|
--- |
|
base_model: '' |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- conll2003 |
|
model-index: |
|
- name: span-marker-roberta-base-conll03 |
|
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. --> |
|
|
|
# span-marker-roberta-base-conll03 |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the conll2003 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0121 |
|
- Overall Precision: 0.9357 |
|
- Overall Recall: 0.9346 |
|
- Overall F1: 0.9351 |
|
- Overall Accuracy: 0.9870 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:| |
|
| 0.0351 | 0.28 | 500 | 0.0272 | 0.8928 | 0.8251 | 0.8576 | 0.9662 | |
|
| 0.0209 | 0.55 | 1000 | 0.0168 | 0.9066 | 0.9167 | 0.9116 | 0.9820 | |
|
| 0.0169 | 0.83 | 1500 | 0.0120 | 0.9380 | 0.9291 | 0.9336 | 0.9863 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
