bert_finetune_prompt_classification
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: 0.1537
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 30
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.945 | 1.0 | 33 | 0.9316 |
| 0.5897 | 1.99 | 66 | 0.3983 |
| 0.2354 | 2.99 | 99 | 0.2213 |
| 0.237 | 3.98 | 132 | 0.1955 |
| 0.2126 | 4.98 | 165 | 0.1485 |
| 0.124 | 5.98 | 198 | 0.1412 |
| 0.1857 | 6.97 | 231 | 0.1540 |
| 0.108 | 8.0 | 265 | 0.1602 |
| 0.0801 | 9.0 | 298 | 0.1561 |
| 0.0421 | 9.99 | 331 | 0.1430 |
| 0.015 | 10.99 | 364 | 0.1480 |
| 0.0113 | 11.95 | 396 | 0.1537 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.0+cu117
- Datasets 2.14.5
- Tokenizers 0.14.1