-univner_en44 |
|
|
|
This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1840 |
|
- Precision: 0.6942 |
|
- Recall: 0.7143 |
|
- F1: 0.7041 |
|
- Accuracy: 0.9764 |
|
|
|
## 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: 3e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 44 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 30 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.145 | 1.2755 | 500 | 0.1299 | 0.4548 | 0.5259 | 0.4878 | 0.9591 | |
|
| 0.0673 | 2.5510 | 1000 | 0.0983 | 0.6367 | 0.6222 | 0.6293 | 0.9703 | |
|
| 0.0396 | 3.8265 | 1500 | 0.1065 | 0.6064 | 0.6874 | 0.6443 | 0.9712 | |
|
| 0.024 | 5.1020 | 2000 | 0.1177 | 0.6607 | 0.6874 | 0.6738 | 0.9738 | |
|
| 0.0156 | 6.3776 | 2500 | 0.1214 | 0.6664 | 0.7277 | 0.6957 | 0.9750 | |
|
| 0.0114 | 7.6531 | 3000 | 0.1301 | 0.6836 | 0.7112 | 0.6971 | 0.9752 | |
|
| 0.0082 | 8.9286 | 3500 | 0.1263 | 0.6790 | 0.7205 | 0.6991 | 0.9758 | |
|
| 0.0058 | 10.2041 | 4000 | 0.1426 | 0.6698 | 0.7267 | 0.6971 | 0.9751 | |
|
| 0.0043 | 11.4796 | 4500 | 0.1452 | 0.6903 | 0.7246 | 0.7071 | 0.9762 | |
|
| 0.0037 | 12.7551 | 5000 | 0.1531 | 0.6667 | 0.7246 | 0.6944 | 0.9757 | |
|
| 0.0028 | 14.0306 | 5500 | 0.1634 | 0.6902 | 0.7195 | 0.7045 | 0.9764 | |
|
| 0.0024 | 15.3061 | 6000 | 0.1628 | 0.7026 | 0.7091 | 0.7058 | 0.9763 | |
|
| 0.002 | 16.5816 | 6500 | 0.1709 | 0.6788 | 0.7133 | 0.6956 | 0.9758 | |
|
| 0.0017 | 17.8571 | 7000 | 0.1760 | 0.7018 | 0.7039 | 0.7028 | 0.9760 | |
|
| 0.0015 | 19.1327 | 7500 | 0.1727 | 0.7049 | 0.7122 | 0.7085 | 0.9769 | |
|
| 0.0012 | 20.4082 | 8000 | 0.1641 | 0.7058 | 0.7153 | 0.7105 | 0.9771 | |
|
| 0.001 | 21.6837 | 8500 | 0.1760 | 0.7172 | 0.7008 | 0.7089 | 0.9771 | |
|
| 0.001 | 22.9592 | 9000 | 0.1777 | 0.7049 | 0.7195 | 0.7121 | 0.9762 | |
|
| 0.0008 | 24.2347 | 9500 | 0.1801 | 0.7131 | 0.7257 | 0.7193 | 0.9771 | |
|
| 0.0007 | 25.5102 | 10000 | 0.1831 | 0.7049 | 0.7122 | 0.7085 | 0.9767 | |
|
| 0.0004 | 26.7857 | 10500 | 0.1846 | 0.6960 | 0.7133 | 0.7045 | 0.9762 | |
|
| 0.0005 | 28.0612 | 11000 | 0.1829 | 0.6995 | 0.7133 | 0.7063 | 0.9765 | |
|
| 0.0004 | 29.3367 | 11500 | 0.1840 | 0.6942 | 0.7143 | 0.7041 | 0.9764 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.1.1+cu121 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.19.1 |
|
|
