|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: bert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: bert-base-uncased-nsp-50000-1e-06-16 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# bert-base-uncased-nsp-50000-1e-06-16 |
|
|
|
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co./bert-base-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2315 |
|
|
|
## 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-06 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 1024 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 30 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 0.6829 | 1.0 | 782 | 0.6331 | |
|
| 0.589 | 2.0 | 1564 | 0.5425 | |
|
| 0.4436 | 3.0 | 2346 | 0.3892 | |
|
| 0.3601 | 4.0 | 3128 | 0.3341 | |
|
| 0.3181 | 5.0 | 3910 | 0.3010 | |
|
| 0.2893 | 6.0 | 4692 | 0.2816 | |
|
| 0.2736 | 7.0 | 5474 | 0.2711 | |
|
| 0.2505 | 8.0 | 6256 | 0.2626 | |
|
| 0.2277 | 9.0 | 7038 | 0.2539 | |
|
| 0.216 | 10.0 | 7820 | 0.2474 | |
|
| 0.207 | 11.0 | 8602 | 0.2452 | |
|
| 0.212 | 12.0 | 9384 | 0.2398 | |
|
| 0.1956 | 13.0 | 10166 | 0.2384 | |
|
| 0.1794 | 14.0 | 10948 | 0.2374 | |
|
| 0.1894 | 15.0 | 11730 | 0.2358 | |
|
| 0.1731 | 16.0 | 12512 | 0.2358 | |
|
| 0.1717 | 17.0 | 13294 | 0.2315 | |
|
| 0.1652 | 18.0 | 14076 | 0.2349 | |
|
| 0.1647 | 19.0 | 14858 | 0.2353 | |
|
| 0.1565 | 20.0 | 15640 | 0.2349 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|