metadata
tags:
- generated_from_trainer
datasets:
- null
metrics:
- precision
- recall
- f1
- accuracy
model_index:
- name: bert-srb-ner-setimes
results:
- task:
name: Token Classification
type: token-classification
metric:
name: Accuracy
type: accuracy
value: 0.9566773594462266
bert-srb-ner-setimes
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1467
- Precision: 0.7672
- Recall: 0.8017
- F1: 0.7841
- Accuracy: 0.9567
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: 32
- 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 | 104 | 0.2279 | 0.6652 | 0.6967 | 0.6806 | 0.9348 |
No log | 2.0 | 208 | 0.1832 | 0.6984 | 0.7409 | 0.7190 | 0.9446 |
No log | 3.0 | 312 | 0.1599 | 0.7525 | 0.7826 | 0.7673 | 0.9527 |
No log | 4.0 | 416 | 0.1501 | 0.7664 | 0.7984 | 0.7821 | 0.9561 |
0.1992 | 5.0 | 520 | 0.1467 | 0.7672 | 0.8017 | 0.7841 | 0.9567 |
Framework versions
- Transformers 4.9.2
- Pytorch 1.9.0
- Datasets 1.11.0
- Tokenizers 0.10.1