bert-base-finetuned-ynat
This model is a fine-tuned version of klue/bert-base on the klue dataset. It achieves the following results on the evaluation set:
- Loss: 0.3817
- F1: 0.8673
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: 256
- eval_batch_size: 256
- seed: 1
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| No log | 1.0 | 179 | 0.3817 | 0.8673 |
| No log | 2.0 | 358 | 0.4065 | 0.8634 |
| 0.2194 | 3.0 | 537 | 0.4077 | 0.8624 |
| 0.2194 | 4.0 | 716 | 0.4443 | 0.8584 |
| 0.2194 | 5.0 | 895 | 0.4795 | 0.8569 |
| 0.1477 | 6.0 | 1074 | 0.5159 | 0.8570 |
| 0.1477 | 7.0 | 1253 | 0.5445 | 0.8569 |
| 0.1477 | 8.0 | 1432 | 0.5711 | 0.8565 |
| 0.0849 | 9.0 | 1611 | 0.5913 | 0.8542 |
| 0.0849 | 10.0 | 1790 | 0.5945 | 0.8553 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 4