test
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: 0.8195
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5374 | 1.0 | 88 | 1.5352 |
| 1.2975 | 2.0 | 176 | 1.2204 |
| 1.0897 | 3.0 | 264 | 1.0198 |
| 0.8539 | 4.0 | 352 | 0.9625 |
| 0.6992 | 5.0 | 440 | 0.9386 |
| 0.5281 | 6.0 | 528 | 0.8497 |
| 0.4184 | 7.0 | 616 | 0.7679 |
| 0.3016 | 8.0 | 704 | 0.8218 |
| 0.2405 | 9.0 | 792 | 0.8153 |
| 0.136 | 9.8914 | 870 | 0.8195 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0
- Downloads last month
- 5
Model tree for carriecheng0924/test
Base model
google-bert/bert-base-uncased