bert-base-chinese-finetuned-adl_hw1
This model is a fine-tuned version of bert-base-chinese on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1972
- Macro F1: 0.8248
- Micro F1: 0.8247
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
- 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: 100
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Macro F1 | Micro F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 169 | 0.3422 | 0.6473 | 0.6768 |
| No log | 2.0 | 338 | 0.2609 | 0.7410 | 0.7465 |
| 0.3314 | 3.0 | 507 | 0.2279 | 0.7826 | 0.7928 |
| 0.3314 | 4.0 | 676 | 0.2063 | 0.7988 | 0.8120 |
| 0.3314 | 5.0 | 845 | 0.1997 | 0.8140 | 0.8165 |
| 0.1549 | 6.0 | 1014 | 0.1987 | 0.8213 | 0.8229 |
| 0.1549 | 7.0 | 1183 | 0.1972 | 0.8248 | 0.8247 |
| 0.1549 | 8.0 | 1352 | 0.1940 | 0.8243 | 0.8230 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.11.0+cu128
- Datasets 2.21.0
- Tokenizers 0.21.4