|
--- |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- wikiann |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model_index: |
|
- name: electra-srb-ner |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: wikiann |
|
type: wikiann |
|
args: sr |
|
metric: |
|
name: Accuracy |
|
type: accuracy |
|
value: 0.95641898994996 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# electra-srb-ner |
|
|
|
This model was trained from scratch on the wikiann dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3017 |
|
- Precision: 0.8911 |
|
- Recall: 0.9081 |
|
- F1: 0.8995 |
|
- Accuracy: 0.9564 |
|
|
|
## 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: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.2535 | 1.0 | 1250 | 0.2015 | 0.8494 | 0.8605 | 0.8549 | 0.9376 | |
|
| 0.1461 | 2.0 | 2500 | 0.1853 | 0.8800 | 0.8681 | 0.8740 | 0.9464 | |
|
| 0.0914 | 3.0 | 3750 | 0.2022 | 0.8695 | 0.8912 | 0.8802 | 0.9485 | |
|
| 0.0545 | 4.0 | 5000 | 0.2214 | 0.8758 | 0.8975 | 0.8865 | 0.9514 | |
|
| 0.0385 | 5.0 | 6250 | 0.2536 | 0.8806 | 0.9010 | 0.8907 | 0.9523 | |
|
| 0.0266 | 6.0 | 7500 | 0.2506 | 0.8834 | 0.9020 | 0.8926 | 0.9539 | |
|
| 0.0133 | 7.0 | 8750 | 0.2745 | 0.8910 | 0.9057 | 0.8983 | 0.9562 | |
|
| 0.0077 | 8.0 | 10000 | 0.2946 | 0.8872 | 0.9065 | 0.8968 | 0.9559 | |
|
| 0.0043 | 9.0 | 11250 | 0.2931 | 0.8902 | 0.9094 | 0.8997 | 0.9567 | |
|
| 0.0022 | 10.0 | 12500 | 0.3017 | 0.8911 | 0.9081 | 0.8995 | 0.9564 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.9.2 |
|
- Pytorch 1.9.0 |
|
- Datasets 1.11.0 |
|
- Tokenizers 0.10.1 |
|
|
