|
--- |
|
base_model: '' |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- few-nerd |
|
model-index: |
|
- name: span-marker-bert-base-fewnerd-coarse-super |
|
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-bert-base-fewnerd-coarse-super |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the few-nerd dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0191 |
|
- Overall Precision: 0.7817 |
|
- Overall Recall: 0.7683 |
|
- Overall F1: 0.7749 |
|
- Overall Accuracy: 0.9394 |
|
|
|
## 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-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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:| |
|
| 0.0393 | 0.16 | 200 | 0.0348 | 0.7084 | 0.6377 | 0.6712 | 0.9082 | |
|
| 0.0311 | 0.33 | 400 | 0.0233 | 0.7744 | 0.6994 | 0.7350 | 0.9225 | |
|
| 0.0242 | 0.49 | 600 | 0.0214 | 0.7725 | 0.7293 | 0.7503 | 0.9323 | |
|
| 0.0238 | 0.65 | 800 | 0.0204 | 0.7744 | 0.7663 | 0.7703 | 0.9359 | |
|
| 0.0212 | 0.81 | 1000 | 0.0193 | 0.7878 | 0.7617 | 0.7746 | 0.9379 | |
|
| 0.0181 | 0.98 | 1200 | 0.0190 | 0.7830 | 0.7671 | 0.7750 | 0.9391 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
