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: 1.2425
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 |
|---|---|---|---|
| 2.1056 | 1.0 | 291 | 1.6941 |
| 1.6321 | 2.0 | 582 | 1.5138 |
| 1.495 | 3.0 | 873 | 1.3614 |
| 1.393 | 4.0 | 1164 | 1.3305 |
| 1.3288 | 5.0 | 1455 | 1.2294 |
| 1.2828 | 6.0 | 1746 | 1.3679 |
| 1.2314 | 7.0 | 2037 | 1.2946 |
| 1.2028 | 8.0 | 2328 | 1.3472 |
| 1.1671 | 9.0 | 2619 | 1.2308 |
| 1.1402 | 10.0 | 2910 | 1.1784 |
| 1.1281 | 11.0 | 3201 | 1.1330 |
| 1.108 | 12.0 | 3492 | 1.1885 |
| 1.0876 | 13.0 | 3783 | 1.2176 |
| 1.0757 | 14.0 | 4074 | 1.2072 |
| 1.0729 | 15.0 | 4365 | 1.2215 |
| 1.0639 | 16.0 | 4656 | 1.2425 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.1
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 5
Model tree for ikedachin/bert-base-uncased-issues-128
Base model
google-bert/bert-base-uncased
Finetuned
this model