metadata
license: mit
base_model: dslim/bert-large-NER
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-NER
results: []
bert-NER
This model is a fine-tuned version of dslim/bert-large-NER on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3135
- Precision: 0.5388
- Recall: 0.7020
- F1: 0.6096
- Accuracy: 0.9072
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: 4
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 429 | 0.3677 | 0.4476 | 0.6465 | 0.5289 | 0.8761 |
| 0.5014 | 2.0 | 858 | 0.2789 | 0.5375 | 0.6515 | 0.5890 | 0.9084 |
| 0.204 | 3.0 | 1287 | 0.3135 | 0.5388 | 0.7020 | 0.6096 | 0.9072 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1