metadata
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
model-index:
- name: Gikubu_bert_base
results: []
Gikubu_bert_base
This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6490
- Rmse: 0.7145
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: 3e-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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Rmse |
|---|---|---|---|---|
| 0.6478 | 1.0 | 1000 | 0.7235 | 0.6742 |
| 0.5231 | 2.0 | 2000 | 0.6490 | 0.7145 |
| 0.3654 | 3.0 | 3000 | 0.9078 | 0.6434 |
| 0.2606 | 4.0 | 4000 | 1.2709 | 0.6738 |
| 0.1703 | 5.0 | 5000 | 1.6260 | 0.6595 |
| 0.0859 | 6.0 | 6000 | 1.9016 | 0.6592 |
| 0.0593 | 7.0 | 7000 | 1.9951 | 0.6656 |
| 0.0412 | 8.0 | 8000 | 2.1283 | 0.6771 |
| 0.0357 | 9.0 | 9000 | 2.1523 | 0.6819 |
| 0.028 | 10.0 | 10000 | 2.1537 | 0.6786 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3