chem-bert-cased
This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7331
- Precision: 0.4357
- Recall: 0.5028
- F1: 0.4668
- Accuracy: 0.7661
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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 51 | 0.9568 | 0.3458 | 0.0882 | 0.1405 | 0.7141 |
No log | 2.0 | 102 | 0.8359 | 0.3301 | 0.2693 | 0.2966 | 0.7363 |
No log | 3.0 | 153 | 0.7562 | 0.3932 | 0.4678 | 0.4273 | 0.7548 |
No log | 4.0 | 204 | 0.7406 | 0.4269 | 0.4059 | 0.4161 | 0.7623 |
No log | 5.0 | 255 | 0.7331 | 0.4357 | 0.5028 | 0.4668 | 0.7661 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 2