metadata
license: apache-2.0
base_model: bert-large-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-large-cased-maplestory-ner-v2-test
results: []
bert-large-cased-maplestory-ner-v2-test
This model is a fine-tuned version of bert-large-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1849
- Precision: 0.8130
- Recall: 0.8378
- F1: 0.8252
- Accuracy: 0.9673
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1976 | 1.0 | 2703 | 0.1770 | 0.7226 | 0.7824 | 0.7513 | 0.9516 |
| 0.1174 | 2.0 | 5406 | 0.1516 | 0.7860 | 0.8090 | 0.7974 | 0.9633 |
| 0.062 | 3.0 | 8109 | 0.1526 | 0.8108 | 0.8184 | 0.8146 | 0.9661 |
| 0.0334 | 4.0 | 10812 | 0.1648 | 0.8061 | 0.8378 | 0.8216 | 0.9668 |
| 0.0177 | 5.0 | 13515 | 0.1849 | 0.8130 | 0.8378 | 0.8252 | 0.9673 |
Framework versions
- Transformers 4.39.3
- Pytorch 1.12.0
- Datasets 2.18.0
- Tokenizers 0.15.2