|
--- |
|
license: mit |
|
base_model: xlm-roberta-base |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- conll2003 |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: XLM-RoBERTa-Base-Conll2003-English-NER-Finetune |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: conll2003 |
|
type: conll2003 |
|
config: conll2003 |
|
split: test |
|
args: conll2003 |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.9051348999129678 |
|
- name: Recall |
|
type: recall |
|
value: 0.9206798866855525 |
|
- name: F1 |
|
type: f1 |
|
value: 0.9128412182919337 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9819532680090449 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# XLM-RoBERTa-Base-Conll2003-English-NER-Finetune |
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the conll2003 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1887 |
|
- Precision: 0.9051 |
|
- Recall: 0.9207 |
|
- F1: 0.9128 |
|
- Accuracy: 0.9820 |
|
|
|
## 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-06 |
|
- 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 |
|
- lr_scheduler_warmup_ratio: 0.05 |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.6956 | 0.3333 | 1441 | 0.1847 | 0.5575 | 0.5845 | 0.5707 | 0.9322 | |
|
| 0.1126 | 0.6667 | 2882 | 0.1192 | 0.8533 | 0.8762 | 0.8646 | 0.9748 | |
|
| 0.0678 | 1.0 | 4323 | 0.1404 | 0.8551 | 0.8899 | 0.8721 | 0.9756 | |
|
| 0.0528 | 1.3333 | 5764 | 0.1332 | 0.8868 | 0.9040 | 0.8953 | 0.9800 | |
|
| 0.0523 | 1.6667 | 7205 | 0.1352 | 0.8868 | 0.9083 | 0.8974 | 0.9800 | |
|
| 0.0494 | 2.0 | 8646 | 0.1437 | 0.8855 | 0.9063 | 0.8958 | 0.9793 | |
|
| 0.0351 | 2.3333 | 10087 | 0.1592 | 0.8867 | 0.9092 | 0.8978 | 0.9794 | |
|
| 0.0341 | 2.6667 | 11528 | 0.1532 | 0.8919 | 0.9131 | 0.9024 | 0.9801 | |
|
| 0.034 | 3.0 | 12969 | 0.1404 | 0.8967 | 0.9155 | 0.9060 | 0.9808 | |
|
| 0.024 | 3.3333 | 14410 | 0.1601 | 0.8978 | 0.9145 | 0.9061 | 0.9805 | |
|
| 0.0267 | 3.6667 | 15851 | 0.1563 | 0.9047 | 0.9180 | 0.9113 | 0.9819 | |
|
| 0.0255 | 4.0 | 17292 | 0.1406 | 0.9093 | 0.9193 | 0.9142 | 0.9827 | |
|
| 0.0199 | 4.3333 | 18733 | 0.1604 | 0.9047 | 0.9225 | 0.9135 | 0.9821 | |
|
| 0.0187 | 4.6667 | 20174 | 0.1541 | 0.9106 | 0.9251 | 0.9178 | 0.9829 | |
|
| 0.0169 | 5.0 | 21615 | 0.1692 | 0.9009 | 0.9163 | 0.9085 | 0.9814 | |
|
| 0.0159 | 5.3333 | 23056 | 0.1738 | 0.9012 | 0.9205 | 0.9107 | 0.9817 | |
|
| 0.0141 | 5.6667 | 24497 | 0.1610 | 0.9039 | 0.9178 | 0.9108 | 0.9821 | |
|
| 0.0141 | 6.0 | 25938 | 0.1797 | 0.8977 | 0.9164 | 0.9070 | 0.9805 | |
|
| 0.0105 | 6.3333 | 27379 | 0.1707 | 0.9026 | 0.9187 | 0.9106 | 0.9821 | |
|
| 0.0104 | 6.6667 | 28820 | 0.1832 | 0.9036 | 0.9191 | 0.9113 | 0.9812 | |
|
| 0.0135 | 7.0 | 30261 | 0.1743 | 0.9024 | 0.9214 | 0.9118 | 0.9817 | |
|
| 0.0101 | 7.3333 | 31702 | 0.1877 | 0.9006 | 0.9194 | 0.9099 | 0.9812 | |
|
| 0.0113 | 7.6667 | 33143 | 0.1893 | 0.9009 | 0.9187 | 0.9097 | 0.9811 | |
|
| 0.0088 | 8.0 | 34584 | 0.1867 | 0.9050 | 0.9196 | 0.9123 | 0.9818 | |
|
| 0.0068 | 8.3333 | 36025 | 0.1901 | 0.9022 | 0.9182 | 0.9101 | 0.9812 | |
|
| 0.0088 | 8.6667 | 37466 | 0.1956 | 0.9037 | 0.9193 | 0.9114 | 0.9813 | |
|
| 0.0085 | 9.0 | 38907 | 0.1873 | 0.9055 | 0.9216 | 0.9135 | 0.9820 | |
|
| 0.0068 | 9.3333 | 40348 | 0.1922 | 0.9049 | 0.9217 | 0.9133 | 0.9817 | |
|
| 0.006 | 9.6667 | 41789 | 0.1915 | 0.9047 | 0.9214 | 0.9130 | 0.9817 | |
|
| 0.006 | 10.0 | 43230 | 0.1887 | 0.9051 | 0.9207 | 0.9128 | 0.9820 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.1 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
