metadata
license: apache-2.0
base_model: cl-tohoku/bert-base-japanese-v3
tags:
- generated_from_trainer
datasets:
- ner-wikipedia-dataset
model-index:
- name: bert-base-japanese-finetuned-crf-ner
results: []
bert-base-japanese-finetuned-crf-ner
This model is a fine-tuned version of cl-tohoku/bert-base-japanese-v3 on the ner-wikipedia-dataset dataset. It achieves the following results on the evaluation set:
- Loss: 2.2869
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 19.818 | 1.0 | 134 | 1.7200 |
| 1.2449 | 2.0 | 268 | 1.4549 |
| 0.5612 | 3.0 | 402 | 1.6533 |
| 0.3228 | 4.0 | 536 | 1.9766 |
| 0.2002 | 5.0 | 670 | 2.2869 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1