metadata
base_model: bert-base-chinese
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: Misinformation-Covid-bert-base-chinese
results: []
Misinformation-Covid-bert-base-chinese
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: 0.6165
- F1: 0.4706
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-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.6722 | 1.0 | 189 | 0.6155 | 0.0 |
| 0.6611 | 2.0 | 378 | 0.5880 | 0.2979 |
| 0.6133 | 3.0 | 567 | 0.5847 | 0.2727 |
| 0.6343 | 4.0 | 756 | 0.5573 | 0.4151 |
| 0.6557 | 5.0 | 945 | 0.5704 | 0.4444 |
| 0.5996 | 6.0 | 1134 | 0.6545 | 0.3750 |
| 0.6239 | 7.0 | 1323 | 0.6037 | 0.4407 |
| 0.6089 | 8.0 | 1512 | 0.6145 | 0.4590 |
| 0.555 | 9.0 | 1701 | 0.6273 | 0.4746 |
| 0.5281 | 10.0 | 1890 | 0.6165 | 0.4706 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.2
- Datasets 2.12.0
- Tokenizers 0.13.3