|
--- |
|
license: mit |
|
base_model: roberta-large |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: roberta-lg-cased-ms-ner-test |
|
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. --> |
|
|
|
# roberta-lg-cased-ms-ner-test |
|
|
|
This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1631 |
|
- Precision: 0.8047 |
|
- Recall: 0.8306 |
|
- F1: 0.8174 |
|
- Accuracy: 0.9660 |
|
|
|
## 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: 2e-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 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.2027 | 1.0 | 2712 | 0.1739 | 0.7335 | 0.7283 | 0.7309 | 0.9518 | |
|
| 0.1304 | 2.0 | 5424 | 0.1446 | 0.7860 | 0.7674 | 0.7766 | 0.9605 | |
|
| 0.0842 | 3.0 | 8136 | 0.1393 | 0.7892 | 0.8118 | 0.8003 | 0.9629 | |
|
| 0.0556 | 4.0 | 10848 | 0.1498 | 0.8001 | 0.8288 | 0.8142 | 0.9648 | |
|
| 0.0363 | 5.0 | 13560 | 0.1631 | 0.8047 | 0.8306 | 0.8174 | 0.9660 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 1.12.0 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
