metadata
license: apache-2.0
base_model: cl-tohoku/bert-large-japanese-v2
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: results
results: []
results
This model is a fine-tuned version of cl-tohoku/bert-large-japanese-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.1789
- Accuracy: 0.196
- F1: 0.1399
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 | Accuracy | F1 |
---|---|---|---|---|---|
3.5154 | 1.0 | 1125 | 3.4451 | 0.146 | 0.0567 |
3.2778 | 2.0 | 2250 | 3.1801 | 0.197 | 0.0963 |
3.0802 | 3.0 | 3375 | 3.1374 | 0.174 | 0.1120 |
2.8756 | 4.0 | 4500 | 3.1239 | 0.191 | 0.1230 |
2.6657 | 5.0 | 5625 | 3.1789 | 0.196 | 0.1399 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3