|
--- |
|
license: mit |
|
base_model: roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: roberta-ner |
|
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-ner |
|
|
|
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1963 |
|
- Precision: 0.3814 |
|
- Recall: 0.4134 |
|
- F1: 0.3968 |
|
- Accuracy: 0.9525 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 60 | 0.2553 | 0.1878 | 0.1075 | 0.1368 | 0.9435 | |
|
| No log | 2.0 | 120 | 0.2114 | 0.3456 | 0.2235 | 0.2714 | 0.9492 | |
|
| No log | 3.0 | 180 | 0.2007 | 0.3372 | 0.3673 | 0.3516 | 0.9494 | |
|
| No log | 4.0 | 240 | 0.1976 | 0.3618 | 0.3911 | 0.3758 | 0.9517 | |
|
| No log | 5.0 | 300 | 0.1963 | 0.3814 | 0.4134 | 0.3968 | 0.9525 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
