metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: bert-base-uncased-issues-128
results: []
bert-base-uncased-issues-128
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2256
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: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 16
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.0959 | 1.0 | 291 | 1.6893 |
| 1.6328 | 2.0 | 582 | 1.5211 |
| 1.4969 | 3.0 | 873 | 1.3475 |
| 1.3972 | 4.0 | 1164 | 1.3374 |
| 1.3331 | 5.0 | 1455 | 1.2506 |
| 1.283 | 6.0 | 1746 | 1.3699 |
| 1.2326 | 7.0 | 2037 | 1.2969 |
| 1.2025 | 8.0 | 2328 | 1.3562 |
| 1.1665 | 9.0 | 2619 | 1.2218 |
| 1.1402 | 10.0 | 2910 | 1.1799 |
| 1.1265 | 11.0 | 3201 | 1.1268 |
| 1.1111 | 12.0 | 3492 | 1.1815 |
| 1.089 | 13.0 | 3783 | 1.2181 |
| 1.0756 | 14.0 | 4074 | 1.2133 |
| 1.0714 | 15.0 | 4365 | 1.2337 |
| 1.0641 | 16.0 | 4656 | 1.2256 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2