<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
bert-base-uncased-JY_Survey
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: 0.0982
- Micro f1: 0.0
- Macro f1: 0.0
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: 3e-05
- train_batch_size: 4
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 12
Training results
Training Loss | Epoch | Step | Validation Loss | Micro f1 | Macro f1 |
---|---|---|---|---|---|
0.667 | 1.0 | 14 | 0.5766 | 0.0668 | 0.0177 |
0.5167 | 2.0 | 28 | 0.4326 | 0.0364 | 0.0029 |
0.3843 | 3.0 | 42 | 0.3208 | 0.0 | 0.0 |
0.2858 | 4.0 | 56 | 0.2337 | 0.0 | 0.0 |
0.2075 | 5.0 | 70 | 0.1780 | 0.0 | 0.0 |
0.1647 | 6.0 | 84 | 0.1482 | 0.0 | 0.0 |
0.1393 | 7.0 | 98 | 0.1302 | 0.0 | 0.0 |
0.122 | 8.0 | 112 | 0.1189 | 0.0 | 0.0 |
0.1112 | 9.0 | 126 | 0.1111 | 0.0 | 0.0 |
0.1059 | 10.0 | 140 | 0.1055 | 0.0 | 0.0 |
0.099 | 11.0 | 154 | 0.1012 | 0.0 | 0.0 |
0.0933 | 12.0 | 168 | 0.0982 | 0.0 | 0.0 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1