metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: tuned_test_trainer-bert-base-uncased
results: []
tuned_test_trainer-bert-base-uncased
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6178
- Rmse: 0.7287
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: 5e-05
- train_batch_size: 16
- 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 |
|---|---|---|---|---|
| 0.7033 | 1.0 | 500 | 0.6323 | 0.6645 |
| 0.5289 | 2.0 | 1000 | 0.6178 | 0.7287 |
| 0.333 | 3.0 | 1500 | 0.7281 | 0.6512 |
| 0.2234 | 4.0 | 2000 | 1.0422 | 0.6663 |
| 0.1501 | 5.0 | 2500 | 1.2281 | 0.6914 |
| 0.0929 | 6.0 | 3000 | 1.5626 | 0.7082 |
| 0.0643 | 7.0 | 3500 | 1.6458 | 0.6950 |
| 0.0386 | 8.0 | 4000 | 1.8954 | 0.6863 |
| 0.0262 | 9.0 | 4500 | 1.9457 | 0.6925 |
| 0.0185 | 10.0 | 5000 | 1.9945 | 0.6793 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1