metadata
library_name: transformers
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: 1.2264
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 16
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.0973 | 1.0 | 291 | 1.6986 |
| 1.6313 | 2.0 | 582 | 1.5032 |
| 1.4983 | 3.0 | 873 | 1.3607 |
| 1.3977 | 4.0 | 1164 | 1.3350 |
| 1.3319 | 5.0 | 1455 | 1.2276 |
| 1.2851 | 6.0 | 1746 | 1.3695 |
| 1.2313 | 7.0 | 2037 | 1.2955 |
| 1.2013 | 8.0 | 2328 | 1.3411 |
| 1.1665 | 9.0 | 2619 | 1.2249 |
| 1.1425 | 10.0 | 2910 | 1.1716 |
| 1.1259 | 11.0 | 3201 | 1.1281 |
| 1.111 | 12.0 | 3492 | 1.1928 |
| 1.0871 | 13.0 | 3783 | 1.2244 |
| 1.0766 | 14.0 | 4074 | 1.2044 |
| 1.0753 | 15.0 | 4365 | 1.2126 |
| 1.0609 | 16.0 | 4656 | 1.2264 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.3.1
- Datasets 2.19.1
- Tokenizers 0.20.1