metadata
tags:
- generated_from_trainer
datasets:
- null
metrics:
- precision
- recall
- f1
- accuracy
model_index:
- name: electra-srb-ner-setimes
results:
- task:
name: Token Classification
type: token-classification
metric:
name: Accuracy
type: accuracy
value: 0.9460162843439789
electra-srb-ner-setimes
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2068
- Precision: 0.7730
- Recall: 0.7554
- F1: 0.7641
- Accuracy: 0.9460
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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 207 | 0.2808 | 0.7288 | 0.6295 | 0.6755 | 0.9227 |
No log | 2.0 | 414 | 0.2098 | 0.7564 | 0.7163 | 0.7358 | 0.9386 |
0.2985 | 3.0 | 621 | 0.2060 | 0.7839 | 0.7267 | 0.7542 | 0.9433 |
0.2985 | 4.0 | 828 | 0.1993 | 0.7425 | 0.7739 | 0.7579 | 0.9444 |
0.1026 | 5.0 | 1035 | 0.2068 | 0.7730 | 0.7554 | 0.7641 | 0.9460 |
Framework versions
- Transformers 4.9.2
- Pytorch 1.9.0
- Datasets 1.11.0
- Tokenizers 0.10.1