pharmaconer
This model is a fine-tuned version of google-bert/bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0513
- Precision: 0.9074
- Recall: 0.8889
- F1: 0.8981
- Accuracy: 0.9933
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 | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.0466 | 1.0 | 1017 | 0.0446 | 0.8008 | 0.8026 | 0.8017 | 0.9875 |
0.0224 | 2.0 | 2034 | 0.0380 | 0.8177 | 0.8826 | 0.8489 | 0.9899 |
0.0111 | 3.0 | 3051 | 0.0403 | 0.9174 | 0.8560 | 0.8856 | 0.9922 |
0.0069 | 4.0 | 4068 | 0.0404 | 0.9024 | 0.8829 | 0.8925 | 0.9929 |
0.004 | 5.0 | 5085 | 0.0409 | 0.9060 | 0.8869 | 0.8963 | 0.9932 |
0.0017 | 6.0 | 6102 | 0.0447 | 0.8896 | 0.8949 | 0.8922 | 0.9928 |
0.001 | 7.0 | 7119 | 0.0499 | 0.8992 | 0.8901 | 0.8946 | 0.9930 |
0.0006 | 8.0 | 8136 | 0.0507 | 0.9047 | 0.8886 | 0.8966 | 0.9931 |
0.0003 | 9.0 | 9153 | 0.0500 | 0.9089 | 0.8895 | 0.8991 | 0.9933 |
0.0004 | 10.0 | 10170 | 0.0513 | 0.9074 | 0.8889 | 0.8981 | 0.9933 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 4