Misinformation-Covid-bert-base-multilingual-cased
This model is a fine-tuned version of bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2140
- F1: 0.4308
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: 4e-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 |
---|---|---|---|---|
0.6698 | 1.0 | 189 | 0.6312 | 0.0 |
0.6473 | 2.0 | 378 | 0.5830 | 0.3279 |
0.6511 | 3.0 | 567 | 0.7518 | 0.3462 |
0.7029 | 4.0 | 756 | 0.7088 | 0.4225 |
0.6913 | 5.0 | 945 | 0.9216 | 0.4242 |
0.617 | 6.0 | 1134 | 1.0679 | 0.4167 |
0.5906 | 7.0 | 1323 | 1.0944 | 0.4348 |
0.5097 | 8.0 | 1512 | 1.1551 | 0.4118 |
0.5056 | 9.0 | 1701 | 1.2152 | 0.4375 |
0.4903 | 10.0 | 1890 | 1.2140 | 0.4308 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.2
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 2