SingSeqBERT-Katchers
This model is a fine-tuned version of google-bert/bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5238
- Accuracy: 0.7898
- F1: 0.7893
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: 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 | Accuracy | F1 |
---|---|---|---|---|---|
0.4927 | 1.0 | 2522 | 0.5391 | 0.7693 | 0.7687 |
0.4503 | 2.0 | 5044 | 0.5258 | 0.7911 | 0.7904 |
0.4146 | 3.0 | 7566 | 0.5238 | 0.7898 | 0.7893 |
0.3882 | 4.0 | 10088 | 0.5512 | 0.7950 | 0.7944 |
0.3633 | 5.0 | 12610 | 0.6592 | 0.7892 | 0.7884 |
0.3638 | 6.0 | 15132 | 0.8374 | 0.7811 | 0.7796 |
0.3212 | 7.0 | 17654 | 0.8621 | 0.7841 | 0.7833 |
0.2878 | 8.0 | 20176 | 0.9864 | 0.7779 | 0.7767 |
0.2407 | 9.0 | 22698 | 1.0765 | 0.7832 | 0.7824 |
0.2051 | 10.0 | 25220 | 1.1017 | 0.7869 | 0.7864 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.0.0
- Datasets 2.14.5
- Tokenizers 0.14.1
- Downloads last month
- 2