metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: bert-base-uncased-pp-20000-1e-06-16
results: []
bert-base-uncased-pp-20000-1e-06-16
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: 0.6773
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 |
|---|---|---|---|
| 0.6973 | 1.0 | 313 | 0.6919 |
| 0.693 | 2.0 | 626 | 0.6875 |
| 0.6907 | 3.0 | 939 | 0.6839 |
| 0.6867 | 4.0 | 1252 | 0.6815 |
| 0.6843 | 5.0 | 1565 | 0.6800 |
| 0.68 | 6.0 | 1878 | 0.6788 |
| 0.6785 | 7.0 | 2191 | 0.6782 |
| 0.6787 | 8.0 | 2504 | 0.6773 |
| 0.6746 | 9.0 | 2817 | 0.6773 |
| 0.6712 | 10.0 | 3130 | 0.6776 |
| 0.6695 | 11.0 | 3443 | 0.6778 |
| 0.6696 | 12.0 | 3756 | 0.6777 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1