|
--- |
|
license: mit |
|
base_model: roberta-large |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: roberta-large-ner-new |
|
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-large-ner-new |
|
|
|
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: 0.1106 |
|
- Precision: 0.9670 |
|
- Recall: 0.9604 |
|
- F1: 0.9637 |
|
- Accuracy: 0.9600 |
|
|
|
## 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: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.1241 | 0.71 | 5000 | 0.1161 | 0.9618 | 0.9505 | 0.9561 | 0.9521 | |
|
| 0.0993 | 1.42 | 10000 | 0.1132 | 0.9633 | 0.9568 | 0.9600 | 0.9562 | |
|
| 0.0812 | 2.13 | 15000 | 0.1223 | 0.9662 | 0.9574 | 0.9618 | 0.9580 | |
|
| 0.074 | 2.84 | 20000 | 0.1118 | 0.9661 | 0.9607 | 0.9634 | 0.9598 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.0 |
|
- Tokenizers 0.15.0 |
|
|
