metadata
license: apache-2.0
base_model: google-bert/bert-base-cased
tags:
- generated_from_trainer
model-index:
- name: bert-finetuned-combo-textbook
results: []
bert-finetuned-combo-textbook
This model is a fine-tuned version of google-bert/bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5965
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: 1e-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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.2161 | 1.0 | 4936 | nan |
| 2.0531 | 2.0 | 9872 | 1.9590 |
| 1.978 | 3.0 | 14808 | nan |
| 1.9616 | 4.0 | 19744 | nan |
| 1.8559 | 5.0 | 24680 | 1.8338 |
| 1.7902 | 6.0 | 29616 | 1.7772 |
| 1.7603 | 7.0 | 34552 | 1.7686 |
| 1.769 | 8.0 | 39488 | 1.7368 |
| 1.6527 | 9.0 | 44424 | nan |
| 1.65 | 10.0 | 49360 | 1.6888 |
| 1.6281 | 11.0 | 54296 | nan |
| 1.591 | 12.0 | 59232 | 1.6576 |
| 1.5508 | 13.0 | 64168 | nan |
| 1.5929 | 14.0 | 69104 | 1.6151 |
| 1.5504 | 15.0 | 74040 | nan |
| 1.5492 | 16.0 | 78976 | 1.6250 |
| 1.5488 | 17.0 | 83912 | 1.6311 |
| 1.5152 | 18.0 | 88848 | nan |
| 1.5066 | 19.0 | 93784 | 1.5964 |
| 1.4764 | 20.0 | 98720 | 1.5965 |
Framework versions
- Transformers 4.38.2
- Pytorch 1.13.1+cu116
- Datasets 2.18.0
- Tokenizers 0.15.2