metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-cross-ner-v4
results: []
bert-finetuned-cross-ner-v4
This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1777
- Precision: 0.8300
- Recall: 0.8637
- F1: 0.8465
- Accuracy: 0.9560
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.2044 | 1.0 | 2607 | 0.1963 | 0.7779 | 0.8180 | 0.7975 | 0.9459 |
0.124 | 2.0 | 5214 | 0.1713 | 0.8158 | 0.8527 | 0.8338 | 0.9546 |
0.0818 | 3.0 | 7821 | 0.1777 | 0.8300 | 0.8637 | 0.8465 | 0.9560 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3