NLPGroupProject-Finetune-Bert
This model is a fine-tuned version of google-bert/bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2570
- Accuracy: 0.716
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.25 | 250 | 0.9015 | 0.677 |
| 0.9879 | 0.5 | 500 | 0.8100 | 0.71 |
| 0.9879 | 0.75 | 750 | 0.9159 | 0.709 |
| 0.8313 | 1.0 | 1000 | 0.9674 | 0.722 |
| 0.8313 | 1.25 | 1250 | 0.9637 | 0.719 |
| 0.628 | 1.5 | 1500 | 0.7818 | 0.719 |
| 0.628 | 1.75 | 1750 | 0.9127 | 0.721 |
| 0.6537 | 2.0 | 2000 | 0.8752 | 0.722 |
| 0.6537 | 2.25 | 2250 | 1.3051 | 0.716 |
| 0.4037 | 2.5 | 2500 | 1.2484 | 0.712 |
| 0.4037 | 2.75 | 2750 | 1.2599 | 0.72 |
| 0.3853 | 3.0 | 3000 | 1.2570 | 0.716 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1